0 files changed, 0 insertions, 0 deletions
diff --git a/tools/testing/selftests/.gitignore b/tools/testing/selftests/.gitignore
index cb24124ac5b9..674aaa02e396 100644
--- a/tools/testing/selftests/.gitignore
+++ b/tools/testing/selftests/.gitignore
@@ -4,7 +4,6 @@ gpiogpio-hammer
 gpioinclude/
 gpiolsgpio
 kselftest_install/
-tpm2/SpaceTest.log
 
 # Python bytecode and cache
 __pycache__/
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 41b649452560..56e44a98d6a5 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -1,42 +1,62 @@
 # SPDX-License-Identifier: GPL-2.0
+TARGETS += acct
 TARGETS += alsa
 TARGETS += amd-pstate
 TARGETS += arm64
 TARGETS += bpf
 TARGETS += breakpoints
+TARGETS += cachestat
 TARGETS += capabilities
 TARGETS += cgroup
 TARGETS += clone3
+TARGETS += connector
 TARGETS += core
 TARGETS += cpufreq
 TARGETS += cpu-hotplug
 TARGETS += damon
+TARGETS += devices/error_logs
+TARGETS += devices/probe
+TARGETS += dmabuf-heaps
 TARGETS += drivers/dma-buf
+TARGETS += drivers/ntsync
 TARGETS += drivers/s390x/uvdevice
+TARGETS += drivers/net
 TARGETS += drivers/net/bonding
 TARGETS += drivers/net/team
+TARGETS += drivers/net/virtio_net
+TARGETS += drivers/platform/x86/intel/ifs
+TARGETS += dt
 TARGETS += efivarfs
 TARGETS += exec
+TARGETS += fchmodat2
 TARGETS += filesystems
 TARGETS += filesystems/binderfs
 TARGETS += filesystems/epoll
 TARGETS += filesystems/fat
+TARGETS += filesystems/overlayfs
+TARGETS += filesystems/statmount
+TARGETS += filesystems/mount-notify
+TARGETS += filesystems/fuse
 TARGETS += firmware
 TARGETS += fpu
 TARGETS += ftrace
 TARGETS += futex
 TARGETS += gpio
+TARGETS += hid
 TARGETS += intel_pstate
 TARGETS += iommu
 TARGETS += ipc
 TARGETS += ir
 TARGETS += kcmp
 TARGETS += kexec
+TARGETS += kselftest_harness
 TARGETS += kvm
 TARGETS += landlock
 TARGETS += lib
 TARGETS += livepatch
+TARGETS += liveupdate
 TARGETS += lkdtm
+TARGETS += lsm
 TARGETS += membarrier
 TARGETS += memfd
 TARGETS += memory-hotplug
@@ -45,29 +65,44 @@ TARGETS += mount
 TARGETS += mount_setattr
 TARGETS += move_mount_set_group
 TARGETS += mqueue
+TARGETS += mseal_system_mappings
 TARGETS += nci
 TARGETS += net
 TARGETS += net/af_unix
+TARGETS += net/can
 TARGETS += net/forwarding
 TARGETS += net/hsr
 TARGETS += net/mptcp
+TARGETS += net/netfilter
 TARGETS += net/openvswitch
-TARGETS += netfilter
+TARGETS += net/ovpn
+TARGETS += net/packetdrill
+TARGETS += net/rds
+TARGETS += net/tcp_ao
+TARGETS += nolibc
 TARGETS += nsfs
+TARGETS += pci_endpoint
+TARGETS += pcie_bwctrl
+TARGETS += perf_events
 TARGETS += pidfd
 TARGETS += pid_namespace
+TARGETS += power_supply
 TARGETS += powerpc
+TARGETS += prctl
 TARGETS += proc
 TARGETS += pstore
 TARGETS += ptrace
 TARGETS += openat2
 TARGETS += resctrl
+TARGETS += riscv
 TARGETS += rlimits
 TARGETS += rseq
 TARGETS += rtc
+TARGETS += rust
+TARGETS += sched_ext
 TARGETS += seccomp
 TARGETS += sgx
-TARGETS += sigaltstack
+TARGETS += signal
 TARGETS += size
 TARGETS += sparc64
 TARGETS += splice
@@ -77,16 +112,23 @@ TARGETS += syscall_user_dispatch
 TARGETS += sysctl
 TARGETS += tc-testing
 TARGETS += tdx
+TARGETS += thermal/intel/power_floor
+TARGETS += thermal/intel/workload_hint
 TARGETS += timens
 ifneq (1, $(quicktest))
 TARGETS += timers
 endif
 TARGETS += tmpfs
 TARGETS += tpm2
-TARGETS += user
+TARGETS += tty
+TARGETS += ublk
+TARGETS += uevent
+TARGETS += user_events
 TARGETS += vDSO
-TARGETS += vm
+TARGETS += mm
+TARGETS += vfio
 TARGETS += x86
+TARGETS += x86/bugs
 TARGETS += zram
 #Please keep the TARGETS list alphabetically sorted
 # Run "make quicktest=1 run_tests" or
@@ -95,10 +137,17 @@ TARGETS += zram
 TARGETS_HOTPLUG = cpu-hotplug
 TARGETS_HOTPLUG += memory-hotplug
 
-# User can optionally provide a TARGETS skiplist.  By default we skip
-# BPF since it has cutting edge build time dependencies which require
-# more effort to install.
-SKIP_TARGETS ?= bpf
+# Networking tests want the net/lib target, include it automatically
+ifneq ($(filter net drivers/net drivers/net/hw,$(TARGETS)),)
+ifeq ($(filter net/lib,$(TARGETS)),)
+	INSTALL_DEP_TARGETS := net/lib
+endif
+endif
+
+# User can optionally provide a TARGETS skiplist. By default we skip
+# targets using BPF since it has cutting edge build time dependencies
+# which require more effort to install.
+SKIP_TARGETS ?= bpf sched_ext
 ifneq ($(SKIP_TARGETS),)
 	TMP := $(filter-out $(SKIP_TARGETS), $(TARGETS))
 	override TARGETS := $(TMP)
@@ -160,7 +209,7 @@ export KHDR_INCLUDES
 
 all:
 	@ret=1;							\
-	for TARGET in $(TARGETS); do				\
+	for TARGET in $(TARGETS) $(INSTALL_DEP_TARGETS); do	\
 		BUILD_TARGET=$$BUILD/$$TARGET;			\
 		mkdir $$BUILD_TARGET  -p;			\
 		$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET	\
@@ -173,6 +222,8 @@ run_tests: all
 	@for TARGET in $(TARGETS); do \
 		BUILD_TARGET=$$BUILD/$$TARGET;	\
 		$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests \
+				SRC_PATH=$(shell readlink -e $$(pwd)) \
+				OBJ_PATH=$(BUILD)                   \
 				O=$(abs_objtree);		    \
 	done;
 
@@ -218,12 +269,17 @@ ifdef INSTALL_PATH
 	install -m 744 kselftest/module.sh $(INSTALL_PATH)/kselftest/
 	install -m 744 kselftest/runner.sh $(INSTALL_PATH)/kselftest/
 	install -m 744 kselftest/prefix.pl $(INSTALL_PATH)/kselftest/
+	install -m 744 kselftest/ktap_helpers.sh $(INSTALL_PATH)/kselftest/
+	install -m 744 kselftest/ksft.py $(INSTALL_PATH)/kselftest/
 	install -m 744 run_kselftest.sh $(INSTALL_PATH)/
 	rm -f $(TEST_LIST)
 	@ret=1;	\
-	for TARGET in $(TARGETS); do \
+	for TARGET in $(TARGETS) $(INSTALL_DEP_TARGETS); do \
 		BUILD_TARGET=$$BUILD/$$TARGET;	\
-		$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install \
+		$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install \
+				INSTALL_PATH=$(INSTALL_PATH)/$$TARGET \
+				SRC_PATH=$(shell readlink -e $$(pwd)) \
+				OBJ_PATH=$(INSTALL_PATH) \
 				O=$(abs_objtree)		\
 				$(if $(FORCE_TARGETS),|| exit);	\
 		ret=$$((ret * $$?));		\
@@ -236,11 +292,19 @@ ifdef INSTALL_PATH
 	@# included in the generated runlist.
 	for TARGET in $(TARGETS); do \
 		BUILD_TARGET=$$BUILD/$$TARGET;	\
-		[ ! -d $(INSTALL_PATH)/$$TARGET ] && echo "Skipping non-existent dir: $$TARGET" && continue; \
-		echo -ne "Emit Tests for $$TARGET\n"; \
+		[ ! -d $(INSTALL_PATH)/$$TARGET ] && printf "Skipping non-existent dir: $$TARGET\n" && continue; \
+		printf "Emit Tests for $$TARGET\n"; \
 		$(MAKE) -s --no-print-directory OUTPUT=$$BUILD_TARGET COLLECTION=$$TARGET \
 			-C $$TARGET emit_tests >> $(TEST_LIST); \
 	done;
+	@VERSION=$$(git describe HEAD 2>/dev/null); \
+	if [ -n "$$VERSION" ]; then \
+		echo "$$VERSION" > $(INSTALL_PATH)/VERSION; \
+		printf "Version saved to $(INSTALL_PATH)/VERSION\n"; \
+	else \
+		printf "Unable to get version from git describe\n"; \
+	fi
+	@echo "**Kselftest Installation is complete: $(INSTALL_PATH)**"
 else
 	$(error Error: set INSTALL_PATH to use install)
 endif
@@ -253,7 +317,7 @@ gen_tar: install
 	@echo "Created ${TAR_PATH}"
 
 clean:
-	@for TARGET in $(TARGETS); do \
+	@for TARGET in $(TARGETS) $(INSTALL_DEP_TARGETS); do \
 		BUILD_TARGET=$$BUILD/$$TARGET;	\
 		$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\
 	done;
diff --git a/tools/testing/selftests/acct/.gitignore b/tools/testing/selftests/acct/.gitignore
new file mode 100644
index 000000000000..7e78aac19038
--- /dev/null
+++ b/tools/testing/selftests/acct/.gitignore
@@ -0,0 +1,3 @@
+acct_syscall
+config
+process_log
+\ No newline at end of file
diff --git a/tools/testing/selftests/acct/Makefile b/tools/testing/selftests/acct/Makefile
new file mode 100644
index 000000000000..7e025099cf65
--- /dev/null
+++ b/tools/testing/selftests/acct/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+TEST_GEN_PROGS := acct_syscall
+CFLAGS += -Wall
+
+include ../lib.mk
+\ No newline at end of file
diff --git a/tools/testing/selftests/acct/acct_syscall.c b/tools/testing/selftests/acct/acct_syscall.c
new file mode 100644
index 000000000000..421adbdc299d
--- /dev/null
+++ b/tools/testing/selftests/acct/acct_syscall.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* kselftest for acct() system call
+ *  The acct() system call enables or disables process accounting.
+ */
+
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+#include <sys/wait.h>
+
+#include "kselftest.h"
+
+int main(void)
+{
+	char filename[] = "process_log";
+	FILE *fp;
+	pid_t child_pid;
+	int sz;
+
+	// Setting up kselftest framework
+	ksft_print_header();
+	ksft_set_plan(1);
+
+	// Check if test is run a root
+	if (geteuid()) {
+		ksft_exit_skip("This test needs root to run!\n");
+		return 1;
+	}
+
+	// Create file to log closed processes
+	fp = fopen(filename, "w");
+
+	if (!fp) {
+		ksft_test_result_error("%s.\n", strerror(errno));
+		ksft_finished();
+		return 1;
+	}
+
+	acct(filename);
+
+	// Handle error conditions
+	if (errno) {
+		ksft_test_result_error("%s.\n", strerror(errno));
+		fclose(fp);
+		ksft_finished();
+		return 1;
+	}
+
+	// Create child process and wait for it to terminate.
+
+	child_pid = fork();
+
+	if (child_pid < 0) {
+		ksft_test_result_error("Creating a child process to log failed\n");
+		acct(NULL);
+		return 1;
+	} else if (child_pid > 0) {
+		wait(NULL);
+		fseek(fp, 0L, SEEK_END);
+		sz = ftell(fp);
+
+		acct(NULL);
+
+		if (sz <= 0) {
+			ksft_test_result_fail("Terminated child process not logged\n");
+			ksft_exit_fail();
+			return 1;
+		}
+
+		ksft_test_result_pass("Successfully logged terminated process.\n");
+		fclose(fp);
+		ksft_exit_pass();
+		return 0;
+	}
+
+	return 1;
+}
diff --git a/tools/testing/selftests/alsa/.gitignore b/tools/testing/selftests/alsa/.gitignore
index 2b0d11797f25..3dd8e1176b89 100644
--- a/tools/testing/selftests/alsa/.gitignore
+++ b/tools/testing/selftests/alsa/.gitignore
@@ -1,2 +1,5 @@
+global-timer
 mixer-test
 pcm-test
+test-pcmtest-driver
+utimer-test
diff --git a/tools/testing/selftests/alsa/Makefile b/tools/testing/selftests/alsa/Makefile
index a8c0383878d3..8dab90ad22bb 100644
--- a/tools/testing/selftests/alsa/Makefile
+++ b/tools/testing/selftests/alsa/Makefile
@@ -1,25 +1,31 @@
 # SPDX-License-Identifier: GPL-2.0
 #
+ifneq ($(shell pkg-config --exists alsa && echo 0 || echo 1),0)
+$(error Package alsa not found, please install alsa development package or \
+	add directory containing `alsa.pc` in PKG_CONFIG_PATH)
+endif
 
-CFLAGS += $(shell pkg-config --cflags alsa)
+CFLAGS += $(shell pkg-config --cflags alsa) $(KHDR_INCLUDES)
 LDLIBS += $(shell pkg-config --libs alsa)
 ifeq ($(LDLIBS),)
 LDLIBS += -lasound
 endif
 CFLAGS += -L$(OUTPUT) -Wl,-rpath=./
 
+LDLIBS+=-lpthread
+
 OVERRIDE_TARGETS = 1
 
-TEST_GEN_PROGS := mixer-test pcm-test
+TEST_GEN_PROGS := mixer-test pcm-test test-pcmtest-driver utimer-test
 
-TEST_GEN_PROGS_EXTENDED := libatest.so
+TEST_GEN_PROGS_EXTENDED := libatest.so global-timer
 
-TEST_FILES := conf.d
+TEST_FILES := conf.d pcm-test.conf
 
 include ../lib.mk
 
 $(OUTPUT)/libatest.so: conf.c alsa-local.h
 	$(CC) $(CFLAGS) -shared -fPIC $< $(LDLIBS) -o $@
 
-$(OUTPUT)/%: %.c $(TEST_GEN_PROGS_EXTENDED) alsa-local.h
+$(OUTPUT)/%: %.c $(OUTPUT)/libatest.so alsa-local.h
 	$(CC) $(CFLAGS) $< $(LDLIBS) -latest -o $@
diff --git a/tools/testing/selftests/alsa/alsa-local.h b/tools/testing/selftests/alsa/alsa-local.h
index 65f197ea9773..29143ef52101 100644
--- a/tools/testing/selftests/alsa/alsa-local.h
+++ b/tools/testing/selftests/alsa/alsa-local.h
@@ -12,6 +12,7 @@
 
 snd_config_t *get_alsalib_config(void);
 
+snd_config_t *conf_load_from_file(const char *filename);
 void conf_load(void);
 void conf_free(void);
 snd_config_t *conf_by_card(int card);
@@ -20,5 +21,17 @@ int conf_get_count(snd_config_t *root, const char *key1, const char *key2);
 const char *conf_get_string(snd_config_t *root, const char *key1, const char *key2, const char *def);
 long conf_get_long(snd_config_t *root, const char *key1, const char *key2, long def);
 int conf_get_bool(snd_config_t *root, const char *key1, const char *key2, int def);
+void conf_get_string_array(snd_config_t *root, const char *key1, const char *key2,
+			   const char **array, int array_size, const char *def);
+
+struct card_cfg_data {
+	int card;
+	snd_config_t *config;
+	const char *filename;
+	const char *config_id;
+	struct card_cfg_data *next;
+};
+
+extern struct card_cfg_data *conf_cards;
 
 #endif /* __ALSA_LOCAL_H */
diff --git a/tools/testing/selftests/alsa/conf.c b/tools/testing/selftests/alsa/conf.c
index c7ffc8f04195..317212078e36 100644
--- a/tools/testing/selftests/alsa/conf.c
+++ b/tools/testing/selftests/alsa/conf.c
@@ -14,19 +14,12 @@
 #include <regex.h>
 #include <sys/stat.h>
 
-#include "../kselftest.h"
+#include "kselftest.h"
 #include "alsa-local.h"
 
 #define SYSFS_ROOT "/sys"
 
-struct card_data {
-	int card;
-	snd_config_t *config;
-	const char *filename;
-	struct card_data *next;
-};
-
-static struct card_data *conf_cards;
+struct card_cfg_data *conf_cards;
 
 static const char *alsa_config =
 "ctl.hw {\n"
@@ -97,9 +90,9 @@ snd_config_t *get_alsalib_config(void)
 	return config;
 }
 
-static struct card_data *conf_data_by_card(int card, bool msg)
+static struct card_cfg_data *conf_data_by_card(int card, bool msg)
 {
-	struct card_data *conf;
+	struct card_cfg_data *conf;
 
 	for (conf = conf_cards; conf; conf = conf->next) {
 		if (conf->card == card) {
@@ -112,7 +105,7 @@ static struct card_data *conf_data_by_card(int card, bool msg)
 	return NULL;
 }
 
-static int dump_config_tree(snd_config_t *top)
+static void dump_config_tree(snd_config_t *top)
 {
 	snd_output_t *out;
 	int err;
@@ -125,7 +118,7 @@ static int dump_config_tree(snd_config_t *top)
 	snd_output_close(out);
 }
 
-static snd_config_t *load(const char *filename)
+snd_config_t *conf_load_from_file(const char *filename)
 {
 	snd_config_t *dst;
 	snd_input_t *input;
@@ -186,7 +179,7 @@ static char *sysfs_get(const char *sysfs_root, const char *id)
 	close(fd);
 	if (len < 0)
 		ksft_exit_fail_msg("sysfs: unable to read value '%s': %s\n",
-				   path, errno);
+				   path, strerror(errno));
 	while (len > 0 && path[len-1] == '\n')
 		len--;
 	path[len] = '\0';
@@ -229,55 +222,31 @@ static bool sysfs_match(const char *sysfs_root, snd_config_t *config)
 	return iter > 0;
 }
 
-static bool test_filename1(int card, const char *filename, const char *sysfs_card_root)
+static void assign_card_config(int card, const char *sysfs_card_root)
 {
-	struct card_data *data, *data2;
-	snd_config_t *config, *sysfs_config, *card_config, *sysfs_card_config, *node;
-	snd_config_iterator_t i, next;
+	struct card_cfg_data *data;
+	snd_config_t *sysfs_card_config;
 
-	config = load(filename);
-	if (snd_config_search(config, "sysfs", &sysfs_config) ||
-	    snd_config_get_type(sysfs_config) != SND_CONFIG_TYPE_COMPOUND)
-		ksft_exit_fail_msg("Missing global sysfs block in filename %s\n", filename);
-	if (snd_config_search(config, "card", &card_config) ||
-	    snd_config_get_type(card_config) != SND_CONFIG_TYPE_COMPOUND)
-		ksft_exit_fail_msg("Missing global card block in filename %s\n", filename);
-	if (!sysfs_match(SYSFS_ROOT, sysfs_config))
-		return false;
-	snd_config_for_each(i, next, card_config) {
-		node = snd_config_iterator_entry(i);
-		if (snd_config_search(node, "sysfs", &sysfs_card_config) ||
-		    snd_config_get_type(sysfs_card_config) != SND_CONFIG_TYPE_COMPOUND)
-			ksft_exit_fail_msg("Missing card sysfs block in filename %s\n", filename);
+	for (data = conf_cards; data; data = data->next) {
+		snd_config_search(data->config, "sysfs", &sysfs_card_config);
 		if (!sysfs_match(sysfs_card_root, sysfs_card_config))
 			continue;
-		data = malloc(sizeof(*data));
-		if (!data)
-			ksft_exit_fail_msg("Out of memory\n");
-		data2 = conf_data_by_card(card, false);
-		if (data2)
-			ksft_exit_fail_msg("Duplicate card '%s' <-> '%s'\n", filename, data2->filename);
+
 		data->card = card;
-		data->filename = filename;
-		data->config = node;
-		data->next = conf_cards;
-		conf_cards = data;
-		return true;
+		break;
 	}
-	return false;
 }
 
-static bool test_filename(const char *filename)
+static void assign_card_configs(void)
 {
 	char fn[128];
 	int card;
 
 	for (card = 0; card < 32; card++) {
 		snprintf(fn, sizeof(fn), "%s/class/sound/card%d", SYSFS_ROOT, card);
-		if (access(fn, R_OK) == 0 && test_filename1(card, filename, fn))
-			return true;
+		if (access(fn, R_OK) == 0)
+			assign_card_config(card, fn);
 	}
-	return false;
 }
 
 static int filename_filter(const struct dirent *dirent)
@@ -296,6 +265,41 @@ static int filename_filter(const struct dirent *dirent)
 	return 0;
 }
 
+static bool match_config(const char *filename)
+{
+	struct card_cfg_data *data;
+	snd_config_t *config, *sysfs_config, *card_config, *sysfs_card_config, *node;
+	snd_config_iterator_t i, next;
+
+	config = conf_load_from_file(filename);
+	if (snd_config_search(config, "sysfs", &sysfs_config) ||
+	    snd_config_get_type(sysfs_config) != SND_CONFIG_TYPE_COMPOUND)
+		ksft_exit_fail_msg("Missing global sysfs block in filename %s\n", filename);
+	if (snd_config_search(config, "card", &card_config) ||
+	    snd_config_get_type(card_config) != SND_CONFIG_TYPE_COMPOUND)
+		ksft_exit_fail_msg("Missing global card block in filename %s\n", filename);
+	if (!sysfs_match(SYSFS_ROOT, sysfs_config))
+		return false;
+	snd_config_for_each(i, next, card_config) {
+		node = snd_config_iterator_entry(i);
+		if (snd_config_search(node, "sysfs", &sysfs_card_config) ||
+		    snd_config_get_type(sysfs_card_config) != SND_CONFIG_TYPE_COMPOUND)
+			ksft_exit_fail_msg("Missing card sysfs block in filename %s\n", filename);
+
+		data = malloc(sizeof(*data));
+		if (!data)
+			ksft_exit_fail_msg("Out of memory\n");
+		data->filename = filename;
+		data->config = node;
+		data->card = -1;
+		if (snd_config_get_id(node, &data->config_id))
+			ksft_exit_fail_msg("snd_config_get_id failed for card\n");
+		data->next = conf_cards;
+		conf_cards = data;
+	}
+	return true;
+}
+
 void conf_load(void)
 {
 	const char *fn = "conf.d";
@@ -311,17 +315,19 @@ void conf_load(void)
 		if (filename == NULL)
 			ksft_exit_fail_msg("Out of memory\n");
 		sprintf(filename, "%s/%s", fn, namelist[j]->d_name);
-		if (test_filename(filename))
+		if (match_config(filename))
 			filename = NULL;
 		free(filename);
 		free(namelist[j]);
 	}
 	free(namelist);
+
+	assign_card_configs();
 }
 
 void conf_free(void)
 {
-	struct card_data *conf;
+	struct card_cfg_data *conf;
 
 	while (conf_cards) {
 		conf = conf_cards;
@@ -332,7 +338,7 @@ void conf_free(void)
 
 snd_config_t *conf_by_card(int card)
 {
-	struct card_data *conf;
+	struct card_cfg_data *conf;
 
 	conf = conf_data_by_card(card, true);
 	if (conf)
@@ -431,7 +437,6 @@ long conf_get_long(snd_config_t *root, const char *key1, const char *key2, long
 int conf_get_bool(snd_config_t *root, const char *key1, const char *key2, int def)
 {
 	snd_config_t *cfg;
-	long l;
 	int ret;
 
 	if (!root)
@@ -443,6 +448,28 @@ int conf_get_bool(snd_config_t *root, const char *key1, const char *key2, int de
 		ksft_exit_fail_msg("key '%s'.'%s' search error: %s\n", key1, key2, snd_strerror(ret));
 	ret = snd_config_get_bool(cfg);
 	if (ret < 0)
-		ksft_exit_fail_msg("key '%s'.'%s' is not an bool\n", key1, key2);
+		ksft_exit_fail_msg("key '%s'.'%s' is not a bool\n", key1, key2);
 	return !!ret;
 }
+
+void conf_get_string_array(snd_config_t *root, const char *key1, const char *key2,
+			   const char **array, int array_size, const char *def)
+{
+	snd_config_t *cfg;
+	char buf[16];
+	int ret, index;
+
+	ret = conf_get_by_keys(root, key1, key2, &cfg);
+	if (ret == -ENOENT)
+		cfg = NULL;
+	else if (ret < 0)
+		ksft_exit_fail_msg("key '%s'.'%s' search error: %s\n", key1, key2, snd_strerror(ret));
+	for (index = 0; index < array_size; index++) {
+		if (cfg == NULL) {
+			array[index] = def;
+		} else {
+			sprintf(buf, "%i", index);
+			array[index] = conf_get_string(cfg, buf, NULL, def);
+		}
+	}
+}
diff --git a/tools/testing/selftests/alsa/conf.d/Lenovo_ThinkPad_P1_Gen2.conf b/tools/testing/selftests/alsa/conf.d/Lenovo_ThinkPad_P1_Gen2.conf
index 9eca985e0c08..5b40a916295d 100644
--- a/tools/testing/selftests/alsa/conf.d/Lenovo_ThinkPad_P1_Gen2.conf
+++ b/tools/testing/selftests/alsa/conf.d/Lenovo_ThinkPad_P1_Gen2.conf
@@ -39,25 +39,30 @@ card.hda {
 	#
 	pcm.0.0 {
 		PLAYBACK {
-			#
-			# Uncomment to override values for specific tests
-			#
-			#test_name1 {
-			#	access RW_INTERLEAVED
-			#	format S16_LE
-			#	rate 48000
-			#	channels 2
-			#	period_size 512
-			#	buffer_size 4096
-			#}
-			#test_name2 {
-			#	access RW_INTERLEAVED
-			#	format S16_LE
-			#	rate 48000
-			#	channels 2
-			#	period_size 24000
-			#	buffer_size 192000
-			#}
+			test.time1 {
+				access RW_INTERLEAVED	# can be omitted - default
+				format S16_LE		# can be omitted - default
+				rate 48000		# can be omitted - default
+				channels 2		# can be omitted - default
+				period_size 512
+				buffer_size 4096
+			}
+			test.time2 {
+				access RW_INTERLEAVED
+				format S16_LE
+				rate 48000
+				channels 2
+				period_size 24000
+				buffer_size 192000
+			}
+			test.time3 {
+				access RW_INTERLEAVED
+				format S16_LE
+				rate 44100
+				channels 2
+				period_size 24000
+				buffer_size 192000
+			}
 		}
 		CAPTURE {
 			# use default tests, check for the presence
diff --git a/tools/testing/selftests/alsa/global-timer.c b/tools/testing/selftests/alsa/global-timer.c
new file mode 100644
index 000000000000..c15ec0ba851a
--- /dev/null
+++ b/tools/testing/selftests/alsa/global-timer.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This tool is used by the utimer test, and it allows us to
+ * count the ticks of a global timer in a certain time frame
+ * (which is set by `timeout` parameter).
+ *
+ * Author: Ivan Orlov <ivan.orlov0322@gmail.com>
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <alsa/asoundlib.h>
+#include <time.h>
+
+static int ticked;
+static void async_callback(snd_async_handler_t *ahandler)
+{
+	ticked++;
+}
+
+static char timer_name[64];
+static void bind_to_timer(int device, int subdevice, int timeout)
+{
+	snd_timer_t *handle;
+	snd_timer_params_t *params;
+	snd_async_handler_t *ahandler;
+
+	time_t end;
+
+	sprintf(timer_name, "hw:CLASS=%d,SCLASS=%d,DEV=%d,SUBDEV=%d",
+		SND_TIMER_CLASS_GLOBAL, SND_TIMER_SCLASS_NONE,
+		device, subdevice);
+
+	snd_timer_params_alloca(&params);
+
+	if (snd_timer_open(&handle, timer_name, SND_TIMER_OPEN_NONBLOCK) < 0) {
+		perror("Can't open the timer");
+		exit(EXIT_FAILURE);
+	}
+
+	snd_timer_params_set_auto_start(params, 1);
+	snd_timer_params_set_ticks(params, 1);
+	if (snd_timer_params(handle, params) < 0) {
+		perror("Can't set timer params");
+		exit(EXIT_FAILURE);
+	}
+
+	if (snd_async_add_timer_handler(&ahandler, handle, async_callback, NULL) < 0) {
+		perror("Can't create a handler");
+		exit(EXIT_FAILURE);
+	}
+	end = time(NULL) + timeout;
+	if (snd_timer_start(handle) < 0) {
+		perror("Failed to start the timer");
+		exit(EXIT_FAILURE);
+	}
+	printf("Timer has started\n");
+	while (time(NULL) <= end) {
+		/*
+		 * Waiting for the timeout to elapse. Can't use sleep here, as it gets
+		 * constantly interrupted by the signal from the timer (SIGIO)
+		 */
+	}
+	snd_timer_stop(handle);
+	snd_timer_close(handle);
+}
+
+int main(int argc, char *argv[])
+{
+	int device, subdevice, timeout;
+
+	if (argc < 4) {
+		perror("Usage: %s <device> <subdevice> <timeout>");
+		return EXIT_FAILURE;
+	}
+
+	setlinebuf(stdout);
+
+	device = atoi(argv[1]);
+	subdevice = atoi(argv[2]);
+	timeout = atoi(argv[3]);
+
+	bind_to_timer(device, subdevice, timeout);
+
+	printf("Total ticks count: %d\n", ticked);
+
+	return EXIT_SUCCESS;
+}
diff --git a/tools/testing/selftests/alsa/mixer-test.c b/tools/testing/selftests/alsa/mixer-test.c
index 05f1749ae19d..d4f845c32804 100644
--- a/tools/testing/selftests/alsa/mixer-test.c
+++ b/tools/testing/selftests/alsa/mixer-test.c
@@ -25,7 +25,7 @@
 #include <poll.h>
 #include <stdint.h>
 
-#include "../kselftest.h"
+#include "kselftest.h"
 #include "alsa-local.h"
 
 #define TESTS_PER_CONTROL 7
@@ -33,6 +33,8 @@
 struct card_data {
 	snd_ctl_t *handle;
 	int card;
+	snd_ctl_card_info_t *info;
+	const char *card_name;
 	struct pollfd pollfd;
 	int num_ctls;
 	snd_ctl_elem_list_t *ctls;
@@ -51,10 +53,10 @@ struct ctl_data {
 	struct ctl_data *next;
 };
 
-int num_cards = 0;
-int num_controls = 0;
-struct card_data *card_list = NULL;
-struct ctl_data *ctl_list = NULL;
+int num_cards;
+int num_controls;
+struct card_data *card_list;
+struct ctl_data *ctl_list;
 
 static void find_controls(void)
 {
@@ -63,6 +65,7 @@ static void find_controls(void)
 	struct card_data *card_data;
 	struct ctl_data *ctl_data;
 	snd_config_t *config;
+	char *card_name, *card_longname;
 
 	card = -1;
 	if (snd_card_next(&card) < 0 || card < 0)
@@ -84,6 +87,33 @@ static void find_controls(void)
 			goto next_card;
 		}
 
+		err = snd_card_get_name(card, &card_name);
+		if (err != 0)
+			card_name = "Unknown";
+		err = snd_card_get_longname(card, &card_longname);
+		if (err != 0)
+			card_longname = "Unknown";
+
+		err = snd_ctl_card_info_malloc(&card_data->info);
+		if (err != 0)
+			ksft_exit_fail_msg("Failed to allocate card info: %d\n",
+				err);
+
+		err = snd_ctl_card_info(card_data->handle, card_data->info);
+		if (err == 0) {
+			card_data->card_name = snd_ctl_card_info_get_id(card_data->info);
+			if (!card_data->card_name)
+				ksft_print_msg("Failed to get card ID\n");
+		} else {
+			ksft_print_msg("Failed to get card info: %d\n", err);
+		}
+
+		if (!card_data->card_name)
+			card_data->card_name = "Unknown";
+
+		ksft_print_msg("Card %d/%s - %s (%s)\n", card,
+			       card_data->card_name, card_name, card_longname);
+
 		/* Count controls */
 		snd_ctl_elem_list_malloc(&card_data->ctls);
 		snd_ctl_elem_list(card_data->handle, card_data->ctls);
@@ -128,7 +158,7 @@ static void find_controls(void)
 			err = snd_ctl_elem_info(card_data->handle,
 						ctl_data->info);
 			if (err < 0) {
-				ksft_print_msg("%s getting info for %d\n",
+				ksft_print_msg("%s getting info for %s\n",
 					       snd_strerror(err),
 					       ctl_data->name);
 			}
@@ -156,7 +186,7 @@ static void find_controls(void)
 		err = snd_ctl_poll_descriptors(card_data->handle,
 					       &card_data->pollfd, 1);
 		if (err != 1) {
-			ksft_exit_fail_msg("snd_ctl_poll_descriptors() failed for %d\n",
+			ksft_exit_fail_msg("snd_ctl_poll_descriptors() failed for card %d: %d\n",
 				       card, err);
 		}
 
@@ -178,7 +208,7 @@ static int wait_for_event(struct ctl_data *ctl, int timeout)
 {
 	unsigned short revents;
 	snd_ctl_event_t *event;
-	int count, err;
+	int err;
 	unsigned int mask = 0;
 	unsigned int ev_id;
 
@@ -309,7 +339,7 @@ static bool ctl_value_index_valid(struct ctl_data *ctl,
 		}
 
 		if (int64_val > snd_ctl_elem_info_get_max64(ctl->info)) {
-			ksft_print_msg("%s.%d value %lld more than maximum %lld\n",
+			ksft_print_msg("%s.%d value %lld more than maximum %ld\n",
 				       ctl->name, index, int64_val,
 				       snd_ctl_elem_info_get_max(ctl->info));
 			return false;
@@ -337,7 +367,7 @@ static bool ctl_value_index_valid(struct ctl_data *ctl,
 		}
 
 		if (int_val >= snd_ctl_elem_info_get_items(ctl->info)) {
-			ksft_print_msg("%s.%d value %ld more than item count %ld\n",
+			ksft_print_msg("%s.%d value %ld more than item count %u\n",
 				       ctl->name, index, int_val,
 				       snd_ctl_elem_info_get_items(ctl->info));
 			return false;
@@ -379,16 +409,16 @@ static void test_ctl_get_value(struct ctl_data *ctl)
 	/* If the control is turned off let's be polite */
 	if (snd_ctl_elem_info_is_inactive(ctl->info)) {
 		ksft_print_msg("%s is inactive\n", ctl->name);
-		ksft_test_result_skip("get_value.%d.%d\n",
-				      ctl->card->card, ctl->elem);
+		ksft_test_result_skip("get_value.%s.%d\n",
+				      ctl->card->card_name, ctl->elem);
 		return;
 	}
 
 	/* Can't test reading on an unreadable control */
 	if (!snd_ctl_elem_info_is_readable(ctl->info)) {
 		ksft_print_msg("%s is not readable\n", ctl->name);
-		ksft_test_result_skip("get_value.%d.%d\n",
-				      ctl->card->card, ctl->elem);
+		ksft_test_result_skip("get_value.%s.%d\n",
+				      ctl->card->card_name, ctl->elem);
 		return;
 	}
 
@@ -403,8 +433,8 @@ static void test_ctl_get_value(struct ctl_data *ctl)
 		err = -EINVAL;
 
 out:
-	ksft_test_result(err >= 0, "get_value.%d.%d\n",
-			 ctl->card->card, ctl->elem);
+	ksft_test_result(err >= 0, "get_value.%s.%d\n",
+			 ctl->card->card_name, ctl->elem);
 }
 
 static bool strend(const char *haystack, const char *needle)
@@ -420,7 +450,9 @@ static bool strend(const char *haystack, const char *needle)
 static void test_ctl_name(struct ctl_data *ctl)
 {
 	bool name_ok = true;
-	bool check;
+
+	ksft_print_msg("%s.%d %s\n", ctl->card->card_name, ctl->elem,
+		       ctl->name);
 
 	/* Only boolean controls should end in Switch */
 	if (strend(ctl->name, " Switch")) {
@@ -441,8 +473,50 @@ static void test_ctl_name(struct ctl_data *ctl)
 		}
 	}
 
-	ksft_test_result(name_ok, "name.%d.%d\n",
-			 ctl->card->card, ctl->elem);
+	ksft_test_result(name_ok, "name.%s.%d\n",
+			 ctl->card->card_name, ctl->elem);
+}
+
+static void show_values(struct ctl_data *ctl, snd_ctl_elem_value_t *orig_val,
+			snd_ctl_elem_value_t *read_val)
+{
+	long long orig_int, read_int;
+	int i;
+
+	for (i = 0; i < snd_ctl_elem_info_get_count(ctl->info); i++) {
+		switch (snd_ctl_elem_info_get_type(ctl->info)) {
+		case SND_CTL_ELEM_TYPE_BOOLEAN:
+			orig_int = snd_ctl_elem_value_get_boolean(orig_val, i);
+			read_int = snd_ctl_elem_value_get_boolean(read_val, i);
+			break;
+
+		case SND_CTL_ELEM_TYPE_INTEGER:
+			orig_int = snd_ctl_elem_value_get_integer(orig_val, i);
+			read_int = snd_ctl_elem_value_get_integer(read_val, i);
+			break;
+
+		case SND_CTL_ELEM_TYPE_INTEGER64:
+			orig_int = snd_ctl_elem_value_get_integer64(orig_val,
+								    i);
+			read_int = snd_ctl_elem_value_get_integer64(read_val,
+								    i);
+			break;
+
+		case SND_CTL_ELEM_TYPE_ENUMERATED:
+			orig_int = snd_ctl_elem_value_get_enumerated(orig_val,
+								     i);
+			read_int = snd_ctl_elem_value_get_enumerated(read_val,
+								     i);
+			break;
+
+		default:
+			return;
+		}
+
+		ksft_print_msg("%s.%d orig %lld read %lld, is_volatile %d\n",
+			       ctl->name, i, orig_int, read_int,
+			       snd_ctl_elem_info_is_volatile(ctl->info));
+	}
 }
 
 static bool show_mismatch(struct ctl_data *ctl, int index,
@@ -572,26 +646,41 @@ static int write_and_verify(struct ctl_data *ctl,
 	}
 
 	/*
+	 * We can't verify any specific value for volatile controls
+	 * but we should still check that whatever we read is a valid
+	 * vale for the control.
+	 */
+	if (snd_ctl_elem_info_is_volatile(ctl->info)) {
+		if (!ctl_value_valid(ctl, read_val)) {
+			ksft_print_msg("Volatile control %s has invalid value\n",
+				       ctl->name);
+			return -EINVAL;
+		}
+
+		return 0;
+	}
+
+	/*
 	 * Check for an event if the value changed, or confirm that
 	 * there was none if it didn't.  We rely on the kernel
 	 * generating the notification before it returns from the
 	 * write, this is currently true, should that ever change this
 	 * will most likely break and need updating.
 	 */
-	if (!snd_ctl_elem_info_is_volatile(ctl->info)) {
-		err = wait_for_event(ctl, 0);
-		if (snd_ctl_elem_value_compare(initial_val, read_val)) {
-			if (err < 1) {
-				ksft_print_msg("No event generated for %s\n",
-					       ctl->name);
-				ctl->event_missing++;
-			}
-		} else {
-			if (err != 0) {
-				ksft_print_msg("Spurious event generated for %s\n",
-					       ctl->name);
-				ctl->event_spurious++;
-			}
+	err = wait_for_event(ctl, 0);
+	if (snd_ctl_elem_value_compare(initial_val, read_val)) {
+		if (err < 1) {
+			ksft_print_msg("No event generated for %s\n",
+				       ctl->name);
+			show_values(ctl, initial_val, read_val);
+			ctl->event_missing++;
+		}
+	} else {
+		if (err != 0) {
+			ksft_print_msg("Spurious event generated for %s\n",
+				       ctl->name);
+			show_values(ctl, initial_val, read_val);
+			ctl->event_spurious++;
 		}
 	}
 
@@ -626,30 +715,30 @@ static void test_ctl_write_default(struct ctl_data *ctl)
 	/* If the control is turned off let's be polite */
 	if (snd_ctl_elem_info_is_inactive(ctl->info)) {
 		ksft_print_msg("%s is inactive\n", ctl->name);
-		ksft_test_result_skip("write_default.%d.%d\n",
-				      ctl->card->card, ctl->elem);
+		ksft_test_result_skip("write_default.%s.%d\n",
+				      ctl->card->card_name, ctl->elem);
 		return;
 	}
 
 	if (!snd_ctl_elem_info_is_writable(ctl->info)) {
 		ksft_print_msg("%s is not writeable\n", ctl->name);
-		ksft_test_result_skip("write_default.%d.%d\n",
-				      ctl->card->card, ctl->elem);
+		ksft_test_result_skip("write_default.%s.%d\n",
+				      ctl->card->card_name, ctl->elem);
 		return;
 	}
 
 	/* No idea what the default was for unreadable controls */
 	if (!snd_ctl_elem_info_is_readable(ctl->info)) {
 		ksft_print_msg("%s couldn't read default\n", ctl->name);
-		ksft_test_result_skip("write_default.%d.%d\n",
-				      ctl->card->card, ctl->elem);
+		ksft_test_result_skip("write_default.%s.%d\n",
+				      ctl->card->card_name, ctl->elem);
 		return;
 	}
 
 	err = write_and_verify(ctl, ctl->def_val, NULL);
 
-	ksft_test_result(err >= 0, "write_default.%d.%d\n",
-			 ctl->card->card, ctl->elem);
+	ksft_test_result(err >= 0, "write_default.%s.%d\n",
+			 ctl->card->card_name, ctl->elem);
 }
 
 static bool test_ctl_write_valid_boolean(struct ctl_data *ctl)
@@ -755,20 +844,19 @@ static bool test_ctl_write_valid_enumerated(struct ctl_data *ctl)
 static void test_ctl_write_valid(struct ctl_data *ctl)
 {
 	bool pass;
-	int err;
 
 	/* If the control is turned off let's be polite */
 	if (snd_ctl_elem_info_is_inactive(ctl->info)) {
 		ksft_print_msg("%s is inactive\n", ctl->name);
-		ksft_test_result_skip("write_valid.%d.%d\n",
-				      ctl->card->card, ctl->elem);
+		ksft_test_result_skip("write_valid.%s.%d\n",
+				      ctl->card->card_name, ctl->elem);
 		return;
 	}
 
 	if (!snd_ctl_elem_info_is_writable(ctl->info)) {
 		ksft_print_msg("%s is not writeable\n", ctl->name);
-		ksft_test_result_skip("write_valid.%d.%d\n",
-				      ctl->card->card, ctl->elem);
+		ksft_test_result_skip("write_valid.%s.%d\n",
+				      ctl->card->card_name, ctl->elem);
 		return;
 	}
 
@@ -791,25 +879,22 @@ static void test_ctl_write_valid(struct ctl_data *ctl)
 
 	default:
 		/* No tests for this yet */
-		ksft_test_result_skip("write_valid.%d.%d\n",
-				      ctl->card->card, ctl->elem);
+		ksft_test_result_skip("write_valid.%s.%d\n",
+				      ctl->card->card_name, ctl->elem);
 		return;
 	}
 
 	/* Restore the default value to minimise disruption */
-	err = write_and_verify(ctl, ctl->def_val, NULL);
-	if (err < 0)
-		pass = false;
+	write_and_verify(ctl, ctl->def_val, NULL);
 
-	ksft_test_result(pass, "write_valid.%d.%d\n",
-			 ctl->card->card, ctl->elem);
+	ksft_test_result(pass, "write_valid.%s.%d\n",
+			 ctl->card->card_name, ctl->elem);
 }
 
 static bool test_ctl_write_invalid_value(struct ctl_data *ctl,
 					 snd_ctl_elem_value_t *val)
 {
 	int err;
-	long val_read;
 
 	/* Ideally this will fail... */
 	err = snd_ctl_elem_write(ctl->card->handle, val);
@@ -829,8 +914,7 @@ static bool test_ctl_write_invalid_value(struct ctl_data *ctl,
 
 static bool test_ctl_write_invalid_boolean(struct ctl_data *ctl)
 {
-	int err, i;
-	long val_read;
+	int i;
 	bool fail = false;
 	snd_ctl_elem_value_t *val;
 	snd_ctl_elem_value_alloca(&val);
@@ -940,8 +1024,7 @@ static bool test_ctl_write_invalid_integer64(struct ctl_data *ctl)
 
 static bool test_ctl_write_invalid_enumerated(struct ctl_data *ctl)
 {
-	int err, i;
-	unsigned int val_read;
+	int i;
 	bool fail = false;
 	snd_ctl_elem_value_t *val;
 	snd_ctl_elem_value_alloca(&val);
@@ -973,20 +1056,19 @@ static bool test_ctl_write_invalid_enumerated(struct ctl_data *ctl)
 static void test_ctl_write_invalid(struct ctl_data *ctl)
 {
 	bool pass;
-	int err;
 
 	/* If the control is turned off let's be polite */
 	if (snd_ctl_elem_info_is_inactive(ctl->info)) {
 		ksft_print_msg("%s is inactive\n", ctl->name);
-		ksft_test_result_skip("write_invalid.%d.%d\n",
-				      ctl->card->card, ctl->elem);
+		ksft_test_result_skip("write_invalid.%s.%d\n",
+				      ctl->card->card_name, ctl->elem);
 		return;
 	}
 
 	if (!snd_ctl_elem_info_is_writable(ctl->info)) {
 		ksft_print_msg("%s is not writeable\n", ctl->name);
-		ksft_test_result_skip("write_invalid.%d.%d\n",
-				      ctl->card->card, ctl->elem);
+		ksft_test_result_skip("write_invalid.%s.%d\n",
+				      ctl->card->card_name, ctl->elem);
 		return;
 	}
 
@@ -1009,30 +1091,28 @@ static void test_ctl_write_invalid(struct ctl_data *ctl)
 
 	default:
 		/* No tests for this yet */
-		ksft_test_result_skip("write_invalid.%d.%d\n",
-				      ctl->card->card, ctl->elem);
+		ksft_test_result_skip("write_invalid.%s.%d\n",
+				      ctl->card->card_name, ctl->elem);
 		return;
 	}
 
 	/* Restore the default value to minimise disruption */
-	err = write_and_verify(ctl, ctl->def_val, NULL);
-	if (err < 0)
-		pass = false;
+	write_and_verify(ctl, ctl->def_val, NULL);
 
-	ksft_test_result(pass, "write_invalid.%d.%d\n",
-			 ctl->card->card, ctl->elem);
+	ksft_test_result(pass, "write_invalid.%s.%d\n",
+			 ctl->card->card_name, ctl->elem);
 }
 
 static void test_ctl_event_missing(struct ctl_data *ctl)
 {
-	ksft_test_result(!ctl->event_missing, "event_missing.%d.%d\n",
-			 ctl->card->card, ctl->elem);
+	ksft_test_result(!ctl->event_missing, "event_missing.%s.%d\n",
+			 ctl->card->card_name, ctl->elem);
 }
 
 static void test_ctl_event_spurious(struct ctl_data *ctl)
 {
-	ksft_test_result(!ctl->event_spurious, "event_spurious.%d.%d\n",
-			 ctl->card->card, ctl->elem);
+	ksft_test_result(!ctl->event_spurious, "event_spurious.%s.%d\n",
+			 ctl->card->card_name, ctl->elem);
 }
 
 int main(void)
diff --git a/tools/testing/selftests/alsa/pcm-test.c b/tools/testing/selftests/alsa/pcm-test.c
index f293c7d81009..ee04ccef7d7c 100644
--- a/tools/testing/selftests/alsa/pcm-test.c
+++ b/tools/testing/selftests/alsa/pcm-test.c
@@ -15,35 +15,47 @@
 #include <stdbool.h>
 #include <errno.h>
 #include <assert.h>
+#include <pthread.h>
 
-#include "../kselftest.h"
+#include "kselftest.h"
 #include "alsa-local.h"
 
 typedef struct timespec timestamp_t;
 
+struct card_data {
+	int card;
+	snd_ctl_card_info_t *info;
+	const char *name;
+	pthread_t thread;
+	struct card_data *next;
+};
+
+struct card_data *card_list;
+
 struct pcm_data {
 	snd_pcm_t *handle;
 	int card;
 	int device;
 	int subdevice;
+	const char *card_name;
 	snd_pcm_stream_t stream;
 	snd_config_t *pcm_config;
 	struct pcm_data *next;
 };
 
-int num_pcms = 0;
-struct pcm_data *pcm_list = NULL;
+struct pcm_data *pcm_list;
 
-int num_missing = 0;
-struct pcm_data *pcm_missing = NULL;
+int num_missing;
+struct pcm_data *pcm_missing;
 
-struct time_test_def {
-	const char *cfg_prefix;
-	const char *format;
-	long rate;
-	long channels;
-	long period_size;
-	long buffer_size;
+snd_config_t *default_pcm_config;
+
+/* Lock while reporting results since kselftest doesn't */
+pthread_mutex_t results_lock = PTHREAD_MUTEX_INITIALIZER;
+
+enum test_class {
+	TEST_CLASS_DEFAULT,
+	TEST_CLASS_SYSTEM,
 };
 
 void timestamp_now(timestamp_t *tstamp)
@@ -140,12 +152,14 @@ static void missing_devices(int card, snd_config_t *card_config)
 static void find_pcms(void)
 {
 	char name[32], key[64];
+	char *card_name, *card_longname;
 	int card, dev, subdev, count, direction, err;
 	snd_pcm_stream_t stream;
 	struct pcm_data *pcm_data;
 	snd_ctl_t *handle;
 	snd_pcm_info_t *pcm_info;
 	snd_config_t *config, *card_config, *pcm_config;
+	struct card_data *card_data;
 
 	snd_pcm_info_alloca(&pcm_info);
 
@@ -156,6 +170,10 @@ static void find_pcms(void)
 	config = get_alsalib_config();
 
 	while (card >= 0) {
+		card_data = calloc(1, sizeof(*card_data));
+		if (!card_data)
+			ksft_exit_fail_msg("Out of memory\n");
+
 		sprintf(name, "hw:%d", card);
 
 		err = snd_ctl_open_lconf(&handle, name, 0, config);
@@ -165,8 +183,39 @@ static void find_pcms(void)
 			goto next_card;
 		}
 
+		err = snd_card_get_name(card, &card_name);
+		if (err != 0)
+			card_name = "Unknown";
+		err = snd_card_get_longname(card, &card_longname);
+		if (err != 0)
+			card_longname = "Unknown";
+
+		err = snd_ctl_card_info_malloc(&card_data->info);
+		if (err != 0)
+			ksft_exit_fail_msg("Failed to allocate card info: %d\n",
+				err);
+
+		err = snd_ctl_card_info(handle, card_data->info);
+		if (err == 0) {
+			card_data->name = snd_ctl_card_info_get_id(card_data->info);
+			if (!card_data->name)
+				ksft_print_msg("Failed to get card ID\n");
+		} else {
+			ksft_print_msg("Failed to get card info: %d\n", err);
+		}
+
+		if (!card_data->name)
+			card_data->name = "Unknown";
+
+		ksft_print_msg("Card %d/%s - %s (%s)\n", card,
+			       card_data->name, card_name, card_longname);
+
 		card_config = conf_by_card(card);
 
+		card_data->card = card;
+		card_data->next = card_list;
+		card_list = card_data;
+
 		dev = -1;
 		while (1) {
 			if (snd_ctl_pcm_next_device(handle, &dev) < 0)
@@ -191,6 +240,10 @@ static void find_pcms(void)
 				if (err < 0)
 					ksft_exit_fail_msg("snd_ctl_pcm_info: %d:%d:%d\n",
 							   dev, 0, stream);
+
+				ksft_print_msg("%s.0 - %s\n", card_data->name,
+					       snd_pcm_info_get_id(pcm_info));
+
 				count = snd_pcm_info_get_subdevices_count(pcm_info);
 				for (subdev = 0; subdev < count; subdev++) {
 					sprintf(key, "pcm.%d.%d.%s", dev, subdev, snd_pcm_stream_name(stream));
@@ -205,11 +258,11 @@ static void find_pcms(void)
 					pcm_data->card = card;
 					pcm_data->device = dev;
 					pcm_data->subdevice = subdev;
+					pcm_data->card_name = card_data->name;
 					pcm_data->stream = stream;
 					pcm_data->pcm_config = conf_get_subtree(card_config, key, NULL);
 					pcm_data->next = pcm_list;
 					pcm_list = pcm_data;
-					num_pcms++;
 				}
 			}
 		}
@@ -228,45 +281,66 @@ static void find_pcms(void)
 	snd_config_delete(config);
 }
 
-static void test_pcm_time1(struct pcm_data *data,
-			   const struct time_test_def *test)
+static void test_pcm_time(struct pcm_data *data, enum test_class class,
+			  const char *test_name, snd_config_t *pcm_cfg)
 {
-	char name[64], key[128], msg[256];
+	char name[64], msg[256];
+	const int duration_s = 2, margin_ms = 100;
+	const int duration_ms = duration_s * 1000;
 	const char *cs;
 	int i, err;
 	snd_pcm_t *handle = NULL;
 	snd_pcm_access_t access = SND_PCM_ACCESS_RW_INTERLEAVED;
-	snd_pcm_format_t format;
+	snd_pcm_format_t format, old_format;
+	const char *alt_formats[8];
 	unsigned char *samples = NULL;
 	snd_pcm_sframes_t frames;
 	long long ms;
 	long rate, channels, period_size, buffer_size;
-	unsigned int rchannels;
 	unsigned int rrate;
 	snd_pcm_uframes_t rperiod_size, rbuffer_size, start_threshold;
 	timestamp_t tstamp;
-	bool pass = false, automatic = true;
+	bool pass = false;
 	snd_pcm_hw_params_t *hw_params;
 	snd_pcm_sw_params_t *sw_params;
-	bool skip = false;
+	const char *test_class_name;
+	bool skip = true;
+	const char *desc;
+
+	switch (class) {
+	case TEST_CLASS_DEFAULT:
+		test_class_name = "default";
+		break;
+	case TEST_CLASS_SYSTEM:
+		test_class_name = "system";
+		break;
+	default:
+		ksft_exit_fail_msg("Unknown test class %d\n", class);
+		break;
+	}
+
+	desc = conf_get_string(pcm_cfg, "description", NULL, NULL);
+	if (desc)
+		ksft_print_msg("%s.%s.%s.%d.%d.%s - %s\n",
+			       test_class_name, test_name,
+			       data->card_name, data->device, data->subdevice,
+			       snd_pcm_stream_name(data->stream),
+			       desc);
+
 
 	snd_pcm_hw_params_alloca(&hw_params);
 	snd_pcm_sw_params_alloca(&sw_params);
 
-	cs = conf_get_string(data->pcm_config, test->cfg_prefix, "format", test->format);
+	cs = conf_get_string(pcm_cfg, "format", NULL, "S16_LE");
 	format = snd_pcm_format_value(cs);
 	if (format == SND_PCM_FORMAT_UNKNOWN)
 		ksft_exit_fail_msg("Wrong format '%s'\n", cs);
-	rate = conf_get_long(data->pcm_config, test->cfg_prefix, "rate", test->rate);
-	channels = conf_get_long(data->pcm_config, test->cfg_prefix, "channels", test->channels);
-	period_size = conf_get_long(data->pcm_config, test->cfg_prefix, "period_size", test->period_size);
-	buffer_size = conf_get_long(data->pcm_config, test->cfg_prefix, "buffer_size", test->buffer_size);
-
-	automatic = strcmp(test->format, snd_pcm_format_name(format)) == 0 &&
-			test->rate == rate &&
-			test->channels == channels &&
-			test->period_size == period_size &&
-			test->buffer_size == buffer_size;
+	conf_get_string_array(pcm_cfg, "alt_formats", NULL,
+				alt_formats, ARRAY_SIZE(alt_formats), NULL);
+	rate = conf_get_long(pcm_cfg, "rate", NULL, 48000);
+	channels = conf_get_long(pcm_cfg, "channels", NULL, 2);
+	period_size = conf_get_long(pcm_cfg, "period_size", NULL, 4096);
+	buffer_size = conf_get_long(pcm_cfg, "buffer_size", NULL, 16384);
 
 	samples = malloc((rate * channels * snd_pcm_format_physical_width(format)) / 8);
 	if (!samples)
@@ -296,32 +370,39 @@ static void test_pcm_time1(struct pcm_data *data,
 					   snd_pcm_access_name(access), snd_strerror(err));
 		goto __close;
 	}
+	i = -1;
 __format:
 	err = snd_pcm_hw_params_set_format(handle, hw_params, format);
 	if (err < 0) {
-		if (automatic && format == SND_PCM_FORMAT_S16_LE) {
-			format = SND_PCM_FORMAT_S32_LE;
-			ksft_print_msg("%s.%d.%d.%d.%s.%s format S16_LE -> S32_LE\n",
-					 test->cfg_prefix,
-					 data->card, data->device, data->subdevice,
-					 snd_pcm_stream_name(data->stream),
-					 snd_pcm_access_name(access));
+		i++;
+		if (i < ARRAY_SIZE(alt_formats) && alt_formats[i]) {
+			old_format = format;
+			format = snd_pcm_format_value(alt_formats[i]);
+			if (format != SND_PCM_FORMAT_UNKNOWN) {
+				ksft_print_msg("%s.%s.%d.%d.%s.%s format %s -> %s\n",
+						 test_name,
+						 data->card_name, data->device, data->subdevice,
+						 snd_pcm_stream_name(data->stream),
+						 snd_pcm_access_name(access),
+						 snd_pcm_format_name(old_format),
+						 snd_pcm_format_name(format));
+				samples = realloc(samples, (rate * channels *
+							    snd_pcm_format_physical_width(format)) / 8);
+				if (!samples)
+					ksft_exit_fail_msg("Out of memory\n");
+				snd_pcm_format_set_silence(format, samples, rate * channels);
+				goto __format;
+			}
 		}
 		snprintf(msg, sizeof(msg), "snd_pcm_hw_params_set_format %s: %s",
 					   snd_pcm_format_name(format), snd_strerror(err));
 		goto __close;
 	}
-	rchannels = channels;
-	err = snd_pcm_hw_params_set_channels_near(handle, hw_params, &rchannels);
+	err = snd_pcm_hw_params_set_channels(handle, hw_params, channels);
 	if (err < 0) {
 		snprintf(msg, sizeof(msg), "snd_pcm_hw_params_set_channels %ld: %s", channels, snd_strerror(err));
 		goto __close;
 	}
-	if (rchannels != channels) {
-		snprintf(msg, sizeof(msg), "channels unsupported %ld != %ld", channels, rchannels);
-		skip = true;
-		goto __close;
-	}
 	rrate = rate;
 	err = snd_pcm_hw_params_set_rate_near(handle, hw_params, &rrate, 0);
 	if (err < 0) {
@@ -329,8 +410,7 @@ __format:
 		goto __close;
 	}
 	if (rrate != rate) {
-		snprintf(msg, sizeof(msg), "rate unsupported %ld != %ld", rate, rrate);
-		skip = true;
+		snprintf(msg, sizeof(msg), "rate mismatch %ld != %u", rate, rrate);
 		goto __close;
 	}
 	rperiod_size = period_size;
@@ -377,9 +457,9 @@ __format:
 		goto __close;
 	}
 
-	ksft_print_msg("%s.%d.%d.%d.%s hw_params.%s.%s.%ld.%ld.%ld.%ld sw_params.%ld\n",
-			 test->cfg_prefix,
-			 data->card, data->device, data->subdevice,
+	ksft_print_msg("%s.%s.%s.%d.%d.%s hw_params.%s.%s.%ld.%ld.%ld.%ld sw_params.%ld\n",
+		         test_class_name, test_name,
+			 data->card_name, data->device, data->subdevice,
 			 snd_pcm_stream_name(data->stream),
 			 snd_pcm_access_name(access),
 			 snd_pcm_format_name(format),
@@ -387,30 +467,33 @@ __format:
 			 (long)rperiod_size, (long)rbuffer_size,
 			 (long)start_threshold);
 
+	/* Set all the params, actually run the test */
+	skip = false;
+
 	timestamp_now(&tstamp);
-	for (i = 0; i < 4; i++) {
+	for (i = 0; i < duration_s; i++) {
 		if (data->stream == SND_PCM_STREAM_PLAYBACK) {
 			frames = snd_pcm_writei(handle, samples, rate);
 			if (frames < 0) {
 				snprintf(msg, sizeof(msg),
-					 "Write failed: expected %d, wrote %li", rate, frames);
+					 "Write failed: expected %ld, wrote %li", rate, frames);
 				goto __close;
 			}
 			if (frames < rate) {
 				snprintf(msg, sizeof(msg),
-					 "expected %d, wrote %li", rate, frames);
+					 "expected %ld, wrote %li", rate, frames);
 				goto __close;
 			}
 		} else {
 			frames = snd_pcm_readi(handle, samples, rate);
 			if (frames < 0) {
 				snprintf(msg, sizeof(msg),
-					 "expected %d, wrote %li", rate, frames);
+					 "expected %ld, wrote %li", rate, frames);
 				goto __close;
 			}
 			if (frames < rate) {
 				snprintf(msg, sizeof(msg),
-					 "expected %d, wrote %li", rate, frames);
+					 "expected %ld, wrote %li", rate, frames);
 				goto __close;
 			}
 		}
@@ -418,69 +501,168 @@ __format:
 
 	snd_pcm_drain(handle);
 	ms = timestamp_diff_ms(&tstamp);
-	if (ms < 3900 || ms > 4100) {
-		snprintf(msg, sizeof(msg), "time mismatch: expected 4000ms got %lld", ms);
+	if (ms < duration_ms - margin_ms || ms > duration_ms + margin_ms) {
+		snprintf(msg, sizeof(msg), "time mismatch: expected %dms got %lld", duration_ms, ms);
 		goto __close;
 	}
 
 	msg[0] = '\0';
 	pass = true;
 __close:
-	if (!skip) {
-		ksft_test_result(pass, "%s.%d.%d.%d.%s%s%s\n",
-				 test->cfg_prefix,
-				 data->card, data->device, data->subdevice,
-				 snd_pcm_stream_name(data->stream),
-				 msg[0] ? " " : "", msg);
-	} else {
-		ksft_test_result_skip("%s.%d.%d.%d.%s%s%s\n",
-				      test->cfg_prefix,
-				      data->card, data->device,
-				      data->subdevice,
-				      snd_pcm_stream_name(data->stream),
-				      msg[0] ? " " : "", msg);
+	pthread_mutex_lock(&results_lock);
+
+	switch (class) {
+	case TEST_CLASS_SYSTEM:
+		test_class_name = "system";
+		/*
+		 * Anything specified as specific to this system
+		 * should always be supported.
+		 */
+		ksft_test_result(!skip, "%s.%s.%s.%d.%d.%s.params\n",
+				 test_class_name, test_name,
+				 data->card_name, data->device,
+				 data->subdevice,
+				 snd_pcm_stream_name(data->stream));
+		break;
+	default:
+		break;
 	}
+
+	if (!skip)
+		ksft_test_result(pass, "%s.%s.%s.%d.%d.%s\n",
+				 test_class_name, test_name,
+				 data->card_name, data->device,
+				 data->subdevice,
+				 snd_pcm_stream_name(data->stream));
+	else
+		ksft_test_result_skip("%s.%s.%s.%d.%d.%s\n",
+				 test_class_name, test_name,
+				 data->card_name, data->device,
+				 data->subdevice,
+				 snd_pcm_stream_name(data->stream));
+
+	if (msg[0])
+		ksft_print_msg("%s\n", msg);
+
+	pthread_mutex_unlock(&results_lock);
+
 	free(samples);
 	if (handle)
 		snd_pcm_close(handle);
 }
 
-static const struct time_test_def time_tests[] = {
-	/* name          format     rate   chan  period  buffer */
-	{ "8k.1.big",    "S16_LE",   8000, 2,     8000,   32000 },
-	{ "8k.2.big",    "S16_LE",   8000, 2,     8000,   32000 },
-	{ "44k1.2.big",  "S16_LE",  44100, 2,    22050,  192000 },
-	{ "48k.2.small", "S16_LE",  48000, 2,      512,    4096 },
-	{ "48k.2.big",   "S16_LE",  48000, 2,    24000,  192000 },
-	{ "48k.6.big",   "S16_LE",  48000, 6,    48000,  576000 },
-	{ "96k.2.big",   "S16_LE",  96000, 2,    48000,  192000 },
-};
+void run_time_tests(struct pcm_data *pcm, enum test_class class,
+		    snd_config_t *cfg)
+{
+	const char *test_name, *test_type;
+	snd_config_t *pcm_cfg;
+	snd_config_iterator_t i, next;
+
+	if (!cfg)
+		return;
+
+	cfg = conf_get_subtree(cfg, "test", NULL);
+	if (cfg == NULL)
+		return;
+
+	snd_config_for_each(i, next, cfg) {
+		pcm_cfg = snd_config_iterator_entry(i);
+		if (snd_config_get_id(pcm_cfg, &test_name) < 0)
+			ksft_exit_fail_msg("snd_config_get_id\n");
+		test_type = conf_get_string(pcm_cfg, "type", NULL, "time");
+		if (strcmp(test_type, "time") == 0)
+			test_pcm_time(pcm, class, test_name, pcm_cfg);
+		else
+			ksft_exit_fail_msg("unknown test type '%s'\n", test_type);
+	}
+}
+
+void *card_thread(void *data)
+{
+	struct card_data *card = data;
+	struct pcm_data *pcm;
+
+	for (pcm = pcm_list; pcm != NULL; pcm = pcm->next) {
+		if (pcm->card != card->card)
+			continue;
+
+		run_time_tests(pcm, TEST_CLASS_DEFAULT, default_pcm_config);
+		run_time_tests(pcm, TEST_CLASS_SYSTEM, pcm->pcm_config);
+	}
+
+	return 0;
+}
 
 int main(void)
 {
+	struct card_data *card;
+	struct card_cfg_data *conf;
 	struct pcm_data *pcm;
-	int i;
+	snd_config_t *global_config, *cfg;
+	int num_pcm_tests = 0, num_tests, num_std_pcm_tests;
+	int ret;
+	void *thread_ret;
 
 	ksft_print_header();
 
+	global_config = conf_load_from_file("pcm-test.conf");
+	default_pcm_config = conf_get_subtree(global_config, "pcm", NULL);
+	if (default_pcm_config == NULL)
+		ksft_exit_fail_msg("default pcm test configuration (pcm compound) is missing\n");
+
 	conf_load();
 
 	find_pcms();
 
-	ksft_set_plan(num_missing + num_pcms * ARRAY_SIZE(time_tests));
+	for (conf = conf_cards; conf; conf = conf->next)
+		if (conf->card < 0)
+			num_missing++;
+
+	num_std_pcm_tests = conf_get_count(default_pcm_config, "test", NULL);
+
+	for (pcm = pcm_list; pcm != NULL; pcm = pcm->next) {
+		num_pcm_tests += num_std_pcm_tests;
+		cfg = pcm->pcm_config;
+		if (cfg == NULL)
+			continue;
+		/* Setting params is reported as a separate test */
+		num_tests = conf_get_count(cfg, "test", NULL) * 2;
+		if (num_tests > 0)
+			num_pcm_tests += num_tests;
+	}
+
+	ksft_set_plan(num_missing + num_pcm_tests);
+
+	for (conf = conf_cards; conf; conf = conf->next)
+		if (conf->card < 0)
+			ksft_test_result_fail("test.missing.%s.%s\n",
+					      conf->filename, conf->config_id);
 
 	for (pcm = pcm_missing; pcm != NULL; pcm = pcm->next) {
-		ksft_test_result(false, "test.missing.%d.%d.%d.%s\n",
-				 pcm->card, pcm->device, pcm->subdevice,
+		ksft_test_result(false, "test.missing.%s.%d.%d.%s\n",
+				 pcm->card_name, pcm->device, pcm->subdevice,
 				 snd_pcm_stream_name(pcm->stream));
 	}
 
-	for (pcm = pcm_list; pcm != NULL; pcm = pcm->next) {
-		for (i = 0; i < ARRAY_SIZE(time_tests); i++) {
-			test_pcm_time1(pcm, &time_tests[i]);
+	for (card = card_list; card != NULL; card = card->next) {
+		ret = pthread_create(&card->thread, NULL, card_thread, card);
+		if (ret != 0) {
+			ksft_exit_fail_msg("Failed to create card %d thread: %d (%s)\n",
+					   card->card, ret,
+					   strerror(errno));
+		}
+	}
+
+	for (card = card_list; card != NULL; card = card->next) {
+		ret = pthread_join(card->thread, &thread_ret);
+		if (ret != 0) {
+			ksft_exit_fail_msg("Failed to join card %d thread: %d (%s)\n",
+					   card->card, ret,
+					   strerror(errno));
 		}
 	}
 
+	snd_config_delete(global_config);
 	conf_free();
 
 	ksft_exit_pass();
diff --git a/tools/testing/selftests/alsa/pcm-test.conf b/tools/testing/selftests/alsa/pcm-test.conf
new file mode 100644
index 000000000000..71bd3f78a6f2
--- /dev/null
+++ b/tools/testing/selftests/alsa/pcm-test.conf
@@ -0,0 +1,63 @@
+pcm.test.time1 {
+	description "8kHz mono large periods"
+	format S16_LE
+	alt_formats [ S32_LE ]
+	rate 8000
+	channels 1
+	period_size 8000
+	buffer_size 32000
+}
+pcm.test.time2 {
+	description "8kHz stereo large periods"
+	format S16_LE
+	alt_formats [ S32_LE ]
+	rate 8000
+	channels 2
+	period_size 8000
+	buffer_size 32000
+}
+pcm.test.time3 {
+	description "44.1kHz stereo large periods"
+	format S16_LE
+	alt_formats [ S32_LE ]
+	rate 44100
+	channels 2
+	period_size 22500
+	buffer_size 192000
+}
+pcm.test.time4 {
+	description "48kHz stereo small periods"
+	format S16_LE
+	alt_formats [ S32_LE ]
+	rate 48000
+	channels 2
+	period_size 512
+	buffer_size 4096
+}
+pcm.test.time5 {
+	description "48kHz stereo large periods"
+	format S16_LE
+	alt_formats [ S32_LE ]
+	rate 48000
+	channels 2
+	period_size 24000
+	buffer_size 192000
+}
+pcm.test.time6 {
+	description "48kHz 6 channel large periods"
+	format S16_LE
+	alt_formats [ S32_LE ]
+	rate 48000
+	channels 2
+	period_size 48000
+	buffer_size 576000
+}
+pcm.test.time7 {
+	description "96kHz stereo large periods"
+	format S16_LE
+	alt_formats [ S32_LE ]
+	rate 96000
+	channels 2
+	period_size 48000
+	buffer_size 192000
+}
diff --git a/tools/testing/selftests/alsa/test-pcmtest-driver.c b/tools/testing/selftests/alsa/test-pcmtest-driver.c
new file mode 100644
index 000000000000..95065ef3b441
--- /dev/null
+++ b/tools/testing/selftests/alsa/test-pcmtest-driver.c
@@ -0,0 +1,330 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This is the test which covers PCM middle layer data transferring using
+ * the virtual pcm test driver (snd-pcmtest).
+ *
+ * Copyright 2023 Ivan Orlov <ivan.orlov0322@gmail.com>
+ */
+#include <string.h>
+#include <alsa/asoundlib.h>
+#include "kselftest_harness.h"
+
+#define CH_NUM 4
+
+struct pattern_buf {
+	char buf[1024];
+	int len;
+};
+
+struct pattern_buf patterns[CH_NUM];
+
+struct pcmtest_test_params {
+	unsigned long buffer_size;
+	unsigned long period_size;
+	unsigned long channels;
+	unsigned int rate;
+	snd_pcm_access_t access;
+	size_t sec_buf_len;
+	size_t sample_size;
+	int time;
+	snd_pcm_format_t format;
+};
+
+static int read_patterns(void)
+{
+	FILE *fp, *fpl;
+	int i;
+	char pf[64];
+	char plf[64];
+
+	for (i = 0; i < CH_NUM; i++) {
+		sprintf(plf, "/sys/kernel/debug/pcmtest/fill_pattern%d_len", i);
+		fpl = fopen(plf, "r");
+		if (!fpl)
+			return -1;
+		fscanf(fpl, "%u", &patterns[i].len);
+		fclose(fpl);
+
+		sprintf(pf, "/sys/kernel/debug/pcmtest/fill_pattern%d", i);
+		fp = fopen(pf, "r");
+		if (!fp)
+			return -1;
+		fread(patterns[i].buf, 1, patterns[i].len, fp);
+		fclose(fp);
+	}
+
+	return 0;
+}
+
+static int get_test_results(char *debug_name)
+{
+	int result;
+	FILE *f;
+	char fname[128];
+
+	sprintf(fname, "/sys/kernel/debug/pcmtest/%s", debug_name);
+
+	f = fopen(fname, "r");
+	if (!f) {
+		printf("Failed to open file\n");
+		return -1;
+	}
+	fscanf(f, "%d", &result);
+	fclose(f);
+
+	return result;
+}
+
+static size_t get_sec_buf_len(unsigned int rate, unsigned long channels, snd_pcm_format_t format)
+{
+	return rate * channels * snd_pcm_format_physical_width(format) / 8;
+}
+
+static int setup_handle(snd_pcm_t **handle, snd_pcm_sw_params_t *swparams,
+			snd_pcm_hw_params_t *hwparams, struct pcmtest_test_params *params,
+			int card, snd_pcm_stream_t stream)
+{
+	char pcm_name[32];
+	int err;
+
+	sprintf(pcm_name, "hw:%d,0,0", card);
+	err = snd_pcm_open(handle, pcm_name, stream, 0);
+	if (err < 0)
+		return err;
+	snd_pcm_hw_params_any(*handle, hwparams);
+	snd_pcm_hw_params_set_rate_resample(*handle, hwparams, 0);
+	snd_pcm_hw_params_set_access(*handle, hwparams, params->access);
+	snd_pcm_hw_params_set_format(*handle, hwparams, params->format);
+	snd_pcm_hw_params_set_channels(*handle, hwparams, params->channels);
+	snd_pcm_hw_params_set_rate_near(*handle, hwparams, &params->rate, 0);
+	snd_pcm_hw_params_set_period_size_near(*handle, hwparams, &params->period_size, 0);
+	snd_pcm_hw_params_set_buffer_size_near(*handle, hwparams, &params->buffer_size);
+	snd_pcm_hw_params(*handle, hwparams);
+	snd_pcm_sw_params_current(*handle, swparams);
+
+	snd_pcm_hw_params_set_rate_resample(*handle, hwparams, 0);
+	snd_pcm_sw_params_set_avail_min(*handle, swparams, params->period_size);
+	snd_pcm_hw_params_set_buffer_size_near(*handle, hwparams, &params->buffer_size);
+	snd_pcm_hw_params_set_period_size_near(*handle, hwparams, &params->period_size, 0);
+	snd_pcm_sw_params(*handle, swparams);
+	snd_pcm_hw_params(*handle, hwparams);
+
+	return 0;
+}
+
+FIXTURE(pcmtest) {
+	int card;
+	snd_pcm_sw_params_t *swparams;
+	snd_pcm_hw_params_t *hwparams;
+	struct pcmtest_test_params params;
+};
+
+FIXTURE_TEARDOWN(pcmtest) {
+}
+
+FIXTURE_SETUP(pcmtest) {
+	char *card_name;
+	int err;
+
+	if (geteuid())
+		SKIP(return, "This test needs root to run!");
+
+	err = read_patterns();
+	if (err)
+		SKIP(return, "Can't read patterns. Probably, module isn't loaded");
+
+	card_name = malloc(127);
+	ASSERT_NE(card_name, NULL);
+	self->params.buffer_size = 16384;
+	self->params.period_size = 4096;
+	self->params.channels = CH_NUM;
+	self->params.rate = 8000;
+	self->params.access = SND_PCM_ACCESS_RW_INTERLEAVED;
+	self->params.format = SND_PCM_FORMAT_S16_LE;
+	self->card = -1;
+	self->params.sample_size = snd_pcm_format_physical_width(self->params.format) / 8;
+
+	self->params.sec_buf_len = get_sec_buf_len(self->params.rate, self->params.channels,
+						   self->params.format);
+	self->params.time = 4;
+
+	while (snd_card_next(&self->card) >= 0) {
+		if (self->card == -1)
+			break;
+		snd_card_get_name(self->card, &card_name);
+		if (!strcmp(card_name, "PCM-Test"))
+			break;
+	}
+	free(card_name);
+	ASSERT_NE(self->card, -1);
+}
+
+/*
+ * Here we are trying to send the looped monotonically increasing sequence of bytes to the driver.
+ * If our data isn't corrupted, the driver will set the content of 'pc_test' debugfs file to '1'
+ */
+TEST_F(pcmtest, playback) {
+	snd_pcm_t *handle;
+	unsigned char *it;
+	size_t write_res;
+	int test_results;
+	int i, cur_ch, pos_in_ch;
+	void *samples;
+	struct pcmtest_test_params *params = &self->params;
+
+	samples = calloc(self->params.sec_buf_len * self->params.time, 1);
+	ASSERT_NE(samples, NULL);
+
+	snd_pcm_sw_params_alloca(&self->swparams);
+	snd_pcm_hw_params_alloca(&self->hwparams);
+
+	ASSERT_EQ(setup_handle(&handle, self->swparams, self->hwparams, params,
+			       self->card, SND_PCM_STREAM_PLAYBACK), 0);
+	snd_pcm_format_set_silence(params->format, samples,
+				   params->rate * params->channels * params->time);
+	it = samples;
+	for (i = 0; i < self->params.sec_buf_len * params->time; i++) {
+		cur_ch = (i / params->sample_size) % CH_NUM;
+		pos_in_ch = i / params->sample_size / CH_NUM * params->sample_size
+			    + (i % params->sample_size);
+		it[i] = patterns[cur_ch].buf[pos_in_ch % patterns[cur_ch].len];
+	}
+	write_res = snd_pcm_writei(handle, samples, params->rate * params->time);
+	ASSERT_GE(write_res, 0);
+
+	snd_pcm_close(handle);
+	free(samples);
+	test_results = get_test_results("pc_test");
+	ASSERT_EQ(test_results, 1);
+}
+
+/*
+ * Here we test that the virtual alsa driver returns looped and monotonically increasing sequence
+ * of bytes. In the interleaved mode the buffer will contain samples in the following order:
+ * C0, C1, C2, C3, C0, C1, ...
+ */
+TEST_F(pcmtest, capture) {
+	snd_pcm_t *handle;
+	unsigned char *it;
+	size_t read_res;
+	int i, cur_ch, pos_in_ch;
+	void *samples;
+	struct pcmtest_test_params *params = &self->params;
+
+	samples = calloc(self->params.sec_buf_len * self->params.time, 1);
+	ASSERT_NE(samples, NULL);
+
+	snd_pcm_sw_params_alloca(&self->swparams);
+	snd_pcm_hw_params_alloca(&self->hwparams);
+
+	ASSERT_EQ(setup_handle(&handle, self->swparams, self->hwparams,
+			       params, self->card, SND_PCM_STREAM_CAPTURE), 0);
+	snd_pcm_format_set_silence(params->format, samples,
+				   params->rate * params->channels * params->time);
+	read_res = snd_pcm_readi(handle, samples, params->rate * params->time);
+	ASSERT_GE(read_res, 0);
+	snd_pcm_close(handle);
+	it = (unsigned char *)samples;
+	for (i = 0; i < self->params.sec_buf_len * self->params.time; i++) {
+		cur_ch = (i / params->sample_size) % CH_NUM;
+		pos_in_ch = i / params->sample_size / CH_NUM * params->sample_size
+			    + (i % params->sample_size);
+		ASSERT_EQ(it[i], patterns[cur_ch].buf[pos_in_ch % patterns[cur_ch].len]);
+	}
+	free(samples);
+}
+
+// Test capture in the non-interleaved access mode. The are buffers for each recorded channel
+TEST_F(pcmtest, ni_capture) {
+	snd_pcm_t *handle;
+	struct pcmtest_test_params params = self->params;
+	char **chan_samples;
+	size_t i, j, read_res;
+
+	chan_samples = calloc(CH_NUM, sizeof(*chan_samples));
+	ASSERT_NE(chan_samples, NULL);
+
+	snd_pcm_sw_params_alloca(&self->swparams);
+	snd_pcm_hw_params_alloca(&self->hwparams);
+
+	params.access = SND_PCM_ACCESS_RW_NONINTERLEAVED;
+
+	ASSERT_EQ(setup_handle(&handle, self->swparams, self->hwparams,
+			       &params, self->card, SND_PCM_STREAM_CAPTURE), 0);
+
+	for (i = 0; i < CH_NUM; i++)
+		chan_samples[i] = calloc(params.sec_buf_len * params.time, 1);
+
+	for (i = 0; i < 1; i++) {
+		read_res = snd_pcm_readn(handle, (void **)chan_samples, params.rate * params.time);
+		ASSERT_GE(read_res, 0);
+	}
+	snd_pcm_close(handle);
+
+	for (i = 0; i < CH_NUM; i++) {
+		for (j = 0; j < params.rate * params.time; j++)
+			ASSERT_EQ(chan_samples[i][j], patterns[i].buf[j % patterns[i].len]);
+		free(chan_samples[i]);
+	}
+	free(chan_samples);
+}
+
+TEST_F(pcmtest, ni_playback) {
+	snd_pcm_t *handle;
+	struct pcmtest_test_params params = self->params;
+	char **chan_samples;
+	size_t i, j, read_res;
+	int test_res;
+
+	chan_samples = calloc(CH_NUM, sizeof(*chan_samples));
+	ASSERT_NE(chan_samples, NULL);
+
+	snd_pcm_sw_params_alloca(&self->swparams);
+	snd_pcm_hw_params_alloca(&self->hwparams);
+
+	params.access = SND_PCM_ACCESS_RW_NONINTERLEAVED;
+
+	ASSERT_EQ(setup_handle(&handle, self->swparams, self->hwparams,
+			       &params, self->card, SND_PCM_STREAM_PLAYBACK), 0);
+
+	for (i = 0; i < CH_NUM; i++) {
+		chan_samples[i] = calloc(params.sec_buf_len * params.time, 1);
+		for (j = 0; j < params.sec_buf_len * params.time; j++)
+			chan_samples[i][j] = patterns[i].buf[j % patterns[i].len];
+	}
+
+	for (i = 0; i < 1; i++) {
+		read_res = snd_pcm_writen(handle, (void **)chan_samples, params.rate * params.time);
+		ASSERT_GE(read_res, 0);
+	}
+
+	snd_pcm_close(handle);
+	test_res = get_test_results("pc_test");
+	ASSERT_EQ(test_res, 1);
+
+	for (i = 0; i < CH_NUM; i++)
+		free(chan_samples[i]);
+	free(chan_samples);
+}
+
+/*
+ * Here we are testing the custom ioctl definition inside the virtual driver. If it triggers
+ * successfully, the driver sets the content of 'ioctl_test' debugfs file to '1'.
+ */
+TEST_F(pcmtest, reset_ioctl) {
+	snd_pcm_t *handle;
+	int test_res;
+	struct pcmtest_test_params *params = &self->params;
+
+	snd_pcm_sw_params_alloca(&self->swparams);
+	snd_pcm_hw_params_alloca(&self->hwparams);
+
+	ASSERT_EQ(setup_handle(&handle, self->swparams, self->hwparams, params,
+			       self->card, SND_PCM_STREAM_CAPTURE), 0);
+	snd_pcm_reset(handle);
+	test_res = get_test_results("ioctl_test");
+	ASSERT_EQ(test_res, 1);
+	snd_pcm_close(handle);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/alsa/utimer-test.c b/tools/testing/selftests/alsa/utimer-test.c
new file mode 100644
index 000000000000..c45cb226bd8f
--- /dev/null
+++ b/tools/testing/selftests/alsa/utimer-test.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This test covers the functionality of userspace-driven ALSA timers. Such timers
+ * are purely virtual (so they don't directly depend on the hardware), and they could be
+ * created and triggered by userspace applications.
+ *
+ * Author: Ivan Orlov <ivan.orlov0322@gmail.com>
+ */
+#include "kselftest_harness.h"
+#include <sound/asound.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <sys/ioctl.h>
+#include <stdlib.h>
+#include <pthread.h>
+#include <string.h>
+
+#define FRAME_RATE 8000
+#define PERIOD_SIZE 4410
+#define UTIMER_DEFAULT_ID -1
+#define UTIMER_DEFAULT_FD -1
+#define NANO 1000000000ULL
+#define TICKS_COUNT 10
+#define TICKS_RECORDING_DELTA 5
+#define TIMER_OUTPUT_BUF_LEN 1024
+#define TIMER_FREQ_SEC 1
+#define RESULT_PREFIX_LEN strlen("Total ticks count: ")
+
+enum timer_app_event {
+	TIMER_APP_STARTED,
+	TIMER_APP_RESULT,
+	TIMER_NO_EVENT,
+};
+
+FIXTURE(timer_f) {
+	struct snd_timer_uinfo *utimer_info;
+};
+
+FIXTURE_SETUP(timer_f) {
+	int timer_dev_fd;
+
+	if (geteuid())
+		SKIP(return, "This test needs root to run!");
+
+	self->utimer_info = calloc(1, sizeof(*self->utimer_info));
+	ASSERT_NE(NULL, self->utimer_info);
+
+	/* Resolution is the time the period of frames takes in nanoseconds */
+	self->utimer_info->resolution = (NANO / FRAME_RATE * PERIOD_SIZE);
+
+	timer_dev_fd = open("/dev/snd/timer", O_RDONLY);
+	ASSERT_GE(timer_dev_fd, 0);
+
+	ASSERT_EQ(ioctl(timer_dev_fd, SNDRV_TIMER_IOCTL_CREATE, self->utimer_info), 0);
+	ASSERT_GE(self->utimer_info->fd, 0);
+
+	close(timer_dev_fd);
+}
+
+FIXTURE_TEARDOWN(timer_f) {
+	close(self->utimer_info->fd);
+	free(self->utimer_info);
+}
+
+static void *ticking_func(void *data)
+{
+	int i;
+	int *fd = (int *)data;
+
+	for (i = 0; i < TICKS_COUNT; i++) {
+		/* Well, trigger the timer! */
+		ioctl(*fd, SNDRV_TIMER_IOCTL_TRIGGER, NULL);
+		sleep(TIMER_FREQ_SEC);
+	}
+
+	return NULL;
+}
+
+static enum timer_app_event parse_timer_output(const char *s)
+{
+	if (strstr(s, "Timer has started"))
+		return TIMER_APP_STARTED;
+	if (strstr(s, "Total ticks count"))
+		return TIMER_APP_RESULT;
+
+	return TIMER_NO_EVENT;
+}
+
+static int parse_timer_result(const char *s)
+{
+	char *end;
+	long d;
+
+	d = strtol(s + RESULT_PREFIX_LEN, &end, 10);
+	if (end == s + RESULT_PREFIX_LEN)
+		return -1;
+
+	return d;
+}
+
+/*
+ * This test triggers the timer and counts ticks at the same time. The amount
+ * of the timer trigger calls should be equal to the amount of ticks received.
+ */
+TEST_F(timer_f, utimer) {
+	char command[64];
+	pthread_t ticking_thread;
+	int total_ticks = 0;
+	FILE *rfp;
+	char *buf = malloc(TIMER_OUTPUT_BUF_LEN);
+
+	ASSERT_NE(buf, NULL);
+
+	/* The timeout should be the ticks interval * count of ticks + some delta */
+	sprintf(command, "./global-timer %d %d %d", SNDRV_TIMER_GLOBAL_UDRIVEN,
+		self->utimer_info->id, TICKS_COUNT * TIMER_FREQ_SEC + TICKS_RECORDING_DELTA);
+
+	rfp = popen(command, "r");
+	while (fgets(buf, TIMER_OUTPUT_BUF_LEN, rfp)) {
+		buf[TIMER_OUTPUT_BUF_LEN - 1] = 0;
+		switch (parse_timer_output(buf)) {
+		case TIMER_APP_STARTED:
+			/* global-timer waits for timer to trigger, so start the ticking thread */
+			pthread_create(&ticking_thread, NULL, ticking_func,
+				       &self->utimer_info->fd);
+			break;
+		case TIMER_APP_RESULT:
+			total_ticks = parse_timer_result(buf);
+			break;
+		case TIMER_NO_EVENT:
+			break;
+		}
+	}
+	pthread_join(ticking_thread, NULL);
+	ASSERT_EQ(total_ticks, TICKS_COUNT);
+	pclose(rfp);
+	free(buf);
+}
+
+TEST(wrong_timers_test) {
+	int timer_dev_fd;
+	int utimer_fd;
+	size_t i;
+	struct snd_timer_uinfo wrong_timer = {
+		.resolution = 0,
+		.id = UTIMER_DEFAULT_ID,
+		.fd = UTIMER_DEFAULT_FD,
+	};
+
+	timer_dev_fd = open("/dev/snd/timer", O_RDONLY);
+	ASSERT_GE(timer_dev_fd, 0);
+
+	utimer_fd = ioctl(timer_dev_fd, SNDRV_TIMER_IOCTL_CREATE, &wrong_timer);
+	ASSERT_LT(utimer_fd, 0);
+	/* Check that id was not updated */
+	ASSERT_EQ(wrong_timer.id, UTIMER_DEFAULT_ID);
+
+	/* Test the NULL as an argument is processed correctly */
+	ASSERT_LT(ioctl(timer_dev_fd, SNDRV_TIMER_IOCTL_CREATE, NULL), 0);
+
+	close(timer_dev_fd);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/amd-pstate/Makefile b/tools/testing/selftests/amd-pstate/Makefile
index 5f195ee756d6..c382f579fe94 100644
--- a/tools/testing/selftests/amd-pstate/Makefile
+++ b/tools/testing/selftests/amd-pstate/Makefile
@@ -4,15 +4,15 @@
 # No binaries, but make sure arg-less "make" doesn't trigger "run_tests"
 all:
 
-uname_M := $(shell uname -m 2>/dev/null || echo not)
-ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
+ARCH ?= $(shell uname -m 2>/dev/null || echo not)
+ARCH := $(shell echo $(ARCH) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
 
 ifeq (x86,$(ARCH))
-TEST_GEN_FILES += ../../../power/x86/amd_pstate_tracer/amd_pstate_trace.py
-TEST_GEN_FILES += ../../../power/x86/intel_pstate_tracer/intel_pstate_tracer.py
+TEST_FILES += ../../../power/x86/amd_pstate_tracer/amd_pstate_trace.py
+TEST_FILES += ../../../power/x86/intel_pstate_tracer/intel_pstate_tracer.py
 endif
 
-TEST_PROGS := run.sh
-TEST_FILES := basic.sh tbench.sh gitsource.sh
+TEST_PROGS += run.sh
+TEST_FILES += basic.sh tbench.sh gitsource.sh
 
 include ../lib.mk
diff --git a/tools/testing/selftests/amd-pstate/gitsource.sh b/tools/testing/selftests/amd-pstate/gitsource.sh
index dbc1fe45599d..4cde62f90468 100755
--- a/tools/testing/selftests/amd-pstate/gitsource.sh
+++ b/tools/testing/selftests/amd-pstate/gitsource.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 # Testing and monitor the cpu desire performance, frequency, load,
@@ -66,12 +66,15 @@ post_clear_gitsource()
 
 install_gitsource()
 {
-	if [ ! -d $git_name ]; then
+	if [ ! -d $SCRIPTDIR/$git_name ]; then
+		pushd $(pwd) > /dev/null 2>&1
+		cd $SCRIPTDIR
 		printf "Download gitsource, please wait a moment ...\n\n"
 		wget -O $git_tar $gitsource_url > /dev/null 2>&1
 
 		printf "Tar gitsource ...\n\n"
 		tar -xzf $git_tar
+		popd > /dev/null 2>&1
 	fi
 }
 
@@ -79,12 +82,14 @@ install_gitsource()
 run_gitsource()
 {
 	echo "Launching amd pstate tracer for $1 #$2 tracer_interval: $TRACER_INTERVAL"
-	./amd_pstate_trace.py -n tracer-gitsource-$1-$2 -i $TRACER_INTERVAL > /dev/null 2>&1 &
+	$TRACER -n tracer-gitsource-$1-$2 -i $TRACER_INTERVAL > /dev/null 2>&1 &
 
 	printf "Make and test gitsource for $1 #$2 make_cpus: $MAKE_CPUS\n"
-	cd $git_name
-	perf stat -a --per-socket -I 1000 -e power/energy-pkg/ /usr/bin/time -o ../$OUTFILE_GIT.time-gitsource-$1-$2.log make test -j$MAKE_CPUS > ../$OUTFILE_GIT-perf-$1-$2.log 2>&1
-	cd ..
+	BACKUP_DIR=$(pwd)
+	pushd $BACKUP_DIR > /dev/null 2>&1
+	cd $SCRIPTDIR/$git_name
+	$PERF stat -a --per-socket -I 1000 -e power/energy-pkg/ /usr/bin/time -o $BACKUP_DIR/$OUTFILE_GIT.time-gitsource-$1-$2.log make test -j$MAKE_CPUS > $BACKUP_DIR/$OUTFILE_GIT-perf-$1-$2.log 2>&1
+	popd > /dev/null 2>&1
 
 	for job in `jobs -p`
 	do
@@ -117,7 +122,7 @@ parse_gitsource()
 	printf "Gitsource-$1-#$2 power consumption(J): $en_sum\n" | tee -a $OUTFILE_GIT.result
 
 	# Permance is the number of run gitsource per second, denoted 1/t, where 1 is the number of run gitsource in t
-	# senconds. It is well known that P=E/t, where P is power measured in watts(W), E is energy measured in joules(J),
+	# seconds. It is well known that P=E/t, where P is power measured in watts(W), E is energy measured in joules(J),
 	# and t is time measured in seconds(s). This means that performance per watt becomes
 	#        1/t     1/t     1
 	#       ----- = ----- = ---
@@ -175,7 +180,7 @@ gather_gitsource()
 	printf "Gitsource-$1 avg power consumption(J): $avg_en\n" | tee -a $OUTFILE_GIT.result
 
 	# Permance is the number of run gitsource per second, denoted 1/t, where 1 is the number of run gitsource in t
-	# senconds. It is well known that P=E/t, where P is power measured in watts(W), E is energy measured in joules(J),
+	# seconds. It is well known that P=E/t, where P is power measured in watts(W), E is energy measured in joules(J),
 	# and t is time measured in seconds(s). This means that performance per watt becomes
 	#        1/t     1/t     1
 	#       ----- = ----- = ---
diff --git a/tools/testing/selftests/amd-pstate/run.sh b/tools/testing/selftests/amd-pstate/run.sh
index 57cad57e59c0..b053eea8bb19 100755
--- a/tools/testing/selftests/amd-pstate/run.sh
+++ b/tools/testing/selftests/amd-pstate/run.sh
@@ -8,9 +8,12 @@ else
 	FILE_MAIN=DONE
 fi
 
-source basic.sh
-source tbench.sh
-source gitsource.sh
+SCRIPTDIR=`dirname "$0"`
+TRACER=$SCRIPTDIR/../../../power/x86/amd_pstate_tracer/amd_pstate_trace.py
+
+source $SCRIPTDIR/basic.sh
+source $SCRIPTDIR/tbench.sh
+source $SCRIPTDIR/gitsource.sh
 
 # amd-pstate-ut only run on x86/x86_64 AMD systems.
 ARCH=$(uname -m 2>/dev/null | sed -e 's/i.86/x86/' -e 's/x86_64/x86/')
@@ -22,6 +25,7 @@ OUTFILE=selftest
 OUTFILE_TBENCH="$OUTFILE.tbench"
 OUTFILE_GIT="$OUTFILE.gitsource"
 
+PERF=/usr/bin/perf
 SYSFS=
 CPUROOT=
 CPUFREQROOT=
@@ -151,6 +155,7 @@ help()
 	[-p <tbench process number>]
 	[-l <loop times for tbench>]
 	[-i <amd tracer interval>]
+	[-b <perf binary>]
 	[-m <comparative test: acpi-cpufreq>]
 	\n"
 	exit 2
@@ -158,7 +163,7 @@ help()
 
 parse_arguments()
 {
-	while getopts ho:c:t:p:l:i:m: arg
+	while getopts ho:c:t:p:l:i:b:m: arg
 	do
 		case $arg in
 			h) # --help
@@ -189,6 +194,10 @@ parse_arguments()
 				TRACER_INTERVAL=$OPTARG
 				;;
 
+			b) # --perf-binary
+				PERF=`realpath $OPTARG`
+				;;
+
 			m) # --comparative-test
 				COMPARATIVE_TEST=$OPTARG
 				;;
@@ -202,8 +211,8 @@ parse_arguments()
 
 command_perf()
 {
-	if ! command -v perf > /dev/null; then
-		echo $msg please install perf. >&2
+	if ! $PERF -v; then
+		echo $msg please install perf or provide perf binary path as argument >&2
 		exit $ksft_skip
 	fi
 }
@@ -244,7 +253,7 @@ prerequisite()
 		if [ "$scaling_driver" != "$CURRENT_TEST" ]; then
 			echo "$0 # Skipped: Test can only run on $CURRENT_TEST driver or run comparative test."
 			echo "$0 # Please set X86_AMD_PSTATE enabled or run comparative test."
-			echo "$0 # Current cpufreq scaling drvier is $scaling_driver."
+			echo "$0 # Current cpufreq scaling driver is $scaling_driver."
 			exit $ksft_skip
 		fi
 	else
@@ -252,7 +261,7 @@ prerequisite()
 			"tbench" | "gitsource")
 				if [ "$scaling_driver" != "$COMPARATIVE_TEST" ]; then
 					echo "$0 # Skipped: Comparison test can only run on $COMPARISON_TEST driver."
-					echo "$0 # Current cpufreq scaling drvier is $scaling_driver."
+					echo "$0 # Current cpufreq scaling driver is $scaling_driver."
 					exit $ksft_skip
 				fi
 				;;
diff --git a/tools/testing/selftests/amd-pstate/tbench.sh b/tools/testing/selftests/amd-pstate/tbench.sh
index 49c9850341f6..2a98d9c9202e 100755
--- a/tools/testing/selftests/amd-pstate/tbench.sh
+++ b/tools/testing/selftests/amd-pstate/tbench.sh
@@ -64,11 +64,11 @@ post_clear_tbench()
 run_tbench()
 {
 	echo "Launching amd pstate tracer for $1 #$2 tracer_interval: $TRACER_INTERVAL"
-	./amd_pstate_trace.py -n tracer-tbench-$1-$2 -i $TRACER_INTERVAL > /dev/null 2>&1 &
+	$TRACER -n tracer-tbench-$1-$2 -i $TRACER_INTERVAL > /dev/null 2>&1 &
 
 	printf "Test tbench for $1 #$2 time_limit: $TIME_LIMIT procs_num: $PROCESS_NUM\n"
 	tbench_srv > /dev/null 2>&1 &
-	perf stat -a --per-socket -I 1000 -e power/energy-pkg/ tbench -t $TIME_LIMIT $PROCESS_NUM > $OUTFILE_TBENCH-perf-$1-$2.log 2>&1
+	$PERF stat -a --per-socket -I 1000 -e power/energy-pkg/ tbench -t $TIME_LIMIT $PROCESS_NUM > $OUTFILE_TBENCH-perf-$1-$2.log 2>&1
 
 	pid=`pidof tbench_srv`
 	kill $pid
diff --git a/tools/testing/selftests/arm64/Makefile b/tools/testing/selftests/arm64/Makefile
index 9460cbe81bcc..c4c72ee2ef55 100644
--- a/tools/testing/selftests/arm64/Makefile
+++ b/tools/testing/selftests/arm64/Makefile
@@ -4,7 +4,7 @@
 ARCH ?= $(shell uname -m 2>/dev/null || echo not)
 
 ifneq (,$(filter $(ARCH),aarch64 arm64))
-ARM64_SUBTARGETS ?= tags signal pauth fp mte bti abi
+ARM64_SUBTARGETS ?= tags signal pauth fp mte bti abi gcs
 else
 ARM64_SUBTARGETS :=
 endif
@@ -19,6 +19,10 @@ CFLAGS += -I$(top_srcdir)/tools/testing/selftests/
 
 CFLAGS += $(KHDR_INCLUDES)
 
+CFLAGS += -I$(top_srcdir)/tools/include
+
+OUTPUT ?= $(CURDIR)
+
 export CFLAGS
 export top_srcdir
 
@@ -42,7 +46,7 @@ run_tests: all
 	done
 
 # Avoid any output on non arm64 on emit_tests
-emit_tests: all
+emit_tests:
 	@for DIR in $(ARM64_SUBTARGETS); do				\
 		BUILD_TARGET=$(OUTPUT)/$$DIR;			\
 		make OUTPUT=$$BUILD_TARGET -C $$DIR $@;		\
diff --git a/tools/testing/selftests/arm64/abi/Makefile b/tools/testing/selftests/arm64/abi/Makefile
index a6d30c620908..483488f8c2ad 100644
--- a/tools/testing/selftests/arm64/abi/Makefile
+++ b/tools/testing/selftests/arm64/abi/Makefile
@@ -12,4 +12,4 @@ $(OUTPUT)/syscall-abi: syscall-abi.c syscall-abi-asm.S
 $(OUTPUT)/tpidr2: tpidr2.c
 	$(CC) -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \
 		-static -include ../../../../include/nolibc/nolibc.h \
-		-ffreestanding -Wall $^ -o $@ -lgcc
+		-I../.. -ffreestanding -Wall $^ -o $@ -lgcc
diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c
index 9f255bc5f31c..c41640f18e4e 100644
--- a/tools/testing/selftests/arm64/abi/hwcap.c
+++ b/tools/testing/selftests/arm64/abi/hwcap.c
@@ -17,21 +17,51 @@
 #include <asm/sigcontext.h>
 #include <asm/unistd.h>
 
-#include "../../kselftest.h"
+#include <linux/auxvec.h>
 
-#define TESTS_PER_HWCAP 2
+#include "kselftest.h"
+
+#define TESTS_PER_HWCAP 3
+
+#ifndef AT_HWCAP3
+#define AT_HWCAP3 29
+#endif
 
 /*
- * Function expected to generate SIGILL when the feature is not
- * supported and return when it is supported. If SIGILL is generated
- * then the handler must be able to skip over the instruction safely.
+ * Function expected to generate exception when the feature is not
+ * supported and return when it is supported. If the specific exception
+ * is generated then the handler must be able to skip over the
+ * instruction safely.
  *
  * Note that it is expected that for many architecture extensions
  * there are no specific traps due to no architecture state being
  * added so we may not fault if running on a kernel which doesn't know
  * to add the hwcap.
  */
-typedef void (*sigill_fn)(void);
+typedef void (*sig_fn)(void);
+
+static void aes_sigill(void)
+{
+	/* AESE V0.16B, V0.16B */
+	asm volatile(".inst 0x4e284800" : : : );
+}
+
+static void atomics_sigill(void)
+{
+	/* STADD W0, [SP] */
+	asm volatile(".inst 0xb82003ff" : : : );
+}
+
+static void cmpbr_sigill(void)
+{
+	/* Not implemented, too complicated and unreliable anyway */
+}
+
+static void crc32_sigill(void)
+{
+	/* CRC32W W0, W0, W1 */
+	asm volatile(".inst 0x1ac14800" : : : );
+}
 
 static void cssc_sigill(void)
 {
@@ -39,17 +69,396 @@ static void cssc_sigill(void)
 	asm volatile(".inst 0xdac01c00" : : : "x0");
 }
 
+static void f8cvt_sigill(void)
+{
+	/* FSCALE V0.4H, V0.4H, V0.4H */
+	asm volatile(".inst 0x2ec03c00");
+}
+
+static void f8dp2_sigill(void)
+{
+	/* FDOT V0.4H, V0.4H, V0.5H */
+	asm volatile(".inst 0xe40fc00");
+}
+
+static void f8dp4_sigill(void)
+{
+	/* FDOT V0.2S, V0.2S, V0.2S */
+	asm volatile(".inst 0xe00fc00");
+}
+
+static void f8fma_sigill(void)
+{
+	/* FMLALB V0.8H, V0.16B, V0.16B */
+	asm volatile(".inst 0xec0fc00");
+}
+
+static void f8mm4_sigill(void)
+{
+	/* FMMLA V0.4SH, V0.16B, V0.16B */
+	asm volatile(".inst 0x6e00ec00");
+}
+
+static void f8mm8_sigill(void)
+{
+	/* FMMLA V0.4S, V0.16B, V0.16B */
+	asm volatile(".inst 0x6e80ec00");
+}
+
+static void faminmax_sigill(void)
+{
+	/* FAMIN V0.4H, V0.4H, V0.4H */
+	asm volatile(".inst 0x2ec01c00");
+}
+
+static void fp_sigill(void)
+{
+	asm volatile("fmov s0, #1");
+}
+
+static void fpmr_sigill(void)
+{
+	asm volatile("mrs x0, S3_3_C4_C4_2" : : : "x0");
+}
+
+static void fprcvt_sigill(void)
+{
+	/* FCVTAS S0, H0 */
+	asm volatile(".inst 0x1efa0000");
+}
+
+static void gcs_sigill(void)
+{
+	unsigned long *gcspr;
+
+	asm volatile(
+		"mrs	%0, S3_3_C2_C5_1"
+	: "=r" (gcspr)
+	:
+	: "cc");
+}
+
+static void ilrcpc_sigill(void)
+{
+	/* LDAPUR W0, [SP, #8] */
+	asm volatile(".inst 0x994083e0" : : : );
+}
+
+static void jscvt_sigill(void)
+{
+	/* FJCVTZS W0, D0 */
+	asm volatile(".inst 0x1e7e0000" : : : );
+}
+
+static void lrcpc_sigill(void)
+{
+	/* LDAPR W0, [SP, #0] */
+	asm volatile(".inst 0xb8bfc3e0" : : : );
+}
+
+static void lse128_sigill(void)
+{
+	u64 __attribute__ ((aligned (16))) mem[2] = { 10, 20 };
+	register u64 *memp asm ("x0") = mem;
+	register u64 val0 asm ("x1") = 5;
+	register u64 val1 asm ("x2") = 4;
+
+	/* SWPP X1, X2, [X0] */
+	asm volatile(".inst 0x19228001"
+		     : "+r" (memp), "+r" (val0), "+r" (val1)
+		     :
+		     : "cc", "memory");
+}
+
+static void lsfe_sigill(void)
+{
+	float __attribute__ ((aligned (16))) mem;
+	register float *memp asm ("x0") = &mem;
+
+	/* STFADD H0, [X0] */
+	asm volatile(".inst 0x7c20801f"
+		     : "+r" (memp)
+		     :
+		     : "memory");
+}
+
+static void lut_sigill(void)
+{
+	/* LUTI2 V0.16B, { V0.16B }, V[0] */
+	asm volatile(".inst 0x4e801000");
+}
+
+static void mops_sigill(void)
+{
+	char dst[1], src[1];
+	register char *dstp asm ("x0") = dst;
+	register char *srcp asm ("x1") = src;
+	register long size asm ("x2") = 1;
+
+	/* CPYP [x0]!, [x1]!, x2! */
+	asm volatile(".inst 0x1d010440"
+		     : "+r" (dstp), "+r" (srcp), "+r" (size)
+		     :
+		     : "cc", "memory");
+}
+
+static void pmull_sigill(void)
+{
+	/* PMULL V0.1Q, V0.1D, V0.1D */
+	asm volatile(".inst 0x0ee0e000" : : : );
+}
+
+static void poe_sigill(void)
+{
+	/* mrs x0, POR_EL0 */
+	asm volatile("mrs x0, S3_3_C10_C2_4" : : : "x0");
+}
+
 static void rng_sigill(void)
 {
 	asm volatile("mrs x0, S3_3_C2_C4_0" : : : "x0");
 }
 
+static void sha1_sigill(void)
+{
+	/* SHA1H S0, S0 */
+	asm volatile(".inst 0x5e280800" : : : );
+}
+
+static void sha2_sigill(void)
+{
+	/* SHA256H Q0, Q0, V0.4S */
+	asm volatile(".inst 0x5e004000" : : : );
+}
+
+static void sha512_sigill(void)
+{
+	/* SHA512H Q0, Q0, V0.2D */
+	asm volatile(".inst 0xce608000" : : : );
+}
+
 static void sme_sigill(void)
 {
 	/* RDSVL x0, #0 */
 	asm volatile(".inst 0x04bf5800" : : : "x0");
 }
 
+static void sme2_sigill(void)
+{
+	/* SMSTART ZA */
+	asm volatile("msr S0_3_C4_C5_3, xzr" : : : );
+
+	/* ZERO ZT0 */
+	asm volatile(".inst 0xc0480001" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void sme2p1_sigill(void)
+{
+	/* SMSTART SM */
+	asm volatile("msr S0_3_C4_C3_3, xzr" : : : );
+
+	/* BFCLAMP { Z0.H - Z1.H }, Z0.H, Z0.H */
+	asm volatile(".inst 0xc120C000" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void sme2p2_sigill(void)
+{
+	/* SMSTART SM */
+	asm volatile("msr S0_3_C4_C3_3, xzr" : : : );
+
+	/* UXTB Z0.D, P0/Z, Z0.D  */
+	asm volatile(".inst 0x4c1a000" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void sme_aes_sigill(void)
+{
+	/* SMSTART SM */
+	asm volatile("msr S0_3_C4_C3_3, xzr" : : : );
+
+	/* AESD z0.b, z0.b, z0.b */
+	asm volatile(".inst 0x4522e400" : : : "z0");
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void sme_sbitperm_sigill(void)
+{
+	/* SMSTART SM */
+	asm volatile("msr S0_3_C4_C3_3, xzr" : : : );
+
+	/* BDEP Z0.B, Z0.B, Z0.B */
+	asm volatile(".inst 0x4500b400" : : : "z0");
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smei16i32_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* SMOPA ZA0.S, P0/M, P0/M, Z0.B, Z0.B */
+	asm volatile(".inst 0xa0800000" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smebi32i32_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* BMOPA ZA0.S, P0/M, P0/M, Z0.B, Z0.B */
+	asm volatile(".inst 0x80800008" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smeb16b16_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* BFADD ZA.H[W0, 0], {Z0.H-Z1.H} */
+	asm volatile(".inst 0xC1E41C00" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smef16f16_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* FADD ZA.H[W0, 0], { Z0.H-Z1.H } */
+	asm volatile(".inst 0xc1a41C00" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smef8f16_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* FDOT ZA.H[W0, 0], Z0.B-Z1.B, Z0.B-Z1.B */
+	asm volatile(".inst 0xc1a01020" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smef8f32_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* FDOT ZA.S[W0, 0], { Z0.B-Z1.B }, Z0.B[0] */
+	asm volatile(".inst 0xc1500038" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smelutv2_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* LUTI4 { Z0.B-Z3.B }, ZT0, { Z0-Z1 } */
+	asm volatile(".inst 0xc08b0000" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smesf8dp2_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* FDOT Z0.H, Z0.B, Z0.B[0] */
+	asm volatile(".inst 0x64204400" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smesf8dp4_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* FDOT Z0.S, Z0.B, Z0.B[0] */
+	asm volatile(".inst 0xc1a41C00" : : : );
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smesf8fma_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* FMLALB Z0.8H, Z0.B, Z0.B */
+	asm volatile(".inst 0x64205000");
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smesfexpa_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* FEXPA Z0.D, Z0.D */
+	asm volatile(".inst 0x04e0b800");
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smesmop4_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* SMOP4A ZA0.S, Z0.B, { Z0.B - Z1.B } */
+	asm volatile(".inst 0x80108000");
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
+static void smestmop_sigill(void)
+{
+	/* SMSTART */
+	asm volatile("msr S0_3_C4_C7_3, xzr" : : : );
+
+	/* STMOPA ZA0.S, { Z0.H - Z1.H }, Z0.H, Z20[0] */
+	asm volatile(".inst 0x80408008");
+
+	/* SMSTOP */
+	asm volatile("msr S0_3_C4_C6_3, xzr" : : : );
+}
+
 static void sve_sigill(void)
 {
 	/* RDVL x0, #0 */
@@ -68,12 +477,42 @@ static void sve2p1_sigill(void)
 	asm volatile(".inst 0x65000000" : : : "z0");
 }
 
+static void sve2p2_sigill(void)
+{
+	/* NOT Z0.D, P0/Z, Z0.D */
+	asm volatile(".inst 0x4cea000" : : : "z0");
+}
+
 static void sveaes_sigill(void)
 {
 	/* AESD z0.b, z0.b, z0.b */
 	asm volatile(".inst 0x4522e400" : : : "z0");
 }
 
+static void sveaes2_sigill(void)
+{
+	/* AESD {Z0.B - Z1.B }, { Z0.B - Z1.B }, Z0.Q */
+	asm volatile(".inst 0x4522ec00" : : : "z0");
+}
+
+static void sveb16b16_sigill(void)
+{
+	/* BFADD Z0.H, Z0.H, Z0.H */
+	asm volatile(".inst 0x65000000" : : : );
+}
+
+static void svebfscale_sigill(void)
+{
+	/* BFSCALE Z0.H, P0/M, Z0.H, Z0.H */
+	asm volatile(".inst 0x65098000" : : : "z0");
+}
+
+static void svef16mm_sigill(void)
+{
+	/* FMMLA Z0.S, Z0.H, Z0.H */
+	asm volatile(".inst 0x6420e400");
+}
+
 static void svepmull_sigill(void)
 {
 	/* PMULLB Z0.Q, Z0.D, Z0.D */
@@ -92,6 +531,12 @@ static void svesha3_sigill(void)
 	asm volatile(".inst 0x4203800" : : : "z0");
 }
 
+static void sveeltperm_sigill(void)
+{
+	/* COMPACT Z0.B, P0, Z0.B */
+	asm volatile(".inst 0x5218000" : : : "x0");
+}
+
 static void svesm4_sigill(void)
 {
 	/* SM4E Z0.S, Z0.S, Z0.S */
@@ -122,15 +567,66 @@ static void svebf16_sigill(void)
 	asm volatile(".inst 0x658aa000" : : : "z0");
 }
 
+static void hbc_sigill(void)
+{
+	/* BC.EQ +4 */
+	asm volatile("cmp xzr, xzr\n"
+		     ".inst 0x54000030" : : : "cc");
+}
+
+static void uscat_sigbus(void)
+{
+	/* unaligned atomic access */
+	asm volatile("ADD x1, sp, #2" : : : );
+	/* STADD W0, [X1] */
+	asm volatile(".inst 0xb820003f" : : : );
+}
+
+static void lrcpc3_sigill(void)
+{
+	int data[2] = { 1, 2 };
+
+	register int *src asm ("x0") = data;
+	register int data0 asm ("w2") = 0;
+	register int data1 asm ("w3") = 0;
+
+	/* LDIAPP w2, w3, [x0] */
+	asm volatile(".inst 0x99431802"
+	              : "=r" (data0), "=r" (data1) : "r" (src) :);
+}
+
 static const struct hwcap_data {
 	const char *name;
 	unsigned long at_hwcap;
 	unsigned long hwcap_bit;
 	const char *cpuinfo;
-	sigill_fn sigill_fn;
+	sig_fn sigill_fn;
 	bool sigill_reliable;
+	sig_fn sigbus_fn;
+	bool sigbus_reliable;
 } hwcaps[] = {
 	{
+		.name = "AES",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_AES,
+		.cpuinfo = "aes",
+		.sigill_fn = aes_sigill,
+	},
+	{
+		.name = "CMPBR",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_CMPBR,
+		.cpuinfo = "cmpbr",
+		.sigill_fn = cmpbr_sigill,
+	},
+	{
+		.name = "CRC32",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_CRC32,
+		.cpuinfo = "crc32",
+		.sigill_fn = crc32_sigill,
+	},
+	{
 		.name = "CSSC",
 		.at_hwcap = AT_HWCAP2,
 		.hwcap_bit = HWCAP2_CSSC,
@@ -138,6 +634,185 @@ static const struct hwcap_data {
 		.sigill_fn = cssc_sigill,
 	},
 	{
+		.name = "F8CVT",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_F8CVT,
+		.cpuinfo = "f8cvt",
+		.sigill_fn = f8cvt_sigill,
+	},
+	{
+		.name = "F8DP4",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_F8DP4,
+		.cpuinfo = "f8dp4",
+		.sigill_fn = f8dp4_sigill,
+	},
+	{
+		.name = "F8DP2",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_F8DP2,
+		.cpuinfo = "f8dp2",
+		.sigill_fn = f8dp2_sigill,
+	},
+	{
+		.name = "F8E5M2",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_F8E5M2,
+		.cpuinfo = "f8e5m2",
+	},
+	{
+		.name = "F8E4M3",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_F8E4M3,
+		.cpuinfo = "f8e4m3",
+	},
+	{
+		.name = "F8FMA",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_F8FMA,
+		.cpuinfo = "f8fma",
+		.sigill_fn = f8fma_sigill,
+	},
+	{
+		.name = "F8MM8",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_F8MM8,
+		.cpuinfo = "f8mm8",
+		.sigill_fn = f8mm8_sigill,
+	},
+	{
+		.name = "F8MM4",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_F8MM4,
+		.cpuinfo = "f8mm4",
+		.sigill_fn = f8mm4_sigill,
+	},
+	{
+		.name = "FAMINMAX",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_FAMINMAX,
+		.cpuinfo = "faminmax",
+		.sigill_fn = faminmax_sigill,
+	},
+	{
+		.name = "FP",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_FP,
+		.cpuinfo = "fp",
+		.sigill_fn = fp_sigill,
+	},
+	{
+		.name = "FPMR",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_FPMR,
+		.cpuinfo = "fpmr",
+		.sigill_fn = fpmr_sigill,
+		.sigill_reliable = true,
+	},
+	{
+		.name = "FPRCVT",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_FPRCVT,
+		.cpuinfo = "fprcvt",
+		.sigill_fn = fprcvt_sigill,
+	},
+	{
+		.name = "GCS",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_GCS,
+		.cpuinfo = "gcs",
+		.sigill_fn = gcs_sigill,
+		.sigill_reliable = true,
+	},
+	{
+		.name = "JSCVT",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_JSCVT,
+		.cpuinfo = "jscvt",
+		.sigill_fn = jscvt_sigill,
+	},
+	{
+		.name = "LRCPC",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_LRCPC,
+		.cpuinfo = "lrcpc",
+		.sigill_fn = lrcpc_sigill,
+	},
+	{
+		.name = "LRCPC2",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_ILRCPC,
+		.cpuinfo = "ilrcpc",
+		.sigill_fn = ilrcpc_sigill,
+	},
+	{
+		.name = "LRCPC3",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_LRCPC3,
+		.cpuinfo = "lrcpc3",
+		.sigill_fn = lrcpc3_sigill,
+	},
+	{
+		.name = "LSE",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_ATOMICS,
+		.cpuinfo = "atomics",
+		.sigill_fn = atomics_sigill,
+	},
+	{
+		.name = "LSE2",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_USCAT,
+		.cpuinfo = "uscat",
+		.sigill_fn = atomics_sigill,
+		.sigbus_fn = uscat_sigbus,
+		.sigbus_reliable = true,
+	},
+	{
+		.name = "LSE128",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_LSE128,
+		.cpuinfo = "lse128",
+		.sigill_fn = lse128_sigill,
+	},
+	{
+		.name = "LSFE",
+		.at_hwcap = AT_HWCAP3,
+		.hwcap_bit = HWCAP3_LSFE,
+		.cpuinfo = "lsfe",
+		.sigill_fn = lsfe_sigill,
+	},
+	{
+		.name = "LUT",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_LUT,
+		.cpuinfo = "lut",
+		.sigill_fn = lut_sigill,
+	},
+	{
+		.name = "MOPS",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_MOPS,
+		.cpuinfo = "mops",
+		.sigill_fn = mops_sigill,
+		.sigill_reliable = true,
+	},
+	{
+		.name = "PMULL",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_PMULL,
+		.cpuinfo = "pmull",
+		.sigill_fn = pmull_sigill,
+	},
+	{
+		.name = "POE",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_POE,
+		.cpuinfo = "poe",
+		.sigill_fn = poe_sigill,
+		.sigill_reliable = true,
+	},
+	{
 		.name = "RNG",
 		.at_hwcap = AT_HWCAP2,
 		.hwcap_bit = HWCAP2_RNG,
@@ -151,6 +826,27 @@ static const struct hwcap_data {
 		.cpuinfo = "rprfm",
 	},
 	{
+		.name = "SHA1",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_SHA1,
+		.cpuinfo = "sha1",
+		.sigill_fn = sha1_sigill,
+	},
+	{
+		.name = "SHA2",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_SHA2,
+		.cpuinfo = "sha2",
+		.sigill_fn = sha2_sigill,
+	},
+	{
+		.name = "SHA512",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_SHA512,
+		.cpuinfo = "sha512",
+		.sigill_fn = sha512_sigill,
+	},
+	{
 		.name = "SME",
 		.at_hwcap = AT_HWCAP2,
 		.hwcap_bit = HWCAP2_SME,
@@ -159,6 +855,133 @@ static const struct hwcap_data {
 		.sigill_reliable = true,
 	},
 	{
+		.name = "SME2",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME2,
+		.cpuinfo = "sme2",
+		.sigill_fn = sme2_sigill,
+		.sigill_reliable = true,
+	},
+	{
+		.name = "SME 2.1",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME2P1,
+		.cpuinfo = "sme2p1",
+		.sigill_fn = sme2p1_sigill,
+	},
+	{
+		.name = "SME 2.2",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_SME2P2,
+		.cpuinfo = "sme2p2",
+		.sigill_fn = sme2p2_sigill,
+	},
+	{
+		.name = "SME AES",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_SME_AES,
+		.cpuinfo = "smeaes",
+		.sigill_fn = sme_aes_sigill,
+	},
+	{
+		.name = "SME I16I32",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME_I16I32,
+		.cpuinfo = "smei16i32",
+		.sigill_fn = smei16i32_sigill,
+	},
+	{
+		.name = "SME BI32I32",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME_BI32I32,
+		.cpuinfo = "smebi32i32",
+		.sigill_fn = smebi32i32_sigill,
+	},
+	{
+		.name = "SME B16B16",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME_B16B16,
+		.cpuinfo = "smeb16b16",
+		.sigill_fn = smeb16b16_sigill,
+	},
+	{
+		.name = "SME F16F16",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME_F16F16,
+		.cpuinfo = "smef16f16",
+		.sigill_fn = smef16f16_sigill,
+	},
+	{
+		.name = "SME F8F16",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME_F8F16,
+		.cpuinfo = "smef8f16",
+		.sigill_fn = smef8f16_sigill,
+	},
+	{
+		.name = "SME F8F32",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME_F8F32,
+		.cpuinfo = "smef8f32",
+		.sigill_fn = smef8f32_sigill,
+	},
+	{
+		.name = "SME LUTV2",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME_LUTV2,
+		.cpuinfo = "smelutv2",
+		.sigill_fn = smelutv2_sigill,
+	},
+	{
+		.name = "SME SBITPERM",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_SME_SBITPERM,
+		.cpuinfo = "smesbitperm",
+		.sigill_fn = sme_sbitperm_sigill,
+	},
+	{
+		.name = "SME SF8FMA",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME_SF8FMA,
+		.cpuinfo = "smesf8fma",
+		.sigill_fn = smesf8fma_sigill,
+	},
+	{
+		.name = "SME SF8DP2",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME_SF8DP2,
+		.cpuinfo = "smesf8dp2",
+		.sigill_fn = smesf8dp2_sigill,
+	},
+	{
+		.name = "SME SF8DP4",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SME_SF8DP4,
+		.cpuinfo = "smesf8dp4",
+		.sigill_fn = smesf8dp4_sigill,
+	},
+	{
+		.name = "SME SFEXPA",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_SME_SFEXPA,
+		.cpuinfo = "smesfexpa",
+		.sigill_fn = smesfexpa_sigill,
+	},
+	{
+		.name = "SME SMOP4",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_SME_SMOP4,
+		.cpuinfo = "smesmop4",
+		.sigill_fn = smesmop4_sigill,
+	},
+	{
+		.name = "SME STMOP",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_SME_STMOP,
+		.cpuinfo = "smestmop",
+		.sigill_fn = smestmop_sigill,
+	},
+	{
 		.name = "SVE",
 		.at_hwcap = AT_HWCAP,
 		.hwcap_bit = HWCAP_SVE,
@@ -181,6 +1004,13 @@ static const struct hwcap_data {
 		.sigill_fn = sve2p1_sigill,
 	},
 	{
+		.name = "SVE 2.2",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_SVE2P2,
+		.cpuinfo = "sve2p2",
+		.sigill_fn = sve2p2_sigill,
+	},
+	{
 		.name = "SVE AES",
 		.at_hwcap = AT_HWCAP2,
 		.hwcap_bit = HWCAP2_SVEAES,
@@ -188,6 +1018,41 @@ static const struct hwcap_data {
 		.sigill_fn = sveaes_sigill,
 	},
 	{
+		.name = "SVE AES2",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_SVE_AES2,
+		.cpuinfo = "sveaes2",
+		.sigill_fn = sveaes2_sigill,
+	},
+	{
+		.name = "SVE BFSCALE",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_SVE_BFSCALE,
+		.cpuinfo = "svebfscale",
+		.sigill_fn = svebfscale_sigill,
+	},
+	{
+		.name = "SVE ELTPERM",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_SVE_ELTPERM,
+		.cpuinfo = "sveeltperm",
+		.sigill_fn = sveeltperm_sigill,
+	},
+	{
+		.name = "SVE F16MM",
+		.at_hwcap = AT_HWCAP,
+		.hwcap_bit = HWCAP_SVE_F16MM,
+		.cpuinfo = "svef16mm",
+		.sigill_fn = svef16mm_sigill,
+	},
+	{
+		.name = "SVE2 B16B16",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_SVE_B16B16,
+		.cpuinfo = "sveb16b16",
+		.sigill_fn = sveb16b16_sigill,
+	},
+	{
 		.name = "SVE2 PMULL",
 		.at_hwcap = AT_HWCAP2,
 		.hwcap_bit = HWCAP2_SVEPMULL,
@@ -249,20 +1114,44 @@ static const struct hwcap_data {
 		.hwcap_bit = HWCAP2_SVE_EBF16,
 		.cpuinfo = "sveebf16",
 	},
+	{
+		.name = "HBC",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_HBC,
+		.cpuinfo = "hbc",
+		.sigill_fn = hbc_sigill,
+		.sigill_reliable = true,
+	},
+	{
+		.name = "MTE_FAR",
+		.at_hwcap = AT_HWCAP3,
+		.hwcap_bit = HWCAP3_MTE_FAR,
+		.cpuinfo = "mtefar",
+	},
+	{
+		.name = "MTE_STOREONLY",
+		.at_hwcap = AT_HWCAP3,
+		.hwcap_bit = HWCAP3_MTE_STORE_ONLY,
+		.cpuinfo = "mtestoreonly",
+	},
 };
 
-static bool seen_sigill;
+typedef void (*sighandler_fn)(int, siginfo_t *, void *);
 
-static void handle_sigill(int sig, siginfo_t *info, void *context)
-{
-	ucontext_t *uc = context;
-
-	seen_sigill = true;
-
-	/* Skip over the offending instruction */
-	uc->uc_mcontext.pc += 4;
+#define DEF_SIGHANDLER_FUNC(SIG, NUM)					\
+static bool seen_##SIG;							\
+static void handle_##SIG(int sig, siginfo_t *info, void *context)	\
+{									\
+	ucontext_t *uc = context;					\
+									\
+	seen_##SIG = true;						\
+	/* Skip over the offending instruction */			\
+	uc->uc_mcontext.pc += 4;					\
 }
 
+DEF_SIGHANDLER_FUNC(sigill, SIGILL);
+DEF_SIGHANDLER_FUNC(sigbus, SIGBUS);
+
 bool cpuinfo_present(const char *name)
 {
 	FILE *f;
@@ -305,25 +1194,78 @@ bool cpuinfo_present(const char *name)
 	return false;
 }
 
-int main(void)
+static int install_sigaction(int signum, sighandler_fn handler)
 {
-	const struct hwcap_data *hwcap;
-	int i, ret;
-	bool have_cpuinfo, have_hwcap;
+	int ret;
 	struct sigaction sa;
 
-	ksft_print_header();
-	ksft_set_plan(ARRAY_SIZE(hwcaps) * TESTS_PER_HWCAP);
-
 	memset(&sa, 0, sizeof(sa));
-	sa.sa_sigaction = handle_sigill;
+	sa.sa_sigaction = handler;
 	sa.sa_flags = SA_RESTART | SA_SIGINFO;
 	sigemptyset(&sa.sa_mask);
-	ret = sigaction(SIGILL, &sa, NULL);
+	ret = sigaction(signum, &sa, NULL);
 	if (ret < 0)
-		ksft_exit_fail_msg("Failed to install SIGILL handler: %s (%d)\n",
+		ksft_exit_fail_msg("Failed to install SIGNAL handler: %s (%d)\n",
 				   strerror(errno), errno);
 
+	return ret;
+}
+
+static void uninstall_sigaction(int signum)
+{
+	if (sigaction(signum, NULL, NULL) < 0)
+		ksft_exit_fail_msg("Failed to uninstall SIGNAL handler: %s (%d)\n",
+				   strerror(errno), errno);
+}
+
+#define DEF_INST_RAISE_SIG(SIG, NUM)					\
+static bool inst_raise_##SIG(const struct hwcap_data *hwcap,		\
+				bool have_hwcap)			\
+{									\
+	if (!hwcap->SIG##_fn) {						\
+		ksft_test_result_skip(#SIG"_%s\n", hwcap->name);	\
+		/* assume that it would raise exception in default */	\
+		return true;						\
+	}								\
+									\
+	install_sigaction(NUM, handle_##SIG);				\
+									\
+	seen_##SIG = false;						\
+	hwcap->SIG##_fn();						\
+									\
+	if (have_hwcap) {						\
+		/* Should be able to use the extension */		\
+		ksft_test_result(!seen_##SIG,				\
+				#SIG"_%s\n", hwcap->name);		\
+	} else if (hwcap->SIG##_reliable) {				\
+		/* Guaranteed a SIGNAL */				\
+		ksft_test_result(seen_##SIG,				\
+				#SIG"_%s\n", hwcap->name);		\
+	} else {							\
+		/* Missing SIGNAL might be fine */			\
+		ksft_print_msg(#SIG"_%sreported for %s\n",		\
+				seen_##SIG ? "" : "not ",		\
+				hwcap->name);				\
+		ksft_test_result_skip(#SIG"_%s\n",			\
+					hwcap->name);			\
+	}								\
+									\
+	uninstall_sigaction(NUM);					\
+	return seen_##SIG;						\
+}
+
+DEF_INST_RAISE_SIG(sigill, SIGILL);
+DEF_INST_RAISE_SIG(sigbus, SIGBUS);
+
+int main(void)
+{
+	int i;
+	const struct hwcap_data *hwcap;
+	bool have_cpuinfo, have_hwcap, raise_sigill;
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(hwcaps) * TESTS_PER_HWCAP);
+
 	for (i = 0; i < ARRAY_SIZE(hwcaps); i++) {
 		hwcap = &hwcaps[i];
 
@@ -336,30 +1278,15 @@ int main(void)
 		ksft_test_result(have_hwcap == have_cpuinfo,
 				 "cpuinfo_match_%s\n", hwcap->name);
 
-		if (hwcap->sigill_fn) {
-			seen_sigill = false;
-			hwcap->sigill_fn();
-
-			if (have_hwcap) {
-				/* Should be able to use the extension */
-				ksft_test_result(!seen_sigill, "sigill_%s\n",
-						 hwcap->name);
-			} else if (hwcap->sigill_reliable) {
-				/* Guaranteed a SIGILL */
-				ksft_test_result(seen_sigill, "sigill_%s\n",
-						 hwcap->name);
-			} else {
-				/* Missing SIGILL might be fine */
-				ksft_print_msg("SIGILL %sreported for %s\n",
-					       seen_sigill ? "" : "not ",
-					       hwcap->name);
-				ksft_test_result_skip("sigill_%s\n",
-						      hwcap->name);
-			}
-		} else {
-			ksft_test_result_skip("sigill_%s\n",
-					      hwcap->name);
-		}
+		/*
+		 * Testing for SIGBUS only makes sense after make sure
+		 * that the instruction does not cause a SIGILL signal.
+		 */
+		raise_sigill = inst_raise_sigill(hwcap, have_hwcap);
+		if (!raise_sigill)
+			inst_raise_sigbus(hwcap, have_hwcap);
+		else
+			ksft_test_result_skip("sigbus_%s\n", hwcap->name);
 	}
 
 	ksft_print_cnts();
diff --git a/tools/testing/selftests/arm64/abi/ptrace.c b/tools/testing/selftests/arm64/abi/ptrace.c
index be952511af22..0e46ac21c81d 100644
--- a/tools/testing/selftests/arm64/abi/ptrace.c
+++ b/tools/testing/selftests/arm64/abi/ptrace.c
@@ -18,9 +18,9 @@
 #include <asm/sigcontext.h>
 #include <asm/ptrace.h>
 
-#include "../../kselftest.h"
+#include "kselftest.h"
 
-#define EXPECTED_TESTS 7
+#define EXPECTED_TESTS 11
 
 #define MAX_TPIDRS 2
 
@@ -47,7 +47,7 @@ static void test_tpidr(pid_t child)
 
 	/* ...write a new value.. */
 	write_iov.iov_len = sizeof(uint64_t);
-	write_val[0] = read_val[0]++;
+	write_val[0] = read_val[0] + 1;
 	ret = ptrace(PTRACE_SETREGSET, child, NT_ARM_TLS, &write_iov);
 	ksft_test_result(ret == 0, "write_tpidr_one\n");
 
@@ -132,13 +132,41 @@ static void test_tpidr(pid_t child)
 	}
 }
 
+static void test_hw_debug(pid_t child, int type, const char *type_name)
+{
+	struct user_hwdebug_state state;
+	struct iovec iov;
+	int slots, arch, ret;
+
+	iov.iov_len = sizeof(state);
+	iov.iov_base = &state;
+
+	/* Should be able to read the values */
+	ret = ptrace(PTRACE_GETREGSET, child, type, &iov);
+	ksft_test_result(ret == 0, "read_%s\n", type_name);
+
+	if (ret == 0) {
+		/* Low 8 bits is the number of slots, next 4 bits the arch */
+		slots = state.dbg_info & 0xff;
+		arch = (state.dbg_info >> 8) & 0xf;
+
+		ksft_print_msg("%s version %d with %d slots\n", type_name,
+			       arch, slots);
+
+		/* Zero is not currently architecturally valid */
+		ksft_test_result(arch, "%s_arch_set\n", type_name);
+	} else {
+		ksft_test_result_skip("%s_arch_set\n", type_name);
+	}
+}
+
 static int do_child(void)
 {
 	if (ptrace(PTRACE_TRACEME, -1, NULL, NULL))
-		ksft_exit_fail_msg("PTRACE_TRACEME", strerror(errno));
+		ksft_exit_fail_perror("PTRACE_TRACEME");
 
 	if (raise(SIGSTOP))
-		ksft_exit_fail_msg("raise(SIGSTOP)", strerror(errno));
+		ksft_exit_fail_perror("raise(SIGSTOP)");
 
 	return EXIT_SUCCESS;
 }
@@ -207,6 +235,8 @@ static int do_parent(pid_t child)
 	ksft_print_msg("Parent is %d, child is %d\n", getpid(), child);
 
 	test_tpidr(child);
+	test_hw_debug(child, NT_ARM_HW_WATCH, "NT_ARM_HW_WATCH");
+	test_hw_debug(child, NT_ARM_HW_BREAK, "NT_ARM_HW_BREAK");
 
 	ret = EXIT_SUCCESS;
 
diff --git a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S
index acd5e9f3bc0b..66ab2e0bae5f 100644
--- a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S
+++ b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S
@@ -23,6 +23,9 @@
 
 .arch_extension sve
 
+#define ID_AA64SMFR0_EL1_SMEver_SHIFT           56
+#define ID_AA64SMFR0_EL1_SMEver_WIDTH           4
+
 /*
  * LDR (vector to ZA array):
  *	LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
@@ -45,6 +48,26 @@
 		| ((\offset) & 7)
 .endm
 
+/*
+ * LDR (ZT0)
+ *
+ *	LDR ZT0, nx
+ */
+.macro _ldr_zt nx
+	.inst	0xe11f8000			\
+		| (((\nx) & 0x1f) << 5)
+.endm
+
+/*
+ * STR (ZT0)
+ *
+ *	STR ZT0, nx
+ */
+.macro _str_zt nx
+	.inst	0xe13f8000			\
+		| (((\nx) & 0x1f) << 5)
+.endm
+
 .globl do_syscall
 do_syscall:
 	// Store callee saved registers x19-x29 (80 bytes) plus x0 and x1
@@ -58,23 +81,31 @@ do_syscall:
 	stp	x27, x28, [sp, #96]
 
 	// Set SVCR if we're doing SME
-	cbz	x1, 1f
+	cbz	x1, load_gpr
 	adrp	x2, svcr_in
 	ldr	x2, [x2, :lo12:svcr_in]
 	msr	S3_3_C4_C2_2, x2
-1:
 
-	// Load ZA if it's enabled - uses x12 as scratch due to SME LDR
-	tbz	x2, #SVCR_ZA_SHIFT, 1f
+	// Load ZA and ZT0 if enabled - uses x12 as scratch due to SME LDR
+	tbz	x2, #SVCR_ZA_SHIFT, load_gpr
 	mov	w12, #0
 	ldr	x2, =za_in
-2:	_ldr_za 12, 2
+1:	_ldr_za 12, 2
 	add	x2, x2, x1
 	add	x12, x12, #1
 	cmp	x1, x12
-	bne	2b
-1:
+	bne	1b
+
+	// ZT0
+	mrs	x2, S3_0_C0_C4_5	// ID_AA64SMFR0_EL1
+	ubfx	x2, x2, #ID_AA64SMFR0_EL1_SMEver_SHIFT, \
+			 #ID_AA64SMFR0_EL1_SMEver_WIDTH
+	cbz	x2, load_gpr
+	adrp	x2, zt_in
+	add	x2, x2, :lo12:zt_in
+	_ldr_zt 2
 
+load_gpr:
 	// Load GPRs x8-x28, and save our SP/FP for later comparison
 	ldr	x2, =gpr_in
 	add	x2, x2, #64
@@ -92,8 +123,11 @@ do_syscall:
 	str	x29, [x2], #8		// FP
 	str	x30, [x2], #8		// LR
 
-	// Load FPRs if we're not doing SVE
-	cbnz	x0, 1f
+	// Load FPRs if we're not doing neither SVE nor streaming SVE
+	cbnz	x0, check_sve_in
+	ldr	x2, =svcr_in
+	tbnz	x2, #SVCR_SM_SHIFT, check_sve_in
+
 	ldr	x2, =fpr_in
 	ldp	q0, q1, [x2]
 	ldp	q2, q3, [x2, #16 * 2]
@@ -111,10 +145,11 @@ do_syscall:
 	ldp	q26, q27, [x2, #16 * 26]
 	ldp	q28, q29, [x2, #16 * 28]
 	ldp	q30, q31, [x2, #16 * 30]
-1:
 
+	b	2f
+
+check_sve_in:
 	// Load the SVE registers if we're doing SVE/SME
-	cbz	x0, 1f
 
 	ldr	x2, =z_in
 	ldr	z0, [x2, #0, MUL VL]
@@ -155,9 +190,9 @@ do_syscall:
 	ldr	x2, =ffr_in
 	ldr	p0, [x2]
 	ldr	x2, [x2, #0]
-	cbz	x2, 2f
+	cbz	x2, 1f
 	wrffr	p0.b
-2:
+1:
 
 	ldr	x2, =p_in
 	ldr	p0, [x2, #0, MUL VL]
@@ -176,7 +211,7 @@ do_syscall:
 	ldr	p13, [x2, #13, MUL VL]
 	ldr	p14, [x2, #14, MUL VL]
 	ldr	p15, [x2, #15, MUL VL]
-1:
+2:
 
 	// Do the syscall
 	svc	#0
@@ -220,23 +255,31 @@ do_syscall:
 	stp	q30, q31, [x2, #16 * 30]
 
 	// Save SVCR if we're doing SME
-	cbz	x1, 1f
+	cbz	x1, check_sve_out
 	mrs	x2, S3_3_C4_C2_2
 	adrp	x3, svcr_out
 	str	x2, [x3, :lo12:svcr_out]
-1:
 
 	// Save ZA if it's enabled - uses x12 as scratch due to SME STR
-	tbz	x2, #SVCR_ZA_SHIFT, 1f
+	tbz	x2, #SVCR_ZA_SHIFT, check_sve_out
 	mov	w12, #0
 	ldr	x2, =za_out
-2:	_str_za 12, 2
+1:	_str_za 12, 2
 	add	x2, x2, x1
 	add	x12, x12, #1
 	cmp	x1, x12
-	bne	2b
-1:
+	bne	1b
+
+	// ZT0
+	mrs	x2, S3_0_C0_C4_5	// ID_AA64SMFR0_EL1
+	ubfx	x2, x2, #ID_AA64SMFR0_EL1_SMEver_SHIFT, \
+			#ID_AA64SMFR0_EL1_SMEver_WIDTH
+	cbz	x2, check_sve_out
+	adrp	x2, zt_out
+	add	x2, x2, :lo12:zt_out
+	_str_zt 2
 
+check_sve_out:
 	// Save the SVE state if we have some
 	cbz	x0, 1f
 
diff --git a/tools/testing/selftests/arm64/abi/syscall-abi.c b/tools/testing/selftests/arm64/abi/syscall-abi.c
index dd7ebe536d05..b67e3e26fa6d 100644
--- a/tools/testing/selftests/arm64/abi/syscall-abi.c
+++ b/tools/testing/selftests/arm64/abi/syscall-abi.c
@@ -16,14 +16,25 @@
 #include <asm/sigcontext.h>
 #include <asm/unistd.h>
 
-#include "../../kselftest.h"
+#include "kselftest.h"
 
 #include "syscall-abi.h"
 
-#define NUM_VL ((SVE_VQ_MAX - SVE_VQ_MIN) + 1)
+/*
+ * The kernel defines a much larger SVE_VQ_MAX than is expressable in
+ * the architecture, this creates a *lot* of overhead filling the
+ * buffers (especially ZA) on emulated platforms so use the actual
+ * architectural maximum instead.
+ */
+#define ARCH_SVE_VQ_MAX 16
 
 static int default_sme_vl;
 
+static int sve_vl_count;
+static unsigned int sve_vls[ARCH_SVE_VQ_MAX];
+static int sme_vl_count;
+static unsigned int sme_vls[ARCH_SVE_VQ_MAX];
+
 extern void do_syscall(int sve_vl, int sme_vl);
 
 static void fill_random(void *buf, size_t size)
@@ -70,7 +81,7 @@ static int check_gpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, uint64_t s
 	 */
 	for (i = 9; i < ARRAY_SIZE(gpr_in); i++) {
 		if (gpr_in[i] != gpr_out[i]) {
-			ksft_print_msg("%s SVE VL %d mismatch in GPR %d: %llx != %llx\n",
+			ksft_print_msg("%s SVE VL %d mismatch in GPR %d: %lx != %lx\n",
 				       cfg->name, sve_vl, i,
 				       gpr_in[i], gpr_out[i]);
 			errors++;
@@ -83,6 +94,7 @@ static int check_gpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, uint64_t s
 #define NUM_FPR 32
 uint64_t fpr_in[NUM_FPR * 2];
 uint64_t fpr_out[NUM_FPR * 2];
+uint64_t fpr_zero[NUM_FPR * 2];
 
 static void setup_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 		      uint64_t svcr)
@@ -97,10 +109,10 @@ static int check_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 	int errors = 0;
 	int i;
 
-	if (!sve_vl) {
+	if (!sve_vl && !(svcr & SVCR_SM_MASK)) {
 		for (i = 0; i < ARRAY_SIZE(fpr_in); i++) {
 			if (fpr_in[i] != fpr_out[i]) {
-				ksft_print_msg("%s Q%d/%d mismatch %llx != %llx\n",
+				ksft_print_msg("%s Q%d/%d mismatch %lx != %lx\n",
 					       cfg->name,
 					       i / 2, i % 2,
 					       fpr_in[i], fpr_out[i]);
@@ -109,14 +121,26 @@ static int check_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 		}
 	}
 
+	/*
+	 * In streaming mode the whole register set should be cleared
+	 * by the transition out of streaming mode.
+	 */
+	if (svcr & SVCR_SM_MASK) {
+		if (memcmp(fpr_zero, fpr_out, sizeof(fpr_out)) != 0) {
+			ksft_print_msg("%s FPSIMD registers non-zero exiting SM\n",
+				       cfg->name);
+			errors++;
+		}
+	}
+
 	return errors;
 }
 
 #define SVE_Z_SHARED_BYTES (128 / 8)
 
-static uint8_t z_zero[__SVE_ZREG_SIZE(SVE_VQ_MAX)];
-uint8_t z_in[SVE_NUM_ZREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
-uint8_t z_out[SVE_NUM_ZREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
+static uint8_t z_zero[__SVE_ZREG_SIZE(ARCH_SVE_VQ_MAX)];
+uint8_t z_in[SVE_NUM_ZREGS * __SVE_ZREG_SIZE(ARCH_SVE_VQ_MAX)];
+uint8_t z_out[SVE_NUM_ZREGS * __SVE_ZREG_SIZE(ARCH_SVE_VQ_MAX)];
 
 static void setup_z(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 		    uint64_t svcr)
@@ -174,8 +198,8 @@ static int check_z(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 	return errors;
 }
 
-uint8_t p_in[SVE_NUM_PREGS * __SVE_PREG_SIZE(SVE_VQ_MAX)];
-uint8_t p_out[SVE_NUM_PREGS * __SVE_PREG_SIZE(SVE_VQ_MAX)];
+uint8_t p_in[SVE_NUM_PREGS * __SVE_PREG_SIZE(ARCH_SVE_VQ_MAX)];
+uint8_t p_out[SVE_NUM_PREGS * __SVE_PREG_SIZE(ARCH_SVE_VQ_MAX)];
 
 static void setup_p(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 		    uint64_t svcr)
@@ -206,8 +230,8 @@ static int check_p(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 	return errors;
 }
 
-uint8_t ffr_in[__SVE_PREG_SIZE(SVE_VQ_MAX)];
-uint8_t ffr_out[__SVE_PREG_SIZE(SVE_VQ_MAX)];
+uint8_t ffr_in[__SVE_PREG_SIZE(ARCH_SVE_VQ_MAX)];
+uint8_t ffr_out[__SVE_PREG_SIZE(ARCH_SVE_VQ_MAX)];
 
 static void setup_ffr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 		      uint64_t svcr)
@@ -270,13 +294,13 @@ static int check_svcr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 	int errors = 0;
 
 	if (svcr_out & SVCR_SM_MASK) {
-		ksft_print_msg("%s Still in SM, SVCR %llx\n",
+		ksft_print_msg("%s Still in SM, SVCR %lx\n",
 			       cfg->name, svcr_out);
 		errors++;
 	}
 
 	if ((svcr_in & SVCR_ZA_MASK) != (svcr_out & SVCR_ZA_MASK)) {
-		ksft_print_msg("%s PSTATE.ZA changed, SVCR %llx != %llx\n",
+		ksft_print_msg("%s PSTATE.ZA changed, SVCR %lx != %lx\n",
 			       cfg->name, svcr_in, svcr_out);
 		errors++;
 	}
@@ -284,8 +308,8 @@ static int check_svcr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 	return errors;
 }
 
-uint8_t za_in[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
-uint8_t za_out[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
+uint8_t za_in[ZA_SIG_REGS_SIZE(ARCH_SVE_VQ_MAX)];
+uint8_t za_out[ZA_SIG_REGS_SIZE(ARCH_SVE_VQ_MAX)];
 
 static void setup_za(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 		     uint64_t svcr)
@@ -311,6 +335,35 @@ static int check_za(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 	return errors;
 }
 
+uint8_t zt_in[ZT_SIG_REG_BYTES] __attribute__((aligned(16)));
+uint8_t zt_out[ZT_SIG_REG_BYTES] __attribute__((aligned(16)));
+
+static void setup_zt(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+		     uint64_t svcr)
+{
+	fill_random(zt_in, sizeof(zt_in));
+	memset(zt_out, 0, sizeof(zt_out));
+}
+
+static int check_zt(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+		    uint64_t svcr)
+{
+	int errors = 0;
+
+	if (!(getauxval(AT_HWCAP2) & HWCAP2_SME2))
+		return 0;
+
+	if (!(svcr & SVCR_ZA_MASK))
+		return 0;
+
+	if (memcmp(zt_in, zt_out, sizeof(zt_in)) != 0) {
+		ksft_print_msg("SME VL %d ZT does not match\n", sme_vl);
+		errors++;
+	}
+
+	return errors;
+}
+
 typedef void (*setup_fn)(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 			 uint64_t svcr);
 typedef int (*check_fn)(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
@@ -334,6 +387,7 @@ static struct {
 	{ setup_ffr, check_ffr },
 	{ setup_svcr, check_svcr },
 	{ setup_za, check_za },
+	{ setup_zt, check_zt },
 };
 
 static bool do_test(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
@@ -355,73 +409,78 @@ static bool do_test(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
 
 static void test_one_syscall(struct syscall_cfg *cfg)
 {
-	int sve_vq, sve_vl;
-	int sme_vq, sme_vl;
+	int sve, sme;
+	int ret;
 
 	/* FPSIMD only case */
 	ksft_test_result(do_test(cfg, 0, default_sme_vl, 0),
 			 "%s FPSIMD\n", cfg->name);
 
-	if (!(getauxval(AT_HWCAP) & HWCAP_SVE))
-		return;
-
-	for (sve_vq = SVE_VQ_MAX; sve_vq > 0; --sve_vq) {
-		sve_vl = prctl(PR_SVE_SET_VL, sve_vq * 16);
-		if (sve_vl == -1)
+	for (sve = 0; sve < sve_vl_count; sve++) {
+		ret = prctl(PR_SVE_SET_VL, sve_vls[sve]);
+		if (ret == -1)
 			ksft_exit_fail_msg("PR_SVE_SET_VL failed: %s (%d)\n",
 					   strerror(errno), errno);
 
-		sve_vl &= PR_SVE_VL_LEN_MASK;
-
-		if (sve_vq != sve_vq_from_vl(sve_vl))
-			sve_vq = sve_vq_from_vl(sve_vl);
-
-		ksft_test_result(do_test(cfg, sve_vl, default_sme_vl, 0),
-				 "%s SVE VL %d\n", cfg->name, sve_vl);
+		ksft_test_result(do_test(cfg, sve_vls[sve], default_sme_vl, 0),
+				 "%s SVE VL %d\n", cfg->name, sve_vls[sve]);
 
-		if (!(getauxval(AT_HWCAP2) & HWCAP2_SME))
-			continue;
-
-		for (sme_vq = SVE_VQ_MAX; sme_vq > 0; --sme_vq) {
-			sme_vl = prctl(PR_SME_SET_VL, sme_vq * 16);
-			if (sme_vl == -1)
+		for (sme = 0; sme < sme_vl_count; sme++) {
+			ret = prctl(PR_SME_SET_VL, sme_vls[sme]);
+			if (ret == -1)
 				ksft_exit_fail_msg("PR_SME_SET_VL failed: %s (%d)\n",
 						   strerror(errno), errno);
 
-			sme_vl &= PR_SME_VL_LEN_MASK;
-
-			if (sme_vq != sve_vq_from_vl(sme_vl))
-				sme_vq = sve_vq_from_vl(sme_vl);
-
-			ksft_test_result(do_test(cfg, sve_vl, sme_vl,
+			ksft_test_result(do_test(cfg, sve_vls[sve],
+						 sme_vls[sme],
 						 SVCR_ZA_MASK | SVCR_SM_MASK),
 					 "%s SVE VL %d/SME VL %d SM+ZA\n",
-					 cfg->name, sve_vl, sme_vl);
-			ksft_test_result(do_test(cfg, sve_vl, sme_vl,
-						 SVCR_SM_MASK),
+					 cfg->name, sve_vls[sve],
+					 sme_vls[sme]);
+			ksft_test_result(do_test(cfg, sve_vls[sve],
+						 sme_vls[sme], SVCR_SM_MASK),
 					 "%s SVE VL %d/SME VL %d SM\n",
-					 cfg->name, sve_vl, sme_vl);
-			ksft_test_result(do_test(cfg, sve_vl, sme_vl,
-						 SVCR_ZA_MASK),
+					 cfg->name, sve_vls[sve],
+					 sme_vls[sme]);
+			ksft_test_result(do_test(cfg, sve_vls[sve],
+						 sme_vls[sme], SVCR_ZA_MASK),
 					 "%s SVE VL %d/SME VL %d ZA\n",
-					 cfg->name, sve_vl, sme_vl);
+					 cfg->name, sve_vls[sve],
+					 sme_vls[sme]);
 		}
 	}
+
+	for (sme = 0; sme < sme_vl_count; sme++) {
+		ret = prctl(PR_SME_SET_VL, sme_vls[sme]);
+		if (ret == -1)
+			ksft_exit_fail_msg("PR_SME_SET_VL failed: %s (%d)\n",
+						   strerror(errno), errno);
+
+		ksft_test_result(do_test(cfg, 0, sme_vls[sme],
+					 SVCR_ZA_MASK | SVCR_SM_MASK),
+				 "%s SME VL %d SM+ZA\n",
+				 cfg->name, sme_vls[sme]);
+		ksft_test_result(do_test(cfg, 0, sme_vls[sme], SVCR_SM_MASK),
+				 "%s SME VL %d SM\n",
+				 cfg->name, sme_vls[sme]);
+		ksft_test_result(do_test(cfg, 0, sme_vls[sme], SVCR_ZA_MASK),
+				 "%s SME VL %d ZA\n",
+				 cfg->name, sme_vls[sme]);
+	}
 }
 
-int sve_count_vls(void)
+void sve_count_vls(void)
 {
 	unsigned int vq;
-	int vl_count = 0;
 	int vl;
 
 	if (!(getauxval(AT_HWCAP) & HWCAP_SVE))
-		return 0;
+		return;
 
 	/*
-	 * Enumerate up to SVE_VQ_MAX vector lengths
+	 * Enumerate up to ARCH_SVE_VQ_MAX vector lengths
 	 */
-	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+	for (vq = ARCH_SVE_VQ_MAX; vq > 0; vq /= 2) {
 		vl = prctl(PR_SVE_SET_VL, vq * 16);
 		if (vl == -1)
 			ksft_exit_fail_msg("PR_SVE_SET_VL failed: %s (%d)\n",
@@ -432,28 +491,22 @@ int sve_count_vls(void)
 		if (vq != sve_vq_from_vl(vl))
 			vq = sve_vq_from_vl(vl);
 
-		vl_count++;
+		sve_vls[sve_vl_count++] = vl;
 	}
-
-	return vl_count;
 }
 
-int sme_count_vls(void)
+void sme_count_vls(void)
 {
 	unsigned int vq;
-	int vl_count = 0;
 	int vl;
 
 	if (!(getauxval(AT_HWCAP2) & HWCAP2_SME))
-		return 0;
-
-	/* Ensure we configure a SME VL, used to flag if SVCR is set */
-	default_sme_vl = 16;
+		return;
 
 	/*
-	 * Enumerate up to SVE_VQ_MAX vector lengths
+	 * Enumerate up to ARCH_SVE_VQ_MAX vector lengths
 	 */
-	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+	for (vq = ARCH_SVE_VQ_MAX; vq > 0; vq /= 2) {
 		vl = prctl(PR_SME_SET_VL, vq * 16);
 		if (vl == -1)
 			ksft_exit_fail_msg("PR_SME_SET_VL failed: %s (%d)\n",
@@ -461,31 +514,47 @@ int sme_count_vls(void)
 
 		vl &= PR_SME_VL_LEN_MASK;
 
+		/* Found lowest VL */
+		if (sve_vq_from_vl(vl) > vq)
+			break;
+
 		if (vq != sve_vq_from_vl(vl))
 			vq = sve_vq_from_vl(vl);
 
-		vl_count++;
+		sme_vls[sme_vl_count++] = vl;
 	}
 
-	return vl_count;
+	/* Ensure we configure a SME VL, used to flag if SVCR is set */
+	default_sme_vl = sme_vls[0];
 }
 
 int main(void)
 {
 	int i;
 	int tests = 1;  /* FPSIMD */
+	int sme_ver;
 
 	srandom(getpid());
 
 	ksft_print_header();
-	tests += sve_count_vls();
-	tests += (sve_count_vls() * sme_count_vls()) * 3;
+
+	sve_count_vls();
+	sme_count_vls();
+
+	tests += sve_vl_count;
+	tests += sme_vl_count * 3;
+	tests += (sve_vl_count * sme_vl_count) * 3;
 	ksft_set_plan(ARRAY_SIZE(syscalls) * tests);
 
+	if (getauxval(AT_HWCAP2) & HWCAP2_SME2)
+		sme_ver = 2;
+	else
+		sme_ver = 1;
+
 	if (getauxval(AT_HWCAP2) & HWCAP2_SME_FA64)
-		ksft_print_msg("SME with FA64\n");
+		ksft_print_msg("SME%d with FA64\n", sme_ver);
 	else if (getauxval(AT_HWCAP2) & HWCAP2_SME)
-		ksft_print_msg("SME without FA64\n");
+		ksft_print_msg("SME%d without FA64\n", sme_ver);
 
 	for (i = 0; i < ARRAY_SIZE(syscalls); i++)
 		test_one_syscall(&syscalls[i]);
diff --git a/tools/testing/selftests/arm64/abi/tpidr2.c b/tools/testing/selftests/arm64/abi/tpidr2.c
index 351a098b503a..1703543fb7c7 100644
--- a/tools/testing/selftests/arm64/abi/tpidr2.c
+++ b/tools/testing/selftests/arm64/abi/tpidr2.c
@@ -3,31 +3,12 @@
 #include <linux/sched.h>
 #include <linux/wait.h>
 
+#include "kselftest.h"
+
 #define SYS_TPIDR2 "S3_3_C13_C0_5"
 
 #define EXPECTED_TESTS 5
 
-static void putstr(const char *str)
-{
-	write(1, str, strlen(str));
-}
-
-static void putnum(unsigned int num)
-{
-	char c;
-
-	if (num / 10)
-		putnum(num / 10);
-
-	c = '0' + (num % 10);
-	write(1, &c, 1);
-}
-
-static int tests_run;
-static int tests_passed;
-static int tests_failed;
-static int tests_skipped;
-
 static void set_tpidr2(uint64_t val)
 {
 	asm volatile (
@@ -50,20 +31,6 @@ static uint64_t get_tpidr2(void)
 	return val;
 }
 
-static void print_summary(void)
-{
-	if (tests_passed + tests_failed + tests_skipped != EXPECTED_TESTS)
-		putstr("# UNEXPECTED TEST COUNT: ");
-
-	putstr("# Totals: pass:");
-	putnum(tests_passed);
-	putstr(" fail:");
-	putnum(tests_failed);
-	putstr(" xfail:0 xpass:0 skip:");
-	putnum(tests_skipped);
-	putstr(" error:0\n");
-}
-
 /* Processes should start with TPIDR2 == 0 */
 static int default_value(void)
 {
@@ -105,9 +72,8 @@ static int write_fork_read(void)
 	if (newpid == 0) {
 		/* In child */
 		if (get_tpidr2() != oldpid) {
-			putstr("# TPIDR2 changed in child: ");
-			putnum(get_tpidr2());
-			putstr("\n");
+			ksft_print_msg("TPIDR2 changed in child: %llx\n",
+				       get_tpidr2());
 			exit(0);
 		}
 
@@ -115,14 +81,12 @@ static int write_fork_read(void)
 		if (get_tpidr2() == getpid()) {
 			exit(1);
 		} else {
-			putstr("# Failed to set TPIDR2 in child\n");
+			ksft_print_msg("Failed to set TPIDR2 in child\n");
 			exit(0);
 		}
 	}
 	if (newpid < 0) {
-		putstr("# fork() failed: -");
-		putnum(-newpid);
-		putstr("\n");
+		ksft_print_msg("fork() failed: %d\n", newpid);
 		return 0;
 	}
 
@@ -132,23 +96,22 @@ static int write_fork_read(void)
 		if (waiting < 0) {
 			if (errno == EINTR)
 				continue;
-			putstr("# waitpid() failed: ");
-			putnum(errno);
-			putstr("\n");
+			ksft_print_msg("waitpid() failed: %d\n", errno);
 			return 0;
 		}
 		if (waiting != newpid) {
-			putstr("# waitpid() returned wrong PID\n");
+			ksft_print_msg("waitpid() returned wrong PID: %d != %d\n",
+				       waiting, newpid);
 			return 0;
 		}
 
 		if (!WIFEXITED(status)) {
-			putstr("# child did not exit\n");
+			ksft_print_msg("child did not exit\n");
 			return 0;
 		}
 
 		if (getpid() != get_tpidr2()) {
-			putstr("# TPIDR2 corrupted in parent\n");
+			ksft_print_msg("TPIDR2 corrupted in parent\n");
 			return 0;
 		}
 
@@ -169,8 +132,10 @@ static int sys_clone(unsigned long clone_flags, unsigned long newsp,
 			   child_tidptr);
 }
 
+#define __STACK_SIZE (8 * 1024 * 1024)
+
 /*
- * If we clone with CLONE_SETTLS then the value in the parent should
+ * If we clone with CLONE_VM then the value in the parent should
  * be unchanged and the child should start with zero and be able to
  * set its own value.
  */
@@ -179,63 +144,65 @@ static int write_clone_read(void)
 	int parent_tid, child_tid;
 	pid_t parent, waiting;
 	int ret, status;
+	void *stack;
 
 	parent = getpid();
 	set_tpidr2(parent);
 
-	ret = sys_clone(CLONE_SETTLS, 0, &parent_tid, 0, &child_tid);
+	stack = malloc(__STACK_SIZE);
+	if (!stack) {
+		ksft_print_msg("malloc() failed\n");
+		return 0;
+	}
+
+	ret = sys_clone(CLONE_VM, (unsigned long)stack + __STACK_SIZE,
+			&parent_tid, 0, &child_tid);
 	if (ret == -1) {
-		putstr("# clone() failed\n");
-		putnum(errno);
-		putstr("\n");
+		ksft_print_msg("clone() failed: %d\n", errno);
 		return 0;
 	}
 
 	if (ret == 0) {
 		/* In child */
 		if (get_tpidr2() != 0) {
-			putstr("# TPIDR2 non-zero in child: ");
-			putnum(get_tpidr2());
-			putstr("\n");
+			ksft_print_msg("TPIDR2 non-zero in child: %llx\n",
+				       get_tpidr2());
 			exit(0);
 		}
 
 		if (gettid() == 0)
-			putstr("# Child TID==0\n");
+			ksft_print_msg("Child TID==0\n");
 		set_tpidr2(gettid());
 		if (get_tpidr2() == gettid()) {
 			exit(1);
 		} else {
-			putstr("# Failed to set TPIDR2 in child\n");
+			ksft_print_msg("Failed to set TPIDR2 in child\n");
 			exit(0);
 		}
 	}
 
 	for (;;) {
-		waiting = wait4(ret, &status, __WCLONE, NULL);
+		waiting = waitpid(ret, &status, __WCLONE);
 
 		if (waiting < 0) {
 			if (errno == EINTR)
 				continue;
-			putstr("# wait4() failed: ");
-			putnum(errno);
-			putstr("\n");
+			ksft_print_msg("waitpid() failed: %d\n", errno);
 			return 0;
 		}
 		if (waiting != ret) {
-			putstr("# wait4() returned wrong PID ");
-			putnum(waiting);
-			putstr("\n");
+			ksft_print_msg("waitpid() returned wrong PID %d\n",
+				       waiting);
 			return 0;
 		}
 
 		if (!WIFEXITED(status)) {
-			putstr("# child did not exit\n");
+			ksft_print_msg("child did not exit\n");
 			return 0;
 		}
 
 		if (parent != get_tpidr2()) {
-			putstr("# TPIDR2 corrupted in parent\n");
+			ksft_print_msg("TPIDR2 corrupted in parent\n");
 			return 0;
 		}
 
@@ -243,29 +210,14 @@ static int write_clone_read(void)
 	}
 }
 
-#define run_test(name)			     \
-	if (name()) {			     \
-		tests_passed++;		     \
-	} else {			     \
-		tests_failed++;		     \
-		putstr("not ");		     \
-	}				     \
-	putstr("ok ");			     \
-	putnum(++tests_run);		     \
-	putstr(" " #name "\n");
-
 int main(int argc, char **argv)
 {
-	int ret, i;
+	int ret;
 
-	putstr("TAP version 13\n");
-	putstr("1..");
-	putnum(EXPECTED_TESTS);
-	putstr("\n");
+	ksft_print_header();
+	ksft_set_plan(5);
 
-	putstr("# PID: ");
-	putnum(getpid());
-	putstr("\n");
+	ksft_print_msg("PID: %d\n", getpid());
 
 	/*
 	 * This test is run with nolibc which doesn't support hwcap and
@@ -274,25 +226,21 @@ int main(int argc, char **argv)
 	 */
 	ret = open("/proc/sys/abi/sme_default_vector_length", O_RDONLY, 0);
 	if (ret >= 0) {
-		run_test(default_value);
-		run_test(write_read);
-		run_test(write_sleep_read);
-		run_test(write_fork_read);
-		run_test(write_clone_read);
+		ksft_test_result(default_value(), "default_value\n");
+		ksft_test_result(write_read(), "write_read\n");
+		ksft_test_result(write_sleep_read(), "write_sleep_read\n");
+		ksft_test_result(write_fork_read(), "write_fork_read\n");
+		ksft_test_result(write_clone_read(), "write_clone_read\n");
 
 	} else {
-		putstr("# SME support not present\n");
+		ksft_print_msg("SME support not present\n");
 
-		for (i = 0; i < EXPECTED_TESTS; i++) {
-			putstr("ok ");
-			putnum(i);
-			putstr(" skipped, TPIDR2 not supported\n");
-		}
-
-		tests_skipped += EXPECTED_TESTS;
+		ksft_test_result_skip("default_value\n");
+		ksft_test_result_skip("write_read\n");
+		ksft_test_result_skip("write_sleep_read\n");
+		ksft_test_result_skip("write_fork_read\n");
+		ksft_test_result_skip("write_clone_read\n");
 	}
 
-	print_summary();
-
-	return 0;
+	ksft_finished();
 }
diff --git a/tools/testing/selftests/arm64/bti/Makefile b/tools/testing/selftests/arm64/bti/Makefile
index ccdac414ad94..05e4ee523a53 100644
--- a/tools/testing/selftests/arm64/bti/Makefile
+++ b/tools/testing/selftests/arm64/bti/Makefile
@@ -2,8 +2,6 @@
 
 TEST_GEN_PROGS := btitest nobtitest
 
-PROGS := $(patsubst %,gen/%,$(TEST_GEN_PROGS))
-
 # These tests are built as freestanding binaries since otherwise BTI
 # support in ld.so is required which is not currently widespread; when
 # it is available it will still be useful to test this separately as the
@@ -18,44 +16,41 @@ CFLAGS_COMMON = -ffreestanding -Wall -Wextra $(CFLAGS)
 BTI_CC_COMMAND = $(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -c -o $@ $<
 NOBTI_CC_COMMAND = $(CC) $(CFLAGS_NOBTI) $(CFLAGS_COMMON) -c -o $@ $<
 
-%-bti.o: %.c
+$(OUTPUT)/%-bti.o: %.c
 	$(BTI_CC_COMMAND)
 
-%-bti.o: %.S
+$(OUTPUT)/%-bti.o: %.S
 	$(BTI_CC_COMMAND)
 
-%-nobti.o: %.c
+$(OUTPUT)/%-nobti.o: %.c
 	$(NOBTI_CC_COMMAND)
 
-%-nobti.o: %.S
+$(OUTPUT)/%-nobti.o: %.S
 	$(NOBTI_CC_COMMAND)
 
 BTI_OBJS =                                      \
-	test-bti.o                           \
-	signal-bti.o                            \
-	start-bti.o                             \
-	syscall-bti.o                           \
-	system-bti.o                            \
-	teststubs-bti.o                         \
-	trampoline-bti.o
-gen/btitest: $(BTI_OBJS)
+	$(OUTPUT)/test-bti.o                    \
+	$(OUTPUT)/signal-bti.o                  \
+	$(OUTPUT)/start-bti.o                   \
+	$(OUTPUT)/syscall-bti.o                 \
+	$(OUTPUT)/system-bti.o                  \
+	$(OUTPUT)/teststubs-bti.o               \
+	$(OUTPUT)/trampoline-bti.o
+$(OUTPUT)/btitest: $(BTI_OBJS)
 	$(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -static -o $@ $^
 
 NOBTI_OBJS =                                    \
-	test-nobti.o                         \
-	signal-nobti.o                          \
-	start-nobti.o                           \
-	syscall-nobti.o                         \
-	system-nobti.o                          \
-	teststubs-nobti.o                       \
-	trampoline-nobti.o
-gen/nobtitest: $(NOBTI_OBJS)
+	$(OUTPUT)/test-nobti.o                  \
+	$(OUTPUT)/signal-nobti.o                \
+	$(OUTPUT)/start-nobti.o                 \
+	$(OUTPUT)/syscall-nobti.o               \
+	$(OUTPUT)/system-nobti.o                \
+	$(OUTPUT)/teststubs-nobti.o             \
+	$(OUTPUT)/trampoline-nobti.o
+$(OUTPUT)/nobtitest: $(NOBTI_OBJS)
 	$(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -static -o $@ $^
 
 # Including KSFT lib.mk here will also mangle the TEST_GEN_PROGS list
 # to account for any OUTPUT target-dirs optionally provided by
 # the toplevel makefile
 include ../../lib.mk
-
-$(TEST_GEN_PROGS): $(PROGS)
-	cp $(PROGS) $(OUTPUT)/
diff --git a/tools/testing/selftests/arm64/bti/assembler.h b/tools/testing/selftests/arm64/bti/assembler.h
index 04e7b72880ef..141cdcbf0b8f 100644
--- a/tools/testing/selftests/arm64/bti/assembler.h
+++ b/tools/testing/selftests/arm64/bti/assembler.h
@@ -14,7 +14,6 @@
 #define GNU_PROPERTY_AARCH64_FEATURE_1_BTI	(1U << 0)
 #define GNU_PROPERTY_AARCH64_FEATURE_1_PAC	(1U << 1)
 
-
 .macro startfn name:req
 	.globl \name
 \name:
diff --git a/tools/testing/selftests/arm64/bti/compiler.h b/tools/testing/selftests/arm64/bti/compiler.h
deleted file mode 100644
index ebb6204f447a..000000000000
--- a/tools/testing/selftests/arm64/bti/compiler.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2019  Arm Limited
- * Original author: Dave Martin <Dave.Martin@arm.com>
- */
-
-#ifndef COMPILER_H
-#define COMPILER_H
-
-#define __always_unused __attribute__((__unused__))
-#define __noreturn __attribute__((__noreturn__))
-#define __unreachable() __builtin_unreachable()
-
-/* curse(e) has value e, but the compiler cannot assume so */
-#define curse(e) ({				\
-	__typeof__(e) __curse_e = (e);		\
-	asm ("" : "+r" (__curse_e));		\
-	__curse_e;				\
-})
-
-#endif /* ! COMPILER_H */
diff --git a/tools/testing/selftests/arm64/bti/gen/.gitignore b/tools/testing/selftests/arm64/bti/gen/.gitignore
deleted file mode 100644
index 73869fabada4..000000000000
--- a/tools/testing/selftests/arm64/bti/gen/.gitignore
+++ /dev/null
@@ -1,2 +0,0 @@
-btitest
-nobtitest
diff --git a/tools/testing/selftests/arm64/bti/system.c b/tools/testing/selftests/arm64/bti/system.c
index 6385d8d4973b..93d772b00bfe 100644
--- a/tools/testing/selftests/arm64/bti/system.c
+++ b/tools/testing/selftests/arm64/bti/system.c
@@ -8,12 +8,10 @@
 
 #include <asm/unistd.h>
 
-#include "compiler.h"
-
 void __noreturn exit(int n)
 {
 	syscall(__NR_exit, n);
-	__unreachable();
+	unreachable();
 }
 
 ssize_t write(int fd, const void *buf, size_t size)
diff --git a/tools/testing/selftests/arm64/bti/system.h b/tools/testing/selftests/arm64/bti/system.h
index aca118589705..2e9ee1284a0c 100644
--- a/tools/testing/selftests/arm64/bti/system.h
+++ b/tools/testing/selftests/arm64/bti/system.h
@@ -14,12 +14,12 @@ typedef __kernel_size_t size_t;
 typedef __kernel_ssize_t ssize_t;
 
 #include <linux/errno.h>
+#include <linux/compiler.h>
+
 #include <asm/hwcap.h>
 #include <asm/ptrace.h>
 #include <asm/unistd.h>
 
-#include "compiler.h"
-
 long syscall(int nr, ...);
 
 void __noreturn exit(int n);
diff --git a/tools/testing/selftests/arm64/bti/test.c b/tools/testing/selftests/arm64/bti/test.c
index 67b77ab83c20..28a8e8a28a84 100644
--- a/tools/testing/selftests/arm64/bti/test.c
+++ b/tools/testing/selftests/arm64/bti/test.c
@@ -6,6 +6,7 @@
 
 #include "system.h"
 
+#include <stdbool.h>
 #include <stddef.h>
 #include <linux/errno.h>
 #include <linux/auxvec.h>
@@ -16,7 +17,6 @@
 typedef struct ucontext ucontext_t;
 
 #include "btitest.h"
-#include "compiler.h"
 #include "signal.h"
 
 #define EXPECTED_TESTS 18
@@ -101,7 +101,8 @@ static void handler(int n, siginfo_t *si __always_unused,
 	uc->uc_mcontext.pstate &= ~PSR_BTYPE_MASK;
 }
 
-static int skip_all;
+/* Does the system have BTI? */
+static bool have_bti;
 
 static void __do_test(void (*trampoline)(void (*)(void)),
 		      void (*fn)(void),
@@ -109,19 +110,11 @@ static void __do_test(void (*trampoline)(void (*)(void)),
 		      const char *name,
 		      int expect_sigill)
 {
-	if (skip_all) {
-		test_skipped++;
-		putstr("ok ");
-		putnum(test_num);
-		putstr(" ");
-		puttestname(name, trampoline_name);
-		putstr(" # SKIP\n");
-
-		return;
-	}
-
-	/* Branch Target exceptions should only happen in BTI binaries: */
-	if (!BTI)
+	/*
+	 * Branch Target exceptions should only happen for BTI
+	 * binaries running on a system with BTI:
+	 */
+	if (!BTI || !have_bti)
 		expect_sigill = 0;
 
 	sigill_expected = expect_sigill;
@@ -199,9 +192,10 @@ void start(int *argcp)
 		putstr("# HWCAP2_BTI present\n");
 		if (!(hwcap & HWCAP_PACA))
 			putstr("# Bad hardware?  Expect problems.\n");
+		have_bti = true;
 	} else {
 		putstr("# HWCAP2_BTI not present\n");
-		skip_all = 1;
+		have_bti = false;
 	}
 
 	putstr("# Test binary");
diff --git a/tools/testing/selftests/arm64/fp/.gitignore b/tools/testing/selftests/arm64/fp/.gitignore
index df79d29664a1..8362e7ec35ad 100644
--- a/tools/testing/selftests/arm64/fp/.gitignore
+++ b/tools/testing/selftests/arm64/fp/.gitignore
@@ -1,6 +1,8 @@
 fp-pidbench
+fp-ptrace
 fp-stress
 fpsimd-test
+kernel-test
 rdvl-sme
 rdvl-sve
 sve-probe-vls
@@ -12,3 +14,5 @@ vlset
 za-fork
 za-ptrace
 za-test
+zt-ptrace
+zt-test
diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile
index 36db61358ed5..d171021e4cdd 100644
--- a/tools/testing/selftests/arm64/fp/Makefile
+++ b/tools/testing/selftests/arm64/fp/Makefile
@@ -3,17 +3,22 @@
 # A proper top_srcdir is needed by KSFT(lib.mk)
 top_srcdir = $(realpath ../../../../../)
 
-CFLAGS += -I$(top_srcdir)/usr/include/
+CFLAGS += $(KHDR_INCLUDES)
 
-TEST_GEN_PROGS := fp-stress \
+TEST_GEN_PROGS := \
+	fp-ptrace \
+	fp-stress \
 	sve-ptrace sve-probe-vls \
 	vec-syscfg \
 	za-fork za-ptrace
 TEST_GEN_PROGS_EXTENDED := fp-pidbench fpsimd-test \
+	kernel-test \
 	rdvl-sme rdvl-sve \
 	sve-test \
 	ssve-test \
 	za-test \
+	zt-ptrace \
+	zt-test \
 	vlset
 TEST_PROGS_EXTENDED := fpsimd-stress sve-stress ssve-stress za-stress
 
@@ -22,6 +27,7 @@ EXTRA_CLEAN += $(OUTPUT)/asm-utils.o $(OUTPUT)/rdvl.o $(OUTPUT)/za-fork-asm.o
 # Build with nolibc to avoid effects due to libc's clone() support
 $(OUTPUT)/fp-pidbench: fp-pidbench.S $(OUTPUT)/asm-utils.o
 	$(CC) -nostdlib $^ -o $@
+$(OUTPUT)/fp-ptrace: fp-ptrace.c fp-ptrace-asm.S
 $(OUTPUT)/fpsimd-test: fpsimd-test.S $(OUTPUT)/asm-utils.o
 	$(CC) -nostdlib $^ -o $@
 $(OUTPUT)/rdvl-sve: rdvl-sve.c $(OUTPUT)/rdvl.o
@@ -36,10 +42,13 @@ $(OUTPUT)/vec-syscfg: vec-syscfg.c $(OUTPUT)/rdvl.o
 $(OUTPUT)/vlset: vlset.c
 $(OUTPUT)/za-fork: za-fork.c $(OUTPUT)/za-fork-asm.o
 	$(CC) -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \
-		-include ../../../../include/nolibc/nolibc.h \
+		-include ../../../../include/nolibc/nolibc.h -I../..\
 		-static -ffreestanding -Wall $^ -o $@
 $(OUTPUT)/za-ptrace: za-ptrace.c
 $(OUTPUT)/za-test: za-test.S $(OUTPUT)/asm-utils.o
 	$(CC) -nostdlib $^ -o $@
+$(OUTPUT)/zt-ptrace: zt-ptrace.c
+$(OUTPUT)/zt-test: zt-test.S $(OUTPUT)/asm-utils.o
+	$(CC) -nostdlib $^ -o $@
 
 include ../../lib.mk
diff --git a/tools/testing/selftests/arm64/fp/assembler.h b/tools/testing/selftests/arm64/fp/assembler.h
index 90bd433d2665..1fc46a5642c2 100644
--- a/tools/testing/selftests/arm64/fp/assembler.h
+++ b/tools/testing/selftests/arm64/fp/assembler.h
@@ -57,7 +57,7 @@ endfunction
 // Utility macro to print a literal string
 // Clobbers x0-x4,x8
 .macro puts string
-	.pushsection .rodata.str1.1, "aMS", 1
+	.pushsection .rodata.str1.1, "aMS", @progbits, 1
 .L__puts_literal\@: .string "\string"
 	.popsection
 
@@ -65,4 +65,19 @@ endfunction
 	bl	puts
 .endm
 
+#define PR_SET_SHADOW_STACK_STATUS      75
+# define PR_SHADOW_STACK_ENABLE         (1UL << 0)
+
+.macro enable_gcs
+	// Run with GCS
+	mov	x0, PR_SET_SHADOW_STACK_STATUS
+	mov	x1, PR_SHADOW_STACK_ENABLE
+	mov	x2, xzr
+	mov	x3, xzr
+	mov	x4, xzr
+	mov	x5, xzr
+	mov	x8, #__NR_prctl
+	svc	#0
+.endm
+
 #endif /* ! ASSEMBLER_H */
diff --git a/tools/testing/selftests/arm64/fp/fp-pidbench.S b/tools/testing/selftests/arm64/fp/fp-pidbench.S
index 16a436389bfc..73830f6bc99b 100644
--- a/tools/testing/selftests/arm64/fp/fp-pidbench.S
+++ b/tools/testing/selftests/arm64/fp/fp-pidbench.S
@@ -31,7 +31,6 @@
 // Main program entry point
 .globl _start
 function _start
-_start:
 	puts	"Iterations per test: "
 	mov	x20, #10000
 	lsl	x20, x20, #8
diff --git a/tools/testing/selftests/arm64/fp/fp-ptrace-asm.S b/tools/testing/selftests/arm64/fp/fp-ptrace-asm.S
new file mode 100644
index 000000000000..82c3ab70e1cf
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/fp-ptrace-asm.S
@@ -0,0 +1,292 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2021-3 ARM Limited.
+//
+// Assembly portion of the FP ptrace test
+
+//
+// Load values from memory into registers, break on a breakpoint, then
+// break on a further breakpoint
+//
+
+#include "fp-ptrace.h"
+#include "sme-inst.h"
+
+.arch_extension sve
+
+// Load and save register values with pauses for ptrace
+//
+// x0 - HAVE_ flags indicating which features are in use
+
+.globl load_and_save
+load_and_save:
+	stp	x11, x12, [sp, #-0x10]!
+
+	// This should be redundant in the SVE case
+	ldr	x7, =v_in
+	ldp	q0, q1, [x7]
+	ldp	q2, q3, [x7, #16 * 2]
+	ldp	q4, q5, [x7, #16 * 4]
+	ldp	q6, q7, [x7, #16 * 6]
+	ldp	q8, q9, [x7, #16 * 8]
+	ldp	q10, q11, [x7, #16 * 10]
+	ldp	q12, q13, [x7, #16 * 12]
+	ldp	q14, q15, [x7, #16 * 14]
+	ldp	q16, q17, [x7, #16 * 16]
+	ldp	q18, q19, [x7, #16 * 18]
+	ldp	q20, q21, [x7, #16 * 20]
+	ldp	q22, q23, [x7, #16 * 22]
+	ldp	q24, q25, [x7, #16 * 24]
+	ldp	q26, q27, [x7, #16 * 26]
+	ldp	q28, q29, [x7, #16 * 28]
+	ldp	q30, q31, [x7, #16 * 30]
+
+	// SME?
+	tbz	x0, #HAVE_SME_SHIFT, check_sve_in
+
+	adrp	x7, svcr_in
+	ldr	x7, [x7, :lo12:svcr_in]
+	// SVCR is 0 by default, avoid triggering SME if not in use
+	cbz	x7, check_sve_in
+	msr	S3_3_C4_C2_2, x7
+
+	// ZA?
+	tbz	x7, #SVCR_ZA_SHIFT, check_sm_in
+	rdsvl	11, 1
+	mov	w12, #0
+	ldr	x6, =za_in
+1:	_ldr_za 12, 6
+	add	x6, x6, x11
+	add	x12, x12, #1
+	cmp	x11, x12
+	bne	1b
+
+	// ZT?
+	tbz	x0, #HAVE_SME2_SHIFT, check_sm_in
+	adrp	x6, zt_in
+	add	x6, x6, :lo12:zt_in
+	_ldr_zt 6
+
+	// In streaming mode?
+check_sm_in:
+	tbz	x7, #SVCR_SM_SHIFT, check_sve_in
+
+	// Load FFR if we have FA64
+	ubfx	x4, x0, #HAVE_FA64_SHIFT, #1
+	b	load_sve
+
+	// SVE?
+check_sve_in:
+	tbz	x0, #HAVE_SVE_SHIFT, check_fpmr_in
+	mov	x4, #1
+
+load_sve:
+	ldr	x7, =z_in
+	ldr	z0, [x7, #0, MUL VL]
+	ldr	z1, [x7, #1, MUL VL]
+	ldr	z2, [x7, #2, MUL VL]
+	ldr	z3, [x7, #3, MUL VL]
+	ldr	z4, [x7, #4, MUL VL]
+	ldr	z5, [x7, #5, MUL VL]
+	ldr	z6, [x7, #6, MUL VL]
+	ldr	z7, [x7, #7, MUL VL]
+	ldr	z8, [x7, #8, MUL VL]
+	ldr	z9, [x7, #9, MUL VL]
+	ldr	z10, [x7, #10, MUL VL]
+	ldr	z11, [x7, #11, MUL VL]
+	ldr	z12, [x7, #12, MUL VL]
+	ldr	z13, [x7, #13, MUL VL]
+	ldr	z14, [x7, #14, MUL VL]
+	ldr	z15, [x7, #15, MUL VL]
+	ldr	z16, [x7, #16, MUL VL]
+	ldr	z17, [x7, #17, MUL VL]
+	ldr	z18, [x7, #18, MUL VL]
+	ldr	z19, [x7, #19, MUL VL]
+	ldr	z20, [x7, #20, MUL VL]
+	ldr	z21, [x7, #21, MUL VL]
+	ldr	z22, [x7, #22, MUL VL]
+	ldr	z23, [x7, #23, MUL VL]
+	ldr	z24, [x7, #24, MUL VL]
+	ldr	z25, [x7, #25, MUL VL]
+	ldr	z26, [x7, #26, MUL VL]
+	ldr	z27, [x7, #27, MUL VL]
+	ldr	z28, [x7, #28, MUL VL]
+	ldr	z29, [x7, #29, MUL VL]
+	ldr	z30, [x7, #30, MUL VL]
+	ldr	z31, [x7, #31, MUL VL]
+
+	// FFR is not present in base SME
+	cbz	x4, 1f
+	ldr	x7, =ffr_in
+	ldr	p0, [x7]
+	ldr	x7, [x7, #0]
+	cbz	x7, 1f
+	wrffr	p0.b
+1:
+
+	ldr	x7, =p_in
+	ldr	p0, [x7, #0, MUL VL]
+	ldr	p1, [x7, #1, MUL VL]
+	ldr	p2, [x7, #2, MUL VL]
+	ldr	p3, [x7, #3, MUL VL]
+	ldr	p4, [x7, #4, MUL VL]
+	ldr	p5, [x7, #5, MUL VL]
+	ldr	p6, [x7, #6, MUL VL]
+	ldr	p7, [x7, #7, MUL VL]
+	ldr	p8, [x7, #8, MUL VL]
+	ldr	p9, [x7, #9, MUL VL]
+	ldr	p10, [x7, #10, MUL VL]
+	ldr	p11, [x7, #11, MUL VL]
+	ldr	p12, [x7, #12, MUL VL]
+	ldr	p13, [x7, #13, MUL VL]
+	ldr	p14, [x7, #14, MUL VL]
+	ldr	p15, [x7, #15, MUL VL]
+
+	// This has to come after we set PSTATE.SM
+check_fpmr_in:
+	tbz	x0, #HAVE_FPMR_SHIFT, wait_for_writes
+	adrp	x7, fpmr_in
+	ldr	x7, [x7, :lo12:fpmr_in]
+	msr	REG_FPMR, x7
+
+wait_for_writes:
+	// Wait for the parent
+	brk #0
+
+	// Save values
+	ldr	x7, =v_out
+	stp	q0, q1, [x7]
+	stp	q2, q3, [x7, #16 * 2]
+	stp	q4, q5, [x7, #16 * 4]
+	stp	q6, q7, [x7, #16 * 6]
+	stp	q8, q9, [x7, #16 * 8]
+	stp	q10, q11, [x7, #16 * 10]
+	stp	q12, q13, [x7, #16 * 12]
+	stp	q14, q15, [x7, #16 * 14]
+	stp	q16, q17, [x7, #16 * 16]
+	stp	q18, q19, [x7, #16 * 18]
+	stp	q20, q21, [x7, #16 * 20]
+	stp	q22, q23, [x7, #16 * 22]
+	stp	q24, q25, [x7, #16 * 24]
+	stp	q26, q27, [x7, #16 * 26]
+	stp	q28, q29, [x7, #16 * 28]
+	stp	q30, q31, [x7, #16 * 30]
+
+	tbz	x0, #HAVE_FPMR_SHIFT, check_sme_out
+	mrs	x7, REG_FPMR
+	adrp	x6, fpmr_out
+	str	x7, [x6, :lo12:fpmr_out]
+
+check_sme_out:
+	tbz	x0, #HAVE_SME_SHIFT, check_sve_out
+
+	rdsvl	11, 1
+	adrp	x6, sme_vl_out
+	str	x11, [x6, :lo12:sme_vl_out]
+
+	mrs	x7, S3_3_C4_C2_2
+	adrp	x6, svcr_out
+	str	x7, [x6, :lo12:svcr_out]
+
+	// ZA?
+	tbz	x7, #SVCR_ZA_SHIFT, check_sm_out
+	mov	w12, #0
+	ldr	x6, =za_out
+1:	_str_za 12, 6
+	add	x6, x6, x11
+	add	x12, x12, #1
+	cmp	x11, x12
+	bne	1b
+
+	// ZT?
+	tbz	x0, #HAVE_SME2_SHIFT, check_sm_out
+	adrp	x6, zt_out
+	add	x6, x6, :lo12:zt_out
+	_str_zt 6
+
+	// In streaming mode?
+check_sm_out:
+	tbz	x7, #SVCR_SM_SHIFT, check_sve_out
+
+	// Do we have FA64 and FFR?
+	ubfx	x4, x0, #HAVE_FA64_SHIFT, #1
+	b	read_sve
+
+	// SVE?
+check_sve_out:
+	tbz	x0, #HAVE_SVE_SHIFT, wait_for_reads
+	mov	x4, #1
+
+	rdvl	x7, #1
+	adrp	x6, sve_vl_out
+	str	x7, [x6, :lo12:sve_vl_out]
+
+read_sve:
+	ldr	x7, =z_out
+	str	z0, [x7, #0, MUL VL]
+	str	z1, [x7, #1, MUL VL]
+	str	z2, [x7, #2, MUL VL]
+	str	z3, [x7, #3, MUL VL]
+	str	z4, [x7, #4, MUL VL]
+	str	z5, [x7, #5, MUL VL]
+	str	z6, [x7, #6, MUL VL]
+	str	z7, [x7, #7, MUL VL]
+	str	z8, [x7, #8, MUL VL]
+	str	z9, [x7, #9, MUL VL]
+	str	z10, [x7, #10, MUL VL]
+	str	z11, [x7, #11, MUL VL]
+	str	z12, [x7, #12, MUL VL]
+	str	z13, [x7, #13, MUL VL]
+	str	z14, [x7, #14, MUL VL]
+	str	z15, [x7, #15, MUL VL]
+	str	z16, [x7, #16, MUL VL]
+	str	z17, [x7, #17, MUL VL]
+	str	z18, [x7, #18, MUL VL]
+	str	z19, [x7, #19, MUL VL]
+	str	z20, [x7, #20, MUL VL]
+	str	z21, [x7, #21, MUL VL]
+	str	z22, [x7, #22, MUL VL]
+	str	z23, [x7, #23, MUL VL]
+	str	z24, [x7, #24, MUL VL]
+	str	z25, [x7, #25, MUL VL]
+	str	z26, [x7, #26, MUL VL]
+	str	z27, [x7, #27, MUL VL]
+	str	z28, [x7, #28, MUL VL]
+	str	z29, [x7, #29, MUL VL]
+	str	z30, [x7, #30, MUL VL]
+	str	z31, [x7, #31, MUL VL]
+
+	ldr	x7, =p_out
+	str	p0, [x7, #0, MUL VL]
+	str	p1, [x7, #1, MUL VL]
+	str	p2, [x7, #2, MUL VL]
+	str	p3, [x7, #3, MUL VL]
+	str	p4, [x7, #4, MUL VL]
+	str	p5, [x7, #5, MUL VL]
+	str	p6, [x7, #6, MUL VL]
+	str	p7, [x7, #7, MUL VL]
+	str	p8, [x7, #8, MUL VL]
+	str	p9, [x7, #9, MUL VL]
+	str	p10, [x7, #10, MUL VL]
+	str	p11, [x7, #11, MUL VL]
+	str	p12, [x7, #12, MUL VL]
+	str	p13, [x7, #13, MUL VL]
+	str	p14, [x7, #14, MUL VL]
+	str	p15, [x7, #15, MUL VL]
+
+	// Only save FFR if it exists
+	cbz	x4, wait_for_reads
+	ldr	x7, =ffr_out
+	rdffr	p0.b
+	str	p0, [x7]
+
+wait_for_reads:
+	// Wait for the parent
+	brk #0
+
+	// Ensure we don't leave ourselves in streaming mode
+	tbz	x0, #HAVE_SME_SHIFT, out
+	msr	S3_3_C4_C2_2, xzr
+
+out:
+	ldp	x11, x12, [sp, #-0x10]
+	ret
diff --git a/tools/testing/selftests/arm64/fp/fp-ptrace.c b/tools/testing/selftests/arm64/fp/fp-ptrace.c
new file mode 100644
index 000000000000..22c584b78be5
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/fp-ptrace.c
@@ -0,0 +1,1692 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023 ARM Limited.
+ * Original author: Mark Brown <broonie@kernel.org>
+ */
+
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <sys/auxv.h>
+#include <sys/prctl.h>
+#include <sys/ptrace.h>
+#include <sys/types.h>
+#include <sys/uio.h>
+#include <sys/wait.h>
+
+#include <linux/kernel.h>
+
+#include <asm/sigcontext.h>
+#include <asm/sve_context.h>
+#include <asm/ptrace.h>
+
+#include "kselftest.h"
+
+#include "fp-ptrace.h"
+
+#include <linux/bits.h>
+
+#define FPMR_LSCALE2_MASK                               GENMASK(37, 32)
+#define FPMR_NSCALE_MASK                                GENMASK(31, 24)
+#define FPMR_LSCALE_MASK                                GENMASK(22, 16)
+#define FPMR_OSC_MASK                                   GENMASK(15, 15)
+#define FPMR_OSM_MASK                                   GENMASK(14, 14)
+
+/* <linux/elf.h> and <sys/auxv.h> don't like each other, so: */
+#ifndef NT_ARM_SVE
+#define NT_ARM_SVE 0x405
+#endif
+
+#ifndef NT_ARM_SSVE
+#define NT_ARM_SSVE 0x40b
+#endif
+
+#ifndef NT_ARM_ZA
+#define NT_ARM_ZA 0x40c
+#endif
+
+#ifndef NT_ARM_ZT
+#define NT_ARM_ZT 0x40d
+#endif
+
+#ifndef NT_ARM_FPMR
+#define NT_ARM_FPMR 0x40e
+#endif
+
+#define ARCH_VQ_MAX 256
+
+/* VL 128..2048 in powers of 2 */
+#define MAX_NUM_VLS 5
+
+/*
+ * FPMR bits we can set without doing feature checks to see if values
+ * are valid.
+ */
+#define FPMR_SAFE_BITS (FPMR_LSCALE2_MASK | FPMR_NSCALE_MASK | \
+			FPMR_LSCALE_MASK | FPMR_OSC_MASK | FPMR_OSM_MASK)
+
+#define NUM_FPR 32
+__uint128_t v_in[NUM_FPR];
+__uint128_t v_expected[NUM_FPR];
+__uint128_t v_out[NUM_FPR];
+
+char z_in[__SVE_ZREGS_SIZE(ARCH_VQ_MAX)];
+char z_expected[__SVE_ZREGS_SIZE(ARCH_VQ_MAX)];
+char z_out[__SVE_ZREGS_SIZE(ARCH_VQ_MAX)];
+
+char p_in[__SVE_PREGS_SIZE(ARCH_VQ_MAX)];
+char p_expected[__SVE_PREGS_SIZE(ARCH_VQ_MAX)];
+char p_out[__SVE_PREGS_SIZE(ARCH_VQ_MAX)];
+
+char ffr_in[__SVE_PREG_SIZE(ARCH_VQ_MAX)];
+char ffr_expected[__SVE_PREG_SIZE(ARCH_VQ_MAX)];
+char ffr_out[__SVE_PREG_SIZE(ARCH_VQ_MAX)];
+
+char za_in[ZA_SIG_REGS_SIZE(ARCH_VQ_MAX)];
+char za_expected[ZA_SIG_REGS_SIZE(ARCH_VQ_MAX)];
+char za_out[ZA_SIG_REGS_SIZE(ARCH_VQ_MAX)];
+
+char zt_in[ZT_SIG_REG_BYTES];
+char zt_expected[ZT_SIG_REG_BYTES];
+char zt_out[ZT_SIG_REG_BYTES];
+
+uint64_t fpmr_in, fpmr_expected, fpmr_out;
+
+uint64_t sve_vl_out;
+uint64_t sme_vl_out;
+uint64_t svcr_in, svcr_expected, svcr_out;
+
+void load_and_save(int flags);
+
+static bool got_alarm;
+
+static void handle_alarm(int sig, siginfo_t *info, void *context)
+{
+	got_alarm = true;
+}
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+static __uint128_t arm64_cpu_to_le128(__uint128_t x)
+{
+	u64 a = swab64(x);
+	u64 b = swab64(x >> 64);
+
+	return ((__uint128_t)a << 64) | b;
+}
+#else
+static __uint128_t arm64_cpu_to_le128(__uint128_t x)
+{
+	return x;
+}
+#endif
+
+#define arm64_le128_to_cpu(x) arm64_cpu_to_le128(x)
+
+static bool sve_supported(void)
+{
+	return getauxval(AT_HWCAP) & HWCAP_SVE;
+}
+
+static bool sme_supported(void)
+{
+	return getauxval(AT_HWCAP2) & HWCAP2_SME;
+}
+
+static bool sme2_supported(void)
+{
+	return getauxval(AT_HWCAP2) & HWCAP2_SME2;
+}
+
+static bool fa64_supported(void)
+{
+	return getauxval(AT_HWCAP2) & HWCAP2_SME_FA64;
+}
+
+static bool fpmr_supported(void)
+{
+	return getauxval(AT_HWCAP2) & HWCAP2_FPMR;
+}
+
+static bool compare_buffer(const char *name, void *out,
+			   void *expected, size_t size)
+{
+	void *tmp;
+
+	if (memcmp(out, expected, size) == 0)
+		return true;
+
+	ksft_print_msg("Mismatch in %s\n", name);
+
+	/* Did we just get zeros back? */
+	tmp = malloc(size);
+	if (!tmp) {
+		ksft_print_msg("OOM allocating %lu bytes for %s\n",
+			       size, name);
+		ksft_exit_fail();
+	}
+	memset(tmp, 0, size);
+
+	if (memcmp(out, tmp, size) == 0)
+		ksft_print_msg("%s is zero\n", name);
+
+	free(tmp);
+
+	return false;
+}
+
+struct test_config {
+	int sve_vl_in;
+	int sve_vl_expected;
+	int sme_vl_in;
+	int sme_vl_expected;
+	int svcr_in;
+	int svcr_expected;
+};
+
+struct test_definition {
+	const char *name;
+	bool sve_vl_change;
+	bool (*supported)(struct test_config *config);
+	void (*set_expected_values)(struct test_config *config);
+	void (*modify_values)(pid_t child, struct test_config *test_config);
+};
+
+static int vl_in(struct test_config *config)
+{
+	int vl;
+
+	if (config->svcr_in & SVCR_SM)
+		vl = config->sme_vl_in;
+	else
+		vl = config->sve_vl_in;
+
+	return vl;
+}
+
+static int vl_expected(struct test_config *config)
+{
+	int vl;
+
+	if (config->svcr_expected & SVCR_SM)
+		vl = config->sme_vl_expected;
+	else
+		vl = config->sve_vl_expected;
+
+	return vl;
+}
+
+static void run_child(struct test_config *config)
+{
+	int ret, flags;
+
+	/* Let the parent attach to us */
+	ret = ptrace(PTRACE_TRACEME, 0, 0, 0);
+	if (ret < 0)
+		ksft_exit_fail_msg("PTRACE_TRACEME failed: %s (%d)\n",
+				   strerror(errno), errno);
+
+	/* VL setup */
+	if (sve_supported()) {
+		ret = prctl(PR_SVE_SET_VL, config->sve_vl_in);
+		if (ret != config->sve_vl_in) {
+			ksft_print_msg("Failed to set SVE VL %d: %d\n",
+				       config->sve_vl_in, ret);
+		}
+	}
+
+	if (sme_supported()) {
+		ret = prctl(PR_SME_SET_VL, config->sme_vl_in);
+		if (ret != config->sme_vl_in) {
+			ksft_print_msg("Failed to set SME VL %d: %d\n",
+				       config->sme_vl_in, ret);
+		}
+	}
+
+	/* Load values and wait for the parent */
+	flags = 0;
+	if (sve_supported())
+		flags |= HAVE_SVE;
+	if (sme_supported())
+		flags |= HAVE_SME;
+	if (sme2_supported())
+		flags |= HAVE_SME2;
+	if (fa64_supported())
+		flags |= HAVE_FA64;
+	if (fpmr_supported())
+		flags |= HAVE_FPMR;
+
+	load_and_save(flags);
+
+	exit(0);
+}
+
+static void read_one_child_regs(pid_t child, char *name,
+				struct iovec *iov_parent,
+				struct iovec *iov_child)
+{
+	int len = iov_parent->iov_len;
+	int ret;
+
+	ret = process_vm_readv(child, iov_parent, 1, iov_child, 1, 0);
+	if (ret == -1)
+		ksft_print_msg("%s read failed: %s (%d)\n",
+			       name, strerror(errno), errno);
+	else if (ret != len)
+		ksft_print_msg("Short read of %s: %d\n", name, ret);
+}
+
+static void read_child_regs(pid_t child)
+{
+	struct iovec iov_parent, iov_child;
+
+	/*
+	 * Since the child fork()ed from us the buffer addresses are
+	 * the same in parent and child.
+	 */
+	iov_parent.iov_base = &v_out;
+	iov_parent.iov_len = sizeof(v_out);
+	iov_child.iov_base = &v_out;
+	iov_child.iov_len = sizeof(v_out);
+	read_one_child_regs(child, "FPSIMD", &iov_parent, &iov_child);
+
+	if (sve_supported() || sme_supported()) {
+		iov_parent.iov_base = &sve_vl_out;
+		iov_parent.iov_len = sizeof(sve_vl_out);
+		iov_child.iov_base = &sve_vl_out;
+		iov_child.iov_len = sizeof(sve_vl_out);
+		read_one_child_regs(child, "SVE VL", &iov_parent, &iov_child);
+
+		iov_parent.iov_base = &z_out;
+		iov_parent.iov_len = sizeof(z_out);
+		iov_child.iov_base = &z_out;
+		iov_child.iov_len = sizeof(z_out);
+		read_one_child_regs(child, "Z", &iov_parent, &iov_child);
+
+		iov_parent.iov_base = &p_out;
+		iov_parent.iov_len = sizeof(p_out);
+		iov_child.iov_base = &p_out;
+		iov_child.iov_len = sizeof(p_out);
+		read_one_child_regs(child, "P", &iov_parent, &iov_child);
+
+		iov_parent.iov_base = &ffr_out;
+		iov_parent.iov_len = sizeof(ffr_out);
+		iov_child.iov_base = &ffr_out;
+		iov_child.iov_len = sizeof(ffr_out);
+		read_one_child_regs(child, "FFR", &iov_parent, &iov_child);
+	}
+
+	if (sme_supported()) {
+		iov_parent.iov_base = &sme_vl_out;
+		iov_parent.iov_len = sizeof(sme_vl_out);
+		iov_child.iov_base = &sme_vl_out;
+		iov_child.iov_len = sizeof(sme_vl_out);
+		read_one_child_regs(child, "SME VL", &iov_parent, &iov_child);
+
+		iov_parent.iov_base = &svcr_out;
+		iov_parent.iov_len = sizeof(svcr_out);
+		iov_child.iov_base = &svcr_out;
+		iov_child.iov_len = sizeof(svcr_out);
+		read_one_child_regs(child, "SVCR", &iov_parent, &iov_child);
+
+		iov_parent.iov_base = &za_out;
+		iov_parent.iov_len = sizeof(za_out);
+		iov_child.iov_base = &za_out;
+		iov_child.iov_len = sizeof(za_out);
+		read_one_child_regs(child, "ZA", &iov_parent, &iov_child);
+	}
+
+	if (sme2_supported()) {
+		iov_parent.iov_base = &zt_out;
+		iov_parent.iov_len = sizeof(zt_out);
+		iov_child.iov_base = &zt_out;
+		iov_child.iov_len = sizeof(zt_out);
+		read_one_child_regs(child, "ZT", &iov_parent, &iov_child);
+	}
+
+	if (fpmr_supported()) {
+		iov_parent.iov_base = &fpmr_out;
+		iov_parent.iov_len = sizeof(fpmr_out);
+		iov_child.iov_base = &fpmr_out;
+		iov_child.iov_len = sizeof(fpmr_out);
+		read_one_child_regs(child, "FPMR", &iov_parent, &iov_child);
+	}
+}
+
+static bool continue_breakpoint(pid_t child,
+				enum __ptrace_request restart_type)
+{
+	struct user_pt_regs pt_regs;
+	struct iovec iov;
+	int ret;
+
+	/* Get PC */
+	iov.iov_base = &pt_regs;
+	iov.iov_len = sizeof(pt_regs);
+	ret = ptrace(PTRACE_GETREGSET, child, NT_PRSTATUS, &iov);
+	if (ret < 0) {
+		ksft_print_msg("Failed to get PC: %s (%d)\n",
+			       strerror(errno), errno);
+		return false;
+	}
+
+	/* Skip over the BRK */
+	pt_regs.pc += 4;
+	ret = ptrace(PTRACE_SETREGSET, child, NT_PRSTATUS, &iov);
+	if (ret < 0) {
+		ksft_print_msg("Failed to skip BRK: %s (%d)\n",
+			       strerror(errno), errno);
+		return false;
+	}
+
+	/* Restart */
+	ret = ptrace(restart_type, child, 0, 0);
+	if (ret < 0) {
+		ksft_print_msg("Failed to restart child: %s (%d)\n",
+			       strerror(errno), errno);
+		return false;
+	}
+
+	return true;
+}
+
+static bool check_ptrace_values_sve(pid_t child, struct test_config *config)
+{
+	struct user_sve_header *sve;
+	struct user_fpsimd_state *fpsimd;
+	struct iovec iov;
+	int ret, vq;
+	bool pass = true;
+
+	if (!sve_supported())
+		return true;
+
+	vq = __sve_vq_from_vl(config->sve_vl_in);
+
+	iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE);
+	iov.iov_base = malloc(iov.iov_len);
+	if (!iov.iov_base) {
+		ksft_print_msg("OOM allocating %lu byte SVE buffer\n",
+			       iov.iov_len);
+		return false;
+	}
+
+	ret = ptrace(PTRACE_GETREGSET, child, NT_ARM_SVE, &iov);
+	if (ret != 0) {
+		ksft_print_msg("Failed to read initial SVE: %s (%d)\n",
+			       strerror(errno), errno);
+		pass = false;
+		goto out;
+	}
+
+	sve = iov.iov_base;
+
+	if (sve->vl != config->sve_vl_in) {
+		ksft_print_msg("Mismatch in initial SVE VL: %d != %d\n",
+			       sve->vl, config->sve_vl_in);
+		pass = false;
+	}
+
+	/* If we are in streaming mode we should just read FPSIMD */
+	if ((config->svcr_in & SVCR_SM) && (sve->flags & SVE_PT_REGS_SVE)) {
+		ksft_print_msg("NT_ARM_SVE reports SVE with PSTATE.SM\n");
+		pass = false;
+	}
+
+	if (svcr_in & SVCR_SM) {
+		if (sve->size != sizeof(sve)) {
+			ksft_print_msg("NT_ARM_SVE reports data with PSTATE.SM\n");
+			pass = false;
+		}
+	} else {
+		if (sve->size != SVE_PT_SIZE(vq, sve->flags)) {
+			ksft_print_msg("Mismatch in SVE header size: %d != %lu\n",
+				       sve->size, SVE_PT_SIZE(vq, sve->flags));
+			pass = false;
+		}
+	}
+
+	/* The registers might be in completely different formats! */
+	if (sve->flags & SVE_PT_REGS_SVE) {
+		if (!compare_buffer("initial SVE Z",
+				    iov.iov_base + SVE_PT_SVE_ZREG_OFFSET(vq, 0),
+				    z_in, SVE_PT_SVE_ZREGS_SIZE(vq)))
+			pass = false;
+
+		if (!compare_buffer("initial SVE P",
+				    iov.iov_base + SVE_PT_SVE_PREG_OFFSET(vq, 0),
+				    p_in, SVE_PT_SVE_PREGS_SIZE(vq)))
+			pass = false;
+
+		if (!compare_buffer("initial SVE FFR",
+				    iov.iov_base + SVE_PT_SVE_FFR_OFFSET(vq),
+				    ffr_in, SVE_PT_SVE_PREG_SIZE(vq)))
+			pass = false;
+	} else {
+		fpsimd = iov.iov_base + SVE_PT_FPSIMD_OFFSET;
+		if (!compare_buffer("initial V via SVE", &fpsimd->vregs[0],
+				    v_in, sizeof(v_in)))
+			pass = false;
+	}
+
+out:
+	free(iov.iov_base);
+	return pass;
+}
+
+static bool check_ptrace_values_ssve(pid_t child, struct test_config *config)
+{
+	struct user_sve_header *sve;
+	struct user_fpsimd_state *fpsimd;
+	struct iovec iov;
+	int ret, vq;
+	bool pass = true;
+
+	if (!sme_supported())
+		return true;
+
+	vq = __sve_vq_from_vl(config->sme_vl_in);
+
+	iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE);
+	iov.iov_base = malloc(iov.iov_len);
+	if (!iov.iov_base) {
+		ksft_print_msg("OOM allocating %lu byte SSVE buffer\n",
+			       iov.iov_len);
+		return false;
+	}
+
+	ret = ptrace(PTRACE_GETREGSET, child, NT_ARM_SSVE, &iov);
+	if (ret != 0) {
+		ksft_print_msg("Failed to read initial SSVE: %s (%d)\n",
+			       strerror(errno), errno);
+		pass = false;
+		goto out;
+	}
+
+	sve = iov.iov_base;
+
+	if (sve->vl != config->sme_vl_in) {
+		ksft_print_msg("Mismatch in initial SSVE VL: %d != %d\n",
+			       sve->vl, config->sme_vl_in);
+		pass = false;
+	}
+
+	if ((config->svcr_in & SVCR_SM) && !(sve->flags & SVE_PT_REGS_SVE)) {
+		ksft_print_msg("NT_ARM_SSVE reports FPSIMD with PSTATE.SM\n");
+		pass = false;
+	}
+
+	if (!(svcr_in & SVCR_SM)) {
+		if (sve->size != sizeof(sve)) {
+			ksft_print_msg("NT_ARM_SSVE reports data without PSTATE.SM\n");
+			pass = false;
+		}
+	} else {
+		if (sve->size != SVE_PT_SIZE(vq, sve->flags)) {
+			ksft_print_msg("Mismatch in SSVE header size: %d != %lu\n",
+				       sve->size, SVE_PT_SIZE(vq, sve->flags));
+			pass = false;
+		}
+	}
+
+	/* The registers might be in completely different formats! */
+	if (sve->flags & SVE_PT_REGS_SVE) {
+		if (!compare_buffer("initial SSVE Z",
+				    iov.iov_base + SVE_PT_SVE_ZREG_OFFSET(vq, 0),
+				    z_in, SVE_PT_SVE_ZREGS_SIZE(vq)))
+			pass = false;
+
+		if (!compare_buffer("initial SSVE P",
+				    iov.iov_base + SVE_PT_SVE_PREG_OFFSET(vq, 0),
+				    p_in, SVE_PT_SVE_PREGS_SIZE(vq)))
+			pass = false;
+
+		if (!compare_buffer("initial SSVE FFR",
+				    iov.iov_base + SVE_PT_SVE_FFR_OFFSET(vq),
+				    ffr_in, SVE_PT_SVE_PREG_SIZE(vq)))
+			pass = false;
+	} else {
+		fpsimd = iov.iov_base + SVE_PT_FPSIMD_OFFSET;
+		if (!compare_buffer("initial V via SSVE",
+				    &fpsimd->vregs[0], v_in, sizeof(v_in)))
+			pass = false;
+	}
+
+out:
+	free(iov.iov_base);
+	return pass;
+}
+
+static bool check_ptrace_values_za(pid_t child, struct test_config *config)
+{
+	struct user_za_header *za;
+	struct iovec iov;
+	int ret, vq;
+	bool pass = true;
+
+	if (!sme_supported())
+		return true;
+
+	vq = __sve_vq_from_vl(config->sme_vl_in);
+
+	iov.iov_len = ZA_SIG_CONTEXT_SIZE(vq);
+	iov.iov_base = malloc(iov.iov_len);
+	if (!iov.iov_base) {
+		ksft_print_msg("OOM allocating %lu byte ZA buffer\n",
+			       iov.iov_len);
+		return false;
+	}
+
+	ret = ptrace(PTRACE_GETREGSET, child, NT_ARM_ZA, &iov);
+	if (ret != 0) {
+		ksft_print_msg("Failed to read initial ZA: %s (%d)\n",
+			       strerror(errno), errno);
+		pass = false;
+		goto out;
+	}
+
+	za = iov.iov_base;
+
+	if (za->vl != config->sme_vl_in) {
+		ksft_print_msg("Mismatch in initial SME VL: %d != %d\n",
+			       za->vl, config->sme_vl_in);
+		pass = false;
+	}
+
+	/* If PSTATE.ZA is not set we should just read the header */
+	if (config->svcr_in & SVCR_ZA) {
+		if (za->size != ZA_PT_SIZE(vq)) {
+			ksft_print_msg("Unexpected ZA ptrace read size: %d != %lu\n",
+				       za->size, ZA_PT_SIZE(vq));
+			pass = false;
+		}
+
+		if (!compare_buffer("initial ZA",
+				    iov.iov_base + ZA_PT_ZA_OFFSET,
+				    za_in, ZA_PT_ZA_SIZE(vq)))
+			pass = false;
+	} else {
+		if (za->size != sizeof(*za)) {
+			ksft_print_msg("Unexpected ZA ptrace read size: %d != %lu\n",
+				       za->size, sizeof(*za));
+			pass = false;
+		}
+	}
+
+out:
+	free(iov.iov_base);
+	return pass;
+}
+
+static bool check_ptrace_values_zt(pid_t child, struct test_config *config)
+{
+	uint8_t buf[512];
+	struct iovec iov;
+	int ret;
+
+	if (!sme2_supported())
+		return true;
+
+	iov.iov_base = &buf;
+	iov.iov_len = ZT_SIG_REG_BYTES;
+	ret = ptrace(PTRACE_GETREGSET, child, NT_ARM_ZT, &iov);
+	if (ret != 0) {
+		ksft_print_msg("Failed to read initial ZT: %s (%d)\n",
+			       strerror(errno), errno);
+		return false;
+	}
+
+	return compare_buffer("initial ZT", buf, zt_in, ZT_SIG_REG_BYTES);
+}
+
+static bool check_ptrace_values_fpmr(pid_t child, struct test_config *config)
+{
+	uint64_t val;
+	struct iovec iov;
+	int ret;
+
+	if (!fpmr_supported())
+		return true;
+
+	iov.iov_base = &val;
+	iov.iov_len = sizeof(val);
+	ret = ptrace(PTRACE_GETREGSET, child, NT_ARM_FPMR, &iov);
+	if (ret != 0) {
+		ksft_print_msg("Failed to read initial FPMR: %s (%d)\n",
+			       strerror(errno), errno);
+		return false;
+	}
+
+	return compare_buffer("initial FPMR", &val, &fpmr_in, sizeof(val));
+}
+
+static bool check_ptrace_values(pid_t child, struct test_config *config)
+{
+	bool pass = true;
+	struct user_fpsimd_state fpsimd;
+	struct iovec iov;
+	int ret;
+
+	iov.iov_base = &fpsimd;
+	iov.iov_len = sizeof(fpsimd);
+	ret = ptrace(PTRACE_GETREGSET, child, NT_PRFPREG, &iov);
+	if (ret == 0) {
+		if (!compare_buffer("initial V", &fpsimd.vregs, v_in,
+				    sizeof(v_in))) {
+			pass = false;
+		}
+	} else {
+		ksft_print_msg("Failed to read initial V: %s (%d)\n",
+			       strerror(errno), errno);
+		pass = false;
+	}
+
+	if (!check_ptrace_values_sve(child, config))
+		pass = false;
+
+	if (!check_ptrace_values_ssve(child, config))
+		pass = false;
+
+	if (!check_ptrace_values_za(child, config))
+		pass = false;
+
+	if (!check_ptrace_values_zt(child, config))
+		pass = false;
+
+	if (!check_ptrace_values_fpmr(child, config))
+		pass = false;
+
+	return pass;
+}
+
+static bool run_parent(pid_t child, struct test_definition *test,
+		       struct test_config *config)
+{
+	int wait_status, ret;
+	pid_t pid;
+	bool pass;
+
+	/* Initial attach */
+	while (1) {
+		pid = waitpid(child, &wait_status, 0);
+		if (pid < 0) {
+			if (errno == EINTR)
+				continue;
+			ksft_exit_fail_msg("waitpid() failed: %s (%d)\n",
+					   strerror(errno), errno);
+		}
+
+		if (pid == child)
+			break;
+	}
+
+	if (WIFEXITED(wait_status)) {
+		ksft_print_msg("Child exited loading values with status %d\n",
+			       WEXITSTATUS(wait_status));
+		pass = false;
+		goto out;
+	}
+
+	if (WIFSIGNALED(wait_status)) {
+		ksft_print_msg("Child died from signal %d loading values\n",
+			       WTERMSIG(wait_status));
+		pass = false;
+		goto out;
+	}
+
+	/* Read initial values via ptrace */
+	pass = check_ptrace_values(child, config);
+
+	/* Do whatever writes we want to do */
+	if (test->modify_values)
+		test->modify_values(child, config);
+
+	if (!continue_breakpoint(child, PTRACE_CONT))
+		goto cleanup;
+
+	while (1) {
+		pid = waitpid(child, &wait_status, 0);
+		if (pid < 0) {
+			if (errno == EINTR)
+				continue;
+			ksft_exit_fail_msg("waitpid() failed: %s (%d)\n",
+					   strerror(errno), errno);
+		}
+
+		if (pid == child)
+			break;
+	}
+
+	if (WIFEXITED(wait_status)) {
+		ksft_print_msg("Child exited saving values with status %d\n",
+			       WEXITSTATUS(wait_status));
+		pass = false;
+		goto out;
+	}
+
+	if (WIFSIGNALED(wait_status)) {
+		ksft_print_msg("Child died from signal %d saving values\n",
+			       WTERMSIG(wait_status));
+		pass = false;
+		goto out;
+	}
+
+	/* See what happened as a result */
+	read_child_regs(child);
+
+	if (!continue_breakpoint(child, PTRACE_DETACH))
+		goto cleanup;
+
+	/* The child should exit cleanly */
+	got_alarm = false;
+	alarm(1);
+	while (1) {
+		if (got_alarm) {
+			ksft_print_msg("Wait for child timed out\n");
+			goto cleanup;
+		}
+
+		pid = waitpid(child, &wait_status, 0);
+		if (pid < 0) {
+			if (errno == EINTR)
+				continue;
+			ksft_exit_fail_msg("waitpid() failed: %s (%d)\n",
+					   strerror(errno), errno);
+		}
+
+		if (pid == child)
+			break;
+	}
+	alarm(0);
+
+	if (got_alarm) {
+		ksft_print_msg("Timed out waiting for child\n");
+		pass = false;
+		goto cleanup;
+	}
+
+	if (pid == child && WIFSIGNALED(wait_status)) {
+		ksft_print_msg("Child died from signal %d cleaning up\n",
+			       WTERMSIG(wait_status));
+		pass = false;
+		goto out;
+	}
+
+	if (pid == child && WIFEXITED(wait_status)) {
+		if (WEXITSTATUS(wait_status) != 0) {
+			ksft_print_msg("Child exited with error %d\n",
+				       WEXITSTATUS(wait_status));
+			pass = false;
+		}
+	} else {
+		ksft_print_msg("Child did not exit cleanly\n");
+		pass = false;
+		goto cleanup;
+	}
+
+	goto out;
+
+cleanup:
+	ret = kill(child, SIGKILL);
+	if (ret != 0) {
+		ksft_print_msg("kill() failed: %s (%d)\n",
+			       strerror(errno), errno);
+		return false;
+	}
+
+	while (1) {
+		pid = waitpid(child, &wait_status, 0);
+		if (pid < 0) {
+			if (errno == EINTR)
+				continue;
+			ksft_exit_fail_msg("waitpid() failed: %s (%d)\n",
+					   strerror(errno), errno);
+		}
+
+		if (pid == child)
+			break;
+	}
+
+out:
+	return pass;
+}
+
+static void fill_random(void *buf, size_t size)
+{
+	int i;
+	uint32_t *lbuf = buf;
+
+	/* random() returns a 32 bit number regardless of the size of long */
+	for (i = 0; i < size / sizeof(uint32_t); i++)
+		lbuf[i] = random();
+}
+
+static void fill_random_ffr(void *buf, size_t vq)
+{
+	uint8_t *lbuf = buf;
+	int bits, i;
+
+	/*
+	 * Only values with a continuous set of 0..n bits set are
+	 * valid for FFR, set all bits then clear a random number of
+	 * high bits.
+	 */
+	memset(buf, 0, __SVE_FFR_SIZE(vq));
+
+	bits = random() % (__SVE_FFR_SIZE(vq) * 8);
+	for (i = 0; i < bits / 8; i++)
+		lbuf[i] = 0xff;
+	if (bits / 8 != __SVE_FFR_SIZE(vq))
+		lbuf[i] = (1 << (bits % 8)) - 1;
+}
+
+static void fpsimd_to_sve(__uint128_t *v, char *z, int vl)
+{
+	int vq = __sve_vq_from_vl(vl);
+	int i;
+	__uint128_t *p;
+
+	if (!vl)
+		return;
+
+	for (i = 0; i < __SVE_NUM_ZREGS; i++) {
+		p = (__uint128_t *)&z[__SVE_ZREG_OFFSET(vq, i)];
+		*p = arm64_cpu_to_le128(v[i]);
+	}
+}
+
+static void set_initial_values(struct test_config *config)
+{
+	int vq = __sve_vq_from_vl(vl_in(config));
+	int sme_vq = __sve_vq_from_vl(config->sme_vl_in);
+
+	svcr_in = config->svcr_in;
+	svcr_expected = config->svcr_expected;
+	svcr_out = 0;
+
+	fill_random(&v_in, sizeof(v_in));
+	memcpy(v_expected, v_in, sizeof(v_in));
+	memset(v_out, 0, sizeof(v_out));
+
+	/* Changes will be handled in the test case */
+	if (sve_supported() || (config->svcr_in & SVCR_SM)) {
+		/* The low 128 bits of Z are shared with the V registers */
+		fill_random(&z_in, __SVE_ZREGS_SIZE(vq));
+		fpsimd_to_sve(v_in, z_in, vl_in(config));
+		memcpy(z_expected, z_in, __SVE_ZREGS_SIZE(vq));
+		memset(z_out, 0, sizeof(z_out));
+
+		fill_random(&p_in, __SVE_PREGS_SIZE(vq));
+		memcpy(p_expected, p_in, __SVE_PREGS_SIZE(vq));
+		memset(p_out, 0, sizeof(p_out));
+
+		if ((config->svcr_in & SVCR_SM) && !fa64_supported())
+			memset(ffr_in, 0, __SVE_PREG_SIZE(vq));
+		else
+			fill_random_ffr(&ffr_in, vq);
+		memcpy(ffr_expected, ffr_in, __SVE_PREG_SIZE(vq));
+		memset(ffr_out, 0, __SVE_PREG_SIZE(vq));
+	}
+
+	if (config->svcr_in & SVCR_ZA)
+		fill_random(za_in, ZA_SIG_REGS_SIZE(sme_vq));
+	else
+		memset(za_in, 0, ZA_SIG_REGS_SIZE(sme_vq));
+	if (config->svcr_expected & SVCR_ZA)
+		memcpy(za_expected, za_in, ZA_SIG_REGS_SIZE(sme_vq));
+	else
+		memset(za_expected, 0, ZA_SIG_REGS_SIZE(sme_vq));
+	if (sme_supported())
+		memset(za_out, 0, sizeof(za_out));
+
+	if (sme2_supported()) {
+		if (config->svcr_in & SVCR_ZA)
+			fill_random(zt_in, ZT_SIG_REG_BYTES);
+		else
+			memset(zt_in, 0, ZT_SIG_REG_BYTES);
+		if (config->svcr_expected & SVCR_ZA)
+			memcpy(zt_expected, zt_in, ZT_SIG_REG_BYTES);
+		else
+			memset(zt_expected, 0, ZT_SIG_REG_BYTES);
+		memset(zt_out, 0, sizeof(zt_out));
+	}
+
+	if (fpmr_supported()) {
+		fill_random(&fpmr_in, sizeof(fpmr_in));
+		fpmr_in &= FPMR_SAFE_BITS;
+		fpmr_expected = fpmr_in;
+	} else {
+		fpmr_in = 0;
+		fpmr_expected = 0;
+		fpmr_out = 0;
+	}
+}
+
+static bool check_memory_values(struct test_config *config)
+{
+	bool pass = true;
+	int vq, sme_vq;
+
+	if (!compare_buffer("saved V", v_out, v_expected, sizeof(v_out)))
+		pass = false;
+
+	vq = __sve_vq_from_vl(vl_expected(config));
+	sme_vq = __sve_vq_from_vl(config->sme_vl_expected);
+
+	if (svcr_out != svcr_expected) {
+		ksft_print_msg("Mismatch in saved SVCR %lx != %lx\n",
+			       svcr_out, svcr_expected);
+		pass = false;
+	}
+
+	if (sve_vl_out != config->sve_vl_expected) {
+		ksft_print_msg("Mismatch in SVE VL: %ld != %d\n",
+			       sve_vl_out, config->sve_vl_expected);
+		pass = false;
+	}
+
+	if (sme_vl_out != config->sme_vl_expected) {
+		ksft_print_msg("Mismatch in SME VL: %ld != %d\n",
+			       sme_vl_out, config->sme_vl_expected);
+		pass = false;
+	}
+
+	if (!compare_buffer("saved Z", z_out, z_expected,
+			    __SVE_ZREGS_SIZE(vq)))
+		pass = false;
+
+	if (!compare_buffer("saved P", p_out, p_expected,
+			    __SVE_PREGS_SIZE(vq)))
+		pass = false;
+
+	if (!compare_buffer("saved FFR", ffr_out, ffr_expected,
+			    __SVE_PREG_SIZE(vq)))
+		pass = false;
+
+	if (!compare_buffer("saved ZA", za_out, za_expected,
+			    ZA_PT_ZA_SIZE(sme_vq)))
+		pass = false;
+
+	if (!compare_buffer("saved ZT", zt_out, zt_expected, ZT_SIG_REG_BYTES))
+		pass = false;
+
+	if (fpmr_out != fpmr_expected) {
+		ksft_print_msg("Mismatch in saved FPMR: %lx != %lx\n",
+			       fpmr_out, fpmr_expected);
+		pass = false;
+	}
+
+	return pass;
+}
+
+static bool sve_sme_same(struct test_config *config)
+{
+	if (config->sve_vl_in != config->sve_vl_expected)
+		return false;
+
+	if (config->sme_vl_in != config->sme_vl_expected)
+		return false;
+
+	if (config->svcr_in != config->svcr_expected)
+		return false;
+
+	return true;
+}
+
+static bool sve_write_supported(struct test_config *config)
+{
+	if (!sve_supported() && !sme_supported())
+		return false;
+
+	if ((config->svcr_in & SVCR_ZA) != (config->svcr_expected & SVCR_ZA))
+		return false;
+
+	if (config->svcr_expected & SVCR_SM) {
+		if (config->sve_vl_in != config->sve_vl_expected) {
+			return false;
+		}
+
+		/* Changing the SME VL disables ZA */
+		if ((config->svcr_expected & SVCR_ZA) &&
+		    (config->sme_vl_in != config->sme_vl_expected)) {
+			return false;
+		}
+	} else {
+		if (config->sme_vl_in != config->sme_vl_expected) {
+			return false;
+		}
+
+		if (!sve_supported())
+			return false;
+	}
+
+	return true;
+}
+
+static bool sve_write_fpsimd_supported(struct test_config *config)
+{
+	if (!sve_supported() && !sme_supported())
+		return false;
+
+	if ((config->svcr_in & SVCR_ZA) != (config->svcr_expected & SVCR_ZA))
+		return false;
+
+	if (config->svcr_expected & SVCR_SM)
+		return false;
+
+	if (config->sme_vl_in != config->sme_vl_expected)
+		return false;
+
+	return true;
+}
+
+static void fpsimd_write_expected(struct test_config *config)
+{
+	int vl;
+
+	fill_random(&v_expected, sizeof(v_expected));
+
+	/* The SVE registers are flushed by a FPSIMD write */
+	vl = vl_expected(config);
+
+	memset(z_expected, 0, __SVE_ZREGS_SIZE(__sve_vq_from_vl(vl)));
+	memset(p_expected, 0, __SVE_PREGS_SIZE(__sve_vq_from_vl(vl)));
+	memset(ffr_expected, 0, __SVE_PREG_SIZE(__sve_vq_from_vl(vl)));
+
+	fpsimd_to_sve(v_expected, z_expected, vl);
+}
+
+static void fpsimd_write(pid_t child, struct test_config *test_config)
+{
+	struct user_fpsimd_state fpsimd;
+	struct iovec iov;
+	int ret;
+
+	memset(&fpsimd, 0, sizeof(fpsimd));
+	memcpy(&fpsimd.vregs, v_expected, sizeof(v_expected));
+
+	iov.iov_base = &fpsimd;
+	iov.iov_len = sizeof(fpsimd);
+	ret = ptrace(PTRACE_SETREGSET, child, NT_PRFPREG, &iov);
+	if (ret == -1)
+		ksft_print_msg("FPSIMD set failed: (%s) %d\n",
+			       strerror(errno), errno);
+}
+
+static bool fpmr_write_supported(struct test_config *config)
+{
+	if (!fpmr_supported())
+		return false;
+
+	if (!sve_sme_same(config))
+		return false;
+
+	return true;
+}
+
+static void fpmr_write_expected(struct test_config *config)
+{
+	fill_random(&fpmr_expected, sizeof(fpmr_expected));
+	fpmr_expected &= FPMR_SAFE_BITS;
+}
+
+static void fpmr_write(pid_t child, struct test_config *config)
+{
+	struct iovec iov;
+	int ret;
+
+	iov.iov_len = sizeof(fpmr_expected);
+	iov.iov_base = &fpmr_expected;
+	ret = ptrace(PTRACE_SETREGSET, child, NT_ARM_FPMR, &iov);
+	if (ret != 0)
+		ksft_print_msg("Failed to write FPMR: %s (%d)\n",
+			       strerror(errno), errno);
+}
+
+static void sve_write_expected(struct test_config *config)
+{
+	int vl = vl_expected(config);
+	int sme_vq = __sve_vq_from_vl(config->sme_vl_expected);
+
+	if (!vl)
+		return;
+
+	fill_random(z_expected, __SVE_ZREGS_SIZE(__sve_vq_from_vl(vl)));
+	fill_random(p_expected, __SVE_PREGS_SIZE(__sve_vq_from_vl(vl)));
+
+	if ((svcr_expected & SVCR_SM) && !fa64_supported())
+		memset(ffr_expected, 0, __SVE_PREG_SIZE(sme_vq));
+	else
+		fill_random_ffr(ffr_expected, __sve_vq_from_vl(vl));
+
+	/* Share the low bits of Z with V */
+	fill_random(&v_expected, sizeof(v_expected));
+	fpsimd_to_sve(v_expected, z_expected, vl);
+
+	if (config->sme_vl_in != config->sme_vl_expected) {
+		memset(za_expected, 0, ZA_PT_ZA_SIZE(sme_vq));
+		memset(zt_expected, 0, sizeof(zt_expected));
+	}
+}
+
+static void sve_write_sve(pid_t child, struct test_config *config)
+{
+	struct user_sve_header *sve;
+	struct iovec iov;
+	int ret, vl, vq, regset;
+
+	vl = vl_expected(config);
+	vq = __sve_vq_from_vl(vl);
+
+	if (!vl)
+		return;
+
+	iov.iov_len = SVE_PT_SIZE(vq, SVE_PT_REGS_SVE);
+	iov.iov_base = malloc(iov.iov_len);
+	if (!iov.iov_base) {
+		ksft_print_msg("Failed allocating %lu byte SVE write buffer\n",
+			       iov.iov_len);
+		return;
+	}
+	memset(iov.iov_base, 0, iov.iov_len);
+
+	sve = iov.iov_base;
+	sve->size = iov.iov_len;
+	sve->flags = SVE_PT_REGS_SVE;
+	sve->vl = vl;
+
+	memcpy(iov.iov_base + SVE_PT_SVE_ZREG_OFFSET(vq, 0),
+	       z_expected, SVE_PT_SVE_ZREGS_SIZE(vq));
+	memcpy(iov.iov_base + SVE_PT_SVE_PREG_OFFSET(vq, 0),
+	       p_expected, SVE_PT_SVE_PREGS_SIZE(vq));
+	memcpy(iov.iov_base + SVE_PT_SVE_FFR_OFFSET(vq),
+	       ffr_expected, SVE_PT_SVE_PREG_SIZE(vq));
+
+	if (svcr_expected & SVCR_SM)
+		regset = NT_ARM_SSVE;
+	else
+		regset = NT_ARM_SVE;
+
+	ret = ptrace(PTRACE_SETREGSET, child, regset, &iov);
+	if (ret != 0)
+		ksft_print_msg("Failed to write SVE: %s (%d)\n",
+			       strerror(errno), errno);
+
+	free(iov.iov_base);
+}
+
+static void sve_write_fpsimd(pid_t child, struct test_config *config)
+{
+	struct user_sve_header *sve;
+	struct user_fpsimd_state *fpsimd;
+	struct iovec iov;
+	int ret, vl, vq;
+
+	vl = vl_expected(config);
+	vq = __sve_vq_from_vl(vl);
+
+	iov.iov_len = SVE_PT_SIZE(vq, SVE_PT_REGS_FPSIMD);
+	iov.iov_base = malloc(iov.iov_len);
+	if (!iov.iov_base) {
+		ksft_print_msg("Failed allocating %lu byte SVE write buffer\n",
+			       iov.iov_len);
+		return;
+	}
+	memset(iov.iov_base, 0, iov.iov_len);
+
+	sve = iov.iov_base;
+	sve->size = iov.iov_len;
+	sve->flags = SVE_PT_REGS_FPSIMD;
+	sve->vl = vl;
+
+	fpsimd = iov.iov_base + SVE_PT_REGS_OFFSET;
+	memcpy(&fpsimd->vregs, v_expected, sizeof(v_expected));
+
+	ret = ptrace(PTRACE_SETREGSET, child, NT_ARM_SVE, &iov);
+	if (ret != 0)
+		ksft_print_msg("Failed to write SVE: %s (%d)\n",
+			       strerror(errno), errno);
+
+	free(iov.iov_base);
+}
+
+static bool za_write_supported(struct test_config *config)
+{
+	if ((config->svcr_in & SVCR_SM) != (config->svcr_expected & SVCR_SM))
+		return false;
+
+	return true;
+}
+
+static void za_write_expected(struct test_config *config)
+{
+	int sme_vq, sve_vq;
+
+	sme_vq = __sve_vq_from_vl(config->sme_vl_expected);
+
+	if (config->svcr_expected & SVCR_ZA) {
+		fill_random(za_expected, ZA_PT_ZA_SIZE(sme_vq));
+	} else {
+		memset(za_expected, 0, ZA_PT_ZA_SIZE(sme_vq));
+		memset(zt_expected, 0, sizeof(zt_expected));
+	}
+
+	/* Changing the SME VL flushes ZT, SVE state */
+	if (config->sme_vl_in != config->sme_vl_expected) {
+		sve_vq = __sve_vq_from_vl(vl_expected(config));
+		memset(z_expected, 0, __SVE_ZREGS_SIZE(sve_vq));
+		memset(p_expected, 0, __SVE_PREGS_SIZE(sve_vq));
+		memset(ffr_expected, 0, __SVE_PREG_SIZE(sve_vq));
+		memset(zt_expected, 0, sizeof(zt_expected));
+
+		fpsimd_to_sve(v_expected, z_expected, vl_expected(config));
+	}
+}
+
+static void za_write(pid_t child, struct test_config *config)
+{
+	struct user_za_header *za;
+	struct iovec iov;
+	int ret, vq;
+
+	vq = __sve_vq_from_vl(config->sme_vl_expected);
+
+	if (config->svcr_expected & SVCR_ZA)
+		iov.iov_len = ZA_PT_SIZE(vq);
+	else
+		iov.iov_len = sizeof(*za);
+	iov.iov_base = malloc(iov.iov_len);
+	if (!iov.iov_base) {
+		ksft_print_msg("Failed allocating %lu byte ZA write buffer\n",
+			       iov.iov_len);
+		return;
+	}
+	memset(iov.iov_base, 0, iov.iov_len);
+
+	za = iov.iov_base;
+	za->size = iov.iov_len;
+	za->vl = config->sme_vl_expected;
+	if (config->svcr_expected & SVCR_ZA)
+		memcpy(iov.iov_base + ZA_PT_ZA_OFFSET, za_expected,
+		       ZA_PT_ZA_SIZE(vq));
+
+	ret = ptrace(PTRACE_SETREGSET, child, NT_ARM_ZA, &iov);
+	if (ret != 0)
+		ksft_print_msg("Failed to write ZA: %s (%d)\n",
+			       strerror(errno), errno);
+
+	free(iov.iov_base);
+}
+
+static bool zt_write_supported(struct test_config *config)
+{
+	if (!sme2_supported())
+		return false;
+	if (config->sme_vl_in != config->sme_vl_expected)
+		return false;
+	if (!(config->svcr_expected & SVCR_ZA))
+		return false;
+	if ((config->svcr_in & SVCR_SM) != (config->svcr_expected & SVCR_SM))
+		return false;
+
+	return true;
+}
+
+static void zt_write_expected(struct test_config *config)
+{
+	int sme_vq;
+
+	sme_vq = __sve_vq_from_vl(config->sme_vl_expected);
+
+	if (config->svcr_expected & SVCR_ZA) {
+		fill_random(zt_expected, sizeof(zt_expected));
+	} else {
+		memset(za_expected, 0, ZA_PT_ZA_SIZE(sme_vq));
+		memset(zt_expected, 0, sizeof(zt_expected));
+	}
+}
+
+static void zt_write(pid_t child, struct test_config *config)
+{
+	struct iovec iov;
+	int ret;
+
+	iov.iov_len = ZT_SIG_REG_BYTES;
+	iov.iov_base = zt_expected;
+	ret = ptrace(PTRACE_SETREGSET, child, NT_ARM_ZT, &iov);
+	if (ret != 0)
+		ksft_print_msg("Failed to write ZT: %s (%d)\n",
+			       strerror(errno), errno);
+}
+
+/* Actually run a test */
+static void run_test(struct test_definition *test, struct test_config *config)
+{
+	pid_t child;
+	char name[1024];
+	bool pass;
+
+	if (sve_supported() && sme_supported())
+		snprintf(name, sizeof(name), "%s, SVE %d->%d, SME %d/%x->%d/%x",
+			 test->name,
+			 config->sve_vl_in, config->sve_vl_expected,
+			 config->sme_vl_in, config->svcr_in,
+			 config->sme_vl_expected, config->svcr_expected);
+	else if (sve_supported())
+		snprintf(name, sizeof(name), "%s, SVE %d->%d", test->name,
+			 config->sve_vl_in, config->sve_vl_expected);
+	else if (sme_supported())
+		snprintf(name, sizeof(name), "%s, SME %d/%x->%d/%x",
+			 test->name,
+			 config->sme_vl_in, config->svcr_in,
+			 config->sme_vl_expected, config->svcr_expected);
+	else
+		snprintf(name, sizeof(name), "%s", test->name);
+
+	if (test->supported && !test->supported(config)) {
+		ksft_test_result_skip("%s\n", name);
+		return;
+	}
+
+	set_initial_values(config);
+
+	if (test->set_expected_values)
+		test->set_expected_values(config);
+
+	child = fork();
+	if (child < 0)
+		ksft_exit_fail_msg("fork() failed: %s (%d)\n",
+				   strerror(errno), errno);
+	/* run_child() never returns */
+	if (child == 0)
+		run_child(config);
+
+	pass = run_parent(child, test, config);
+	if (!check_memory_values(config))
+		pass = false;
+
+	ksft_test_result(pass, "%s\n", name);
+}
+
+static void run_tests(struct test_definition defs[], int count,
+		      struct test_config *config)
+{
+	int i;
+
+	for (i = 0; i < count; i++)
+		run_test(&defs[i], config);
+}
+
+static struct test_definition base_test_defs[] = {
+	{
+		.name = "No writes",
+		.supported = sve_sme_same,
+	},
+	{
+		.name = "FPSIMD write",
+		.supported = sve_sme_same,
+		.set_expected_values = fpsimd_write_expected,
+		.modify_values = fpsimd_write,
+	},
+	{
+		.name = "FPMR write",
+		.supported = fpmr_write_supported,
+		.set_expected_values = fpmr_write_expected,
+		.modify_values = fpmr_write,
+	},
+};
+
+static struct test_definition sve_test_defs[] = {
+	{
+		.name = "SVE write",
+		.supported = sve_write_supported,
+		.set_expected_values = sve_write_expected,
+		.modify_values = sve_write_sve,
+	},
+	{
+		.name = "SVE write FPSIMD format",
+		.supported = sve_write_fpsimd_supported,
+		.set_expected_values = fpsimd_write_expected,
+		.modify_values = sve_write_fpsimd,
+	},
+};
+
+static struct test_definition za_test_defs[] = {
+	{
+		.name = "ZA write",
+		.supported = za_write_supported,
+		.set_expected_values = za_write_expected,
+		.modify_values = za_write,
+	},
+};
+
+static struct test_definition zt_test_defs[] = {
+	{
+		.name = "ZT write",
+		.supported = zt_write_supported,
+		.set_expected_values = zt_write_expected,
+		.modify_values = zt_write,
+	},
+};
+
+static int sve_vls[MAX_NUM_VLS], sme_vls[MAX_NUM_VLS];
+static int sve_vl_count, sme_vl_count;
+
+static void probe_vls(const char *name, int vls[], int *vl_count, int set_vl)
+{
+	unsigned int vq;
+	int vl;
+
+	*vl_count = 0;
+
+	for (vq = ARCH_VQ_MAX; vq > 0; vq /= 2) {
+		vl = prctl(set_vl, vq * 16);
+		if (vl == -1)
+			ksft_exit_fail_msg("SET_VL failed: %s (%d)\n",
+					   strerror(errno), errno);
+
+		vl &= PR_SVE_VL_LEN_MASK;
+
+		if (*vl_count && (vl == vls[*vl_count - 1]))
+			break;
+
+		vq = sve_vq_from_vl(vl);
+
+		vls[*vl_count] = vl;
+		*vl_count += 1;
+	}
+
+	if (*vl_count > 2) {
+		/* Just use the minimum and maximum */
+		vls[1] = vls[*vl_count - 1];
+		ksft_print_msg("%d %s VLs, using %d and %d\n",
+			       *vl_count, name, vls[0], vls[1]);
+		*vl_count = 2;
+	} else {
+		ksft_print_msg("%d %s VLs\n", *vl_count, name);
+	}
+}
+
+static struct {
+	int svcr_in, svcr_expected;
+} svcr_combinations[] = {
+	{ .svcr_in = 0, .svcr_expected = 0, },
+	{ .svcr_in = 0, .svcr_expected = SVCR_SM, },
+	{ .svcr_in = 0, .svcr_expected = SVCR_ZA, },
+	/* Can't enable both SM and ZA with a single ptrace write */
+
+	{ .svcr_in = SVCR_SM, .svcr_expected = 0, },
+	{ .svcr_in = SVCR_SM, .svcr_expected = SVCR_SM, },
+	{ .svcr_in = SVCR_SM, .svcr_expected = SVCR_ZA, },
+	{ .svcr_in = SVCR_SM, .svcr_expected = SVCR_SM | SVCR_ZA, },
+
+	{ .svcr_in = SVCR_ZA, .svcr_expected = 0, },
+	{ .svcr_in = SVCR_ZA, .svcr_expected = SVCR_SM, },
+	{ .svcr_in = SVCR_ZA, .svcr_expected = SVCR_ZA, },
+	{ .svcr_in = SVCR_ZA, .svcr_expected = SVCR_SM | SVCR_ZA, },
+
+	{ .svcr_in = SVCR_SM | SVCR_ZA, .svcr_expected = 0, },
+	{ .svcr_in = SVCR_SM | SVCR_ZA, .svcr_expected = SVCR_SM, },
+	{ .svcr_in = SVCR_SM | SVCR_ZA, .svcr_expected = SVCR_ZA, },
+	{ .svcr_in = SVCR_SM | SVCR_ZA, .svcr_expected = SVCR_SM | SVCR_ZA, },
+};
+
+static void run_sve_tests(void)
+{
+	struct test_config test_config;
+	int i, j;
+
+	if (!sve_supported())
+		return;
+
+	test_config.sme_vl_in = sme_vls[0];
+	test_config.sme_vl_expected = sme_vls[0];
+	test_config.svcr_in = 0;
+	test_config.svcr_expected = 0;
+
+	for (i = 0; i < sve_vl_count; i++) {
+		test_config.sve_vl_in = sve_vls[i];
+
+		for (j = 0; j < sve_vl_count; j++) {
+			test_config.sve_vl_expected = sve_vls[j];
+
+			run_tests(base_test_defs,
+				  ARRAY_SIZE(base_test_defs),
+				  &test_config);
+			if (sve_supported())
+				run_tests(sve_test_defs,
+					  ARRAY_SIZE(sve_test_defs),
+					  &test_config);
+		}
+	}
+}
+
+static void run_sme_tests(void)
+{
+	struct test_config test_config;
+	int i, j, k;
+
+	if (!sme_supported())
+		return;
+
+	test_config.sve_vl_in = sve_vls[0];
+	test_config.sve_vl_expected = sve_vls[0];
+
+	/*
+	 * Every SME VL/SVCR combination
+	 */
+	for (i = 0; i < sme_vl_count; i++) {
+		test_config.sme_vl_in = sme_vls[i];
+
+		for (j = 0; j < sme_vl_count; j++) {
+			test_config.sme_vl_expected = sme_vls[j];
+
+			for (k = 0; k < ARRAY_SIZE(svcr_combinations); k++) {
+				test_config.svcr_in = svcr_combinations[k].svcr_in;
+				test_config.svcr_expected = svcr_combinations[k].svcr_expected;
+
+				run_tests(base_test_defs,
+					  ARRAY_SIZE(base_test_defs),
+					  &test_config);
+				run_tests(sve_test_defs,
+					  ARRAY_SIZE(sve_test_defs),
+					  &test_config);
+				run_tests(za_test_defs,
+					  ARRAY_SIZE(za_test_defs),
+					  &test_config);
+
+				if (sme2_supported())
+					run_tests(zt_test_defs,
+						  ARRAY_SIZE(zt_test_defs),
+						  &test_config);
+			}
+		}
+	}
+}
+
+int main(void)
+{
+	struct test_config test_config;
+	struct sigaction sa;
+	int tests, ret, tmp;
+
+	srandom(getpid());
+
+	ksft_print_header();
+
+	if (sve_supported()) {
+		probe_vls("SVE", sve_vls, &sve_vl_count, PR_SVE_SET_VL);
+
+		tests = ARRAY_SIZE(base_test_defs) +
+			ARRAY_SIZE(sve_test_defs);
+		tests *= sve_vl_count * sve_vl_count;
+	} else {
+		/* Only run the FPSIMD tests */
+		sve_vl_count = 1;
+		tests = ARRAY_SIZE(base_test_defs);
+	}
+
+	if (sme_supported()) {
+		probe_vls("SME", sme_vls, &sme_vl_count, PR_SME_SET_VL);
+
+		tmp = ARRAY_SIZE(base_test_defs) + ARRAY_SIZE(sve_test_defs)
+			+ ARRAY_SIZE(za_test_defs);
+
+		if (sme2_supported())
+			tmp += ARRAY_SIZE(zt_test_defs);
+
+		tmp *= sme_vl_count * sme_vl_count;
+		tmp *= ARRAY_SIZE(svcr_combinations);
+		tests += tmp;
+	} else {
+		sme_vl_count = 1;
+	}
+
+	if (sme2_supported())
+		ksft_print_msg("SME2 supported\n");
+
+	if (fa64_supported())
+		ksft_print_msg("FA64 supported\n");
+
+	if (fpmr_supported())
+		ksft_print_msg("FPMR supported\n");
+
+	ksft_set_plan(tests);
+
+	/* Get signal handers ready before we start any children */
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handle_alarm;
+	sa.sa_flags = SA_RESTART | SA_SIGINFO;
+	sigemptyset(&sa.sa_mask);
+	ret = sigaction(SIGALRM, &sa, NULL);
+	if (ret < 0)
+		ksft_print_msg("Failed to install SIGALRM handler: %s (%d)\n",
+			       strerror(errno), errno);
+
+	/*
+	 * Run the test set if there is no SVE or SME, with those we
+	 * have to pick a VL for each run.
+	 */
+	if (!sve_supported() && !sme_supported()) {
+		test_config.sve_vl_in = 0;
+		test_config.sve_vl_expected = 0;
+		test_config.sme_vl_in = 0;
+		test_config.sme_vl_expected = 0;
+		test_config.svcr_in = 0;
+		test_config.svcr_expected = 0;
+
+		run_tests(base_test_defs, ARRAY_SIZE(base_test_defs),
+			  &test_config);
+	}
+
+	run_sve_tests();
+	run_sme_tests();
+
+	ksft_finished();
+}
diff --git a/tools/testing/selftests/arm64/fp/fp-ptrace.h b/tools/testing/selftests/arm64/fp/fp-ptrace.h
new file mode 100644
index 000000000000..c06919aaf1f7
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/fp-ptrace.h
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2021-3 ARM Limited.
+
+#ifndef FP_PTRACE_H
+#define FP_PTRACE_H
+
+#define SVCR_SM_SHIFT 0
+#define SVCR_ZA_SHIFT 1
+
+#define SVCR_SM (1 << SVCR_SM_SHIFT)
+#define SVCR_ZA (1 << SVCR_ZA_SHIFT)
+
+#define HAVE_SVE_SHIFT		0
+#define HAVE_SME_SHIFT		1
+#define HAVE_SME2_SHIFT		2
+#define HAVE_FA64_SHIFT		3
+#define HAVE_FPMR_SHIFT		4
+
+#define HAVE_SVE	(1 << HAVE_SVE_SHIFT)
+#define HAVE_SME	(1 << HAVE_SME_SHIFT)
+#define HAVE_SME2	(1 << HAVE_SME2_SHIFT)
+#define HAVE_FA64	(1 << HAVE_FA64_SHIFT)
+#define HAVE_FPMR	(1 << HAVE_FPMR_SHIFT)
+
+#endif
diff --git a/tools/testing/selftests/arm64/fp/fp-stress.c b/tools/testing/selftests/arm64/fp/fp-stress.c
index f8b2f41aac36..65e01aba96ff 100644
--- a/tools/testing/selftests/arm64/fp/fp-stress.c
+++ b/tools/testing/selftests/arm64/fp/fp-stress.c
@@ -24,10 +24,13 @@
 #include <sys/wait.h>
 #include <asm/hwcap.h>
 
-#include "../../kselftest.h"
+#include "kselftest.h"
 
 #define MAX_VLS 16
 
+#define SIGNAL_INTERVAL_MS 25
+#define LOG_INTERVALS (1000 / SIGNAL_INTERVAL_MS)
+
 struct child_data {
 	char *name, *output;
 	pid_t pid;
@@ -79,7 +82,7 @@ static void child_start(struct child_data *child, const char *program)
 		 */
 		ret = dup2(pipefd[1], 1);
 		if (ret == -1) {
-			fprintf(stderr, "dup2() %d\n", errno);
+			printf("dup2() %d\n", errno);
 			exit(EXIT_FAILURE);
 		}
 
@@ -89,7 +92,7 @@ static void child_start(struct child_data *child, const char *program)
 		 */
 		ret = dup2(startup_pipe[0], 3);
 		if (ret == -1) {
-			fprintf(stderr, "dup2() %d\n", errno);
+			printf("dup2() %d\n", errno);
 			exit(EXIT_FAILURE);
 		}
 
@@ -102,21 +105,20 @@ static void child_start(struct child_data *child, const char *program)
 
 		/*
 		 * Read from the startup pipe, there should be no data
-		 * and we should block until it is closed.  We just
-		 * carry on on error since this isn't super critical.
+		 * and we should block until it is closed. We just
+		 * carry-on on error since this isn't super critical.
 		 */
 		ret = read(3, &i, sizeof(i));
 		if (ret < 0)
-			fprintf(stderr, "read(startp pipe) failed: %s (%d)\n",
-				strerror(errno), errno);
+			printf("read(startp pipe) failed: %s (%d)\n",
+			       strerror(errno), errno);
 		if (ret > 0)
-			fprintf(stderr, "%d bytes of data on startup pipe\n",
-				ret);
+			printf("%d bytes of data on startup pipe\n", ret);
 		close(3);
 
 		ret = execl(program, program, NULL);
-		fprintf(stderr, "execl(%s) failed: %d (%s)\n",
-			program, errno, strerror(errno));
+		printf("execl(%s) failed: %d (%s)\n",
+		       program, errno, strerror(errno));
 
 		exit(EXIT_FAILURE);
 	} else {
@@ -221,7 +223,7 @@ static void child_output(struct child_data *child, uint32_t events,
 static void child_tickle(struct child_data *child)
 {
 	if (child->output_seen && !child->exited)
-		kill(child->pid, SIGUSR2);
+		kill(child->pid, SIGUSR1);
 }
 
 static void child_stop(struct child_data *child)
@@ -319,6 +321,19 @@ static void start_fpsimd(struct child_data *child, int cpu, int copy)
 	ksft_print_msg("Started %s\n", child->name);
 }
 
+static void start_kernel(struct child_data *child, int cpu, int copy)
+{
+	int ret;
+
+	ret = asprintf(&child->name, "KERNEL-%d-%d", cpu, copy);
+	if (ret == -1)
+		ksft_exit_fail_msg("asprintf() failed\n");
+
+	child_start(child, "./kernel-test");
+
+	ksft_print_msg("Started %s\n", child->name);
+}
+
 static void start_sve(struct child_data *child, int vl, int cpu)
 {
 	int ret;
@@ -370,6 +385,19 @@ static void start_za(struct child_data *child, int vl, int cpu)
 	ksft_print_msg("Started %s\n", child->name);
 }
 
+static void start_zt(struct child_data *child, int cpu)
+{
+	int ret;
+
+	ret = asprintf(&child->name, "ZT-%d", cpu);
+	if (ret == -1)
+		ksft_exit_fail_msg("asprintf() failed\n");
+
+	child_start(child, "./zt-test");
+
+	ksft_print_msg("Started %s\n", child->name);
+}
+
 static void probe_vls(int vls[], int *vl_count, int set_vl)
 {
 	unsigned int vq;
@@ -377,7 +405,7 @@ static void probe_vls(int vls[], int *vl_count, int set_vl)
 
 	*vl_count = 0;
 
-	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+	for (vq = SVE_VQ_MAX; vq > 0; vq /= 2) {
 		vl = prctl(set_vl, vq * 16);
 		if (vl == -1)
 			ksft_exit_fail_msg("SET_VL failed: %s (%d)\n",
@@ -385,6 +413,9 @@ static void probe_vls(int vls[], int *vl_count, int set_vl)
 
 		vl &= PR_SVE_VL_LEN_MASK;
 
+		if (*vl_count && (vl == vls[*vl_count - 1]))
+			break;
+
 		vq = sve_vq_from_vl(vl);
 
 		vls[*vl_count] = vl;
@@ -420,12 +451,14 @@ static const struct option options[] = {
 int main(int argc, char **argv)
 {
 	int ret;
-	int timeout = 10;
+	int timeout = 10 * (1000 / SIGNAL_INTERVAL_MS);
+	int poll_interval = 5000;
 	int cpus, i, j, c;
-	int sve_vl_count, sme_vl_count, fpsimd_per_cpu;
+	int sve_vl_count, sme_vl_count;
 	bool all_children_started = false;
 	int seen_children;
 	int sve_vls[MAX_VLS], sme_vls[MAX_VLS];
+	bool have_sme2;
 	struct sigaction sa;
 
 	while ((c = getopt_long(argc, argv, "t:", options, NULL)) != -1) {
@@ -458,21 +491,24 @@ int main(int argc, char **argv)
 		sme_vl_count = 0;
 	}
 
-	/* Force context switching if we only have FPSIMD */
-	if (!sve_vl_count && !sme_vl_count)
-		fpsimd_per_cpu = 2;
-	else
-		fpsimd_per_cpu = 1;
-	tests += cpus * fpsimd_per_cpu;
+	if (getauxval(AT_HWCAP2) & HWCAP2_SME2) {
+		tests += cpus;
+		have_sme2 = true;
+	} else {
+		have_sme2 = false;
+	}
+
+	tests += cpus * 2;
 
 	ksft_print_header();
 	ksft_set_plan(tests);
 
-	ksft_print_msg("%d CPUs, %d SVE VLs, %d SME VLs\n",
-		       cpus, sve_vl_count, sme_vl_count);
+	ksft_print_msg("%d CPUs, %d SVE VLs, %d SME VLs, SME2 %s\n",
+		       cpus, sve_vl_count, sme_vl_count,
+		       have_sme2 ? "present" : "absent");
 
 	if (timeout > 0)
-		ksft_print_msg("Will run for %ds\n", timeout);
+		ksft_print_msg("Will run for %d\n", timeout);
 	else
 		ksft_print_msg("Will run until terminated\n");
 
@@ -513,12 +549,12 @@ int main(int argc, char **argv)
 
 	evs = calloc(tests, sizeof(*evs));
 	if (!evs)
-		ksft_exit_fail_msg("Failed to allocated %d epoll events\n",
+		ksft_exit_fail_msg("Failed to allocate %d epoll events\n",
 				   tests);
 
 	for (i = 0; i < cpus; i++) {
-		for (j = 0; j < fpsimd_per_cpu; j++)
-			start_fpsimd(&children[num_children++], i, j);
+		start_fpsimd(&children[num_children++], i, 0);
+		start_kernel(&children[num_children++], i, 0);
 
 		for (j = 0; j < sve_vl_count; j++)
 			start_sve(&children[num_children++], sve_vls[j], i);
@@ -527,6 +563,9 @@ int main(int argc, char **argv)
 			start_ssve(&children[num_children++], sme_vls[j], i);
 			start_za(&children[num_children++], sme_vls[j], i);
 		}
+
+		if (have_sme2)
+			start_zt(&children[num_children++], i);
 	}
 
 	/*
@@ -542,14 +581,14 @@ int main(int argc, char **argv)
 			break;
 
 		/*
-		 * Timeout is counted in seconds with no output, the
-		 * tests print during startup then are silent when
-		 * running so this should ensure they all ran enough
-		 * to install the signal handler, this is especially
-		 * useful in emulation where we will both be slow and
-		 * likely to have a large set of VLs.
+		 * Timeout is counted in poll intervals with no
+		 * output, the tests print during startup then are
+		 * silent when running so this should ensure they all
+		 * ran enough to install the signal handler, this is
+		 * especially useful in emulation where we will both
+		 * be slow and likely to have a large set of VLs.
 		 */
-		ret = epoll_wait(epoll_fd, evs, tests, 1000);
+		ret = epoll_wait(epoll_fd, evs, tests, poll_interval);
 		if (ret < 0) {
 			if (errno == EINTR)
 				continue;
@@ -587,10 +626,12 @@ int main(int argc, char **argv)
 			}
 
 			all_children_started = true;
+			poll_interval = SIGNAL_INTERVAL_MS;
 		}
 
-		ksft_print_msg("Sending signals, timeout remaining: %d\n",
-			       timeout);
+		if ((timeout % LOG_INTERVALS) == 0)
+			ksft_print_msg("Sending signals, timeout remaining: %d\n",
+				       timeout);
 
 		for (i = 0; i < num_children; i++)
 			child_tickle(&children[i]);
@@ -615,7 +656,5 @@ int main(int argc, char **argv)
 
 	drain_output(true);
 
-	ksft_print_cnts();
-
-	return 0;
+	ksft_finished();
 }
diff --git a/tools/testing/selftests/arm64/fp/fpsimd-test.S b/tools/testing/selftests/arm64/fp/fpsimd-test.S
index 918d04885a33..f89d67894c2e 100644
--- a/tools/testing/selftests/arm64/fp/fpsimd-test.S
+++ b/tools/testing/selftests/arm64/fp/fpsimd-test.S
@@ -134,8 +134,7 @@ function check_vreg
 	b	memcmp
 endfunction
 
-// Any SVE register modified here can cause corruption in the main
-// thread -- but *only* the registers modified here.
+// Modify live register state, the signal return will undo our changes
 function irritator_handler
 	// Increment the irritation signal count (x23):
 	ldr	x0, [x2, #ucontext_regs + 8 * 23]
@@ -143,7 +142,6 @@ function irritator_handler
 	str	x0, [x2, #ucontext_regs + 8 * 23]
 
 	// Corrupt some random V-regs
-	adr	x0, .text + (irritator_handler - .text) / 16 * 16
 	movi	v0.8b, #7
 	movi	v9.16b, #9
 	movi	v31.8b, #31
@@ -215,7 +213,8 @@ endfunction
 // Main program entry point
 .globl _start
 function _start
-_start:
+	enable_gcs
+
 	mov	x23, #0		// signal count
 
 	mov	w0, #SIGINT
diff --git a/tools/testing/selftests/arm64/fp/kernel-test.c b/tools/testing/selftests/arm64/fp/kernel-test.c
new file mode 100644
index 000000000000..0c40007d1282
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/kernel-test.c
@@ -0,0 +1,326 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2024 ARM Limited.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <signal.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <sys/socket.h>
+
+#include <linux/kernel.h>
+#include <linux/if_alg.h>
+
+#define DATA_SIZE (16 * 4096)
+
+static int base, sock;
+
+static int digest_len;
+static char *ref;
+static char *digest;
+static char *alg_name;
+
+static struct iovec data_iov;
+static int zerocopy[2];
+static int sigs;
+static int iter;
+
+static void handle_exit_signal(int sig, siginfo_t *info, void *context)
+{
+	printf("Terminated by signal %d, iterations=%d, signals=%d\n",
+	       sig, iter, sigs);
+	exit(0);
+}
+
+static void handle_kick_signal(int sig, siginfo_t *info, void *context)
+{
+	sigs++;
+}
+
+static char *drivers[] = {
+	"sha1-ce",
+	"sha224-arm64",
+	"sha224-arm64-neon",
+	"sha224-ce",
+	"sha256-arm64",
+	"sha256-arm64-neon",
+	"sha256-ce",
+	"sha384-ce",
+	"sha512-ce",
+	"sha3-224-ce",
+	"sha3-256-ce",
+	"sha3-384-ce",
+	"sha3-512-ce",
+	"sm3-ce",
+	"sm3-neon",
+};
+
+static bool create_socket(void)
+{
+	FILE *proc;
+	struct sockaddr_alg addr;
+	char buf[1024];
+	char *c, *driver_name;
+	bool is_shash, match;
+	int ret, i;
+
+	ret = socket(AF_ALG, SOCK_SEQPACKET, 0);
+	if (ret < 0) {
+		if (errno == EAFNOSUPPORT) {
+			printf("AF_ALG not supported\n");
+			return false;
+		}
+
+		printf("Failed to create AF_ALG socket: %s (%d)\n",
+		       strerror(errno), errno);
+		return false;
+	}
+	base = ret;
+
+	memset(&addr, 0, sizeof(addr));
+	addr.salg_family = AF_ALG;
+	strncpy((char *)addr.salg_type, "hash", sizeof(addr.salg_type));
+
+	proc = fopen("/proc/crypto", "r");
+	if (!proc) {
+		printf("Unable to open /proc/crypto\n");
+		return false;
+	}
+
+	driver_name = NULL;
+	is_shash = false;
+	match = false;
+
+	/* Look through /proc/crypto for a driver with kernel mode FP usage */
+	while (!match) {
+		c = fgets(buf, sizeof(buf), proc);
+		if (!c) {
+			if (feof(proc)) {
+				printf("Nothing found in /proc/crypto\n");
+				return false;
+			}
+			continue;
+		}
+
+		/* Algorithm descriptions are separated by a blank line */
+		if (*c == '\n') {
+			if (is_shash && driver_name) {
+				for (i = 0; i < ARRAY_SIZE(drivers); i++) {
+					if (strcmp(drivers[i],
+						   driver_name) == 0) {
+						match = true;
+					}
+				}
+			}
+
+			if (!match) {
+				digest_len = 0;
+
+				free(driver_name);
+				driver_name = NULL;
+
+				free(alg_name);
+				alg_name = NULL;
+
+				is_shash = false;
+			}
+			continue;
+		}
+
+		/* Remove trailing newline */
+		c = strchr(buf, '\n');
+		if (c)
+			*c = '\0';
+
+		/* Find the field/value separator and start of the value */
+		c = strchr(buf, ':');
+		if (!c)
+			continue;
+		c += 2;
+
+		if (strncmp(buf, "digestsize", strlen("digestsize")) == 0)
+			sscanf(c, "%d", &digest_len);
+
+		if (strncmp(buf, "name", strlen("name")) == 0)
+			alg_name = strdup(c);
+
+		if (strncmp(buf, "driver", strlen("driver")) == 0)
+			driver_name = strdup(c);
+
+		if (strncmp(buf, "type", strlen("type")) == 0)
+			if (strncmp(c, "shash", strlen("shash")) == 0)
+				is_shash = true;
+	}
+
+	strncpy((char *)addr.salg_name, alg_name,
+		sizeof(addr.salg_name) - 1);
+
+	ret = bind(base, (struct sockaddr *)&addr, sizeof(addr));
+	if (ret < 0) {
+		printf("Failed to bind %s: %s (%d)\n",
+		       addr.salg_name, strerror(errno), errno);
+		return false;
+	}
+
+	ret = accept(base, NULL, 0);
+	if (ret < 0) {
+		printf("Failed to accept %s: %s (%d)\n",
+		       addr.salg_name, strerror(errno), errno);
+		return false;
+	}
+
+	sock = ret;
+
+	ret = pipe(zerocopy);
+	if (ret != 0) {
+		printf("Failed to create zerocopy pipe: %s (%d)\n",
+		       strerror(errno), errno);
+		return false;
+	}
+
+	ref = malloc(digest_len);
+	if (!ref) {
+		printf("Failed to allocate %d byte reference\n", digest_len);
+		return false;
+	}
+
+	digest = malloc(digest_len);
+	if (!digest) {
+		printf("Failed to allocate %d byte digest\n", digest_len);
+		return false;
+	}
+
+	return true;
+}
+
+static bool compute_digest(void *buf)
+{
+	struct iovec iov;
+	int ret, wrote;
+
+	iov = data_iov;
+	while (iov.iov_len) {
+		ret = vmsplice(zerocopy[1], &iov, 1, SPLICE_F_GIFT);
+		if (ret < 0) {
+			printf("Failed to send buffer: %s (%d)\n",
+			       strerror(errno), errno);
+			return false;
+		}
+
+		wrote = ret;
+		ret = splice(zerocopy[0], NULL, sock, NULL, wrote, 0);
+		if (ret < 0) {
+			printf("Failed to splice buffer: %s (%d)\n",
+			       strerror(errno), errno);
+		} else if (ret != wrote) {
+			printf("Short splice: %d < %d\n", ret, wrote);
+		}
+
+		iov.iov_len -= wrote;
+		iov.iov_base += wrote;
+	}
+
+reread:
+	ret = recv(sock, buf, digest_len, 0);
+	if (ret == 0) {
+		printf("No digest returned\n");
+		return false;
+	}
+	if (ret != digest_len) {
+		if (errno == -EAGAIN)
+			goto reread;
+		printf("Failed to get digest: %s (%d)\n",
+		       strerror(errno), errno);
+		return false;
+	}
+
+	return true;
+}
+
+int main(void)
+{
+	char *data;
+	struct sigaction sa;
+	int ret;
+
+	/* Ensure we have unbuffered output */
+	setvbuf(stdout, NULL, _IOLBF, 0);
+
+	/* The parent will communicate with us via signals */
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handle_exit_signal;
+	sa.sa_flags = SA_RESTART | SA_SIGINFO;
+	sigemptyset(&sa.sa_mask);
+	ret = sigaction(SIGTERM, &sa, NULL);
+	if (ret < 0)
+		printf("Failed to install SIGTERM handler: %s (%d)\n",
+		       strerror(errno), errno);
+
+	sa.sa_sigaction = handle_kick_signal;
+	ret = sigaction(SIGUSR1, &sa, NULL);
+	if (ret < 0)
+		printf("Failed to install SIGUSR1 handler: %s (%d)\n",
+		       strerror(errno), errno);
+	ret = sigaction(SIGUSR2, &sa, NULL);
+	if (ret < 0)
+		printf("Failed to install SIGUSR2 handler: %s (%d)\n",
+		       strerror(errno), errno);
+
+	data = malloc(DATA_SIZE);
+	if (!data) {
+		printf("Failed to allocate data buffer\n");
+		return EXIT_FAILURE;
+	}
+	memset(data, 0, DATA_SIZE);
+
+	data_iov.iov_base = data;
+	data_iov.iov_len = DATA_SIZE;
+
+	/*
+	 * If we can't create a socket assume it's a lack of system
+	 * support and fall back to a basic FPSIMD test for the
+	 * benefit of fp-stress.
+	 */
+	if (!create_socket()) {
+		execl("./fpsimd-test", "./fpsimd-test", NULL);
+		printf("Failed to fall back to fspimd-test: %d (%s)\n",
+			errno, strerror(errno));
+		return EXIT_FAILURE;
+	}
+
+	/*
+	 * Compute a reference digest we hope is repeatable, we do
+	 * this at runtime partly to make it easier to play with
+	 * parameters.
+	 */
+	if (!compute_digest(ref)) {
+		printf("Failed to compute reference digest\n");
+		return EXIT_FAILURE;
+	}
+
+	printf("AF_ALG using %s\n", alg_name);
+
+	while (true) {
+		if (!compute_digest(digest)) {
+			printf("Failed to compute digest, iter=%d\n", iter);
+			return EXIT_FAILURE;
+		}
+
+		if (memcmp(ref, digest, digest_len) != 0) {
+			printf("Digest mismatch, iter=%d\n", iter);
+			return EXIT_FAILURE;
+		}
+
+		iter++;
+	}
+
+	return EXIT_FAILURE;
+}
diff --git a/tools/testing/selftests/arm64/fp/sme-inst.h b/tools/testing/selftests/arm64/fp/sme-inst.h
index 7191e53ca1c0..85b9184e0835 100644
--- a/tools/testing/selftests/arm64/fp/sme-inst.h
+++ b/tools/testing/selftests/arm64/fp/sme-inst.h
@@ -5,6 +5,8 @@
 #ifndef SME_INST_H
 #define SME_INST_H
 
+#define REG_FPMR                                        S3_3_C4_C4_2
+
 /*
  * RDSVL X\nx, #\imm
  */
@@ -48,4 +50,24 @@
 		| ((\offset) & 7)
 .endm
 
+/*
+ * LDR (ZT0)
+ *
+ *	LDR ZT0, nx
+ */
+.macro _ldr_zt nx
+	.inst	0xe11f8000			\
+		| (((\nx) & 0x1f) << 5)
+.endm
+
+/*
+ * STR (ZT0)
+ *
+ *	STR ZT0, nx
+ */
+.macro _str_zt nx
+	.inst	0xe13f8000			\
+		| (((\nx) & 0x1f) << 5)
+.endm
+
 #endif
diff --git a/tools/testing/selftests/arm64/fp/sve-probe-vls.c b/tools/testing/selftests/arm64/fp/sve-probe-vls.c
index a24eca7a4ecb..df0c1b6eb114 100644
--- a/tools/testing/selftests/arm64/fp/sve-probe-vls.c
+++ b/tools/testing/selftests/arm64/fp/sve-probe-vls.c
@@ -12,7 +12,7 @@
 #include <sys/prctl.h>
 #include <asm/sigcontext.h>
 
-#include "../../kselftest.h"
+#include "kselftest.h"
 #include "rdvl.h"
 
 int main(int argc, char **argv)
diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c
index 8c4847977583..28f6b996c5e2 100644
--- a/tools/testing/selftests/arm64/fp/sve-ptrace.c
+++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c
@@ -19,7 +19,7 @@
 #include <asm/sigcontext.h>
 #include <asm/ptrace.h>
 
-#include "../../kselftest.h"
+#include "kselftest.h"
 
 /* <linux/elf.h> and <sys/auxv.h> don't like each other, so: */
 #ifndef NT_ARM_SVE
@@ -30,6 +30,16 @@
 #define NT_ARM_SSVE 0x40b
 #endif
 
+/*
+ * The architecture defines the maximum VQ as 16 but for extensibility
+ * the kernel specifies the SVE_VQ_MAX as 512 resulting in us running
+ * a *lot* more tests than are useful if we use it.  Until the
+ * architecture is extended let's limit our coverage to what is
+ * currently allowed, plus one extra to ensure we cover constraining
+ * the VL as expected.
+ */
+#define TEST_VQ_MAX 17
+
 struct vec_type {
 	const char *name;
 	unsigned long hwcap_type;
@@ -55,8 +65,8 @@ static const struct vec_type vec_types[] = {
 	},
 };
 
-#define VL_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 4)
-#define FLAG_TESTS 2
+#define VL_TESTS (((TEST_VQ_MAX - SVE_VQ_MIN) + 1) * 4)
+#define FLAG_TESTS 4
 #define FPSIMD_TESTS 2
 
 #define EXPECTED_TESTS ((VL_TESTS + FLAG_TESTS + FPSIMD_TESTS) * ARRAY_SIZE(vec_types))
@@ -72,10 +82,12 @@ static void fill_buf(char *buf, size_t size)
 static int do_child(void)
 {
 	if (ptrace(PTRACE_TRACEME, -1, NULL, NULL))
-		ksft_exit_fail_msg("PTRACE_TRACEME", strerror(errno));
+		ksft_exit_fail_msg("ptrace(PTRACE_TRACEME) failed: %s (%d)\n",
+				   strerror(errno), errno);
 
 	if (raise(SIGSTOP))
-		ksft_exit_fail_msg("raise(SIGSTOP)", strerror(errno));
+		ksft_exit_fail_msg("raise(SIGSTOP) failed: %s (%d)\n",
+				   strerror(errno), errno);
 
 	return EXIT_SUCCESS;
 }
@@ -83,19 +95,27 @@ static int do_child(void)
 static int get_fpsimd(pid_t pid, struct user_fpsimd_state *fpsimd)
 {
 	struct iovec iov;
+	int ret;
 
 	iov.iov_base = fpsimd;
 	iov.iov_len = sizeof(*fpsimd);
-	return ptrace(PTRACE_GETREGSET, pid, NT_PRFPREG, &iov);
+	ret = ptrace(PTRACE_GETREGSET, pid, NT_PRFPREG, &iov);
+	if (ret == -1)
+		ksft_perror("ptrace(PTRACE_GETREGSET)");
+	return ret;
 }
 
 static int set_fpsimd(pid_t pid, struct user_fpsimd_state *fpsimd)
 {
 	struct iovec iov;
+	int ret;
 
 	iov.iov_base = fpsimd;
 	iov.iov_len = sizeof(*fpsimd);
-	return ptrace(PTRACE_SETREGSET, pid, NT_PRFPREG, &iov);
+	ret = ptrace(PTRACE_SETREGSET, pid, NT_PRFPREG, &iov);
+	if (ret == -1)
+		ksft_perror("ptrace(PTRACE_SETREGSET)");
+	return ret;
 }
 
 static struct user_sve_header *get_sve(pid_t pid, const struct vec_type *type,
@@ -103,8 +123,9 @@ static struct user_sve_header *get_sve(pid_t pid, const struct vec_type *type,
 {
 	struct user_sve_header *sve;
 	void *p;
-	size_t sz = sizeof *sve;
+	size_t sz = sizeof(*sve);
 	struct iovec iov;
+	int ret;
 
 	while (1) {
 		if (*size < sz) {
@@ -120,8 +141,11 @@ static struct user_sve_header *get_sve(pid_t pid, const struct vec_type *type,
 
 		iov.iov_base = *buf;
 		iov.iov_len = sz;
-		if (ptrace(PTRACE_GETREGSET, pid, type->regset, &iov))
+		ret = ptrace(PTRACE_GETREGSET, pid, type->regset, &iov);
+		if (ret) {
+			ksft_perror("ptrace(PTRACE_GETREGSET)");
 			goto error;
+		}
 
 		sve = *buf;
 		if (sve->size <= sz)
@@ -140,10 +164,46 @@ static int set_sve(pid_t pid, const struct vec_type *type,
 		   const struct user_sve_header *sve)
 {
 	struct iovec iov;
+	int ret;
 
 	iov.iov_base = (void *)sve;
 	iov.iov_len = sve->size;
-	return ptrace(PTRACE_SETREGSET, pid, type->regset, &iov);
+	ret = ptrace(PTRACE_SETREGSET, pid, type->regset, &iov);
+	if (ret == -1)
+		ksft_perror("ptrace(PTRACE_SETREGSET)");
+	return ret;
+}
+
+/* A read operation fails */
+static void read_fails(pid_t child, const struct vec_type *type)
+{
+	struct user_sve_header *new_sve = NULL;
+	size_t new_sve_size = 0;
+	void *ret;
+
+	ret = get_sve(child, type, (void **)&new_sve, &new_sve_size);
+
+	ksft_test_result(ret == NULL, "%s unsupported read fails\n",
+			 type->name);
+
+	free(new_sve);
+}
+
+/* A write operation fails */
+static void write_fails(pid_t child, const struct vec_type *type)
+{
+	struct user_sve_header sve;
+	int ret;
+
+	/* Just the header, no data */
+	memset(&sve, 0, sizeof(sve));
+	sve.size = sizeof(sve);
+	sve.flags = SVE_PT_REGS_SVE;
+	sve.vl = SVE_VL_MIN;
+	ret = set_sve(child, type, &sve);
+
+	ksft_test_result(ret != 0, "%s unsupported write fails\n",
+			 type->name);
 }
 
 /* Validate setting and getting the inherit flag */
@@ -158,7 +218,7 @@ static void ptrace_set_get_inherit(pid_t child, const struct vec_type *type)
 	memset(&sve, 0, sizeof(sve));
 	sve.size = sizeof(sve);
 	sve.vl = sve_vl_from_vq(SVE_VQ_MIN);
-	sve.flags = SVE_PT_VL_INHERIT;
+	sve.flags = SVE_PT_VL_INHERIT | SVE_PT_REGS_SVE;
 	ret = set_sve(child, type, &sve);
 	if (ret != 0) {
 		ksft_test_result_fail("Failed to set %s SVE_PT_VL_INHERIT\n",
@@ -223,6 +283,7 @@ static void ptrace_set_get_vl(pid_t child, const struct vec_type *type,
 	/* Set the VL by doing a set with no register payload */
 	memset(&sve, 0, sizeof(sve));
 	sve.size = sizeof(sve);
+	sve.flags = SVE_PT_REGS_SVE;
 	sve.vl = vl;
 	ret = set_sve(child, type, &sve);
 	if (ret != 0) {
@@ -241,7 +302,7 @@ static void ptrace_set_get_vl(pid_t child, const struct vec_type *type,
 		return;
 	}
 
-	ksft_test_result(new_sve->vl = prctl_vl, "Set %s VL %u\n",
+	ksft_test_result(new_sve->vl == prctl_vl, "Set %s VL %u\n",
 			 type->name, vl);
 
 	free(new_sve);
@@ -257,6 +318,25 @@ static void check_u32(unsigned int vl, const char *reg,
 	}
 }
 
+/* Set out of range VLs */
+static void ptrace_set_vl_ranges(pid_t child, const struct vec_type *type)
+{
+	struct user_sve_header sve;
+	int ret;
+
+	memset(&sve, 0, sizeof(sve));
+	sve.flags = SVE_PT_REGS_SVE;
+	sve.size = sizeof(sve);
+
+	ret = set_sve(child, type, &sve);
+	ksft_test_result(ret != 0, "%s Set invalid VL 0\n", type->name);
+
+	sve.vl = SVE_VL_MAX + SVE_VQ_BYTES;
+	ret = set_sve(child, type, &sve);
+	ksft_test_result(ret != 0, "%s Set invalid VL %d\n", type->name,
+			 SVE_VL_MAX + SVE_VQ_BYTES);
+}
+
 /* Access the FPSIMD registers via the SVE regset */
 static void ptrace_sve_fpsimd(pid_t child, const struct vec_type *type)
 {
@@ -289,8 +369,10 @@ static void ptrace_sve_fpsimd(pid_t child, const struct vec_type *type)
 			p[j] = j;
 	}
 
+	/* This should only succeed for SVE */
 	ret = set_sve(child, type, sve);
-	ksft_test_result(ret == 0, "%s FPSIMD set via SVE: %d\n",
+	ksft_test_result((type->regset == NT_ARM_SVE) == (ret == 0),
+			 "%s FPSIMD set via SVE: %d\n",
 			 type->name, ret);
 	if (ret)
 		goto out;
@@ -312,6 +394,58 @@ out:
 	free(svebuf);
 }
 
+/* Write the FPSIMD registers via the SVE regset when SVE is not supported */
+static void ptrace_sve_fpsimd_no_sve(pid_t child)
+{
+	void *svebuf;
+	struct user_sve_header *sve;
+	struct user_fpsimd_state *fpsimd, new_fpsimd;
+	unsigned int i, j;
+	unsigned char *p;
+	int ret;
+
+	svebuf = malloc(SVE_PT_SIZE(0, SVE_PT_REGS_FPSIMD));
+	if (!svebuf) {
+		ksft_test_result_fail("Failed to allocate FPSIMD buffer\n");
+		return;
+	}
+
+	/* On a system without SVE the VL should be set to 0 */
+	memset(svebuf, 0, SVE_PT_SIZE(0, SVE_PT_REGS_FPSIMD));
+	sve = svebuf;
+	sve->flags = SVE_PT_REGS_FPSIMD;
+	sve->size = SVE_PT_SIZE(0, SVE_PT_REGS_FPSIMD);
+	sve->vl = 0;
+
+	/* Try to set a known FPSIMD state via PT_REGS_SVE */
+	fpsimd = (struct user_fpsimd_state *)((char *)sve +
+					      SVE_PT_FPSIMD_OFFSET);
+	for (i = 0; i < 32; ++i) {
+		p = (unsigned char *)&fpsimd->vregs[i];
+
+		for (j = 0; j < sizeof(fpsimd->vregs[i]); ++j)
+			p[j] = j;
+	}
+
+	ret = set_sve(child, &vec_types[0], sve);
+	ksft_test_result(ret == 0, "FPSIMD write via SVE\n");
+	if (ret) {
+		ksft_test_result_skip("Verify FPSIMD write via SVE\n");
+		goto out;
+	}
+
+	/* Verify via the FPSIMD regset */
+	if (get_fpsimd(child, &new_fpsimd)) {
+		ksft_test_result_skip("Verify FPSIMD write via SVE\n");
+		goto out;
+	}
+	ksft_test_result(memcmp(fpsimd, &new_fpsimd, sizeof(*fpsimd)) == 0,
+			 "Verify FPSIMD write via SVE\n");
+
+out:
+	free(svebuf);
+}
+
 /* Validate attempting to set SVE data and read SVE data */
 static void ptrace_set_sve_get_sve_data(pid_t child,
 					const struct vec_type *type,
@@ -330,7 +464,7 @@ static void ptrace_set_sve_get_sve_data(pid_t child,
 	data_size = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE);
 	write_buf = malloc(data_size);
 	if (!write_buf) {
-		ksft_test_result_fail("Error allocating %d byte buffer for %s VL %u\n",
+		ksft_test_result_fail("Error allocating %ld byte buffer for %s VL %u\n",
 				      data_size, type->name, vl);
 		return;
 	}
@@ -431,7 +565,7 @@ static void ptrace_set_sve_get_fpsimd_data(pid_t child,
 	data_size = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE);
 	write_buf = malloc(data_size);
 	if (!write_buf) {
-		ksft_test_result_fail("Error allocating %d byte buffer for %s VL %u\n",
+		ksft_test_result_fail("Error allocating %ld byte buffer for %s VL %u\n",
 				      data_size, type->name, vl);
 		return;
 	}
@@ -535,7 +669,7 @@ static void ptrace_set_fpsimd_get_sve_data(pid_t child,
 	read_sve = read_buf;
 
 	if (read_sve->vl != vl) {
-		ksft_test_result_fail("Child VL != expected VL %d\n",
+		ksft_test_result_fail("Child VL != expected VL: %u != %u\n",
 				      read_sve->vl, vl);
 		goto out;
 	}
@@ -545,7 +679,7 @@ static void ptrace_set_fpsimd_get_sve_data(pid_t child,
 	case SVE_PT_REGS_FPSIMD:
 		expected_size = SVE_PT_FPSIMD_SIZE(vq, SVE_PT_REGS_FPSIMD);
 		if (read_sve_size < expected_size) {
-			ksft_test_result_fail("Read %d bytes, expected %d\n",
+			ksft_test_result_fail("Read %ld bytes, expected %ld\n",
 					      read_sve_size, expected_size);
 			goto out;
 		}
@@ -561,7 +695,7 @@ static void ptrace_set_fpsimd_get_sve_data(pid_t child,
 	case SVE_PT_REGS_SVE:
 		expected_size = SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE);
 		if (read_sve_size < expected_size) {
-			ksft_test_result_fail("Read %d bytes, expected %d\n",
+			ksft_test_result_fail("Read %ld bytes, expected %ld\n",
 					      read_sve_size, expected_size);
 			goto out;
 		}
@@ -668,6 +802,20 @@ static int do_parent(pid_t child)
 	}
 
 	for (i = 0; i < ARRAY_SIZE(vec_types); i++) {
+		/*
+		 * If the vector type isn't supported reads and writes
+		 * should fail.
+		 */
+		if (!(getauxval(vec_types[i].hwcap_type) & vec_types[i].hwcap)) {
+			read_fails(child, &vec_types[i]);
+			write_fails(child, &vec_types[i]);
+		} else {
+			ksft_test_result_skip("%s unsupported read fails\n",
+					      vec_types[i].name);
+			ksft_test_result_skip("%s unsupported write fails\n",
+					      vec_types[i].name);
+		}
+
 		/* FPSIMD via SVE regset */
 		if (getauxval(vec_types[i].hwcap_type) & vec_types[i].hwcap) {
 			ptrace_sve_fpsimd(child, &vec_types[i]);
@@ -688,8 +836,19 @@ static int do_parent(pid_t child)
 					      vec_types[i].name);
 		}
 
+		/* Setting out of bounds VLs should fail */
+		if (getauxval(vec_types[i].hwcap_type) & vec_types[i].hwcap) {
+			ptrace_set_vl_ranges(child, &vec_types[i]);
+		} else {
+			ksft_test_result_skip("%s Set invalid VL 0\n",
+					      vec_types[i].name);
+			ksft_test_result_skip("%s Set invalid VL %d\n",
+					      vec_types[i].name,
+					      SVE_VL_MAX + SVE_VQ_BYTES);
+		}
+
 		/* Step through every possible VQ */
-		for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) {
+		for (vq = SVE_VQ_MIN; vq <= TEST_VQ_MAX; vq++) {
 			vl = sve_vl_from_vq(vq);
 
 			/* First, try to set this vector length */
@@ -719,6 +878,15 @@ static int do_parent(pid_t child)
 		}
 	}
 
+	/* We support SVE writes of FPSMID format on SME only systems */
+	if (!(getauxval(AT_HWCAP) & HWCAP_SVE) &&
+	    (getauxval(AT_HWCAP2) & HWCAP2_SME)) {
+		ptrace_sve_fpsimd_no_sve(child);
+	} else {
+		ksft_test_result_skip("FPSIMD write via SVE\n");
+		ksft_test_result_skip("Verify FPSIMD write via SVE\n");
+	}
+
 	ret = EXIT_SUCCESS;
 
 error:
@@ -738,9 +906,6 @@ int main(void)
 	ksft_print_header();
 	ksft_set_plan(EXPECTED_TESTS);
 
-	if (!(getauxval(AT_HWCAP) & HWCAP_SVE))
-		ksft_exit_skip("SVE not available\n");
-
 	child = fork();
 	if (!child)
 		return do_child();
diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S
index 2a18cb4c528c..80e072f221cd 100644
--- a/tools/testing/selftests/arm64/fp/sve-test.S
+++ b/tools/testing/selftests/arm64/fp/sve-test.S
@@ -291,8 +291,7 @@ function check_ffr
 #endif
 endfunction
 
-// Any SVE register modified here can cause corruption in the main
-// thread -- but *only* the registers modified here.
+// Modify live register state, the signal return will undo our changes
 function irritator_handler
 	// Increment the irritation signal count (x23):
 	ldr	x0, [x2, #ucontext_regs + 8 * 23]
@@ -300,13 +299,12 @@ function irritator_handler
 	str	x0, [x2, #ucontext_regs + 8 * 23]
 
 	// Corrupt some random Z-regs
-	adr	x0, .text + (irritator_handler - .text) / 16 * 16
 	movi	v0.8b, #1
 	movi	v9.16b, #2
 	movi	v31.8b, #3
-#ifndef SSVE
 	// And P0
-	rdffr	p0.b
+	ptrue	p0.d
+#ifndef SSVE
 	// And FFR
 	wrffr	p15.b
 #endif
@@ -378,7 +376,8 @@ endfunction
 // Main program entry point
 .globl _start
 function _start
-_start:
+	enable_gcs
+
 	mov	x23, #0		// Irritation signal count
 
 	mov	w0, #SIGINT
@@ -474,6 +473,13 @@ _start:
 //	mov	x8, #__NR_sched_yield	// Encourage preemption
 //	svc	#0
 
+#ifdef SSVE
+	mrs	x0, S3_3_C4_C2_2	// SVCR should have ZA=0,SM=1
+	and	x1, x0, #3
+	cmp	x1, #1
+	b.ne	svcr_barf
+#endif
+
 	mov	x21, #0
 0:	mov	x0, x21
 	bl	check_zreg
@@ -509,6 +515,10 @@ function barf
 	mov	x11, x1	// actual data
 	mov	x12, x2	// data size
 
+#ifdef SSVE
+	mrs	x13, S3_3_C4_C2_2
+#endif
+
 	puts	"Mismatch: PID="
 	mov	x0, x20
 	bl	putdec
@@ -528,6 +538,12 @@ function barf
 	bl	dumphex
 	puts	"]\n"
 
+#ifdef SSVE
+	puts	"\tSVCR: "
+	mov	x0, x13
+	bl	putdecn
+#endif
+
 	mov	x8, #__NR_getpid
 	svc	#0
 // fpsimd.c acitivty log dump hack
@@ -554,3 +570,15 @@ function vl_barf
 	mov	x1, #1
 	svc	#0
 endfunction
+
+function svcr_barf
+	mov	x10, x0
+
+	puts	"Bad SVCR: "
+	mov	x0, x10
+	bl	putdecn
+
+	mov	x8, #__NR_exit
+	mov	x1, #1
+	svc	#0
+endfunction
diff --git a/tools/testing/selftests/arm64/fp/vec-syscfg.c b/tools/testing/selftests/arm64/fp/vec-syscfg.c
index 9bcfcdc34ee9..8dd932fdcdc4 100644
--- a/tools/testing/selftests/arm64/fp/vec-syscfg.c
+++ b/tools/testing/selftests/arm64/fp/vec-syscfg.c
@@ -6,6 +6,7 @@
 #include <assert.h>
 #include <errno.h>
 #include <fcntl.h>
+#include <stdbool.h>
 #include <stddef.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -18,7 +19,7 @@
 #include <asm/sigcontext.h>
 #include <asm/hwcap.h>
 
-#include "../../kselftest.h"
+#include "kselftest.h"
 #include "rdvl.h"
 
 #define ARCH_MIN_VL SVE_VL_MIN
@@ -39,9 +40,11 @@ struct vec_data {
 	int max_vl;
 };
 
+#define VEC_SVE 0
+#define VEC_SME 1
 
 static struct vec_data vec_data[] = {
-	{
+	[VEC_SVE] = {
 		.name = "SVE",
 		.hwcap_type = AT_HWCAP,
 		.hwcap = HWCAP_SVE,
@@ -51,7 +54,7 @@ static struct vec_data vec_data[] = {
 		.prctl_set = PR_SVE_SET_VL,
 		.default_vl_file = "/proc/sys/abi/sve_default_vector_length",
 	},
-	{
+	[VEC_SME] = {
 		.name = "SME",
 		.hwcap_type = AT_HWCAP2,
 		.hwcap = HWCAP2_SME,
@@ -63,6 +66,11 @@ static struct vec_data vec_data[] = {
 	},
 };
 
+static bool vec_type_supported(struct vec_data *data)
+{
+	return getauxval(data->hwcap_type) & data->hwcap;
+}
+
 static int stdio_read_integer(FILE *f, const char *what, int *val)
 {
 	int n = 0;
@@ -551,7 +559,8 @@ static void prctl_set_onexec(struct vec_data *data)
 /* For each VQ verify that setting via prctl() does the right thing */
 static void prctl_set_all_vqs(struct vec_data *data)
 {
-	int ret, vq, vl, new_vl;
+	int ret, vq, vl, new_vl, i;
+	int orig_vls[ARRAY_SIZE(vec_data)];
 	int errors = 0;
 
 	if (!data->min_vl || !data->max_vl) {
@@ -560,6 +569,12 @@ static void prctl_set_all_vqs(struct vec_data *data)
 		return;
 	}
 
+	for (i = 0; i < ARRAY_SIZE(vec_data); i++) {
+		if (!vec_type_supported(&vec_data[i]))
+			continue;
+		orig_vls[i] = vec_data[i].rdvl();
+	}
+
 	for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) {
 		vl = sve_vl_from_vq(vq);
 
@@ -582,6 +597,22 @@ static void prctl_set_all_vqs(struct vec_data *data)
 			errors++;
 		}
 
+		/* Did any other VLs change? */
+		for (i = 0; i < ARRAY_SIZE(vec_data); i++) {
+			if (&vec_data[i] == data)
+				continue;
+
+			if (!vec_type_supported(&vec_data[i]))
+				continue;
+
+			if (vec_data[i].rdvl() != orig_vls[i]) {
+				ksft_print_msg("%s VL changed from %d to %d\n",
+					       vec_data[i].name, orig_vls[i],
+					       vec_data[i].rdvl());
+				errors++;
+			}
+		}
+
 		/* Was that the VL we asked for? */
 		if (new_vl == vl)
 			continue;
@@ -644,18 +675,106 @@ static const test_type tests[] = {
 	prctl_set_all_vqs,
 };
 
+static inline void smstart(void)
+{
+	asm volatile("msr S0_3_C4_C7_3, xzr");
+}
+
+static inline void smstart_sm(void)
+{
+	asm volatile("msr S0_3_C4_C3_3, xzr");
+}
+
+static inline void smstop(void)
+{
+	asm volatile("msr S0_3_C4_C6_3, xzr");
+}
+
+/*
+ * Verify we can change the SVE vector length while SME is active and
+ * continue to use SME afterwards.
+ */
+static void change_sve_with_za(void)
+{
+	struct vec_data *sve_data = &vec_data[VEC_SVE];
+	bool pass = true;
+	int ret, i;
+
+	if (sve_data->min_vl == sve_data->max_vl) {
+		ksft_print_msg("Only one SVE VL supported, can't change\n");
+		ksft_test_result_skip("change_sve_while_sme\n");
+		return;
+	}
+
+	/* Ensure we will trigger a change when we set the maximum */
+	ret = prctl(sve_data->prctl_set, sve_data->min_vl);
+	if (ret != sve_data->min_vl) {
+		ksft_print_msg("Failed to set SVE VL %d: %d\n",
+			       sve_data->min_vl, ret);
+		pass = false;
+	}
+
+	/* Enable SM and ZA */
+	smstart();
+
+	/* Trigger another VL change */
+	ret = prctl(sve_data->prctl_set, sve_data->max_vl);
+	if (ret != sve_data->max_vl) {
+		ksft_print_msg("Failed to set SVE VL %d: %d\n",
+			       sve_data->max_vl, ret);
+		pass = false;
+	}
+
+	/*
+	 * Spin for a bit with SM enabled to try to trigger another
+	 * save/restore.  We can't use syscalls without exiting
+	 * streaming mode.
+	 */
+	for (i = 0; i < 100000000; i++)
+		smstart_sm();
+
+	/*
+	 * TODO: Verify that ZA was preserved over the VL change and
+	 * spin.
+	 */
+
+	/* Clean up after ourselves */
+	smstop();
+	ret = prctl(sve_data->prctl_set, sve_data->default_vl);
+	if (ret != sve_data->default_vl) {
+	        ksft_print_msg("Failed to restore SVE VL %d: %d\n",
+			       sve_data->default_vl, ret);
+		pass = false;
+	}
+
+	ksft_test_result(pass, "change_sve_with_za\n");
+}
+
+typedef void (*test_all_type)(void);
+
+static const struct {
+	const char *name;
+	test_all_type test;
+}  all_types_tests[] = {
+	{ "change_sve_with_za", change_sve_with_za },
+};
+
 int main(void)
 {
+	bool all_supported = true;
 	int i, j;
 
 	ksft_print_header();
-	ksft_set_plan(ARRAY_SIZE(tests) * ARRAY_SIZE(vec_data));
+	ksft_set_plan(ARRAY_SIZE(tests) * ARRAY_SIZE(vec_data) +
+		      ARRAY_SIZE(all_types_tests));
 
 	for (i = 0; i < ARRAY_SIZE(vec_data); i++) {
 		struct vec_data *data = &vec_data[i];
 		unsigned long supported;
 
-		supported = getauxval(data->hwcap_type) & data->hwcap;
+		supported = vec_type_supported(data);
+		if (!supported)
+			all_supported = false;
 
 		for (j = 0; j < ARRAY_SIZE(tests); j++) {
 			if (supported)
@@ -666,5 +785,12 @@ int main(void)
 		}
 	}
 
+	for (i = 0; i < ARRAY_SIZE(all_types_tests); i++) {
+		if (all_supported)
+			all_types_tests[i].test();
+		else
+			ksft_test_result_skip("%s\n", all_types_tests[i].name);
+	}
+
 	ksft_exit_pass();
 }
diff --git a/tools/testing/selftests/arm64/fp/za-fork.c b/tools/testing/selftests/arm64/fp/za-fork.c
index ff475c649e96..587b94648222 100644
--- a/tools/testing/selftests/arm64/fp/za-fork.c
+++ b/tools/testing/selftests/arm64/fp/za-fork.c
@@ -9,42 +9,9 @@
 #include <linux/sched.h>
 #include <linux/wait.h>
 
-#define EXPECTED_TESTS 1
-
-static void putstr(const char *str)
-{
-	write(1, str, strlen(str));
-}
-
-static void putnum(unsigned int num)
-{
-	char c;
-
-	if (num / 10)
-		putnum(num / 10);
-
-	c = '0' + (num % 10);
-	write(1, &c, 1);
-}
+#include "kselftest.h"
 
-static int tests_run;
-static int tests_passed;
-static int tests_failed;
-static int tests_skipped;
-
-static void print_summary(void)
-{
-	if (tests_passed + tests_failed + tests_skipped != EXPECTED_TESTS)
-		putstr("# UNEXPECTED TEST COUNT: ");
-
-	putstr("# Totals: pass:");
-	putnum(tests_passed);
-	putstr(" fail:");
-	putnum(tests_failed);
-	putstr(" xfail:0 xpass:0 skip:");
-	putnum(tests_skipped);
-	putstr(" error:0\n");
-}
+#define EXPECTED_TESTS 1
 
 int fork_test(void);
 int verify_fork(void);
@@ -63,22 +30,21 @@ int fork_test_c(void)
 	if (newpid == 0) {
 		/* In child */
 		if (!verify_fork()) {
-			putstr("# ZA state invalid in child\n");
+			ksft_print_msg("ZA state invalid in child\n");
 			exit(0);
 		} else {
 			exit(1);
 		}
 	}
 	if (newpid < 0) {
-		putstr("# fork() failed: -");
-		putnum(-newpid);
-		putstr("\n");
+		ksft_print_msg("fork() failed: %d\n", newpid);
+
 		return 0;
 	}
 
 	parent_result = verify_fork();
 	if (!parent_result)
-		putstr("# ZA state invalid in parent\n");
+		ksft_print_msg("ZA state invalid in parent\n");
 
 	for (;;) {
 		waiting = waitpid(newpid, &child_status, 0);
@@ -86,18 +52,16 @@ int fork_test_c(void)
 		if (waiting < 0) {
 			if (errno == EINTR)
 				continue;
-			putstr("# waitpid() failed: ");
-			putnum(errno);
-			putstr("\n");
+			ksft_print_msg("waitpid() failed: %d\n", errno);
 			return 0;
 		}
 		if (waiting != newpid) {
-			putstr("# waitpid() returned wrong PID\n");
+			ksft_print_msg("waitpid() returned wrong PID\n");
 			return 0;
 		}
 
 		if (!WIFEXITED(child_status)) {
-			putstr("# child did not exit\n");
+			ksft_print_msg("child did not exit\n");
 			return 0;
 		}
 
@@ -105,29 +69,14 @@ int fork_test_c(void)
 	}
 }
 
-#define run_test(name)			     \
-	if (name()) {			     \
-		tests_passed++;		     \
-	} else {			     \
-		tests_failed++;		     \
-		putstr("not ");		     \
-	}				     \
-	putstr("ok ");			     \
-	putnum(++tests_run);		     \
-	putstr(" " #name "\n");
-
 int main(int argc, char **argv)
 {
 	int ret, i;
 
-	putstr("TAP version 13\n");
-	putstr("1..");
-	putnum(EXPECTED_TESTS);
-	putstr("\n");
+	ksft_print_header();
+	ksft_set_plan(EXPECTED_TESTS);
 
-	putstr("# PID: ");
-	putnum(getpid());
-	putstr("\n");
+	ksft_print_msg("PID: %d\n", getpid());
 
 	/*
 	 * This test is run with nolibc which doesn't support hwcap and
@@ -136,21 +85,16 @@ int main(int argc, char **argv)
 	 */
 	ret = open("/proc/sys/abi/sme_default_vector_length", O_RDONLY, 0);
 	if (ret >= 0) {
-		run_test(fork_test);
+		ksft_test_result(fork_test(), "fork_test\n");
 
 	} else {
-		putstr("# SME support not present\n");
-
+		ksft_print_msg("SME not supported\n");
 		for (i = 0; i < EXPECTED_TESTS; i++) {
-			putstr("ok ");
-			putnum(i);
-			putstr(" skipped\n");
+			ksft_test_result_skip("fork_test\n");
 		}
-
-		tests_skipped += EXPECTED_TESTS;
 	}
 
-	print_summary();
+	ksft_finished();
 
 	return 0;
 }
diff --git a/tools/testing/selftests/arm64/fp/za-ptrace.c b/tools/testing/selftests/arm64/fp/za-ptrace.c
index bf6158654056..787eed22d059 100644
--- a/tools/testing/selftests/arm64/fp/za-ptrace.c
+++ b/tools/testing/selftests/arm64/fp/za-ptrace.c
@@ -18,14 +18,24 @@
 #include <asm/sigcontext.h>
 #include <asm/ptrace.h>
 
-#include "../../kselftest.h"
+#include "kselftest.h"
 
 /* <linux/elf.h> and <sys/auxv.h> don't like each other, so: */
 #ifndef NT_ARM_ZA
 #define NT_ARM_ZA 0x40c
 #endif
 
-#define EXPECTED_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 3)
+/*
+ * The architecture defines the maximum VQ as 16 but for extensibility
+ * the kernel specifies the SVE_VQ_MAX as 512 resulting in us running
+ * a *lot* more tests than are useful if we use it.  Until the
+ * architecture is extended let's limit our coverage to what is
+ * currently allowed, plus one extra to ensure we cover constraining
+ * the VL as expected.
+ */
+#define TEST_VQ_MAX 17
+
+#define EXPECTED_TESTS (((TEST_VQ_MAX - SVE_VQ_MIN) + 1) * 3)
 
 static void fill_buf(char *buf, size_t size)
 {
@@ -38,10 +48,12 @@ static void fill_buf(char *buf, size_t size)
 static int do_child(void)
 {
 	if (ptrace(PTRACE_TRACEME, -1, NULL, NULL))
-		ksft_exit_fail_msg("PTRACE_TRACEME", strerror(errno));
+		ksft_exit_fail_msg("ptrace(PTRACE_TRACEME) failed: %s (%d)",
+				   strerror(errno), errno);
 
 	if (raise(SIGSTOP))
-		ksft_exit_fail_msg("raise(SIGSTOP)", strerror(errno));
+		ksft_exit_fail_msg("raise(SIGSTOP) failed: %s (%d)\n",
+				   strerror(errno), errno);
 
 	return EXIT_SUCCESS;
 }
@@ -191,7 +203,7 @@ static void ptrace_set_get_data(pid_t child, unsigned int vl)
 	data_size = ZA_PT_SIZE(vq);
 	write_buf = malloc(data_size);
 	if (!write_buf) {
-		ksft_test_result_fail("Error allocating %d byte buffer for VL %u\n",
+		ksft_test_result_fail("Error allocating %ld byte buffer for VL %u\n",
 				      data_size, vl);
 		return;
 	}
@@ -301,7 +313,7 @@ static int do_parent(pid_t child)
 	ksft_print_msg("Parent is %d, child is %d\n", getpid(), child);
 
 	/* Step through every possible VQ */
-	for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) {
+	for (vq = SVE_VQ_MIN; vq <= TEST_VQ_MAX; vq++) {
 		vl = sve_vl_from_vq(vq);
 
 		/* First, try to set this vector length */
diff --git a/tools/testing/selftests/arm64/fp/za-test.S b/tools/testing/selftests/arm64/fp/za-test.S
index 53c54af65704..9c33e13e9dc4 100644
--- a/tools/testing/selftests/arm64/fp/za-test.S
+++ b/tools/testing/selftests/arm64/fp/za-test.S
@@ -148,21 +148,16 @@ function check_za
 	b	memcmp
 endfunction
 
-// Any SME register modified here can cause corruption in the main
-// thread -- but *only* the locations modified here.
+// Modify the live SME register state, signal return will undo our changes
 function irritator_handler
 	// Increment the irritation signal count (x23):
 	ldr	x0, [x2, #ucontext_regs + 8 * 23]
 	add	x0, x0, #1
 	str	x0, [x2, #ucontext_regs + 8 * 23]
 
-	// Corrupt some random ZA data
-#if 0
-	adr	x0, .text + (irritator_handler - .text) / 16 * 16
-	movi	v0.8b, #1
-	movi	v9.16b, #2
-	movi	v31.8b, #3
-#endif
+	// This will reset ZA to all bits 0
+	smstop
+	smstart_za
 
 	ret
 endfunction
@@ -231,7 +226,8 @@ endfunction
 // Main program entry point
 .globl _start
 function _start
-_start:
+	enable_gcs
+
 	mov	x23, #0		// signal count
 
 	mov	w0, #SIGINT
@@ -334,6 +330,9 @@ function barf
 //	mov	w8, #__NR_exit
 //	svc	#0
 // end hack
+
+	mrs	x13, S3_3_C4_C2_2
+
 	smstop
 	mov	x10, x0	// expected data
 	mov	x11, x1	// actual data
@@ -357,6 +356,9 @@ function barf
 	mov	x1, x12
 	bl	dumphex
 	puts	"]\n"
+	puts	"\tSVCR: "
+	mov	x0, x13
+	bl	putdecn
 
 	mov	x8, #__NR_getpid
 	svc	#0
diff --git a/tools/testing/selftests/arm64/fp/zt-ptrace.c b/tools/testing/selftests/arm64/fp/zt-ptrace.c
new file mode 100644
index 000000000000..f3fa49fd0fbd
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/zt-ptrace.c
@@ -0,0 +1,366 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021 ARM Limited.
+ */
+#include <errno.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/auxv.h>
+#include <sys/prctl.h>
+#include <sys/ptrace.h>
+#include <sys/types.h>
+#include <sys/uio.h>
+#include <sys/wait.h>
+#include <asm/sigcontext.h>
+#include <asm/ptrace.h>
+
+#include "kselftest.h"
+
+/* <linux/elf.h> and <sys/auxv.h> don't like each other, so: */
+#ifndef NT_ARM_ZA
+#define NT_ARM_ZA 0x40c
+#endif
+#ifndef NT_ARM_ZT
+#define NT_ARM_ZT 0x40d
+#endif
+
+#define EXPECTED_TESTS 3
+
+static int sme_vl;
+
+static void fill_buf(char *buf, size_t size)
+{
+	int i;
+
+	for (i = 0; i < size; i++)
+		buf[i] = random();
+}
+
+static int do_child(void)
+{
+	if (ptrace(PTRACE_TRACEME, -1, NULL, NULL))
+		ksft_exit_fail_msg("ptrace(PTRACE_TRACEME) failed: %s (%d)\n",
+				   strerror(errno), errno);
+
+	if (raise(SIGSTOP))
+		ksft_exit_fail_msg("raise(SIGSTOP) failed: %s (%d)\n",
+				   strerror(errno), errno);
+
+	return EXIT_SUCCESS;
+}
+
+static struct user_za_header *get_za(pid_t pid, void **buf, size_t *size)
+{
+	struct user_za_header *za;
+	void *p;
+	size_t sz = sizeof(*za);
+	struct iovec iov;
+
+	while (1) {
+		if (*size < sz) {
+			p = realloc(*buf, sz);
+			if (!p) {
+				errno = ENOMEM;
+				goto error;
+			}
+
+			*buf = p;
+			*size = sz;
+		}
+
+		iov.iov_base = *buf;
+		iov.iov_len = sz;
+		if (ptrace(PTRACE_GETREGSET, pid, NT_ARM_ZA, &iov))
+			goto error;
+
+		za = *buf;
+		if (za->size <= sz)
+			break;
+
+		sz = za->size;
+	}
+
+	return za;
+
+error:
+	return NULL;
+}
+
+static int set_za(pid_t pid, const struct user_za_header *za)
+{
+	struct iovec iov;
+
+	iov.iov_base = (void *)za;
+	iov.iov_len = za->size;
+	return ptrace(PTRACE_SETREGSET, pid, NT_ARM_ZA, &iov);
+}
+
+static int get_zt(pid_t pid, char zt[ZT_SIG_REG_BYTES])
+{
+	struct iovec iov;
+
+	iov.iov_base = zt;
+	iov.iov_len = ZT_SIG_REG_BYTES;
+	return ptrace(PTRACE_GETREGSET, pid, NT_ARM_ZT, &iov);
+}
+
+static int set_zt(pid_t pid, const char zt[ZT_SIG_REG_BYTES])
+{
+	struct iovec iov;
+
+	iov.iov_base = (void *)zt;
+	iov.iov_len = ZT_SIG_REG_BYTES;
+	return ptrace(PTRACE_SETREGSET, pid, NT_ARM_ZT, &iov);
+}
+
+/* Reading with ZA disabled returns all zeros */
+static void ptrace_za_disabled_read_zt(pid_t child)
+{
+	struct user_za_header za;
+	char zt[ZT_SIG_REG_BYTES];
+	int ret, i;
+	bool fail = false;
+
+	/* Disable PSTATE.ZA using the ZA interface */
+	memset(&za, 0, sizeof(za));
+	za.vl = sme_vl;
+	za.size = sizeof(za);
+
+	ret = set_za(child, &za);
+	if (ret != 0) {
+		ksft_print_msg("Failed to disable ZA\n");
+		fail = true;
+	}
+
+	/* Read back ZT */
+	ret = get_zt(child, zt);
+	if (ret != 0) {
+		ksft_print_msg("Failed to read ZT\n");
+		fail = true;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(zt); i++) {
+		if (zt[i]) {
+			ksft_print_msg("zt[%d]: 0x%x != 0\n", i, zt[i]);
+			fail = true;
+		}
+	}
+
+	ksft_test_result(!fail, "ptrace_za_disabled_read_zt\n");
+}
+
+/* Writing then reading ZT should return the data written */
+static void ptrace_set_get_zt(pid_t child)
+{
+	char zt_in[ZT_SIG_REG_BYTES];
+	char zt_out[ZT_SIG_REG_BYTES];
+	int ret, i;
+	bool fail = false;
+
+	fill_buf(zt_in, sizeof(zt_in));
+
+	ret = set_zt(child, zt_in);
+	if (ret != 0) {
+		ksft_print_msg("Failed to set ZT\n");
+		fail = true;
+	}
+
+	ret = get_zt(child, zt_out);
+	if (ret != 0) {
+		ksft_print_msg("Failed to read ZT\n");
+		fail = true;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(zt_in); i++) {
+		if (zt_in[i] != zt_out[i]) {
+			ksft_print_msg("zt[%d]: 0x%x != 0x%x\n", i, 
+				       zt_in[i], zt_out[i]);
+			fail = true;
+		}
+	}
+
+	ksft_test_result(!fail, "ptrace_set_get_zt\n");
+}
+
+/* Writing ZT should set PSTATE.ZA */
+static void ptrace_enable_za_via_zt(pid_t child)
+{
+	struct user_za_header za_in;
+	struct user_za_header *za_out;
+	char zt[ZT_SIG_REG_BYTES];
+	char *za_data;
+	size_t za_out_size;
+	int ret, i, vq;
+	bool fail = false;
+
+	/* Disable PSTATE.ZA using the ZA interface */
+	memset(&za_in, 0, sizeof(za_in));
+	za_in.vl = sme_vl;
+	za_in.size = sizeof(za_in);
+
+	ret = set_za(child, &za_in);
+	if (ret != 0) {
+		ksft_print_msg("Failed to disable ZA\n");
+		fail = true;
+	}
+
+	/* Write ZT */
+	fill_buf(zt, sizeof(zt));
+	ret = set_zt(child, zt);
+	if (ret != 0) {
+		ksft_print_msg("Failed to set ZT\n");
+		fail = true;
+	}
+
+	/* Read back ZA and check for register data */
+	za_out = NULL;
+	za_out_size = 0;
+	if (get_za(child, (void **)&za_out, &za_out_size)) {
+		/* Should have an unchanged VL */
+		if (za_out->vl != sme_vl) {
+			ksft_print_msg("VL changed from %d to %d\n",
+				       sme_vl, za_out->vl);
+			fail = true;
+		}
+		vq = __sve_vq_from_vl(za_out->vl);
+		za_data = (char *)za_out + ZA_PT_ZA_OFFSET;
+
+		/* Should have register data */
+		if (za_out->size < ZA_PT_SIZE(vq)) {
+			ksft_print_msg("ZA data less than expected: %u < %u\n",
+				       za_out->size, (unsigned int)ZA_PT_SIZE(vq));
+			fail = true;
+			vq = 0;
+		}
+
+		/* That register data should be non-zero */
+		for (i = 0; i < ZA_PT_ZA_SIZE(vq); i++) {
+			if (za_data[i]) {
+				ksft_print_msg("ZA byte %d is %x\n",
+					       i, za_data[i]);
+				fail = true;
+			}
+		}
+	} else {
+		ksft_print_msg("Failed to read ZA\n");
+		fail = true;
+	}
+
+	ksft_test_result(!fail, "ptrace_enable_za_via_zt\n");
+}
+
+static int do_parent(pid_t child)
+{
+	int ret = EXIT_FAILURE;
+	pid_t pid;
+	int status;
+	siginfo_t si;
+
+	/* Attach to the child */
+	while (1) {
+		int sig;
+
+		pid = wait(&status);
+		if (pid == -1) {
+			perror("wait");
+			goto error;
+		}
+
+		/*
+		 * This should never happen but it's hard to flag in
+		 * the framework.
+		 */
+		if (pid != child)
+			continue;
+
+		if (WIFEXITED(status) || WIFSIGNALED(status))
+			ksft_exit_fail_msg("Child died unexpectedly\n");
+
+		if (!WIFSTOPPED(status))
+			goto error;
+
+		sig = WSTOPSIG(status);
+
+		if (ptrace(PTRACE_GETSIGINFO, pid, NULL, &si)) {
+			if (errno == ESRCH)
+				goto disappeared;
+
+			if (errno == EINVAL) {
+				sig = 0; /* bust group-stop */
+				goto cont;
+			}
+
+			ksft_test_result_fail("PTRACE_GETSIGINFO: %s\n",
+					      strerror(errno));
+			goto error;
+		}
+
+		if (sig == SIGSTOP && si.si_code == SI_TKILL &&
+		    si.si_pid == pid)
+			break;
+
+	cont:
+		if (ptrace(PTRACE_CONT, pid, NULL, sig)) {
+			if (errno == ESRCH)
+				goto disappeared;
+
+			ksft_test_result_fail("PTRACE_CONT: %s\n",
+					      strerror(errno));
+			goto error;
+		}
+	}
+
+	ksft_print_msg("Parent is %d, child is %d\n", getpid(), child);
+
+	ptrace_za_disabled_read_zt(child);
+	ptrace_set_get_zt(child);
+	ptrace_enable_za_via_zt(child);
+
+	ret = EXIT_SUCCESS;
+
+error:
+	kill(child, SIGKILL);
+
+disappeared:
+	return ret;
+}
+
+int main(void)
+{
+	int ret = EXIT_SUCCESS;
+	pid_t child;
+
+	srandom(getpid());
+
+	ksft_print_header();
+
+	if (!(getauxval(AT_HWCAP2) & HWCAP2_SME2)) {
+		ksft_set_plan(1);
+		ksft_exit_skip("SME2 not available\n");
+	}
+
+	/* We need a valid SME VL to enable/disable ZA */
+	sme_vl = prctl(PR_SME_GET_VL);
+	if (sme_vl == -1) {
+		ksft_set_plan(1);
+		ksft_exit_skip("Failed to read SME VL: %d (%s)\n",
+			       errno, strerror(errno));
+	}
+
+	ksft_set_plan(EXPECTED_TESTS);
+
+	child = fork();
+	if (!child)
+		return do_child();
+
+	if (do_parent(child))
+		ret = EXIT_FAILURE;
+
+	ksft_print_cnts();
+
+	return ret;
+}
diff --git a/tools/testing/selftests/arm64/fp/zt-test.S b/tools/testing/selftests/arm64/fp/zt-test.S
new file mode 100644
index 000000000000..a8df05771670
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/zt-test.S
@@ -0,0 +1,318 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2021-2 ARM Limited.
+// Original author: Mark Brown <broonie@kernel.org>
+//
+// Scalable Matrix Extension ZT context switch test
+// Repeatedly writes unique test patterns into ZT0
+// and reads them back to verify integrity.
+
+#include <asm/unistd.h>
+#include "assembler.h"
+#include "asm-offsets.h"
+#include "sme-inst.h"
+
+.arch_extension sve
+
+#define ZT_SZ	512
+#define ZT_B	(ZT_SZ / 8)
+
+// Declare some storage space to shadow ZT register contents and a
+// scratch buffer.
+.pushsection .text
+.data
+.align 4
+ztref:
+	.space	ZT_B
+scratch:
+	.space	ZT_B
+.popsection
+
+
+// Generate a test pattern for storage in ZT
+// x0: pid
+// x1: generation
+
+// These values are used to construct a 32-bit pattern that is repeated in the
+// scratch buffer as many times as will fit:
+// bits 31:24	generation number (increments once per test_loop)
+// bits 23: 8	pid
+// bits  7: 0	32-bit lane index
+
+function pattern
+	mov	w3, wzr
+	bfi	w3, w0, #8, #16		// PID
+	bfi	w3, w1, #24, #8		// Generation
+
+	ldr	x0, =scratch
+	mov	w1, #ZT_B / 4
+
+0:	str	w3, [x0], #4
+	add	w3, w3, #1		// Lane
+	subs	w1, w1, #1
+	b.ne	0b
+
+	ret
+endfunction
+
+// Set up test pattern in a ZT horizontal vector
+// x0: pid
+// x1: generation
+function setup_zt
+	mov	x4, x30
+
+	bl	pattern			// Get pattern in scratch buffer
+	ldr	x0, =ztref
+	ldr	x1, =scratch
+	mov	x2, #ZT_B
+	bl	memcpy
+
+	ldr	x0, =ztref
+	_ldr_zt 0			// load zt0 from pointer x0
+
+	ret	x4
+endfunction
+
+// Trivial memory compare: compare x2 bytes starting at address x0 with
+// bytes starting at address x1.
+// Returns only if all bytes match; otherwise, the program is aborted.
+// Clobbers x0-x5.
+function memcmp
+	cbz	x2, 2f
+
+	stp	x0, x1, [sp, #-0x20]!
+	str	x2, [sp, #0x10]
+
+	mov	x5, #0
+0:	ldrb	w3, [x0, x5]
+	ldrb	w4, [x1, x5]
+	add	x5, x5, #1
+	cmp	w3, w4
+	b.ne	1f
+	subs	x2, x2, #1
+	b.ne	0b
+
+1:	ldr	x2, [sp, #0x10]
+	ldp	x0, x1, [sp], #0x20
+	b.ne	barf
+
+2:	ret
+endfunction
+
+// Verify that a ZT vector matches its shadow in memory, else abort
+// Clobbers x0-x3
+function check_zt
+	mov	x3, x30
+
+	ldr	x0, =scratch		// Poison scratch
+	mov	x1, #ZT_B
+	bl	memfill_ae
+
+	ldr	x0, =scratch
+	_str_zt 0
+
+	ldr	x0, =ztref
+	ldr	x1, =scratch
+	mov	x2, #ZT_B
+	mov	x30, x3
+	b	memcmp
+endfunction
+
+// Modify the live SME register state, signal return will undo our changes
+function irritator_handler
+	// Increment the irritation signal count (x23):
+	ldr	x0, [x2, #ucontext_regs + 8 * 23]
+	add	x0, x0, #1
+	str	x0, [x2, #ucontext_regs + 8 * 23]
+
+	// This will reset ZT to all bits 0
+	smstop
+	smstart_za
+
+	ret
+endfunction
+
+function tickle_handler
+	// Increment the signal count (x23):
+	ldr	x0, [x2, #ucontext_regs + 8 * 23]
+	add	x0, x0, #1
+	str	x0, [x2, #ucontext_regs + 8 * 23]
+
+	ret
+endfunction
+
+function terminate_handler
+	mov	w21, w0
+	mov	x20, x2
+
+	puts	"Terminated by signal "
+	mov	w0, w21
+	bl	putdec
+	puts	", no error, iterations="
+	ldr	x0, [x20, #ucontext_regs + 8 * 22]
+	bl	putdec
+	puts	", signals="
+	ldr	x0, [x20, #ucontext_regs + 8 * 23]
+	bl	putdecn
+
+	mov	x0, #0
+	mov	x8, #__NR_exit
+	svc	#0
+endfunction
+
+// w0: signal number
+// x1: sa_action
+// w2: sa_flags
+// Clobbers x0-x6,x8
+function setsignal
+	str	x30, [sp, #-((sa_sz + 15) / 16 * 16 + 16)]!
+
+	mov	w4, w0
+	mov	x5, x1
+	mov	w6, w2
+
+	add	x0, sp, #16
+	mov	x1, #sa_sz
+	bl	memclr
+
+	mov	w0, w4
+	add	x1, sp, #16
+	str	w6, [x1, #sa_flags]
+	str	x5, [x1, #sa_handler]
+	mov	x2, #0
+	mov	x3, #sa_mask_sz
+	mov	x8, #__NR_rt_sigaction
+	svc	#0
+
+	cbz	w0, 1f
+
+	puts	"sigaction failure\n"
+	b	.Labort
+
+1:	ldr	x30, [sp], #((sa_sz + 15) / 16 * 16 + 16)
+	ret
+endfunction
+
+// Main program entry point
+.globl _start
+function _start
+	enable_gcs
+
+	mov	x23, #0		// signal count
+
+	mov	w0, #SIGINT
+	adr	x1, terminate_handler
+	mov	w2, #SA_SIGINFO
+	bl	setsignal
+
+	mov	w0, #SIGTERM
+	adr	x1, terminate_handler
+	mov	w2, #SA_SIGINFO
+	bl	setsignal
+
+	mov	w0, #SIGUSR1
+	adr	x1, irritator_handler
+	mov	w2, #SA_SIGINFO
+	orr	w2, w2, #SA_NODEFER
+	bl	setsignal
+
+	mov	w0, #SIGUSR2
+	adr	x1, tickle_handler
+	mov	w2, #SA_SIGINFO
+	orr	w2, w2, #SA_NODEFER
+	bl	setsignal
+
+	smstart_za
+
+	// Obtain our PID, to ensure test pattern uniqueness between processes
+	mov	x8, #__NR_getpid
+	svc	#0
+	mov	x20, x0
+
+	puts	"PID:\t"
+	mov	x0, x20
+	bl	putdecn
+
+	mov	x22, #0		// generation number, increments per iteration
+.Ltest_loop:
+	mov	x0, x20
+	mov	x1, x22
+	bl	setup_zt
+
+	mov	x8, #__NR_sched_yield	// Encourage preemption
+	svc	#0
+
+	mrs	x0, S3_3_C4_C2_2	// SVCR should have ZA=1,SM=0
+	and	x1, x0, #3
+	cmp	x1, #2
+	b.ne	svcr_barf
+
+	bl	check_zt
+
+	add	x22, x22, #1	// Everything still working
+	b	.Ltest_loop
+
+.Labort:
+	mov	x0, #0
+	mov	x1, #SIGABRT
+	mov	x8, #__NR_kill
+	svc	#0
+endfunction
+
+function barf
+// fpsimd.c acitivty log dump hack
+//	ldr	w0, =0xdeadc0de
+//	mov	w8, #__NR_exit
+//	svc	#0
+// end hack
+
+	mrs	x13, S3_3_C4_C2_2
+	smstop
+	mov	x10, x0	// expected data
+	mov	x11, x1	// actual data
+	mov	x12, x2	// data size
+
+	puts	"Mismatch: PID="
+	mov	x0, x20
+	bl	putdec
+	puts	", iteration="
+	mov	x0, x22
+	bl	putdecn
+	puts	"\tExpected ["
+	mov	x0, x10
+	mov	x1, x12
+	bl	dumphex
+	puts	"]\n\tGot      ["
+	mov	x0, x11
+	mov	x1, x12
+	bl	dumphex
+	puts	"]\n"
+	puts	"\tSVCR: "
+	mov	x0, x13
+	bl	putdecn
+
+	mov	x8, #__NR_getpid
+	svc	#0
+// fpsimd.c acitivty log dump hack
+//	ldr	w0, =0xdeadc0de
+//	mov	w8, #__NR_exit
+//	svc	#0
+// ^ end of hack
+	mov	x1, #SIGABRT
+	mov	x8, #__NR_kill
+	svc	#0
+//	mov	x8, #__NR_exit
+//	mov	x1, #1
+//	svc	#0
+endfunction
+
+function svcr_barf
+	mov	x10, x0
+
+	puts	"Bad SVCR: "
+	mov	x0, x10
+	bl	putdecn
+
+	mov	x8, #__NR_exit
+	mov	x1, #1
+	svc	#0
+endfunction
diff --git a/tools/testing/selftests/arm64/gcs/.gitignore b/tools/testing/selftests/arm64/gcs/.gitignore
new file mode 100644
index 000000000000..bbb8e40a7e52
--- /dev/null
+++ b/tools/testing/selftests/arm64/gcs/.gitignore
@@ -0,0 +1,7 @@
+basic-gcs
+libc-gcs
+gcs-locking
+gcs-stress
+gcs-stress-thread
+gcspushm
+gcsstr
diff --git a/tools/testing/selftests/arm64/gcs/Makefile b/tools/testing/selftests/arm64/gcs/Makefile
new file mode 100644
index 000000000000..1fbbf0ca1f02
--- /dev/null
+++ b/tools/testing/selftests/arm64/gcs/Makefile
@@ -0,0 +1,30 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2023 ARM Limited
+#
+# In order to avoid interaction with the toolchain and dynamic linker the
+# portions of these tests that interact with the GCS are implemented using
+# nolibc.
+#
+
+TEST_GEN_PROGS := basic-gcs libc-gcs gcs-locking gcs-stress gcspushm gcsstr
+TEST_GEN_PROGS_EXTENDED := gcs-stress-thread
+
+LDLIBS+=-lpthread
+
+include ../../lib.mk
+
+$(OUTPUT)/basic-gcs: basic-gcs.c
+	$(CC) $(CFLAGS) -fno-asynchronous-unwind-tables -fno-ident -s -nostdlib -nostdinc \
+		-static -I../../../../include/nolibc -include ../../../../include/nolibc/nolibc.h \
+		-I../../../../../usr/include \
+		-std=gnu99 -I../.. -g \
+		-ffreestanding $^ -o $@ -lgcc
+
+$(OUTPUT)/gcs-stress-thread: gcs-stress-thread.S
+	$(CC) -nostdlib $^ -o $@
+
+$(OUTPUT)/gcspushm: gcspushm.S
+	$(CC) -nostdlib $^ -o $@
+
+$(OUTPUT)/gcsstr: gcsstr.S
+	$(CC) -nostdlib $^ -o $@
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/delay.h b/tools/testing/selftests/arm64/gcs/asm-offsets.h
index e69de29bb2d1..e69de29bb2d1 100644
--- a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/delay.h
+++ b/tools/testing/selftests/arm64/gcs/asm-offsets.h
diff --git a/tools/testing/selftests/arm64/gcs/basic-gcs.c b/tools/testing/selftests/arm64/gcs/basic-gcs.c
new file mode 100644
index 000000000000..250977abc398
--- /dev/null
+++ b/tools/testing/selftests/arm64/gcs/basic-gcs.c
@@ -0,0 +1,420 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023 ARM Limited.
+ */
+
+#include <limits.h>
+#include <stdbool.h>
+
+#include <linux/prctl.h>
+
+#include <sys/mman.h>
+#include <asm/mman.h>
+#include <asm/hwcap.h>
+#include <linux/sched.h>
+
+#include "kselftest.h"
+#include "gcs-util.h"
+
+/* nolibc doesn't have sysconf(), just hard code the maximum */
+static size_t page_size = 65536;
+
+static  __attribute__((noinline)) void valid_gcs_function(void)
+{
+	/* Do something the compiler can't optimise out */
+	my_syscall1(__NR_prctl, PR_SVE_GET_VL);
+}
+
+static inline int gcs_set_status(unsigned long mode)
+{
+	bool enabling = mode & PR_SHADOW_STACK_ENABLE;
+	int ret;
+	unsigned long new_mode;
+
+	/*
+	 * The prctl takes 1 argument but we need to ensure that the
+	 * other 3 values passed in registers to the syscall are zero
+	 * since the kernel validates them.
+	 */
+	ret = my_syscall5(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, mode,
+			  0, 0, 0);
+
+	if (ret == 0) {
+		ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS,
+				  &new_mode, 0, 0, 0);
+		if (ret == 0) {
+			if (new_mode != mode) {
+				ksft_print_msg("Mode set to %lx not %lx\n",
+					       new_mode, mode);
+				ret = -EINVAL;
+			}
+		} else {
+			ksft_print_msg("Failed to validate mode: %d\n", ret);
+		}
+
+		if (enabling != chkfeat_gcs()) {
+			ksft_print_msg("%senabled by prctl but %senabled in CHKFEAT\n",
+				       enabling ? "" : "not ",
+				       chkfeat_gcs() ? "" : "not ");
+			ret = -EINVAL;
+		}
+	}
+
+	return ret;
+}
+
+/* Try to read the status */
+static bool read_status(void)
+{
+	unsigned long state;
+	int ret;
+
+	ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS,
+			  &state, 0, 0, 0);
+	if (ret != 0) {
+		ksft_print_msg("Failed to read state: %d\n", ret);
+		return false;
+	}
+
+	return state & PR_SHADOW_STACK_ENABLE;
+}
+
+/* Just a straight enable */
+static bool base_enable(void)
+{
+	int ret;
+
+	ret = gcs_set_status(PR_SHADOW_STACK_ENABLE);
+	if (ret) {
+		ksft_print_msg("PR_SHADOW_STACK_ENABLE failed %d\n", ret);
+		return false;
+	}
+
+	return true;
+}
+
+/* Check we can read GCSPR_EL0 when GCS is enabled */
+static bool read_gcspr_el0(void)
+{
+	unsigned long *gcspr_el0;
+
+	ksft_print_msg("GET GCSPR\n");
+	gcspr_el0 = get_gcspr();
+	ksft_print_msg("GCSPR_EL0 is %p\n", gcspr_el0);
+
+	return true;
+}
+
+/* Also allow writes to stack */
+static bool enable_writeable(void)
+{
+	int ret;
+
+	ret = gcs_set_status(PR_SHADOW_STACK_ENABLE | PR_SHADOW_STACK_WRITE);
+	if (ret) {
+		ksft_print_msg("PR_SHADOW_STACK_ENABLE writeable failed: %d\n", ret);
+		return false;
+	}
+
+	ret = gcs_set_status(PR_SHADOW_STACK_ENABLE);
+	if (ret) {
+		ksft_print_msg("failed to restore plain enable %d\n", ret);
+		return false;
+	}
+
+	return true;
+}
+
+/* Also allow writes to stack */
+static bool enable_push_pop(void)
+{
+	int ret;
+
+	ret = gcs_set_status(PR_SHADOW_STACK_ENABLE | PR_SHADOW_STACK_PUSH);
+	if (ret) {
+		ksft_print_msg("PR_SHADOW_STACK_ENABLE with push failed: %d\n",
+			       ret);
+		return false;
+	}
+
+	ret = gcs_set_status(PR_SHADOW_STACK_ENABLE);
+	if (ret) {
+		ksft_print_msg("failed to restore plain enable %d\n", ret);
+		return false;
+	}
+
+	return true;
+}
+
+/* Enable GCS and allow everything */
+static bool enable_all(void)
+{
+	int ret;
+
+	ret = gcs_set_status(PR_SHADOW_STACK_ENABLE | PR_SHADOW_STACK_PUSH |
+			     PR_SHADOW_STACK_WRITE);
+	if (ret) {
+		ksft_print_msg("PR_SHADOW_STACK_ENABLE with everything failed: %d\n",
+			       ret);
+		return false;
+	}
+
+	ret = gcs_set_status(PR_SHADOW_STACK_ENABLE);
+	if (ret) {
+		ksft_print_msg("failed to restore plain enable %d\n", ret);
+		return false;
+	}
+
+	return true;
+}
+
+static bool enable_invalid(void)
+{
+	int ret = gcs_set_status(ULONG_MAX);
+	if (ret == 0) {
+		ksft_print_msg("GCS_SET_STATUS %lx succeeded\n", ULONG_MAX);
+		return false;
+	}
+
+	return true;
+}
+
+/* Map a GCS */
+static bool map_guarded_stack(void)
+{
+	int ret;
+	uint64_t *buf;
+	uint64_t expected_cap;
+	int elem;
+	bool pass = true;
+
+	buf = (void *)my_syscall3(__NR_map_shadow_stack, 0, page_size,
+				  SHADOW_STACK_SET_MARKER |
+				  SHADOW_STACK_SET_TOKEN);
+	if (buf == MAP_FAILED) {
+		ksft_print_msg("Failed to map %lu byte GCS: %d\n",
+			       page_size, errno);
+		return false;
+	}
+	ksft_print_msg("Mapped GCS at %p-%p\n", buf,
+		       (void *)((uint64_t)buf + page_size));
+
+	/* The top of the newly allocated region should be 0 */
+	elem = (page_size / sizeof(uint64_t)) - 1;
+	if (buf[elem]) {
+		ksft_print_msg("Last entry is 0x%llx not 0x0\n", buf[elem]);
+		pass = false;
+	}
+
+	/* Then a valid cap token */
+	elem--;
+	expected_cap = ((uint64_t)buf + page_size - 16);
+	expected_cap &= GCS_CAP_ADDR_MASK;
+	expected_cap |= GCS_CAP_VALID_TOKEN;
+	if (buf[elem] != expected_cap) {
+		ksft_print_msg("Cap entry is 0x%llx not 0x%llx\n",
+			       buf[elem], expected_cap);
+		pass = false;
+	}
+	ksft_print_msg("cap token is 0x%llx\n", buf[elem]);
+
+	/* The rest should be zeros */
+	for (elem = 0; elem < page_size / sizeof(uint64_t) - 2; elem++) {
+		if (!buf[elem])
+			continue;
+		ksft_print_msg("GCS slot %d is 0x%llx not 0x0\n",
+			       elem, buf[elem]);
+		pass = false;
+	}
+
+	ret = munmap(buf, page_size);
+	if (ret != 0) {
+		ksft_print_msg("Failed to unmap %ld byte GCS: %d\n",
+			       page_size, errno);
+		pass = false;
+	}
+
+	return pass;
+}
+
+/* A fork()ed process can run */
+static bool test_fork(void)
+{
+	unsigned long child_mode;
+	int ret, status;
+	pid_t pid;
+	bool pass = true;
+
+	pid = fork();
+	if (pid == -1) {
+		ksft_print_msg("fork() failed: %d\n", errno);
+		pass = false;
+		goto out;
+	}
+	if (pid == 0) {
+		/* In child, make sure we can call a function, read
+		 * the GCS pointer and status and then exit */
+		valid_gcs_function();
+		get_gcspr();
+
+		ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS,
+				  &child_mode, 0, 0, 0);
+		if (ret == 0 && !(child_mode & PR_SHADOW_STACK_ENABLE)) {
+			ksft_print_msg("GCS not enabled in child\n");
+			ret = -EINVAL;
+		}
+
+		exit(ret);
+	}
+
+	/*
+	 * In parent, check we can still do function calls then block
+	 * for the child.
+	 */
+	valid_gcs_function();
+
+	ksft_print_msg("Waiting for child %d\n", pid);
+
+	ret = waitpid(pid, &status, 0);
+	if (ret == -1) {
+		ksft_print_msg("Failed to wait for child: %d\n",
+			       errno);
+		return false;
+	}
+
+	if (!WIFEXITED(status)) {
+		ksft_print_msg("Child exited due to signal %d\n",
+			       WTERMSIG(status));
+		pass = false;
+	} else {
+		if (WEXITSTATUS(status)) {
+			ksft_print_msg("Child exited with status %d\n",
+				       WEXITSTATUS(status));
+			pass = false;
+		}
+	}
+
+out:
+
+	return pass;
+}
+
+/* A vfork()ed process can run and exit */
+static bool test_vfork(void)
+{
+	unsigned long child_mode;
+	int ret, status;
+	pid_t pid;
+	bool pass = true;
+
+	pid = vfork();
+	if (pid == -1) {
+		ksft_print_msg("vfork() failed: %d\n", errno);
+		pass = false;
+		goto out;
+	}
+	if (pid == 0) {
+		/*
+		 * In child, make sure we can call a function, read
+		 * the GCS pointer and status and then exit.
+		 */
+		valid_gcs_function();
+		get_gcspr();
+
+		ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS,
+				  &child_mode, 0, 0, 0);
+		if (ret == 0 && !(child_mode & PR_SHADOW_STACK_ENABLE)) {
+			ksft_print_msg("GCS not enabled in child\n");
+			ret = EXIT_FAILURE;
+		}
+
+		_exit(ret);
+	}
+
+	/*
+	 * In parent, check we can still do function calls then check
+	 * on the child.
+	 */
+	valid_gcs_function();
+
+	ksft_print_msg("Waiting for child %d\n", pid);
+
+	ret = waitpid(pid, &status, 0);
+	if (ret == -1) {
+		ksft_print_msg("Failed to wait for child: %d\n",
+			       errno);
+		return false;
+	}
+
+	if (!WIFEXITED(status)) {
+		ksft_print_msg("Child exited due to signal %d\n",
+			       WTERMSIG(status));
+		pass = false;
+	} else if (WEXITSTATUS(status)) {
+		ksft_print_msg("Child exited with status %d\n",
+			       WEXITSTATUS(status));
+		pass = false;
+	}
+
+out:
+
+	return pass;
+}
+
+typedef bool (*gcs_test)(void);
+
+static struct {
+	char *name;
+	gcs_test test;
+	bool needs_enable;
+} tests[] = {
+	{ "read_status", read_status },
+	{ "base_enable", base_enable, true },
+	{ "read_gcspr_el0", read_gcspr_el0 },
+	{ "enable_writeable", enable_writeable, true },
+	{ "enable_push_pop", enable_push_pop, true },
+	{ "enable_all", enable_all, true },
+	{ "enable_invalid", enable_invalid, true },
+	{ "map_guarded_stack", map_guarded_stack },
+	{ "fork", test_fork },
+	{ "vfork", test_vfork },
+};
+
+int main(void)
+{
+	int i, ret;
+	unsigned long gcs_mode;
+
+	ksft_print_header();
+
+	if (!(getauxval(AT_HWCAP) & HWCAP_GCS))
+		ksft_exit_skip("SKIP GCS not supported\n");
+
+	ret = my_syscall5(__NR_prctl, PR_GET_SHADOW_STACK_STATUS,
+			  &gcs_mode, 0, 0, 0);
+	if (ret != 0)
+		ksft_exit_fail_msg("Failed to read GCS state: %d\n", ret);
+
+	if (!(gcs_mode & PR_SHADOW_STACK_ENABLE)) {
+		gcs_mode = PR_SHADOW_STACK_ENABLE;
+		ret = my_syscall5(__NR_prctl, PR_SET_SHADOW_STACK_STATUS,
+				  gcs_mode, 0, 0, 0);
+		if (ret != 0)
+			ksft_exit_fail_msg("Failed to enable GCS: %d\n", ret);
+	}
+
+	ksft_set_plan(ARRAY_SIZE(tests));
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		ksft_test_result((*tests[i].test)(), "%s\n", tests[i].name);
+	}
+
+	/* One last test: disable GCS, we can do this one time */
+	ret = my_syscall5(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, 0, 0, 0, 0);
+	if (ret != 0)
+		ksft_print_msg("Failed to disable GCS: %d\n", ret);
+
+	ksft_finished();
+
+	return 0;
+}
diff --git a/tools/testing/selftests/arm64/gcs/gcs-locking.c b/tools/testing/selftests/arm64/gcs/gcs-locking.c
new file mode 100644
index 000000000000..1e6abb136ffd
--- /dev/null
+++ b/tools/testing/selftests/arm64/gcs/gcs-locking.c
@@ -0,0 +1,199 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023 ARM Limited.
+ *
+ * Tests for GCS mode locking.  These tests rely on both having GCS
+ * unconfigured on entry and on the kselftest harness running each
+ * test in a fork()ed process which will have it's own mode.
+ */
+
+#include <limits.h>
+
+#include <sys/auxv.h>
+#include <sys/prctl.h>
+
+#include <asm/hwcap.h>
+
+#include "kselftest_harness.h"
+
+#include "gcs-util.h"
+
+#define my_syscall2(num, arg1, arg2)                                          \
+({                                                                            \
+	register long _num  __asm__ ("x8") = (num);                           \
+	register long _arg1 __asm__ ("x0") = (long)(arg1);                    \
+	register long _arg2 __asm__ ("x1") = (long)(arg2);                    \
+	register long _arg3 __asm__ ("x2") = 0;                               \
+	register long _arg4 __asm__ ("x3") = 0;                               \
+	register long _arg5 __asm__ ("x4") = 0;                               \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"svc #0\n"                                                    \
+		: "=r"(_arg1)                                                 \
+		: "r"(_arg1), "r"(_arg2),                                     \
+		  "r"(_arg3), "r"(_arg4),                                     \
+		  "r"(_arg5), "r"(_num)					      \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+/* No mode bits are rejected for locking */
+TEST(lock_all_modes)
+{
+	int ret;
+
+	ret = prctl(PR_LOCK_SHADOW_STACK_STATUS, ULONG_MAX, 0, 0, 0);
+	ASSERT_EQ(ret, 0);
+}
+
+FIXTURE(valid_modes)
+{
+};
+
+FIXTURE_VARIANT(valid_modes)
+{
+	unsigned long mode;
+};
+
+FIXTURE_VARIANT_ADD(valid_modes, enable)
+{
+	.mode = PR_SHADOW_STACK_ENABLE,
+};
+
+FIXTURE_VARIANT_ADD(valid_modes, enable_write)
+{
+	.mode = PR_SHADOW_STACK_ENABLE | PR_SHADOW_STACK_WRITE,
+};
+
+FIXTURE_VARIANT_ADD(valid_modes, enable_push)
+{
+	.mode = PR_SHADOW_STACK_ENABLE | PR_SHADOW_STACK_PUSH,
+};
+
+FIXTURE_VARIANT_ADD(valid_modes, enable_write_push)
+{
+	.mode = PR_SHADOW_STACK_ENABLE | PR_SHADOW_STACK_WRITE |
+		PR_SHADOW_STACK_PUSH,
+};
+
+FIXTURE_SETUP(valid_modes)
+{
+}
+
+FIXTURE_TEARDOWN(valid_modes)
+{
+}
+
+/* We can set the mode at all */
+TEST_F(valid_modes, set)
+{
+	int ret;
+
+	ret = my_syscall2(__NR_prctl, PR_SET_SHADOW_STACK_STATUS,
+			  variant->mode);
+	ASSERT_EQ(ret, 0);
+
+	_exit(0);
+}
+
+/* Enabling, locking then disabling is rejected */
+TEST_F(valid_modes, enable_lock_disable)
+{
+	unsigned long mode;
+	int ret;
+
+	ret = my_syscall2(__NR_prctl, PR_SET_SHADOW_STACK_STATUS,
+			  variant->mode);
+	ASSERT_EQ(ret, 0);
+
+	ret = prctl(PR_GET_SHADOW_STACK_STATUS, &mode, 0, 0, 0);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(mode, variant->mode);
+
+	ret = prctl(PR_LOCK_SHADOW_STACK_STATUS, variant->mode, 0, 0, 0);
+	ASSERT_EQ(ret, 0);
+
+	ret = my_syscall2(__NR_prctl, PR_SET_SHADOW_STACK_STATUS, 0);
+	ASSERT_EQ(ret, -EBUSY);
+
+	_exit(0);
+}
+
+/* Locking then enabling is rejected */
+TEST_F(valid_modes, lock_enable)
+{
+	unsigned long mode;
+	int ret;
+
+	ret = prctl(PR_LOCK_SHADOW_STACK_STATUS, variant->mode, 0, 0, 0);
+	ASSERT_EQ(ret, 0);
+
+	ret = my_syscall2(__NR_prctl, PR_SET_SHADOW_STACK_STATUS,
+			  variant->mode);
+	ASSERT_EQ(ret, -EBUSY);
+
+	ret = prctl(PR_GET_SHADOW_STACK_STATUS, &mode, 0, 0, 0);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(mode, 0);
+
+	_exit(0);
+}
+
+/* Locking then changing other modes is fine */
+TEST_F(valid_modes, lock_enable_disable_others)
+{
+	unsigned long mode;
+	int ret;
+
+	ret = my_syscall2(__NR_prctl, PR_SET_SHADOW_STACK_STATUS,
+			  variant->mode);
+	ASSERT_EQ(ret, 0);
+
+	ret = prctl(PR_GET_SHADOW_STACK_STATUS, &mode, 0, 0, 0);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(mode, variant->mode);
+
+	ret = prctl(PR_LOCK_SHADOW_STACK_STATUS, variant->mode, 0, 0, 0);
+	ASSERT_EQ(ret, 0);
+
+	ret = my_syscall2(__NR_prctl, PR_SET_SHADOW_STACK_STATUS,
+			  PR_SHADOW_STACK_ALL_MODES);
+	ASSERT_EQ(ret, 0);
+
+	ret = prctl(PR_GET_SHADOW_STACK_STATUS, &mode, 0, 0, 0);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(mode, PR_SHADOW_STACK_ALL_MODES);
+
+	ret = my_syscall2(__NR_prctl, PR_SET_SHADOW_STACK_STATUS,
+			  variant->mode);
+	ASSERT_EQ(ret, 0);
+
+	ret = prctl(PR_GET_SHADOW_STACK_STATUS, &mode, 0, 0, 0);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(mode, variant->mode);
+
+	_exit(0);
+}
+
+int main(int argc, char **argv)
+{
+	unsigned long mode;
+	int ret;
+
+	if (!(getauxval(AT_HWCAP) & HWCAP_GCS))
+		ksft_exit_skip("SKIP GCS not supported\n");
+
+	ret = prctl(PR_GET_SHADOW_STACK_STATUS, &mode, 0, 0, 0);
+	if (ret) {
+		ksft_print_msg("Failed to read GCS state: %d\n", ret);
+		return EXIT_FAILURE;
+	}
+
+	if (mode & PR_SHADOW_STACK_ENABLE) {
+		ksft_print_msg("GCS was enabled, test unsupported\n");
+		return KSFT_SKIP;
+	}
+
+	return test_harness_run(argc, argv);
+}
diff --git a/tools/testing/selftests/arm64/gcs/gcs-stress-thread.S b/tools/testing/selftests/arm64/gcs/gcs-stress-thread.S
new file mode 100644
index 000000000000..b88b25217da5
--- /dev/null
+++ b/tools/testing/selftests/arm64/gcs/gcs-stress-thread.S
@@ -0,0 +1,311 @@
+// Program that loops for ever doing lots of recursions and system calls,
+// intended to be used as part of a stress test for GCS context switching.
+//
+// Copyright 2015-2023 Arm Ltd
+
+#include <asm/unistd.h>
+
+#define sa_sz 32
+#define sa_flags 8
+#define sa_handler 0
+#define sa_mask_sz 8
+
+#define si_code 8
+
+#define SIGINT 2
+#define SIGABRT 6
+#define SIGUSR1 10
+#define SIGSEGV 11
+#define SIGUSR2 12
+#define SIGTERM 15
+#define SEGV_CPERR 10
+
+#define SA_NODEFER 1073741824
+#define SA_SIGINFO 4
+#define ucontext_regs 184
+
+#define PR_SET_SHADOW_STACK_STATUS      75
+# define PR_SHADOW_STACK_ENABLE         (1UL << 0)
+
+#define	GCSPR_EL0 S3_3_C2_C5_1
+
+.macro function name
+	.macro endfunction
+		.type \name, @function
+		.purgem endfunction
+	.endm
+\name:
+.endm
+
+// Print a single character x0 to stdout
+// Clobbers x0-x2,x8
+function putc
+	str	x0, [sp, #-16]!
+
+	mov	x0, #1			// STDOUT_FILENO
+	mov	x1, sp
+	mov	x2, #1
+	mov	x8, #__NR_write
+	svc	#0
+
+	add	sp, sp, #16
+	ret
+endfunction
+.globl	putc
+
+// Print a NUL-terminated string starting at address x0 to stdout
+// Clobbers x0-x3,x8
+function puts
+	mov	x1, x0
+
+	mov	x2, #0
+0:	ldrb	w3, [x0], #1
+	cbz	w3, 1f
+	add	x2, x2, #1
+	b	0b
+
+1:	mov	w0, #1			// STDOUT_FILENO
+	mov	x8, #__NR_write
+	svc	#0
+
+	ret
+endfunction
+.globl	puts
+
+// Utility macro to print a literal string
+// Clobbers x0-x4,x8
+.macro puts string
+	.pushsection .rodata.str1.1, "aMS", @progbits, 1
+.L__puts_literal\@: .string "\string"
+	.popsection
+
+	ldr	x0, =.L__puts_literal\@
+	bl	puts
+.endm
+
+// Print an unsigned decimal number x0 to stdout
+// Clobbers x0-x4,x8
+function putdec
+	mov	x1, sp
+	str	x30, [sp, #-32]!	// Result can't be > 20 digits
+
+	mov	x2, #0
+	strb	w2, [x1, #-1]!		// Write the NUL terminator
+
+	mov	x2, #10
+0:	udiv	x3, x0, x2		// div-mod loop to generate the digits
+	msub	x0, x3, x2, x0
+	add	w0, w0, #'0'
+	strb	w0, [x1, #-1]!
+	mov	x0, x3
+	cbnz	x3, 0b
+
+	ldrb	w0, [x1]
+	cbnz	w0, 1f
+	mov	w0, #'0'		// Print "0" for 0, not ""
+	strb	w0, [x1, #-1]!
+
+1:	mov	x0, x1
+	bl	puts
+
+	ldr	x30, [sp], #32
+	ret
+endfunction
+.globl	putdec
+
+// Print an unsigned decimal number x0 to stdout, followed by a newline
+// Clobbers x0-x5,x8
+function putdecn
+	mov	x5, x30
+
+	bl	putdec
+	mov	x0, #'\n'
+	bl	putc
+
+	ret	x5
+endfunction
+.globl	putdecn
+
+// Fill x1 bytes starting at x0 with 0.
+// Clobbers x1, x2.
+function memclr
+	mov	w2, #0
+endfunction
+.globl	memclr
+	// fall through to memfill
+
+// Trivial memory fill: fill x1 bytes starting at address x0 with byte w2
+// Clobbers x1
+function memfill
+	cmp	x1, #0
+	b.eq	1f
+
+0:	strb	w2, [x0], #1
+	subs	x1, x1, #1
+	b.ne	0b
+
+1:	ret
+endfunction
+.globl	memfill
+
+// w0: signal number
+// x1: sa_action
+// w2: sa_flags
+// Clobbers x0-x6,x8
+function setsignal
+	str	x30, [sp, #-((sa_sz + 15) / 16 * 16 + 16)]!
+
+	mov	w4, w0
+	mov	x5, x1
+	mov	w6, w2
+
+	add	x0, sp, #16
+	mov	x1, #sa_sz
+	bl	memclr
+
+	mov	w0, w4
+	add	x1, sp, #16
+	str	w6, [x1, #sa_flags]
+	str	x5, [x1, #sa_handler]
+	mov	x2, #0
+	mov	x3, #sa_mask_sz
+	mov	x8, #__NR_rt_sigaction
+	svc	#0
+
+	cbz	w0, 1f
+
+	puts	"sigaction failure\n"
+	b	abort
+
+1:	ldr	x30, [sp], #((sa_sz + 15) / 16 * 16 + 16)
+	ret
+endfunction
+
+
+function tickle_handler
+	// Perhaps collect GCSPR_EL0 here in future?
+	ret
+endfunction
+
+function terminate_handler
+	mov	w21, w0
+	mov	x20, x2
+
+	puts	"Terminated by signal "
+	mov	w0, w21
+	bl	putdec
+	puts	", no error\n"
+
+	mov	x0, #0
+	mov	x8, #__NR_exit
+	svc	#0
+endfunction
+
+function segv_handler
+	// stash the siginfo_t *
+	mov	x20, x1
+
+	// Disable GCS, we don't want additional faults logging things
+	mov	x0, PR_SET_SHADOW_STACK_STATUS
+	mov	x1, xzr
+	mov	x2, xzr
+	mov	x3, xzr
+	mov	x4, xzr
+	mov	x5, xzr
+	mov	x8, #__NR_prctl
+	svc	#0
+
+	puts	"Got SIGSEGV code "
+
+	ldr	x21, [x20, #si_code]
+	mov	x0, x21
+	bl	putdec
+
+	// GCS faults should have si_code SEGV_CPERR
+	cmp	x21, #SEGV_CPERR
+	bne	1f
+
+	puts	" (GCS violation)"
+1:
+	mov	x0, '\n'
+	bl	putc
+	b	abort
+endfunction
+
+// Recurse x20 times
+.macro recurse id
+function recurse\id
+	stp	x29, x30, [sp, #-16]!
+	mov	x29, sp
+
+	cmp	x20, 0
+	beq	1f
+	sub	x20, x20, 1
+	bl	recurse\id
+
+1:
+	ldp	x29, x30, [sp], #16
+
+	// Do a syscall immediately prior to returning to try to provoke
+	// scheduling and migration at a point where coherency issues
+	// might trigger.
+	mov	x8, #__NR_getpid
+	svc	#0
+
+	ret
+endfunction
+.endm
+
+// Generate and use two copies so we're changing the GCS contents
+recurse 1
+recurse 2
+
+.globl _start
+function _start
+	// Run with GCS
+	mov	x0, PR_SET_SHADOW_STACK_STATUS
+	mov	x1, PR_SHADOW_STACK_ENABLE
+	mov	x2, xzr
+	mov	x3, xzr
+	mov	x4, xzr
+	mov	x5, xzr
+	mov	x8, #__NR_prctl
+	svc	#0
+	cbz	x0, 1f
+	puts	"Failed to enable GCS\n"
+	b	abort
+1:
+
+	mov	w0, #SIGTERM
+	adr	x1, terminate_handler
+	mov	w2, #SA_SIGINFO
+	bl	setsignal
+
+	mov	w0, #SIGUSR1
+	adr	x1, tickle_handler
+	mov	w2, #SA_SIGINFO
+	orr	w2, w2, #SA_NODEFER
+	bl	setsignal
+
+	mov	w0, #SIGSEGV
+	adr	x1, segv_handler
+	mov	w2, #SA_SIGINFO
+	orr	w2, w2, #SA_NODEFER
+	bl	setsignal
+
+	puts	"Running\n"
+
+loop:
+	// Small recursion depth so we're frequently flipping between
+	// the two recursors and changing what's on the stack
+	mov	x20, #5
+	bl	recurse1
+	mov	x20, #5
+	bl	recurse2
+	b	loop
+endfunction
+
+abort:
+	mov	x0, #255
+	mov	x8, #__NR_exit
+	svc	#0
diff --git a/tools/testing/selftests/arm64/gcs/gcs-stress.c b/tools/testing/selftests/arm64/gcs/gcs-stress.c
new file mode 100644
index 000000000000..86d8cd42aee7
--- /dev/null
+++ b/tools/testing/selftests/arm64/gcs/gcs-stress.c
@@ -0,0 +1,530 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2022-3 ARM Limited.
+ */
+
+#define _GNU_SOURCE
+#define _POSIX_C_SOURCE 199309L
+
+#include <errno.h>
+#include <getopt.h>
+#include <poll.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/auxv.h>
+#include <sys/epoll.h>
+#include <sys/prctl.h>
+#include <sys/types.h>
+#include <sys/uio.h>
+#include <sys/wait.h>
+#include <asm/hwcap.h>
+
+#include "kselftest.h"
+
+struct child_data {
+	char *name, *output;
+	pid_t pid;
+	int stdout;
+	bool output_seen;
+	bool exited;
+	int exit_status;
+	int exit_signal;
+};
+
+static int epoll_fd;
+static struct child_data *children;
+static struct epoll_event *evs;
+static int tests;
+static int num_children;
+static bool terminate;
+
+static int startup_pipe[2];
+
+static int num_processors(void)
+{
+	long nproc = sysconf(_SC_NPROCESSORS_CONF);
+	if (nproc < 0) {
+		perror("Unable to read number of processors\n");
+		exit(EXIT_FAILURE);
+	}
+
+	return nproc;
+}
+
+static void start_thread(struct child_data *child, int id)
+{
+	int ret, pipefd[2], i;
+	struct epoll_event ev;
+
+	ret = pipe(pipefd);
+	if (ret != 0)
+		ksft_exit_fail_msg("Failed to create stdout pipe: %s (%d)\n",
+				   strerror(errno), errno);
+
+	child->pid = fork();
+	if (child->pid == -1)
+		ksft_exit_fail_msg("fork() failed: %s (%d)\n",
+				   strerror(errno), errno);
+
+	if (!child->pid) {
+		/*
+		 * In child, replace stdout with the pipe, errors to
+		 * stderr from here as kselftest prints to stdout.
+		 */
+		ret = dup2(pipefd[1], 1);
+		if (ret == -1) {
+			fprintf(stderr, "dup2() %d\n", errno);
+			exit(EXIT_FAILURE);
+		}
+
+		/*
+		 * Duplicate the read side of the startup pipe to
+		 * FD 3 so we can close everything else.
+		 */
+		ret = dup2(startup_pipe[0], 3);
+		if (ret == -1) {
+			fprintf(stderr, "dup2() %d\n", errno);
+			exit(EXIT_FAILURE);
+		}
+
+		/*
+		 * Very dumb mechanism to clean open FDs other than
+		 * stdio. We don't want O_CLOEXEC for the pipes...
+		 */
+		for (i = 4; i < 8192; i++)
+			close(i);
+
+		/*
+		 * Read from the startup pipe, there should be no data
+		 * and we should block until it is closed.  We just
+		 * carry on on error since this isn't super critical.
+		 */
+		ret = read(3, &i, sizeof(i));
+		if (ret < 0)
+			fprintf(stderr, "read(startp pipe) failed: %s (%d)\n",
+				strerror(errno), errno);
+		if (ret > 0)
+			fprintf(stderr, "%d bytes of data on startup pipe\n",
+				ret);
+		close(3);
+
+		ret = execl("gcs-stress-thread", "gcs-stress-thread", NULL);
+		fprintf(stderr, "execl(gcs-stress-thread) failed: %d (%s)\n",
+			errno, strerror(errno));
+
+		exit(EXIT_FAILURE);
+	} else {
+		/*
+		 * In parent, remember the child and close our copy of the
+		 * write side of stdout.
+		 */
+		close(pipefd[1]);
+		child->stdout = pipefd[0];
+		child->output = NULL;
+		child->exited = false;
+		child->output_seen = false;
+
+		ev.events = EPOLLIN | EPOLLHUP;
+		ev.data.ptr = child;
+
+		ret = asprintf(&child->name, "Thread-%d", id);
+		if (ret == -1)
+			ksft_exit_fail_msg("asprintf() failed\n");
+
+		ret = epoll_ctl(epoll_fd, EPOLL_CTL_ADD, child->stdout, &ev);
+		if (ret < 0) {
+			ksft_exit_fail_msg("%s EPOLL_CTL_ADD failed: %s (%d)\n",
+					   child->name, strerror(errno), errno);
+		}
+	}
+
+	ksft_print_msg("Started %s\n", child->name);
+	num_children++;
+}
+
+static bool child_output_read(struct child_data *child)
+{
+	char read_data[1024];
+	char work[1024];
+	int ret, len, cur_work, cur_read;
+
+	ret = read(child->stdout, read_data, sizeof(read_data));
+	if (ret < 0) {
+		if (errno == EINTR)
+			return true;
+
+		ksft_print_msg("%s: read() failed: %s (%d)\n",
+			       child->name, strerror(errno),
+			       errno);
+		return false;
+	}
+	len = ret;
+
+	child->output_seen = true;
+
+	/* Pick up any partial read */
+	if (child->output) {
+		strncpy(work, child->output, sizeof(work) - 1);
+		cur_work = strnlen(work, sizeof(work));
+		free(child->output);
+		child->output = NULL;
+	} else {
+		cur_work = 0;
+	}
+
+	cur_read = 0;
+	while (cur_read < len) {
+		work[cur_work] = read_data[cur_read++];
+
+		if (work[cur_work] == '\n') {
+			work[cur_work] = '\0';
+			ksft_print_msg("%s: %s\n", child->name, work);
+			cur_work = 0;
+		} else {
+			cur_work++;
+		}
+	}
+
+	if (cur_work) {
+		work[cur_work] = '\0';
+		ret = asprintf(&child->output, "%s", work);
+		if (ret == -1)
+			ksft_exit_fail_msg("Out of memory\n");
+	}
+
+	return false;
+}
+
+static void child_output(struct child_data *child, uint32_t events,
+			 bool flush)
+{
+	bool read_more;
+
+	if (events & EPOLLIN) {
+		do {
+			read_more = child_output_read(child);
+		} while (read_more);
+	}
+
+	if (events & EPOLLHUP) {
+		close(child->stdout);
+		child->stdout = -1;
+		flush = true;
+	}
+
+	if (flush && child->output) {
+		ksft_print_msg("%s: %s<EOF>\n", child->name, child->output);
+		free(child->output);
+		child->output = NULL;
+	}
+}
+
+static void child_tickle(struct child_data *child)
+{
+	if (child->output_seen && !child->exited)
+		kill(child->pid, SIGUSR1);
+}
+
+static void child_stop(struct child_data *child)
+{
+	if (!child->exited)
+		kill(child->pid, SIGTERM);
+}
+
+static void child_cleanup(struct child_data *child)
+{
+	pid_t ret;
+	int status;
+	bool fail = false;
+
+	if (!child->exited) {
+		do {
+			ret = waitpid(child->pid, &status, 0);
+			if (ret == -1 && errno == EINTR)
+				continue;
+
+			if (ret == -1) {
+				ksft_print_msg("waitpid(%d) failed: %s (%d)\n",
+					       child->pid, strerror(errno),
+					       errno);
+				fail = true;
+				break;
+			}
+
+			if (WIFEXITED(status)) {
+				child->exit_status = WEXITSTATUS(status);
+				child->exited = true;
+			}
+
+			if (WIFSIGNALED(status)) {
+				child->exit_signal = WTERMSIG(status);
+				ksft_print_msg("%s: Exited due to signal %d\n",
+					       child->name, child->exit_signal);
+				fail = true;
+				child->exited = true;
+			}
+		} while (!child->exited);
+	}
+
+	if (!child->output_seen) {
+		ksft_print_msg("%s no output seen\n", child->name);
+		fail = true;
+	}
+
+	if (child->exit_status != 0) {
+		ksft_print_msg("%s exited with error code %d\n",
+			       child->name, child->exit_status);
+		fail = true;
+	}
+
+	ksft_test_result(!fail, "%s\n", child->name);
+}
+
+static void handle_child_signal(int sig, siginfo_t *info, void *context)
+{
+	int i;
+	bool found = false;
+
+	for (i = 0; i < num_children; i++) {
+		if (children[i].pid == info->si_pid) {
+			children[i].exited = true;
+			children[i].exit_status = info->si_status;
+			found = true;
+			break;
+		}
+	}
+
+	if (!found)
+		ksft_print_msg("SIGCHLD for unknown PID %d with status %d\n",
+			       info->si_pid, info->si_status);
+}
+
+static void handle_exit_signal(int sig, siginfo_t *info, void *context)
+{
+	int i;
+
+	/* If we're already exiting then don't signal again */
+	if (terminate)
+		return;
+
+	ksft_print_msg("Got signal, exiting...\n");
+
+	terminate = true;
+
+	/*
+	 * This should be redundant, the main loop should clean up
+	 * after us, but for safety stop everything we can here.
+	 */
+	for (i = 0; i < num_children; i++)
+		child_stop(&children[i]);
+}
+
+/* Handle any pending output without blocking */
+static void drain_output(bool flush)
+{
+	int ret = 1;
+	int i;
+
+	while (ret > 0) {
+		ret = epoll_wait(epoll_fd, evs, tests, 0);
+		if (ret < 0) {
+			if (errno == EINTR)
+				continue;
+			ksft_print_msg("epoll_wait() failed: %s (%d)\n",
+				       strerror(errno), errno);
+		}
+
+		for (i = 0; i < ret; i++)
+			child_output(evs[i].data.ptr, evs[i].events, flush);
+	}
+}
+
+static const struct option options[] = {
+	{ "timeout",	required_argument, NULL, 't' },
+	{ }
+};
+
+int main(int argc, char **argv)
+{
+	int seen_children;
+	bool all_children_started = false;
+	int gcs_threads;
+	int timeout = 10;
+	int ret, cpus, i, c;
+	struct sigaction sa;
+
+	while ((c = getopt_long(argc, argv, "t:", options, NULL)) != -1) {
+		switch (c) {
+		case 't':
+			ret = sscanf(optarg, "%d", &timeout);
+			if (ret != 1)
+				ksft_exit_fail_msg("Failed to parse timeout %s\n",
+						   optarg);
+			break;
+		default:
+			ksft_exit_fail_msg("Unknown argument\n");
+		}
+	}
+
+	cpus = num_processors();
+	tests = 0;
+
+	if (getauxval(AT_HWCAP) & HWCAP_GCS) {
+		/* One extra thread, trying to trigger migrations */
+		gcs_threads = cpus + 1;
+		tests += gcs_threads;
+	} else {
+		gcs_threads = 0;
+	}
+
+	ksft_print_header();
+	ksft_set_plan(tests);
+
+	ksft_print_msg("%d CPUs, %d GCS threads\n",
+		       cpus, gcs_threads);
+
+	if (!tests)
+		ksft_exit_skip("No tests scheduled\n");
+
+	if (timeout > 0)
+		ksft_print_msg("Will run for %ds\n", timeout);
+	else
+		ksft_print_msg("Will run until terminated\n");
+
+	children = calloc(sizeof(*children), tests);
+	if (!children)
+		ksft_exit_fail_msg("Unable to allocate child data\n");
+
+	ret = epoll_create1(EPOLL_CLOEXEC);
+	if (ret < 0)
+		ksft_exit_fail_msg("epoll_create1() failed: %s (%d)\n",
+				   strerror(errno), ret);
+	epoll_fd = ret;
+
+	/* Create a pipe which children will block on before execing */
+	ret = pipe(startup_pipe);
+	if (ret != 0)
+		ksft_exit_fail_msg("Failed to create startup pipe: %s (%d)\n",
+				   strerror(errno), errno);
+
+	/* Get signal handers ready before we start any children */
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handle_exit_signal;
+	sa.sa_flags = SA_RESTART | SA_SIGINFO;
+	sigemptyset(&sa.sa_mask);
+	ret = sigaction(SIGINT, &sa, NULL);
+	if (ret < 0)
+		ksft_print_msg("Failed to install SIGINT handler: %s (%d)\n",
+			       strerror(errno), errno);
+	ret = sigaction(SIGTERM, &sa, NULL);
+	if (ret < 0)
+		ksft_print_msg("Failed to install SIGTERM handler: %s (%d)\n",
+			       strerror(errno), errno);
+	sa.sa_sigaction = handle_child_signal;
+	ret = sigaction(SIGCHLD, &sa, NULL);
+	if (ret < 0)
+		ksft_print_msg("Failed to install SIGCHLD handler: %s (%d)\n",
+			       strerror(errno), errno);
+
+	evs = calloc(tests, sizeof(*evs));
+	if (!evs)
+		ksft_exit_fail_msg("Failed to allocate %d epoll events\n",
+				   tests);
+
+	for (i = 0; i < gcs_threads; i++)
+		start_thread(&children[i], i);
+
+	/*
+	 * All children started, close the startup pipe and let them
+	 * run.
+	 */
+	close(startup_pipe[0]);
+	close(startup_pipe[1]);
+
+	timeout *= 10;
+	for (;;) {
+		/* Did we get a signal asking us to exit? */
+		if (terminate)
+			break;
+
+		/*
+		 * Timeout is counted in 100ms with no output, the
+		 * tests print during startup then are silent when
+		 * running so this should ensure they all ran enough
+		 * to install the signal handler, this is especially
+		 * useful in emulation where we will both be slow and
+		 * likely to have a large set of VLs.
+		 */
+		ret = epoll_wait(epoll_fd, evs, tests, 100);
+		if (ret < 0) {
+			if (errno == EINTR)
+				continue;
+			ksft_exit_fail_msg("epoll_wait() failed: %s (%d)\n",
+					   strerror(errno), errno);
+		}
+
+		/* Output? */
+		if (ret > 0) {
+			for (i = 0; i < ret; i++) {
+				child_output(evs[i].data.ptr, evs[i].events,
+					     false);
+			}
+			continue;
+		}
+
+		/* Otherwise epoll_wait() timed out */
+
+		/*
+		 * If the child processes have not produced output they
+		 * aren't actually running the tests yet.
+		 */
+		if (!all_children_started) {
+			seen_children = 0;
+
+			for (i = 0; i < num_children; i++)
+				if (children[i].output_seen ||
+				    children[i].exited)
+					seen_children++;
+
+			if (seen_children != num_children) {
+				ksft_print_msg("Waiting for %d children\n",
+					       num_children - seen_children);
+				continue;
+			}
+
+			all_children_started = true;
+		}
+
+		ksft_print_msg("Sending signals, timeout remaining: %d00ms\n",
+			       timeout);
+
+		for (i = 0; i < num_children; i++)
+			child_tickle(&children[i]);
+
+		/* Negative timeout means run indefinitely */
+		if (timeout < 0)
+			continue;
+		if (--timeout == 0)
+			break;
+	}
+
+	ksft_print_msg("Finishing up...\n");
+	terminate = true;
+
+	for (i = 0; i < tests; i++)
+		child_stop(&children[i]);
+
+	drain_output(false);
+
+	for (i = 0; i < tests; i++)
+		child_cleanup(&children[i]);
+
+	drain_output(true);
+
+	ksft_finished();
+}
diff --git a/tools/testing/selftests/arm64/gcs/gcs-util.h b/tools/testing/selftests/arm64/gcs/gcs-util.h
new file mode 100644
index 000000000000..c99a6b39ac14
--- /dev/null
+++ b/tools/testing/selftests/arm64/gcs/gcs-util.h
@@ -0,0 +1,100 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 ARM Limited.
+ */
+
+#ifndef GCS_UTIL_H
+#define GCS_UTIL_H
+
+#include <stdbool.h>
+
+#ifndef __NR_map_shadow_stack
+#define __NR_map_shadow_stack 453
+#endif
+
+#ifndef __NR_prctl
+#define __NR_prctl 167
+#endif
+
+#ifndef NT_ARM_GCS
+#define NT_ARM_GCS 0x410
+
+struct user_gcs {
+	__u64 features_enabled;
+	__u64 features_locked;
+	__u64 gcspr_el0;
+};
+#endif
+
+/* Shadow Stack/Guarded Control Stack interface */
+#define PR_GET_SHADOW_STACK_STATUS	74
+#define PR_SET_SHADOW_STACK_STATUS      75
+#define PR_LOCK_SHADOW_STACK_STATUS     76
+
+# define PR_SHADOW_STACK_ENABLE         (1UL << 0)
+# define PR_SHADOW_STACK_WRITE		(1UL << 1)
+# define PR_SHADOW_STACK_PUSH		(1UL << 2)
+
+#define PR_SHADOW_STACK_ALL_MODES \
+	PR_SHADOW_STACK_ENABLE | PR_SHADOW_STACK_WRITE | PR_SHADOW_STACK_PUSH
+
+#define SHADOW_STACK_SET_TOKEN (1ULL << 0)     /* Set up a restore token in the shadow stack */
+#define SHADOW_STACK_SET_MARKER (1ULL << 1)     /* Set up a top of stack merker in the shadow stack */
+
+#define GCS_CAP_ADDR_MASK		(0xfffffffffffff000UL)
+#define GCS_CAP_TOKEN_MASK		(0x0000000000000fffUL)
+#define GCS_CAP_VALID_TOKEN		1
+#define GCS_CAP_IN_PROGRESS_TOKEN	5
+
+#define GCS_CAP(x) (((unsigned long)(x) & GCS_CAP_ADDR_MASK) | \
+		    GCS_CAP_VALID_TOKEN)
+
+static inline unsigned long *get_gcspr(void)
+{
+	unsigned long *gcspr;
+
+	asm volatile(
+		"mrs	%0, S3_3_C2_C5_1"
+	: "=r" (gcspr)
+	:
+	: "cc");
+
+	return gcspr;
+}
+
+static inline void __attribute__((always_inline)) gcsss1(unsigned long *Xt)
+{
+	asm volatile (
+		"sys #3, C7, C7, #2, %0\n"
+		:
+		: "rZ" (Xt)
+		: "memory");
+}
+
+static inline unsigned long __attribute__((always_inline)) *gcsss2(void)
+{
+	unsigned long *Xt;
+
+	asm volatile(
+		"SYSL %0, #3, C7, C7, #3\n"
+		: "=r" (Xt)
+		:
+		: "memory");
+
+	return Xt;
+}
+
+static inline bool chkfeat_gcs(void)
+{
+	register long val __asm__ ("x16") = 1;
+
+	/* CHKFEAT x16 */
+	asm volatile(
+		"hint #0x28\n"
+		: "=r" (val)
+		: "r" (val));
+
+	return val != 1;
+}
+
+#endif
diff --git a/tools/testing/selftests/arm64/gcs/gcspushm.S b/tools/testing/selftests/arm64/gcs/gcspushm.S
new file mode 100644
index 000000000000..bbe17c1325ac
--- /dev/null
+++ b/tools/testing/selftests/arm64/gcs/gcspushm.S
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0-only
+//
+// Copyright 2024 Arm Limited
+//
+// Give ourselves GCS push permissions then use them
+
+#include <asm/unistd.h>
+
+/* Shadow Stack/Guarded Control Stack interface */
+#define PR_GET_SHADOW_STACK_STATUS	74
+#define PR_SET_SHADOW_STACK_STATUS      75
+#define PR_LOCK_SHADOW_STACK_STATUS     76
+
+# define PR_SHADOW_STACK_ENABLE         (1UL << 0)
+# define PR_SHADOW_STACK_WRITE		(1UL << 1)
+# define PR_SHADOW_STACK_PUSH		(1UL << 2)
+
+#define KSFT_SKIP 4
+
+.macro function name
+	.macro endfunction
+		.type \name, @function
+		.purgem endfunction
+	.endm
+\name:
+.endm
+
+// Print a single character x0 to stdout
+// Clobbers x0-x2,x8
+function putc
+	str	x0, [sp, #-16]!
+
+	mov	x0, #1			// STDOUT_FILENO
+	mov	x1, sp
+	mov	x2, #1
+	mov	x8, #__NR_write
+	svc	#0
+
+	add	sp, sp, #16
+	ret
+endfunction
+.globl	putc
+
+// Print a NUL-terminated string starting at address x0 to stdout
+// Clobbers x0-x3,x8
+function puts
+	mov	x1, x0
+
+	mov	x2, #0
+0:	ldrb	w3, [x0], #1
+	cbz	w3, 1f
+	add	x2, x2, #1
+	b	0b
+
+1:	mov	w0, #1			// STDOUT_FILENO
+	mov	x8, #__NR_write
+	svc	#0
+
+	ret
+endfunction
+.globl	puts
+
+// Utility macro to print a literal string
+// Clobbers x0-x4,x8
+.macro puts string
+	.pushsection .rodata.str1.1, "aMS", @progbits, 1
+.L__puts_literal\@: .string "\string"
+	.popsection
+
+	ldr	x0, =.L__puts_literal\@
+	bl	puts
+.endm
+
+.globl _start
+function _start
+	// Run with GCS
+	mov	x0, PR_SET_SHADOW_STACK_STATUS
+	mov	x1, PR_SHADOW_STACK_ENABLE | PR_SHADOW_STACK_PUSH
+	mov	x2, xzr
+	mov	x3, xzr
+	mov	x4, xzr
+	mov	x5, xzr
+	mov	x8, #__NR_prctl
+	svc	#0
+	cbz	x0, 1f
+	puts	"Failed to enable GCS with push permission\n"
+	mov	x0, #KSFT_SKIP
+	b	2f
+1:
+	sys	#3, c7, c7, #0, x0	// GCSPUSHM
+	sysl	x0, #3, c7, c7, #1	// GCSPOPM
+
+	mov	x0, #0
+2:
+	mov	x8, #__NR_exit
+	svc	#0
diff --git a/tools/testing/selftests/arm64/gcs/gcsstr.S b/tools/testing/selftests/arm64/gcs/gcsstr.S
new file mode 100644
index 000000000000..a42bba6e30b1
--- /dev/null
+++ b/tools/testing/selftests/arm64/gcs/gcsstr.S
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0-only
+//
+// Copyright 2024 Arm Limited
+//
+// Give ourselves GCS write permissions then use them
+
+#include <asm/unistd.h>
+
+/* Shadow Stack/Guarded Control Stack interface */
+#define PR_GET_SHADOW_STACK_STATUS	74
+#define PR_SET_SHADOW_STACK_STATUS      75
+#define PR_LOCK_SHADOW_STACK_STATUS     76
+
+# define PR_SHADOW_STACK_ENABLE         (1UL << 0)
+# define PR_SHADOW_STACK_WRITE		(1UL << 1)
+# define PR_SHADOW_STACK_PUSH		(1UL << 2)
+
+#define	GCSPR_EL0 S3_3_C2_C5_1
+
+#define KSFT_SKIP 4
+
+.macro function name
+	.macro endfunction
+		.type \name, @function
+		.purgem endfunction
+	.endm
+\name:
+.endm
+
+// Print a single character x0 to stdout
+// Clobbers x0-x2,x8
+function putc
+	str	x0, [sp, #-16]!
+
+	mov	x0, #1			// STDOUT_FILENO
+	mov	x1, sp
+	mov	x2, #1
+	mov	x8, #__NR_write
+	svc	#0
+
+	add	sp, sp, #16
+	ret
+endfunction
+.globl	putc
+
+// Print a NUL-terminated string starting at address x0 to stdout
+// Clobbers x0-x3,x8
+function puts
+	mov	x1, x0
+
+	mov	x2, #0
+0:	ldrb	w3, [x0], #1
+	cbz	w3, 1f
+	add	x2, x2, #1
+	b	0b
+
+1:	mov	w0, #1			// STDOUT_FILENO
+	mov	x8, #__NR_write
+	svc	#0
+
+	ret
+endfunction
+.globl	puts
+
+// Utility macro to print a literal string
+// Clobbers x0-x4,x8
+.macro puts string
+	.pushsection .rodata.str1.1, "aMS", @progbits, 1
+.L__puts_literal\@: .string "\string"
+	.popsection
+
+	ldr	x0, =.L__puts_literal\@
+	bl	puts
+.endm
+
+.globl _start
+function _start
+	// Run with GCS
+	mov	x0, PR_SET_SHADOW_STACK_STATUS
+	mov	x1, PR_SHADOW_STACK_ENABLE | PR_SHADOW_STACK_WRITE
+	mov	x2, xzr
+	mov	x3, xzr
+	mov	x4, xzr
+	mov	x5, xzr
+	mov	x8, #__NR_prctl
+	svc	#0
+	cbz	x0, 1f
+	puts	"Failed to enable GCS with write permission\n"
+	mov	x0, #KSFT_SKIP
+	b	2f
+1:
+	mrs	x0, GCSPR_EL0
+	sub	x0, x0, #8
+	.inst	0xd91f1c01	// GCSSTR x1, x0
+
+	mov	x0, #0
+2:
+	mov	x8, #__NR_exit
+	svc	#0
diff --git a/tools/testing/selftests/arm64/gcs/libc-gcs.c b/tools/testing/selftests/arm64/gcs/libc-gcs.c
new file mode 100644
index 000000000000..17b2fabfec38
--- /dev/null
+++ b/tools/testing/selftests/arm64/gcs/libc-gcs.c
@@ -0,0 +1,728 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023 ARM Limited.
+ */
+
+#define _GNU_SOURCE
+
+#include <pthread.h>
+#include <stdbool.h>
+
+#include <sys/auxv.h>
+#include <sys/mman.h>
+#include <sys/prctl.h>
+#include <sys/ptrace.h>
+#include <sys/uio.h>
+
+#include <asm/hwcap.h>
+#include <asm/mman.h>
+
+#include <linux/compiler.h>
+
+#include "kselftest_harness.h"
+
+#include "gcs-util.h"
+
+#define my_syscall2(num, arg1, arg2)                                          \
+({                                                                            \
+	register long _num  __asm__ ("x8") = (num);                           \
+	register long _arg1 __asm__ ("x0") = (long)(arg1);                    \
+	register long _arg2 __asm__ ("x1") = (long)(arg2);                    \
+	register long _arg3 __asm__ ("x2") = 0;                               \
+	register long _arg4 __asm__ ("x3") = 0;                               \
+	register long _arg5 __asm__ ("x4") = 0;                               \
+	                                                                      \
+	__asm__  volatile (                                                   \
+		"svc #0\n"                                                    \
+		: "=r"(_arg1)                                                 \
+		: "r"(_arg1), "r"(_arg2),                                     \
+		  "r"(_arg3), "r"(_arg4),                                     \
+		  "r"(_arg5), "r"(_num)					      \
+		: "memory", "cc"                                              \
+	);                                                                    \
+	_arg1;                                                                \
+})
+
+static noinline void gcs_recurse(int depth)
+{
+	if (depth)
+		gcs_recurse(depth - 1);
+
+	/* Prevent tail call optimization so we actually recurse */
+	asm volatile("dsb sy" : : : "memory");
+}
+
+/* Smoke test that a function call and return works*/
+TEST(can_call_function)
+{
+	gcs_recurse(0);
+}
+
+static void *gcs_test_thread(void *arg)
+{
+	int ret;
+	unsigned long mode;
+
+	/*
+	 * Some libcs don't seem to fill unused arguments with 0 but
+	 * the kernel validates this so we supply all 5 arguments.
+	 */
+	ret = prctl(PR_GET_SHADOW_STACK_STATUS, &mode, 0, 0, 0);
+	if (ret != 0) {
+		ksft_print_msg("PR_GET_SHADOW_STACK_STATUS failed: %d\n", ret);
+		return NULL;
+	}
+
+	if (!(mode & PR_SHADOW_STACK_ENABLE)) {
+		ksft_print_msg("GCS not enabled in thread, mode is %lu\n",
+			       mode);
+		return NULL;
+	}
+
+	/* Just in case... */
+	gcs_recurse(0);
+
+	/* Use a non-NULL value to indicate a pass */
+	return &gcs_test_thread;
+}
+
+/* Verify that if we start a new thread it has GCS enabled */
+TEST(gcs_enabled_thread)
+{
+	pthread_t thread;
+	void *thread_ret;
+	int ret;
+
+	ret = pthread_create(&thread, NULL, gcs_test_thread, NULL);
+	ASSERT_TRUE(ret == 0);
+	if (ret != 0)
+		return;
+
+	ret = pthread_join(thread, &thread_ret);
+	ASSERT_TRUE(ret == 0);
+	if (ret != 0)
+		return;
+
+	ASSERT_TRUE(thread_ret != NULL);
+}
+
+/* Read the GCS until we find the terminator */
+TEST(gcs_find_terminator)
+{
+	unsigned long *gcs, *cur;
+
+	gcs = get_gcspr();
+	cur = gcs;
+	while (*cur)
+		cur++;
+
+	ksft_print_msg("GCS in use from %p-%p\n", gcs, cur);
+
+	/*
+	 * We should have at least whatever called into this test so
+	 * the two pointer should differ.
+	 */
+	ASSERT_TRUE(gcs != cur);
+}
+
+/*
+ * We can access a GCS via ptrace
+ *
+ * This could usefully have a fixture but note that each test is
+ * fork()ed into a new child whcih causes issues.  Might be better to
+ * lift at least some of this out into a separate, non-harness, test
+ * program.
+ */
+TEST(ptrace_read_write)
+{
+	pid_t child, pid;
+	int ret, status;
+	siginfo_t si;
+	uint64_t val, rval, gcspr;
+	struct user_gcs child_gcs;
+	struct iovec iov, local_iov, remote_iov;
+
+	child = fork();
+	if (child == -1) {
+		ksft_print_msg("fork() failed: %d (%s)\n",
+			       errno, strerror(errno));
+		ASSERT_NE(child, -1);
+	}
+
+	if (child == 0) {
+		/*
+		 * In child, make sure there's something on the stack and
+		 * ask to be traced.
+		 */
+		gcs_recurse(0);
+		if (ptrace(PTRACE_TRACEME, -1, NULL, NULL))
+			ksft_exit_fail_msg("PTRACE_TRACEME %s",
+					   strerror(errno));
+
+		if (raise(SIGSTOP))
+			ksft_exit_fail_msg("raise(SIGSTOP) %s",
+					   strerror(errno));
+
+		return;
+	}
+
+	ksft_print_msg("Child: %d\n", child);
+
+	/* Attach to the child */
+	while (1) {
+		int sig;
+
+		pid = wait(&status);
+		if (pid == -1) {
+			ksft_print_msg("wait() failed: %s",
+				       strerror(errno));
+			goto error;
+		}
+
+		/*
+		 * This should never happen but it's hard to flag in
+		 * the framework.
+		 */
+		if (pid != child)
+			continue;
+
+		if (WIFEXITED(status) || WIFSIGNALED(status))
+			ksft_exit_fail_msg("Child died unexpectedly\n");
+
+		if (!WIFSTOPPED(status))
+			goto error;
+
+		sig = WSTOPSIG(status);
+
+		if (ptrace(PTRACE_GETSIGINFO, pid, NULL, &si)) {
+			if (errno == ESRCH) {
+				ASSERT_NE(errno, ESRCH);
+				return;
+			}
+
+			if (errno == EINVAL) {
+				sig = 0; /* bust group-stop */
+				goto cont;
+			}
+
+			ksft_print_msg("PTRACE_GETSIGINFO: %s\n",
+				       strerror(errno));
+			goto error;
+		}
+
+		if (sig == SIGSTOP && si.si_code == SI_TKILL &&
+		    si.si_pid == pid)
+			break;
+
+	cont:
+		if (ptrace(PTRACE_CONT, pid, NULL, sig)) {
+			if (errno == ESRCH) {
+				ASSERT_NE(errno, ESRCH);
+				return;
+			}
+
+			ksft_print_msg("PTRACE_CONT: %s\n", strerror(errno));
+			goto error;
+		}
+	}
+
+	/* Where is the child GCS? */
+	iov.iov_base = &child_gcs;
+	iov.iov_len = sizeof(child_gcs);
+	ret = ptrace(PTRACE_GETREGSET, child, NT_ARM_GCS, &iov);
+	if (ret != 0) {
+		ksft_print_msg("Failed to read child GCS state: %s (%d)\n",
+			       strerror(errno), errno);
+		goto error;
+	}
+
+	/* We should have inherited GCS over fork(), confirm */
+	if (!(child_gcs.features_enabled & PR_SHADOW_STACK_ENABLE)) {
+		ASSERT_TRUE(child_gcs.features_enabled &
+			    PR_SHADOW_STACK_ENABLE);
+		goto error;
+	}
+
+	gcspr = child_gcs.gcspr_el0;
+	ksft_print_msg("Child GCSPR 0x%lx, flags %llx, locked %llx\n",
+		       gcspr, child_gcs.features_enabled,
+		       child_gcs.features_locked);
+
+	/* Ideally we'd cross check with the child memory map */
+
+	errno = 0;
+	val = ptrace(PTRACE_PEEKDATA, child, (void *)gcspr, NULL);
+	ret = errno;
+	if (ret != 0)
+		ksft_print_msg("PTRACE_PEEKDATA failed: %s (%d)\n",
+			       strerror(ret), ret);
+	EXPECT_EQ(ret, 0);
+
+	/* The child should be in a function, the GCSPR shouldn't be 0 */
+	EXPECT_NE(val, 0);
+
+	/* Same thing via process_vm_readv() */
+	local_iov.iov_base = &rval;
+	local_iov.iov_len = sizeof(rval);
+	remote_iov.iov_base = (void *)gcspr;
+	remote_iov.iov_len = sizeof(rval);
+	ret = process_vm_readv(child, &local_iov, 1, &remote_iov, 1, 0);
+	if (ret == -1)
+		ksft_print_msg("process_vm_readv() failed: %s (%d)\n",
+			       strerror(errno), errno);
+	EXPECT_EQ(ret, sizeof(rval));
+	EXPECT_EQ(val, rval);
+
+	/* Write data via a peek */
+	ret = ptrace(PTRACE_POKEDATA, child, (void *)gcspr, NULL);
+	if (ret == -1)
+		ksft_print_msg("PTRACE_POKEDATA failed: %s (%d)\n",
+			       strerror(errno), errno);
+	EXPECT_EQ(ret, 0);
+	EXPECT_EQ(0, ptrace(PTRACE_PEEKDATA, child, (void *)gcspr, NULL));
+
+	/* Restore what we had before */
+	ret = ptrace(PTRACE_POKEDATA, child, (void *)gcspr, val);
+	if (ret == -1)
+		ksft_print_msg("PTRACE_POKEDATA failed: %s (%d)\n",
+			       strerror(errno), errno);
+	EXPECT_EQ(ret, 0);
+	EXPECT_EQ(val, ptrace(PTRACE_PEEKDATA, child, (void *)gcspr, NULL));
+
+	/* That's all, folks */
+	kill(child, SIGKILL);
+	return;
+
+error:
+	kill(child, SIGKILL);
+	ASSERT_FALSE(true);
+}
+
+FIXTURE(map_gcs)
+{
+	unsigned long *stack;
+};
+
+FIXTURE_VARIANT(map_gcs)
+{
+	size_t stack_size;
+	unsigned long flags;
+};
+
+FIXTURE_VARIANT_ADD(map_gcs, s2k_cap_marker)
+{
+	.stack_size = 2 * 1024,
+	.flags = SHADOW_STACK_SET_MARKER | SHADOW_STACK_SET_TOKEN,
+};
+
+FIXTURE_VARIANT_ADD(map_gcs, s2k_cap)
+{
+	.stack_size = 2 * 1024,
+	.flags = SHADOW_STACK_SET_TOKEN,
+};
+
+FIXTURE_VARIANT_ADD(map_gcs, s2k_marker)
+{
+	.stack_size = 2 * 1024,
+	.flags = SHADOW_STACK_SET_MARKER,
+};
+
+FIXTURE_VARIANT_ADD(map_gcs, s2k)
+{
+	.stack_size = 2 * 1024,
+	.flags = 0,
+};
+
+FIXTURE_VARIANT_ADD(map_gcs, s4k_cap_marker)
+{
+	.stack_size = 4 * 1024,
+	.flags = SHADOW_STACK_SET_MARKER | SHADOW_STACK_SET_TOKEN,
+};
+
+FIXTURE_VARIANT_ADD(map_gcs, s4k_cap)
+{
+	.stack_size = 4 * 1024,
+	.flags = SHADOW_STACK_SET_TOKEN,
+};
+
+FIXTURE_VARIANT_ADD(map_gcs, s3k_marker)
+{
+	.stack_size = 4 * 1024,
+	.flags = SHADOW_STACK_SET_MARKER,
+};
+
+FIXTURE_VARIANT_ADD(map_gcs, s4k)
+{
+	.stack_size = 4 * 1024,
+	.flags = 0,
+};
+
+FIXTURE_VARIANT_ADD(map_gcs, s16k_cap_marker)
+{
+	.stack_size = 16 * 1024,
+	.flags = SHADOW_STACK_SET_MARKER | SHADOW_STACK_SET_TOKEN,
+};
+
+FIXTURE_VARIANT_ADD(map_gcs, s16k_cap)
+{
+	.stack_size = 16 * 1024,
+	.flags = SHADOW_STACK_SET_TOKEN,
+};
+
+FIXTURE_VARIANT_ADD(map_gcs, s16k_marker)
+{
+	.stack_size = 16 * 1024,
+	.flags = SHADOW_STACK_SET_MARKER,
+};
+
+FIXTURE_VARIANT_ADD(map_gcs, s16k)
+{
+	.stack_size = 16 * 1024,
+	.flags = 0,
+};
+
+FIXTURE_VARIANT_ADD(map_gcs, s64k_cap_marker)
+{
+	.stack_size = 64 * 1024,
+	.flags = SHADOW_STACK_SET_MARKER | SHADOW_STACK_SET_TOKEN,
+};
+
+FIXTURE_VARIANT_ADD(map_gcs, s64k_cap)
+{
+	.stack_size = 64 * 1024,
+	.flags = SHADOW_STACK_SET_TOKEN,
+};
+
+FIXTURE_VARIANT_ADD(map_gcs, s64k_marker)
+{
+	.stack_size = 64 * 1024,
+	.flags = SHADOW_STACK_SET_MARKER,
+};
+
+FIXTURE_VARIANT_ADD(map_gcs, s64k)
+{
+	.stack_size = 64 * 1024,
+	.flags = 0,
+};
+
+FIXTURE_VARIANT_ADD(map_gcs, s128k_cap_marker)
+{
+	.stack_size = 128 * 1024,
+	.flags = SHADOW_STACK_SET_MARKER | SHADOW_STACK_SET_TOKEN,
+};
+
+FIXTURE_VARIANT_ADD(map_gcs, s128k_cap)
+{
+	.stack_size = 128 * 1024,
+	.flags = SHADOW_STACK_SET_TOKEN,
+};
+
+FIXTURE_VARIANT_ADD(map_gcs, s128k_marker)
+{
+	.stack_size = 128 * 1024,
+	.flags = SHADOW_STACK_SET_MARKER,
+};
+
+FIXTURE_VARIANT_ADD(map_gcs, s128k)
+{
+	.stack_size = 128 * 1024,
+	.flags = 0,
+};
+
+FIXTURE_SETUP(map_gcs)
+{
+	self->stack = (void *)syscall(__NR_map_shadow_stack, 0,
+				      variant->stack_size, 
+				      variant->flags);
+	ASSERT_FALSE(self->stack == MAP_FAILED);
+	ksft_print_msg("Allocated stack from %p-%p\n", self->stack,
+		       self->stack + variant->stack_size);
+}
+
+FIXTURE_TEARDOWN(map_gcs)
+{
+	int ret;
+
+	if (self->stack != MAP_FAILED) {
+		ret = munmap(self->stack, variant->stack_size);
+		ASSERT_EQ(ret, 0);
+	}
+}
+
+/* The stack has a cap token */
+TEST_F(map_gcs, stack_capped)
+{
+	unsigned long *stack = self->stack;
+	size_t cap_index;
+
+	cap_index = (variant->stack_size / sizeof(unsigned long));
+
+	switch (variant->flags & (SHADOW_STACK_SET_MARKER | SHADOW_STACK_SET_TOKEN)) {
+	case SHADOW_STACK_SET_MARKER | SHADOW_STACK_SET_TOKEN:
+		cap_index -= 2;
+		break;
+	case SHADOW_STACK_SET_TOKEN:
+		cap_index -= 1;
+		break;
+	case SHADOW_STACK_SET_MARKER:
+	case 0:
+		/* No cap, no test */
+		return;
+	}
+
+	ASSERT_EQ(stack[cap_index], GCS_CAP(&stack[cap_index]));
+}
+
+/* The top of the stack is 0 */
+TEST_F(map_gcs, stack_terminated)
+{
+	unsigned long *stack = self->stack;
+	size_t term_index;
+
+	if (!(variant->flags & SHADOW_STACK_SET_MARKER))
+		return;
+
+	term_index = (variant->stack_size / sizeof(unsigned long)) - 1;
+
+	ASSERT_EQ(stack[term_index], 0);
+}
+
+/* Writes should fault */
+TEST_F_SIGNAL(map_gcs, not_writeable, SIGSEGV)
+{
+	self->stack[0] = 0;
+}
+
+/* Put it all together, we can safely switch to and from the stack */
+TEST_F(map_gcs, stack_switch)
+{
+	size_t cap_index;
+	cap_index = (variant->stack_size / sizeof(unsigned long));
+	unsigned long *orig_gcspr_el0, *pivot_gcspr_el0;
+
+	/* Skip over the stack terminator and point at the cap */
+	switch (variant->flags & (SHADOW_STACK_SET_MARKER | SHADOW_STACK_SET_TOKEN)) {
+	case SHADOW_STACK_SET_MARKER | SHADOW_STACK_SET_TOKEN:
+		cap_index -= 2;
+		break;
+	case SHADOW_STACK_SET_TOKEN:
+		cap_index -= 1;
+		break;
+	case SHADOW_STACK_SET_MARKER:
+	case 0:
+		/* No cap, no test */
+		return;
+	}
+	pivot_gcspr_el0 = &self->stack[cap_index];
+
+	/* Pivot to the new GCS */
+	ksft_print_msg("Pivoting to %p from %p, target has value 0x%lx\n",
+		       pivot_gcspr_el0, get_gcspr(),
+		       *pivot_gcspr_el0);
+	gcsss1(pivot_gcspr_el0);
+	orig_gcspr_el0 = gcsss2();
+	ksft_print_msg("Pivoted to %p from %p, target has value 0x%lx\n",
+		       get_gcspr(), orig_gcspr_el0,
+		       *pivot_gcspr_el0);
+
+	ksft_print_msg("Pivoted, GCSPR_EL0 now %p\n", get_gcspr());
+
+	/* New GCS must be in the new buffer */
+	ASSERT_TRUE((unsigned long)get_gcspr() > (unsigned long)self->stack);
+	ASSERT_TRUE((unsigned long)get_gcspr() <=
+		    (unsigned long)self->stack + variant->stack_size);
+
+	/* We should be able to use all but 2 slots of the new stack */
+	ksft_print_msg("Recursing %zu levels\n", cap_index - 1);
+	gcs_recurse(cap_index - 1);
+
+	/* Pivot back to the original GCS */
+	gcsss1(orig_gcspr_el0);
+	pivot_gcspr_el0 = gcsss2();
+
+	gcs_recurse(0);
+	ksft_print_msg("Pivoted back to GCSPR_EL0 0x%p\n", get_gcspr());
+}
+
+/* We fault if we try to go beyond the end of the stack */
+TEST_F_SIGNAL(map_gcs, stack_overflow, SIGSEGV)
+{
+	size_t cap_index;
+	cap_index = (variant->stack_size / sizeof(unsigned long));
+	unsigned long *orig_gcspr_el0, *pivot_gcspr_el0;
+
+	/* Skip over the stack terminator and point at the cap */
+	switch (variant->flags & (SHADOW_STACK_SET_MARKER | SHADOW_STACK_SET_TOKEN)) {
+	case SHADOW_STACK_SET_MARKER | SHADOW_STACK_SET_TOKEN:
+		cap_index -= 2;
+		break;
+	case SHADOW_STACK_SET_TOKEN:
+		cap_index -= 1;
+		break;
+	case SHADOW_STACK_SET_MARKER:
+	case 0:
+		/* No cap, no test but we need to SEGV to avoid a false fail */
+		orig_gcspr_el0 = get_gcspr();
+		*orig_gcspr_el0 = 0;
+		return;
+	}
+	pivot_gcspr_el0 = &self->stack[cap_index];
+
+	/* Pivot to the new GCS */
+	ksft_print_msg("Pivoting to %p from %p, target has value 0x%lx\n",
+		       pivot_gcspr_el0, get_gcspr(),
+		       *pivot_gcspr_el0);
+	gcsss1(pivot_gcspr_el0);
+	orig_gcspr_el0 = gcsss2();
+	ksft_print_msg("Pivoted to %p from %p, target has value 0x%lx\n",
+		       pivot_gcspr_el0, orig_gcspr_el0,
+		       *pivot_gcspr_el0);
+
+	ksft_print_msg("Pivoted, GCSPR_EL0 now %p\n", get_gcspr());
+
+	/* New GCS must be in the new buffer */
+	ASSERT_TRUE((unsigned long)get_gcspr() > (unsigned long)self->stack);
+	ASSERT_TRUE((unsigned long)get_gcspr() <=
+		    (unsigned long)self->stack + variant->stack_size);
+
+	/* Now try to recurse, we should fault doing this. */
+	ksft_print_msg("Recursing %zu levels...\n", cap_index + 1);
+	gcs_recurse(cap_index + 1);
+	ksft_print_msg("...done\n");
+
+	/* Clean up properly to try to guard against spurious passes. */
+	gcsss1(orig_gcspr_el0);
+	pivot_gcspr_el0 = gcsss2();
+	ksft_print_msg("Pivoted back to GCSPR_EL0 0x%p\n", get_gcspr());
+}
+
+FIXTURE(map_invalid_gcs)
+{
+};
+
+FIXTURE_VARIANT(map_invalid_gcs)
+{
+	size_t stack_size;
+};
+
+FIXTURE_SETUP(map_invalid_gcs)
+{
+}
+
+FIXTURE_TEARDOWN(map_invalid_gcs)
+{
+}
+
+/* GCS must be larger than 16 bytes */
+FIXTURE_VARIANT_ADD(map_invalid_gcs, too_small)
+{
+	.stack_size = 8,
+};
+
+/* GCS size must be 16 byte aligned */
+FIXTURE_VARIANT_ADD(map_invalid_gcs, unligned_1)  { .stack_size = 1024 + 1  };
+FIXTURE_VARIANT_ADD(map_invalid_gcs, unligned_2)  { .stack_size = 1024 + 2  };
+FIXTURE_VARIANT_ADD(map_invalid_gcs, unligned_3)  { .stack_size = 1024 + 3  };
+FIXTURE_VARIANT_ADD(map_invalid_gcs, unligned_4)  { .stack_size = 1024 + 4  };
+FIXTURE_VARIANT_ADD(map_invalid_gcs, unligned_5)  { .stack_size = 1024 + 5  };
+FIXTURE_VARIANT_ADD(map_invalid_gcs, unligned_6)  { .stack_size = 1024 + 6  };
+FIXTURE_VARIANT_ADD(map_invalid_gcs, unligned_7)  { .stack_size = 1024 + 7  };
+
+TEST_F(map_invalid_gcs, do_map)
+{
+	void *stack;
+
+	stack = (void *)syscall(__NR_map_shadow_stack, 0,
+				variant->stack_size, 0);
+	ASSERT_TRUE(stack == MAP_FAILED);
+	if (stack != MAP_FAILED)
+		munmap(stack, variant->stack_size);
+}
+
+FIXTURE(invalid_mprotect)
+{
+	unsigned long *stack;
+	size_t stack_size;
+};
+
+FIXTURE_VARIANT(invalid_mprotect)
+{
+	unsigned long flags;
+};
+
+FIXTURE_SETUP(invalid_mprotect)
+{
+	self->stack_size = sysconf(_SC_PAGE_SIZE);
+	self->stack = (void *)syscall(__NR_map_shadow_stack, 0,
+				      self->stack_size, 0);
+	ASSERT_FALSE(self->stack == MAP_FAILED);
+	ksft_print_msg("Allocated stack from %p-%p\n", self->stack,
+		       self->stack + self->stack_size);
+}
+
+FIXTURE_TEARDOWN(invalid_mprotect)
+{
+	int ret;
+
+	if (self->stack != MAP_FAILED) {
+		ret = munmap(self->stack, self->stack_size);
+		ASSERT_EQ(ret, 0);
+	}
+}
+
+FIXTURE_VARIANT_ADD(invalid_mprotect, exec)
+{
+	.flags = PROT_EXEC,
+};
+
+TEST_F(invalid_mprotect, do_map)
+{
+	int ret;
+
+	ret = mprotect(self->stack, self->stack_size, variant->flags);
+	ASSERT_EQ(ret, -1);
+}
+
+TEST_F(invalid_mprotect, do_map_read)
+{
+	int ret;
+
+	ret = mprotect(self->stack, self->stack_size,
+		       variant->flags | PROT_READ);
+	ASSERT_EQ(ret, -1);
+}
+
+int main(int argc, char **argv)
+{
+	unsigned long gcs_mode;
+	int ret;
+
+	if (!(getauxval(AT_HWCAP) & HWCAP_GCS))
+		ksft_exit_skip("SKIP GCS not supported\n");
+
+	/* 
+	 * Force shadow stacks on, our tests *should* be fine with or
+	 * without libc support and with or without this having ended
+	 * up tagged for GCS and enabled by the dynamic linker.  We
+	 * can't use the libc prctl() function since we can't return
+	 * from enabling the stack.
+	 */
+	ret = my_syscall2(__NR_prctl, PR_GET_SHADOW_STACK_STATUS, &gcs_mode);
+	if (ret) {
+		ksft_print_msg("Failed to read GCS state: %d\n", ret);
+		return EXIT_FAILURE;
+	}
+	
+	if (!(gcs_mode & PR_SHADOW_STACK_ENABLE)) {
+		gcs_mode = PR_SHADOW_STACK_ENABLE;
+		ret = my_syscall2(__NR_prctl, PR_SET_SHADOW_STACK_STATUS,
+				  gcs_mode);
+		if (ret) {
+			ksft_print_msg("Failed to configure GCS: %d\n", ret);
+			return EXIT_FAILURE;
+		}
+	}
+
+	/* Avoid returning in case libc doesn't understand GCS */
+	exit(test_harness_run(argc, argv));
+}
diff --git a/tools/testing/selftests/arm64/mte/Makefile b/tools/testing/selftests/arm64/mte/Makefile
index 037046f5784e..0d7ac3db8390 100644
--- a/tools/testing/selftests/arm64/mte/Makefile
+++ b/tools/testing/selftests/arm64/mte/Makefile
@@ -1,24 +1,33 @@
 # SPDX-License-Identifier: GPL-2.0
 # Copyright (C) 2020 ARM Limited
 
-# preserve CC value from top level Makefile
-ifeq ($(CC),cc)
-CC := $(CROSS_COMPILE)gcc
-endif
-
 CFLAGS += -std=gnu99 -I. -pthread
 LDFLAGS += -pthread
 SRCS := $(filter-out mte_common_util.c,$(wildcard *.c))
 PROGS := $(patsubst %.c,%,$(SRCS))
 
+ifeq ($(LLVM),)
+# For GCC check that the toolchain has MTE support.
+
+# preserve CC value from top level Makefile
+ifeq ($(CC),cc)
+CC := $(CROSS_COMPILE)gcc
+endif
+
 #check if the compiler works well
 mte_cc_support := $(shell if ($(CC) $(CFLAGS) -march=armv8.5-a+memtag -E -x c /dev/null -o /dev/null 2>&1) then echo "1"; fi)
 
+else
+
+# All supported clang versions also support MTE.
+mte_cc_support := 1
+
+endif
+
 ifeq ($(mte_cc_support),1)
 # Generated binaries to be installed by top KSFT script
 TEST_GEN_PROGS := $(PROGS)
 
-# Get Kernel headers installed and use them.
 else
     $(warning compiler "$(CC)" does not support the ARMv8.5 MTE extension.)
     $(warning test program "mte" will not be created.)
diff --git a/tools/testing/selftests/arm64/mte/check_buffer_fill.c b/tools/testing/selftests/arm64/mte/check_buffer_fill.c
index 1dbbbd47dd50..ff4e07503349 100644
--- a/tools/testing/selftests/arm64/mte/check_buffer_fill.c
+++ b/tools/testing/selftests/arm64/mte/check_buffer_fill.c
@@ -31,7 +31,7 @@ static int check_buffer_by_byte(int mem_type, int mode)
 	int i, j, item;
 	bool err;
 
-	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG);
+	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false);
 	item = ARRAY_SIZE(sizes);
 
 	for (i = 0; i < item; i++) {
@@ -68,7 +68,7 @@ static int check_buffer_underflow_by_byte(int mem_type, int mode,
 	bool err;
 	char *und_ptr = NULL;
 
-	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG);
+	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false);
 	item = ARRAY_SIZE(sizes);
 	for (i = 0; i < item; i++) {
 		ptr = (char *)mte_allocate_memory_tag_range(sizes[i], mem_type, 0,
@@ -91,7 +91,7 @@ static int check_buffer_underflow_by_byte(int mem_type, int mode,
 		for (j = 0; j < sizes[i]; j++) {
 			if (ptr[j] != '1') {
 				err = true;
-				ksft_print_msg("Buffer is not filled at index:%d of ptr:0x%lx\n",
+				ksft_print_msg("Buffer is not filled at index:%d of ptr:0x%p\n",
 						j, ptr);
 				break;
 			}
@@ -164,7 +164,7 @@ static int check_buffer_overflow_by_byte(int mem_type, int mode,
 	size_t tagged_size, overflow_size;
 	char *over_ptr = NULL;
 
-	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG);
+	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false);
 	item = ARRAY_SIZE(sizes);
 	for (i = 0; i < item; i++) {
 		ptr = (char *)mte_allocate_memory_tag_range(sizes[i], mem_type, 0,
@@ -189,7 +189,7 @@ static int check_buffer_overflow_by_byte(int mem_type, int mode,
 		for (j = 0; j < sizes[i]; j++) {
 			if (ptr[j] != '1') {
 				err = true;
-				ksft_print_msg("Buffer is not filled at index:%d of ptr:0x%lx\n",
+				ksft_print_msg("Buffer is not filled at index:%d of ptr:0x%p\n",
 						j, ptr);
 				break;
 			}
@@ -337,7 +337,7 @@ static int check_buffer_by_block(int mem_type, int mode)
 {
 	int i, item, result = KSFT_PASS;
 
-	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG);
+	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false);
 	item = ARRAY_SIZE(sizes);
 	cur_mte_cxt.fault_valid = false;
 	for (i = 0; i < item; i++) {
@@ -368,7 +368,7 @@ static int check_memory_initial_tags(int mem_type, int mode, int mapping)
 	int run, fd;
 	int total = ARRAY_SIZE(sizes);
 
-	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG);
+	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false);
 	for (run = 0; run < total; run++) {
 		/* check initial tags for anonymous mmap */
 		ptr = (char *)mte_allocate_memory(sizes[run], mem_type, mapping, false);
@@ -415,7 +415,7 @@ int main(int argc, char *argv[])
 		return err;
 
 	/* Register SIGSEGV handler */
-	mte_register_signal(SIGSEGV, mte_default_handler);
+	mte_register_signal(SIGSEGV, mte_default_handler, false);
 
 	/* Set test plan */
 	ksft_set_plan(20);
diff --git a/tools/testing/selftests/arm64/mte/check_child_memory.c b/tools/testing/selftests/arm64/mte/check_child_memory.c
index 7597fc632cad..5e97ee792e4d 100644
--- a/tools/testing/selftests/arm64/mte/check_child_memory.c
+++ b/tools/testing/selftests/arm64/mte/check_child_memory.c
@@ -88,7 +88,7 @@ static int check_child_memory_mapping(int mem_type, int mode, int mapping)
 	int item = ARRAY_SIZE(sizes);
 
 	item = ARRAY_SIZE(sizes);
-	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG);
+	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false);
 	for (run = 0; run < item; run++) {
 		ptr = (char *)mte_allocate_memory_tag_range(sizes[run], mem_type, mapping,
 							    UNDERFLOW, OVERFLOW);
@@ -109,7 +109,7 @@ static int check_child_file_mapping(int mem_type, int mode, int mapping)
 	int run, fd, map_size, result = KSFT_PASS;
 	int total = ARRAY_SIZE(sizes);
 
-	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG);
+	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false);
 	for (run = 0; run < total; run++) {
 		fd = create_temp_file();
 		if (fd == -1)
@@ -160,8 +160,8 @@ int main(int argc, char *argv[])
 		return err;
 
 	/* Register SIGSEGV handler */
-	mte_register_signal(SIGSEGV, mte_default_handler);
-	mte_register_signal(SIGBUS, mte_default_handler);
+	mte_register_signal(SIGSEGV, mte_default_handler, false);
+	mte_register_signal(SIGBUS, mte_default_handler, false);
 
 	/* Set test plan */
 	ksft_set_plan(12);
diff --git a/tools/testing/selftests/arm64/mte/check_hugetlb_options.c b/tools/testing/selftests/arm64/mte/check_hugetlb_options.c
new file mode 100644
index 000000000000..aad1234c7e0f
--- /dev/null
+++ b/tools/testing/selftests/arm64/mte/check_hugetlb_options.c
@@ -0,0 +1,296 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2024 Ampere Computing LLC
+
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <fcntl.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <ucontext.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+
+#include "kselftest.h"
+#include "mte_common_util.h"
+#include "mte_def.h"
+
+#define TAG_CHECK_ON		0
+#define TAG_CHECK_OFF		1
+
+static unsigned long default_huge_page_size(void)
+{
+	unsigned long hps = 0;
+	char *line = NULL;
+	size_t linelen = 0;
+	FILE *f = fopen("/proc/meminfo", "r");
+
+	if (!f)
+		return 0;
+	while (getline(&line, &linelen, f) > 0) {
+		if (sscanf(line, "Hugepagesize:       %lu kB", &hps) == 1) {
+			hps <<= 10;
+			break;
+		}
+	}
+
+	free(line);
+	fclose(f);
+	return hps;
+}
+
+static bool is_hugetlb_allocated(void)
+{
+	unsigned long hps = 0;
+	char *line = NULL;
+	size_t linelen = 0;
+	FILE *f = fopen("/proc/meminfo", "r");
+
+	if (!f)
+		return false;
+	while (getline(&line, &linelen, f) > 0) {
+		if (sscanf(line, "Hugetlb:       %lu kB", &hps) == 1) {
+			hps <<= 10;
+			break;
+		}
+	}
+
+	free(line);
+	fclose(f);
+
+	if (hps > 0)
+		return true;
+
+	return false;
+}
+
+static void write_sysfs(char *str, unsigned long val)
+{
+	FILE *f;
+
+	f = fopen(str, "w");
+	if (!f) {
+		ksft_print_msg("ERR: missing %s\n", str);
+		return;
+	}
+	fprintf(f, "%lu", val);
+	fclose(f);
+}
+
+static void allocate_hugetlb()
+{
+	write_sysfs("/proc/sys/vm/nr_hugepages", 2);
+}
+
+static void free_hugetlb()
+{
+	write_sysfs("/proc/sys/vm/nr_hugepages", 0);
+}
+
+static int check_child_tag_inheritance(char *ptr, int size, int mode)
+{
+	int i, parent_tag, child_tag, fault, child_status;
+	pid_t child;
+
+	parent_tag = MT_FETCH_TAG((uintptr_t)ptr);
+	fault = 0;
+
+	child = fork();
+	if (child == -1) {
+		ksft_print_msg("FAIL: child process creation\n");
+		return KSFT_FAIL;
+	} else if (child == 0) {
+		mte_initialize_current_context(mode, (uintptr_t)ptr, size);
+		/* Do copy on write */
+		memset(ptr, '1', size);
+		mte_wait_after_trig();
+		if (cur_mte_cxt.fault_valid == true) {
+			fault = 1;
+			goto check_child_tag_inheritance_err;
+		}
+		for (i = 0; i < size; i += MT_GRANULE_SIZE) {
+			child_tag = MT_FETCH_TAG((uintptr_t)(mte_get_tag_address(ptr + i)));
+			if (parent_tag != child_tag) {
+				ksft_print_msg("FAIL: child mte tag (%d) mismatch\n", i);
+				fault = 1;
+				goto check_child_tag_inheritance_err;
+			}
+		}
+check_child_tag_inheritance_err:
+		_exit(fault);
+	}
+	/* Wait for child process to terminate */
+	wait(&child_status);
+	if (WIFEXITED(child_status))
+		fault = WEXITSTATUS(child_status);
+	else
+		fault = 1;
+	return (fault) ? KSFT_FAIL : KSFT_PASS;
+}
+
+static int check_mte_memory(char *ptr, int size, int mode, int tag_check)
+{
+	mte_initialize_current_context(mode, (uintptr_t)ptr, size);
+	memset(ptr, '1', size);
+	mte_wait_after_trig();
+	if (cur_mte_cxt.fault_valid == true)
+		return KSFT_FAIL;
+
+	return KSFT_PASS;
+}
+
+static int check_hugetlb_memory_mapping(int mem_type, int mode, int mapping, int tag_check)
+{
+	char *ptr, *map_ptr;
+	int result;
+	unsigned long map_size;
+
+	map_size = default_huge_page_size();
+
+	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false);
+	map_ptr = (char *)mte_allocate_memory(map_size, mem_type, mapping, false);
+	if (check_allocated_memory(map_ptr, map_size, mem_type, false) != KSFT_PASS)
+		return KSFT_FAIL;
+
+	mte_initialize_current_context(mode, (uintptr_t)map_ptr, map_size);
+	/* Only mte enabled memory will allow tag insertion */
+	ptr = mte_insert_tags((void *)map_ptr, map_size);
+	if (!ptr || cur_mte_cxt.fault_valid == true) {
+		ksft_print_msg("FAIL: Insert tags on anonymous mmap memory\n");
+		munmap((void *)map_ptr, map_size);
+		return KSFT_FAIL;
+	}
+	result = check_mte_memory(ptr, map_size, mode, tag_check);
+	mte_clear_tags((void *)ptr, map_size);
+	mte_free_memory((void *)map_ptr, map_size, mem_type, false);
+	if (result == KSFT_FAIL)
+		return KSFT_FAIL;
+
+	return KSFT_PASS;
+}
+
+static int check_clear_prot_mte_flag(int mem_type, int mode, int mapping)
+{
+	char *map_ptr;
+	int prot_flag, result;
+	unsigned long map_size;
+
+	prot_flag = PROT_READ | PROT_WRITE;
+	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false);
+	map_size = default_huge_page_size();
+	map_ptr = (char *)mte_allocate_memory_tag_range(map_size, mem_type, mapping,
+							0, 0);
+	if (check_allocated_memory_range(map_ptr, map_size, mem_type,
+					 0, 0) != KSFT_PASS)
+		return KSFT_FAIL;
+	/* Try to clear PROT_MTE property and verify it by tag checking */
+	if (mprotect(map_ptr, map_size, prot_flag)) {
+		mte_free_memory_tag_range((void *)map_ptr, map_size, mem_type,
+					  0, 0);
+		ksft_print_msg("FAIL: mprotect not ignoring clear PROT_MTE property\n");
+		return KSFT_FAIL;
+	}
+	result = check_mte_memory(map_ptr, map_size, mode, TAG_CHECK_ON);
+	mte_free_memory_tag_range((void *)map_ptr, map_size, mem_type, 0, 0);
+	if (result != KSFT_PASS)
+		return KSFT_FAIL;
+
+	return KSFT_PASS;
+}
+
+static int check_child_hugetlb_memory_mapping(int mem_type, int mode, int mapping)
+{
+	char *ptr;
+	int result;
+	unsigned long map_size;
+
+	map_size = default_huge_page_size();
+
+	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false);
+	ptr = (char *)mte_allocate_memory_tag_range(map_size, mem_type, mapping,
+						    0, 0);
+	if (check_allocated_memory_range(ptr, map_size, mem_type,
+					 0, 0) != KSFT_PASS)
+		return KSFT_FAIL;
+	result = check_child_tag_inheritance(ptr, map_size, mode);
+	mte_free_memory_tag_range((void *)ptr, map_size, mem_type, 0, 0);
+	if (result == KSFT_FAIL)
+		return result;
+
+	return KSFT_PASS;
+}
+
+int main(int argc, char *argv[])
+{
+	int err;
+	void *map_ptr;
+	unsigned long map_size;
+
+	err = mte_default_setup();
+	if (err)
+		return err;
+
+	/* Register signal handlers */
+	mte_register_signal(SIGBUS, mte_default_handler, false);
+	mte_register_signal(SIGSEGV, mte_default_handler, false);
+
+	allocate_hugetlb();
+
+	if (!is_hugetlb_allocated()) {
+		ksft_print_msg("ERR: Unable allocate hugetlb pages\n");
+		return KSFT_FAIL;
+	}
+
+	/* Check if MTE supports hugetlb mappings */
+	map_size = default_huge_page_size();
+	map_ptr = mmap(NULL, map_size, PROT_READ | PROT_MTE,
+		       MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0);
+	if (map_ptr == MAP_FAILED)
+		ksft_exit_skip("PROT_MTE not supported with MAP_HUGETLB mappings\n");
+	else
+		munmap(map_ptr, map_size);
+
+	/* Set test plan */
+	ksft_set_plan(12);
+
+	mte_enable_pstate_tco();
+
+	evaluate_test(check_hugetlb_memory_mapping(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE | MAP_HUGETLB, TAG_CHECK_OFF),
+	"Check hugetlb memory with private mapping, sync error mode, mmap memory and tag check off\n");
+
+	mte_disable_pstate_tco();
+	evaluate_test(check_hugetlb_memory_mapping(USE_MMAP, MTE_NONE_ERR, MAP_PRIVATE | MAP_HUGETLB, TAG_CHECK_OFF),
+	"Check hugetlb memory with private mapping, no error mode, mmap memory and tag check off\n");
+
+	evaluate_test(check_hugetlb_memory_mapping(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE | MAP_HUGETLB, TAG_CHECK_ON),
+	"Check hugetlb memory with private mapping, sync error mode, mmap memory and tag check on\n");
+	evaluate_test(check_hugetlb_memory_mapping(USE_MPROTECT, MTE_SYNC_ERR, MAP_PRIVATE | MAP_HUGETLB, TAG_CHECK_ON),
+	"Check hugetlb memory with private mapping, sync error mode, mmap/mprotect memory and tag check on\n");
+	evaluate_test(check_hugetlb_memory_mapping(USE_MMAP, MTE_ASYNC_ERR, MAP_PRIVATE | MAP_HUGETLB, TAG_CHECK_ON),
+	"Check hugetlb memory with private mapping, async error mode, mmap memory and tag check on\n");
+	evaluate_test(check_hugetlb_memory_mapping(USE_MPROTECT, MTE_ASYNC_ERR, MAP_PRIVATE | MAP_HUGETLB, TAG_CHECK_ON),
+	"Check hugetlb memory with private mapping, async error mode, mmap/mprotect memory and tag check on\n");
+
+	evaluate_test(check_clear_prot_mte_flag(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE | MAP_HUGETLB),
+	"Check clear PROT_MTE flags with private mapping, sync error mode and mmap memory\n");
+	evaluate_test(check_clear_prot_mte_flag(USE_MPROTECT, MTE_SYNC_ERR, MAP_PRIVATE | MAP_HUGETLB),
+	"Check clear PROT_MTE flags with private mapping and sync error mode and mmap/mprotect memory\n");
+
+	evaluate_test(check_child_hugetlb_memory_mapping(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE | MAP_HUGETLB),
+		"Check child hugetlb memory with private mapping, sync error mode and mmap memory\n");
+	evaluate_test(check_child_hugetlb_memory_mapping(USE_MMAP, MTE_ASYNC_ERR, MAP_PRIVATE | MAP_HUGETLB),
+		"Check child hugetlb memory with private mapping, async error mode and mmap memory\n");
+	evaluate_test(check_child_hugetlb_memory_mapping(USE_MPROTECT, MTE_SYNC_ERR, MAP_PRIVATE | MAP_HUGETLB),
+		"Check child hugetlb memory with private mapping, sync error mode and mmap/mprotect memory\n");
+	evaluate_test(check_child_hugetlb_memory_mapping(USE_MPROTECT, MTE_ASYNC_ERR, MAP_PRIVATE | MAP_HUGETLB),
+		"Check child hugetlb memory with private mapping, async error mode and mmap/mprotect memory\n");
+
+	mte_restore_setup();
+	free_hugetlb();
+	ksft_print_cnts();
+	return ksft_get_fail_cnt() == 0 ? KSFT_PASS : KSFT_FAIL;
+}
diff --git a/tools/testing/selftests/arm64/mte/check_ksm_options.c b/tools/testing/selftests/arm64/mte/check_ksm_options.c
index 88c74bc46d4f..0cf5faef1724 100644
--- a/tools/testing/selftests/arm64/mte/check_ksm_options.c
+++ b/tools/testing/selftests/arm64/mte/check_ksm_options.c
@@ -106,7 +106,7 @@ static int check_madvise_options(int mem_type, int mode, int mapping)
 		return err;
 	}
 
-	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG);
+	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false);
 	ptr = mte_allocate_memory(TEST_UNIT * page_sz, mem_type, mapping, true);
 	if (check_allocated_memory(ptr, TEST_UNIT * page_sz, mem_type, false) != KSFT_PASS)
 		return KSFT_FAIL;
@@ -141,8 +141,8 @@ int main(int argc, char *argv[])
 		return KSFT_FAIL;
 	}
 	/* Register signal handlers */
-	mte_register_signal(SIGBUS, mte_default_handler);
-	mte_register_signal(SIGSEGV, mte_default_handler);
+	mte_register_signal(SIGBUS, mte_default_handler, false);
+	mte_register_signal(SIGSEGV, mte_default_handler, false);
 
 	/* Set test plan */
 	ksft_set_plan(4);
diff --git a/tools/testing/selftests/arm64/mte/check_mmap_options.c b/tools/testing/selftests/arm64/mte/check_mmap_options.c
index 17694caaff53..c100af3012cb 100644
--- a/tools/testing/selftests/arm64/mte/check_mmap_options.c
+++ b/tools/testing/selftests/arm64/mte/check_mmap_options.c
@@ -3,6 +3,7 @@
 
 #define _GNU_SOURCE
 
+#include <assert.h>
 #include <errno.h>
 #include <fcntl.h>
 #include <signal.h>
@@ -23,6 +24,35 @@
 #define OVERFLOW		MT_GRANULE_SIZE
 #define TAG_CHECK_ON		0
 #define TAG_CHECK_OFF		1
+#define ATAG_CHECK_ON		1
+#define ATAG_CHECK_OFF		0
+
+#define TEST_NAME_MAX		256
+
+enum mte_mem_check_type {
+	CHECK_ANON_MEM = 0,
+	CHECK_FILE_MEM = 1,
+	CHECK_CLEAR_PROT_MTE = 2,
+};
+
+enum mte_tag_op_type {
+	TAG_OP_ALL = 0,
+	TAG_OP_STONLY = 1,
+};
+
+struct check_mmap_testcase {
+	int check_type;
+	int mem_type;
+	int mte_sync;
+	int mapping;
+	int tag_check;
+	int atag_check;
+	int tag_op;
+	bool enable_tco;
+};
+
+#define TAG_OP_ALL		0
+#define TAG_OP_STONLY		1
 
 static size_t page_size;
 static int sizes[] = {
@@ -30,8 +60,17 @@ static int sizes[] = {
 	/* page size - 1*/ 0, /* page_size */ 0, /* page size + 1 */ 0
 };
 
-static int check_mte_memory(char *ptr, int size, int mode, int tag_check)
+static int check_mte_memory(char *ptr, int size, int mode,
+		int tag_check,int atag_check, int tag_op)
 {
+	char buf[MT_GRANULE_SIZE];
+
+	if (!mtefar_support && atag_check == ATAG_CHECK_ON)
+		return KSFT_SKIP;
+
+	if (atag_check == ATAG_CHECK_ON)
+		ptr = mte_insert_atag(ptr);
+
 	mte_initialize_current_context(mode, (uintptr_t)ptr, size);
 	memset(ptr, '1', size);
 	mte_wait_after_trig();
@@ -54,16 +93,34 @@ static int check_mte_memory(char *ptr, int size, int mode, int tag_check)
 	if (cur_mte_cxt.fault_valid == true && tag_check == TAG_CHECK_OFF)
 		return KSFT_FAIL;
 
+	if (tag_op == TAG_OP_STONLY) {
+		mte_initialize_current_context(mode, (uintptr_t)ptr, -UNDERFLOW);
+		memcpy(buf, ptr - UNDERFLOW, MT_GRANULE_SIZE);
+		mte_wait_after_trig();
+		if (cur_mte_cxt.fault_valid == true)
+			return KSFT_FAIL;
+
+		mte_initialize_current_context(mode, (uintptr_t)ptr, size + OVERFLOW);
+		memcpy(buf, ptr + size, MT_GRANULE_SIZE);
+		mte_wait_after_trig();
+		if (cur_mte_cxt.fault_valid == true)
+			return KSFT_FAIL;
+	}
+
 	return KSFT_PASS;
 }
 
-static int check_anonymous_memory_mapping(int mem_type, int mode, int mapping, int tag_check)
+static int check_anonymous_memory_mapping(int mem_type, int mode, int mapping,
+		int tag_check, int atag_check, int tag_op)
 {
 	char *ptr, *map_ptr;
 	int run, result, map_size;
 	int item = ARRAY_SIZE(sizes);
 
-	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG);
+	if (tag_op == TAG_OP_STONLY && !mtestonly_support)
+		return KSFT_SKIP;
+
+	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, tag_op);
 	for (run = 0; run < item; run++) {
 		map_size = sizes[run] + OVERFLOW + UNDERFLOW;
 		map_ptr = (char *)mte_allocate_memory(map_size, mem_type, mapping, false);
@@ -79,23 +136,27 @@ static int check_anonymous_memory_mapping(int mem_type, int mode, int mapping, i
 			munmap((void *)map_ptr, map_size);
 			return KSFT_FAIL;
 		}
-		result = check_mte_memory(ptr, sizes[run], mode, tag_check);
+		result = check_mte_memory(ptr, sizes[run], mode, tag_check, atag_check, tag_op);
 		mte_clear_tags((void *)ptr, sizes[run]);
 		mte_free_memory((void *)map_ptr, map_size, mem_type, false);
-		if (result == KSFT_FAIL)
-			return KSFT_FAIL;
+		if (result != KSFT_PASS)
+			return result;
 	}
 	return KSFT_PASS;
 }
 
-static int check_file_memory_mapping(int mem_type, int mode, int mapping, int tag_check)
+static int check_file_memory_mapping(int mem_type, int mode, int mapping,
+		int tag_check, int atag_check, int tag_op)
 {
 	char *ptr, *map_ptr;
 	int run, fd, map_size;
 	int total = ARRAY_SIZE(sizes);
 	int result = KSFT_PASS;
 
-	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG);
+	if (tag_op == TAG_OP_STONLY && !mtestonly_support)
+		return KSFT_SKIP;
+
+	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, tag_op);
 	for (run = 0; run < total; run++) {
 		fd = create_temp_file();
 		if (fd == -1)
@@ -117,24 +178,24 @@ static int check_file_memory_mapping(int mem_type, int mode, int mapping, int ta
 			close(fd);
 			return KSFT_FAIL;
 		}
-		result = check_mte_memory(ptr, sizes[run], mode, tag_check);
+		result = check_mte_memory(ptr, sizes[run], mode, tag_check, atag_check, tag_op);
 		mte_clear_tags((void *)ptr, sizes[run]);
 		munmap((void *)map_ptr, map_size);
 		close(fd);
-		if (result == KSFT_FAIL)
-			break;
+		if (result != KSFT_PASS)
+			return result;
 	}
-	return result;
+	return KSFT_PASS;
 }
 
-static int check_clear_prot_mte_flag(int mem_type, int mode, int mapping)
+static int check_clear_prot_mte_flag(int mem_type, int mode, int mapping, int atag_check)
 {
 	char *ptr, *map_ptr;
 	int run, prot_flag, result, fd, map_size;
 	int total = ARRAY_SIZE(sizes);
 
 	prot_flag = PROT_READ | PROT_WRITE;
-	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG);
+	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false);
 	for (run = 0; run < total; run++) {
 		map_size = sizes[run] + OVERFLOW + UNDERFLOW;
 		ptr = (char *)mte_allocate_memory_tag_range(sizes[run], mem_type, mapping,
@@ -150,10 +211,10 @@ static int check_clear_prot_mte_flag(int mem_type, int mode, int mapping)
 			ksft_print_msg("FAIL: mprotect not ignoring clear PROT_MTE property\n");
 			return KSFT_FAIL;
 		}
-		result = check_mte_memory(ptr, sizes[run], mode, TAG_CHECK_ON);
+		result = check_mte_memory(ptr, sizes[run], mode, TAG_CHECK_ON, atag_check, TAG_OP_ALL);
 		mte_free_memory_tag_range((void *)ptr, sizes[run], mem_type, UNDERFLOW, OVERFLOW);
 		if (result != KSFT_PASS)
-			return KSFT_FAIL;
+			return result;
 
 		fd = create_temp_file();
 		if (fd == -1)
@@ -174,19 +235,715 @@ static int check_clear_prot_mte_flag(int mem_type, int mode, int mapping)
 			close(fd);
 			return KSFT_FAIL;
 		}
-		result = check_mte_memory(ptr, sizes[run], mode, TAG_CHECK_ON);
+		result = check_mte_memory(ptr, sizes[run], mode, TAG_CHECK_ON, atag_check, TAG_OP_ALL);
 		mte_free_memory_tag_range((void *)ptr, sizes[run], mem_type, UNDERFLOW, OVERFLOW);
 		close(fd);
 		if (result != KSFT_PASS)
-			return KSFT_FAIL;
+			return result;
 	}
 	return KSFT_PASS;
 }
 
+const char *format_test_name(struct check_mmap_testcase *tc)
+{
+	static char test_name[TEST_NAME_MAX];
+	const char *check_type_str;
+	const char *mem_type_str;
+	const char *sync_str;
+	const char *mapping_str;
+	const char *tag_check_str;
+	const char *atag_check_str;
+	const char *tag_op_str;
+
+	switch (tc->check_type) {
+	case CHECK_ANON_MEM:
+		check_type_str = "anonymous memory";
+		break;
+	case CHECK_FILE_MEM:
+		check_type_str = "file memory";
+		break;
+	case CHECK_CLEAR_PROT_MTE:
+		check_type_str = "clear PROT_MTE flags";
+		break;
+	default:
+		assert(0);
+		break;
+	}
+
+	switch (tc->mem_type) {
+	case USE_MMAP:
+		mem_type_str = "mmap";
+		break;
+	case USE_MPROTECT:
+		mem_type_str = "mmap/mprotect";
+		break;
+	default:
+		assert(0);
+		break;
+	}
+
+	switch (tc->mte_sync) {
+	case MTE_NONE_ERR:
+		sync_str = "no error";
+		break;
+	case MTE_SYNC_ERR:
+		sync_str = "sync error";
+		break;
+	case MTE_ASYNC_ERR:
+		sync_str = "async error";
+		break;
+	default:
+		assert(0);
+		break;
+	}
+
+	switch (tc->mapping) {
+	case MAP_SHARED:
+		mapping_str = "shared";
+		break;
+	case MAP_PRIVATE:
+		mapping_str = "private";
+		break;
+	default:
+		assert(0);
+		break;
+	}
+
+	switch (tc->tag_check) {
+	case TAG_CHECK_ON:
+		tag_check_str = "tag check on";
+		break;
+	case TAG_CHECK_OFF:
+		tag_check_str = "tag check off";
+		break;
+	default:
+		assert(0);
+		break;
+	}
+
+	switch (tc->atag_check) {
+	case ATAG_CHECK_ON:
+		atag_check_str = "with address tag [63:60]";
+		break;
+	case ATAG_CHECK_OFF:
+		atag_check_str = "without address tag [63:60]";
+		break;
+	default:
+		assert(0);
+		break;
+	}
+
+	snprintf(test_name, sizeof(test_name),
+	         "Check %s with %s mapping, %s mode, %s memory and %s (%s)\n",
+	         check_type_str, mapping_str, sync_str, mem_type_str,
+	         tag_check_str, atag_check_str);
+
+	switch (tc->tag_op) {
+	case TAG_OP_ALL:
+		tag_op_str = "";
+		break;
+	case TAG_OP_STONLY:
+		tag_op_str = " / store-only";
+		break;
+	default:
+		assert(0);
+		break;
+	}
+
+	snprintf(test_name, TEST_NAME_MAX,
+	         "Check %s with %s mapping, %s mode, %s memory and %s (%s%s)\n",
+	         check_type_str, mapping_str, sync_str, mem_type_str,
+	         tag_check_str, atag_check_str, tag_op_str);
+
+	return test_name;
+}
+
 int main(int argc, char *argv[])
 {
-	int err;
+	int err, i;
 	int item = ARRAY_SIZE(sizes);
+	struct check_mmap_testcase test_cases[]= {
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_OFF,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = true,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_OFF,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = true,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_NONE_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_OFF,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_NONE_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_OFF,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_ASYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_ASYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_ASYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_ASYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_ASYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_ASYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_ASYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_ASYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_CLEAR_PROT_MTE,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_CLEAR_PROT_MTE,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_ON,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_ON,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_ON,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_ON,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_ON,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_ON,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_ON,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_ON,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_ASYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_ON,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_ASYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_ASYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_ASYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_ASYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_ASYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_ASYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_ASYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_ASYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_OFF,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_ON,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_ON,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_ON,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_ANON_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_ON,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_ON,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_ON,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_ON,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_SHARED,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_ON,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_FILE_MEM,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_ASYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_ON,
+			.tag_op = TAG_OP_STONLY,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_CLEAR_PROT_MTE,
+			.mem_type = USE_MMAP,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_ON,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+		{
+			.check_type = CHECK_CLEAR_PROT_MTE,
+			.mem_type = USE_MPROTECT,
+			.mte_sync = MTE_SYNC_ERR,
+			.mapping = MAP_PRIVATE,
+			.tag_check = TAG_CHECK_ON,
+			.atag_check = ATAG_CHECK_ON,
+			.tag_op = TAG_OP_ALL,
+			.enable_tco = false,
+		},
+	};
 
 	err = mte_default_setup();
 	if (err)
@@ -200,64 +957,51 @@ int main(int argc, char *argv[])
 	sizes[item - 2] = page_size;
 	sizes[item - 1] = page_size + 1;
 
-	/* Register signal handlers */
-	mte_register_signal(SIGBUS, mte_default_handler);
-	mte_register_signal(SIGSEGV, mte_default_handler);
-
 	/* Set test plan */
-	ksft_set_plan(22);
-
-	mte_enable_pstate_tco();
-
-	evaluate_test(check_anonymous_memory_mapping(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE, TAG_CHECK_OFF),
-	"Check anonymous memory with private mapping, sync error mode, mmap memory and tag check off\n");
-	evaluate_test(check_file_memory_mapping(USE_MPROTECT, MTE_SYNC_ERR, MAP_PRIVATE, TAG_CHECK_OFF),
-	"Check file memory with private mapping, sync error mode, mmap/mprotect memory and tag check off\n");
-
-	mte_disable_pstate_tco();
-	evaluate_test(check_anonymous_memory_mapping(USE_MMAP, MTE_NONE_ERR, MAP_PRIVATE, TAG_CHECK_OFF),
-	"Check anonymous memory with private mapping, no error mode, mmap memory and tag check off\n");
-	evaluate_test(check_file_memory_mapping(USE_MPROTECT, MTE_NONE_ERR, MAP_PRIVATE, TAG_CHECK_OFF),
-	"Check file memory with private mapping, no error mode, mmap/mprotect memory and tag check off\n");
-
-	evaluate_test(check_anonymous_memory_mapping(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE, TAG_CHECK_ON),
-	"Check anonymous memory with private mapping, sync error mode, mmap memory and tag check on\n");
-	evaluate_test(check_anonymous_memory_mapping(USE_MPROTECT, MTE_SYNC_ERR, MAP_PRIVATE, TAG_CHECK_ON),
-	"Check anonymous memory with private mapping, sync error mode, mmap/mprotect memory and tag check on\n");
-	evaluate_test(check_anonymous_memory_mapping(USE_MMAP, MTE_SYNC_ERR, MAP_SHARED, TAG_CHECK_ON),
-	"Check anonymous memory with shared mapping, sync error mode, mmap memory and tag check on\n");
-	evaluate_test(check_anonymous_memory_mapping(USE_MPROTECT, MTE_SYNC_ERR, MAP_SHARED, TAG_CHECK_ON),
-	"Check anonymous memory with shared mapping, sync error mode, mmap/mprotect memory and tag check on\n");
-	evaluate_test(check_anonymous_memory_mapping(USE_MMAP, MTE_ASYNC_ERR, MAP_PRIVATE, TAG_CHECK_ON),
-	"Check anonymous memory with private mapping, async error mode, mmap memory and tag check on\n");
-	evaluate_test(check_anonymous_memory_mapping(USE_MPROTECT, MTE_ASYNC_ERR, MAP_PRIVATE, TAG_CHECK_ON),
-	"Check anonymous memory with private mapping, async error mode, mmap/mprotect memory and tag check on\n");
-	evaluate_test(check_anonymous_memory_mapping(USE_MMAP, MTE_ASYNC_ERR, MAP_SHARED, TAG_CHECK_ON),
-	"Check anonymous memory with shared mapping, async error mode, mmap memory and tag check on\n");
-	evaluate_test(check_anonymous_memory_mapping(USE_MPROTECT, MTE_ASYNC_ERR, MAP_SHARED, TAG_CHECK_ON),
-	"Check anonymous memory with shared mapping, async error mode, mmap/mprotect memory and tag check on\n");
-
-	evaluate_test(check_file_memory_mapping(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE, TAG_CHECK_ON),
-	"Check file memory with private mapping, sync error mode, mmap memory and tag check on\n");
-	evaluate_test(check_file_memory_mapping(USE_MPROTECT, MTE_SYNC_ERR, MAP_PRIVATE, TAG_CHECK_ON),
-	"Check file memory with private mapping, sync error mode, mmap/mprotect memory and tag check on\n");
-	evaluate_test(check_file_memory_mapping(USE_MMAP, MTE_SYNC_ERR, MAP_SHARED, TAG_CHECK_ON),
-	"Check file memory with shared mapping, sync error mode, mmap memory and tag check on\n");
-	evaluate_test(check_file_memory_mapping(USE_MPROTECT, MTE_SYNC_ERR, MAP_SHARED, TAG_CHECK_ON),
-	"Check file memory with shared mapping, sync error mode, mmap/mprotect memory and tag check on\n");
-	evaluate_test(check_file_memory_mapping(USE_MMAP, MTE_ASYNC_ERR, MAP_PRIVATE, TAG_CHECK_ON),
-	"Check file memory with private mapping, async error mode, mmap memory and tag check on\n");
-	evaluate_test(check_file_memory_mapping(USE_MPROTECT, MTE_ASYNC_ERR, MAP_PRIVATE, TAG_CHECK_ON),
-	"Check file memory with private mapping, async error mode, mmap/mprotect memory and tag check on\n");
-	evaluate_test(check_file_memory_mapping(USE_MMAP, MTE_ASYNC_ERR, MAP_SHARED, TAG_CHECK_ON),
-	"Check file memory with shared mapping, async error mode, mmap memory and tag check on\n");
-	evaluate_test(check_file_memory_mapping(USE_MPROTECT, MTE_ASYNC_ERR, MAP_SHARED, TAG_CHECK_ON),
-	"Check file memory with shared mapping, async error mode, mmap/mprotect memory and tag check on\n");
-
-	evaluate_test(check_clear_prot_mte_flag(USE_MMAP, MTE_SYNC_ERR, MAP_PRIVATE),
-	"Check clear PROT_MTE flags with private mapping, sync error mode and mmap memory\n");
-	evaluate_test(check_clear_prot_mte_flag(USE_MPROTECT, MTE_SYNC_ERR, MAP_PRIVATE),
-	"Check clear PROT_MTE flags with private mapping and sync error mode and mmap/mprotect memory\n");
+	ksft_set_plan(ARRAY_SIZE(test_cases));
+
+	for (i = 0 ; i < ARRAY_SIZE(test_cases); i++) {
+		/* Register signal handlers */
+		mte_register_signal(SIGBUS, mte_default_handler,
+				    test_cases[i].atag_check == ATAG_CHECK_ON);
+		mte_register_signal(SIGSEGV, mte_default_handler,
+				    test_cases[i].atag_check == ATAG_CHECK_ON);
+
+		if (test_cases[i].enable_tco)
+			mte_enable_pstate_tco();
+		else
+			mte_disable_pstate_tco();
+
+		switch (test_cases[i].check_type) {
+		case CHECK_ANON_MEM:
+			evaluate_test(check_anonymous_memory_mapping(test_cases[i].mem_type,
+								     test_cases[i].mte_sync,
+								     test_cases[i].mapping,
+								     test_cases[i].tag_check,
+								     test_cases[i].atag_check,
+								     test_cases[i].tag_op),
+				      format_test_name(&test_cases[i]));
+			break;
+		case CHECK_FILE_MEM:
+			evaluate_test(check_file_memory_mapping(test_cases[i].mem_type,
+							        test_cases[i].mte_sync,
+							        test_cases[i].mapping,
+							        test_cases[i].tag_check,
+							        test_cases[i].atag_check,
+								test_cases[i].tag_op),
+				      format_test_name(&test_cases[i]));
+			break;
+		case CHECK_CLEAR_PROT_MTE:
+			evaluate_test(check_clear_prot_mte_flag(test_cases[i].mem_type,
+							        test_cases[i].mte_sync,
+							        test_cases[i].mapping,
+							        test_cases[i].atag_check),
+				      format_test_name(&test_cases[i]));
+			break;
+		default:
+			exit(KSFT_FAIL);
+		}
+	}
 
 	mte_restore_setup();
 	ksft_print_cnts();
diff --git a/tools/testing/selftests/arm64/mte/check_prctl.c b/tools/testing/selftests/arm64/mte/check_prctl.c
index f139a33a43ef..f7f320defa7b 100644
--- a/tools/testing/selftests/arm64/mte/check_prctl.c
+++ b/tools/testing/selftests/arm64/mte/check_prctl.c
@@ -12,6 +12,10 @@
 
 #include "kselftest.h"
 
+#ifndef AT_HWCAP3
+#define AT_HWCAP3 29
+#endif
+
 static int set_tagged_addr_ctrl(int val)
 {
 	int ret;
@@ -60,7 +64,7 @@ void check_basic_read(void)
 /*
  * Attempt to set a specified combination of modes.
  */
-void set_mode_test(const char *name, int hwcap2, int mask)
+void set_mode_test(const char *name, int hwcap2, int hwcap3, int mask)
 {
 	int ret;
 
@@ -69,6 +73,11 @@ void set_mode_test(const char *name, int hwcap2, int mask)
 		return;
 	}
 
+	if ((getauxval(AT_HWCAP3) & hwcap3) != hwcap3) {
+		ksft_test_result_skip("%s\n", name);
+		return;
+	}
+
 	ret = set_tagged_addr_ctrl(mask);
 	if (ret < 0) {
 		ksft_test_result_fail("%s\n", name);
@@ -81,11 +90,11 @@ void set_mode_test(const char *name, int hwcap2, int mask)
 		return;
 	}
 
-	if ((ret & PR_MTE_TCF_MASK) == mask) {
+	if ((ret & (PR_MTE_TCF_MASK | PR_MTE_STORE_ONLY)) == mask) {
 		ksft_test_result_pass("%s\n", name);
 	} else {
 		ksft_print_msg("Got %x, expected %x\n",
-			       (ret & PR_MTE_TCF_MASK), mask);
+			       (ret & (int)PR_MTE_TCF_MASK), mask);
 		ksft_test_result_fail("%s\n", name);
 	}
 }
@@ -93,12 +102,16 @@ void set_mode_test(const char *name, int hwcap2, int mask)
 struct mte_mode {
 	int mask;
 	int hwcap2;
+	int hwcap3;
 	const char *name;
 } mte_modes[] = {
-	{ PR_MTE_TCF_NONE,  0,          "NONE"  },
-	{ PR_MTE_TCF_SYNC,  HWCAP2_MTE, "SYNC"  },
-	{ PR_MTE_TCF_ASYNC, HWCAP2_MTE, "ASYNC" },
-	{ PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC,  HWCAP2_MTE, "SYNC+ASYNC"  },
+	{ PR_MTE_TCF_NONE,                                        0,          0,                     "NONE"  },
+	{ PR_MTE_TCF_SYNC,                                        HWCAP2_MTE, 0,                     "SYNC"  },
+	{ PR_MTE_TCF_ASYNC,                                       HWCAP2_MTE, 0,                     "ASYNC" },
+	{ PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC,                     HWCAP2_MTE, 0,                     "SYNC+ASYNC"  },
+	{ PR_MTE_TCF_SYNC | PR_MTE_STORE_ONLY,                    HWCAP2_MTE, HWCAP3_MTE_STORE_ONLY, "SYNC+STONLY" },
+	{ PR_MTE_TCF_ASYNC | PR_MTE_STORE_ONLY,                   HWCAP2_MTE, HWCAP3_MTE_STORE_ONLY, "ASYNC+STONLY" },
+	{ PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC | PR_MTE_STORE_ONLY, HWCAP2_MTE, HWCAP3_MTE_STORE_ONLY, "SYNC+ASYNC+STONLY" },
 };
 
 int main(void)
@@ -106,11 +119,11 @@ int main(void)
 	int i;
 
 	ksft_print_header();
-	ksft_set_plan(5);
+	ksft_set_plan(ARRAY_SIZE(mte_modes));
 
 	check_basic_read();
 	for (i = 0; i < ARRAY_SIZE(mte_modes); i++)
-		set_mode_test(mte_modes[i].name, mte_modes[i].hwcap2,
+		set_mode_test(mte_modes[i].name, mte_modes[i].hwcap2, mte_modes[i].hwcap3,
 			      mte_modes[i].mask);
 
 	ksft_print_cnts();
diff --git a/tools/testing/selftests/arm64/mte/check_tags_inclusion.c b/tools/testing/selftests/arm64/mte/check_tags_inclusion.c
index 2b1425b92b69..4b764f2a8185 100644
--- a/tools/testing/selftests/arm64/mte/check_tags_inclusion.c
+++ b/tools/testing/selftests/arm64/mte/check_tags_inclusion.c
@@ -57,7 +57,7 @@ static int check_single_included_tags(int mem_type, int mode)
 		return KSFT_FAIL;
 
 	for (tag = 0; (tag < MT_TAG_COUNT) && (result == KSFT_PASS); tag++) {
-		ret = mte_switch_mode(mode, MT_INCLUDE_VALID_TAG(tag));
+		ret = mte_switch_mode(mode, MT_INCLUDE_VALID_TAG(tag), false);
 		if (ret != 0)
 			result = KSFT_FAIL;
 		/* Try to catch a excluded tag by a number of tries. */
@@ -65,7 +65,7 @@ static int check_single_included_tags(int mem_type, int mode)
 			ptr = mte_insert_tags(ptr, BUFFER_SIZE);
 			/* Check tag value */
 			if (MT_FETCH_TAG((uintptr_t)ptr) == tag) {
-				ksft_print_msg("FAIL: wrong tag = 0x%x with include mask=0x%x\n",
+				ksft_print_msg("FAIL: wrong tag = 0x%lx with include mask=0x%x\n",
 					       MT_FETCH_TAG((uintptr_t)ptr),
 					       MT_INCLUDE_VALID_TAG(tag));
 				result = KSFT_FAIL;
@@ -91,13 +91,13 @@ static int check_multiple_included_tags(int mem_type, int mode)
 
 	for (tag = 0; (tag < MT_TAG_COUNT - 1) && (result == KSFT_PASS); tag++) {
 		excl_mask |= 1 << tag;
-		mte_switch_mode(mode, MT_INCLUDE_VALID_TAGS(excl_mask));
+		mte_switch_mode(mode, MT_INCLUDE_VALID_TAGS(excl_mask), false);
 		/* Try to catch a excluded tag by a number of tries. */
 		for (run = 0; (run < RUNS) && (result == KSFT_PASS); run++) {
 			ptr = mte_insert_tags(ptr, BUFFER_SIZE);
 			/* Check tag value */
 			if (MT_FETCH_TAG((uintptr_t)ptr) < tag) {
-				ksft_print_msg("FAIL: wrong tag = 0x%x with include mask=0x%x\n",
+				ksft_print_msg("FAIL: wrong tag = 0x%lx with include mask=0x%lx\n",
 					       MT_FETCH_TAG((uintptr_t)ptr),
 					       MT_INCLUDE_VALID_TAGS(excl_mask));
 				result = KSFT_FAIL;
@@ -120,7 +120,7 @@ static int check_all_included_tags(int mem_type, int mode)
 				   mem_type, false) != KSFT_PASS)
 		return KSFT_FAIL;
 
-	ret = mte_switch_mode(mode, MT_INCLUDE_TAG_MASK);
+	ret = mte_switch_mode(mode, MT_INCLUDE_TAG_MASK, false);
 	if (ret != 0)
 		return KSFT_FAIL;
 	/* Try to catch a excluded tag by a number of tries. */
@@ -145,7 +145,7 @@ static int check_none_included_tags(int mem_type, int mode)
 	if (check_allocated_memory(ptr, BUFFER_SIZE, mem_type, false) != KSFT_PASS)
 		return KSFT_FAIL;
 
-	ret = mte_switch_mode(mode, MT_EXCLUDE_TAG_MASK);
+	ret = mte_switch_mode(mode, MT_EXCLUDE_TAG_MASK, false);
 	if (ret != 0)
 		return KSFT_FAIL;
 	/* Try to catch a excluded tag by a number of tries. */
@@ -180,7 +180,7 @@ int main(int argc, char *argv[])
 		return err;
 
 	/* Register SIGSEGV handler */
-	mte_register_signal(SIGSEGV, mte_default_handler);
+	mte_register_signal(SIGSEGV, mte_default_handler, false);
 
 	/* Set test plan */
 	ksft_set_plan(4);
diff --git a/tools/testing/selftests/arm64/mte/check_user_mem.c b/tools/testing/selftests/arm64/mte/check_user_mem.c
index f4ae5f87a3b7..fb7936c4e097 100644
--- a/tools/testing/selftests/arm64/mte/check_user_mem.c
+++ b/tools/testing/selftests/arm64/mte/check_user_mem.c
@@ -44,7 +44,7 @@ static int check_usermem_access_fault(int mem_type, int mode, int mapping,
 
 	err = KSFT_PASS;
 	len = 2 * page_sz;
-	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG);
+	mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG, false);
 	fd = create_temp_file();
 	if (fd == -1)
 		return KSFT_FAIL;
@@ -211,7 +211,7 @@ int main(int argc, char *argv[])
 		return err;
 
 	/* Register signal handlers */
-	mte_register_signal(SIGSEGV, mte_default_handler);
+	mte_register_signal(SIGSEGV, mte_default_handler, false);
 
 	/* Set test plan */
 	ksft_set_plan(64);
diff --git a/tools/testing/selftests/arm64/mte/mte_common_util.c b/tools/testing/selftests/arm64/mte/mte_common_util.c
index 00ffd34c66d3..397e57dd946a 100644
--- a/tools/testing/selftests/arm64/mte/mte_common_util.c
+++ b/tools/testing/selftests/arm64/mte/mte_common_util.c
@@ -6,6 +6,7 @@
 #include <signal.h>
 #include <stdio.h>
 #include <stdlib.h>
+#include <time.h>
 #include <unistd.h>
 
 #include <linux/auxvec.h>
@@ -19,39 +20,64 @@
 #include "mte_common_util.h"
 #include "mte_def.h"
 
+#ifndef SA_EXPOSE_TAGBITS
+#define SA_EXPOSE_TAGBITS 0x00000800
+#endif
+
 #define INIT_BUFFER_SIZE       256
 
 struct mte_fault_cxt cur_mte_cxt;
+bool mtefar_support;
+bool mtestonly_support;
 static unsigned int mte_cur_mode;
 static unsigned int mte_cur_pstate_tco;
+static bool mte_cur_stonly;
 
 void mte_default_handler(int signum, siginfo_t *si, void *uc)
 {
+	struct sigaction sa;
 	unsigned long addr = (unsigned long)si->si_addr;
+	unsigned char si_tag, si_atag;
+
+	sigaction(signum, NULL, &sa);
+
+	if (sa.sa_flags & SA_EXPOSE_TAGBITS) {
+		si_tag = MT_FETCH_TAG(addr);
+		si_atag = MT_FETCH_ATAG(addr);
+		addr = MT_CLEAR_TAGS(addr);
+	} else {
+		si_tag = 0;
+		si_atag = 0;
+	}
 
 	if (signum == SIGSEGV) {
 #ifdef DEBUG
-		ksft_print_msg("INFO: SIGSEGV signal at pc=%lx, fault addr=%lx, si_code=%lx\n",
-				((ucontext_t *)uc)->uc_mcontext.pc, addr, si->si_code);
+		ksft_print_msg("INFO: SIGSEGV signal at pc=%lx, fault addr=%lx, si_code=%lx, si_tag=%x, si_atag=%x\n",
+				((ucontext_t *)uc)->uc_mcontext.pc, addr, si->si_code, si_tag, si_atag);
 #endif
 		if (si->si_code == SEGV_MTEAERR) {
 			if (cur_mte_cxt.trig_si_code == si->si_code)
 				cur_mte_cxt.fault_valid = true;
 			else
-				ksft_print_msg("Got unexpected SEGV_MTEAERR at pc=$lx, fault addr=%lx\n",
+				ksft_print_msg("Got unexpected SEGV_MTEAERR at pc=%llx, fault addr=%lx\n",
 					       ((ucontext_t *)uc)->uc_mcontext.pc,
 					       addr);
 			return;
 		}
 		/* Compare the context for precise error */
 		else if (si->si_code == SEGV_MTESERR) {
+			if ((!mtefar_support && si_atag) || (si_atag != MT_FETCH_ATAG(cur_mte_cxt.trig_addr))) {
+				ksft_print_msg("Invalid MTE synchronous exception caught for address tag! si_tag=%x, si_atag: %x\n", si_tag, si_atag);
+				exit(KSFT_FAIL);
+			}
+
 			if (cur_mte_cxt.trig_si_code == si->si_code &&
 			    ((cur_mte_cxt.trig_range >= 0 &&
-			      addr >= MT_CLEAR_TAG(cur_mte_cxt.trig_addr) &&
-			      addr <= (MT_CLEAR_TAG(cur_mte_cxt.trig_addr) + cur_mte_cxt.trig_range)) ||
+			      addr >= MT_CLEAR_TAGS(cur_mte_cxt.trig_addr) &&
+			      addr <= (MT_CLEAR_TAGS(cur_mte_cxt.trig_addr) + cur_mte_cxt.trig_range)) ||
 			     (cur_mte_cxt.trig_range < 0 &&
-			      addr <= MT_CLEAR_TAG(cur_mte_cxt.trig_addr) &&
-			      addr >= (MT_CLEAR_TAG(cur_mte_cxt.trig_addr) + cur_mte_cxt.trig_range)))) {
+			      addr <= MT_CLEAR_TAGS(cur_mte_cxt.trig_addr) &&
+			      addr >= (MT_CLEAR_TAGS(cur_mte_cxt.trig_addr) + cur_mte_cxt.trig_range)))) {
 				cur_mte_cxt.fault_valid = true;
 				/* Adjust the pc by 4 */
 				((ucontext_t *)uc)->uc_mcontext.pc += 4;
@@ -64,14 +90,14 @@ void mte_default_handler(int signum, siginfo_t *si, void *uc)
 			exit(1);
 		}
 	} else if (signum == SIGBUS) {
-		ksft_print_msg("INFO: SIGBUS signal at pc=%lx, fault addr=%lx, si_code=%lx\n",
+		ksft_print_msg("INFO: SIGBUS signal at pc=%llx, fault addr=%lx, si_code=%x\n",
 				((ucontext_t *)uc)->uc_mcontext.pc, addr, si->si_code);
 		if ((cur_mte_cxt.trig_range >= 0 &&
-		     addr >= MT_CLEAR_TAG(cur_mte_cxt.trig_addr) &&
-		     addr <= (MT_CLEAR_TAG(cur_mte_cxt.trig_addr) + cur_mte_cxt.trig_range)) ||
+		     addr >= MT_CLEAR_TAGS(cur_mte_cxt.trig_addr) &&
+		     addr <= (MT_CLEAR_TAGS(cur_mte_cxt.trig_addr) + cur_mte_cxt.trig_range)) ||
 		    (cur_mte_cxt.trig_range < 0 &&
-		     addr <= MT_CLEAR_TAG(cur_mte_cxt.trig_addr) &&
-		     addr >= (MT_CLEAR_TAG(cur_mte_cxt.trig_addr) + cur_mte_cxt.trig_range))) {
+		     addr <= MT_CLEAR_TAGS(cur_mte_cxt.trig_addr) &&
+		     addr >= (MT_CLEAR_TAGS(cur_mte_cxt.trig_addr) + cur_mte_cxt.trig_range))) {
 			cur_mte_cxt.fault_valid = true;
 			/* Adjust the pc by 4 */
 			((ucontext_t *)uc)->uc_mcontext.pc += 4;
@@ -79,12 +105,17 @@ void mte_default_handler(int signum, siginfo_t *si, void *uc)
 	}
 }
 
-void mte_register_signal(int signal, void (*handler)(int, siginfo_t *, void *))
+void mte_register_signal(int signal, void (*handler)(int, siginfo_t *, void *),
+			 bool export_tags)
 {
 	struct sigaction sa;
 
 	sa.sa_sigaction = handler;
 	sa.sa_flags = SA_SIGINFO;
+
+	if (export_tags && signal == SIGSEGV)
+		sa.sa_flags |= SA_EXPOSE_TAGBITS;
+
 	sigemptyset(&sa.sa_mask);
 	sigaction(signal, &sa, NULL);
 }
@@ -100,7 +131,7 @@ void *mte_insert_tags(void *ptr, size_t size)
 	int align_size;
 
 	if (!ptr || (unsigned long)(ptr) & MT_ALIGN_GRANULE) {
-		ksft_print_msg("FAIL: Addr=%lx: invalid\n", ptr);
+		ksft_print_msg("FAIL: Addr=%p: invalid\n", ptr);
 		return NULL;
 	}
 	align_size = MT_ALIGN_UP(size);
@@ -112,7 +143,7 @@ void *mte_insert_tags(void *ptr, size_t size)
 void mte_clear_tags(void *ptr, size_t size)
 {
 	if (!ptr || (unsigned long)(ptr) & MT_ALIGN_GRANULE) {
-		ksft_print_msg("FAIL: Addr=%lx: invalid\n", ptr);
+		ksft_print_msg("FAIL: Addr=%p: invalid\n", ptr);
 		return;
 	}
 	size = MT_ALIGN_UP(size);
@@ -120,6 +151,19 @@ void mte_clear_tags(void *ptr, size_t size)
 	mte_clear_tag_address_range(ptr, size);
 }
 
+void *mte_insert_atag(void *ptr)
+{
+	unsigned char atag;
+
+	atag =  mtefar_support ? (random() % MT_ATAG_MASK) + 1 : 0;
+	return (void *)MT_SET_ATAG((unsigned long)ptr, atag);
+}
+
+void *mte_clear_atag(void *ptr)
+{
+	return (void *)MT_CLEAR_ATAG((unsigned long)ptr);
+}
+
 static void *__mte_allocate_memory_range(size_t size, int mem_type, int mapping,
 					 size_t range_before, size_t range_after,
 					 bool tags, int fd)
@@ -150,13 +194,13 @@ static void *__mte_allocate_memory_range(size_t size, int mem_type, int mapping,
 		map_flag |= MAP_PRIVATE;
 	ptr = mmap(NULL, entire_size, prot_flag, map_flag, fd, 0);
 	if (ptr == MAP_FAILED) {
-		ksft_print_msg("FAIL: mmap allocation\n");
+		ksft_perror("mmap()");
 		return NULL;
 	}
 	if (mem_type == USE_MPROTECT) {
 		if (mprotect(ptr, entire_size, prot_flag | PROT_MTE)) {
+			ksft_perror("mprotect(PROT_MTE)");
 			munmap(ptr, size);
-			ksft_print_msg("FAIL: mprotect PROT_MTE property\n");
 			return NULL;
 		}
 	}
@@ -190,13 +234,13 @@ void *mte_allocate_file_memory(size_t size, int mem_type, int mapping, bool tags
 	lseek(fd, 0, SEEK_SET);
 	for (index = INIT_BUFFER_SIZE; index < size; index += INIT_BUFFER_SIZE) {
 		if (write(fd, buffer, INIT_BUFFER_SIZE) != INIT_BUFFER_SIZE) {
-			perror("initialising buffer");
+			ksft_perror("initialising buffer");
 			return NULL;
 		}
 	}
 	index -= INIT_BUFFER_SIZE;
 	if (write(fd, buffer, size - index) != size - index) {
-		perror("initialising buffer");
+		ksft_perror("initialising buffer");
 		return NULL;
 	}
 	return __mte_allocate_memory_range(size, mem_type, mapping, 0, 0, tags, fd);
@@ -217,12 +261,12 @@ void *mte_allocate_file_memory_tag_range(size_t size, int mem_type, int mapping,
 	lseek(fd, 0, SEEK_SET);
 	for (index = INIT_BUFFER_SIZE; index < map_size; index += INIT_BUFFER_SIZE)
 		if (write(fd, buffer, INIT_BUFFER_SIZE) != INIT_BUFFER_SIZE) {
-			perror("initialising buffer");
+			ksft_perror("initialising buffer");
 			return NULL;
 		}
 	index -= INIT_BUFFER_SIZE;
 	if (write(fd, buffer, map_size - index) != map_size - index) {
-		perror("initialising buffer");
+		ksft_perror("initialising buffer");
 		return NULL;
 	}
 	return __mte_allocate_memory_range(size, mem_type, mapping, range_before,
@@ -272,7 +316,7 @@ void mte_initialize_current_context(int mode, uintptr_t ptr, ssize_t range)
 		cur_mte_cxt.trig_si_code = 0;
 }
 
-int mte_switch_mode(int mte_option, unsigned long incl_mask)
+int mte_switch_mode(int mte_option, unsigned long incl_mask, bool stonly)
 {
 	unsigned long en = 0;
 
@@ -304,6 +348,9 @@ int mte_switch_mode(int mte_option, unsigned long incl_mask)
 		break;
 	}
 
+	if (mtestonly_support && stonly)
+		en |= PR_MTE_STORE_ONLY;
+
 	en |= (incl_mask << PR_MTE_TAG_SHIFT);
 	/* Enable address tagging ABI, mte error reporting mode and tag inclusion mask. */
 	if (prctl(PR_SET_TAGGED_ADDR_CTRL, en, 0, 0, 0) != 0) {
@@ -316,13 +363,21 @@ int mte_switch_mode(int mte_option, unsigned long incl_mask)
 int mte_default_setup(void)
 {
 	unsigned long hwcaps2 = getauxval(AT_HWCAP2);
+	unsigned long hwcaps3 = getauxval(AT_HWCAP3);
 	unsigned long en = 0;
 	int ret;
 
-	if (!(hwcaps2 & HWCAP2_MTE)) {
-		ksft_print_msg("SKIP: MTE features unavailable\n");
-		return KSFT_SKIP;
-	}
+	/* To generate random address tag */
+	srandom(time(NULL));
+
+	if (!(hwcaps2 & HWCAP2_MTE))
+		ksft_exit_skip("MTE features unavailable\n");
+
+	mtefar_support = !!(hwcaps3 & HWCAP3_MTE_FAR);
+
+	if (hwcaps3 & HWCAP3_MTE_STORE_ONLY)
+		mtestonly_support = true;
+
 	/* Get current mte mode */
 	ret = prctl(PR_GET_TAGGED_ADDR_CTRL, en, 0, 0, 0);
 	if (ret < 0) {
@@ -336,6 +391,8 @@ int mte_default_setup(void)
 	else if (ret & PR_MTE_TCF_NONE)
 		mte_cur_mode = MTE_NONE_ERR;
 
+	mte_cur_stonly = (ret & PR_MTE_STORE_ONLY) ? true : false;
+
 	mte_cur_pstate_tco = mte_get_pstate_tco();
 	/* Disable PSTATE.TCO */
 	mte_disable_pstate_tco();
@@ -344,7 +401,7 @@ int mte_default_setup(void)
 
 void mte_restore_setup(void)
 {
-	mte_switch_mode(mte_cur_mode, MTE_ALLOW_NON_ZERO_TAG);
+	mte_switch_mode(mte_cur_mode, MTE_ALLOW_NON_ZERO_TAG, mte_cur_stonly);
 	if (mte_cur_pstate_tco == MT_PSTATE_TCO_EN)
 		mte_enable_pstate_tco();
 	else if (mte_cur_pstate_tco == MT_PSTATE_TCO_DIS)
@@ -359,7 +416,7 @@ int create_temp_file(void)
 	/* Create a file in the tmpfs filesystem */
 	fd = mkstemp(&filename[0]);
 	if (fd == -1) {
-		perror(filename);
+		ksft_perror(filename);
 		ksft_print_msg("FAIL: Unable to open temporary file\n");
 		return 0;
 	}
diff --git a/tools/testing/selftests/arm64/mte/mte_common_util.h b/tools/testing/selftests/arm64/mte/mte_common_util.h
index 2d3e71724e55..250d671329a5 100644
--- a/tools/testing/selftests/arm64/mte/mte_common_util.h
+++ b/tools/testing/selftests/arm64/mte/mte_common_util.h
@@ -37,10 +37,13 @@ struct mte_fault_cxt {
 };
 
 extern struct mte_fault_cxt cur_mte_cxt;
+extern bool mtefar_support;
+extern bool mtestonly_support;
 
 /* MTE utility functions */
 void mte_default_handler(int signum, siginfo_t *si, void *uc);
-void mte_register_signal(int signal, void (*handler)(int, siginfo_t *, void *));
+void mte_register_signal(int signal, void (*handler)(int, siginfo_t *, void *),
+			 bool export_tags);
 void mte_wait_after_trig(void);
 void *mte_allocate_memory(size_t size, int mem_type, int mapping, bool tags);
 void *mte_allocate_memory_tag_range(size_t size, int mem_type, int mapping,
@@ -54,9 +57,11 @@ void mte_free_memory_tag_range(void *ptr, size_t size, int mem_type,
 			       size_t range_before, size_t range_after);
 void *mte_insert_tags(void *ptr, size_t size);
 void mte_clear_tags(void *ptr, size_t size);
+void *mte_insert_atag(void *ptr);
+void *mte_clear_atag(void *ptr);
 int mte_default_setup(void);
 void mte_restore_setup(void);
-int mte_switch_mode(int mte_option, unsigned long incl_mask);
+int mte_switch_mode(int mte_option, unsigned long incl_mask, bool stonly);
 void mte_initialize_current_context(int mode, uintptr_t ptr, ssize_t range);
 
 /* Common utility functions */
@@ -77,13 +82,13 @@ static inline void evaluate_test(int err, const char *msg)
 {
 	switch (err) {
 	case KSFT_PASS:
-		ksft_test_result_pass(msg);
+		ksft_test_result_pass("%s", msg);
 		break;
 	case KSFT_FAIL:
-		ksft_test_result_fail(msg);
+		ksft_test_result_fail("%s", msg);
 		break;
 	case KSFT_SKIP:
-		ksft_test_result_skip(msg);
+		ksft_test_result_skip("%s", msg);
 		break;
 	default:
 		ksft_test_result_error("Unknown return code %d from %s",
diff --git a/tools/testing/selftests/arm64/mte/mte_def.h b/tools/testing/selftests/arm64/mte/mte_def.h
index 9b188254b61a..6ad22f07c9b8 100644
--- a/tools/testing/selftests/arm64/mte/mte_def.h
+++ b/tools/testing/selftests/arm64/mte/mte_def.h
@@ -42,6 +42,8 @@
 #define MT_TAG_COUNT		16
 #define MT_INCLUDE_TAG_MASK	0xFFFF
 #define MT_EXCLUDE_TAG_MASK	0x0
+#define MT_ATAG_SHIFT		60
+#define MT_ATAG_MASK		0xFUL
 
 #define MT_ALIGN_GRANULE	(MT_GRANULE_SIZE - 1)
 #define MT_CLEAR_TAG(x)		((x) & ~(MT_TAG_MASK << MT_TAG_SHIFT))
@@ -49,6 +51,12 @@
 #define MT_FETCH_TAG(x)		((x >> MT_TAG_SHIFT) & (MT_TAG_MASK))
 #define MT_ALIGN_UP(x)		((x + MT_ALIGN_GRANULE) & ~(MT_ALIGN_GRANULE))
 
+#define MT_CLEAR_ATAG(x)	((x) & ~(MT_TAG_MASK << MT_ATAG_SHIFT))
+#define MT_SET_ATAG(x, y)	((x) | (((y) & MT_ATAG_MASK) << MT_ATAG_SHIFT))
+#define MT_FETCH_ATAG(x)	((x >> MT_ATAG_SHIFT) & (MT_ATAG_MASK))
+
+#define MT_CLEAR_TAGS(x) 	(MT_CLEAR_ATAG(MT_CLEAR_TAG(x)))
+
 #define MT_PSTATE_TCO_SHIFT	25
 #define MT_PSTATE_TCO_MASK	~(0x1 << MT_PSTATE_TCO_SHIFT)
 #define MT_PSTATE_TCO_EN	1
diff --git a/tools/testing/selftests/arm64/pauth/Makefile b/tools/testing/selftests/arm64/pauth/Makefile
index 72e290b0b10c..b5a1c80e0ead 100644
--- a/tools/testing/selftests/arm64/pauth/Makefile
+++ b/tools/testing/selftests/arm64/pauth/Makefile
@@ -7,8 +7,14 @@ CC := $(CROSS_COMPILE)gcc
 endif
 
 CFLAGS += -mbranch-protection=pac-ret
+
+# All supported LLVMs have PAC, test for GCC
+ifeq ($(LLVM),1)
+pauth_cc_support := 1
+else
 # check if the compiler supports ARMv8.3 and branch protection with PAuth
 pauth_cc_support := $(shell if ($(CC) $(CFLAGS) -march=armv8.3-a -E -x c /dev/null -o /dev/null 2>&1) then echo "1"; fi)
+endif
 
 ifeq ($(pauth_cc_support),1)
 TEST_GEN_PROGS := pac
diff --git a/tools/testing/selftests/arm64/pauth/exec_target.c b/tools/testing/selftests/arm64/pauth/exec_target.c
index 4435600ca400..e597861b26d6 100644
--- a/tools/testing/selftests/arm64/pauth/exec_target.c
+++ b/tools/testing/selftests/arm64/pauth/exec_target.c
@@ -13,7 +13,12 @@ int main(void)
 	unsigned long hwcaps;
 	size_t val;
 
-	fread(&val, sizeof(size_t), 1, stdin);
+	size_t size = fread(&val, sizeof(size_t), 1, stdin);
+
+	if (size != 1) {
+		fprintf(stderr, "Could not read input from stdin\n");
+		return EXIT_FAILURE;
+	}
 
 	/* don't try to execute illegal (unimplemented) instructions) caller
 	 * should have checked this and keep worker simple
diff --git a/tools/testing/selftests/arm64/pauth/pac.c b/tools/testing/selftests/arm64/pauth/pac.c
index b743daa772f5..67d138057707 100644
--- a/tools/testing/selftests/arm64/pauth/pac.c
+++ b/tools/testing/selftests/arm64/pauth/pac.c
@@ -10,10 +10,10 @@
 #include <setjmp.h>
 #include <sched.h>
 
-#include "../../kselftest_harness.h"
+#include "kselftest_harness.h"
 #include "helper.h"
 
-#define PAC_COLLISION_ATTEMPTS 10
+#define PAC_COLLISION_ATTEMPTS 1000
 /*
  * The kernel sets TBID by default. So bits 55 and above should remain
  * untouched no matter what.
@@ -182,6 +182,9 @@ int exec_sign_all(struct signatures *signed_vals, size_t val)
 		return -1;
 	}
 
+	close(new_stdin[1]);
+	close(new_stdout[0]);
+
 	return 0;
 }
 
diff --git a/tools/testing/selftests/arm64/signal/.gitignore b/tools/testing/selftests/arm64/signal/.gitignore
index e8d2b57f73ec..b257db665a35 100644
--- a/tools/testing/selftests/arm64/signal/.gitignore
+++ b/tools/testing/selftests/arm64/signal/.gitignore
@@ -1,8 +1,13 @@
 # SPDX-License-Identifier: GPL-2.0-only
 mangle_*
 fake_sigreturn_*
+fpmr_*
+poe_*
+gcs_*
 sme_*
 ssve_*
 sve_*
+tpidr2_*
 za_*
+zt_*
 !*.[ch]
diff --git a/tools/testing/selftests/arm64/signal/Makefile b/tools/testing/selftests/arm64/signal/Makefile
index be7520a863b0..1381039fb36f 100644
--- a/tools/testing/selftests/arm64/signal/Makefile
+++ b/tools/testing/selftests/arm64/signal/Makefile
@@ -2,7 +2,7 @@
 # Copyright (C) 2019 ARM Limited
 
 # Additional include paths needed by kselftest.h and local headers
-CFLAGS += -D_GNU_SOURCE -std=gnu99 -I.
+CFLAGS += -std=gnu99 -I.
 
 SRCS := $(filter-out testcases/testcases.c,$(wildcard testcases/*.c))
 PROGS := $(patsubst %.c,%,$(SRCS))
@@ -22,6 +22,10 @@ $(TEST_GEN_PROGS): $(PROGS)
 
 # Common test-unit targets to build common-layout test-cases executables
 # Needs secondary expansion to properly include the testcase c-file in pre-reqs
+COMMON_SOURCES := test_signals.c test_signals_utils.c testcases/testcases.c \
+	signals.S sve_helpers.c
+COMMON_HEADERS := test_signals.h test_signals_utils.h testcases/testcases.h
+
 .SECONDEXPANSION:
-$(PROGS): test_signals.c test_signals_utils.c testcases/testcases.c signals.S $$@.c test_signals.h test_signals_utils.h testcases/testcases.h
-	$(CC) $(CFLAGS) $^ -o $@
+$(PROGS): $$@.c ${COMMON_SOURCES} ${COMMON_HEADERS}
+	$(CC) $(CFLAGS) ${@}.c ${COMMON_SOURCES} -o $@
diff --git a/tools/testing/selftests/arm64/signal/sve_helpers.c b/tools/testing/selftests/arm64/signal/sve_helpers.c
new file mode 100644
index 000000000000..0acc121af306
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/sve_helpers.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 ARM Limited
+ *
+ * Common helper functions for SVE and SME functionality.
+ */
+
+#include <stdbool.h>
+#include <kselftest.h>
+#include <asm/sigcontext.h>
+#include <sys/prctl.h>
+
+unsigned int vls[SVE_VQ_MAX];
+unsigned int nvls;
+
+int sve_fill_vls(bool use_sme, int min_vls)
+{
+	int vq, vl;
+	int pr_set_vl = use_sme ? PR_SME_SET_VL : PR_SVE_SET_VL;
+	int len_mask = use_sme ? PR_SME_VL_LEN_MASK : PR_SVE_VL_LEN_MASK;
+
+	/*
+	 * Enumerate up to SVE_VQ_MAX vector lengths
+	 */
+	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+		vl = prctl(pr_set_vl, vq * 16);
+		if (vl == -1)
+			return KSFT_FAIL;
+
+		vl &= len_mask;
+
+		/*
+		 * Unlike SVE, SME does not require the minimum vector length
+		 * to be implemented, or the VLs to be consecutive, so any call
+		 * to the prctl might return the single implemented VL, which
+		 * might be larger than 16. So to avoid this loop never
+		 * terminating,  bail out here when we find a higher VL than
+		 * we asked for.
+		 * See the ARM ARM, DDI 0487K.a, B1.4.2: I_QQRNR and I_NWYBP.
+		 */
+		if (vq < sve_vq_from_vl(vl))
+			break;
+
+		/* Skip missing VLs */
+		vq = sve_vq_from_vl(vl);
+
+		vls[nvls++] = vl;
+	}
+
+	if (nvls < min_vls) {
+		fprintf(stderr, "Only %d VL supported\n", nvls);
+		return KSFT_SKIP;
+	}
+
+	return KSFT_PASS;
+}
diff --git a/tools/testing/selftests/arm64/signal/sve_helpers.h b/tools/testing/selftests/arm64/signal/sve_helpers.h
new file mode 100644
index 000000000000..ca133b93375f
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/sve_helpers.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2024 ARM Limited
+ *
+ * Common helper functions for SVE and SME functionality.
+ */
+
+#ifndef __SVE_HELPERS_H__
+#define __SVE_HELPERS_H__
+
+#include <stdbool.h>
+
+#define VLS_USE_SVE	false
+#define VLS_USE_SME	true
+
+extern unsigned int vls[];
+extern unsigned int nvls;
+
+int sve_fill_vls(bool use_sme, int min_vls);
+
+static inline uint64_t get_svcr(void)
+{
+	uint64_t val;
+
+	asm volatile (
+		"mrs	%0, S3_3_C4_C2_2\n"
+		: "=r"(val)
+		:
+		: "cc");
+
+	return val;
+}
+
+#endif
diff --git a/tools/testing/selftests/arm64/signal/test_signals.c b/tools/testing/selftests/arm64/signal/test_signals.c
index 416b1ff43199..1304c8ec0f2f 100644
--- a/tools/testing/selftests/arm64/signal/test_signals.c
+++ b/tools/testing/selftests/arm64/signal/test_signals.c
@@ -7,16 +7,28 @@
  * Each test provides its own tde struct tdescr descriptor to link with
  * this wrapper. Framework provides common helpers.
  */
+
+#include <sys/auxv.h>
+#include <sys/prctl.h>
+
 #include <kselftest.h>
 
 #include "test_signals.h"
 #include "test_signals_utils.h"
 
-struct tdescr *current;
+struct tdescr *current = &tde;
 
 int main(int argc, char *argv[])
 {
-	current = &tde;
+	/*
+	 * Ensure GCS is at least enabled throughout the tests if
+	 * supported, otherwise the inability to return from the
+	 * function that enabled GCS makes it very inconvenient to set
+	 * up test cases.  The prctl() may fail if GCS was locked by
+	 * libc setup code.
+	 */
+	if (getauxval(AT_HWCAP) & HWCAP_GCS)
+		gcs_set_state(PR_SHADOW_STACK_ENABLE);
 
 	ksft_print_msg("%s :: %s\n", current->name, current->descr);
 	if (test_setup(current) && test_init(current)) {
@@ -25,5 +37,6 @@ int main(int argc, char *argv[])
 	}
 	test_result(current);
 
-	return current->result;
+	/* Do not return in case GCS was enabled */
+	exit(current->result);
 }
diff --git a/tools/testing/selftests/arm64/signal/test_signals.h b/tools/testing/selftests/arm64/signal/test_signals.h
index 0c645834ddc3..ee75a2c25ce7 100644
--- a/tools/testing/selftests/arm64/signal/test_signals.h
+++ b/tools/testing/selftests/arm64/signal/test_signals.h
@@ -34,6 +34,8 @@ enum {
 	FSVE_BIT,
 	FSME_BIT,
 	FSME_FA64_BIT,
+	FSME2_BIT,
+	FGCS_BIT,
 	FMAX_END
 };
 
@@ -41,6 +43,8 @@ enum {
 #define FEAT_SVE		(1UL << FSVE_BIT)
 #define FEAT_SME		(1UL << FSME_BIT)
 #define FEAT_SME_FA64		(1UL << FSME_FA64_BIT)
+#define FEAT_SME2		(1UL << FSME2_BIT)
+#define FEAT_GCS		(1UL << FGCS_BIT)
 
 /*
  * A descriptor used to describe and configure a test case.
@@ -67,6 +71,10 @@ struct tdescr {
 	 * Zero when no signal is expected on success
 	 */
 	int			sig_ok;
+	/*
+	 * expected si_code for sig_ok, or 0 to not check
+	 */
+	int			sig_ok_code;
 	/* signum expected on unsupported CPU features. */
 	int			sig_unsupp;
 	/* a timeout in second for test completion */
diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c
index 308e229e58ab..5d3621921cfe 100644
--- a/tools/testing/selftests/arm64/signal/test_signals_utils.c
+++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c
@@ -29,6 +29,8 @@ static char const *const feats_names[FMAX_END] = {
 	" SVE ",
 	" SME ",
 	" FA64 ",
+	" SME2 ",
+	" GCS ",
 };
 
 #define MAX_FEATS_SZ	128
@@ -141,16 +143,25 @@ static bool handle_signal_ok(struct tdescr *td,
 			"current->token ZEROED...test is probably broken!\n");
 		abort();
 	}
-	/*
-	 * Trying to narrow down the SEGV to the ones generated by Kernel itself
-	 * via arm64_notify_segfault(). This is a best-effort check anyway, and
-	 * the si_code check may need to change if this aspect of the kernel
-	 * ABI changes.
-	 */
-	if (td->sig_ok == SIGSEGV && si->si_code != SEGV_ACCERR) {
-		fprintf(stdout,
-			"si_code != SEGV_ACCERR...test is probably broken!\n");
-		abort();
+	if (td->sig_ok_code) {
+		if (si->si_code != td->sig_ok_code) {
+			fprintf(stdout, "si_code is %d not %d\n",
+				si->si_code, td->sig_ok_code);
+			abort();
+		}
+	} else {
+		/*
+		 * Trying to narrow down the SEGV to the ones
+		 * generated by Kernel itself via
+		 * arm64_notify_segfault(). This is a best-effort
+		 * check anyway, and the si_code check may need to
+		 * change if this aspect of the kernel ABI changes.
+		 */
+		if (td->sig_ok == SIGSEGV && si->si_code != SEGV_ACCERR) {
+			fprintf(stdout,
+				"si_code != SEGV_ACCERR...test is probably broken!\n");
+			abort();
+		}
 	}
 	td->pass = 1;
 	/*
@@ -192,8 +203,10 @@ static bool handle_signal_copyctx(struct tdescr *td,
 		 * in the copy, this was previously validated in
 		 * ASSERT_GOOD_CONTEXT().
 		 */
-		to_copy = offset + sizeof(struct extra_context) + 16 +
-			extra->size;
+		to_copy = __builtin_offsetof(ucontext_t,
+					     uc_mcontext.__reserved);
+		to_copy += offset + sizeof(struct extra_context) + 16;
+		to_copy += extra->size;
 		copied_extra = (struct extra_context *)&(td->live_uc->uc_mcontext.__reserved[offset]);
 	} else {
 		copied_extra = NULL;
@@ -246,7 +259,8 @@ static void default_handler(int signum, siginfo_t *si, void *uc)
 			fprintf(stderr, "-- Timeout !\n");
 		} else {
 			fprintf(stderr,
-				"-- RX UNEXPECTED SIGNAL: %d\n", signum);
+				"-- RX UNEXPECTED SIGNAL: %d code %d address %p\n",
+				signum, si->si_code, si->si_addr);
 		}
 		default_result(current, 1);
 	}
@@ -323,6 +337,10 @@ int test_init(struct tdescr *td)
 			td->feats_supported |= FEAT_SME;
 		if (getauxval(AT_HWCAP2) & HWCAP2_SME_FA64)
 			td->feats_supported |= FEAT_SME_FA64;
+		if (getauxval(AT_HWCAP2) & HWCAP2_SME2)
+			td->feats_supported |= FEAT_SME2;
+		if (getauxval(AT_HWCAP) & HWCAP_GCS)
+			td->feats_supported |= FEAT_GCS;
 		if (feats_ok(td)) {
 			if (td->feats_required & td->feats_supported)
 				fprintf(stderr,
diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.h b/tools/testing/selftests/arm64/signal/test_signals_utils.h
index 222093f51b67..36fc12b3cd60 100644
--- a/tools/testing/selftests/arm64/signal/test_signals_utils.h
+++ b/tools/testing/selftests/arm64/signal/test_signals_utils.h
@@ -6,8 +6,11 @@
 
 #include <assert.h>
 #include <stdio.h>
+#include <stdint.h>
 #include <string.h>
 
+#include <linux/compiler.h>
+
 #include "test_signals.h"
 
 int test_init(struct tdescr *td);
@@ -16,6 +19,44 @@ void test_cleanup(struct tdescr *td);
 int test_run(struct tdescr *td);
 void test_result(struct tdescr *td);
 
+#ifndef __NR_prctl
+#define __NR_prctl 167
+#endif
+
+/*
+ * The prctl takes 1 argument but we need to ensure that the other
+ * values passed in registers to the syscall are zero since the kernel
+ * validates them.
+ */
+#define gcs_set_state(state)					\
+	({								\
+		register long _num  __asm__ ("x8") = __NR_prctl;	\
+		register long _arg1 __asm__ ("x0") =  PR_SET_SHADOW_STACK_STATUS; \
+		register long _arg2 __asm__ ("x1") = (long)(state);	\
+		register long _arg3 __asm__ ("x2") = 0;			\
+		register long _arg4 __asm__ ("x3") = 0;			\
+		register long _arg5 __asm__ ("x4") = 0;			\
+	                                                                      \
+		__asm__  volatile (					\
+			"svc #0\n"					\
+			: "=r"(_arg1)					\
+			: "r"(_arg1), "r"(_arg2),			\
+			  "r"(_arg3), "r"(_arg4),			\
+			  "r"(_arg5), "r"(_num)				\
+			: "memory", "cc"				\
+			);						\
+		_arg1;							\
+	})
+
+static inline __attribute__((always_inline)) uint64_t get_gcspr_el0(void)
+{
+	uint64_t val;
+
+	asm volatile("mrs %0, S3_3_C2_C5_1" : "=r" (val));
+
+	return val;
+}
+
 static inline bool feats_ok(struct tdescr *td)
 {
 	if (td->feats_incompatible & td->feats_supported)
@@ -60,13 +101,25 @@ static __always_inline bool get_current_context(struct tdescr *td,
 						size_t dest_sz)
 {
 	static volatile bool seen_already;
+	int i;
+	char *uc = (char *)dest_uc;
 
 	assert(td && dest_uc);
 	/* it's a genuine invocation..reinit */
 	seen_already = 0;
 	td->live_uc_valid = 0;
 	td->live_sz = dest_sz;
-	memset(dest_uc, 0x00, td->live_sz);
+
+	/*
+	 * This is a memset() but we don't want the compiler to
+	 * optimise it into either instructions or a library call
+	 * which might be incompatible with streaming mode.
+	 */
+	for (i = 0; i < td->live_sz; i++) {
+		uc[i] = 0;
+		OPTIMIZER_HIDE_VAR(uc[0]);
+	}
+
 	td->live_uc = dest_uc;
 	/*
 	 * Grab ucontext_t triggering a SIGTRAP.
@@ -104,6 +157,17 @@ static __always_inline bool get_current_context(struct tdescr *td,
 		      : "memory");
 
 	/*
+	 * If we were grabbing a streaming mode context then we may
+	 * have entered streaming mode behind the system's back and
+	 * libc or compiler generated code might decide to do
+	 * something invalid in streaming mode, or potentially even
+	 * the state of ZA.  Issue a SMSTOP to exit both now we have
+	 * grabbed the state.
+	 */
+	if (td->feats_supported & FEAT_SME)
+		asm volatile("msr S0_3_C4_C6_3, xzr");
+
+	/*
 	 * If we get here with seen_already==1 it implies the td->live_uc
 	 * context has been used to get back here....this probably means
 	 * a test has failed to cause a SEGV...anyway live_uc does not
diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c
index ebd5815b54bb..dfd6a2badf9f 100644
--- a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c
+++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c
@@ -6,44 +6,28 @@
  * handler, this is not supported and is expected to segfault.
  */
 
+#include <kselftest.h>
 #include <signal.h>
 #include <ucontext.h>
 #include <sys/prctl.h>
 
 #include "test_signals_utils.h"
+#include "sve_helpers.h"
 #include "testcases.h"
 
 struct fake_sigframe sf;
-static unsigned int vls[SVE_VQ_MAX];
-unsigned int nvls = 0;
 
 static bool sme_get_vls(struct tdescr *td)
 {
-	int vq, vl;
+	int res = sve_fill_vls(VLS_USE_SME, 2);
 
-	/*
-	 * Enumerate up to SVE_VQ_MAX vector lengths
-	 */
-	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
-		vl = prctl(PR_SVE_SET_VL, vq * 16);
-		if (vl == -1)
-			return false;
+	if (!res)
+		return true;
 
-		vl &= PR_SME_VL_LEN_MASK;
+	if (res == KSFT_SKIP)
+		td->result = KSFT_SKIP;
 
-		/* Skip missing VLs */
-		vq = sve_vq_from_vl(vl);
-
-		vls[nvls++] = vl;
-	}
-
-	/* We need at least two VLs */
-	if (nvls < 2) {
-		fprintf(stderr, "Only %d VL supported\n", nvls);
-		return false;
-	}
-
-	return true;
+	return false;
 }
 
 static int fake_sigreturn_ssve_change_vl(struct tdescr *td,
@@ -51,30 +35,30 @@ static int fake_sigreturn_ssve_change_vl(struct tdescr *td,
 {
 	size_t resv_sz, offset;
 	struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf);
-	struct sve_context *sve;
+	struct za_context *za;
 
 	/* Get a signal context with a SME ZA frame in it */
 	if (!get_current_context(td, &sf.uc, sizeof(sf.uc)))
 		return 1;
 
 	resv_sz = GET_SF_RESV_SIZE(sf);
-	head = get_header(head, SVE_MAGIC, resv_sz, &offset);
+	head = get_header(head, ZA_MAGIC, resv_sz, &offset);
 	if (!head) {
-		fprintf(stderr, "No SVE context\n");
+		fprintf(stderr, "No ZA context\n");
 		return 1;
 	}
 
-	if (head->size != sizeof(struct sve_context)) {
+	if (head->size != sizeof(struct za_context)) {
 		fprintf(stderr, "Register data present, aborting\n");
 		return 1;
 	}
 
-	sve = (struct sve_context *)head;
+	za = (struct za_context *)head;
 
 	/* No changes are supported; init left us at minimum VL so go to max */
 	fprintf(stderr, "Attempting to change VL from %d to %d\n",
-		sve->vl, vls[0]);
-	sve->vl = vls[0];
+		za->vl, vls[0]);
+	za->vl = vls[0];
 
 	fake_sigreturn(&sf, sizeof(sf), 0);
 
diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sve_change_vl.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sve_change_vl.c
index e2a452190511..e1ccf8f85a70 100644
--- a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sve_change_vl.c
+++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sve_change_vl.c
@@ -12,40 +12,22 @@
 #include <sys/prctl.h>
 
 #include "test_signals_utils.h"
+#include "sve_helpers.h"
 #include "testcases.h"
 
 struct fake_sigframe sf;
-static unsigned int vls[SVE_VQ_MAX];
-unsigned int nvls = 0;
 
 static bool sve_get_vls(struct tdescr *td)
 {
-	int vq, vl;
+	int res = sve_fill_vls(VLS_USE_SVE, 2);
 
-	/*
-	 * Enumerate up to SVE_VQ_MAX vector lengths
-	 */
-	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
-		vl = prctl(PR_SVE_SET_VL, vq * 16);
-		if (vl == -1)
-			return false;
+	if (!res)
+		return true;
 
-		vl &= PR_SVE_VL_LEN_MASK;
-
-		/* Skip missing VLs */
-		vq = sve_vq_from_vl(vl);
-
-		vls[nvls++] = vl;
-	}
-
-	/* We need at least two VLs */
-	if (nvls < 2) {
-		fprintf(stderr, "Only %d VL supported\n", nvls);
+	if (res == KSFT_SKIP)
 		td->result = KSFT_SKIP;
-		return false;
-	}
 
-	return true;
+	return false;
 }
 
 static int fake_sigreturn_sve_change_vl(struct tdescr *td,
diff --git a/tools/testing/selftests/arm64/signal/testcases/fpmr_siginfo.c b/tools/testing/selftests/arm64/signal/testcases/fpmr_siginfo.c
new file mode 100644
index 000000000000..e9d24685e741
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/fpmr_siginfo.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 ARM Limited
+ *
+ * Verify that the FPMR register context in signal frames is set up as
+ * expected.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/auxv.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+#include <asm/sigcontext.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+static union {
+	ucontext_t uc;
+	char buf[1024 * 128];
+} context;
+
+#define SYS_FPMR "S3_3_C4_C4_2"
+
+static uint64_t get_fpmr(void)
+{
+	uint64_t val;
+
+	asm volatile (
+		"mrs	%0, " SYS_FPMR "\n"
+		: "=r"(val)
+		:
+		: "cc");
+
+	return val;
+}
+
+int fpmr_present(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+	struct _aarch64_ctx *head = GET_BUF_RESV_HEAD(context);
+	struct fpmr_context *fpmr_ctx;
+	size_t offset;
+	bool in_sigframe;
+	bool have_fpmr;
+	__u64 orig_fpmr;
+
+	have_fpmr = getauxval(AT_HWCAP2) & HWCAP2_FPMR;
+	if (have_fpmr)
+		orig_fpmr = get_fpmr();
+
+	if (!get_current_context(td, &context.uc, sizeof(context)))
+		return 1;
+
+	fpmr_ctx = (struct fpmr_context *)
+		get_header(head, FPMR_MAGIC, td->live_sz, &offset);
+
+	in_sigframe = fpmr_ctx != NULL;
+
+	fprintf(stderr, "FPMR sigframe %s on system %s FPMR\n",
+		in_sigframe ? "present" : "absent",
+		have_fpmr ? "with" : "without");
+
+	td->pass = (in_sigframe == have_fpmr);
+
+	if (have_fpmr && fpmr_ctx) {
+		if (fpmr_ctx->fpmr != orig_fpmr) {
+			fprintf(stderr, "FPMR in frame is %llx, was %llx\n",
+				fpmr_ctx->fpmr, orig_fpmr);
+			td->pass = false;
+		}
+	}
+
+	return 0;
+}
+
+struct tdescr tde = {
+	.name = "FPMR",
+	.descr = "Validate that FPMR is present as expected",
+	.timeout = 3,
+	.run = fpmr_present,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/gcs_exception_fault.c b/tools/testing/selftests/arm64/signal/testcases/gcs_exception_fault.c
new file mode 100644
index 000000000000..6228448b2ae7
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/gcs_exception_fault.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 ARM Limited
+ */
+
+#include <errno.h>
+#include <signal.h>
+#include <unistd.h>
+
+#include <sys/mman.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+/*
+ * We should get this from asm/siginfo.h but the testsuite is being
+ * clever with redefining siginfo_t.
+ */
+#ifndef SEGV_CPERR
+#define SEGV_CPERR 10
+#endif
+
+static inline void gcsss1(uint64_t Xt)
+{
+	asm volatile (
+		"sys #3, C7, C7, #2, %0\n"
+		:
+		: "rZ" (Xt)
+		: "memory");
+}
+
+static int gcs_op_fault_trigger(struct tdescr *td)
+{
+	/*
+	 * The slot below our current GCS should be in a valid GCS but
+	 * must not have a valid cap in it.
+	 */
+	gcsss1(get_gcspr_el0() - 8);
+
+	return 0;
+}
+
+static int gcs_op_fault_signal(struct tdescr *td, siginfo_t *si,
+				  ucontext_t *uc)
+{
+	ASSERT_GOOD_CONTEXT(uc);
+
+	return 1;
+}
+
+struct tdescr tde = {
+	.name = "Invalid GCS operation",
+	.descr = "An invalid GCS operation generates the expected signal",
+	.feats_required = FEAT_GCS,
+	.timeout = 3,
+	.sig_ok = SIGSEGV,
+	.sig_ok_code = SEGV_CPERR,
+	.sanity_disabled = true,
+	.trigger = gcs_op_fault_trigger,
+	.run = gcs_op_fault_signal,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/gcs_frame.c b/tools/testing/selftests/arm64/signal/testcases/gcs_frame.c
new file mode 100644
index 000000000000..b405d82321da
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/gcs_frame.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 ARM Limited
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+static union {
+	ucontext_t uc;
+	char buf[1024 * 64];
+} context;
+
+static int gcs_regs(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+	size_t offset;
+	struct _aarch64_ctx *head = GET_BUF_RESV_HEAD(context);
+	struct gcs_context *gcs;
+	unsigned long expected, gcspr;
+	uint64_t *u64_val;
+	int ret;
+
+	ret = prctl(PR_GET_SHADOW_STACK_STATUS, &expected, 0, 0, 0);
+	if (ret != 0) {
+		fprintf(stderr, "Unable to query GCS status\n");
+		return 1;
+	}
+
+	/* We expect a cap to be added to the GCS in the signal frame */
+	gcspr = get_gcspr_el0();
+	gcspr -= 8;
+	fprintf(stderr, "Expecting GCSPR_EL0 %lx\n", gcspr);
+
+	if (!get_current_context(td, &context.uc, sizeof(context))) {
+		fprintf(stderr, "Failed getting context\n");
+		return 1;
+	}
+
+	/* Ensure that the signal restore token was consumed */
+	u64_val = (uint64_t *)get_gcspr_el0() + 1;
+	if (*u64_val) {
+		fprintf(stderr, "GCS value at %p is %lx not 0\n",
+			u64_val, *u64_val);
+		return 1;
+	}
+
+	fprintf(stderr, "Got context\n");
+
+	head = get_header(head, GCS_MAGIC, GET_BUF_RESV_SIZE(context),
+			  &offset);
+	if (!head) {
+		fprintf(stderr, "No GCS context\n");
+		return 1;
+	}
+
+	gcs = (struct gcs_context *)head;
+
+	/* Basic size validation is done in get_current_context() */
+
+	if (gcs->features_enabled != expected) {
+		fprintf(stderr, "Features enabled %llx but expected %lx\n",
+			gcs->features_enabled, expected);
+		return 1;
+	}
+
+	if (gcs->gcspr != gcspr) {
+		fprintf(stderr, "Got GCSPR %llx but expected %lx\n",
+			gcs->gcspr, gcspr);
+		return 1;
+	}
+
+	fprintf(stderr, "GCS context validated\n");
+	td->pass = 1;
+
+	return 0;
+}
+
+struct tdescr tde = {
+	.name = "GCS basics",
+	.descr = "Validate a GCS signal context",
+	.feats_required = FEAT_GCS,
+	.timeout = 3,
+	.run = gcs_regs,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/gcs_write_fault.c b/tools/testing/selftests/arm64/signal/testcases/gcs_write_fault.c
new file mode 100644
index 000000000000..faeabb18c4b2
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/gcs_write_fault.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 ARM Limited
+ */
+
+#include <errno.h>
+#include <signal.h>
+#include <unistd.h>
+
+#include <sys/mman.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+static uint64_t *gcs_page;
+
+#ifndef __NR_map_shadow_stack
+#define __NR_map_shadow_stack 453
+#endif
+
+static bool alloc_gcs(struct tdescr *td)
+{
+	long page_size = sysconf(_SC_PAGE_SIZE);
+
+	gcs_page = (void *)syscall(__NR_map_shadow_stack, 0,
+				   page_size, 0);
+	if (gcs_page == MAP_FAILED) {
+		fprintf(stderr, "Failed to map %ld byte GCS: %d\n",
+			page_size, errno);
+		return false;
+	}
+
+	return true;
+}
+
+static int gcs_write_fault_trigger(struct tdescr *td)
+{
+	/* Verify that the page is readable (ie, not completely unmapped) */
+	fprintf(stderr, "Read value 0x%lx\n", gcs_page[0]);
+
+	/* A regular write should trigger a fault */
+	gcs_page[0] = EINVAL;
+
+	return 0;
+}
+
+static int gcs_write_fault_signal(struct tdescr *td, siginfo_t *si,
+				  ucontext_t *uc)
+{
+	ASSERT_GOOD_CONTEXT(uc);
+
+	return 1;
+}
+
+
+struct tdescr tde = {
+	.name = "GCS write fault",
+	.descr = "Normal writes to a GCS segfault",
+	.feats_required = FEAT_GCS,
+	.timeout = 3,
+	.sig_ok = SIGSEGV,
+	.sanity_disabled = true,
+	.init = alloc_gcs,
+	.trigger = gcs_write_fault_trigger,
+	.run = gcs_write_fault_signal,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/poe_siginfo.c b/tools/testing/selftests/arm64/signal/testcases/poe_siginfo.c
new file mode 100644
index 000000000000..36bd9940ee05
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/poe_siginfo.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 Arm Limited
+ *
+ * Verify that the POR_EL0 register context in signal frames is set up as
+ * expected.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/auxv.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+#include <asm/sigcontext.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+static union {
+	ucontext_t uc;
+	char buf[1024 * 128];
+} context;
+
+#define SYS_POR_EL0 "S3_3_C10_C2_4"
+
+static uint64_t get_por_el0(void)
+{
+	uint64_t val;
+
+	asm volatile(
+		"mrs	%0, " SYS_POR_EL0 "\n"
+		: "=r"(val)
+		:
+		: );
+
+	return val;
+}
+
+int poe_present(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+	struct _aarch64_ctx *head = GET_BUF_RESV_HEAD(context);
+	struct poe_context *poe_ctx;
+	size_t offset;
+	bool in_sigframe;
+	bool have_poe;
+	__u64 orig_poe;
+
+	have_poe = getauxval(AT_HWCAP2) & HWCAP2_POE;
+	if (have_poe)
+		orig_poe = get_por_el0();
+
+	if (!get_current_context(td, &context.uc, sizeof(context)))
+		return 1;
+
+	poe_ctx = (struct poe_context *)
+		get_header(head, POE_MAGIC, td->live_sz, &offset);
+
+	in_sigframe = poe_ctx != NULL;
+
+	fprintf(stderr, "POR_EL0 sigframe %s on system %s POE\n",
+		in_sigframe ? "present" : "absent",
+		have_poe ? "with" : "without");
+
+	td->pass = (in_sigframe == have_poe);
+
+	/*
+	 * Check that the value we read back was the one present at
+	 * the time that the signal was triggered.
+	 */
+	if (have_poe && poe_ctx) {
+		if (poe_ctx->por_el0 != orig_poe) {
+			fprintf(stderr, "POR_EL0 in frame is %llx, was %llx\n",
+				poe_ctx->por_el0, orig_poe);
+			td->pass = false;
+		}
+	}
+
+	return 0;
+}
+
+struct tdescr tde = {
+	.name = "POR_EL0",
+	.descr = "Validate that POR_EL0 is present as expected",
+	.timeout = 3,
+	.run = poe_present,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c
index d0a178945b1a..1dbca9afb13c 100644
--- a/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c
+++ b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c
@@ -6,47 +6,31 @@
  * set up as expected.
  */
 
+#include <kselftest.h>
 #include <signal.h>
 #include <ucontext.h>
 #include <sys/prctl.h>
 
 #include "test_signals_utils.h"
+#include "sve_helpers.h"
 #include "testcases.h"
 
 static union {
 	ucontext_t uc;
 	char buf[1024 * 64];
 } context;
-static unsigned int vls[SVE_VQ_MAX];
-unsigned int nvls = 0;
 
 static bool sme_get_vls(struct tdescr *td)
 {
-	int vq, vl;
+	int res = sve_fill_vls(VLS_USE_SME, 1);
 
-	/*
-	 * Enumerate up to SVE_VQ_MAX vector lengths
-	 */
-	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
-		vl = prctl(PR_SME_SET_VL, vq * 16);
-		if (vl == -1)
-			return false;
-
-		vl &= PR_SME_VL_LEN_MASK;
-
-		/* Skip missing VLs */
-		vq = sve_vq_from_vl(vl);
+	if (!res)
+		return true;
 
-		vls[nvls++] = vl;
-	}
-
-	/* We need at least one VL */
-	if (nvls < 1) {
-		fprintf(stderr, "Only %d VL supported\n", nvls);
-		return false;
-	}
+	if (res == KSFT_SKIP)
+		td->result = KSFT_SKIP;
 
-	return true;
+	return false;
 }
 
 static void setup_ssve_regs(void)
@@ -92,10 +76,20 @@ static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc,
 		return 1;
 	}
 
+	if (!(ssve->flags & SVE_SIG_FLAG_SM)) {
+		fprintf(stderr, "SVE_SIG_FLAG_SM not set in SVE record\n");
+		return 1;
+	}
+
 	/* The actual size validation is done in get_current_context() */
 	fprintf(stderr, "Got expected size %u and VL %d\n",
 		head->size, ssve->vl);
 
+	if (get_svcr() != 0) {
+		fprintf(stderr, "Unexpected SVCR %lx\n", get_svcr());
+		return 1;
+	}
+
 	return 0;
 }
 
@@ -116,12 +110,7 @@ static int sme_regs(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
 struct tdescr tde = {
 	.name = "Streaming SVE registers",
 	.descr = "Check that we get the right Streaming SVE registers reported",
-	/*
-	 * We shouldn't require FA64 but things like memset() used in the
-	 * helpers might use unsupported instructions so for now disable
-	 * the test unless we've got the full instruction set.
-	 */
-	.feats_required = FEAT_SME | FEAT_SME_FA64,
+	.feats_required = FEAT_SME,
 	.timeout = 3,
 	.init = sme_get_vls,
 	.run = sme_regs,
diff --git a/tools/testing/selftests/arm64/signal/testcases/ssve_za_regs.c b/tools/testing/selftests/arm64/signal/testcases/ssve_za_regs.c
new file mode 100644
index 000000000000..5557e116e973
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/ssve_za_regs.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 ARM Limited
+ *
+ * Verify that both the streaming SVE and ZA register context in
+ * signal frames is set up as expected when enabled simultaneously.
+ */
+
+#include <kselftest.h>
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "sve_helpers.h"
+#include "testcases.h"
+
+static union {
+	ucontext_t uc;
+	char buf[1024 * 128];
+} context;
+
+static bool sme_get_vls(struct tdescr *td)
+{
+	int res = sve_fill_vls(VLS_USE_SME, 1);
+
+	if (!res)
+		return true;
+
+	if (res == KSFT_SKIP)
+		td->result = KSFT_SKIP;
+
+	return false;
+}
+
+static void setup_regs(void)
+{
+	/* smstart sm; real data is TODO */
+	asm volatile(".inst 0xd503437f" : : : );
+
+	/* smstart za; real data is TODO */
+	asm volatile(".inst 0xd503457f" : : : );
+}
+
+static char zeros[ZA_SIG_REGS_SIZE(SVE_VQ_MAX)];
+
+static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc,
+			 unsigned int vl)
+{
+	size_t offset;
+	struct _aarch64_ctx *head = GET_BUF_RESV_HEAD(context);
+	struct _aarch64_ctx *regs;
+	struct sve_context *ssve;
+	struct za_context *za;
+	int ret;
+
+	fprintf(stderr, "Testing VL %d\n", vl);
+
+	ret = prctl(PR_SME_SET_VL, vl);
+	if (ret != vl) {
+		fprintf(stderr, "Failed to set VL, got %d\n", ret);
+		return 1;
+	}
+
+	/*
+	 * Get a signal context which should have the SVE and ZA
+	 * frames in it.
+	 */
+	setup_regs();
+	if (!get_current_context(td, &context.uc, sizeof(context)))
+		return 1;
+
+	regs = get_header(head, SVE_MAGIC, GET_BUF_RESV_SIZE(context),
+			  &offset);
+	if (!regs) {
+		fprintf(stderr, "No SVE context\n");
+		return 1;
+	}
+
+	ssve = (struct sve_context *)regs;
+	if (ssve->vl != vl) {
+		fprintf(stderr, "Got SSVE VL %d, expected %d\n", ssve->vl, vl);
+		return 1;
+	}
+
+	if (!(ssve->flags & SVE_SIG_FLAG_SM)) {
+		fprintf(stderr, "SVE_SIG_FLAG_SM not set in SVE record\n");
+		return 1;
+	}
+
+	fprintf(stderr, "Got expected SSVE size %u and VL %d\n",
+		regs->size, ssve->vl);
+
+	regs = get_header(head, ZA_MAGIC, GET_BUF_RESV_SIZE(context),
+			  &offset);
+	if (!regs) {
+		fprintf(stderr, "No ZA context\n");
+		return 1;
+	}
+
+	za = (struct za_context *)regs;
+	if (za->vl != vl) {
+		fprintf(stderr, "Got ZA VL %d, expected %d\n", za->vl, vl);
+		return 1;
+	}
+
+	fprintf(stderr, "Got expected ZA size %u and VL %d\n",
+		regs->size, za->vl);
+
+	/* We didn't load any data into ZA so it should be all zeros */
+	if (memcmp(zeros, (char *)za + ZA_SIG_REGS_OFFSET,
+		   ZA_SIG_REGS_SIZE(sve_vq_from_vl(za->vl))) != 0) {
+		fprintf(stderr, "ZA data invalid\n");
+		return 1;
+	}
+
+	return 0;
+}
+
+static int sme_regs(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+	int i;
+
+	for (i = 0; i < nvls; i++) {
+		if (do_one_sme_vl(td, si, uc, vls[i]))
+			return 1;
+	}
+
+	td->pass = 1;
+
+	return 0;
+}
+
+struct tdescr tde = {
+	.name = "Streaming SVE registers",
+	.descr = "Check that we get the right Streaming SVE registers reported",
+	.feats_required = FEAT_SME,
+	.timeout = 3,
+	.init = sme_get_vls,
+	.run = sme_regs,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/sve_regs.c b/tools/testing/selftests/arm64/signal/testcases/sve_regs.c
index 8b16eabbb769..8143eb1c58c1 100644
--- a/tools/testing/selftests/arm64/signal/testcases/sve_regs.c
+++ b/tools/testing/selftests/arm64/signal/testcases/sve_regs.c
@@ -6,47 +6,31 @@
  * expected.
  */
 
+#include <kselftest.h>
 #include <signal.h>
 #include <ucontext.h>
 #include <sys/prctl.h>
 
 #include "test_signals_utils.h"
+#include "sve_helpers.h"
 #include "testcases.h"
 
 static union {
 	ucontext_t uc;
 	char buf[1024 * 64];
 } context;
-static unsigned int vls[SVE_VQ_MAX];
-unsigned int nvls = 0;
 
 static bool sve_get_vls(struct tdescr *td)
 {
-	int vq, vl;
+	int res = sve_fill_vls(VLS_USE_SVE, 1);
 
-	/*
-	 * Enumerate up to SVE_VQ_MAX vector lengths
-	 */
-	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
-		vl = prctl(PR_SVE_SET_VL, vq * 16);
-		if (vl == -1)
-			return false;
-
-		vl &= PR_SVE_VL_LEN_MASK;
-
-		/* Skip missing VLs */
-		vq = sve_vq_from_vl(vl);
+	if (!res)
+		return true;
 
-		vls[nvls++] = vl;
-	}
-
-	/* We need at least one VL */
-	if (nvls < 1) {
-		fprintf(stderr, "Only %d VL supported\n", nvls);
-		return false;
-	}
+	if (res == KSFT_SKIP)
+		td->result = KSFT_SKIP;
 
-	return true;
+	return false;
 }
 
 static void setup_sve_regs(void)
diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.c b/tools/testing/selftests/arm64/signal/testcases/testcases.c
index d2eda7b5de26..0c1a6b26afac 100644
--- a/tools/testing/selftests/arm64/signal/testcases/testcases.c
+++ b/tools/testing/selftests/arm64/signal/testcases/testcases.c
@@ -6,29 +6,6 @@
 
 #include "testcases.h"
 
-struct _aarch64_ctx *get_header(struct _aarch64_ctx *head, uint32_t magic,
-				size_t resv_sz, size_t *offset)
-{
-	size_t offs = 0;
-	struct _aarch64_ctx *found = NULL;
-
-	if (!head || resv_sz < HDR_SZ)
-		return found;
-
-	while (offs <= resv_sz - HDR_SZ &&
-	       head->magic != magic && head->magic) {
-		offs += head->size;
-		head = GET_RESV_NEXT_HEAD(head);
-	}
-	if (head->magic == magic) {
-		found = head;
-		if (offset)
-			*offset = offs;
-	}
-
-	return found;
-}
-
 bool validate_extra_context(struct extra_context *extra, char **err,
 			    void **extra_data, size_t *extra_size)
 {
@@ -108,6 +85,26 @@ bool validate_za_context(struct za_context *za, char **err)
 	return true;
 }
 
+bool validate_zt_context(struct zt_context *zt, char **err)
+{
+	if (!zt || !err)
+		return false;
+
+	/* If the context is present there should be at least one register */
+	if (zt->nregs == 0) {
+		*err = "no registers";
+		return false;
+	}
+
+	/* Size should agree with the number of registers */
+	if (zt->head.size != ZT_SIG_CONTEXT_SIZE(zt->nregs)) {
+		*err = "register count does not match size";
+		return false;
+	}
+
+	return true;
+}
+
 bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 {
 	bool terminated = false;
@@ -117,6 +114,7 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 	struct extra_context *extra = NULL;
 	struct sve_context *sve = NULL;
 	struct za_context *za = NULL;
+	struct zt_context *zt = NULL;
 	struct _aarch64_ctx *head =
 		(struct _aarch64_ctx *)uc->uc_mcontext.__reserved;
 	void *extra_data = NULL;
@@ -163,6 +161,14 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 			if (head->size != sizeof(struct esr_context))
 				*err = "Bad size for esr_context";
 			break;
+		case POE_MAGIC:
+			if (head->size != sizeof(struct poe_context))
+				*err = "Bad size for poe_context";
+			break;
+		case TPIDR2_MAGIC:
+			if (head->size != sizeof(struct tpidr2_context))
+				*err = "Bad size for tpidr2_context";
+			break;
 		case SVE_MAGIC:
 			if (flags & SVE_CTX)
 				*err = "Multiple SVE_MAGIC";
@@ -177,6 +183,28 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 			za = (struct za_context *)head;
 			new_flags |= ZA_CTX;
 			break;
+		case ZT_MAGIC:
+			if (flags & ZT_CTX)
+				*err = "Multiple ZT_MAGIC";
+			/* Size is validated in validate_za_context() */
+			zt = (struct zt_context *)head;
+			new_flags |= ZT_CTX;
+			break;
+		case FPMR_MAGIC:
+			if (flags & FPMR_CTX)
+				*err = "Multiple FPMR_MAGIC";
+			else if (head->size !=
+				 sizeof(struct fpmr_context))
+				*err = "Bad size for fpmr_context";
+			new_flags |= FPMR_CTX;
+			break;
+		case GCS_MAGIC:
+			if (flags & GCS_CTX)
+				*err = "Multiple GCS_MAGIC";
+			if (head->size != sizeof(struct gcs_context))
+				*err = "Bad size for gcs_context";
+			new_flags |= GCS_CTX;
+			break;
 		case EXTRA_MAGIC:
 			if (flags & EXTRA_CTX)
 				*err = "Multiple EXTRA_MAGIC";
@@ -234,6 +262,9 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 		if (new_flags & ZA_CTX)
 			if (!validate_za_context(za, err))
 				return false;
+		if (new_flags & ZT_CTX)
+			if (!validate_zt_context(zt, err))
+				return false;
 
 		flags |= new_flags;
 
@@ -245,6 +276,11 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
 		return false;
 	}
 
+	if (terminated && (flags & ZT_CTX) && !(flags & ZA_CTX)) {
+		*err = "ZT context but no ZA context";
+		return false;
+	}
+
 	return true;
 }
 
diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.h b/tools/testing/selftests/arm64/signal/testcases/testcases.h
index 040afded0b76..98b97efdda23 100644
--- a/tools/testing/selftests/arm64/signal/testcases/testcases.h
+++ b/tools/testing/selftests/arm64/signal/testcases/testcases.h
@@ -18,12 +18,18 @@
 #define SVE_CTX		(1 << 1)
 #define ZA_CTX		(1 << 2)
 #define EXTRA_CTX	(1 << 3)
+#define ZT_CTX		(1 << 4)
+#define FPMR_CTX	(1 << 5)
+#define GCS_CTX		(1 << 6)
 
 #define KSFT_BAD_MAGIC	0xdeadbeef
 
 #define HDR_SZ \
 	sizeof(struct _aarch64_ctx)
 
+#define GET_UC_RESV_HEAD(uc) \
+	(struct _aarch64_ctx *)(&(uc->uc_mcontext.__reserved))
+
 #define GET_SF_RESV_HEAD(sf) \
 	(struct _aarch64_ctx *)(&(sf).uc.uc_mcontext.__reserved)
 
@@ -86,8 +92,29 @@ struct fake_sigframe {
 
 bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err);
 
-struct _aarch64_ctx *get_header(struct _aarch64_ctx *head, uint32_t magic,
-				size_t resv_sz, size_t *offset);
+static inline struct _aarch64_ctx *get_header(struct _aarch64_ctx *head, uint32_t magic,
+				size_t resv_sz, size_t *offset)
+{
+	size_t offs = 0;
+	struct _aarch64_ctx *found = NULL;
+
+	if (!head || resv_sz < HDR_SZ)
+		return found;
+
+	while (offs <= resv_sz - HDR_SZ &&
+	       head->magic != magic && head->magic) {
+		offs += head->size;
+		head = GET_RESV_NEXT_HEAD(head);
+	}
+	if (head->magic == magic) {
+		found = head;
+		if (offset)
+			*offset = offs;
+	}
+
+	return found;
+}
+
 
 static inline struct _aarch64_ctx *get_terminator(struct _aarch64_ctx *head,
 						  size_t resv_sz,
diff --git a/tools/testing/selftests/arm64/signal/testcases/tpidr2_restore.c b/tools/testing/selftests/arm64/signal/testcases/tpidr2_restore.c
new file mode 100644
index 000000000000..f9a86c00c28c
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/tpidr2_restore.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2023 ARM Limited
+ *
+ * Verify that the TPIDR2 register context in signal frames is restored.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/auxv.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+#include <asm/sigcontext.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+#define SYS_TPIDR2 "S3_3_C13_C0_5"
+
+static uint64_t get_tpidr2(void)
+{
+	uint64_t val;
+
+	asm volatile (
+		"mrs	%0, " SYS_TPIDR2 "\n"
+		: "=r"(val)
+		:
+		: "cc");
+
+	return val;
+}
+
+static void set_tpidr2(uint64_t val)
+{
+	asm volatile (
+		"msr	" SYS_TPIDR2 ", %0\n"
+		:
+		: "r"(val)
+		: "cc");
+}
+
+
+static uint64_t initial_tpidr2;
+
+static bool save_tpidr2(struct tdescr *td)
+{
+	initial_tpidr2 = get_tpidr2();
+	fprintf(stderr, "Initial TPIDR2: %lx\n", initial_tpidr2);
+
+	return true;
+}
+
+static int modify_tpidr2(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+	uint64_t my_tpidr2 = get_tpidr2();
+
+	my_tpidr2++;
+	fprintf(stderr, "Setting TPIDR2 to %lx\n", my_tpidr2);
+	set_tpidr2(my_tpidr2);
+
+	return 0;
+}
+
+static void check_tpidr2(struct tdescr *td)
+{
+	uint64_t tpidr2 = get_tpidr2();
+
+	td->pass = tpidr2 == initial_tpidr2;
+
+	if (td->pass)
+		fprintf(stderr, "TPIDR2 restored\n");
+	else
+		fprintf(stderr, "TPIDR2 was %lx but is now %lx\n",
+			initial_tpidr2, tpidr2);
+}
+
+struct tdescr tde = {
+	.name = "TPIDR2 restore",
+	.descr = "Validate that TPIDR2 is restored from the sigframe",
+	.feats_required = FEAT_SME,
+	.timeout = 3,
+	.sig_trig = SIGUSR1,
+	.init = save_tpidr2,
+	.run = modify_tpidr2,
+	.check_result = check_tpidr2,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/tpidr2_siginfo.c b/tools/testing/selftests/arm64/signal/testcases/tpidr2_siginfo.c
new file mode 100644
index 000000000000..6a2c82bf7ead
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/tpidr2_siginfo.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022 ARM Limited
+ *
+ * Verify that the TPIDR2 register context in signal frames is set up as
+ * expected.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/auxv.h>
+#include <sys/prctl.h>
+#include <unistd.h>
+#include <asm/sigcontext.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+static union {
+	ucontext_t uc;
+	char buf[1024 * 128];
+} context;
+
+#define SYS_TPIDR2 "S3_3_C13_C0_5"
+
+static uint64_t get_tpidr2(void)
+{
+	uint64_t val;
+
+	asm volatile (
+		"mrs	%0, " SYS_TPIDR2 "\n"
+		: "=r"(val)
+		:
+		: "cc");
+
+	return val;
+}
+
+int tpidr2_present(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+	struct _aarch64_ctx *head = GET_BUF_RESV_HEAD(context);
+	struct tpidr2_context *tpidr2_ctx;
+	size_t offset;
+	bool in_sigframe;
+	bool have_sme;
+	__u64 orig_tpidr2;
+
+	have_sme = getauxval(AT_HWCAP2) & HWCAP2_SME;
+	if (have_sme)
+		orig_tpidr2 = get_tpidr2();
+
+	if (!get_current_context(td, &context.uc, sizeof(context)))
+		return 1;
+
+	tpidr2_ctx = (struct tpidr2_context *)
+		get_header(head, TPIDR2_MAGIC, td->live_sz, &offset);
+
+	in_sigframe = tpidr2_ctx != NULL;
+
+	fprintf(stderr, "TPIDR2 sigframe %s on system %s SME\n",
+		in_sigframe ? "present" : "absent",
+		have_sme ? "with" : "without");
+
+	td->pass = (in_sigframe == have_sme);
+
+	/*
+	 * Check that the value we read back was the one present at
+	 * the time that the signal was triggered.  TPIDR2 is owned by
+	 * libc so we can't safely choose the value and it is possible
+	 * that we may need to revisit this in future if something
+	 * starts deciding to set a new TPIDR2 between us reading and
+	 * the signal.
+	 */
+	if (have_sme && tpidr2_ctx) {
+		if (tpidr2_ctx->tpidr2 != orig_tpidr2) {
+			fprintf(stderr, "TPIDR2 in frame is %llx, was %llx\n",
+				tpidr2_ctx->tpidr2, orig_tpidr2);
+			td->pass = false;
+		}
+	}
+
+	return 0;
+}
+
+struct tdescr tde = {
+	.name = "TPIDR2",
+	.descr = "Validate that TPIDR2 is present as expected",
+	.timeout = 3,
+	.run = tpidr2_present,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/za_no_regs.c b/tools/testing/selftests/arm64/signal/testcases/za_no_regs.c
index 4d6f94b6178f..ce26e9c2fa5e 100644
--- a/tools/testing/selftests/arm64/signal/testcases/za_no_regs.c
+++ b/tools/testing/selftests/arm64/signal/testcases/za_no_regs.c
@@ -6,47 +6,31 @@
  * expected.
  */
 
+#include <kselftest.h>
 #include <signal.h>
 #include <ucontext.h>
 #include <sys/prctl.h>
 
 #include "test_signals_utils.h"
+#include "sve_helpers.h"
 #include "testcases.h"
 
 static union {
 	ucontext_t uc;
 	char buf[1024 * 128];
 } context;
-static unsigned int vls[SVE_VQ_MAX];
-unsigned int nvls = 0;
 
 static bool sme_get_vls(struct tdescr *td)
 {
-	int vq, vl;
+	int res = sve_fill_vls(VLS_USE_SME, 1);
 
-	/*
-	 * Enumerate up to SME_VQ_MAX vector lengths
-	 */
-	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
-		vl = prctl(PR_SME_SET_VL, vq * 16);
-		if (vl == -1)
-			return false;
-
-		vl &= PR_SME_VL_LEN_MASK;
-
-		/* Skip missing VLs */
-		vq = sve_vq_from_vl(vl);
+	if (!res)
+		return true;
 
-		vls[nvls++] = vl;
-	}
-
-	/* We need at least one VL */
-	if (nvls < 1) {
-		fprintf(stderr, "Only %d VL supported\n", nvls);
-		return false;
-	}
+	if (res == KSFT_SKIP)
+		td->result = KSFT_SKIP;
 
-	return true;
+	return false;
 }
 
 static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc,
diff --git a/tools/testing/selftests/arm64/signal/testcases/za_regs.c b/tools/testing/selftests/arm64/signal/testcases/za_regs.c
index ea45acb115d5..badaead5326a 100644
--- a/tools/testing/selftests/arm64/signal/testcases/za_regs.c
+++ b/tools/testing/selftests/arm64/signal/testcases/za_regs.c
@@ -6,47 +6,31 @@
  * expected.
  */
 
+#include <kselftest.h>
 #include <signal.h>
 #include <ucontext.h>
 #include <sys/prctl.h>
 
 #include "test_signals_utils.h"
+#include "sve_helpers.h"
 #include "testcases.h"
 
 static union {
 	ucontext_t uc;
 	char buf[1024 * 128];
 } context;
-static unsigned int vls[SVE_VQ_MAX];
-unsigned int nvls = 0;
 
 static bool sme_get_vls(struct tdescr *td)
 {
-	int vq, vl;
+	int res = sve_fill_vls(VLS_USE_SME, 1);
 
-	/*
-	 * Enumerate up to SME_VQ_MAX vector lengths
-	 */
-	for (vq = SVE_VQ_MAX; vq > 0; --vq) {
-		vl = prctl(PR_SME_SET_VL, vq * 16);
-		if (vl == -1)
-			return false;
-
-		vl &= PR_SME_VL_LEN_MASK;
-
-		/* Skip missing VLs */
-		vq = sve_vq_from_vl(vl);
-
-		vls[nvls++] = vl;
-	}
+	if (!res)
+		return true;
 
-	/* We need at least one VL */
-	if (nvls < 1) {
-		fprintf(stderr, "Only %d VL supported\n", nvls);
-		return false;
-	}
+	if (res == KSFT_SKIP)
+		td->result = KSFT_SKIP;
 
-	return true;
+	return false;
 }
 
 static void setup_za_regs(void)
@@ -107,6 +91,11 @@ static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc,
 		return 1;
 	}
 
+	if (get_svcr() != 0) {
+		fprintf(stderr, "Unexpected SVCR %lx\n", get_svcr());
+		return 1;
+	}
+
 	return 0;
 }
 
diff --git a/tools/testing/selftests/arm64/signal/testcases/zt_no_regs.c b/tools/testing/selftests/arm64/signal/testcases/zt_no_regs.c
new file mode 100644
index 000000000000..34f69bcf821e
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/zt_no_regs.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 ARM Limited
+ *
+ * Verify that using an instruction not supported in streaming mode
+ * traps when in streaming mode.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+static union {
+	ucontext_t uc;
+	char buf[1024 * 128];
+} context;
+
+int zt_no_regs_run(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+	size_t offset;
+	struct _aarch64_ctx *head = GET_BUF_RESV_HEAD(context);
+
+	/*
+	 * Get a signal context which should not have a ZT frame and
+	 * registers in it.
+	 */
+	if (!get_current_context(td, &context.uc, sizeof(context)))
+		return 1;
+
+	head = get_header(head, ZT_MAGIC, GET_BUF_RESV_SIZE(context), &offset);
+	if (head) {
+		fprintf(stderr, "Got unexpected ZT context\n");
+		return 1;
+	}
+
+	td->pass = 1;
+
+	return 0;
+}
+
+struct tdescr tde = {
+	.name = "ZT register data not present",
+	.descr = "Validate that ZT is not present when ZA is disabled",
+	.feats_required = FEAT_SME2,
+	.timeout = 3,
+	.sanity_disabled = true,
+	.run = zt_no_regs_run,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/zt_regs.c b/tools/testing/selftests/arm64/signal/testcases/zt_regs.c
new file mode 100644
index 000000000000..2e384d731618
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/zt_regs.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 ARM Limited
+ *
+ * Verify that using an instruction not supported in streaming mode
+ * traps when in streaming mode.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+static union {
+	ucontext_t uc;
+	char buf[1024 * 128];
+} context;
+
+static void enable_za(void)
+{
+	/* smstart za; real data is TODO */
+	asm volatile(".inst 0xd503457f" : : : );
+}
+
+int zt_regs_run(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+	size_t offset;
+	struct _aarch64_ctx *head = GET_BUF_RESV_HEAD(context);
+	struct zt_context *zt;
+	char *zeros;
+
+	/*
+	 * Get a signal context which should have a ZT frame and registers
+	 * in it.
+	 */
+	enable_za();
+	if (!get_current_context(td, &context.uc, sizeof(context)))
+		return 1;
+
+	head = get_header(head, ZT_MAGIC, GET_BUF_RESV_SIZE(context), &offset);
+	if (!head) {
+		fprintf(stderr, "No ZT context\n");
+		return 1;
+	}
+
+	zt = (struct zt_context *)head;
+	if (zt->nregs == 0) {
+		fprintf(stderr, "Got context with no registers\n");
+		return 1;
+	}
+
+	fprintf(stderr, "Got expected size %u for %d registers\n",
+		head->size, zt->nregs);
+
+	/* We didn't load any data into ZT so it should be all zeros */
+	zeros = malloc(ZT_SIG_REGS_SIZE(zt->nregs));
+	if (!zeros) {
+		fprintf(stderr, "Out of memory, nregs=%u\n", zt->nregs);
+		return 1;
+	}
+	memset(zeros, 0, ZT_SIG_REGS_SIZE(zt->nregs));
+
+	if (memcmp(zeros, (char *)zt + ZT_SIG_REGS_OFFSET,
+		   ZT_SIG_REGS_SIZE(zt->nregs)) != 0) {
+		fprintf(stderr, "ZT data invalid\n");
+		free(zeros);
+		return 1;
+	}
+
+	free(zeros);
+
+	td->pass = 1;
+
+	return 0;
+}
+
+struct tdescr tde = {
+	.name = "ZT register data",
+	.descr = "Validate that ZT is present and has data when ZA is enabled",
+	.feats_required = FEAT_SME2,
+	.timeout = 3,
+	.sanity_disabled = true,
+	.run = zt_regs_run,
+};
diff --git a/tools/testing/selftests/arm64/tags/Makefile b/tools/testing/selftests/arm64/tags/Makefile
index 41cb75070511..0a77f35295fb 100644
--- a/tools/testing/selftests/arm64/tags/Makefile
+++ b/tools/testing/selftests/arm64/tags/Makefile
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 
-CFLAGS += -I../../../../../usr/include/
+CFLAGS += $(KHDR_INCLUDES)
 TEST_GEN_PROGS := tags_test
-TEST_PROGS := run_tags_test.sh
 
 include ../../lib.mk
diff --git a/tools/testing/selftests/arm64/tags/run_tags_test.sh b/tools/testing/selftests/arm64/tags/run_tags_test.sh
deleted file mode 100755
index 745f11379930..000000000000
--- a/tools/testing/selftests/arm64/tags/run_tags_test.sh
+++ /dev/null
@@ -1,12 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-
-echo "--------------------"
-echo "running tags test"
-echo "--------------------"
-./tags_test
-if [ $? -ne 0 ]; then
-	echo "[FAIL]"
-else
-	echo "[PASS]"
-fi
diff --git a/tools/testing/selftests/arm64/tags/tags_test.c b/tools/testing/selftests/arm64/tags/tags_test.c
index 5701163460ef..375ab47f0edb 100644
--- a/tools/testing/selftests/arm64/tags/tags_test.c
+++ b/tools/testing/selftests/arm64/tags/tags_test.c
@@ -6,6 +6,7 @@
 #include <stdint.h>
 #include <sys/prctl.h>
 #include <sys/utsname.h>
+#include "kselftest.h"
 
 #define SHIFT_TAG(tag)		((uint64_t)(tag) << 56)
 #define SET_TAG(ptr, tag)	(((uint64_t)(ptr) & ~SHIFT_TAG(0xff)) | \
@@ -16,16 +17,21 @@ int main(void)
 	static int tbi_enabled = 0;
 	unsigned long tag = 0;
 	struct utsname *ptr;
-	int err;
+
+	ksft_print_header();
+	ksft_set_plan(1);
 
 	if (prctl(PR_SET_TAGGED_ADDR_CTRL, PR_TAGGED_ADDR_ENABLE, 0, 0, 0) == 0)
 		tbi_enabled = 1;
 	ptr = (struct utsname *)malloc(sizeof(*ptr));
+	if (!ptr)
+		ksft_exit_fail_perror("Failed to allocate utsname buffer");
+
 	if (tbi_enabled)
 		tag = 0x42;
 	ptr = (struct utsname *)SET_TAG(ptr, tag);
-	err = uname(ptr);
+	ksft_test_result(!uname(ptr), "Syscall successful with tagged address\n");
 	free(ptr);
 
-	return err;
+	ksft_finished();
 }
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 07d2d0a8c5cb..19c1638e312a 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -5,44 +5,43 @@ bpf-syscall*
 test_verifier
 test_maps
 test_lru_map
-test_lpm_map
 test_tag
 FEATURE-DUMP.libbpf
+FEATURE-DUMP.selftests
 fixdep
-test_dev_cgroup
 /test_progs
 /test_progs-no_alu32
 /test_progs-bpf_gcc
+/test_progs-cpuv4
 test_verifier_log
 feature
-test_sock
-test_sock_addr
 urandom_read
 test_sockmap
 test_lirc_mode2_user
-get_cgroup_id_user
-test_skb_cgroup_id_user
-test_cgroup_storage
-test_flow_dissector
 flow_dissector_load
 test_tcpnotify_user
 test_libbpf
-test_tcp_check_syncookie_user
-test_sysctl
 xdping
 test_cpp
+test_progs_verification_cert
+*.d
 *.subskel.h
 *.skel.h
 *.lskel.h
 /no_alu32
 /bpf_gcc
+/cpuv4
+/host-tools
 /tools
-/runqslower
 /bench
 /veristat
 /sign-file
+/uprobe_multi
 *.ko
 *.tmp
 xskxceiver
 xdp_redirect_multi
 xdp_synproxy
+xdp_hw_metadata
+xdp_features
+verification_cert.h
diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64
deleted file mode 100644
index 99cc33c51eaa..000000000000
--- a/tools/testing/selftests/bpf/DENYLIST.aarch64
+++ /dev/null
@@ -1,84 +0,0 @@
-bloom_filter_map                                 # libbpf: prog 'check_bloom': failed to attach: ERROR: strerror_r(-524)=22
-bpf_cookie/lsm
-bpf_cookie/multi_kprobe_attach_api
-bpf_cookie/multi_kprobe_link_api
-bpf_cookie/trampoline
-bpf_loop/check_callback_fn_stop                  # link unexpected error: -524
-bpf_loop/check_invalid_flags
-bpf_loop/check_nested_calls
-bpf_loop/check_non_constant_callback
-bpf_loop/check_nr_loops
-bpf_loop/check_null_callback_ctx
-bpf_loop/check_stack
-bpf_mod_race                                     # bpf_mod_kfunc_race__attach unexpected error: -524 (errno 524)
-bpf_tcp_ca/dctcp_fallback
-btf_dump/btf_dump: var_data                      # find type id unexpected find type id: actual -2 < expected 0
-cgroup_hierarchical_stats                        # attach unexpected error: -524 (errno 524)
-d_path/basic                                     # setup attach failed: -524
-deny_namespace                                   # attach unexpected error: -524 (errno 524)
-fentry_fexit                                     # fentry_attach unexpected error: -1 (errno 524)
-fentry_test                                      # fentry_attach unexpected error: -1 (errno 524)
-fexit_sleep                                      # fexit_attach fexit attach failed: -1
-fexit_stress                                     # fexit attach unexpected fexit attach: actual -524 < expected 0
-fexit_test                                       # fexit_attach unexpected error: -1 (errno 524)
-get_func_args_test                               # get_func_args_test__attach unexpected error: -524 (errno 524) (trampoline)
-get_func_ip_test                                 # get_func_ip_test__attach unexpected error: -524 (errno 524) (trampoline)
-htab_update/reenter_update
-kfree_skb                                        # attach fentry unexpected error: -524 (trampoline)
-kfunc_call/subprog                               # extern (var ksym) 'bpf_prog_active': not found in kernel BTF
-kfunc_call/subprog_lskel                         # skel unexpected error: -2
-kfunc_dynptr_param/dynptr_data_null              # libbpf: prog 'dynptr_data_null': failed to attach: ERROR: strerror_r(-524)=22
-kprobe_multi_bench_attach                        # bpf_program__attach_kprobe_multi_opts unexpected error: -95
-kprobe_multi_test/attach_api_addrs               # bpf_program__attach_kprobe_multi_opts unexpected error: -95
-kprobe_multi_test/attach_api_pattern             # bpf_program__attach_kprobe_multi_opts unexpected error: -95
-kprobe_multi_test/attach_api_syms                # bpf_program__attach_kprobe_multi_opts unexpected error: -95
-kprobe_multi_test/bench_attach                   # bpf_program__attach_kprobe_multi_opts unexpected error: -95
-kprobe_multi_test/link_api_addrs                 # link_fd unexpected link_fd: actual -95 < expected 0
-kprobe_multi_test/link_api_syms                  # link_fd unexpected link_fd: actual -95 < expected 0
-kprobe_multi_test/skel_api                       # kprobe_multi__attach unexpected error: -524 (errno 524)
-ksyms_module/libbpf                              # 'bpf_testmod_ksym_percpu': not found in kernel BTF
-ksyms_module/lskel                               # test_ksyms_module_lskel__open_and_load unexpected error: -2
-libbpf_get_fd_by_id_opts                         # test_libbpf_get_fd_by_id_opts__attach unexpected error: -524 (errno 524)
-linked_list
-lookup_key                                       # test_lookup_key__attach unexpected error: -524 (errno 524)
-lru_bug                                          # lru_bug__attach unexpected error: -524 (errno 524)
-modify_return                                    # modify_return__attach failed unexpected error: -524 (errno 524)
-module_attach                                    # skel_attach skeleton attach failed: -524
-mptcp/base                                       # run_test mptcp unexpected error: -524 (errno 524)
-netcnt                                           # packets unexpected packets: actual 10001 != expected 10000
-rcu_read_lock                                    # failed to attach: ERROR: strerror_r(-524)=22
-recursion                                        # skel_attach unexpected error: -524 (errno 524)
-ringbuf                                          # skel_attach skeleton attachment failed: -1
-setget_sockopt                                   # attach_cgroup unexpected error: -524
-sk_storage_tracing                               # test_sk_storage_tracing__attach unexpected error: -524 (errno 524)
-skc_to_unix_sock                                 # could not attach BPF object unexpected error: -524 (errno 524)
-socket_cookie                                    # prog_attach unexpected error: -524
-stacktrace_build_id                              # compare_stack_ips stackmap vs. stack_amap err -1 errno 2
-task_local_storage/exit_creds                    # skel_attach unexpected error: -524 (errno 524)
-task_local_storage/recursion                     # skel_attach unexpected error: -524 (errno 524)
-test_bprm_opts                                   # attach attach failed: -524
-test_ima                                         # attach attach failed: -524
-test_local_storage                               # attach lsm attach failed: -524
-test_lsm                                         # test_lsm_first_attach unexpected error: -524 (errno 524)
-test_overhead                                    # attach_fentry unexpected error: -524
-timer                                            # timer unexpected error: -524 (errno 524)
-timer_crash                                      # timer_crash__attach unexpected error: -524 (errno 524)
-timer_mim                                        # timer_mim unexpected error: -524 (errno 524)
-trace_printk                                     # trace_printk__attach unexpected error: -1 (errno 524)
-trace_vprintk                                    # trace_vprintk__attach unexpected error: -1 (errno 524)
-tracing_struct                                   # tracing_struct__attach unexpected error: -524 (errno 524)
-trampoline_count                                 # attach_prog unexpected error: -524
-unpriv_bpf_disabled                              # skel_attach unexpected error: -524 (errno 524)
-user_ringbuf/test_user_ringbuf_post_misaligned   # misaligned_skel unexpected error: -524 (errno 524)
-user_ringbuf/test_user_ringbuf_post_producer_wrong_offset
-user_ringbuf/test_user_ringbuf_post_larger_than_ringbuf_sz
-user_ringbuf/test_user_ringbuf_basic             # ringbuf_basic_skel unexpected error: -524 (errno 524)
-user_ringbuf/test_user_ringbuf_sample_full_ring_buffer
-user_ringbuf/test_user_ringbuf_post_alignment_autoadjust
-user_ringbuf/test_user_ringbuf_overfill
-user_ringbuf/test_user_ringbuf_discards_properly_ignored
-user_ringbuf/test_user_ringbuf_loop
-user_ringbuf/test_user_ringbuf_msg_protocol
-user_ringbuf/test_user_ringbuf_blocking_reserve
-verify_pkcs7_sig                                 # test_verify_pkcs7_sig__attach unexpected error: -524 (errno 524)
-vmlinux                                          # skel_attach skeleton attach failed: -524
diff --git a/tools/testing/selftests/bpf/DENYLIST.riscv64 b/tools/testing/selftests/bpf/DENYLIST.riscv64
new file mode 100644
index 000000000000..4fc4dfdde293
--- /dev/null
+++ b/tools/testing/selftests/bpf/DENYLIST.riscv64
@@ -0,0 +1,3 @@
+# riscv64 deny list for BPF CI and local vmtest
+exceptions					# JIT does not support exceptions
+tailcalls/tailcall_bpf2bpf*			# JIT does not support mixing bpf2bpf and tailcalls
diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x
index 585fcf73c731..a17baf8c6fd7 100644
--- a/tools/testing/selftests/bpf/DENYLIST.s390x
+++ b/tools/testing/selftests/bpf/DENYLIST.s390x
@@ -1,88 +1,4 @@
 # TEMPORARY
 # Alphabetical order
-atomics                                  # attach(add): actual -524 <= expected 0                                      (trampoline)
-bloom_filter_map                         # failed to find kernel BTF type ID of '__x64_sys_getpgid': -3                (?)
-bpf_cookie                               # failed to open_and_load program: -524 (trampoline)
-bpf_iter_setsockopt                      # JIT does not support calling kernel function                                (kfunc)
-bpf_loop                                 # attaches to __x64_sys_nanosleep
-bpf_mod_race                             # BPF trampoline
-bpf_nf                                   # JIT does not support calling kernel function
-bpf_tcp_ca                               # JIT does not support calling kernel function                                (kfunc)
-cb_refs                                  # expected error message unexpected error: -524                               (trampoline)
-cgroup_hierarchical_stats                # JIT does not support calling kernel function                                (kfunc)
-cgrp_kfunc                               # JIT does not support calling kernel function
-cgrp_local_storage                       # prog_attach unexpected error: -524                                          (trampoline)
-core_read_macros                         # unknown func bpf_probe_read#4                                               (overlapping)
-d_path                                   # failed to auto-attach program 'prog_stat': -524                             (trampoline)
-deny_namespace                           # failed to attach: ERROR: strerror_r(-524)=22                                (trampoline)
-dummy_st_ops                             # test_run unexpected error: -524 (errno 524)                                 (trampoline)
-fentry_fexit                             # fentry attach failed: -524                                                  (trampoline)
-fentry_test                              # fentry_first_attach unexpected error: -524                                  (trampoline)
-fexit_bpf2bpf                            # freplace_attach_trace unexpected error: -524                                (trampoline)
-fexit_sleep                              # fexit_skel_load fexit skeleton failed                                       (trampoline)
-fexit_stress                             # fexit attach failed prog 0 failed: -524                                     (trampoline)
-fexit_test                               # fexit_first_attach unexpected error: -524                                   (trampoline)
-get_func_args_test	                 # trampoline
-get_func_ip_test                         # get_func_ip_test__attach unexpected error: -524                             (trampoline)
 get_stack_raw_tp                         # user_stack corrupted user stack                                             (no backchain userspace)
-htab_update                              # failed to attach: ERROR: strerror_r(-524)=22                                (trampoline)
-kfree_skb                                # attach fentry unexpected error: -524                                        (trampoline)
-kfunc_call                               # 'bpf_prog_active': not found in kernel BTF                                  (?)
-kfunc_dynptr_param                       # JIT does not support calling kernel function                                (kfunc)
-kprobe_multi_bench_attach                # bpf_program__attach_kprobe_multi_opts unexpected error: -95
-kprobe_multi_test                        # relies on fentry
-ksyms_module                             # test_ksyms_module__open_and_load unexpected error: -9                       (?)
-ksyms_module_libbpf                      # JIT does not support calling kernel function                                (kfunc)
-ksyms_module_lskel                       # test_ksyms_module_lskel__open_and_load unexpected error: -9                 (?)
-libbpf_get_fd_by_id_opts                 # failed to attach: ERROR: strerror_r(-524)=22                                (trampoline)
-linked_list				 # JIT does not support calling kernel function                                (kfunc)
-lookup_key                               # JIT does not support calling kernel function                                (kfunc)
-lru_bug                                  # prog 'printk': failed to auto-attach: -524
-map_kptr                                 # failed to open_and_load program: -524 (trampoline)
-modify_return                            # modify_return attach failed: -524                                           (trampoline)
-module_attach                            # skel_attach skeleton attach failed: -524                                    (trampoline)
-mptcp
-netcnt                                   # failed to load BPF skeleton 'netcnt_prog': -7                               (?)
-probe_user                               # check_kprobe_res wrong kprobe res from probe read                           (?)
-rcu_read_lock                            # failed to find kernel BTF type ID of '__x64_sys_getpgid': -3                (?)
-recursion                                # skel_attach unexpected error: -524                                          (trampoline)
-ringbuf                                  # skel_load skeleton load failed                                              (?)
-select_reuseport                         # intermittently fails on new s390x setup
-send_signal                              # intermittently fails to receive signal
-setget_sockopt                           # attach unexpected error: -524                                               (trampoline)
-sk_assign                                # Can't read on server: Invalid argument                                      (?)
-sk_lookup                                # endianness problem
-sk_storage_tracing                       # test_sk_storage_tracing__attach unexpected error: -524                      (trampoline)
-skc_to_unix_sock                         # could not attach BPF object unexpected error: -524                          (trampoline)
-socket_cookie                            # prog_attach unexpected error: -524                                          (trampoline)
 stacktrace_build_id                      # compare_map_keys stackid_hmap vs. stackmap err -2 errno 2                   (?)
-tailcalls                                # tail_calls are not allowed in non-JITed programs with bpf-to-bpf calls      (?)
-task_kfunc                               # JIT does not support calling kernel function
-task_local_storage                       # failed to auto-attach program 'trace_exit_creds': -524                      (trampoline)
-test_bpffs                               # bpffs test  failed 255                                                      (iterator)
-test_bprm_opts                           # failed to auto-attach program 'secure_exec': -524                           (trampoline)
-test_ima                                 # failed to auto-attach program 'ima': -524                                   (trampoline)
-test_local_storage                       # failed to auto-attach program 'unlink_hook': -524                           (trampoline)
-test_lsm                                 # attach unexpected error: -524                                               (trampoline)
-test_overhead                            # attach_fentry unexpected error: -524                                        (trampoline)
-test_profiler                            # unknown func bpf_probe_read_str#45                                          (overlapping)
-timer                                    # failed to auto-attach program 'test1': -524                                 (trampoline)
-timer_crash                              # trampoline
-timer_mim                                # failed to auto-attach program 'test1': -524                                 (trampoline)
-trace_ext                                # failed to auto-attach program 'test_pkt_md_access_new': -524                (trampoline)
-trace_printk                             # trace_printk__load unexpected error: -2 (errno 2)                           (?)
-trace_vprintk                            # trace_vprintk__open_and_load unexpected error: -9                           (?)
-tracing_struct                           # failed to auto-attach: -524                                                 (trampoline)
-trampoline_count                         # prog 'prog1': failed to attach: ERROR: strerror_r(-524)=22                  (trampoline)
-type_cast                                # JIT does not support calling kernel function
-unpriv_bpf_disabled                      # fentry
-user_ringbuf                             # failed to find kernel BTF type ID of '__s390x_sys_prctl': -3                (?)
-verif_stats                              # trace_vprintk__open_and_load unexpected error: -9                           (?)
-verify_pkcs7_sig                         # JIT does not support calling kernel function                                (kfunc)
-vmlinux                                  # failed to auto-attach program 'handle__fentry': -524                        (trampoline)
-xdp_adjust_tail                          # case-128 err 0 errno 28 retval 1 size 128 expect-size 3520                  (?)
-xdp_bonding                              # failed to auto-attach program 'trace_on_entry': -524                        (trampoline)
-xdp_bpf2bpf                              # failed to auto-attach program 'trace_on_entry': -524                        (trampoline)
-xdp_do_redirect                          # prog_run_max_size unexpected error: -22 (errno 22)
-xdp_synproxy                             # JIT does not support calling kernel function                                (kfunc)
-xfrm_info                                # JIT does not support calling kernel function                                (kfunc)
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index c22c43bbee19..b7030a6e2e76 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -10,11 +10,16 @@ TOOLSDIR := $(abspath ../../..)
 LIBDIR := $(TOOLSDIR)/lib
 BPFDIR := $(LIBDIR)/bpf
 TOOLSINCDIR := $(TOOLSDIR)/include
+TOOLSARCHINCDIR := $(TOOLSDIR)/arch/$(SRCARCH)/include
 BPFTOOLDIR := $(TOOLSDIR)/bpf/bpftool
 APIDIR := $(TOOLSINCDIR)/uapi
+ifneq ($(O),)
+GENDIR := $(O)/include/generated
+else
 GENDIR := $(abspath ../../../../include/generated)
+endif
 GENHDR := $(GENDIR)/autoconf.h
-HOSTPKG_CONFIG := pkg-config
+PKG_CONFIG ?= $(CROSS_COMPILE)pkg-config
 
 ifneq ($(wildcard $(GENHDR)),)
   GENFLAGS := -DHAVE_GENHDR
@@ -22,84 +27,116 @@ endif
 
 BPF_GCC		?= $(shell command -v bpf-gcc;)
 SAN_CFLAGS	?=
-CFLAGS += -g -O0 -rdynamic -Wall -Werror $(GENFLAGS) $(SAN_CFLAGS)	\
+SAN_LDFLAGS	?= $(SAN_CFLAGS)
+RELEASE		?=
+OPT_FLAGS	?= $(if $(RELEASE),-O2,-O0)
+
+LIBELF_CFLAGS	:= $(shell $(PKG_CONFIG) libelf --cflags 2>/dev/null)
+LIBELF_LIBS	:= $(shell $(PKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf)
+
+SKIP_DOCS	?=
+SKIP_LLVM	?=
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+endif
+
+CFLAGS += -g $(OPT_FLAGS) -rdynamic -std=gnu11				\
+	  -Wall -Werror -fno-omit-frame-pointer				\
+	  -Wno-unused-but-set-variable					\
+	  $(GENFLAGS) $(SAN_CFLAGS) $(LIBELF_CFLAGS)			\
 	  -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR)		\
-	  -I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT)
-LDFLAGS += $(SAN_CFLAGS)
-LDLIBS += -lelf -lz -lrt -lpthread
+	  -I$(TOOLSINCDIR) -I$(TOOLSARCHINCDIR) -I$(APIDIR) -I$(OUTPUT)
+LDFLAGS += $(SAN_LDFLAGS)
+LDLIBS += $(LIBELF_LIBS) -lz -lrt -lpthread
+
+PCAP_CFLAGS	:= $(shell $(PKG_CONFIG) --cflags libpcap 2>/dev/null && echo "-DTRAFFIC_MONITOR=1")
+PCAP_LIBS	:= $(shell $(PKG_CONFIG) --libs libpcap 2>/dev/null)
+LDLIBS += $(PCAP_LIBS)
+CFLAGS += $(PCAP_CFLAGS)
+
+# Some utility functions use LLVM libraries
+jit_disasm_helpers.c-CFLAGS = $(LLVM_CFLAGS)
 
-# Silence some warnings when compiled with clang
 ifneq ($(LLVM),)
+# Silence some warnings when compiled with clang
 CFLAGS += -Wno-unused-command-line-argument
 endif
 
+# Check whether bpf cpu=v4 is supported or not by clang
+ifneq ($(shell $(CLANG) --target=bpf -mcpu=help 2>&1 | grep 'v4'),)
+CLANG_CPUV4 := 1
+endif
+
 # Order correspond to 'make run_tests' order
-TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
-	test_verifier_log test_dev_cgroup \
-	test_sock test_sockmap get_cgroup_id_user \
-	test_cgroup_storage \
-	test_tcpnotify_user test_sysctl \
+TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_progs \
+	test_sockmap \
+	test_tcpnotify_user \
 	test_progs-no_alu32
+TEST_INST_SUBDIRS := no_alu32
 
 # Also test bpf-gcc, if present
 ifneq ($(BPF_GCC),)
 TEST_GEN_PROGS += test_progs-bpf_gcc
+TEST_INST_SUBDIRS += bpf_gcc
+
+# The following tests contain C code that, although technically legal,
+# triggers GCC warnings that cannot be disabled: declaration of
+# anonymous struct types in function parameter lists.
+progs/btf_dump_test_case_bitfields.c-bpf_gcc-CFLAGS := -Wno-error
+progs/btf_dump_test_case_namespacing.c-bpf_gcc-CFLAGS := -Wno-error
+progs/btf_dump_test_case_packing.c-bpf_gcc-CFLAGS := -Wno-error
+progs/btf_dump_test_case_padding.c-bpf_gcc-CFLAGS := -Wno-error
+progs/btf_dump_test_case_syntax.c-bpf_gcc-CFLAGS := -Wno-error
+
+endif
+
+ifneq ($(CLANG_CPUV4),)
+TEST_GEN_PROGS += test_progs-cpuv4
+TEST_INST_SUBDIRS += cpuv4
 endif
 
-TEST_GEN_FILES = test_lwt_ip_encap.bpf.o test_tc_edt.bpf.o
 TEST_FILES = xsk_prereqs.sh $(wildcard progs/btf_dump_test_case_*.c)
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
-	test_xdp_redirect.sh \
-	test_xdp_redirect_multi.sh \
-	test_xdp_meta.sh \
-	test_xdp_veth.sh \
-	test_offload.py \
-	test_sock_addr.sh \
-	test_tunnel.sh \
-	test_lwt_seg6local.sh \
 	test_lirc_mode2.sh \
-	test_skb_cgroup_id.sh \
-	test_flow_dissector.sh \
-	test_xdp_vlan_mode_generic.sh \
-	test_xdp_vlan_mode_native.sh \
-	test_lwt_ip_encap.sh \
-	test_tcp_check_syncookie.sh \
-	test_tc_tunnel.sh \
-	test_tc_edt.sh \
 	test_xdping.sh \
 	test_bpftool_build.sh \
 	test_bpftool.sh \
+	test_bpftool_map.sh \
 	test_bpftool_metadata.sh \
 	test_doc_build.sh \
-	test_xsk.sh
+	test_xsk.sh \
+	test_xdp_features.sh
 
-TEST_PROGS_EXTENDED := with_addr.sh \
-	with_tunnels.sh ima_setup.sh verify_sig_setup.sh \
-	test_xdp_vlan.sh test_bpftool.py
+TEST_PROGS_EXTENDED := \
+	ima_setup.sh verify_sig_setup.sh \
+	test_bpftool.py
+
+TEST_KMODS := bpf_testmod.ko bpf_test_no_cfi.ko bpf_test_modorder_x.ko \
+	bpf_test_modorder_y.ko bpf_test_rqspinlock.ko
+TEST_KMOD_TARGETS = $(addprefix $(OUTPUT)/,$(TEST_KMODS))
 
 # Compile but not part of 'make run_tests'
-TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
-	flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
-	test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \
-	xskxceiver xdp_redirect_multi xdp_synproxy veristat
-
-TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read $(OUTPUT)/sign-file
-TEST_GEN_FILES += liburandom_read.so
-
-# Emit succinct information message describing current building step
-# $1 - generic step name (e.g., CC, LINK, etc);
-# $2 - optional "flavor" specifier; if provided, will be emitted as [flavor];
-# $3 - target (assumed to be file); only file name will be emitted;
-# $4 - optional extra arg, emitted as-is, if provided.
-ifeq ($(V),1)
-Q =
-msg =
-else
-Q = @
-msg = @printf '  %-8s%s %s%s\n' "$(1)" "$(if $(2), [$(2)])" "$(notdir $(3))" "$(if $(4), $(4))";
-MAKEFLAGS += --no-print-directory
+TEST_GEN_PROGS_EXTENDED = \
+	bench \
+	flow_dissector_load \
+	test_cpp \
+	test_lirc_mode2_user \
+	veristat \
+	xdp_features \
+	xdp_hw_metadata \
+	xdp_synproxy \
+	xdping \
+	xskxceiver
+
+TEST_GEN_FILES += $(TEST_KMODS) liburandom_read.so urandom_read sign-file uprobe_multi
+
+ifneq ($(V),1)
 submake_extras := feature_display=0
 endif
 
@@ -110,13 +147,50 @@ override define CLEAN
 	$(Q)$(RM) -r $(TEST_GEN_PROGS)
 	$(Q)$(RM) -r $(TEST_GEN_PROGS_EXTENDED)
 	$(Q)$(RM) -r $(TEST_GEN_FILES)
+	$(Q)$(RM) -r $(TEST_KMODS)
 	$(Q)$(RM) -r $(EXTRA_CLEAN)
-	$(Q)$(MAKE) -C bpf_testmod clean
+	$(Q)$(MAKE) -C test_kmods clean
 	$(Q)$(MAKE) docs-clean
 endef
 
 include ../lib.mk
 
+NON_CHECK_FEAT_TARGETS := clean docs-clean
+CHECK_FEAT := $(filter-out $(NON_CHECK_FEAT_TARGETS),$(or $(MAKECMDGOALS), "none"))
+ifneq ($(CHECK_FEAT),)
+FEATURE_USER := .selftests
+FEATURE_TESTS := llvm
+FEATURE_DISPLAY := $(FEATURE_TESTS)
+
+# Makefile.feature expects OUTPUT to end with a slash
+ifeq ($(shell expr $(MAKE_VERSION) \>= 4.4), 1)
+$(let OUTPUT,$(OUTPUT)/,\
+	$(eval include ../../../build/Makefile.feature))
+else
+override OUTPUT := $(OUTPUT)/
+$(eval include ../../../build/Makefile.feature)
+override OUTPUT := $(patsubst %/,%,$(OUTPUT))
+endif
+endif
+
+ifneq ($(SKIP_LLVM),1)
+ifeq ($(feature-llvm),1)
+  LLVM_CFLAGS  += -DHAVE_LLVM_SUPPORT
+  LLVM_CONFIG_LIB_COMPONENTS := mcdisassembler all-targets
+  # both llvm-config and lib.mk add -D_GNU_SOURCE, which ends up as conflict
+  LLVM_CFLAGS  += $(filter-out -D_GNU_SOURCE,$(shell $(LLVM_CONFIG) --cflags))
+  # Prefer linking statically if it's available, otherwise fallback to shared
+  ifeq ($(shell $(LLVM_CONFIG) --link-static --libs >/dev/null 2>&1 && echo static),static)
+    LLVM_LDLIBS  += $(shell $(LLVM_CONFIG) --link-static --libs $(LLVM_CONFIG_LIB_COMPONENTS))
+    LLVM_LDLIBS  += $(filter-out -lxml2,$(shell $(LLVM_CONFIG) --link-static --system-libs $(LLVM_CONFIG_LIB_COMPONENTS)))
+    LLVM_LDLIBS  += -lstdc++
+  else
+    LLVM_LDLIBS  += $(shell $(LLVM_CONFIG) --link-shared --libs $(LLVM_CONFIG_LIB_COMPONENTS))
+  endif
+  LLVM_LDFLAGS += $(shell $(LLVM_CONFIG) --ldflags)
+endif
+endif
+
 SCRATCH_DIR := $(OUTPUT)/tools
 BUILD_DIR := $(SCRATCH_DIR)/build
 INCLUDE_DIR := $(SCRATCH_DIR)/include
@@ -132,8 +206,6 @@ HOST_INCLUDE_DIR	:= $(INCLUDE_DIR)
 endif
 HOST_BPFOBJ := $(HOST_BUILD_DIR)/libbpf/libbpf.a
 RESOLVE_BTFIDS := $(HOST_BUILD_DIR)/resolve_btfids/resolve_btfids
-RUNQSLOWER_OUTPUT := $(BUILD_DIR)/runqslower/
-
 VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux)				\
 		     $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux)	\
 		     ../../../../vmlinux				\
@@ -144,20 +216,18 @@ ifeq ($(VMLINUX_BTF),)
 $(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)")
 endif
 
-# Define simple and short `make test_progs`, `make test_sysctl`, etc targets
+# Define simple and short `make test_progs`, `make test_maps`, etc targets
 # to build individual tests.
 # NOTE: Semicolon at the end is critical to override lib.mk's default static
 # rule for binaries.
-$(notdir $(TEST_GEN_PROGS)						\
-	 $(TEST_PROGS)							\
-	 $(TEST_PROGS_EXTENDED)						\
-	 $(TEST_GEN_PROGS_EXTENDED)					\
-	 $(TEST_CUSTOM_PROGS)): %: $(OUTPUT)/% ;
+$(notdir $(TEST_GEN_PROGS) $(TEST_KMODS)				\
+	 $(TEST_GEN_PROGS_EXTENDED)): %: $(OUTPUT)/% ;
 
 # sort removes libbpf duplicates when not cross-building
-MAKE_DIRS := $(sort $(BUILD_DIR)/libbpf $(HOST_BUILD_DIR)/libbpf	       \
-	       $(HOST_BUILD_DIR)/bpftool $(HOST_BUILD_DIR)/resolve_btfids      \
-	       $(RUNQSLOWER_OUTPUT) $(INCLUDE_DIR))
+MAKE_DIRS := $(sort $(BUILD_DIR)/libbpf $(HOST_BUILD_DIR)/libbpf	\
+	       $(BUILD_DIR)/bpftool $(HOST_BUILD_DIR)/bpftool		\
+	       $(HOST_BUILD_DIR)/resolve_btfids				\
+	       $(INCLUDE_DIR))
 $(MAKE_DIRS):
 	$(call msg,MKDIR,,$@)
 	$(Q)mkdir -p $@
@@ -171,89 +241,115 @@ $(OUTPUT)/%:%.c
 	$(Q)$(LINK.c) $^ $(LDLIBS) -o $@
 
 # LLVM's ld.lld doesn't support all the architectures, so use it only on x86
-ifeq ($(SRCARCH),x86)
+ifeq ($(SRCARCH),$(filter $(SRCARCH),x86 riscv))
 LLD := lld
 else
-LLD := ld
+LLD := $(shell command -v $(LD))
 endif
 
 # Filter out -static for liburandom_read.so and its dependent targets so that static builds
 # do not fail. Static builds leave urandom_read relying on system-wide shared libraries.
-$(OUTPUT)/liburandom_read.so: urandom_read_lib1.c urandom_read_lib2.c
+$(OUTPUT)/liburandom_read.so: urandom_read_lib1.c urandom_read_lib2.c liburandom_read.map
 	$(call msg,LIB,,$@)
-	$(Q)$(CLANG) $(filter-out -static,$(CFLAGS) $(LDFLAGS)) $^ $(LDLIBS)   \
+	$(Q)$(CLANG) $(CLANG_TARGET_ARCH) \
+		     $(filter-out -static,$(CFLAGS) $(LDFLAGS)) \
+		     $(filter %.c,$^) $(filter-out -static,$(LDLIBS)) \
+		     -Wno-unused-command-line-argument \
 		     -fuse-ld=$(LLD) -Wl,-znoseparate-code -Wl,--build-id=sha1 \
+		     -Wl,--version-script=liburandom_read.map \
 		     -fPIC -shared -o $@
 
 $(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_read.so
 	$(call msg,BINARY,,$@)
-	$(Q)$(CLANG) $(filter-out -static,$(CFLAGS) $(LDFLAGS)) $(filter %.c,$^) \
-		     liburandom_read.so $(LDLIBS)			       \
+	$(Q)$(CLANG) $(CLANG_TARGET_ARCH) \
+		     $(filter-out -static,$(CFLAGS) $(LDFLAGS)) $(filter %.c,$^) \
+		     -Wno-unused-command-line-argument \
+		     -lurandom_read $(filter-out -static,$(LDLIBS)) -L$(OUTPUT) \
 		     -fuse-ld=$(LLD) -Wl,-znoseparate-code -Wl,--build-id=sha1 \
 		     -Wl,-rpath=. -o $@
 
 $(OUTPUT)/sign-file: ../../../../scripts/sign-file.c
 	$(call msg,SIGN-FILE,,$@)
-	$(Q)$(CC) $(shell $(HOSTPKG_CONFIG)--cflags libcrypto 2> /dev/null) \
+	$(Q)$(CC) $(shell $(PKG_CONFIG) --cflags libcrypto 2> /dev/null) \
 		  $< -o $@ \
-		  $(shell $(HOSTPKG_CONFIG) --libs libcrypto 2> /dev/null || echo -lcrypto)
-
-$(OUTPUT)/bpf_testmod.ko: $(VMLINUX_BTF) $(wildcard bpf_testmod/Makefile bpf_testmod/*.[ch])
+		  $(shell $(PKG_CONFIG) --libs libcrypto 2> /dev/null || echo -lcrypto)
+
+# This should really be a grouped target, but make versions before 4.3 don't
+# support that for regular rules. However, pattern matching rules are implicitly
+# treated as grouped even with older versions of make, so as a workaround, the
+# subst() turns the rule into a pattern matching rule
+$(addprefix test_kmods/,$(subst .ko,%ko,$(TEST_KMODS))): $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard test_kmods/Makefile test_kmods/*.[ch])
+	$(Q)$(RM) test_kmods/*.ko test_kmods/*.mod.o # force re-compilation
+	$(Q)$(MAKE) $(submake_extras) -C test_kmods	\
+		RESOLVE_BTFIDS=$(RESOLVE_BTFIDS)	\
+		EXTRA_CFLAGS='' EXTRA_LDFLAGS=''
+
+$(TEST_KMOD_TARGETS): $(addprefix test_kmods/,$(TEST_KMODS))
 	$(call msg,MOD,,$@)
-	$(Q)$(RM) bpf_testmod/bpf_testmod.ko # force re-compilation
-	$(Q)$(MAKE) $(submake_extras) RESOLVE_BTFIDS=$(RESOLVE_BTFIDS) -C bpf_testmod
-	$(Q)cp bpf_testmod/bpf_testmod.ko $@
+	$(Q)cp test_kmods/$(@F) $@
 
-DEFAULT_BPFTOOL := $(HOST_SCRATCH_DIR)/sbin/bpftool
 
-$(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL) $(RUNQSLOWER_OUTPUT)
-	$(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower	       \
-		    OUTPUT=$(RUNQSLOWER_OUTPUT) VMLINUX_BTF=$(VMLINUX_BTF)     \
-		    BPFTOOL_OUTPUT=$(HOST_BUILD_DIR)/bpftool/		       \
-		    BPFOBJ_OUTPUT=$(BUILD_DIR)/libbpf			       \
-		    BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) &&	       \
-		    cp $(RUNQSLOWER_OUTPUT)runqslower $@
+DEFAULT_BPFTOOL := $(HOST_SCRATCH_DIR)/sbin/bpftool
+ifneq ($(CROSS_COMPILE),)
+CROSS_BPFTOOL := $(SCRATCH_DIR)/sbin/bpftool
+TRUNNER_BPFTOOL := $(CROSS_BPFTOOL)
+USE_BOOTSTRAP := ""
+else
+TRUNNER_BPFTOOL := $(DEFAULT_BPFTOOL)
+USE_BOOTSTRAP := "bootstrap/"
+endif
 
-TEST_GEN_PROGS_EXTENDED += $(DEFAULT_BPFTOOL)
+TEST_GEN_PROGS_EXTENDED += $(TRUNNER_BPFTOOL)
 
 $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(BPFOBJ)
 
-CGROUP_HELPERS	:= $(OUTPUT)/cgroup_helpers.o
 TESTING_HELPERS	:= $(OUTPUT)/testing_helpers.o
+CGROUP_HELPERS	:= $(OUTPUT)/cgroup_helpers.o
+UNPRIV_HELPERS  := $(OUTPUT)/unpriv_helpers.o
 TRACE_HELPERS	:= $(OUTPUT)/trace_helpers.o
+JSON_WRITER		:= $(OUTPUT)/json_writer.o
 CAP_HELPERS	:= $(OUTPUT)/cap_helpers.o
+NETWORK_HELPERS := $(OUTPUT)/network_helpers.o
 
-$(OUTPUT)/test_dev_cgroup: $(CGROUP_HELPERS) $(TESTING_HELPERS)
-$(OUTPUT)/test_skb_cgroup_id_user: $(CGROUP_HELPERS) $(TESTING_HELPERS)
-$(OUTPUT)/test_sock: $(CGROUP_HELPERS) $(TESTING_HELPERS)
-$(OUTPUT)/test_sock_addr: $(CGROUP_HELPERS) $(TESTING_HELPERS)
 $(OUTPUT)/test_sockmap: $(CGROUP_HELPERS) $(TESTING_HELPERS)
 $(OUTPUT)/test_tcpnotify_user: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(TRACE_HELPERS)
-$(OUTPUT)/get_cgroup_id_user: $(CGROUP_HELPERS) $(TESTING_HELPERS)
-$(OUTPUT)/test_cgroup_storage: $(CGROUP_HELPERS) $(TESTING_HELPERS)
 $(OUTPUT)/test_sock_fields: $(CGROUP_HELPERS) $(TESTING_HELPERS)
-$(OUTPUT)/test_sysctl: $(CGROUP_HELPERS) $(TESTING_HELPERS)
 $(OUTPUT)/test_tag: $(TESTING_HELPERS)
 $(OUTPUT)/test_lirc_mode2_user: $(TESTING_HELPERS)
 $(OUTPUT)/xdping: $(TESTING_HELPERS)
 $(OUTPUT)/flow_dissector_load: $(TESTING_HELPERS)
 $(OUTPUT)/test_maps: $(TESTING_HELPERS)
-$(OUTPUT)/test_verifier: $(TESTING_HELPERS) $(CAP_HELPERS)
+$(OUTPUT)/test_verifier: $(TESTING_HELPERS) $(CAP_HELPERS) $(UNPRIV_HELPERS)
 $(OUTPUT)/xsk.o: $(BPFOBJ)
-$(OUTPUT)/xskxceiver: $(OUTPUT)/xsk.o
 
 BPFTOOL ?= $(DEFAULT_BPFTOOL)
 $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)    \
 		    $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool
 	$(Q)$(MAKE) $(submake_extras)  -C $(BPFTOOLDIR)			       \
-		    ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) 	       \
-		    EXTRA_CFLAGS='-g -O0'				       \
+		    ARCH= CROSS_COMPILE= CC="$(HOSTCC)" LD="$(HOSTLD)" 	       \
+		    EXTRA_CFLAGS='-g $(OPT_FLAGS) $(EXTRA_CFLAGS)'	       \
+		    EXTRA_LDFLAGS='$(EXTRA_LDFLAGS)'			       \
 		    OUTPUT=$(HOST_BUILD_DIR)/bpftool/			       \
 		    LIBBPF_OUTPUT=$(HOST_BUILD_DIR)/libbpf/		       \
 		    LIBBPF_DESTDIR=$(HOST_SCRATCH_DIR)/			       \
 		    prefix= DESTDIR=$(HOST_SCRATCH_DIR)/ install-bin
 
+ifneq ($(CROSS_COMPILE),)
+$(CROSS_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)	\
+		    $(BPFOBJ) | $(BUILD_DIR)/bpftool
+	$(Q)$(MAKE) $(submake_extras)  -C $(BPFTOOLDIR)				\
+		    ARCH=$(ARCH) CROSS_COMPILE=$(CROSS_COMPILE)			\
+		    EXTRA_CFLAGS='-g $(OPT_FLAGS) $(EXTRA_CFLAGS)'		\
+		    EXTRA_LDFLAGS='$(EXTRA_LDFLAGS)'				\
+		    OUTPUT=$(BUILD_DIR)/bpftool/				\
+		    LIBBPF_OUTPUT=$(BUILD_DIR)/libbpf/				\
+		    LIBBPF_DESTDIR=$(SCRATCH_DIR)/				\
+		    prefix= DESTDIR=$(SCRATCH_DIR)/ install-bin
+endif
+
+ifneq ($(SKIP_DOCS),1)
 all: docs
+endif
 
 docs:
 	$(Q)RST2MAN_OPTS="--exit-status=1" $(MAKE) $(submake_extras)	\
@@ -269,7 +365,8 @@ $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)		       \
 	   $(APIDIR)/linux/bpf.h					       \
 	   | $(BUILD_DIR)/libbpf
 	$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \
-		    EXTRA_CFLAGS='-g -O0'				       \
+		    EXTRA_CFLAGS='-g $(OPT_FLAGS) $(SAN_CFLAGS) $(EXTRA_CFLAGS)' \
+		    EXTRA_LDFLAGS='$(SAN_LDFLAGS) $(EXTRA_LDFLAGS)'	       \
 		    DESTDIR=$(SCRATCH_DIR) prefix= all install_headers
 
 ifneq ($(BPFOBJ),$(HOST_BPFOBJ))
@@ -277,15 +374,22 @@ $(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)		       \
 		$(APIDIR)/linux/bpf.h					       \
 		| $(HOST_BUILD_DIR)/libbpf
 	$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR)                             \
-		    EXTRA_CFLAGS='-g -O0' ARCH= CROSS_COMPILE=		       \
-		    OUTPUT=$(HOST_BUILD_DIR)/libbpf/ CC=$(HOSTCC) LD=$(HOSTLD) \
+		    ARCH= CROSS_COMPILE=				       \
+		    EXTRA_CFLAGS='-g $(OPT_FLAGS) $(EXTRA_CFLAGS)'	       \
+		    EXTRA_LDFLAGS='$(EXTRA_LDFLAGS)'			       \
+		    OUTPUT=$(HOST_BUILD_DIR)/libbpf/			       \
+		    CC="$(HOSTCC)" LD="$(HOSTLD)"			       \
 		    DESTDIR=$(HOST_SCRATCH_DIR)/ prefix= all install_headers
 endif
 
+# vmlinux.h is first dumped to a temporary file and then compared to
+# the previous version. This helps to avoid unnecessary re-builds of
+# $(TRUNNER_BPF_OBJS)
 $(INCLUDE_DIR)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) | $(INCLUDE_DIR)
 ifeq ($(VMLINUX_H),)
 	$(call msg,GEN,,$@)
-	$(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $@
+	$(Q)$(BPFTOOL) btf dump file $(VMLINUX_BTF) format c > $(INCLUDE_DIR)/.vmlinux.h.tmp
+	$(Q)cmp -s $(INCLUDE_DIR)/.vmlinux.h.tmp $@ || mv $(INCLUDE_DIR)/.vmlinux.h.tmp $@
 else
 	$(call msg,CP,,$@)
 	$(Q)cp "$(VMLINUX_H)" $@
@@ -299,12 +403,12 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids	\
 		       $(TOOLSDIR)/lib/ctype.c			\
 		       $(TOOLSDIR)/lib/str_error_r.c
 	$(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/resolve_btfids	\
-		CC=$(HOSTCC) LD=$(HOSTLD) AR=$(HOSTAR) \
+		CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" \
 		LIBBPF_INCLUDE=$(HOST_INCLUDE_DIR) \
 		OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ)
 
 # Get Clang's default includes on this system, as opposed to those seen by
-# '-target bpf'. This fixes "missing" files on some architectures/distros,
+# '--target=bpf'. This fixes "missing" files on some architectures/distros,
 # such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
 #
 # Use '-idirafter': Don't interfere with include mechanics except where the
@@ -312,25 +416,33 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids	\
 define get_sys_includes
 $(shell $(1) $(2) -v -E - </dev/null 2>&1 \
 	| sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \
-$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}')
+$(shell $(1) $(2) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}') \
+$(shell $(1) $(2) -dM -E - </dev/null | grep '__loongarch_grlen ' | awk '{printf("-D__BITS_PER_LONG=%d", $$3)}') \
+$(shell $(1) $(2) -dM -E - </dev/null | grep -E 'MIPS(EL|EB)|_MIPS_SZ(PTR|LONG) |_MIPS_SIM |_ABI(O32|N32|64) ' | awk '{printf("-D%s=%s ", $$2, $$3)}')
 endef
 
 # Determine target endianness.
-IS_LITTLE_ENDIAN = $(shell $(CC) -dM -E - </dev/null | \
+IS_LITTLE_ENDIAN := $(shell $(CC) -dM -E - </dev/null | \
 			grep 'define __BYTE_ORDER__ __ORDER_LITTLE_ENDIAN__')
-MENDIAN=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian)
+MENDIAN:=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian)
+BPF_TARGET_ENDIAN:=$(if $(IS_LITTLE_ENDIAN),--target=bpfel,--target=bpfeb)
 
 ifneq ($(CROSS_COMPILE),)
 CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%))
 endif
 
 CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH))
-BPF_CFLAGS = -g -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) 		\
+BPF_CFLAGS = -g -Wall -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN)	\
 	     -I$(INCLUDE_DIR) -I$(CURDIR) -I$(APIDIR)			\
-	     -I$(abspath $(OUTPUT)/../usr/include)
+	     -I$(abspath $(OUTPUT)/../usr/include)			\
+	     -std=gnu11		 					\
+	     -fno-strict-aliasing 					\
+	     -Wno-compare-distinct-pointer-types			\
+	     -Wno-initializer-overrides					\
+	     #
+# TODO: enable me -Wsign-compare
 
-CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \
-	       -Wno-compare-distinct-pointer-types
+CLANG_CFLAGS = $(CLANG_SYS_INCLUDES)
 
 $(OUTPUT)/test_l4lb_noinline.o: BPF_CFLAGS += -fno-inline
 $(OUTPUT)/test_xdp_noinline.o: BPF_CFLAGS += -fno-inline
@@ -342,19 +454,25 @@ $(OUTPUT)/cgroup_getset_retval_hooks.o: cgroup_getset_retval_hooks.h
 # $1 - input .c file
 # $2 - output .o file
 # $3 - CFLAGS
+# $4 - binary name
 define CLANG_BPF_BUILD_RULE
-	$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
-	$(Q)$(CLANG) $3 -O2 -target bpf -c $1 -mcpu=v3 -o $2
+	$(call msg,CLNG-BPF,$4,$2)
+	$(Q)$(CLANG) $3 -O2 $(BPF_TARGET_ENDIAN) -c $1 -mcpu=v3 -o $2
 endef
 # Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32
 define CLANG_NOALU32_BPF_BUILD_RULE
-	$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
-	$(Q)$(CLANG) $3 -O2 -target bpf -c $1 -mcpu=v2 -o $2
+	$(call msg,CLNG-BPF,$4,$2)
+	$(Q)$(CLANG) $3 -O2 $(BPF_TARGET_ENDIAN) -c $1 -mcpu=v2 -o $2
+endef
+# Similar to CLANG_BPF_BUILD_RULE, but with cpu-v4
+define CLANG_CPUV4_BPF_BUILD_RULE
+	$(call msg,CLNG-BPF,$4,$2)
+	$(Q)$(CLANG) $3 -O2 $(BPF_TARGET_ENDIAN) -c $1 -mcpu=v4 -o $2
 endef
 # Build BPF object using GCC
 define GCC_BPF_BUILD_RULE
-	$(call msg,GCC-BPF,$(TRUNNER_BINARY),$2)
-	$(Q)$(BPF_GCC) $3 -O2 -c $1 -o $2
+	$(call msg,GCC-BPF,$4,$2)
+	$(Q)$(BPF_GCC) $3 -DBPF_NO_PRESERVE_ACCESS_INDEX -Wno-attributes -O2 -c $1 -o $2
 endef
 
 SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c
@@ -364,15 +482,17 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h		\
 		test_subskeleton.skel.h test_subskeleton_lib.skel.h	\
 		test_usdt.skel.h
 
-LSKELS := fentry_test.c fexit_test.c fexit_sleep.c atomics.c 		\
-	trace_printk.c trace_vprintk.c map_ptr_kern.c 			\
+LSKELS := fexit_sleep.c trace_printk.c trace_vprintk.c map_ptr_kern.c 	\
 	core_kern.c core_kern_overflow.c test_ringbuf.c			\
-	test_ringbuf_map_key.c
+	test_ringbuf_n.c test_ringbuf_map_key.c test_ringbuf_write.c    \
+	test_ringbuf_overwrite.c
+
+LSKELS_SIGNED := fentry_test.c fexit_test.c atomics.c
 
 # Generate both light skeleton and libbpf skeleton for these
 LSKELS_EXTRA := test_ksyms_module.c test_ksyms_weak.c kfunc_call_test.c \
 	kfunc_call_test_subprog.c
-SKEL_BLACKLIST += $$(LSKELS)
+SKEL_BLACKLIST += $$(LSKELS) $$(LSKELS_SIGNED)
 
 test_static_linked.skel.h-deps := test_static_linked1.bpf.o test_static_linked2.bpf.o
 linked_funcs.skel.h-deps := linked_funcs1.bpf.o linked_funcs2.bpf.o
@@ -383,22 +503,35 @@ linked_maps.skel.h-deps := linked_maps1.bpf.o linked_maps2.bpf.o
 test_subskeleton.skel.h-deps := test_subskeleton_lib2.bpf.o test_subskeleton_lib.bpf.o test_subskeleton.bpf.o
 test_subskeleton_lib.skel.h-deps := test_subskeleton_lib2.bpf.o test_subskeleton_lib.bpf.o
 test_usdt.skel.h-deps := test_usdt.bpf.o test_usdt_multispec.bpf.o
+xsk_xdp_progs.skel.h-deps := xsk_xdp_progs.bpf.o
+xdp_hw_metadata.skel.h-deps := xdp_hw_metadata.bpf.o
+xdp_features.skel.h-deps := xdp_features.bpf.o
 
-LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps)))
+LINKED_BPF_OBJS := $(foreach skel,$(LINKED_SKELS),$($(skel)-deps))
+LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.c,$(LINKED_BPF_OBJS))
+
+HEADERS_FOR_BPF_OBJS := $(wildcard $(BPFDIR)/*.bpf.h)		\
+			$(addprefix $(BPFDIR)/,	bpf_core_read.h	\
+			                        bpf_endian.h	\
+						bpf_helpers.h	\
+			                        bpf_tracing.h)
 
 # Set up extra TRUNNER_XXX "temporary" variables in the environment (relies on
 # $eval()) and pass control to DEFINE_TEST_RUNNER_RULES.
 # Parameters:
 # $1 - test runner base binary name (e.g., test_progs)
-# $2 - test runner extra "flavor" (e.g., no_alu32, gcc-bpf, etc)
+# $2 - test runner extra "flavor" (e.g., no_alu32, cpuv4, bpf_gcc, etc)
 define DEFINE_TEST_RUNNER
 
+LSKEL_SIGN := -S -k $(PRIVATE_KEY) -i $(VERIFICATION_CERT)
 TRUNNER_OUTPUT := $(OUTPUT)$(if $2,/)$2
 TRUNNER_BINARY := $1$(if $2,-)$2
 TRUNNER_TEST_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.test.o,	\
 				 $$(notdir $$(wildcard $(TRUNNER_TESTS_DIR)/*.c)))
 TRUNNER_EXTRA_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o,		\
 				 $$(filter %.c,$(TRUNNER_EXTRA_SOURCES)))
+TRUNNER_LIB_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o,		\
+				 $$(filter %.c,$(TRUNNER_LIB_SOURCES)))
 TRUNNER_EXTRA_HDRS := $$(filter %.h,$(TRUNNER_EXTRA_SOURCES))
 TRUNNER_TESTS_HDR := $(TRUNNER_TESTS_DIR)/tests.h
 TRUNNER_BPF_SRCS := $$(notdir $$(wildcard $(TRUNNER_BPF_PROGS_DIR)/*.c))
@@ -408,6 +541,7 @@ TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h,	\
 					       $$(TRUNNER_BPF_SRCS)))
 TRUNNER_BPF_LSKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.lskel.h, $$(LSKELS) $$(LSKELS_EXTRA))
 TRUNNER_BPF_SKELS_LINKED := $$(addprefix $$(TRUNNER_OUTPUT)/,$(LINKED_SKELS))
+TRUNNER_BPF_LSKELS_SIGNED := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.lskel.h, $$(LSKELS_SIGNED))
 TEST_GEN_FILES += $$(TRUNNER_BPF_OBJS)
 
 # Evaluate rules now with extra TRUNNER_XXX variables above already defined
@@ -418,7 +552,7 @@ endef
 # Using TRUNNER_XXX variables, provided by callers of DEFINE_TEST_RUNNER and
 # set up by DEFINE_TEST_RUNNER itself, create test runner build rules with:
 # $1 - test runner base binary name (e.g., test_progs)
-# $2 - test runner extra "flavor" (e.g., no_alu32, gcc-bpf, etc)
+# $2 - test runner extra "flavor" (e.g., no_alu32, cpuv4, bpf_gcc, etc)
 define DEFINE_TEST_RUNNER_RULES
 
 ifeq ($($(TRUNNER_OUTPUT)-dir),)
@@ -436,11 +570,12 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.bpf.o:				\
 		     $(TRUNNER_BPF_PROGS_DIR)/%.c			\
 		     $(TRUNNER_BPF_PROGS_DIR)/*.h			\
 		     $$(INCLUDE_DIR)/vmlinux.h				\
-		     $(wildcard $(BPFDIR)/bpf_*.h)			\
-		     $(wildcard $(BPFDIR)/*.bpf.h)			\
+		     $(HEADERS_FOR_BPF_OBJS)				\
 		     | $(TRUNNER_OUTPUT) $$(BPFOBJ)
 	$$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@,			\
-					  $(TRUNNER_BPF_CFLAGS))
+					  $(TRUNNER_BPF_CFLAGS)         \
+					  $$($$<-CFLAGS)		\
+					  $$($$<-$2-CFLAGS),$(TRUNNER_BINARY))
 
 $(TRUNNER_BPF_SKELS): %.skel.h: %.bpf.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@)
@@ -450,6 +585,7 @@ $(TRUNNER_BPF_SKELS): %.skel.h: %.bpf.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$(Q)diff $$(<:.o=.linked2.o) $$(<:.o=.linked3.o)
 	$(Q)$$(BPFTOOL) gen skeleton $$(<:.o=.linked3.o) name $$(notdir $$(<:.bpf.o=)) > $$@
 	$(Q)$$(BPFTOOL) gen subskeleton $$(<:.o=.linked3.o) name $$(notdir $$(<:.bpf.o=)) > $$(@:.skel.h=.subskel.h)
+	$(Q)rm -f $$(<:.o=.linked1.o) $$(<:.o=.linked2.o) $$(<:.o=.linked3.o)
 
 $(TRUNNER_BPF_LSKELS): %.lskel.h: %.bpf.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@)
@@ -458,8 +594,22 @@ $(TRUNNER_BPF_LSKELS): %.lskel.h: %.bpf.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$(Q)$$(BPFTOOL) gen object $$(<:.o=.llinked3.o) $$(<:.o=.llinked2.o)
 	$(Q)diff $$(<:.o=.llinked2.o) $$(<:.o=.llinked3.o)
 	$(Q)$$(BPFTOOL) gen skeleton -L $$(<:.o=.llinked3.o) name $$(notdir $$(<:.bpf.o=_lskel)) > $$@
+	$(Q)rm -f $$(<:.o=.llinked1.o) $$(<:.o=.llinked2.o) $$(<:.o=.llinked3.o)
+
+$(TRUNNER_BPF_LSKELS_SIGNED): %.lskel.h: %.bpf.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
+	$$(call msg,GEN-SKEL,$(TRUNNER_BINARY) (signed),$$@)
+	$(Q)$$(BPFTOOL) gen object $$(<:.o=.llinked1.o) $$<
+	$(Q)$$(BPFTOOL) gen object $$(<:.o=.llinked2.o) $$(<:.o=.llinked1.o)
+	$(Q)$$(BPFTOOL) gen object $$(<:.o=.llinked3.o) $$(<:.o=.llinked2.o)
+	$(Q)diff $$(<:.o=.llinked2.o) $$(<:.o=.llinked3.o)
+	$(Q)$$(BPFTOOL) gen skeleton $(LSKEL_SIGN) $$(<:.o=.llinked3.o) name $$(notdir $$(<:.bpf.o=_lskel)) > $$@
+	$(Q)rm -f $$(<:.o=.llinked1.o) $$(<:.o=.llinked2.o) $$(<:.o=.llinked3.o)
+
+$(LINKED_BPF_OBJS): %: $(TRUNNER_OUTPUT)/%
 
-$(TRUNNER_BPF_SKELS_LINKED): $(TRUNNER_BPF_OBJS) $(BPFTOOL) | $(TRUNNER_OUTPUT)
+# .SECONDEXPANSION here allows to correctly expand %-deps variables as prerequisites
+.SECONDEXPANSION:
+$(TRUNNER_BPF_SKELS_LINKED): $(TRUNNER_OUTPUT)/%: $$$$(%-deps) $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$$(call msg,LINK-BPF,$(TRUNNER_BINARY),$$(@:.skel.h=.bpf.o))
 	$(Q)$$(BPFTOOL) gen object $$(@:.skel.h=.linked1.o) $$(addprefix $(TRUNNER_OUTPUT)/,$$($$(@F)-deps))
 	$(Q)$$(BPFTOOL) gen object $$(@:.skel.h=.linked2.o) $$(@:.skel.h=.linked1.o)
@@ -468,6 +618,16 @@ $(TRUNNER_BPF_SKELS_LINKED): $(TRUNNER_BPF_OBJS) $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@)
 	$(Q)$$(BPFTOOL) gen skeleton $$(@:.skel.h=.linked3.o) name $$(notdir $$(@:.skel.h=)) > $$@
 	$(Q)$$(BPFTOOL) gen subskeleton $$(@:.skel.h=.linked3.o) name $$(notdir $$(@:.skel.h=)) > $$(@:.skel.h=.subskel.h)
+	$(Q)rm -f $$(@:.skel.h=.linked1.o) $$(@:.skel.h=.linked2.o) $$(@:.skel.h=.linked3.o)
+
+# When the compiler generates a %.d file, only skel basenames (not
+# full paths) are specified as prerequisites for corresponding %.o
+# file. vpath directives below instruct make to search for skel files
+# in TRUNNER_OUTPUT, if they are not present in the working directory.
+vpath %.skel.h $(TRUNNER_OUTPUT)
+vpath %.lskel.h $(TRUNNER_OUTPUT)
+vpath %.subskel.h $(TRUNNER_OUTPUT)
+
 endif
 
 # ensure we set up tests.h header generation rule just once
@@ -485,23 +645,40 @@ endif
 # Note: we cd into output directory to ensure embedded BPF object is found
 $(TRUNNER_TEST_OBJS): $(TRUNNER_OUTPUT)/%.test.o:			\
 		      $(TRUNNER_TESTS_DIR)/%.c				\
-		      $(TRUNNER_EXTRA_HDRS)				\
-		      $(TRUNNER_BPF_OBJS)				\
-		      $(TRUNNER_BPF_SKELS)				\
-		      $(TRUNNER_BPF_LSKELS)				\
-		      $(TRUNNER_BPF_SKELS_LINKED)			\
-		      $$(BPFOBJ) | $(TRUNNER_OUTPUT)
+		      | $(TRUNNER_OUTPUT)/%.test.d
 	$$(call msg,TEST-OBJ,$(TRUNNER_BINARY),$$@)
-	$(Q)cd $$(@D) && $$(CC) -I. $$(CFLAGS) -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F)
+	$(Q)cd $$(@D) && $$(CC) -I. $$(CFLAGS) -MMD -MT $$@ -c $(CURDIR)/$$< $$(LDLIBS) -o $$(@F)
+
+$(TRUNNER_TEST_OBJS:.o=.d): $(TRUNNER_OUTPUT)/%.test.d:			\
+			    $(TRUNNER_TESTS_DIR)/%.c			\
+			    $(TRUNNER_EXTRA_HDRS)			\
+			    $(TRUNNER_BPF_SKELS)			\
+			    $(TRUNNER_BPF_LSKELS)			\
+			    $(TRUNNER_BPF_LSKELS_SIGNED)		\
+			    $(TRUNNER_BPF_SKELS_LINKED)			\
+			    $$(BPFOBJ) | $(TRUNNER_OUTPUT)
+
+ifeq ($(filter clean docs-clean,$(MAKECMDGOALS)),)
+include $(wildcard $(TRUNNER_TEST_OBJS:.o=.d))
+endif
+
+# add per extra obj CFGLAGS definitions
+$(foreach N,$(patsubst $(TRUNNER_OUTPUT)/%.o,%,$(TRUNNER_EXTRA_OBJS)),	\
+	$(eval $(TRUNNER_OUTPUT)/$(N).o: CFLAGS += $($(N).c-CFLAGS)))
 
 $(TRUNNER_EXTRA_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
 		       %.c						\
 		       $(TRUNNER_EXTRA_HDRS)				\
+		       $(VERIFY_SIG_HDR)				\
 		       $(TRUNNER_TESTS_HDR)				\
 		       $$(BPFOBJ) | $(TRUNNER_OUTPUT)
 	$$(call msg,EXT-OBJ,$(TRUNNER_BINARY),$$@)
 	$(Q)$$(CC) $$(CFLAGS) -c $$< $$(LDLIBS) -o $$@
 
+$(TRUNNER_LIB_OBJS): $(TRUNNER_OUTPUT)/%.o:$(TOOLSDIR)/lib/%.c
+	$$(call msg,LIB-OBJ,$(TRUNNER_BINARY),$$@)
+	$(Q)$$(CC) $$(CFLAGS) -c $$< $$(LDLIBS) -o $$@
+
 # non-flavored in-srctree builds receive special treatment, in particular, we
 # do not need to copy extra resources (see e.g. test_btf_dump_case())
 $(TRUNNER_BINARY)-extras: $(TRUNNER_EXTRA_FILES) | $(TRUNNER_OUTPUT)
@@ -510,30 +687,68 @@ ifneq ($2:$(OUTPUT),:$(shell pwd))
 	$(Q)rsync -aq $$^ $(TRUNNER_OUTPUT)/
 endif
 
+# some X.test.o files have runtime dependencies on Y.bpf.o files
+$(OUTPUT)/$(TRUNNER_BINARY): | $(TRUNNER_BPF_OBJS)
+
 $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS)			\
 			     $(TRUNNER_EXTRA_OBJS) $$(BPFOBJ)		\
+			     $(TRUNNER_LIB_OBJS)			\
 			     $(RESOLVE_BTFIDS)				\
+			     $(TRUNNER_BPFTOOL)				\
+			     $(OUTPUT)/veristat				\
 			     | $(TRUNNER_BINARY)-extras
 	$$(call msg,BINARY,,$$@)
-	$(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@
+	$(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) $$(LLVM_LDLIBS) $$(LDFLAGS) $$(LLVM_LDFLAGS) -o $$@
 	$(Q)$(RESOLVE_BTFIDS) --btf $(TRUNNER_OUTPUT)/btf_data.bpf.o $$@
-	$(Q)ln -sf $(if $2,..,.)/tools/build/bpftool/bootstrap/bpftool $(if $2,$2/)bpftool
+	$(Q)ln -sf $(if $2,..,.)/tools/build/bpftool/$(USE_BOOTSTRAP)bpftool \
+		   $(OUTPUT)/$(if $2,$2/)bpftool
 
 endef
 
+VERIFY_SIG_SETUP := $(CURDIR)/verify_sig_setup.sh
+VERIFY_SIG_HDR := verification_cert.h
+VERIFICATION_CERT   := $(BUILD_DIR)/signing_key.der
+PRIVATE_KEY := $(BUILD_DIR)/signing_key.pem
+
+$(VERIFICATION_CERT) $(PRIVATE_KEY): $(VERIFY_SIG_SETUP)
+	$(Q)mkdir -p $(BUILD_DIR)
+	$(Q)$(VERIFY_SIG_SETUP) genkey $(BUILD_DIR)
+
+$(VERIFY_SIG_HDR): $(VERIFICATION_CERT)
+	$(Q)ln -fs $< test_progs_verification_cert && \
+	xxd -i test_progs_verification_cert > $@
+
 # Define test_progs test runner.
 TRUNNER_TESTS_DIR := prog_tests
 TRUNNER_BPF_PROGS_DIR := progs
-TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c	\
-			 network_helpers.c testing_helpers.c		\
-			 btf_helpers.c flow_dissector_load.h		\
-			 cap_helpers.c test_loader.c
-TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko	\
+TRUNNER_EXTRA_SOURCES := test_progs.c		\
+			 cgroup_helpers.c	\
+			 trace_helpers.c	\
+			 network_helpers.c	\
+			 testing_helpers.c	\
+			 btf_helpers.c		\
+			 cap_helpers.c		\
+			 unpriv_helpers.c 	\
+			 netlink_helpers.c	\
+			 jit_disasm_helpers.c	\
+			 io_helpers.c		\
+			 test_loader.c		\
+			 xsk.c			\
+			 disasm.c		\
+			 disasm_helpers.c	\
+			 json_writer.c 		\
+			 $(VERIFY_SIG_HDR)		\
+			 flow_dissector_load.h	\
+			 ip_check_defrag_frags.h
+TRUNNER_LIB_SOURCES := find_bit.c
+TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read				\
 		       $(OUTPUT)/liburandom_read.so			\
 		       $(OUTPUT)/xdp_synproxy				\
 		       $(OUTPUT)/sign-file				\
+		       $(OUTPUT)/uprobe_multi				\
+		       $(TEST_KMOD_TARGETS)				\
 		       ima_setup.sh 					\
-		       verify_sig_setup.sh				\
+		       $(VERIFY_SIG_SETUP)				\
 		       $(wildcard progs/btf_dump_test_case_*.c)		\
 		       $(wildcard progs/*.bpf.o)
 TRUNNER_BPF_BUILD_RULE := CLANG_BPF_BUILD_RULE
@@ -545,6 +760,13 @@ TRUNNER_BPF_BUILD_RULE := CLANG_NOALU32_BPF_BUILD_RULE
 TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS)
 $(eval $(call DEFINE_TEST_RUNNER,test_progs,no_alu32))
 
+# Define test_progs-cpuv4 test runner.
+ifneq ($(CLANG_CPUV4),)
+TRUNNER_BPF_BUILD_RULE := CLANG_CPUV4_BPF_BUILD_RULE
+TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS) -DENABLE_ATOMICS_TESTS
+$(eval $(call DEFINE_TEST_RUNNER,test_progs,cpuv4))
+endif
+
 # Define test_progs BPF-GCC-flavored test runner.
 ifneq ($(BPF_GCC),)
 TRUNNER_BPF_BUILD_RULE := GCC_BPF_BUILD_RULE
@@ -556,6 +778,7 @@ endif
 TRUNNER_TESTS_DIR := map_tests
 TRUNNER_BPF_PROGS_DIR := progs
 TRUNNER_EXTRA_SOURCES := test_maps.c
+TRUNNER_LIB_SOURCES :=
 TRUNNER_EXTRA_FILES :=
 TRUNNER_BPF_BUILD_RULE := $$(error no BPF objects should be built)
 TRUNNER_BPF_CFLAGS :=
@@ -576,10 +799,27 @@ $(OUTPUT)/test_verifier: test_verifier.c verifier/tests.h $(BPFOBJ) | $(OUTPUT)
 	$(call msg,BINARY,,$@)
 	$(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
 
+# Include find_bit.c to compile xskxceiver.
+EXTRA_SRC := $(TOOLSDIR)/lib/find_bit.c prog_tests/test_xsk.c prog_tests/test_xsk.h
+$(OUTPUT)/xskxceiver: $(EXTRA_SRC) xskxceiver.c xskxceiver.h $(OUTPUT)/network_helpers.o $(OUTPUT)/xsk.o $(OUTPUT)/xsk_xdp_progs.skel.h $(BPFOBJ) | $(OUTPUT)
+	$(call msg,BINARY,,$@)
+	$(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
+
+$(OUTPUT)/xdp_hw_metadata: xdp_hw_metadata.c $(OUTPUT)/network_helpers.o $(OUTPUT)/xsk.o $(OUTPUT)/xdp_hw_metadata.skel.h | $(OUTPUT)
+	$(call msg,BINARY,,$@)
+	$(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
+
+$(OUTPUT)/xdp_features: xdp_features.c $(OUTPUT)/network_helpers.o $(OUTPUT)/xdp_features.skel.h | $(OUTPUT)
+	$(call msg,BINARY,,$@)
+	$(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
+
 # Make sure we are able to include and link libbpf against c++.
+CXXFLAGS += $(CFLAGS)
+CXXFLAGS := $(subst -D_GNU_SOURCE=,,$(CXXFLAGS))
+CXXFLAGS := $(subst -std=gnu11,-std=gnu++11,$(CXXFLAGS))
 $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ)
 	$(call msg,CXX,,$@)
-	$(Q)$(CXX) $(CFLAGS) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@
+	$(Q)$(CXX) $(CXXFLAGS) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@
 
 # Benchmark runner
 $(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h $(BPFOBJ)
@@ -595,11 +835,18 @@ $(OUTPUT)/bench_strncmp.o: $(OUTPUT)/strncmp_bench.skel.h
 $(OUTPUT)/bench_bpf_hashmap_full_update.o: $(OUTPUT)/bpf_hashmap_full_update_bench.skel.h
 $(OUTPUT)/bench_local_storage.o: $(OUTPUT)/local_storage_bench.skel.h
 $(OUTPUT)/bench_local_storage_rcu_tasks_trace.o: $(OUTPUT)/local_storage_rcu_tasks_trace_bench.skel.h
+$(OUTPUT)/bench_local_storage_create.o: $(OUTPUT)/bench_local_storage_create.skel.h
+$(OUTPUT)/bench_bpf_hashmap_lookup.o: $(OUTPUT)/bpf_hashmap_lookup.skel.h
+$(OUTPUT)/bench_htab_mem.o: $(OUTPUT)/htab_mem_bench.skel.h
+$(OUTPUT)/bench_bpf_crypto.o: $(OUTPUT)/crypto_bench.skel.h
+$(OUTPUT)/bench_sockmap.o: $(OUTPUT)/bench_sockmap_prog.skel.h
+$(OUTPUT)/bench_lpm_trie_map.o: $(OUTPUT)/lpm_trie_bench.skel.h $(OUTPUT)/lpm_trie_map.skel.h
 $(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ)
 $(OUTPUT)/bench: LDLIBS += -lm
 $(OUTPUT)/bench: $(OUTPUT)/bench.o \
 		 $(TESTING_HELPERS) \
 		 $(TRACE_HELPERS) \
+		 $(CGROUP_HELPERS) \
 		 $(OUTPUT)/bench_count.o \
 		 $(OUTPUT)/bench_rename.o \
 		 $(OUTPUT)/bench_trigger.o \
@@ -609,20 +856,53 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \
 		 $(OUTPUT)/bench_strncmp.o \
 		 $(OUTPUT)/bench_bpf_hashmap_full_update.o \
 		 $(OUTPUT)/bench_local_storage.o \
-		 $(OUTPUT)/bench_local_storage_rcu_tasks_trace.o
+		 $(OUTPUT)/bench_local_storage_rcu_tasks_trace.o \
+		 $(OUTPUT)/bench_bpf_hashmap_lookup.o \
+		 $(OUTPUT)/bench_local_storage_create.o \
+		 $(OUTPUT)/bench_htab_mem.o \
+		 $(OUTPUT)/bench_bpf_crypto.o \
+		 $(OUTPUT)/bench_sockmap.o \
+		 $(OUTPUT)/bench_lpm_trie_map.o \
+		 #
 	$(call msg,BINARY,,$@)
 	$(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@
 
+# This works around GCC warning about snprintf truncating strings like:
+#
+#   char a[PATH_MAX], b[PATH_MAX];
+#   snprintf(a, "%s/foo", b);      // triggers -Wformat-truncation
+$(OUTPUT)/veristat.o: CFLAGS += -Wno-format-truncation
 $(OUTPUT)/veristat.o: $(BPFOBJ)
 $(OUTPUT)/veristat: $(OUTPUT)/veristat.o
 	$(call msg,BINARY,,$@)
 	$(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@
 
-EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) $(HOST_SCRATCH_DIR)	\
+# Linking uprobe_multi can fail due to relocation overflows on mips.
+$(OUTPUT)/uprobe_multi: CFLAGS += $(if $(filter mips, $(ARCH)),-mxgot)
+$(OUTPUT)/uprobe_multi: uprobe_multi.c uprobe_multi.ld
+	$(call msg,BINARY,,$@)
+	$(Q)$(CC) $(CFLAGS) -Wl,-T,uprobe_multi.ld -O0 $(LDFLAGS) 	\
+		$(filter-out %.ld,$^) $(LDLIBS) -o $@
+
+EXTRA_CLEAN := $(SCRATCH_DIR) $(HOST_SCRATCH_DIR)			\
 	prog_tests/tests.h map_tests/tests.h verifier/tests.h		\
-	feature bpftool							\
-	$(addprefix $(OUTPUT)/,*.o *.skel.h *.lskel.h *.subskel.h	\
-			       no_alu32 bpf_gcc bpf_testmod.ko		\
-			       liburandom_read.so)
+	feature bpftool $(TEST_KMOD_TARGETS)				\
+	$(addprefix $(OUTPUT)/,*.o *.d *.skel.h *.lskel.h *.subskel.h	\
+			       no_alu32 cpuv4 bpf_gcc			\
+			       liburandom_read.so)			\
+	$(OUTPUT)/FEATURE-DUMP.selftests				\
+	test_progs_verification_cert
 
 .PHONY: docs docs-clean
+
+# Delete partially updated (corrupted) files on error
+.DELETE_ON_ERROR:
+
+DEFAULT_INSTALL_RULE := $(INSTALL_RULE)
+override define INSTALL_RULE
+	$(DEFAULT_INSTALL_RULE)
+	@for DIR in $(TEST_INST_SUBDIRS); do		  \
+		mkdir -p $(INSTALL_PATH)/$$DIR;   \
+		rsync -a $(OUTPUT)/$$DIR/*.bpf.o $(INSTALL_PATH)/$$DIR;\
+	done
+endef
diff --git a/tools/testing/selftests/bpf/Makefile.docs b/tools/testing/selftests/bpf/Makefile.docs
index eb6a4fea8c79..f7f9e7088bb3 100644
--- a/tools/testing/selftests/bpf/Makefile.docs
+++ b/tools/testing/selftests/bpf/Makefile.docs
@@ -7,12 +7,6 @@ INSTALL ?= install
 RM ?= rm -f
 RMDIR ?= rmdir --ignore-fail-on-non-empty
 
-ifeq ($(V),1)
-  Q =
-else
-  Q = @
-endif
-
 prefix ?= /usr/local
 mandir ?= $(prefix)/man
 man2dir = $(mandir)/man2
diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst
index cb9b95702ac6..776fbe3cb8f9 100644
--- a/tools/testing/selftests/bpf/README.rst
+++ b/tools/testing/selftests/bpf/README.rst
@@ -77,7 +77,7 @@ In case of linker errors when running selftests, try using static linking:
 
 .. code-block:: console
 
-  $ LDLIBS=-static vmtest.sh
+  $ LDLIBS=-static PKG_CONFIG='pkg-config --static' vmtest.sh
 
 .. note:: Some distros may not support static linking.
 
@@ -85,7 +85,37 @@ In case of linker errors when running selftests, try using static linking:
           If you want to change pahole and llvm, you can change `PATH` environment
           variable in the beginning of script.
 
-.. note:: The script currently only supports x86_64 and s390x architectures.
+Running vmtest on RV64
+======================
+To speed up testing and avoid various dependency issues, it is recommended to
+run vmtest in a Docker container. Before running vmtest, we need to prepare
+Docker container and local rootfs image. The overall steps are as follows:
+
+1. Create Docker container as shown in link [0].
+
+2. Use mkrootfs_debian.sh script [1] to build local rootfs image:
+
+.. code-block:: console
+
+  $ sudo ./mkrootfs_debian.sh --arch riscv64 --distro noble
+
+3. Start Docker container [0] and run vmtest in the container:
+
+.. code-block:: console
+
+  $ PLATFORM=riscv64 CROSS_COMPILE=riscv64-linux-gnu- \
+    tools/testing/selftests/bpf/vmtest.sh \
+    -l <path of local rootfs image> -- \
+    ./test_progs -d \
+        \"$(cat tools/testing/selftests/bpf/DENYLIST.riscv64 \
+            | cut -d'#' -f1 \
+            | sed -e 's/^[[:space:]]*//' \
+                  -e 's/[[:space:]]*$//' \
+            | tr -s '\n' ',' \
+        )\"
+
+Link: https://github.com/pulehui/riscv-bpf-vmtest.git [0]
+Link: https://github.com/libbpf/ci/blob/main/rootfs/mkrootfs_debian.sh [1]
 
 Additional information about selftest failures are
 documented here.
@@ -115,7 +145,7 @@ the insn 20 undoes map_value addition. It is currently impossible for the
 verifier to understand such speculative pointer arithmetic.
 Hence `this patch`__ addresses it on the compiler side. It was committed on llvm 12.
 
-__ https://reviews.llvm.org/D85570
+__ https://github.com/llvm/llvm-project/commit/ddf1864ace484035e3cde5e83b3a31ac81e059c6
 
 The corresponding C code
 
@@ -165,7 +195,7 @@ This is due to a llvm BPF backend bug. `The fix`__
 has been pushed to llvm 10.x release branch and will be
 available in 10.0.1. The patch is available in llvm 11.0.0 trunk.
 
-__  https://reviews.llvm.org/D78466
+__  https://github.com/llvm/llvm-project/commit/3cb7e7bf959dcd3b8080986c62e10a75c7af43f0
 
 bpf_verif_scale/loop6.bpf.o test failure with Clang 12
 ======================================================
@@ -204,7 +234,7 @@ r5(w5) is eventually saved on stack at insn #24 for later use.
 This cause later verifier failure. The bug has been `fixed`__ in
 Clang 13.
 
-__  https://reviews.llvm.org/D97479
+__  https://github.com/llvm/llvm-project/commit/1959ead525b8830cc8a345f45e1c3ef9902d3229
 
 BPF CO-RE-based tests and Clang version
 =======================================
@@ -221,11 +251,11 @@ failures:
 - __builtin_btf_type_id() [0_, 1_, 2_];
 - __builtin_preserve_type_info(), __builtin_preserve_enum_value() [3_, 4_].
 
-.. _0: https://reviews.llvm.org/D74572
-.. _1: https://reviews.llvm.org/D74668
-.. _2: https://reviews.llvm.org/D85174
-.. _3: https://reviews.llvm.org/D83878
-.. _4: https://reviews.llvm.org/D83242
+.. _0: https://github.com/llvm/llvm-project/commit/6b01b465388b204d543da3cf49efd6080db094a9
+.. _1: https://github.com/llvm/llvm-project/commit/072cde03aaa13a2c57acf62d79876bf79aa1919f
+.. _2: https://github.com/llvm/llvm-project/commit/00602ee7ef0bf6c68d690a2bd729c12b95c95c99
+.. _3: https://github.com/llvm/llvm-project/commit/6d218b4adb093ff2e9764febbbc89f429412006c
+.. _4: https://github.com/llvm/llvm-project/commit/6d6750696400e7ce988d66a1a00e1d0cb32815f8
 
 Floating-point tests and Clang version
 ======================================
@@ -234,7 +264,7 @@ Certain selftests, e.g. core_reloc, require support for the floating-point
 types, which was introduced in `Clang 13`__. The older Clang versions will
 either crash when compiling these tests, or generate an incorrect BTF.
 
-__  https://reviews.llvm.org/D83289
+__  https://github.com/llvm/llvm-project/commit/a7137b238a07d9399d3ae96c0b461571bd5aa8b2
 
 Kernel function call test and Clang version
 ===========================================
@@ -248,7 +278,7 @@ Without it, the error from compiling bpf selftests looks like:
 
   libbpf: failed to find BTF for extern 'tcp_slow_start' [25] section: -2
 
-__ https://reviews.llvm.org/D93563
+__ https://github.com/llvm/llvm-project/commit/886f9ff53155075bd5f1e994f17b85d1e1b7470c
 
 btf_tag test and Clang version
 ==============================
@@ -264,8 +294,8 @@ Without them, the btf_tag selftest will be skipped and you will observe:
 
   #<test_num> btf_tag:SKIP
 
-.. _0: https://reviews.llvm.org/D111588
-.. _1: https://reviews.llvm.org/D111199
+.. _0: https://github.com/llvm/llvm-project/commit/a162b67c98066218d0d00aa13b99afb95d9bb5e6
+.. _1: https://github.com/llvm/llvm-project/commit/3466e00716e12e32fdb100e3fcfca5c2b3e8d784
 
 Clang dependencies for static linking tests
 ===========================================
@@ -274,7 +304,7 @@ linked_vars, linked_maps, and linked_funcs tests depend on `Clang fix`__ to
 generate valid BTF information for weak variables. Please make sure you use
 Clang that contains the fix.
 
-__ https://reviews.llvm.org/D100362
+__ https://github.com/llvm/llvm-project/commit/968292cb93198442138128d850fd54dc7edc0035
 
 Clang relocation changes
 ========================
@@ -292,7 +322,7 @@ Here, ``type 2`` refers to new relocation type ``R_BPF_64_ABS64``.
 To fix this issue, user newer libbpf.
 
 .. Links
-.. _clang reloc patch: https://reviews.llvm.org/D102712
+.. _clang reloc patch: https://github.com/llvm/llvm-project/commit/6a2ea84600ba4bd3b2733bd8f08f5115eb32164b
 .. _kernel llvm reloc: /Documentation/bpf/llvm_reloc.rst
 
 Clang dependencies for the u32 spill test (xdpwall)
@@ -304,6 +334,6 @@ from running test_progs will look like:
 
 .. code-block:: console
 
-  test_xdpwall:FAIL:Does LLVM have https://reviews.llvm.org/D109073? unexpected error: -4007
+  test_xdpwall:FAIL:Does LLVM have https://github.com/llvm/llvm-project/commit/ea72b0319d7b0f0c2fcf41d121afa5d031b319d5? unexpected error: -4007
 
-__ https://reviews.llvm.org/D109073
+__ https://github.com/llvm/llvm-project/commit/ea72b0319d7b0f0c2fcf41d121afa5d031b319d5
diff --git a/tools/testing/selftests/bpf/autoconf_helper.h b/tools/testing/selftests/bpf/autoconf_helper.h
new file mode 100644
index 000000000000..5b243b9cdf8c
--- /dev/null
+++ b/tools/testing/selftests/bpf/autoconf_helper.h
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#ifdef HAVE_GENHDR
+# include "autoconf.h"
+#else
+# if defined(__i386) || defined(__x86_64) || defined(__s390x__) || defined(__aarch64__)
+#  define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS 1
+# endif
+#endif
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index c1f20a147462..bd29bb2e6cb5 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -10,13 +10,15 @@
 #include <sys/sysinfo.h>
 #include <signal.h>
 #include "bench.h"
+#include "bpf_util.h"
 #include "testing_helpers.h"
 
 struct env env = {
 	.warmup_sec = 1,
 	.duration_sec = 5,
 	.affinity = false,
-	.consumer_cnt = 1,
+	.quiet = false,
+	.consumer_cnt = 0,
 	.producer_cnt = 1,
 };
 
@@ -262,6 +264,7 @@ static const struct argp_option opts[] = {
 	{ "consumers", 'c', "NUM", 0, "Number of consumer threads"},
 	{ "verbose", 'v', NULL, 0, "Verbose debug output"},
 	{ "affinity", 'a', NULL, 0, "Set consumer/producer thread affinity"},
+	{ "quiet", 'q', NULL, 0, "Be more quiet"},
 	{ "prod-affinity", ARG_PROD_AFFINITY_SET, "CPUSET", 0,
 	  "Set of CPUs for producer threads; implies --affinity"},
 	{ "cons-affinity", ARG_CONS_AFFINITY_SET, "CPUSET", 0,
@@ -275,6 +278,13 @@ extern struct argp bench_bpf_loop_argp;
 extern struct argp bench_local_storage_argp;
 extern struct argp bench_local_storage_rcu_tasks_trace_argp;
 extern struct argp bench_strncmp_argp;
+extern struct argp bench_hashmap_lookup_argp;
+extern struct argp bench_local_storage_create_argp;
+extern struct argp bench_htab_mem_argp;
+extern struct argp bench_trigger_batch_argp;
+extern struct argp bench_crypto_argp;
+extern struct argp bench_sockmap_argp;
+extern struct argp bench_lpm_trie_map_argp;
 
 static const struct argp_child bench_parsers[] = {
 	{ &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 },
@@ -284,13 +294,21 @@ static const struct argp_child bench_parsers[] = {
 	{ &bench_strncmp_argp, 0, "bpf_strncmp helper benchmark", 0 },
 	{ &bench_local_storage_rcu_tasks_trace_argp, 0,
 		"local_storage RCU Tasks Trace slowdown benchmark", 0 },
+	{ &bench_hashmap_lookup_argp, 0, "Hashmap lookup benchmark", 0 },
+	{ &bench_local_storage_create_argp, 0, "local-storage-create benchmark", 0 },
+	{ &bench_htab_mem_argp, 0, "hash map memory benchmark", 0 },
+	{ &bench_trigger_batch_argp, 0, "BPF triggering benchmark", 0 },
+	{ &bench_crypto_argp, 0, "bpf crypto benchmark", 0 },
+	{ &bench_sockmap_argp, 0, "bpf sockmap benchmark", 0 },
+	{ &bench_lpm_trie_map_argp, 0, "LPM trie map benchmark", 0 },
 	{},
 };
 
+/* Make pos_args global, so that we can run argp_parse twice, if necessary */
+static int pos_args;
+
 static error_t parse_arg(int key, char *arg, struct argp_state *state)
 {
-	static int pos_args;
-
 	switch (key) {
 	case 'v':
 		env.verbose = true;
@@ -314,14 +332,14 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 		break;
 	case 'p':
 		env.producer_cnt = strtol(arg, NULL, 10);
-		if (env.producer_cnt <= 0) {
+		if (env.producer_cnt < 0) {
 			fprintf(stderr, "Invalid producer count: %s\n", arg);
 			argp_usage(state);
 		}
 		break;
 	case 'c':
 		env.consumer_cnt = strtol(arg, NULL, 10);
-		if (env.consumer_cnt <= 0) {
+		if (env.consumer_cnt < 0) {
 			fprintf(stderr, "Invalid consumer count: %s\n", arg);
 			argp_usage(state);
 		}
@@ -329,6 +347,9 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 	case 'a':
 		env.affinity = true;
 		break;
+	case 'q':
+		env.quiet = true;
+		break;
 	case ARG_PROD_AFFINITY_SET:
 		env.affinity = true;
 		if (parse_num_list(arg, &env.prod_cpus.cpus,
@@ -359,7 +380,7 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 	return 0;
 }
 
-static void parse_cmdline_args(int argc, char **argv)
+static void parse_cmdline_args_init(int argc, char **argv)
 {
 	static const struct argp argp = {
 		.options = opts,
@@ -369,9 +390,25 @@ static void parse_cmdline_args(int argc, char **argv)
 	};
 	if (argp_parse(&argp, argc, argv, 0, NULL, NULL))
 		exit(1);
-	if (!env.list && !env.bench_name) {
-		argp_help(&argp, stderr, ARGP_HELP_DOC, "bench");
-		exit(1);
+}
+
+static void parse_cmdline_args_final(int argc, char **argv)
+{
+	struct argp_child bench_parsers[2] = {};
+	const struct argp argp = {
+		.options = opts,
+		.parser = parse_arg,
+		.doc = argp_program_doc,
+		.children = bench_parsers,
+	};
+
+	/* Parse arguments the second time with the correct set of parsers */
+	if (bench->argp) {
+		bench_parsers[0].argp = bench->argp;
+		bench_parsers[0].header = bench->name;
+		pos_args = 0;
+		if (argp_parse(&argp, argc, argv, 0, NULL, NULL))
+			exit(1);
 	}
 }
 
@@ -415,12 +452,14 @@ static void setup_timer()
 static void set_thread_affinity(pthread_t thread, int cpu)
 {
 	cpu_set_t cpuset;
+	int err;
 
 	CPU_ZERO(&cpuset);
 	CPU_SET(cpu, &cpuset);
-	if (pthread_setaffinity_np(thread, sizeof(cpuset), &cpuset)) {
+	err = pthread_setaffinity_np(thread, sizeof(cpuset), &cpuset);
+	if (err) {
 		fprintf(stderr, "setting affinity to CPU #%d failed: %d\n",
-			cpu, errno);
+			cpu, -err);
 		exit(1);
 	}
 }
@@ -441,7 +480,7 @@ static int next_cpu(struct cpu_set *cpu_set)
 		exit(1);
 	}
 
-	return cpu_set->next_cpu++;
+	return cpu_set->next_cpu++ % env.nr_cpus;
 }
 
 static struct bench_state {
@@ -461,18 +500,45 @@ extern const struct bench bench_rename_kretprobe;
 extern const struct bench bench_rename_rawtp;
 extern const struct bench bench_rename_fentry;
 extern const struct bench bench_rename_fexit;
-extern const struct bench bench_trig_base;
-extern const struct bench bench_trig_tp;
-extern const struct bench bench_trig_rawtp;
+
+/* pure counting benchmarks to establish theoretical limits */
+extern const struct bench bench_trig_usermode_count;
+extern const struct bench bench_trig_syscall_count;
+extern const struct bench bench_trig_kernel_count;
+
+/* batched, staying mostly in-kernel benchmarks */
 extern const struct bench bench_trig_kprobe;
+extern const struct bench bench_trig_kretprobe;
+extern const struct bench bench_trig_kprobe_multi;
+extern const struct bench bench_trig_kretprobe_multi;
 extern const struct bench bench_trig_fentry;
-extern const struct bench bench_trig_fentry_sleep;
+extern const struct bench bench_trig_kprobe_multi_all;
+extern const struct bench bench_trig_kretprobe_multi_all;
+extern const struct bench bench_trig_fexit;
 extern const struct bench bench_trig_fmodret;
-extern const struct bench bench_trig_uprobe_base;
-extern const struct bench bench_trig_uprobe_with_nop;
-extern const struct bench bench_trig_uretprobe_with_nop;
-extern const struct bench bench_trig_uprobe_without_nop;
-extern const struct bench bench_trig_uretprobe_without_nop;
+extern const struct bench bench_trig_tp;
+extern const struct bench bench_trig_rawtp;
+
+/* uprobe/uretprobe benchmarks */
+extern const struct bench bench_trig_uprobe_nop;
+extern const struct bench bench_trig_uretprobe_nop;
+extern const struct bench bench_trig_uprobe_push;
+extern const struct bench bench_trig_uretprobe_push;
+extern const struct bench bench_trig_uprobe_ret;
+extern const struct bench bench_trig_uretprobe_ret;
+extern const struct bench bench_trig_uprobe_multi_nop;
+extern const struct bench bench_trig_uretprobe_multi_nop;
+extern const struct bench bench_trig_uprobe_multi_push;
+extern const struct bench bench_trig_uretprobe_multi_push;
+extern const struct bench bench_trig_uprobe_multi_ret;
+extern const struct bench bench_trig_uretprobe_multi_ret;
+#ifdef __x86_64__
+extern const struct bench bench_trig_uprobe_nop5;
+extern const struct bench bench_trig_uretprobe_nop5;
+extern const struct bench bench_trig_uprobe_multi_nop5;
+extern const struct bench bench_trig_uretprobe_multi_nop5;
+#endif
+
 extern const struct bench bench_rb_libbpf;
 extern const struct bench bench_rb_custom;
 extern const struct bench bench_pb_libbpf;
@@ -490,6 +556,19 @@ extern const struct bench bench_local_storage_cache_seq_get;
 extern const struct bench bench_local_storage_cache_interleaved_get;
 extern const struct bench bench_local_storage_cache_hashmap_control;
 extern const struct bench bench_local_storage_tasks_trace;
+extern const struct bench bench_bpf_hashmap_lookup;
+extern const struct bench bench_local_storage_create;
+extern const struct bench bench_htab_mem;
+extern const struct bench bench_crypto_encrypt;
+extern const struct bench bench_crypto_decrypt;
+extern const struct bench bench_sockmap;
+extern const struct bench bench_lpm_trie_noop;
+extern const struct bench bench_lpm_trie_baseline;
+extern const struct bench bench_lpm_trie_lookup;
+extern const struct bench bench_lpm_trie_insert;
+extern const struct bench bench_lpm_trie_update;
+extern const struct bench bench_lpm_trie_delete;
+extern const struct bench bench_lpm_trie_free;
 
 static const struct bench *benchs[] = {
 	&bench_count_global,
@@ -500,18 +579,42 @@ static const struct bench *benchs[] = {
 	&bench_rename_rawtp,
 	&bench_rename_fentry,
 	&bench_rename_fexit,
-	&bench_trig_base,
-	&bench_trig_tp,
-	&bench_trig_rawtp,
+	/* pure counting benchmarks for establishing theoretical limits */
+	&bench_trig_usermode_count,
+	&bench_trig_kernel_count,
+	&bench_trig_syscall_count,
+	/* batched, staying mostly in-kernel triggers */
 	&bench_trig_kprobe,
+	&bench_trig_kretprobe,
+	&bench_trig_kprobe_multi,
+	&bench_trig_kretprobe_multi,
 	&bench_trig_fentry,
-	&bench_trig_fentry_sleep,
+	&bench_trig_kprobe_multi_all,
+	&bench_trig_kretprobe_multi_all,
+	&bench_trig_fexit,
 	&bench_trig_fmodret,
-	&bench_trig_uprobe_base,
-	&bench_trig_uprobe_with_nop,
-	&bench_trig_uretprobe_with_nop,
-	&bench_trig_uprobe_without_nop,
-	&bench_trig_uretprobe_without_nop,
+	&bench_trig_tp,
+	&bench_trig_rawtp,
+	/* uprobes */
+	&bench_trig_uprobe_nop,
+	&bench_trig_uretprobe_nop,
+	&bench_trig_uprobe_push,
+	&bench_trig_uretprobe_push,
+	&bench_trig_uprobe_ret,
+	&bench_trig_uretprobe_ret,
+	&bench_trig_uprobe_multi_nop,
+	&bench_trig_uretprobe_multi_nop,
+	&bench_trig_uprobe_multi_push,
+	&bench_trig_uretprobe_multi_push,
+	&bench_trig_uprobe_multi_ret,
+	&bench_trig_uretprobe_multi_ret,
+#ifdef __x86_64__
+	&bench_trig_uprobe_nop5,
+	&bench_trig_uretprobe_nop5,
+	&bench_trig_uprobe_multi_nop5,
+	&bench_trig_uretprobe_multi_nop5,
+#endif
+	/* ringbuf/perfbuf benchmarks */
 	&bench_rb_libbpf,
 	&bench_rb_custom,
 	&bench_pb_libbpf,
@@ -529,17 +632,29 @@ static const struct bench *benchs[] = {
 	&bench_local_storage_cache_interleaved_get,
 	&bench_local_storage_cache_hashmap_control,
 	&bench_local_storage_tasks_trace,
+	&bench_bpf_hashmap_lookup,
+	&bench_local_storage_create,
+	&bench_htab_mem,
+	&bench_crypto_encrypt,
+	&bench_crypto_decrypt,
+	&bench_sockmap,
+	&bench_lpm_trie_noop,
+	&bench_lpm_trie_baseline,
+	&bench_lpm_trie_lookup,
+	&bench_lpm_trie_insert,
+	&bench_lpm_trie_update,
+	&bench_lpm_trie_delete,
+	&bench_lpm_trie_free,
 };
 
-static void setup_benchmark()
+static void find_benchmark(void)
 {
-	int i, err;
+	int i;
 
 	if (!env.bench_name) {
 		fprintf(stderr, "benchmark name is not specified\n");
 		exit(1);
 	}
-
 	for (i = 0; i < ARRAY_SIZE(benchs); i++) {
 		if (strcmp(benchs[i]->name, env.bench_name) == 0) {
 			bench = benchs[i];
@@ -550,8 +665,14 @@ static void setup_benchmark()
 		fprintf(stderr, "benchmark '%s' not found\n", env.bench_name);
 		exit(1);
 	}
+}
 
-	printf("Setting up benchmark '%s'...\n", bench->name);
+static void setup_benchmark(void)
+{
+	int i, err;
+
+	if (!env.quiet)
+		printf("Setting up benchmark '%s'...\n", bench->name);
 
 	state.producers = calloc(env.producer_cnt, sizeof(*state.producers));
 	state.consumers = calloc(env.consumer_cnt, sizeof(*state.consumers));
@@ -566,11 +687,15 @@ static void setup_benchmark()
 		bench->setup();
 
 	for (i = 0; i < env.consumer_cnt; i++) {
+		if (!bench->consumer_thread) {
+			fprintf(stderr, "benchmark doesn't support consumers!\n");
+			exit(1);
+		}
 		err = pthread_create(&state.consumers[i], NULL,
 				     bench->consumer_thread, (void *)(long)i);
 		if (err) {
 			fprintf(stderr, "failed to create consumer thread #%d: %d\n",
-				i, -errno);
+				i, -err);
 			exit(1);
 		}
 		if (env.affinity)
@@ -585,11 +710,15 @@ static void setup_benchmark()
 		env.prod_cpus.next_cpu = env.cons_cpus.next_cpu;
 
 	for (i = 0; i < env.producer_cnt; i++) {
+		if (!bench->producer_thread) {
+			fprintf(stderr, "benchmark doesn't support producers!\n");
+			exit(1);
+		}
 		err = pthread_create(&state.producers[i], NULL,
 				     bench->producer_thread, (void *)(long)i);
 		if (err) {
 			fprintf(stderr, "failed to create producer thread #%d: %d\n",
-				i, -errno);
+				i, -err);
 			exit(1);
 		}
 		if (env.affinity)
@@ -597,7 +726,8 @@ static void setup_benchmark()
 					    next_cpu(&env.prod_cpus));
 	}
 
-	printf("Benchmark '%s' started.\n", bench->name);
+	if (!env.quiet)
+		printf("Benchmark '%s' started.\n", bench->name);
 }
 
 static pthread_mutex_t bench_done_mtx = PTHREAD_MUTEX_INITIALIZER;
@@ -621,7 +751,8 @@ static void collect_measurements(long delta_ns) {
 
 int main(int argc, char **argv)
 {
-	parse_cmdline_args(argc, argv);
+	env.nr_cpus = get_nprocs();
+	parse_cmdline_args_init(argc, argv);
 
 	if (env.list) {
 		int i;
@@ -633,6 +764,9 @@ int main(int argc, char **argv)
 		return 0;
 	}
 
+	find_benchmark();
+	parse_cmdline_args_final(argc, argv);
+
 	setup_benchmark();
 
 	setup_timer();
diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h
index d748255877e2..bea323820ffb 100644
--- a/tools/testing/selftests/bpf/bench.h
+++ b/tools/testing/selftests/bpf/bench.h
@@ -10,6 +10,7 @@
 #include <math.h>
 #include <time.h>
 #include <sys/syscall.h>
+#include <limits.h>
 
 struct cpu_set {
 	bool *cpus;
@@ -24,8 +25,10 @@ struct env {
 	bool verbose;
 	bool list;
 	bool affinity;
+	bool quiet;
 	int consumer_cnt;
 	int producer_cnt;
+	int nr_cpus;
 	struct cpu_set prod_cpus;
 	struct cpu_set cons_cpus;
 };
@@ -43,10 +46,12 @@ struct bench_res {
 	unsigned long gp_ns;
 	unsigned long gp_ct;
 	unsigned int stime;
+	unsigned long duration_ns;
 };
 
 struct bench {
 	const char *name;
+	const struct argp *argp;
 	void (*validate)(void);
 	void (*setup)(void);
 	void *(*producer_thread)(void *ctx);
@@ -78,15 +83,6 @@ void grace_period_latency_basic_stats(struct bench_res res[], int res_cnt,
 void grace_period_ticks_basic_stats(struct bench_res res[], int res_cnt,
 				    struct basic_stats *gp_stat);
 
-static inline __u64 get_time_ns(void)
-{
-	struct timespec t;
-
-	clock_gettime(CLOCK_MONOTONIC, &t);
-
-	return (u64)t.tv_sec * 1000000000 + t.tv_nsec;
-}
-
 static inline void atomic_inc(long *value)
 {
 	(void)__atomic_add_fetch(value, 1, __ATOMIC_RELAXED);
diff --git a/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c b/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c
index 5bcb8a8cdeb2..e289dd1a14ee 100644
--- a/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c
+++ b/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c
@@ -107,9 +107,9 @@ const struct argp bench_bloom_map_argp = {
 
 static void validate(void)
 {
-	if (env.consumer_cnt != 1) {
+	if (env.consumer_cnt != 0) {
 		fprintf(stderr,
-			"The bloom filter benchmarks do not support multi-consumer use\n");
+			"The bloom filter benchmarks do not support consumer\n");
 		exit(1);
 	}
 }
@@ -421,17 +421,12 @@ static void measure(struct bench_res *res)
 	last_false_hits = total_false_hits;
 }
 
-static void *consumer(void *input)
-{
-	return NULL;
-}
-
 const struct bench bench_bloom_lookup = {
 	.name = "bloom-lookup",
+	.argp = &bench_bloom_map_argp,
 	.validate = validate,
 	.setup = bloom_lookup_setup,
 	.producer_thread = producer,
-	.consumer_thread = consumer,
 	.measure = measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
@@ -439,10 +434,10 @@ const struct bench bench_bloom_lookup = {
 
 const struct bench bench_bloom_update = {
 	.name = "bloom-update",
+	.argp = &bench_bloom_map_argp,
 	.validate = validate,
 	.setup = bloom_update_setup,
 	.producer_thread = producer,
-	.consumer_thread = consumer,
 	.measure = measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
@@ -450,10 +445,10 @@ const struct bench bench_bloom_update = {
 
 const struct bench bench_bloom_false_positive = {
 	.name = "bloom-false-positive",
+	.argp = &bench_bloom_map_argp,
 	.validate = validate,
 	.setup = false_positive_setup,
 	.producer_thread = producer,
-	.consumer_thread = consumer,
 	.measure = measure,
 	.report_progress = false_hits_report_progress,
 	.report_final = false_hits_report_final,
@@ -461,10 +456,10 @@ const struct bench bench_bloom_false_positive = {
 
 const struct bench bench_hashmap_without_bloom = {
 	.name = "hashmap-without-bloom",
+	.argp = &bench_bloom_map_argp,
 	.validate = validate,
 	.setup = hashmap_no_bloom_setup,
 	.producer_thread = producer,
-	.consumer_thread = consumer,
 	.measure = measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
@@ -472,10 +467,10 @@ const struct bench bench_hashmap_without_bloom = {
 
 const struct bench bench_hashmap_with_bloom = {
 	.name = "hashmap-with-bloom",
+	.argp = &bench_bloom_map_argp,
 	.validate = validate,
 	.setup = hashmap_with_bloom_setup,
 	.producer_thread = producer,
-	.consumer_thread = consumer,
 	.measure = measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_crypto.c b/tools/testing/selftests/bpf/benchs/bench_bpf_crypto.c
new file mode 100644
index 000000000000..2845edaba8db
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_bpf_crypto.c
@@ -0,0 +1,185 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <argp.h>
+#include "bench.h"
+#include "crypto_bench.skel.h"
+
+#define MAX_CIPHER_LEN 32
+static char *input;
+static struct crypto_ctx {
+	struct crypto_bench *skel;
+	int pfd;
+} ctx;
+
+static struct crypto_args {
+	u32 crypto_len;
+	char *crypto_cipher;
+} args = {
+	.crypto_len = 16,
+	.crypto_cipher = "ecb(aes)",
+};
+
+enum {
+	ARG_CRYPTO_LEN = 5000,
+	ARG_CRYPTO_CIPHER = 5001,
+};
+
+static const struct argp_option opts[] = {
+	{ "crypto-len", ARG_CRYPTO_LEN, "CRYPTO_LEN", 0,
+	  "Set the length of crypto buffer" },
+	{ "crypto-cipher", ARG_CRYPTO_CIPHER, "CRYPTO_CIPHER", 0,
+	  "Set the cipher to use (default:ecb(aes))" },
+	{},
+};
+
+static error_t crypto_parse_arg(int key, char *arg, struct argp_state *state)
+{
+	switch (key) {
+	case ARG_CRYPTO_LEN:
+		args.crypto_len = strtoul(arg, NULL, 10);
+		if (!args.crypto_len ||
+		    args.crypto_len > sizeof(ctx.skel->bss->dst)) {
+			fprintf(stderr, "Invalid crypto buffer len (limit %zu)\n",
+				sizeof(ctx.skel->bss->dst));
+			argp_usage(state);
+		}
+		break;
+	case ARG_CRYPTO_CIPHER:
+		args.crypto_cipher = strdup(arg);
+		if (!strlen(args.crypto_cipher) ||
+		    strlen(args.crypto_cipher) > MAX_CIPHER_LEN) {
+			fprintf(stderr, "Invalid crypto cipher len (limit %d)\n",
+				MAX_CIPHER_LEN);
+			argp_usage(state);
+		}
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+
+	return 0;
+}
+
+const struct argp bench_crypto_argp = {
+	.options = opts,
+	.parser = crypto_parse_arg,
+};
+
+static void crypto_validate(void)
+{
+	if (env.consumer_cnt != 0) {
+		fprintf(stderr, "bpf crypto benchmark doesn't support consumer!\n");
+		exit(1);
+	}
+}
+
+static void crypto_setup(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+
+	int err, pfd;
+	size_t i, sz;
+
+	sz = args.crypto_len;
+	if (!sz || sz > sizeof(ctx.skel->bss->dst)) {
+		fprintf(stderr, "invalid encrypt buffer size (source %zu, target %zu)\n",
+			sz, sizeof(ctx.skel->bss->dst));
+		exit(1);
+	}
+
+	setup_libbpf();
+
+	ctx.skel = crypto_bench__open();
+	if (!ctx.skel) {
+		fprintf(stderr, "failed to open skeleton\n");
+		exit(1);
+	}
+
+	snprintf(ctx.skel->bss->cipher, 128, "%s", args.crypto_cipher);
+	memcpy(ctx.skel->bss->key, "12345678testtest", 16);
+	ctx.skel->bss->key_len = 16;
+	ctx.skel->bss->authsize = 0;
+
+	srandom(time(NULL));
+	input = malloc(sz);
+	for (i = 0; i < sz - 1; i++)
+		input[i] = '1' + random() % 9;
+	input[sz - 1] = '\0';
+
+	ctx.skel->rodata->len = args.crypto_len;
+
+	err = crypto_bench__load(ctx.skel);
+	if (err) {
+		fprintf(stderr, "failed to load skeleton\n");
+		crypto_bench__destroy(ctx.skel);
+		exit(1);
+	}
+
+	pfd = bpf_program__fd(ctx.skel->progs.crypto_setup);
+	if (pfd < 0) {
+		fprintf(stderr, "failed to get fd for setup prog\n");
+		crypto_bench__destroy(ctx.skel);
+		exit(1);
+	}
+
+	err = bpf_prog_test_run_opts(pfd, &opts);
+	if (err || ctx.skel->bss->status) {
+		fprintf(stderr, "failed to run setup prog: err %d, status %d\n",
+			err, ctx.skel->bss->status);
+		crypto_bench__destroy(ctx.skel);
+		exit(1);
+	}
+}
+
+static void crypto_encrypt_setup(void)
+{
+	crypto_setup();
+	ctx.pfd = bpf_program__fd(ctx.skel->progs.crypto_encrypt);
+}
+
+static void crypto_decrypt_setup(void)
+{
+	crypto_setup();
+	ctx.pfd = bpf_program__fd(ctx.skel->progs.crypto_decrypt);
+}
+
+static void crypto_measure(struct bench_res *res)
+{
+	res->hits = atomic_swap(&ctx.skel->bss->hits, 0);
+}
+
+static void *crypto_producer(void *unused)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		.repeat = 64,
+		.data_in = input,
+		.data_size_in = args.crypto_len,
+	);
+
+	while (true)
+		(void)bpf_prog_test_run_opts(ctx.pfd, &opts);
+	return NULL;
+}
+
+const struct bench bench_crypto_encrypt = {
+	.name = "crypto-encrypt",
+	.argp = &bench_crypto_argp,
+	.validate = crypto_validate,
+	.setup = crypto_encrypt_setup,
+	.producer_thread = crypto_producer,
+	.measure = crypto_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_crypto_decrypt = {
+	.name = "crypto-decrypt",
+	.argp = &bench_crypto_argp,
+	.validate = crypto_validate,
+	.setup = crypto_decrypt_setup,
+	.producer_thread = crypto_producer,
+	.measure = crypto_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c
index cec51e0ff4b8..ee1dc12c5e5e 100644
--- a/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c
+++ b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_full_update.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2022 Bytedance */
 
-#include <argp.h>
 #include "bench.h"
 #include "bpf_hashmap_full_update_bench.skel.h"
 #include "bpf_util.h"
@@ -15,8 +14,8 @@ static struct ctx {
 
 static void validate(void)
 {
-	if (env.consumer_cnt != 1) {
-		fprintf(stderr, "benchmark doesn't support multi-consumer!\n");
+	if (env.consumer_cnt != 0) {
+		fprintf(stderr, "benchmark doesn't support consumer!\n");
 		exit(1);
 	}
 }
@@ -31,11 +30,6 @@ static void *producer(void *input)
 	return NULL;
 }
 
-static void *consumer(void *input)
-{
-	return NULL;
-}
-
 static void measure(struct bench_res *res)
 {
 }
@@ -68,7 +62,7 @@ static void setup(void)
 		bpf_map_update_elem(map_fd, &i, &i, BPF_ANY);
 }
 
-void hashmap_report_final(struct bench_res res[], int res_cnt)
+static void hashmap_report_final(struct bench_res res[], int res_cnt)
 {
 	unsigned int nr_cpus = bpf_num_possible_cpus();
 	int i;
@@ -85,11 +79,10 @@ void hashmap_report_final(struct bench_res res[], int res_cnt)
 }
 
 const struct bench bench_bpf_hashmap_full_update = {
-	.name = "bpf-hashmap-ful-update",
+	.name = "bpf-hashmap-full-update",
 	.validate = validate,
 	.setup = setup,
 	.producer_thread = producer,
-	.consumer_thread = consumer,
 	.measure = measure,
 	.report_progress = NULL,
 	.report_final = hashmap_report_final,
diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_lookup.c b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_lookup.c
new file mode 100644
index 000000000000..279ff1b8b5b2
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_bpf_hashmap_lookup.c
@@ -0,0 +1,277 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+
+#include <sys/random.h>
+#include <argp.h>
+#include "bench.h"
+#include "bpf_hashmap_lookup.skel.h"
+#include "bpf_util.h"
+
+/* BPF triggering benchmarks */
+static struct ctx {
+	struct bpf_hashmap_lookup *skel;
+} ctx;
+
+/* only available to kernel, so define it here */
+#define BPF_MAX_LOOPS (1<<23)
+
+#define MAX_KEY_SIZE 1024 /* the size of the key map */
+
+static struct {
+	__u32 key_size;
+	__u32 map_flags;
+	__u32 max_entries;
+	__u32 nr_entries;
+	__u32 nr_loops;
+} args = {
+	.key_size = 4,
+	.map_flags = 0,
+	.max_entries = 1000,
+	.nr_entries = 500,
+	.nr_loops = 1000000,
+};
+
+enum {
+	ARG_KEY_SIZE = 8001,
+	ARG_MAP_FLAGS,
+	ARG_MAX_ENTRIES,
+	ARG_NR_ENTRIES,
+	ARG_NR_LOOPS,
+};
+
+static const struct argp_option opts[] = {
+	{ "key_size", ARG_KEY_SIZE, "KEY_SIZE", 0,
+	  "The hashmap key size (max 1024)"},
+	{ "map_flags", ARG_MAP_FLAGS, "MAP_FLAGS", 0,
+	  "The hashmap flags passed to BPF_MAP_CREATE"},
+	{ "max_entries", ARG_MAX_ENTRIES, "MAX_ENTRIES", 0,
+	  "The hashmap max entries"},
+	{ "nr_entries", ARG_NR_ENTRIES, "NR_ENTRIES", 0,
+	  "The number of entries to insert/lookup"},
+	{ "nr_loops", ARG_NR_LOOPS, "NR_LOOPS", 0,
+	  "The number of loops for the benchmark"},
+	{},
+};
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+	long ret;
+
+	switch (key) {
+	case ARG_KEY_SIZE:
+		ret = strtol(arg, NULL, 10);
+		if (ret < 1 || ret > MAX_KEY_SIZE) {
+			fprintf(stderr, "invalid key_size");
+			argp_usage(state);
+		}
+		args.key_size = ret;
+		break;
+	case ARG_MAP_FLAGS:
+		ret = strtol(arg, NULL, 0);
+		if (ret < 0 || ret > UINT_MAX) {
+			fprintf(stderr, "invalid map_flags");
+			argp_usage(state);
+		}
+		args.map_flags = ret;
+		break;
+	case ARG_MAX_ENTRIES:
+		ret = strtol(arg, NULL, 10);
+		if (ret < 1 || ret > UINT_MAX) {
+			fprintf(stderr, "invalid max_entries");
+			argp_usage(state);
+		}
+		args.max_entries = ret;
+		break;
+	case ARG_NR_ENTRIES:
+		ret = strtol(arg, NULL, 10);
+		if (ret < 1 || ret > UINT_MAX) {
+			fprintf(stderr, "invalid nr_entries");
+			argp_usage(state);
+		}
+		args.nr_entries = ret;
+		break;
+	case ARG_NR_LOOPS:
+		ret = strtol(arg, NULL, 10);
+		if (ret < 1 || ret > BPF_MAX_LOOPS) {
+			fprintf(stderr, "invalid nr_loops: %ld (min=1 max=%u)\n",
+				ret, BPF_MAX_LOOPS);
+			argp_usage(state);
+		}
+		args.nr_loops = ret;
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+
+	return 0;
+}
+
+const struct argp bench_hashmap_lookup_argp = {
+	.options = opts,
+	.parser = parse_arg,
+};
+
+static void validate(void)
+{
+	if (env.consumer_cnt != 0) {
+		fprintf(stderr, "benchmark doesn't support consumer!\n");
+		exit(1);
+	}
+
+	if (args.nr_entries > args.max_entries) {
+		fprintf(stderr, "args.nr_entries is too big! (max %u, got %u)\n",
+			args.max_entries, args.nr_entries);
+		exit(1);
+	}
+}
+
+static void *producer(void *input)
+{
+	while (true) {
+		/* trigger the bpf program */
+		syscall(__NR_getpgid);
+	}
+	return NULL;
+}
+
+static void measure(struct bench_res *res)
+{
+}
+
+static inline void patch_key(u32 i, u32 *key)
+{
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	*key = i + 1;
+#else
+	*key = __builtin_bswap32(i + 1);
+#endif
+	/* the rest of key is random */
+}
+
+static void setup(void)
+{
+	struct bpf_link *link;
+	int map_fd;
+	int ret;
+	int i;
+
+	setup_libbpf();
+
+	ctx.skel = bpf_hashmap_lookup__open();
+	if (!ctx.skel) {
+		fprintf(stderr, "failed to open skeleton\n");
+		exit(1);
+	}
+
+	bpf_map__set_max_entries(ctx.skel->maps.hash_map_bench, args.max_entries);
+	bpf_map__set_key_size(ctx.skel->maps.hash_map_bench, args.key_size);
+	bpf_map__set_value_size(ctx.skel->maps.hash_map_bench, 8);
+	bpf_map__set_map_flags(ctx.skel->maps.hash_map_bench, args.map_flags);
+
+	ctx.skel->bss->nr_entries = args.nr_entries;
+	ctx.skel->bss->nr_loops = args.nr_loops / args.nr_entries;
+
+	if (args.key_size > 4) {
+		for (i = 1; i < args.key_size/4; i++)
+			ctx.skel->bss->key[i] = 2654435761 * i;
+	}
+
+	ret = bpf_hashmap_lookup__load(ctx.skel);
+	if (ret) {
+		bpf_hashmap_lookup__destroy(ctx.skel);
+		fprintf(stderr, "failed to load map: %s", strerror(-ret));
+		exit(1);
+	}
+
+	/* fill in the hash_map */
+	map_fd = bpf_map__fd(ctx.skel->maps.hash_map_bench);
+	for (u64 i = 0; i < args.nr_entries; i++) {
+		patch_key(i, ctx.skel->bss->key);
+		bpf_map_update_elem(map_fd, ctx.skel->bss->key, &i, BPF_ANY);
+	}
+
+	link = bpf_program__attach(ctx.skel->progs.benchmark);
+	if (!link) {
+		fprintf(stderr, "failed to attach program!\n");
+		exit(1);
+	}
+}
+
+static inline double events_from_time(u64 time)
+{
+	if (time)
+		return args.nr_loops * 1000000000llu / time / 1000000.0L;
+
+	return 0;
+}
+
+static int compute_events(u64 *times, double *events_mean, double *events_stddev, u64 *mean_time)
+{
+	int i, n = 0;
+
+	*events_mean = 0;
+	*events_stddev = 0;
+	*mean_time = 0;
+
+	for (i = 0; i < 32; i++) {
+		if (!times[i])
+			break;
+		*mean_time += times[i];
+		*events_mean += events_from_time(times[i]);
+		n += 1;
+	}
+	if (!n)
+		return 0;
+
+	*mean_time /= n;
+	*events_mean /= n;
+
+	if (n > 1) {
+		for (i = 0; i < n; i++) {
+			double events_i = *events_mean - events_from_time(times[i]);
+			*events_stddev += events_i * events_i / (n - 1);
+		}
+		*events_stddev = sqrt(*events_stddev);
+	}
+
+	return n;
+}
+
+static void hashmap_report_final(struct bench_res res[], int res_cnt)
+{
+	unsigned int nr_cpus = bpf_num_possible_cpus();
+	double events_mean, events_stddev;
+	u64 mean_time;
+	int i, n;
+
+	for (i = 0; i < nr_cpus; i++) {
+		n = compute_events(ctx.skel->bss->percpu_times[i], &events_mean,
+				   &events_stddev, &mean_time);
+		if (n == 0)
+			continue;
+
+		if (env.quiet) {
+			/* we expect only one cpu to be present */
+			if (env.affinity)
+				printf("%.3lf\n", events_mean);
+			else
+				printf("cpu%02d %.3lf\n", i, events_mean);
+		} else {
+			printf("cpu%02d: lookup %.3lfM ± %.3lfM events/sec"
+			       " (approximated from %d samples of ~%lums)\n",
+			       i, events_mean, 2*events_stddev,
+			       n, mean_time / 1000000);
+		}
+	}
+}
+
+const struct bench bench_bpf_hashmap_lookup = {
+	.name = "bpf-hashmap-lookup",
+	.argp = &bench_hashmap_lookup_argp,
+	.validate = validate,
+	.setup = setup,
+	.producer_thread = producer,
+	.measure = measure,
+	.report_progress = NULL,
+	.report_final = hashmap_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c b/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c
index d0a6572bfab6..a705cfb2bccc 100644
--- a/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c
+++ b/tools/testing/selftests/bpf/benchs/bench_bpf_loop.c
@@ -47,8 +47,8 @@ const struct argp bench_bpf_loop_argp = {
 
 static void validate(void)
 {
-	if (env.consumer_cnt != 1) {
-		fprintf(stderr, "benchmark doesn't support multi-consumer!\n");
+	if (env.consumer_cnt != 0) {
+		fprintf(stderr, "benchmark doesn't support consumer!\n");
 		exit(1);
 	}
 }
@@ -62,11 +62,6 @@ static void *producer(void *input)
 	return NULL;
 }
 
-static void *consumer(void *input)
-{
-	return NULL;
-}
-
 static void measure(struct bench_res *res)
 {
 	res->hits = atomic_swap(&ctx.skel->bss->hits, 0);
@@ -95,10 +90,10 @@ static void setup(void)
 
 const struct bench bench_bpf_loop = {
 	.name = "bpf-loop",
+	.argp = &bench_bpf_loop_argp,
 	.validate = validate,
 	.setup = setup,
 	.producer_thread = producer,
-	.consumer_thread = consumer,
 	.measure = measure,
 	.report_progress = ops_report_progress,
 	.report_final = ops_report_final,
diff --git a/tools/testing/selftests/bpf/benchs/bench_count.c b/tools/testing/selftests/bpf/benchs/bench_count.c
index 078972ce208e..ba89ed3936b7 100644
--- a/tools/testing/selftests/bpf/benchs/bench_count.c
+++ b/tools/testing/selftests/bpf/benchs/bench_count.c
@@ -18,11 +18,6 @@ static void *count_global_producer(void *input)
 	return NULL;
 }
 
-static void *count_global_consumer(void *input)
-{
-	return NULL;
-}
-
 static void count_global_measure(struct bench_res *res)
 {
 	struct count_global_ctx *ctx = &count_global_ctx;
@@ -40,7 +35,7 @@ static void count_local_setup(void)
 {
 	struct count_local_ctx *ctx = &count_local_ctx;
 
-	ctx->hits = calloc(env.consumer_cnt, sizeof(*ctx->hits));
+	ctx->hits = calloc(env.producer_cnt, sizeof(*ctx->hits));
 	if (!ctx->hits)
 		exit(1);
 }
@@ -56,11 +51,6 @@ static void *count_local_producer(void *input)
 	return NULL;
 }
 
-static void *count_local_consumer(void *input)
-{
-	return NULL;
-}
-
 static void count_local_measure(struct bench_res *res)
 {
 	struct count_local_ctx *ctx = &count_local_ctx;
@@ -74,7 +64,6 @@ static void count_local_measure(struct bench_res *res)
 const struct bench bench_count_global = {
 	.name = "count-global",
 	.producer_thread = count_global_producer,
-	.consumer_thread = count_global_consumer,
 	.measure = count_global_measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
@@ -84,7 +73,6 @@ const struct bench bench_count_local = {
 	.name = "count-local",
 	.setup = count_local_setup,
 	.producer_thread = count_local_producer,
-	.consumer_thread = count_local_consumer,
 	.measure = count_local_measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
diff --git a/tools/testing/selftests/bpf/benchs/bench_htab_mem.c b/tools/testing/selftests/bpf/benchs/bench_htab_mem.c
new file mode 100644
index 000000000000..297e32390cd1
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_htab_mem.c
@@ -0,0 +1,350 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <argp.h>
+#include <stdbool.h>
+#include <pthread.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/param.h>
+#include <fcntl.h>
+
+#include "bench.h"
+#include "bpf_util.h"
+#include "cgroup_helpers.h"
+#include "htab_mem_bench.skel.h"
+
+struct htab_mem_use_case {
+	const char *name;
+	const char **progs;
+	/* Do synchronization between addition thread and deletion thread */
+	bool need_sync;
+};
+
+static struct htab_mem_ctx {
+	const struct htab_mem_use_case *uc;
+	struct htab_mem_bench *skel;
+	pthread_barrier_t *notify;
+	int fd;
+} ctx;
+
+const char *ow_progs[] = {"overwrite", NULL};
+const char *batch_progs[] = {"batch_add_batch_del", NULL};
+const char *add_del_progs[] = {"add_only", "del_only", NULL};
+const static struct htab_mem_use_case use_cases[] = {
+	{ .name = "overwrite", .progs = ow_progs },
+	{ .name = "batch_add_batch_del", .progs = batch_progs },
+	{ .name = "add_del_on_diff_cpu", .progs = add_del_progs, .need_sync = true },
+};
+
+static struct htab_mem_args {
+	u32 value_size;
+	const char *use_case;
+	bool preallocated;
+} args = {
+	.value_size = 8,
+	.use_case = "overwrite",
+	.preallocated = false,
+};
+
+enum {
+	ARG_VALUE_SIZE = 10000,
+	ARG_USE_CASE = 10001,
+	ARG_PREALLOCATED = 10002,
+};
+
+static const struct argp_option opts[] = {
+	{ "value-size", ARG_VALUE_SIZE, "VALUE_SIZE", 0,
+	  "Set the value size of hash map (default 8)" },
+	{ "use-case", ARG_USE_CASE, "USE_CASE", 0,
+	  "Set the use case of hash map: overwrite|batch_add_batch_del|add_del_on_diff_cpu" },
+	{ "preallocated", ARG_PREALLOCATED, NULL, 0, "use preallocated hash map" },
+	{},
+};
+
+static error_t htab_mem_parse_arg(int key, char *arg, struct argp_state *state)
+{
+	switch (key) {
+	case ARG_VALUE_SIZE:
+		args.value_size = strtoul(arg, NULL, 10);
+		if (args.value_size > 4096) {
+			fprintf(stderr, "too big value size %u\n", args.value_size);
+			argp_usage(state);
+		}
+		break;
+	case ARG_USE_CASE:
+		args.use_case = strdup(arg);
+		if (!args.use_case) {
+			fprintf(stderr, "no mem for use-case\n");
+			argp_usage(state);
+		}
+		break;
+	case ARG_PREALLOCATED:
+		args.preallocated = true;
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+
+	return 0;
+}
+
+const struct argp bench_htab_mem_argp = {
+	.options = opts,
+	.parser = htab_mem_parse_arg,
+};
+
+static void htab_mem_validate(void)
+{
+	if (!strcmp(use_cases[2].name, args.use_case) && env.producer_cnt % 2) {
+		fprintf(stderr, "%s needs an even number of producers\n", args.use_case);
+		exit(1);
+	}
+}
+
+static int htab_mem_bench_init_barriers(void)
+{
+	pthread_barrier_t *barriers;
+	unsigned int i, nr;
+
+	if (!ctx.uc->need_sync)
+		return 0;
+
+	nr = (env.producer_cnt + 1) / 2;
+	barriers = calloc(nr, sizeof(*barriers));
+	if (!barriers)
+		return -1;
+
+	/* Used for synchronization between two threads */
+	for (i = 0; i < nr; i++)
+		pthread_barrier_init(&barriers[i], NULL, 2);
+
+	ctx.notify = barriers;
+	return 0;
+}
+
+static void htab_mem_bench_exit_barriers(void)
+{
+	unsigned int i, nr;
+
+	if (!ctx.notify)
+		return;
+
+	nr = (env.producer_cnt + 1) / 2;
+	for (i = 0; i < nr; i++)
+		pthread_barrier_destroy(&ctx.notify[i]);
+	free(ctx.notify);
+}
+
+static const struct htab_mem_use_case *htab_mem_find_use_case_or_exit(const char *name)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(use_cases); i++) {
+		if (!strcmp(name, use_cases[i].name))
+			return &use_cases[i];
+	}
+
+	fprintf(stderr, "no such use-case: %s\n", name);
+	fprintf(stderr, "available use case:");
+	for (i = 0; i < ARRAY_SIZE(use_cases); i++)
+		fprintf(stderr, " %s", use_cases[i].name);
+	fprintf(stderr, "\n");
+	exit(1);
+}
+
+static void htab_mem_setup(void)
+{
+	struct bpf_map *map;
+	const char **names;
+	int err;
+
+	setup_libbpf();
+
+	ctx.uc = htab_mem_find_use_case_or_exit(args.use_case);
+	err = htab_mem_bench_init_barriers();
+	if (err) {
+		fprintf(stderr, "failed to init barrier\n");
+		exit(1);
+	}
+
+	ctx.fd = cgroup_setup_and_join("/htab_mem");
+	if (ctx.fd < 0)
+		goto cleanup;
+
+	ctx.skel = htab_mem_bench__open();
+	if (!ctx.skel) {
+		fprintf(stderr, "failed to open skeleton\n");
+		goto cleanup;
+	}
+
+	map = ctx.skel->maps.htab;
+	bpf_map__set_value_size(map, args.value_size);
+	/* Ensure that different CPUs can operate on different subset */
+	bpf_map__set_max_entries(map, MAX(8192, 64 * env.nr_cpus));
+	if (args.preallocated)
+		bpf_map__set_map_flags(map, bpf_map__map_flags(map) & ~BPF_F_NO_PREALLOC);
+
+	names = ctx.uc->progs;
+	while (*names) {
+		struct bpf_program *prog;
+
+		prog = bpf_object__find_program_by_name(ctx.skel->obj, *names);
+		if (!prog) {
+			fprintf(stderr, "no such program %s\n", *names);
+			goto cleanup;
+		}
+		bpf_program__set_autoload(prog, true);
+		names++;
+	}
+	ctx.skel->bss->nr_thread = env.producer_cnt;
+
+	err = htab_mem_bench__load(ctx.skel);
+	if (err) {
+		fprintf(stderr, "failed to load skeleton\n");
+		goto cleanup;
+	}
+	err = htab_mem_bench__attach(ctx.skel);
+	if (err) {
+		fprintf(stderr, "failed to attach skeleton\n");
+		goto cleanup;
+	}
+	return;
+
+cleanup:
+	htab_mem_bench__destroy(ctx.skel);
+	htab_mem_bench_exit_barriers();
+	if (ctx.fd >= 0) {
+		close(ctx.fd);
+		cleanup_cgroup_environment();
+	}
+	exit(1);
+}
+
+static void htab_mem_add_fn(pthread_barrier_t *notify)
+{
+	while (true) {
+		/* Do addition */
+		(void)syscall(__NR_getpgid, 0);
+		/* Notify deletion thread to do deletion */
+		pthread_barrier_wait(notify);
+		/* Wait for deletion to complete */
+		pthread_barrier_wait(notify);
+	}
+}
+
+static void htab_mem_delete_fn(pthread_barrier_t *notify)
+{
+	while (true) {
+		/* Wait for addition to complete */
+		pthread_barrier_wait(notify);
+		/* Do deletion */
+		(void)syscall(__NR_getppid);
+		/* Notify addition thread to do addition */
+		pthread_barrier_wait(notify);
+	}
+}
+
+static void *htab_mem_producer(void *arg)
+{
+	pthread_barrier_t *notify;
+	int seq;
+
+	if (!ctx.uc->need_sync) {
+		while (true)
+			(void)syscall(__NR_getpgid, 0);
+		return NULL;
+	}
+
+	seq = (long)arg;
+	notify = &ctx.notify[seq / 2];
+	if (seq & 1)
+		htab_mem_delete_fn(notify);
+	else
+		htab_mem_add_fn(notify);
+	return NULL;
+}
+
+static void htab_mem_read_mem_cgrp_file(const char *name, unsigned long *value)
+{
+	char buf[32];
+	ssize_t got;
+	int fd;
+
+	fd = openat(ctx.fd, name, O_RDONLY);
+	if (fd < 0) {
+		/* cgroup v1 ? */
+		fprintf(stderr, "no %s\n", name);
+		*value = 0;
+		return;
+	}
+
+	got = read(fd, buf, sizeof(buf) - 1);
+	close(fd);
+	if (got <= 0) {
+		*value = 0;
+		return;
+	}
+	buf[got] = 0;
+
+	*value = strtoull(buf, NULL, 0);
+}
+
+static void htab_mem_measure(struct bench_res *res)
+{
+	res->hits = atomic_swap(&ctx.skel->bss->op_cnt, 0) / env.producer_cnt;
+	htab_mem_read_mem_cgrp_file("memory.current", &res->gp_ct);
+}
+
+static void htab_mem_report_progress(int iter, struct bench_res *res, long delta_ns)
+{
+	double loop, mem;
+
+	loop = res->hits / 1000.0 / (delta_ns / 1000000000.0);
+	mem = res->gp_ct / 1048576.0;
+	printf("Iter %3d (%7.3lfus): ", iter, (delta_ns - 1000000000) / 1000.0);
+	printf("per-prod-op %7.2lfk/s, memory usage %7.2lfMiB\n", loop, mem);
+}
+
+static void htab_mem_report_final(struct bench_res res[], int res_cnt)
+{
+	double mem_mean = 0.0, mem_stddev = 0.0;
+	double loop_mean = 0.0, loop_stddev = 0.0;
+	unsigned long peak_mem;
+	int i;
+
+	for (i = 0; i < res_cnt; i++) {
+		loop_mean += res[i].hits / 1000.0 / (0.0 + res_cnt);
+		mem_mean += res[i].gp_ct / 1048576.0 / (0.0 + res_cnt);
+	}
+	if (res_cnt > 1)  {
+		for (i = 0; i < res_cnt; i++) {
+			loop_stddev += (loop_mean - res[i].hits / 1000.0) *
+				       (loop_mean - res[i].hits / 1000.0) /
+				       (res_cnt - 1.0);
+			mem_stddev += (mem_mean - res[i].gp_ct / 1048576.0) *
+				      (mem_mean - res[i].gp_ct / 1048576.0) /
+				      (res_cnt - 1.0);
+		}
+		loop_stddev = sqrt(loop_stddev);
+		mem_stddev = sqrt(mem_stddev);
+	}
+
+	htab_mem_read_mem_cgrp_file("memory.peak", &peak_mem);
+	printf("Summary: per-prod-op %7.2lf \u00B1 %7.2lfk/s, memory usage %7.2lf \u00B1 %7.2lfMiB,"
+	       " peak memory usage %7.2lfMiB\n",
+	       loop_mean, loop_stddev, mem_mean, mem_stddev, peak_mem / 1048576.0);
+
+	close(ctx.fd);
+	cleanup_cgroup_environment();
+}
+
+const struct bench bench_htab_mem = {
+	.name = "htab-mem",
+	.argp = &bench_htab_mem_argp,
+	.validate = htab_mem_validate,
+	.setup = htab_mem_setup,
+	.producer_thread = htab_mem_producer,
+	.measure = htab_mem_measure,
+	.report_progress = htab_mem_report_progress,
+	.report_final = htab_mem_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/bench_local_storage.c b/tools/testing/selftests/bpf/benchs/bench_local_storage.c
index 5a378c84e81f..452499428ceb 100644
--- a/tools/testing/selftests/bpf/benchs/bench_local_storage.c
+++ b/tools/testing/selftests/bpf/benchs/bench_local_storage.c
@@ -74,8 +74,8 @@ static void validate(void)
 		fprintf(stderr, "benchmark doesn't support multi-producer!\n");
 		exit(1);
 	}
-	if (env.consumer_cnt != 1) {
-		fprintf(stderr, "benchmark doesn't support multi-consumer!\n");
+	if (env.consumer_cnt != 0) {
+		fprintf(stderr, "benchmark doesn't support consumer!\n");
 		exit(1);
 	}
 
@@ -230,11 +230,6 @@ static inline void trigger_bpf_program(void)
 	syscall(__NR_getpgid);
 }
 
-static void *consumer(void *input)
-{
-	return NULL;
-}
-
 static void *producer(void *input)
 {
 	while (true)
@@ -255,10 +250,10 @@ static void *producer(void *input)
  */
 const struct bench bench_local_storage_cache_seq_get = {
 	.name = "local-storage-cache-seq-get",
+	.argp = &bench_local_storage_argp,
 	.validate = validate,
 	.setup = local_storage_cache_get_setup,
 	.producer_thread = producer,
-	.consumer_thread = consumer,
 	.measure = measure,
 	.report_progress = local_storage_report_progress,
 	.report_final = local_storage_report_final,
@@ -266,10 +261,10 @@ const struct bench bench_local_storage_cache_seq_get = {
 
 const struct bench bench_local_storage_cache_interleaved_get = {
 	.name = "local-storage-cache-int-get",
+	.argp = &bench_local_storage_argp,
 	.validate = validate,
 	.setup = local_storage_cache_get_interleaved_setup,
 	.producer_thread = producer,
-	.consumer_thread = consumer,
 	.measure = measure,
 	.report_progress = local_storage_report_progress,
 	.report_final = local_storage_report_final,
@@ -277,10 +272,10 @@ const struct bench bench_local_storage_cache_interleaved_get = {
 
 const struct bench bench_local_storage_cache_hashmap_control = {
 	.name = "local-storage-cache-hashmap-control",
+	.argp = &bench_local_storage_argp,
 	.validate = validate,
 	.setup = hashmap_setup,
 	.producer_thread = producer,
-	.consumer_thread = consumer,
 	.measure = measure,
 	.report_progress = local_storage_report_progress,
 	.report_final = local_storage_report_final,
diff --git a/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c b/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c
new file mode 100644
index 000000000000..e2ff8ea1cb79
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_local_storage_create.c
@@ -0,0 +1,258 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <pthread.h>
+#include <argp.h>
+
+#include "bench.h"
+#include "bench_local_storage_create.skel.h"
+
+struct thread {
+	int *fds;
+	pthread_t *pthds;
+	int *pthd_results;
+};
+
+static struct bench_local_storage_create *skel;
+static struct thread *threads;
+static long create_owner_errs;
+static int storage_type = BPF_MAP_TYPE_SK_STORAGE;
+static int batch_sz = 32;
+
+enum {
+	ARG_BATCH_SZ = 9000,
+	ARG_STORAGE_TYPE = 9001,
+};
+
+static const struct argp_option opts[] = {
+	{ "batch-size", ARG_BATCH_SZ, "BATCH_SIZE", 0,
+	  "The number of storage creations in each batch" },
+	{ "storage-type", ARG_STORAGE_TYPE, "STORAGE_TYPE", 0,
+	  "The type of local storage to test (socket or task)" },
+	{},
+};
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+	int ret;
+
+	switch (key) {
+	case ARG_BATCH_SZ:
+		ret = atoi(arg);
+		if (ret < 1) {
+			fprintf(stderr, "invalid batch-size\n");
+			argp_usage(state);
+		}
+		batch_sz = ret;
+		break;
+	case ARG_STORAGE_TYPE:
+		if (!strcmp(arg, "task")) {
+			storage_type = BPF_MAP_TYPE_TASK_STORAGE;
+		} else if (!strcmp(arg, "socket")) {
+			storage_type = BPF_MAP_TYPE_SK_STORAGE;
+		} else {
+			fprintf(stderr, "invalid storage-type (socket or task)\n");
+			argp_usage(state);
+		}
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+
+	return 0;
+}
+
+const struct argp bench_local_storage_create_argp = {
+	.options = opts,
+	.parser = parse_arg,
+};
+
+static void validate(void)
+{
+	if (env.consumer_cnt != 0) {
+		fprintf(stderr,
+			"local-storage-create benchmark does not need consumer\n");
+		exit(1);
+	}
+}
+
+static void setup(void)
+{
+	int i;
+
+	skel = bench_local_storage_create__open_and_load();
+	if (!skel) {
+		fprintf(stderr, "error loading skel\n");
+		exit(1);
+	}
+
+	skel->bss->bench_pid = getpid();
+	if (storage_type == BPF_MAP_TYPE_SK_STORAGE) {
+		if (!bpf_program__attach(skel->progs.socket_post_create)) {
+			fprintf(stderr, "Error attaching bpf program\n");
+			exit(1);
+		}
+	} else {
+		if (!bpf_program__attach(skel->progs.sched_process_fork)) {
+			fprintf(stderr, "Error attaching bpf program\n");
+			exit(1);
+		}
+	}
+
+	if (!bpf_program__attach(skel->progs.kmalloc)) {
+		fprintf(stderr, "Error attaching bpf program\n");
+		exit(1);
+	}
+
+	threads = calloc(env.producer_cnt, sizeof(*threads));
+
+	if (!threads) {
+		fprintf(stderr, "cannot alloc thread_res\n");
+		exit(1);
+	}
+
+	for (i = 0; i < env.producer_cnt; i++) {
+		struct thread *t = &threads[i];
+
+		if (storage_type == BPF_MAP_TYPE_SK_STORAGE) {
+			t->fds = malloc(batch_sz * sizeof(*t->fds));
+			if (!t->fds) {
+				fprintf(stderr, "cannot alloc t->fds\n");
+				exit(1);
+			}
+		} else {
+			t->pthds = malloc(batch_sz * sizeof(*t->pthds));
+			if (!t->pthds) {
+				fprintf(stderr, "cannot alloc t->pthds\n");
+				exit(1);
+			}
+			t->pthd_results = malloc(batch_sz * sizeof(*t->pthd_results));
+			if (!t->pthd_results) {
+				fprintf(stderr, "cannot alloc t->pthd_results\n");
+				exit(1);
+			}
+		}
+	}
+}
+
+static void measure(struct bench_res *res)
+{
+	res->hits = atomic_swap(&skel->bss->create_cnts, 0);
+	res->drops = atomic_swap(&skel->bss->kmalloc_cnts, 0);
+}
+
+static void *sk_producer(void *input)
+{
+	struct thread *t = &threads[(long)(input)];
+	int *fds = t->fds;
+	int i;
+
+	while (true) {
+		for (i = 0; i < batch_sz; i++) {
+			fds[i] = socket(AF_INET6, SOCK_DGRAM, 0);
+			if (fds[i] == -1)
+				atomic_inc(&create_owner_errs);
+		}
+
+		for (i = 0; i < batch_sz; i++) {
+			if (fds[i] != -1)
+				close(fds[i]);
+		}
+	}
+
+	return NULL;
+}
+
+static void *thread_func(void *arg)
+{
+	return NULL;
+}
+
+static void *task_producer(void *input)
+{
+	struct thread *t = &threads[(long)(input)];
+	pthread_t *pthds = t->pthds;
+	int *pthd_results = t->pthd_results;
+	int i;
+
+	while (true) {
+		for (i = 0; i < batch_sz; i++) {
+			pthd_results[i] = pthread_create(&pthds[i], NULL, thread_func, NULL);
+			if (pthd_results[i])
+				atomic_inc(&create_owner_errs);
+		}
+
+		for (i = 0; i < batch_sz; i++) {
+			if (!pthd_results[i])
+				pthread_join(pthds[i], NULL);
+		}
+	}
+
+	return NULL;
+}
+
+static void *producer(void *input)
+{
+	if (storage_type == BPF_MAP_TYPE_SK_STORAGE)
+		return sk_producer(input);
+	else
+		return task_producer(input);
+}
+
+static void report_progress(int iter, struct bench_res *res, long delta_ns)
+{
+	double creates_per_sec, kmallocs_per_create;
+
+	creates_per_sec = res->hits / 1000.0 / (delta_ns / 1000000000.0);
+	kmallocs_per_create = (double)res->drops / res->hits;
+
+	printf("Iter %3d (%7.3lfus): ",
+	       iter, (delta_ns - 1000000000) / 1000.0);
+	printf("creates %8.3lfk/s (%7.3lfk/prod), ",
+	       creates_per_sec, creates_per_sec / env.producer_cnt);
+	printf("%3.2lf kmallocs/create\n", kmallocs_per_create);
+}
+
+static void report_final(struct bench_res res[], int res_cnt)
+{
+	double creates_mean = 0.0, creates_stddev = 0.0;
+	long total_creates = 0, total_kmallocs = 0;
+	int i;
+
+	for (i = 0; i < res_cnt; i++) {
+		creates_mean += res[i].hits / 1000.0 / (0.0 + res_cnt);
+		total_creates += res[i].hits;
+		total_kmallocs += res[i].drops;
+	}
+
+	if (res_cnt > 1)  {
+		for (i = 0; i < res_cnt; i++)
+			creates_stddev += (creates_mean - res[i].hits / 1000.0) *
+				       (creates_mean - res[i].hits / 1000.0) /
+				       (res_cnt - 1.0);
+		creates_stddev = sqrt(creates_stddev);
+	}
+	printf("Summary: creates %8.3lf \u00B1 %5.3lfk/s (%7.3lfk/prod), ",
+	       creates_mean, creates_stddev, creates_mean / env.producer_cnt);
+	printf("%4.2lf kmallocs/create\n", (double)total_kmallocs / total_creates);
+	if (create_owner_errs || skel->bss->create_errs)
+		printf("%s() errors %ld create_errs %ld\n",
+		       storage_type == BPF_MAP_TYPE_SK_STORAGE ?
+		       "socket" : "pthread_create",
+		       create_owner_errs,
+		       skel->bss->create_errs);
+}
+
+/* Benchmark performance of creating bpf local storage  */
+const struct bench bench_local_storage_create = {
+	.name = "local-storage-create",
+	.argp = &bench_local_storage_create_argp,
+	.validate = validate,
+	.setup = setup,
+	.producer_thread = producer,
+	.measure = measure,
+	.report_progress = report_progress,
+	.report_final = report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/bench_local_storage_rcu_tasks_trace.c b/tools/testing/selftests/bpf/benchs/bench_local_storage_rcu_tasks_trace.c
index 43f109d93130..edf0b00418c1 100644
--- a/tools/testing/selftests/bpf/benchs/bench_local_storage_rcu_tasks_trace.c
+++ b/tools/testing/selftests/bpf/benchs/bench_local_storage_rcu_tasks_trace.c
@@ -12,17 +12,14 @@
 static struct {
 	__u32 nr_procs;
 	__u32 kthread_pid;
-	bool quiet;
 } args = {
 	.nr_procs = 1000,
 	.kthread_pid = 0,
-	.quiet = false,
 };
 
 enum {
 	ARG_NR_PROCS = 7000,
 	ARG_KTHREAD_PID = 7001,
-	ARG_QUIET = 7002,
 };
 
 static const struct argp_option opts[] = {
@@ -30,8 +27,6 @@ static const struct argp_option opts[] = {
 		"Set number of user processes to spin up"},
 	{ "kthread_pid", ARG_KTHREAD_PID, "PID", 0,
 		"Pid of rcu_tasks_trace kthread for ticks tracking"},
-	{ "quiet", ARG_QUIET, "{0,1}", 0,
-		"If true, don't report progress"},
 	{},
 };
 
@@ -56,14 +51,6 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 		}
 		args.kthread_pid = ret;
 		break;
-	case ARG_QUIET:
-		ret = strtol(arg, NULL, 10);
-		if (ret < 0 || ret > 1) {
-			fprintf(stderr, "invalid quiet %ld\n", ret);
-			argp_usage(state);
-		}
-		args.quiet = ret;
-		break;
 break;
 	default:
 		return ARGP_ERR_UNKNOWN;
@@ -85,8 +72,8 @@ static void validate(void)
 		fprintf(stderr, "benchmark doesn't support multi-producer!\n");
 		exit(1);
 	}
-	if (env.consumer_cnt != 1) {
-		fprintf(stderr, "benchmark doesn't support multi-consumer!\n");
+	if (env.consumer_cnt != 0) {
+		fprintf(stderr, "benchmark doesn't support consumer!\n");
 		exit(1);
 	}
 
@@ -210,11 +197,6 @@ static void measure(struct bench_res *res)
 	ctx.prev_kthread_stime = ticks;
 }
 
-static void *consumer(void *input)
-{
-	return NULL;
-}
-
 static void *producer(void *input)
 {
 	while (true)
@@ -230,7 +212,7 @@ static void report_progress(int iter, struct bench_res *res, long delta_ns)
 		exit(1);
 	}
 
-	if (args.quiet)
+	if (env.quiet)
 		return;
 
 	printf("Iter %d\t avg tasks_trace grace period latency\t%lf ns\n",
@@ -271,10 +253,10 @@ static void report_final(struct bench_res res[], int res_cnt)
  */
 const struct bench bench_local_storage_tasks_trace = {
 	.name = "local-storage-tasks-trace",
+	.argp = &bench_local_storage_rcu_tasks_trace_argp,
 	.validate = validate,
 	.setup = local_storage_tasks_trace_setup,
 	.producer_thread = producer,
-	.consumer_thread = consumer,
 	.measure = measure,
 	.report_progress = report_progress,
 	.report_final = report_final,
diff --git a/tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c b/tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c
new file mode 100644
index 000000000000..246f6cb3387d
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c
@@ -0,0 +1,555 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Cloudflare */
+
+/*
+ * All of these benchmarks operate on tries with keys in the range
+ * [0, args.nr_entries), i.e. there are no gaps or partially filled
+ * branches of the trie for any key < args.nr_entries.
+ *
+ * This gives an idea of worst-case behaviour.
+ */
+
+#include <argp.h>
+#include <linux/time64.h>
+#include <linux/if_ether.h>
+#include "lpm_trie_bench.skel.h"
+#include "lpm_trie_map.skel.h"
+#include "bench.h"
+#include "testing_helpers.h"
+#include "progs/lpm_trie.h"
+
+static struct ctx {
+	struct lpm_trie_bench *bench;
+} ctx;
+
+static struct {
+	__u32 nr_entries;
+	__u32 prefixlen;
+	bool random;
+} args = {
+	.nr_entries = 0,
+	.prefixlen = 32,
+	.random = false,
+};
+
+enum {
+	ARG_NR_ENTRIES = 9000,
+	ARG_PREFIX_LEN,
+	ARG_RANDOM,
+};
+
+static const struct argp_option opts[] = {
+	{ "nr_entries", ARG_NR_ENTRIES, "NR_ENTRIES", 0,
+	  "Number of unique entries in the LPM trie" },
+	{ "prefix_len", ARG_PREFIX_LEN, "PREFIX_LEN", 0,
+	  "Number of prefix bits to use in the LPM trie" },
+	{ "random", ARG_RANDOM, NULL, 0, "Access random keys during op" },
+	{},
+};
+
+static error_t lpm_parse_arg(int key, char *arg, struct argp_state *state)
+{
+	long ret;
+
+	switch (key) {
+	case ARG_NR_ENTRIES:
+		ret = strtol(arg, NULL, 10);
+		if (ret < 1 || ret > UINT_MAX) {
+			fprintf(stderr, "Invalid nr_entries count.");
+			argp_usage(state);
+		}
+		args.nr_entries = ret;
+		break;
+	case ARG_PREFIX_LEN:
+		ret = strtol(arg, NULL, 10);
+		if (ret < 1 || ret > UINT_MAX) {
+			fprintf(stderr, "Invalid prefix_len value.");
+			argp_usage(state);
+		}
+		args.prefixlen = ret;
+		break;
+	case ARG_RANDOM:
+		args.random = true;
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+	return 0;
+}
+
+const struct argp bench_lpm_trie_map_argp = {
+	.options = opts,
+	.parser = lpm_parse_arg,
+};
+
+static void validate_common(void)
+{
+	if (env.consumer_cnt != 0) {
+		fprintf(stderr, "benchmark doesn't support consumer\n");
+		exit(1);
+	}
+
+	if (args.nr_entries == 0) {
+		fprintf(stderr, "Missing --nr_entries parameter\n");
+		exit(1);
+	}
+
+	if ((1UL << args.prefixlen) < args.nr_entries) {
+		fprintf(stderr, "prefix_len value too small for nr_entries\n");
+		exit(1);
+	}
+}
+
+static void lpm_insert_validate(void)
+{
+	validate_common();
+
+	if (env.producer_cnt != 1) {
+		fprintf(stderr, "lpm-trie-insert requires a single producer\n");
+		exit(1);
+	}
+
+	if (args.random) {
+		fprintf(stderr, "lpm-trie-insert does not support --random\n");
+		exit(1);
+	}
+}
+
+static void lpm_delete_validate(void)
+{
+	validate_common();
+
+	if (env.producer_cnt != 1) {
+		fprintf(stderr, "lpm-trie-delete requires a single producer\n");
+		exit(1);
+	}
+
+	if (args.random) {
+		fprintf(stderr, "lpm-trie-delete does not support --random\n");
+		exit(1);
+	}
+}
+
+static void lpm_free_validate(void)
+{
+	validate_common();
+
+	if (env.producer_cnt != 1) {
+		fprintf(stderr, "lpm-trie-free requires a single producer\n");
+		exit(1);
+	}
+
+	if (args.random) {
+		fprintf(stderr, "lpm-trie-free does not support --random\n");
+		exit(1);
+	}
+}
+
+static struct trie_key *keys;
+static __u32 *vals;
+
+static void fill_map(int map_fd)
+{
+	int err;
+
+	DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+		.elem_flags = 0,
+		.flags = 0,
+	);
+
+	err = bpf_map_update_batch(map_fd, keys, vals, &args.nr_entries, &opts);
+	if (err) {
+		fprintf(stderr, "failed to batch update keys to map: %d\n",
+			-err);
+		exit(1);
+	}
+}
+
+static void empty_map(int map_fd)
+{
+	int err;
+
+	DECLARE_LIBBPF_OPTS(bpf_map_batch_opts, opts,
+		.elem_flags = 0,
+		.flags = 0,
+	);
+
+	err = bpf_map_delete_batch(map_fd, keys, &args.nr_entries, &opts);
+	if (err) {
+		fprintf(stderr, "failed to batch delete keys for map: %d\n",
+			-err);
+		exit(1);
+	}
+}
+
+static void attach_prog(void)
+{
+	int i;
+
+	ctx.bench = lpm_trie_bench__open_and_load();
+	if (!ctx.bench) {
+		fprintf(stderr, "failed to open skeleton\n");
+		exit(1);
+	}
+
+	ctx.bench->bss->nr_entries = args.nr_entries;
+	ctx.bench->bss->prefixlen = args.prefixlen;
+	ctx.bench->bss->random = args.random;
+
+	if (lpm_trie_bench__attach(ctx.bench)) {
+		fprintf(stderr, "failed to attach skeleton\n");
+		exit(1);
+	}
+
+	keys = calloc(args.nr_entries, sizeof(*keys));
+	vals = calloc(args.nr_entries, sizeof(*vals));
+
+	for (i = 0; i < args.nr_entries; i++) {
+		struct trie_key *k = &keys[i];
+		__u32 *v = &vals[i];
+
+		k->prefixlen = args.prefixlen;
+		k->data = i;
+		*v = 1;
+	}
+}
+
+static void attach_prog_and_fill_map(void)
+{
+	int fd;
+
+	attach_prog();
+
+	fd = bpf_map__fd(ctx.bench->maps.trie_map);
+	fill_map(fd);
+}
+
+static void lpm_noop_setup(void)
+{
+	attach_prog();
+	ctx.bench->bss->op = LPM_OP_NOOP;
+}
+
+static void lpm_baseline_setup(void)
+{
+	attach_prog();
+	ctx.bench->bss->op = LPM_OP_BASELINE;
+}
+
+static void lpm_lookup_setup(void)
+{
+	attach_prog_and_fill_map();
+	ctx.bench->bss->op = LPM_OP_LOOKUP;
+}
+
+static void lpm_insert_setup(void)
+{
+	attach_prog();
+	ctx.bench->bss->op = LPM_OP_INSERT;
+}
+
+static void lpm_update_setup(void)
+{
+	attach_prog_and_fill_map();
+	ctx.bench->bss->op = LPM_OP_UPDATE;
+}
+
+static void lpm_delete_setup(void)
+{
+	attach_prog_and_fill_map();
+	ctx.bench->bss->op = LPM_OP_DELETE;
+}
+
+static void lpm_free_setup(void)
+{
+	attach_prog();
+	ctx.bench->bss->op = LPM_OP_FREE;
+}
+
+static void lpm_measure(struct bench_res *res)
+{
+	res->hits = atomic_swap(&ctx.bench->bss->hits, 0);
+	res->duration_ns = atomic_swap(&ctx.bench->bss->duration_ns, 0);
+}
+
+static void bench_reinit_map(void)
+{
+	int fd = bpf_map__fd(ctx.bench->maps.trie_map);
+
+	switch (ctx.bench->bss->op) {
+	case LPM_OP_INSERT:
+		/* trie_map needs to be emptied */
+		empty_map(fd);
+		break;
+	case LPM_OP_DELETE:
+		/* trie_map needs to be refilled */
+		fill_map(fd);
+		break;
+	default:
+		fprintf(stderr, "Unexpected REINIT return code for op %d\n",
+				ctx.bench->bss->op);
+		exit(1);
+	}
+}
+
+/* For NOOP, BASELINE, LOOKUP, INSERT, UPDATE, and DELETE */
+static void *lpm_producer(void *unused __always_unused)
+{
+	int err;
+	char in[ETH_HLEN]; /* unused */
+
+	LIBBPF_OPTS(bpf_test_run_opts, opts, .data_in = in,
+		    .data_size_in = sizeof(in), .repeat = 1, );
+
+	while (true) {
+		int fd = bpf_program__fd(ctx.bench->progs.run_bench);
+		err = bpf_prog_test_run_opts(fd, &opts);
+		if (err) {
+			fprintf(stderr, "failed to run BPF prog: %d\n", err);
+			exit(1);
+		}
+
+		/* Check for kernel error code */
+		if ((int)opts.retval < 0) {
+			fprintf(stderr, "BPF prog returned error: %d\n",
+				opts.retval);
+			exit(1);
+		}
+
+		switch (opts.retval) {
+		case LPM_BENCH_SUCCESS:
+			break;
+		case LPM_BENCH_REINIT_MAP:
+			bench_reinit_map();
+			break;
+		default:
+			fprintf(stderr, "Unexpected BPF prog return code %d for op %d\n",
+					opts.retval, ctx.bench->bss->op);
+			exit(1);
+		}
+	}
+
+	return NULL;
+}
+
+static void *lpm_free_producer(void *unused __always_unused)
+{
+	while (true) {
+		struct lpm_trie_map *skel;
+
+		skel = lpm_trie_map__open_and_load();
+		if (!skel) {
+			fprintf(stderr, "failed to open skeleton\n");
+			exit(1);
+		}
+
+		fill_map(bpf_map__fd(skel->maps.trie_free_map));
+		lpm_trie_map__destroy(skel);
+	}
+
+	return NULL;
+}
+
+/*
+ * The standard bench op_report_*() functions assume measurements are
+ * taken over a 1-second interval but operations that modify the map
+ * (INSERT, DELETE, and FREE) cannot run indefinitely without
+ * "resetting" the map to the initial state. Depending on the size of
+ * the map, this likely needs to happen before the 1-second timer fires.
+ *
+ * Calculate the fraction of a second over which the op measurement was
+ * taken (to ignore any time spent doing the reset) and report the
+ * throughput results per second.
+ */
+static void frac_second_report_progress(int iter, struct bench_res *res,
+					long delta_ns, double rate_divisor,
+					char rate)
+{
+	double hits_per_sec, hits_per_prod;
+
+	hits_per_sec = res->hits / rate_divisor /
+		(res->duration_ns / (double)NSEC_PER_SEC);
+	hits_per_prod = hits_per_sec / env.producer_cnt;
+
+	printf("Iter %3d (%7.3lfus): ", iter,
+	       (delta_ns - NSEC_PER_SEC) / 1000.0);
+	printf("hits %8.3lf%c/s (%7.3lf%c/prod)\n", hits_per_sec, rate,
+	       hits_per_prod, rate);
+}
+
+static void frac_second_report_final(struct bench_res res[], int res_cnt,
+				     double lat_divisor, double rate_divisor,
+				     char rate, const char *unit)
+{
+	double hits_mean = 0.0, hits_stddev = 0.0;
+	double latency = 0.0;
+	int i;
+
+	for (i = 0; i < res_cnt; i++) {
+		double val = res[i].hits / rate_divisor /
+			     (res[i].duration_ns / (double)NSEC_PER_SEC);
+		hits_mean += val / (0.0 + res_cnt);
+		latency += res[i].duration_ns / res[i].hits / (0.0 + res_cnt);
+	}
+
+	if (res_cnt > 1) {
+		for (i = 0; i < res_cnt; i++) {
+			double val =
+				res[i].hits / rate_divisor /
+				(res[i].duration_ns / (double)NSEC_PER_SEC);
+			hits_stddev += (hits_mean - val) * (hits_mean - val) /
+				       (res_cnt - 1.0);
+		}
+
+		hits_stddev = sqrt(hits_stddev);
+	}
+	printf("Summary: throughput %8.3lf \u00B1 %5.3lf %c ops/s (%7.3lf%c ops/prod), ",
+	       hits_mean, hits_stddev, rate, hits_mean / env.producer_cnt,
+	       rate);
+	printf("latency %8.3lf %s/op\n",
+	       latency / lat_divisor / env.producer_cnt, unit);
+}
+
+static void insert_ops_report_progress(int iter, struct bench_res *res,
+				       long delta_ns)
+{
+	double rate_divisor = 1000000.0;
+	char rate = 'M';
+
+	frac_second_report_progress(iter, res, delta_ns, rate_divisor, rate);
+}
+
+static void delete_ops_report_progress(int iter, struct bench_res *res,
+				       long delta_ns)
+{
+	double rate_divisor = 1000000.0;
+	char rate = 'M';
+
+	frac_second_report_progress(iter, res, delta_ns, rate_divisor, rate);
+}
+
+static void free_ops_report_progress(int iter, struct bench_res *res,
+				     long delta_ns)
+{
+	double rate_divisor = 1000.0;
+	char rate = 'K';
+
+	frac_second_report_progress(iter, res, delta_ns, rate_divisor, rate);
+}
+
+static void insert_ops_report_final(struct bench_res res[], int res_cnt)
+{
+	double lat_divisor = 1.0;
+	double rate_divisor = 1000000.0;
+	const char *unit = "ns";
+	char rate = 'M';
+
+	frac_second_report_final(res, res_cnt, lat_divisor, rate_divisor, rate,
+				 unit);
+}
+
+static void delete_ops_report_final(struct bench_res res[], int res_cnt)
+{
+	double lat_divisor = 1.0;
+	double rate_divisor = 1000000.0;
+	const char *unit = "ns";
+	char rate = 'M';
+
+	frac_second_report_final(res, res_cnt, lat_divisor, rate_divisor, rate,
+				 unit);
+}
+
+static void free_ops_report_final(struct bench_res res[], int res_cnt)
+{
+	double lat_divisor = 1000000.0;
+	double rate_divisor = 1000.0;
+	const char *unit = "ms";
+	char rate = 'K';
+
+	frac_second_report_final(res, res_cnt, lat_divisor, rate_divisor, rate,
+				 unit);
+}
+
+/* noop bench measures harness-overhead */
+const struct bench bench_lpm_trie_noop = {
+	.name = "lpm-trie-noop",
+	.argp = &bench_lpm_trie_map_argp,
+	.validate = validate_common,
+	.setup = lpm_noop_setup,
+	.producer_thread = lpm_producer,
+	.measure = lpm_measure,
+	.report_progress = ops_report_progress,
+	.report_final = ops_report_final,
+};
+
+/* baseline overhead for lookup and update */
+const struct bench bench_lpm_trie_baseline = {
+	.name = "lpm-trie-baseline",
+	.argp = &bench_lpm_trie_map_argp,
+	.validate = validate_common,
+	.setup = lpm_baseline_setup,
+	.producer_thread = lpm_producer,
+	.measure = lpm_measure,
+	.report_progress = ops_report_progress,
+	.report_final = ops_report_final,
+};
+
+/* measure cost of doing a lookup on existing entries in a full trie */
+const struct bench bench_lpm_trie_lookup = {
+	.name = "lpm-trie-lookup",
+	.argp = &bench_lpm_trie_map_argp,
+	.validate = validate_common,
+	.setup = lpm_lookup_setup,
+	.producer_thread = lpm_producer,
+	.measure = lpm_measure,
+	.report_progress = ops_report_progress,
+	.report_final = ops_report_final,
+};
+
+/* measure cost of inserting new entries into an empty trie */
+const struct bench bench_lpm_trie_insert = {
+	.name = "lpm-trie-insert",
+	.argp = &bench_lpm_trie_map_argp,
+	.validate = lpm_insert_validate,
+	.setup = lpm_insert_setup,
+	.producer_thread = lpm_producer,
+	.measure = lpm_measure,
+	.report_progress = insert_ops_report_progress,
+	.report_final = insert_ops_report_final,
+};
+
+/* measure cost of updating existing entries in a full trie */
+const struct bench bench_lpm_trie_update = {
+	.name = "lpm-trie-update",
+	.argp = &bench_lpm_trie_map_argp,
+	.validate = validate_common,
+	.setup = lpm_update_setup,
+	.producer_thread = lpm_producer,
+	.measure = lpm_measure,
+	.report_progress = ops_report_progress,
+	.report_final = ops_report_final,
+};
+
+/* measure cost of deleting existing entries from a full trie */
+const struct bench bench_lpm_trie_delete = {
+	.name = "lpm-trie-delete",
+	.argp = &bench_lpm_trie_map_argp,
+	.validate = lpm_delete_validate,
+	.setup = lpm_delete_setup,
+	.producer_thread = lpm_producer,
+	.measure = lpm_measure,
+	.report_progress = delete_ops_report_progress,
+	.report_final = delete_ops_report_final,
+};
+
+/* measure cost of freeing a full trie */
+const struct bench bench_lpm_trie_free = {
+	.name = "lpm-trie-free",
+	.argp = &bench_lpm_trie_map_argp,
+	.validate = lpm_free_validate,
+	.setup = lpm_free_setup,
+	.producer_thread = lpm_free_producer,
+	.measure = lpm_measure,
+	.report_progress = free_ops_report_progress,
+	.report_final = free_ops_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/bench_rename.c b/tools/testing/selftests/bpf/benchs/bench_rename.c
index 3c203b6d6a6e..bf66893c7a33 100644
--- a/tools/testing/selftests/bpf/benchs/bench_rename.c
+++ b/tools/testing/selftests/bpf/benchs/bench_rename.c
@@ -17,8 +17,8 @@ static void validate(void)
 		fprintf(stderr, "benchmark doesn't support multi-producer!\n");
 		exit(1);
 	}
-	if (env.consumer_cnt != 1) {
-		fprintf(stderr, "benchmark doesn't support multi-consumer!\n");
+	if (env.consumer_cnt != 0) {
+		fprintf(stderr, "benchmark doesn't support consumer!\n");
 		exit(1);
 	}
 }
@@ -106,17 +106,11 @@ static void setup_fexit(void)
 	attach_bpf(ctx.skel->progs.prog5);
 }
 
-static void *consumer(void *input)
-{
-	return NULL;
-}
-
 const struct bench bench_rename_base = {
 	.name = "rename-base",
 	.validate = validate,
 	.setup = setup_base,
 	.producer_thread = producer,
-	.consumer_thread = consumer,
 	.measure = measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
@@ -127,7 +121,6 @@ const struct bench bench_rename_kprobe = {
 	.validate = validate,
 	.setup = setup_kprobe,
 	.producer_thread = producer,
-	.consumer_thread = consumer,
 	.measure = measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
@@ -138,7 +131,6 @@ const struct bench bench_rename_kretprobe = {
 	.validate = validate,
 	.setup = setup_kretprobe,
 	.producer_thread = producer,
-	.consumer_thread = consumer,
 	.measure = measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
@@ -149,7 +141,6 @@ const struct bench bench_rename_rawtp = {
 	.validate = validate,
 	.setup = setup_rawtp,
 	.producer_thread = producer,
-	.consumer_thread = consumer,
 	.measure = measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
@@ -160,7 +151,6 @@ const struct bench bench_rename_fentry = {
 	.validate = validate,
 	.setup = setup_fentry,
 	.producer_thread = producer,
-	.consumer_thread = consumer,
 	.measure = measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
@@ -171,7 +161,6 @@ const struct bench bench_rename_fexit = {
 	.validate = validate,
 	.setup = setup_fexit,
 	.producer_thread = producer,
-	.consumer_thread = consumer,
 	.measure = measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
index c2554f9695ff..01bdce692799 100644
--- a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
+++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
@@ -19,6 +19,8 @@ static struct {
 	int ringbuf_sz; /* per-ringbuf, in bytes */
 	bool ringbuf_use_output; /* use slower output API */
 	int perfbuf_sz; /* per-CPU size, in pages */
+	bool overwrite;
+	bool bench_producer;
 } args = {
 	.back2back = false,
 	.batch_cnt = 500,
@@ -27,6 +29,8 @@ static struct {
 	.ringbuf_sz = 512 * 1024,
 	.ringbuf_use_output = false,
 	.perfbuf_sz = 128,
+	.overwrite = false,
+	.bench_producer = false,
 };
 
 enum {
@@ -35,6 +39,8 @@ enum {
 	ARG_RB_BATCH_CNT = 2002,
 	ARG_RB_SAMPLED = 2003,
 	ARG_RB_SAMPLE_RATE = 2004,
+	ARG_RB_OVERWRITE = 2005,
+	ARG_RB_BENCH_PRODUCER = 2006,
 };
 
 static const struct argp_option opts[] = {
@@ -43,6 +49,8 @@ static const struct argp_option opts[] = {
 	{ "rb-batch-cnt", ARG_RB_BATCH_CNT, "CNT", 0, "Set BPF-side record batch count"},
 	{ "rb-sampled", ARG_RB_SAMPLED, NULL, 0, "Notification sampling"},
 	{ "rb-sample-rate", ARG_RB_SAMPLE_RATE, "RATE", 0, "Notification sample rate"},
+	{ "rb-overwrite", ARG_RB_OVERWRITE, NULL, 0, "Overwrite mode"},
+	{ "rb-bench-producer", ARG_RB_BENCH_PRODUCER, NULL, 0, "Benchmark producer"},
 	{},
 };
 
@@ -72,6 +80,12 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 			argp_usage(state);
 		}
 		break;
+	case ARG_RB_OVERWRITE:
+		args.overwrite = true;
+		break;
+	case ARG_RB_BENCH_PRODUCER:
+		args.bench_producer = true;
+		break;
 	default:
 		return ARGP_ERR_UNKNOWN;
 	}
@@ -95,8 +109,33 @@ static inline void bufs_trigger_batch(void)
 
 static void bufs_validate(void)
 {
-	if (env.consumer_cnt != 1) {
-		fprintf(stderr, "rb-libbpf benchmark doesn't support multi-consumer!\n");
+	if (args.bench_producer && strcmp(env.bench_name, "rb-libbpf")) {
+		fprintf(stderr, "--rb-bench-producer only works with rb-libbpf!\n");
+		exit(1);
+	}
+
+	if (args.overwrite && !args.bench_producer) {
+		fprintf(stderr, "overwrite mode only works with --rb-bench-producer for now!\n");
+		exit(1);
+	}
+
+	if (args.bench_producer && env.consumer_cnt != 0) {
+		fprintf(stderr, "no consumer is needed for --rb-bench-producer!\n");
+		exit(1);
+	}
+
+	if (args.bench_producer && args.back2back) {
+		fprintf(stderr, "back-to-back mode makes no sense for --rb-bench-producer!\n");
+		exit(1);
+	}
+
+	if (args.bench_producer && args.sampled) {
+		fprintf(stderr, "sampling mode makes no sense for --rb-bench-producer!\n");
+		exit(1);
+	}
+
+	if (!args.bench_producer && env.consumer_cnt != 1) {
+		fprintf(stderr, "benchmarks without --rb-bench-producer require exactly one consumer!\n");
 		exit(1);
 	}
 
@@ -128,12 +167,17 @@ static void ringbuf_libbpf_measure(struct bench_res *res)
 {
 	struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx;
 
-	res->hits = atomic_swap(&buf_hits.value, 0);
+	if (args.bench_producer)
+		res->hits = atomic_swap(&ctx->skel->bss->hits, 0);
+	else
+		res->hits = atomic_swap(&buf_hits.value, 0);
 	res->drops = atomic_swap(&ctx->skel->bss->dropped, 0);
 }
 
 static struct ringbuf_bench *ringbuf_setup_skeleton(void)
 {
+	__u32 flags;
+	struct bpf_map *ringbuf;
 	struct ringbuf_bench *skel;
 
 	setup_libbpf();
@@ -146,12 +190,19 @@ static struct ringbuf_bench *ringbuf_setup_skeleton(void)
 
 	skel->rodata->batch_cnt = args.batch_cnt;
 	skel->rodata->use_output = args.ringbuf_use_output ? 1 : 0;
+	skel->rodata->bench_producer = args.bench_producer;
 
 	if (args.sampled)
 		/* record data + header take 16 bytes */
 		skel->rodata->wakeup_data_size = args.sample_rate * 16;
 
-	bpf_map__set_max_entries(skel->maps.ringbuf, args.ringbuf_sz);
+	ringbuf = skel->maps.ringbuf;
+	if (args.overwrite) {
+		flags = bpf_map__map_flags(ringbuf) | BPF_F_RB_OVERWRITE;
+		bpf_map__set_map_flags(ringbuf, flags);
+	}
+
+	bpf_map__set_max_entries(ringbuf, args.ringbuf_sz);
 
 	if (ringbuf_bench__load(skel)) {
 		fprintf(stderr, "failed to load skeleton\n");
@@ -171,10 +222,12 @@ static void ringbuf_libbpf_setup(void)
 {
 	struct ringbuf_libbpf_ctx *ctx = &ringbuf_libbpf_ctx;
 	struct bpf_link *link;
+	int map_fd;
 
 	ctx->skel = ringbuf_setup_skeleton();
-	ctx->ringbuf = ring_buffer__new(bpf_map__fd(ctx->skel->maps.ringbuf),
-					buf_process_sample, NULL, NULL);
+
+	map_fd = bpf_map__fd(ctx->skel->maps.ringbuf);
+	ctx->ringbuf = ring_buffer__new(map_fd, buf_process_sample, NULL, NULL);
 	if (!ctx->ringbuf) {
 		fprintf(stderr, "failed to create ringbuf\n");
 		exit(1);
@@ -399,7 +452,7 @@ static void perfbuf_libbpf_setup(void)
 	ctx->skel = perfbuf_setup_skeleton();
 
 	memset(&attr, 0, sizeof(attr));
-	attr.config = PERF_COUNT_SW_BPF_OUTPUT,
+	attr.config = PERF_COUNT_SW_BPF_OUTPUT;
 	attr.type = PERF_TYPE_SOFTWARE;
 	attr.sample_type = PERF_SAMPLE_RAW;
 	/* notify only every Nth sample */
@@ -518,6 +571,7 @@ static void *perfbuf_custom_consumer(void *input)
 
 const struct bench bench_rb_libbpf = {
 	.name = "rb-libbpf",
+	.argp = &bench_ringbufs_argp,
 	.validate = bufs_validate,
 	.setup = ringbuf_libbpf_setup,
 	.producer_thread = bufs_sample_producer,
@@ -529,6 +583,7 @@ const struct bench bench_rb_libbpf = {
 
 const struct bench bench_rb_custom = {
 	.name = "rb-custom",
+	.argp = &bench_ringbufs_argp,
 	.validate = bufs_validate,
 	.setup = ringbuf_custom_setup,
 	.producer_thread = bufs_sample_producer,
@@ -540,6 +595,7 @@ const struct bench bench_rb_custom = {
 
 const struct bench bench_pb_libbpf = {
 	.name = "pb-libbpf",
+	.argp = &bench_ringbufs_argp,
 	.validate = bufs_validate,
 	.setup = perfbuf_libbpf_setup,
 	.producer_thread = bufs_sample_producer,
@@ -551,6 +607,7 @@ const struct bench bench_pb_libbpf = {
 
 const struct bench bench_pb_custom = {
 	.name = "pb-custom",
+	.argp = &bench_ringbufs_argp,
 	.validate = bufs_validate,
 	.setup = perfbuf_libbpf_setup,
 	.producer_thread = bufs_sample_producer,
diff --git a/tools/testing/selftests/bpf/benchs/bench_sockmap.c b/tools/testing/selftests/bpf/benchs/bench_sockmap.c
new file mode 100644
index 000000000000..cfc072aa7fff
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_sockmap.c
@@ -0,0 +1,599 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <error.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <sys/sendfile.h>
+#include <arpa/inet.h>
+#include <fcntl.h>
+#include <argp.h>
+#include "bench.h"
+#include "bench_sockmap_prog.skel.h"
+#include "bpf_util.h"
+
+#define FILE_SIZE (128 * 1024)
+#define DATA_REPEAT_SIZE 10
+
+static const char snd_data[DATA_REPEAT_SIZE] = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9};
+
+/* c1 <-> [p1, p2] <-> c2
+ * RX bench(BPF_SK_SKB_STREAM_VERDICT):
+ *	ARG_FW_RX_PASS:
+ *		send(p2) -> recv(c2) -> bpf skb passthrough -> recv(c2)
+ *	ARG_FW_RX_VERDICT_EGRESS:
+ *		send(c1) -> verdict skb to tx queuec of p2 -> recv(c2)
+ *	ARG_FW_RX_VERDICT_INGRESS:
+ *		send(c1) -> verdict skb to rx queuec of c2 -> recv(c2)
+ *
+ * TX bench(BPF_SK_MSG_VERDIC):
+ *	ARG_FW_TX_PASS:
+ *		send(p2) -> bpf msg passthrough -> send(p2) -> recv(c2)
+ *	ARG_FW_TX_VERDICT_INGRESS:
+ *		send(p2) -> verdict msg to rx queue of c2 -> recv(c2)
+ *	ARG_FW_TX_VERDICT_EGRESS:
+ *		send(p1) -> verdict msg to tx queue of p2 -> recv(c2)
+ */
+enum SOCKMAP_ARG_FLAG {
+	ARG_FW_RX_NORMAL = 11000,
+	ARG_FW_RX_PASS,
+	ARG_FW_RX_VERDICT_EGRESS,
+	ARG_FW_RX_VERDICT_INGRESS,
+	ARG_FW_TX_NORMAL,
+	ARG_FW_TX_PASS,
+	ARG_FW_TX_VERDICT_INGRESS,
+	ARG_FW_TX_VERDICT_EGRESS,
+	ARG_CTL_RX_STRP,
+	ARG_CONSUMER_DELAY_TIME,
+	ARG_PRODUCER_DURATION,
+};
+
+#define TXMODE_NORMAL()				\
+	((ctx.mode) == ARG_FW_TX_NORMAL)
+
+#define TXMODE_BPF_INGRESS()			\
+	((ctx.mode) == ARG_FW_TX_VERDICT_INGRESS)
+
+#define TXMODE_BPF_EGRESS()			\
+	((ctx.mode) == ARG_FW_TX_VERDICT_EGRESS)
+
+#define TXMODE_BPF_PASS()			\
+	((ctx.mode) == ARG_FW_TX_PASS)
+
+#define TXMODE_BPF() (				\
+	TXMODE_BPF_PASS() ||			\
+	TXMODE_BPF_INGRESS() ||			\
+	TXMODE_BPF_EGRESS())
+
+#define TXMODE() (				\
+	TXMODE_NORMAL() ||			\
+	TXMODE_BPF())
+
+#define RXMODE_NORMAL()				\
+	((ctx.mode) == ARG_FW_RX_NORMAL)
+
+#define RXMODE_BPF_PASS()			\
+	((ctx.mode) == ARG_FW_RX_PASS)
+
+#define RXMODE_BPF_VERDICT_EGRESS()		\
+	((ctx.mode) == ARG_FW_RX_VERDICT_EGRESS)
+
+#define RXMODE_BPF_VERDICT_INGRESS()		\
+	((ctx.mode) == ARG_FW_RX_VERDICT_INGRESS)
+
+#define RXMODE_BPF_VERDICT() (			\
+	RXMODE_BPF_VERDICT_INGRESS() ||		\
+	RXMODE_BPF_VERDICT_EGRESS())
+
+#define RXMODE_BPF() (				\
+	RXMODE_BPF_PASS() ||			\
+	RXMODE_BPF_VERDICT())
+
+#define RXMODE() (				\
+	RXMODE_NORMAL() ||			\
+	RXMODE_BPF())
+
+static struct socmap_ctx {
+	struct bench_sockmap_prog *skel;
+	enum SOCKMAP_ARG_FLAG mode;
+	#define c1	fds[0]
+	#define p1	fds[1]
+	#define c2	fds[2]
+	#define p2	fds[3]
+	#define sfd	fds[4]
+	int		fds[5];
+	long		send_calls;
+	long		read_calls;
+	long		prod_send;
+	long		user_read;
+	int		file_size;
+	int		delay_consumer;
+	int		prod_run_time;
+	int		strp_size;
+} ctx = {
+	.prod_send	= 0,
+	.user_read	= 0,
+	.file_size	= FILE_SIZE,
+	.mode		= ARG_FW_RX_VERDICT_EGRESS,
+	.fds		= {0},
+	.delay_consumer = 0,
+	.prod_run_time	= 0,
+	.strp_size	= 0,
+};
+
+static void bench_sockmap_prog_destroy(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(ctx.fds); i++) {
+		if (ctx.fds[i] > 0)
+			close(ctx.fds[i]);
+	}
+
+	bench_sockmap_prog__destroy(ctx.skel);
+}
+
+static void init_addr(struct sockaddr_storage *ss,
+		      socklen_t *len)
+{
+	struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss));
+
+	addr4->sin_family = AF_INET;
+	addr4->sin_port = 0;
+	addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+	*len = sizeof(*addr4);
+}
+
+static bool set_non_block(int fd, bool blocking)
+{
+	int flags = fcntl(fd, F_GETFL, 0);
+
+	if (flags == -1)
+		return false;
+	flags = blocking ? (flags | O_NONBLOCK) : (flags & ~O_NONBLOCK);
+	return (fcntl(fd, F_SETFL, flags) == 0);
+}
+
+static int create_pair(int *c, int *p, int type)
+{
+	struct sockaddr_storage addr;
+	int err, cfd, pfd;
+	socklen_t addr_len = sizeof(struct sockaddr_storage);
+
+	err = getsockname(ctx.sfd, (struct sockaddr *)&addr, &addr_len);
+	if (err) {
+		fprintf(stderr, "getsockname error %d\n", errno);
+		return err;
+	}
+	cfd = socket(AF_INET, type, 0);
+	if (cfd < 0) {
+		fprintf(stderr, "socket error %d\n", errno);
+		return err;
+	}
+
+	err = connect(cfd, (struct sockaddr *)&addr, addr_len);
+	if (err && errno != EINPROGRESS) {
+		fprintf(stderr, "connect error %d\n", errno);
+		return err;
+	}
+
+	pfd = accept(ctx.sfd, NULL, NULL);
+	if (pfd < 0) {
+		fprintf(stderr, "accept error %d\n", errno);
+		return err;
+	}
+	*c = cfd;
+	*p = pfd;
+	return 0;
+}
+
+static int create_sockets(void)
+{
+	struct sockaddr_storage addr;
+	int err, one = 1;
+	socklen_t addr_len;
+
+	init_addr(&addr, &addr_len);
+	ctx.sfd = socket(AF_INET, SOCK_STREAM, 0);
+	if (ctx.sfd < 0) {
+		fprintf(stderr, "socket error:%d\n", errno);
+		return ctx.sfd;
+	}
+	err = setsockopt(ctx.sfd, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one));
+	if (err) {
+		fprintf(stderr, "setsockopt error:%d\n", errno);
+		return err;
+	}
+
+	err = bind(ctx.sfd, (struct sockaddr *)&addr, addr_len);
+	if (err) {
+		fprintf(stderr, "bind error:%d\n", errno);
+		return err;
+	}
+
+	err = listen(ctx.sfd, SOMAXCONN);
+	if (err) {
+		fprintf(stderr, "listen error:%d\n", errno);
+		return err;
+	}
+
+	err = create_pair(&ctx.c1, &ctx.p1, SOCK_STREAM);
+	if (err) {
+		fprintf(stderr, "create_pair 1 error\n");
+		return err;
+	}
+
+	err = create_pair(&ctx.c2, &ctx.p2, SOCK_STREAM);
+	if (err) {
+		fprintf(stderr, "create_pair 2 error\n");
+		return err;
+	}
+	printf("create socket fd c1:%d p1:%d c2:%d p2:%d\n",
+	       ctx.c1, ctx.p1, ctx.c2, ctx.p2);
+	return 0;
+}
+
+static void validate(void)
+{
+	if (env.consumer_cnt != 2 || env.producer_cnt != 1 ||
+	    !env.affinity)
+		goto err;
+	return;
+err:
+	fprintf(stderr, "argument '-c 2 -p 1 -a' is necessary");
+	exit(1);
+}
+
+static int setup_rx_sockmap(void)
+{
+	int verdict, pass, parser, map;
+	int zero = 0, one = 1;
+	int err;
+
+	parser = bpf_program__fd(ctx.skel->progs.prog_skb_parser);
+	verdict = bpf_program__fd(ctx.skel->progs.prog_skb_verdict);
+	pass = bpf_program__fd(ctx.skel->progs.prog_skb_pass);
+	map = bpf_map__fd(ctx.skel->maps.sock_map_rx);
+
+	if (ctx.strp_size != 0) {
+		ctx.skel->bss->pkt_size = ctx.strp_size;
+		err = bpf_prog_attach(parser, map, BPF_SK_SKB_STREAM_PARSER, 0);
+		if (err)
+			return err;
+	}
+
+	if (RXMODE_BPF_VERDICT())
+		err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0);
+	else if (RXMODE_BPF_PASS())
+		err = bpf_prog_attach(pass, map, BPF_SK_SKB_STREAM_VERDICT, 0);
+	if (err)
+		return err;
+
+	if (RXMODE_BPF_PASS())
+		return bpf_map_update_elem(map, &zero, &ctx.c2, BPF_NOEXIST);
+
+	err = bpf_map_update_elem(map, &zero, &ctx.p1, BPF_NOEXIST);
+	if (err < 0)
+		return err;
+
+	if (RXMODE_BPF_VERDICT_INGRESS()) {
+		ctx.skel->bss->verdict_dir = BPF_F_INGRESS;
+		err = bpf_map_update_elem(map, &one, &ctx.c2, BPF_NOEXIST);
+	} else {
+		err = bpf_map_update_elem(map, &one, &ctx.p2, BPF_NOEXIST);
+	}
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static int setup_tx_sockmap(void)
+{
+	int zero = 0, one = 1;
+	int prog, map;
+	int err;
+
+	map = bpf_map__fd(ctx.skel->maps.sock_map_tx);
+	prog = TXMODE_BPF_PASS() ?
+		bpf_program__fd(ctx.skel->progs.prog_skmsg_pass) :
+		bpf_program__fd(ctx.skel->progs.prog_skmsg_verdict);
+
+	err = bpf_prog_attach(prog, map, BPF_SK_MSG_VERDICT, 0);
+	if (err)
+		return err;
+
+	if (TXMODE_BPF_EGRESS()) {
+		err = bpf_map_update_elem(map, &zero, &ctx.p1, BPF_NOEXIST);
+		err |= bpf_map_update_elem(map, &one, &ctx.p2, BPF_NOEXIST);
+	} else {
+		ctx.skel->bss->verdict_dir = BPF_F_INGRESS;
+		err = bpf_map_update_elem(map, &zero, &ctx.p2, BPF_NOEXIST);
+		err |= bpf_map_update_elem(map, &one, &ctx.c2, BPF_NOEXIST);
+	}
+
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static void setup(void)
+{
+	int err;
+
+	ctx.skel = bench_sockmap_prog__open_and_load();
+	if (!ctx.skel) {
+		fprintf(stderr, "error loading skel\n");
+		exit(1);
+	}
+
+	if (create_sockets()) {
+		fprintf(stderr, "create_net_mode error\n");
+		goto err;
+	}
+
+	if (RXMODE_BPF()) {
+		err = setup_rx_sockmap();
+		if (err) {
+			fprintf(stderr, "setup_rx_sockmap error:%d\n", err);
+			goto err;
+		}
+	} else if (TXMODE_BPF()) {
+		err = setup_tx_sockmap();
+		if (err) {
+			fprintf(stderr, "setup_tx_sockmap error:%d\n", err);
+			goto err;
+		}
+	} else {
+		fprintf(stderr, "unknown sockmap bench mode: %d\n", ctx.mode);
+		goto err;
+	}
+
+	return;
+
+err:
+	bench_sockmap_prog_destroy();
+	exit(1);
+}
+
+static void measure(struct bench_res *res)
+{
+	res->drops = atomic_swap(&ctx.prod_send, 0);
+	res->hits = atomic_swap(&ctx.skel->bss->process_byte, 0);
+	res->false_hits = atomic_swap(&ctx.user_read, 0);
+	res->important_hits = atomic_swap(&ctx.send_calls, 0);
+	res->important_hits |= atomic_swap(&ctx.read_calls, 0) << 32;
+}
+
+static void verify_data(int *check_pos, char *buf, int rcv)
+{
+	for (int i = 0 ; i < rcv; i++) {
+		if (buf[i] != snd_data[(*check_pos) % DATA_REPEAT_SIZE]) {
+			fprintf(stderr, "verify data fail");
+			exit(1);
+		}
+		(*check_pos)++;
+		if (*check_pos >= FILE_SIZE)
+			*check_pos = 0;
+	}
+}
+
+static void *consumer(void *input)
+{
+	int rcv, sent;
+	int check_pos = 0;
+	int tid = (long)input;
+	int recv_buf_size = FILE_SIZE;
+	char *buf = malloc(recv_buf_size);
+	int delay_read = ctx.delay_consumer;
+
+	if (!buf) {
+		fprintf(stderr, "fail to init read buffer");
+		return NULL;
+	}
+
+	while (true) {
+		if (tid == 1) {
+			/* consumer 1 is unused for tx test and stream verdict test */
+			if (RXMODE_BPF() || TXMODE())
+				return NULL;
+			/* it's only for RX_NORMAL which service as reserve-proxy mode */
+			rcv = read(ctx.p1, buf, recv_buf_size);
+			if (rcv < 0) {
+				fprintf(stderr, "fail to read p1");
+				return NULL;
+			}
+
+			sent = send(ctx.p2, buf, recv_buf_size, 0);
+			if (sent < 0) {
+				fprintf(stderr, "fail to send p2");
+				return NULL;
+			}
+		} else {
+			if (delay_read != 0) {
+				if (delay_read < 0)
+					return NULL;
+				sleep(delay_read);
+				delay_read = 0;
+			}
+			/* read real endpoint by consumer 0 */
+			atomic_inc(&ctx.read_calls);
+			rcv = read(ctx.c2, buf, recv_buf_size);
+			if (rcv < 0 && errno != EAGAIN) {
+				fprintf(stderr, "%s fail to read c2 %d\n", __func__, errno);
+				return NULL;
+			}
+			verify_data(&check_pos, buf, rcv);
+			atomic_add(&ctx.user_read, rcv);
+		}
+	}
+
+	return NULL;
+}
+
+static void *producer(void *input)
+{
+	int off = 0, fp, need_sent, sent;
+	int file_size = ctx.file_size;
+	struct timespec ts1, ts2;
+	int target;
+	FILE *file;
+
+	file = tmpfile();
+	if (!file) {
+		fprintf(stderr, "create file for sendfile");
+		return NULL;
+	}
+
+	/* we need simple verify */
+	for (int i = 0; i < file_size; i++) {
+		if (fwrite(&snd_data[off], sizeof(char), 1, file) != 1) {
+			fprintf(stderr, "init tmpfile error");
+			return NULL;
+		}
+		if (++off >= sizeof(snd_data))
+			off = 0;
+	}
+	fflush(file);
+	fseek(file, 0, SEEK_SET);
+
+	fp = fileno(file);
+	need_sent = file_size;
+	clock_gettime(CLOCK_MONOTONIC, &ts1);
+
+	if (RXMODE_BPF_VERDICT())
+		target = ctx.c1;
+	else if (TXMODE_BPF_EGRESS())
+		target = ctx.p1;
+	else
+		target = ctx.p2;
+	set_non_block(target, true);
+	while (true) {
+		if (ctx.prod_run_time) {
+			clock_gettime(CLOCK_MONOTONIC, &ts2);
+			if (ts2.tv_sec - ts1.tv_sec > ctx.prod_run_time)
+				return NULL;
+		}
+
+		errno = 0;
+		atomic_inc(&ctx.send_calls);
+		sent = sendfile(target, fp, NULL, need_sent);
+		if (sent < 0) {
+			if (errno != EAGAIN && errno != ENOMEM && errno != ENOBUFS) {
+				fprintf(stderr, "sendfile return %d, errorno %d:%s\n",
+					sent, errno, strerror(errno));
+				return NULL;
+			}
+			continue;
+		} else if (sent < need_sent) {
+			need_sent -= sent;
+			atomic_add(&ctx.prod_send, sent);
+			continue;
+		}
+		atomic_add(&ctx.prod_send, need_sent);
+		need_sent = file_size;
+		lseek(fp, 0, SEEK_SET);
+	}
+
+	return NULL;
+}
+
+static void report_progress(int iter, struct bench_res *res, long delta_ns)
+{
+	double speed_mbs, prod_mbs, bpf_mbs, send_hz, read_hz;
+
+	prod_mbs = res->drops / 1000000.0 / (delta_ns / 1000000000.0);
+	speed_mbs = res->false_hits / 1000000.0 / (delta_ns / 1000000000.0);
+	bpf_mbs = res->hits / 1000000.0 / (delta_ns / 1000000000.0);
+	send_hz = (res->important_hits & 0xFFFFFFFF) / (delta_ns / 1000000000.0);
+	read_hz = (res->important_hits >> 32) / (delta_ns / 1000000000.0);
+
+	printf("Iter %3d (%7.3lfus): ",
+	       iter, (delta_ns - 1000000000) / 1000.0);
+	printf("Send Speed %8.3lf MB/s (%8.3lf calls/s), BPF Speed %8.3lf MB/s, "
+	       "Rcv Speed %8.3lf MB/s (%8.3lf calls/s)\n",
+	       prod_mbs, send_hz, bpf_mbs, speed_mbs, read_hz);
+}
+
+static void report_final(struct bench_res res[], int res_cnt)
+{
+	double verdict_mbs_mean = 0.0;
+	long verdict_total = 0;
+	int i;
+
+	for (i = 0; i < res_cnt; i++) {
+		verdict_mbs_mean += res[i].hits / 1000000.0 / (0.0 + res_cnt);
+		verdict_total += res[i].hits / 1000000.0;
+	}
+
+	printf("Summary: total trans %8.3lu MB \u00B1 %5.3lf MB/s\n",
+	       verdict_total, verdict_mbs_mean);
+}
+
+static const struct argp_option opts[] = {
+	{ "rx-normal", ARG_FW_RX_NORMAL, NULL, 0,
+		"simple reserve-proxy mode, no bfp enabled"},
+	{ "rx-pass", ARG_FW_RX_PASS, NULL, 0,
+		"run bpf prog but no redir applied"},
+	{ "rx-strp", ARG_CTL_RX_STRP, "Byte", 0,
+		"enable strparser and set the encapsulation size"},
+	{ "rx-verdict-egress", ARG_FW_RX_VERDICT_EGRESS, NULL, 0,
+		"forward data with bpf(stream verdict)"},
+	{ "rx-verdict-ingress", ARG_FW_RX_VERDICT_INGRESS, NULL, 0,
+		"forward data with bpf(stream verdict)"},
+	{ "tx-normal", ARG_FW_TX_NORMAL, NULL, 0,
+		"simple c-s mode, no bfp enabled"},
+	{ "tx-pass", ARG_FW_TX_PASS, NULL, 0,
+		"run bpf prog but no redir applied"},
+	{ "tx-verdict-ingress", ARG_FW_TX_VERDICT_INGRESS, NULL, 0,
+		"forward msg to ingress queue of another socket"},
+	{ "tx-verdict-egress", ARG_FW_TX_VERDICT_EGRESS, NULL, 0,
+		"forward msg to egress queue of another socket"},
+	{ "delay-consumer", ARG_CONSUMER_DELAY_TIME, "SEC", 0,
+		"delay consumer start"},
+	{ "producer-duration", ARG_PRODUCER_DURATION, "SEC", 0,
+		"producer duration"},
+	{},
+};
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+	switch (key) {
+	case ARG_FW_RX_NORMAL...ARG_FW_TX_VERDICT_EGRESS:
+		ctx.mode = key;
+		break;
+	case ARG_CONSUMER_DELAY_TIME:
+		ctx.delay_consumer = strtol(arg, NULL, 10);
+		break;
+	case ARG_PRODUCER_DURATION:
+		ctx.prod_run_time = strtol(arg, NULL, 10);
+		break;
+	case ARG_CTL_RX_STRP:
+		ctx.strp_size = strtol(arg, NULL, 10);
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+
+	return 0;
+}
+
+/* exported into benchmark runner */
+const struct argp bench_sockmap_argp = {
+	.options	= opts,
+	.parser		= parse_arg,
+};
+
+/* Benchmark performance of creating bpf local storage  */
+const struct bench bench_sockmap = {
+	.name			= "sockmap",
+	.argp			= &bench_sockmap_argp,
+	.validate		= validate,
+	.setup			= setup,
+	.producer_thread	= producer,
+	.consumer_thread	= consumer,
+	.measure		= measure,
+	.report_progress	= report_progress,
+	.report_final		= report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/bench_strncmp.c b/tools/testing/selftests/bpf/benchs/bench_strncmp.c
index 494b591c0289..a5e1428fd7a0 100644
--- a/tools/testing/selftests/bpf/benchs/bench_strncmp.c
+++ b/tools/testing/selftests/bpf/benchs/bench_strncmp.c
@@ -50,8 +50,8 @@ const struct argp bench_strncmp_argp = {
 
 static void strncmp_validate(void)
 {
-	if (env.consumer_cnt != 1) {
-		fprintf(stderr, "strncmp benchmark doesn't support multi-consumer!\n");
+	if (env.consumer_cnt != 0) {
+		fprintf(stderr, "strncmp benchmark doesn't support consumer!\n");
 		exit(1);
 	}
 }
@@ -128,11 +128,6 @@ static void *strncmp_producer(void *ctx)
 	return NULL;
 }
 
-static void *strncmp_consumer(void *ctx)
-{
-	return NULL;
-}
-
 static void strncmp_measure(struct bench_res *res)
 {
 	res->hits = atomic_swap(&ctx.skel->bss->hits, 0);
@@ -140,10 +135,10 @@ static void strncmp_measure(struct bench_res *res)
 
 const struct bench bench_strncmp_no_helper = {
 	.name = "strncmp-no-helper",
+	.argp = &bench_strncmp_argp,
 	.validate = strncmp_validate,
 	.setup = strncmp_no_helper_setup,
 	.producer_thread = strncmp_producer,
-	.consumer_thread = strncmp_consumer,
 	.measure = strncmp_measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
@@ -151,10 +146,10 @@ const struct bench bench_strncmp_no_helper = {
 
 const struct bench bench_strncmp_helper = {
 	.name = "strncmp-helper",
+	.argp = &bench_strncmp_argp,
 	.validate = strncmp_validate,
 	.setup = strncmp_helper_setup,
 	.producer_thread = strncmp_producer,
-	.consumer_thread = strncmp_consumer,
 	.measure = strncmp_measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c
index 0c481de2833d..34018fc3927f 100644
--- a/tools/testing/selftests/bpf/benchs/bench_trigger.c
+++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c
@@ -1,59 +1,162 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
+#define _GNU_SOURCE
+#include <argp.h>
+#include <unistd.h>
+#include <stdint.h>
+#include "bpf_util.h"
 #include "bench.h"
 #include "trigger_bench.skel.h"
 #include "trace_helpers.h"
 
+#define MAX_TRIG_BATCH_ITERS 1000
+
+static struct {
+	__u32 batch_iters;
+} args = {
+	.batch_iters = 100,
+};
+
+enum {
+	ARG_TRIG_BATCH_ITERS = 7000,
+};
+
+static const struct argp_option opts[] = {
+	{ "trig-batch-iters", ARG_TRIG_BATCH_ITERS, "BATCH_ITER_CNT", 0,
+		"Number of in-kernel iterations per one driver test run"},
+	{},
+};
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+	long ret;
+
+	switch (key) {
+	case ARG_TRIG_BATCH_ITERS:
+		ret = strtol(arg, NULL, 10);
+		if (ret < 1 || ret > MAX_TRIG_BATCH_ITERS) {
+			fprintf(stderr, "invalid --trig-batch-iters value (should be between %d and %d)\n",
+				1, MAX_TRIG_BATCH_ITERS);
+			argp_usage(state);
+		}
+		args.batch_iters = ret;
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+
+	return 0;
+}
+
+const struct argp bench_trigger_batch_argp = {
+	.options = opts,
+	.parser = parse_arg,
+};
+
+/* adjust slot shift in inc_hits() if changing */
+#define MAX_BUCKETS 256
+
+#pragma GCC diagnostic ignored "-Wattributes"
+
 /* BPF triggering benchmarks */
 static struct trigger_ctx {
 	struct trigger_bench *skel;
+	bool usermode_counters;
+	int driver_prog_fd;
 } ctx;
 
-static struct counter base_hits;
+static struct counter base_hits[MAX_BUCKETS];
+
+static __always_inline void inc_counter(struct counter *counters)
+{
+	static __thread int tid = 0;
+	unsigned slot;
+
+	if (unlikely(tid == 0))
+		tid = sys_gettid();
+
+	/* multiplicative hashing, it's fast */
+	slot = 2654435769U * tid;
+	slot >>= 24;
+
+	atomic_inc(&base_hits[slot].value); /* use highest byte as an index */
+}
+
+static long sum_and_reset_counters(struct counter *counters)
+{
+	int i;
+	long sum = 0;
+
+	for (i = 0; i < MAX_BUCKETS; i++)
+		sum += atomic_swap(&counters[i].value, 0);
+	return sum;
+}
 
 static void trigger_validate(void)
 {
-	if (env.consumer_cnt != 1) {
-		fprintf(stderr, "benchmark doesn't support multi-consumer!\n");
+	if (env.consumer_cnt != 0) {
+		fprintf(stderr, "benchmark doesn't support consumer!\n");
 		exit(1);
 	}
 }
 
-static void *trigger_base_producer(void *input)
+static void *trigger_producer(void *input)
 {
-	while (true) {
-		(void)syscall(__NR_getpgid);
-		atomic_inc(&base_hits.value);
+	if (ctx.usermode_counters) {
+		while (true) {
+			(void)syscall(__NR_getpgid);
+			inc_counter(base_hits);
+		}
+	} else {
+		while (true)
+			(void)syscall(__NR_getpgid);
 	}
 	return NULL;
 }
 
-static void trigger_base_measure(struct bench_res *res)
+static void *trigger_producer_batch(void *input)
 {
-	res->hits = atomic_swap(&base_hits.value, 0);
-}
+	int fd = ctx.driver_prog_fd ?: bpf_program__fd(ctx.skel->progs.trigger_driver);
 
-static void *trigger_producer(void *input)
-{
 	while (true)
-		(void)syscall(__NR_getpgid);
+		bpf_prog_test_run_opts(fd, NULL);
+
 	return NULL;
 }
 
 static void trigger_measure(struct bench_res *res)
 {
-	res->hits = atomic_swap(&ctx.skel->bss->hits, 0);
+	if (ctx.usermode_counters)
+		res->hits = sum_and_reset_counters(base_hits);
+	else
+		res->hits = sum_and_reset_counters(ctx.skel->bss->hits);
 }
 
 static void setup_ctx(void)
 {
 	setup_libbpf();
 
-	ctx.skel = trigger_bench__open_and_load();
+	ctx.skel = trigger_bench__open();
 	if (!ctx.skel) {
 		fprintf(stderr, "failed to open skeleton\n");
 		exit(1);
 	}
+
+	/* default "driver" BPF program */
+	bpf_program__set_autoload(ctx.skel->progs.trigger_driver, true);
+
+	ctx.skel->rodata->batch_iters = args.batch_iters;
+}
+
+static void load_ctx(void)
+{
+	int err;
+
+	err = trigger_bench__load(ctx.skel);
+	if (err) {
+		fprintf(stderr, "failed to open skeleton\n");
+		exit(1);
+	}
 }
 
 static void attach_bpf(struct bpf_program *prog)
@@ -67,45 +170,163 @@ static void attach_bpf(struct bpf_program *prog)
 	}
 }
 
-static void trigger_tp_setup(void)
+static void trigger_syscall_count_setup(void)
 {
-	setup_ctx();
-	attach_bpf(ctx.skel->progs.bench_trigger_tp);
+	ctx.usermode_counters = true;
 }
 
-static void trigger_rawtp_setup(void)
+/* Batched, staying mostly in-kernel triggering setups */
+static void trigger_kernel_count_setup(void)
 {
 	setup_ctx();
-	attach_bpf(ctx.skel->progs.bench_trigger_raw_tp);
+	bpf_program__set_autoload(ctx.skel->progs.trigger_driver, false);
+	bpf_program__set_autoload(ctx.skel->progs.trigger_kernel_count, true);
+	load_ctx();
+	/* override driver program */
+	ctx.driver_prog_fd = bpf_program__fd(ctx.skel->progs.trigger_kernel_count);
 }
 
 static void trigger_kprobe_setup(void)
 {
 	setup_ctx();
+	bpf_program__set_autoload(ctx.skel->progs.bench_trigger_kprobe, true);
+	load_ctx();
 	attach_bpf(ctx.skel->progs.bench_trigger_kprobe);
 }
 
+static void trigger_kretprobe_setup(void)
+{
+	setup_ctx();
+	bpf_program__set_autoload(ctx.skel->progs.bench_trigger_kretprobe, true);
+	load_ctx();
+	attach_bpf(ctx.skel->progs.bench_trigger_kretprobe);
+}
+
+static void trigger_kprobe_multi_setup(void)
+{
+	setup_ctx();
+	bpf_program__set_autoload(ctx.skel->progs.bench_trigger_kprobe_multi, true);
+	load_ctx();
+	attach_bpf(ctx.skel->progs.bench_trigger_kprobe_multi);
+}
+
+static void trigger_kretprobe_multi_setup(void)
+{
+	setup_ctx();
+	bpf_program__set_autoload(ctx.skel->progs.bench_trigger_kretprobe_multi, true);
+	load_ctx();
+	attach_bpf(ctx.skel->progs.bench_trigger_kretprobe_multi);
+}
+
 static void trigger_fentry_setup(void)
 {
 	setup_ctx();
+	bpf_program__set_autoload(ctx.skel->progs.bench_trigger_fentry, true);
+	load_ctx();
 	attach_bpf(ctx.skel->progs.bench_trigger_fentry);
 }
 
-static void trigger_fentry_sleep_setup(void)
+static void attach_ksyms_all(struct bpf_program *empty, bool kretprobe)
 {
+	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
+	char **syms = NULL;
+	size_t cnt = 0;
+
+	/* Some recursive functions will be skipped in
+	 * bpf_get_ksyms -> skip_entry, as they can introduce sufficient
+	 * overhead. However, it's difficut to skip all the recursive
+	 * functions for a debug kernel.
+	 *
+	 * So, don't run the kprobe-multi-all and kretprobe-multi-all on
+	 * a debug kernel.
+	 */
+	if (bpf_get_ksyms(&syms, &cnt, true)) {
+		fprintf(stderr, "failed to get ksyms\n");
+		exit(1);
+	}
+
+	opts.syms = (const char **) syms;
+	opts.cnt = cnt;
+	opts.retprobe = kretprobe;
+	/* attach empty to all the kernel functions except bpf_get_numa_node_id. */
+	if (!bpf_program__attach_kprobe_multi_opts(empty, NULL, &opts)) {
+		fprintf(stderr, "failed to attach bpf_program__attach_kprobe_multi_opts to all\n");
+		exit(1);
+	}
+}
+
+static void trigger_kprobe_multi_all_setup(void)
+{
+	struct bpf_program *prog, *empty;
+
+	setup_ctx();
+	empty = ctx.skel->progs.bench_kprobe_multi_empty;
+	prog = ctx.skel->progs.bench_trigger_kprobe_multi;
+	bpf_program__set_autoload(empty, true);
+	bpf_program__set_autoload(prog, true);
+	load_ctx();
+
+	attach_ksyms_all(empty, false);
+	attach_bpf(prog);
+}
+
+static void trigger_kretprobe_multi_all_setup(void)
+{
+	struct bpf_program *prog, *empty;
+
 	setup_ctx();
-	attach_bpf(ctx.skel->progs.bench_trigger_fentry_sleep);
+	empty = ctx.skel->progs.bench_kretprobe_multi_empty;
+	prog = ctx.skel->progs.bench_trigger_kretprobe_multi;
+	bpf_program__set_autoload(empty, true);
+	bpf_program__set_autoload(prog, true);
+	load_ctx();
+
+	attach_ksyms_all(empty, true);
+	attach_bpf(prog);
+}
+
+static void trigger_fexit_setup(void)
+{
+	setup_ctx();
+	bpf_program__set_autoload(ctx.skel->progs.bench_trigger_fexit, true);
+	load_ctx();
+	attach_bpf(ctx.skel->progs.bench_trigger_fexit);
 }
 
 static void trigger_fmodret_setup(void)
 {
 	setup_ctx();
+	bpf_program__set_autoload(ctx.skel->progs.trigger_driver, false);
+	bpf_program__set_autoload(ctx.skel->progs.trigger_driver_kfunc, true);
+	bpf_program__set_autoload(ctx.skel->progs.bench_trigger_fmodret, true);
+	load_ctx();
+	/* override driver program */
+	ctx.driver_prog_fd = bpf_program__fd(ctx.skel->progs.trigger_driver_kfunc);
 	attach_bpf(ctx.skel->progs.bench_trigger_fmodret);
 }
 
-static void *trigger_consumer(void *input)
+static void trigger_tp_setup(void)
 {
-	return NULL;
+	setup_ctx();
+	bpf_program__set_autoload(ctx.skel->progs.trigger_driver, false);
+	bpf_program__set_autoload(ctx.skel->progs.trigger_driver_kfunc, true);
+	bpf_program__set_autoload(ctx.skel->progs.bench_trigger_tp, true);
+	load_ctx();
+	/* override driver program */
+	ctx.driver_prog_fd = bpf_program__fd(ctx.skel->progs.trigger_driver_kfunc);
+	attach_bpf(ctx.skel->progs.bench_trigger_tp);
+}
+
+static void trigger_rawtp_setup(void)
+{
+	setup_ctx();
+	bpf_program__set_autoload(ctx.skel->progs.trigger_driver, false);
+	bpf_program__set_autoload(ctx.skel->progs.trigger_driver_kfunc, true);
+	bpf_program__set_autoload(ctx.skel->progs.bench_trigger_rawtp, true);
+	load_ctx();
+	/* override driver program */
+	ctx.driver_prog_fd = bpf_program__fd(ctx.skel->progs.trigger_driver_kfunc);
+	attach_bpf(ctx.skel->progs.bench_trigger_rawtp);
 }
 
 /* make sure call is not inlined and not avoided by compiler, so __weak and
@@ -115,214 +336,276 @@ static void *trigger_consumer(void *input)
  * instructions. So use two different targets, one of which starts with nop
  * and another doesn't.
  *
- * GCC doesn't generate stack setup preample for these functions due to them
+ * GCC doesn't generate stack setup preamble for these functions due to them
  * having no input arguments and doing nothing in the body.
  */
-__weak void uprobe_target_with_nop(void)
+__nocf_check __weak void uprobe_target_nop(void)
 {
 	asm volatile ("nop");
 }
 
-__weak void uprobe_target_without_nop(void)
+__weak void opaque_noop_func(void)
+{
+}
+
+__nocf_check __weak int uprobe_target_push(void)
+{
+	/* overhead of function call is negligible compared to uprobe
+	 * triggering, so this shouldn't affect benchmark results much
+	 */
+	opaque_noop_func();
+	return 1;
+}
+
+__nocf_check __weak void uprobe_target_ret(void)
 {
 	asm volatile ("");
 }
 
-static void *uprobe_base_producer(void *input)
+static void *uprobe_producer_count(void *input)
 {
 	while (true) {
-		uprobe_target_with_nop();
-		atomic_inc(&base_hits.value);
+		uprobe_target_nop();
+		inc_counter(base_hits);
 	}
 	return NULL;
 }
 
-static void *uprobe_producer_with_nop(void *input)
+static void *uprobe_producer_nop(void *input)
+{
+	while (true)
+		uprobe_target_nop();
+	return NULL;
+}
+
+static void *uprobe_producer_push(void *input)
+{
+	while (true)
+		uprobe_target_push();
+	return NULL;
+}
+
+static void *uprobe_producer_ret(void *input)
 {
 	while (true)
-		uprobe_target_with_nop();
+		uprobe_target_ret();
 	return NULL;
 }
 
-static void *uprobe_producer_without_nop(void *input)
+#ifdef __x86_64__
+__nocf_check __weak void uprobe_target_nop5(void)
+{
+	asm volatile (".byte 0x0f, 0x1f, 0x44, 0x00, 0x00");
+}
+
+static void *uprobe_producer_nop5(void *input)
 {
 	while (true)
-		uprobe_target_without_nop();
+		uprobe_target_nop5();
 	return NULL;
 }
+#endif
 
-static void usetup(bool use_retprobe, bool use_nop)
+static void usetup(bool use_retprobe, bool use_multi, void *target_addr)
 {
 	size_t uprobe_offset;
 	struct bpf_link *link;
+	int err;
 
 	setup_libbpf();
 
-	ctx.skel = trigger_bench__open_and_load();
+	ctx.skel = trigger_bench__open();
 	if (!ctx.skel) {
 		fprintf(stderr, "failed to open skeleton\n");
 		exit(1);
 	}
 
-	if (use_nop)
-		uprobe_offset = get_uprobe_offset(&uprobe_target_with_nop);
+	if (use_multi)
+		bpf_program__set_autoload(ctx.skel->progs.bench_trigger_uprobe_multi, true);
 	else
-		uprobe_offset = get_uprobe_offset(&uprobe_target_without_nop);
+		bpf_program__set_autoload(ctx.skel->progs.bench_trigger_uprobe, true);
 
-	link = bpf_program__attach_uprobe(ctx.skel->progs.bench_trigger_uprobe,
-					  use_retprobe,
-					  -1 /* all PIDs */,
-					  "/proc/self/exe",
-					  uprobe_offset);
+	err = trigger_bench__load(ctx.skel);
+	if (err) {
+		fprintf(stderr, "failed to load skeleton\n");
+		exit(1);
+	}
+
+	uprobe_offset = get_uprobe_offset(target_addr);
+	if (use_multi) {
+		LIBBPF_OPTS(bpf_uprobe_multi_opts, opts,
+			.retprobe = use_retprobe,
+			.cnt = 1,
+			.offsets = &uprobe_offset,
+		);
+		link = bpf_program__attach_uprobe_multi(
+			ctx.skel->progs.bench_trigger_uprobe_multi,
+			-1 /* all PIDs */, "/proc/self/exe", NULL, &opts);
+		ctx.skel->links.bench_trigger_uprobe_multi = link;
+	} else {
+		link = bpf_program__attach_uprobe(ctx.skel->progs.bench_trigger_uprobe,
+						  use_retprobe,
+						  -1 /* all PIDs */,
+						  "/proc/self/exe",
+						  uprobe_offset);
+		ctx.skel->links.bench_trigger_uprobe = link;
+	}
 	if (!link) {
-		fprintf(stderr, "failed to attach uprobe!\n");
+		fprintf(stderr, "failed to attach %s!\n", use_multi ? "multi-uprobe" : "uprobe");
 		exit(1);
 	}
-	ctx.skel->links.bench_trigger_uprobe = link;
 }
 
-static void uprobe_setup_with_nop(void)
+static void usermode_count_setup(void)
 {
-	usetup(false, true);
+	ctx.usermode_counters = true;
 }
 
-static void uretprobe_setup_with_nop(void)
+static void uprobe_nop_setup(void)
 {
-	usetup(true, true);
+	usetup(false, false /* !use_multi */, &uprobe_target_nop);
 }
 
-static void uprobe_setup_without_nop(void)
+static void uretprobe_nop_setup(void)
 {
-	usetup(false, false);
+	usetup(true, false /* !use_multi */, &uprobe_target_nop);
 }
 
-static void uretprobe_setup_without_nop(void)
+static void uprobe_push_setup(void)
 {
-	usetup(true, false);
+	usetup(false, false /* !use_multi */, &uprobe_target_push);
 }
 
-const struct bench bench_trig_base = {
-	.name = "trig-base",
-	.validate = trigger_validate,
-	.producer_thread = trigger_base_producer,
-	.consumer_thread = trigger_consumer,
-	.measure = trigger_base_measure,
-	.report_progress = hits_drops_report_progress,
-	.report_final = hits_drops_report_final,
-};
+static void uretprobe_push_setup(void)
+{
+	usetup(true, false /* !use_multi */, &uprobe_target_push);
+}
 
-const struct bench bench_trig_tp = {
-	.name = "trig-tp",
-	.validate = trigger_validate,
-	.setup = trigger_tp_setup,
-	.producer_thread = trigger_producer,
-	.consumer_thread = trigger_consumer,
-	.measure = trigger_measure,
-	.report_progress = hits_drops_report_progress,
-	.report_final = hits_drops_report_final,
-};
+static void uprobe_ret_setup(void)
+{
+	usetup(false, false /* !use_multi */, &uprobe_target_ret);
+}
 
-const struct bench bench_trig_rawtp = {
-	.name = "trig-rawtp",
-	.validate = trigger_validate,
-	.setup = trigger_rawtp_setup,
-	.producer_thread = trigger_producer,
-	.consumer_thread = trigger_consumer,
-	.measure = trigger_measure,
-	.report_progress = hits_drops_report_progress,
-	.report_final = hits_drops_report_final,
-};
+static void uretprobe_ret_setup(void)
+{
+	usetup(true, false /* !use_multi */, &uprobe_target_ret);
+}
 
-const struct bench bench_trig_kprobe = {
-	.name = "trig-kprobe",
-	.validate = trigger_validate,
-	.setup = trigger_kprobe_setup,
-	.producer_thread = trigger_producer,
-	.consumer_thread = trigger_consumer,
-	.measure = trigger_measure,
-	.report_progress = hits_drops_report_progress,
-	.report_final = hits_drops_report_final,
-};
+static void uprobe_multi_nop_setup(void)
+{
+	usetup(false, true /* use_multi */, &uprobe_target_nop);
+}
 
-const struct bench bench_trig_fentry = {
-	.name = "trig-fentry",
-	.validate = trigger_validate,
-	.setup = trigger_fentry_setup,
-	.producer_thread = trigger_producer,
-	.consumer_thread = trigger_consumer,
-	.measure = trigger_measure,
-	.report_progress = hits_drops_report_progress,
-	.report_final = hits_drops_report_final,
-};
+static void uretprobe_multi_nop_setup(void)
+{
+	usetup(true, true /* use_multi */, &uprobe_target_nop);
+}
 
-const struct bench bench_trig_fentry_sleep = {
-	.name = "trig-fentry-sleep",
-	.validate = trigger_validate,
-	.setup = trigger_fentry_sleep_setup,
-	.producer_thread = trigger_producer,
-	.consumer_thread = trigger_consumer,
-	.measure = trigger_measure,
-	.report_progress = hits_drops_report_progress,
-	.report_final = hits_drops_report_final,
-};
+static void uprobe_multi_push_setup(void)
+{
+	usetup(false, true /* use_multi */, &uprobe_target_push);
+}
 
-const struct bench bench_trig_fmodret = {
-	.name = "trig-fmodret",
-	.validate = trigger_validate,
-	.setup = trigger_fmodret_setup,
-	.producer_thread = trigger_producer,
-	.consumer_thread = trigger_consumer,
-	.measure = trigger_measure,
-	.report_progress = hits_drops_report_progress,
-	.report_final = hits_drops_report_final,
-};
+static void uretprobe_multi_push_setup(void)
+{
+	usetup(true, true /* use_multi */, &uprobe_target_push);
+}
 
-const struct bench bench_trig_uprobe_base = {
-	.name = "trig-uprobe-base",
-	.setup = NULL, /* no uprobe/uretprobe is attached */
-	.producer_thread = uprobe_base_producer,
-	.consumer_thread = trigger_consumer,
-	.measure = trigger_base_measure,
-	.report_progress = hits_drops_report_progress,
-	.report_final = hits_drops_report_final,
-};
+static void uprobe_multi_ret_setup(void)
+{
+	usetup(false, true /* use_multi */, &uprobe_target_ret);
+}
 
-const struct bench bench_trig_uprobe_with_nop = {
-	.name = "trig-uprobe-with-nop",
-	.setup = uprobe_setup_with_nop,
-	.producer_thread = uprobe_producer_with_nop,
-	.consumer_thread = trigger_consumer,
-	.measure = trigger_measure,
-	.report_progress = hits_drops_report_progress,
-	.report_final = hits_drops_report_final,
-};
+static void uretprobe_multi_ret_setup(void)
+{
+	usetup(true, true /* use_multi */, &uprobe_target_ret);
+}
 
-const struct bench bench_trig_uretprobe_with_nop = {
-	.name = "trig-uretprobe-with-nop",
-	.setup = uretprobe_setup_with_nop,
-	.producer_thread = uprobe_producer_with_nop,
-	.consumer_thread = trigger_consumer,
-	.measure = trigger_measure,
-	.report_progress = hits_drops_report_progress,
-	.report_final = hits_drops_report_final,
-};
+#ifdef __x86_64__
+static void uprobe_nop5_setup(void)
+{
+	usetup(false, false /* !use_multi */, &uprobe_target_nop5);
+}
 
-const struct bench bench_trig_uprobe_without_nop = {
-	.name = "trig-uprobe-without-nop",
-	.setup = uprobe_setup_without_nop,
-	.producer_thread = uprobe_producer_without_nop,
-	.consumer_thread = trigger_consumer,
-	.measure = trigger_measure,
-	.report_progress = hits_drops_report_progress,
-	.report_final = hits_drops_report_final,
-};
+static void uretprobe_nop5_setup(void)
+{
+	usetup(true, false /* !use_multi */, &uprobe_target_nop5);
+}
+
+static void uprobe_multi_nop5_setup(void)
+{
+	usetup(false, true /* use_multi */, &uprobe_target_nop5);
+}
+
+static void uretprobe_multi_nop5_setup(void)
+{
+	usetup(true, true /* use_multi */, &uprobe_target_nop5);
+}
+#endif
 
-const struct bench bench_trig_uretprobe_without_nop = {
-	.name = "trig-uretprobe-without-nop",
-	.setup = uretprobe_setup_without_nop,
-	.producer_thread = uprobe_producer_without_nop,
-	.consumer_thread = trigger_consumer,
+const struct bench bench_trig_syscall_count = {
+	.name = "trig-syscall-count",
+	.validate = trigger_validate,
+	.setup = trigger_syscall_count_setup,
+	.producer_thread = trigger_producer,
 	.measure = trigger_measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
 };
+
+/* batched (staying mostly in kernel) kprobe/fentry benchmarks */
+#define BENCH_TRIG_KERNEL(KIND, NAME)					\
+const struct bench bench_trig_##KIND = {				\
+	.name = "trig-" NAME,						\
+	.setup = trigger_##KIND##_setup,				\
+	.producer_thread = trigger_producer_batch,			\
+	.measure = trigger_measure,					\
+	.report_progress = hits_drops_report_progress,			\
+	.report_final = hits_drops_report_final,			\
+	.argp = &bench_trigger_batch_argp,				\
+}
+
+BENCH_TRIG_KERNEL(kernel_count, "kernel-count");
+BENCH_TRIG_KERNEL(kprobe, "kprobe");
+BENCH_TRIG_KERNEL(kretprobe, "kretprobe");
+BENCH_TRIG_KERNEL(kprobe_multi, "kprobe-multi");
+BENCH_TRIG_KERNEL(kretprobe_multi, "kretprobe-multi");
+BENCH_TRIG_KERNEL(fentry, "fentry");
+BENCH_TRIG_KERNEL(kprobe_multi_all, "kprobe-multi-all");
+BENCH_TRIG_KERNEL(kretprobe_multi_all, "kretprobe-multi-all");
+BENCH_TRIG_KERNEL(fexit, "fexit");
+BENCH_TRIG_KERNEL(fmodret, "fmodret");
+BENCH_TRIG_KERNEL(tp, "tp");
+BENCH_TRIG_KERNEL(rawtp, "rawtp");
+
+/* uprobe benchmarks */
+#define BENCH_TRIG_USERMODE(KIND, PRODUCER, NAME)			\
+const struct bench bench_trig_##KIND = {				\
+	.name = "trig-" NAME,						\
+	.validate = trigger_validate,					\
+	.setup = KIND##_setup,						\
+	.producer_thread = uprobe_producer_##PRODUCER,			\
+	.measure = trigger_measure,					\
+	.report_progress = hits_drops_report_progress,			\
+	.report_final = hits_drops_report_final,			\
+}
+
+BENCH_TRIG_USERMODE(usermode_count, count, "usermode-count");
+BENCH_TRIG_USERMODE(uprobe_nop, nop, "uprobe-nop");
+BENCH_TRIG_USERMODE(uprobe_push, push, "uprobe-push");
+BENCH_TRIG_USERMODE(uprobe_ret, ret, "uprobe-ret");
+BENCH_TRIG_USERMODE(uretprobe_nop, nop, "uretprobe-nop");
+BENCH_TRIG_USERMODE(uretprobe_push, push, "uretprobe-push");
+BENCH_TRIG_USERMODE(uretprobe_ret, ret, "uretprobe-ret");
+BENCH_TRIG_USERMODE(uprobe_multi_nop, nop, "uprobe-multi-nop");
+BENCH_TRIG_USERMODE(uprobe_multi_push, push, "uprobe-multi-push");
+BENCH_TRIG_USERMODE(uprobe_multi_ret, ret, "uprobe-multi-ret");
+BENCH_TRIG_USERMODE(uretprobe_multi_nop, nop, "uretprobe-multi-nop");
+BENCH_TRIG_USERMODE(uretprobe_multi_push, push, "uretprobe-multi-push");
+BENCH_TRIG_USERMODE(uretprobe_multi_ret, ret, "uretprobe-multi-ret");
+#ifdef __x86_64__
+BENCH_TRIG_USERMODE(uprobe_nop5, nop5, "uprobe-nop5");
+BENCH_TRIG_USERMODE(uretprobe_nop5, nop5, "uretprobe-nop5");
+BENCH_TRIG_USERMODE(uprobe_multi_nop5, nop5, "uprobe-multi-nop5");
+BENCH_TRIG_USERMODE(uretprobe_multi_nop5, nop5, "uretprobe-multi-nop5");
+#endif
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_bpf_hashmap_full_update.sh b/tools/testing/selftests/bpf/benchs/run_bench_bpf_hashmap_full_update.sh
index 1e2de838f9fa..cd2efd3fdef3 100755
--- a/tools/testing/selftests/bpf/benchs/run_bench_bpf_hashmap_full_update.sh
+++ b/tools/testing/selftests/bpf/benchs/run_bench_bpf_hashmap_full_update.sh
@@ -6,6 +6,6 @@ source ./benchs/run_common.sh
 set -eufo pipefail
 
 nr_threads=`expr $(cat /proc/cpuinfo | grep "processor"| wc -l) - 1`
-summary=$($RUN_BENCH -p $nr_threads bpf-hashmap-ful-update)
+summary=$($RUN_BENCH -p $nr_threads bpf-hashmap-full-update)
 printf "$summary"
 printf "\n"
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_htab_mem.sh b/tools/testing/selftests/bpf/benchs/run_bench_htab_mem.sh
new file mode 100755
index 000000000000..9ff5832463a2
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/run_bench_htab_mem.sh
@@ -0,0 +1,40 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source ./benchs/run_common.sh
+
+set -eufo pipefail
+
+htab_mem()
+{
+	echo -n "per-prod-op: "
+	echo -n "$*" | sed -E "s/.* per-prod-op\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+k\/s).*/\1/"
+	echo -n -e ", avg mem: "
+	echo -n "$*" | sed -E "s/.* memory usage\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+MiB).*/\1/"
+	echo -n ", peak mem: "
+	echo "$*" | sed -E "s/.* peak memory usage\s+([0-9]+\.[0-9]+MiB).*/\1/"
+}
+
+summarize_htab_mem()
+{
+	local bench="$1"
+	local summary=$(echo $2 | tail -n1)
+
+	printf "%-20s %s\n" "$bench" "$(htab_mem $summary)"
+}
+
+htab_mem_bench()
+{
+	local name
+
+	for name in overwrite batch_add_batch_del add_del_on_diff_cpu
+	do
+		summarize_htab_mem "$name" "$($RUN_BENCH htab-mem --use-case $name -p8 "$@")"
+	done
+}
+
+header "preallocated"
+htab_mem_bench "--preallocated"
+
+header "normal bpf ma"
+htab_mem_bench
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_local_storage_rcu_tasks_trace.sh b/tools/testing/selftests/bpf/benchs/run_bench_local_storage_rcu_tasks_trace.sh
index 5dac1f02892c..3e8a969f2096 100755
--- a/tools/testing/selftests/bpf/benchs/run_bench_local_storage_rcu_tasks_trace.sh
+++ b/tools/testing/selftests/bpf/benchs/run_bench_local_storage_rcu_tasks_trace.sh
@@ -8,4 +8,4 @@ if [ -z $kthread_pid ]; then
 	exit 1
 fi
 
-./bench --nr_procs 15000 --kthread_pid $kthread_pid -d 600 --quiet 1 local-storage-tasks-trace
+./bench --nr_procs 15000 --kthread_pid $kthread_pid -d 600 --quiet local-storage-tasks-trace
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_rename.sh b/tools/testing/selftests/bpf/benchs/run_bench_rename.sh
index 16f774b1cdbe..7b281dbe4165 100755
--- a/tools/testing/selftests/bpf/benchs/run_bench_rename.sh
+++ b/tools/testing/selftests/bpf/benchs/run_bench_rename.sh
@@ -2,7 +2,7 @@
 
 set -eufo pipefail
 
-for i in base kprobe kretprobe rawtp fentry fexit fmodret
+for i in base kprobe kretprobe rawtp fentry fexit
 do
 	summary=$(sudo ./bench -w2 -d5 -a rename-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-)
 	printf "%-10s: %s\n" $i "$summary"
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh
index ada028aa9007..83e05e837871 100755
--- a/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh
+++ b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh
@@ -4,46 +4,52 @@ source ./benchs/run_common.sh
 
 set -eufo pipefail
 
+RUN_RB_BENCH="$RUN_BENCH -c1"
+
 header "Single-producer, parallel producer"
 for b in rb-libbpf rb-custom pb-libbpf pb-custom; do
-	summarize $b "$($RUN_BENCH $b)"
+	summarize $b "$($RUN_RB_BENCH $b)"
 done
 
 header "Single-producer, parallel producer, sampled notification"
 for b in rb-libbpf rb-custom pb-libbpf pb-custom; do
-	summarize $b "$($RUN_BENCH --rb-sampled $b)"
+	summarize $b "$($RUN_RB_BENCH --rb-sampled $b)"
 done
 
 header "Single-producer, back-to-back mode"
 for b in rb-libbpf rb-custom pb-libbpf pb-custom; do
-	summarize $b "$($RUN_BENCH --rb-b2b $b)"
-	summarize $b-sampled "$($RUN_BENCH --rb-sampled --rb-b2b $b)"
+	summarize $b "$($RUN_RB_BENCH --rb-b2b $b)"
+	summarize $b-sampled "$($RUN_RB_BENCH --rb-sampled --rb-b2b $b)"
 done
 
 header "Ringbuf back-to-back, effect of sample rate"
 for b in 1 5 10 25 50 100 250 500 1000 2000 3000; do
-	summarize "rb-sampled-$b" "$($RUN_BENCH --rb-b2b --rb-batch-cnt $b --rb-sampled --rb-sample-rate $b rb-custom)"
+	summarize "rb-sampled-$b" "$($RUN_RB_BENCH --rb-b2b --rb-batch-cnt $b --rb-sampled --rb-sample-rate $b rb-custom)"
 done
 header "Perfbuf back-to-back, effect of sample rate"
 for b in 1 5 10 25 50 100 250 500 1000 2000 3000; do
-	summarize "pb-sampled-$b" "$($RUN_BENCH --rb-b2b --rb-batch-cnt $b --rb-sampled --rb-sample-rate $b pb-custom)"
+	summarize "pb-sampled-$b" "$($RUN_RB_BENCH --rb-b2b --rb-batch-cnt $b --rb-sampled --rb-sample-rate $b pb-custom)"
 done
 
 header "Ringbuf back-to-back, reserve+commit vs output"
-summarize "reserve" "$($RUN_BENCH --rb-b2b                 rb-custom)"
-summarize "output"  "$($RUN_BENCH --rb-b2b --rb-use-output rb-custom)"
+summarize "reserve" "$($RUN_RB_BENCH --rb-b2b                 rb-custom)"
+summarize "output"  "$($RUN_RB_BENCH --rb-b2b --rb-use-output rb-custom)"
 
 header "Ringbuf sampled, reserve+commit vs output"
-summarize "reserve-sampled" "$($RUN_BENCH --rb-sampled                 rb-custom)"
-summarize "output-sampled"  "$($RUN_BENCH --rb-sampled --rb-use-output rb-custom)"
+summarize "reserve-sampled" "$($RUN_RB_BENCH --rb-sampled                 rb-custom)"
+summarize "output-sampled"  "$($RUN_RB_BENCH --rb-sampled --rb-use-output rb-custom)"
 
 header "Single-producer, consumer/producer competing on the same CPU, low batch count"
 for b in rb-libbpf rb-custom pb-libbpf pb-custom; do
-	summarize $b "$($RUN_BENCH --rb-batch-cnt 1 --rb-sample-rate 1 --prod-affinity 0 --cons-affinity 0 $b)"
+	summarize $b "$($RUN_RB_BENCH --rb-batch-cnt 1 --rb-sample-rate 1 --prod-affinity 0 --cons-affinity 0 $b)"
 done
 
 header "Ringbuf, multi-producer contention"
 for b in 1 2 3 4 8 12 16 20 24 28 32 36 40 44 48 52; do
-	summarize "rb-libbpf nr_prod $b" "$($RUN_BENCH -p$b --rb-batch-cnt 50 rb-libbpf)"
+	summarize "rb-libbpf nr_prod $b" "$($RUN_RB_BENCH -p$b --rb-batch-cnt 50 rb-libbpf)"
 done
 
+header "Ringbuf, multi-producer contention in overwrite mode, no consumer"
+for b in 1 2 3 4 8 12 16 20 24 28 32 36 40 44 48 52; do
+	summarize "rb-prod nr_prod $b" "$($RUN_BENCH -p$b --rb-batch-cnt 50 --rb-overwrite --rb-bench-producer rb-libbpf)"
+done
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh b/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh
index 78e83f243294..f7573708a0c3 100755
--- a/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh
+++ b/tools/testing/selftests/bpf/benchs/run_bench_trigger.sh
@@ -2,8 +2,22 @@
 
 set -eufo pipefail
 
-for i in base tp rawtp kprobe fentry fmodret
-do
-	summary=$(sudo ./bench -w2 -d5 -a trig-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-)
-	printf "%-10s: %s\n" $i "$summary"
+def_tests=( \
+	usermode-count kernel-count syscall-count \
+	fentry fexit fmodret \
+	rawtp tp \
+	kprobe kprobe-multi kprobe-multi-all \
+	kretprobe kretprobe-multi kretprobe-multi-all \
+)
+
+tests=("$@")
+if [ ${#tests[@]} -eq 0 ]; then
+	tests=("${def_tests[@]}")
+fi
+
+p=${PROD_CNT:-1}
+
+for t in "${tests[@]}"; do
+	summary=$(sudo ./bench -w2 -d5 -a -p$p trig-$t | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-)
+	printf "%-15s: %s\n" $t "$summary"
 done
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh b/tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh
new file mode 100755
index 000000000000..03f55405484b
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+
+set -eufo pipefail
+
+for i in usermode-count syscall-count {uprobe,uretprobe}-{nop,push,ret,nop5}
+do
+	summary=$(sudo ./bench -w2 -d5 -a trig-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-)
+	printf "%-15s: %s\n" $i "$summary"
+done
diff --git a/tools/testing/selftests/bpf/bpf_arena_alloc.h b/tools/testing/selftests/bpf/bpf_arena_alloc.h
new file mode 100644
index 000000000000..c27678299e0c
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_arena_alloc.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#pragma once
+#include "bpf_arena_common.h"
+
+#ifndef __round_mask
+#define __round_mask(x, y) ((__typeof__(x))((y)-1))
+#endif
+#ifndef round_up
+#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
+#endif
+
+#ifdef __BPF__
+#define NR_CPUS (sizeof(struct cpumask) * 8)
+
+static void __arena * __arena page_frag_cur_page[NR_CPUS];
+static int __arena page_frag_cur_offset[NR_CPUS];
+
+/* Simple page_frag allocator */
+static inline void __arena* bpf_alloc(unsigned int size)
+{
+	__u64 __arena *obj_cnt;
+	__u32 cpu = bpf_get_smp_processor_id();
+	void __arena *page = page_frag_cur_page[cpu];
+	int __arena *cur_offset = &page_frag_cur_offset[cpu];
+	int offset;
+
+	size = round_up(size, 8);
+	if (size >= PAGE_SIZE - 8)
+		return NULL;
+	if (!page) {
+refill:
+		page = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+		if (!page)
+			return NULL;
+		cast_kern(page);
+		page_frag_cur_page[cpu] = page;
+		*cur_offset = PAGE_SIZE - 8;
+		obj_cnt = page + PAGE_SIZE - 8;
+		*obj_cnt = 0;
+	} else {
+		cast_kern(page);
+		obj_cnt = page + PAGE_SIZE - 8;
+	}
+
+	offset = *cur_offset - size;
+	if (offset < 0)
+		goto refill;
+
+	(*obj_cnt)++;
+	*cur_offset = offset;
+	return page + offset;
+}
+
+static inline void bpf_free(void __arena *addr)
+{
+	__u64 __arena *obj_cnt;
+
+	addr = (void __arena *)(((long)addr) & ~(PAGE_SIZE - 1));
+	obj_cnt = addr + PAGE_SIZE - 8;
+	if (--(*obj_cnt) == 0)
+		bpf_arena_free_pages(&arena, addr, 1);
+}
+#else
+static inline void __arena* bpf_alloc(unsigned int size) { return NULL; }
+static inline void bpf_free(void __arena *addr) {}
+#endif
diff --git a/tools/testing/selftests/bpf/bpf_arena_common.h b/tools/testing/selftests/bpf/bpf_arena_common.h
new file mode 100644
index 000000000000..16f8ce832004
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_arena_common.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#pragma once
+
+#ifndef WRITE_ONCE
+#define WRITE_ONCE(x, val) ((*(volatile typeof(x) *) &(x)) = (val))
+#endif
+
+#ifndef NUMA_NO_NODE
+#define	NUMA_NO_NODE	(-1)
+#endif
+
+#ifndef arena_container_of
+#define arena_container_of(ptr, type, member)			\
+	({							\
+		void __arena *__mptr = (void __arena *)(ptr);	\
+		((type *)(__mptr - offsetof(type, member)));	\
+	})
+#endif
+
+#ifdef __BPF__ /* when compiled as bpf program */
+
+#ifndef PAGE_SIZE
+#define PAGE_SIZE __PAGE_SIZE
+/*
+ * for older kernels try sizeof(struct genradix_node)
+ * or flexible:
+ * static inline long __bpf_page_size(void) {
+ *   return bpf_core_enum_value(enum page_size_enum___l, __PAGE_SIZE___l) ?: sizeof(struct genradix_node);
+ * }
+ * but generated code is not great.
+ */
+#endif
+
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST) && !defined(BPF_ARENA_FORCE_ASM)
+#define __arena __attribute__((address_space(1)))
+#define __arena_global __attribute__((address_space(1)))
+#define cast_kern(ptr) /* nop for bpf prog. emitted by LLVM */
+#define cast_user(ptr) /* nop for bpf prog. emitted by LLVM */
+#else
+#define __arena
+#define __arena_global SEC(".addr_space.1")
+#define cast_kern(ptr) bpf_addr_space_cast(ptr, 0, 1)
+#define cast_user(ptr) bpf_addr_space_cast(ptr, 1, 0)
+#endif
+
+void __arena* bpf_arena_alloc_pages(void *map, void __arena *addr, __u32 page_cnt,
+				    int node_id, __u64 flags) __ksym __weak;
+int bpf_arena_reserve_pages(void *map, void __arena *addr, __u32 page_cnt) __ksym __weak;
+void bpf_arena_free_pages(void *map, void __arena *ptr, __u32 page_cnt) __ksym __weak;
+
+#define arena_base(map) ((void __arena *)((struct bpf_arena *)(map))->user_vm_start)
+
+#else /* when compiled as user space code */
+
+#define __arena
+#define __arg_arena
+#define cast_kern(ptr) /* nop for user space */
+#define cast_user(ptr) /* nop for user space */
+__weak char arena[1];
+
+#ifndef offsetof
+#define offsetof(type, member)  ((unsigned long)&((type *)0)->member)
+#endif
+
+static inline void __arena* bpf_arena_alloc_pages(void *map, void *addr, __u32 page_cnt,
+						  int node_id, __u64 flags)
+{
+	return NULL;
+}
+static inline void bpf_arena_free_pages(void *map, void __arena *ptr, __u32 page_cnt)
+{
+}
+
+#endif
diff --git a/tools/testing/selftests/bpf/bpf_arena_htab.h b/tools/testing/selftests/bpf/bpf_arena_htab.h
new file mode 100644
index 000000000000..acc01a876668
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_arena_htab.h
@@ -0,0 +1,100 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#pragma once
+#include <errno.h>
+#include "bpf_arena_alloc.h"
+#include "bpf_arena_list.h"
+
+struct htab_bucket {
+	struct arena_list_head head;
+};
+typedef struct htab_bucket __arena htab_bucket_t;
+
+struct htab {
+	htab_bucket_t *buckets;
+	int n_buckets;
+};
+typedef struct htab __arena htab_t;
+
+static inline htab_bucket_t *__select_bucket(htab_t *htab, __u32 hash)
+{
+	htab_bucket_t *b = htab->buckets;
+
+	cast_kern(b);
+	return &b[hash & (htab->n_buckets - 1)];
+}
+
+static inline arena_list_head_t *select_bucket(htab_t *htab, __u32 hash)
+{
+	return &__select_bucket(htab, hash)->head;
+}
+
+struct hashtab_elem {
+	int hash;
+	int key;
+	int value;
+	struct arena_list_node hash_node;
+};
+typedef struct hashtab_elem __arena hashtab_elem_t;
+
+static hashtab_elem_t *lookup_elem_raw(arena_list_head_t *head, __u32 hash, int key)
+{
+	hashtab_elem_t *l;
+
+	list_for_each_entry(l, head, hash_node)
+		if (l->hash == hash && l->key == key)
+			return l;
+
+	return NULL;
+}
+
+static int htab_hash(int key)
+{
+	return key;
+}
+
+__weak int htab_lookup_elem(htab_t *htab __arg_arena, int key)
+{
+	hashtab_elem_t *l_old;
+	arena_list_head_t *head;
+
+	cast_kern(htab);
+	head = select_bucket(htab, key);
+	l_old = lookup_elem_raw(head, htab_hash(key), key);
+	if (l_old)
+		return l_old->value;
+	return 0;
+}
+
+__weak int htab_update_elem(htab_t *htab __arg_arena, int key, int value)
+{
+	hashtab_elem_t *l_new = NULL, *l_old;
+	arena_list_head_t *head;
+
+	cast_kern(htab);
+	head = select_bucket(htab, key);
+	l_old = lookup_elem_raw(head, htab_hash(key), key);
+
+	l_new = bpf_alloc(sizeof(*l_new));
+	if (!l_new)
+		return -ENOMEM;
+	l_new->key = key;
+	l_new->hash = htab_hash(key);
+	l_new->value = value;
+
+	list_add_head(&l_new->hash_node, head);
+	if (l_old) {
+		list_del(&l_old->hash_node);
+		bpf_free(l_old);
+	}
+	return 0;
+}
+
+void htab_init(htab_t *htab)
+{
+	void __arena *buckets = bpf_arena_alloc_pages(&arena, NULL, 2, NUMA_NO_NODE, 0);
+
+	cast_user(buckets);
+	htab->buckets = buckets;
+	htab->n_buckets = 2 * PAGE_SIZE / sizeof(struct htab_bucket);
+}
diff --git a/tools/testing/selftests/bpf/bpf_arena_list.h b/tools/testing/selftests/bpf/bpf_arena_list.h
new file mode 100644
index 000000000000..e16fa7d95fcf
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_arena_list.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#pragma once
+#include "bpf_arena_common.h"
+
+struct arena_list_node;
+
+typedef struct arena_list_node __arena arena_list_node_t;
+
+struct arena_list_node {
+	arena_list_node_t *next;
+	arena_list_node_t * __arena *pprev;
+};
+
+struct arena_list_head {
+	struct arena_list_node __arena *first;
+};
+typedef struct arena_list_head __arena arena_list_head_t;
+
+#define list_entry(ptr, type, member) arena_container_of(ptr, type, member)
+
+#define list_entry_safe(ptr, type, member) \
+	({ typeof(*ptr) * ___ptr = (ptr); \
+	 ___ptr ? ({ cast_kern(___ptr); list_entry(___ptr, type, member); }) : NULL; \
+	 })
+
+#ifndef __BPF__
+static inline void *bpf_iter_num_new(struct bpf_iter_num *it, int i, int j) { return NULL; }
+static inline void bpf_iter_num_destroy(struct bpf_iter_num *it) {}
+static inline bool bpf_iter_num_next(struct bpf_iter_num *it) { return true; }
+#define cond_break ({})
+#define can_loop true
+#endif
+
+/* Safely walk link list elements. Deletion of elements is allowed. */
+#define list_for_each_entry(pos, head, member)					\
+	for (void * ___tmp = (pos = list_entry_safe((head)->first,		\
+						    typeof(*(pos)), member),	\
+			      (void *)0);					\
+	     pos && ({ ___tmp = (void *)pos->member.next; 1; }) && can_loop;    \
+	     pos = list_entry_safe((void __arena *)___tmp, typeof(*(pos)), member))
+
+static inline void list_add_head(arena_list_node_t *n, arena_list_head_t *h)
+{
+	arena_list_node_t *first = h->first, * __arena *tmp;
+
+	cast_user(first);
+	cast_kern(n);
+	WRITE_ONCE(n->next, first);
+	cast_kern(first);
+	if (first) {
+		tmp = &n->next;
+		cast_user(tmp);
+		WRITE_ONCE(first->pprev, tmp);
+	}
+	cast_user(n);
+	WRITE_ONCE(h->first, n);
+
+	tmp = &h->first;
+	cast_user(tmp);
+	cast_kern(n);
+	WRITE_ONCE(n->pprev, tmp);
+}
+
+static inline void __list_del(arena_list_node_t *n)
+{
+	arena_list_node_t *next = n->next;
+	arena_list_node_t * __arena *pprev = n->pprev;
+
+	cast_user(next);
+	cast_kern(pprev);
+	WRITE_ONCE(*pprev, next);
+	if (next) {
+		cast_user(pprev);
+		cast_kern(next);
+		WRITE_ONCE(next->pprev, pprev);
+	}
+}
+
+#define POISON_POINTER_DELTA 0
+
+#define LIST_POISON1  ((void __arena *) 0x100 + POISON_POINTER_DELTA)
+#define LIST_POISON2  ((void __arena *) 0x122 + POISON_POINTER_DELTA)
+
+static inline void list_del(arena_list_node_t *n)
+{
+	__list_del(n);
+	n->next = LIST_POISON1;
+	n->pprev = LIST_POISON2;
+}
diff --git a/tools/testing/selftests/bpf/bpf_arena_strsearch.h b/tools/testing/selftests/bpf/bpf_arena_strsearch.h
new file mode 100644
index 000000000000..c1b6eaa905bb
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_arena_strsearch.h
@@ -0,0 +1,128 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#pragma once
+#include "bpf_arena_common.h"
+
+__noinline int bpf_arena_strlen(const char __arena *s __arg_arena)
+{
+	const char __arena *sc;
+
+	for (sc = s; *sc != '\0'; ++sc)
+		cond_break;
+	return sc - s;
+}
+
+/**
+ * glob_match - Shell-style pattern matching, like !fnmatch(pat, str, 0)
+ * @pat: Shell-style pattern to match, e.g. "*.[ch]".
+ * @str: String to match.  The pattern must match the entire string.
+ *
+ * Perform shell-style glob matching, returning true (1) if the match
+ * succeeds, or false (0) if it fails.  Equivalent to !fnmatch(@pat, @str, 0).
+ *
+ * Pattern metacharacters are ?, *, [ and \.
+ * (And, inside character classes, !, - and ].)
+ *
+ * This is small and simple implementation intended for device blacklists
+ * where a string is matched against a number of patterns.  Thus, it
+ * does not preprocess the patterns.  It is non-recursive, and run-time
+ * is at most quadratic: strlen(@str)*strlen(@pat).
+ *
+ * An example of the worst case is glob_match("*aaaaa", "aaaaaaaaaa");
+ * it takes 6 passes over the pattern before matching the string.
+ *
+ * Like !fnmatch(@pat, @str, 0) and unlike the shell, this does NOT
+ * treat / or leading . specially; it isn't actually used for pathnames.
+ *
+ * Note that according to glob(7) (and unlike bash), character classes
+ * are complemented by a leading !; this does not support the regex-style
+ * [^a-z] syntax.
+ *
+ * An opening bracket without a matching close is matched literally.
+ */
+__noinline bool glob_match(char const __arena *pat __arg_arena, char const __arena *str __arg_arena)
+{
+	/*
+	 * Backtrack to previous * on mismatch and retry starting one
+	 * character later in the string.  Because * matches all characters
+	 * (no exception for /), it can be easily proved that there's
+	 * never a need to backtrack multiple levels.
+	 */
+	char const __arena *back_pat = NULL, *back_str;
+
+	/*
+	 * Loop over each token (character or class) in pat, matching
+	 * it against the remaining unmatched tail of str.  Return false
+	 * on mismatch, or true after matching the trailing nul bytes.
+	 */
+	for (;;) {
+		unsigned char c = *str++;
+		unsigned char d = *pat++;
+
+		switch (d) {
+		case '?':	/* Wildcard: anything but nul */
+			if (c == '\0')
+				return false;
+			break;
+		case '*':	/* Any-length wildcard */
+			if (*pat == '\0')	/* Optimize trailing * case */
+				return true;
+			back_pat = pat;
+			back_str = --str;	/* Allow zero-length match */
+			break;
+		case '[': {	/* Character class */
+			bool match = false, inverted = (*pat == '!');
+			char const __arena *class = pat + inverted;
+			unsigned char a = *class++;
+
+			/*
+			 * Iterate over each span in the character class.
+			 * A span is either a single character a, or a
+			 * range a-b.  The first span may begin with ']'.
+			 */
+			do {
+				unsigned char b = a;
+
+				if (a == '\0')	/* Malformed */
+					goto literal;
+
+				if (class[0] == '-' && class[1] != ']') {
+					b = class[1];
+
+					if (b == '\0')
+						goto literal;
+
+					class += 2;
+					/* Any special action if a > b? */
+				}
+				match |= (a <= c && c <= b);
+				cond_break;
+			} while ((a = *class++) != ']');
+
+			if (match == inverted)
+				goto backtrack;
+			pat = class;
+			}
+			break;
+		case '\\':
+			d = *pat++;
+			__attribute__((__fallthrough__));
+		default:	/* Literal character */
+literal:
+			if (c == d) {
+				if (d == '\0')
+					return true;
+				break;
+			}
+backtrack:
+			if (c == '\0' || !back_pat)
+				return false;	/* No point continuing */
+			/* Try again from last *, one character later in str. */
+			pat = back_pat;
+			str = ++back_str;
+			break;
+		}
+		cond_break;
+	}
+	return false;
+}
diff --git a/tools/testing/selftests/bpf/bpf_atomic.h b/tools/testing/selftests/bpf/bpf_atomic.h
new file mode 100644
index 000000000000..c550e5711967
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_atomic.h
@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#ifndef BPF_ATOMIC_H
+#define BPF_ATOMIC_H
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_experimental.h"
+
+extern bool CONFIG_X86_64 __kconfig __weak;
+
+/*
+ * __unqual_typeof(x) - Declare an unqualified scalar type, leaving
+ *			non-scalar types unchanged,
+ *
+ * Prefer C11 _Generic for better compile-times and simpler code. Note: 'char'
+ * is not type-compatible with 'signed char', and we define a separate case.
+ *
+ * This is copied verbatim from kernel's include/linux/compiler_types.h, but
+ * with default expression (for pointers) changed from (x) to (typeof(x)0).
+ *
+ * This is because LLVM has a bug where for lvalue (x), it does not get rid of
+ * an extra address_space qualifier, but does in case of rvalue (typeof(x)0).
+ * Hence, for pointers, we need to create an rvalue expression to get the
+ * desired type. See https://github.com/llvm/llvm-project/issues/53400.
+ */
+#define __scalar_type_to_expr_cases(type) \
+	unsigned type : (unsigned type)0, signed type : (signed type)0
+
+#define __unqual_typeof(x)                              \
+	typeof(_Generic((x),                            \
+		char: (char)0,                          \
+		__scalar_type_to_expr_cases(char),      \
+		__scalar_type_to_expr_cases(short),     \
+		__scalar_type_to_expr_cases(int),       \
+		__scalar_type_to_expr_cases(long),      \
+		__scalar_type_to_expr_cases(long long), \
+		default: (typeof(x))0))
+
+/* No-op for BPF */
+#define cpu_relax() ({})
+
+#define READ_ONCE(x) (*(volatile typeof(x) *)&(x))
+
+#define WRITE_ONCE(x, val) ((*(volatile typeof(x) *)&(x)) = (val))
+
+#define cmpxchg(p, old, new) __sync_val_compare_and_swap((p), old, new)
+
+#define try_cmpxchg(p, pold, new)                                 \
+	({                                                        \
+		__unqual_typeof(*(pold)) __o = *(pold);           \
+		__unqual_typeof(*(p)) __r = cmpxchg(p, __o, new); \
+		if (__r != __o)                                   \
+			*(pold) = __r;                            \
+		__r == __o;                                       \
+	})
+
+#define try_cmpxchg_relaxed(p, pold, new) try_cmpxchg(p, pold, new)
+
+#define try_cmpxchg_acquire(p, pold, new) try_cmpxchg(p, pold, new)
+
+#define smp_mb()                                 \
+	({                                       \
+		volatile unsigned long __val;    \
+		__sync_fetch_and_add(&__val, 0); \
+	})
+
+#define smp_rmb()                   \
+	({                          \
+		if (!CONFIG_X86_64) \
+			smp_mb();   \
+		else                \
+			barrier();  \
+	})
+
+#define smp_wmb()                   \
+	({                          \
+		if (!CONFIG_X86_64) \
+			smp_mb();   \
+		else                \
+			barrier();  \
+	})
+
+/* Control dependency provides LOAD->STORE, provide LOAD->LOAD */
+#define smp_acquire__after_ctrl_dep() ({ smp_rmb(); })
+
+#define smp_load_acquire(p)                                  \
+	({                                                   \
+		__unqual_typeof(*(p)) __v = READ_ONCE(*(p)); \
+		if (!CONFIG_X86_64)                          \
+			smp_mb();                            \
+		barrier();                                   \
+		__v;                                         \
+	})
+
+#define smp_store_release(p, val)      \
+	({                             \
+		if (!CONFIG_X86_64)    \
+			smp_mb();      \
+		barrier();             \
+		WRITE_ONCE(*(p), val); \
+	})
+
+#define smp_cond_load_relaxed_label(p, cond_expr, label)                \
+	({                                                              \
+		typeof(p) __ptr = (p);                                  \
+		__unqual_typeof(*(p)) VAL;                              \
+		for (;;) {                                              \
+			VAL = (__unqual_typeof(*(p)))READ_ONCE(*__ptr); \
+			if (cond_expr)                                  \
+				break;                                  \
+			cond_break_label(label);                        \
+			cpu_relax();                                    \
+		}                                                       \
+		(typeof(*(p)))VAL;                                      \
+	})
+
+#define smp_cond_load_acquire_label(p, cond_expr, label)                  \
+	({                                                                \
+		__unqual_typeof(*p) __val =                               \
+			smp_cond_load_relaxed_label(p, cond_expr, label); \
+		smp_acquire__after_ctrl_dep();                            \
+		(typeof(*(p)))__val;                                      \
+	})
+
+#define atomic_read(p) READ_ONCE((p)->counter)
+
+#define atomic_cond_read_relaxed_label(p, cond_expr, label) \
+	smp_cond_load_relaxed_label(&(p)->counter, cond_expr, label)
+
+#define atomic_cond_read_acquire_label(p, cond_expr, label) \
+	smp_cond_load_acquire_label(&(p)->counter, cond_expr, label)
+
+#define atomic_try_cmpxchg_relaxed(p, pold, new) \
+	try_cmpxchg_relaxed(&(p)->counter, pold, new)
+
+#define atomic_try_cmpxchg_acquire(p, pold, new) \
+	try_cmpxchg_acquire(&(p)->counter, pold, new)
+
+#endif /* BPF_ATOMIC_H */
diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index 424f7bbbfe9b..2cd9165c7348 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -14,7 +14,8 @@
  *	type ID of a struct in program BTF.
  *
  *	The 'local_type_id' parameter must be a known constant.
- *	The 'meta' parameter is a hidden argument that is ignored.
+ *	The 'meta' parameter is rewritten by the verifier, no need for BPF
+ *	program to set it.
  * Returns
  *	A pointer to an object of the type corresponding to the passed in
  *	'local_type_id', or NULL on failure.
@@ -28,7 +29,8 @@ extern void *bpf_obj_new_impl(__u64 local_type_id, void *meta) __ksym;
  *	Free an allocated object. All fields of the object that require
  *	destruction will be destructed before the storage is freed.
  *
- *	The 'meta' parameter is a hidden argument that is ignored.
+ *	The 'meta' parameter is rewritten by the verifier, no need for BPF
+ *	program to set it.
  * Returns
  *	Void.
  */
@@ -38,18 +40,50 @@ extern void bpf_obj_drop_impl(void *kptr, void *meta) __ksym;
 #define bpf_obj_drop(kptr) bpf_obj_drop_impl(kptr, NULL)
 
 /* Description
+ *	Increment the refcount on a refcounted local kptr, turning the
+ *	non-owning reference input into an owning reference in the process.
+ *
+ *	The 'meta' parameter is rewritten by the verifier, no need for BPF
+ *	program to set it.
+ * Returns
+ *	An owning reference to the object pointed to by 'kptr'
+ */
+extern void *bpf_refcount_acquire_impl(void *kptr, void *meta) __ksym;
+
+/* Convenience macro to wrap over bpf_refcount_acquire_impl */
+#define bpf_refcount_acquire(kptr) bpf_refcount_acquire_impl(kptr, NULL)
+
+/* Description
  *	Add a new entry to the beginning of the BPF linked list.
+ *
+ *	The 'meta' and 'off' parameters are rewritten by the verifier, no need
+ *	for BPF programs to set them
  * Returns
- *	Void.
+ *	0 if the node was successfully added
+ *	-EINVAL if the node wasn't added because it's already in a list
  */
-extern void bpf_list_push_front(struct bpf_list_head *head, struct bpf_list_node *node) __ksym;
+extern int bpf_list_push_front_impl(struct bpf_list_head *head,
+				    struct bpf_list_node *node,
+				    void *meta, __u64 off) __ksym;
+
+/* Convenience macro to wrap over bpf_list_push_front_impl */
+#define bpf_list_push_front(head, node) bpf_list_push_front_impl(head, node, NULL, 0)
 
 /* Description
  *	Add a new entry to the end of the BPF linked list.
+ *
+ *	The 'meta' and 'off' parameters are rewritten by the verifier, no need
+ *	for BPF programs to set them
  * Returns
- *	Void.
+ *	0 if the node was successfully added
+ *	-EINVAL if the node wasn't added because it's already in a list
  */
-extern void bpf_list_push_back(struct bpf_list_head *head, struct bpf_list_node *node) __ksym;
+extern int bpf_list_push_back_impl(struct bpf_list_head *head,
+				   struct bpf_list_node *node,
+				   void *meta, __u64 off) __ksym;
+
+/* Convenience macro to wrap over bpf_list_push_back_impl */
+#define bpf_list_push_back(head, node) bpf_list_push_back_impl(head, node, NULL, 0)
 
 /* Description
  *	Remove the entry at the beginning of the BPF linked list.
@@ -65,4 +99,558 @@ extern struct bpf_list_node *bpf_list_pop_front(struct bpf_list_head *head) __ks
  */
 extern struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head) __ksym;
 
+/* Description
+ *	Remove 'node' from rbtree with root 'root'
+ * Returns
+ * 	Pointer to the removed node, or NULL if 'root' didn't contain 'node'
+ */
+extern struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root,
+					     struct bpf_rb_node *node) __ksym;
+
+/* Description
+ *	Add 'node' to rbtree with root 'root' using comparator 'less'
+ *
+ *	The 'meta' and 'off' parameters are rewritten by the verifier, no need
+ *	for BPF programs to set them
+ * Returns
+ *	0 if the node was successfully added
+ *	-EINVAL if the node wasn't added because it's already in a tree
+ */
+extern int bpf_rbtree_add_impl(struct bpf_rb_root *root, struct bpf_rb_node *node,
+			       bool (less)(struct bpf_rb_node *a, const struct bpf_rb_node *b),
+			       void *meta, __u64 off) __ksym;
+
+/* Convenience macro to wrap over bpf_rbtree_add_impl */
+#define bpf_rbtree_add(head, node, less) bpf_rbtree_add_impl(head, node, less, NULL, 0)
+
+/* Description
+ *	Return the first (leftmost) node in input tree
+ * Returns
+ *	Pointer to the node, which is _not_ removed from the tree. If the tree
+ *	contains no nodes, returns NULL.
+ */
+extern struct bpf_rb_node *bpf_rbtree_first(struct bpf_rb_root *root) __ksym;
+
+/* Description
+ *	Allocates a percpu object of the type represented by 'local_type_id' in
+ *	program BTF. User may use the bpf_core_type_id_local macro to pass the
+ *	type ID of a struct in program BTF.
+ *
+ *	The 'local_type_id' parameter must be a known constant.
+ *	The 'meta' parameter is rewritten by the verifier, no need for BPF
+ *	program to set it.
+ * Returns
+ *	A pointer to a percpu object of the type corresponding to the passed in
+ *	'local_type_id', or NULL on failure.
+ */
+extern void *bpf_percpu_obj_new_impl(__u64 local_type_id, void *meta) __ksym;
+
+/* Convenience macro to wrap over bpf_percpu_obj_new_impl */
+#define bpf_percpu_obj_new(type) ((type __percpu_kptr *)bpf_percpu_obj_new_impl(bpf_core_type_id_local(type), NULL))
+
+/* Description
+ *	Free an allocated percpu object. All fields of the object that require
+ *	destruction will be destructed before the storage is freed.
+ *
+ *	The 'meta' parameter is rewritten by the verifier, no need for BPF
+ *	program to set it.
+ * Returns
+ *	Void.
+ */
+extern void bpf_percpu_obj_drop_impl(void *kptr, void *meta) __ksym;
+
+struct bpf_iter_task_vma;
+
+extern int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it,
+				 struct task_struct *task,
+				 __u64 addr) __ksym;
+extern struct vm_area_struct *bpf_iter_task_vma_next(struct bpf_iter_task_vma *it) __ksym;
+extern void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it) __ksym;
+
+/* Convenience macro to wrap over bpf_obj_drop_impl */
+#define bpf_percpu_obj_drop(kptr) bpf_percpu_obj_drop_impl(kptr, NULL)
+
+/* Description
+ *	Throw a BPF exception from the program, immediately terminating its
+ *	execution and unwinding the stack. The supplied 'cookie' parameter
+ *	will be the return value of the program when an exception is thrown,
+ *	and the default exception callback is used. Otherwise, if an exception
+ *	callback is set using the '__exception_cb(callback)' declaration tag
+ *	on the main program, the 'cookie' parameter will be the callback's only
+ *	input argument.
+ *
+ *	Thus, in case of default exception callback, 'cookie' is subjected to
+ *	constraints on the program's return value (as with R0 on exit).
+ *	Otherwise, the return value of the marked exception callback will be
+ *	subjected to the same checks.
+ *
+ *	Note that throwing an exception with lingering resources (locks,
+ *	references, etc.) will lead to a verification error.
+ *
+ *	Note that callbacks *cannot* call this helper.
+ * Returns
+ *	Never.
+ * Throws
+ *	An exception with the specified 'cookie' value.
+ */
+extern void bpf_throw(u64 cookie) __ksym;
+
+/* Description
+ *	Acquire a reference on the exe_file member field belonging to the
+ *	mm_struct that is nested within the supplied task_struct. The supplied
+ *	task_struct must be trusted/referenced.
+ * Returns
+ *	A referenced file pointer pointing to the exe_file member field of the
+ *	mm_struct nested in the supplied task_struct, or NULL.
+ */
+extern struct file *bpf_get_task_exe_file(struct task_struct *task) __ksym;
+
+/* Description
+ *	Release a reference on the supplied file. The supplied file must be
+ *	acquired.
+ */
+extern void bpf_put_file(struct file *file) __ksym;
+
+/* Description
+ *	Resolve a pathname for the supplied path and store it in the supplied
+ *	buffer. The supplied path must be trusted/referenced.
+ * Returns
+ *	A positive integer corresponding to the length of the resolved pathname,
+ *	including the NULL termination character, stored in the supplied
+ *	buffer. On error, a negative integer is returned.
+ */
+extern int bpf_path_d_path(const struct path *path, char *buf, size_t buf__sz) __ksym;
+
+/* This macro must be used to mark the exception callback corresponding to the
+ * main program. For example:
+ *
+ * int exception_cb(u64 cookie) {
+ *	return cookie;
+ * }
+ *
+ * SEC("tc")
+ * __exception_cb(exception_cb)
+ * int main_prog(struct __sk_buff *ctx) {
+ *	...
+ *	return TC_ACT_OK;
+ * }
+ *
+ * Here, exception callback for the main program will be 'exception_cb'. Note
+ * that this attribute can only be used once, and multiple exception callbacks
+ * specified for the main program will lead to verification error.
+ */
+#define __exception_cb(name) __attribute__((btf_decl_tag("exception_callback:" #name)))
+
+#define __bpf_assert_signed(x) _Generic((x), \
+    unsigned long: 0,       \
+    unsigned long long: 0,  \
+    signed long: 1,         \
+    signed long long: 1     \
+)
+
+#define __bpf_assert_check(LHS, op, RHS)								 \
+	_Static_assert(sizeof(&(LHS)), "1st argument must be an lvalue expression");			 \
+	_Static_assert(sizeof(LHS) == 8, "Only 8-byte integers are supported\n");			 \
+	_Static_assert(__builtin_constant_p(__bpf_assert_signed(LHS)), "internal static assert");	 \
+	_Static_assert(__builtin_constant_p((RHS)), "2nd argument must be a constant expression")
+
+#define __bpf_assert(LHS, op, cons, RHS, VAL)							\
+	({											\
+		(void)bpf_throw;								\
+		asm volatile ("if %[lhs] " op " %[rhs] goto +2; r1 = %[value]; call bpf_throw"	\
+			       : : [lhs] "r"(LHS), [rhs] cons(RHS), [value] "ri"(VAL) : );	\
+	})
+
+#define __bpf_assert_op_sign(LHS, op, cons, RHS, VAL, supp_sign)			\
+	({										\
+		__bpf_assert_check(LHS, op, RHS);					\
+		if (__bpf_assert_signed(LHS) && !(supp_sign))				\
+			__bpf_assert(LHS, "s" #op, cons, RHS, VAL);			\
+		else									\
+			__bpf_assert(LHS, #op, cons, RHS, VAL);				\
+	 })
+
+#define __bpf_assert_op(LHS, op, RHS, VAL, supp_sign)					\
+	({										\
+		if (sizeof(typeof(RHS)) == 8) {						\
+			const typeof(RHS) rhs_var = (RHS);				\
+			__bpf_assert_op_sign(LHS, op, "r", rhs_var, VAL, supp_sign);	\
+		} else {								\
+			__bpf_assert_op_sign(LHS, op, "i", RHS, VAL, supp_sign);	\
+		}									\
+	 })
+
+#define __cmp_cannot_be_signed(x) \
+	__builtin_strcmp(#x, "==") == 0 || __builtin_strcmp(#x, "!=") == 0 || \
+	__builtin_strcmp(#x, "&") == 0
+
+#define __is_signed_type(type) (((type)(-1)) < (type)1)
+
+#define __bpf_cmp(LHS, OP, PRED, RHS, DEFAULT)						\
+	({											\
+		__label__ l_true;								\
+		bool ret = DEFAULT;								\
+		asm volatile goto("if %[lhs] " OP " %[rhs] goto %l[l_true]"		\
+				  :: [lhs] "r"((short)LHS), [rhs] PRED (RHS) :: l_true);	\
+		ret = !DEFAULT;									\
+l_true:												\
+		ret;										\
+       })
+
+/* C type conversions coupled with comparison operator are tricky.
+ * Make sure BPF program is compiled with -Wsign-compare then
+ * __lhs OP __rhs below will catch the mistake.
+ * Be aware that we check only __lhs to figure out the sign of compare.
+ */
+#define _bpf_cmp(LHS, OP, RHS, UNLIKELY)								\
+	({											\
+		typeof(LHS) __lhs = (LHS);							\
+		typeof(RHS) __rhs = (RHS);							\
+		bool ret;									\
+		_Static_assert(sizeof(&(LHS)), "1st argument must be an lvalue expression");	\
+		(void)(__lhs OP __rhs);								\
+		if (__cmp_cannot_be_signed(OP) || !__is_signed_type(typeof(__lhs))) {		\
+			if (sizeof(__rhs) == 8)							\
+				/* "i" will truncate 64-bit constant into s32,			\
+				 * so we have to use extra register via "r".			\
+				 */								\
+				ret = __bpf_cmp(__lhs, #OP, "r", __rhs, UNLIKELY);		\
+			else									\
+				ret = __bpf_cmp(__lhs, #OP, "ri", __rhs, UNLIKELY);		\
+		} else {									\
+			if (sizeof(__rhs) == 8)							\
+				ret = __bpf_cmp(__lhs, "s"#OP, "r", __rhs, UNLIKELY);		\
+			else									\
+				ret = __bpf_cmp(__lhs, "s"#OP, "ri", __rhs, UNLIKELY);		\
+		}										\
+		ret;										\
+       })
+
+#ifndef bpf_cmp_unlikely
+#define bpf_cmp_unlikely(LHS, OP, RHS) _bpf_cmp(LHS, OP, RHS, true)
+#endif
+
+#ifndef bpf_cmp_likely
+#define bpf_cmp_likely(LHS, OP, RHS)								\
+	({											\
+		bool ret = 0;									\
+		if (__builtin_strcmp(#OP, "==") == 0)						\
+			ret = _bpf_cmp(LHS, !=, RHS, false);					\
+		else if (__builtin_strcmp(#OP, "!=") == 0)					\
+			ret = _bpf_cmp(LHS, ==, RHS, false);					\
+		else if (__builtin_strcmp(#OP, "<=") == 0)					\
+			ret = _bpf_cmp(LHS, >, RHS, false);					\
+		else if (__builtin_strcmp(#OP, "<") == 0)					\
+			ret = _bpf_cmp(LHS, >=, RHS, false);					\
+		else if (__builtin_strcmp(#OP, ">") == 0)					\
+			ret = _bpf_cmp(LHS, <=, RHS, false);					\
+		else if (__builtin_strcmp(#OP, ">=") == 0)					\
+			ret = _bpf_cmp(LHS, <, RHS, false);					\
+		else										\
+			asm volatile("r0 " #OP " invalid compare");				\
+		ret;										\
+       })
+#endif
+
+/*
+ * Note that cond_break can only be portably used in the body of a breakable
+ * construct, whereas can_loop can be used anywhere.
+ */
+#ifdef __BPF_FEATURE_MAY_GOTO
+#define can_loop					\
+	({ __label__ l_break, l_continue;		\
+	bool ret = true;				\
+	asm volatile goto("may_goto %l[l_break]"	\
+		      :::: l_break);			\
+	goto l_continue;				\
+	l_break: ret = false;				\
+	l_continue:;					\
+	ret;						\
+	})
+
+#define __cond_break(expr)				\
+	({ __label__ l_break, l_continue;		\
+	asm volatile goto("may_goto %l[l_break]"	\
+		      :::: l_break);			\
+	goto l_continue;				\
+	l_break: expr;					\
+	l_continue:;					\
+	})
+#else
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+#define can_loop					\
+	({ __label__ l_break, l_continue;		\
+	bool ret = true;				\
+	asm volatile goto("1:.byte 0xe5;		\
+		      .byte 0;				\
+		      .long ((%l[l_break] - 1b - 8) / 8) & 0xffff;	\
+		      .short 0"				\
+		      :::: l_break);			\
+	goto l_continue;				\
+	l_break: ret = false;				\
+	l_continue:;					\
+	ret;						\
+	})
+
+#define __cond_break(expr)				\
+	({ __label__ l_break, l_continue;		\
+	asm volatile goto("1:.byte 0xe5;		\
+		      .byte 0;				\
+		      .long ((%l[l_break] - 1b - 8) / 8) & 0xffff;	\
+		      .short 0"				\
+		      :::: l_break);			\
+	goto l_continue;				\
+	l_break: expr;					\
+	l_continue:;					\
+	})
+#else
+#define can_loop					\
+	({ __label__ l_break, l_continue;		\
+	bool ret = true;				\
+	asm volatile goto("1:.byte 0xe5;		\
+		      .byte 0;				\
+		      .long (((%l[l_break] - 1b - 8) / 8) & 0xffff) << 16;	\
+		      .short 0"				\
+		      :::: l_break);			\
+	goto l_continue;				\
+	l_break: ret = false;				\
+	l_continue:;					\
+	ret;						\
+	})
+
+#define __cond_break(expr)				\
+	({ __label__ l_break, l_continue;		\
+	asm volatile goto("1:.byte 0xe5;		\
+		      .byte 0;				\
+		      .long (((%l[l_break] - 1b - 8) / 8) & 0xffff) << 16;	\
+		      .short 0"				\
+		      :::: l_break);			\
+	goto l_continue;				\
+	l_break: expr;					\
+	l_continue:;					\
+	})
+#endif
+#endif
+
+#define cond_break __cond_break(break)
+#define cond_break_label(label) __cond_break(goto label)
+
+#ifndef bpf_nop_mov
+#define bpf_nop_mov(var) \
+	asm volatile("%[reg]=%[reg]"::[reg]"r"((short)var))
+#endif
+
+/* emit instruction:
+ * rX = rX .off = BPF_ADDR_SPACE_CAST .imm32 = (dst_as << 16) | src_as
+ */
+#ifndef bpf_addr_space_cast
+#define bpf_addr_space_cast(var, dst_as, src_as)\
+	asm volatile(".byte 0xBF;		\
+		     .ifc %[reg], r0;		\
+		     .byte 0x00;		\
+		     .endif;			\
+		     .ifc %[reg], r1;		\
+		     .byte 0x11;		\
+		     .endif;			\
+		     .ifc %[reg], r2;		\
+		     .byte 0x22;		\
+		     .endif;			\
+		     .ifc %[reg], r3;		\
+		     .byte 0x33;		\
+		     .endif;			\
+		     .ifc %[reg], r4;		\
+		     .byte 0x44;		\
+		     .endif;			\
+		     .ifc %[reg], r5;		\
+		     .byte 0x55;		\
+		     .endif;			\
+		     .ifc %[reg], r6;		\
+		     .byte 0x66;		\
+		     .endif;			\
+		     .ifc %[reg], r7;		\
+		     .byte 0x77;		\
+		     .endif;			\
+		     .ifc %[reg], r8;		\
+		     .byte 0x88;		\
+		     .endif;			\
+		     .ifc %[reg], r9;		\
+		     .byte 0x99;		\
+		     .endif;			\
+		     .short %[off];		\
+		     .long %[as]"		\
+		     : [reg]"+r"(var)		\
+		     : [off]"i"(BPF_ADDR_SPACE_CAST) \
+		     , [as]"i"((dst_as << 16) | src_as));
+#endif
+
+void bpf_preempt_disable(void) __weak __ksym;
+void bpf_preempt_enable(void) __weak __ksym;
+
+typedef struct {
+} __bpf_preempt_t;
+
+static inline __bpf_preempt_t __bpf_preempt_constructor(void)
+{
+	__bpf_preempt_t ret = {};
+
+	bpf_preempt_disable();
+	return ret;
+}
+static inline void __bpf_preempt_destructor(__bpf_preempt_t *t)
+{
+	bpf_preempt_enable();
+}
+#define bpf_guard_preempt() \
+	__bpf_preempt_t ___bpf_apply(preempt, __COUNTER__)			\
+	__attribute__((__unused__, __cleanup__(__bpf_preempt_destructor))) =	\
+	__bpf_preempt_constructor()
+
+/* Description
+ *	Assert that a conditional expression is true.
+ * Returns
+ *	Void.
+ * Throws
+ *	An exception with the value zero when the assertion fails.
+ */
+#define bpf_assert(cond) if (!(cond)) bpf_throw(0);
+
+/* Description
+ *	Assert that a conditional expression is true.
+ * Returns
+ *	Void.
+ * Throws
+ *	An exception with the specified value when the assertion fails.
+ */
+#define bpf_assert_with(cond, value) if (!(cond)) bpf_throw(value);
+
+/* Description
+ *	Assert that LHS is in the range [BEG, END] (inclusive of both). This
+ *	statement updates the known bounds of LHS during verification. Note
+ *	that both BEG and END must be constant values, and must fit within the
+ *	data type of LHS.
+ * Returns
+ *	Void.
+ * Throws
+ *	An exception with the value zero when the assertion fails.
+ */
+#define bpf_assert_range(LHS, BEG, END)					\
+	({								\
+		_Static_assert(BEG <= END, "BEG must be <= END");	\
+		barrier_var(LHS);					\
+		__bpf_assert_op(LHS, >=, BEG, 0, false);		\
+		__bpf_assert_op(LHS, <=, END, 0, false);		\
+	})
+
+/* Description
+ *	Assert that LHS is in the range [BEG, END] (inclusive of both). This
+ *	statement updates the known bounds of LHS during verification. Note
+ *	that both BEG and END must be constant values, and must fit within the
+ *	data type of LHS.
+ * Returns
+ *	Void.
+ * Throws
+ *	An exception with the specified value when the assertion fails.
+ */
+#define bpf_assert_range_with(LHS, BEG, END, value)			\
+	({								\
+		_Static_assert(BEG <= END, "BEG must be <= END");	\
+		barrier_var(LHS);					\
+		__bpf_assert_op(LHS, >=, BEG, value, false);		\
+		__bpf_assert_op(LHS, <=, END, value, false);		\
+	})
+
+struct bpf_iter_css_task;
+struct cgroup_subsys_state;
+extern int bpf_iter_css_task_new(struct bpf_iter_css_task *it,
+		struct cgroup_subsys_state *css, unsigned int flags) __weak __ksym;
+extern struct task_struct *bpf_iter_css_task_next(struct bpf_iter_css_task *it) __weak __ksym;
+extern void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it) __weak __ksym;
+
+struct bpf_iter_task;
+extern int bpf_iter_task_new(struct bpf_iter_task *it,
+		struct task_struct *task, unsigned int flags) __weak __ksym;
+extern struct task_struct *bpf_iter_task_next(struct bpf_iter_task *it) __weak __ksym;
+extern void bpf_iter_task_destroy(struct bpf_iter_task *it) __weak __ksym;
+
+struct bpf_iter_css;
+extern int bpf_iter_css_new(struct bpf_iter_css *it,
+				struct cgroup_subsys_state *start, unsigned int flags) __weak __ksym;
+extern struct cgroup_subsys_state *bpf_iter_css_next(struct bpf_iter_css *it) __weak __ksym;
+extern void bpf_iter_css_destroy(struct bpf_iter_css *it) __weak __ksym;
+
+extern int bpf_wq_init(struct bpf_wq *wq, void *p__map, unsigned int flags) __weak __ksym;
+extern int bpf_wq_start(struct bpf_wq *wq, unsigned int flags) __weak __ksym;
+extern int bpf_wq_set_callback_impl(struct bpf_wq *wq,
+		int (callback_fn)(void *map, int *key, void *value),
+		unsigned int flags__k, void *aux__ign) __ksym;
+#define bpf_wq_set_callback(timer, cb, flags) \
+	bpf_wq_set_callback_impl(timer, cb, flags, NULL)
+
+struct bpf_iter_kmem_cache;
+extern int bpf_iter_kmem_cache_new(struct bpf_iter_kmem_cache *it) __weak __ksym;
+extern struct kmem_cache *bpf_iter_kmem_cache_next(struct bpf_iter_kmem_cache *it) __weak __ksym;
+extern void bpf_iter_kmem_cache_destroy(struct bpf_iter_kmem_cache *it) __weak __ksym;
+
+struct bpf_iter_dmabuf;
+extern int bpf_iter_dmabuf_new(struct bpf_iter_dmabuf *it) __weak __ksym;
+extern struct dma_buf *bpf_iter_dmabuf_next(struct bpf_iter_dmabuf *it) __weak __ksym;
+extern void bpf_iter_dmabuf_destroy(struct bpf_iter_dmabuf *it) __weak __ksym;
+
+extern int bpf_cgroup_read_xattr(struct cgroup *cgroup, const char *name__str,
+				 struct bpf_dynptr *value_p) __weak __ksym;
+
+#define PREEMPT_BITS	8
+#define SOFTIRQ_BITS	8
+#define HARDIRQ_BITS	4
+#define NMI_BITS	4
+
+#define PREEMPT_SHIFT	0
+#define SOFTIRQ_SHIFT	(PREEMPT_SHIFT + PREEMPT_BITS)
+#define HARDIRQ_SHIFT	(SOFTIRQ_SHIFT + SOFTIRQ_BITS)
+#define NMI_SHIFT	(HARDIRQ_SHIFT + HARDIRQ_BITS)
+
+#define __IRQ_MASK(x)	((1UL << (x))-1)
+
+#define SOFTIRQ_MASK	(__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT)
+#define HARDIRQ_MASK	(__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT)
+#define NMI_MASK	(__IRQ_MASK(NMI_BITS)     << NMI_SHIFT)
+
+extern bool CONFIG_PREEMPT_RT __kconfig __weak;
+#ifdef bpf_target_x86
+extern const int __preempt_count __ksym;
+#endif
+
+struct task_struct___preempt_rt {
+	int softirq_disable_cnt;
+} __attribute__((preserve_access_index));
+
+static inline int get_preempt_count(void)
+{
+#if defined(bpf_target_x86)
+	return *(int *) bpf_this_cpu_ptr(&__preempt_count);
+#elif defined(bpf_target_arm64)
+	return bpf_get_current_task_btf()->thread_info.preempt.count;
+#endif
+	return 0;
+}
+
+/* Description
+ *	Report whether it is in interrupt context. Only works on the following archs:
+ *	* x86
+ *	* arm64
+ */
+static inline int bpf_in_interrupt(void)
+{
+	struct task_struct___preempt_rt *tsk;
+	int pcnt;
+
+	pcnt = get_preempt_count();
+	if (!CONFIG_PREEMPT_RT)
+		return pcnt & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_MASK);
+
+	tsk = (void *) bpf_get_current_task_btf();
+	return (pcnt & (NMI_MASK | HARDIRQ_MASK)) |
+	       (tsk->softirq_disable_cnt & SOFTIRQ_MASK);
+}
+
 #endif
diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h
new file mode 100644
index 000000000000..e0189254bb6e
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_kfuncs.h
@@ -0,0 +1,98 @@
+#ifndef __BPF_KFUNCS__
+#define __BPF_KFUNCS__
+
+struct bpf_sock_addr_kern;
+
+/* Description
+ *  Initializes an skb-type dynptr
+ * Returns
+ *  Error code
+ */
+extern int bpf_dynptr_from_skb(struct __sk_buff *skb, __u64 flags,
+    struct bpf_dynptr *ptr__uninit) __ksym __weak;
+
+/* Description
+ *  Initializes an xdp-type dynptr
+ * Returns
+ *  Error code
+ */
+extern int bpf_dynptr_from_xdp(struct xdp_md *xdp, __u64 flags,
+			       struct bpf_dynptr *ptr__uninit) __ksym __weak;
+
+extern int bpf_dynptr_from_skb_meta(struct __sk_buff *skb, __u64 flags,
+				    struct bpf_dynptr *ptr__uninit) __ksym __weak;
+
+/* Description
+ *  Obtain a read-only pointer to the dynptr's data
+ * Returns
+ *  Either a direct pointer to the dynptr data or a pointer to the user-provided
+ *  buffer if unable to obtain a direct pointer
+ */
+extern void *bpf_dynptr_slice(const struct bpf_dynptr *ptr, __u64 offset,
+			      void *buffer, __u64 buffer__szk) __ksym __weak;
+
+/* Description
+ *  Obtain a read-write pointer to the dynptr's data
+ * Returns
+ *  Either a direct pointer to the dynptr data or a pointer to the user-provided
+ *  buffer if unable to obtain a direct pointer
+ */
+extern void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr *ptr, __u64 offset, void *buffer,
+				   __u64 buffer__szk) __ksym __weak;
+
+extern int bpf_dynptr_adjust(const struct bpf_dynptr *ptr, __u64 start, __u64 end) __ksym __weak;
+extern bool bpf_dynptr_is_null(const struct bpf_dynptr *ptr) __ksym __weak;
+extern bool bpf_dynptr_is_rdonly(const struct bpf_dynptr *ptr) __ksym __weak;
+extern __u64 bpf_dynptr_size(const struct bpf_dynptr *ptr) __ksym __weak;
+extern int bpf_dynptr_clone(const struct bpf_dynptr *ptr, struct bpf_dynptr *clone__init) __ksym __weak;
+
+/* Description
+ *  Modify the address of a AF_UNIX sockaddr.
+ * Returns
+ *  -EINVAL if the address size is too big or, 0 if the sockaddr was successfully modified.
+ */
+extern int bpf_sock_addr_set_sun_path(struct bpf_sock_addr_kern *sa_kern,
+				      const __u8 *sun_path, __u32 sun_path__sz) __ksym;
+
+/* Description
+ *  Allocate and configure a reqsk and link it with a listener and skb.
+ * Returns
+ *  Error code
+ */
+struct sock;
+struct bpf_tcp_req_attrs;
+extern int bpf_sk_assign_tcp_reqsk(struct __sk_buff *skb, struct sock *sk,
+				   struct bpf_tcp_req_attrs *attrs, int attrs__sz) __ksym;
+
+void *bpf_cast_to_kern_ctx(void *) __ksym;
+
+extern void *bpf_rdonly_cast(const void *obj, __u32 btf_id) __ksym __weak;
+
+extern int bpf_get_file_xattr(struct file *file, const char *name,
+			      struct bpf_dynptr *value_ptr) __ksym;
+extern int bpf_get_fsverity_digest(struct file *file, struct bpf_dynptr *digest_ptr) __ksym;
+
+extern struct bpf_key *bpf_lookup_user_key(__s32 serial, __u64 flags) __ksym;
+extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym;
+extern void bpf_key_put(struct bpf_key *key) __ksym;
+extern int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_ptr,
+				      struct bpf_dynptr *sig_ptr,
+				      struct bpf_key *trusted_keyring) __ksym;
+
+extern bool bpf_session_is_return(void) __ksym __weak;
+extern __u64 *bpf_session_cookie(void) __ksym __weak;
+
+struct dentry;
+/* Description
+ *  Returns xattr of a dentry
+ * Returns
+ *  Error code
+ */
+extern int bpf_get_dentry_xattr(struct dentry *dentry, const char *name,
+			      struct bpf_dynptr *value_ptr) __ksym __weak;
+
+extern int bpf_set_dentry_xattr(struct dentry *dentry, const char *name__str,
+				const struct bpf_dynptr *value_p, int flags) __ksym __weak;
+extern int bpf_remove_dentry_xattr(struct dentry *dentry, const char *name__str) __ksym __weak;
+
+#endif
diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
deleted file mode 100644
index 82a7c9de95f9..000000000000
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ /dev/null
@@ -1,241 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __BPF_TCP_HELPERS_H
-#define __BPF_TCP_HELPERS_H
-
-#include <stdbool.h>
-#include <linux/types.h>
-#include <bpf/bpf_helpers.h>
-#include <bpf/bpf_core_read.h>
-#include <bpf/bpf_tracing.h>
-
-#define BPF_STRUCT_OPS(name, args...) \
-SEC("struct_ops/"#name) \
-BPF_PROG(name, args)
-
-#ifndef SOL_TCP
-#define SOL_TCP 6
-#endif
-
-#ifndef TCP_CA_NAME_MAX
-#define TCP_CA_NAME_MAX	16
-#endif
-
-#define tcp_jiffies32 ((__u32)bpf_jiffies64())
-
-struct sock_common {
-	unsigned char	skc_state;
-	__u16		skc_num;
-} __attribute__((preserve_access_index));
-
-enum sk_pacing {
-	SK_PACING_NONE		= 0,
-	SK_PACING_NEEDED	= 1,
-	SK_PACING_FQ		= 2,
-};
-
-struct sock {
-	struct sock_common	__sk_common;
-#define sk_state		__sk_common.skc_state
-	unsigned long		sk_pacing_rate;
-	__u32			sk_pacing_status; /* see enum sk_pacing */
-} __attribute__((preserve_access_index));
-
-struct inet_sock {
-	struct sock		sk;
-} __attribute__((preserve_access_index));
-
-struct inet_connection_sock {
-	struct inet_sock	  icsk_inet;
-	__u8			  icsk_ca_state:6,
-				  icsk_ca_setsockopt:1,
-				  icsk_ca_dst_locked:1;
-	struct {
-		__u8		  pending;
-	} icsk_ack;
-	__u64			  icsk_ca_priv[104 / sizeof(__u64)];
-} __attribute__((preserve_access_index));
-
-struct request_sock {
-	struct sock_common		__req_common;
-} __attribute__((preserve_access_index));
-
-struct tcp_sock {
-	struct inet_connection_sock	inet_conn;
-
-	__u32	rcv_nxt;
-	__u32	snd_nxt;
-	__u32	snd_una;
-	__u32	window_clamp;
-	__u8	ecn_flags;
-	__u32	delivered;
-	__u32	delivered_ce;
-	__u32	snd_cwnd;
-	__u32	snd_cwnd_cnt;
-	__u32	snd_cwnd_clamp;
-	__u32	snd_ssthresh;
-	__u8	syn_data:1,	/* SYN includes data */
-		syn_fastopen:1,	/* SYN includes Fast Open option */
-		syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */
-		syn_fastopen_ch:1, /* Active TFO re-enabling probe */
-		syn_data_acked:1,/* data in SYN is acked by SYN-ACK */
-		save_syn:1,	/* Save headers of SYN packet */
-		is_cwnd_limited:1,/* forward progress limited by snd_cwnd? */
-		syn_smc:1;	/* SYN includes SMC */
-	__u32	max_packets_out;
-	__u32	lsndtime;
-	__u32	prior_cwnd;
-	__u64	tcp_mstamp;	/* most recent packet received/sent */
-	bool	is_mptcp;
-} __attribute__((preserve_access_index));
-
-static __always_inline struct inet_connection_sock *inet_csk(const struct sock *sk)
-{
-	return (struct inet_connection_sock *)sk;
-}
-
-static __always_inline void *inet_csk_ca(const struct sock *sk)
-{
-	return (void *)inet_csk(sk)->icsk_ca_priv;
-}
-
-static __always_inline struct tcp_sock *tcp_sk(const struct sock *sk)
-{
-	return (struct tcp_sock *)sk;
-}
-
-static __always_inline bool before(__u32 seq1, __u32 seq2)
-{
-	return (__s32)(seq1-seq2) < 0;
-}
-#define after(seq2, seq1) 	before(seq1, seq2)
-
-#define	TCP_ECN_OK		1
-#define	TCP_ECN_QUEUE_CWR	2
-#define	TCP_ECN_DEMAND_CWR	4
-#define	TCP_ECN_SEEN		8
-
-enum inet_csk_ack_state_t {
-	ICSK_ACK_SCHED	= 1,
-	ICSK_ACK_TIMER  = 2,
-	ICSK_ACK_PUSHED = 4,
-	ICSK_ACK_PUSHED2 = 8,
-	ICSK_ACK_NOW = 16	/* Send the next ACK immediately (once) */
-};
-
-enum tcp_ca_event {
-	CA_EVENT_TX_START = 0,
-	CA_EVENT_CWND_RESTART = 1,
-	CA_EVENT_COMPLETE_CWR = 2,
-	CA_EVENT_LOSS = 3,
-	CA_EVENT_ECN_NO_CE = 4,
-	CA_EVENT_ECN_IS_CE = 5,
-};
-
-struct ack_sample {
-	__u32 pkts_acked;
-	__s32 rtt_us;
-	__u32 in_flight;
-} __attribute__((preserve_access_index));
-
-struct rate_sample {
-	__u64  prior_mstamp; /* starting timestamp for interval */
-	__u32  prior_delivered;	/* tp->delivered at "prior_mstamp" */
-	__s32  delivered;		/* number of packets delivered over interval */
-	long interval_us;	/* time for tp->delivered to incr "delivered" */
-	__u32 snd_interval_us;	/* snd interval for delivered packets */
-	__u32 rcv_interval_us;	/* rcv interval for delivered packets */
-	long rtt_us;		/* RTT of last (S)ACKed packet (or -1) */
-	int  losses;		/* number of packets marked lost upon ACK */
-	__u32  acked_sacked;	/* number of packets newly (S)ACKed upon ACK */
-	__u32  prior_in_flight;	/* in flight before this ACK */
-	bool is_app_limited;	/* is sample from packet with bubble in pipe? */
-	bool is_retrans;	/* is sample from retransmission? */
-	bool is_ack_delayed;	/* is this (likely) a delayed ACK? */
-} __attribute__((preserve_access_index));
-
-#define TCP_CA_NAME_MAX		16
-#define TCP_CONG_NEEDS_ECN	0x2
-
-struct tcp_congestion_ops {
-	char name[TCP_CA_NAME_MAX];
-	__u32 flags;
-
-	/* initialize private data (optional) */
-	void (*init)(struct sock *sk);
-	/* cleanup private data  (optional) */
-	void (*release)(struct sock *sk);
-
-	/* return slow start threshold (required) */
-	__u32 (*ssthresh)(struct sock *sk);
-	/* do new cwnd calculation (required) */
-	void (*cong_avoid)(struct sock *sk, __u32 ack, __u32 acked);
-	/* call before changing ca_state (optional) */
-	void (*set_state)(struct sock *sk, __u8 new_state);
-	/* call when cwnd event occurs (optional) */
-	void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev);
-	/* call when ack arrives (optional) */
-	void (*in_ack_event)(struct sock *sk, __u32 flags);
-	/* new value of cwnd after loss (required) */
-	__u32  (*undo_cwnd)(struct sock *sk);
-	/* hook for packet ack accounting (optional) */
-	void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample);
-	/* override sysctl_tcp_min_tso_segs */
-	__u32 (*min_tso_segs)(struct sock *sk);
-	/* returns the multiplier used in tcp_sndbuf_expand (optional) */
-	__u32 (*sndbuf_expand)(struct sock *sk);
-	/* call when packets are delivered to update cwnd and pacing rate,
-	 * after all the ca_state processing. (optional)
-	 */
-	void (*cong_control)(struct sock *sk, const struct rate_sample *rs);
-	void *owner;
-};
-
-#define min(a, b) ((a) < (b) ? (a) : (b))
-#define max(a, b) ((a) > (b) ? (a) : (b))
-#define min_not_zero(x, y) ({			\
-	typeof(x) __x = (x);			\
-	typeof(y) __y = (y);			\
-	__x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); })
-
-static __always_inline bool tcp_in_slow_start(const struct tcp_sock *tp)
-{
-	return tp->snd_cwnd < tp->snd_ssthresh;
-}
-
-static __always_inline bool tcp_is_cwnd_limited(const struct sock *sk)
-{
-	const struct tcp_sock *tp = tcp_sk(sk);
-
-	/* If in slow start, ensure cwnd grows to twice what was ACKed. */
-	if (tcp_in_slow_start(tp))
-		return tp->snd_cwnd < 2 * tp->max_packets_out;
-
-	return !!BPF_CORE_READ_BITFIELD(tp, is_cwnd_limited);
-}
-
-static __always_inline bool tcp_cc_eq(const char *a, const char *b)
-{
-	int i;
-
-	for (i = 0; i < TCP_CA_NAME_MAX; i++) {
-		if (a[i] != b[i])
-			return false;
-		if (!a[i])
-			break;
-	}
-
-	return true;
-}
-
-extern __u32 tcp_slow_start(struct tcp_sock *tp, __u32 acked) __ksym;
-extern void tcp_cong_avoid_ai(struct tcp_sock *tp, __u32 w, __u32 acked) __ksym;
-
-struct mptcp_sock {
-	struct inet_connection_sock	sk;
-
-	__u32		token;
-	struct sock	*first;
-	char		ca_name[TCP_CA_NAME_MAX];
-} __attribute__((preserve_access_index));
-
-#endif
diff --git a/tools/testing/selftests/bpf/bpf_testmod/Makefile b/tools/testing/selftests/bpf/bpf_testmod/Makefile
deleted file mode 100644
index 15cb36c4483a..000000000000
--- a/tools/testing/selftests/bpf/bpf_testmod/Makefile
+++ /dev/null
@@ -1,20 +0,0 @@
-BPF_TESTMOD_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST)))))
-KDIR ?= $(abspath $(BPF_TESTMOD_DIR)/../../../../..)
-
-ifeq ($(V),1)
-Q =
-else
-Q = @
-endif
-
-MODULES = bpf_testmod.ko
-
-obj-m += bpf_testmod.o
-CFLAGS_bpf_testmod.o = -I$(src)
-
-all:
-	+$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) modules
-
-clean:
-	+$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) clean
-
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
deleted file mode 100644
index 5085fea3cac5..000000000000
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ /dev/null
@@ -1,256 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2020 Facebook */
-#include <linux/btf.h>
-#include <linux/btf_ids.h>
-#include <linux/error-injection.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/percpu-defs.h>
-#include <linux/sysfs.h>
-#include <linux/tracepoint.h>
-#include "bpf_testmod.h"
-
-#define CREATE_TRACE_POINTS
-#include "bpf_testmod-events.h"
-
-typedef int (*func_proto_typedef)(long);
-typedef int (*func_proto_typedef_nested1)(func_proto_typedef);
-typedef int (*func_proto_typedef_nested2)(func_proto_typedef_nested1);
-
-DEFINE_PER_CPU(int, bpf_testmod_ksym_percpu) = 123;
-long bpf_testmod_test_struct_arg_result;
-
-struct bpf_testmod_struct_arg_1 {
-	int a;
-};
-struct bpf_testmod_struct_arg_2 {
-	long a;
-	long b;
-};
-
-noinline int
-bpf_testmod_test_struct_arg_1(struct bpf_testmod_struct_arg_2 a, int b, int c) {
-	bpf_testmod_test_struct_arg_result = a.a + a.b  + b + c;
-	return bpf_testmod_test_struct_arg_result;
-}
-
-noinline int
-bpf_testmod_test_struct_arg_2(int a, struct bpf_testmod_struct_arg_2 b, int c) {
-	bpf_testmod_test_struct_arg_result = a + b.a + b.b + c;
-	return bpf_testmod_test_struct_arg_result;
-}
-
-noinline int
-bpf_testmod_test_struct_arg_3(int a, int b, struct bpf_testmod_struct_arg_2 c) {
-	bpf_testmod_test_struct_arg_result = a + b + c.a + c.b;
-	return bpf_testmod_test_struct_arg_result;
-}
-
-noinline int
-bpf_testmod_test_struct_arg_4(struct bpf_testmod_struct_arg_1 a, int b,
-			      int c, int d, struct bpf_testmod_struct_arg_2 e) {
-	bpf_testmod_test_struct_arg_result = a.a + b + c + d + e.a + e.b;
-	return bpf_testmod_test_struct_arg_result;
-}
-
-noinline int
-bpf_testmod_test_struct_arg_5(void) {
-	bpf_testmod_test_struct_arg_result = 1;
-	return bpf_testmod_test_struct_arg_result;
-}
-
-noinline void
-bpf_testmod_test_mod_kfunc(int i)
-{
-	*(int *)this_cpu_ptr(&bpf_testmod_ksym_percpu) = i;
-}
-
-struct bpf_testmod_btf_type_tag_1 {
-	int a;
-};
-
-struct bpf_testmod_btf_type_tag_2 {
-	struct bpf_testmod_btf_type_tag_1 __user *p;
-};
-
-struct bpf_testmod_btf_type_tag_3 {
-	struct bpf_testmod_btf_type_tag_1 __percpu *p;
-};
-
-noinline int
-bpf_testmod_test_btf_type_tag_user_1(struct bpf_testmod_btf_type_tag_1 __user *arg) {
-	BTF_TYPE_EMIT(func_proto_typedef);
-	BTF_TYPE_EMIT(func_proto_typedef_nested1);
-	BTF_TYPE_EMIT(func_proto_typedef_nested2);
-	return arg->a;
-}
-
-noinline int
-bpf_testmod_test_btf_type_tag_user_2(struct bpf_testmod_btf_type_tag_2 *arg) {
-	return arg->p->a;
-}
-
-noinline int
-bpf_testmod_test_btf_type_tag_percpu_1(struct bpf_testmod_btf_type_tag_1 __percpu *arg) {
-	return arg->a;
-}
-
-noinline int
-bpf_testmod_test_btf_type_tag_percpu_2(struct bpf_testmod_btf_type_tag_3 *arg) {
-	return arg->p->a;
-}
-
-noinline int bpf_testmod_loop_test(int n)
-{
-	int i, sum = 0;
-
-	/* the primary goal of this test is to test LBR. Create a lot of
-	 * branches in the function, so we can catch it easily.
-	 */
-	for (i = 0; i < n; i++)
-		sum += i;
-	return sum;
-}
-
-__weak noinline struct file *bpf_testmod_return_ptr(int arg)
-{
-	static struct file f = {};
-
-	switch (arg) {
-	case 1: return (void *)EINVAL;		/* user addr */
-	case 2: return (void *)0xcafe4a11;	/* user addr */
-	case 3: return (void *)-EINVAL;		/* canonical, but invalid */
-	case 4: return (void *)(1ull << 60);	/* non-canonical and invalid */
-	case 5: return (void *)~(1ull << 30);	/* trigger extable */
-	case 6: return &f;			/* valid addr */
-	case 7: return (void *)((long)&f | 1);	/* kernel tricks */
-	default: return NULL;
-	}
-}
-
-noinline int bpf_testmod_fentry_test1(int a)
-{
-	return a + 1;
-}
-
-noinline int bpf_testmod_fentry_test2(int a, u64 b)
-{
-	return a + b;
-}
-
-noinline int bpf_testmod_fentry_test3(char a, int b, u64 c)
-{
-	return a + b + c;
-}
-
-int bpf_testmod_fentry_ok;
-
-noinline ssize_t
-bpf_testmod_test_read(struct file *file, struct kobject *kobj,
-		      struct bin_attribute *bin_attr,
-		      char *buf, loff_t off, size_t len)
-{
-	struct bpf_testmod_test_read_ctx ctx = {
-		.buf = buf,
-		.off = off,
-		.len = len,
-	};
-	struct bpf_testmod_struct_arg_1 struct_arg1 = {10};
-	struct bpf_testmod_struct_arg_2 struct_arg2 = {2, 3};
-	int i = 1;
-
-	while (bpf_testmod_return_ptr(i))
-		i++;
-
-	(void)bpf_testmod_test_struct_arg_1(struct_arg2, 1, 4);
-	(void)bpf_testmod_test_struct_arg_2(1, struct_arg2, 4);
-	(void)bpf_testmod_test_struct_arg_3(1, 4, struct_arg2);
-	(void)bpf_testmod_test_struct_arg_4(struct_arg1, 1, 2, 3, struct_arg2);
-	(void)bpf_testmod_test_struct_arg_5();
-
-	/* This is always true. Use the check to make sure the compiler
-	 * doesn't remove bpf_testmod_loop_test.
-	 */
-	if (bpf_testmod_loop_test(101) > 100)
-		trace_bpf_testmod_test_read(current, &ctx);
-
-	/* Magic number to enable writable tp */
-	if (len == 64) {
-		struct bpf_testmod_test_writable_ctx writable = {
-			.val = 1024,
-		};
-		trace_bpf_testmod_test_writable_bare(&writable);
-		if (writable.early_ret)
-			return snprintf(buf, len, "%d\n", writable.val);
-	}
-
-	if (bpf_testmod_fentry_test1(1) != 2 ||
-	    bpf_testmod_fentry_test2(2, 3) != 5 ||
-	    bpf_testmod_fentry_test3(4, 5, 6) != 15)
-		goto out;
-
-	bpf_testmod_fentry_ok = 1;
-out:
-	return -EIO; /* always fail */
-}
-EXPORT_SYMBOL(bpf_testmod_test_read);
-ALLOW_ERROR_INJECTION(bpf_testmod_test_read, ERRNO);
-
-noinline ssize_t
-bpf_testmod_test_write(struct file *file, struct kobject *kobj,
-		      struct bin_attribute *bin_attr,
-		      char *buf, loff_t off, size_t len)
-{
-	struct bpf_testmod_test_write_ctx ctx = {
-		.buf = buf,
-		.off = off,
-		.len = len,
-	};
-
-	trace_bpf_testmod_test_write_bare(current, &ctx);
-
-	return -EIO; /* always fail */
-}
-EXPORT_SYMBOL(bpf_testmod_test_write);
-ALLOW_ERROR_INJECTION(bpf_testmod_test_write, ERRNO);
-
-static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = {
-	.attr = { .name = "bpf_testmod", .mode = 0666, },
-	.read = bpf_testmod_test_read,
-	.write = bpf_testmod_test_write,
-};
-
-BTF_SET8_START(bpf_testmod_check_kfunc_ids)
-BTF_ID_FLAGS(func, bpf_testmod_test_mod_kfunc)
-BTF_SET8_END(bpf_testmod_check_kfunc_ids)
-
-static const struct btf_kfunc_id_set bpf_testmod_kfunc_set = {
-	.owner = THIS_MODULE,
-	.set   = &bpf_testmod_check_kfunc_ids,
-};
-
-extern int bpf_fentry_test1(int a);
-
-static int bpf_testmod_init(void)
-{
-	int ret;
-
-	ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_testmod_kfunc_set);
-	if (ret < 0)
-		return ret;
-	if (bpf_fentry_test1(0) < 0)
-		return -EINVAL;
-	return sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
-}
-
-static void bpf_testmod_exit(void)
-{
-	return sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
-}
-
-module_init(bpf_testmod_init);
-module_exit(bpf_testmod_exit);
-
-MODULE_AUTHOR("Andrii Nakryiko");
-MODULE_DESCRIPTION("BPF selftests module");
-MODULE_LICENSE("Dual BSD/GPL");
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h
deleted file mode 100644
index 0d71e2607832..000000000000
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (c) 2020 Facebook */
-#ifndef _BPF_TESTMOD_H
-#define _BPF_TESTMOD_H
-
-#include <linux/types.h>
-
-struct bpf_testmod_test_read_ctx {
-	char *buf;
-	loff_t off;
-	size_t len;
-};
-
-struct bpf_testmod_test_write_ctx {
-	char *buf;
-	loff_t off;
-	size_t len;
-};
-
-struct bpf_testmod_test_writable_ctx {
-	bool early_ret;
-	int val;
-};
-
-#endif /* _BPF_TESTMOD_H */
diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h
index 10587a29b967..4bc2d25f33e1 100644
--- a/tools/testing/selftests/bpf/bpf_util.h
+++ b/tools/testing/selftests/bpf/bpf_util.h
@@ -6,6 +6,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <errno.h>
+#include <syscall.h>
 #include <bpf/libbpf.h> /* libbpf_num_possible_cpus */
 
 static inline unsigned int bpf_num_possible_cpus(void)
@@ -59,4 +60,18 @@ static inline void bpf_strlcpy(char *dst, const char *src, size_t sz)
 	(offsetof(TYPE, MEMBER)	+ sizeof_field(TYPE, MEMBER))
 #endif
 
+/* Availability of gettid across glibc versions is hit-and-miss, therefore
+ * fallback to syscall in this macro and use it everywhere.
+ */
+#ifndef sys_gettid
+#define sys_gettid() syscall(SYS_gettid)
+#endif
+
+/* and poison usage to ensure it does not creep back in. */
+#pragma GCC poison gettid
+
+#ifndef ENOTSUPP
+#define ENOTSUPP 524
+#endif
+
 #endif /* __BPF_UTIL__ */
diff --git a/tools/testing/selftests/bpf/cap_helpers.c b/tools/testing/selftests/bpf/cap_helpers.c
index d5ac507401d7..98f840c3a38f 100644
--- a/tools/testing/selftests/bpf/cap_helpers.c
+++ b/tools/testing/selftests/bpf/cap_helpers.c
@@ -19,7 +19,7 @@ int cap_enable_effective(__u64 caps, __u64 *old_caps)
 
 	err = capget(&hdr, data);
 	if (err)
-		return err;
+		return -errno;
 
 	if (old_caps)
 		*old_caps = (__u64)(data[1].effective) << 32 | data[0].effective;
@@ -32,7 +32,7 @@ int cap_enable_effective(__u64 caps, __u64 *old_caps)
 	data[1].effective |= cap1;
 	err = capset(&hdr, data);
 	if (err)
-		return err;
+		return -errno;
 
 	return 0;
 }
@@ -49,7 +49,7 @@ int cap_disable_effective(__u64 caps, __u64 *old_caps)
 
 	err = capget(&hdr, data);
 	if (err)
-		return err;
+		return -errno;
 
 	if (old_caps)
 		*old_caps = (__u64)(data[1].effective) << 32 | data[0].effective;
@@ -61,7 +61,7 @@ int cap_disable_effective(__u64 caps, __u64 *old_caps)
 	data[1].effective &= ~cap1;
 	err = capset(&hdr, data);
 	if (err)
-		return err;
+		return -errno;
 
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/cap_helpers.h b/tools/testing/selftests/bpf/cap_helpers.h
index 6d163530cb0f..8dcb28557f76 100644
--- a/tools/testing/selftests/bpf/cap_helpers.h
+++ b/tools/testing/selftests/bpf/cap_helpers.h
@@ -4,6 +4,7 @@
 
 #include <linux/types.h>
 #include <linux/capability.h>
+#include <errno.h>
 
 #ifndef CAP_PERFMON
 #define CAP_PERFMON		38
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index 9e95b37a7dff..20cede4db3ce 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -4,6 +4,7 @@
 #include <sys/mount.h>
 #include <sys/stat.h>
 #include <sys/types.h>
+#include <sys/xattr.h>
 #include <linux/limits.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -45,9 +46,16 @@
 #define format_parent_cgroup_path(buf, path) \
 	format_cgroup_path_pid(buf, path, getppid())
 
-#define format_classid_path(buf)				\
-	snprintf(buf, sizeof(buf), "%s%s", NETCLS_MOUNT_PATH,	\
-		 CGROUP_WORK_DIR)
+#define format_classid_path_pid(buf, pid)				\
+	snprintf(buf, sizeof(buf), "%s%s%d", NETCLS_MOUNT_PATH,	\
+		 CGROUP_WORK_DIR, pid)
+
+#define format_classid_path(buf)	\
+	format_classid_path_pid(buf, getpid())
+
+static __thread bool cgroup_workdir_mounted;
+
+static void __cleanup_cgroup_environment(void);
 
 static int __enable_controllers(const char *cgroup_path, const char *controllers)
 {
@@ -195,6 +203,11 @@ int setup_cgroup_environment(void)
 
 	format_cgroup_path(cgroup_workdir, "");
 
+	if (mkdir(CGROUP_MOUNT_PATH, 0777) && errno != EEXIST) {
+		log_err("mkdir mount");
+		return 1;
+	}
+
 	if (unshare(CLONE_NEWNS)) {
 		log_err("unshare");
 		return 1;
@@ -209,9 +222,10 @@ int setup_cgroup_environment(void)
 		log_err("mount cgroup2");
 		return 1;
 	}
+	cgroup_workdir_mounted = true;
 
 	/* Cleanup existing failed runs, now that the environment is setup */
-	cleanup_cgroup_environment();
+	__cleanup_cgroup_environment();
 
 	if (mkdir(cgroup_workdir, 0777) && errno != EEXIST) {
 		log_err("mkdir cgroup work dir");
@@ -278,6 +292,18 @@ int join_cgroup(const char *relative_path)
 }
 
 /**
+ * join_root_cgroup() - Join the root cgroup
+ *
+ * This function joins the root cgroup.
+ *
+ * On success, it returns 0, otherwise on failure it returns 1.
+ */
+int join_root_cgroup(void)
+{
+	return join_cgroup_from_top(CGROUP_MOUNT_PATH);
+}
+
+/**
  * join_parent_cgroup() - Join a cgroup in the parent process workdir
  * @relative_path: The cgroup path, relative to parent process workdir, to join
  *
@@ -294,10 +320,45 @@ int join_parent_cgroup(const char *relative_path)
 }
 
 /**
+ * set_cgroup_xattr() - Set xattr on a cgroup dir
+ * @relative_path: The cgroup path, relative to the workdir, to set xattr
+ * @name: xattr name
+ * @value: xattr value
+ *
+ * This function set xattr on cgroup dir.
+ *
+ * On success, it returns 0, otherwise on failure it returns -1.
+ */
+int set_cgroup_xattr(const char *relative_path,
+		     const char *name,
+		     const char *value)
+{
+	char cgroup_path[PATH_MAX + 1];
+
+	format_cgroup_path(cgroup_path, relative_path);
+	return setxattr(cgroup_path, name, value, strlen(value) + 1, 0);
+}
+
+/**
+ * __cleanup_cgroup_environment() - Delete temporary cgroups
+ *
+ * This is a helper for cleanup_cgroup_environment() that is responsible for
+ * deletion of all temporary cgroups that have been created during the test.
+ */
+static void __cleanup_cgroup_environment(void)
+{
+	char cgroup_workdir[PATH_MAX + 1];
+
+	format_cgroup_path(cgroup_workdir, "");
+	join_cgroup_from_top(CGROUP_MOUNT_PATH);
+	nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT);
+}
+
+/**
  * cleanup_cgroup_environment() - Cleanup Cgroup Testing Environment
  *
  * This is an idempotent function to delete all temporary cgroups that
- * have been created during the test, including the cgroup testing work
+ * have been created during the test and unmount the cgroup testing work
  * directory.
  *
  * At call time, it moves the calling process to the root cgroup, and then
@@ -308,11 +369,10 @@ int join_parent_cgroup(const char *relative_path)
  */
 void cleanup_cgroup_environment(void)
 {
-	char cgroup_workdir[PATH_MAX + 1];
-
-	format_cgroup_path(cgroup_workdir, "");
-	join_cgroup_from_top(CGROUP_MOUNT_PATH);
-	nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT);
+	__cleanup_cgroup_environment();
+	if (cgroup_workdir_mounted && umount(CGROUP_MOUNT_PATH))
+		log_err("umount cgroup2");
+	cgroup_workdir_mounted = false;
 }
 
 /**
@@ -352,6 +412,26 @@ void remove_cgroup(const char *relative_path)
 		log_err("rmdiring cgroup %s .. %s", relative_path, cgroup_path);
 }
 
+/*
+ * remove_cgroup_pid() - Remove a cgroup setup by process identified by PID
+ * @relative_path: The cgroup path, relative to the workdir, to remove
+ * @pid: PID to be used to find cgroup_path
+ *
+ * This function expects a cgroup to already be created, relative to the cgroup
+ * work dir. It also expects the cgroup doesn't have any children or live
+ * processes and it removes the cgroup.
+ *
+ * On failure, it will print an error to stderr.
+ */
+void remove_cgroup_pid(const char *relative_path, int pid)
+{
+	char cgroup_path[PATH_MAX + 1];
+
+	format_cgroup_path_pid(cgroup_path, relative_path, pid);
+	if (rmdir(cgroup_path))
+		log_err("rmdiring cgroup %s .. %s", relative_path, cgroup_path);
+}
+
 /**
  * create_and_get_cgroup() - Create a cgroup, relative to workdir, and get the FD
  * @relative_path: The cgroup path, relative to the workdir, to join
@@ -383,26 +463,23 @@ int create_and_get_cgroup(const char *relative_path)
 }
 
 /**
- * get_cgroup_id() - Get cgroup id for a particular cgroup path
- * @relative_path: The cgroup path, relative to the workdir, to join
+ * get_cgroup_id_from_path - Get cgroup id for a particular cgroup path
+ * @cgroup_workdir: The absolute cgroup path
  *
  * On success, it returns the cgroup id. On failure it returns 0,
  * which is an invalid cgroup id.
  * If there is a failure, it prints the error to stderr.
  */
-unsigned long long get_cgroup_id(const char *relative_path)
+static unsigned long long get_cgroup_id_from_path(const char *cgroup_workdir)
 {
 	int dirfd, err, flags, mount_id, fhsize;
 	union {
 		unsigned long long cgid;
 		unsigned char raw_bytes[8];
 	} id;
-	char cgroup_workdir[PATH_MAX + 1];
 	struct file_handle *fhp, *fhp2;
 	unsigned long long ret = 0;
 
-	format_cgroup_path(cgroup_workdir, relative_path);
-
 	dirfd = AT_FDCWD;
 	flags = 0;
 	fhsize = sizeof(*fhp);
@@ -438,6 +515,14 @@ free_mem:
 	return ret;
 }
 
+unsigned long long get_cgroup_id(const char *relative_path)
+{
+	char cgroup_workdir[PATH_MAX + 1];
+
+	format_cgroup_path(cgroup_workdir, relative_path);
+	return get_cgroup_id_from_path(cgroup_workdir);
+}
+
 int cgroup_setup_and_join(const char *path) {
 	int cg_fd;
 
@@ -464,6 +549,9 @@ int cgroup_setup_and_join(const char *path) {
 /**
  * setup_classid_environment() - Setup the cgroupv1 net_cls environment
  *
+ * This function should only be called in a custom mount namespace, e.g.
+ * created by running setup_cgroup_environment.
+ *
  * After calling this function, cleanup_classid_environment should be called
  * once testing is complete.
  *
@@ -487,10 +575,20 @@ int setup_classid_environment(void)
 		return 1;
 	}
 
-	if (mount("net_cls", NETCLS_MOUNT_PATH, "cgroup", 0, "net_cls") &&
-	    errno != EBUSY) {
-		log_err("mount cgroup net_cls");
-		return 1;
+	if (mount("net_cls", NETCLS_MOUNT_PATH, "cgroup", 0, "net_cls")) {
+		if (errno != EBUSY) {
+			log_err("mount cgroup net_cls");
+			return 1;
+		}
+
+		if (rmdir(NETCLS_MOUNT_PATH)) {
+			log_err("rmdir cgroup net_cls");
+			return 1;
+		}
+		if (umount(CGROUP_MOUNT_DFLT)) {
+			log_err("umount cgroup base");
+			return 1;
+		}
 	}
 
 	cleanup_classid_environment();
@@ -505,15 +603,16 @@ int setup_classid_environment(void)
 
 /**
  * set_classid() - Set a cgroupv1 net_cls classid
- * @id: the numeric classid
  *
- * Writes the passed classid into the cgroup work dir's net_cls.classid
+ * Writes the classid into the cgroup work dir's net_cls.classid
  * file in order to later on trigger socket tagging.
  *
+ * We leverage the current pid as the classid, ensuring unique identification.
+ *
  * On success, it returns 0, otherwise on failure it returns 1. If there
  * is a failure, it prints the error to stderr.
  */
-int set_classid(unsigned int id)
+int set_classid(void)
 {
 	char cgroup_workdir[PATH_MAX - 42];
 	char cgroup_classid_path[PATH_MAX + 1];
@@ -529,7 +628,7 @@ int set_classid(unsigned int id)
 		return 1;
 	}
 
-	if (dprintf(fd, "%u\n", id) < 0) {
+	if (dprintf(fd, "%u\n", getpid()) < 0) {
 		log_err("Setting cgroup classid");
 		rc = 1;
 	}
@@ -571,3 +670,82 @@ void cleanup_classid_environment(void)
 	join_cgroup_from_top(NETCLS_MOUNT_PATH);
 	nftw(cgroup_workdir, nftwfunc, WALK_FD_LIMIT, FTW_DEPTH | FTW_MOUNT);
 }
+
+/**
+ * get_classid_cgroup_id - Get the cgroup id of a net_cls cgroup
+ */
+unsigned long long get_classid_cgroup_id(void)
+{
+	char cgroup_workdir[PATH_MAX + 1];
+
+	format_classid_path(cgroup_workdir);
+	return get_cgroup_id_from_path(cgroup_workdir);
+}
+
+/**
+ * get_cgroup1_hierarchy_id - Retrieves the ID of a cgroup1 hierarchy from the cgroup1 subsys name.
+ * @subsys_name: The cgroup1 subsys name, which can be retrieved from /proc/self/cgroup. It can be
+ * a named cgroup like "name=systemd", a controller name like "net_cls", or multi-controllers like
+ * "net_cls,net_prio".
+ */
+int get_cgroup1_hierarchy_id(const char *subsys_name)
+{
+	char *c, *c2, *c3, *c4;
+	bool found = false;
+	char line[1024];
+	FILE *file;
+	int i, id;
+
+	if (!subsys_name)
+		return -1;
+
+	file = fopen("/proc/self/cgroup", "r");
+	if (!file) {
+		log_err("fopen /proc/self/cgroup");
+		return -1;
+	}
+
+	while (fgets(line, 1024, file)) {
+		i = 0;
+		for (c = strtok_r(line, ":", &c2); c && i < 2; c = strtok_r(NULL, ":", &c2)) {
+			if (i == 0) {
+				id = strtol(c, NULL, 10);
+			} else if (i == 1) {
+				if (!strcmp(c, subsys_name)) {
+					found = true;
+					break;
+				}
+
+				/* Multiple subsystems may share one single mount point */
+				for (c3 = strtok_r(c, ",", &c4); c3;
+				     c3 = strtok_r(NULL, ",", &c4)) {
+					if (!strcmp(c, subsys_name)) {
+						found = true;
+						break;
+					}
+				}
+			}
+			i++;
+		}
+		if (found)
+			break;
+	}
+	fclose(file);
+	return found ? id : -1;
+}
+
+/**
+ * open_classid() - Open a cgroupv1 net_cls classid
+ *
+ * This function expects the cgroup work dir to be already created, as we
+ * open it here.
+ *
+ * On success, it returns the file descriptor. On failure it returns -1.
+ */
+int open_classid(void)
+{
+	char cgroup_workdir[PATH_MAX + 1];
+
+	format_classid_path(cgroup_workdir);
+	return open(cgroup_workdir, O_RDONLY);
+}
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h
index f099a166c94d..3857304be874 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.h
+++ b/tools/testing/selftests/bpf/cgroup_helpers.h
@@ -19,17 +19,26 @@ int cgroup_setup_and_join(const char *relative_path);
 int get_root_cgroup(void);
 int create_and_get_cgroup(const char *relative_path);
 void remove_cgroup(const char *relative_path);
+void remove_cgroup_pid(const char *relative_path, int pid);
 unsigned long long get_cgroup_id(const char *relative_path);
+int get_cgroup1_hierarchy_id(const char *subsys_name);
 
 int join_cgroup(const char *relative_path);
+int join_root_cgroup(void);
 int join_parent_cgroup(const char *relative_path);
 
+int set_cgroup_xattr(const char *relative_path,
+		     const char *name,
+		     const char *value);
+
 int setup_cgroup_environment(void);
 void cleanup_cgroup_environment(void);
 
 /* cgroupv1 related */
-int set_classid(unsigned int id);
+int set_classid(void);
 int join_classid(void);
+unsigned long long get_classid_cgroup_id(void);
+int open_classid(void);
 
 int setup_classid_environment(void);
 void cleanup_classid_environment(void);
diff --git a/tools/testing/selftests/bpf/cgroup_tcp_skb.h b/tools/testing/selftests/bpf/cgroup_tcp_skb.h
new file mode 100644
index 000000000000..7f6b24f102fb
--- /dev/null
+++ b/tools/testing/selftests/bpf/cgroup_tcp_skb.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+/* Define states of a socket to tracking messages sending to and from the
+ * socket.
+ *
+ * These states are based on rfc9293 with some modifications to support
+ * tracking of messages sent out from a socket. For example, when a SYN is
+ * received, a new socket is transiting to the SYN_RECV state defined in
+ * rfc9293. But, we put it in SYN_RECV_SENDING_SYN_ACK state and when
+ * SYN-ACK is sent out, it moves to SYN_RECV state. With this modification,
+ * we can track the message sent out from a socket.
+ */
+
+#ifndef __CGROUP_TCP_SKB_H__
+#define __CGROUP_TCP_SKB_H__
+
+enum {
+	INIT,
+	CLOSED,
+	SYN_SENT,
+	SYN_RECV_SENDING_SYN_ACK,
+	SYN_RECV,
+	ESTABLISHED,
+	FIN_WAIT1,
+	FIN_WAIT2,
+	CLOSE_WAIT_SENDING_ACK,
+	CLOSE_WAIT,
+	CLOSING,
+	LAST_ACK,
+	TIME_WAIT_SENDING_ACK,
+	TIME_WAIT,
+};
+
+#endif /* __CGROUP_TCP_SKB_H__ */
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 63cd4ab70171..558839e3c185 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -4,6 +4,7 @@ CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y
 CONFIG_BPF=y
 CONFIG_BPF_EVENTS=y
 CONFIG_BPF_JIT=y
+CONFIG_BPF_KPROBE_OVERRIDE=y
 CONFIG_BPF_LIRC_MODE2=y
 CONFIG_BPF_LSM=y
 CONFIG_BPF_STREAM_PARSER=y
@@ -12,12 +13,24 @@ CONFIG_BPF_SYSCALL=y
 CONFIG_CGROUP_BPF=y
 CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_SHA256=y
+CONFIG_CRYPTO_USER_API=y
 CONFIG_CRYPTO_USER_API_HASH=y
+CONFIG_CRYPTO_USER_API_SKCIPHER=y
+CONFIG_CRYPTO_SKCIPHER=y
+CONFIG_CRYPTO_ECB=y
+CONFIG_CRYPTO_AES=y
+CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_INFO_BTF=y
+CONFIG_DEBUG_INFO_DWARF4=y
+CONFIG_DMABUF_HEAPS=y
+CONFIG_DMABUF_HEAPS_SYSTEM=y
+CONFIG_DUMMY=y
 CONFIG_DYNAMIC_FTRACE=y
 CONFIG_FPROBE=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_FUNCTION_ERROR_INJECTION=y
 CONFIG_FUNCTION_TRACER=y
+CONFIG_FS_VERITY=y
 CONFIG_GENEVE=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
@@ -37,6 +50,7 @@ CONFIG_IPV6_SIT=y
 CONFIG_IPV6_TUNNEL=y
 CONFIG_KEYS=y
 CONFIG_LIRC=y
+CONFIG_LIVEPATCH=y
 CONFIG_LWTUNNEL=y
 CONFIG_MODULE_SIG=y
 CONFIG_MODULE_SRCVERSION_ALL=y
@@ -47,33 +61,73 @@ CONFIG_MPLS=y
 CONFIG_MPLS_IPTUNNEL=y
 CONFIG_MPLS_ROUTING=y
 CONFIG_MPTCP=y
+CONFIG_NET_ACT_GACT=y
+CONFIG_NET_ACT_MIRRED=y
+CONFIG_NET_ACT_SKBMOD=y
+CONFIG_NET_CLS=y
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_CLS_BPF=y
 CONFIG_NET_CLS_FLOWER=y
+CONFIG_NET_CLS_MATCHALL=y
 CONFIG_NET_FOU=y
 CONFIG_NET_FOU_IP_TUNNELS=y
 CONFIG_NET_IPGRE=y
 CONFIG_NET_IPGRE_DEMUX=y
 CONFIG_NET_IPIP=y
 CONFIG_NET_MPLS_GSO=y
+CONFIG_NET_SCH_BPF=y
+CONFIG_NET_SCH_FQ=y
 CONFIG_NET_SCH_INGRESS=y
+CONFIG_NET_SCH_HTB=y
 CONFIG_NET_SCHED=y
 CONFIG_NETDEVSIM=y
 CONFIG_NETFILTER=y
+CONFIG_NETFILTER_ADVANCED=y
 CONFIG_NETFILTER_SYNPROXY=y
 CONFIG_NETFILTER_XT_CONNMARK=y
 CONFIG_NETFILTER_XT_MATCH_STATE=y
 CONFIG_NETFILTER_XT_TARGET_CT=y
+CONFIG_NETKIT=y
 CONFIG_NF_CONNTRACK=y
 CONFIG_NF_CONNTRACK_MARK=y
+CONFIG_NF_CONNTRACK_ZONES=y
 CONFIG_NF_DEFRAG_IPV4=y
 CONFIG_NF_DEFRAG_IPV6=y
+CONFIG_NF_TABLES=y
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
+CONFIG_NF_TABLES_IPV4=y
+CONFIG_NF_TABLES_IPV6=y
+CONFIG_NETFILTER_INGRESS=y
+CONFIG_IP_NF_IPTABLES_LEGACY=y
+CONFIG_IP6_NF_IPTABLES_LEGACY=y
+CONFIG_NETFILTER_XTABLES_LEGACY=y
+CONFIG_NF_FLOW_TABLE=y
+CONFIG_NF_FLOW_TABLE_INET=y
+CONFIG_NETFILTER_NETLINK=y
+CONFIG_NFT_FLOW_OFFLOAD=y
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP6_NF_IPTABLES=y
+CONFIG_IP6_NF_FILTER=y
 CONFIG_NF_NAT=y
+CONFIG_PACKET=y
 CONFIG_RC_CORE=y
+CONFIG_SAMPLES=y
+CONFIG_SAMPLE_LIVEPATCH=m
 CONFIG_SECURITY=y
 CONFIG_SECURITYFS=y
+CONFIG_SYN_COOKIES=y
 CONFIG_TEST_BPF=m
+CONFIG_UDMABUF=y
 CONFIG_USERFAULTFD=y
+CONFIG_VSOCKETS=y
 CONFIG_VXLAN=y
 CONFIG_XDP_SOCKETS=y
 CONFIG_XFRM_INTERFACE=y
+CONFIG_TCP_CONG_DCTCP=y
+CONFIG_TCP_CONG_BBR=y
+CONFIG_INFINIBAND=y
+CONFIG_SMC=y
+CONFIG_SMC_HS_CTRL_BPF=y
+CONFIG_DIBS=y
+CONFIG_DIBS_LO=y
+\ No newline at end of file
diff --git a/tools/testing/selftests/bpf/config.aarch64 b/tools/testing/selftests/bpf/config.aarch64
index 1f0437644186..7efad36ceb26 100644
--- a/tools/testing/selftests/bpf/config.aarch64
+++ b/tools/testing/selftests/bpf/config.aarch64
@@ -1,4 +1,3 @@
-CONFIG_9P_FS=y
 CONFIG_ARCH_VEXPRESS=y
 CONFIG_ARCH_WANT_DEFAULT_BPF_JIT=y
 CONFIG_ARM_SMMU_V3=y
@@ -12,7 +11,6 @@ CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_BONDING=y
-CONFIG_BPFILTER=y
 CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_JIT_DEFAULT_ON=y
 CONFIG_BPF_PRELOAD_UMD=y
@@ -33,10 +31,8 @@ CONFIG_COMPAT=y
 CONFIG_CPUSETS=y
 CONFIG_CRASH_DUMP=y
 CONFIG_CRYPTO_USER_API_RNG=y
-CONFIG_CRYPTO_USER_API_SKCIPHER=y
 CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_DEBUG_INFO_BTF=y
-CONFIG_DEBUG_INFO_DWARF4=y
+CONFIG_DEBUG_INFO_REDUCED=n
 CONFIG_DEBUG_LIST=y
 CONFIG_DEBUG_LOCKDEP=y
 CONFIG_DEBUG_NOTIFIERS=y
@@ -46,9 +42,7 @@ CONFIG_DEBUG_SG=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_DEVTMPFS=y
-CONFIG_DRM_VIRTIO_GPU=y
 CONFIG_DRM=y
-CONFIG_DUMMY=y
 CONFIG_EXPERT=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_EXT4_FS_SECURITY=y
@@ -67,19 +61,16 @@ CONFIG_HAVE_KRETPROBES=y
 CONFIG_HEADERS_INSTALL=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_HUGETLBFS=y
-CONFIG_HW_RANDOM_VIRTIO=y
 CONFIG_HW_RANDOM=y
 CONFIG_HZ_100=y
 CONFIG_IDLE_PAGE_TRACKING=y
 CONFIG_IKHEADERS=y
 CONFIG_INET6_ESP=y
-CONFIG_INET_ESP=y
 CONFIG_INET=y
 CONFIG_INPUT_EVDEV=y
 CONFIG_IP_ADVANCED_ROUTER=y
 CONFIG_IP_MULTICAST=y
 CONFIG_IP_MULTIPLE_TABLES=y
-CONFIG_IP_NF_IPTABLES=y
 CONFIG_IPV6_SEG6_LWTUNNEL=y
 CONFIG_IPVLAN=y
 CONFIG_JUMP_LABEL=y
@@ -99,25 +90,19 @@ CONFIG_MEMCG=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_NAMESPACES=y
-CONFIG_NET_9P_VIRTIO=y
-CONFIG_NET_9P=y
 CONFIG_NET_ACT_BPF=y
-CONFIG_NET_ACT_GACT=y
 CONFIG_NETDEVICES=y
 CONFIG_NETFILTER_XT_MATCH_BPF=y
 CONFIG_NETFILTER_XT_TARGET_MARK=y
 CONFIG_NET_KEY=y
-CONFIG_NET_SCH_FQ=y
 CONFIG_NET_VRF=y
 CONFIG_NET=y
-CONFIG_NF_TABLES=y
 CONFIG_NLMON=y
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NR_CPUS=256
 CONFIG_NUMA=y
 CONFIG_OVERLAY_FS=y
 CONFIG_PACKET_DIAG=y
-CONFIG_PACKET=y
 CONFIG_PANIC_ON_OOPS=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_PCI_HOST_GENERIC=y
@@ -140,7 +125,6 @@ CONFIG_SCHED_TRACER=y
 CONFIG_SCSI_CONSTANTS=y
 CONFIG_SCSI_LOGGING=y
 CONFIG_SCSI_SCAN_ASYNC=y
-CONFIG_SCSI_VIRTIO=y
 CONFIG_SCSI=y
 CONFIG_SECURITY_NETWORK=y
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
@@ -155,7 +139,6 @@ CONFIG_TASK_XACCT=y
 CONFIG_TCG_TIS=y
 CONFIG_TCG_TPM=y
 CONFIG_TCP_CONG_ADVANCED=y
-CONFIG_TCP_CONG_DCTCP=y
 CONFIG_TLS=y
 CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_TMPFS=y
@@ -164,18 +147,8 @@ CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_TUN=y
 CONFIG_UNIX=y
 CONFIG_UPROBES=y
-CONFIG_USELIB=y
 CONFIG_USER_NS=y
 CONFIG_VETH=y
-CONFIG_VIRTIO_BALLOON=y
-CONFIG_VIRTIO_BLK=y
-CONFIG_VIRTIO_CONSOLE=y
-CONFIG_VIRTIO_FS=y
-CONFIG_VIRTIO_INPUT=y
-CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y
-CONFIG_VIRTIO_MMIO=y
-CONFIG_VIRTIO_NET=y
-CONFIG_VIRTIO_PCI=y
 CONFIG_VLAN_8021Q=y
-CONFIG_VSOCKETS=y
+CONFIG_VSOCKETS_LOOPBACK=y
 CONFIG_XFRM_USER=y
diff --git a/tools/testing/selftests/bpf/config.ppc64el b/tools/testing/selftests/bpf/config.ppc64el
new file mode 100644
index 000000000000..b53afb5e0b71
--- /dev/null
+++ b/tools/testing/selftests/bpf/config.ppc64el
@@ -0,0 +1,92 @@
+CONFIG_ALTIVEC=y
+CONFIG_AUDIT=y
+CONFIG_BLK_CGROUP=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BONDING=y
+CONFIG_BPF_JIT_ALWAYS_ON=y
+CONFIG_BPF_PRELOAD_UMD=y
+CONFIG_BPF_PRELOAD=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_DEVICE=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_HUGETLB=y
+CONFIG_CGROUP_NET_CLASSID=y
+CONFIG_CGROUP_PERF=y
+CONFIG_CGROUP_PIDS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_CGROUPS=y
+CONFIG_CMDLINE_BOOL=y
+CONFIG_CMDLINE="console=hvc0 wg.success=hvc1 panic_on_warn=1"
+CONFIG_CPU_LITTLE_ENDIAN=y
+CONFIG_CPUSETS=y
+CONFIG_DEBUG_ATOMIC_SLEEP=y
+CONFIG_DEBUG_FS=y
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_DEVTMPFS=y
+CONFIG_EXPERT=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_FRAME_POINTER=y
+CONFIG_FRAME_WARN=1280
+CONFIG_HARDLOCKUP_DETECTOR=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_HUGETLBFS=y
+CONFIG_HVC_CONSOLE=y
+CONFIG_INET=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IPV6_SEG6_LWTUNNEL=y
+CONFIG_JUMP_LABEL=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_KPROBES=y
+CONFIG_MEMCG=y
+CONFIG_NAMESPACES=y
+CONFIG_NET_ACT_BPF=y
+CONFIG_NETDEVICES=y
+CONFIG_NETFILTER_XT_MATCH_BPF=y
+CONFIG_NET_L3_MASTER_DEV=y
+CONFIG_NET_VRF=y
+CONFIG_NET=y
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NONPORTABLE=y
+CONFIG_NR_CPUS=256
+CONFIG_PANIC_ON_OOPS=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_PCI_HOST_GENERIC=y
+CONFIG_PCI=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_PPC64=y
+CONFIG_PPC_OF_BOOT_TRAMPOLINE=y
+CONFIG_PPC_PSERIES=y
+CONFIG_PPC_RADIX_MMU=y
+CONFIG_PRINTK_TIME=y
+CONFIG_PROC_KCORE=y
+CONFIG_PROFILING=y
+CONFIG_RCU_CPU_STALL_TIMEOUT=60
+CONFIG_RT_GROUP_SCHED=y
+CONFIG_SECTION_MISMATCH_WARN_ONLY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_SMP=y
+CONFIG_SOC_VIRT=y
+CONFIG_SYSVIPC=y
+CONFIG_TCP_CONG_ADVANCED=y
+CONFIG_THREAD_SHIFT=14
+CONFIG_TLS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_TMPFS=y
+CONFIG_TUN=y
+CONFIG_UNIX=y
+CONFIG_UPROBES=y
+CONFIG_USER_NS=y
+CONFIG_VETH=y
+CONFIG_VLAN_8021Q=y
+CONFIG_VSOCKETS_LOOPBACK=y
+CONFIG_VSX=y
+CONFIG_XFRM_USER=y
diff --git a/tools/testing/selftests/bpf/config.riscv64 b/tools/testing/selftests/bpf/config.riscv64
new file mode 100644
index 000000000000..7bee24a79a71
--- /dev/null
+++ b/tools/testing/selftests/bpf/config.riscv64
@@ -0,0 +1,83 @@
+CONFIG_AUDIT=y
+CONFIG_BLK_CGROUP=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BONDING=y
+CONFIG_BPF_JIT_ALWAYS_ON=y
+CONFIG_BPF_PRELOAD=y
+CONFIG_BPF_PRELOAD_UMD=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_DEVICE=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_HUGETLB=y
+CONFIG_CGROUP_NET_CLASSID=y
+CONFIG_CGROUP_PERF=y
+CONFIG_CGROUP_PIDS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_CPUSETS=y
+CONFIG_DEBUG_ATOMIC_SLEEP=y
+CONFIG_DEBUG_FS=y
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_EXPERT=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_FRAME_POINTER=y
+CONFIG_HARDLOCKUP_DETECTOR=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_HUGETLBFS=y
+CONFIG_INET=y
+CONFIG_IPV6_SEG6_LWTUNNEL=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_JUMP_LABEL=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_KPROBES=y
+CONFIG_MEMCG=y
+CONFIG_NAMESPACES=y
+CONFIG_NET=y
+CONFIG_NETDEVICES=y
+CONFIG_NETFILTER_XT_MATCH_BPF=y
+CONFIG_NET_ACT_BPF=y
+CONFIG_NET_L3_MASTER_DEV=y
+CONFIG_NET_VRF=y
+CONFIG_NONPORTABLE=y
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NR_CPUS=256
+CONFIG_PANIC_ON_OOPS=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_PCI=y
+CONFIG_PCI_HOST_GENERIC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_PRINTK_TIME=y
+CONFIG_PROC_KCORE=y
+CONFIG_PROFILING=y
+CONFIG_RCU_CPU_STALL_TIMEOUT=60
+CONFIG_RISCV_EFFICIENT_UNALIGNED_ACCESS=y
+CONFIG_RISCV_ISA_C=y
+CONFIG_RISCV_PMU=y
+CONFIG_RISCV_PMU_SBI=y
+CONFIG_RT_GROUP_SCHED=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_SMP=y
+CONFIG_SOC_VIRT=y
+CONFIG_SYSVIPC=y
+CONFIG_TCP_CONG_ADVANCED=y
+CONFIG_TLS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_TUN=y
+CONFIG_UNIX=y
+CONFIG_UPROBES=y
+CONFIG_USER_NS=y
+CONFIG_VETH=y
+CONFIG_VLAN_8021Q=y
+CONFIG_VSOCKETS_LOOPBACK=y
+CONFIG_XFRM_USER=y
diff --git a/tools/testing/selftests/bpf/config.s390x b/tools/testing/selftests/bpf/config.s390x
index d49f6170e7bd..db61878148e4 100644
--- a/tools/testing/selftests/bpf/config.s390x
+++ b/tools/testing/selftests/bpf/config.s390x
@@ -1,4 +1,3 @@
-CONFIG_9P_FS=y
 CONFIG_ARCH_WANT_DEFAULT_BPF_JIT=y
 CONFIG_AUDIT=y
 CONFIG_BLK_CGROUP=y
@@ -10,7 +9,6 @@ CONFIG_BPF_JIT_ALWAYS_ON=y
 CONFIG_BPF_JIT_DEFAULT_ON=y
 CONFIG_BPF_PRELOAD=y
 CONFIG_BPF_PRELOAD_UMD=y
-CONFIG_BPFILTER=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_FREEZER=y
@@ -24,10 +22,7 @@ CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_CPUSETS=y
 CONFIG_CRASH_DUMP=y
 CONFIG_CRYPTO_USER_API_RNG=y
-CONFIG_CRYPTO_USER_API_SKCIPHER=y
 CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_DEBUG_INFO_BTF=y
-CONFIG_DEBUG_INFO_DWARF4=y
 CONFIG_DEBUG_LIST=y
 CONFIG_DEBUG_LOCKDEP=y
 CONFIG_DEBUG_NOTIFIERS=y
@@ -58,11 +53,9 @@ CONFIG_IDLE_PAGE_TRACKING=y
 CONFIG_IKHEADERS=y
 CONFIG_INET6_ESP=y
 CONFIG_INET=y
-CONFIG_INET_ESP=y
 CONFIG_IP_ADVANCED_ROUTER=y
 CONFIG_IP_MULTICAST=y
 CONFIG_IP_MULTIPLE_TABLES=y
-CONFIG_IP_NF_IPTABLES=y
 CONFIG_IPV6_SEG6_LWTUNNEL=y
 CONFIG_IPVLAN=y
 CONFIG_JUMP_LABEL=y
@@ -84,21 +77,15 @@ CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_NAMESPACES=y
 CONFIG_NET=y
-CONFIG_NET_9P=y
-CONFIG_NET_9P_VIRTIO=y
 CONFIG_NET_ACT_BPF=y
-CONFIG_NET_ACT_GACT=y
 CONFIG_NET_KEY=y
-CONFIG_NET_SCH_FQ=y
 CONFIG_NET_VRF=y
 CONFIG_NETDEVICES=y
 CONFIG_NETFILTER_XT_MATCH_BPF=y
 CONFIG_NETFILTER_XT_TARGET_MARK=y
-CONFIG_NF_TABLES=y
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NR_CPUS=256
 CONFIG_NUMA=y
-CONFIG_PACKET=y
 CONFIG_PANIC_ON_OOPS=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_PCI=y
@@ -114,7 +101,6 @@ CONFIG_SAMPLE_SECCOMP=y
 CONFIG_SAMPLES=y
 CONFIG_SCHED_TRACER=y
 CONFIG_SCSI=y
-CONFIG_SCSI_VIRTIO=y
 CONFIG_SECURITY_NETWORK=y
 CONFIG_STACK_TRACER=y
 CONFIG_STATIC_KEYS_SELFTEST=y
@@ -124,7 +110,6 @@ CONFIG_TASK_IO_ACCOUNTING=y
 CONFIG_TASK_XACCT=y
 CONFIG_TASKSTATS=y
 CONFIG_TCP_CONG_ADVANCED=y
-CONFIG_TCP_CONG_DCTCP=y
 CONFIG_TLS=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
@@ -133,12 +118,8 @@ CONFIG_TRANSPARENT_HUGEPAGE=y
 CONFIG_TUN=y
 CONFIG_UNIX=y
 CONFIG_UPROBES=y
-CONFIG_USELIB=y
 CONFIG_USER_NS=y
 CONFIG_VETH=y
-CONFIG_VIRTIO_BALLOON=y
-CONFIG_VIRTIO_BLK=y
-CONFIG_VIRTIO_NET=y
-CONFIG_VIRTIO_PCI=y
 CONFIG_VLAN_8021Q=y
+CONFIG_VSOCKETS_LOOPBACK=y
 CONFIG_XFRM_USER=y
diff --git a/tools/testing/selftests/bpf/config.vm b/tools/testing/selftests/bpf/config.vm
new file mode 100644
index 000000000000..da543b24c144
--- /dev/null
+++ b/tools/testing/selftests/bpf/config.vm
@@ -0,0 +1,15 @@
+CONFIG_9P_FS_POSIX_ACL=y
+CONFIG_9P_FS_SECURITY=y
+CONFIG_9P_FS=y
+CONFIG_CRYPTO_DEV_VIRTIO=y
+CONFIG_FUSE_FS=y
+CONFIG_FUSE_PASSTHROUGH=y
+CONFIG_NET_9P_VIRTIO=y
+CONFIG_NET_9P=y
+CONFIG_VIRTIO_BALLOON=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_VIRTIO_CONSOLE=y
+CONFIG_VIRTIO_FS=y
+CONFIG_VIRTIO_NET=y
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_VSOCKETS_COMMON=y
diff --git a/tools/testing/selftests/bpf/config.x86_64 b/tools/testing/selftests/bpf/config.x86_64
index dd97d61d325c..42ad817b00ae 100644
--- a/tools/testing/selftests/bpf/config.x86_64
+++ b/tools/testing/selftests/bpf/config.x86_64
@@ -1,6 +1,3 @@
-CONFIG_9P_FS=y
-CONFIG_9P_FS_POSIX_ACL=y
-CONFIG_9P_FS_SECURITY=y
 CONFIG_AGP=y
 CONFIG_AGP_AMD64=y
 CONFIG_AGP_INTEL=y
@@ -20,10 +17,8 @@ CONFIG_BLK_DEV_THROTTLING=y
 CONFIG_BONDING=y
 CONFIG_BOOTTIME_TRACING=y
 CONFIG_BPF_JIT_ALWAYS_ON=y
-CONFIG_BPF_KPROBE_OVERRIDE=y
 CONFIG_BPF_PRELOAD=y
 CONFIG_BPF_PRELOAD_UMD=y
-CONFIG_BPFILTER=y
 CONFIG_BSD_DISKLABEL=y
 CONFIG_BSD_PROCESS_ACCT=y
 CONFIG_CFS_BANDWIDTH=y
@@ -44,15 +39,11 @@ CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_STAT=y
 CONFIG_CPU_IDLE_GOV_LADDER=y
 CONFIG_CPUSETS=y
-CONFIG_CRC_T10DIF=y
 CONFIG_CRYPTO_BLAKE2B=y
-CONFIG_CRYPTO_DEV_VIRTIO=y
 CONFIG_CRYPTO_SEQIV=y
 CONFIG_CRYPTO_XXHASH=y
 CONFIG_DCB=y
 CONFIG_DEBUG_ATOMIC_SLEEP=y
-CONFIG_DEBUG_CREDENTIALS=y
-CONFIG_DEBUG_INFO_BTF=y
 CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_DEBUG_MEMORY_INIT=y
 CONFIG_DEFAULT_FQ_CODEL=y
@@ -112,12 +103,10 @@ CONFIG_HZ_1000=y
 CONFIG_INET=y
 CONFIG_INPUT_EVDEV=y
 CONFIG_INTEL_POWERCLAMP=y
-CONFIG_IP6_NF_IPTABLES=y
 CONFIG_IP_ADVANCED_ROUTER=y
 CONFIG_IP_MROUTE=y
 CONFIG_IP_MULTICAST=y
 CONFIG_IP_MULTIPLE_TABLES=y
-CONFIG_IP_NF_IPTABLES=y
 CONFIG_IP_PIMSM_V1=y
 CONFIG_IP_PIMSM_V2=y
 CONFIG_IP_ROUTE_MULTIPATH=y
@@ -146,8 +135,6 @@ CONFIG_MEMORY_FAILURE=y
 CONFIG_MINIX_SUBPARTITION=y
 CONFIG_NAMESPACES=y
 CONFIG_NET=y
-CONFIG_NET_9P=y
-CONFIG_NET_9P_VIRTIO=y
 CONFIG_NET_ACT_BPF=y
 CONFIG_NET_CLS_CGROUP=y
 CONFIG_NET_EMATCH=y
@@ -172,7 +159,6 @@ CONFIG_NUMA=y
 CONFIG_NUMA_BALANCING=y
 CONFIG_NVMEM=y
 CONFIG_OSF_PARTITION=y
-CONFIG_PACKET=y
 CONFIG_PANIC_ON_OOPS=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_PCI=y
@@ -229,12 +215,8 @@ CONFIG_USER_NS=y
 CONFIG_VALIDATE_FS_PARSER=y
 CONFIG_VETH=y
 CONFIG_VIRT_DRIVERS=y
-CONFIG_VIRTIO_BALLOON=y
-CONFIG_VIRTIO_BLK=y
-CONFIG_VIRTIO_CONSOLE=y
-CONFIG_VIRTIO_NET=y
-CONFIG_VIRTIO_PCI=y
 CONFIG_VLAN_8021Q=y
+CONFIG_VSOCKETS_LOOPBACK=y
 CONFIG_X86_ACPI_CPUFREQ=y
 CONFIG_X86_CPUID=y
 CONFIG_X86_MSR=y
diff --git a/tools/testing/selftests/bpf/disasm.c b/tools/testing/selftests/bpf/disasm.c
new file mode 120000
index 000000000000..b1571927bd54
--- /dev/null
+++ b/tools/testing/selftests/bpf/disasm.c
@@ -0,0 +1 @@
+../../../../kernel/bpf/disasm.c
+\ No newline at end of file
diff --git a/tools/testing/selftests/bpf/disasm.h b/tools/testing/selftests/bpf/disasm.h
new file mode 120000
index 000000000000..8054fd497340
--- /dev/null
+++ b/tools/testing/selftests/bpf/disasm.h
@@ -0,0 +1 @@
+../../../../kernel/bpf/disasm.h
+\ No newline at end of file
diff --git a/tools/testing/selftests/bpf/disasm_helpers.c b/tools/testing/selftests/bpf/disasm_helpers.c
new file mode 100644
index 000000000000..f529f1c8c171
--- /dev/null
+++ b/tools/testing/selftests/bpf/disasm_helpers.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+#include <bpf/bpf.h>
+#include "disasm.h"
+
+struct print_insn_context {
+	char scratch[16];
+	char *buf;
+	size_t sz;
+};
+
+static void print_insn_cb(void *private_data, const char *fmt, ...)
+{
+	struct print_insn_context *ctx = private_data;
+	va_list args;
+
+	va_start(args, fmt);
+	vsnprintf(ctx->buf, ctx->sz, fmt, args);
+	va_end(args);
+}
+
+static const char *print_call_cb(void *private_data, const struct bpf_insn *insn)
+{
+	struct print_insn_context *ctx = private_data;
+
+	/* For pseudo calls verifier.c:jit_subprogs() hides original
+	 * imm to insn->off and changes insn->imm to be an index of
+	 * the subprog instead.
+	 */
+	if (insn->src_reg == BPF_PSEUDO_CALL) {
+		snprintf(ctx->scratch, sizeof(ctx->scratch), "%+d", insn->off);
+		return ctx->scratch;
+	}
+
+	return NULL;
+}
+
+struct bpf_insn *disasm_insn(struct bpf_insn *insn, char *buf, size_t buf_sz)
+{
+	struct print_insn_context ctx = {
+		.buf = buf,
+		.sz = buf_sz,
+	};
+	struct bpf_insn_cbs cbs = {
+		.cb_print	= print_insn_cb,
+		.cb_call	= print_call_cb,
+		.private_data	= &ctx,
+	};
+	char *tmp, *pfx_end, *sfx_start;
+	bool double_insn;
+	int len;
+
+	print_bpf_insn(&cbs, insn, true);
+	/* We share code with kernel BPF disassembler, it adds '(FF) ' prefix
+	 * for each instruction (FF stands for instruction `code` byte).
+	 * Remove the prefix inplace, and also simplify call instructions.
+	 * E.g.: "(85) call foo#10" -> "call foo".
+	 * Also remove newline in the end (the 'max(strlen(buf) - 1, 0)' thing).
+	 */
+	pfx_end = buf + 5;
+	sfx_start = buf + max((int)strlen(buf) - 1, 0);
+	if (strncmp(pfx_end, "call ", 5) == 0 && (tmp = strrchr(buf, '#')))
+		sfx_start = tmp;
+	len = sfx_start - pfx_end;
+	memmove(buf, pfx_end, len);
+	buf[len] = 0;
+	double_insn = insn->code == (BPF_LD | BPF_IMM | BPF_DW);
+	return insn + (double_insn ? 2 : 1);
+}
diff --git a/tools/testing/selftests/bpf/disasm_helpers.h b/tools/testing/selftests/bpf/disasm_helpers.h
new file mode 100644
index 000000000000..7b26cab70099
--- /dev/null
+++ b/tools/testing/selftests/bpf/disasm_helpers.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+
+#ifndef __DISASM_HELPERS_H
+#define __DISASM_HELPERS_H
+
+#include <stdlib.h>
+
+struct bpf_insn;
+
+struct bpf_insn *disasm_insn(struct bpf_insn *insn, char *buf, size_t buf_sz);
+
+#endif /* __DISASM_HELPERS_H */
diff --git a/tools/testing/selftests/bpf/generate_udp_fragments.py b/tools/testing/selftests/bpf/generate_udp_fragments.py
new file mode 100755
index 000000000000..2b8a1187991c
--- /dev/null
+++ b/tools/testing/selftests/bpf/generate_udp_fragments.py
@@ -0,0 +1,90 @@
+#!/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+This script helps generate fragmented UDP packets.
+
+While it is technically possible to dynamically generate
+fragmented packets in C, it is much harder to read and write
+said code. `scapy` is relatively industry standard and really
+easy to read / write.
+
+So we choose to write this script that generates a valid C
+header. Rerun script and commit generated file after any
+modifications.
+"""
+
+import argparse
+import os
+
+from scapy.all import *
+
+
+# These constants must stay in sync with `ip_check_defrag.c`
+VETH1_ADDR = "172.16.1.200"
+VETH0_ADDR6 = "fc00::100"
+VETH1_ADDR6 = "fc00::200"
+CLIENT_PORT = 48878
+SERVER_PORT = 48879
+MAGIC_MESSAGE = "THIS IS THE ORIGINAL MESSAGE, PLEASE REASSEMBLE ME"
+
+
+def print_header(f):
+    f.write("// SPDX-License-Identifier: GPL-2.0\n")
+    f.write("/* DO NOT EDIT -- this file is generated */\n")
+    f.write("\n")
+    f.write("#ifndef _IP_CHECK_DEFRAG_FRAGS_H\n")
+    f.write("#define _IP_CHECK_DEFRAG_FRAGS_H\n")
+    f.write("\n")
+    f.write("#include <stdint.h>\n")
+    f.write("\n")
+
+
+def print_frags(f, frags, v6):
+    for idx, frag in enumerate(frags):
+        # 10 bytes per line to keep width in check
+        chunks = [frag[i : i + 10] for i in range(0, len(frag), 10)]
+        chunks_fmted = [", ".join([str(hex(b)) for b in chunk]) for chunk in chunks]
+        suffix = "6" if v6 else ""
+
+        f.write(f"static uint8_t frag{suffix}_{idx}[] = {{\n")
+        for chunk in chunks_fmted:
+            f.write(f"\t{chunk},\n")
+        f.write(f"}};\n")
+
+
+def print_trailer(f):
+    f.write("\n")
+    f.write("#endif /* _IP_CHECK_DEFRAG_FRAGS_H */\n")
+
+
+def main(f):
+    # srcip of 0 is filled in by IP_HDRINCL
+    sip = "0.0.0.0"
+    sip6 = VETH0_ADDR6
+    dip = VETH1_ADDR
+    dip6 = VETH1_ADDR6
+    sport = CLIENT_PORT
+    dport = SERVER_PORT
+    payload = MAGIC_MESSAGE.encode()
+
+    # Disable UDPv4 checksums to keep code simpler
+    pkt = IP(src=sip,dst=dip) / UDP(sport=sport,dport=dport,chksum=0) / Raw(load=payload)
+    # UDPv6 requires a checksum
+    # Also pin the ipv6 fragment header ID, otherwise it's a random value
+    pkt6 = IPv6(src=sip6,dst=dip6) / IPv6ExtHdrFragment(id=0xBEEF) / UDP(sport=sport,dport=dport) / Raw(load=payload)
+
+    frags = [f.build() for f in pkt.fragment(24)]
+    frags6 = [f.build() for f in fragment6(pkt6, 72)]
+
+    print_header(f)
+    print_frags(f, frags, False)
+    print_frags(f, frags6, True)
+    print_trailer(f)
+
+
+if __name__ == "__main__":
+    dir = os.path.dirname(os.path.realpath(__file__))
+    header = f"{dir}/ip_check_defrag_frags.h"
+    with open(header, "w") as f:
+        main(f)
diff --git a/tools/testing/selftests/bpf/get_cgroup_id_user.c b/tools/testing/selftests/bpf/get_cgroup_id_user.c
deleted file mode 100644
index 156743cf5870..000000000000
--- a/tools/testing/selftests/bpf/get_cgroup_id_user.c
+++ /dev/null
@@ -1,146 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright (c) 2018 Facebook
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <errno.h>
-#include <fcntl.h>
-#include <syscall.h>
-#include <unistd.h>
-#include <linux/perf_event.h>
-#include <sys/ioctl.h>
-#include <sys/time.h>
-#include <sys/types.h>
-#include <sys/stat.h>
-
-#include <linux/bpf.h>
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-#include "cgroup_helpers.h"
-#include "testing_helpers.h"
-
-#define CHECK(condition, tag, format...) ({		\
-	int __ret = !!(condition);			\
-	if (__ret) {					\
-		printf("%s:FAIL:%s ", __func__, tag);	\
-		printf(format);				\
-	} else {					\
-		printf("%s:PASS:%s\n", __func__, tag);	\
-	}						\
-	__ret;						\
-})
-
-static int bpf_find_map(const char *test, struct bpf_object *obj,
-			const char *name)
-{
-	struct bpf_map *map;
-
-	map = bpf_object__find_map_by_name(obj, name);
-	if (!map)
-		return -1;
-	return bpf_map__fd(map);
-}
-
-#define TEST_CGROUP "/test-bpf-get-cgroup-id/"
-
-int main(int argc, char **argv)
-{
-	const char *probe_name = "syscalls/sys_enter_nanosleep";
-	const char *file = "get_cgroup_id_kern.bpf.o";
-	int err, bytes, efd, prog_fd, pmu_fd;
-	int cgroup_fd, cgidmap_fd, pidmap_fd;
-	struct perf_event_attr attr = {};
-	struct bpf_object *obj;
-	__u64 kcgid = 0, ucgid;
-	__u32 key = 0, pid;
-	int exit_code = 1;
-	char buf[256];
-	const struct timespec req = {
-		.tv_sec = 1,
-		.tv_nsec = 0,
-	};
-
-	cgroup_fd = cgroup_setup_and_join(TEST_CGROUP);
-	if (CHECK(cgroup_fd < 0, "cgroup_setup_and_join", "err %d errno %d\n", cgroup_fd, errno))
-		return 1;
-
-	/* Use libbpf 1.0 API mode */
-	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
-
-	err = bpf_prog_test_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd);
-	if (CHECK(err, "bpf_prog_test_load", "err %d errno %d\n", err, errno))
-		goto cleanup_cgroup_env;
-
-	cgidmap_fd = bpf_find_map(__func__, obj, "cg_ids");
-	if (CHECK(cgidmap_fd < 0, "bpf_find_map", "err %d errno %d\n",
-		  cgidmap_fd, errno))
-		goto close_prog;
-
-	pidmap_fd = bpf_find_map(__func__, obj, "pidmap");
-	if (CHECK(pidmap_fd < 0, "bpf_find_map", "err %d errno %d\n",
-		  pidmap_fd, errno))
-		goto close_prog;
-
-	pid = getpid();
-	bpf_map_update_elem(pidmap_fd, &key, &pid, 0);
-
-	snprintf(buf, sizeof(buf),
-		 "/sys/kernel/debug/tracing/events/%s/id", probe_name);
-	efd = open(buf, O_RDONLY, 0);
-	if (CHECK(efd < 0, "open", "err %d errno %d\n", efd, errno))
-		goto close_prog;
-	bytes = read(efd, buf, sizeof(buf));
-	close(efd);
-	if (CHECK(bytes <= 0 || bytes >= sizeof(buf), "read",
-		  "bytes %d errno %d\n", bytes, errno))
-		goto close_prog;
-
-	attr.config = strtol(buf, NULL, 0);
-	attr.type = PERF_TYPE_TRACEPOINT;
-	attr.sample_type = PERF_SAMPLE_RAW;
-	attr.sample_period = 1;
-	attr.wakeup_events = 1;
-
-	/* attach to this pid so the all bpf invocations will be in the
-	 * cgroup associated with this pid.
-	 */
-	pmu_fd = syscall(__NR_perf_event_open, &attr, getpid(), -1, -1, 0);
-	if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", pmu_fd,
-		  errno))
-		goto close_prog;
-
-	err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
-	if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n", err,
-		  errno))
-		goto close_pmu;
-
-	err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
-	if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n", err,
-		  errno))
-		goto close_pmu;
-
-	/* trigger some syscalls */
-	syscall(__NR_nanosleep, &req, NULL);
-
-	err = bpf_map_lookup_elem(cgidmap_fd, &key, &kcgid);
-	if (CHECK(err, "bpf_map_lookup_elem", "err %d errno %d\n", err, errno))
-		goto close_pmu;
-
-	ucgid = get_cgroup_id(TEST_CGROUP);
-	if (CHECK(kcgid != ucgid, "compare_cgroup_id",
-		  "kern cgid %llx user cgid %llx", kcgid, ucgid))
-		goto close_pmu;
-
-	exit_code = 0;
-	printf("%s:PASS\n", argv[0]);
-
-close_pmu:
-	close(pmu_fd);
-close_prog:
-	bpf_object__close(obj);
-cleanup_cgroup_env:
-	cleanup_cgroup_environment();
-	return exit_code;
-}
diff --git a/tools/testing/selftests/bpf/gnu/stubs.h b/tools/testing/selftests/bpf/gnu/stubs.h
index 719225b16626..1c638d9dce1a 100644
--- a/tools/testing/selftests/bpf/gnu/stubs.h
+++ b/tools/testing/selftests/bpf/gnu/stubs.h
@@ -1 +1 @@
-/* dummy .h to trick /usr/include/features.h to work with 'clang -target bpf' */
+/* dummy .h to trick /usr/include/features.h to work with 'clang --target=bpf' */
diff --git a/tools/testing/selftests/bpf/io_helpers.c b/tools/testing/selftests/bpf/io_helpers.c
new file mode 100644
index 000000000000..4ada0a74aa1f
--- /dev/null
+++ b/tools/testing/selftests/bpf/io_helpers.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <sys/select.h>
+#include <unistd.h>
+#include <errno.h>
+
+int read_with_timeout(int fd, char *buf, size_t count, long usec)
+{
+	const long M = 1000 * 1000;
+	struct timeval tv = { usec / M, usec % M };
+	fd_set fds;
+	int err;
+
+	FD_ZERO(&fds);
+	FD_SET(fd, &fds);
+	err = select(fd + 1, &fds, NULL, NULL, &tv);
+	if (err < 0)
+		return err;
+	if (FD_ISSET(fd, &fds))
+		return read(fd, buf, count);
+	return -EAGAIN;
+}
diff --git a/tools/testing/selftests/bpf/io_helpers.h b/tools/testing/selftests/bpf/io_helpers.h
new file mode 100644
index 000000000000..21e1134cd3ce
--- /dev/null
+++ b/tools/testing/selftests/bpf/io_helpers.h
@@ -0,0 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <unistd.h>
+
+/* As a regular read(2), but allows to specify a timeout in micro-seconds.
+ * Returns -EAGAIN on timeout.
+ */
+int read_with_timeout(int fd, char *buf, size_t count, long usec);
diff --git a/tools/testing/selftests/bpf/ip_check_defrag_frags.h b/tools/testing/selftests/bpf/ip_check_defrag_frags.h
new file mode 100644
index 000000000000..70ab7e9fa22b
--- /dev/null
+++ b/tools/testing/selftests/bpf/ip_check_defrag_frags.h
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+/* DO NOT EDIT -- this file is generated */
+
+#ifndef _IP_CHECK_DEFRAG_FRAGS_H
+#define _IP_CHECK_DEFRAG_FRAGS_H
+
+#include <stdint.h>
+
+static uint8_t frag_0[] = {
+	0x45, 0x0, 0x0, 0x2c, 0x0, 0x1, 0x20, 0x0, 0x40, 0x11,
+	0xac, 0xe8, 0x0, 0x0, 0x0, 0x0, 0xac, 0x10, 0x1, 0xc8,
+	0xbe, 0xee, 0xbe, 0xef, 0x0, 0x3a, 0x0, 0x0, 0x54, 0x48,
+	0x49, 0x53, 0x20, 0x49, 0x53, 0x20, 0x54, 0x48, 0x45, 0x20,
+	0x4f, 0x52, 0x49, 0x47,
+};
+static uint8_t frag_1[] = {
+	0x45, 0x0, 0x0, 0x2c, 0x0, 0x1, 0x20, 0x3, 0x40, 0x11,
+	0xac, 0xe5, 0x0, 0x0, 0x0, 0x0, 0xac, 0x10, 0x1, 0xc8,
+	0x49, 0x4e, 0x41, 0x4c, 0x20, 0x4d, 0x45, 0x53, 0x53, 0x41,
+	0x47, 0x45, 0x2c, 0x20, 0x50, 0x4c, 0x45, 0x41, 0x53, 0x45,
+	0x20, 0x52, 0x45, 0x41,
+};
+static uint8_t frag_2[] = {
+	0x45, 0x0, 0x0, 0x1e, 0x0, 0x1, 0x0, 0x6, 0x40, 0x11,
+	0xcc, 0xf0, 0x0, 0x0, 0x0, 0x0, 0xac, 0x10, 0x1, 0xc8,
+	0x53, 0x53, 0x45, 0x4d, 0x42, 0x4c, 0x45, 0x20, 0x4d, 0x45,
+};
+static uint8_t frag6_0[] = {
+	0x60, 0x0, 0x0, 0x0, 0x0, 0x20, 0x2c, 0x40, 0xfc, 0x0,
+	0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+	0x0, 0x0, 0x1, 0x0, 0xfc, 0x0, 0x0, 0x0, 0x0, 0x0,
+	0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x2, 0x0,
+	0x11, 0x0, 0x0, 0x1, 0x0, 0x0, 0xbe, 0xef, 0xbe, 0xee,
+	0xbe, 0xef, 0x0, 0x3a, 0xd0, 0xf8, 0x54, 0x48, 0x49, 0x53,
+	0x20, 0x49, 0x53, 0x20, 0x54, 0x48, 0x45, 0x20, 0x4f, 0x52,
+	0x49, 0x47,
+};
+static uint8_t frag6_1[] = {
+	0x60, 0x0, 0x0, 0x0, 0x0, 0x20, 0x2c, 0x40, 0xfc, 0x0,
+	0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+	0x0, 0x0, 0x1, 0x0, 0xfc, 0x0, 0x0, 0x0, 0x0, 0x0,
+	0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x2, 0x0,
+	0x11, 0x0, 0x0, 0x19, 0x0, 0x0, 0xbe, 0xef, 0x49, 0x4e,
+	0x41, 0x4c, 0x20, 0x4d, 0x45, 0x53, 0x53, 0x41, 0x47, 0x45,
+	0x2c, 0x20, 0x50, 0x4c, 0x45, 0x41, 0x53, 0x45, 0x20, 0x52,
+	0x45, 0x41,
+};
+static uint8_t frag6_2[] = {
+	0x60, 0x0, 0x0, 0x0, 0x0, 0x12, 0x2c, 0x40, 0xfc, 0x0,
+	0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+	0x0, 0x0, 0x1, 0x0, 0xfc, 0x0, 0x0, 0x0, 0x0, 0x0,
+	0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x2, 0x0,
+	0x11, 0x0, 0x0, 0x30, 0x0, 0x0, 0xbe, 0xef, 0x53, 0x53,
+	0x45, 0x4d, 0x42, 0x4c, 0x45, 0x20, 0x4d, 0x45,
+};
+
+#endif /* _IP_CHECK_DEFRAG_FRAGS_H */
diff --git a/tools/testing/selftests/bpf/jit_disasm_helpers.c b/tools/testing/selftests/bpf/jit_disasm_helpers.c
new file mode 100644
index 000000000000..febd6b12e372
--- /dev/null
+++ b/tools/testing/selftests/bpf/jit_disasm_helpers.c
@@ -0,0 +1,245 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <test_progs.h>
+
+#ifdef HAVE_LLVM_SUPPORT
+
+#include <llvm-c/Core.h>
+#include <llvm-c/Disassembler.h>
+#include <llvm-c/Target.h>
+#include <llvm-c/TargetMachine.h>
+
+/* The intent is to use get_jited_program_text() for small test
+ * programs written in BPF assembly, thus assume that 32 local labels
+ * would be sufficient.
+ */
+#define MAX_LOCAL_LABELS 32
+
+/* Local labels are encoded as 'L42', this requires 4 bytes of storage:
+ * 3 characters + zero byte
+ */
+#define LOCAL_LABEL_LEN 4
+
+static bool llvm_initialized;
+
+struct local_labels {
+	bool print_phase;
+	__u32 prog_len;
+	__u32 cnt;
+	__u32 pcs[MAX_LOCAL_LABELS];
+	char names[MAX_LOCAL_LABELS][LOCAL_LABEL_LEN];
+};
+
+static const char *lookup_symbol(void *data, uint64_t ref_value, uint64_t *ref_type,
+				 uint64_t ref_pc, const char **ref_name)
+{
+	struct local_labels *labels = data;
+	uint64_t type = *ref_type;
+	int i;
+
+	*ref_type = LLVMDisassembler_ReferenceType_InOut_None;
+	*ref_name = NULL;
+	if (type != LLVMDisassembler_ReferenceType_In_Branch)
+		return NULL;
+	/* Depending on labels->print_phase either discover local labels or
+	 * return a name assigned with local jump target:
+	 * - if print_phase is true and ref_value is in labels->pcs,
+	 *   return corresponding labels->name.
+	 * - if print_phase is false, save program-local jump targets
+	 *   in labels->pcs;
+	 */
+	if (labels->print_phase) {
+		for (i = 0; i < labels->cnt; ++i)
+			if (labels->pcs[i] == ref_value)
+				return labels->names[i];
+	} else {
+		if (labels->cnt < MAX_LOCAL_LABELS && ref_value < labels->prog_len)
+			labels->pcs[labels->cnt++] = ref_value;
+	}
+	return NULL;
+}
+
+static int disasm_insn(LLVMDisasmContextRef ctx, uint8_t *image, __u32 len, __u32 pc,
+		       char *buf, __u32 buf_sz)
+{
+	int i, cnt;
+
+	cnt = LLVMDisasmInstruction(ctx, image + pc, len - pc, pc,
+				    buf, buf_sz);
+	if (cnt > 0)
+		return cnt;
+	PRINT_FAIL("Can't disasm instruction at offset %d:", pc);
+	for (i = 0; i < 16 && pc + i < len; ++i)
+		printf(" %02x", image[pc + i]);
+	printf("\n");
+	return -EINVAL;
+}
+
+static int cmp_u32(const void *_a, const void *_b)
+{
+	__u32 a = *(__u32 *)_a;
+	__u32 b = *(__u32 *)_b;
+
+	if (a < b)
+		return -1;
+	if (a > b)
+		return 1;
+	return 0;
+}
+
+static int disasm_one_func(FILE *text_out, uint8_t *image, __u32 len)
+{
+	char *label, *colon, *triple = NULL;
+	LLVMDisasmContextRef ctx = NULL;
+	struct local_labels labels = {};
+	__u32 *label_pc, pc;
+	int i, cnt, err = 0;
+	char buf[64];
+
+	triple = LLVMGetDefaultTargetTriple();
+	ctx = LLVMCreateDisasm(triple, &labels, 0, NULL, lookup_symbol);
+	if (!ASSERT_OK_PTR(ctx, "LLVMCreateDisasm")) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	cnt = LLVMSetDisasmOptions(ctx, LLVMDisassembler_Option_PrintImmHex);
+	if (!ASSERT_EQ(cnt, 1, "LLVMSetDisasmOptions")) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	/* discover labels */
+	labels.prog_len = len;
+	pc = 0;
+	while (pc < len) {
+		cnt = disasm_insn(ctx, image, len, pc, buf, 1);
+		if (cnt < 0) {
+			err = cnt;
+			goto out;
+		}
+		pc += cnt;
+	}
+	qsort(labels.pcs, labels.cnt, sizeof(*labels.pcs), cmp_u32);
+	for (i = 0; i < labels.cnt; ++i)
+		/* gcc is unable to infer upper bound for labels.cnt and assumes
+		 * it to be U32_MAX. U32_MAX takes 10 decimal digits.
+		 * snprintf below prints into labels.names[*],
+		 * which has space only for two digits and a letter.
+		 * To avoid truncation warning use (i % MAX_LOCAL_LABELS),
+		 * which informs gcc about printed value upper bound.
+		 */
+		snprintf(labels.names[i], sizeof(labels.names[i]), "L%d", i % MAX_LOCAL_LABELS);
+
+	/* now print with labels */
+	labels.print_phase = true;
+	pc = 0;
+	while (pc < len) {
+		cnt = disasm_insn(ctx, image, len, pc, buf, sizeof(buf));
+		if (cnt < 0) {
+			err = cnt;
+			goto out;
+		}
+		label_pc = bsearch(&pc, labels.pcs, labels.cnt, sizeof(*labels.pcs), cmp_u32);
+		label = "";
+		colon = "";
+		if (label_pc) {
+			label = labels.names[label_pc - labels.pcs];
+			colon = ":";
+		}
+		fprintf(text_out, "%x:\t", pc);
+		for (i = 0; i < cnt; ++i)
+			fprintf(text_out, "%02x ", image[pc + i]);
+		for (i = cnt * 3; i < 12 * 3; ++i)
+			fputc(' ', text_out);
+		fprintf(text_out, "%s%s%s\n", label, colon, buf);
+		pc += cnt;
+	}
+
+out:
+	if (triple)
+		LLVMDisposeMessage(triple);
+	if (ctx)
+		LLVMDisasmDispose(ctx);
+	return err;
+}
+
+int get_jited_program_text(int fd, char *text, size_t text_sz)
+{
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
+	__u32 jited_funcs, len, pc;
+	__u32 *func_lens = NULL;
+	FILE *text_out = NULL;
+	uint8_t *image = NULL;
+	int i, err = 0;
+
+	if (!llvm_initialized) {
+		LLVMInitializeAllTargetInfos();
+		LLVMInitializeAllTargetMCs();
+		LLVMInitializeAllDisassemblers();
+		llvm_initialized = 1;
+	}
+
+	text_out = fmemopen(text, text_sz, "w");
+	if (!ASSERT_OK_PTR(text_out, "open_memstream")) {
+		err = -errno;
+		goto out;
+	}
+
+	/* first call is to find out jited program len */
+	err = bpf_prog_get_info_by_fd(fd, &info, &info_len);
+	if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd #1"))
+		goto out;
+
+	len = info.jited_prog_len;
+	image = malloc(len);
+	if (!ASSERT_OK_PTR(image, "malloc(info.jited_prog_len)")) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	jited_funcs = info.nr_jited_func_lens;
+	func_lens = malloc(jited_funcs * sizeof(__u32));
+	if (!ASSERT_OK_PTR(func_lens, "malloc(info.nr_jited_func_lens)")) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	memset(&info, 0, sizeof(info));
+	info.jited_prog_insns = (__u64)image;
+	info.jited_prog_len = len;
+	info.jited_func_lens = (__u64)func_lens;
+	info.nr_jited_func_lens = jited_funcs;
+	err = bpf_prog_get_info_by_fd(fd, &info, &info_len);
+	if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd #2"))
+		goto out;
+
+	for (pc = 0, i = 0; i < jited_funcs; ++i) {
+		fprintf(text_out, "func #%d:\n", i);
+		disasm_one_func(text_out, image + pc, func_lens[i]);
+		fprintf(text_out, "\n");
+		pc += func_lens[i];
+	}
+
+out:
+	if (text_out)
+		fclose(text_out);
+	if (image)
+		free(image);
+	if (func_lens)
+		free(func_lens);
+	return err;
+}
+
+#else /* HAVE_LLVM_SUPPORT */
+
+int get_jited_program_text(int fd, char *text, size_t text_sz)
+{
+	if (env.verbosity >= VERBOSE_VERY)
+		printf("compiled w/o llvm development libraries, can't dis-assembly binary code");
+	return -EOPNOTSUPP;
+}
+
+#endif /* HAVE_LLVM_SUPPORT */
diff --git a/tools/testing/selftests/bpf/jit_disasm_helpers.h b/tools/testing/selftests/bpf/jit_disasm_helpers.h
new file mode 100644
index 000000000000..e6924fd65ecf
--- /dev/null
+++ b/tools/testing/selftests/bpf/jit_disasm_helpers.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+
+#ifndef __JIT_DISASM_HELPERS_H
+#define __JIT_DISASM_HELPERS_H
+
+#include <stddef.h>
+
+int get_jited_program_text(int fd, char *text, size_t text_sz);
+
+#endif /* __JIT_DISASM_HELPERS_H */
diff --git a/tools/testing/selftests/bpf/json_writer.c b/tools/testing/selftests/bpf/json_writer.c
new file mode 120000
index 000000000000..5effa31e2f39
--- /dev/null
+++ b/tools/testing/selftests/bpf/json_writer.c
@@ -0,0 +1 @@
+../../../bpf/bpftool/json_writer.c
+\ No newline at end of file
diff --git a/tools/testing/selftests/bpf/json_writer.h b/tools/testing/selftests/bpf/json_writer.h
new file mode 120000
index 000000000000..e0a264c26752
--- /dev/null
+++ b/tools/testing/selftests/bpf/json_writer.h
@@ -0,0 +1 @@
+../../../bpf/bpftool/json_writer.h
+\ No newline at end of file
diff --git a/tools/testing/selftests/bpf/liburandom_read.map b/tools/testing/selftests/bpf/liburandom_read.map
new file mode 100644
index 000000000000..38a97a419a04
--- /dev/null
+++ b/tools/testing/selftests/bpf/liburandom_read.map
@@ -0,0 +1,15 @@
+LIBURANDOM_READ_1.0.0 {
+	global:
+		urandlib_api;
+		urandlib_api_sameoffset;
+		urandlib_read_without_sema;
+		urandlib_read_with_sema;
+		urandlib_read_with_sema_semaphore;
+	local:
+		*;
+};
+
+LIBURANDOM_READ_2.0.0 {
+	global:
+		urandlib_api;
+} LIBURANDOM_READ_1.0.0;
diff --git a/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c
index 1230ccf90128..5da493b94ae2 100644
--- a/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c
+++ b/tools/testing/selftests/bpf/map_tests/htab_map_batch_ops.c
@@ -197,7 +197,7 @@ void __test_map_lookup_and_delete_batch(bool is_pcpu)
 		CHECK(total != max_entries, "delete with steps",
 		      "total = %u, max_entries = %u\n", total, max_entries);
 
-		/* check map is empty, errono == ENOENT */
+		/* check map is empty, errno == ENOENT */
 		err = bpf_map_get_next_key(map_fd, NULL, &key);
 		CHECK(!err || errno != ENOENT, "bpf_map_get_next_key()",
 		      "error: %s\n", strerror(errno));
diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c
index c028d621c744..d32e4edac930 100644
--- a/tools/testing/selftests/bpf/test_lpm_map.c
+++ b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_basic_ops.c
@@ -20,10 +20,12 @@
 #include <string.h>
 #include <time.h>
 #include <unistd.h>
+#include <endian.h>
 #include <arpa/inet.h>
 #include <sys/time.h>
 
 #include <bpf/bpf.h>
+#include <test_maps.h>
 
 #include "bpf_util.h"
 
@@ -33,6 +35,22 @@ struct tlpm_node {
 	uint8_t key[];
 };
 
+struct lpm_trie_bytes_key {
+	union {
+		struct bpf_lpm_trie_key_hdr hdr;
+		__u32 prefixlen;
+	};
+	unsigned char data[8];
+};
+
+struct lpm_trie_int_key {
+	union {
+		struct bpf_lpm_trie_key_hdr hdr;
+		__u32 prefixlen;
+	};
+	unsigned int data;
+};
+
 static struct tlpm_node *tlpm_match(struct tlpm_node *list,
 				    const uint8_t *key,
 				    size_t n_bits);
@@ -211,7 +229,7 @@ static void test_lpm_map(int keysize)
 	volatile size_t n_matches, n_matches_after_delete;
 	size_t i, j, n_nodes, n_lookups;
 	struct tlpm_node *t, *list = NULL;
-	struct bpf_lpm_trie_key *key;
+	struct bpf_lpm_trie_key_u8 *key;
 	uint8_t *data, *value;
 	int r, map;
 
@@ -223,7 +241,7 @@ static void test_lpm_map(int keysize)
 	n_matches = 0;
 	n_matches_after_delete = 0;
 	n_nodes = 1 << 8;
-	n_lookups = 1 << 16;
+	n_lookups = 1 << 9;
 
 	data = alloca(keysize);
 	memset(data, 0, keysize);
@@ -331,8 +349,8 @@ static void test_lpm_map(int keysize)
 static void test_lpm_ipaddr(void)
 {
 	LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC);
-	struct bpf_lpm_trie_key *key_ipv4;
-	struct bpf_lpm_trie_key *key_ipv6;
+	struct bpf_lpm_trie_key_u8 *key_ipv4;
+	struct bpf_lpm_trie_key_u8 *key_ipv6;
 	size_t key_size_ipv4;
 	size_t key_size_ipv6;
 	int map_fd_ipv4;
@@ -423,7 +441,7 @@ static void test_lpm_ipaddr(void)
 static void test_lpm_delete(void)
 {
 	LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC);
-	struct bpf_lpm_trie_key *key;
+	struct bpf_lpm_trie_key_u8 *key;
 	size_t key_size;
 	int map_fd;
 	__u64 value;
@@ -532,7 +550,7 @@ static void test_lpm_delete(void)
 static void test_lpm_get_next_key(void)
 {
 	LIBBPF_OPTS(bpf_map_create_opts, opts, .map_flags = BPF_F_NO_PREALLOC);
-	struct bpf_lpm_trie_key *key_p, *next_key_p;
+	struct bpf_lpm_trie_key_u8 *key_p, *next_key_p;
 	size_t key_size;
 	__u32 value = 0;
 	int map_fd;
@@ -693,9 +711,9 @@ static void *lpm_test_command(void *arg)
 {
 	int i, j, ret, iter, key_size;
 	struct lpm_mt_test_info *info = arg;
-	struct bpf_lpm_trie_key *key_p;
+	struct bpf_lpm_trie_key_u8 *key_p;
 
-	key_size = sizeof(struct bpf_lpm_trie_key) + sizeof(__u32);
+	key_size = sizeof(*key_p) + sizeof(__u32);
 	key_p = alloca(key_size);
 	for (iter = 0; iter < info->iter; iter++)
 		for (i = 0; i < MAX_TEST_KEYS; i++) {
@@ -717,7 +735,7 @@ static void *lpm_test_command(void *arg)
 				ret = bpf_map_lookup_elem(info->map_fd, key_p, &value);
 				assert(ret == 0 || errno == ENOENT);
 			} else {
-				struct bpf_lpm_trie_key *next_key_p = alloca(key_size);
+				struct bpf_lpm_trie_key_u8 *next_key_p = alloca(key_size);
 				ret = bpf_map_get_next_key(info->map_fd, key_p, next_key_p);
 				assert(ret == 0 || errno == ENOENT || errno == ENOMEM);
 			}
@@ -752,7 +770,7 @@ static void test_lpm_multi_thread(void)
 
 	/* create a trie */
 	value_size = sizeof(__u32);
-	key_size = sizeof(struct bpf_lpm_trie_key) + value_size;
+	key_size = sizeof(struct bpf_lpm_trie_key_hdr) + value_size;
 	map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, NULL, key_size, value_size, 100, &opts);
 
 	/* create 4 threads to test update, delete, lookup and get_next_key */
@@ -770,16 +788,385 @@ static void test_lpm_multi_thread(void)
 	close(map_fd);
 }
 
-int main(void)
+static int lpm_trie_create(unsigned int key_size, unsigned int value_size, unsigned int max_entries)
+{
+	LIBBPF_OPTS(bpf_map_create_opts, opts);
+	int fd;
+
+	opts.map_flags = BPF_F_NO_PREALLOC;
+	fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, "lpm_trie", key_size, value_size, max_entries,
+			    &opts);
+	CHECK(fd < 0, "bpf_map_create", "error %d\n", errno);
+
+	return fd;
+}
+
+static void test_lpm_trie_update_flags(void)
+{
+	struct lpm_trie_int_key key;
+	unsigned int value, got;
+	int fd, err;
+
+	fd = lpm_trie_create(sizeof(key), sizeof(value), 3);
+
+	/* invalid flags (Error) */
+	key.prefixlen = 32;
+	key.data = 0;
+	value = 0;
+	err = bpf_map_update_elem(fd, &key, &value, BPF_F_LOCK);
+	CHECK(err != -EINVAL, "invalid update flag", "error %d\n", err);
+
+	/* invalid flags (Error) */
+	key.prefixlen = 32;
+	key.data = 0;
+	value = 0;
+	err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST | BPF_EXIST);
+	CHECK(err != -EINVAL, "invalid update flag", "error %d\n", err);
+
+	/* overwrite an empty qp-trie (Error) */
+	key.prefixlen = 32;
+	key.data = 0;
+	value = 2;
+	err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST);
+	CHECK(err != -ENOENT, "overwrite empty qp-trie", "error %d\n", err);
+
+	/* add a new node */
+	key.prefixlen = 16;
+	key.data = 0;
+	value = 1;
+	err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+	CHECK(err, "add new elem", "error %d\n", err);
+	got = 0;
+	err = bpf_map_lookup_elem(fd, &key, &got);
+	CHECK(err, "lookup elem", "error %d\n", err);
+	CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+	/* add the same node as new node (Error) */
+	err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+	CHECK(err != -EEXIST, "add new elem again", "error %d\n", err);
+
+	/* overwrite the existed node */
+	value = 4;
+	err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST);
+	CHECK(err, "overwrite elem", "error %d\n", err);
+	got = 0;
+	err = bpf_map_lookup_elem(fd, &key, &got);
+	CHECK(err, "lookup elem", "error %d\n", err);
+	CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+	/* overwrite the node */
+	value = 1;
+	err = bpf_map_update_elem(fd, &key, &value, BPF_ANY);
+	CHECK(err, "update elem", "error %d\n", err);
+	got = 0;
+	err = bpf_map_lookup_elem(fd, &key, &got);
+	CHECK(err, "lookup elem", "error %d\n", err);
+	CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+	/* overwrite a non-existent node which is the prefix of the first
+	 * node (Error).
+	 */
+	key.prefixlen = 8;
+	key.data = 0;
+	value = 2;
+	err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST);
+	CHECK(err != -ENOENT, "overwrite nonexistent elem", "error %d\n", err);
+
+	/* add a new node which is the prefix of the first node */
+	err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+	CHECK(err, "add new elem", "error %d\n", err);
+	got = 0;
+	err = bpf_map_lookup_elem(fd, &key, &got);
+	CHECK(err, "lookup key", "error %d\n", err);
+	CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+	/* add another new node which will be the sibling of the first node */
+	key.prefixlen = 9;
+	key.data = htobe32(1 << 23);
+	value = 5;
+	err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+	CHECK(err, "add new elem", "error %d\n", err);
+	got = 0;
+	err = bpf_map_lookup_elem(fd, &key, &got);
+	CHECK(err, "lookup key", "error %d\n", err);
+	CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+	/* overwrite the third node */
+	value = 3;
+	err = bpf_map_update_elem(fd, &key, &value, BPF_ANY);
+	CHECK(err, "overwrite elem", "error %d\n", err);
+	got = 0;
+	err = bpf_map_lookup_elem(fd, &key, &got);
+	CHECK(err, "lookup key", "error %d\n", err);
+	CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+	/* delete the second node to make it an intermediate node */
+	key.prefixlen = 8;
+	key.data = 0;
+	err = bpf_map_delete_elem(fd, &key);
+	CHECK(err, "del elem", "error %d\n", err);
+
+	/* overwrite the intermediate node (Error) */
+	value = 2;
+	err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST);
+	CHECK(err != -ENOENT, "overwrite nonexistent elem", "error %d\n", err);
+
+	close(fd);
+}
+
+static void test_lpm_trie_update_full_map(void)
+{
+	struct lpm_trie_int_key key;
+	int value, got;
+	int fd, err;
+
+	fd = lpm_trie_create(sizeof(key), sizeof(value), 3);
+
+	/* add a new node */
+	key.prefixlen = 16;
+	key.data = 0;
+	value = 0;
+	err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+	CHECK(err, "add new elem", "error %d\n", err);
+	got = 0;
+	err = bpf_map_lookup_elem(fd, &key, &got);
+	CHECK(err, "lookup elem", "error %d\n", err);
+	CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+	/* add new node */
+	key.prefixlen = 8;
+	key.data = 0;
+	value = 1;
+	err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+	CHECK(err, "add new elem", "error %d\n", err);
+	got = 0;
+	err = bpf_map_lookup_elem(fd, &key, &got);
+	CHECK(err, "lookup elem", "error %d\n", err);
+	CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+	/* add new node */
+	key.prefixlen = 9;
+	key.data = htobe32(1 << 23);
+	value = 2;
+	err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+	CHECK(err, "add new elem", "error %d\n", err);
+	got = 0;
+	err = bpf_map_lookup_elem(fd, &key, &got);
+	CHECK(err, "lookup elem", "error %d\n", err);
+	CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+	/* try to add more node (Error) */
+	key.prefixlen = 32;
+	key.data = 0;
+	value = 3;
+	err = bpf_map_update_elem(fd, &key, &value, BPF_ANY);
+	CHECK(err != -ENOSPC, "add to full trie", "error %d\n", err);
+
+	/* update the value of an existed node with BPF_EXIST */
+	key.prefixlen = 16;
+	key.data = 0;
+	value = 4;
+	err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST);
+	CHECK(err, "overwrite elem", "error %d\n", err);
+	got = 0;
+	err = bpf_map_lookup_elem(fd, &key, &got);
+	CHECK(err, "lookup elem", "error %d\n", err);
+	CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+	/* update the value of an existed node with BPF_ANY */
+	key.prefixlen = 9;
+	key.data = htobe32(1 << 23);
+	value = 5;
+	err = bpf_map_update_elem(fd, &key, &value, BPF_ANY);
+	CHECK(err, "overwrite elem", "error %d\n", err);
+	got = 0;
+	err = bpf_map_lookup_elem(fd, &key, &got);
+	CHECK(err, "lookup elem", "error %d\n", err);
+	CHECK(got != value, "check value", "got %d exp %d\n", got, value);
+
+	close(fd);
+}
+
+static int cmp_str(const void *a, const void *b)
+{
+	const char *str_a = *(const char **)a, *str_b = *(const char **)b;
+
+	return strcmp(str_a, str_b);
+}
+
+/* Save strings in LPM trie. The trailing '\0' for each string will be
+ * accounted in the prefixlen. The strings returned during the iteration
+ * should be sorted as expected.
+ */
+static void test_lpm_trie_iterate_strs(void)
+{
+	static const char * const keys[] = {
+		"ab", "abO", "abc", "abo", "abS", "abcd",
+	};
+	const char *sorted_keys[ARRAY_SIZE(keys)];
+	struct lpm_trie_bytes_key key, next_key;
+	unsigned int value, got, i, j, len;
+	struct lpm_trie_bytes_key *cur;
+	int fd, err;
+
+	fd = lpm_trie_create(sizeof(key), sizeof(value), ARRAY_SIZE(keys));
+
+	for (i = 0; i < ARRAY_SIZE(keys); i++) {
+		unsigned int flags;
+
+		/* add i-th element */
+		flags = i % 2 ? BPF_NOEXIST : 0;
+		len = strlen(keys[i]);
+		/* include the trailing '\0' */
+		key.prefixlen = (len + 1) * 8;
+		memset(key.data, 0, sizeof(key.data));
+		memcpy(key.data, keys[i], len);
+		value = i + 100;
+		err = bpf_map_update_elem(fd, &key, &value, flags);
+		CHECK(err, "add elem", "#%u error %d\n", i, err);
+
+		err = bpf_map_lookup_elem(fd, &key, &got);
+		CHECK(err, "lookup elem", "#%u error %d\n", i, err);
+		CHECK(got != value, "lookup elem", "#%u expect %u got %u\n", i, value, got);
+
+		/* re-add i-th element (Error) */
+		err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+		CHECK(err != -EEXIST, "re-add elem", "#%u error %d\n", i, err);
+
+		/* Overwrite i-th element */
+		flags = i % 2 ? 0 : BPF_EXIST;
+		value = i;
+		err = bpf_map_update_elem(fd, &key, &value, flags);
+		CHECK(err, "update elem", "error %d\n", err);
+
+		/* Lookup #[0~i] elements */
+		for (j = 0; j <= i; j++) {
+			len = strlen(keys[j]);
+			key.prefixlen = (len + 1) * 8;
+			memset(key.data, 0, sizeof(key.data));
+			memcpy(key.data, keys[j], len);
+			err = bpf_map_lookup_elem(fd, &key, &got);
+			CHECK(err, "lookup elem", "#%u/%u error %d\n", i, j, err);
+			CHECK(got != j, "lookup elem", "#%u/%u expect %u got %u\n",
+			      i, j, value, got);
+		}
+	}
+
+	/* Add element to a full qp-trie (Error) */
+	key.prefixlen = sizeof(key.data) * 8;
+	memset(key.data, 0, sizeof(key.data));
+	value = 0;
+	err = bpf_map_update_elem(fd, &key, &value, 0);
+	CHECK(err != -ENOSPC, "add to full qp-trie", "error %d\n", err);
+
+	/* Iterate sorted elements: no deletion */
+	memcpy(sorted_keys, keys, sizeof(keys));
+	qsort(sorted_keys, ARRAY_SIZE(sorted_keys), sizeof(sorted_keys[0]), cmp_str);
+	cur = NULL;
+	for (i = 0; i < ARRAY_SIZE(sorted_keys); i++) {
+		len = strlen(sorted_keys[i]);
+		err = bpf_map_get_next_key(fd, cur, &next_key);
+		CHECK(err, "iterate", "#%u error %d\n", i, err);
+		CHECK(next_key.prefixlen != (len + 1) * 8, "iterate",
+		      "#%u invalid len %u expect %u\n",
+		      i, next_key.prefixlen, (len + 1) * 8);
+		CHECK(memcmp(sorted_keys[i], next_key.data, len + 1), "iterate",
+		      "#%u got %.*s exp %.*s\n", i, len, next_key.data, len, sorted_keys[i]);
+
+		cur = &next_key;
+	}
+	err = bpf_map_get_next_key(fd, cur, &next_key);
+	CHECK(err != -ENOENT, "more element", "error %d\n", err);
+
+	/* Iterate sorted elements: delete the found key after each iteration */
+	cur = NULL;
+	for (i = 0; i < ARRAY_SIZE(sorted_keys); i++) {
+		len = strlen(sorted_keys[i]);
+		err = bpf_map_get_next_key(fd, cur, &next_key);
+		CHECK(err, "iterate", "#%u error %d\n", i, err);
+		CHECK(next_key.prefixlen != (len + 1) * 8, "iterate",
+		      "#%u invalid len %u expect %u\n",
+		      i, next_key.prefixlen, (len + 1) * 8);
+		CHECK(memcmp(sorted_keys[i], next_key.data, len + 1), "iterate",
+		      "#%u got %.*s exp %.*s\n", i, len, next_key.data, len, sorted_keys[i]);
+
+		cur = &next_key;
+
+		err = bpf_map_delete_elem(fd, cur);
+		CHECK(err, "delete", "#%u error %d\n", i, err);
+	}
+	err = bpf_map_get_next_key(fd, cur, &next_key);
+	CHECK(err != -ENOENT, "non-empty qp-trie", "error %d\n", err);
+
+	close(fd);
+}
+
+/* Use the fixed prefixlen (32) and save integers in LPM trie. The iteration of
+ * LPM trie will return these integers in big-endian order, therefore, convert
+ * these integers to big-endian before update. After each iteration, delete the
+ * found key (the smallest integer) and expect the next iteration will return
+ * the second smallest number.
+ */
+static void test_lpm_trie_iterate_ints(void)
+{
+	struct lpm_trie_int_key key, next_key;
+	unsigned int i, max_entries;
+	struct lpm_trie_int_key *cur;
+	unsigned int *data_set;
+	int fd, err;
+	bool value;
+
+	max_entries = 4096;
+	data_set = calloc(max_entries, sizeof(*data_set));
+	CHECK(!data_set, "malloc", "no mem\n");
+	for (i = 0; i < max_entries; i++)
+		data_set[i] = i;
+
+	fd = lpm_trie_create(sizeof(key), sizeof(value), max_entries);
+	value = true;
+	for (i = 0; i < max_entries; i++) {
+		key.prefixlen = 32;
+		key.data = htobe32(data_set[i]);
+
+		err = bpf_map_update_elem(fd, &key, &value, BPF_NOEXIST);
+		CHECK(err, "add elem", "#%u error %d\n", i, err);
+	}
+
+	cur = NULL;
+	for (i = 0; i < max_entries; i++) {
+		err = bpf_map_get_next_key(fd, cur, &next_key);
+		CHECK(err, "iterate", "#%u error %d\n", i, err);
+		CHECK(next_key.prefixlen != 32, "iterate", "#%u invalid len %u\n",
+		      i, next_key.prefixlen);
+		CHECK(be32toh(next_key.data) != data_set[i], "iterate", "#%u got 0x%x exp 0x%x\n",
+		      i, be32toh(next_key.data), data_set[i]);
+		cur = &next_key;
+
+		/*
+		 * Delete the minimal key, the next call of bpf_get_next_key()
+		 * will return the second minimal key.
+		 */
+		err = bpf_map_delete_elem(fd, &next_key);
+		CHECK(err, "del elem", "#%u elem error %d\n", i, err);
+	}
+	err = bpf_map_get_next_key(fd, cur, &next_key);
+	CHECK(err != -ENOENT, "more element", "error %d\n", err);
+
+	err = bpf_map_get_next_key(fd, NULL, &next_key);
+	CHECK(err != -ENOENT, "no-empty qp-trie", "error %d\n", err);
+
+	free(data_set);
+
+	close(fd);
+}
+
+void test_lpm_trie_map_basic_ops(void)
 {
 	int i;
 
 	/* we want predictable, pseudo random tests */
 	srand(0xf00ba1);
 
-	/* Use libbpf 1.0 API mode */
-	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
-
 	test_lpm_basic();
 	test_lpm_order();
 
@@ -792,6 +1179,10 @@ int main(void)
 	test_lpm_get_next_key();
 	test_lpm_multi_thread();
 
-	printf("test_lpm: OK\n");
-	return 0;
+	test_lpm_trie_update_flags();
+	test_lpm_trie_update_full_map();
+	test_lpm_trie_iterate_strs();
+	test_lpm_trie_iterate_ints();
+
+	printf("%s: PASS\n", __func__);
 }
diff --git a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c
index b66d56ddb7ef..fe3e19f96244 100644
--- a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c
+++ b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_batch_ops.c
@@ -135,7 +135,7 @@ void test_lpm_trie_map_batch_ops(void)
 		CHECK(total != max_entries, "delete with steps",
 		      "total = %u, max_entries = %u\n", total, max_entries);
 
-		/* check map is empty, errono == ENOENT */
+		/* check map is empty, errno == ENOENT */
 		err = bpf_map_get_next_key(map_fd, NULL, &key);
 		CHECK(!err || errno != ENOENT, "bpf_map_get_next_key()",
 		      "error: %s\n", strerror(errno));
diff --git a/tools/testing/selftests/bpf/map_tests/lpm_trie_map_get_next_key.c b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_get_next_key.c
new file mode 100644
index 000000000000..0ba015686492
--- /dev/null
+++ b/tools/testing/selftests/bpf/map_tests/lpm_trie_map_get_next_key.c
@@ -0,0 +1,109 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <linux/bpf.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include <unistd.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <string.h>
+#include <pthread.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include <test_maps.h>
+
+struct test_lpm_key {
+	__u32 prefix;
+	__u32 data;
+};
+
+struct get_next_key_ctx {
+	struct test_lpm_key key;
+	bool start;
+	bool stop;
+	int map_fd;
+	int loop;
+};
+
+static void *get_next_key_fn(void *arg)
+{
+	struct get_next_key_ctx *ctx = arg;
+	struct test_lpm_key next_key;
+	int i = 0;
+
+	while (!ctx->start)
+		usleep(1);
+
+	while (!ctx->stop && i++ < ctx->loop)
+		bpf_map_get_next_key(ctx->map_fd, &ctx->key, &next_key);
+
+	return NULL;
+}
+
+static void abort_get_next_key(struct get_next_key_ctx *ctx, pthread_t *tids,
+			       unsigned int nr)
+{
+	unsigned int i;
+
+	ctx->stop = true;
+	ctx->start = true;
+	for (i = 0; i < nr; i++)
+		pthread_join(tids[i], NULL);
+}
+
+/* This test aims to prevent regression of future. As long as the kernel does
+ * not panic, it is considered as success.
+ */
+void test_lpm_trie_map_get_next_key(void)
+{
+#define MAX_NR_THREADS 8
+	LIBBPF_OPTS(bpf_map_create_opts, create_opts,
+		    .map_flags = BPF_F_NO_PREALLOC);
+	struct test_lpm_key key = {};
+	__u32 val = 0;
+	int map_fd;
+	const __u32 max_prefixlen = 8 * (sizeof(key) - sizeof(key.prefix));
+	const __u32 max_entries = max_prefixlen + 1;
+	unsigned int i, nr = MAX_NR_THREADS, loop = 65536;
+	pthread_t tids[MAX_NR_THREADS];
+	struct get_next_key_ctx ctx;
+	int err;
+
+	map_fd = bpf_map_create(BPF_MAP_TYPE_LPM_TRIE, "lpm_trie_map",
+				sizeof(struct test_lpm_key), sizeof(__u32),
+				max_entries, &create_opts);
+	CHECK(map_fd == -1, "bpf_map_create()", "error:%s\n",
+	      strerror(errno));
+
+	for (i = 0; i <= max_prefixlen; i++) {
+		key.prefix = i;
+		err = bpf_map_update_elem(map_fd, &key, &val, BPF_ANY);
+		CHECK(err, "bpf_map_update_elem()", "error:%s\n",
+		      strerror(errno));
+	}
+
+	ctx.start = false;
+	ctx.stop = false;
+	ctx.map_fd = map_fd;
+	ctx.loop = loop;
+	memcpy(&ctx.key, &key, sizeof(key));
+
+	for (i = 0; i < nr; i++) {
+		err = pthread_create(&tids[i], NULL, get_next_key_fn, &ctx);
+		if (err) {
+			abort_get_next_key(&ctx, tids, i);
+			CHECK(err, "pthread_create", "error %d\n", err);
+		}
+	}
+
+	ctx.start = true;
+	for (i = 0; i < nr; i++)
+		pthread_join(tids[i], NULL);
+
+	printf("%s:PASS\n", __func__);
+
+	close(map_fd);
+}
diff --git a/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c
index f472d28ad11a..79c3ccadb962 100644
--- a/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c
+++ b/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c
@@ -18,7 +18,7 @@ static __u32 get_map_id_from_fd(int map_fd)
 	uint32_t info_len = sizeof(map_info);
 	int ret;
 
-	ret = bpf_obj_get_info_by_fd(map_fd, &map_info, &info_len);
+	ret = bpf_map_get_info_by_fd(map_fd, &map_info, &info_len);
 	CHECK(ret < 0, "Finding map info failed", "error:%s\n",
 	      strerror(errno));
 
@@ -33,11 +33,11 @@ static void create_inner_maps(enum bpf_map_type map_type,
 {
 	int map_fd, map_index, ret;
 	__u32 map_key = 0, map_id;
-	char map_name[15];
+	char map_name[16];
 
 	for (map_index = 0; map_index < OUTER_MAP_ENTRIES; map_index++) {
 		memset(map_name, 0, sizeof(map_name));
-		sprintf(map_name, "inner_map_fd_%d", map_index);
+		snprintf(map_name, sizeof(map_name), "inner_map_fd_%d", map_index);
 		map_fd = bpf_map_create(map_type, map_name, sizeof(__u32),
 					sizeof(__u32), 1, NULL);
 		CHECK(map_fd < 0,
@@ -120,11 +120,12 @@ static void validate_fetch_results(int outer_map_fd,
 
 static void fetch_and_validate(int outer_map_fd,
 			       struct bpf_map_batch_opts *opts,
-			       __u32 batch_size, bool delete_entries)
+			       __u32 batch_size, bool delete_entries,
+			       bool has_holes)
 {
-	__u32 *fetched_keys, *fetched_values, total_fetched = 0;
-	__u32 batch_key = 0, fetch_count, step_size;
-	int err, max_entries = OUTER_MAP_ENTRIES;
+	int err, max_entries = OUTER_MAP_ENTRIES - !!has_holes;
+	__u32 *fetched_keys, *fetched_values, total_fetched = 0, i;
+	__u32 batch_key = 0, fetch_count, step_size = batch_size;
 	__u32 value_size = sizeof(__u32);
 
 	/* Total entries needs to be fetched */
@@ -134,9 +135,8 @@ static void fetch_and_validate(int outer_map_fd,
 	      "Memory allocation failed for fetched_keys or fetched_values",
 	      "error=%s\n", strerror(errno));
 
-	for (step_size = batch_size;
-	     step_size <= max_entries;
-	     step_size += batch_size) {
+	/* hash map may not always return full batch */
+	for (i = 0; i < OUTER_MAP_ENTRIES; i++) {
 		fetch_count = step_size;
 		err = delete_entries
 		      ? bpf_map_lookup_and_delete_batch(outer_map_fd,
@@ -155,6 +155,7 @@ static void fetch_and_validate(int outer_map_fd,
 		if (err && errno == ENOSPC) {
 			/* Fetch again with higher batch size */
 			total_fetched = 0;
+			step_size += batch_size;
 			continue;
 		}
 
@@ -184,18 +185,19 @@ static void fetch_and_validate(int outer_map_fd,
 }
 
 static void _map_in_map_batch_ops(enum bpf_map_type outer_map_type,
-				  enum bpf_map_type inner_map_type)
+				  enum bpf_map_type inner_map_type,
+				  bool has_holes)
 {
+	__u32 max_entries = OUTER_MAP_ENTRIES - !!has_holes;
 	__u32 *outer_map_keys, *inner_map_fds;
-	__u32 max_entries = OUTER_MAP_ENTRIES;
 	LIBBPF_OPTS(bpf_map_batch_opts, opts);
 	__u32 value_size = sizeof(__u32);
 	int batch_size[2] = {5, 10};
 	__u32 map_index, op_index;
 	int outer_map_fd, ret;
 
-	outer_map_keys = calloc(max_entries, value_size);
-	inner_map_fds = calloc(max_entries, value_size);
+	outer_map_keys = calloc(OUTER_MAP_ENTRIES, value_size);
+	inner_map_fds = calloc(OUTER_MAP_ENTRIES, value_size);
 	CHECK((!outer_map_keys || !inner_map_fds),
 	      "Memory allocation failed for outer_map_keys or inner_map_fds",
 	      "error=%s\n", strerror(errno));
@@ -209,6 +211,24 @@ static void _map_in_map_batch_ops(enum bpf_map_type outer_map_type,
 			((outer_map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)
 			 ? 9 : 1000) - map_index;
 
+	/* This condition is only meaningful for array of maps.
+	 *
+	 * max_entries == OUTER_MAP_ENTRIES - 1 if it is true. Say
+	 * max_entries is short for n, then outer_map_keys looks like:
+	 *
+	 *   [n, n-1, ... 2, 1]
+	 *
+	 * We change it to
+	 *
+	 *   [n, n-1, ... 2, 0]
+	 *
+	 * So it will leave key 1 as a hole. It will serve to test the
+	 * correctness when batch on an array: a "non-exist" key might be
+	 * actually allocated and returned from key iteration.
+	 */
+	if (has_holes)
+		outer_map_keys[max_entries - 1]--;
+
 	/* batch operation - map_update */
 	ret = bpf_map_update_batch(outer_map_fd, outer_map_keys,
 				   inner_map_fds, &max_entries, &opts);
@@ -219,15 +239,17 @@ static void _map_in_map_batch_ops(enum bpf_map_type outer_map_type,
 	/* batch operation - map_lookup */
 	for (op_index = 0; op_index < 2; ++op_index)
 		fetch_and_validate(outer_map_fd, &opts,
-				   batch_size[op_index], false);
+				   batch_size[op_index], false,
+				   has_holes);
 
 	/* batch operation - map_lookup_delete */
 	if (outer_map_type == BPF_MAP_TYPE_HASH_OF_MAPS)
 		fetch_and_validate(outer_map_fd, &opts,
-				   max_entries, true /*delete*/);
+				   max_entries, true /*delete*/,
+				   has_holes);
 
 	/* close all map fds */
-	for (map_index = 0; map_index < max_entries; map_index++)
+	for (map_index = 0; map_index < OUTER_MAP_ENTRIES; map_index++)
 		close(inner_map_fds[map_index]);
 	close(outer_map_fd);
 
@@ -237,16 +259,20 @@ static void _map_in_map_batch_ops(enum bpf_map_type outer_map_type,
 
 void test_map_in_map_batch_ops_array(void)
 {
-	_map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_ARRAY);
+	_map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_ARRAY, false);
 	printf("%s:PASS with inner ARRAY map\n", __func__);
-	_map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_HASH);
+	_map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_HASH, false);
 	printf("%s:PASS with inner HASH map\n", __func__);
+	_map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_ARRAY, true);
+	printf("%s:PASS with inner ARRAY map with holes\n", __func__);
+	_map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_HASH, true);
+	printf("%s:PASS with inner HASH map with holes\n", __func__);
 }
 
 void test_map_in_map_batch_ops_hash(void)
 {
-	_map_in_map_batch_ops(BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_ARRAY);
+	_map_in_map_batch_ops(BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_ARRAY, false);
 	printf("%s:PASS with inner ARRAY map\n", __func__);
-	_map_in_map_batch_ops(BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_HASH);
+	_map_in_map_batch_ops(BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_HASH, false);
 	printf("%s:PASS with inner HASH map\n", __func__);
 }
diff --git a/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c b/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
new file mode 100644
index 000000000000..1c7c04288eff
--- /dev/null
+++ b/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
@@ -0,0 +1,488 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+
+#include <errno.h>
+#include <unistd.h>
+#include <pthread.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include <bpf_util.h>
+#include <test_maps.h>
+
+#include "map_percpu_stats.skel.h"
+
+#define MAX_ENTRIES			16384
+#define MAX_ENTRIES_HASH_OF_MAPS	64
+#define N_THREADS			8
+#define MAX_MAP_KEY_SIZE		4
+#define PCPU_MIN_UNIT_SIZE		32768
+
+static void map_info(int map_fd, struct bpf_map_info *info)
+{
+	__u32 len = sizeof(*info);
+	int ret;
+
+	memset(info, 0, sizeof(*info));
+
+	ret = bpf_obj_get_info_by_fd(map_fd, info, &len);
+	CHECK(ret < 0, "bpf_obj_get_info_by_fd", "error: %s\n", strerror(errno));
+}
+
+static const char *map_type_to_s(__u32 type)
+{
+	switch (type) {
+	case BPF_MAP_TYPE_HASH:
+		return "HASH";
+	case BPF_MAP_TYPE_PERCPU_HASH:
+		return "PERCPU_HASH";
+	case BPF_MAP_TYPE_LRU_HASH:
+		return "LRU_HASH";
+	case BPF_MAP_TYPE_LRU_PERCPU_HASH:
+		return "LRU_PERCPU_HASH";
+	case BPF_MAP_TYPE_HASH_OF_MAPS:
+		return "BPF_MAP_TYPE_HASH_OF_MAPS";
+	default:
+		return "<define-me>";
+	}
+}
+
+static __u32 map_count_elements(__u32 type, int map_fd)
+{
+	__u32 key = -1;
+	int n = 0;
+
+	while (!bpf_map_get_next_key(map_fd, &key, &key))
+		n++;
+	return n;
+}
+
+#define BATCH	true
+
+static void delete_and_lookup_batch(int map_fd, void *keys, __u32 count)
+{
+	static __u8 values[(8 << 10) * MAX_ENTRIES];
+	void *in_batch = NULL, *out_batch;
+	__u32 save_count = count;
+	int ret;
+
+	ret = bpf_map_lookup_and_delete_batch(map_fd,
+					      &in_batch, &out_batch,
+					      keys, values, &count,
+					      NULL);
+
+	/*
+	 * Despite what uapi header says, lookup_and_delete_batch will return
+	 * -ENOENT in case we successfully have deleted all elements, so check
+	 * this separately
+	 */
+	CHECK(ret < 0 && (errno != ENOENT || !count), "bpf_map_lookup_and_delete_batch",
+		       "error: %s\n", strerror(errno));
+
+	CHECK(count != save_count,
+			"bpf_map_lookup_and_delete_batch",
+			"deleted not all elements: removed=%u expected=%u\n",
+			count, save_count);
+}
+
+static void delete_all_elements(__u32 type, int map_fd, bool batch)
+{
+	static __u8 val[8 << 10]; /* enough for 1024 CPUs */
+	__u32 key = -1;
+	void *keys;
+	__u32 i, n;
+	int ret;
+
+	keys = calloc(MAX_MAP_KEY_SIZE, MAX_ENTRIES);
+	CHECK(!keys, "calloc", "error: %s\n", strerror(errno));
+
+	for (n = 0; !bpf_map_get_next_key(map_fd, &key, &key); n++)
+		memcpy(keys + n*MAX_MAP_KEY_SIZE, &key, MAX_MAP_KEY_SIZE);
+
+	if (batch) {
+		/* Can't mix delete_batch and delete_and_lookup_batch because
+		 * they have different semantics in relation to the keys
+		 * argument. However, delete_batch utilize map_delete_elem,
+		 * so we actually test it in non-batch scenario */
+		delete_and_lookup_batch(map_fd, keys, n);
+	} else {
+		/* Intentionally mix delete and lookup_and_delete so we can test both */
+		for (i = 0; i < n; i++) {
+			void *keyp = keys + i*MAX_MAP_KEY_SIZE;
+
+			if (i % 2 || type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+				ret = bpf_map_delete_elem(map_fd, keyp);
+				CHECK(ret < 0, "bpf_map_delete_elem",
+					       "error: key %u: %s\n", i, strerror(errno));
+			} else {
+				ret = bpf_map_lookup_and_delete_elem(map_fd, keyp, val);
+				CHECK(ret < 0, "bpf_map_lookup_and_delete_elem",
+					       "error: key %u: %s\n", i, strerror(errno));
+			}
+		}
+	}
+
+	free(keys);
+}
+
+static bool is_lru(__u32 map_type)
+{
+	return map_type == BPF_MAP_TYPE_LRU_HASH ||
+	       map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
+}
+
+static bool is_percpu(__u32 map_type)
+{
+	return map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+	       map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
+}
+
+struct upsert_opts {
+	__u32 map_type;
+	int map_fd;
+	__u32 n;
+	bool retry_for_nomem;
+};
+
+static int create_small_hash(void)
+{
+	int map_fd;
+
+	map_fd = bpf_map_create(BPF_MAP_TYPE_HASH, "small", 4, 4, 4, NULL);
+	CHECK(map_fd < 0, "bpf_map_create()", "error:%s (name=%s)\n",
+			strerror(errno), "small");
+
+	return map_fd;
+}
+
+static bool retry_for_nomem_fn(int err)
+{
+	return err == ENOMEM;
+}
+
+static void *patch_map_thread(void *arg)
+{
+	/* 8KB is enough for 1024 CPUs. And it is shared between N_THREADS. */
+	static __u8 blob[8 << 10];
+	struct upsert_opts *opts = arg;
+	void *val_ptr;
+	int val;
+	int ret;
+	int i;
+
+	for (i = 0; i < opts->n; i++) {
+		if (opts->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+			val = create_small_hash();
+			val_ptr = &val;
+		} else if (is_percpu(opts->map_type)) {
+			val_ptr = blob;
+		} else {
+			val = rand();
+			val_ptr = &val;
+		}
+
+		/* 2 seconds may be enough ? */
+		if (opts->retry_for_nomem)
+			ret = map_update_retriable(opts->map_fd, &i, val_ptr, 0,
+						   40, retry_for_nomem_fn);
+		else
+			ret = bpf_map_update_elem(opts->map_fd, &i, val_ptr, 0);
+		CHECK(ret < 0, "bpf_map_update_elem", "key=%d error: %s\n", i, strerror(errno));
+
+		if (opts->map_type == BPF_MAP_TYPE_HASH_OF_MAPS)
+			close(val);
+	}
+	return NULL;
+}
+
+static void upsert_elements(struct upsert_opts *opts)
+{
+	pthread_t threads[N_THREADS];
+	int ret;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(threads); i++) {
+		ret = pthread_create(&i[threads], NULL, patch_map_thread, opts);
+		CHECK(ret != 0, "pthread_create", "error: %s\n", strerror(ret));
+	}
+
+	for (i = 0; i < ARRAY_SIZE(threads); i++) {
+		ret = pthread_join(i[threads], NULL);
+		CHECK(ret != 0, "pthread_join", "error: %s\n", strerror(ret));
+	}
+}
+
+static __u32 read_cur_elements(int iter_fd)
+{
+	char buf[64];
+	ssize_t n;
+	__u32 ret;
+
+	n = read(iter_fd, buf, sizeof(buf)-1);
+	CHECK(n <= 0, "read", "error: %s\n", strerror(errno));
+	buf[n] = '\0';
+
+	errno = 0;
+	ret = (__u32)strtol(buf, NULL, 10);
+	CHECK(errno != 0, "strtol", "error: %s\n", strerror(errno));
+
+	return ret;
+}
+
+static __u32 get_cur_elements(int map_id)
+{
+	struct map_percpu_stats *skel;
+	struct bpf_link *link;
+	__u32 n_elements;
+	int iter_fd;
+	int ret;
+
+	skel = map_percpu_stats__open();
+	CHECK(skel == NULL, "map_percpu_stats__open", "error: %s", strerror(errno));
+
+	skel->bss->target_id = map_id;
+
+	ret = map_percpu_stats__load(skel);
+	CHECK(ret != 0, "map_percpu_stats__load", "error: %s", strerror(errno));
+
+	link = bpf_program__attach_iter(skel->progs.dump_bpf_map, NULL);
+	CHECK(!link, "bpf_program__attach_iter", "error: %s\n", strerror(errno));
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	CHECK(iter_fd < 0, "bpf_iter_create", "error: %s\n", strerror(errno));
+
+	n_elements = read_cur_elements(iter_fd);
+
+	close(iter_fd);
+	bpf_link__destroy(link);
+	map_percpu_stats__destroy(skel);
+
+	return n_elements;
+}
+
+static void check_expected_number_elements(__u32 n_inserted, int map_fd,
+					   struct bpf_map_info *info)
+{
+	__u32 n_real;
+	__u32 n_iter;
+
+	/* Count the current number of elements in the map by iterating through
+	 * all the map keys via bpf_get_next_key
+	 */
+	n_real = map_count_elements(info->type, map_fd);
+
+	/* The "real" number of elements should be the same as the inserted
+	 * number of elements in all cases except LRU maps, where some elements
+	 * may have been evicted
+	 */
+	if (n_inserted == 0 || !is_lru(info->type))
+		CHECK(n_inserted != n_real, "map_count_elements",
+		      "n_real(%u) != n_inserted(%u)\n", n_real, n_inserted);
+
+	/* Count the current number of elements in the map using an iterator */
+	n_iter = get_cur_elements(info->id);
+
+	/* Both counts should be the same, as all updates are over */
+	CHECK(n_iter != n_real, "get_cur_elements",
+	      "n_iter=%u, expected %u (map_type=%s,map_flags=%08x)\n",
+	      n_iter, n_real, map_type_to_s(info->type), info->map_flags);
+}
+
+static void __test(int map_fd)
+{
+	struct upsert_opts opts = {
+		.map_fd = map_fd,
+	};
+	struct bpf_map_info info;
+
+	map_info(map_fd, &info);
+	opts.map_type = info.type;
+	opts.n = info.max_entries;
+
+	/* Reduce the number of elements we are updating such that we don't
+	 * bump into -E2BIG from non-preallocated hash maps, but still will
+	 * have some evictions for LRU maps  */
+	if (opts.map_type != BPF_MAP_TYPE_HASH_OF_MAPS)
+		opts.n -= 512;
+	else
+		opts.n /= 2;
+
+	/* per-cpu bpf memory allocator may not be able to allocate per-cpu
+	 * pointer successfully and it can not refill free llist timely, and
+	 * bpf_map_update_elem() will return -ENOMEM. so just retry to mitigate
+	 * the problem temporarily.
+	 */
+	opts.retry_for_nomem = is_percpu(opts.map_type) && (info.map_flags & BPF_F_NO_PREALLOC);
+
+	/*
+	 * Upsert keys [0, n) under some competition: with random values from
+	 * N_THREADS threads. Check values, then delete all elements and check
+	 * values again.
+	 */
+	upsert_elements(&opts);
+	check_expected_number_elements(opts.n, map_fd, &info);
+	delete_all_elements(info.type, map_fd, !BATCH);
+	check_expected_number_elements(0, map_fd, &info);
+
+	/* Now do the same, but using batch delete operations */
+	upsert_elements(&opts);
+	check_expected_number_elements(opts.n, map_fd, &info);
+	delete_all_elements(info.type, map_fd, BATCH);
+	check_expected_number_elements(0, map_fd, &info);
+
+	close(map_fd);
+}
+
+static int map_create_opts(__u32 type, const char *name,
+			   struct bpf_map_create_opts *map_opts,
+			   __u32 key_size, __u32 val_size)
+{
+	int max_entries;
+	int map_fd;
+
+	if (type == BPF_MAP_TYPE_HASH_OF_MAPS)
+		max_entries = MAX_ENTRIES_HASH_OF_MAPS;
+	else
+		max_entries = MAX_ENTRIES;
+
+	map_fd = bpf_map_create(type, name, key_size, val_size, max_entries, map_opts);
+	CHECK(map_fd < 0, "bpf_map_create()", "error:%s (name=%s)\n",
+			strerror(errno), name);
+
+	return map_fd;
+}
+
+static int map_create(__u32 type, const char *name, struct bpf_map_create_opts *map_opts)
+{
+	return map_create_opts(type, name, map_opts, sizeof(int), sizeof(int));
+}
+
+static int create_hash(void)
+{
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts, .map_flags = BPF_F_NO_PREALLOC);
+
+	return map_create(BPF_MAP_TYPE_HASH, "hash", &map_opts);
+}
+
+static int create_percpu_hash(void)
+{
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts, .map_flags = BPF_F_NO_PREALLOC);
+
+	return map_create(BPF_MAP_TYPE_PERCPU_HASH, "percpu_hash", &map_opts);
+}
+
+static int create_hash_prealloc(void)
+{
+	return map_create(BPF_MAP_TYPE_HASH, "hash", NULL);
+}
+
+static int create_percpu_hash_prealloc(void)
+{
+	return map_create(BPF_MAP_TYPE_PERCPU_HASH, "percpu_hash_prealloc", NULL);
+}
+
+static int create_lru_hash(__u32 type, __u32 map_flags)
+{
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts, .map_flags = map_flags);
+
+	return map_create(type, "lru_hash", &map_opts);
+}
+
+static int create_hash_of_maps(void)
+{
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts,
+		.map_flags = BPF_F_NO_PREALLOC,
+		.inner_map_fd = create_small_hash(),
+	);
+	int ret;
+
+	ret = map_create_opts(BPF_MAP_TYPE_HASH_OF_MAPS, "hash_of_maps",
+			      &map_opts, sizeof(int), sizeof(int));
+	close(map_opts.inner_map_fd);
+	return ret;
+}
+
+static void map_percpu_stats_hash(void)
+{
+	__test(create_hash());
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_percpu_hash(void)
+{
+	__test(create_percpu_hash());
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_hash_prealloc(void)
+{
+	__test(create_hash_prealloc());
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_percpu_hash_prealloc(void)
+{
+	__test(create_percpu_hash_prealloc());
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_lru_hash(void)
+{
+	__test(create_lru_hash(BPF_MAP_TYPE_LRU_HASH, 0));
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_lru_hash_no_common(void)
+{
+	__test(create_lru_hash(BPF_MAP_TYPE_LRU_HASH, BPF_F_NO_COMMON_LRU));
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_percpu_lru_hash(void)
+{
+	__test(create_lru_hash(BPF_MAP_TYPE_LRU_PERCPU_HASH, 0));
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_percpu_lru_hash_no_common(void)
+{
+	__test(create_lru_hash(BPF_MAP_TYPE_LRU_PERCPU_HASH, BPF_F_NO_COMMON_LRU));
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_hash_of_maps(void)
+{
+	__test(create_hash_of_maps());
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_map_value_size(void)
+{
+	int fd;
+	int value_sz = PCPU_MIN_UNIT_SIZE + 1;
+	struct bpf_map_create_opts opts = { .sz = sizeof(opts) };
+	enum bpf_map_type map_types[] = { BPF_MAP_TYPE_PERCPU_ARRAY,
+					  BPF_MAP_TYPE_PERCPU_HASH,
+					  BPF_MAP_TYPE_LRU_PERCPU_HASH };
+	for (int i = 0; i < ARRAY_SIZE(map_types); i++) {
+		fd = bpf_map_create(map_types[i], NULL, sizeof(__u32), value_sz, 1, &opts);
+		CHECK(fd < 0 && errno != E2BIG, "percpu map value size",
+			"error: %s\n", strerror(errno));
+	}
+	printf("test_%s:PASS\n", __func__);
+}
+
+void test_map_percpu_stats(void)
+{
+	map_percpu_stats_hash();
+	map_percpu_stats_percpu_hash();
+	map_percpu_stats_hash_prealloc();
+	map_percpu_stats_percpu_hash_prealloc();
+	map_percpu_stats_lru_hash();
+	map_percpu_stats_lru_hash_no_common();
+	map_percpu_stats_percpu_lru_hash();
+	map_percpu_stats_percpu_lru_hash_no_common();
+	map_percpu_stats_hash_of_maps();
+	map_percpu_stats_map_value_size();
+}
diff --git a/tools/testing/selftests/bpf/map_tests/sk_storage_map.c b/tools/testing/selftests/bpf/map_tests/sk_storage_map.c
index 18405c3b7cee..af10c309359a 100644
--- a/tools/testing/selftests/bpf/map_tests/sk_storage_map.c
+++ b/tools/testing/selftests/bpf/map_tests/sk_storage_map.c
@@ -412,7 +412,7 @@ static void test_sk_storage_map_stress_free(void)
 		rlim_new.rlim_max = rlim_new.rlim_cur + 128;
 		err = setrlimit(RLIMIT_NOFILE, &rlim_new);
 		CHECK(err, "setrlimit(RLIMIT_NOFILE)", "rlim_new:%lu errno:%d",
-		      rlim_new.rlim_cur, errno);
+		      (unsigned long) rlim_new.rlim_cur, errno);
 	}
 
 	err = do_sk_storage_map_stress_free();
diff --git a/tools/testing/selftests/bpf/map_tests/task_storage_map.c b/tools/testing/selftests/bpf/map_tests/task_storage_map.c
index 7d050364efca..a4121d2248ac 100644
--- a/tools/testing/selftests/bpf/map_tests/task_storage_map.c
+++ b/tools/testing/selftests/bpf/map_tests/task_storage_map.c
@@ -12,6 +12,7 @@
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
 
+#include "bpf_util.h"
 #include "test_maps.h"
 #include "task_local_storage_helpers.h"
 #include "read_bpf_task_storage_busy.skel.h"
@@ -77,8 +78,8 @@ void test_task_storage_map_stress_lookup(void)
 	CHECK(err, "open_and_load", "error %d\n", err);
 
 	/* Only for a fully preemptible kernel */
-	if (!skel->kconfig->CONFIG_PREEMPT) {
-		printf("%s SKIP (no CONFIG_PREEMPT)\n", __func__);
+	if (!skel->kconfig->CONFIG_PREEMPTION) {
+		printf("%s SKIP (no CONFIG_PREEMPTION)\n", __func__);
 		read_bpf_task_storage_busy__destroy(skel);
 		skips++;
 		return;
@@ -115,7 +116,7 @@ void test_task_storage_map_stress_lookup(void)
 	CHECK(err, "attach", "error %d\n", err);
 
 	/* Trigger program */
-	syscall(SYS_gettid);
+	sys_gettid();
 	skel->bss->pid = 0;
 
 	CHECK(skel->bss->busy != 0, "bad bpf_task_storage_busy", "got %d\n", skel->bss->busy);
diff --git a/tools/testing/selftests/bpf/netcnt_common.h b/tools/testing/selftests/bpf/netcnt_common.h
index 0ab1c88041cd..2d4a58e4e39c 100644
--- a/tools/testing/selftests/bpf/netcnt_common.h
+++ b/tools/testing/selftests/bpf/netcnt_common.h
@@ -8,11 +8,11 @@
 
 /* sizeof(struct bpf_local_storage_elem):
  *
- * It really is about 128 bytes on x86_64, but allocate more to account for
- * possible layout changes, different architectures, etc.
+ * It is about 128 bytes on x86_64 and 512 bytes on s390x, but allocate more to
+ * account for possible layout changes, different architectures, etc.
  * The kernel will wrap up to PAGE_SIZE internally anyway.
  */
-#define SIZEOF_BPF_LOCAL_STORAGE_ELEM		256
+#define SIZEOF_BPF_LOCAL_STORAGE_ELEM		768
 
 /* Try to estimate kernel's BPF_LOCAL_STORAGE_MAX_VALUE_SIZE: */
 #define BPF_LOCAL_STORAGE_MAX_VALUE_SIZE	(0xFFFF - \
diff --git a/tools/testing/selftests/bpf/netlink_helpers.c b/tools/testing/selftests/bpf/netlink_helpers.c
new file mode 100644
index 000000000000..caf36eb1d032
--- /dev/null
+++ b/tools/testing/selftests/bpf/netlink_helpers.c
@@ -0,0 +1,358 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Taken & modified from iproute2's libnetlink.c
+ * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <errno.h>
+#include <time.h>
+#include <sys/socket.h>
+
+#include "netlink_helpers.h"
+
+static int rcvbuf = 1024 * 1024;
+
+void rtnl_close(struct rtnl_handle *rth)
+{
+	if (rth->fd >= 0) {
+		close(rth->fd);
+		rth->fd = -1;
+	}
+}
+
+int rtnl_open_byproto(struct rtnl_handle *rth, unsigned int subscriptions,
+		      int protocol)
+{
+	socklen_t addr_len;
+	int sndbuf = 32768;
+	int one = 1;
+
+	memset(rth, 0, sizeof(*rth));
+	rth->proto = protocol;
+	rth->fd = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, protocol);
+	if (rth->fd < 0) {
+		perror("Cannot open netlink socket");
+		return -1;
+	}
+	if (setsockopt(rth->fd, SOL_SOCKET, SO_SNDBUF,
+		       &sndbuf, sizeof(sndbuf)) < 0) {
+		perror("SO_SNDBUF");
+		goto err;
+	}
+	if (setsockopt(rth->fd, SOL_SOCKET, SO_RCVBUF,
+		       &rcvbuf, sizeof(rcvbuf)) < 0) {
+		perror("SO_RCVBUF");
+		goto err;
+	}
+
+	/* Older kernels may no support extended ACK reporting */
+	setsockopt(rth->fd, SOL_NETLINK, NETLINK_EXT_ACK,
+		   &one, sizeof(one));
+
+	memset(&rth->local, 0, sizeof(rth->local));
+	rth->local.nl_family = AF_NETLINK;
+	rth->local.nl_groups = subscriptions;
+
+	if (bind(rth->fd, (struct sockaddr *)&rth->local,
+		 sizeof(rth->local)) < 0) {
+		perror("Cannot bind netlink socket");
+		goto err;
+	}
+	addr_len = sizeof(rth->local);
+	if (getsockname(rth->fd, (struct sockaddr *)&rth->local,
+			&addr_len) < 0) {
+		perror("Cannot getsockname");
+		goto err;
+	}
+	if (addr_len != sizeof(rth->local)) {
+		fprintf(stderr, "Wrong address length %d\n", addr_len);
+		goto err;
+	}
+	if (rth->local.nl_family != AF_NETLINK) {
+		fprintf(stderr, "Wrong address family %d\n",
+			rth->local.nl_family);
+		goto err;
+	}
+	rth->seq = time(NULL);
+	return 0;
+err:
+	rtnl_close(rth);
+	return -1;
+}
+
+int rtnl_open(struct rtnl_handle *rth, unsigned int subscriptions)
+{
+	return rtnl_open_byproto(rth, subscriptions, NETLINK_ROUTE);
+}
+
+static int __rtnl_recvmsg(int fd, struct msghdr *msg, int flags)
+{
+	int len;
+
+	do {
+		len = recvmsg(fd, msg, flags);
+	} while (len < 0 && (errno == EINTR || errno == EAGAIN));
+	if (len < 0) {
+		fprintf(stderr, "netlink receive error %s (%d)\n",
+			strerror(errno), errno);
+		return -errno;
+	}
+	if (len == 0) {
+		fprintf(stderr, "EOF on netlink\n");
+		return -ENODATA;
+	}
+	return len;
+}
+
+static int rtnl_recvmsg(int fd, struct msghdr *msg, char **answer)
+{
+	struct iovec *iov = msg->msg_iov;
+	char *buf;
+	int len;
+
+	iov->iov_base = NULL;
+	iov->iov_len = 0;
+
+	len = __rtnl_recvmsg(fd, msg, MSG_PEEK | MSG_TRUNC);
+	if (len < 0)
+		return len;
+	if (len < 32768)
+		len = 32768;
+	buf = malloc(len);
+	if (!buf) {
+		fprintf(stderr, "malloc error: not enough buffer\n");
+		return -ENOMEM;
+	}
+	iov->iov_base = buf;
+	iov->iov_len = len;
+	len = __rtnl_recvmsg(fd, msg, 0);
+	if (len < 0) {
+		free(buf);
+		return len;
+	}
+	if (answer)
+		*answer = buf;
+	else
+		free(buf);
+	return len;
+}
+
+static void rtnl_talk_error(struct nlmsghdr *h, struct nlmsgerr *err,
+			    nl_ext_ack_fn_t errfn)
+{
+	fprintf(stderr, "RTNETLINK answers: %s\n",
+		strerror(-err->error));
+}
+
+static int __rtnl_talk_iov(struct rtnl_handle *rtnl, struct iovec *iov,
+			   size_t iovlen, struct nlmsghdr **answer,
+			   bool show_rtnl_err, nl_ext_ack_fn_t errfn)
+{
+	struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK };
+	struct iovec riov;
+	struct msghdr msg = {
+		.msg_name	= &nladdr,
+		.msg_namelen	= sizeof(nladdr),
+		.msg_iov	= iov,
+		.msg_iovlen	= iovlen,
+	};
+	unsigned int seq = 0;
+	struct nlmsghdr *h;
+	int i, status;
+	char *buf;
+
+	for (i = 0; i < iovlen; i++) {
+		h = iov[i].iov_base;
+		h->nlmsg_seq = seq = ++rtnl->seq;
+		if (answer == NULL)
+			h->nlmsg_flags |= NLM_F_ACK;
+	}
+	status = sendmsg(rtnl->fd, &msg, 0);
+	if (status < 0) {
+		perror("Cannot talk to rtnetlink");
+		return -1;
+	}
+	/* change msg to use the response iov */
+	msg.msg_iov = &riov;
+	msg.msg_iovlen = 1;
+	i = 0;
+	while (1) {
+next:
+		status = rtnl_recvmsg(rtnl->fd, &msg, &buf);
+		++i;
+		if (status < 0)
+			return status;
+		if (msg.msg_namelen != sizeof(nladdr)) {
+			fprintf(stderr,
+				"Sender address length == %d!\n",
+				msg.msg_namelen);
+			exit(1);
+		}
+		for (h = (struct nlmsghdr *)buf; status >= sizeof(*h); ) {
+			int len = h->nlmsg_len;
+			int l = len - sizeof(*h);
+
+			if (l < 0 || len > status) {
+				if (msg.msg_flags & MSG_TRUNC) {
+					fprintf(stderr, "Truncated message!\n");
+					free(buf);
+					return -1;
+				}
+				fprintf(stderr,
+					"Malformed message: len=%d!\n",
+					len);
+				exit(1);
+			}
+			if (nladdr.nl_pid != 0 ||
+			    h->nlmsg_pid != rtnl->local.nl_pid ||
+			    h->nlmsg_seq > seq || h->nlmsg_seq < seq - iovlen) {
+				/* Don't forget to skip that message. */
+				status -= NLMSG_ALIGN(len);
+				h = (struct nlmsghdr *)((char *)h + NLMSG_ALIGN(len));
+				continue;
+			}
+			if (h->nlmsg_type == NLMSG_ERROR) {
+				struct nlmsgerr *err = (struct nlmsgerr *)NLMSG_DATA(h);
+				int error = err->error;
+
+				if (l < sizeof(struct nlmsgerr)) {
+					fprintf(stderr, "ERROR truncated\n");
+					free(buf);
+					return -1;
+				}
+				if (error) {
+					errno = -error;
+					if (rtnl->proto != NETLINK_SOCK_DIAG &&
+					    show_rtnl_err)
+						rtnl_talk_error(h, err, errfn);
+				}
+				if (i < iovlen) {
+					free(buf);
+					goto next;
+				}
+				if (error) {
+					free(buf);
+					return -i;
+				}
+				if (answer)
+					*answer = (struct nlmsghdr *)buf;
+				else
+					free(buf);
+				return 0;
+			}
+			if (answer) {
+				*answer = (struct nlmsghdr *)buf;
+				return 0;
+			}
+			fprintf(stderr, "Unexpected reply!\n");
+			status -= NLMSG_ALIGN(len);
+			h = (struct nlmsghdr *)((char *)h + NLMSG_ALIGN(len));
+		}
+		free(buf);
+		if (msg.msg_flags & MSG_TRUNC) {
+			fprintf(stderr, "Message truncated!\n");
+			continue;
+		}
+		if (status) {
+			fprintf(stderr, "Remnant of size %d!\n", status);
+			exit(1);
+		}
+	}
+}
+
+static int __rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
+		       struct nlmsghdr **answer, bool show_rtnl_err,
+		       nl_ext_ack_fn_t errfn)
+{
+	struct iovec iov = {
+		.iov_base	= n,
+		.iov_len	= n->nlmsg_len,
+	};
+
+	return __rtnl_talk_iov(rtnl, &iov, 1, answer, show_rtnl_err, errfn);
+}
+
+int rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
+	      struct nlmsghdr **answer)
+{
+	return __rtnl_talk(rtnl, n, answer, true, NULL);
+}
+
+int addattr(struct nlmsghdr *n, int maxlen, int type)
+{
+	return addattr_l(n, maxlen, type, NULL, 0);
+}
+
+int addattr8(struct nlmsghdr *n, int maxlen, int type, __u8 data)
+{
+	return addattr_l(n, maxlen, type, &data, sizeof(__u8));
+}
+
+int addattr16(struct nlmsghdr *n, int maxlen, int type, __u16 data)
+{
+	return addattr_l(n, maxlen, type, &data, sizeof(__u16));
+}
+
+int addattr32(struct nlmsghdr *n, int maxlen, int type, __u32 data)
+{
+	return addattr_l(n, maxlen, type, &data, sizeof(__u32));
+}
+
+int addattr64(struct nlmsghdr *n, int maxlen, int type, __u64 data)
+{
+	return addattr_l(n, maxlen, type, &data, sizeof(__u64));
+}
+
+int addattrstrz(struct nlmsghdr *n, int maxlen, int type, const char *str)
+{
+	return addattr_l(n, maxlen, type, str, strlen(str)+1);
+}
+
+int addattr_l(struct nlmsghdr *n, int maxlen, int type, const void *data,
+	      int alen)
+{
+	int len = RTA_LENGTH(alen);
+	struct rtattr *rta;
+
+	if (NLMSG_ALIGN(n->nlmsg_len) + RTA_ALIGN(len) > maxlen) {
+		fprintf(stderr, "%s: Message exceeded bound of %d\n",
+			__func__, maxlen);
+		return -1;
+	}
+	rta = NLMSG_TAIL(n);
+	rta->rta_type = type;
+	rta->rta_len = len;
+	if (alen)
+		memcpy(RTA_DATA(rta), data, alen);
+	n->nlmsg_len = NLMSG_ALIGN(n->nlmsg_len) + RTA_ALIGN(len);
+	return 0;
+}
+
+int addraw_l(struct nlmsghdr *n, int maxlen, const void *data, int len)
+{
+	if (NLMSG_ALIGN(n->nlmsg_len) + NLMSG_ALIGN(len) > maxlen) {
+		fprintf(stderr, "%s: Message exceeded bound of %d\n",
+			__func__, maxlen);
+		return -1;
+	}
+
+	memcpy(NLMSG_TAIL(n), data, len);
+	memset((void *) NLMSG_TAIL(n) + len, 0, NLMSG_ALIGN(len) - len);
+	n->nlmsg_len = NLMSG_ALIGN(n->nlmsg_len) + NLMSG_ALIGN(len);
+	return 0;
+}
+
+struct rtattr *addattr_nest(struct nlmsghdr *n, int maxlen, int type)
+{
+	struct rtattr *nest = NLMSG_TAIL(n);
+
+	addattr_l(n, maxlen, type, NULL, 0);
+	return nest;
+}
+
+int addattr_nest_end(struct nlmsghdr *n, struct rtattr *nest)
+{
+	nest->rta_len = (void *)NLMSG_TAIL(n) - (void *)nest;
+	return n->nlmsg_len;
+}
diff --git a/tools/testing/selftests/bpf/netlink_helpers.h b/tools/testing/selftests/bpf/netlink_helpers.h
new file mode 100644
index 000000000000..68116818a47e
--- /dev/null
+++ b/tools/testing/selftests/bpf/netlink_helpers.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef NETLINK_HELPERS_H
+#define NETLINK_HELPERS_H
+
+#include <string.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+
+struct rtnl_handle {
+	int			fd;
+	struct sockaddr_nl	local;
+	struct sockaddr_nl	peer;
+	__u32			seq;
+	__u32			dump;
+	int			proto;
+	FILE			*dump_fp;
+#define RTNL_HANDLE_F_LISTEN_ALL_NSID		0x01
+#define RTNL_HANDLE_F_SUPPRESS_NLERR		0x02
+#define RTNL_HANDLE_F_STRICT_CHK		0x04
+	int			flags;
+};
+
+#define NLMSG_TAIL(nmsg) \
+	((struct rtattr *) (((void *) (nmsg)) + NLMSG_ALIGN((nmsg)->nlmsg_len)))
+
+typedef int (*nl_ext_ack_fn_t)(const char *errmsg, uint32_t off,
+			       const struct nlmsghdr *inner_nlh);
+
+int rtnl_open(struct rtnl_handle *rth, unsigned int subscriptions)
+	      __attribute__((warn_unused_result));
+void rtnl_close(struct rtnl_handle *rth);
+int rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
+	      struct nlmsghdr **answer)
+	      __attribute__((warn_unused_result));
+
+int addattr(struct nlmsghdr *n, int maxlen, int type);
+int addattr8(struct nlmsghdr *n, int maxlen, int type, __u8 data);
+int addattr16(struct nlmsghdr *n, int maxlen, int type, __u16 data);
+int addattr32(struct nlmsghdr *n, int maxlen, int type, __u32 data);
+int addattr64(struct nlmsghdr *n, int maxlen, int type, __u64 data);
+int addattrstrz(struct nlmsghdr *n, int maxlen, int type, const char *data);
+int addattr_l(struct nlmsghdr *n, int maxlen, int type, const void *data, int alen);
+int addraw_l(struct nlmsghdr *n, int maxlen, const void *data, int len);
+struct rtattr *addattr_nest(struct nlmsghdr *n, int maxlen, int type);
+int addattr_nest_end(struct nlmsghdr *n, struct rtattr *nest);
+#endif /* NETLINK_HELPERS_H */
diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index 01de33191226..0a6a5561bed3 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -11,16 +11,31 @@
 #include <arpa/inet.h>
 #include <sys/mount.h>
 #include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/un.h>
+#include <sys/eventfd.h>
 
 #include <linux/err.h>
 #include <linux/in.h>
 #include <linux/in6.h>
 #include <linux/limits.h>
 
+#include <linux/ip.h>
+#include <netinet/udp.h>
+#include <netinet/tcp.h>
+#include <net/if.h>
+
 #include "bpf_util.h"
 #include "network_helpers.h"
 #include "test_progs.h"
 
+#ifdef TRAFFIC_MONITOR
+/* Prevent pcap.h from including pcap/bpf.h and causing conflicts */
+#define PCAP_DONT_INCLUDE_PCAP_BPF_H 1
+#include <pcap/pcap.h>
+#include <pcap/dlt.h>
+#endif
+
 #ifndef IPPROTO_MPTCP
 #define IPPROTO_MPTCP 262
 #endif
@@ -51,6 +66,8 @@ struct ipv6_packet pkt_v6 = {
 	.tcp.doff = 5,
 };
 
+static const struct network_helper_opts default_opts;
+
 int settimeo(int fd, int timeout_ms)
 {
 	struct timeval timeout = { .tv_sec = 3 };
@@ -77,34 +94,42 @@ int settimeo(int fd, int timeout_ms)
 
 #define save_errno_close(fd) ({ int __save = errno; close(fd); errno = __save; })
 
-static int __start_server(int type, int protocol, const struct sockaddr *addr,
-			  socklen_t addrlen, int timeout_ms, bool reuseport)
+int start_server_addr(int type, const struct sockaddr_storage *addr, socklen_t addrlen,
+		      const struct network_helper_opts *opts)
 {
-	int on = 1;
-	int fd;
+	int on = 1, fd;
 
-	fd = socket(addr->sa_family, type, protocol);
+	if (!opts)
+		opts = &default_opts;
+
+	fd = socket(addr->ss_family, type, opts->proto);
 	if (fd < 0) {
 		log_err("Failed to create server socket");
 		return -1;
 	}
 
-	if (settimeo(fd, timeout_ms))
+	if (settimeo(fd, opts->timeout_ms))
 		goto error_close;
 
-	if (reuseport &&
-	    setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &on, sizeof(on))) {
-		log_err("Failed to set SO_REUSEPORT");
-		return -1;
+	if (type == SOCK_STREAM &&
+	    setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &on, sizeof(on))) {
+		log_err("Failed to enable SO_REUSEADDR");
+		goto error_close;
+	}
+
+	if (opts->post_socket_cb &&
+	    opts->post_socket_cb(fd, opts->cb_opts)) {
+		log_err("Failed to call post_socket_cb");
+		goto error_close;
 	}
 
-	if (bind(fd, addr, addrlen) < 0) {
+	if (bind(fd, (struct sockaddr *)addr, addrlen) < 0) {
 		log_err("Failed to bind socket");
 		goto error_close;
 	}
 
 	if (type == SOCK_STREAM) {
-		if (listen(fd, 1) < 0) {
+		if (listen(fd, opts->backlog ? MAX(opts->backlog, 0) : 1) < 0) {
 			log_err("Failed to listed on socket");
 			goto error_close;
 		}
@@ -117,35 +142,45 @@ error_close:
 	return -1;
 }
 
-static int start_server_proto(int family, int type, int protocol,
-			      const char *addr_str, __u16 port, int timeout_ms)
+int start_server_str(int family, int type, const char *addr_str, __u16 port,
+		     const struct network_helper_opts *opts)
 {
 	struct sockaddr_storage addr;
 	socklen_t addrlen;
 
+	if (!opts)
+		opts = &default_opts;
+
 	if (make_sockaddr(family, addr_str, port, &addr, &addrlen))
 		return -1;
 
-	return __start_server(type, protocol, (struct sockaddr *)&addr,
-			      addrlen, timeout_ms, false);
+	return start_server_addr(type, &addr, addrlen, opts);
 }
 
 int start_server(int family, int type, const char *addr_str, __u16 port,
 		 int timeout_ms)
 {
-	return start_server_proto(family, type, 0, addr_str, port, timeout_ms);
+	struct network_helper_opts opts = {
+		.timeout_ms	= timeout_ms,
+	};
+
+	return start_server_str(family, type, addr_str, port, &opts);
 }
 
-int start_mptcp_server(int family, const char *addr_str, __u16 port,
-		       int timeout_ms)
+static int reuseport_cb(int fd, void *opts)
 {
-	return start_server_proto(family, SOCK_STREAM, IPPROTO_MPTCP, addr_str,
-				  port, timeout_ms);
+	int on = 1;
+
+	return setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &on, sizeof(on));
 }
 
 int *start_reuseport_server(int family, int type, const char *addr_str,
 			    __u16 port, int timeout_ms, unsigned int nr_listens)
 {
+	struct network_helper_opts opts = {
+		.timeout_ms = timeout_ms,
+		.post_socket_cb = reuseport_cb,
+	};
 	struct sockaddr_storage addr;
 	unsigned int nr_fds = 0;
 	socklen_t addrlen;
@@ -161,8 +196,7 @@ int *start_reuseport_server(int family, int type, const char *addr_str,
 	if (!fds)
 		return NULL;
 
-	fds[0] = __start_server(type, 0, (struct sockaddr *)&addr, addrlen,
-				timeout_ms, true);
+	fds[0] = start_server_addr(type, &addr, addrlen, &opts);
 	if (fds[0] == -1)
 		goto close_fds;
 	nr_fds = 1;
@@ -171,8 +205,7 @@ int *start_reuseport_server(int family, int type, const char *addr_str,
 		goto close_fds;
 
 	for (; nr_fds < nr_listens; nr_fds++) {
-		fds[nr_fds] = __start_server(type, 0, (struct sockaddr *)&addr,
-					     addrlen, timeout_ms, true);
+		fds[nr_fds] = start_server_addr(type, &addr, addrlen, &opts);
 		if (fds[nr_fds] == -1)
 			goto close_fds;
 	}
@@ -230,41 +263,77 @@ error_close:
 	return -1;
 }
 
-static int connect_fd_to_addr(int fd,
-			      const struct sockaddr_storage *addr,
-			      socklen_t addrlen, const bool must_fail)
+int client_socket(int family, int type,
+		  const struct network_helper_opts *opts)
 {
-	int ret;
+	int fd;
 
-	errno = 0;
-	ret = connect(fd, (const struct sockaddr *)addr, addrlen);
-	if (must_fail) {
-		if (!ret) {
-			log_err("Unexpected success to connect to server");
-			return -1;
-		}
-		if (errno != EPERM) {
-			log_err("Unexpected error from connect to server");
-			return -1;
-		}
-	} else {
-		if (ret) {
-			log_err("Failed to connect to server");
-			return -1;
-		}
+	if (!opts)
+		opts = &default_opts;
+
+	fd = socket(family, type, opts->proto);
+	if (fd < 0) {
+		log_err("Failed to create client socket");
+		return -1;
 	}
 
-	return 0;
+	if (settimeo(fd, opts->timeout_ms))
+		goto error_close;
+
+	if (opts->post_socket_cb &&
+	    opts->post_socket_cb(fd, opts->cb_opts))
+		goto error_close;
+
+	return fd;
+
+error_close:
+	save_errno_close(fd);
+	return -1;
 }
 
-static const struct network_helper_opts default_opts;
+int connect_to_addr(int type, const struct sockaddr_storage *addr, socklen_t addrlen,
+		    const struct network_helper_opts *opts)
+{
+	int fd;
+
+	if (!opts)
+		opts = &default_opts;
+
+	fd = client_socket(addr->ss_family, type, opts);
+	if (fd < 0) {
+		log_err("Failed to create client socket");
+		return -1;
+	}
+
+	if (connect(fd, (const struct sockaddr *)addr, addrlen)) {
+		log_err("Failed to connect to server");
+		save_errno_close(fd);
+		return -1;
+	}
+
+	return fd;
+}
+
+int connect_to_addr_str(int family, int type, const char *addr_str, __u16 port,
+			const struct network_helper_opts *opts)
+{
+	struct sockaddr_storage addr;
+	socklen_t addrlen;
+
+	if (!opts)
+		opts = &default_opts;
+
+	if (make_sockaddr(family, addr_str, port, &addr, &addrlen))
+		return -1;
+
+	return connect_to_addr(type, &addr, addrlen, opts);
+}
 
 int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts)
 {
 	struct sockaddr_storage addr;
-	struct sockaddr_in *addr_in;
 	socklen_t addrlen, optlen;
-	int fd, type, protocol;
+	int type;
 
 	if (!opts)
 		opts = &default_opts;
@@ -275,40 +344,13 @@ int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts)
 		return -1;
 	}
 
-	if (getsockopt(server_fd, SOL_SOCKET, SO_PROTOCOL, &protocol, &optlen)) {
-		log_err("getsockopt(SOL_PROTOCOL)");
-		return -1;
-	}
-
 	addrlen = sizeof(addr);
 	if (getsockname(server_fd, (struct sockaddr *)&addr, &addrlen)) {
 		log_err("Failed to get server addr");
 		return -1;
 	}
 
-	addr_in = (struct sockaddr_in *)&addr;
-	fd = socket(addr_in->sin_family, type, protocol);
-	if (fd < 0) {
-		log_err("Failed to create client socket");
-		return -1;
-	}
-
-	if (settimeo(fd, opts->timeout_ms))
-		goto error_close;
-
-	if (opts->cc && opts->cc[0] &&
-	    setsockopt(fd, SOL_TCP, TCP_CONGESTION, opts->cc,
-		       strlen(opts->cc) + 1))
-		goto error_close;
-
-	if (connect_fd_to_addr(fd, &addr, addrlen, opts->must_fail))
-		goto error_close;
-
-	return fd;
-
-error_close:
-	save_errno_close(fd);
-	return -1;
+	return connect_to_addr(type, &addr, addrlen, opts);
 }
 
 int connect_to_fd(int server_fd, int timeout_ms)
@@ -316,6 +358,15 @@ int connect_to_fd(int server_fd, int timeout_ms)
 	struct network_helper_opts opts = {
 		.timeout_ms = timeout_ms,
 	};
+	socklen_t optlen;
+	int protocol;
+
+	optlen = sizeof(protocol);
+	if (getsockopt(server_fd, SOL_SOCKET, SO_PROTOCOL, &protocol, &optlen)) {
+		log_err("getsockopt(SOL_PROTOCOL)");
+		return -1;
+	}
+	opts.proto = protocol;
 
 	return connect_to_fd_opts(server_fd, &opts);
 }
@@ -333,8 +384,10 @@ int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms)
 		return -1;
 	}
 
-	if (connect_fd_to_addr(client_fd, &addr, len, false))
+	if (connect(client_fd, (const struct sockaddr *)&addr, len)) {
+		log_err("Failed to connect to server");
 		return -1;
+	}
 
 	return 0;
 }
@@ -370,6 +423,19 @@ int make_sockaddr(int family, const char *addr_str, __u16 port,
 		if (len)
 			*len = sizeof(*sin6);
 		return 0;
+	} else if (family == AF_UNIX) {
+		/* Note that we always use abstract unix sockets to avoid having
+		 * to clean up leftover files.
+		 */
+		struct sockaddr_un *sun = (void *)addr;
+
+		memset(addr, 0, sizeof(*sun));
+		sun->sun_family = family;
+		sun->sun_path[0] = 0;
+		strcpy(sun->sun_path + 1, addr_str);
+		if (len)
+			*len = offsetof(struct sockaddr_un, sun_path) + 1 + strlen(addr_str);
+		return 0;
 	}
 	return -1;
 }
@@ -386,6 +452,69 @@ char *ping_command(int family)
 	return "ping";
 }
 
+int append_tid(char *str, size_t sz)
+{
+	size_t end;
+
+	if (!str)
+		return -1;
+
+	end = strlen(str);
+	if (end + 8 > sz)
+		return -1;
+
+	sprintf(&str[end], "%07ld", sys_gettid());
+	str[end + 7] = '\0';
+
+	return 0;
+}
+
+int remove_netns(const char *name)
+{
+	char *cmd;
+	int r;
+
+	r = asprintf(&cmd, "ip netns del %s >/dev/null 2>&1", name);
+	if (r < 0) {
+		log_err("Failed to malloc cmd");
+		return -1;
+	}
+
+	r = system(cmd);
+	free(cmd);
+	return r;
+}
+
+int make_netns(const char *name)
+{
+	char *cmd;
+	int r;
+
+	r = asprintf(&cmd, "ip netns add %s", name);
+	if (r < 0) {
+		log_err("Failed to malloc cmd");
+		return -1;
+	}
+
+	r = system(cmd);
+	free(cmd);
+
+	if (r)
+		return r;
+
+	r = asprintf(&cmd, "ip -n %s link set lo up", name);
+	if (r < 0) {
+		log_err("Failed to malloc cmd for setting up lo");
+		remove_netns(name);
+		return -1;
+	}
+
+	r = system(cmd);
+	free(cmd);
+
+	return r;
+}
+
 struct nstoken {
 	int orig_netns_fd;
 };
@@ -398,32 +527,755 @@ struct nstoken *open_netns(const char *name)
 	struct nstoken *token;
 
 	token = calloc(1, sizeof(struct nstoken));
-	if (!ASSERT_OK_PTR(token, "malloc token"))
+	if (!token) {
+		log_err("Failed to malloc token");
 		return NULL;
+	}
 
 	token->orig_netns_fd = open("/proc/self/ns/net", O_RDONLY);
-	if (!ASSERT_GE(token->orig_netns_fd, 0, "open /proc/self/ns/net"))
+	if (token->orig_netns_fd == -1) {
+		log_err("Failed to open(/proc/self/ns/net)");
 		goto fail;
+	}
 
 	snprintf(nspath, sizeof(nspath), "%s/%s", "/var/run/netns", name);
 	nsfd = open(nspath, O_RDONLY | O_CLOEXEC);
-	if (!ASSERT_GE(nsfd, 0, "open netns fd"))
+	if (nsfd == -1) {
+		log_err("Failed to open(%s)", nspath);
 		goto fail;
+	}
 
 	err = setns(nsfd, CLONE_NEWNET);
 	close(nsfd);
-	if (!ASSERT_OK(err, "setns"))
+	if (err) {
+		log_err("Failed to setns(nsfd)");
 		goto fail;
+	}
 
 	return token;
 fail:
+	if (token->orig_netns_fd != -1)
+		close(token->orig_netns_fd);
 	free(token);
 	return NULL;
 }
 
 void close_netns(struct nstoken *token)
 {
-	ASSERT_OK(setns(token->orig_netns_fd, CLONE_NEWNET), "setns");
+	if (!token)
+		return;
+
+	if (setns(token->orig_netns_fd, CLONE_NEWNET))
+		log_err("Failed to setns(orig_netns_fd)");
 	close(token->orig_netns_fd);
 	free(token);
 }
+
+int open_tuntap(const char *dev_name, bool need_mac)
+{
+	int err = 0;
+	struct ifreq ifr;
+	int fd = open("/dev/net/tun", O_RDWR);
+
+	if (!ASSERT_GE(fd, 0, "open(/dev/net/tun)"))
+		return -1;
+
+	ifr.ifr_flags = IFF_NO_PI | (need_mac ? IFF_TAP : IFF_TUN);
+	strncpy(ifr.ifr_name, dev_name, IFNAMSIZ - 1);
+	ifr.ifr_name[IFNAMSIZ - 1] = '\0';
+
+	err = ioctl(fd, TUNSETIFF, &ifr);
+	if (!ASSERT_OK(err, "ioctl(TUNSETIFF)")) {
+		close(fd);
+		return -1;
+	}
+
+	err = fcntl(fd, F_SETFL, O_NONBLOCK);
+	if (!ASSERT_OK(err, "fcntl(O_NONBLOCK)")) {
+		close(fd);
+		return -1;
+	}
+
+	return fd;
+}
+
+int get_socket_local_port(int sock_fd)
+{
+	struct sockaddr_storage addr;
+	socklen_t addrlen = sizeof(addr);
+	int err;
+
+	err = getsockname(sock_fd, (struct sockaddr *)&addr, &addrlen);
+	if (err < 0)
+		return err;
+
+	if (addr.ss_family == AF_INET) {
+		struct sockaddr_in *sin = (struct sockaddr_in *)&addr;
+
+		return sin->sin_port;
+	} else if (addr.ss_family == AF_INET6) {
+		struct sockaddr_in6 *sin = (struct sockaddr_in6 *)&addr;
+
+		return sin->sin6_port;
+	}
+
+	return -1;
+}
+
+int get_hw_ring_size(char *ifname, struct ethtool_ringparam *ring_param)
+{
+	struct ifreq ifr = {0};
+	int sockfd, err;
+
+	sockfd = socket(AF_INET, SOCK_DGRAM, 0);
+	if (sockfd < 0)
+		return -errno;
+
+	memcpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name));
+
+	ring_param->cmd = ETHTOOL_GRINGPARAM;
+	ifr.ifr_data = (char *)ring_param;
+
+	if (ioctl(sockfd, SIOCETHTOOL, &ifr) < 0) {
+		err = errno;
+		close(sockfd);
+		return -err;
+	}
+
+	close(sockfd);
+	return 0;
+}
+
+int set_hw_ring_size(char *ifname, struct ethtool_ringparam *ring_param)
+{
+	struct ifreq ifr = {0};
+	int sockfd, err;
+
+	sockfd = socket(AF_INET, SOCK_DGRAM, 0);
+	if (sockfd < 0)
+		return -errno;
+
+	memcpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name));
+
+	ring_param->cmd = ETHTOOL_SRINGPARAM;
+	ifr.ifr_data = (char *)ring_param;
+
+	if (ioctl(sockfd, SIOCETHTOOL, &ifr) < 0) {
+		err = errno;
+		close(sockfd);
+		return -err;
+	}
+
+	close(sockfd);
+	return 0;
+}
+
+struct send_recv_arg {
+	int		fd;
+	uint32_t	bytes;
+	int		stop;
+};
+
+static void *send_recv_server(void *arg)
+{
+	struct send_recv_arg *a = (struct send_recv_arg *)arg;
+	ssize_t nr_sent = 0, bytes = 0;
+	char batch[1500];
+	int err = 0, fd;
+
+	fd = accept(a->fd, NULL, NULL);
+	while (fd == -1) {
+		if (errno == EINTR)
+			continue;
+		err = -errno;
+		goto done;
+	}
+
+	if (settimeo(fd, 0)) {
+		err = -errno;
+		goto done;
+	}
+
+	while (bytes < a->bytes && !READ_ONCE(a->stop)) {
+		nr_sent = send(fd, &batch,
+			       MIN(a->bytes - bytes, sizeof(batch)), 0);
+		if (nr_sent == -1 && errno == EINTR)
+			continue;
+		if (nr_sent == -1) {
+			err = -errno;
+			break;
+		}
+		bytes += nr_sent;
+	}
+
+	if (bytes != a->bytes) {
+		log_err("send %zd expected %u", bytes, a->bytes);
+		if (!err)
+			err = bytes > a->bytes ? -E2BIG : -EINTR;
+	}
+
+done:
+	if (fd >= 0)
+		close(fd);
+	if (err) {
+		WRITE_ONCE(a->stop, 1);
+		return ERR_PTR(err);
+	}
+	return NULL;
+}
+
+int send_recv_data(int lfd, int fd, uint32_t total_bytes)
+{
+	ssize_t nr_recv = 0, bytes = 0;
+	struct send_recv_arg arg = {
+		.fd	= lfd,
+		.bytes	= total_bytes,
+		.stop	= 0,
+	};
+	pthread_t srv_thread;
+	void *thread_ret;
+	char batch[1500];
+	int err = 0;
+
+	err = pthread_create(&srv_thread, NULL, send_recv_server, (void *)&arg);
+	if (err) {
+		log_err("Failed to pthread_create");
+		return err;
+	}
+
+	/* recv total_bytes */
+	while (bytes < total_bytes && !READ_ONCE(arg.stop)) {
+		nr_recv = recv(fd, &batch,
+			       MIN(total_bytes - bytes, sizeof(batch)), 0);
+		if (nr_recv == -1 && errno == EINTR)
+			continue;
+		if (nr_recv == -1) {
+			err = -errno;
+			break;
+		}
+		bytes += nr_recv;
+	}
+
+	if (bytes != total_bytes) {
+		log_err("recv %zd expected %u", bytes, total_bytes);
+		if (!err)
+			err = bytes > total_bytes ? -E2BIG : -EINTR;
+	}
+
+	WRITE_ONCE(arg.stop, 1);
+	pthread_join(srv_thread, &thread_ret);
+	if (IS_ERR(thread_ret)) {
+		log_err("Failed in thread_ret %ld", PTR_ERR(thread_ret));
+		err = err ? : PTR_ERR(thread_ret);
+	}
+
+	return err;
+}
+
+int tc_prog_attach(const char *dev, int ingress_fd, int egress_fd)
+{
+	int ifindex, ret;
+
+	if (!ASSERT_TRUE(ingress_fd >= 0 || egress_fd >= 0,
+			 "at least one program fd is valid"))
+		return -1;
+
+	ifindex = if_nametoindex(dev);
+	if (!ASSERT_NEQ(ifindex, 0, "get ifindex"))
+		return -1;
+
+	DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = ifindex,
+			    .attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS);
+	DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts1, .handle = 1,
+			    .priority = 1, .prog_fd = ingress_fd);
+	DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts2, .handle = 1,
+			    .priority = 1, .prog_fd = egress_fd);
+
+	ret = bpf_tc_hook_create(&hook);
+	if (!ASSERT_OK(ret, "create tc hook"))
+		return ret;
+
+	if (ingress_fd >= 0) {
+		hook.attach_point = BPF_TC_INGRESS;
+		ret = bpf_tc_attach(&hook, &opts1);
+		if (!ASSERT_OK(ret, "bpf_tc_attach")) {
+			bpf_tc_hook_destroy(&hook);
+			return ret;
+		}
+	}
+
+	if (egress_fd >= 0) {
+		hook.attach_point = BPF_TC_EGRESS;
+		ret = bpf_tc_attach(&hook, &opts2);
+		if (!ASSERT_OK(ret, "bpf_tc_attach")) {
+			bpf_tc_hook_destroy(&hook);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+#ifdef TRAFFIC_MONITOR
+struct tmonitor_ctx {
+	pcap_t *pcap;
+	pcap_dumper_t *dumper;
+	pthread_t thread;
+	int wake_fd;
+
+	volatile bool done;
+	char pkt_fname[PATH_MAX];
+	int pcap_fd;
+};
+
+static int __base_pr(const char *format, va_list args)
+{
+	return vfprintf(stdout, format, args);
+}
+
+static tm_print_fn_t __tm_pr = __base_pr;
+
+tm_print_fn_t traffic_monitor_set_print(tm_print_fn_t fn)
+{
+	tm_print_fn_t old_print_fn;
+
+	old_print_fn = __atomic_exchange_n(&__tm_pr, fn, __ATOMIC_RELAXED);
+
+	return old_print_fn;
+}
+
+void tm_print(const char *format, ...)
+{
+	tm_print_fn_t print_fn;
+	va_list args;
+
+	print_fn = __atomic_load_n(&__tm_pr, __ATOMIC_RELAXED);
+	if (!print_fn)
+		return;
+
+	va_start(args, format);
+	print_fn(format, args);
+	va_end(args);
+}
+
+/* Is this packet captured with a Ethernet protocol type? */
+static bool is_ethernet(const u_char *packet)
+{
+	u16 arphdr_type;
+
+	memcpy(&arphdr_type, packet + 8, 2);
+	arphdr_type = ntohs(arphdr_type);
+
+	/* Except the following cases, the protocol type contains the
+	 * Ethernet protocol type for the packet.
+	 *
+	 * https://www.tcpdump.org/linktypes/LINKTYPE_LINUX_SLL2.html
+	 */
+	switch (arphdr_type) {
+	case 770: /* ARPHRD_FRAD */
+	case 778: /* ARPHDR_IPGRE */
+	case 803: /* ARPHRD_IEEE80211_RADIOTAP */
+		tm_print("Packet captured: arphdr_type=%d\n", arphdr_type);
+		return false;
+	}
+	return true;
+}
+
+static const char * const pkt_types[] = {
+	"In",
+	"B",			/* Broadcast */
+	"M",			/* Multicast */
+	"C",			/* Captured with the promiscuous mode */
+	"Out",
+};
+
+static const char *pkt_type_str(u16 pkt_type)
+{
+	if (pkt_type < ARRAY_SIZE(pkt_types))
+		return pkt_types[pkt_type];
+	return "Unknown";
+}
+
+#define MAX_FLAGS_STRLEN 21
+/* Show the information of the transport layer in the packet */
+static void show_transport(const u_char *packet, u16 len, u32 ifindex,
+			   const char *src_addr, const char *dst_addr,
+			   u16 proto, bool ipv6, u8 pkt_type)
+{
+	char *ifname, _ifname[IF_NAMESIZE], flags[MAX_FLAGS_STRLEN] = "";
+	const char *transport_str;
+	u16 src_port, dst_port;
+	struct udphdr *udp;
+	struct tcphdr *tcp;
+
+	ifname = if_indextoname(ifindex, _ifname);
+	if (!ifname) {
+		snprintf(_ifname, sizeof(_ifname), "unknown(%d)", ifindex);
+		ifname = _ifname;
+	}
+
+	if (proto == IPPROTO_UDP) {
+		udp = (struct udphdr *)packet;
+		src_port = ntohs(udp->source);
+		dst_port = ntohs(udp->dest);
+		transport_str = "UDP";
+	} else if (proto == IPPROTO_TCP) {
+		tcp = (struct tcphdr *)packet;
+		src_port = ntohs(tcp->source);
+		dst_port = ntohs(tcp->dest);
+		transport_str = "TCP";
+	} else if (proto == IPPROTO_ICMP) {
+		tm_print("%-7s %-3s IPv4 %s > %s: ICMP, length %d, type %d, code %d\n",
+			 ifname, pkt_type_str(pkt_type), src_addr, dst_addr, len,
+			 packet[0], packet[1]);
+		return;
+	} else if (proto == IPPROTO_ICMPV6) {
+		tm_print("%-7s %-3s IPv6 %s > %s: ICMPv6, length %d, type %d, code %d\n",
+			 ifname, pkt_type_str(pkt_type), src_addr, dst_addr, len,
+			 packet[0], packet[1]);
+		return;
+	} else {
+		tm_print("%-7s %-3s %s %s > %s: protocol %d\n",
+			 ifname, pkt_type_str(pkt_type), ipv6 ? "IPv6" : "IPv4",
+			 src_addr, dst_addr, proto);
+		return;
+	}
+
+	/* TCP or UDP*/
+
+	if (proto == IPPROTO_TCP)
+		snprintf(flags, MAX_FLAGS_STRLEN, "%s%s%s%s",
+			 tcp->fin ? ", FIN" : "",
+			 tcp->syn ? ", SYN" : "",
+			 tcp->rst ? ", RST" : "",
+			 tcp->ack ? ", ACK" : "");
+
+	if (ipv6)
+		tm_print("%-7s %-3s IPv6 %s.%d > %s.%d: %s, length %d%s\n",
+			 ifname, pkt_type_str(pkt_type), src_addr, src_port,
+			 dst_addr, dst_port, transport_str, len, flags);
+	else
+		tm_print("%-7s %-3s IPv4 %s:%d > %s:%d: %s, length %d%s\n",
+			 ifname, pkt_type_str(pkt_type), src_addr, src_port,
+			 dst_addr, dst_port, transport_str, len, flags);
+}
+
+static void show_ipv6_packet(const u_char *packet, u32 ifindex, u8 pkt_type)
+{
+	char src_buf[INET6_ADDRSTRLEN], dst_buf[INET6_ADDRSTRLEN];
+	struct ipv6hdr *pkt = (struct ipv6hdr *)packet;
+	const char *src, *dst;
+	u_char proto;
+
+	src = inet_ntop(AF_INET6, &pkt->saddr, src_buf, sizeof(src_buf));
+	if (!src)
+		src = "<invalid>";
+	dst = inet_ntop(AF_INET6, &pkt->daddr, dst_buf, sizeof(dst_buf));
+	if (!dst)
+		dst = "<invalid>";
+	proto = pkt->nexthdr;
+	show_transport(packet + sizeof(struct ipv6hdr),
+		       ntohs(pkt->payload_len),
+		       ifindex, src, dst, proto, true, pkt_type);
+}
+
+static void show_ipv4_packet(const u_char *packet, u32 ifindex, u8 pkt_type)
+{
+	char src_buf[INET_ADDRSTRLEN], dst_buf[INET_ADDRSTRLEN];
+	struct iphdr *pkt = (struct iphdr *)packet;
+	const char *src, *dst;
+	u_char proto;
+
+	src = inet_ntop(AF_INET, &pkt->saddr, src_buf, sizeof(src_buf));
+	if (!src)
+		src = "<invalid>";
+	dst = inet_ntop(AF_INET, &pkt->daddr, dst_buf, sizeof(dst_buf));
+	if (!dst)
+		dst = "<invalid>";
+	proto = pkt->protocol;
+	show_transport(packet + sizeof(struct iphdr),
+		       ntohs(pkt->tot_len),
+		       ifindex, src, dst, proto, false, pkt_type);
+}
+
+static void *traffic_monitor_thread(void *arg)
+{
+	char *ifname, _ifname[IF_NAMESIZE];
+	const u_char *packet, *payload;
+	struct tmonitor_ctx *ctx = arg;
+	pcap_dumper_t *dumper = ctx->dumper;
+	int fd = ctx->pcap_fd, nfds, r;
+	int wake_fd = ctx->wake_fd;
+	struct pcap_pkthdr header;
+	pcap_t *pcap = ctx->pcap;
+	u32 ifindex;
+	fd_set fds;
+	u16 proto;
+	u8 ptype;
+
+	nfds = (fd > wake_fd ? fd : wake_fd) + 1;
+	FD_ZERO(&fds);
+
+	while (!ctx->done) {
+		FD_SET(fd, &fds);
+		FD_SET(wake_fd, &fds);
+		r = select(nfds, &fds, NULL, NULL, NULL);
+		if (!r)
+			continue;
+		if (r < 0) {
+			if (errno == EINTR)
+				continue;
+			log_err("Fail to select on pcap fd and wake fd");
+			break;
+		}
+
+		/* This instance of pcap is non-blocking */
+		packet = pcap_next(pcap, &header);
+		if (!packet)
+			continue;
+
+		/* According to the man page of pcap_dump(), first argument
+		 * is the pcap_dumper_t pointer even it's argument type is
+		 * u_char *.
+		 */
+		pcap_dump((u_char *)dumper, &header, packet);
+
+		/* Not sure what other types of packets look like. Here, we
+		 * parse only Ethernet and compatible packets.
+		 */
+		if (!is_ethernet(packet))
+			continue;
+
+		/* Skip SLL2 header
+		 * https://www.tcpdump.org/linktypes/LINKTYPE_LINUX_SLL2.html
+		 *
+		 * Although the document doesn't mention that, the payload
+		 * doesn't include the Ethernet header. The payload starts
+		 * from the first byte of the network layer header.
+		 */
+		payload = packet + 20;
+
+		memcpy(&proto, packet, 2);
+		proto = ntohs(proto);
+		memcpy(&ifindex, packet + 4, 4);
+		ifindex = ntohl(ifindex);
+		ptype = packet[10];
+
+		if (proto == ETH_P_IPV6) {
+			show_ipv6_packet(payload, ifindex, ptype);
+		} else if (proto == ETH_P_IP) {
+			show_ipv4_packet(payload, ifindex, ptype);
+		} else {
+			ifname = if_indextoname(ifindex, _ifname);
+			if (!ifname) {
+				snprintf(_ifname, sizeof(_ifname), "unknown(%d)", ifindex);
+				ifname = _ifname;
+			}
+
+			tm_print("%-7s %-3s Unknown network protocol type 0x%x\n",
+				 ifname, pkt_type_str(ptype), proto);
+		}
+	}
+
+	return NULL;
+}
+
+/* Prepare the pcap handle to capture packets.
+ *
+ * This pcap is non-blocking and immediate mode is enabled to receive
+ * captured packets as soon as possible.  The snaplen is set to 1024 bytes
+ * to limit the size of captured content. The format of the link-layer
+ * header is set to DLT_LINUX_SLL2 to enable handling various link-layer
+ * technologies.
+ */
+static pcap_t *traffic_monitor_prepare_pcap(void)
+{
+	char errbuf[PCAP_ERRBUF_SIZE];
+	pcap_t *pcap;
+	int r;
+
+	/* Listen on all NICs in the namespace */
+	pcap = pcap_create("any", errbuf);
+	if (!pcap) {
+		log_err("Failed to open pcap: %s", errbuf);
+		return NULL;
+	}
+	/* Limit the size of the packet (first N bytes) */
+	r = pcap_set_snaplen(pcap, 1024);
+	if (r) {
+		log_err("Failed to set snaplen: %s", pcap_geterr(pcap));
+		goto error;
+	}
+	/* To receive packets as fast as possible */
+	r = pcap_set_immediate_mode(pcap, 1);
+	if (r) {
+		log_err("Failed to set immediate mode: %s", pcap_geterr(pcap));
+		goto error;
+	}
+	r = pcap_setnonblock(pcap, 1, errbuf);
+	if (r) {
+		log_err("Failed to set nonblock: %s", errbuf);
+		goto error;
+	}
+	r = pcap_activate(pcap);
+	if (r) {
+		log_err("Failed to activate pcap: %s", pcap_geterr(pcap));
+		goto error;
+	}
+	/* Determine the format of the link-layer header */
+	r = pcap_set_datalink(pcap, DLT_LINUX_SLL2);
+	if (r) {
+		log_err("Failed to set datalink: %s", pcap_geterr(pcap));
+		goto error;
+	}
+
+	return pcap;
+error:
+	pcap_close(pcap);
+	return NULL;
+}
+
+static void encode_test_name(char *buf, size_t len, const char *test_name, const char *subtest_name)
+{
+	char *p;
+
+	if (subtest_name)
+		snprintf(buf, len, "%s__%s", test_name, subtest_name);
+	else
+		snprintf(buf, len, "%s", test_name);
+	while ((p = strchr(buf, '/')))
+		*p = '_';
+	while ((p = strchr(buf, ' ')))
+		*p = '_';
+}
+
+#define PCAP_DIR "/tmp/tmon_pcap"
+
+/* Start to monitor the network traffic in the given network namespace.
+ *
+ * netns: the name of the network namespace to monitor. If NULL, the
+ *        current network namespace is monitored.
+ * test_name: the name of the running test.
+ * subtest_name: the name of the running subtest if there is. It should be
+ *               NULL if it is not a subtest.
+ *
+ * This function will start a thread to capture packets going through NICs
+ * in the give network namespace.
+ */
+struct tmonitor_ctx *traffic_monitor_start(const char *netns, const char *test_name,
+					   const char *subtest_name)
+{
+	struct nstoken *nstoken = NULL;
+	struct tmonitor_ctx *ctx;
+	char test_name_buf[64];
+	static int tmon_seq;
+	int r;
+
+	if (netns) {
+		nstoken = open_netns(netns);
+		if (!nstoken)
+			return NULL;
+	}
+	ctx = malloc(sizeof(*ctx));
+	if (!ctx) {
+		log_err("Failed to malloc ctx");
+		goto fail_ctx;
+	}
+	memset(ctx, 0, sizeof(*ctx));
+
+	encode_test_name(test_name_buf, sizeof(test_name_buf), test_name, subtest_name);
+	snprintf(ctx->pkt_fname, sizeof(ctx->pkt_fname),
+		 PCAP_DIR "/packets-%d-%d-%s-%s.log", getpid(), tmon_seq++,
+		 test_name_buf, netns ? netns : "unknown");
+
+	r = mkdir(PCAP_DIR, 0755);
+	if (r && errno != EEXIST) {
+		log_err("Failed to create " PCAP_DIR);
+		goto fail_pcap;
+	}
+
+	ctx->pcap = traffic_monitor_prepare_pcap();
+	if (!ctx->pcap)
+		goto fail_pcap;
+	ctx->pcap_fd = pcap_get_selectable_fd(ctx->pcap);
+	if (ctx->pcap_fd < 0) {
+		log_err("Failed to get pcap fd");
+		goto fail_dumper;
+	}
+
+	/* Create a packet file */
+	ctx->dumper = pcap_dump_open(ctx->pcap, ctx->pkt_fname);
+	if (!ctx->dumper) {
+		log_err("Failed to open pcap dump: %s", ctx->pkt_fname);
+		goto fail_dumper;
+	}
+
+	/* Create an eventfd to wake up the monitor thread */
+	ctx->wake_fd = eventfd(0, 0);
+	if (ctx->wake_fd < 0) {
+		log_err("Failed to create eventfd");
+		goto fail_eventfd;
+	}
+
+	r = pthread_create(&ctx->thread, NULL, traffic_monitor_thread, ctx);
+	if (r) {
+		log_err("Failed to create thread");
+		goto fail;
+	}
+
+	close_netns(nstoken);
+
+	return ctx;
+
+fail:
+	close(ctx->wake_fd);
+
+fail_eventfd:
+	pcap_dump_close(ctx->dumper);
+	unlink(ctx->pkt_fname);
+
+fail_dumper:
+	pcap_close(ctx->pcap);
+
+fail_pcap:
+	free(ctx);
+
+fail_ctx:
+	close_netns(nstoken);
+
+	return NULL;
+}
+
+static void traffic_monitor_release(struct tmonitor_ctx *ctx)
+{
+	pcap_close(ctx->pcap);
+	pcap_dump_close(ctx->dumper);
+
+	close(ctx->wake_fd);
+
+	free(ctx);
+}
+
+/* Stop the network traffic monitor.
+ *
+ * ctx: the context returned by traffic_monitor_start()
+ */
+void traffic_monitor_stop(struct tmonitor_ctx *ctx)
+{
+	__u64 w = 1;
+
+	if (!ctx)
+		return;
+
+	/* Stop the monitor thread */
+	ctx->done = true;
+	/* Wake up the background thread. */
+	write(ctx->wake_fd, &w, sizeof(w));
+	pthread_join(ctx->thread, NULL);
+
+	tm_print("Packet file: %s\n", strrchr(ctx->pkt_fname, '/') + 1);
+
+	traffic_monitor_release(ctx);
+}
+
+#endif /* TRAFFIC_MONITOR */
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index f882c691b790..79a010c88e11 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -1,16 +1,24 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __NETWORK_HELPERS_H
 #define __NETWORK_HELPERS_H
+#include <arpa/inet.h>
 #include <sys/socket.h>
 #include <sys/types.h>
 #include <linux/types.h>
 typedef __u16 __sum16;
 #include <linux/if_ether.h>
 #include <linux/if_packet.h>
+#include <linux/if_tun.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <linux/ethtool.h>
+#include <linux/sockios.h>
+#include <linux/err.h>
 #include <netinet/tcp.h>
+#include <netinet/udp.h>
 #include <bpf/bpf_endian.h>
+#include <net/if.h>
+#include <stdio.h>
 
 #define MAGIC_VAL 0x1234
 #define NUM_ITER 100000
@@ -18,9 +26,20 @@ typedef __u16 __sum16;
 #define MAGIC_BYTES 123
 
 struct network_helper_opts {
-	const char *cc;
 	int timeout_ms;
-	bool must_fail;
+	int proto;
+	/* +ve: Passed to listen() as-is.
+	 *   0: Default when the test does not set
+	 *      a particular value during the struct init.
+	 *      It is changed to 1 before passing to listen().
+	 *      Most tests only have one on-going connection.
+	 * -ve: It is changed to 0 before passing to listen().
+	 *      It is useful to force syncookie without
+	 *	changing the "tcp_syncookies" sysctl from 1 to 2.
+	 */
+	int backlog;
+	int (*post_socket_cb)(int fd, void *opts);
+	void *cb_opts;
 };
 
 /* ipv4 test vector */
@@ -40,14 +59,22 @@ struct ipv6_packet {
 extern struct ipv6_packet pkt_v6;
 
 int settimeo(int fd, int timeout_ms);
+int start_server_str(int family, int type, const char *addr_str, __u16 port,
+		     const struct network_helper_opts *opts);
 int start_server(int family, int type, const char *addr, __u16 port,
 		 int timeout_ms);
-int start_mptcp_server(int family, const char *addr, __u16 port,
-		       int timeout_ms);
 int *start_reuseport_server(int family, int type, const char *addr_str,
 			    __u16 port, int timeout_ms,
 			    unsigned int nr_listens);
+int start_server_addr(int type, const struct sockaddr_storage *addr, socklen_t len,
+		      const struct network_helper_opts *opts);
 void free_fds(int *fds, unsigned int nr_close_fds);
+int client_socket(int family, int type,
+		  const struct network_helper_opts *opts);
+int connect_to_addr(int type, const struct sockaddr_storage *addr, socklen_t len,
+		    const struct network_helper_opts *opts);
+int connect_to_addr_str(int family, int type, const char *addr_str, __u16 port,
+			const struct network_helper_opts *opts);
 int connect_to_fd(int server_fd, int timeout_ms);
 int connect_to_fd_opts(int server_fd, const struct network_helper_opts *opts);
 int connect_fd_to_fd(int client_fd, int server_fd, int timeout_ms);
@@ -56,6 +83,11 @@ int fastopen_connect(int server_fd, const char *data, unsigned int data_len,
 int make_sockaddr(int family, const char *addr_str, __u16 port,
 		  struct sockaddr_storage *addr, socklen_t *len);
 char *ping_command(int family);
+int get_socket_local_port(int sock_fd);
+int get_hw_ring_size(char *ifname, struct ethtool_ringparam *ring_param);
+int set_hw_ring_size(char *ifname, struct ethtool_ringparam *ring_param);
+
+int open_tuntap(const char *dev_name, bool need_mac);
 
 struct nstoken;
 /**
@@ -66,4 +98,199 @@ struct nstoken;
  */
 struct nstoken *open_netns(const char *name);
 void close_netns(struct nstoken *token);
+int send_recv_data(int lfd, int fd, uint32_t total_bytes);
+int make_netns(const char *name);
+int remove_netns(const char *name);
+
+/**
+ * append_tid() - Append thread ID to the given string.
+ *
+ * @str: string to extend
+ * @sz: string's size
+ *
+ * 8 characters are used to append the thread ID (7 digits + '\0')
+ *
+ * Returns -1 on errors, 0 otherwise
+ */
+int append_tid(char *str, size_t sz);
+
+static __u16 csum_fold(__u32 csum)
+{
+	csum = (csum & 0xffff) + (csum >> 16);
+	csum = (csum & 0xffff) + (csum >> 16);
+
+	return (__u16)~csum;
+}
+
+static __wsum csum_partial(const void *buf, int len, __wsum sum)
+{
+	__u16 *p = (__u16 *)buf;
+	int num_u16 = len >> 1;
+	int i;
+
+	for (i = 0; i < num_u16; i++)
+		sum += p[i];
+
+	return sum;
+}
+
+static inline __sum16 build_ip_csum(struct iphdr *iph)
+{
+	__u32 sum = 0;
+	__u16 *p;
+
+	iph->check = 0;
+	p = (void *)iph;
+	sum = csum_partial(p, iph->ihl << 2, 0);
+
+	return csum_fold(sum);
+}
+
+/**
+ * csum_tcpudp_magic - compute IP pseudo-header checksum
+ *
+ * Compute the IPv4 pseudo header checksum. The helper can take a
+ * accumulated sum from the transport layer to accumulate it and directly
+ * return the transport layer
+ *
+ * @saddr: IP source address
+ * @daddr: IP dest address
+ * @len: IP data size
+ * @proto: transport layer protocol
+ * @csum: The accumulated partial sum to add to the computation
+ *
+ * Returns the folded sum
+ */
+static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
+					__u32 len, __u8 proto,
+					__wsum csum)
+{
+	__u64 s = csum;
+
+	s += (__u32)saddr;
+	s += (__u32)daddr;
+	s += htons(proto + len);
+	s = (s & 0xffffffff) + (s >> 32);
+	s = (s & 0xffffffff) + (s >> 32);
+
+	return csum_fold((__u32)s);
+}
+
+/**
+ * csum_ipv6_magic - compute IPv6 pseudo-header checksum
+ *
+ * Compute the ipv6 pseudo header checksum. The helper can take a
+ * accumulated sum from the transport layer to accumulate it and directly
+ * return the transport layer
+ *
+ * @saddr: IPv6 source address
+ * @daddr: IPv6 dest address
+ * @len: IPv6 data size
+ * @proto: transport layer protocol
+ * @csum: The accumulated partial sum to add to the computation
+ *
+ * Returns the folded sum
+ */
+static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+				      const struct in6_addr *daddr,
+					__u32 len, __u8 proto,
+					__wsum csum)
+{
+	__u64 s = csum;
+	int i;
+
+	for (i = 0; i < 4; i++)
+		s += (__u32)saddr->s6_addr32[i];
+	for (i = 0; i < 4; i++)
+		s += (__u32)daddr->s6_addr32[i];
+	s += htons(proto + len);
+	s = (s & 0xffffffff) + (s >> 32);
+	s = (s & 0xffffffff) + (s >> 32);
+
+	return csum_fold((__u32)s);
+}
+
+/**
+ * build_udp_v4_csum - compute UDP checksum for UDP over IPv4
+ *
+ * Compute the checksum to embed in UDP header, composed of the sum of IP
+ * pseudo-header checksum, UDP header checksum and UDP data checksum
+ * @iph IP header
+ * @udph UDP header, which must be immediately followed by UDP data
+ *
+ * Returns the total checksum
+ */
+
+static inline __sum16 build_udp_v4_csum(const struct iphdr *iph,
+					const struct udphdr *udph)
+{
+	unsigned long sum;
+
+	sum = csum_partial(udph, ntohs(udph->len), 0);
+	return csum_tcpudp_magic(iph->saddr, iph->daddr, ntohs(udph->len),
+				 IPPROTO_UDP, sum);
+}
+
+/**
+ * build_udp_v6_csum - compute UDP checksum for UDP over IPv6
+ *
+ * Compute the checksum to embed in UDP header, composed of the sum of IPv6
+ * pseudo-header checksum, UDP header checksum and UDP data checksum
+ * @ip6h IPv6 header
+ * @udph UDP header, which must be immediately followed by UDP data
+ *
+ * Returns the total checksum
+ */
+static inline __sum16 build_udp_v6_csum(const struct ipv6hdr *ip6h,
+					const struct udphdr *udph)
+{
+	unsigned long sum;
+
+	sum = csum_partial(udph, ntohs(udph->len), 0);
+	return csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, ntohs(udph->len),
+			       IPPROTO_UDP, sum);
+}
+
+struct tmonitor_ctx;
+
+typedef int (*tm_print_fn_t)(const char *format, va_list args);
+
+/**
+ * tc_prog_attach - attach BPF program(s) to an interface
+ *
+ * Takes file descriptors pointing to at least one, at most two BPF
+ * programs, and attach those programs to an interface ingress, egress or
+ * both.
+ *
+ * @dev: string containing the interface name
+ * @ingress_fd: file descriptor of the program to attach to interface ingress
+ * @egress_fd: file descriptor of the program to attach to interface egress
+ *
+ * Returns 0 on success, -1 if no valid file descriptor has been found, if
+ * the interface name is invalid or if an error ocurred during attach.
+ */
+int tc_prog_attach(const char *dev, int ingress_fd, int egress_fd);
+
+#ifdef TRAFFIC_MONITOR
+struct tmonitor_ctx *traffic_monitor_start(const char *netns, const char *test_name,
+					   const char *subtest_name);
+void traffic_monitor_stop(struct tmonitor_ctx *ctx);
+tm_print_fn_t traffic_monitor_set_print(tm_print_fn_t fn);
+#else
+static inline struct tmonitor_ctx *traffic_monitor_start(const char *netns, const char *test_name,
+							 const char *subtest_name)
+{
+	return NULL;
+}
+
+static inline void traffic_monitor_stop(struct tmonitor_ctx *ctx)
+{
+}
+
+static inline tm_print_fn_t traffic_monitor_set_print(tm_print_fn_t fn)
+{
+	return NULL;
+}
+#endif
+
 #endif
diff --git a/tools/testing/selftests/bpf/prog_tests/access_variable_array.c b/tools/testing/selftests/bpf/prog_tests/access_variable_array.c
new file mode 100644
index 000000000000..08131782437c
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/access_variable_array.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Bytedance */
+
+#include <test_progs.h>
+#include "test_access_variable_array.skel.h"
+
+void test_access_variable_array(void)
+{
+	struct test_access_variable_array *skel;
+
+	skel = test_access_variable_array__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_access_variable_array__open_and_load"))
+		return;
+
+	test_access_variable_array__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c
index 4666f88f2bb4..24c509ce4e5b 100644
--- a/tools/testing/selftests/bpf/prog_tests/align.c
+++ b/tools/testing/selftests/bpf/prog_tests/align.c
@@ -6,6 +6,7 @@
 
 struct bpf_reg_match {
 	unsigned int line;
+	const char *reg;
 	const char *match;
 };
 
@@ -39,13 +40,13 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{0, "R1=ctx(off=0,imm=0)"},
-			{0, "R10=fp0"},
-			{0, "R3_w=2"},
-			{1, "R3_w=4"},
-			{2, "R3_w=8"},
-			{3, "R3_w=16"},
-			{4, "R3_w=32"},
+			{0, "R1", "ctx()"},
+			{0, "R10", "fp0"},
+			{0, "R3", "2"},
+			{1, "R3", "4"},
+			{2, "R3", "8"},
+			{3, "R3", "16"},
+			{4, "R3", "32"},
 		},
 	},
 	{
@@ -67,19 +68,19 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{0, "R1=ctx(off=0,imm=0)"},
-			{0, "R10=fp0"},
-			{0, "R3_w=1"},
-			{1, "R3_w=2"},
-			{2, "R3_w=4"},
-			{3, "R3_w=8"},
-			{4, "R3_w=16"},
-			{5, "R3_w=1"},
-			{6, "R4_w=32"},
-			{7, "R4_w=16"},
-			{8, "R4_w=8"},
-			{9, "R4_w=4"},
-			{10, "R4_w=2"},
+			{0, "R1", "ctx()"},
+			{0, "R10", "fp0"},
+			{0, "R3", "1"},
+			{1, "R3", "2"},
+			{2, "R3", "4"},
+			{3, "R3", "8"},
+			{4, "R3", "16"},
+			{5, "R3", "1"},
+			{6, "R4", "32"},
+			{7, "R4", "16"},
+			{8, "R4", "8"},
+			{9, "R4", "4"},
+			{10, "R4", "2"},
 		},
 	},
 	{
@@ -96,14 +97,14 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{0, "R1=ctx(off=0,imm=0)"},
-			{0, "R10=fp0"},
-			{0, "R3_w=4"},
-			{1, "R3_w=8"},
-			{2, "R3_w=10"},
-			{3, "R4_w=8"},
-			{4, "R4_w=12"},
-			{5, "R4_w=14"},
+			{0, "R1", "ctx()"},
+			{0, "R10", "fp0"},
+			{0, "R3", "4"},
+			{1, "R3", "8"},
+			{2, "R3", "10"},
+			{3, "R4", "8"},
+			{4, "R4", "12"},
+			{5, "R4", "14"},
 		},
 	},
 	{
@@ -118,12 +119,12 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{0, "R1=ctx(off=0,imm=0)"},
-			{0, "R10=fp0"},
-			{0, "R3_w=7"},
-			{1, "R3_w=7"},
-			{2, "R3_w=14"},
-			{3, "R3_w=56"},
+			{0, "R1", "ctx()"},
+			{0, "R10", "fp0"},
+			{0, "R3", "7"},
+			{1, "R3", "7"},
+			{2, "R3", "14"},
+			{3, "R3", "56"},
 		},
 	},
 
@@ -161,19 +162,19 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{6, "R0_w=pkt(off=8,r=8,imm=0)"},
-			{6, "R3_w=scalar(umax=255,var_off=(0x0; 0xff))"},
-			{7, "R3_w=scalar(umax=510,var_off=(0x0; 0x1fe))"},
-			{8, "R3_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"},
-			{9, "R3_w=scalar(umax=2040,var_off=(0x0; 0x7f8))"},
-			{10, "R3_w=scalar(umax=4080,var_off=(0x0; 0xff0))"},
-			{12, "R3_w=pkt_end(off=0,imm=0)"},
-			{17, "R4_w=scalar(umax=255,var_off=(0x0; 0xff))"},
-			{18, "R4_w=scalar(umax=8160,var_off=(0x0; 0x1fe0))"},
-			{19, "R4_w=scalar(umax=4080,var_off=(0x0; 0xff0))"},
-			{20, "R4_w=scalar(umax=2040,var_off=(0x0; 0x7f8))"},
-			{21, "R4_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"},
-			{22, "R4_w=scalar(umax=510,var_off=(0x0; 0x1fe))"},
+			{6, "R0", "pkt(off=8,r=8)"},
+			{6, "R3", "var_off=(0x0; 0xff)"},
+			{7, "R3", "var_off=(0x0; 0x1fe)"},
+			{8, "R3", "var_off=(0x0; 0x3fc)"},
+			{9, "R3", "var_off=(0x0; 0x7f8)"},
+			{10, "R3", "var_off=(0x0; 0xff0)"},
+			{12, "R3", "pkt_end()"},
+			{17, "R4", "var_off=(0x0; 0xff)"},
+			{18, "R4", "var_off=(0x0; 0x1fe0)"},
+			{19, "R4", "var_off=(0x0; 0xff0)"},
+			{20, "R4", "var_off=(0x0; 0x7f8)"},
+			{21, "R4", "var_off=(0x0; 0x3fc)"},
+			{22, "R4", "var_off=(0x0; 0x1fe)"},
 		},
 	},
 	{
@@ -194,16 +195,16 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{6, "R3_w=scalar(umax=255,var_off=(0x0; 0xff))"},
-			{7, "R4_w=scalar(id=1,umax=255,var_off=(0x0; 0xff))"},
-			{8, "R4_w=scalar(umax=255,var_off=(0x0; 0xff))"},
-			{9, "R4_w=scalar(id=1,umax=255,var_off=(0x0; 0xff))"},
-			{10, "R4_w=scalar(umax=510,var_off=(0x0; 0x1fe))"},
-			{11, "R4_w=scalar(id=1,umax=255,var_off=(0x0; 0xff))"},
-			{12, "R4_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"},
-			{13, "R4_w=scalar(id=1,umax=255,var_off=(0x0; 0xff))"},
-			{14, "R4_w=scalar(umax=2040,var_off=(0x0; 0x7f8))"},
-			{15, "R4_w=scalar(umax=4080,var_off=(0x0; 0xff0))"},
+			{6, "R3", "var_off=(0x0; 0xff)"},
+			{7, "R4", "var_off=(0x0; 0xff)"},
+			{8, "R4", "var_off=(0x0; 0xff)"},
+			{9, "R4", "var_off=(0x0; 0xff)"},
+			{10, "R4", "var_off=(0x0; 0x1fe)"},
+			{11, "R4", "var_off=(0x0; 0xff)"},
+			{12, "R4", "var_off=(0x0; 0x3fc)"},
+			{13, "R4", "var_off=(0x0; 0xff)"},
+			{14, "R4", "var_off=(0x0; 0x7f8)"},
+			{15, "R4", "var_off=(0x0; 0xff0)"},
 		},
 	},
 	{
@@ -234,14 +235,14 @@ static struct bpf_align_test tests[] = {
 		},
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.matches = {
-			{2, "R5_w=pkt(off=0,r=0,imm=0)"},
-			{4, "R5_w=pkt(off=14,r=0,imm=0)"},
-			{5, "R4_w=pkt(off=14,r=0,imm=0)"},
-			{9, "R2=pkt(off=0,r=18,imm=0)"},
-			{10, "R5=pkt(off=14,r=18,imm=0)"},
-			{10, "R4_w=scalar(umax=255,var_off=(0x0; 0xff))"},
-			{13, "R4_w=scalar(umax=65535,var_off=(0x0; 0xffff))"},
-			{14, "R4_w=scalar(umax=65535,var_off=(0x0; 0xffff))"},
+			{2, "R5", "pkt(r=0)"},
+			{4, "R5", "pkt(off=14,r=0)"},
+			{5, "R4", "pkt(off=14,r=0)"},
+			{9, "R2", "pkt(r=18)"},
+			{10, "R5", "pkt(off=14,r=18)"},
+			{10, "R4", "var_off=(0x0; 0xff)"},
+			{13, "R4", "var_off=(0x0; 0xffff)"},
+			{14, "R4", "var_off=(0x0; 0xffff)"},
 		},
 	},
 	{
@@ -298,20 +299,20 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{6, "R2_w=pkt(off=0,r=8,imm=0)"},
-			{7, "R6_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"},
+			{6, "R2", "pkt(r=8)"},
+			{7, "R6", "var_off=(0x0; 0x3fc)"},
 			/* Offset is added to packet pointer R5, resulting in
 			 * known fixed offset, and variable offset from R6.
 			 */
-			{11, "R5_w=pkt(id=1,off=14,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
+			{11, "R5", "pkt(id=1,off=14,"},
 			/* At the time the word size load is performed from R5,
 			 * it's total offset is NET_IP_ALIGN + reg->off (0) +
 			 * reg->aux_off (14) which is 16.  Then the variable
 			 * offset is considered using reg->aux_off_align which
 			 * is 4 and meets the load's requirements.
 			 */
-			{15, "R4=pkt(id=1,off=18,r=18,umax=1020,var_off=(0x0; 0x3fc))"},
-			{15, "R5=pkt(id=1,off=14,r=18,umax=1020,var_off=(0x0; 0x3fc))"},
+			{15, "R4", "var_off=(0x0; 0x3fc)"},
+			{15, "R5", "var_off=(0x0; 0x3fc)"},
 			/* Variable offset is added to R5 packet pointer,
 			 * resulting in auxiliary alignment of 4. To avoid BPF
 			 * verifier's precision backtracking logging
@@ -319,46 +320,46 @@ static struct bpf_align_test tests[] = {
 			 * instruction to validate R5 state. We also check
 			 * that R4 is what it should be in such case.
 			 */
-			{18, "R4_w=pkt(id=2,off=0,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
-			{18, "R5_w=pkt(id=2,off=0,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
+			{18, "R4", "var_off=(0x0; 0x3fc)"},
+			{18, "R5", "var_off=(0x0; 0x3fc)"},
 			/* Constant offset is added to R5, resulting in
 			 * reg->off of 14.
 			 */
-			{19, "R5_w=pkt(id=2,off=14,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
+			{19, "R5", "pkt(id=2,off=14,"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off
 			 * (14) which is 16.  Then the variable offset is 4-byte
 			 * aligned, so the total offset is 4-byte aligned and
 			 * meets the load's requirements.
 			 */
-			{24, "R4=pkt(id=2,off=18,r=18,umax=1020,var_off=(0x0; 0x3fc))"},
-			{24, "R5=pkt(id=2,off=14,r=18,umax=1020,var_off=(0x0; 0x3fc))"},
+			{24, "R4", "var_off=(0x0; 0x3fc)"},
+			{24, "R5", "var_off=(0x0; 0x3fc)"},
 			/* Constant offset is added to R5 packet pointer,
 			 * resulting in reg->off value of 14.
 			 */
-			{26, "R5_w=pkt(off=14,r=8"},
+			{26, "R5", "pkt(off=14,r=8)"},
 			/* Variable offset is added to R5, resulting in a
 			 * variable offset of (4n). See comment for insn #18
 			 * for R4 = R5 trick.
 			 */
-			{28, "R4_w=pkt(id=3,off=14,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
-			{28, "R5_w=pkt(id=3,off=14,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
+			{28, "R4", "var_off=(0x0; 0x3fc)"},
+			{28, "R5", "var_off=(0x0; 0x3fc)"},
 			/* Constant is added to R5 again, setting reg->off to 18. */
-			{29, "R5_w=pkt(id=3,off=18,r=0,umax=1020,var_off=(0x0; 0x3fc))"},
+			{29, "R5", "pkt(id=3,off=18,"},
 			/* And once more we add a variable; resulting var_off
 			 * is still (4n), fixed offset is not changed.
 			 * Also, we create a new reg->id.
 			 */
-			{31, "R4_w=pkt(id=4,off=18,r=0,umax=2040,var_off=(0x0; 0x7fc)"},
-			{31, "R5_w=pkt(id=4,off=18,r=0,umax=2040,var_off=(0x0; 0x7fc)"},
+			{31, "R4", "var_off=(0x0; 0x7fc)"},
+			{31, "R5", "var_off=(0x0; 0x7fc)"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (18)
 			 * which is 20.  Then the variable offset is (4n), so
 			 * the total offset is 4-byte aligned and meets the
 			 * load's requirements.
 			 */
-			{35, "R4=pkt(id=4,off=22,r=22,umax=2040,var_off=(0x0; 0x7fc)"},
-			{35, "R5=pkt(id=4,off=18,r=22,umax=2040,var_off=(0x0; 0x7fc)"},
+			{35, "R4", "var_off=(0x0; 0x7fc)"},
+			{35, "R5", "var_off=(0x0; 0x7fc)"},
 		},
 	},
 	{
@@ -396,36 +397,36 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{6, "R2_w=pkt(off=0,r=8,imm=0)"},
-			{7, "R6_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"},
+			{6, "R2", "pkt(r=8)"},
+			{7, "R6", "var_off=(0x0; 0x3fc)"},
 			/* Adding 14 makes R6 be (4n+2) */
-			{8, "R6_w=scalar(umin=14,umax=1034,var_off=(0x2; 0x7fc))"},
+			{8, "R6", "var_off=(0x2; 0x7fc)"},
 			/* Packet pointer has (4n+2) offset */
-			{11, "R5_w=pkt(id=1,off=0,r=0,umin=14,umax=1034,var_off=(0x2; 0x7fc)"},
-			{12, "R4=pkt(id=1,off=4,r=0,umin=14,umax=1034,var_off=(0x2; 0x7fc)"},
+			{11, "R5", "var_off=(0x2; 0x7fc)"},
+			{12, "R4", "var_off=(0x2; 0x7fc)"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (0)
 			 * which is 2.  Then the variable offset is (4n+2), so
 			 * the total offset is 4-byte aligned and meets the
 			 * load's requirements.
 			 */
-			{15, "R5=pkt(id=1,off=0,r=4,umin=14,umax=1034,var_off=(0x2; 0x7fc)"},
+			{15, "R5", "var_off=(0x2; 0x7fc)"},
 			/* Newly read value in R6 was shifted left by 2, so has
 			 * known alignment of 4.
 			 */
-			{17, "R6_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"},
+			{17, "R6", "var_off=(0x0; 0x3fc)"},
 			/* Added (4n) to packet pointer's (4n+2) var_off, giving
 			 * another (4n+2).
 			 */
-			{19, "R5_w=pkt(id=2,off=0,r=0,umin=14,umax=2054,var_off=(0x2; 0xffc)"},
-			{20, "R4=pkt(id=2,off=4,r=0,umin=14,umax=2054,var_off=(0x2; 0xffc)"},
+			{19, "R5", "var_off=(0x2; 0xffc)"},
+			{20, "R4", "var_off=(0x2; 0xffc)"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (0)
 			 * which is 2.  Then the variable offset is (4n+2), so
 			 * the total offset is 4-byte aligned and meets the
 			 * load's requirements.
 			 */
-			{23, "R5=pkt(id=2,off=0,r=4,umin=14,umax=2054,var_off=(0x2; 0xffc)"},
+			{23, "R5", "var_off=(0x2; 0xffc)"},
 		},
 	},
 	{
@@ -458,18 +459,18 @@ static struct bpf_align_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 		.result = REJECT,
 		.matches = {
-			{3, "R5_w=pkt_end(off=0,imm=0)"},
+			{3, "R5", "pkt_end()"},
 			/* (ptr - ptr) << 2 == unknown, (4n) */
-			{5, "R5_w=scalar(smax=9223372036854775804,umax=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc)"},
+			{5, "R5", "var_off=(0x0; 0xfffffffffffffffc)"},
 			/* (4n) + 14 == (4n+2).  We blow our bounds, because
 			 * the add could overflow.
 			 */
-			{6, "R5_w=scalar(smin=-9223372036854775806,smax=9223372036854775806,umin=2,umax=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"},
+			{6, "R5", "var_off=(0x2; 0xfffffffffffffffc)"},
 			/* Checked s>=0 */
-			{9, "R5=scalar(umin=2,umax=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
+			{9, "R5", "var_off=(0x2; 0x7ffffffffffffffc)"},
 			/* packet pointer + nonnegative (4n+2) */
-			{11, "R6_w=pkt(id=1,off=0,r=0,umin=2,umax=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
-			{12, "R4_w=pkt(id=1,off=4,r=0,umin=2,umax=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
+			{11, "R6", "var_off=(0x2; 0x7ffffffffffffffc)"},
+			{12, "R4", "var_off=(0x2; 0x7ffffffffffffffc)"},
 			/* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine.
 			 * We checked the bounds, but it might have been able
 			 * to overflow if the packet pointer started in the
@@ -477,7 +478,7 @@ static struct bpf_align_test tests[] = {
 			 * So we did not get a 'range' on R6, and the access
 			 * attempt will fail.
 			 */
-			{15, "R6_w=pkt(id=1,off=0,r=0,umin=2,umax=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
+			{15, "R6", "var_off=(0x2; 0x7ffffffffffffffc)"},
 		}
 	},
 	{
@@ -512,24 +513,23 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{6, "R2_w=pkt(off=0,r=8,imm=0)"},
-			{8, "R6_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"},
+			{6, "R2", "pkt(r=8)"},
+			{8, "R6", "var_off=(0x0; 0x3fc)"},
 			/* Adding 14 makes R6 be (4n+2) */
-			{9, "R6_w=scalar(umin=14,umax=1034,var_off=(0x2; 0x7fc))"},
+			{9, "R6", "var_off=(0x2; 0x7fc)"},
 			/* New unknown value in R7 is (4n) */
-			{10, "R7_w=scalar(umax=1020,var_off=(0x0; 0x3fc))"},
+			{10, "R7", "var_off=(0x0; 0x3fc)"},
 			/* Subtracting it from R6 blows our unsigned bounds */
-			{11, "R6=scalar(smin=-1006,smax=1034,umin=2,umax=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"},
+			{11, "R6", "var_off=(0x2; 0xfffffffffffffffc)"},
 			/* Checked s>= 0 */
-			{14, "R6=scalar(umin=2,umax=1034,var_off=(0x2; 0x7fc))"},
+			{14, "R6", "var_off=(0x2; 0x7fc)"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (0)
 			 * which is 2.  Then the variable offset is (4n+2), so
 			 * the total offset is 4-byte aligned and meets the
 			 * load's requirements.
 			 */
-			{20, "R5=pkt(id=2,off=0,r=4,umin=2,umax=1034,var_off=(0x2; 0x7fc)"},
-
+			{20, "R5", "var_off=(0x2; 0x7fc)"},
 		},
 	},
 	{
@@ -566,23 +566,23 @@ static struct bpf_align_test tests[] = {
 			/* Calculated offset in R6 has unknown value, but known
 			 * alignment of 4.
 			 */
-			{6, "R2_w=pkt(off=0,r=8,imm=0)"},
-			{9, "R6_w=scalar(umax=60,var_off=(0x0; 0x3c))"},
+			{6, "R2", "pkt(r=8)"},
+			{9, "R6", "var_off=(0x0; 0x3c)"},
 			/* Adding 14 makes R6 be (4n+2) */
-			{10, "R6_w=scalar(umin=14,umax=74,var_off=(0x2; 0x7c))"},
+			{10, "R6", "var_off=(0x2; 0x7c)"},
 			/* Subtracting from packet pointer overflows ubounds */
-			{13, "R5_w=pkt(id=2,off=0,r=8,umin=18446744073709551542,umax=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c)"},
+			{13, "R5", "var_off=(0xffffffffffffff82; 0x7c)"},
 			/* New unknown value in R7 is (4n), >= 76 */
-			{14, "R7_w=scalar(umin=76,umax=1096,var_off=(0x0; 0x7fc))"},
+			{14, "R7", "var_off=(0x0; 0x7fc)"},
 			/* Adding it to packet pointer gives nice bounds again */
-			{16, "R5_w=pkt(id=3,off=0,r=0,umin=2,umax=1082,var_off=(0x2; 0xfffffffc)"},
+			{16, "R5", "var_off=(0x2; 0x7fc)"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (0)
 			 * which is 2.  Then the variable offset is (4n+2), so
 			 * the total offset is 4-byte aligned and meets the
 			 * load's requirements.
 			 */
-			{20, "R5=pkt(id=3,off=0,r=4,umin=2,umax=1082,var_off=(0x2; 0xfffffffc)"},
+			{20, "R5", "var_off=(0x2; 0x7fc)"},
 		},
 	},
 };
@@ -610,9 +610,11 @@ static int do_test_single(struct bpf_align_test *test)
 		.log_size = sizeof(bpf_vlog),
 		.log_level = 2,
 	);
+	const char *main_pass_start = "0: R1=ctx() R10=fp0";
 	const char *line_ptr;
 	int cur_line = -1;
 	int prog_len, i;
+	char *start;
 	int fd_prog;
 	int ret;
 
@@ -632,9 +634,16 @@ static int do_test_single(struct bpf_align_test *test)
 		ret = 0;
 		/* We make a local copy so that we can strtok() it */
 		strncpy(bpf_vlog_copy, bpf_vlog, sizeof(bpf_vlog_copy));
-		line_ptr = strtok(bpf_vlog_copy, "\n");
+		start = strstr(bpf_vlog_copy, main_pass_start);
+		if (!start) {
+			ret = 1;
+			printf("Can't find initial line '%s'\n", main_pass_start);
+			goto out;
+		}
+		line_ptr = strtok(start, "\n");
 		for (i = 0; i < MAX_MATCHES; i++) {
 			struct bpf_reg_match m = test->matches[i];
+			const char *p;
 			int tmp;
 
 			if (!m.match)
@@ -649,8 +658,8 @@ static int do_test_single(struct bpf_align_test *test)
 				line_ptr = strtok(NULL, "\n");
 			}
 			if (!line_ptr) {
-				printf("Failed to find line %u for match: %s\n",
-				       m.line, m.match);
+				printf("Failed to find line %u for match: %s=%s\n",
+				       m.line, m.reg, m.match);
 				ret = 1;
 				printf("%s", bpf_vlog);
 				break;
@@ -658,23 +667,30 @@ static int do_test_single(struct bpf_align_test *test)
 			/* Check the next line as well in case the previous line
 			 * did not have a corresponding bpf insn. Example:
 			 * func#0 @0
-			 * 0: R1=ctx(off=0,imm=0) R10=fp0
+			 * 0: R1=ctx() R10=fp0
 			 * 0: (b7) r3 = 2                 ; R3_w=2
+			 *
+			 * Sometimes it's actually two lines below, e.g. when
+			 * searching for "6: R3_w=scalar(umax=255,var_off=(0x0; 0xff))":
+			 *   from 4 to 6: R0_w=pkt(off=8,r=8) R1=ctx() R2_w=pkt(r=8) R3_w=pkt_end() R10=fp0
+			 *   6: R0_w=pkt(off=8,r=8) R1=ctx() R2_w=pkt(r=8) R3_w=pkt_end() R10=fp0
+			 *   6: (71) r3 = *(u8 *)(r2 +0)           ; R2_w=pkt(r=8) R3_w=scalar(umax=255,var_off=(0x0; 0xff))
 			 */
-			if (!strstr(line_ptr, m.match)) {
+			while (!(p = strstr(line_ptr, m.reg)) || !strstr(p, m.match)) {
 				cur_line = -1;
 				line_ptr = strtok(NULL, "\n");
-				sscanf(line_ptr, "%u: ", &cur_line);
+				sscanf(line_ptr ?: "", "%u: ", &cur_line);
+				if (!line_ptr || cur_line != m.line)
+					break;
 			}
-			if (cur_line != m.line || !line_ptr ||
-			    !strstr(line_ptr, m.match)) {
-				printf("Failed to find match %u: %s\n",
-				       m.line, m.match);
+			if (cur_line != m.line || !line_ptr || !(p = strstr(line_ptr, m.reg)) || !strstr(p, m.match)) {
+				printf("Failed to find match %u: %s=%s\n", m.line, m.reg, m.match);
 				ret = 1;
 				printf("%s", bpf_vlog);
 				break;
 			}
 		}
+out:
 		if (fd_prog >= 0)
 			close(fd_prog);
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/arena_atomics.c b/tools/testing/selftests/bpf/prog_tests/arena_atomics.c
new file mode 100644
index 000000000000..d98577a6babc
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/arena_atomics.c
@@ -0,0 +1,268 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include "arena_atomics.skel.h"
+
+static void test_add(struct arena_atomics *skel)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	int err, prog_fd;
+
+	/* No need to attach it, just run it directly */
+	prog_fd = bpf_program__fd(skel->progs.add);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	if (!ASSERT_OK(err, "test_run_opts err"))
+		return;
+	if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+		return;
+
+	ASSERT_EQ(skel->arena->add64_value, 3, "add64_value");
+	ASSERT_EQ(skel->arena->add64_result, 1, "add64_result");
+
+	ASSERT_EQ(skel->arena->add32_value, 3, "add32_value");
+	ASSERT_EQ(skel->arena->add32_result, 1, "add32_result");
+
+	ASSERT_EQ(skel->arena->add_stack_value_copy, 3, "add_stack_value");
+	ASSERT_EQ(skel->arena->add_stack_result, 1, "add_stack_result");
+
+	ASSERT_EQ(skel->arena->add_noreturn_value, 3, "add_noreturn_value");
+}
+
+static void test_sub(struct arena_atomics *skel)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	int err, prog_fd;
+
+	/* No need to attach it, just run it directly */
+	prog_fd = bpf_program__fd(skel->progs.sub);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	if (!ASSERT_OK(err, "test_run_opts err"))
+		return;
+	if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+		return;
+
+	ASSERT_EQ(skel->arena->sub64_value, -1, "sub64_value");
+	ASSERT_EQ(skel->arena->sub64_result, 1, "sub64_result");
+
+	ASSERT_EQ(skel->arena->sub32_value, -1, "sub32_value");
+	ASSERT_EQ(skel->arena->sub32_result, 1, "sub32_result");
+
+	ASSERT_EQ(skel->arena->sub_stack_value_copy, -1, "sub_stack_value");
+	ASSERT_EQ(skel->arena->sub_stack_result, 1, "sub_stack_result");
+
+	ASSERT_EQ(skel->arena->sub_noreturn_value, -1, "sub_noreturn_value");
+}
+
+static void test_and(struct arena_atomics *skel)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	int err, prog_fd;
+
+	/* No need to attach it, just run it directly */
+	prog_fd = bpf_program__fd(skel->progs.and);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	if (!ASSERT_OK(err, "test_run_opts err"))
+		return;
+	if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+		return;
+
+	ASSERT_EQ(skel->arena->and64_value, 0x010ull << 32, "and64_value");
+	ASSERT_EQ(skel->arena->and32_value, 0x010, "and32_value");
+}
+
+static void test_or(struct arena_atomics *skel)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	int err, prog_fd;
+
+	/* No need to attach it, just run it directly */
+	prog_fd = bpf_program__fd(skel->progs.or);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	if (!ASSERT_OK(err, "test_run_opts err"))
+		return;
+	if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+		return;
+
+	ASSERT_EQ(skel->arena->or64_value, 0x111ull << 32, "or64_value");
+	ASSERT_EQ(skel->arena->or32_value, 0x111, "or32_value");
+}
+
+static void test_xor(struct arena_atomics *skel)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	int err, prog_fd;
+
+	/* No need to attach it, just run it directly */
+	prog_fd = bpf_program__fd(skel->progs.xor);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	if (!ASSERT_OK(err, "test_run_opts err"))
+		return;
+	if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+		return;
+
+	ASSERT_EQ(skel->arena->xor64_value, 0x101ull << 32, "xor64_value");
+	ASSERT_EQ(skel->arena->xor32_value, 0x101, "xor32_value");
+}
+
+static void test_cmpxchg(struct arena_atomics *skel)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	int err, prog_fd;
+
+	/* No need to attach it, just run it directly */
+	prog_fd = bpf_program__fd(skel->progs.cmpxchg);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	if (!ASSERT_OK(err, "test_run_opts err"))
+		return;
+	if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+		return;
+
+	ASSERT_EQ(skel->arena->cmpxchg64_value, 2, "cmpxchg64_value");
+	ASSERT_EQ(skel->arena->cmpxchg64_result_fail, 1, "cmpxchg_result_fail");
+	ASSERT_EQ(skel->arena->cmpxchg64_result_succeed, 1, "cmpxchg_result_succeed");
+
+	ASSERT_EQ(skel->arena->cmpxchg32_value, 2, "lcmpxchg32_value");
+	ASSERT_EQ(skel->arena->cmpxchg32_result_fail, 1, "cmpxchg_result_fail");
+	ASSERT_EQ(skel->arena->cmpxchg32_result_succeed, 1, "cmpxchg_result_succeed");
+}
+
+static void test_xchg(struct arena_atomics *skel)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	int err, prog_fd;
+
+	/* No need to attach it, just run it directly */
+	prog_fd = bpf_program__fd(skel->progs.xchg);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	if (!ASSERT_OK(err, "test_run_opts err"))
+		return;
+	if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+		return;
+
+	ASSERT_EQ(skel->arena->xchg64_value, 2, "xchg64_value");
+	ASSERT_EQ(skel->arena->xchg64_result, 1, "xchg64_result");
+
+	ASSERT_EQ(skel->arena->xchg32_value, 2, "xchg32_value");
+	ASSERT_EQ(skel->arena->xchg32_result, 1, "xchg32_result");
+}
+
+static void test_uaf(struct arena_atomics *skel)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	int err, prog_fd;
+
+	/* No need to attach it, just run it directly */
+	prog_fd = bpf_program__fd(skel->progs.uaf);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	if (!ASSERT_OK(err, "test_run_opts err"))
+		return;
+	if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+		return;
+
+	ASSERT_EQ(skel->arena->uaf_recovery_fails, 0, "uaf_recovery_fails");
+}
+
+static void test_load_acquire(struct arena_atomics *skel)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	int err, prog_fd;
+
+	if (skel->data->skip_lacq_srel_tests) {
+		printf("%s:SKIP: ENABLE_ATOMICS_TESTS not defined, Clang doesn't support addr_space_cast, and/or JIT doesn't support load-acquire\n",
+		       __func__);
+		test__skip();
+		return;
+	}
+
+	/* No need to attach it, just run it directly */
+	prog_fd = bpf_program__fd(skel->progs.load_acquire);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	if (!ASSERT_OK(err, "test_run_opts err"))
+		return;
+	if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+		return;
+
+	ASSERT_EQ(skel->arena->load_acquire8_result, 0x12,
+		  "load_acquire8_result");
+	ASSERT_EQ(skel->arena->load_acquire16_result, 0x1234,
+		  "load_acquire16_result");
+	ASSERT_EQ(skel->arena->load_acquire32_result, 0x12345678,
+		  "load_acquire32_result");
+	ASSERT_EQ(skel->arena->load_acquire64_result, 0x1234567890abcdef,
+		  "load_acquire64_result");
+}
+
+static void test_store_release(struct arena_atomics *skel)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	int err, prog_fd;
+
+	if (skel->data->skip_lacq_srel_tests) {
+		printf("%s:SKIP: ENABLE_ATOMICS_TESTS not defined, Clang doesn't support addr_space_cast, and/or JIT doesn't support store-release\n",
+		       __func__);
+		test__skip();
+		return;
+	}
+
+	/* No need to attach it, just run it directly */
+	prog_fd = bpf_program__fd(skel->progs.store_release);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	if (!ASSERT_OK(err, "test_run_opts err"))
+		return;
+	if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+		return;
+
+	ASSERT_EQ(skel->arena->store_release8_result, 0x12,
+		  "store_release8_result");
+	ASSERT_EQ(skel->arena->store_release16_result, 0x1234,
+		  "store_release16_result");
+	ASSERT_EQ(skel->arena->store_release32_result, 0x12345678,
+		  "store_release32_result");
+	ASSERT_EQ(skel->arena->store_release64_result, 0x1234567890abcdef,
+		  "store_release64_result");
+}
+
+void test_arena_atomics(void)
+{
+	struct arena_atomics *skel;
+	int err;
+
+	skel = arena_atomics__open();
+	if (!ASSERT_OK_PTR(skel, "arena atomics skeleton open"))
+		return;
+
+	if (skel->data->skip_all_tests) {
+		printf("%s:SKIP:no ENABLE_ATOMICS_TESTS or no addr_space_cast support in clang",
+		       __func__);
+		test__skip();
+		goto cleanup;
+	}
+	err = arena_atomics__load(skel);
+	if (!ASSERT_OK(err, "arena atomics skeleton load"))
+		return;
+	skel->bss->pid = getpid();
+
+	if (test__start_subtest("add"))
+		test_add(skel);
+	if (test__start_subtest("sub"))
+		test_sub(skel);
+	if (test__start_subtest("and"))
+		test_and(skel);
+	if (test__start_subtest("or"))
+		test_or(skel);
+	if (test__start_subtest("xor"))
+		test_xor(skel);
+	if (test__start_subtest("cmpxchg"))
+		test_cmpxchg(skel);
+	if (test__start_subtest("xchg"))
+		test_xchg(skel);
+	if (test__start_subtest("uaf"))
+		test_uaf(skel);
+	if (test__start_subtest("load_acquire"))
+		test_load_acquire(skel);
+	if (test__start_subtest("store_release"))
+		test_store_release(skel);
+
+cleanup:
+	arena_atomics__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/arena_htab.c b/tools/testing/selftests/bpf/prog_tests/arena_htab.c
new file mode 100644
index 000000000000..d69fd2465f53
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/arena_htab.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <sys/mman.h>
+#include <network_helpers.h>
+#include <sys/user.h>
+#ifndef PAGE_SIZE /* on some archs it comes in sys/user.h */
+#include <unistd.h>
+#define PAGE_SIZE getpagesize()
+#endif
+#include "arena_htab_asm.skel.h"
+#include "arena_htab.skel.h"
+
+#include "bpf_arena_htab.h"
+
+static void test_arena_htab_common(struct htab *htab)
+{
+	int i;
+
+	printf("htab %p buckets %p n_buckets %d\n", htab, htab->buckets, htab->n_buckets);
+	ASSERT_OK_PTR(htab->buckets, "htab->buckets shouldn't be NULL");
+	for (i = 0; htab->buckets && i < 16; i += 4) {
+		/*
+		 * Walk htab buckets and link lists since all pointers are correct,
+		 * though they were written by bpf program.
+		 */
+		int val = htab_lookup_elem(htab, i);
+
+		ASSERT_EQ(i, val, "key == value");
+	}
+}
+
+static void test_arena_htab_llvm(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	struct arena_htab *skel;
+	struct htab *htab;
+	size_t arena_sz;
+	void *area;
+	int ret;
+
+	skel = arena_htab__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "arena_htab__open_and_load"))
+		return;
+
+	area = bpf_map__initial_value(skel->maps.arena, &arena_sz);
+	/* fault-in a page with pgoff == 0 as sanity check */
+	*(volatile int *)area = 0x55aa;
+
+	/* bpf prog will allocate more pages */
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.arena_htab_llvm), &opts);
+	ASSERT_OK(ret, "ret");
+	ASSERT_OK(opts.retval, "retval");
+	if (skel->bss->skip) {
+		printf("%s:SKIP:compiler doesn't support arena_cast\n", __func__);
+		test__skip();
+		goto out;
+	}
+	htab = skel->bss->htab_for_user;
+	test_arena_htab_common(htab);
+out:
+	arena_htab__destroy(skel);
+}
+
+static void test_arena_htab_asm(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	struct arena_htab_asm *skel;
+	struct htab *htab;
+	int ret;
+
+	skel = arena_htab_asm__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "arena_htab_asm__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.arena_htab_asm), &opts);
+	ASSERT_OK(ret, "ret");
+	ASSERT_OK(opts.retval, "retval");
+	htab = skel->bss->htab_for_user;
+	test_arena_htab_common(htab);
+	arena_htab_asm__destroy(skel);
+}
+
+void test_arena_htab(void)
+{
+	if (test__start_subtest("arena_htab_llvm"))
+		test_arena_htab_llvm();
+	if (test__start_subtest("arena_htab_asm"))
+		test_arena_htab_asm();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/arena_list.c b/tools/testing/selftests/bpf/prog_tests/arena_list.c
new file mode 100644
index 000000000000..d15867cddde0
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/arena_list.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <sys/mman.h>
+#include <network_helpers.h>
+#include <sys/user.h>
+#ifndef PAGE_SIZE /* on some archs it comes in sys/user.h */
+#include <unistd.h>
+#define PAGE_SIZE getpagesize()
+#endif
+
+#include "bpf_arena_list.h"
+#include "arena_list.skel.h"
+
+struct elem {
+	struct arena_list_node node;
+	__u64 value;
+};
+
+static int list_sum(struct arena_list_head *head)
+{
+	struct elem __arena *n;
+	int sum = 0;
+
+	list_for_each_entry(n, head, node)
+		sum += n->value;
+	return sum;
+}
+
+static void test_arena_list_add_del(int cnt)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	struct arena_list *skel;
+	int expected_sum = (u64)cnt * (cnt - 1) / 2;
+	int ret, sum;
+
+	skel = arena_list__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "arena_list__open_and_load"))
+		return;
+
+	skel->bss->cnt = cnt;
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.arena_list_add), &opts);
+	ASSERT_OK(ret, "ret_add");
+	ASSERT_OK(opts.retval, "retval");
+	if (skel->bss->skip) {
+		printf("%s:SKIP:compiler doesn't support arena_cast\n", __func__);
+		test__skip();
+		goto out;
+	}
+	sum = list_sum(skel->bss->list_head);
+	ASSERT_EQ(sum, expected_sum, "sum of elems");
+	ASSERT_EQ(skel->arena->arena_sum, expected_sum, "__arena sum of elems");
+	ASSERT_EQ(skel->arena->test_val, cnt + 1, "num of elems");
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.arena_list_del), &opts);
+	ASSERT_OK(ret, "ret_del");
+	sum = list_sum(skel->bss->list_head);
+	ASSERT_EQ(sum, 0, "sum of list elems after del");
+	ASSERT_EQ(skel->bss->list_sum, expected_sum, "sum of list elems computed by prog");
+	ASSERT_EQ(skel->arena->arena_sum, expected_sum, "__arena sum of elems");
+out:
+	arena_list__destroy(skel);
+}
+
+void test_arena_list(void)
+{
+	if (test__start_subtest("arena_list_1"))
+		test_arena_list_add_del(1);
+	if (test__start_subtest("arena_list_1000"))
+		test_arena_list_add_del(1000);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c b/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c
new file mode 100644
index 000000000000..693fd86fbde6
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/arena_spin_lock.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <network_helpers.h>
+#include <sys/sysinfo.h>
+
+struct __qspinlock { int val; };
+typedef struct __qspinlock arena_spinlock_t;
+
+struct arena_qnode {
+	unsigned long next;
+	int count;
+	int locked;
+};
+
+#include "arena_spin_lock.skel.h"
+
+static long cpu;
+static int repeat;
+
+pthread_barrier_t barrier;
+
+static void *spin_lock_thread(void *arg)
+{
+	int err, prog_fd = *(u32 *)arg;
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = repeat,
+	);
+	cpu_set_t cpuset;
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(__sync_fetch_and_add(&cpu, 1), &cpuset);
+	ASSERT_OK(pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset), "cpu affinity");
+
+	err = pthread_barrier_wait(&barrier);
+	if (err != PTHREAD_BARRIER_SERIAL_THREAD && err != 0)
+		ASSERT_FALSE(true, "pthread_barrier");
+
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run err");
+
+	if (topts.retval == -EOPNOTSUPP)
+		goto end;
+
+	ASSERT_EQ((int)topts.retval, 0, "test_run retval");
+
+end:
+	pthread_exit(arg);
+}
+
+static void test_arena_spin_lock_size(int size)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	struct arena_spin_lock *skel;
+	pthread_t thread_id[16];
+	int prog_fd, i, err;
+	int nthreads;
+	void *ret;
+
+	nthreads = MIN(get_nprocs(), ARRAY_SIZE(thread_id));
+	if (nthreads < 2) {
+		test__skip();
+		return;
+	}
+
+	skel = arena_spin_lock__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "arena_spin_lock__open_and_load"))
+		return;
+
+	if (skel->data->test_skip == 2) {
+		test__skip();
+		goto end;
+	}
+	skel->bss->cs_count = size;
+	skel->bss->limit = repeat * nthreads;
+
+	ASSERT_OK(pthread_barrier_init(&barrier, NULL, nthreads), "barrier init");
+
+	prog_fd = bpf_program__fd(skel->progs.prog);
+	for (i = 0; i < nthreads; i++) {
+		err = pthread_create(&thread_id[i], NULL, &spin_lock_thread, &prog_fd);
+		if (!ASSERT_OK(err, "pthread_create"))
+			goto end_barrier;
+	}
+
+	for (i = 0; i < nthreads; i++) {
+		if (!ASSERT_OK(pthread_join(thread_id[i], &ret), "pthread_join"))
+			goto end_barrier;
+		if (!ASSERT_EQ(ret, &prog_fd, "ret == prog_fd"))
+			goto end_barrier;
+	}
+
+	if (skel->data->test_skip == 3) {
+		printf("%s:SKIP: CONFIG_NR_CPUS exceed the maximum supported by arena spinlock\n",
+		       __func__);
+		test__skip();
+		goto end_barrier;
+	}
+
+	ASSERT_EQ(skel->bss->counter, repeat * nthreads, "check counter value");
+
+end_barrier:
+	pthread_barrier_destroy(&barrier);
+end:
+	arena_spin_lock__destroy(skel);
+	return;
+}
+
+void test_arena_spin_lock(void)
+{
+	repeat = 1000;
+	if (test__start_subtest("arena_spin_lock_1"))
+		test_arena_spin_lock_size(1);
+	cpu = 0;
+	if (test__start_subtest("arena_spin_lock_1000"))
+		test_arena_spin_lock_size(1000);
+	cpu = 0;
+	repeat = 100;
+	if (test__start_subtest("arena_spin_lock_50000"))
+		test_arena_spin_lock_size(50000);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/arena_strsearch.c b/tools/testing/selftests/bpf/prog_tests/arena_strsearch.c
new file mode 100644
index 000000000000..f81a0c066505
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/arena_strsearch.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include "arena_strsearch.skel.h"
+
+static void test_arena_str(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	struct arena_strsearch *skel;
+	int ret;
+
+	skel = arena_strsearch__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "arena_strsearch__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.arena_strsearch), &opts);
+	ASSERT_OK(ret, "ret_add");
+	ASSERT_OK(opts.retval, "retval");
+	if (skel->bss->skip) {
+		printf("%s:SKIP:compiler doesn't support arena_cast\n", __func__);
+		test__skip();
+	}
+	arena_strsearch__destroy(skel);
+}
+
+void test_arena_strsearch(void)
+{
+	if (test__start_subtest("arena_strsearch"))
+		test_arena_str();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/arg_parsing.c b/tools/testing/selftests/bpf/prog_tests/arg_parsing.c
index b17bfa0e0aac..e27d66b75fb1 100644
--- a/tools/testing/selftests/bpf/prog_tests/arg_parsing.c
+++ b/tools/testing/selftests/bpf/prog_tests/arg_parsing.c
@@ -96,12 +96,86 @@ static void test_parse_test_list(void)
 		goto error;
 	ASSERT_OK(strcmp("*bpf_cookie*", set.tests[0].name), "test name");
 	ASSERT_OK(strcmp("*trace*", set.tests[0].subtests[0]), "subtest name");
+	free_test_filter_set(&set);
+
+	ASSERT_OK(parse_test_list("t/subtest1,t/subtest2", &set, true),
+		  "parsing");
+	if (!ASSERT_EQ(set.cnt, 1, "count of test filters"))
+		goto error;
+	if (!ASSERT_OK_PTR(set.tests, "test filters initialized"))
+		goto error;
+	if (!ASSERT_EQ(set.tests[0].subtest_cnt, 2, "subtest filters count"))
+		goto error;
+	ASSERT_OK(strcmp("t", set.tests[0].name), "test name");
+	ASSERT_OK(strcmp("subtest1", set.tests[0].subtests[0]), "subtest name");
+	ASSERT_OK(strcmp("subtest2", set.tests[0].subtests[1]), "subtest name");
 error:
 	free_test_filter_set(&set);
 }
 
+static void test_parse_test_list_file(void)
+{
+	struct test_filter_set set;
+	char tmpfile[80];
+	FILE *fp;
+	int fd;
+
+	snprintf(tmpfile, sizeof(tmpfile), "/tmp/bpf_arg_parsing_test.XXXXXX");
+	fd = mkstemp(tmpfile);
+	if (!ASSERT_GE(fd, 0, "create tmp"))
+		return;
+
+	fp = fdopen(fd, "w");
+	if (!ASSERT_NEQ(fp, NULL, "fdopen tmp")) {
+		close(fd);
+		goto out_remove;
+	}
+
+	fprintf(fp, "# comment\n");
+	fprintf(fp, "  test_with_spaces    \n");
+	fprintf(fp, "testA/subtest    # comment\n");
+	fprintf(fp, "testB#comment with no space\n");
+	fprintf(fp, "testB # duplicate\n");
+	fprintf(fp, "testA/subtest # subtest duplicate\n");
+	fprintf(fp, "testA/subtest2\n");
+	fprintf(fp, "testC_no_eof_newline");
+	fflush(fp);
+
+	if (!ASSERT_OK(ferror(fp), "prepare tmp"))
+		goto out_fclose;
+
+	if (!ASSERT_OK(fsync(fileno(fp)), "fsync tmp"))
+		goto out_fclose;
+
+	init_test_filter_set(&set);
+
+	if (!ASSERT_OK(parse_test_list_file(tmpfile, &set, true), "parse file"))
+		goto out_fclose;
+
+	if (!ASSERT_EQ(set.cnt, 4, "test  count"))
+		goto out_free_set;
+
+	ASSERT_OK(strcmp("test_with_spaces", set.tests[0].name), "test 0 name");
+	ASSERT_EQ(set.tests[0].subtest_cnt, 0, "test 0 subtest count");
+	ASSERT_OK(strcmp("testA", set.tests[1].name), "test 1 name");
+	ASSERT_EQ(set.tests[1].subtest_cnt, 2, "test 1 subtest count");
+	ASSERT_OK(strcmp("subtest", set.tests[1].subtests[0]), "test 1 subtest 0");
+	ASSERT_OK(strcmp("subtest2", set.tests[1].subtests[1]), "test 1 subtest 1");
+	ASSERT_OK(strcmp("testB", set.tests[2].name), "test 2 name");
+	ASSERT_OK(strcmp("testC_no_eof_newline", set.tests[3].name), "test 3 name");
+
+out_free_set:
+	free_test_filter_set(&set);
+out_fclose:
+	fclose(fp);
+out_remove:
+	remove(tmpfile);
+}
+
 void test_arg_parsing(void)
 {
 	if (test__start_subtest("test_parse_test_list"))
 		test_parse_test_list();
+	if (test__start_subtest("test_parse_test_list_file"))
+		test_parse_test_list_file();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/assign_reuse.c b/tools/testing/selftests/bpf/prog_tests/assign_reuse.c
new file mode 100644
index 000000000000..989ee4d9785b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/assign_reuse.c
@@ -0,0 +1,199 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+#include <uapi/linux/if_link.h>
+#include <test_progs.h>
+
+#include <netinet/tcp.h>
+#include <netinet/udp.h>
+
+#include "network_helpers.h"
+#include "test_assign_reuse.skel.h"
+
+#define NS_TEST "assign_reuse"
+#define LOOPBACK 1
+#define PORT 4443
+
+static int attach_reuseport(int sock_fd, int prog_fd)
+{
+	return setsockopt(sock_fd, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF,
+			  &prog_fd, sizeof(prog_fd));
+}
+
+static __u64 cookie(int fd)
+{
+	__u64 cookie = 0;
+	socklen_t cookie_len = sizeof(cookie);
+	int ret;
+
+	ret = getsockopt(fd, SOL_SOCKET, SO_COOKIE, &cookie, &cookie_len);
+	ASSERT_OK(ret, "cookie");
+	ASSERT_GT(cookie, 0, "cookie_invalid");
+
+	return cookie;
+}
+
+static int echo_test_udp(int fd_sv)
+{
+	struct sockaddr_storage addr = {};
+	socklen_t len = sizeof(addr);
+	char buff[1] = {};
+	int fd_cl = -1, ret;
+
+	fd_cl = connect_to_fd(fd_sv, 100);
+	ASSERT_GT(fd_cl, 0, "create_client");
+	ASSERT_EQ(getsockname(fd_cl, (void *)&addr, &len), 0, "getsockname");
+
+	ASSERT_EQ(send(fd_cl, buff, sizeof(buff), 0), 1, "send_client");
+
+	ret = recv(fd_sv, buff, sizeof(buff), 0);
+	if (ret < 0) {
+		close(fd_cl);
+		return errno;
+	}
+
+	ASSERT_EQ(ret, 1, "recv_server");
+	ASSERT_EQ(sendto(fd_sv, buff, sizeof(buff), 0, (void *)&addr, len), 1, "send_server");
+	ASSERT_EQ(recv(fd_cl, buff, sizeof(buff), 0), 1, "recv_client");
+	close(fd_cl);
+	return 0;
+}
+
+static int echo_test_tcp(int fd_sv)
+{
+	char buff[1] = {};
+	int fd_cl = -1, fd_sv_cl = -1;
+
+	fd_cl = connect_to_fd(fd_sv, 100);
+	if (fd_cl < 0)
+		return errno;
+
+	fd_sv_cl = accept(fd_sv, NULL, NULL);
+	ASSERT_GE(fd_sv_cl, 0, "accept_fd");
+
+	ASSERT_EQ(send(fd_cl, buff, sizeof(buff), 0), 1, "send_client");
+	ASSERT_EQ(recv(fd_sv_cl, buff, sizeof(buff), 0), 1, "recv_server");
+	ASSERT_EQ(send(fd_sv_cl, buff, sizeof(buff), 0), 1, "send_server");
+	ASSERT_EQ(recv(fd_cl, buff, sizeof(buff), 0), 1, "recv_client");
+	close(fd_sv_cl);
+	close(fd_cl);
+	return 0;
+}
+
+void run_assign_reuse(int family, int sotype, const char *ip, __u16 port)
+{
+	DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook,
+		.ifindex = LOOPBACK,
+		.attach_point = BPF_TC_INGRESS,
+	);
+	DECLARE_LIBBPF_OPTS(bpf_tc_opts, tc_opts,
+		.handle = 1,
+		.priority = 1,
+	);
+	bool hook_created = false, tc_attached = false;
+	int ret, fd_tc, fd_accept, fd_drop, fd_map;
+	int *fd_sv = NULL;
+	__u64 fd_val;
+	struct test_assign_reuse *skel;
+	const int zero = 0;
+
+	skel = test_assign_reuse__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	skel->rodata->dest_port = port;
+
+	ret = test_assign_reuse__load(skel);
+	if (!ASSERT_OK(ret, "skel_load"))
+		goto cleanup;
+
+	ASSERT_EQ(skel->bss->sk_cookie_seen, 0, "cookie_init");
+
+	fd_tc = bpf_program__fd(skel->progs.tc_main);
+	fd_accept = bpf_program__fd(skel->progs.reuse_accept);
+	fd_drop = bpf_program__fd(skel->progs.reuse_drop);
+	fd_map = bpf_map__fd(skel->maps.sk_map);
+
+	fd_sv = start_reuseport_server(family, sotype, ip, port, 100, 1);
+	if (!ASSERT_NEQ(fd_sv, NULL, "start_reuseport_server"))
+		goto cleanup;
+
+	ret = attach_reuseport(*fd_sv, fd_drop);
+	if (!ASSERT_OK(ret, "attach_reuseport"))
+		goto cleanup;
+
+	fd_val = *fd_sv;
+	ret = bpf_map_update_elem(fd_map, &zero, &fd_val, BPF_NOEXIST);
+	if (!ASSERT_OK(ret, "bpf_sk_map"))
+		goto cleanup;
+
+	ret = bpf_tc_hook_create(&tc_hook);
+	if (ret == 0)
+		hook_created = true;
+	ret = ret == -EEXIST ? 0 : ret;
+	if (!ASSERT_OK(ret, "bpf_tc_hook_create"))
+		goto cleanup;
+
+	tc_opts.prog_fd = fd_tc;
+	ret = bpf_tc_attach(&tc_hook, &tc_opts);
+	if (!ASSERT_OK(ret, "bpf_tc_attach"))
+		goto cleanup;
+	tc_attached = true;
+
+	if (sotype == SOCK_STREAM)
+		ASSERT_EQ(echo_test_tcp(*fd_sv), ECONNREFUSED, "drop_tcp");
+	else
+		ASSERT_EQ(echo_test_udp(*fd_sv), EAGAIN, "drop_udp");
+	ASSERT_EQ(skel->bss->reuseport_executed, 1, "program executed once");
+
+	skel->bss->sk_cookie_seen = 0;
+	skel->bss->reuseport_executed = 0;
+	ASSERT_OK(attach_reuseport(*fd_sv, fd_accept), "attach_reuseport(accept)");
+
+	if (sotype == SOCK_STREAM)
+		ASSERT_EQ(echo_test_tcp(*fd_sv), 0, "echo_tcp");
+	else
+		ASSERT_EQ(echo_test_udp(*fd_sv), 0, "echo_udp");
+
+	ASSERT_EQ(skel->bss->sk_cookie_seen, cookie(*fd_sv),
+		  "cookie_mismatch");
+	ASSERT_EQ(skel->bss->reuseport_executed, 1, "program executed once");
+cleanup:
+	if (tc_attached) {
+		tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0;
+		ret = bpf_tc_detach(&tc_hook, &tc_opts);
+		ASSERT_OK(ret, "bpf_tc_detach");
+	}
+	if (hook_created) {
+		tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS;
+		bpf_tc_hook_destroy(&tc_hook);
+	}
+	test_assign_reuse__destroy(skel);
+	free_fds(fd_sv, 1);
+}
+
+void test_assign_reuse(void)
+{
+	struct nstoken *tok = NULL;
+
+	SYS(out, "ip netns add %s", NS_TEST);
+	SYS(cleanup, "ip -net %s link set dev lo up", NS_TEST);
+
+	tok = open_netns(NS_TEST);
+	if (!ASSERT_OK_PTR(tok, "netns token"))
+		return;
+
+	if (test__start_subtest("tcpv4"))
+		run_assign_reuse(AF_INET, SOCK_STREAM, "127.0.0.1", PORT);
+	if (test__start_subtest("tcpv6"))
+		run_assign_reuse(AF_INET6, SOCK_STREAM, "::1", PORT);
+	if (test__start_subtest("udpv4"))
+		run_assign_reuse(AF_INET, SOCK_DGRAM, "127.0.0.1", PORT);
+	if (test__start_subtest("udpv6"))
+		run_assign_reuse(AF_INET6, SOCK_DGRAM, "::1", PORT);
+
+cleanup:
+	close_netns(tok);
+	SYS_NOFAIL("ip netns delete %s", NS_TEST);
+out:
+	return;
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/async_stack_depth.c b/tools/testing/selftests/bpf/prog_tests/async_stack_depth.c
new file mode 100644
index 000000000000..118abc29b236
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/async_stack_depth.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+#include "async_stack_depth.skel.h"
+
+void test_async_stack_depth(void)
+{
+	RUN_TESTS(async_stack_depth);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/atomics.c b/tools/testing/selftests/bpf/prog_tests/atomics.c
index 13e101f370a1..92b5f378bfb8 100644
--- a/tools/testing/selftests/bpf/prog_tests/atomics.c
+++ b/tools/testing/selftests/bpf/prog_tests/atomics.c
@@ -165,11 +165,17 @@ static void test_xchg(struct atomics_lskel *skel)
 void test_atomics(void)
 {
 	struct atomics_lskel *skel;
+	int err;
 
-	skel = atomics_lskel__open_and_load();
-	if (!ASSERT_OK_PTR(skel, "atomics skeleton load"))
+	skel = atomics_lskel__open();
+	if (!ASSERT_OK_PTR(skel, "atomics skeleton open"))
 		return;
 
+	skel->keyring_id = KEY_SPEC_SESSION_KEYRING;
+	err = atomics_lskel__load(skel);
+	if (!ASSERT_OK(err, "atomics skeleton load"))
+		goto cleanup;
+
 	if (skel->data->skip_tests) {
 		printf("%s:SKIP:no ENABLE_ATOMICS_TESTS (missing Clang BPF atomics support)",
 		       __func__);
diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
index 9566d9d2f6ee..9e77e5da7097 100644
--- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c
+++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
@@ -1,6 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include "test_attach_kprobe_sleepable.skel.h"
+#include "test_attach_probe_manual.skel.h"
 #include "test_attach_probe.skel.h"
+#include "kprobe_write_ctx.skel.h"
 
 /* this is how USDT semaphore is actually defined, except volatile modifier */
 volatile unsigned short uprobe_ref_ctr __attribute__((unused)) __attribute((section(".probes")));
@@ -23,81 +26,54 @@ static noinline void trigger_func3(void)
 	asm volatile ("");
 }
 
+/* attach point for ref_ctr */
+static noinline void trigger_func4(void)
+{
+	asm volatile ("");
+}
+
 static char test_data[] = "test_data";
 
-void test_attach_probe(void)
+/* manual attach kprobe/kretprobe/uprobe/uretprobe testings */
+static void test_attach_probe_manual(enum probe_attach_mode attach_mode)
 {
 	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
+	DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, kprobe_opts);
 	struct bpf_link *kprobe_link, *kretprobe_link;
 	struct bpf_link *uprobe_link, *uretprobe_link;
-	struct test_attach_probe* skel;
-	ssize_t uprobe_offset, ref_ctr_offset;
-	struct bpf_link *uprobe_err_link;
-	bool legacy;
-	char *mem;
-
-	/* Check if new-style kprobe/uprobe API is supported.
-	 * Kernels that support new FD-based kprobe and uprobe BPF attachment
-	 * through perf_event_open() syscall expose
-	 * /sys/bus/event_source/devices/kprobe/type and
-	 * /sys/bus/event_source/devices/uprobe/type files, respectively. They
-	 * contain magic numbers that are passed as "type" field of
-	 * perf_event_attr. Lack of such file in the system indicates legacy
-	 * kernel with old-style kprobe/uprobe attach interface through
-	 * creating per-probe event through tracefs. For such cases
-	 * ref_ctr_offset feature is not supported, so we don't test it.
-	 */
-	legacy = access("/sys/bus/event_source/devices/kprobe/type", F_OK) != 0;
+	struct test_attach_probe_manual *skel;
+	ssize_t uprobe_offset;
 
-	uprobe_offset = get_uprobe_offset(&trigger_func);
-	if (!ASSERT_GE(uprobe_offset, 0, "uprobe_offset"))
-		return;
-
-	ref_ctr_offset = get_rel_offset((uintptr_t)&uprobe_ref_ctr);
-	if (!ASSERT_GE(ref_ctr_offset, 0, "ref_ctr_offset"))
+	skel = test_attach_probe_manual__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_kprobe_manual_open_and_load"))
 		return;
 
-	skel = test_attach_probe__open();
-	if (!ASSERT_OK_PTR(skel, "skel_open"))
-		return;
-
-	/* sleepable kprobe test case needs flags set before loading */
-	if (!ASSERT_OK(bpf_program__set_flags(skel->progs.handle_kprobe_sleepable,
-		BPF_F_SLEEPABLE), "kprobe_sleepable_flags"))
-		goto cleanup;
-
-	if (!ASSERT_OK(test_attach_probe__load(skel), "skel_load"))
-		goto cleanup;
-	if (!ASSERT_OK_PTR(skel->bss, "check_bss"))
+	uprobe_offset = get_uprobe_offset(&trigger_func);
+	if (!ASSERT_GE(uprobe_offset, 0, "uprobe_offset"))
 		goto cleanup;
 
 	/* manual-attach kprobe/kretprobe */
-	kprobe_link = bpf_program__attach_kprobe(skel->progs.handle_kprobe,
-						 false /* retprobe */,
-						 SYS_NANOSLEEP_KPROBE_NAME);
+	kprobe_opts.attach_mode = attach_mode;
+	kprobe_opts.retprobe = false;
+	kprobe_link = bpf_program__attach_kprobe_opts(skel->progs.handle_kprobe,
+						      SYS_NANOSLEEP_KPROBE_NAME,
+						      &kprobe_opts);
 	if (!ASSERT_OK_PTR(kprobe_link, "attach_kprobe"))
 		goto cleanup;
 	skel->links.handle_kprobe = kprobe_link;
 
-	kretprobe_link = bpf_program__attach_kprobe(skel->progs.handle_kretprobe,
-						    true /* retprobe */,
-						    SYS_NANOSLEEP_KPROBE_NAME);
+	kprobe_opts.retprobe = true;
+	kretprobe_link = bpf_program__attach_kprobe_opts(skel->progs.handle_kretprobe,
+							 SYS_NANOSLEEP_KPROBE_NAME,
+							 &kprobe_opts);
 	if (!ASSERT_OK_PTR(kretprobe_link, "attach_kretprobe"))
 		goto cleanup;
 	skel->links.handle_kretprobe = kretprobe_link;
 
-	/* auto-attachable kprobe and kretprobe */
-	skel->links.handle_kprobe_auto = bpf_program__attach(skel->progs.handle_kprobe_auto);
-	ASSERT_OK_PTR(skel->links.handle_kprobe_auto, "attach_kprobe_auto");
-
-	skel->links.handle_kretprobe_auto = bpf_program__attach(skel->progs.handle_kretprobe_auto);
-	ASSERT_OK_PTR(skel->links.handle_kretprobe_auto, "attach_kretprobe_auto");
-
-	if (!legacy)
-		ASSERT_EQ(uprobe_ref_ctr, 0, "uprobe_ref_ctr_before");
-
+	/* manual-attach uprobe/uretprobe */
+	uprobe_opts.attach_mode = attach_mode;
+	uprobe_opts.ref_ctr_offset = 0;
 	uprobe_opts.retprobe = false;
-	uprobe_opts.ref_ctr_offset = legacy ? 0 : ref_ctr_offset;
 	uprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe,
 						      0 /* self pid */,
 						      "/proc/self/exe",
@@ -107,12 +83,7 @@ void test_attach_probe(void)
 		goto cleanup;
 	skel->links.handle_uprobe = uprobe_link;
 
-	if (!legacy)
-		ASSERT_GT(uprobe_ref_ctr, 0, "uprobe_ref_ctr_after");
-
-	/* if uprobe uses ref_ctr, uretprobe has to use ref_ctr as well */
 	uprobe_opts.retprobe = true;
-	uprobe_opts.ref_ctr_offset = legacy ? 0 : ref_ctr_offset;
 	uretprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uretprobe,
 							 -1 /* any pid */,
 							 "/proc/self/exe",
@@ -121,12 +92,7 @@ void test_attach_probe(void)
 		goto cleanup;
 	skel->links.handle_uretprobe = uretprobe_link;
 
-	/* verify auto-attach fails for old-style uprobe definition */
-	uprobe_err_link = bpf_program__attach(skel->progs.handle_uprobe_byname);
-	if (!ASSERT_EQ(libbpf_get_error(uprobe_err_link), -EOPNOTSUPP,
-		       "auto-attach should fail for old-style name"))
-		goto cleanup;
-
+	/* attach uprobe by function name manually */
 	uprobe_opts.func_name = "trigger_func2";
 	uprobe_opts.retprobe = false;
 	uprobe_opts.ref_ctr_offset = 0;
@@ -138,16 +104,172 @@ void test_attach_probe(void)
 	if (!ASSERT_OK_PTR(skel->links.handle_uprobe_byname, "attach_uprobe_byname"))
 		goto cleanup;
 
+	/* trigger & validate kprobe && kretprobe */
+	usleep(1);
+
+	/* trigger & validate uprobe & uretprobe */
+	trigger_func();
+
+	/* trigger & validate uprobe attached by name */
+	trigger_func2();
+
+	ASSERT_EQ(skel->bss->kprobe_res, 1, "check_kprobe_res");
+	ASSERT_EQ(skel->bss->kretprobe_res, 2, "check_kretprobe_res");
+	ASSERT_EQ(skel->bss->uprobe_res, 3, "check_uprobe_res");
+	ASSERT_EQ(skel->bss->uretprobe_res, 4, "check_uretprobe_res");
+	ASSERT_EQ(skel->bss->uprobe_byname_res, 5, "check_uprobe_byname_res");
+
+cleanup:
+	test_attach_probe_manual__destroy(skel);
+}
+
+/* attach uprobe/uretprobe long event name testings */
+static void test_attach_uprobe_long_event_name(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
+	struct bpf_link *uprobe_link, *uretprobe_link;
+	struct test_attach_probe_manual *skel;
+	ssize_t uprobe_offset;
+	char path[PATH_MAX] = {0};
+
+	skel = test_attach_probe_manual__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_kprobe_manual_open_and_load"))
+		return;
+
+	uprobe_offset = get_uprobe_offset(&trigger_func);
+	if (!ASSERT_GE(uprobe_offset, 0, "uprobe_offset"))
+		goto cleanup;
+
+	if (!ASSERT_GT(readlink("/proc/self/exe", path, PATH_MAX - 1), 0, "readlink"))
+		goto cleanup;
+
+	/* manual-attach uprobe/uretprobe */
+	uprobe_opts.attach_mode = PROBE_ATTACH_MODE_LEGACY;
+	uprobe_opts.ref_ctr_offset = 0;
+	uprobe_opts.retprobe = false;
+	uprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe,
+						      0 /* self pid */,
+						      path,
+						      uprobe_offset,
+						      &uprobe_opts);
+	if (!ASSERT_OK_PTR(uprobe_link, "attach_uprobe_long_event_name"))
+		goto cleanup;
+	skel->links.handle_uprobe = uprobe_link;
+
+	uprobe_opts.retprobe = true;
+	uretprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uretprobe,
+							 -1 /* any pid */,
+							 path,
+							 uprobe_offset, &uprobe_opts);
+	if (!ASSERT_OK_PTR(uretprobe_link, "attach_uretprobe_long_event_name"))
+		goto cleanup;
+	skel->links.handle_uretprobe = uretprobe_link;
+
+cleanup:
+	test_attach_probe_manual__destroy(skel);
+}
+
+/* attach kprobe/kretprobe long event name testings */
+static void test_attach_kprobe_long_event_name(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, kprobe_opts);
+	struct bpf_link *kprobe_link, *kretprobe_link;
+	struct test_attach_probe_manual *skel;
+
+	skel = test_attach_probe_manual__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_kprobe_manual_open_and_load"))
+		return;
+
+	/* manual-attach kprobe/kretprobe */
+	kprobe_opts.attach_mode = PROBE_ATTACH_MODE_LEGACY;
+	kprobe_opts.retprobe = false;
+	kprobe_link = bpf_program__attach_kprobe_opts(skel->progs.handle_kprobe,
+						      "bpf_testmod_looooooooooooooooooooooooooooooong_name",
+						      &kprobe_opts);
+	if (!ASSERT_OK_PTR(kprobe_link, "attach_kprobe_long_event_name"))
+		goto cleanup;
+	skel->links.handle_kprobe = kprobe_link;
+
+	kprobe_opts.retprobe = true;
+	kretprobe_link = bpf_program__attach_kprobe_opts(skel->progs.handle_kretprobe,
+							 "bpf_testmod_looooooooooooooooooooooooooooooong_name",
+							 &kprobe_opts);
+	if (!ASSERT_OK_PTR(kretprobe_link, "attach_kretprobe_long_event_name"))
+		goto cleanup;
+	skel->links.handle_kretprobe = kretprobe_link;
+
+cleanup:
+	test_attach_probe_manual__destroy(skel);
+}
+
+#ifdef __x86_64__
+/* attach kprobe/kretprobe long event name testings */
+static void test_attach_kprobe_write_ctx(void)
+{
+	struct kprobe_write_ctx *skel = NULL;
+	struct bpf_link *link = NULL;
+
+	skel = kprobe_write_ctx__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "kprobe_write_ctx__open_and_load"))
+		return;
+
+	link = bpf_program__attach_kprobe_opts(skel->progs.kprobe_write_ctx,
+					     "bpf_fentry_test1", NULL);
+	if (!ASSERT_ERR_PTR(link, "bpf_program__attach_kprobe_opts"))
+		bpf_link__destroy(link);
+
+	kprobe_write_ctx__destroy(skel);
+}
+#else
+static void test_attach_kprobe_write_ctx(void)
+{
+	test__skip();
+}
+#endif
+
+static void test_attach_probe_auto(struct test_attach_probe *skel)
+{
+	struct bpf_link *uprobe_err_link;
+
+	/* auto-attachable kprobe and kretprobe */
+	skel->links.handle_kprobe_auto = bpf_program__attach(skel->progs.handle_kprobe_auto);
+	ASSERT_OK_PTR(skel->links.handle_kprobe_auto, "attach_kprobe_auto");
+
+	skel->links.handle_kretprobe_auto = bpf_program__attach(skel->progs.handle_kretprobe_auto);
+	ASSERT_OK_PTR(skel->links.handle_kretprobe_auto, "attach_kretprobe_auto");
+
+	/* verify auto-attach fails for old-style uprobe definition */
+	uprobe_err_link = bpf_program__attach(skel->progs.handle_uprobe_byname);
+	if (!ASSERT_EQ(libbpf_get_error(uprobe_err_link), -EOPNOTSUPP,
+		       "auto-attach should fail for old-style name"))
+		return;
+
 	/* verify auto-attach works */
 	skel->links.handle_uretprobe_byname =
 			bpf_program__attach(skel->progs.handle_uretprobe_byname);
 	if (!ASSERT_OK_PTR(skel->links.handle_uretprobe_byname, "attach_uretprobe_byname"))
-		goto cleanup;
+		return;
+
+	/* trigger & validate kprobe && kretprobe */
+	usleep(1);
+
+	/* trigger & validate uprobe attached by name */
+	trigger_func2();
+
+	ASSERT_EQ(skel->bss->kprobe2_res, 11, "check_kprobe_auto_res");
+	ASSERT_EQ(skel->bss->kretprobe2_res, 22, "check_kretprobe_auto_res");
+	ASSERT_EQ(skel->bss->uretprobe_byname_res, 6, "check_uretprobe_byname_res");
+}
+
+static void test_uprobe_lib(struct test_attach_probe *skel)
+{
+	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
+	FILE *devnull;
 
 	/* test attach by name for a library function, using the library
 	 * as the binary argument. libc.so.6 will be resolved via dlopen()/dlinfo().
 	 */
-	uprobe_opts.func_name = "malloc";
+	uprobe_opts.func_name = "fopen";
 	uprobe_opts.retprobe = false;
 	skel->links.handle_uprobe_byname2 =
 			bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe_byname2,
@@ -155,9 +277,9 @@ void test_attach_probe(void)
 							"libc.so.6",
 							0, &uprobe_opts);
 	if (!ASSERT_OK_PTR(skel->links.handle_uprobe_byname2, "attach_uprobe_byname2"))
-		goto cleanup;
+		return;
 
-	uprobe_opts.func_name = "free";
+	uprobe_opts.func_name = "fclose";
 	uprobe_opts.retprobe = true;
 	skel->links.handle_uretprobe_byname2 =
 			bpf_program__attach_uprobe_opts(skel->progs.handle_uretprobe_byname2,
@@ -165,62 +287,153 @@ void test_attach_probe(void)
 							"libc.so.6",
 							0, &uprobe_opts);
 	if (!ASSERT_OK_PTR(skel->links.handle_uretprobe_byname2, "attach_uretprobe_byname2"))
+		return;
+
+	/* trigger & validate shared library u[ret]probes attached by name */
+	devnull = fopen("/dev/null", "r");
+	fclose(devnull);
+
+	ASSERT_EQ(skel->bss->uprobe_byname2_res, 7, "check_uprobe_byname2_res");
+	ASSERT_EQ(skel->bss->uretprobe_byname2_res, 8, "check_uretprobe_byname2_res");
+}
+
+static void test_uprobe_ref_ctr(struct test_attach_probe *skel)
+{
+	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
+	struct bpf_link *uprobe_link, *uretprobe_link;
+	ssize_t uprobe_offset, ref_ctr_offset;
+
+	uprobe_offset = get_uprobe_offset(&trigger_func4);
+	if (!ASSERT_GE(uprobe_offset, 0, "uprobe_offset_ref_ctr"))
+		return;
+
+	ref_ctr_offset = get_rel_offset((uintptr_t)&uprobe_ref_ctr);
+	if (!ASSERT_GE(ref_ctr_offset, 0, "ref_ctr_offset"))
+		return;
+
+	ASSERT_EQ(uprobe_ref_ctr, 0, "uprobe_ref_ctr_before");
+
+	uprobe_opts.retprobe = false;
+	uprobe_opts.ref_ctr_offset = ref_ctr_offset;
+	uprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe_ref_ctr,
+						      0 /* self pid */,
+						      "/proc/self/exe",
+						      uprobe_offset,
+						      &uprobe_opts);
+	if (!ASSERT_OK_PTR(uprobe_link, "attach_uprobe_ref_ctr"))
+		return;
+	skel->links.handle_uprobe_ref_ctr = uprobe_link;
+
+	ASSERT_GT(uprobe_ref_ctr, 0, "uprobe_ref_ctr_after");
+
+	/* if uprobe uses ref_ctr, uretprobe has to use ref_ctr as well */
+	uprobe_opts.retprobe = true;
+	uprobe_opts.ref_ctr_offset = ref_ctr_offset;
+	uretprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uretprobe_ref_ctr,
+							 -1 /* any pid */,
+							 "/proc/self/exe",
+							 uprobe_offset, &uprobe_opts);
+	if (!ASSERT_OK_PTR(uretprobe_link, "attach_uretprobe_ref_ctr"))
+		return;
+	skel->links.handle_uretprobe_ref_ctr = uretprobe_link;
+}
+
+static void test_kprobe_sleepable(void)
+{
+	struct test_attach_kprobe_sleepable *skel;
+
+	skel = test_attach_kprobe_sleepable__open();
+	if (!ASSERT_OK_PTR(skel, "skel_kprobe_sleepable_open"))
+		return;
+
+	/* sleepable kprobe test case needs flags set before loading */
+	if (!ASSERT_OK(bpf_program__set_flags(skel->progs.handle_kprobe_sleepable,
+		BPF_F_SLEEPABLE), "kprobe_sleepable_flags"))
+		goto cleanup;
+
+	if (!ASSERT_OK(test_attach_kprobe_sleepable__load(skel),
+		       "skel_kprobe_sleepable_load"))
 		goto cleanup;
 
 	/* sleepable kprobes should not attach successfully */
 	skel->links.handle_kprobe_sleepable = bpf_program__attach(skel->progs.handle_kprobe_sleepable);
-	if (!ASSERT_ERR_PTR(skel->links.handle_kprobe_sleepable, "attach_kprobe_sleepable"))
-		goto cleanup;
+	ASSERT_ERR_PTR(skel->links.handle_kprobe_sleepable, "attach_kprobe_sleepable");
 
+cleanup:
+	test_attach_kprobe_sleepable__destroy(skel);
+}
+
+static void test_uprobe_sleepable(struct test_attach_probe *skel)
+{
 	/* test sleepable uprobe and uretprobe variants */
 	skel->links.handle_uprobe_byname3_sleepable = bpf_program__attach(skel->progs.handle_uprobe_byname3_sleepable);
 	if (!ASSERT_OK_PTR(skel->links.handle_uprobe_byname3_sleepable, "attach_uprobe_byname3_sleepable"))
-		goto cleanup;
+		return;
 
 	skel->links.handle_uprobe_byname3 = bpf_program__attach(skel->progs.handle_uprobe_byname3);
 	if (!ASSERT_OK_PTR(skel->links.handle_uprobe_byname3, "attach_uprobe_byname3"))
-		goto cleanup;
+		return;
 
 	skel->links.handle_uretprobe_byname3_sleepable = bpf_program__attach(skel->progs.handle_uretprobe_byname3_sleepable);
 	if (!ASSERT_OK_PTR(skel->links.handle_uretprobe_byname3_sleepable, "attach_uretprobe_byname3_sleepable"))
-		goto cleanup;
+		return;
 
 	skel->links.handle_uretprobe_byname3 = bpf_program__attach(skel->progs.handle_uretprobe_byname3);
 	if (!ASSERT_OK_PTR(skel->links.handle_uretprobe_byname3, "attach_uretprobe_byname3"))
-		goto cleanup;
+		return;
 
 	skel->bss->user_ptr = test_data;
 
-	/* trigger & validate kprobe && kretprobe */
-	usleep(1);
+	/* trigger & validate sleepable uprobe attached by name */
+	trigger_func3();
 
-	/* trigger & validate shared library u[ret]probes attached by name */
-	mem = malloc(1);
-	free(mem);
+	ASSERT_EQ(skel->bss->uprobe_byname3_sleepable_res, 9, "check_uprobe_byname3_sleepable_res");
+	ASSERT_EQ(skel->bss->uprobe_byname3_str_sleepable_res, 10, "check_uprobe_byname3_str_sleepable_res");
+	ASSERT_EQ(skel->bss->uprobe_byname3_res, 11, "check_uprobe_byname3_res");
+	ASSERT_EQ(skel->bss->uretprobe_byname3_sleepable_res, 12, "check_uretprobe_byname3_sleepable_res");
+	ASSERT_EQ(skel->bss->uretprobe_byname3_str_sleepable_res, 13, "check_uretprobe_byname3_str_sleepable_res");
+	ASSERT_EQ(skel->bss->uretprobe_byname3_res, 14, "check_uretprobe_byname3_res");
+}
 
-	/* trigger & validate uprobe & uretprobe */
-	trigger_func();
+void test_attach_probe(void)
+{
+	struct test_attach_probe *skel;
 
-	/* trigger & validate uprobe attached by name */
-	trigger_func2();
+	skel = test_attach_probe__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
 
-	/* trigger & validate sleepable uprobe attached by name */
-	trigger_func3();
+	if (!ASSERT_OK(test_attach_probe__load(skel), "skel_load"))
+		goto cleanup;
+	if (!ASSERT_OK_PTR(skel->bss, "check_bss"))
+		goto cleanup;
 
-	ASSERT_EQ(skel->bss->kprobe_res, 1, "check_kprobe_res");
-	ASSERT_EQ(skel->bss->kprobe2_res, 11, "check_kprobe_auto_res");
-	ASSERT_EQ(skel->bss->kretprobe_res, 2, "check_kretprobe_res");
-	ASSERT_EQ(skel->bss->kretprobe2_res, 22, "check_kretprobe_auto_res");
-	ASSERT_EQ(skel->bss->uprobe_res, 3, "check_uprobe_res");
-	ASSERT_EQ(skel->bss->uretprobe_res, 4, "check_uretprobe_res");
-	ASSERT_EQ(skel->bss->uprobe_byname_res, 5, "check_uprobe_byname_res");
-	ASSERT_EQ(skel->bss->uretprobe_byname_res, 6, "check_uretprobe_byname_res");
-	ASSERT_EQ(skel->bss->uprobe_byname2_res, 7, "check_uprobe_byname2_res");
-	ASSERT_EQ(skel->bss->uretprobe_byname2_res, 8, "check_uretprobe_byname2_res");
-	ASSERT_EQ(skel->bss->uprobe_byname3_sleepable_res, 9, "check_uprobe_byname3_sleepable_res");
-	ASSERT_EQ(skel->bss->uprobe_byname3_res, 10, "check_uprobe_byname3_res");
-	ASSERT_EQ(skel->bss->uretprobe_byname3_sleepable_res, 11, "check_uretprobe_byname3_sleepable_res");
-	ASSERT_EQ(skel->bss->uretprobe_byname3_res, 12, "check_uretprobe_byname3_res");
+	if (test__start_subtest("manual-default"))
+		test_attach_probe_manual(PROBE_ATTACH_MODE_DEFAULT);
+	if (test__start_subtest("manual-legacy"))
+		test_attach_probe_manual(PROBE_ATTACH_MODE_LEGACY);
+	if (test__start_subtest("manual-perf"))
+		test_attach_probe_manual(PROBE_ATTACH_MODE_PERF);
+	if (test__start_subtest("manual-link"))
+		test_attach_probe_manual(PROBE_ATTACH_MODE_LINK);
+
+	if (test__start_subtest("auto"))
+		test_attach_probe_auto(skel);
+	if (test__start_subtest("kprobe-sleepable"))
+		test_kprobe_sleepable();
+	if (test__start_subtest("uprobe-lib"))
+		test_uprobe_lib(skel);
+	if (test__start_subtest("uprobe-sleepable"))
+		test_uprobe_sleepable(skel);
+	if (test__start_subtest("uprobe-ref_ctr"))
+		test_uprobe_ref_ctr(skel);
+
+	if (test__start_subtest("uprobe-long_name"))
+		test_attach_uprobe_long_event_name();
+	if (test__start_subtest("kprobe-long_name"))
+		test_attach_kprobe_long_event_name();
+	if (test__start_subtest("kprobe-write-ctx"))
+		test_attach_kprobe_write_ctx();
 
 cleanup:
 	test_attach_probe__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/bad_struct_ops.c b/tools/testing/selftests/bpf/prog_tests/bad_struct_ops.c
new file mode 100644
index 000000000000..6a707213e46b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bad_struct_ops.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "bad_struct_ops.skel.h"
+#include "bad_struct_ops2.skel.h"
+
+static void invalid_prog_reuse(void)
+{
+	struct bad_struct_ops *skel;
+	char *log = NULL;
+	int err;
+
+	skel = bad_struct_ops__open();
+	if (!ASSERT_OK_PTR(skel, "bad_struct_ops__open"))
+		return;
+
+	if (start_libbpf_log_capture())
+		goto cleanup;
+
+	err = bad_struct_ops__load(skel);
+	log = stop_libbpf_log_capture();
+	ASSERT_ERR(err, "bad_struct_ops__load should fail");
+	ASSERT_HAS_SUBSTR(log,
+		"struct_ops init_kern testmod_2 func ptr test_1: invalid reuse of prog test_1",
+		"expected init_kern message");
+
+cleanup:
+	free(log);
+	bad_struct_ops__destroy(skel);
+}
+
+static void unused_program(void)
+{
+	struct bad_struct_ops2 *skel;
+	char *log = NULL;
+	int err;
+
+	skel = bad_struct_ops2__open();
+	if (!ASSERT_OK_PTR(skel, "bad_struct_ops2__open"))
+		return;
+
+	/* struct_ops programs not referenced from any maps are open
+	 * with autoload set to true.
+	 */
+	ASSERT_TRUE(bpf_program__autoload(skel->progs.foo), "foo autoload == true");
+
+	if (start_libbpf_log_capture())
+		goto cleanup;
+
+	err = bad_struct_ops2__load(skel);
+	ASSERT_ERR(err, "bad_struct_ops2__load should fail");
+	log = stop_libbpf_log_capture();
+	ASSERT_HAS_SUBSTR(log, "prog 'foo': failed to load",
+			  "message about 'foo' failing to load");
+
+cleanup:
+	free(log);
+	bad_struct_ops2__destroy(skel);
+}
+
+void test_bad_struct_ops(void)
+{
+	if (test__start_subtest("invalid_prog_reuse"))
+		invalid_prog_reuse();
+	if (test__start_subtest("unused_program"))
+		unused_program();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/bind_perm.c b/tools/testing/selftests/bpf/prog_tests/bind_perm.c
index a1766a298bb7..f7cd129cb82b 100644
--- a/tools/testing/selftests/bpf/prog_tests/bind_perm.c
+++ b/tools/testing/selftests/bpf/prog_tests/bind_perm.c
@@ -9,8 +9,6 @@
 #include "cap_helpers.h"
 #include "bind_perm.skel.h"
 
-static int duration;
-
 static int create_netns(void)
 {
 	if (!ASSERT_OK(unshare(CLONE_NEWNET), "create netns"))
@@ -27,7 +25,7 @@ void try_bind(int family, int port, int expected_errno)
 	int fd = -1;
 
 	fd = socket(family, SOCK_STREAM, 0);
-	if (CHECK(fd < 0, "fd", "errno %d", errno))
+	if (!ASSERT_GE(fd, 0, "socket"))
 		goto close_socket;
 
 	if (family == AF_INET) {
@@ -60,7 +58,7 @@ void test_bind_perm(void)
 		return;
 
 	cgroup_fd = test__join_cgroup("/bind_perm");
-	if (CHECK(cgroup_fd < 0, "cg-join", "errno %d", errno))
+	if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup"))
 		return;
 
 	skel = bind_perm__open_and_load();
diff --git a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
index d2d9e965eba5..42b49870e520 100644
--- a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
@@ -2,13 +2,18 @@
 /* Copyright (c) 2021 Facebook */
 
 #include <sys/syscall.h>
+#include <limits.h>
 #include <test_progs.h>
 #include "bloom_filter_map.skel.h"
 
+#ifndef NUMA_NO_NODE
+#define NUMA_NO_NODE	(-1)
+#endif
+
 static void test_fail_cases(void)
 {
 	LIBBPF_OPTS(bpf_map_create_opts, opts);
-	__u32 value;
+	__u32 value = 0;
 	int fd, err;
 
 	/* Invalid key size */
@@ -21,6 +26,11 @@ static void test_fail_cases(void)
 	if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid value size 0"))
 		close(fd);
 
+	/* Invalid value size: too big */
+	fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, INT32_MAX, 100, NULL);
+	if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid value too large"))
+		close(fd);
+
 	/* Invalid max entries size */
 	fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, sizeof(value), 0, NULL);
 	if (!ASSERT_LT(fd, 0, "bpf_map_create bloom filter invalid max entries size"))
@@ -63,6 +73,7 @@ static void test_success_cases(void)
 
 	/* Create a map */
 	opts.map_flags = BPF_F_ZERO_SEED | BPF_F_NUMA_NODE;
+	opts.numa_node = NUMA_NO_NODE;
 	fd = bpf_map_create(BPF_MAP_TYPE_BLOOM_FILTER, NULL, 0, sizeof(value), 100, &opts);
 	if (!ASSERT_GE(fd, 0, "bpf_map_create bloom filter success case"))
 		return;
@@ -193,8 +204,8 @@ error:
 
 void test_bloom_filter_map(void)
 {
-	__u32 *rand_vals, nr_rand_vals;
-	struct bloom_filter_map *skel;
+	__u32 *rand_vals = NULL, nr_rand_vals = 0;
+	struct bloom_filter_map *skel = NULL;
 	int err;
 
 	test_fail_cases();
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
index 2be2d61954bc..75f4dff7d042 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
@@ -11,6 +11,7 @@
 #include <bpf/btf.h>
 #include "test_bpf_cookie.skel.h"
 #include "kprobe_multi.skel.h"
+#include "uprobe_multi.skel.h"
 
 /* uprobe attach point */
 static noinline void trigger_func(void)
@@ -239,6 +240,81 @@ cleanup:
 	bpf_link__destroy(link1);
 	kprobe_multi__destroy(skel);
 }
+
+/* defined in prog_tests/uprobe_multi_test.c */
+void uprobe_multi_func_1(void);
+void uprobe_multi_func_2(void);
+void uprobe_multi_func_3(void);
+
+static void uprobe_multi_test_run(struct uprobe_multi *skel)
+{
+	skel->bss->uprobe_multi_func_1_addr = (__u64) uprobe_multi_func_1;
+	skel->bss->uprobe_multi_func_2_addr = (__u64) uprobe_multi_func_2;
+	skel->bss->uprobe_multi_func_3_addr = (__u64) uprobe_multi_func_3;
+
+	skel->bss->pid = getpid();
+	skel->bss->test_cookie = true;
+
+	uprobe_multi_func_1();
+	uprobe_multi_func_2();
+	uprobe_multi_func_3();
+
+	ASSERT_EQ(skel->bss->uprobe_multi_func_1_result, 1, "uprobe_multi_func_1_result");
+	ASSERT_EQ(skel->bss->uprobe_multi_func_2_result, 1, "uprobe_multi_func_2_result");
+	ASSERT_EQ(skel->bss->uprobe_multi_func_3_result, 1, "uprobe_multi_func_3_result");
+
+	ASSERT_EQ(skel->bss->uretprobe_multi_func_1_result, 1, "uretprobe_multi_func_1_result");
+	ASSERT_EQ(skel->bss->uretprobe_multi_func_2_result, 1, "uretprobe_multi_func_2_result");
+	ASSERT_EQ(skel->bss->uretprobe_multi_func_3_result, 1, "uretprobe_multi_func_3_result");
+}
+
+static void uprobe_multi_attach_api_subtest(void)
+{
+	struct bpf_link *link1 = NULL, *link2 = NULL;
+	struct uprobe_multi *skel = NULL;
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts);
+	const char *syms[3] = {
+		"uprobe_multi_func_1",
+		"uprobe_multi_func_2",
+		"uprobe_multi_func_3",
+	};
+	__u64 cookies[3];
+
+	cookies[0] = 3; /* uprobe_multi_func_1 */
+	cookies[1] = 1; /* uprobe_multi_func_2 */
+	cookies[2] = 2; /* uprobe_multi_func_3 */
+
+	opts.syms = syms;
+	opts.cnt = ARRAY_SIZE(syms);
+	opts.cookies = &cookies[0];
+
+	skel = uprobe_multi__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi"))
+		goto cleanup;
+
+	link1 = bpf_program__attach_uprobe_multi(skel->progs.uprobe, -1,
+						 "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link1, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	cookies[0] = 2; /* uprobe_multi_func_1 */
+	cookies[1] = 3; /* uprobe_multi_func_2 */
+	cookies[2] = 1; /* uprobe_multi_func_3 */
+
+	opts.retprobe = true;
+	link2 = bpf_program__attach_uprobe_multi(skel->progs.uretprobe, -1,
+						      "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link2, "bpf_program__attach_uprobe_multi_retprobe"))
+		goto cleanup;
+
+	uprobe_multi_test_run(skel);
+
+cleanup:
+	bpf_link__destroy(link2);
+	bpf_link__destroy(link1);
+	uprobe_multi__destroy(skel);
+}
+
 static void uprobe_subtest(struct test_bpf_cookie *skel)
 {
 	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, opts);
@@ -374,8 +450,7 @@ static void pe_subtest(struct test_bpf_cookie *skel)
 	attr.size = sizeof(attr);
 	attr.type = PERF_TYPE_SOFTWARE;
 	attr.config = PERF_COUNT_SW_CPU_CLOCK;
-	attr.freq = 1;
-	attr.sample_freq = 1000;
+	attr.sample_period = 100000;
 	pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC);
 	if (!ASSERT_GE(pfd, 0, "perf_fd"))
 		goto cleanup;
@@ -413,10 +488,28 @@ cleanup:
 	bpf_link__destroy(link);
 }
 
+static int verify_tracing_link_info(int fd, u64 cookie)
+{
+	struct bpf_link_info info;
+	int err;
+	u32 len = sizeof(info);
+
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	if (!ASSERT_OK(err, "get_link_info"))
+		return -1;
+
+	if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_TRACING, "link_type"))
+		return -1;
+
+	ASSERT_EQ(info.tracing.cookie, cookie, "tracing_cookie");
+
+	return 0;
+}
+
 static void tracing_subtest(struct test_bpf_cookie *skel)
 {
 	__u64 cookie;
-	int prog_fd;
+	int prog_fd, err;
 	int fentry_fd = -1, fexit_fd = -1, fmod_ret_fd = -1;
 	LIBBPF_OPTS(bpf_test_run_opts, opts);
 	LIBBPF_OPTS(bpf_link_create_opts, link_opts);
@@ -431,6 +524,10 @@ static void tracing_subtest(struct test_bpf_cookie *skel)
 	if (!ASSERT_GE(fentry_fd, 0, "fentry.link_create"))
 		goto cleanup;
 
+	err = verify_tracing_link_info(fentry_fd, cookie);
+	if (!ASSERT_OK(err, "verify_tracing_link_info"))
+		goto cleanup;
+
 	cookie = 0x20000000000000L;
 	prog_fd = bpf_program__fd(skel->progs.fexit_test1);
 	link_opts.tracing.cookie = cookie;
@@ -472,6 +569,7 @@ static void lsm_subtest(struct test_bpf_cookie *skel)
 	int prog_fd;
 	int lsm_fd = -1;
 	LIBBPF_OPTS(bpf_link_create_opts, link_opts);
+	int err;
 
 	skel->bss->lsm_res = 0;
 
@@ -482,8 +580,9 @@ static void lsm_subtest(struct test_bpf_cookie *skel)
 	if (!ASSERT_GE(lsm_fd, 0, "lsm.link_create"))
 		goto cleanup;
 
-	stack_mprotect();
-	if (!ASSERT_EQ(errno, EPERM, "stack_mprotect"))
+	err = stack_mprotect();
+	if (!ASSERT_EQ(err, -1, "stack_mprotect") ||
+	    !ASSERT_EQ(errno, EPERM, "stack_mprotect"))
 		goto cleanup;
 
 	usleep(1);
@@ -495,6 +594,139 @@ cleanup:
 		close(lsm_fd);
 }
 
+static void tp_btf_subtest(struct test_bpf_cookie *skel)
+{
+	__u64 cookie;
+	int prog_fd, link_fd = -1;
+	struct bpf_link *link = NULL;
+	LIBBPF_OPTS(bpf_link_create_opts, link_opts);
+	LIBBPF_OPTS(bpf_raw_tp_opts, raw_tp_opts);
+	LIBBPF_OPTS(bpf_trace_opts, trace_opts);
+
+	/* There are three different ways to attach tp_btf (BTF-aware raw
+	 * tracepoint) programs. Let's test all of them.
+	 */
+	prog_fd = bpf_program__fd(skel->progs.handle_tp_btf);
+
+	/* low-level BPF_RAW_TRACEPOINT_OPEN command wrapper */
+	skel->bss->tp_btf_res = 0;
+
+	raw_tp_opts.cookie = cookie = 0x11000000000000L;
+	link_fd = bpf_raw_tracepoint_open_opts(prog_fd, &raw_tp_opts);
+	if (!ASSERT_GE(link_fd, 0, "bpf_raw_tracepoint_open_opts"))
+		goto cleanup;
+
+	usleep(1); /* trigger */
+	close(link_fd); /* detach */
+	link_fd = -1;
+
+	ASSERT_EQ(skel->bss->tp_btf_res, cookie, "raw_tp_open_res");
+
+	/* low-level generic bpf_link_create() API */
+	skel->bss->tp_btf_res = 0;
+
+	link_opts.tracing.cookie = cookie = 0x22000000000000L;
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_RAW_TP, &link_opts);
+	if (!ASSERT_GE(link_fd, 0, "bpf_link_create"))
+		goto cleanup;
+
+	usleep(1); /* trigger */
+	close(link_fd); /* detach */
+	link_fd = -1;
+
+	ASSERT_EQ(skel->bss->tp_btf_res, cookie, "link_create_res");
+
+	/* high-level bpf_link-based bpf_program__attach_trace_opts() API */
+	skel->bss->tp_btf_res = 0;
+
+	trace_opts.cookie = cookie = 0x33000000000000L;
+	link = bpf_program__attach_trace_opts(skel->progs.handle_tp_btf, &trace_opts);
+	if (!ASSERT_OK_PTR(link, "attach_trace_opts"))
+		goto cleanup;
+
+	usleep(1); /* trigger */
+	bpf_link__destroy(link); /* detach */
+	link = NULL;
+
+	ASSERT_EQ(skel->bss->tp_btf_res, cookie, "attach_trace_opts_res");
+
+cleanup:
+	if (link_fd >= 0)
+		close(link_fd);
+	bpf_link__destroy(link);
+}
+
+static int verify_raw_tp_link_info(int fd, u64 cookie)
+{
+	struct bpf_link_info info;
+	int err;
+	u32 len = sizeof(info);
+
+	memset(&info, 0, sizeof(info));
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	if (!ASSERT_OK(err, "get_link_info"))
+		return -1;
+
+	if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_RAW_TRACEPOINT, "link_type"))
+		return -1;
+
+	ASSERT_EQ(info.raw_tracepoint.cookie, cookie, "raw_tp_cookie");
+
+	return 0;
+}
+
+static void raw_tp_subtest(struct test_bpf_cookie *skel)
+{
+	__u64 cookie;
+	int err, prog_fd, link_fd = -1;
+	struct bpf_link *link = NULL;
+	LIBBPF_OPTS(bpf_raw_tp_opts, raw_tp_opts);
+	LIBBPF_OPTS(bpf_raw_tracepoint_opts, opts);
+
+	/* There are two different ways to attach raw_tp programs */
+	prog_fd = bpf_program__fd(skel->progs.handle_raw_tp);
+
+	/* low-level BPF_RAW_TRACEPOINT_OPEN command wrapper */
+	skel->bss->raw_tp_res = 0;
+
+	raw_tp_opts.tp_name = "sys_enter";
+	raw_tp_opts.cookie = cookie = 0x55000000000000L;
+	link_fd = bpf_raw_tracepoint_open_opts(prog_fd, &raw_tp_opts);
+	if (!ASSERT_GE(link_fd, 0, "bpf_raw_tracepoint_open_opts"))
+		goto cleanup;
+
+	usleep(1); /* trigger */
+
+	err = verify_raw_tp_link_info(link_fd, cookie);
+	if (!ASSERT_OK(err, "verify_raw_tp_link_info"))
+		goto cleanup;
+
+	close(link_fd); /* detach */
+	link_fd = -1;
+
+	ASSERT_EQ(skel->bss->raw_tp_res, cookie, "raw_tp_open_res");
+
+	/* high-level bpf_link-based bpf_program__attach_raw_tracepoint_opts() API */
+	skel->bss->raw_tp_res = 0;
+
+	opts.cookie = cookie = 0x66000000000000L;
+	link = bpf_program__attach_raw_tracepoint_opts(skel->progs.handle_raw_tp,
+						       "sys_enter", &opts);
+	if (!ASSERT_OK_PTR(link, "attach_raw_tp_opts"))
+		goto cleanup;
+
+	usleep(1); /* trigger */
+	bpf_link__destroy(link); /* detach */
+	link = NULL;
+
+	ASSERT_EQ(skel->bss->raw_tp_res, cookie, "attach_raw_tp_opts_res");
+
+cleanup:
+	if (link_fd >= 0)
+		close(link_fd);
+	bpf_link__destroy(link);
+}
+
 void test_bpf_cookie(void)
 {
 	struct test_bpf_cookie *skel;
@@ -503,7 +735,7 @@ void test_bpf_cookie(void)
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
 		return;
 
-	skel->bss->my_tid = syscall(SYS_gettid);
+	skel->bss->my_tid = sys_gettid();
 
 	if (test__start_subtest("kprobe"))
 		kprobe_subtest(skel);
@@ -513,6 +745,8 @@ void test_bpf_cookie(void)
 		kprobe_multi_attach_api_subtest();
 	if (test__start_subtest("uprobe"))
 		uprobe_subtest(skel);
+	if (test__start_subtest("multi_uprobe_attach_api"))
+		uprobe_multi_attach_api_subtest();
 	if (test__start_subtest("tracepoint"))
 		tp_subtest(skel);
 	if (test__start_subtest("perf_event"))
@@ -521,6 +755,9 @@ void test_bpf_cookie(void)
 		tracing_subtest(skel);
 	if (test__start_subtest("lsm"))
 		lsm_subtest(skel);
-
+	if (test__start_subtest("tp_btf"))
+		tp_btf_subtest(skel);
+	if (test__start_subtest("raw_tp"))
+		raw_tp_subtest(skel);
 	test_bpf_cookie__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_gotox.c b/tools/testing/selftests/bpf/prog_tests/bpf_gotox.c
new file mode 100644
index 000000000000..d138cc7b1bda
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_gotox.c
@@ -0,0 +1,292 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in6.h>
+#include <linux/udp.h>
+#include <linux/tcp.h>
+
+#include <sys/syscall.h>
+#include <bpf/bpf.h>
+
+#include "bpf_gotox.skel.h"
+
+static void __test_run(struct bpf_program *prog, void *ctx_in, size_t ctx_size_in)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+			    .ctx_in = ctx_in,
+			    .ctx_size_in = ctx_size_in,
+		   );
+	int err, prog_fd;
+
+	prog_fd = bpf_program__fd(prog);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run_opts err");
+}
+
+static void __subtest(struct bpf_gotox *skel, void (*check)(struct bpf_gotox *))
+{
+	if (skel->data->skip)
+		test__skip();
+	else
+		check(skel);
+}
+
+static void check_simple(struct bpf_gotox *skel,
+			 struct bpf_program *prog,
+			 __u64 ctx_in,
+			 __u64 expected)
+{
+	skel->bss->ret_user = 0;
+
+	__test_run(prog, &ctx_in, sizeof(ctx_in));
+
+	if (!ASSERT_EQ(skel->bss->ret_user, expected, "skel->bss->ret_user"))
+		return;
+}
+
+static void check_simple_fentry(struct bpf_gotox *skel,
+				struct bpf_program *prog,
+				__u64 ctx_in,
+				__u64 expected)
+{
+	skel->bss->in_user = ctx_in;
+	skel->bss->ret_user = 0;
+
+	/* trigger */
+	usleep(1);
+
+	if (!ASSERT_EQ(skel->bss->ret_user, expected, "skel->bss->ret_user"))
+		return;
+}
+
+/* validate that for two loads of the same jump table libbpf generates only one map */
+static void check_one_map_two_jumps(struct bpf_gotox *skel)
+{
+	struct bpf_prog_info prog_info;
+	struct bpf_map_info map_info;
+	__u32 len;
+	__u32 map_ids[16];
+	int prog_fd, map_fd;
+	int ret;
+	int i;
+	bool seen = false;
+
+	memset(&prog_info, 0, sizeof(prog_info));
+	prog_info.map_ids = (long)map_ids;
+	prog_info.nr_map_ids = ARRAY_SIZE(map_ids);
+	prog_fd = bpf_program__fd(skel->progs.one_map_two_jumps);
+	if (!ASSERT_GE(prog_fd, 0, "bpf_program__fd(one_map_two_jumps)"))
+		return;
+
+	len = sizeof(prog_info);
+	ret = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &len);
+	if (!ASSERT_OK(ret, "bpf_obj_get_info_by_fd(prog_fd)"))
+		return;
+
+	for (i = 0; i < prog_info.nr_map_ids; i++) {
+		map_fd  = bpf_map_get_fd_by_id(map_ids[i]);
+		if (!ASSERT_GE(map_fd, 0, "bpf_map_get_fd_by_id"))
+			return;
+
+		len = sizeof(map_info);
+		memset(&map_info, 0, len);
+		ret = bpf_obj_get_info_by_fd(map_fd, &map_info, &len);
+		if (!ASSERT_OK(ret, "bpf_obj_get_info_by_fd(map_fd)")) {
+			close(map_fd);
+			return;
+		}
+
+		if (map_info.type == BPF_MAP_TYPE_INSN_ARRAY) {
+			if (!ASSERT_EQ(seen, false, "more than one INSN_ARRAY map")) {
+				close(map_fd);
+				return;
+			}
+			seen = true;
+		}
+		close(map_fd);
+	}
+
+	ASSERT_EQ(seen, true, "no INSN_ARRAY map");
+}
+
+static void check_one_switch(struct bpf_gotox *skel)
+{
+	__u64 in[]   = {0, 1, 2, 3, 4,  5, 77};
+	__u64 out[]  = {2, 3, 4, 5, 7, 19, 19};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(in); i++)
+		check_simple(skel, skel->progs.one_switch, in[i], out[i]);
+}
+
+static void check_one_switch_non_zero_sec_off(struct bpf_gotox *skel)
+{
+	__u64 in[]   = {0, 1, 2, 3, 4,  5, 77};
+	__u64 out[]  = {2, 3, 4, 5, 7, 19, 19};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(in); i++)
+		check_simple(skel, skel->progs.one_switch_non_zero_sec_off, in[i], out[i]);
+}
+
+static void check_two_switches(struct bpf_gotox *skel)
+{
+	__u64 in[]   = {0, 1, 2, 3, 4,  5, 77};
+	__u64 out[] = {103, 104, 107, 205, 115, 1019, 1019};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(in); i++)
+		check_simple(skel, skel->progs.two_switches, in[i], out[i]);
+}
+
+static void check_big_jump_table(struct bpf_gotox *skel)
+{
+	__u64 in[]  = {0, 11, 27, 31, 22, 45, 99};
+	__u64 out[] = {2,  3,  4,  5, 19, 19, 19};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(in); i++)
+		check_simple(skel, skel->progs.big_jump_table, in[i], out[i]);
+}
+
+static void check_one_jump_two_maps(struct bpf_gotox *skel)
+{
+	__u64 in[]  = {0, 1, 2, 3, 4,  5, 77};
+	__u64 out[] = {12, 15, 7 , 15, 12, 15, 15};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(in); i++)
+		check_simple(skel, skel->progs.one_jump_two_maps, in[i], out[i]);
+}
+
+static void check_static_global(struct bpf_gotox *skel)
+{
+	__u64 in[]   = {0, 1, 2, 3, 4,  5, 77};
+	__u64 out[]  = {2, 3, 4, 5, 7, 19, 19};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(in); i++)
+		check_simple(skel, skel->progs.use_static_global1, in[i], out[i]);
+	for (i = 0; i < ARRAY_SIZE(in); i++)
+		check_simple(skel, skel->progs.use_static_global2, in[i], out[i]);
+}
+
+static void check_nonstatic_global(struct bpf_gotox *skel)
+{
+	__u64 in[]   = {0, 1, 2, 3, 4,  5, 77};
+	__u64 out[]  = {2, 3, 4, 5, 7, 19, 19};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(in); i++)
+		check_simple(skel, skel->progs.use_nonstatic_global1, in[i], out[i]);
+
+	for (i = 0; i < ARRAY_SIZE(in); i++)
+		check_simple(skel, skel->progs.use_nonstatic_global2, in[i], out[i]);
+}
+
+static void check_other_sec(struct bpf_gotox *skel)
+{
+	struct bpf_link *link;
+	__u64 in[]   = {0, 1, 2, 3, 4,  5, 77};
+	__u64 out[]  = {2, 3, 4, 5, 7, 19, 19};
+	int i;
+
+	link = bpf_program__attach(skel->progs.simple_test_other_sec);
+	if (!ASSERT_OK_PTR(link, "link"))
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(in); i++)
+		check_simple_fentry(skel, skel->progs.simple_test_other_sec, in[i], out[i]);
+
+	bpf_link__destroy(link);
+}
+
+static void check_static_global_other_sec(struct bpf_gotox *skel)
+{
+	struct bpf_link *link;
+	__u64 in[]   = {0, 1, 2, 3, 4,  5, 77};
+	__u64 out[]  = {2, 3, 4, 5, 7, 19, 19};
+	int i;
+
+	link = bpf_program__attach(skel->progs.use_static_global_other_sec);
+	if (!ASSERT_OK_PTR(link, "link"))
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(in); i++)
+		check_simple_fentry(skel, skel->progs.use_static_global_other_sec, in[i], out[i]);
+
+	bpf_link__destroy(link);
+}
+
+static void check_nonstatic_global_other_sec(struct bpf_gotox *skel)
+{
+	struct bpf_link *link;
+	__u64 in[]   = {0, 1, 2, 3, 4,  5, 77};
+	__u64 out[]  = {2, 3, 4, 5, 7, 19, 19};
+	int i;
+
+	link = bpf_program__attach(skel->progs.use_nonstatic_global_other_sec);
+	if (!ASSERT_OK_PTR(link, "link"))
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(in); i++)
+		check_simple_fentry(skel, skel->progs.use_nonstatic_global_other_sec, in[i], out[i]);
+
+	bpf_link__destroy(link);
+}
+
+void test_bpf_gotox(void)
+{
+	struct bpf_gotox *skel;
+	int ret;
+
+	skel = bpf_gotox__open();
+	if (!ASSERT_NEQ(skel, NULL, "bpf_gotox__open"))
+		return;
+
+	ret = bpf_gotox__load(skel);
+	if (!ASSERT_OK(ret, "bpf_gotox__load"))
+		return;
+
+	skel->bss->pid = getpid();
+
+	if (test__start_subtest("one-switch"))
+		__subtest(skel, check_one_switch);
+
+	if (test__start_subtest("one-switch-non-zero-sec-offset"))
+		__subtest(skel, check_one_switch_non_zero_sec_off);
+
+	if (test__start_subtest("two-switches"))
+		__subtest(skel, check_two_switches);
+
+	if (test__start_subtest("big-jump-table"))
+		__subtest(skel, check_big_jump_table);
+
+	if (test__start_subtest("static-global"))
+		__subtest(skel, check_static_global);
+
+	if (test__start_subtest("nonstatic-global"))
+		__subtest(skel, check_nonstatic_global);
+
+	if (test__start_subtest("other-sec"))
+		__subtest(skel, check_other_sec);
+
+	if (test__start_subtest("static-global-other-sec"))
+		__subtest(skel, check_static_global_other_sec);
+
+	if (test__start_subtest("nonstatic-global-other-sec"))
+		__subtest(skel, check_nonstatic_global_other_sec);
+
+	if (test__start_subtest("one-jump-two-maps"))
+		__subtest(skel, check_one_jump_two_maps);
+
+	if (test__start_subtest("one-map-two-jumps"))
+		__subtest(skel, check_one_map_two_jumps);
+
+	bpf_gotox__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_insn_array.c b/tools/testing/selftests/bpf/prog_tests/bpf_insn_array.c
new file mode 100644
index 000000000000..269870bec941
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_insn_array.c
@@ -0,0 +1,504 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <bpf/bpf.h>
+#include <test_progs.h>
+
+#ifdef __x86_64__
+static int map_create(__u32 map_type, __u32 max_entries)
+{
+	const char *map_name = "insn_array";
+	__u32 key_size = 4;
+	__u32 value_size = sizeof(struct bpf_insn_array_value);
+
+	return bpf_map_create(map_type, map_name, key_size, value_size, max_entries, NULL);
+}
+
+static int prog_load(struct bpf_insn *insns, __u32 insn_cnt, int *fd_array, __u32 fd_array_cnt)
+{
+	LIBBPF_OPTS(bpf_prog_load_opts, opts);
+
+	opts.fd_array = fd_array;
+	opts.fd_array_cnt = fd_array_cnt;
+
+	return bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "GPL", insns, insn_cnt, &opts);
+}
+
+static void __check_success(struct bpf_insn *insns, __u32 insn_cnt, __u32 *map_in, __u32 *map_out)
+{
+	struct bpf_insn_array_value val = {};
+	int prog_fd = -1, map_fd, i;
+
+	map_fd = map_create(BPF_MAP_TYPE_INSN_ARRAY, insn_cnt);
+	if (!ASSERT_GE(map_fd, 0, "map_create"))
+		return;
+
+	for (i = 0; i < insn_cnt; i++) {
+		val.orig_off = map_in[i];
+		if (!ASSERT_EQ(bpf_map_update_elem(map_fd, &i, &val, 0), 0, "bpf_map_update_elem"))
+			goto cleanup;
+	}
+
+	if (!ASSERT_EQ(bpf_map_freeze(map_fd), 0, "bpf_map_freeze"))
+		goto cleanup;
+
+	prog_fd = prog_load(insns, insn_cnt, &map_fd, 1);
+	if (!ASSERT_GE(prog_fd, 0, "bpf(BPF_PROG_LOAD)"))
+		goto cleanup;
+
+	for (i = 0; i < insn_cnt; i++) {
+		char buf[64];
+
+		if (!ASSERT_EQ(bpf_map_lookup_elem(map_fd, &i, &val), 0, "bpf_map_lookup_elem"))
+			goto cleanup;
+
+		snprintf(buf, sizeof(buf), "val.xlated_off should be equal map_out[%d]", i);
+		ASSERT_EQ(val.xlated_off, map_out[i], buf);
+	}
+
+cleanup:
+	close(prog_fd);
+	close(map_fd);
+}
+
+/*
+ * Load a program, which will not be anyhow mangled by the verifier.  Add an
+ * insn_array map pointing to every instruction. Check that it hasn't changed
+ * after the program load.
+ */
+static void check_one_to_one_mapping(void)
+{
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 4),
+		BPF_MOV64_IMM(BPF_REG_0, 3),
+		BPF_MOV64_IMM(BPF_REG_0, 2),
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	__u32 map_in[] = {0, 1, 2, 3, 4, 5};
+	__u32 map_out[] = {0, 1, 2, 3, 4, 5};
+
+	__check_success(insns, ARRAY_SIZE(insns), map_in, map_out);
+}
+
+/*
+ * Load a program with two patches (get jiffies, for simplicity). Add an
+ * insn_array map pointing to every instruction. Check how it was changed
+ * after the program load.
+ */
+static void check_simple(void)
+{
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 2),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_jiffies64),
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_jiffies64),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	__u32 map_in[] = {0, 1, 2, 3, 4, 5};
+	__u32 map_out[] = {0, 1, 4, 5, 8, 9};
+
+	__check_success(insns, ARRAY_SIZE(insns), map_in, map_out);
+}
+
+/*
+ * Verifier can delete code in two cases: nops & dead code. From insn
+ * array's point of view, the two cases are the same, so test using
+ * the simplest method: by loading some nops
+ */
+static void check_deletions(void)
+{
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 2),
+		BPF_JMP_IMM(BPF_JA, 0, 0, 0), /* nop */
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_JMP_IMM(BPF_JA, 0, 0, 0), /* nop */
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	__u32 map_in[] = {0, 1, 2, 3, 4, 5};
+	__u32 map_out[] = {0, -1, 1, -1, 2, 3};
+
+	__check_success(insns, ARRAY_SIZE(insns), map_in, map_out);
+}
+
+/*
+ * Same test as check_deletions, but also add code which adds instructions
+ */
+static void check_deletions_with_functions(void)
+{
+	struct bpf_insn insns[] = {
+		BPF_JMP_IMM(BPF_JA, 0, 0, 0), /* nop */
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_jiffies64),
+		BPF_JMP_IMM(BPF_JA, 0, 0, 0), /* nop */
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+		BPF_JMP_IMM(BPF_JA, 0, 0, 0), /* nop */
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_jiffies64),
+		BPF_JMP_IMM(BPF_JA, 0, 0, 0), /* nop */
+		BPF_MOV64_IMM(BPF_REG_0, 2),
+		BPF_EXIT_INSN(),
+	};
+	__u32 map_in[] =  { 0, 1,  2, 3, 4, 5, /* func */  6, 7,  8, 9, 10};
+	__u32 map_out[] = {-1, 0, -1, 3, 4, 5, /* func */ -1, 6, -1, 9, 10};
+
+	__check_success(insns, ARRAY_SIZE(insns), map_in, map_out);
+}
+
+/*
+ * Try to load a program with a map which points to outside of the program
+ */
+static void check_out_of_bounds_index(void)
+{
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 4),
+		BPF_MOV64_IMM(BPF_REG_0, 3),
+		BPF_MOV64_IMM(BPF_REG_0, 2),
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int prog_fd, map_fd;
+	struct bpf_insn_array_value val = {};
+	int key;
+
+	map_fd = map_create(BPF_MAP_TYPE_INSN_ARRAY, 1);
+	if (!ASSERT_GE(map_fd, 0, "map_create"))
+		return;
+
+	key = 0;
+	val.orig_off = ARRAY_SIZE(insns); /* too big */
+	if (!ASSERT_EQ(bpf_map_update_elem(map_fd, &key, &val, 0), 0, "bpf_map_update_elem"))
+		goto cleanup;
+
+	if (!ASSERT_EQ(bpf_map_freeze(map_fd), 0, "bpf_map_freeze"))
+		goto cleanup;
+
+	prog_fd = prog_load(insns, ARRAY_SIZE(insns), &map_fd, 1);
+	if (!ASSERT_EQ(prog_fd, -EINVAL, "program should have been rejected (prog_fd != -EINVAL)")) {
+		close(prog_fd);
+		goto cleanup;
+	}
+
+cleanup:
+	close(map_fd);
+}
+
+/*
+ * Try to load a program with a map which points to the middle of 16-bit insn
+ */
+static void check_mid_insn_index(void)
+{
+	struct bpf_insn insns[] = {
+		BPF_LD_IMM64(BPF_REG_0, 0), /* 2 x 8 */
+		BPF_EXIT_INSN(),
+	};
+	int prog_fd, map_fd;
+	struct bpf_insn_array_value val = {};
+	int key;
+
+	map_fd = map_create(BPF_MAP_TYPE_INSN_ARRAY, 1);
+	if (!ASSERT_GE(map_fd, 0, "map_create"))
+		return;
+
+	key = 0;
+	val.orig_off = 1; /* middle of 16-byte instruction */
+	if (!ASSERT_EQ(bpf_map_update_elem(map_fd, &key, &val, 0), 0, "bpf_map_update_elem"))
+		goto cleanup;
+
+	if (!ASSERT_EQ(bpf_map_freeze(map_fd), 0, "bpf_map_freeze"))
+		goto cleanup;
+
+	prog_fd = prog_load(insns, ARRAY_SIZE(insns), &map_fd, 1);
+	if (!ASSERT_EQ(prog_fd, -EINVAL, "program should have been rejected (prog_fd != -EINVAL)")) {
+		close(prog_fd);
+		goto cleanup;
+	}
+
+cleanup:
+	close(map_fd);
+}
+
+static void check_incorrect_index(void)
+{
+	check_out_of_bounds_index();
+	check_mid_insn_index();
+}
+
+static int set_bpf_jit_harden(char *level)
+{
+	char old_level;
+	int err = -1;
+	int fd = -1;
+
+	fd = open("/proc/sys/net/core/bpf_jit_harden", O_RDWR | O_NONBLOCK);
+	if (fd < 0) {
+		ASSERT_FAIL("open .../bpf_jit_harden returned %d (errno=%d)", fd, errno);
+		return -1;
+	}
+
+	err = read(fd, &old_level, 1);
+	if (err != 1) {
+		ASSERT_FAIL("read from .../bpf_jit_harden returned %d (errno=%d)", err, errno);
+		err = -1;
+		goto end;
+	}
+
+	lseek(fd, 0, SEEK_SET);
+
+	err = write(fd, level, 1);
+	if (err != 1) {
+		ASSERT_FAIL("write to .../bpf_jit_harden returned %d (errno=%d)", err, errno);
+		err = -1;
+		goto end;
+	}
+
+	err = 0;
+	*level = old_level;
+end:
+	if (fd >= 0)
+		close(fd);
+	return err;
+}
+
+static void check_blindness(void)
+{
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 4),
+		BPF_MOV64_IMM(BPF_REG_0, 3),
+		BPF_MOV64_IMM(BPF_REG_0, 2),
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+	};
+	int prog_fd = -1, map_fd;
+	struct bpf_insn_array_value val = {};
+	char bpf_jit_harden = '@'; /* non-exizsting value */
+	int i;
+
+	map_fd = map_create(BPF_MAP_TYPE_INSN_ARRAY, ARRAY_SIZE(insns));
+	if (!ASSERT_GE(map_fd, 0, "map_create"))
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(insns); i++) {
+		val.orig_off = i;
+		if (!ASSERT_EQ(bpf_map_update_elem(map_fd, &i, &val, 0), 0, "bpf_map_update_elem"))
+			goto cleanup;
+	}
+
+	if (!ASSERT_EQ(bpf_map_freeze(map_fd), 0, "bpf_map_freeze"))
+		goto cleanup;
+
+	bpf_jit_harden = '2';
+	if (set_bpf_jit_harden(&bpf_jit_harden)) {
+		bpf_jit_harden = '@'; /* open, read or write failed => no write was done */
+		goto cleanup;
+	}
+
+	prog_fd = prog_load(insns, ARRAY_SIZE(insns), &map_fd, 1);
+	if (!ASSERT_GE(prog_fd, 0, "bpf(BPF_PROG_LOAD)"))
+		goto cleanup;
+
+	for (i = 0; i < ARRAY_SIZE(insns); i++) {
+		char fmt[32];
+
+		if (!ASSERT_EQ(bpf_map_lookup_elem(map_fd, &i, &val), 0, "bpf_map_lookup_elem"))
+			goto cleanup;
+
+		snprintf(fmt, sizeof(fmt), "val should be equal 3*%d", i);
+		ASSERT_EQ(val.xlated_off, i * 3, fmt);
+	}
+
+cleanup:
+	/* restore the old one */
+	if (bpf_jit_harden != '@')
+		set_bpf_jit_harden(&bpf_jit_harden);
+
+	close(prog_fd);
+	close(map_fd);
+}
+
+/* Once map was initialized, it should be frozen */
+static void check_load_unfrozen_map(void)
+{
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int prog_fd = -1, map_fd;
+	struct bpf_insn_array_value val = {};
+	int i;
+
+	map_fd = map_create(BPF_MAP_TYPE_INSN_ARRAY, ARRAY_SIZE(insns));
+	if (!ASSERT_GE(map_fd, 0, "map_create"))
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(insns); i++) {
+		val.orig_off = i;
+		if (!ASSERT_EQ(bpf_map_update_elem(map_fd, &i, &val, 0), 0, "bpf_map_update_elem"))
+			goto cleanup;
+	}
+
+	prog_fd = prog_load(insns, ARRAY_SIZE(insns), &map_fd, 1);
+	if (!ASSERT_EQ(prog_fd, -EINVAL, "program should have been rejected (prog_fd != -EINVAL)"))
+		goto cleanup;
+
+	/* correctness: now freeze the map, the program should load fine */
+
+	if (!ASSERT_EQ(bpf_map_freeze(map_fd), 0, "bpf_map_freeze"))
+		goto cleanup;
+
+	prog_fd = prog_load(insns, ARRAY_SIZE(insns), &map_fd, 1);
+	if (!ASSERT_GE(prog_fd, 0, "bpf(BPF_PROG_LOAD)"))
+		goto cleanup;
+
+	for (i = 0; i < ARRAY_SIZE(insns); i++) {
+		if (!ASSERT_EQ(bpf_map_lookup_elem(map_fd, &i, &val), 0, "bpf_map_lookup_elem"))
+			goto cleanup;
+
+		ASSERT_EQ(val.xlated_off, i, "val should be equal i");
+	}
+
+cleanup:
+	close(prog_fd);
+	close(map_fd);
+}
+
+/* Map can be used only by one BPF program */
+static void check_no_map_reuse(void)
+{
+	struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int prog_fd = -1, map_fd, extra_fd = -1;
+	struct bpf_insn_array_value val = {};
+	int i;
+
+	map_fd = map_create(BPF_MAP_TYPE_INSN_ARRAY, ARRAY_SIZE(insns));
+	if (!ASSERT_GE(map_fd, 0, "map_create"))
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(insns); i++) {
+		val.orig_off = i;
+		if (!ASSERT_EQ(bpf_map_update_elem(map_fd, &i, &val, 0), 0, "bpf_map_update_elem"))
+			goto cleanup;
+	}
+
+	if (!ASSERT_EQ(bpf_map_freeze(map_fd), 0, "bpf_map_freeze"))
+		goto cleanup;
+
+	prog_fd = prog_load(insns, ARRAY_SIZE(insns), &map_fd, 1);
+	if (!ASSERT_GE(prog_fd, 0, "bpf(BPF_PROG_LOAD)"))
+		goto cleanup;
+
+	for (i = 0; i < ARRAY_SIZE(insns); i++) {
+		if (!ASSERT_EQ(bpf_map_lookup_elem(map_fd, &i, &val), 0, "bpf_map_lookup_elem"))
+			goto cleanup;
+
+		ASSERT_EQ(val.xlated_off, i, "val should be equal i");
+	}
+
+	extra_fd = prog_load(insns, ARRAY_SIZE(insns), &map_fd, 1);
+	if (!ASSERT_EQ(extra_fd, -EBUSY, "program should have been rejected (extra_fd != -EBUSY)"))
+		goto cleanup;
+
+	/* correctness: check that prog is still loadable without fd_array */
+	extra_fd = prog_load(insns, ARRAY_SIZE(insns), NULL, 0);
+	if (!ASSERT_GE(extra_fd, 0, "bpf(BPF_PROG_LOAD): expected no error"))
+		goto cleanup;
+
+cleanup:
+	close(extra_fd);
+	close(prog_fd);
+	close(map_fd);
+}
+
+static void check_bpf_no_lookup(void)
+{
+	struct bpf_insn insns[] = {
+		BPF_LD_MAP_FD(BPF_REG_1, 0),
+		BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+		BPF_EXIT_INSN(),
+	};
+	int prog_fd = -1, map_fd;
+
+	map_fd = map_create(BPF_MAP_TYPE_INSN_ARRAY, 1);
+	if (!ASSERT_GE(map_fd, 0, "map_create"))
+		return;
+
+	insns[0].imm = map_fd;
+
+	if (!ASSERT_EQ(bpf_map_freeze(map_fd), 0, "bpf_map_freeze"))
+		goto cleanup;
+
+	prog_fd = prog_load(insns, ARRAY_SIZE(insns), NULL, 0);
+	if (!ASSERT_EQ(prog_fd, -EINVAL, "program should have been rejected (prog_fd != -EINVAL)"))
+		goto cleanup;
+
+	/* correctness: check that prog is still loadable with normal map */
+	close(map_fd);
+	map_fd = map_create(BPF_MAP_TYPE_ARRAY, 1);
+	insns[0].imm = map_fd;
+	prog_fd = prog_load(insns, ARRAY_SIZE(insns), NULL, 0);
+	if (!ASSERT_GE(prog_fd, 0, "bpf(BPF_PROG_LOAD)"))
+		goto cleanup;
+
+cleanup:
+	close(prog_fd);
+	close(map_fd);
+}
+
+static void check_bpf_side(void)
+{
+	check_bpf_no_lookup();
+}
+
+static void __test_bpf_insn_array(void)
+{
+	/* Test if offsets are adjusted properly */
+
+	if (test__start_subtest("one2one"))
+		check_one_to_one_mapping();
+
+	if (test__start_subtest("simple"))
+		check_simple();
+
+	if (test__start_subtest("deletions"))
+		check_deletions();
+
+	if (test__start_subtest("deletions-with-functions"))
+		check_deletions_with_functions();
+
+	if (test__start_subtest("blindness"))
+		check_blindness();
+
+	/* Check all kinds of operations and related restrictions */
+
+	if (test__start_subtest("incorrect-index"))
+		check_incorrect_index();
+
+	if (test__start_subtest("load-unfrozen-map"))
+		check_load_unfrozen_map();
+
+	if (test__start_subtest("no-map-reuse"))
+		check_no_map_reuse();
+
+	if (test__start_subtest("bpf-side-ops"))
+		check_bpf_side();
+}
+#else
+static void __test_bpf_insn_array(void)
+{
+	test__skip();
+}
+#endif
+
+void test_bpf_insn_array(void)
+{
+	__test_bpf_insn_array();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index 6f8ed61fc4b4..5225d69bf79b 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -7,10 +7,10 @@
 #include "bpf_iter_ipv6_route.skel.h"
 #include "bpf_iter_netlink.skel.h"
 #include "bpf_iter_bpf_map.skel.h"
-#include "bpf_iter_task.skel.h"
+#include "bpf_iter_tasks.skel.h"
 #include "bpf_iter_task_stack.skel.h"
 #include "bpf_iter_task_file.skel.h"
-#include "bpf_iter_task_vma.skel.h"
+#include "bpf_iter_task_vmas.skel.h"
 #include "bpf_iter_task_btf.skel.h"
 #include "bpf_iter_tcp4.skel.h"
 #include "bpf_iter_tcp6.skel.h"
@@ -34,8 +34,6 @@
 #include "bpf_iter_ksym.skel.h"
 #include "bpf_iter_sockmap.skel.h"
 
-static int duration;
-
 static void test_btf_id_or_null(void)
 {
 	struct bpf_iter_test_kern3 *skel;
@@ -64,7 +62,7 @@ static void do_dummy_read_opts(struct bpf_program *prog, struct bpf_iter_attach_
 	/* not check contents, but ensure read() ends without error */
 	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
 		;
-	CHECK(len < 0, "read", "read failed: %s\n", strerror(errno));
+	ASSERT_GE(len, 0, "read");
 
 	close(iter_fd);
 
@@ -195,8 +193,8 @@ static void check_bpf_link_info(const struct bpf_program *prog)
 		return;
 
 	info_len = sizeof(info);
-	err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &info, &info_len);
-	ASSERT_OK(err, "bpf_obj_get_info_by_fd");
+	err = bpf_link_get_info_by_fd(bpf_link__fd(link), &info, &info_len);
+	ASSERT_OK(err, "bpf_link_get_info_by_fd");
 	ASSERT_EQ(info.iter.task.tid, getpid(), "check_task_tid");
 
 	bpf_link__destroy(link);
@@ -215,12 +213,12 @@ static void *do_nothing_wait(void *arg)
 static void test_task_common_nocheck(struct bpf_iter_attach_opts *opts,
 				     int *num_unknown, int *num_known)
 {
-	struct bpf_iter_task *skel;
+	struct bpf_iter_tasks *skel;
 	pthread_t thread_id;
 	void *ret;
 
-	skel = bpf_iter_task__open_and_load();
-	if (!ASSERT_OK_PTR(skel, "bpf_iter_task__open_and_load"))
+	skel = bpf_iter_tasks__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "bpf_iter_tasks__open_and_load"))
 		return;
 
 	ASSERT_OK(pthread_mutex_lock(&do_nothing_mutex), "pthread_mutex_lock");
@@ -228,7 +226,7 @@ static void test_task_common_nocheck(struct bpf_iter_attach_opts *opts,
 	ASSERT_OK(pthread_create(&thread_id, NULL, &do_nothing_wait, NULL),
 		  "pthread_create");
 
-	skel->bss->tid = getpid();
+	skel->bss->tid = sys_gettid();
 
 	do_dummy_read_opts(skel->progs.dump_task, opts);
 
@@ -239,7 +237,7 @@ static void test_task_common_nocheck(struct bpf_iter_attach_opts *opts,
 	ASSERT_FALSE(pthread_join(thread_id, &ret) || ret != NULL,
 		     "pthread_join");
 
-	bpf_iter_task__destroy(skel);
+	bpf_iter_tasks__destroy(skel);
 }
 
 static void test_task_common(struct bpf_iter_attach_opts *opts, int num_unknown, int num_known)
@@ -251,25 +249,42 @@ static void test_task_common(struct bpf_iter_attach_opts *opts, int num_unknown,
 	ASSERT_EQ(num_known_tid, num_known, "check_num_known_tid");
 }
 
-static void test_task_tid(void)
+static void *run_test_task_tid(void *arg)
 {
 	LIBBPF_OPTS(bpf_iter_attach_opts, opts);
 	union bpf_iter_link_info linfo;
 	int num_unknown_tid, num_known_tid;
 
+	ASSERT_NEQ(getpid(), sys_gettid(), "check_new_thread_id");
+
 	memset(&linfo, 0, sizeof(linfo));
-	linfo.task.tid = getpid();
+	linfo.task.tid = sys_gettid();
 	opts.link_info = &linfo;
 	opts.link_info_len = sizeof(linfo);
 	test_task_common(&opts, 0, 1);
 
 	linfo.task.tid = 0;
 	linfo.task.pid = getpid();
-	test_task_common(&opts, 1, 1);
+	/* This includes the parent thread, this thread, watchdog timer thread
+	 * and the do_nothing_wait thread
+	 */
+	test_task_common(&opts, 3, 1);
 
 	test_task_common_nocheck(NULL, &num_unknown_tid, &num_known_tid);
-	ASSERT_GT(num_unknown_tid, 1, "check_num_unknown_tid");
+	ASSERT_GT(num_unknown_tid, 2, "check_num_unknown_tid");
 	ASSERT_EQ(num_known_tid, 1, "check_num_known_tid");
+
+	return NULL;
+}
+
+static void test_task_tid(void)
+{
+	pthread_t thread_id;
+
+	/* Create a new thread so pid and tid aren't the same */
+	ASSERT_OK(pthread_create(&thread_id, NULL, &run_test_task_tid, NULL),
+		  "pthread_create");
+	ASSERT_FALSE(pthread_join(thread_id, NULL), "pthread_join");
 }
 
 static void test_task_pid(void)
@@ -282,7 +297,7 @@ static void test_task_pid(void)
 	opts.link_info = &linfo;
 	opts.link_info_len = sizeof(linfo);
 
-	test_task_common(&opts, 1, 1);
+	test_task_common(&opts, 2, 1);
 }
 
 static void test_task_pidfd(void)
@@ -300,27 +315,95 @@ static void test_task_pidfd(void)
 	opts.link_info = &linfo;
 	opts.link_info_len = sizeof(linfo);
 
-	test_task_common(&opts, 1, 1);
+	test_task_common(&opts, 2, 1);
 
 	close(pidfd);
 }
 
 static void test_task_sleepable(void)
 {
-	struct bpf_iter_task *skel;
+	struct bpf_iter_tasks *skel;
+	int pid, status, err, data_pipe[2], finish_pipe[2], c = 0;
+	char *test_data = NULL;
+	char *test_data_long = NULL;
+	char *data[2];
+
+	if (!ASSERT_OK(pipe(data_pipe), "data_pipe") ||
+	    !ASSERT_OK(pipe(finish_pipe), "finish_pipe"))
+		return;
 
-	skel = bpf_iter_task__open_and_load();
-	if (!ASSERT_OK_PTR(skel, "bpf_iter_task__open_and_load"))
+	skel = bpf_iter_tasks__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "bpf_iter_tasks__open_and_load"))
 		return;
 
+	pid = fork();
+	if (!ASSERT_GE(pid, 0, "fork"))
+		return;
+
+	if (pid == 0) {
+		/* child */
+		close(data_pipe[0]);
+		close(finish_pipe[1]);
+
+		test_data = malloc(sizeof(char) * 10);
+		strncpy(test_data, "test_data", 10);
+		test_data[9] = '\0';
+
+		test_data_long = malloc(sizeof(char) * 5000);
+		for (int i = 0; i < 5000; ++i) {
+			if (i % 2 == 0)
+				test_data_long[i] = 'b';
+			else
+				test_data_long[i] = 'a';
+		}
+		test_data_long[4999] = '\0';
+
+		data[0] = test_data;
+		data[1] = test_data_long;
+
+		write(data_pipe[1], &data, sizeof(data));
+
+		/* keep child alive until after the test */
+		err = read(finish_pipe[0], &c, 1);
+		if (err != 1)
+			exit(-1);
+
+		close(data_pipe[1]);
+		close(finish_pipe[0]);
+		_exit(0);
+	}
+
+	/* parent */
+	close(data_pipe[1]);
+	close(finish_pipe[0]);
+
+	err = read(data_pipe[0], &data, sizeof(data));
+	ASSERT_EQ(err, sizeof(data), "read_check");
+
+	skel->bss->user_ptr = data[0];
+	skel->bss->user_ptr_long = data[1];
+	skel->bss->pid = pid;
+
 	do_dummy_read(skel->progs.dump_task_sleepable);
 
 	ASSERT_GT(skel->bss->num_expected_failure_copy_from_user_task, 0,
 		  "num_expected_failure_copy_from_user_task");
 	ASSERT_GT(skel->bss->num_success_copy_from_user_task, 0,
 		  "num_success_copy_from_user_task");
+	ASSERT_GT(skel->bss->num_expected_failure_copy_from_user_task_str, 0,
+		  "num_expected_failure_copy_from_user_task_str");
+	ASSERT_GT(skel->bss->num_success_copy_from_user_task_str, 0,
+		  "num_success_copy_from_user_task_str");
+
+	bpf_iter_tasks__destroy(skel);
 
-	bpf_iter_task__destroy(skel);
+	write(finish_pipe[1], &c, 1);
+	err = waitpid(pid, &status, 0);
+	ASSERT_EQ(err, pid, "waitpid");
+	ASSERT_EQ(status, 0, "zero_child_exit");
+
+	close(data_pipe[0]);
+	close(finish_pipe[1]);
 }
 
 static void test_task_stack(void)
@@ -334,6 +417,8 @@ static void test_task_stack(void)
 	do_dummy_read(skel->progs.dump_task_stack);
 	do_dummy_read(skel->progs.get_task_user_stacks);
 
+	ASSERT_EQ(skel->bss->num_user_stacks, 1, "num_user_stacks");
+
 	bpf_iter_task_stack__destroy(skel);
 }
 
@@ -413,7 +498,7 @@ static int do_btf_read(struct bpf_iter_task_btf *skel)
 		goto free_link;
 	}
 
-	if (CHECK(err < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(err, 0, "read"))
 		goto free_link;
 
 	ASSERT_HAS_SUBSTR(taskbuf, "(struct task_struct)",
@@ -526,11 +611,11 @@ static int do_read_with_fd(int iter_fd, const char *expected,
 	start = 0;
 	while ((len = read(iter_fd, buf + start, read_buf_len)) > 0) {
 		start += len;
-		if (CHECK(start >= 16, "read", "read len %d\n", len))
+		if (!ASSERT_LT(start, 16, "read"))
 			return -1;
 		read_buf_len = read_one_char ? 1 : 16 - start;
 	}
-	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(len, 0, "read"))
 		return -1;
 
 	if (!ASSERT_STREQ(buf, expected, "read"))
@@ -571,8 +656,7 @@ static int do_read(const char *path, const char *expected)
 	int err, iter_fd;
 
 	iter_fd = open(path, O_RDONLY);
-	if (CHECK(iter_fd < 0, "open", "open %s failed: %s\n",
-		  path, strerror(errno)))
+	if (!ASSERT_GE(iter_fd, 0, "open"))
 		return -1;
 
 	err = do_read_with_fd(iter_fd, expected, false);
@@ -600,7 +684,7 @@ static void test_file_iter(void)
 	unlink(path);
 
 	err = bpf_link__pin(link, path);
-	if (CHECK(err, "pin_iter", "pin_iter to %s failed: %d\n", path, err))
+	if (!ASSERT_OK(err, "pin_iter"))
 		goto free_link;
 
 	err = do_read(path, "abcd");
@@ -651,12 +735,10 @@ static void test_overflow(bool test_e2big_overflow, bool ret1)
 	 * overflow and needs restart.
 	 */
 	map1_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 8, 1, NULL);
-	if (CHECK(map1_fd < 0, "bpf_map_create",
-		  "map_creation failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(map1_fd, 0, "bpf_map_create"))
 		goto out;
 	map2_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 8, 1, NULL);
-	if (CHECK(map2_fd < 0, "bpf_map_create",
-		  "map_creation failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(map2_fd, 0, "bpf_map_create"))
 		goto free_map1;
 
 	/* bpf_seq_printf kernel buffer is 8 pages, so one map
@@ -684,15 +766,13 @@ static void test_overflow(bool test_e2big_overflow, bool ret1)
 
 	/* setup filtering map_id in bpf program */
 	map_info_len = sizeof(map_info);
-	err = bpf_obj_get_info_by_fd(map1_fd, &map_info, &map_info_len);
-	if (CHECK(err, "get_map_info", "get map info failed: %s\n",
-		  strerror(errno)))
+	err = bpf_map_get_info_by_fd(map1_fd, &map_info, &map_info_len);
+	if (!ASSERT_OK(err, "get_map_info"))
 		goto free_map2;
 	skel->bss->map1_id = map_info.id;
 
-	err = bpf_obj_get_info_by_fd(map2_fd, &map_info, &map_info_len);
-	if (CHECK(err, "get_map_info", "get map info failed: %s\n",
-		  strerror(errno)))
+	err = bpf_map_get_info_by_fd(map2_fd, &map_info, &map_info_len);
+	if (!ASSERT_OK(err, "get_map_info"))
 		goto free_map2;
 	skel->bss->map2_id = map_info.id;
 
@@ -705,7 +785,7 @@ static void test_overflow(bool test_e2big_overflow, bool ret1)
 		goto free_link;
 
 	buf = malloc(expected_read_len);
-	if (!buf)
+	if (!ASSERT_OK_PTR(buf, "malloc"))
 		goto close_iter;
 
 	/* do read */
@@ -714,16 +794,14 @@ static void test_overflow(bool test_e2big_overflow, bool ret1)
 		while ((len = read(iter_fd, buf, expected_read_len)) > 0)
 			total_read_len += len;
 
-		CHECK(len != -1 || errno != E2BIG, "read",
-		      "expected ret -1, errno E2BIG, but get ret %d, error %s\n",
-			  len, strerror(errno));
+		ASSERT_EQ(len, -1, "read");
+		ASSERT_EQ(errno, E2BIG, "read");
 		goto free_buf;
 	} else if (!ret1) {
 		while ((len = read(iter_fd, buf, expected_read_len)) > 0)
 			total_read_len += len;
 
-		if (CHECK(len < 0, "read", "read failed: %s\n",
-			  strerror(errno)))
+		if (!ASSERT_GE(len, 0, "read"))
 			goto free_buf;
 	} else {
 		do {
@@ -732,8 +810,7 @@ static void test_overflow(bool test_e2big_overflow, bool ret1)
 				total_read_len += len;
 		} while (len > 0 || len == -EAGAIN);
 
-		if (CHECK(len < 0, "read", "read failed: %s\n",
-			  strerror(errno)))
+		if (!ASSERT_GE(len, 0, "read"))
 			goto free_buf;
 	}
 
@@ -836,7 +913,7 @@ static void test_bpf_hash_map(void)
 	/* do some tests */
 	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
 		;
-	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(len, 0, "read"))
 		goto close_iter;
 
 	/* test results */
@@ -878,6 +955,8 @@ static void test_bpf_percpu_hash_map(void)
 
 	skel->rodata->num_cpus = bpf_num_possible_cpus();
 	val = malloc(8 * bpf_num_possible_cpus());
+	if (!ASSERT_OK_PTR(val, "malloc"))
+		goto out;
 
 	err = bpf_iter_bpf_percpu_hash_map__load(skel);
 	if (!ASSERT_OK_PTR(skel, "bpf_iter_bpf_percpu_hash_map__load"))
@@ -917,7 +996,7 @@ static void test_bpf_percpu_hash_map(void)
 	/* do some tests */
 	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
 		;
-	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(len, 0, "read"))
 		goto close_iter;
 
 	/* test results */
@@ -983,17 +1062,14 @@ static void test_bpf_array_map(void)
 	start = 0;
 	while ((len = read(iter_fd, buf + start, sizeof(buf) - start)) > 0)
 		start += len;
-	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(len, 0, "read"))
 		goto close_iter;
 
 	/* test results */
 	res_first_key = *(__u32 *)buf;
 	res_first_val = *(__u64 *)(buf + sizeof(__u32));
-	if (CHECK(res_first_key != 0 || res_first_val != first_val,
-		  "bpf_seq_write",
-		  "seq_write failure: first key %u vs expected 0, "
-		  " first value %llu vs expected %llu\n",
-		  res_first_key, res_first_val, first_val))
+	if (!ASSERT_EQ(res_first_key, 0, "bpf_seq_write") ||
+			!ASSERT_EQ(res_first_val, first_val, "bpf_seq_write"))
 		goto close_iter;
 
 	if (!ASSERT_EQ(skel->bss->key_sum, expected_key, "key_sum"))
@@ -1057,6 +1133,8 @@ static void test_bpf_percpu_array_map(void)
 
 	skel->rodata->num_cpus = bpf_num_possible_cpus();
 	val = malloc(8 * bpf_num_possible_cpus());
+	if (!ASSERT_OK_PTR(val, "malloc"))
+		goto out;
 
 	err = bpf_iter_bpf_percpu_array_map__load(skel);
 	if (!ASSERT_OK_PTR(skel, "bpf_iter_bpf_percpu_array_map__load"))
@@ -1092,7 +1170,7 @@ static void test_bpf_percpu_array_map(void)
 	/* do some tests */
 	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
 		;
-	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(len, 0, "read"))
 		goto close_iter;
 
 	/* test results */
@@ -1131,6 +1209,7 @@ static void test_bpf_sk_storage_delete(void)
 	sock_fd = socket(AF_INET6, SOCK_STREAM, 0);
 	if (!ASSERT_GE(sock_fd, 0, "socket"))
 		goto out;
+
 	err = bpf_map_update_elem(map_fd, &sock_fd, &val, BPF_NOEXIST);
 	if (!ASSERT_OK(err, "map_update"))
 		goto out;
@@ -1151,14 +1230,19 @@ static void test_bpf_sk_storage_delete(void)
 	/* do some tests */
 	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
 		;
-	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(len, 0, "read"))
 		goto close_iter;
 
 	/* test results */
 	err = bpf_map_lookup_elem(map_fd, &sock_fd, &val);
-	if (CHECK(!err || errno != ENOENT, "bpf_map_lookup_elem",
-		  "map value wasn't deleted (err=%d, errno=%d)\n", err, errno))
-		goto close_iter;
+
+	 /* Note: The following assertions serve to ensure
+	  * the value was deleted. It does so by asserting
+	  * that bpf_map_lookup_elem has failed. This might
+	  * seem counterintuitive at first.
+	  */
+	ASSERT_ERR(err, "bpf_map_lookup_elem");
+	ASSERT_EQ(errno, ENOENT, "bpf_map_lookup_elem");
 
 close_iter:
 	close(iter_fd);
@@ -1203,17 +1287,15 @@ static void test_bpf_sk_storage_get(void)
 	do_dummy_read(skel->progs.fill_socket_owner);
 
 	err = bpf_map_lookup_elem(map_fd, &sock_fd, &val);
-	if (CHECK(err || val != getpid(), "bpf_map_lookup_elem",
-	    "map value wasn't set correctly (expected %d, got %d, err=%d)\n",
-	    getpid(), val, err))
+	if (!ASSERT_OK(err, "bpf_map_lookup_elem") ||
+			!ASSERT_EQ(val, getpid(), "bpf_map_lookup_elem"))
 		goto close_socket;
 
 	do_dummy_read(skel->progs.negate_socket_local_storage);
 
 	err = bpf_map_lookup_elem(map_fd, &sock_fd, &val);
-	CHECK(err || val != -getpid(), "bpf_map_lookup_elem",
-	      "map value wasn't set correctly (expected %d, got %d, err=%d)\n",
-	      -getpid(), val, err);
+	ASSERT_OK(err, "bpf_map_lookup_elem");
+	ASSERT_EQ(val, -getpid(), "bpf_map_lookup_elem");
 
 close_socket:
 	close(sock_fd);
@@ -1221,7 +1303,7 @@ out:
 	bpf_iter_bpf_sk_storage_helpers__destroy(skel);
 }
 
-static void test_bpf_sk_stoarge_map_iter_fd(void)
+static void test_bpf_sk_storage_map_iter_fd(void)
 {
 	struct bpf_iter_bpf_sk_storage_map *skel;
 
@@ -1290,7 +1372,7 @@ static void test_bpf_sk_storage_map(void)
 	/* do some tests */
 	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
 		;
-	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+	if (!ASSERT_GE(len, 0, "read"))
 		goto close_iter;
 
 	/* test results */
@@ -1399,19 +1481,19 @@ static void str_strip_first_line(char *str)
 static void test_task_vma_common(struct bpf_iter_attach_opts *opts)
 {
 	int err, iter_fd = -1, proc_maps_fd = -1;
-	struct bpf_iter_task_vma *skel;
+	struct bpf_iter_task_vmas *skel;
 	int len, read_size = 4;
 	char maps_path[64];
 
-	skel = bpf_iter_task_vma__open();
-	if (!ASSERT_OK_PTR(skel, "bpf_iter_task_vma__open"))
+	skel = bpf_iter_task_vmas__open();
+	if (!ASSERT_OK_PTR(skel, "bpf_iter_task_vmas__open"))
 		return;
 
 	skel->bss->pid = getpid();
 	skel->bss->one_task = opts ? 1 : 0;
 
-	err = bpf_iter_task_vma__load(skel);
-	if (!ASSERT_OK(err, "bpf_iter_task_vma__load"))
+	err = bpf_iter_task_vmas__load(skel);
+	if (!ASSERT_OK(err, "bpf_iter_task_vmas__load"))
 		goto out;
 
 	skel->links.proc_maps = bpf_program__attach_iter(
@@ -1462,7 +1544,78 @@ static void test_task_vma_common(struct bpf_iter_attach_opts *opts)
 out:
 	close(proc_maps_fd);
 	close(iter_fd);
-	bpf_iter_task_vma__destroy(skel);
+	bpf_iter_task_vmas__destroy(skel);
+}
+
+static void test_task_vma_dead_task(void)
+{
+	struct bpf_iter_task_vmas *skel;
+	int wstatus, child_pid = -1;
+	time_t start_tm, cur_tm;
+	int err, iter_fd = -1;
+	int wait_sec = 3;
+
+	skel = bpf_iter_task_vmas__open();
+	if (!ASSERT_OK_PTR(skel, "bpf_iter_task_vmas__open"))
+		return;
+
+	skel->bss->pid = getpid();
+
+	err = bpf_iter_task_vmas__load(skel);
+	if (!ASSERT_OK(err, "bpf_iter_task_vmas__load"))
+		goto out;
+
+	skel->links.proc_maps = bpf_program__attach_iter(
+		skel->progs.proc_maps, NULL);
+
+	if (!ASSERT_OK_PTR(skel->links.proc_maps, "bpf_program__attach_iter")) {
+		skel->links.proc_maps = NULL;
+		goto out;
+	}
+
+	start_tm = time(NULL);
+	cur_tm = start_tm;
+
+	child_pid = fork();
+	if (child_pid == 0) {
+		/* Fork short-lived processes in the background. */
+		while (cur_tm < start_tm + wait_sec) {
+			system("echo > /dev/null");
+			cur_tm = time(NULL);
+		}
+		exit(0);
+	}
+
+	if (!ASSERT_GE(child_pid, 0, "fork_child"))
+		goto out;
+
+	while (cur_tm < start_tm + wait_sec) {
+		iter_fd = bpf_iter_create(bpf_link__fd(skel->links.proc_maps));
+		if (!ASSERT_GE(iter_fd, 0, "create_iter"))
+			goto out;
+
+		/* Drain all data from iter_fd. */
+		while (cur_tm < start_tm + wait_sec) {
+			err = read_fd_into_buffer(iter_fd, task_vma_output, CMP_BUFFER_SIZE);
+			if (!ASSERT_GE(err, 0, "read_iter_fd"))
+				goto out;
+
+			cur_tm = time(NULL);
+
+			if (err == 0)
+				break;
+		}
+
+		close(iter_fd);
+		iter_fd = -1;
+	}
+
+	check_bpf_link_info(skel->progs.proc_maps);
+
+out:
+	waitpid(child_pid, &wstatus, 0);
+	close(iter_fd);
+	bpf_iter_task_vmas__destroy(skel);
 }
 
 void test_bpf_sockmap_map_iter_fd(void)
@@ -1586,6 +1739,8 @@ void test_bpf_iter(void)
 		test_task_file();
 	if (test__start_subtest("task_vma"))
 		test_task_vma();
+	if (test__start_subtest("task_vma_dead_task"))
+		test_task_vma_dead_task();
 	if (test__start_subtest("task_btf"))
 		test_task_btf();
 	if (test__start_subtest("tcp4"))
@@ -1623,7 +1778,7 @@ void test_bpf_iter(void)
 	if (test__start_subtest("bpf_sk_storage_map"))
 		test_bpf_sk_storage_map();
 	if (test__start_subtest("bpf_sk_storage_map_iter_fd"))
-		test_bpf_sk_stoarge_map_iter_fd();
+		test_bpf_sk_storage_map_iter_fd();
 	if (test__start_subtest("bpf_sk_storage_delete"))
 		test_bpf_sk_storage_delete();
 	if (test__start_subtest("bpf_sk_storage_get"))
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c
index b52ff8ce34db..16bed9dd8e6a 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c
@@ -95,7 +95,7 @@ static unsigned short get_local_port(int fd)
 	struct sockaddr_in6 addr;
 	socklen_t addrlen = sizeof(addr);
 
-	if (!getsockname(fd, &addr, &addrlen))
+	if (!getsockname(fd, (struct sockaddr *)&addr, &addrlen))
 		return ntohs(addr.sin6_port);
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c
index a4d0cc9d3367..ecc3d47919ad 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c
@@ -11,6 +11,7 @@
 #include "ksym_race.skel.h"
 #include "bpf_mod_race.skel.h"
 #include "kfunc_call_race.skel.h"
+#include "testing_helpers.h"
 
 /* This test crafts a race between btf_try_get_module and do_init_module, and
  * checks whether btf_try_get_module handles the invocation for a well-formed
@@ -44,35 +45,10 @@ enum bpf_test_state {
 
 static _Atomic enum bpf_test_state state = _TS_INVALID;
 
-static int sys_finit_module(int fd, const char *param_values, int flags)
-{
-	return syscall(__NR_finit_module, fd, param_values, flags);
-}
-
-static int sys_delete_module(const char *name, unsigned int flags)
-{
-	return syscall(__NR_delete_module, name, flags);
-}
-
-static int load_module(const char *mod)
-{
-	int ret, fd;
-
-	fd = open("bpf_testmod.ko", O_RDONLY);
-	if (fd < 0)
-		return fd;
-
-	ret = sys_finit_module(fd, "", 0);
-	close(fd);
-	if (ret < 0)
-		return ret;
-	return 0;
-}
-
 static void *load_module_thread(void *p)
 {
 
-	if (!ASSERT_NEQ(load_module("bpf_testmod.ko"), 0, "load_module_thread must fail"))
+	if (!ASSERT_NEQ(load_bpf_testmod(false), 0, "load_module_thread must fail"))
 		atomic_store(&state, TS_MODULE_LOAD);
 	else
 		atomic_store(&state, TS_MODULE_LOAD_FAIL);
@@ -102,7 +78,7 @@ static int test_setup_uffd(void *fault_addr)
 	}
 
 	uffd_register.range.start = (unsigned long)fault_addr;
-	uffd_register.range.len = 4096;
+	uffd_register.range.len = getpagesize();
 	uffd_register.mode = UFFDIO_REGISTER_MODE_MISSING;
 	if (ioctl(uffd, UFFDIO_REGISTER, &uffd_register)) {
 		close(uffd);
@@ -124,7 +100,7 @@ static void test_bpf_mod_race_config(const struct test_config *config)
 	if (!ASSERT_NEQ(fault_addr, MAP_FAILED, "mmap for uffd registration"))
 		return;
 
-	if (!ASSERT_OK(sys_delete_module("bpf_testmod", 0), "unload bpf_testmod"))
+	if (!ASSERT_OK(unload_bpf_testmod(false), "unload bpf_testmod"))
 		goto end_mmap;
 
 	skel = bpf_mod_race__open();
@@ -202,8 +178,8 @@ end_destroy:
 	bpf_mod_race__destroy(skel);
 	ASSERT_OK(kern_sync_rcu(), "kern_sync_rcu");
 end_module:
-	sys_delete_module("bpf_testmod", 0);
-	ASSERT_OK(load_module("bpf_testmod.ko"), "restore bpf_testmod");
+	unload_bpf_testmod(false);
+	ASSERT_OK(load_bpf_testmod(false), "restore bpf_testmod");
 end_mmap:
 	munmap(fault_addr, 4096);
 	atomic_store(&state, _TS_INVALID);
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
index c8ba4009e4ab..dd6512fa652b 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
@@ -63,6 +63,12 @@ static void test_bpf_nf_ct(int mode)
 		.repeat = 1,
 	);
 
+	if (SYS_NOFAIL("iptables-legacy --version")) {
+		fprintf(stdout, "Missing required iptables-legacy tool\n");
+		test__skip();
+		return;
+	}
+
 	skel = test_bpf_nf__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "test_bpf_nf__open_and_load"))
 		return;
@@ -72,11 +78,14 @@ static void test_bpf_nf_ct(int mode)
 	if (!ASSERT_OK(system(cmd), cmd))
 		goto end;
 
-	srv_port = (mode == TEST_XDP) ? 5005 : 5006;
-	srv_fd = start_server(AF_INET, SOCK_STREAM, "127.0.0.1", srv_port, TIMEOUT_MS);
+	srv_fd = start_server(AF_INET, SOCK_STREAM, "127.0.0.1", 0, TIMEOUT_MS);
 	if (!ASSERT_GE(srv_fd, 0, "start_server"))
 		goto end;
 
+	srv_port = get_socket_local_port(srv_fd);
+	if (!ASSERT_GE(srv_port, 0, "get_sock_local_port"))
+		goto end;
+
 	client_fd = connect_to_server(srv_fd);
 	if (!ASSERT_GE(client_fd, 0, "connect_to_server"))
 		goto end;
@@ -91,7 +100,7 @@ static void test_bpf_nf_ct(int mode)
 	skel->bss->saddr = peer_addr.sin_addr.s_addr;
 	skel->bss->sport = peer_addr.sin_port;
 	skel->bss->daddr = peer_addr.sin_addr.s_addr;
-	skel->bss->dport = htons(srv_port);
+	skel->bss->dport = srv_port;
 
 	if (mode == TEST_XDP)
 		prog_fd = bpf_program__fd(skel->progs.nf_xdp_ct_test);
@@ -104,6 +113,7 @@ static void test_bpf_nf_ct(int mode)
 
 	ASSERT_EQ(skel->bss->test_einval_bpf_tuple, -EINVAL, "Test EINVAL for NULL bpf_tuple");
 	ASSERT_EQ(skel->bss->test_einval_reserved, -EINVAL, "Test EINVAL for reserved not set to 0");
+	ASSERT_EQ(skel->bss->test_einval_reserved_new, -EINVAL, "Test EINVAL for reserved in new struct not set to 0");
 	ASSERT_EQ(skel->bss->test_einval_netns_id, -EINVAL, "Test EINVAL for netns_id < -1");
 	ASSERT_EQ(skel->bss->test_einval_len_opts, -EINVAL, "Test EINVAL for len__opts != NF_BPF_CT_OPTS_SZ");
 	ASSERT_EQ(skel->bss->test_eproto_l4proto, -EPROTO, "Test EPROTO for l4proto != TCP or UDP");
@@ -122,13 +132,20 @@ static void test_bpf_nf_ct(int mode)
 	ASSERT_EQ(skel->bss->test_exist_lookup_mark, 43, "Test existing connection lookup ctmark");
 	ASSERT_EQ(skel->data->test_snat_addr, 0, "Test for source natting");
 	ASSERT_EQ(skel->data->test_dnat_addr, 0, "Test for destination natting");
+	ASSERT_EQ(skel->data->test_ct_zone_id_alloc_entry, 0, "Test for alloc new entry in specified ct zone");
+	ASSERT_EQ(skel->data->test_ct_zone_id_insert_entry, 0, "Test for insert new entry in specified ct zone");
+	ASSERT_EQ(skel->data->test_ct_zone_id_succ_lookup, 0, "Test for successful lookup in specified ct_zone");
+	ASSERT_EQ(skel->bss->test_ct_zone_dir_enoent_lookup, -ENOENT, "Test ENOENT for lookup with wrong ct zone dir");
+	ASSERT_EQ(skel->bss->test_ct_zone_id_enoent_lookup, -ENOENT, "Test ENOENT for lookup in wrong ct zone");
+
 end:
-	if (srv_client_fd != -1)
-		close(srv_client_fd);
 	if (client_fd != -1)
 		close(client_fd);
+	if (srv_client_fd != -1)
+		close(srv_client_fd);
 	if (srv_fd != -1)
 		close(srv_fd);
+
 	snprintf(cmd, sizeof(cmd), iptables, "-D");
 	system(cmd);
 	test_bpf_nf__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
index e1c1e521cca2..f09d6ac2ef09 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
@@ -25,7 +25,7 @@ void serial_test_bpf_obj_id(void)
 	 */
 	__u32 map_ids[nr_iters + 1];
 	char jited_insns[128], xlated_insns[128], zeros[128], tp_name[128];
-	__u32 i, next_id, info_len, nr_id_found, duration = 0;
+	__u32 i, next_id, info_len, nr_id_found;
 	struct timespec real_time_ts, boot_time_ts;
 	int err = 0;
 	__u64 array_value;
@@ -33,18 +33,18 @@ void serial_test_bpf_obj_id(void)
 	time_t now, load_time;
 
 	err = bpf_prog_get_fd_by_id(0);
-	CHECK(err >= 0 || errno != ENOENT,
-	      "get-fd-by-notexist-prog-id", "err %d errno %d\n", err, errno);
+	ASSERT_LT(err, 0, "bpf_prog_get_fd_by_id");
+	ASSERT_EQ(errno, ENOENT, "bpf_prog_get_fd_by_id");
 
 	err = bpf_map_get_fd_by_id(0);
-	CHECK(err >= 0 || errno != ENOENT,
-	      "get-fd-by-notexist-map-id", "err %d errno %d\n", err, errno);
+	ASSERT_LT(err, 0, "bpf_map_get_fd_by_id");
+	ASSERT_EQ(errno, ENOENT, "bpf_map_get_fd_by_id");
 
 	err = bpf_link_get_fd_by_id(0);
-	CHECK(err >= 0 || errno != ENOENT,
-	      "get-fd-by-notexist-link-id", "err %d errno %d\n", err, errno);
+	ASSERT_LT(err, 0, "bpf_map_get_fd_by_id");
+	ASSERT_EQ(errno, ENOENT, "bpf_map_get_fd_by_id");
 
-	/* Check bpf_obj_get_info_by_fd() */
+	/* Check bpf_map_get_info_by_fd() */
 	bzero(zeros, sizeof(zeros));
 	for (i = 0; i < nr_iters; i++) {
 		now = time(NULL);
@@ -53,25 +53,26 @@ void serial_test_bpf_obj_id(void)
 		/* test_obj_id.o is a dumb prog. It should never fail
 		 * to load.
 		 */
-		if (CHECK_FAIL(err))
+		if (!ASSERT_OK(err, "bpf_prog_test_load"))
 			continue;
 
 		/* Insert a magic value to the map */
 		map_fds[i] = bpf_find_map(__func__, objs[i], "test_map_id");
-		if (CHECK_FAIL(map_fds[i] < 0))
+		if (!ASSERT_GE(map_fds[i], 0, "bpf_find_map"))
 			goto done;
+
 		err = bpf_map_update_elem(map_fds[i], &array_key,
 					  &array_magic_value, 0);
-		if (CHECK_FAIL(err))
+		if (!ASSERT_OK(err, "bpf_map_update_elem"))
 			goto done;
 
-		prog = bpf_object__find_program_by_name(objs[i],
-							"test_obj_id");
-		if (CHECK_FAIL(!prog))
+		prog = bpf_object__find_program_by_name(objs[i], "test_obj_id");
+		if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
 			goto done;
+
 		links[i] = bpf_program__attach(prog);
 		err = libbpf_get_error(links[i]);
-		if (CHECK(err, "prog_attach", "prog #%d, err %d\n", i, err)) {
+		if (!ASSERT_OK(err, "bpf_program__attach")) {
 			links[i] = NULL;
 			goto done;
 		}
@@ -79,26 +80,16 @@ void serial_test_bpf_obj_id(void)
 		/* Check getting map info */
 		info_len = sizeof(struct bpf_map_info) * 2;
 		bzero(&map_infos[i], info_len);
-		err = bpf_obj_get_info_by_fd(map_fds[i], &map_infos[i],
+		err = bpf_map_get_info_by_fd(map_fds[i], &map_infos[i],
 					     &info_len);
-		if (CHECK(err ||
-			  map_infos[i].type != BPF_MAP_TYPE_ARRAY ||
-			  map_infos[i].key_size != sizeof(__u32) ||
-			  map_infos[i].value_size != sizeof(__u64) ||
-			  map_infos[i].max_entries != 1 ||
-			  map_infos[i].map_flags != 0 ||
-			  info_len != sizeof(struct bpf_map_info) ||
-			  strcmp((char *)map_infos[i].name, expected_map_name),
-			  "get-map-info(fd)",
-			  "err %d errno %d type %d(%d) info_len %u(%zu) key_size %u value_size %u max_entries %u map_flags %X name %s(%s)\n",
-			  err, errno,
-			  map_infos[i].type, BPF_MAP_TYPE_ARRAY,
-			  info_len, sizeof(struct bpf_map_info),
-			  map_infos[i].key_size,
-			  map_infos[i].value_size,
-			  map_infos[i].max_entries,
-			  map_infos[i].map_flags,
-			  map_infos[i].name, expected_map_name))
+		if (!ASSERT_OK(err, "bpf_map_get_info_by_fd") ||
+				!ASSERT_EQ(map_infos[i].type, BPF_MAP_TYPE_ARRAY, "map_type") ||
+				!ASSERT_EQ(map_infos[i].key_size, sizeof(__u32), "key_size") ||
+				!ASSERT_EQ(map_infos[i].value_size, sizeof(__u64), "value_size") ||
+				!ASSERT_EQ(map_infos[i].max_entries, 1, "max_entries") ||
+				!ASSERT_EQ(map_infos[i].map_flags, 0, "map_flags") ||
+				!ASSERT_EQ(info_len, sizeof(struct bpf_map_info), "map_info_len") ||
+				!ASSERT_STREQ((char *)map_infos[i].name, expected_map_name, "map_name"))
 			goto done;
 
 		/* Check getting prog info */
@@ -112,48 +103,34 @@ void serial_test_bpf_obj_id(void)
 		prog_infos[i].xlated_prog_len = sizeof(xlated_insns);
 		prog_infos[i].map_ids = ptr_to_u64(map_ids + i);
 		prog_infos[i].nr_map_ids = 2;
+
 		err = clock_gettime(CLOCK_REALTIME, &real_time_ts);
-		if (CHECK_FAIL(err))
+		if (!ASSERT_OK(err, "clock_gettime"))
 			goto done;
+
 		err = clock_gettime(CLOCK_BOOTTIME, &boot_time_ts);
-		if (CHECK_FAIL(err))
+		if (!ASSERT_OK(err, "clock_gettime"))
 			goto done;
-		err = bpf_obj_get_info_by_fd(prog_fds[i], &prog_infos[i],
-					     &info_len);
+
+		err = bpf_prog_get_info_by_fd(prog_fds[i], &prog_infos[i],
+					      &info_len);
 		load_time = (real_time_ts.tv_sec - boot_time_ts.tv_sec)
 			+ (prog_infos[i].load_time / nsec_per_sec);
-		if (CHECK(err ||
-			  prog_infos[i].type != BPF_PROG_TYPE_RAW_TRACEPOINT ||
-			  info_len != sizeof(struct bpf_prog_info) ||
-			  (env.jit_enabled && !prog_infos[i].jited_prog_len) ||
-			  (env.jit_enabled &&
-			   !memcmp(jited_insns, zeros, sizeof(zeros))) ||
-			  !prog_infos[i].xlated_prog_len ||
-			  !memcmp(xlated_insns, zeros, sizeof(zeros)) ||
-			  load_time < now - 60 || load_time > now + 60 ||
-			  prog_infos[i].created_by_uid != my_uid ||
-			  prog_infos[i].nr_map_ids != 1 ||
-			  *(int *)(long)prog_infos[i].map_ids != map_infos[i].id ||
-			  strcmp((char *)prog_infos[i].name, expected_prog_name),
-			  "get-prog-info(fd)",
-			  "err %d errno %d i %d type %d(%d) info_len %u(%zu) "
-			  "jit_enabled %d jited_prog_len %u xlated_prog_len %u "
-			  "jited_prog %d xlated_prog %d load_time %lu(%lu) "
-			  "uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) "
-			  "name %s(%s)\n",
-			  err, errno, i,
-			  prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER,
-			  info_len, sizeof(struct bpf_prog_info),
-			  env.jit_enabled,
-			  prog_infos[i].jited_prog_len,
-			  prog_infos[i].xlated_prog_len,
-			  !!memcmp(jited_insns, zeros, sizeof(zeros)),
-			  !!memcmp(xlated_insns, zeros, sizeof(zeros)),
-			  load_time, now,
-			  prog_infos[i].created_by_uid, my_uid,
-			  prog_infos[i].nr_map_ids, 1,
-			  *(int *)(long)prog_infos[i].map_ids, map_infos[i].id,
-			  prog_infos[i].name, expected_prog_name))
+
+		if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd") ||
+				!ASSERT_EQ(prog_infos[i].type, BPF_PROG_TYPE_RAW_TRACEPOINT, "prog_type") ||
+				!ASSERT_EQ(info_len, sizeof(struct bpf_prog_info), "prog_info_len") ||
+				!ASSERT_FALSE((env.jit_enabled && !prog_infos[i].jited_prog_len), "jited_prog_len") ||
+				!ASSERT_FALSE((env.jit_enabled && !memcmp(jited_insns, zeros, sizeof(zeros))),
+					"jited_insns") ||
+				!ASSERT_NEQ(prog_infos[i].xlated_prog_len, 0, "xlated_prog_len") ||
+				!ASSERT_NEQ(memcmp(xlated_insns, zeros, sizeof(zeros)), 0, "xlated_insns") ||
+				!ASSERT_GE(load_time, (now - 60), "load_time") ||
+				!ASSERT_LE(load_time, (now + 60), "load_time") ||
+				!ASSERT_EQ(prog_infos[i].created_by_uid, my_uid, "created_by_uid") ||
+				!ASSERT_EQ(prog_infos[i].nr_map_ids, 1, "nr_map_ids") ||
+				!ASSERT_EQ(*(int *)(long)prog_infos[i].map_ids, map_infos[i].id, "map_ids") ||
+				!ASSERT_STREQ((char *)prog_infos[i].name, expected_prog_name, "prog_name"))
 			goto done;
 
 		/* Check getting link info */
@@ -161,27 +138,14 @@ void serial_test_bpf_obj_id(void)
 		bzero(&link_infos[i], info_len);
 		link_infos[i].raw_tracepoint.tp_name = ptr_to_u64(&tp_name);
 		link_infos[i].raw_tracepoint.tp_name_len = sizeof(tp_name);
-		err = bpf_obj_get_info_by_fd(bpf_link__fd(links[i]),
-					     &link_infos[i], &info_len);
-		if (CHECK(err ||
-			  link_infos[i].type != BPF_LINK_TYPE_RAW_TRACEPOINT ||
-			  link_infos[i].prog_id != prog_infos[i].id ||
-			  link_infos[i].raw_tracepoint.tp_name != ptr_to_u64(&tp_name) ||
-			  strcmp(u64_to_ptr(link_infos[i].raw_tracepoint.tp_name),
-				 "sys_enter") ||
-			  info_len != sizeof(struct bpf_link_info),
-			  "get-link-info(fd)",
-			  "err %d errno %d info_len %u(%zu) type %d(%d) id %d "
-			  "prog_id %d (%d) tp_name %s(%s)\n",
-			  err, errno,
-			  info_len, sizeof(struct bpf_link_info),
-			  link_infos[i].type, BPF_LINK_TYPE_RAW_TRACEPOINT,
-			  link_infos[i].id,
-			  link_infos[i].prog_id, prog_infos[i].id,
-			  (const char *)u64_to_ptr(link_infos[i].raw_tracepoint.tp_name),
-			  "sys_enter"))
+		err = bpf_link_get_info_by_fd(bpf_link__fd(links[i]),
+					      &link_infos[i], &info_len);
+		if (!ASSERT_OK(err, "bpf_link_get_info_by_fd") ||
+				!ASSERT_EQ(link_infos[i].type, BPF_LINK_TYPE_RAW_TRACEPOINT, "link_type") ||
+				!ASSERT_EQ(link_infos[i].prog_id, prog_infos[i].id, "prog_id") ||
+				!ASSERT_EQ(link_infos[i].raw_tracepoint.tp_name, ptr_to_u64(&tp_name), "&tp_name") ||
+				!ASSERT_STREQ(u64_to_ptr(link_infos[i].raw_tracepoint.tp_name), "sys_enter", "tp_name"))
 			goto done;
-
 	}
 
 	/* Check bpf_prog_get_next_id() */
@@ -190,7 +154,7 @@ void serial_test_bpf_obj_id(void)
 	while (!bpf_prog_get_next_id(next_id, &next_id)) {
 		struct bpf_prog_info prog_info = {};
 		__u32 saved_map_id;
-		int prog_fd;
+		int prog_fd, cmp_res;
 
 		info_len = sizeof(prog_info);
 
@@ -198,9 +162,7 @@ void serial_test_bpf_obj_id(void)
 		if (prog_fd < 0 && errno == ENOENT)
 			/* The bpf_prog is in the dead row */
 			continue;
-		if (CHECK(prog_fd < 0, "get-prog-fd(next_id)",
-			  "prog_fd %d next_id %d errno %d\n",
-			  prog_fd, next_id, errno))
+		if (!ASSERT_GE(prog_fd, 0, "bpf_prog_get_fd_by_id"))
 			break;
 
 		for (i = 0; i < nr_iters; i++)
@@ -217,10 +179,9 @@ void serial_test_bpf_obj_id(void)
 		 * prog_info.map_ids = NULL
 		 */
 		prog_info.nr_map_ids = 1;
-		err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len);
-		if (CHECK(!err || errno != EFAULT,
-			  "get-prog-fd-bad-nr-map-ids", "err %d errno %d(%d)",
-			  err, errno, EFAULT))
+		err = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &info_len);
+		if (!ASSERT_ERR(err, "bpf_prog_get_info_by_fd") ||
+				!ASSERT_EQ(errno, EFAULT, "bpf_prog_get_info_by_fd"))
 			break;
 		bzero(&prog_info, sizeof(prog_info));
 		info_len = sizeof(prog_info);
@@ -228,30 +189,25 @@ void serial_test_bpf_obj_id(void)
 		saved_map_id = *(int *)((long)prog_infos[i].map_ids);
 		prog_info.map_ids = prog_infos[i].map_ids;
 		prog_info.nr_map_ids = 2;
-		err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len);
+		err = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &info_len);
 		prog_infos[i].jited_prog_insns = 0;
 		prog_infos[i].xlated_prog_insns = 0;
-		CHECK(err || info_len != sizeof(struct bpf_prog_info) ||
-		      memcmp(&prog_info, &prog_infos[i], info_len) ||
-		      *(int *)(long)prog_info.map_ids != saved_map_id,
-		      "get-prog-info(next_id->fd)",
-		      "err %d errno %d info_len %u(%zu) memcmp %d map_id %u(%u)\n",
-		      err, errno, info_len, sizeof(struct bpf_prog_info),
-		      memcmp(&prog_info, &prog_infos[i], info_len),
-		      *(int *)(long)prog_info.map_ids, saved_map_id);
+		cmp_res = memcmp(&prog_info, &prog_infos[i], info_len);
+
+		ASSERT_OK(err, "bpf_prog_get_info_by_fd");
+		ASSERT_EQ(info_len, sizeof(struct bpf_prog_info), "prog_info_len");
+		ASSERT_OK(cmp_res, "memcmp");
+		ASSERT_EQ(*(int *)(long)prog_info.map_ids, saved_map_id, "map_id");
 		close(prog_fd);
 	}
-	CHECK(nr_id_found != nr_iters,
-	      "check total prog id found by get_next_id",
-	      "nr_id_found %u(%u)\n",
-	      nr_id_found, nr_iters);
+	ASSERT_EQ(nr_id_found, nr_iters, "prog_nr_id_found");
 
 	/* Check bpf_map_get_next_id() */
 	nr_id_found = 0;
 	next_id = 0;
 	while (!bpf_map_get_next_id(next_id, &next_id)) {
 		struct bpf_map_info map_info = {};
-		int map_fd;
+		int map_fd, cmp_res;
 
 		info_len = sizeof(map_info);
 
@@ -259,9 +215,7 @@ void serial_test_bpf_obj_id(void)
 		if (map_fd < 0 && errno == ENOENT)
 			/* The bpf_map is in the dead row */
 			continue;
-		if (CHECK(map_fd < 0, "get-map-fd(next_id)",
-			  "map_fd %d next_id %u errno %d\n",
-			  map_fd, next_id, errno))
+		if (!ASSERT_GE(map_fd, 0, "bpf_map_get_fd_by_id"))
 			break;
 
 		for (i = 0; i < nr_iters; i++)
@@ -274,25 +228,19 @@ void serial_test_bpf_obj_id(void)
 		nr_id_found++;
 
 		err = bpf_map_lookup_elem(map_fd, &array_key, &array_value);
-		if (CHECK_FAIL(err))
+		if (!ASSERT_OK(err, "bpf_map_lookup_elem"))
 			goto done;
 
-		err = bpf_obj_get_info_by_fd(map_fd, &map_info, &info_len);
-		CHECK(err || info_len != sizeof(struct bpf_map_info) ||
-		      memcmp(&map_info, &map_infos[i], info_len) ||
-		      array_value != array_magic_value,
-		      "check get-map-info(next_id->fd)",
-		      "err %d errno %d info_len %u(%zu) memcmp %d array_value %llu(%llu)\n",
-		      err, errno, info_len, sizeof(struct bpf_map_info),
-		      memcmp(&map_info, &map_infos[i], info_len),
-		      array_value, array_magic_value);
+		err = bpf_map_get_info_by_fd(map_fd, &map_info, &info_len);
+		cmp_res = memcmp(&map_info, &map_infos[i], info_len);
+		ASSERT_OK(err, "bpf_map_get_info_by_fd");
+		ASSERT_EQ(info_len, sizeof(struct bpf_map_info), "info_len");
+		ASSERT_OK(cmp_res, "memcmp");
+		ASSERT_EQ(array_value, array_magic_value, "array_value");
 
 		close(map_fd);
 	}
-	CHECK(nr_id_found != nr_iters,
-	      "check total map id found by get_next_id",
-	      "nr_id_found %u(%u)\n",
-	      nr_id_found, nr_iters);
+	ASSERT_EQ(nr_id_found, nr_iters, "map_nr_id_found");
 
 	/* Check bpf_link_get_next_id() */
 	nr_id_found = 0;
@@ -308,9 +256,7 @@ void serial_test_bpf_obj_id(void)
 		if (link_fd < 0 && errno == ENOENT)
 			/* The bpf_link is in the dead row */
 			continue;
-		if (CHECK(link_fd < 0, "get-link-fd(next_id)",
-			  "link_fd %d next_id %u errno %d\n",
-			  link_fd, next_id, errno))
+		if (!ASSERT_GE(link_fd, 0, "bpf_link_get_fd_by_id"))
 			break;
 
 		for (i = 0; i < nr_iters; i++)
@@ -322,20 +268,16 @@ void serial_test_bpf_obj_id(void)
 
 		nr_id_found++;
 
-		err = bpf_obj_get_info_by_fd(link_fd, &link_info, &info_len);
+		err = bpf_link_get_info_by_fd(link_fd, &link_info, &info_len);
 		cmp_res = memcmp(&link_info, &link_infos[i],
 				offsetof(struct bpf_link_info, raw_tracepoint));
-		CHECK(err || info_len != sizeof(link_info) || cmp_res,
-		      "check get-link-info(next_id->fd)",
-		      "err %d errno %d info_len %u(%zu) memcmp %d\n",
-		      err, errno, info_len, sizeof(struct bpf_link_info),
-		      cmp_res);
+		ASSERT_OK(err, "bpf_link_get_info_by_fd");
+		ASSERT_EQ(info_len, sizeof(link_info), "info_len");
+		ASSERT_OK(cmp_res, "memcmp");
 
 		close(link_fd);
 	}
-	CHECK(nr_id_found != nr_iters,
-	      "check total link id found by get_next_id",
-	      "nr_id_found %u(%u)\n", nr_id_found, nr_iters);
+	ASSERT_EQ(nr_id_found, nr_iters, "link_nr_id_found");
 
 done:
 	for (i = 0; i < nr_iters; i++) {
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c
new file mode 100644
index 000000000000..ee0458a5ce78
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c
@@ -0,0 +1,269 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+#define _GNU_SOURCE
+#include <test_progs.h>
+#include <bpf/btf.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <linux/unistd.h>
+#include <linux/mount.h>
+#include <sys/syscall.h>
+#include "bpf/libbpf_internal.h"
+
+static inline int sys_fsopen(const char *fsname, unsigned flags)
+{
+	return syscall(__NR_fsopen, fsname, flags);
+}
+
+static inline int sys_fsconfig(int fs_fd, unsigned cmd, const char *key, const void *val, int aux)
+{
+	return syscall(__NR_fsconfig, fs_fd, cmd, key, val, aux);
+}
+
+static inline int sys_fsmount(int fs_fd, unsigned flags, unsigned ms_flags)
+{
+	return syscall(__NR_fsmount, fs_fd, flags, ms_flags);
+}
+
+__attribute__((unused))
+static inline int sys_move_mount(int from_dfd, const char *from_path,
+			         int to_dfd, const char *to_path,
+			         unsigned int ms_flags)
+{
+	return syscall(__NR_move_mount, from_dfd, from_path, to_dfd, to_path, ms_flags);
+}
+
+static void bpf_obj_pinning_detached(void)
+{
+	LIBBPF_OPTS(bpf_obj_pin_opts, pin_opts);
+	LIBBPF_OPTS(bpf_obj_get_opts, get_opts);
+	int fs_fd = -1, mnt_fd = -1;
+	int map_fd = -1, map_fd2 = -1;
+	int zero = 0, src_value, dst_value, err;
+	const char *map_name = "fsmount_map";
+
+	/* A bunch of below UAPI calls are constructed based on reading:
+	 * https://brauner.io/2023/02/28/mounting-into-mount-namespaces.html
+	 */
+
+	/* create VFS context */
+	fs_fd = sys_fsopen("bpf", 0);
+	if (!ASSERT_GE(fs_fd, 0, "fs_fd"))
+		goto cleanup;
+
+	/* instantiate FS object */
+	err = sys_fsconfig(fs_fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0);
+	if (!ASSERT_OK(err, "fs_create"))
+		goto cleanup;
+
+	/* create O_PATH fd for detached mount */
+	mnt_fd = sys_fsmount(fs_fd, 0, 0);
+	if (!ASSERT_GE(mnt_fd, 0, "mnt_fd"))
+		goto cleanup;
+
+	/* If we wanted to expose detached mount in the file system, we'd do
+	 * something like below. But the whole point is that we actually don't
+	 * even have to expose BPF FS in the file system to be able to work
+	 * (pin/get objects) with it.
+	 *
+	 * err = sys_move_mount(mnt_fd, "", -EBADF, mnt_path, MOVE_MOUNT_F_EMPTY_PATH);
+	 * if (!ASSERT_OK(err, "move_mount"))
+	 *	goto cleanup;
+	 */
+
+	/* create BPF map to pin */
+	map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, map_name, 4, 4, 1, NULL);
+	if (!ASSERT_GE(map_fd, 0, "map_fd"))
+		goto cleanup;
+
+	/* pin BPF map into detached BPF FS through mnt_fd */
+	pin_opts.file_flags = BPF_F_PATH_FD;
+	pin_opts.path_fd = mnt_fd;
+	err = bpf_obj_pin_opts(map_fd, map_name, &pin_opts);
+	if (!ASSERT_OK(err, "map_pin"))
+		goto cleanup;
+
+	/* get BPF map from detached BPF FS through mnt_fd */
+	get_opts.file_flags = BPF_F_PATH_FD;
+	get_opts.path_fd = mnt_fd;
+	map_fd2 = bpf_obj_get_opts(map_name, &get_opts);
+	if (!ASSERT_GE(map_fd2, 0, "map_get"))
+		goto cleanup;
+
+	/* update map through one FD */
+	src_value = 0xcafebeef;
+	err = bpf_map_update_elem(map_fd, &zero, &src_value, 0);
+	ASSERT_OK(err, "map_update");
+
+	/* check values written/read through different FDs do match */
+	dst_value = 0;
+	err = bpf_map_lookup_elem(map_fd2, &zero, &dst_value);
+	ASSERT_OK(err, "map_lookup");
+	ASSERT_EQ(dst_value, src_value, "map_value_eq1");
+	ASSERT_EQ(dst_value, 0xcafebeef, "map_value_eq2");
+
+cleanup:
+	if (map_fd >= 0)
+		ASSERT_OK(close(map_fd), "close_map_fd");
+	if (map_fd2 >= 0)
+		ASSERT_OK(close(map_fd2), "close_map_fd2");
+	if (fs_fd >= 0)
+		ASSERT_OK(close(fs_fd), "close_fs_fd");
+	if (mnt_fd >= 0)
+		ASSERT_OK(close(mnt_fd), "close_mnt_fd");
+}
+
+enum path_kind
+{
+	PATH_STR_ABS,
+	PATH_STR_REL,
+	PATH_FD_REL,
+};
+
+static void validate_pin(int map_fd, const char *map_name, int src_value,
+			 enum path_kind path_kind)
+{
+	LIBBPF_OPTS(bpf_obj_pin_opts, pin_opts);
+	char abs_path[PATH_MAX], old_cwd[PATH_MAX];
+	const char *pin_path = NULL;
+	int zero = 0, dst_value, map_fd2, err;
+
+	snprintf(abs_path, sizeof(abs_path), "/sys/fs/bpf/%s", map_name);
+	old_cwd[0] = '\0';
+
+	switch (path_kind) {
+	case PATH_STR_ABS:
+		/* absolute path */
+		pin_path = abs_path;
+		break;
+	case PATH_STR_REL:
+		/* cwd + relative path */
+		ASSERT_OK_PTR(getcwd(old_cwd, sizeof(old_cwd)), "getcwd");
+		ASSERT_OK(chdir("/sys/fs/bpf"), "chdir");
+		pin_path = map_name;
+		break;
+	case PATH_FD_REL:
+		/* dir fd + relative path */
+		pin_opts.file_flags = BPF_F_PATH_FD;
+		pin_opts.path_fd = open("/sys/fs/bpf", O_PATH);
+		ASSERT_GE(pin_opts.path_fd, 0, "path_fd");
+		pin_path = map_name;
+		break;
+	}
+
+	/* pin BPF map using specified path definition */
+	err = bpf_obj_pin_opts(map_fd, pin_path, &pin_opts);
+	ASSERT_OK(err, "obj_pin");
+
+	/* cleanup */
+	if (path_kind == PATH_FD_REL && pin_opts.path_fd >= 0)
+		close(pin_opts.path_fd);
+	if (old_cwd[0])
+		ASSERT_OK(chdir(old_cwd), "restore_cwd");
+
+	map_fd2 = bpf_obj_get(abs_path);
+	if (!ASSERT_GE(map_fd2, 0, "map_get"))
+		goto cleanup;
+
+	/* update map through one FD */
+	err = bpf_map_update_elem(map_fd, &zero, &src_value, 0);
+	ASSERT_OK(err, "map_update");
+
+	/* check values written/read through different FDs do match */
+	dst_value = 0;
+	err = bpf_map_lookup_elem(map_fd2, &zero, &dst_value);
+	ASSERT_OK(err, "map_lookup");
+	ASSERT_EQ(dst_value, src_value, "map_value_eq");
+cleanup:
+	if (map_fd2 >= 0)
+		ASSERT_OK(close(map_fd2), "close_map_fd2");
+	unlink(abs_path);
+}
+
+static void validate_get(int map_fd, const char *map_name, int src_value,
+			 enum path_kind path_kind)
+{
+	LIBBPF_OPTS(bpf_obj_get_opts, get_opts);
+	char abs_path[PATH_MAX], old_cwd[PATH_MAX];
+	const char *pin_path = NULL;
+	int zero = 0, dst_value, map_fd2, err;
+
+	snprintf(abs_path, sizeof(abs_path), "/sys/fs/bpf/%s", map_name);
+	/* pin BPF map using specified path definition */
+	err = bpf_obj_pin(map_fd, abs_path);
+	if (!ASSERT_OK(err, "pin_map"))
+		return;
+
+	old_cwd[0] = '\0';
+
+	switch (path_kind) {
+	case PATH_STR_ABS:
+		/* absolute path */
+		pin_path = abs_path;
+		break;
+	case PATH_STR_REL:
+		/* cwd + relative path */
+		ASSERT_OK_PTR(getcwd(old_cwd, sizeof(old_cwd)), "getcwd");
+		ASSERT_OK(chdir("/sys/fs/bpf"), "chdir");
+		pin_path = map_name;
+		break;
+	case PATH_FD_REL:
+		/* dir fd + relative path */
+		get_opts.file_flags = BPF_F_PATH_FD;
+		get_opts.path_fd = open("/sys/fs/bpf", O_PATH);
+		ASSERT_GE(get_opts.path_fd, 0, "path_fd");
+		pin_path = map_name;
+		break;
+	}
+
+	map_fd2 = bpf_obj_get_opts(pin_path, &get_opts);
+	if (!ASSERT_GE(map_fd2, 0, "map_get"))
+		goto cleanup;
+
+	/* cleanup */
+	if (path_kind == PATH_FD_REL && get_opts.path_fd >= 0)
+		close(get_opts.path_fd);
+	if (old_cwd[0])
+		ASSERT_OK(chdir(old_cwd), "restore_cwd");
+
+	/* update map through one FD */
+	err = bpf_map_update_elem(map_fd, &zero, &src_value, 0);
+	ASSERT_OK(err, "map_update");
+
+	/* check values written/read through different FDs do match */
+	dst_value = 0;
+	err = bpf_map_lookup_elem(map_fd2, &zero, &dst_value);
+	ASSERT_OK(err, "map_lookup");
+	ASSERT_EQ(dst_value, src_value, "map_value_eq");
+cleanup:
+	if (map_fd2 >= 0)
+		ASSERT_OK(close(map_fd2), "close_map_fd2");
+	unlink(abs_path);
+}
+
+static void bpf_obj_pinning_mounted(enum path_kind path_kind)
+{
+	const char *map_name = "mounted_map";
+	int map_fd;
+
+	/* create BPF map to pin */
+	map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, map_name, 4, 4, 1, NULL);
+	if (!ASSERT_GE(map_fd, 0, "map_fd"))
+		return;
+
+	validate_pin(map_fd, map_name, 100 + (int)path_kind, path_kind);
+	validate_get(map_fd, map_name, 200 + (int)path_kind, path_kind);
+	ASSERT_OK(close(map_fd), "close_map_fd");
+}
+
+void test_bpf_obj_pinning()
+{
+	if (test__start_subtest("detached"))
+		bpf_obj_pinning_detached();
+	if (test__start_subtest("mounted-str-abs"))
+		bpf_obj_pinning_mounted(PATH_STR_ABS);
+	if (test__start_subtest("mounted-str-rel"))
+		bpf_obj_pinning_mounted(PATH_STR_REL);
+	if (test__start_subtest("mounted-fd-rel"))
+		bpf_obj_pinning_mounted(PATH_FD_REL);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_qdisc.c b/tools/testing/selftests/bpf/prog_tests/bpf_qdisc.c
new file mode 100644
index 000000000000..730357cd0c9a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_qdisc.c
@@ -0,0 +1,231 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/pkt_sched.h>
+#include <linux/rtnetlink.h>
+#include <test_progs.h>
+
+#include "network_helpers.h"
+#include "bpf_qdisc_fifo.skel.h"
+#include "bpf_qdisc_fq.skel.h"
+#include "bpf_qdisc_fail__incompl_ops.skel.h"
+
+#define LO_IFINDEX 1
+
+static const unsigned int total_bytes = 10 * 1024 * 1024;
+
+static void do_test(char *qdisc)
+{
+	DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = LO_IFINDEX,
+			    .attach_point = BPF_TC_QDISC,
+			    .parent = TC_H_ROOT,
+			    .handle = 0x8000000,
+			    .qdisc = qdisc);
+	int srv_fd = -1, cli_fd = -1;
+	int err;
+
+	err = bpf_tc_hook_create(&hook);
+	if (!ASSERT_OK(err, "attach qdisc"))
+		return;
+
+	srv_fd = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
+	if (!ASSERT_OK_FD(srv_fd, "start server"))
+		goto done;
+
+	cli_fd = connect_to_fd(srv_fd, 0);
+	if (!ASSERT_OK_FD(cli_fd, "connect to client"))
+		goto done;
+
+	err = send_recv_data(srv_fd, cli_fd, total_bytes);
+	ASSERT_OK(err, "send_recv_data");
+
+done:
+	if (srv_fd != -1)
+		close(srv_fd);
+	if (cli_fd != -1)
+		close(cli_fd);
+
+	bpf_tc_hook_destroy(&hook);
+}
+
+static void test_fifo(void)
+{
+	struct bpf_qdisc_fifo *fifo_skel;
+
+	fifo_skel = bpf_qdisc_fifo__open_and_load();
+	if (!ASSERT_OK_PTR(fifo_skel, "bpf_qdisc_fifo__open_and_load"))
+		return;
+
+	if (!ASSERT_OK(bpf_qdisc_fifo__attach(fifo_skel), "bpf_qdisc_fifo__attach"))
+		goto out;
+
+	do_test("bpf_fifo");
+out:
+	bpf_qdisc_fifo__destroy(fifo_skel);
+}
+
+static void test_fq(void)
+{
+	struct bpf_qdisc_fq *fq_skel;
+
+	fq_skel = bpf_qdisc_fq__open_and_load();
+	if (!ASSERT_OK_PTR(fq_skel, "bpf_qdisc_fq__open_and_load"))
+		return;
+
+	if (!ASSERT_OK(bpf_qdisc_fq__attach(fq_skel), "bpf_qdisc_fq__attach"))
+		goto out;
+
+	do_test("bpf_fq");
+out:
+	bpf_qdisc_fq__destroy(fq_skel);
+}
+
+static void test_qdisc_attach_to_mq(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook,
+			    .attach_point = BPF_TC_QDISC,
+			    .parent = TC_H_MAKE(1 << 16, 1),
+			    .handle = 0x11 << 16,
+			    .qdisc = "bpf_fifo");
+	struct bpf_qdisc_fifo *fifo_skel;
+	int err;
+
+	fifo_skel = bpf_qdisc_fifo__open_and_load();
+	if (!ASSERT_OK_PTR(fifo_skel, "bpf_qdisc_fifo__open_and_load"))
+		return;
+
+	if (!ASSERT_OK(bpf_qdisc_fifo__attach(fifo_skel), "bpf_qdisc_fifo__attach"))
+		goto out;
+
+	SYS(out, "ip link add veth0 type veth peer veth1");
+	hook.ifindex = if_nametoindex("veth0");
+	SYS(out, "tc qdisc add dev veth0 root handle 1: mq");
+
+	err = bpf_tc_hook_create(&hook);
+	ASSERT_OK(err, "attach qdisc");
+
+	bpf_tc_hook_destroy(&hook);
+
+	SYS(out, "tc qdisc delete dev veth0 root mq");
+out:
+	bpf_qdisc_fifo__destroy(fifo_skel);
+}
+
+static void test_qdisc_attach_to_non_root(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = LO_IFINDEX,
+			    .attach_point = BPF_TC_QDISC,
+			    .parent = TC_H_MAKE(1 << 16, 1),
+			    .handle = 0x11 << 16,
+			    .qdisc = "bpf_fifo");
+	struct bpf_qdisc_fifo *fifo_skel;
+	int err;
+
+	fifo_skel = bpf_qdisc_fifo__open_and_load();
+	if (!ASSERT_OK_PTR(fifo_skel, "bpf_qdisc_fifo__open_and_load"))
+		return;
+
+	if (!ASSERT_OK(bpf_qdisc_fifo__attach(fifo_skel), "bpf_qdisc_fifo__attach"))
+		goto out;
+
+	SYS(out, "tc qdisc add dev lo root handle 1: htb");
+	SYS(out_del_htb, "tc class add dev lo parent 1: classid 1:1 htb rate 75Kbit");
+
+	err = bpf_tc_hook_create(&hook);
+	if (!ASSERT_ERR(err, "attach qdisc"))
+		bpf_tc_hook_destroy(&hook);
+
+out_del_htb:
+	SYS(out, "tc qdisc delete dev lo root htb");
+out:
+	bpf_qdisc_fifo__destroy(fifo_skel);
+}
+
+static void test_incompl_ops(void)
+{
+	struct bpf_qdisc_fail__incompl_ops *skel;
+	struct bpf_link *link;
+
+	skel = bpf_qdisc_fail__incompl_ops__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "bpf_qdisc_fifo__open_and_load"))
+		return;
+
+	link = bpf_map__attach_struct_ops(skel->maps.test);
+	if (!ASSERT_ERR_PTR(link, "bpf_map__attach_struct_ops"))
+		bpf_link__destroy(link);
+
+	bpf_qdisc_fail__incompl_ops__destroy(skel);
+}
+
+static int get_default_qdisc(char *qdisc_name)
+{
+	FILE *f;
+	int num;
+
+	f = fopen("/proc/sys/net/core/default_qdisc", "r");
+	if (!f)
+		return -errno;
+
+	num = fscanf(f, "%s", qdisc_name);
+	fclose(f);
+
+	return num == 1 ? 0 : -EFAULT;
+}
+
+static void test_default_qdisc_attach_to_mq(void)
+{
+	char default_qdisc[IFNAMSIZ] = {};
+	struct bpf_qdisc_fifo *fifo_skel;
+	struct netns_obj *netns = NULL;
+	int err;
+
+	fifo_skel = bpf_qdisc_fifo__open_and_load();
+	if (!ASSERT_OK_PTR(fifo_skel, "bpf_qdisc_fifo__open_and_load"))
+		return;
+
+	if (!ASSERT_OK(bpf_qdisc_fifo__attach(fifo_skel), "bpf_qdisc_fifo__attach"))
+		goto out;
+
+	err = get_default_qdisc(default_qdisc);
+	if (!ASSERT_OK(err, "read sysctl net.core.default_qdisc"))
+		goto out;
+
+	err = write_sysctl("/proc/sys/net/core/default_qdisc", "bpf_fifo");
+	if (!ASSERT_OK(err, "write sysctl net.core.default_qdisc"))
+		goto out;
+
+	netns = netns_new("bpf_qdisc_ns", true);
+	if (!ASSERT_OK_PTR(netns, "netns_new"))
+		goto out;
+
+	SYS(out, "ip link add veth0 type veth peer veth1");
+	SYS(out, "tc qdisc add dev veth0 root handle 1: mq");
+
+	ASSERT_EQ(fifo_skel->bss->init_called, true, "init_called");
+
+	SYS(out, "tc qdisc delete dev veth0 root mq");
+out:
+	netns_free(netns);
+	if (default_qdisc[0])
+		write_sysctl("/proc/sys/net/core/default_qdisc", default_qdisc);
+
+	bpf_qdisc_fifo__destroy(fifo_skel);
+}
+
+void test_ns_bpf_qdisc(void)
+{
+	if (test__start_subtest("fifo"))
+		test_fifo();
+	if (test__start_subtest("fq"))
+		test_fq();
+	if (test__start_subtest("attach to mq"))
+		test_qdisc_attach_to_mq();
+	if (test__start_subtest("attach to non root"))
+		test_qdisc_attach_to_non_root();
+	if (test__start_subtest("incompl_ops"))
+		test_incompl_ops();
+}
+
+void serial_test_bpf_qdisc_default(void)
+{
+	test_default_qdisc_attach_to_mq();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
index e980188d4124..b7d1b52309d0 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -8,172 +8,98 @@
 #include "bpf_dctcp.skel.h"
 #include "bpf_cubic.skel.h"
 #include "bpf_tcp_nogpl.skel.h"
+#include "tcp_ca_update.skel.h"
 #include "bpf_dctcp_release.skel.h"
 #include "tcp_ca_write_sk_pacing.skel.h"
 #include "tcp_ca_incompl_cong_ops.skel.h"
 #include "tcp_ca_unsupp_cong_op.skel.h"
-
-#ifndef ENOTSUPP
-#define ENOTSUPP 524
-#endif
+#include "tcp_ca_kfunc.skel.h"
+#include "bpf_cc_cubic.skel.h"
 
 static const unsigned int total_bytes = 10 * 1024 * 1024;
 static int expected_stg = 0xeB9F;
-static int stop, duration;
+
+struct cb_opts {
+	const char *cc;
+	int map_fd;
+};
 
 static int settcpca(int fd, const char *tcp_ca)
 {
 	int err;
 
 	err = setsockopt(fd, IPPROTO_TCP, TCP_CONGESTION, tcp_ca, strlen(tcp_ca));
-	if (CHECK(err == -1, "setsockopt(fd, TCP_CONGESTION)", "errno:%d\n",
-		  errno))
+	if (!ASSERT_NEQ(err, -1, "setsockopt"))
 		return -1;
 
 	return 0;
 }
 
-static void *server(void *arg)
+static bool start_test(char *addr_str,
+		       const struct network_helper_opts *srv_opts,
+		       const struct network_helper_opts *cli_opts,
+		       int *srv_fd, int *cli_fd)
 {
-	int lfd = (int)(long)arg, err = 0, fd;
-	ssize_t nr_sent = 0, bytes = 0;
-	char batch[1500];
-
-	fd = accept(lfd, NULL, NULL);
-	while (fd == -1) {
-		if (errno == EINTR)
-			continue;
-		err = -errno;
-		goto done;
-	}
-
-	if (settimeo(fd, 0)) {
-		err = -errno;
-		goto done;
-	}
+	*srv_fd = start_server_str(AF_INET6, SOCK_STREAM, addr_str, 0, srv_opts);
+	if (!ASSERT_NEQ(*srv_fd, -1, "start_server_str"))
+		goto err;
 
-	while (bytes < total_bytes && !READ_ONCE(stop)) {
-		nr_sent = send(fd, &batch,
-			       MIN(total_bytes - bytes, sizeof(batch)), 0);
-		if (nr_sent == -1 && errno == EINTR)
-			continue;
-		if (nr_sent == -1) {
-			err = -errno;
-			break;
-		}
-		bytes += nr_sent;
-	}
+	/* connect to server */
+	*cli_fd = connect_to_fd_opts(*srv_fd, cli_opts);
+	if (!ASSERT_NEQ(*cli_fd, -1, "connect_to_fd_opts"))
+		goto err;
 
-	CHECK(bytes != total_bytes, "send", "%zd != %u nr_sent:%zd errno:%d\n",
-	      bytes, total_bytes, nr_sent, errno);
+	return true;
 
-done:
-	if (fd >= 0)
-		close(fd);
-	if (err) {
-		WRITE_ONCE(stop, 1);
-		return ERR_PTR(err);
+err:
+	if (*srv_fd != -1) {
+		close(*srv_fd);
+		*srv_fd = -1;
+	}
+	if (*cli_fd != -1) {
+		close(*cli_fd);
+		*cli_fd = -1;
 	}
-	return NULL;
+	return false;
 }
 
-static void do_test(const char *tcp_ca, const struct bpf_map *sk_stg_map)
+static void do_test(const struct network_helper_opts *opts)
 {
-	struct sockaddr_in6 sa6 = {};
-	ssize_t nr_recv = 0, bytes = 0;
 	int lfd = -1, fd = -1;
-	pthread_t srv_thread;
-	socklen_t addrlen = sizeof(sa6);
-	void *thread_ret;
-	char batch[1500];
-	int err;
 
-	WRITE_ONCE(stop, 0);
-
-	lfd = socket(AF_INET6, SOCK_STREAM, 0);
-	if (CHECK(lfd == -1, "socket", "errno:%d\n", errno))
-		return;
-	fd = socket(AF_INET6, SOCK_STREAM, 0);
-	if (CHECK(fd == -1, "socket", "errno:%d\n", errno)) {
-		close(lfd);
-		return;
-	}
-
-	if (settcpca(lfd, tcp_ca) || settcpca(fd, tcp_ca) ||
-	    settimeo(lfd, 0) || settimeo(fd, 0))
+	if (!start_test(NULL, opts, opts, &lfd, &fd))
 		goto done;
 
-	/* bind, listen and start server thread to accept */
-	sa6.sin6_family = AF_INET6;
-	sa6.sin6_addr = in6addr_loopback;
-	err = bind(lfd, (struct sockaddr *)&sa6, addrlen);
-	if (CHECK(err == -1, "bind", "errno:%d\n", errno))
-		goto done;
-	err = getsockname(lfd, (struct sockaddr *)&sa6, &addrlen);
-	if (CHECK(err == -1, "getsockname", "errno:%d\n", errno))
-		goto done;
-	err = listen(lfd, 1);
-	if (CHECK(err == -1, "listen", "errno:%d\n", errno))
-		goto done;
+	ASSERT_OK(send_recv_data(lfd, fd, total_bytes), "send_recv_data");
 
-	if (sk_stg_map) {
-		err = bpf_map_update_elem(bpf_map__fd(sk_stg_map), &fd,
-					  &expected_stg, BPF_NOEXIST);
-		if (CHECK(err, "bpf_map_update_elem(sk_stg_map)",
-			  "err:%d errno:%d\n", err, errno))
-			goto done;
-	}
-
-	/* connect to server */
-	err = connect(fd, (struct sockaddr *)&sa6, addrlen);
-	if (CHECK(err == -1, "connect", "errno:%d\n", errno))
-		goto done;
-
-	if (sk_stg_map) {
-		int tmp_stg;
-
-		err = bpf_map_lookup_elem(bpf_map__fd(sk_stg_map), &fd,
-					  &tmp_stg);
-		if (CHECK(!err || errno != ENOENT,
-			  "bpf_map_lookup_elem(sk_stg_map)",
-			  "err:%d errno:%d\n", err, errno))
-			goto done;
-	}
-
-	err = pthread_create(&srv_thread, NULL, server, (void *)(long)lfd);
-	if (CHECK(err != 0, "pthread_create", "err:%d errno:%d\n", err, errno))
-		goto done;
-
-	/* recv total_bytes */
-	while (bytes < total_bytes && !READ_ONCE(stop)) {
-		nr_recv = recv(fd, &batch,
-			       MIN(total_bytes - bytes, sizeof(batch)), 0);
-		if (nr_recv == -1 && errno == EINTR)
-			continue;
-		if (nr_recv == -1)
-			break;
-		bytes += nr_recv;
-	}
+done:
+	if (lfd != -1)
+		close(lfd);
+	if (fd != -1)
+		close(fd);
+}
 
-	CHECK(bytes != total_bytes, "recv", "%zd != %u nr_recv:%zd errno:%d\n",
-	      bytes, total_bytes, nr_recv, errno);
+static int cc_cb(int fd, void *opts)
+{
+	struct cb_opts *cb_opts = (struct cb_opts *)opts;
 
-	WRITE_ONCE(stop, 1);
-	pthread_join(srv_thread, &thread_ret);
-	CHECK(IS_ERR(thread_ret), "pthread_join", "thread_ret:%ld",
-	      PTR_ERR(thread_ret));
-done:
-	close(lfd);
-	close(fd);
+	return settcpca(fd, cb_opts->cc);
 }
 
 static void test_cubic(void)
 {
+	struct cb_opts cb_opts = {
+		.cc = "bpf_cubic",
+	};
+	struct network_helper_opts opts = {
+		.post_socket_cb	= cc_cb,
+		.cb_opts	= &cb_opts,
+	};
 	struct bpf_cubic *cubic_skel;
 	struct bpf_link *link;
 
 	cubic_skel = bpf_cubic__open_and_load();
-	if (CHECK(!cubic_skel, "bpf_cubic__open_and_load", "failed\n"))
+	if (!ASSERT_OK_PTR(cubic_skel, "bpf_cubic__open_and_load"))
 		return;
 
 	link = bpf_map__attach_struct_ops(cubic_skel->maps.cubic);
@@ -182,19 +108,50 @@ static void test_cubic(void)
 		return;
 	}
 
-	do_test("bpf_cubic", NULL);
+	do_test(&opts);
+
+	ASSERT_EQ(cubic_skel->bss->bpf_cubic_acked_called, 1, "pkts_acked called");
 
 	bpf_link__destroy(link);
 	bpf_cubic__destroy(cubic_skel);
 }
 
+static int stg_post_socket_cb(int fd, void *opts)
+{
+	struct cb_opts *cb_opts = (struct cb_opts *)opts;
+	int err;
+
+	err = settcpca(fd, cb_opts->cc);
+	if (err)
+		return err;
+
+	err = bpf_map_update_elem(cb_opts->map_fd, &fd,
+				  &expected_stg, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(sk_stg_map)"))
+		return err;
+
+	return 0;
+}
+
 static void test_dctcp(void)
 {
+	struct cb_opts cb_opts = {
+		.cc = "bpf_dctcp",
+	};
+	struct network_helper_opts opts = {
+		.post_socket_cb	= cc_cb,
+		.cb_opts	= &cb_opts,
+	};
+	struct network_helper_opts cli_opts = {
+		.post_socket_cb	= stg_post_socket_cb,
+		.cb_opts	= &cb_opts,
+	};
+	int lfd = -1, fd = -1, tmp_stg, err;
 	struct bpf_dctcp *dctcp_skel;
 	struct bpf_link *link;
 
 	dctcp_skel = bpf_dctcp__open_and_load();
-	if (CHECK(!dctcp_skel, "bpf_dctcp__open_and_load", "failed\n"))
+	if (!ASSERT_OK_PTR(dctcp_skel, "bpf_dctcp__open_and_load"))
 		return;
 
 	link = bpf_map__attach_struct_ops(dctcp_skel->maps.dctcp);
@@ -203,13 +160,58 @@ static void test_dctcp(void)
 		return;
 	}
 
-	do_test("bpf_dctcp", dctcp_skel->maps.sk_stg_map);
-	CHECK(dctcp_skel->bss->stg_result != expected_stg,
-	      "Unexpected stg_result", "stg_result (%x) != expected_stg (%x)\n",
-	      dctcp_skel->bss->stg_result, expected_stg);
+	cb_opts.map_fd = bpf_map__fd(dctcp_skel->maps.sk_stg_map);
+	if (!start_test(NULL, &opts, &cli_opts, &lfd, &fd))
+		goto done;
+
+	err = bpf_map_lookup_elem(cb_opts.map_fd, &fd, &tmp_stg);
+	if (!ASSERT_ERR(err, "bpf_map_lookup_elem(sk_stg_map)") ||
+			!ASSERT_EQ(errno, ENOENT, "bpf_map_lookup_elem(sk_stg_map)"))
+		goto done;
+
+	ASSERT_OK(send_recv_data(lfd, fd, total_bytes), "send_recv_data");
+	ASSERT_EQ(dctcp_skel->bss->stg_result, expected_stg, "stg_result");
 
+done:
 	bpf_link__destroy(link);
 	bpf_dctcp__destroy(dctcp_skel);
+	if (lfd != -1)
+		close(lfd);
+	if (fd != -1)
+		close(fd);
+}
+
+static void test_dctcp_autoattach_map(void)
+{
+	struct cb_opts cb_opts = {
+		.cc = "bpf_dctcp",
+	};
+	struct network_helper_opts opts = {
+		.post_socket_cb	= cc_cb,
+		.cb_opts	= &cb_opts,
+	};
+	struct bpf_dctcp *dctcp_skel;
+	struct bpf_link *link;
+
+	dctcp_skel = bpf_dctcp__open_and_load();
+	if (!ASSERT_OK_PTR(dctcp_skel, "bpf_dctcp__open_and_load"))
+		return;
+
+	bpf_map__set_autoattach(dctcp_skel->maps.dctcp, true);
+	bpf_map__set_autoattach(dctcp_skel->maps.dctcp_nouse, false);
+
+	if (!ASSERT_OK(bpf_dctcp__attach(dctcp_skel), "bpf_dctcp__attach"))
+		goto destroy;
+
+	/* struct_ops is auto-attached  */
+	link = dctcp_skel->links.dctcp;
+	if (!ASSERT_OK_PTR(link, "link"))
+		goto destroy;
+
+	do_test(&opts);
+
+destroy:
+	bpf_dctcp__destroy(dctcp_skel);
 }
 
 static char *err_str;
@@ -257,18 +259,29 @@ static void test_invalid_license(void)
 static void test_dctcp_fallback(void)
 {
 	int err, lfd = -1, cli_fd = -1, srv_fd = -1;
-	struct network_helper_opts opts = {
-		.cc = "cubic",
-	};
 	struct bpf_dctcp *dctcp_skel;
 	struct bpf_link *link = NULL;
+	struct cb_opts dctcp = {
+		.cc = "bpf_dctcp",
+	};
+	struct network_helper_opts srv_opts = {
+		.post_socket_cb = cc_cb,
+		.cb_opts = &dctcp,
+	};
+	struct cb_opts cubic = {
+		.cc = "cubic",
+	};
+	struct network_helper_opts cli_opts = {
+		.post_socket_cb = cc_cb,
+		.cb_opts = &cubic,
+	};
 	char srv_cc[16];
 	socklen_t cc_len = sizeof(srv_cc);
 
 	dctcp_skel = bpf_dctcp__open();
 	if (!ASSERT_OK_PTR(dctcp_skel, "dctcp_skel"))
 		return;
-	strcpy(dctcp_skel->rodata->fallback, "cubic");
+	strcpy(dctcp_skel->rodata->fallback_cc, "cubic");
 	if (!ASSERT_OK(bpf_dctcp__load(dctcp_skel), "bpf_dctcp__load"))
 		goto done;
 
@@ -276,13 +289,7 @@ static void test_dctcp_fallback(void)
 	if (!ASSERT_OK_PTR(link, "dctcp link"))
 		goto done;
 
-	lfd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
-	if (!ASSERT_GE(lfd, 0, "lfd") ||
-	    !ASSERT_OK(settcpca(lfd, "bpf_dctcp"), "lfd=>bpf_dctcp"))
-		goto done;
-
-	cli_fd = connect_to_fd_opts(lfd, &opts);
-	if (!ASSERT_GE(cli_fd, 0, "cli_fd"))
+	if (!start_test("::1", &srv_opts, &cli_opts, &lfd, &cli_fd))
 		goto done;
 
 	srv_fd = accept(lfd, NULL, 0);
@@ -316,7 +323,7 @@ static void test_rel_setsockopt(void)
 	struct bpf_dctcp_release *rel_skel;
 	libbpf_print_fn_t old_print_fn;
 
-	err_str = "unknown func bpf_setsockopt";
+	err_str = "program of this type cannot use helper bpf_setsockopt";
 	found = false;
 
 	old_print_fn = libbpf_set_print(libbpf_debug_print);
@@ -381,6 +388,221 @@ static void test_unsupp_cong_op(void)
 	libbpf_set_print(old_print_fn);
 }
 
+static void test_update_ca(void)
+{
+	struct cb_opts cb_opts = {
+		.cc = "tcp_ca_update",
+	};
+	struct network_helper_opts opts = {
+		.post_socket_cb	= cc_cb,
+		.cb_opts	= &cb_opts,
+	};
+	struct tcp_ca_update *skel;
+	struct bpf_link *link;
+	int saved_ca1_cnt;
+	int err;
+
+	skel = tcp_ca_update__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open"))
+		return;
+
+	link = bpf_map__attach_struct_ops(skel->maps.ca_update_1);
+	if (!ASSERT_OK_PTR(link, "attach_struct_ops"))
+		goto out;
+
+	do_test(&opts);
+	saved_ca1_cnt = skel->bss->ca1_cnt;
+	ASSERT_GT(saved_ca1_cnt, 0, "ca1_ca1_cnt");
+
+	err = bpf_link__update_map(link, skel->maps.ca_update_2);
+	ASSERT_OK(err, "update_map");
+
+	do_test(&opts);
+	ASSERT_EQ(skel->bss->ca1_cnt, saved_ca1_cnt, "ca2_ca1_cnt");
+	ASSERT_GT(skel->bss->ca2_cnt, 0, "ca2_ca2_cnt");
+
+	bpf_link__destroy(link);
+out:
+	tcp_ca_update__destroy(skel);
+}
+
+static void test_update_wrong(void)
+{
+	struct cb_opts cb_opts = {
+		.cc = "tcp_ca_update",
+	};
+	struct network_helper_opts opts = {
+		.post_socket_cb	= cc_cb,
+		.cb_opts	= &cb_opts,
+	};
+	struct tcp_ca_update *skel;
+	struct bpf_link *link;
+	int saved_ca1_cnt;
+	int err;
+
+	skel = tcp_ca_update__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open"))
+		return;
+
+	link = bpf_map__attach_struct_ops(skel->maps.ca_update_1);
+	if (!ASSERT_OK_PTR(link, "attach_struct_ops"))
+		goto out;
+
+	do_test(&opts);
+	saved_ca1_cnt = skel->bss->ca1_cnt;
+	ASSERT_GT(saved_ca1_cnt, 0, "ca1_ca1_cnt");
+
+	err = bpf_link__update_map(link, skel->maps.ca_wrong);
+	ASSERT_ERR(err, "update_map");
+
+	do_test(&opts);
+	ASSERT_GT(skel->bss->ca1_cnt, saved_ca1_cnt, "ca2_ca1_cnt");
+
+	bpf_link__destroy(link);
+out:
+	tcp_ca_update__destroy(skel);
+}
+
+static void test_mixed_links(void)
+{
+	struct cb_opts cb_opts = {
+		.cc = "tcp_ca_update",
+	};
+	struct network_helper_opts opts = {
+		.post_socket_cb	= cc_cb,
+		.cb_opts	= &cb_opts,
+	};
+	struct tcp_ca_update *skel;
+	struct bpf_link *link, *link_nl;
+	int err;
+
+	skel = tcp_ca_update__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open"))
+		return;
+
+	link_nl = bpf_map__attach_struct_ops(skel->maps.ca_no_link);
+	if (!ASSERT_OK_PTR(link_nl, "attach_struct_ops_nl"))
+		goto out;
+
+	link = bpf_map__attach_struct_ops(skel->maps.ca_update_1);
+	ASSERT_OK_PTR(link, "attach_struct_ops");
+
+	do_test(&opts);
+	ASSERT_GT(skel->bss->ca1_cnt, 0, "ca1_ca1_cnt");
+
+	err = bpf_link__update_map(link, skel->maps.ca_no_link);
+	ASSERT_ERR(err, "update_map");
+
+	bpf_link__destroy(link);
+	bpf_link__destroy(link_nl);
+out:
+	tcp_ca_update__destroy(skel);
+}
+
+static void test_multi_links(void)
+{
+	struct tcp_ca_update *skel;
+	struct bpf_link *link;
+
+	skel = tcp_ca_update__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open"))
+		return;
+
+	link = bpf_map__attach_struct_ops(skel->maps.ca_update_1);
+	ASSERT_OK_PTR(link, "attach_struct_ops_1st");
+	bpf_link__destroy(link);
+
+	/* A map should be able to be used to create links multiple
+	 * times.
+	 */
+	link = bpf_map__attach_struct_ops(skel->maps.ca_update_1);
+	ASSERT_OK_PTR(link, "attach_struct_ops_2nd");
+	bpf_link__destroy(link);
+
+	tcp_ca_update__destroy(skel);
+}
+
+static void test_link_replace(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_link_update_opts, opts);
+	struct tcp_ca_update *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = tcp_ca_update__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open"))
+		return;
+
+	link = bpf_map__attach_struct_ops(skel->maps.ca_update_1);
+	ASSERT_OK_PTR(link, "attach_struct_ops_1st");
+	bpf_link__destroy(link);
+
+	link = bpf_map__attach_struct_ops(skel->maps.ca_update_2);
+	if (!ASSERT_OK_PTR(link, "attach_struct_ops_2nd"))
+		goto out;
+
+	/* BPF_F_REPLACE with a wrong old map Fd. It should fail!
+	 *
+	 * With BPF_F_REPLACE, the link should be updated only if the
+	 * old map fd given here matches the map backing the link.
+	 */
+	opts.old_map_fd = bpf_map__fd(skel->maps.ca_update_1);
+	opts.flags = BPF_F_REPLACE;
+	err = bpf_link_update(bpf_link__fd(link),
+			      bpf_map__fd(skel->maps.ca_update_1),
+			      &opts);
+	ASSERT_ERR(err, "bpf_link_update_fail");
+
+	/* BPF_F_REPLACE with a correct old map Fd. It should success! */
+	opts.old_map_fd = bpf_map__fd(skel->maps.ca_update_2);
+	err = bpf_link_update(bpf_link__fd(link),
+			      bpf_map__fd(skel->maps.ca_update_1),
+			      &opts);
+	ASSERT_OK(err, "bpf_link_update_success");
+
+	bpf_link__destroy(link);
+
+out:
+	tcp_ca_update__destroy(skel);
+}
+
+static void test_tcp_ca_kfunc(void)
+{
+	struct tcp_ca_kfunc *skel;
+
+	skel = tcp_ca_kfunc__open_and_load();
+	ASSERT_OK_PTR(skel, "tcp_ca_kfunc__open_and_load");
+	tcp_ca_kfunc__destroy(skel);
+}
+
+static void test_cc_cubic(void)
+{
+	struct cb_opts cb_opts = {
+		.cc = "bpf_cc_cubic",
+	};
+	struct network_helper_opts opts = {
+		.post_socket_cb	= cc_cb,
+		.cb_opts	= &cb_opts,
+	};
+	struct bpf_cc_cubic *cc_cubic_skel;
+	struct bpf_link *link;
+
+	cc_cubic_skel = bpf_cc_cubic__open_and_load();
+	if (!ASSERT_OK_PTR(cc_cubic_skel, "bpf_cc_cubic__open_and_load"))
+		return;
+
+	link = bpf_map__attach_struct_ops(cc_cubic_skel->maps.cc_cubic);
+	if (!ASSERT_OK_PTR(link, "bpf_map__attach_struct_ops")) {
+		bpf_cc_cubic__destroy(cc_cubic_skel);
+		return;
+	}
+
+	do_test(&opts);
+
+	bpf_link__destroy(link);
+	bpf_cc_cubic__destroy(cc_cubic_skel);
+}
+
 void test_bpf_tcp_ca(void)
 {
 	if (test__start_subtest("dctcp"))
@@ -399,4 +621,20 @@ void test_bpf_tcp_ca(void)
 		test_incompl_cong_ops();
 	if (test__start_subtest("unsupp_cong_op"))
 		test_unsupp_cong_op();
+	if (test__start_subtest("update_ca"))
+		test_update_ca();
+	if (test__start_subtest("update_wrong"))
+		test_update_wrong();
+	if (test__start_subtest("mixed_links"))
+		test_mixed_links();
+	if (test__start_subtest("multi_links"))
+		test_multi_links();
+	if (test__start_subtest("link_replace"))
+		test_link_replace();
+	if (test__start_subtest("tcp_ca_kfunc"))
+		test_tcp_ca_kfunc();
+	if (test__start_subtest("cc_cubic"))
+		test_cc_cubic();
+	if (test__start_subtest("dctcp_autoattach_map"))
+		test_dctcp_autoattach_map();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
index 5ca252823294..73f669014b69 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
@@ -35,7 +35,7 @@ static int check_load(const char *file, enum bpf_prog_type type)
 	}
 
 	bpf_program__set_type(prog, type);
-	bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32);
+	bpf_program__set_flags(prog, testing_prog_flags());
 	bpf_program__set_log_level(prog, 4 | extra_prog_load_log_flags);
 
 	err = bpf_object__load(obj);
@@ -45,12 +45,6 @@ err_out:
 	return err;
 }
 
-struct scale_test_def {
-	const char *file;
-	enum bpf_prog_type attach_type;
-	bool fails;
-};
-
 static void scale_test(const char *file,
 		       enum bpf_prog_type attach_type,
 		       bool should_fail)
@@ -144,6 +138,12 @@ void test_verif_scale_pyperf600_nounroll()
 	scale_test("pyperf600_nounroll.bpf.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
 }
 
+void test_verif_scale_pyperf600_iter()
+{
+	/* open-coded BPF iterator version */
+	scale_test("pyperf600_iter.bpf.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
 void test_verif_scale_loop1()
 {
 	scale_test("loop1.bpf.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index de1b5b9eb93a..054ecb6b1e9f 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -879,6 +879,34 @@ static struct btf_raw_test raw_tests[] = {
 	.btf_load_err = true,
 	.err_str = "Invalid elem",
 },
+{
+	.descr = "var after datasec, ptr followed by modifier",
+	.raw_types = {
+		/* .bss section */				/* [1] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 2),
+			sizeof(void*)+4),
+		BTF_VAR_SECINFO_ENC(4, 0, sizeof(void*)),
+		BTF_VAR_SECINFO_ENC(6, sizeof(void*), 4),
+		/* int */					/* [2] */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+		/* int* */					/* [3] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2),
+		BTF_VAR_ENC(NAME_TBD, 3, 0),			/* [4] */
+		/* const int */					/* [5] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 2),
+		BTF_VAR_ENC(NAME_TBD, 5, 0),			/* [6] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0a\0b\0c\0",
+	.str_sec_size = sizeof("\0a\0b\0c\0"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = sizeof(void*)+4,
+	.key_type_id = 0,
+	.value_type_id = 1,
+	.max_entries = 1,
+},
 /* Test member exceeds the size of struct.
  *
  * struct A {
@@ -3507,6 +3535,66 @@ static struct btf_raw_test raw_tests[] = {
 	.value_type_id = 1,
 	.max_entries = 1,
 },
+{
+	.descr = "datasec: name '?.foo bar:buz' is ok",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* VAR x */                                     /* [2] */
+		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
+		BTF_VAR_STATIC,
+		/* DATASEC ?.data */                            /* [3] */
+		BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+		BTF_VAR_SECINFO_ENC(2, 0, 4),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0x\0?.foo bar:buz"),
+},
+{
+	.descr = "datasec: name with non-printable first char not is ok",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* VAR x */                                     /* [2] */
+		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
+		BTF_VAR_STATIC,
+		/* DATASEC ?.data */                            /* [3] */
+		BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+		BTF_VAR_SECINFO_ENC(2, 0, 4),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0x\0\7foo"),
+	.err_str = "Invalid name",
+	.btf_load_err = true,
+},
+{
+	.descr = "datasec: name '\\0' is not ok",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* VAR x */                                     /* [2] */
+		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
+		BTF_VAR_STATIC,
+		/* DATASEC \0 */                                /* [3] */
+		BTF_TYPE_ENC(3, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+		BTF_VAR_SECINFO_ENC(2, 0, 4),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0x\0"),
+	.err_str = "Invalid name",
+	.btf_load_err = true,
+},
+{
+	.descr = "type name '?foo' is not ok",
+	.raw_types = {
+		/* union ?foo; */
+		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_FWD, 1, 0), 0), /* [1] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0?foo"),
+	.err_str = "Invalid name",
+	.btf_load_err = true,
+},
 
 {
 	.descr = "float test #1, well-formed",
@@ -3778,11 +3866,11 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "vlen != 0",
 },
 {
-	.descr = "decl_tag test #8, invalid kflag",
+	.descr = "decl_tag test #8, tag with kflag",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [2] */
-		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 1, 0), 2), (-1),
+		BTF_DECL_ATTR_ENC(NAME_TBD, 2, -1),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0local\0tag1"),
@@ -3793,8 +3881,6 @@ static struct btf_raw_test raw_tests[] = {
 	.key_type_id = 1,
 	.value_type_id = 1,
 	.max_entries = 1,
-	.btf_load_err = true,
-	.err_str = "Invalid btf_info kind_flag",
 },
 {
 	.descr = "decl_tag test #9, var, invalid component_idx",
@@ -3963,6 +4049,46 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "Invalid arg#1",
 },
 {
+	.descr = "decl_tag test #18, decl_tag as the map key type",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_STRUCT_ENC(0, 2, 8),			/* [2] */
+		BTF_MEMBER_ENC(NAME_TBD, 1, 0),
+		BTF_MEMBER_ENC(NAME_TBD, 1, 32),
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, -1),		/* [3] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0m1\0m2\0tag"),
+	.map_type = BPF_MAP_TYPE_HASH,
+	.map_name = "tag_type_check_btf",
+	.key_size = 8,
+	.value_size = 4,
+	.key_type_id = 3,
+	.value_type_id = 1,
+	.max_entries = 1,
+	.map_create_err = true,
+},
+{
+	.descr = "decl_tag test #19, decl_tag as the map value type",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_STRUCT_ENC(0, 2, 8),			/* [2] */
+		BTF_MEMBER_ENC(NAME_TBD, 1, 0),
+		BTF_MEMBER_ENC(NAME_TBD, 1, 32),
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, -1),		/* [3] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0m1\0m2\0tag"),
+	.map_type = BPF_MAP_TYPE_HASH,
+	.map_name = "tag_type_check_btf",
+	.key_size = 4,
+	.value_size = 8,
+	.key_type_id = 1,
+	.value_type_id = 3,
+	.max_entries = 1,
+	.map_create_err = true,
+},
+{
 	.descr = "type_tag test #1",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
@@ -4079,6 +4205,23 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "Type tags don't precede modifiers",
 },
 {
+	.descr = "type_tag test #7, tag with kflag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_ATTR_ENC(NAME_TBD, 1),			/* [2] */
+		BTF_PTR_ENC(2),					/* [3] */
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0tag"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "tag_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 1,
+},
+{
 	.descr = "enum64 test #1, unsigned, size 8",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),			/* [1] */
@@ -4295,6 +4438,9 @@ static void do_test_raw(unsigned int test_num)
 	if (err || btf_fd < 0)
 		goto done;
 
+	if (!test->map_type)
+		goto done;
+
 	opts.btf_fd = btf_fd;
 	opts.btf_key_type_id = test->key_type_id;
 	opts.btf_value_type_id = test->value_type_id;
@@ -4422,7 +4568,7 @@ static int test_big_btf_info(unsigned int test_num)
 	info->btf = ptr_to_u64(user_btf);
 	info->btf_size = raw_btf_size;
 
-	err = bpf_obj_get_info_by_fd(btf_fd, info, &info_len);
+	err = bpf_btf_get_info_by_fd(btf_fd, info, &info_len);
 	if (CHECK(!err, "!err")) {
 		err = -1;
 		goto done;
@@ -4435,7 +4581,7 @@ static int test_big_btf_info(unsigned int test_num)
 	 * to userspace.
 	 */
 	info_garbage.garbage = 0;
-	err = bpf_obj_get_info_by_fd(btf_fd, info, &info_len);
+	err = bpf_btf_get_info_by_fd(btf_fd, info, &info_len);
 	if (CHECK(err || info_len != sizeof(*info),
 		  "err:%d errno:%d info_len:%u sizeof(*info):%zu",
 		  err, errno, info_len, sizeof(*info))) {
@@ -4499,7 +4645,7 @@ static int test_btf_id(unsigned int test_num)
 
 	/* Test BPF_OBJ_GET_INFO_BY_ID on btf_id */
 	info_len = sizeof(info[0]);
-	err = bpf_obj_get_info_by_fd(btf_fd[0], &info[0], &info_len);
+	err = bpf_btf_get_info_by_fd(btf_fd[0], &info[0], &info_len);
 	if (CHECK(err, "errno:%d", errno)) {
 		err = -1;
 		goto done;
@@ -4512,7 +4658,7 @@ static int test_btf_id(unsigned int test_num)
 	}
 
 	ret = 0;
-	err = bpf_obj_get_info_by_fd(btf_fd[1], &info[1], &info_len);
+	err = bpf_btf_get_info_by_fd(btf_fd[1], &info[1], &info_len);
 	if (CHECK(err || info[0].id != info[1].id ||
 		  info[0].btf_size != info[1].btf_size ||
 		  (ret = memcmp(user_btf[0], user_btf[1], info[0].btf_size)),
@@ -4535,7 +4681,7 @@ static int test_btf_id(unsigned int test_num)
 	}
 
 	info_len = sizeof(map_info);
-	err = bpf_obj_get_info_by_fd(map_fd, &map_info, &info_len);
+	err = bpf_map_get_info_by_fd(map_fd, &map_info, &info_len);
 	if (CHECK(err || map_info.btf_id != info[0].id ||
 		  map_info.btf_key_type_id != 1 || map_info.btf_value_type_id != 2,
 		  "err:%d errno:%d info.id:%u btf_id:%u btf_key_type_id:%u btf_value_type_id:%u",
@@ -4562,11 +4708,6 @@ static int test_btf_id(unsigned int test_num)
 	/* The map holds the last ref to BTF and its btf_id */
 	close(map_fd);
 	map_fd = -1;
-	btf_fd[0] = bpf_btf_get_fd_by_id(map_info.btf_id);
-	if (CHECK(btf_fd[0] >= 0, "BTF lingers")) {
-		err = -1;
-		goto done;
-	}
 
 	fprintf(stderr, "OK");
 
@@ -4638,7 +4779,7 @@ static void do_test_get_info(unsigned int test_num)
 	info.btf_size = user_btf_size;
 
 	ret = 0;
-	err = bpf_obj_get_info_by_fd(btf_fd, &info, &info_len);
+	err = bpf_btf_get_info_by_fd(btf_fd, &info, &info_len);
 	if (CHECK(err || !info.id || info_len != sizeof(info) ||
 		  info.btf_size != raw_btf_size ||
 		  (ret = memcmp(raw_btf, user_btf, expected_nbytes)),
@@ -4755,7 +4896,7 @@ static void do_test_file(unsigned int test_num)
 
 	/* get necessary program info */
 	info_len = sizeof(struct bpf_prog_info);
-	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len);
 
 	if (CHECK(err < 0, "invalid get info (1st) errno:%d", errno)) {
 		fprintf(stderr, "%s\n", btf_log_buf);
@@ -4787,7 +4928,7 @@ static void do_test_file(unsigned int test_num)
 	info.func_info_rec_size = rec_size;
 	info.func_info = ptr_to_u64(func_info);
 
-	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len);
 
 	if (CHECK(err < 0, "invalid get info (2nd) errno:%d", errno)) {
 		fprintf(stderr, "%s\n", btf_log_buf);
@@ -4894,7 +5035,7 @@ struct pprint_mapv_int128 {
 static struct btf_raw_test pprint_test_template[] = {
 {
 	.raw_types = {
-		/* unsighed char */			/* [1] */
+		/* unsigned char */			/* [1] */
 		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1),
 		/* unsigned short */			/* [2] */
 		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 16, 2),
@@ -4961,7 +5102,7 @@ static struct btf_raw_test pprint_test_template[] = {
 	 * be encoded with kind_flag set.
 	 */
 	.raw_types = {
-		/* unsighed char */			/* [1] */
+		/* unsigned char */			/* [1] */
 		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1),
 		/* unsigned short */			/* [2] */
 		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 16, 2),
@@ -5028,7 +5169,7 @@ static struct btf_raw_test pprint_test_template[] = {
 	 * will have both int and enum types.
 	 */
 	.raw_types = {
-		/* unsighed char */			/* [1] */
+		/* unsigned char */			/* [1] */
 		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1),
 		/* unsigned short */			/* [2] */
 		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 16, 2),
@@ -5197,6 +5338,7 @@ static size_t get_pprint_mapv_size(enum pprint_mapv_kind_t mapv_kind)
 #endif
 
 	assert(0);
+	return 0;
 }
 
 static void set_pprint_mapv(enum pprint_mapv_kind_t mapv_kind,
@@ -6405,7 +6547,7 @@ static int test_get_finfo(const struct prog_info_raw_test *test,
 
 	/* get necessary lens */
 	info_len = sizeof(struct bpf_prog_info);
-	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len);
 	if (CHECK(err < 0, "invalid get info (1st) errno:%d", errno)) {
 		fprintf(stderr, "%s\n", btf_log_buf);
 		return -1;
@@ -6435,7 +6577,7 @@ static int test_get_finfo(const struct prog_info_raw_test *test,
 	info.nr_func_info = nr_func_info;
 	info.func_info_rec_size = rec_size;
 	info.func_info = ptr_to_u64(func_info);
-	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len);
 	if (CHECK(err < 0, "invalid get info (2nd) errno:%d", errno)) {
 		fprintf(stderr, "%s\n", btf_log_buf);
 		err = -1;
@@ -6499,7 +6641,7 @@ static int test_get_linfo(const struct prog_info_raw_test *test,
 	nr_jited_func_lens = nr_jited_ksyms;
 
 	info_len = sizeof(struct bpf_prog_info);
-	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len);
 	if (CHECK(err < 0, "err:%d errno:%d", err, errno)) {
 		err = -1;
 		goto done;
@@ -6573,7 +6715,7 @@ static int test_get_linfo(const struct prog_info_raw_test *test,
 		info.jited_func_lens = ptr_to_u64(jited_func_lens);
 	}
 
-	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len);
 
 	/*
 	 * Only recheck the info.*line_info* fields.
@@ -7228,7 +7370,7 @@ static struct btf_dedup_test dedup_tests[] = {
 			BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
 				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1),
 				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1),
-			BTF_FUNC_ENC(NAME_NTH(4), 2),			/* [4] */
+			BTF_FUNC_ENC(NAME_NTH(4), 3),			/* [4] */
 			/* tag -> t */
 			BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1),		/* [5] */
 			BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1),		/* [6] */
@@ -7249,7 +7391,7 @@ static struct btf_dedup_test dedup_tests[] = {
 			BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
 				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1),
 				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1),
-			BTF_FUNC_ENC(NAME_NTH(4), 2),			/* [4] */
+			BTF_FUNC_ENC(NAME_NTH(4), 3),			/* [4] */
 			BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1),		/* [5] */
 			BTF_DECL_TAG_ENC(NAME_NTH(5), 4, -1),		/* [6] */
 			BTF_DECL_TAG_ENC(NAME_NTH(5), 4, 1),		/* [7] */
@@ -7354,6 +7496,71 @@ static struct btf_dedup_test dedup_tests[] = {
 	},
 },
 {
+	.descr = "dedup: recursive typedef",
+	/*
+	 * This test simulates a recursive typedef, which in GO is defined as such:
+	 *
+	 *   type Foo func() Foo
+	 *
+	 * In BTF terms, this is represented as a TYPEDEF referencing
+	 * a FUNC_PROTO that returns the same TYPEDEF.
+	 */
+	.input = {
+		.raw_types = {
+			/*
+			 * [1] typedef Foo -> func() Foo
+			 * [2] func_proto() -> Foo
+			 * [3] typedef Foo -> func() Foo
+			 * [4] func_proto() -> Foo
+			 */
+			BTF_TYPEDEF_ENC(NAME_NTH(1), 2),	/* [1] */
+			BTF_FUNC_PROTO_ENC(1, 0),		/* [2] */
+			BTF_TYPEDEF_ENC(NAME_NTH(1), 4),	/* [3] */
+			BTF_FUNC_PROTO_ENC(3, 0),		/* [4] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0Foo"),
+	},
+	.expect = {
+		.raw_types = {
+			BTF_TYPEDEF_ENC(NAME_NTH(1), 2),	/* [1] */
+			BTF_FUNC_PROTO_ENC(1, 0),		/* [2] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0Foo"),
+	},
+},
+{
+	.descr = "dedup: typedef",
+    /*
+     * // CU 1:
+     * typedef int foo;
+     *
+     * // CU 2:
+     * typedef int foo;
+     */
+	.input = {
+		.raw_types = {
+			/* CU 1 */
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+			BTF_TYPEDEF_ENC(NAME_NTH(1), 1),		/* [2] */
+			/* CU 2 */
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [3] */
+			BTF_TYPEDEF_ENC(NAME_NTH(1), 3),		/* [4] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0foo"),
+	},
+	.expect = {
+		.raw_types = {
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+			BTF_TYPEDEF_ENC(NAME_NTH(1), 1),		/* [2] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0foo"),
+	},
+},
+{
 	.descr = "dedup: typedef tags",
 	.input = {
 		.raw_types = {
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c b/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c
index d9024c7a892a..5bc15bb6b7ce 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c
@@ -440,6 +440,105 @@ cleanup:
 	btf__free(btf1);
 }
 
+/* Ensure module split BTF dedup worked correctly; when dedup fails badly
+ * core kernel types are in split BTF also, so ensure that references to
+ * such types point at base - not split - BTF.
+ *
+ * bpf_testmod_test_write() has multiple core kernel type parameters;
+ *
+ * ssize_t
+ * bpf_testmod_test_write(struct file *file, struct kobject *kobj,
+ *                        struct bin_attribute *bin_attr,
+ *                        char *buf, loff_t off, size_t len);
+ *
+ * Ensure each of the FUNC_PROTO params is a core kernel type.
+ *
+ * Do the same for
+ *
+ * __bpf_kfunc struct sock *bpf_kfunc_call_test3(struct sock *sk);
+ *
+ * ...and
+ *
+ * __bpf_kfunc void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb);
+ *
+ */
+const char *mod_funcs[] = {
+	"bpf_testmod_test_write",
+	"bpf_kfunc_call_test3",
+	"bpf_kfunc_call_test_pass_ctx"
+};
+
+static void test_split_module(void)
+{
+	struct btf *vmlinux_btf, *btf1 = NULL;
+	int i, nr_base_types;
+
+	vmlinux_btf = btf__load_vmlinux_btf();
+	if (!ASSERT_OK_PTR(vmlinux_btf, "vmlinux_btf"))
+		return;
+	nr_base_types = btf__type_cnt(vmlinux_btf);
+	if (!ASSERT_GT(nr_base_types, 0, "nr_base_types"))
+		goto cleanup;
+
+	btf1 = btf__parse_split("/sys/kernel/btf/bpf_testmod", vmlinux_btf);
+	if (!ASSERT_OK_PTR(btf1, "split_btf"))
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(mod_funcs); i++) {
+		const struct btf_param *p;
+		const struct btf_type *t;
+		__u16 vlen;
+		__u32 id;
+		int j;
+
+		id = btf__find_by_name_kind(btf1, mod_funcs[i], BTF_KIND_FUNC);
+		if (!ASSERT_GE(id, nr_base_types, "func_id"))
+			goto cleanup;
+		t = btf__type_by_id(btf1, id);
+		if (!ASSERT_OK_PTR(t, "func_id_type"))
+			goto cleanup;
+		t = btf__type_by_id(btf1, t->type);
+		if (!ASSERT_OK_PTR(t, "func_proto_id_type"))
+			goto cleanup;
+		if (!ASSERT_EQ(btf_is_func_proto(t), true, "is_func_proto"))
+			goto cleanup;
+		vlen = btf_vlen(t);
+
+		for (j = 0, p = btf_params(t); j < vlen; j++, p++) {
+			/* bpf_testmod uses resilient split BTF, so any
+			 * reference types will be added to split BTF and their
+			 * associated targets will be base BTF types; for example
+			 * for a "struct sock *" the PTR will be in split BTF
+			 * while the "struct sock" will be in base.
+			 *
+			 * In some cases like loff_t we have to resolve
+			 * multiple typedefs hence the while() loop below.
+			 *
+			 * Note that resilient split BTF generation depends
+			 * on pahole version, so we do not assert that
+			 * reference types are in split BTF, as if pahole
+			 * does not support resilient split BTF they will
+			 * also be base BTF types.
+			 */
+			id = p->type;
+			do {
+				t = btf__type_by_id(btf1, id);
+				if (!ASSERT_OK_PTR(t, "param_ref_type"))
+					goto cleanup;
+				if (!btf_is_mod(t) && !btf_is_ptr(t) && !btf_is_typedef(t))
+					break;
+				id = t->type;
+			} while (true);
+
+			if (!ASSERT_LT(id, nr_base_types, "verify_base_type"))
+				goto cleanup;
+		}
+	}
+cleanup:
+	btf__free(btf1);
+	btf__free(vmlinux_btf);
+}
+
 void test_btf_dedup_split()
 {
 	if (test__start_subtest("split_simple"))
@@ -450,4 +549,6 @@ void test_btf_dedup_split()
 		test_split_fwd_resolve();
 	if (test__start_subtest("split_dup_struct_in_cu"))
 		test_split_dup_struct_in_cu();
+	if (test__start_subtest("split_module"))
+		test_split_module();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_distill.c b/tools/testing/selftests/bpf/prog_tests/btf_distill.c
new file mode 100644
index 000000000000..fb67ae195a73
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/btf_distill.c
@@ -0,0 +1,692 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024, Oracle and/or its affiliates. */
+
+#include <test_progs.h>
+#include <bpf/btf.h>
+#include "btf_helpers.h"
+
+/* Fabricate base, split BTF with references to base types needed; then create
+ * split BTF with distilled base BTF and ensure expectations are met:
+ *  - only referenced base types from split BTF are present
+ *  - struct/union/enum are represented as empty unless anonymous, when they
+ *    are represented in full in split BTF
+ */
+static void test_distilled_base(void)
+{
+	struct btf *btf1 = NULL, *btf2 = NULL, *btf3 = NULL, *btf4 = NULL;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+		return;
+
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);	/* [1] int */
+	btf__add_ptr(btf1, 1);				/* [2] ptr to int */
+	btf__add_struct(btf1, "s1", 8);			/* [3] struct s1 { */
+	btf__add_field(btf1, "f1", 2, 0, 0);		/*      int *f1; */
+							/* } */
+	btf__add_struct(btf1, "", 12);			/* [4] struct { */
+	btf__add_field(btf1, "f1", 1, 0, 0);		/*	int f1; */
+	btf__add_field(btf1, "f2", 3, 32, 0);		/*	struct s1 f2; */
+							/* } */
+	btf__add_int(btf1, "unsigned int", 4, 0);	/* [5] unsigned int */
+	btf__add_union(btf1, "u1", 12);			/* [6] union u1 { */
+	btf__add_field(btf1, "f1", 1, 0, 0);		/*	int f1; */
+	btf__add_field(btf1, "f2", 2, 0, 0);		/*	int *f2; */
+							/* } */
+	btf__add_union(btf1, "", 4);			/* [7] union { */
+	btf__add_field(btf1, "f1", 1, 0, 0);		/*	int f1; */
+							/* } */
+	btf__add_enum(btf1, "e1", 4);			/* [8] enum e1 { */
+	btf__add_enum_value(btf1, "v1", 1);		/*	v1 = 1; */
+							/* } */
+	btf__add_enum(btf1, "", 4);			/* [9] enum { */
+	btf__add_enum_value(btf1, "av1", 2);		/*	av1 = 2; */
+							/* } */
+	btf__add_enum64(btf1, "e641", 8, true);		/* [10] enum64 { */
+	btf__add_enum64_value(btf1, "v1", 1024);	/*	v1 = 1024; */
+							/* } */
+	btf__add_enum64(btf1, "", 8, true);		/* [11] enum64 { */
+	btf__add_enum64_value(btf1, "v1", 1025);	/*	v1 = 1025; */
+							/* } */
+	btf__add_struct(btf1, "unneeded", 4);		/* [12] struct unneeded { */
+	btf__add_field(btf1, "f1", 1, 0, 0);		/*	int f1; */
+							/* } */
+	btf__add_struct(btf1, "embedded", 4);		/* [13] struct embedded { */
+	btf__add_field(btf1, "f1", 1, 0, 0);		/*	int f1; */
+							/* } */
+	btf__add_func_proto(btf1, 1);			/* [14] int (*)(int *p1); */
+	btf__add_func_param(btf1, "p1", 1);
+
+	btf__add_array(btf1, 1, 1, 3);			/* [15] int [3]; */
+
+	btf__add_struct(btf1, "from_proto", 4);		/* [16] struct from_proto { */
+	btf__add_field(btf1, "f1", 1, 0, 0);		/*	int f1; */
+							/* } */
+	btf__add_union(btf1, "u1", 4);			/* [17] union u1 { */
+	btf__add_field(btf1, "f1", 1, 0, 0);		/*	 int f1; */
+							/* } */
+	VALIDATE_RAW_BTF(
+		btf1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1",
+		"[3] STRUCT 's1' size=8 vlen=1\n"
+		"\t'f1' type_id=2 bits_offset=0",
+		"[4] STRUCT '(anon)' size=12 vlen=2\n"
+		"\t'f1' type_id=1 bits_offset=0\n"
+		"\t'f2' type_id=3 bits_offset=32",
+		"[5] INT 'unsigned int' size=4 bits_offset=0 nr_bits=32 encoding=(none)",
+		"[6] UNION 'u1' size=12 vlen=2\n"
+		"\t'f1' type_id=1 bits_offset=0\n"
+		"\t'f2' type_id=2 bits_offset=0",
+		"[7] UNION '(anon)' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[8] ENUM 'e1' encoding=UNSIGNED size=4 vlen=1\n"
+		"\t'v1' val=1",
+		"[9] ENUM '(anon)' encoding=UNSIGNED size=4 vlen=1\n"
+		"\t'av1' val=2",
+		"[10] ENUM64 'e641' encoding=SIGNED size=8 vlen=1\n"
+		"\t'v1' val=1024",
+		"[11] ENUM64 '(anon)' encoding=SIGNED size=8 vlen=1\n"
+		"\t'v1' val=1025",
+		"[12] STRUCT 'unneeded' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[13] STRUCT 'embedded' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[14] FUNC_PROTO '(anon)' ret_type_id=1 vlen=1\n"
+		"\t'p1' type_id=1",
+		"[15] ARRAY '(anon)' type_id=1 index_type_id=1 nr_elems=3",
+		"[16] STRUCT 'from_proto' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[17] UNION 'u1' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0");
+
+	btf2 = btf__new_empty_split(btf1);
+	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+		goto cleanup;
+
+	btf__add_ptr(btf2, 3);				/* [18] ptr to struct s1 */
+	/* add ptr to struct anon */
+	btf__add_ptr(btf2, 4);				/* [19] ptr to struct (anon) */
+	btf__add_const(btf2, 6);			/* [20] const union u1 */
+	btf__add_restrict(btf2, 7);			/* [21] restrict union (anon) */
+	btf__add_volatile(btf2, 8);			/* [22] volatile enum e1 */
+	btf__add_typedef(btf2, "et", 9);		/* [23] typedef enum (anon) */
+	btf__add_const(btf2, 10);			/* [24] const enum64 e641 */
+	btf__add_ptr(btf2, 11);				/* [25] restrict enum64 (anon) */
+	btf__add_struct(btf2, "with_embedded", 4);	/* [26] struct with_embedded { */
+	btf__add_field(btf2, "f1", 13, 0, 0);		/*	struct embedded f1; */
+							/* } */
+	btf__add_func(btf2, "fn", BTF_FUNC_STATIC, 14);	/* [27] int fn(int p1); */
+	btf__add_typedef(btf2, "arraytype", 15);	/* [28] typedef int[3] foo; */
+	btf__add_func_proto(btf2, 1);			/* [29] int (*)(struct from proto p1); */
+	btf__add_func_param(btf2, "p1", 16);
+
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1",
+		"[3] STRUCT 's1' size=8 vlen=1\n"
+		"\t'f1' type_id=2 bits_offset=0",
+		"[4] STRUCT '(anon)' size=12 vlen=2\n"
+		"\t'f1' type_id=1 bits_offset=0\n"
+		"\t'f2' type_id=3 bits_offset=32",
+		"[5] INT 'unsigned int' size=4 bits_offset=0 nr_bits=32 encoding=(none)",
+		"[6] UNION 'u1' size=12 vlen=2\n"
+		"\t'f1' type_id=1 bits_offset=0\n"
+		"\t'f2' type_id=2 bits_offset=0",
+		"[7] UNION '(anon)' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[8] ENUM 'e1' encoding=UNSIGNED size=4 vlen=1\n"
+		"\t'v1' val=1",
+		"[9] ENUM '(anon)' encoding=UNSIGNED size=4 vlen=1\n"
+		"\t'av1' val=2",
+		"[10] ENUM64 'e641' encoding=SIGNED size=8 vlen=1\n"
+		"\t'v1' val=1024",
+		"[11] ENUM64 '(anon)' encoding=SIGNED size=8 vlen=1\n"
+		"\t'v1' val=1025",
+		"[12] STRUCT 'unneeded' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[13] STRUCT 'embedded' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[14] FUNC_PROTO '(anon)' ret_type_id=1 vlen=1\n"
+		"\t'p1' type_id=1",
+		"[15] ARRAY '(anon)' type_id=1 index_type_id=1 nr_elems=3",
+		"[16] STRUCT 'from_proto' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[17] UNION 'u1' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[18] PTR '(anon)' type_id=3",
+		"[19] PTR '(anon)' type_id=4",
+		"[20] CONST '(anon)' type_id=6",
+		"[21] RESTRICT '(anon)' type_id=7",
+		"[22] VOLATILE '(anon)' type_id=8",
+		"[23] TYPEDEF 'et' type_id=9",
+		"[24] CONST '(anon)' type_id=10",
+		"[25] PTR '(anon)' type_id=11",
+		"[26] STRUCT 'with_embedded' size=4 vlen=1\n"
+		"\t'f1' type_id=13 bits_offset=0",
+		"[27] FUNC 'fn' type_id=14 linkage=static",
+		"[28] TYPEDEF 'arraytype' type_id=15",
+		"[29] FUNC_PROTO '(anon)' ret_type_id=1 vlen=1\n"
+		"\t'p1' type_id=16");
+
+	if (!ASSERT_EQ(0, btf__distill_base(btf2, &btf3, &btf4),
+		       "distilled_base") ||
+	    !ASSERT_OK_PTR(btf3, "distilled_base") ||
+	    !ASSERT_OK_PTR(btf4, "distilled_split") ||
+	    !ASSERT_EQ(8, btf__type_cnt(btf3), "distilled_base_type_cnt"))
+		goto cleanup;
+
+	VALIDATE_RAW_BTF(
+		btf4,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] STRUCT 's1' size=8 vlen=0",
+		"[3] UNION 'u1' size=12 vlen=0",
+		"[4] ENUM 'e1' encoding=UNSIGNED size=4 vlen=0",
+		"[5] ENUM 'e641' encoding=UNSIGNED size=8 vlen=0",
+		"[6] STRUCT 'embedded' size=4 vlen=0",
+		"[7] STRUCT 'from_proto' size=4 vlen=0",
+		/* split BTF; these types should match split BTF above from 17-28, with
+		 * updated type id references
+		 */
+		"[8] PTR '(anon)' type_id=2",
+		"[9] PTR '(anon)' type_id=20",
+		"[10] CONST '(anon)' type_id=3",
+		"[11] RESTRICT '(anon)' type_id=21",
+		"[12] VOLATILE '(anon)' type_id=4",
+		"[13] TYPEDEF 'et' type_id=22",
+		"[14] CONST '(anon)' type_id=5",
+		"[15] PTR '(anon)' type_id=23",
+		"[16] STRUCT 'with_embedded' size=4 vlen=1\n"
+		"\t'f1' type_id=6 bits_offset=0",
+		"[17] FUNC 'fn' type_id=24 linkage=static",
+		"[18] TYPEDEF 'arraytype' type_id=25",
+		"[19] FUNC_PROTO '(anon)' ret_type_id=1 vlen=1\n"
+		"\t'p1' type_id=7",
+		/* split BTF types added from original base BTF below */
+		"[20] STRUCT '(anon)' size=12 vlen=2\n"
+		"\t'f1' type_id=1 bits_offset=0\n"
+		"\t'f2' type_id=2 bits_offset=32",
+		"[21] UNION '(anon)' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[22] ENUM '(anon)' encoding=UNSIGNED size=4 vlen=1\n"
+		"\t'av1' val=2",
+		"[23] ENUM64 '(anon)' encoding=SIGNED size=8 vlen=1\n"
+		"\t'v1' val=1025",
+		"[24] FUNC_PROTO '(anon)' ret_type_id=1 vlen=1\n"
+		"\t'p1' type_id=1",
+		"[25] ARRAY '(anon)' type_id=1 index_type_id=1 nr_elems=3");
+
+	if (!ASSERT_EQ(btf__relocate(btf4, btf1), 0, "relocate_split"))
+		goto cleanup;
+
+	VALIDATE_RAW_BTF(
+		btf4,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1",
+		"[3] STRUCT 's1' size=8 vlen=1\n"
+		"\t'f1' type_id=2 bits_offset=0",
+		"[4] STRUCT '(anon)' size=12 vlen=2\n"
+		"\t'f1' type_id=1 bits_offset=0\n"
+		"\t'f2' type_id=3 bits_offset=32",
+		"[5] INT 'unsigned int' size=4 bits_offset=0 nr_bits=32 encoding=(none)",
+		"[6] UNION 'u1' size=12 vlen=2\n"
+		"\t'f1' type_id=1 bits_offset=0\n"
+		"\t'f2' type_id=2 bits_offset=0",
+		"[7] UNION '(anon)' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[8] ENUM 'e1' encoding=UNSIGNED size=4 vlen=1\n"
+		"\t'v1' val=1",
+		"[9] ENUM '(anon)' encoding=UNSIGNED size=4 vlen=1\n"
+		"\t'av1' val=2",
+		"[10] ENUM64 'e641' encoding=SIGNED size=8 vlen=1\n"
+		"\t'v1' val=1024",
+		"[11] ENUM64 '(anon)' encoding=SIGNED size=8 vlen=1\n"
+		"\t'v1' val=1025",
+		"[12] STRUCT 'unneeded' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[13] STRUCT 'embedded' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[14] FUNC_PROTO '(anon)' ret_type_id=1 vlen=1\n"
+		"\t'p1' type_id=1",
+		"[15] ARRAY '(anon)' type_id=1 index_type_id=1 nr_elems=3",
+		"[16] STRUCT 'from_proto' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[17] UNION 'u1' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[18] PTR '(anon)' type_id=3",
+		"[19] PTR '(anon)' type_id=30",
+		"[20] CONST '(anon)' type_id=6",
+		"[21] RESTRICT '(anon)' type_id=31",
+		"[22] VOLATILE '(anon)' type_id=8",
+		"[23] TYPEDEF 'et' type_id=32",
+		"[24] CONST '(anon)' type_id=10",
+		"[25] PTR '(anon)' type_id=33",
+		"[26] STRUCT 'with_embedded' size=4 vlen=1\n"
+		"\t'f1' type_id=13 bits_offset=0",
+		"[27] FUNC 'fn' type_id=34 linkage=static",
+		"[28] TYPEDEF 'arraytype' type_id=35",
+		"[29] FUNC_PROTO '(anon)' ret_type_id=1 vlen=1\n"
+		"\t'p1' type_id=16",
+		/* below here are (duplicate) anon base types added by distill
+		 * process to split BTF.
+		 */
+		"[30] STRUCT '(anon)' size=12 vlen=2\n"
+		"\t'f1' type_id=1 bits_offset=0\n"
+		"\t'f2' type_id=3 bits_offset=32",
+		"[31] UNION '(anon)' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[32] ENUM '(anon)' encoding=UNSIGNED size=4 vlen=1\n"
+		"\t'av1' val=2",
+		"[33] ENUM64 '(anon)' encoding=SIGNED size=8 vlen=1\n"
+		"\t'v1' val=1025",
+		"[34] FUNC_PROTO '(anon)' ret_type_id=1 vlen=1\n"
+		"\t'p1' type_id=1",
+		"[35] ARRAY '(anon)' type_id=1 index_type_id=1 nr_elems=3");
+
+cleanup:
+	btf__free(btf4);
+	btf__free(btf3);
+	btf__free(btf2);
+	btf__free(btf1);
+}
+
+/* ensure we can cope with multiple types with the same name in
+ * distilled base BTF.  In this case because sizes are different,
+ * we can still disambiguate them.
+ */
+static void test_distilled_base_multi(void)
+{
+	struct btf *btf1 = NULL, *btf2 = NULL, *btf3 = NULL, *btf4 = NULL;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+		return;
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);   /* [1] int */
+	btf__add_int(btf1, "int", 8, BTF_INT_SIGNED);	/* [2] int */
+	VALIDATE_RAW_BTF(
+		btf1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=8 bits_offset=0 nr_bits=64 encoding=SIGNED");
+	btf2 = btf__new_empty_split(btf1);
+	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+		goto cleanup;
+	btf__add_ptr(btf2, 1);
+	btf__add_const(btf2, 2);
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=8 bits_offset=0 nr_bits=64 encoding=SIGNED",
+		"[3] PTR '(anon)' type_id=1",
+		"[4] CONST '(anon)' type_id=2");
+	if (!ASSERT_EQ(0, btf__distill_base(btf2, &btf3, &btf4),
+		       "distilled_base") ||
+	    !ASSERT_OK_PTR(btf3, "distilled_base") ||
+	    !ASSERT_OK_PTR(btf4, "distilled_split") ||
+	    !ASSERT_EQ(3, btf__type_cnt(btf3), "distilled_base_type_cnt"))
+		goto cleanup;
+	VALIDATE_RAW_BTF(
+		btf3,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=8 bits_offset=0 nr_bits=64 encoding=SIGNED");
+	if (!ASSERT_EQ(btf__relocate(btf4, btf1), 0, "relocate_split"))
+		goto cleanup;
+
+	VALIDATE_RAW_BTF(
+		btf4,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=8 bits_offset=0 nr_bits=64 encoding=SIGNED",
+		"[3] PTR '(anon)' type_id=1",
+		"[4] CONST '(anon)' type_id=2");
+
+cleanup:
+	btf__free(btf4);
+	btf__free(btf3);
+	btf__free(btf2);
+	btf__free(btf1);
+}
+
+/* If a needed type is not present in the base BTF we wish to relocate
+ * with, btf__relocate() should error our.
+ */
+static void test_distilled_base_missing_err(void)
+{
+	struct btf *btf1 = NULL, *btf2 = NULL, *btf3 = NULL, *btf4 = NULL, *btf5 = NULL;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+		return;
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);   /* [1] int */
+	btf__add_int(btf1, "int", 8, BTF_INT_SIGNED);   /* [2] int */
+	VALIDATE_RAW_BTF(
+		btf1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=8 bits_offset=0 nr_bits=64 encoding=SIGNED");
+	btf2 = btf__new_empty_split(btf1);
+	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+		goto cleanup;
+	btf__add_ptr(btf2, 1);
+	btf__add_const(btf2, 2);
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=8 bits_offset=0 nr_bits=64 encoding=SIGNED",
+		"[3] PTR '(anon)' type_id=1",
+		"[4] CONST '(anon)' type_id=2");
+	if (!ASSERT_EQ(0, btf__distill_base(btf2, &btf3, &btf4),
+		       "distilled_base") ||
+	    !ASSERT_OK_PTR(btf3, "distilled_base") ||
+	    !ASSERT_OK_PTR(btf4, "distilled_split") ||
+	    !ASSERT_EQ(3, btf__type_cnt(btf3), "distilled_base_type_cnt"))
+		goto cleanup;
+	VALIDATE_RAW_BTF(
+		btf3,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=8 bits_offset=0 nr_bits=64 encoding=SIGNED");
+	btf5 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf5, "empty_reloc_btf"))
+		goto cleanup;
+	btf__add_int(btf5, "int", 4, BTF_INT_SIGNED);   /* [1] int */
+	VALIDATE_RAW_BTF(
+		btf5,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED");
+	ASSERT_EQ(btf__relocate(btf4, btf5), -EINVAL, "relocate_split");
+
+cleanup:
+	btf__free(btf5);
+	btf__free(btf4);
+	btf__free(btf3);
+	btf__free(btf2);
+	btf__free(btf1);
+}
+
+/* With 2 types of same size in distilled base BTF, relocation should
+ * fail as we have no means to choose between them.
+ */
+static void test_distilled_base_multi_err(void)
+{
+	struct btf *btf1 = NULL, *btf2 = NULL, *btf3 = NULL, *btf4 = NULL;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+		return;
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);   /* [1] int */
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);   /* [2] int */
+	VALIDATE_RAW_BTF(
+		btf1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED");
+	btf2 = btf__new_empty_split(btf1);
+	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+		goto cleanup;
+	btf__add_ptr(btf2, 1);
+	btf__add_const(btf2, 2);
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[3] PTR '(anon)' type_id=1",
+		"[4] CONST '(anon)' type_id=2");
+	if (!ASSERT_EQ(0, btf__distill_base(btf2, &btf3, &btf4),
+		       "distilled_base") ||
+	    !ASSERT_OK_PTR(btf3, "distilled_base") ||
+	    !ASSERT_OK_PTR(btf4, "distilled_split") ||
+	    !ASSERT_EQ(3, btf__type_cnt(btf3), "distilled_base_type_cnt"))
+		goto cleanup;
+	VALIDATE_RAW_BTF(
+		btf3,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED");
+	ASSERT_EQ(btf__relocate(btf4, btf1), -EINVAL, "relocate_split");
+cleanup:
+	btf__free(btf4);
+	btf__free(btf3);
+	btf__free(btf2);
+	btf__free(btf1);
+}
+
+/* With 2 types of same size in base BTF, relocation should
+ * fail as we have no means to choose between them.
+ */
+static void test_distilled_base_multi_err2(void)
+{
+	struct btf *btf1 = NULL, *btf2 = NULL, *btf3 = NULL, *btf4 = NULL, *btf5 = NULL;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+		return;
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);   /* [1] int */
+	VALIDATE_RAW_BTF(
+		btf1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED");
+	btf2 = btf__new_empty_split(btf1);
+	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+		goto cleanup;
+	btf__add_ptr(btf2, 1);
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1");
+	if (!ASSERT_EQ(0, btf__distill_base(btf2, &btf3, &btf4),
+		       "distilled_base") ||
+	    !ASSERT_OK_PTR(btf3, "distilled_base") ||
+	    !ASSERT_OK_PTR(btf4, "distilled_split") ||
+	    !ASSERT_EQ(2, btf__type_cnt(btf3), "distilled_base_type_cnt"))
+		goto cleanup;
+	VALIDATE_RAW_BTF(
+		btf3,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED");
+	btf5 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf5, "empty_reloc_btf"))
+		goto cleanup;
+	btf__add_int(btf5, "int", 4, BTF_INT_SIGNED);   /* [1] int */
+	btf__add_int(btf5, "int", 4, BTF_INT_SIGNED);   /* [2] int */
+	VALIDATE_RAW_BTF(
+		btf5,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED");
+	ASSERT_EQ(btf__relocate(btf4, btf5), -EINVAL, "relocate_split");
+cleanup:
+	btf__free(btf5);
+	btf__free(btf4);
+	btf__free(btf3);
+	btf__free(btf2);
+	btf__free(btf1);
+}
+
+/* create split reference BTF from vmlinux + split BTF with a few type references;
+ * ensure the resultant split reference BTF is as expected, containing only types
+ * needed to disambiguate references from split BTF.
+ */
+static void test_distilled_base_vmlinux(void)
+{
+	struct btf *split_btf = NULL, *vmlinux_btf = btf__load_vmlinux_btf();
+	struct btf *split_dist = NULL, *base_dist = NULL;
+	__s32 int_id, myint_id;
+
+	if (!ASSERT_OK_PTR(vmlinux_btf, "load_vmlinux"))
+		return;
+	int_id = btf__find_by_name_kind(vmlinux_btf, "int", BTF_KIND_INT);
+	if (!ASSERT_GT(int_id, 0, "find_int"))
+		goto cleanup;
+	split_btf = btf__new_empty_split(vmlinux_btf);
+	if (!ASSERT_OK_PTR(split_btf, "new_split"))
+		goto cleanup;
+	myint_id = btf__add_typedef(split_btf, "myint", int_id);
+	btf__add_ptr(split_btf, myint_id);
+
+	if (!ASSERT_EQ(btf__distill_base(split_btf, &base_dist, &split_dist), 0,
+		       "distill_vmlinux_base"))
+		goto cleanup;
+
+	if (!ASSERT_OK_PTR(split_dist, "split_distilled") ||
+	    !ASSERT_OK_PTR(base_dist, "base_dist"))
+		goto cleanup;
+	VALIDATE_RAW_BTF(
+		split_dist,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] TYPEDEF 'myint' type_id=1",
+		"[3] PTR '(anon)' type_id=2");
+
+cleanup:
+	btf__free(split_dist);
+	btf__free(base_dist);
+	btf__free(split_btf);
+	btf__free(vmlinux_btf);
+}
+
+/* Split and new base BTFs should inherit endianness from source BTF. */
+static void test_distilled_endianness(void)
+{
+	struct btf *base = NULL, *split = NULL, *new_base = NULL, *new_split = NULL;
+	struct btf *new_base1 = NULL, *new_split1 = NULL;
+	enum btf_endianness inverse_endianness;
+	const void *raw_data;
+	__u32 size;
+
+	base = btf__new_empty();
+	if (!ASSERT_OK_PTR(base, "empty_main_btf"))
+		return;
+	inverse_endianness = btf__endianness(base) == BTF_LITTLE_ENDIAN ? BTF_BIG_ENDIAN
+									: BTF_LITTLE_ENDIAN;
+	btf__set_endianness(base, inverse_endianness);
+	btf__add_int(base, "int", 4, BTF_INT_SIGNED);   /* [1] int */
+	VALIDATE_RAW_BTF(
+		base,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED");
+	split = btf__new_empty_split(base);
+	if (!ASSERT_OK_PTR(split, "empty_split_btf"))
+		goto cleanup;
+	btf__add_ptr(split, 1);
+	VALIDATE_RAW_BTF(
+		split,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1");
+	if (!ASSERT_EQ(0, btf__distill_base(split, &new_base, &new_split),
+		       "distilled_base") ||
+	    !ASSERT_OK_PTR(new_base, "distilled_base") ||
+	    !ASSERT_OK_PTR(new_split, "distilled_split") ||
+	    !ASSERT_EQ(2, btf__type_cnt(new_base), "distilled_base_type_cnt"))
+		goto cleanup;
+	VALIDATE_RAW_BTF(
+		new_split,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1");
+
+	raw_data = btf__raw_data(new_base, &size);
+	if (!ASSERT_OK_PTR(raw_data, "btf__raw_data #1"))
+		goto cleanup;
+	new_base1 = btf__new(raw_data, size);
+	if (!ASSERT_OK_PTR(new_base1, "new_base1 = btf__new()"))
+		goto cleanup;
+	raw_data = btf__raw_data(new_split, &size);
+	if (!ASSERT_OK_PTR(raw_data, "btf__raw_data #2"))
+		goto cleanup;
+	new_split1 = btf__new_split(raw_data, size, new_base1);
+	if (!ASSERT_OK_PTR(new_split1, "new_split1 = btf__new()"))
+		goto cleanup;
+
+	ASSERT_EQ(btf__endianness(new_base1), inverse_endianness, "new_base1 endianness");
+	ASSERT_EQ(btf__endianness(new_split1), inverse_endianness, "new_split1 endianness");
+	VALIDATE_RAW_BTF(
+		new_split1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1");
+cleanup:
+	btf__free(new_split1);
+	btf__free(new_base1);
+	btf__free(new_split);
+	btf__free(new_base);
+	btf__free(split);
+	btf__free(base);
+}
+
+/* If a needed composite type, which is the member of composite type
+ * in the split BTF, has a different size in the base BTF we wish to
+ * relocate with, btf__relocate() should error out.
+ */
+static void test_distilled_base_embedded_err(void)
+{
+	struct btf *btf1 = NULL, *btf2 = NULL, *btf3 = NULL, *btf4 = NULL, *btf5 = NULL;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+		return;
+
+	btf__add_int(btf1, "int", 4, BTF_INT_SIGNED);   /* [1] int */
+	btf__add_struct(btf1, "s1", 4);                 /* [2] struct s1 { */
+	btf__add_field(btf1, "f1", 1, 0, 0);            /*      int f1; */
+							/* } */
+	VALIDATE_RAW_BTF(
+		btf1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] STRUCT 's1' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0");
+
+	btf2 = btf__new_empty_split(btf1);
+	if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+		goto cleanup;
+
+	btf__add_struct(btf2, "with_embedded", 8);      /* [3] struct with_embedded { */
+	btf__add_field(btf2, "e1", 2, 0, 0);		/*      struct s1 e1; */
+							/* } */
+
+	VALIDATE_RAW_BTF(
+		btf2,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] STRUCT 's1' size=4 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0",
+		"[3] STRUCT 'with_embedded' size=8 vlen=1\n"
+		"\t'e1' type_id=2 bits_offset=0");
+
+	if (!ASSERT_EQ(0, btf__distill_base(btf2, &btf3, &btf4),
+		       "distilled_base") ||
+	    !ASSERT_OK_PTR(btf3, "distilled_base") ||
+	    !ASSERT_OK_PTR(btf4, "distilled_split") ||
+	    !ASSERT_EQ(2, btf__type_cnt(btf3), "distilled_base_type_cnt"))
+		goto cleanup;
+
+	VALIDATE_RAW_BTF(
+		btf4,
+		"[1] STRUCT 's1' size=4 vlen=0",
+		"[2] STRUCT 'with_embedded' size=8 vlen=1\n"
+		"\t'e1' type_id=1 bits_offset=0");
+
+	btf5 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf5, "empty_reloc_btf"))
+		goto cleanup;
+
+	btf__add_int(btf5, "int", 4, BTF_INT_SIGNED);   /* [1] int */
+	/* struct with the same name but different size */
+	btf__add_struct(btf5, "s1", 8);                 /* [2] struct s1 { */
+	btf__add_field(btf5, "f1", 1, 0, 0);            /*      int f1; */
+							/* } */
+
+	ASSERT_EQ(btf__relocate(btf4, btf5), -EINVAL, "relocate_split");
+cleanup:
+	btf__free(btf5);
+	btf__free(btf4);
+	btf__free(btf3);
+	btf__free(btf2);
+	btf__free(btf1);
+}
+
+void test_btf_distill(void)
+{
+	if (test__start_subtest("distilled_base"))
+		test_distilled_base();
+	if (test__start_subtest("distilled_base_multi"))
+		test_distilled_base_multi();
+	if (test__start_subtest("distilled_base_missing_err"))
+		test_distilled_base_missing_err();
+	if (test__start_subtest("distilled_base_multi_err"))
+		test_distilled_base_multi_err();
+	if (test__start_subtest("distilled_base_multi_err2"))
+		test_distilled_base_multi_err2();
+	if (test__start_subtest("distilled_base_embedded_err"))
+		test_distilled_base_embedded_err();
+	if (test__start_subtest("distilled_base_vmlinux"))
+		test_distilled_base_vmlinux();
+	if (test__start_subtest("distilled_endianness"))
+		test_distilled_endianness();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index 0ba2e8b9c6ac..10cba526d3e6 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -63,7 +63,7 @@ static int test_btf_dump_case(int n, struct btf_dump_test_case *t)
 
 	/* tests with t->known_ptr_sz have no "long" or "unsigned long" type,
 	 * so it's impossible to determine correct pointer size; but if they
-	 * do, it should be 8 regardless of host architecture, becaues BPF
+	 * do, it should be 8 regardless of host architecture, because BPF
 	 * target is always 64-bit
 	 */
 	if (!t->known_ptr_sz) {
@@ -126,26 +126,69 @@ done:
 	return err;
 }
 
-static char *dump_buf;
-static size_t dump_buf_sz;
-static FILE *dump_buf_file;
+struct test_ctx {
+	struct btf *btf;
+	struct btf_dump *d;
+	char *dump_buf;
+	size_t dump_buf_sz;
+	FILE *dump_buf_file;
+};
 
-static void test_btf_dump_incremental(void)
+static void test_ctx__free(struct test_ctx *t)
 {
-	struct btf *btf = NULL;
-	struct btf_dump *d = NULL;
-	int id, err, i;
+	fclose(t->dump_buf_file);
+	free(t->dump_buf);
+	btf_dump__free(t->d);
+	btf__free(t->btf);
+}
 
-	dump_buf_file = open_memstream(&dump_buf, &dump_buf_sz);
-	if (!ASSERT_OK_PTR(dump_buf_file, "dump_memstream"))
-		return;
-	btf = btf__new_empty();
-	if (!ASSERT_OK_PTR(btf, "new_empty"))
+static int test_ctx__init(struct test_ctx *t)
+{
+	t->dump_buf_file = open_memstream(&t->dump_buf, &t->dump_buf_sz);
+	if (!ASSERT_OK_PTR(t->dump_buf_file, "dump_memstream"))
+		return -1;
+	t->btf = btf__new_empty();
+	if (!ASSERT_OK_PTR(t->btf, "new_empty"))
 		goto err_out;
-	d = btf_dump__new(btf, btf_dump_printf, dump_buf_file, NULL);
-	if (!ASSERT_OK(libbpf_get_error(d), "btf_dump__new"))
+	t->d = btf_dump__new(t->btf, btf_dump_printf, t->dump_buf_file, NULL);
+	if (!ASSERT_OK(libbpf_get_error(t->d), "btf_dump__new"))
 		goto err_out;
 
+	return 0;
+
+err_out:
+	test_ctx__free(t);
+	return -1;
+}
+
+static void test_ctx__dump_and_compare(struct test_ctx *t,
+				       const char *expected_output,
+				       const char *message)
+{
+	int i, err;
+
+	for (i = 1; i < btf__type_cnt(t->btf); i++) {
+		err = btf_dump__dump_type(t->d, i);
+		ASSERT_OK(err, "dump_type_ok");
+	}
+
+	fflush(t->dump_buf_file);
+	t->dump_buf[t->dump_buf_sz] = 0; /* some libc implementations don't do this */
+
+	ASSERT_STREQ(t->dump_buf, expected_output, message);
+}
+
+static void test_btf_dump_incremental(void)
+{
+	struct test_ctx t = {};
+	struct btf *btf;
+	int id, err;
+
+	if (test_ctx__init(&t))
+		return;
+
+	btf = t.btf;
+
 	/* First, generate BTF corresponding to the following C code:
 	 *
 	 * enum x;
@@ -182,15 +225,7 @@ static void test_btf_dump_incremental(void)
 	err = btf__add_field(btf, "x", 4, 0, 0);
 	ASSERT_OK(err, "field_ok");
 
-	for (i = 1; i < btf__type_cnt(btf); i++) {
-		err = btf_dump__dump_type(d, i);
-		ASSERT_OK(err, "dump_type_ok");
-	}
-
-	fflush(dump_buf_file);
-	dump_buf[dump_buf_sz] = 0; /* some libc implementations don't do this */
-
-	ASSERT_STREQ(dump_buf,
+	test_ctx__dump_and_compare(&t,
 "enum x;\n"
 "\n"
 "enum x {\n"
@@ -221,7 +256,7 @@ static void test_btf_dump_incremental(void)
 	 * enum values don't conflict;
 	 *
 	 */
-	fseek(dump_buf_file, 0, SEEK_SET);
+	fseek(t.dump_buf_file, 0, SEEK_SET);
 
 	id = btf__add_struct(btf, "s", 4);
 	ASSERT_EQ(id, 7, "struct_id");
@@ -232,14 +267,7 @@ static void test_btf_dump_incremental(void)
 	err = btf__add_field(btf, "s", 6, 64, 0);
 	ASSERT_OK(err, "field_ok");
 
-	for (i = 1; i < btf__type_cnt(btf); i++) {
-		err = btf_dump__dump_type(d, i);
-		ASSERT_OK(err, "dump_type_ok");
-	}
-
-	fflush(dump_buf_file);
-	dump_buf[dump_buf_sz] = 0; /* some libc implementations don't do this */
-	ASSERT_STREQ(dump_buf,
+	test_ctx__dump_and_compare(&t,
 "struct s___2 {\n"
 "	enum x x;\n"
 "	enum {\n"
@@ -248,11 +276,53 @@ static void test_btf_dump_incremental(void)
 "	struct s s;\n"
 "};\n\n" , "c_dump1");
 
-err_out:
-	fclose(dump_buf_file);
-	free(dump_buf);
-	btf_dump__free(d);
-	btf__free(btf);
+	test_ctx__free(&t);
+}
+
+static void test_btf_dump_type_tags(void)
+{
+	struct test_ctx t = {};
+	struct btf *btf;
+	int id, err;
+
+	if (test_ctx__init(&t))
+		return;
+
+	btf = t.btf;
+
+	/* Generate BTF corresponding to the following C code:
+	 *
+	 * struct s {
+	 *   void __attribute__((btf_type_tag(\"void_tag\"))) *p1;
+	 *   void __attribute__((void_attr)) *p2;
+	 * };
+	 *
+	 */
+
+	id = btf__add_type_tag(btf, "void_tag", 0);
+	ASSERT_EQ(id, 1, "type_tag_id");
+	id = btf__add_ptr(btf, id);
+	ASSERT_EQ(id, 2, "void_ptr_id1");
+
+	id = btf__add_type_attr(btf, "void_attr", 0);
+	ASSERT_EQ(id, 3, "type_attr_id");
+	id = btf__add_ptr(btf, id);
+	ASSERT_EQ(id, 4, "void_ptr_id2");
+
+	id = btf__add_struct(btf, "s", 8);
+	ASSERT_EQ(id, 5, "struct_id");
+	err = btf__add_field(btf, "p1", 2, 0, 0);
+	ASSERT_OK(err, "field_ok1");
+	err = btf__add_field(btf, "p2", 4, 0, 0);
+	ASSERT_OK(err, "field_ok2");
+
+	test_ctx__dump_and_compare(&t,
+"struct s {\n"
+"	void __attribute__((btf_type_tag(\"void_tag\"))) *p1;\n"
+"	void __attribute__((void_attr)) *p2;\n"
+"};\n\n", "dump_and_compare");
+
+	test_ctx__free(&t);
 }
 
 #define STRSIZE				4096
@@ -653,7 +723,7 @@ static void test_btf_dump_struct_data(struct btf *btf, struct btf_dump *d,
 		cmpstr =
 "(struct file_operations){\n"
 "	.owner = (struct module *)0xffffffffffffffff,\n"
-"	.llseek = (loff_t (*)(struct file *, loff_t, int))0xffffffffffffffff,";
+"	.fop_flags = (fop_flags_t)4294967295,";
 
 		ASSERT_STRNEQ(str, cmpstr, strlen(cmpstr), "file_operations");
 	}
@@ -801,12 +871,128 @@ static void test_btf_dump_struct_data(struct btf *btf, struct btf_dump *d,
 static void test_btf_dump_var_data(struct btf *btf, struct btf_dump *d,
 				   char *str)
 {
-#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
+#if 0
 	TEST_BTF_DUMP_VAR(btf, d, NULL, str, "cpu_number", int, BTF_F_COMPACT,
 			  "int cpu_number = (int)100", 100);
 #endif
-	TEST_BTF_DUMP_VAR(btf, d, NULL, str, "cpu_profile_flip", int, BTF_F_COMPACT,
-			  "static int cpu_profile_flip = (int)2", 2);
+	TEST_BTF_DUMP_VAR(btf, d, NULL, str, "bpf_cgrp_storage_busy", int, BTF_F_COMPACT,
+			  "static int bpf_cgrp_storage_busy = (int)2", 2);
+}
+
+struct btf_dump_string_ctx {
+	struct btf *btf;
+	struct btf_dump *d;
+	char *str;
+	struct btf_dump_type_data_opts *opts;
+	int array_id;
+};
+
+static int btf_dump_one_string(struct btf_dump_string_ctx *ctx,
+			       char *ptr, size_t ptr_sz,
+			       const char *expected_val)
+{
+	size_t type_sz;
+	int ret;
+
+	ctx->str[0] = '\0';
+	type_sz = btf__resolve_size(ctx->btf, ctx->array_id);
+	ret = btf_dump__dump_type_data(ctx->d, ctx->array_id, ptr, ptr_sz, ctx->opts);
+	if (type_sz <= ptr_sz) {
+		if (!ASSERT_EQ(ret, type_sz, "failed/unexpected type_sz"))
+			return -EINVAL;
+	}
+	if (!ASSERT_STREQ(ctx->str, expected_val, "ensure expected/actual match"))
+		return -EFAULT;
+	return 0;
+}
+
+static void btf_dump_strings(struct btf_dump_string_ctx *ctx)
+{
+	struct btf_dump_type_data_opts *opts = ctx->opts;
+
+	opts->emit_strings = true;
+
+	opts->compact = true;
+	opts->emit_zeroes = false;
+
+	opts->skip_names = false;
+	btf_dump_one_string(ctx, "foo", 4, "(char[4])\"foo\"");
+
+	opts->skip_names = true;
+	btf_dump_one_string(ctx, "foo", 4, "\"foo\"");
+
+	/* This should have no effect. */
+	opts->emit_zeroes = false;
+	btf_dump_one_string(ctx, "foo", 4, "\"foo\"");
+
+	/* This should have no effect. */
+	opts->compact = false;
+	btf_dump_one_string(ctx, "foo", 4, "\"foo\"");
+
+	/* Non-printable characters come out as hex. */
+	btf_dump_one_string(ctx, "fo\xff", 4, "\"fo\\xff\"");
+	btf_dump_one_string(ctx, "fo\x7", 4, "\"fo\\x07\"");
+
+	/*
+	 * Strings that are too long for the specified type ("char[4]")
+	 * should fall back to the current behavior.
+	 */
+	opts->compact = true;
+	btf_dump_one_string(ctx, "abcde", 6, "['a','b','c','d',]");
+
+	/*
+	 * Strings that are too short for the specified type ("char[4]")
+	 * should work normally.
+	 */
+	btf_dump_one_string(ctx, "ab", 3, "\"ab\"");
+
+	/* Non-NUL-terminated arrays don't get printed as strings. */
+	char food[4] = { 'f', 'o', 'o', 'd' };
+	char bye[3] = { 'b', 'y', 'e' };
+
+	btf_dump_one_string(ctx, food, 4, "['f','o','o','d',]");
+	btf_dump_one_string(ctx, bye, 3, "['b','y','e',]");
+
+	/* The embedded NUL should terminate the string. */
+	char embed[4] = { 'f', 'o', '\0', 'd' };
+
+	btf_dump_one_string(ctx, embed, 4, "\"fo\"");
+}
+
+static void test_btf_dump_string_data(void)
+{
+	struct test_ctx t = {};
+	char str[STRSIZE];
+	struct btf_dump *d;
+	DECLARE_LIBBPF_OPTS(btf_dump_type_data_opts, opts);
+	struct btf_dump_string_ctx ctx;
+	int char_id, int_id, array_id;
+
+	if (test_ctx__init(&t))
+		return;
+
+	d = btf_dump__new(t.btf, btf_dump_snprintf, str, NULL);
+	if (!ASSERT_OK_PTR(d, "could not create BTF dump"))
+		return;
+
+	/* Generate BTF for a four-element char array. */
+	char_id = btf__add_int(t.btf, "char", 1, BTF_INT_CHAR);
+	ASSERT_EQ(char_id, 1, "char_id");
+	int_id = btf__add_int(t.btf, "int", 4, BTF_INT_SIGNED);
+	ASSERT_EQ(int_id, 2, "int_id");
+	array_id = btf__add_array(t.btf, int_id, char_id, 4);
+	ASSERT_EQ(array_id, 3, "array_id");
+
+	ctx.btf = t.btf;
+	ctx.d = d;
+	ctx.str = str;
+	ctx.opts = &opts;
+	ctx.array_id = array_id;
+
+	btf_dump_strings(&ctx);
+
+	btf_dump__free(d);
+	test_ctx__free(&t);
 }
 
 static void test_btf_datasec(struct btf *btf, struct btf_dump *d, char *str,
@@ -874,6 +1060,9 @@ void test_btf_dump() {
 	if (test__start_subtest("btf_dump: incremental"))
 		test_btf_dump_incremental();
 
+	if (test__start_subtest("btf_dump: type_tags"))
+		test_btf_dump_type_tags();
+
 	btf = libbpf_find_kernel_btf();
 	if (!ASSERT_OK_PTR(btf, "no kernel BTF found"))
 		return;
@@ -897,6 +1086,8 @@ void test_btf_dump() {
 		test_btf_dump_struct_data(btf, d, str);
 	if (test__start_subtest("btf_dump: var_data"))
 		test_btf_dump_var_data(btf, d, str);
+	if (test__start_subtest("btf_dump: string_data"))
+		test_btf_dump_string_data();
 	btf_dump__free(d);
 	btf__free(btf);
 
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_field_iter.c b/tools/testing/selftests/bpf/prog_tests/btf_field_iter.c
new file mode 100644
index 000000000000..32159d3eb281
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/btf_field_iter.c
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024, Oracle and/or its affiliates. */
+
+#include <test_progs.h>
+#include <bpf/btf.h>
+#include "btf_helpers.h"
+#include "bpf/libbpf_internal.h"
+
+struct field_data {
+	__u32 ids[5];
+	const char *strs[5];
+} fields[] = {
+	{ .ids = {},		.strs = {} },
+	{ .ids = {},		.strs = { "int" } },
+	{ .ids = {},		.strs = { "int64" } },
+	{ .ids = { 1 },		.strs = { "" } },
+	{ .ids = { 2, 1 },	.strs = { "" } },
+	{ .ids = { 3, 1 },	.strs = { "s1", "f1", "f2" } },
+	{ .ids = { 1, 5 },	.strs = { "u1", "f1", "f2" } },
+	{ .ids = {},		.strs = { "e1", "v1", "v2" } },
+	{ .ids = {},		.strs = { "fw1" } },
+	{ .ids = { 1 },		.strs = { "t" } },
+	{ .ids = { 2 },		.strs = { "" } },
+	{ .ids = { 1 },		.strs = { "" } },
+	{ .ids = { 3 },		.strs = { "" } },
+	{ .ids = { 1, 1, 3 },	.strs = { "", "p1", "p2" } },
+	{ .ids = { 13 },	.strs = { "func" } },
+	{ .ids = { 1 },		.strs = { "var1" } },
+	{ .ids = { 3 },		.strs = { "var2" } },
+	{ .ids = {},		.strs = { "float" } },
+	{ .ids = { 11 },	.strs = { "decltag" } },
+	{ .ids = { 6 },		.strs = { "typetag" } },
+	{ .ids = {},		.strs = { "e64", "eval1", "eval2", "eval3" } },
+	{ .ids = { 15, 16 },	.strs = { "datasec1" } }
+
+};
+
+/* Fabricate BTF with various types and check BTF field iteration finds types,
+ * strings expected.
+ */
+void test_btf_field_iter(void)
+{
+	struct btf *btf = NULL;
+	int id;
+
+	btf = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf, "empty_btf"))
+		return;
+
+	btf__add_int(btf, "int", 4, BTF_INT_SIGNED);	/* [1] int */
+	btf__add_int(btf, "int64", 8, BTF_INT_SIGNED);	/* [2] int64 */
+	btf__add_ptr(btf, 1);				/* [3] int * */
+	btf__add_array(btf, 1, 2, 3);			/* [4] int64[3] */
+	btf__add_struct(btf, "s1", 12);			/* [5] struct s1 { */
+	btf__add_field(btf, "f1", 3, 0, 0);		/*      int *f1; */
+	btf__add_field(btf, "f2", 1, 0, 0);		/*	int f2; */
+							/* } */
+	btf__add_union(btf, "u1", 12);			/* [6] union u1 { */
+	btf__add_field(btf, "f1", 1, 0, 0);		/*	int f1; */
+	btf__add_field(btf, "f2", 5, 0, 0);		/*	struct s1 f2; */
+							/* } */
+	btf__add_enum(btf, "e1", 4);			/* [7] enum e1 { */
+	btf__add_enum_value(btf, "v1", 1);		/*	v1 = 1; */
+	btf__add_enum_value(btf, "v2", 2);		/*	v2 = 2; */
+							/* } */
+
+	btf__add_fwd(btf, "fw1", BTF_FWD_STRUCT);	/* [8] struct fw1; */
+	btf__add_typedef(btf, "t", 1);			/* [9] typedef int t; */
+	btf__add_volatile(btf, 2);			/* [10] volatile int64; */
+	btf__add_const(btf, 1);				/* [11] const int; */
+	btf__add_restrict(btf, 3);			/* [12] restrict int *; */
+	btf__add_func_proto(btf, 1);			/* [13] int (*)(int p1, int *p2); */
+	btf__add_func_param(btf, "p1", 1);
+	btf__add_func_param(btf, "p2", 3);
+
+	btf__add_func(btf, "func", BTF_FUNC_GLOBAL, 13);/* [14] int func(int p1, int *p2); */
+	btf__add_var(btf, "var1", BTF_VAR_STATIC, 1);	/* [15] static int var1; */
+	btf__add_var(btf, "var2", BTF_VAR_STATIC, 3);	/* [16] static int *var2; */
+	btf__add_float(btf, "float", 4);		/* [17] float; */
+	btf__add_decl_tag(btf, "decltag", 11, -1);	/* [18] decltag const int; */
+	btf__add_type_tag(btf, "typetag", 6);		/* [19] typetag union u1; */
+	btf__add_enum64(btf, "e64", 8, true);		/* [20] enum { */
+	btf__add_enum64_value(btf, "eval1", 1000);	/*	 eval1 = 1000, */
+	btf__add_enum64_value(btf, "eval2", 2000);	/*	 eval2 = 2000, */
+	btf__add_enum64_value(btf, "eval3", 3000);	/*	 eval3 = 3000 */
+							/* } */
+	btf__add_datasec(btf, "datasec1", 12);		/* [21] datasec datasec1 */
+	btf__add_datasec_var_info(btf, 15, 0, 4);
+	btf__add_datasec_var_info(btf, 16, 4, 8);
+
+	VALIDATE_RAW_BTF(
+		btf,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] INT 'int64' size=8 bits_offset=0 nr_bits=64 encoding=SIGNED",
+		"[3] PTR '(anon)' type_id=1",
+		"[4] ARRAY '(anon)' type_id=2 index_type_id=1 nr_elems=3",
+		"[5] STRUCT 's1' size=12 vlen=2\n"
+		"\t'f1' type_id=3 bits_offset=0\n"
+		"\t'f2' type_id=1 bits_offset=0",
+		"[6] UNION 'u1' size=12 vlen=2\n"
+		"\t'f1' type_id=1 bits_offset=0\n"
+		"\t'f2' type_id=5 bits_offset=0",
+		"[7] ENUM 'e1' encoding=UNSIGNED size=4 vlen=2\n"
+		"\t'v1' val=1\n"
+		"\t'v2' val=2",
+		"[8] FWD 'fw1' fwd_kind=struct",
+		"[9] TYPEDEF 't' type_id=1",
+		"[10] VOLATILE '(anon)' type_id=2",
+		"[11] CONST '(anon)' type_id=1",
+		"[12] RESTRICT '(anon)' type_id=3",
+		"[13] FUNC_PROTO '(anon)' ret_type_id=1 vlen=2\n"
+		"\t'p1' type_id=1\n"
+		"\t'p2' type_id=3",
+		"[14] FUNC 'func' type_id=13 linkage=global",
+		"[15] VAR 'var1' type_id=1, linkage=static",
+		"[16] VAR 'var2' type_id=3, linkage=static",
+		"[17] FLOAT 'float' size=4",
+		"[18] DECL_TAG 'decltag' type_id=11 component_idx=-1",
+		"[19] TYPE_TAG 'typetag' type_id=6",
+		"[20] ENUM64 'e64' encoding=SIGNED size=8 vlen=3\n"
+		"\t'eval1' val=1000\n"
+		"\t'eval2' val=2000\n"
+		"\t'eval3' val=3000",
+		"[21] DATASEC 'datasec1' size=12 vlen=2\n"
+		"\ttype_id=15 offset=0 size=4\n"
+		"\ttype_id=16 offset=4 size=8");
+
+	for (id = 1; id < btf__type_cnt(btf); id++) {
+		struct btf_type *t = btf_type_by_id(btf, id);
+		struct btf_field_iter it_strs, it_ids;
+		int str_idx = 0, id_idx = 0;
+		__u32 *next_str, *next_id;
+
+		if (!ASSERT_OK_PTR(t, "btf_type_by_id"))
+			break;
+		if (!ASSERT_OK(btf_field_iter_init(&it_strs, t, BTF_FIELD_ITER_STRS),
+			       "iter_init_strs"))
+			break;
+		if (!ASSERT_OK(btf_field_iter_init(&it_ids, t, BTF_FIELD_ITER_IDS),
+			       "iter_init_ids"))
+			break;
+		while ((next_str = btf_field_iter_next(&it_strs))) {
+			const char *str = btf__str_by_offset(btf, *next_str);
+
+			if (!ASSERT_OK(strcmp(fields[id].strs[str_idx], str), "field_str_match"))
+				break;
+			str_idx++;
+		}
+		/* ensure no more strings are expected */
+		ASSERT_EQ(fields[id].strs[str_idx], NULL, "field_str_cnt");
+
+		while ((next_id = btf_field_iter_next(&it_ids))) {
+			if (!ASSERT_EQ(*next_id, fields[id].ids[id_idx], "field_id_match"))
+				break;
+			id_idx++;
+		}
+		/* ensure no more ids are expected */
+		ASSERT_EQ(fields[id].ids[id_idx], 0, "field_id_cnt");
+	}
+	btf__free(btf);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
index eb90a6b8850d..f66ceccd7029 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_map_in_map.c
@@ -14,7 +14,7 @@ static __u32 bpf_map_id(struct bpf_map *map)
 	int err;
 
 	memset(&info, 0, info_len);
-	err = bpf_obj_get_info_by_fd(bpf_map__fd(map), &info, &info_len);
+	err = bpf_map_get_info_by_fd(bpf_map__fd(map), &info, &info_len);
 	if (err)
 		return 0;
 	return info.id;
@@ -25,7 +25,7 @@ static void test_lookup_update(void)
 	int map1_fd, map2_fd, map3_fd, map4_fd, map5_fd, map1_id, map2_id;
 	int outer_arr_fd, outer_hash_fd, outer_arr_dyn_fd;
 	struct test_btf_map_in_map *skel;
-	int err, key = 0, val, i, fd;
+	int err, key = 0, val, i;
 
 	skel = test_btf_map_in_map__open_and_load();
 	if (CHECK(!skel, "skel_open", "failed to open&load skeleton\n"))
@@ -102,30 +102,6 @@ static void test_lookup_update(void)
 	CHECK(map1_id == 0, "map1_id", "failed to get ID 1\n");
 	CHECK(map2_id == 0, "map2_id", "failed to get ID 2\n");
 
-	test_btf_map_in_map__destroy(skel);
-	skel = NULL;
-
-	/* we need to either wait for or force synchronize_rcu(), before
-	 * checking for "still exists" condition, otherwise map could still be
-	 * resolvable by ID, causing false positives.
-	 *
-	 * Older kernels (5.8 and earlier) freed map only after two
-	 * synchronize_rcu()s, so trigger two, to be entirely sure.
-	 */
-	CHECK(kern_sync_rcu(), "sync_rcu", "failed\n");
-	CHECK(kern_sync_rcu(), "sync_rcu", "failed\n");
-
-	fd = bpf_map_get_fd_by_id(map1_id);
-	if (CHECK(fd >= 0, "map1_leak", "inner_map1 leaked!\n")) {
-		close(fd);
-		goto cleanup;
-	}
-	fd = bpf_map_get_fd_by_id(map2_id);
-	if (CHECK(fd >= 0, "map2_leak", "inner_map2 leaked!\n")) {
-		close(fd);
-		goto cleanup;
-	}
-
 cleanup:
 	test_btf_map_in_map__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
index ef4d6a3ae423..cf15cc3be491 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
@@ -17,32 +17,37 @@
 #include "test_progs.h"
 #include "test_btf_skc_cls_ingress.skel.h"
 
-static struct test_btf_skc_cls_ingress *skel;
-static struct sockaddr_in6 srv_sa6;
-static __u32 duration;
+#define TEST_NS "skc_cls_ingress"
 
-static int prepare_netns(void)
+#define BIT(n)		(1 << (n))
+#define TEST_MODE_IPV4	BIT(0)
+#define TEST_MODE_IPV6	BIT(1)
+#define TEST_MODE_DUAL	(TEST_MODE_IPV4 | TEST_MODE_IPV6)
+
+#define SERVER_ADDR_IPV4	"127.0.0.1"
+#define SERVER_ADDR_IPV6	"::1"
+#define SERVER_ADDR_DUAL	"::0"
+/* RFC791, 576 for minimal IPv4 datagram, minus 40 bytes of TCP header */
+#define MIN_IPV4_MSS		536
+
+static struct netns_obj *prepare_netns(struct test_btf_skc_cls_ingress *skel)
 {
 	LIBBPF_OPTS(bpf_tc_hook, qdisc_lo, .attach_point = BPF_TC_INGRESS);
 	LIBBPF_OPTS(bpf_tc_opts, tc_attach,
 		    .prog_fd = bpf_program__fd(skel->progs.cls_ingress));
+	struct netns_obj *ns = NULL;
 
-	if (CHECK(unshare(CLONE_NEWNET), "create netns",
-		  "unshare(CLONE_NEWNET): %s (%d)",
-		  strerror(errno), errno))
-		return -1;
-
-	if (CHECK(system("ip link set dev lo up"),
-		  "ip link set dev lo up", "failed\n"))
-		return -1;
+	ns = netns_new(TEST_NS, true);
+	if (!ASSERT_OK_PTR(ns, "create and join netns"))
+		return ns;
 
 	qdisc_lo.ifindex = if_nametoindex("lo");
 	if (!ASSERT_OK(bpf_tc_hook_create(&qdisc_lo), "qdisc add dev lo clsact"))
-		return -1;
+		goto free_ns;
 
 	if (!ASSERT_OK(bpf_tc_attach(&qdisc_lo, &tc_attach),
 		       "filter add dev lo ingress"))
-		return -1;
+		goto free_ns;
 
 	/* Ensure 20 bytes options (i.e. in total 40 bytes tcp header) for the
 	 * bpf_tcp_gen_syncookie() helper.
@@ -50,71 +55,142 @@ static int prepare_netns(void)
 	if (write_sysctl("/proc/sys/net/ipv4/tcp_window_scaling", "1") ||
 	    write_sysctl("/proc/sys/net/ipv4/tcp_timestamps", "1") ||
 	    write_sysctl("/proc/sys/net/ipv4/tcp_sack", "1"))
-		return -1;
+		goto free_ns;
+
+	return ns;
 
-	return 0;
+free_ns:
+	netns_free(ns);
+	return NULL;
 }
 
-static void reset_test(void)
+static void reset_test(struct test_btf_skc_cls_ingress *skel)
 {
+	memset(&skel->bss->srv_sa4, 0, sizeof(skel->bss->srv_sa4));
 	memset(&skel->bss->srv_sa6, 0, sizeof(skel->bss->srv_sa6));
 	skel->bss->listen_tp_sport = 0;
 	skel->bss->req_sk_sport = 0;
 	skel->bss->recv_cookie = 0;
 	skel->bss->gen_cookie = 0;
 	skel->bss->linum = 0;
+	skel->bss->mss = 0;
 }
 
-static void print_err_line(void)
+static void print_err_line(struct test_btf_skc_cls_ingress *skel)
 {
 	if (skel->bss->linum)
 		printf("bpf prog error at line %u\n", skel->bss->linum);
 }
 
-static void test_conn(void)
+static int v6only_true(int fd, void *opts)
+{
+	int mode = true;
+
+	return setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, &mode, sizeof(mode));
+}
+
+static int v6only_false(int fd, void *opts)
 {
+	int mode = false;
+
+	return setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, &mode, sizeof(mode));
+}
+
+static void run_test(struct test_btf_skc_cls_ingress *skel, bool gen_cookies,
+		     int ip_mode)
+{
+	const char *tcp_syncookies = gen_cookies ? "2" : "1";
 	int listen_fd = -1, cli_fd = -1, srv_fd = -1, err;
-	socklen_t addrlen = sizeof(srv_sa6);
+	struct network_helper_opts opts = { 0 };
+	struct sockaddr_storage *addr;
+	struct sockaddr_in6 srv_sa6;
+	struct sockaddr_in srv_sa4;
+	socklen_t addr_len;
+	int sock_family;
+	char *srv_addr;
 	int srv_port;
 
-	if (write_sysctl("/proc/sys/net/ipv4/tcp_syncookies", "1"))
+	switch (ip_mode) {
+	case TEST_MODE_IPV4:
+		sock_family = AF_INET;
+		srv_addr = SERVER_ADDR_IPV4;
+		addr = (struct sockaddr_storage *)&srv_sa4;
+		addr_len = sizeof(srv_sa4);
+		break;
+	case TEST_MODE_IPV6:
+		opts.post_socket_cb = v6only_true;
+		sock_family = AF_INET6;
+		srv_addr = SERVER_ADDR_IPV6;
+		addr = (struct sockaddr_storage *)&srv_sa6;
+		addr_len = sizeof(srv_sa6);
+		break;
+	case TEST_MODE_DUAL:
+		opts.post_socket_cb = v6only_false;
+		sock_family = AF_INET6;
+		srv_addr = SERVER_ADDR_DUAL;
+		addr = (struct sockaddr_storage *)&srv_sa6;
+		addr_len = sizeof(srv_sa6);
+		break;
+	default:
+		PRINT_FAIL("Unknown IP mode %d", ip_mode);
 		return;
+	}
 
-	listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
-	if (CHECK_FAIL(listen_fd == -1))
+	if (write_sysctl("/proc/sys/net/ipv4/tcp_syncookies", tcp_syncookies))
 		return;
 
-	err = getsockname(listen_fd, (struct sockaddr *)&srv_sa6, &addrlen);
-	if (CHECK(err, "getsockname(listen_fd)", "err:%d errno:%d\n", err,
-		  errno))
-		goto done;
-	memcpy(&skel->bss->srv_sa6, &srv_sa6, sizeof(srv_sa6));
-	srv_port = ntohs(srv_sa6.sin6_port);
+	listen_fd = start_server_str(sock_family, SOCK_STREAM, srv_addr,  0,
+				     &opts);
+	if (!ASSERT_OK_FD(listen_fd, "start server"))
+		return;
 
-	cli_fd = connect_to_fd(listen_fd, 0);
-	if (CHECK_FAIL(cli_fd == -1))
+	err = getsockname(listen_fd, (struct sockaddr *)addr, &addr_len);
+	if (!ASSERT_OK(err, "getsockname(listen_fd)"))
 		goto done;
 
-	srv_fd = accept(listen_fd, NULL, NULL);
-	if (CHECK_FAIL(srv_fd == -1))
+	switch (ip_mode) {
+	case TEST_MODE_IPV4:
+		memcpy(&skel->bss->srv_sa4, &srv_sa4, sizeof(srv_sa4));
+		srv_port = ntohs(srv_sa4.sin_port);
+		break;
+	case TEST_MODE_IPV6:
+	case TEST_MODE_DUAL:
+		memcpy(&skel->bss->srv_sa6, &srv_sa6, sizeof(srv_sa6));
+		srv_port = ntohs(srv_sa6.sin6_port);
+		break;
+	default:
 		goto done;
+	}
 
-	if (CHECK(skel->bss->listen_tp_sport != srv_port ||
-		  skel->bss->req_sk_sport != srv_port,
-		  "Unexpected sk src port",
-		  "listen_tp_sport:%u req_sk_sport:%u expected:%u\n",
-		  skel->bss->listen_tp_sport, skel->bss->req_sk_sport,
-		  srv_port))
+	cli_fd = connect_to_fd(listen_fd, 0);
+	if (!ASSERT_OK_FD(cli_fd, "connect client"))
 		goto done;
 
-	if (CHECK(skel->bss->gen_cookie || skel->bss->recv_cookie,
-		  "Unexpected syncookie states",
-		  "gen_cookie:%u recv_cookie:%u\n",
-		  skel->bss->gen_cookie, skel->bss->recv_cookie))
+	srv_fd = accept(listen_fd, NULL, NULL);
+	if (!ASSERT_OK_FD(srv_fd, "accept connection"))
 		goto done;
 
-	CHECK(skel->bss->linum, "bpf prog detected error", "at line %u\n",
-	      skel->bss->linum);
+	ASSERT_EQ(skel->bss->listen_tp_sport, srv_port, "listen tp src port");
+
+	if (!gen_cookies) {
+		ASSERT_EQ(skel->bss->req_sk_sport, srv_port,
+			  "request socket source port with syncookies disabled");
+		ASSERT_EQ(skel->bss->gen_cookie, 0,
+			  "generated syncookie with syncookies disabled");
+		ASSERT_EQ(skel->bss->recv_cookie, 0,
+			  "received syncookie with syncookies disabled");
+	} else {
+		ASSERT_EQ(skel->bss->req_sk_sport, 0,
+			  "request socket source port with syncookies enabled");
+		ASSERT_NEQ(skel->bss->gen_cookie, 0,
+			   "syncookie properly generated");
+		ASSERT_EQ(skel->bss->gen_cookie, skel->bss->recv_cookie,
+			  "matching syncookies on client and server");
+		ASSERT_GT(skel->bss->mss, MIN_IPV4_MSS,
+			  "MSS in cookie min value");
+		ASSERT_LT(skel->bss->mss, USHRT_MAX,
+			  "MSS in cookie max value");
+	}
 
 done:
 	if (listen_fd != -1)
@@ -125,96 +201,74 @@ done:
 		close(srv_fd);
 }
 
-static void test_syncookie(void)
+static void test_conn_ipv4(struct test_btf_skc_cls_ingress *skel)
 {
-	int listen_fd = -1, cli_fd = -1, srv_fd = -1, err;
-	socklen_t addrlen = sizeof(srv_sa6);
-	int srv_port;
-
-	/* Enforce syncookie mode */
-	if (write_sysctl("/proc/sys/net/ipv4/tcp_syncookies", "2"))
-		return;
-
-	listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
-	if (CHECK_FAIL(listen_fd == -1))
-		return;
-
-	err = getsockname(listen_fd, (struct sockaddr *)&srv_sa6, &addrlen);
-	if (CHECK(err, "getsockname(listen_fd)", "err:%d errno:%d\n", err,
-		  errno))
-		goto done;
-	memcpy(&skel->bss->srv_sa6, &srv_sa6, sizeof(srv_sa6));
-	srv_port = ntohs(srv_sa6.sin6_port);
-
-	cli_fd = connect_to_fd(listen_fd, 0);
-	if (CHECK_FAIL(cli_fd == -1))
-		goto done;
-
-	srv_fd = accept(listen_fd, NULL, NULL);
-	if (CHECK_FAIL(srv_fd == -1))
-		goto done;
+	run_test(skel, false, TEST_MODE_IPV4);
+}
 
-	if (CHECK(skel->bss->listen_tp_sport != srv_port,
-		  "Unexpected tp src port",
-		  "listen_tp_sport:%u expected:%u\n",
-		  skel->bss->listen_tp_sport, srv_port))
-		goto done;
+static void test_conn_ipv6(struct test_btf_skc_cls_ingress *skel)
+{
+	run_test(skel, false, TEST_MODE_IPV6);
+}
 
-	if (CHECK(skel->bss->req_sk_sport,
-		  "Unexpected req_sk src port",
-		  "req_sk_sport:%u expected:0\n",
-		   skel->bss->req_sk_sport))
-		goto done;
+static void test_conn_dual(struct test_btf_skc_cls_ingress *skel)
+{
+	run_test(skel, false, TEST_MODE_DUAL);
+}
 
-	if (CHECK(!skel->bss->gen_cookie ||
-		  skel->bss->gen_cookie != skel->bss->recv_cookie,
-		  "Unexpected syncookie states",
-		  "gen_cookie:%u recv_cookie:%u\n",
-		  skel->bss->gen_cookie, skel->bss->recv_cookie))
-		goto done;
+static void test_syncookie_ipv4(struct test_btf_skc_cls_ingress *skel)
+{
+	run_test(skel, true, TEST_MODE_IPV4);
+}
 
-	CHECK(skel->bss->linum, "bpf prog detected error", "at line %u\n",
-	      skel->bss->linum);
+static void test_syncookie_ipv6(struct test_btf_skc_cls_ingress *skel)
+{
+	run_test(skel, true, TEST_MODE_IPV6);
+}
 
-done:
-	if (listen_fd != -1)
-		close(listen_fd);
-	if (cli_fd != -1)
-		close(cli_fd);
-	if (srv_fd != -1)
-		close(srv_fd);
+static void test_syncookie_dual(struct test_btf_skc_cls_ingress *skel)
+{
+	run_test(skel, true, TEST_MODE_DUAL);
 }
 
 struct test {
 	const char *desc;
-	void (*run)(void);
+	void (*run)(struct test_btf_skc_cls_ingress *skel);
 };
 
 #define DEF_TEST(name) { #name, test_##name }
 static struct test tests[] = {
-	DEF_TEST(conn),
-	DEF_TEST(syncookie),
+	DEF_TEST(conn_ipv4),
+	DEF_TEST(conn_ipv6),
+	DEF_TEST(conn_dual),
+	DEF_TEST(syncookie_ipv4),
+	DEF_TEST(syncookie_ipv6),
+	DEF_TEST(syncookie_dual),
 };
 
 void test_btf_skc_cls_ingress(void)
 {
+	struct test_btf_skc_cls_ingress *skel;
+	struct netns_obj *ns;
 	int i;
 
 	skel = test_btf_skc_cls_ingress__open_and_load();
-	if (CHECK(!skel, "test_btf_skc_cls_ingress__open_and_load", "failed\n"))
+	if (!ASSERT_OK_PTR(skel, "test_btf_skc_cls_ingress__open_and_load"))
 		return;
 
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		if (!test__start_subtest(tests[i].desc))
 			continue;
 
-		if (prepare_netns())
+		ns = prepare_netns(skel);
+		if (!ns)
 			break;
 
-		tests[i].run();
+		tests[i].run(skel);
 
-		print_err_line();
-		reset_test();
+		print_err_line(skel);
+		reset_test(skel);
+		netns_free(ns);
 	}
 
 	test_btf_skc_cls_ingress__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_split.c b/tools/testing/selftests/bpf/prog_tests/btf_split.c
index eef1158676ed..2d47cad50a51 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_split.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_split.c
@@ -12,10 +12,45 @@ static void btf_dump_printf(void *ctx, const char *fmt, va_list args)
 	vfprintf(ctx, fmt, args);
 }
 
-void test_btf_split() {
+/* Write raw BTF to file, return number of bytes written or negative errno */
+static ssize_t btf_raw_write(struct btf *btf, char *file)
+{
+	ssize_t written = 0;
+	const void *data;
+	__u32 size = 0;
+	int fd, ret;
+
+	fd = mkstemp(file);
+	if (!ASSERT_GE(fd, 0, "create_file"))
+		return -errno;
+
+	data = btf__raw_data(btf, &size);
+	if (!ASSERT_OK_PTR(data, "btf__raw_data")) {
+		close(fd);
+		return -EINVAL;
+	}
+	while (written < size) {
+		ret = write(fd, data + written, size - written);
+		if (!ASSERT_GE(ret, 0, "write succeeded")) {
+			close(fd);
+			return -errno;
+		}
+		written += ret;
+	}
+	close(fd);
+	return written;
+}
+
+static void __test_btf_split(bool multi)
+{
+	char multisplit_btf_file[] = "/tmp/test_btf_multisplit.XXXXXX";
+	char split_btf_file[] = "/tmp/test_btf_split.XXXXXX";
+	char base_btf_file[] = "/tmp/test_btf_base.XXXXXX";
+	ssize_t multisplit_btf_sz = 0, split_btf_sz = 0, base_btf_sz = 0;
 	struct btf_dump *d = NULL;
-	const struct btf_type *t;
-	struct btf *btf1, *btf2;
+	const struct btf_type *t, *ot;
+	struct btf *btf1 = NULL, *btf2 = NULL, *btf3 = NULL;
+	struct btf *btf4 = NULL, *btf5 = NULL, *btf6 = NULL;
 	int str_off, i, err;
 
 	btf1 = btf__new_empty();
@@ -63,14 +98,46 @@ void test_btf_split() {
 	ASSERT_EQ(btf_vlen(t), 3, "split_struct_vlen");
 	ASSERT_STREQ(btf__str_by_offset(btf2, t->name_off), "s2", "split_struct_name");
 
+	if (multi) {
+		btf3 = btf__new_empty_split(btf2);
+		if (!ASSERT_OK_PTR(btf3, "multi_split_btf"))
+			goto cleanup;
+	} else {
+		btf3 = btf2;
+	}
+
+	btf__add_union(btf3, "u1", 16);			/* [5] union u1 {	*/
+	btf__add_field(btf3, "f1", 4, 0, 0);		/*	struct s2 f1;	*/
+	btf__add_field(btf3, "uf2", 1, 0, 0);		/*	int f2;		*/
+							/* } */
+
+	if (multi) {
+		t = btf__type_by_id(btf2, 5);
+		ASSERT_NULL(t, "multisplit_type_in_first_split");
+	}
+
+	t = btf__type_by_id(btf3, 5);
+	if (!ASSERT_OK_PTR(t, "split_union_type"))
+		goto cleanup;
+	ASSERT_EQ(btf_is_union(t), true, "split_union_kind");
+	ASSERT_EQ(btf_vlen(t), 2, "split_union_vlen");
+	ASSERT_STREQ(btf__str_by_offset(btf3, t->name_off), "u1", "split_union_name");
+	ASSERT_EQ(btf__type_cnt(btf3), 6, "split_type_cnt");
+
+	t = btf__type_by_id(btf3, 1);
+	if (!ASSERT_OK_PTR(t, "split_base_type"))
+		goto cleanup;
+	ASSERT_EQ(btf_is_int(t), true, "split_base_int");
+	ASSERT_STREQ(btf__str_by_offset(btf3, t->name_off), "int", "split_base_type_name");
+
 	/* BTF-to-C dump of split BTF */
 	dump_buf_file = open_memstream(&dump_buf, &dump_buf_sz);
 	if (!ASSERT_OK_PTR(dump_buf_file, "dump_memstream"))
 		return;
-	d = btf_dump__new(btf2, btf_dump_printf, dump_buf_file, NULL);
+	d = btf_dump__new(btf3, btf_dump_printf, dump_buf_file, NULL);
 	if (!ASSERT_OK_PTR(d, "btf_dump__new"))
 		goto cleanup;
-	for (i = 1; i < btf__type_cnt(btf2); i++) {
+	for (i = 1; i < btf__type_cnt(btf3); i++) {
 		err = btf_dump__dump_type(d, i);
 		ASSERT_OK(err, "dump_type_ok");
 	}
@@ -79,14 +146,56 @@ void test_btf_split() {
 	ASSERT_STREQ(dump_buf,
 "struct s1 {\n"
 "	int f1;\n"
-"};\n"
-"\n"
+"};\n\n"
 "struct s2 {\n"
 "	struct s1 f1;\n"
 "	int f2;\n"
 "	int *f3;\n"
+"};\n\n"
+"union u1 {\n"
+"	struct s2 f1;\n"
+"	int uf2;\n"
 "};\n\n", "c_dump");
 
+	/* write base, split BTFs to files and ensure parsing succeeds */
+	base_btf_sz = btf_raw_write(btf1, base_btf_file);
+	if (base_btf_sz < 0)
+		goto cleanup;
+	split_btf_sz = btf_raw_write(btf2, split_btf_file);
+	if (split_btf_sz < 0)
+		goto cleanup;
+	btf4 = btf__parse(base_btf_file, NULL);
+	if (!ASSERT_OK_PTR(btf4, "parse_base"))
+		goto cleanup;
+	btf5 = btf__parse_split(split_btf_file, btf4);
+	if (!ASSERT_OK_PTR(btf5, "parse_split"))
+		goto cleanup;
+	if (multi) {
+		multisplit_btf_sz = btf_raw_write(btf3, multisplit_btf_file);
+		if (multisplit_btf_sz < 0)
+			goto cleanup;
+		btf6 = btf__parse_split(multisplit_btf_file, btf5);
+		if (!ASSERT_OK_PTR(btf6, "parse_multisplit"))
+			goto cleanup;
+	} else {
+		btf6 = btf5;
+	}
+
+	if (!ASSERT_EQ(btf__type_cnt(btf3), btf__type_cnt(btf6), "cmp_type_cnt"))
+		goto cleanup;
+
+	/* compare parsed to original BTF */
+	for (i = 1; i < btf__type_cnt(btf6); i++) {
+		t = btf__type_by_id(btf6, i);
+		if (!ASSERT_OK_PTR(t, "type_in_parsed_btf"))
+			goto cleanup;
+		ot = btf__type_by_id(btf3, i);
+		if (!ASSERT_OK_PTR(ot, "type_in_orig_btf"))
+			goto cleanup;
+		if (!ASSERT_EQ(memcmp(t, ot, sizeof(*ot)), 0, "cmp_parsed_orig_btf"))
+			goto cleanup;
+	}
+
 cleanup:
 	if (dump_buf_file)
 		fclose(dump_buf_file);
@@ -94,4 +203,24 @@ cleanup:
 	btf_dump__free(d);
 	btf__free(btf1);
 	btf__free(btf2);
+	if (btf2 != btf3)
+		btf__free(btf3);
+	btf__free(btf4);
+	btf__free(btf5);
+	if (btf5 != btf6)
+		btf__free(btf6);
+	if (base_btf_sz > 0)
+		unlink(base_btf_file);
+	if (split_btf_sz > 0)
+		unlink(split_btf_file);
+	if (multisplit_btf_sz > 0)
+		unlink(multisplit_btf_file);
+}
+
+void test_btf_split(void)
+{
+	if (test__start_subtest("single_split"))
+		__test_btf_split(false);
+	if (test__start_subtest("multi_split"))
+		__test_btf_split(true);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_sysfs.c b/tools/testing/selftests/bpf/prog_tests/btf_sysfs.c
new file mode 100644
index 000000000000..3923e64c4c1d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/btf_sysfs.c
@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/* Copyright (c) 2025 Isovalent */
+
+#include <test_progs.h>
+#include <bpf/btf.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+#include <unistd.h>
+
+static void test_btf_mmap_sysfs(const char *path, struct btf *base)
+{
+	struct stat st;
+	__u64 btf_size, end;
+	void *raw_data = NULL;
+	int fd = -1;
+	long page_size;
+	struct btf *btf = NULL;
+
+	page_size = sysconf(_SC_PAGESIZE);
+	if (!ASSERT_GE(page_size, 0, "get_page_size"))
+		goto cleanup;
+
+	if (!ASSERT_OK(stat(path, &st), "stat_btf"))
+		goto cleanup;
+
+	btf_size = st.st_size;
+	end = (btf_size + page_size - 1) / page_size * page_size;
+
+	fd = open(path, O_RDONLY);
+	if (!ASSERT_GE(fd, 0, "open_btf"))
+		goto cleanup;
+
+	raw_data = mmap(NULL, btf_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
+	if (!ASSERT_EQ(raw_data, MAP_FAILED, "mmap_btf_writable"))
+		goto cleanup;
+
+	raw_data = mmap(NULL, btf_size, PROT_READ, MAP_SHARED, fd, 0);
+	if (!ASSERT_EQ(raw_data, MAP_FAILED, "mmap_btf_shared"))
+		goto cleanup;
+
+	raw_data = mmap(NULL, end + 1, PROT_READ, MAP_PRIVATE, fd, 0);
+	if (!ASSERT_EQ(raw_data, MAP_FAILED, "mmap_btf_invalid_size"))
+		goto cleanup;
+
+	raw_data = mmap(NULL, end, PROT_READ, MAP_PRIVATE, fd, 0);
+	if (!ASSERT_OK_PTR(raw_data, "mmap_btf"))
+		goto cleanup;
+
+	if (!ASSERT_EQ(mprotect(raw_data, btf_size, PROT_READ | PROT_WRITE), -1,
+	    "mprotect_writable"))
+		goto cleanup;
+
+	if (!ASSERT_EQ(mprotect(raw_data, btf_size, PROT_READ | PROT_EXEC), -1,
+	    "mprotect_executable"))
+		goto cleanup;
+
+	/* Check padding is zeroed */
+	for (int i = btf_size; i < end; i++) {
+		if (((__u8 *)raw_data)[i] != 0) {
+			PRINT_FAIL("tail of BTF is not zero at page offset %d\n", i);
+			goto cleanup;
+		}
+	}
+
+	btf = btf__new_split(raw_data, btf_size, base);
+	if (!ASSERT_OK_PTR(btf, "parse_btf"))
+		goto cleanup;
+
+cleanup:
+	btf__free(btf);
+	if (raw_data && raw_data != MAP_FAILED)
+		munmap(raw_data, btf_size);
+	if (fd >= 0)
+		close(fd);
+}
+
+void test_btf_sysfs(void)
+{
+	test_btf_mmap_sysfs("/sys/kernel/btf/vmlinux", NULL);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/build_id.c b/tools/testing/selftests/bpf/prog_tests/build_id.c
new file mode 100644
index 000000000000..aec9c8d6bc96
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/build_id.c
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+
+#include "test_build_id.skel.h"
+
+static char build_id[BPF_BUILD_ID_SIZE];
+static int build_id_sz;
+
+static void print_stack(struct bpf_stack_build_id *stack, int frame_cnt)
+{
+	int i, j;
+
+	for (i = 0; i < frame_cnt; i++) {
+		printf("FRAME #%02d: ", i);
+		switch (stack[i].status) {
+		case BPF_STACK_BUILD_ID_EMPTY:
+			printf("<EMPTY>\n");
+			break;
+		case BPF_STACK_BUILD_ID_VALID:
+			printf("BUILD ID = ");
+			for (j = 0; j < BPF_BUILD_ID_SIZE; j++)
+				printf("%02hhx", (unsigned)stack[i].build_id[j]);
+			printf(" OFFSET = %llx", (unsigned long long)stack[i].offset);
+			break;
+		case BPF_STACK_BUILD_ID_IP:
+			printf("IP = %llx", (unsigned long long)stack[i].ip);
+			break;
+		default:
+			printf("UNEXPECTED STATUS %d ", stack[i].status);
+			break;
+		}
+		printf("\n");
+	}
+}
+
+static void subtest_nofault(bool build_id_resident)
+{
+	struct test_build_id *skel;
+	struct bpf_stack_build_id *stack;
+	int frame_cnt;
+
+	skel = test_build_id__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	skel->links.uprobe_nofault = bpf_program__attach(skel->progs.uprobe_nofault);
+	if (!ASSERT_OK_PTR(skel->links.uprobe_nofault, "link"))
+		goto cleanup;
+
+	if (build_id_resident)
+		ASSERT_OK(system("./uprobe_multi uprobe-paged-in"), "trigger_uprobe");
+	else
+		ASSERT_OK(system("./uprobe_multi uprobe-paged-out"), "trigger_uprobe");
+
+	if (!ASSERT_GT(skel->bss->res_nofault, 0, "res"))
+		goto cleanup;
+
+	stack = skel->bss->stack_nofault;
+	frame_cnt = skel->bss->res_nofault / sizeof(struct bpf_stack_build_id);
+	if (env.verbosity >= VERBOSE_NORMAL)
+		print_stack(stack, frame_cnt);
+
+	if (build_id_resident) {
+		ASSERT_EQ(stack[0].status, BPF_STACK_BUILD_ID_VALID, "build_id_status");
+		ASSERT_EQ(memcmp(stack[0].build_id, build_id, build_id_sz), 0, "build_id_match");
+	} else {
+		ASSERT_EQ(stack[0].status, BPF_STACK_BUILD_ID_IP, "build_id_status");
+	}
+
+cleanup:
+	test_build_id__destroy(skel);
+}
+
+static void subtest_sleepable(void)
+{
+	struct test_build_id *skel;
+	struct bpf_stack_build_id *stack;
+	int frame_cnt;
+
+	skel = test_build_id__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	skel->links.uprobe_sleepable = bpf_program__attach(skel->progs.uprobe_sleepable);
+	if (!ASSERT_OK_PTR(skel->links.uprobe_sleepable, "link"))
+		goto cleanup;
+
+	/* force build ID to not be paged in */
+	ASSERT_OK(system("./uprobe_multi uprobe-paged-out"), "trigger_uprobe");
+
+	if (!ASSERT_GT(skel->bss->res_sleepable, 0, "res"))
+		goto cleanup;
+
+	stack = skel->bss->stack_sleepable;
+	frame_cnt = skel->bss->res_sleepable / sizeof(struct bpf_stack_build_id);
+	if (env.verbosity >= VERBOSE_NORMAL)
+		print_stack(stack, frame_cnt);
+
+	ASSERT_EQ(stack[0].status, BPF_STACK_BUILD_ID_VALID, "build_id_status");
+	ASSERT_EQ(memcmp(stack[0].build_id, build_id, build_id_sz), 0, "build_id_match");
+
+cleanup:
+	test_build_id__destroy(skel);
+}
+
+void serial_test_build_id(void)
+{
+	build_id_sz = read_build_id("uprobe_multi", build_id, sizeof(build_id));
+	ASSERT_EQ(build_id_sz, BPF_BUILD_ID_SIZE, "parse_build_id");
+
+	if (test__start_subtest("nofault-paged-out"))
+		subtest_nofault(false /* not resident */);
+	if (test__start_subtest("nofault-paged-in"))
+		subtest_nofault(true /* resident */);
+	if (test__start_subtest("sleepable"))
+		subtest_sleepable();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cb_refs.c b/tools/testing/selftests/bpf/prog_tests/cb_refs.c
index 3bff680de16c..c40df623a8f7 100644
--- a/tools/testing/selftests/bpf/prog_tests/cb_refs.c
+++ b/tools/testing/selftests/bpf/prog_tests/cb_refs.c
@@ -11,8 +11,8 @@ struct {
 	const char *prog_name;
 	const char *err_msg;
 } cb_refs_tests[] = {
-	{ "underflow_prog", "reference has not been acquired before" },
-	{ "leak_prog", "Unreleased reference" },
+	{ "underflow_prog", "must point to scalar, or struct with scalar" },
+	{ "leak_prog", "Possibly NULL pointer passed to helper arg2" },
 	{ "nested_cb", "Unreleased reference id=4 alloc_insn=2" }, /* alloc_insn=2{4,5} */
 	{ "non_cb_transfer_ref", "Unreleased reference id=4 alloc_insn=1" }, /* alloc_insn=1{1,2} */
 };
diff --git a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c
index 621c57222191..10224f845568 100644
--- a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c
@@ -56,8 +56,9 @@ static bool assert_storage_noexist(struct bpf_map *map, const void *key)
 
 static bool connect_send(const char *cgroup_path)
 {
-	bool res = true;
 	int server_fd = -1, client_fd = -1;
+	char message[] = "message";
+	bool res = true;
 
 	if (join_cgroup(cgroup_path))
 		goto out_clean;
@@ -70,7 +71,10 @@ static bool connect_send(const char *cgroup_path)
 	if (client_fd < 0)
 		goto out_clean;
 
-	if (send(client_fd, "message", strlen("message"), 0) < 0)
+	if (send(client_fd, &message, sizeof(message), 0) < 0)
+		goto out_clean;
+
+	if (read(server_fd, &message, sizeof(message)) < 0)
 		goto out_clean;
 
 	res = false;
@@ -210,7 +214,7 @@ static void test_isolated(int parent_cgroup_fd, int child_cgroup_fd)
 	/* Attach to parent and child cgroup, trigger packet from child.
 	 * Assert that there is six additional runs, parent cgroup egresses and
 	 * ingress, child cgroup egresses and ingress.
-	 * Assert that egree and ingress storages are separate.
+	 * Assert that egress and ingress storages are separate.
 	 */
 	child_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1,
 							child_cgroup_fd);
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c b/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c
new file mode 100644
index 000000000000..25332e596750
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup1_hierarchy.c
@@ -0,0 +1,163 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */
+
+#include <sys/types.h>
+#include <unistd.h>
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+#include "test_cgroup1_hierarchy.skel.h"
+
+static void bpf_cgroup1(struct test_cgroup1_hierarchy *skel)
+{
+	struct bpf_link *lsm_link, *fentry_link;
+	int err;
+
+	/* Attach LSM prog first */
+	lsm_link = bpf_program__attach_lsm(skel->progs.lsm_run);
+	if (!ASSERT_OK_PTR(lsm_link, "lsm_attach"))
+		return;
+
+	/* LSM prog will be triggered when attaching fentry */
+	fentry_link = bpf_program__attach_trace(skel->progs.fentry_run);
+	ASSERT_NULL(fentry_link, "fentry_attach_fail");
+
+	err = bpf_link__destroy(lsm_link);
+	ASSERT_OK(err, "destroy_lsm");
+}
+
+static void bpf_cgroup1_sleepable(struct test_cgroup1_hierarchy *skel)
+{
+	struct bpf_link *lsm_link, *fentry_link;
+	int err;
+
+	/* Attach LSM prog first */
+	lsm_link = bpf_program__attach_lsm(skel->progs.lsm_s_run);
+	if (!ASSERT_OK_PTR(lsm_link, "lsm_attach"))
+		return;
+
+	/* LSM prog will be triggered when attaching fentry */
+	fentry_link = bpf_program__attach_trace(skel->progs.fentry_run);
+	ASSERT_NULL(fentry_link, "fentry_attach_fail");
+
+	err = bpf_link__destroy(lsm_link);
+	ASSERT_OK(err, "destroy_lsm");
+}
+
+static void bpf_cgroup1_invalid_id(struct test_cgroup1_hierarchy *skel)
+{
+	struct bpf_link *lsm_link, *fentry_link;
+	int err;
+
+	/* Attach LSM prog first */
+	lsm_link = bpf_program__attach_lsm(skel->progs.lsm_run);
+	if (!ASSERT_OK_PTR(lsm_link, "lsm_attach"))
+		return;
+
+	/* LSM prog will be triggered when attaching fentry */
+	fentry_link = bpf_program__attach_trace(skel->progs.fentry_run);
+	if (!ASSERT_OK_PTR(fentry_link, "fentry_attach_success"))
+		goto cleanup;
+
+	err = bpf_link__destroy(fentry_link);
+	ASSERT_OK(err, "destroy_lsm");
+
+cleanup:
+	err = bpf_link__destroy(lsm_link);
+	ASSERT_OK(err, "destroy_fentry");
+}
+
+void test_cgroup1_hierarchy(void)
+{
+	struct test_cgroup1_hierarchy *skel;
+	__u64 current_cgid;
+	int hid, err;
+
+	skel = test_cgroup1_hierarchy__open();
+	if (!ASSERT_OK_PTR(skel, "open"))
+		return;
+
+	skel->bss->target_pid = getpid();
+
+	err = bpf_program__set_attach_target(skel->progs.fentry_run, 0, "bpf_fentry_test1");
+	if (!ASSERT_OK(err, "fentry_set_target"))
+		goto destroy;
+
+	err = test_cgroup1_hierarchy__load(skel);
+	if (!ASSERT_OK(err, "load"))
+		goto destroy;
+
+	/* Setup cgroup1 hierarchy */
+	err = setup_cgroup_environment();
+	if (!ASSERT_OK(err, "setup_cgroup_environment"))
+		goto destroy;
+	err = setup_classid_environment();
+	if (!ASSERT_OK(err, "setup_classid_environment"))
+		goto cleanup_cgroup;
+
+	err = join_classid();
+	if (!ASSERT_OK(err, "join_cgroup1"))
+		goto cleanup;
+
+	current_cgid = get_classid_cgroup_id();
+	if (!ASSERT_GE(current_cgid, 0, "cgroup1 id"))
+		goto cleanup;
+
+	hid = get_cgroup1_hierarchy_id("net_cls");
+	if (!ASSERT_GE(hid, 0, "cgroup1 id"))
+		goto cleanup;
+	skel->bss->target_hid = hid;
+
+	if (test__start_subtest("test_cgroup1_hierarchy")) {
+		skel->bss->target_ancestor_cgid = current_cgid;
+		bpf_cgroup1(skel);
+	}
+
+	if (test__start_subtest("test_root_cgid")) {
+		skel->bss->target_ancestor_cgid = 1;
+		skel->bss->target_ancestor_level = 0;
+		bpf_cgroup1(skel);
+	}
+
+	if (test__start_subtest("test_invalid_level")) {
+		skel->bss->target_ancestor_cgid = 1;
+		skel->bss->target_ancestor_level = 1;
+		bpf_cgroup1_invalid_id(skel);
+	}
+
+	if (test__start_subtest("test_invalid_cgid")) {
+		skel->bss->target_ancestor_cgid = 0;
+		bpf_cgroup1_invalid_id(skel);
+	}
+
+	if (test__start_subtest("test_invalid_hid")) {
+		skel->bss->target_ancestor_cgid = 1;
+		skel->bss->target_ancestor_level = 0;
+		skel->bss->target_hid = -1;
+		bpf_cgroup1_invalid_id(skel);
+	}
+
+	if (test__start_subtest("test_invalid_cgrp_name")) {
+		skel->bss->target_hid = get_cgroup1_hierarchy_id("net_cl");
+		skel->bss->target_ancestor_cgid = current_cgid;
+		bpf_cgroup1_invalid_id(skel);
+	}
+
+	if (test__start_subtest("test_invalid_cgrp_name2")) {
+		skel->bss->target_hid = get_cgroup1_hierarchy_id("net_cls,");
+		skel->bss->target_ancestor_cgid = current_cgid;
+		bpf_cgroup1_invalid_id(skel);
+	}
+
+	if (test__start_subtest("test_sleepable_prog")) {
+		skel->bss->target_hid = hid;
+		skel->bss->target_ancestor_cgid = current_cgid;
+		bpf_cgroup1_sleepable(skel);
+	}
+
+cleanup:
+	cleanup_classid_environment();
+cleanup_cgroup:
+	cleanup_cgroup_environment();
+destroy:
+	test_cgroup1_hierarchy__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_ancestor.c b/tools/testing/selftests/bpf/prog_tests/cgroup_ancestor.c
new file mode 100644
index 000000000000..3f9ffdf71343
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_ancestor.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "cgroup_helpers.h"
+#include "cgroup_ancestor.skel.h"
+
+#define CGROUP_PATH "/skb_cgroup_test"
+#define TEST_NS "cgroup_ancestor_ns"
+#define NUM_CGROUP_LEVELS 4
+#define WAIT_AUTO_IP_MAX_ATTEMPT 10
+#define DST_ADDR "::1"
+#define DST_PORT 1234
+#define MAX_ASSERT_NAME 32
+
+struct test_data {
+	struct cgroup_ancestor *skel;
+	struct bpf_tc_hook qdisc;
+	struct bpf_tc_opts tc_attach;
+	struct nstoken *ns;
+};
+
+static int send_datagram(void)
+{
+	unsigned char buf[] = "some random test data";
+	struct sockaddr_in6 addr = { .sin6_family = AF_INET6,
+				     .sin6_port = htons(DST_PORT), };
+	int sock, n;
+
+	if (!ASSERT_EQ(inet_pton(AF_INET6, DST_ADDR, &addr.sin6_addr), 1,
+		       "inet_pton"))
+		return -1;
+
+	sock = socket(AF_INET6, SOCK_DGRAM, 0);
+	if (!ASSERT_OK_FD(sock, "create socket"))
+		return sock;
+
+	if (!ASSERT_OK(connect(sock, (struct sockaddr *)&addr, sizeof(addr)), "connect")) {
+		close(sock);
+		return -1;
+	}
+
+	n = sendto(sock, buf, sizeof(buf), 0, (const struct sockaddr *)&addr,
+		   sizeof(addr));
+	close(sock);
+	return ASSERT_EQ(n, sizeof(buf), "send data") ? 0 : -1;
+}
+
+static int setup_network(struct test_data *t)
+{
+	SYS(fail, "ip netns add %s", TEST_NS);
+	t->ns = open_netns(TEST_NS);
+	if (!ASSERT_OK_PTR(t->ns, "open netns"))
+		goto cleanup_ns;
+
+	SYS(close_ns, "ip link set lo up");
+
+	memset(&t->qdisc, 0, sizeof(t->qdisc));
+	t->qdisc.sz = sizeof(t->qdisc);
+	t->qdisc.attach_point = BPF_TC_EGRESS;
+	t->qdisc.ifindex = if_nametoindex("lo");
+	if (!ASSERT_NEQ(t->qdisc.ifindex, 0, "if_nametoindex"))
+		goto close_ns;
+	if (!ASSERT_OK(bpf_tc_hook_create(&t->qdisc), "qdisc add"))
+		goto close_ns;
+
+	memset(&t->tc_attach, 0, sizeof(t->tc_attach));
+	t->tc_attach.sz = sizeof(t->tc_attach);
+	t->tc_attach.prog_fd = bpf_program__fd(t->skel->progs.log_cgroup_id);
+	if (!ASSERT_OK(bpf_tc_attach(&t->qdisc, &t->tc_attach), "filter add"))
+		goto cleanup_qdisc;
+
+	return 0;
+
+cleanup_qdisc:
+	bpf_tc_hook_destroy(&t->qdisc);
+close_ns:
+	close_netns(t->ns);
+cleanup_ns:
+	SYS_NOFAIL("ip netns del %s", TEST_NS);
+fail:
+	return 1;
+}
+
+static void cleanup_network(struct test_data *t)
+{
+	bpf_tc_detach(&t->qdisc, &t->tc_attach);
+	bpf_tc_hook_destroy(&t->qdisc);
+	close_netns(t->ns);
+	SYS_NOFAIL("ip netns del %s", TEST_NS);
+}
+
+static void check_ancestors_ids(struct test_data *t)
+{
+	__u64 expected_ids[NUM_CGROUP_LEVELS];
+	char assert_name[MAX_ASSERT_NAME];
+	__u32 level;
+
+	expected_ids[0] = get_cgroup_id("/.."); /* root cgroup */
+	expected_ids[1] = get_cgroup_id("");
+	expected_ids[2] = get_cgroup_id(CGROUP_PATH);
+	expected_ids[3] = 0; /* non-existent cgroup */
+
+	for (level = 0; level < NUM_CGROUP_LEVELS; level++) {
+		snprintf(assert_name, MAX_ASSERT_NAME,
+			 "ancestor id at level %d", level);
+		ASSERT_EQ(t->skel->bss->cgroup_ids[level], expected_ids[level],
+			  assert_name);
+	}
+}
+
+void test_cgroup_ancestor(void)
+{
+	struct test_data t;
+	int cgroup_fd;
+
+	t.skel = cgroup_ancestor__open_and_load();
+	if (!ASSERT_OK_PTR(t.skel, "open and load"))
+		return;
+
+	t.skel->bss->dport = htons(DST_PORT);
+	cgroup_fd = cgroup_setup_and_join(CGROUP_PATH);
+	if (cgroup_fd < 0)
+		goto cleanup_progs;
+
+	if (setup_network(&t))
+		goto cleanup_cgroups;
+
+	if (send_datagram())
+		goto cleanup_network;
+
+	check_ancestors_ids(&t);
+
+cleanup_network:
+	cleanup_network(&t);
+cleanup_cgroups:
+	close(cgroup_fd);
+	cleanup_cgroup_environment();
+cleanup_progs:
+	cgroup_ancestor__destroy(t.skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_dev.c b/tools/testing/selftests/bpf/prog_tests/cgroup_dev.c
new file mode 100644
index 000000000000..5ab7547e38c0
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_dev.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <sys/stat.h>
+#include <sys/sysmacros.h>
+#include <errno.h>
+#include "test_progs.h"
+#include "cgroup_helpers.h"
+#include "dev_cgroup.skel.h"
+
+#define TEST_CGROUP "/test-bpf-based-device-cgroup/"
+#define TEST_BUFFER_SIZE 64
+
+static void test_mknod(const char *path, mode_t mode, int dev_major,
+		       int dev_minor, int expected_ret, int expected_errno)
+{
+	int ret;
+
+	unlink(path);
+	ret = mknod(path, mode, makedev(dev_major, dev_minor));
+	ASSERT_EQ(ret, expected_ret, "mknod");
+	if (expected_ret)
+		ASSERT_EQ(errno, expected_errno, "mknod errno");
+	else
+		unlink(path);
+}
+
+static void test_read(const char *path, char *buf, int buf_size,
+		      int expected_ret, int expected_errno)
+{
+	int ret, fd;
+
+	fd = open(path, O_RDONLY);
+
+	/* A bare open on unauthorized device should fail */
+	if (expected_ret < 0) {
+		ASSERT_EQ(fd, expected_ret, "open ret for read");
+		ASSERT_EQ(errno, expected_errno, "open errno for read");
+		if (fd >= 0)
+			close(fd);
+		return;
+	}
+
+	if (!ASSERT_OK_FD(fd, "open ret for read"))
+		return;
+
+	ret = read(fd, buf, buf_size);
+	ASSERT_EQ(ret, expected_ret, "read");
+
+	close(fd);
+}
+
+static void test_write(const char *path, char *buf, int buf_size,
+		       int expected_ret, int expected_errno)
+{
+	int ret, fd;
+
+	fd = open(path, O_WRONLY);
+
+	/* A bare open on unauthorized device should fail */
+	if (expected_ret < 0) {
+		ASSERT_EQ(fd, expected_ret, "open ret for write");
+		ASSERT_EQ(errno, expected_errno, "open errno for write");
+		if (fd >= 0)
+			close(fd);
+		return;
+	}
+
+	if (!ASSERT_OK_FD(fd, "open ret for write"))
+		return;
+
+	ret = write(fd, buf, buf_size);
+	ASSERT_EQ(ret, expected_ret, "write");
+
+	close(fd);
+}
+
+void test_cgroup_dev(void)
+{
+	char buf[TEST_BUFFER_SIZE] = "some random test data";
+	struct dev_cgroup *skel;
+	int cgroup_fd;
+
+	cgroup_fd = cgroup_setup_and_join(TEST_CGROUP);
+	if (!ASSERT_OK_FD(cgroup_fd, "cgroup switch"))
+		return;
+
+	skel = dev_cgroup__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "load program"))
+		goto cleanup_cgroup;
+
+	skel->links.bpf_prog1 =
+		bpf_program__attach_cgroup(skel->progs.bpf_prog1, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.bpf_prog1, "attach_program"))
+		goto cleanup_progs;
+
+	if (test__start_subtest("allow-mknod"))
+		test_mknod("/dev/test_dev_cgroup_null", S_IFCHR, 1, 3, 0, 0);
+
+	if (test__start_subtest("allow-read"))
+		test_read("/dev/urandom", buf, TEST_BUFFER_SIZE,
+			  TEST_BUFFER_SIZE, 0);
+
+	if (test__start_subtest("allow-write"))
+		test_write("/dev/null", buf, TEST_BUFFER_SIZE,
+			   TEST_BUFFER_SIZE, 0);
+
+	if (test__start_subtest("deny-mknod"))
+		test_mknod("/dev/test_dev_cgroup_zero", S_IFCHR, 1, 5, -1,
+			   EPERM);
+
+	if (test__start_subtest("deny-read"))
+		test_read("/dev/random", buf, TEST_BUFFER_SIZE, -1, EPERM);
+
+	if (test__start_subtest("deny-write"))
+		test_write("/dev/zero", buf, TEST_BUFFER_SIZE, -1, EPERM);
+
+	if (test__start_subtest("deny-mknod-wrong-type"))
+		test_mknod("/dev/test_dev_cgroup_block", S_IFBLK, 1, 3, -1,
+			   EPERM);
+
+cleanup_progs:
+	dev_cgroup__destroy(skel);
+cleanup_cgroup:
+	cleanup_cgroup_environment();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_get_current_cgroup_id.c b/tools/testing/selftests/bpf/prog_tests/cgroup_get_current_cgroup_id.c
new file mode 100644
index 000000000000..7a1643b03bf3
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_get_current_cgroup_id.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <sys/stat.h>
+#include <sys/sysmacros.h>
+#include "test_progs.h"
+#include "cgroup_helpers.h"
+#include "get_cgroup_id_kern.skel.h"
+
+#define TEST_CGROUP "/test-bpf-get-cgroup-id/"
+
+void test_cgroup_get_current_cgroup_id(void)
+{
+	struct get_cgroup_id_kern *skel;
+	const struct timespec req = {
+		.tv_sec = 0,
+		.tv_nsec = 1,
+	};
+	int cgroup_fd;
+	__u64 ucgid;
+
+	cgroup_fd = cgroup_setup_and_join(TEST_CGROUP);
+	if (!ASSERT_OK_FD(cgroup_fd, "cgroup switch"))
+		return;
+
+	skel = get_cgroup_id_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "load program"))
+		goto cleanup_cgroup;
+
+	if (!ASSERT_OK(get_cgroup_id_kern__attach(skel), "attach bpf program"))
+		goto cleanup_progs;
+
+	skel->bss->expected_pid = getpid();
+	/* trigger the syscall on which is attached the tested prog */
+	if (!ASSERT_OK(syscall(__NR_nanosleep, &req, NULL), "nanosleep"))
+		goto cleanup_progs;
+
+	ucgid = get_cgroup_id(TEST_CGROUP);
+
+	ASSERT_EQ(skel->bss->cg_id, ucgid, "compare cgroup ids");
+
+cleanup_progs:
+	get_cgroup_id_kern__destroy(skel);
+cleanup_cgroup:
+	close(cgroup_fd);
+	cleanup_cgroup_environment();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c b/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c
index 4d2fa99273d8..2bb5773d6f99 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_getset_retval.c
@@ -25,6 +25,8 @@ static void test_setsockopt_set(int cgroup_fd, int sock_fd)
 	if (!ASSERT_OK_PTR(obj, "skel-load"))
 		return;
 
+	obj->bss->page_size = sysconf(_SC_PAGESIZE);
+
 	/* Attach setsockopt that sets EUNATCH, assert that
 	 * we actually get that error when we run setsockopt()
 	 */
@@ -59,6 +61,8 @@ static void test_setsockopt_set_and_get(int cgroup_fd, int sock_fd)
 	if (!ASSERT_OK_PTR(obj, "skel-load"))
 		return;
 
+	obj->bss->page_size = sysconf(_SC_PAGESIZE);
+
 	/* Attach setsockopt that sets EUNATCH, and one that gets the
 	 * previously set errno. Assert that we get the same errno back.
 	 */
@@ -100,6 +104,8 @@ static void test_setsockopt_default_zero(int cgroup_fd, int sock_fd)
 	if (!ASSERT_OK_PTR(obj, "skel-load"))
 		return;
 
+	obj->bss->page_size = sysconf(_SC_PAGESIZE);
+
 	/* Attach setsockopt that gets the previously set errno.
 	 * Assert that, without anything setting one, we get 0.
 	 */
@@ -134,6 +140,8 @@ static void test_setsockopt_default_zero_and_set(int cgroup_fd, int sock_fd)
 	if (!ASSERT_OK_PTR(obj, "skel-load"))
 		return;
 
+	obj->bss->page_size = sysconf(_SC_PAGESIZE);
+
 	/* Attach setsockopt that gets the previously set errno, and then
 	 * one that sets the errno to EUNATCH. Assert that the get does not
 	 * see EUNATCH set later, and does not prevent EUNATCH from being set.
@@ -177,6 +185,8 @@ static void test_setsockopt_override(int cgroup_fd, int sock_fd)
 	if (!ASSERT_OK_PTR(obj, "skel-load"))
 		return;
 
+	obj->bss->page_size = sysconf(_SC_PAGESIZE);
+
 	/* Attach setsockopt that sets EUNATCH, then one that sets EISCONN,
 	 * and then one that gets the exported errno. Assert both the syscall
 	 * and the helper sees the last set errno.
@@ -224,6 +234,8 @@ static void test_setsockopt_legacy_eperm(int cgroup_fd, int sock_fd)
 	if (!ASSERT_OK_PTR(obj, "skel-load"))
 		return;
 
+	obj->bss->page_size = sysconf(_SC_PAGESIZE);
+
 	/* Attach setsockopt that return a reject without setting errno
 	 * (legacy reject), and one that gets the errno. Assert that for
 	 * backward compatibility the syscall result in EPERM, and this
@@ -268,6 +280,8 @@ static void test_setsockopt_legacy_no_override(int cgroup_fd, int sock_fd)
 	if (!ASSERT_OK_PTR(obj, "skel-load"))
 		return;
 
+	obj->bss->page_size = sysconf(_SC_PAGESIZE);
+
 	/* Attach setsockopt that sets EUNATCH, then one that return a reject
 	 * without setting errno, and then one that gets the exported errno.
 	 * Assert both the syscall and the helper's errno are unaffected by
@@ -319,6 +333,8 @@ static void test_getsockopt_get(int cgroup_fd, int sock_fd)
 	if (!ASSERT_OK_PTR(obj, "skel-load"))
 		return;
 
+	obj->bss->page_size = sysconf(_SC_PAGESIZE);
+
 	/* Attach getsockopt that gets previously set errno. Assert that the
 	 * error from kernel is in both ctx_retval_value and retval_value.
 	 */
@@ -359,6 +375,8 @@ static void test_getsockopt_override(int cgroup_fd, int sock_fd)
 	if (!ASSERT_OK_PTR(obj, "skel-load"))
 		return;
 
+	obj->bss->page_size = sysconf(_SC_PAGESIZE);
+
 	/* Attach getsockopt that sets retval to -EISCONN. Assert that this
 	 * overrides the value from kernel.
 	 */
@@ -396,6 +414,8 @@ static void test_getsockopt_retval_sync(int cgroup_fd, int sock_fd)
 	if (!ASSERT_OK_PTR(obj, "skel-load"))
 		return;
 
+	obj->bss->page_size = sysconf(_SC_PAGESIZE);
+
 	/* Attach getsockopt that sets retval to -EISCONN, and one that clears
 	 * ctx retval. Assert that the clearing ctx retval is synced to helper
 	 * and clears any errors both from kernel and BPF..
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c b/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c
index e02feb5fae97..574d9a0cdc8e 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_iter.c
@@ -4,6 +4,7 @@
 #include <test_progs.h>
 #include <bpf/libbpf.h>
 #include <bpf/btf.h>
+#include "iters_css_task.skel.h"
 #include "cgroup_iter.skel.h"
 #include "cgroup_helpers.h"
 
@@ -263,6 +264,35 @@ close_cgrp:
 	close(cgrp_fd);
 }
 
+static void test_walk_self_only_css_task(void)
+{
+	struct iters_css_task *skel;
+	int err;
+
+	skel = iters_css_task__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	bpf_program__set_autoload(skel->progs.cgroup_id_printer, true);
+
+	err = iters_css_task__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	err = join_cgroup(cg_path[CHILD2]);
+	if (!ASSERT_OK(err, "join_cgroup"))
+		goto cleanup;
+
+	skel->bss->target_pid = getpid();
+	snprintf(expected_output, sizeof(expected_output),
+		PROLOGUE "%8llu\n" EPILOGUE, cg_id[CHILD2]);
+	read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[CHILD2],
+		BPF_CGROUP_ITER_SELF_ONLY, "test_walk_self_only_css_task");
+	ASSERT_EQ(skel->bss->css_task_cnt, 1, "css_task_cnt");
+cleanup:
+	iters_css_task__destroy(skel);
+}
+
 void test_cgroup_iter(void)
 {
 	struct cgroup_iter *skel = NULL;
@@ -293,6 +323,9 @@ void test_cgroup_iter(void)
 		test_walk_self_only(skel);
 	if (test__start_subtest("cgroup_iter__dead_self_only"))
 		test_walk_dead_self_only(skel);
+	if (test__start_subtest("cgroup_iter__self_only_css_task"))
+		test_walk_self_only_css_task();
+
 out:
 	cgroup_iter__destroy(skel);
 	cleanup_cgroups();
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_opts.c b/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_opts.c
new file mode 100644
index 000000000000..bb60704a3ef9
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_opts.c
@@ -0,0 +1,617 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+#include "cgroup_mprog.skel.h"
+
+static void assert_mprog_count(int cg, int atype, int expected)
+{
+	__u32 count = 0, attach_flags = 0;
+	int err;
+
+	err = bpf_prog_query(cg, atype, 0, &attach_flags,
+			     NULL, &count);
+	ASSERT_EQ(count, expected, "count");
+	ASSERT_EQ(err, 0, "prog_query");
+}
+
+static void test_prog_attach_detach(int atype)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+	struct cgroup_mprog *skel;
+	__u32 prog_ids[10];
+	int cg, err;
+
+	cg = test__join_cgroup("/prog_attach_detach");
+	if (!ASSERT_GE(cg, 0, "join_cgroup /prog_attach_detach"))
+		return;
+
+	skel = cgroup_mprog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.getsockopt_1);
+	fd2 = bpf_program__fd(skel->progs.getsockopt_2);
+	fd3 = bpf_program__fd(skel->progs.getsockopt_3);
+	fd4 = bpf_program__fd(skel->progs.getsockopt_4);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+	id4 = id_from_prog_fd(fd4);
+
+	assert_mprog_count(cg, atype, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE | BPF_F_AFTER,
+		.expected_revision = 1,
+	);
+
+	/* ordering: [fd1] */
+	err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(cg, atype, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE,
+		.expected_revision = 2,
+	);
+
+	/* ordering: [fd2, fd1] */
+	err = bpf_prog_attach_opts(fd2, cg, atype, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup1;
+
+	assert_mprog_count(cg, atype, 2);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER,
+		.relative_fd = fd2,
+		.expected_revision = 3,
+	);
+
+	/* ordering: [fd2, fd3, fd1] */
+	err = bpf_prog_attach_opts(fd3, cg, atype, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup2;
+
+	assert_mprog_count(cg, atype, 3);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ALLOW_MULTI,
+		.expected_revision = 4,
+	);
+
+	/* ordering: [fd2, fd3, fd1, fd4] */
+	err = bpf_prog_attach_opts(fd4, cg, atype, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup3;
+
+	assert_mprog_count(cg, atype, 4);
+
+	/* retrieve optq.prog_cnt */
+	err = bpf_prog_query_opts(cg, atype, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	/* optq.prog_cnt will be used in below query */
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.prog_ids = prog_ids;
+	err = bpf_prog_query_opts(cg, atype, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id1, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+	ASSERT_EQ(optq.link_ids, NULL, "link_ids");
+
+cleanup4:
+	optd.expected_revision = 5;
+	err = bpf_prog_detach_opts(fd4, cg, atype, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(cg, atype, 3);
+
+cleanup3:
+	LIBBPF_OPTS_RESET(optd);
+	err = bpf_prog_detach_opts(fd3, cg, atype, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(cg, atype, 2);
+
+	/* Check revision after two detach operations */
+	err = bpf_prog_query_opts(cg, atype, &optq);
+	ASSERT_OK(err, "prog_query");
+	ASSERT_EQ(optq.revision, 7, "revision");
+
+cleanup2:
+	err = bpf_prog_detach_opts(fd2, cg, atype, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(cg, atype, 1);
+
+cleanup1:
+	err = bpf_prog_detach_opts(fd1, cg, atype, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(cg, atype, 0);
+
+cleanup:
+	cgroup_mprog__destroy(skel);
+	close(cg);
+}
+
+static void test_link_attach_detach(int atype)
+{
+	LIBBPF_OPTS(bpf_cgroup_opts, opta);
+	LIBBPF_OPTS(bpf_cgroup_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	struct bpf_link *link1, *link2, *link3, *link4;
+	__u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+	struct cgroup_mprog *skel;
+	__u32 prog_ids[10];
+	int cg, err;
+
+	cg = test__join_cgroup("/link_attach_detach");
+	if (!ASSERT_GE(cg, 0, "join_cgroup /link_attach_detach"))
+		return;
+
+	skel = cgroup_mprog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.getsockopt_1);
+	fd2 = bpf_program__fd(skel->progs.getsockopt_2);
+	fd3 = bpf_program__fd(skel->progs.getsockopt_3);
+	fd4 = bpf_program__fd(skel->progs.getsockopt_4);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+	id4 = id_from_prog_fd(fd4);
+
+	assert_mprog_count(cg, atype, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.expected_revision = 1,
+	);
+
+	/* ordering: [fd1] */
+	link1 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_1, cg, &opta);
+	if (!ASSERT_OK_PTR(link1, "link_attach"))
+		goto cleanup;
+
+	assert_mprog_count(cg, atype, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE | BPF_F_LINK,
+		.relative_id = id_from_link_fd(bpf_link__fd(link1)),
+		.expected_revision = 2,
+	);
+
+	/* ordering: [fd2, fd1] */
+	link2 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_2, cg, &opta);
+	if (!ASSERT_OK_PTR(link2, "link_attach"))
+		goto cleanup1;
+
+	assert_mprog_count(cg, atype, 2);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_AFTER | BPF_F_LINK,
+		.relative_fd = bpf_link__fd(link2),
+		.expected_revision = 3,
+	);
+
+	/* ordering: [fd2, fd3, fd1] */
+	link3 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_3, cg, &opta);
+	if (!ASSERT_OK_PTR(link3, "link_attach"))
+		goto cleanup2;
+
+	assert_mprog_count(cg, atype, 3);
+
+	LIBBPF_OPTS_RESET(opta,
+		.expected_revision = 4,
+	);
+
+	/* ordering: [fd2, fd3, fd1, fd4] */
+	link4 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_4, cg, &opta);
+	if (!ASSERT_OK_PTR(link4, "link_attach"))
+		goto cleanup3;
+
+	assert_mprog_count(cg, atype, 4);
+
+	/* retrieve optq.prog_cnt */
+	err = bpf_prog_query_opts(cg, atype, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	/* optq.prog_cnt will be used in below query */
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.prog_ids = prog_ids;
+	err = bpf_prog_query_opts(cg, atype, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id1, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+	ASSERT_EQ(optq.link_ids, NULL, "link_ids");
+
+cleanup4:
+	bpf_link__destroy(link4);
+	assert_mprog_count(cg, atype, 3);
+
+cleanup3:
+	bpf_link__destroy(link3);
+	assert_mprog_count(cg, atype, 2);
+
+	/* Check revision after two detach operations */
+	err = bpf_prog_query_opts(cg, atype, &optq);
+	ASSERT_OK(err, "prog_query");
+	ASSERT_EQ(optq.revision, 7, "revision");
+
+cleanup2:
+	bpf_link__destroy(link2);
+	assert_mprog_count(cg, atype, 1);
+
+cleanup1:
+	bpf_link__destroy(link1);
+	assert_mprog_count(cg, atype, 0);
+
+cleanup:
+	cgroup_mprog__destroy(skel);
+	close(cg);
+}
+
+static void test_preorder_prog_attach_detach(int atype)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	__u32 fd1, fd2, fd3, fd4;
+	struct cgroup_mprog *skel;
+	int cg, err;
+
+	cg = test__join_cgroup("/preorder_prog_attach_detach");
+	if (!ASSERT_GE(cg, 0, "join_cgroup /preorder_prog_attach_detach"))
+		return;
+
+	skel = cgroup_mprog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.getsockopt_1);
+	fd2 = bpf_program__fd(skel->progs.getsockopt_2);
+	fd3 = bpf_program__fd(skel->progs.getsockopt_3);
+	fd4 = bpf_program__fd(skel->progs.getsockopt_4);
+
+	assert_mprog_count(cg, atype, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ALLOW_MULTI,
+		.expected_revision = 1,
+	);
+
+	/* ordering: [fd1] */
+	err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(cg, atype, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ALLOW_MULTI | BPF_F_PREORDER,
+		.expected_revision = 2,
+	);
+
+	/* ordering: [fd1, fd2] */
+	err = bpf_prog_attach_opts(fd2, cg, atype, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup1;
+
+	assert_mprog_count(cg, atype, 2);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER,
+		.relative_fd = fd2,
+		.expected_revision = 3,
+	);
+
+	err = bpf_prog_attach_opts(fd3, cg, atype, &opta);
+	if (!ASSERT_EQ(err, -EINVAL, "prog_attach"))
+		goto cleanup2;
+
+	assert_mprog_count(cg, atype, 2);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER | BPF_F_PREORDER,
+		.relative_fd = fd2,
+		.expected_revision = 3,
+	);
+
+	/* ordering: [fd1, fd2, fd3] */
+	err = bpf_prog_attach_opts(fd3, cg, atype, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup2;
+
+	assert_mprog_count(cg, atype, 3);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ALLOW_MULTI,
+		.expected_revision = 4,
+	);
+
+	/* ordering: [fd2, fd3, fd1, fd4] */
+	err = bpf_prog_attach_opts(fd4, cg, atype, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup3;
+
+	assert_mprog_count(cg, atype, 4);
+
+	err = bpf_prog_detach_opts(fd4, cg, atype, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(cg, atype, 3);
+
+cleanup3:
+	err = bpf_prog_detach_opts(fd3, cg, atype, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(cg, atype, 2);
+
+cleanup2:
+	err = bpf_prog_detach_opts(fd2, cg, atype, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(cg, atype, 1);
+
+cleanup1:
+	err = bpf_prog_detach_opts(fd1, cg, atype, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(cg, atype, 0);
+
+cleanup:
+	cgroup_mprog__destroy(skel);
+	close(cg);
+}
+
+static void test_preorder_link_attach_detach(int atype)
+{
+	LIBBPF_OPTS(bpf_cgroup_opts, opta);
+	struct bpf_link *link1, *link2, *link3, *link4;
+	struct cgroup_mprog *skel;
+	__u32 fd2;
+	int cg;
+
+	cg = test__join_cgroup("/preorder_link_attach_detach");
+	if (!ASSERT_GE(cg, 0, "join_cgroup /preorder_link_attach_detach"))
+		return;
+
+	skel = cgroup_mprog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd2 = bpf_program__fd(skel->progs.getsockopt_2);
+
+	assert_mprog_count(cg, atype, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.expected_revision = 1,
+	);
+
+	/* ordering: [fd1] */
+	link1 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_1, cg, &opta);
+	if (!ASSERT_OK_PTR(link1, "link_attach"))
+		goto cleanup;
+
+	assert_mprog_count(cg, atype, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_PREORDER,
+		.expected_revision = 2,
+	);
+
+	/* ordering: [fd1, fd2] */
+	link2 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_2, cg, &opta);
+	if (!ASSERT_OK_PTR(link2, "link_attach"))
+		goto cleanup1;
+
+	assert_mprog_count(cg, atype, 2);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_AFTER,
+		.relative_fd = fd2,
+		.expected_revision = 3,
+	);
+
+	link3 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_3, cg, &opta);
+	if (!ASSERT_ERR_PTR(link3, "link_attach"))
+		goto cleanup2;
+
+	assert_mprog_count(cg, atype, 2);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_AFTER | BPF_F_PREORDER | BPF_F_LINK,
+		.relative_fd = bpf_link__fd(link2),
+		.expected_revision = 3,
+	);
+
+	/* ordering: [fd1, fd2, fd3] */
+	link3 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_3, cg, &opta);
+	if (!ASSERT_OK_PTR(link3, "link_attach"))
+		goto cleanup2;
+
+	assert_mprog_count(cg, atype, 3);
+
+	LIBBPF_OPTS_RESET(opta,
+		.expected_revision = 4,
+	);
+
+	/* ordering: [fd2, fd3, fd1, fd4] */
+	link4 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_4, cg, &opta);
+	if (!ASSERT_OK_PTR(link4, "prog_attach"))
+		goto cleanup3;
+
+	assert_mprog_count(cg, atype, 4);
+
+	bpf_link__destroy(link4);
+	assert_mprog_count(cg, atype, 3);
+
+cleanup3:
+	bpf_link__destroy(link3);
+	assert_mprog_count(cg, atype, 2);
+
+cleanup2:
+	bpf_link__destroy(link2);
+	assert_mprog_count(cg, atype, 1);
+
+cleanup1:
+	bpf_link__destroy(link1);
+	assert_mprog_count(cg, atype, 0);
+
+cleanup:
+	cgroup_mprog__destroy(skel);
+	close(cg);
+}
+
+static void test_invalid_attach_detach(int atype)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	__u32 fd1, fd2, id2;
+	struct cgroup_mprog *skel;
+	int cg, err;
+
+	cg = test__join_cgroup("/invalid_attach_detach");
+	if (!ASSERT_GE(cg, 0, "join_cgroup /invalid_attach_detach"))
+		return;
+
+	skel = cgroup_mprog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.getsockopt_1);
+	fd2 = bpf_program__fd(skel->progs.getsockopt_2);
+
+	id2 = id_from_prog_fd(fd2);
+
+	assert_mprog_count(cg, atype, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE | BPF_F_AFTER,
+		.relative_id = id2,
+	);
+
+	err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+	ASSERT_EQ(err, -EINVAL, "prog_attach");
+	assert_mprog_count(cg, atype, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE | BPF_F_ID,
+	);
+
+	err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+	ASSERT_EQ(err, -ENOENT, "prog_attach");
+	assert_mprog_count(cg, atype, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER | BPF_F_ID,
+	);
+
+	err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+	ASSERT_EQ(err, -ENOENT, "prog_attach");
+	assert_mprog_count(cg, atype, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE | BPF_F_AFTER,
+		.relative_id = id2,
+	);
+
+	err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+	ASSERT_EQ(err, -EINVAL, "prog_attach");
+	assert_mprog_count(cg, atype, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ALLOW_MULTI | BPF_F_LINK,
+		.relative_id = id2,
+	);
+
+	err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+	ASSERT_EQ(err, -EINVAL, "prog_attach");
+	assert_mprog_count(cg, atype, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ALLOW_MULTI,
+		.relative_id = id2,
+	);
+
+	err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+	ASSERT_EQ(err, -EINVAL, "prog_attach");
+	assert_mprog_count(cg, atype, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+	ASSERT_EQ(err, -ENOENT, "prog_attach");
+	assert_mprog_count(cg, atype, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+	ASSERT_EQ(err, -ENOENT, "prog_attach");
+	assert_mprog_count(cg, atype, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ALLOW_MULTI,
+	);
+
+	err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+	assert_mprog_count(cg, atype, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER,
+	);
+
+	err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+	ASSERT_EQ(err, -EINVAL, "prog_attach");
+	assert_mprog_count(cg, atype, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ALLOW_MULTI | BPF_F_REPLACE | BPF_F_AFTER,
+		.replace_prog_fd = fd1,
+	);
+
+	err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+	ASSERT_EQ(err, -EINVAL, "prog_attach");
+	assert_mprog_count(cg, atype, 1);
+cleanup:
+	cgroup_mprog__destroy(skel);
+	close(cg);
+}
+
+void test_cgroup_mprog_opts(void)
+{
+	if (test__start_subtest("prog_attach_detach"))
+		test_prog_attach_detach(BPF_CGROUP_GETSOCKOPT);
+	if (test__start_subtest("link_attach_detach"))
+		test_link_attach_detach(BPF_CGROUP_GETSOCKOPT);
+	if (test__start_subtest("preorder_prog_attach_detach"))
+		test_preorder_prog_attach_detach(BPF_CGROUP_GETSOCKOPT);
+	if (test__start_subtest("preorder_link_attach_detach"))
+		test_preorder_link_attach_detach(BPF_CGROUP_GETSOCKOPT);
+	if (test__start_subtest("invalid_attach_detach"))
+		test_invalid_attach_detach(BPF_CGROUP_GETSOCKOPT);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_ordering.c b/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_ordering.c
new file mode 100644
index 000000000000..a36d2e968bc5
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_ordering.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+#include "cgroup_preorder.skel.h"
+
+static int run_getsockopt_test(int cg_parent, int sock_fd, bool has_relative_fd)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opts);
+	enum bpf_attach_type prog_p_atype, prog_p2_atype;
+	int prog_p_fd, prog_p2_fd;
+	struct cgroup_preorder *skel = NULL;
+	struct bpf_program *prog;
+	__u8 *result, buf;
+	socklen_t optlen = 1;
+	int err = 0;
+
+	skel = cgroup_preorder__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "cgroup_preorder__open_and_load"))
+		return 0;
+
+	LIBBPF_OPTS_RESET(opts);
+	opts.flags = BPF_F_ALLOW_MULTI;
+	prog = skel->progs.parent;
+	prog_p_fd = bpf_program__fd(prog);
+	prog_p_atype = bpf_program__expected_attach_type(prog);
+	err = bpf_prog_attach_opts(prog_p_fd, cg_parent, prog_p_atype, &opts);
+	if (!ASSERT_OK(err, "bpf_prog_attach_opts-parent"))
+		goto close_skel;
+
+	opts.flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE;
+	if (has_relative_fd)
+		opts.relative_fd = prog_p_fd;
+	prog = skel->progs.parent_2;
+	prog_p2_fd = bpf_program__fd(prog);
+	prog_p2_atype = bpf_program__expected_attach_type(prog);
+	err = bpf_prog_attach_opts(prog_p2_fd, cg_parent, prog_p2_atype, &opts);
+	if (!ASSERT_OK(err, "bpf_prog_attach_opts-parent_2"))
+		goto detach_parent;
+
+	err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+	if (!ASSERT_OK(err, "getsockopt"))
+		goto detach_parent_2;
+
+	result = skel->bss->result;
+	ASSERT_TRUE(result[0] == 4 && result[1] == 3, "result values");
+
+detach_parent_2:
+	ASSERT_OK(bpf_prog_detach2(prog_p2_fd, cg_parent, prog_p2_atype),
+		  "bpf_prog_detach2-parent_2");
+detach_parent:
+	ASSERT_OK(bpf_prog_detach2(prog_p_fd, cg_parent, prog_p_atype),
+		  "bpf_prog_detach2-parent");
+close_skel:
+	cgroup_preorder__destroy(skel);
+	return err;
+}
+
+void test_cgroup_mprog_ordering(void)
+{
+	int cg_parent = -1, sock_fd = -1;
+
+	cg_parent = test__join_cgroup("/parent");
+	if (!ASSERT_GE(cg_parent, 0, "join_cgroup /parent"))
+		goto out;
+
+	sock_fd = socket(AF_INET, SOCK_STREAM, 0);
+	if (!ASSERT_GE(sock_fd, 0, "socket"))
+		goto out;
+
+	ASSERT_OK(run_getsockopt_test(cg_parent, sock_fd, false), "getsockopt_test_1");
+	ASSERT_OK(run_getsockopt_test(cg_parent, sock_fd, true), "getsockopt_test_2");
+
+out:
+	close(sock_fd);
+	close(cg_parent);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_preorder.c b/tools/testing/selftests/bpf/prog_tests/cgroup_preorder.c
new file mode 100644
index 000000000000..d4d583872fa2
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_preorder.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+#include "cgroup_preorder.skel.h"
+
+static int run_getsockopt_test(int cg_parent, int cg_child, int sock_fd, bool all_preorder)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opts);
+	enum bpf_attach_type prog_c_atype, prog_c2_atype, prog_p_atype, prog_p2_atype;
+	int prog_c_fd, prog_c2_fd, prog_p_fd, prog_p2_fd;
+	struct cgroup_preorder *skel = NULL;
+	struct bpf_program *prog;
+	__u8 *result, buf;
+	socklen_t optlen;
+	int err = 0;
+
+	skel = cgroup_preorder__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "cgroup_preorder__open_and_load"))
+		return 0;
+
+	buf = 0x00;
+	err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1);
+	if (!ASSERT_OK(err, "setsockopt"))
+		goto close_skel;
+
+	opts.flags = BPF_F_ALLOW_MULTI;
+	if (all_preorder)
+		opts.flags |= BPF_F_PREORDER;
+	prog = skel->progs.child;
+	prog_c_fd = bpf_program__fd(prog);
+	prog_c_atype = bpf_program__expected_attach_type(prog);
+	err = bpf_prog_attach_opts(prog_c_fd, cg_child, prog_c_atype, &opts);
+	if (!ASSERT_OK(err, "bpf_prog_attach_opts-child"))
+		goto close_skel;
+
+	opts.flags = BPF_F_ALLOW_MULTI | BPF_F_PREORDER;
+	prog = skel->progs.child_2;
+	prog_c2_fd = bpf_program__fd(prog);
+	prog_c2_atype = bpf_program__expected_attach_type(prog);
+	err = bpf_prog_attach_opts(prog_c2_fd, cg_child, prog_c2_atype, &opts);
+	if (!ASSERT_OK(err, "bpf_prog_attach_opts-child_2"))
+		goto detach_child;
+
+	optlen = 1;
+	err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+	if (!ASSERT_OK(err, "getsockopt"))
+		goto detach_child_2;
+
+	result = skel->bss->result;
+	if (all_preorder)
+		ASSERT_TRUE(result[0] == 1 && result[1] == 2, "child only");
+	else
+		ASSERT_TRUE(result[0] == 2 && result[1] == 1, "child only");
+
+	skel->bss->idx = 0;
+	memset(result, 0, 4);
+
+	opts.flags = BPF_F_ALLOW_MULTI;
+	if (all_preorder)
+		opts.flags |= BPF_F_PREORDER;
+	prog = skel->progs.parent;
+	prog_p_fd = bpf_program__fd(prog);
+	prog_p_atype = bpf_program__expected_attach_type(prog);
+	err = bpf_prog_attach_opts(prog_p_fd, cg_parent, prog_p_atype, &opts);
+	if (!ASSERT_OK(err, "bpf_prog_attach_opts-parent"))
+		goto detach_child_2;
+
+	opts.flags = BPF_F_ALLOW_MULTI | BPF_F_PREORDER;
+	prog = skel->progs.parent_2;
+	prog_p2_fd = bpf_program__fd(prog);
+	prog_p2_atype = bpf_program__expected_attach_type(prog);
+	err = bpf_prog_attach_opts(prog_p2_fd, cg_parent, prog_p2_atype, &opts);
+	if (!ASSERT_OK(err, "bpf_prog_attach_opts-parent_2"))
+		goto detach_parent;
+
+	err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+	if (!ASSERT_OK(err, "getsockopt"))
+		goto detach_parent_2;
+
+	if (all_preorder)
+		ASSERT_TRUE(result[0] == 3 && result[1] == 4 && result[2] == 1 && result[3] == 2,
+			    "parent and child");
+	else
+		ASSERT_TRUE(result[0] == 4 && result[1] == 2 && result[2] == 1 && result[3] == 3,
+			    "parent and child");
+
+detach_parent_2:
+	ASSERT_OK(bpf_prog_detach2(prog_p2_fd, cg_parent, prog_p2_atype),
+		  "bpf_prog_detach2-parent_2");
+detach_parent:
+	ASSERT_OK(bpf_prog_detach2(prog_p_fd, cg_parent, prog_p_atype),
+		  "bpf_prog_detach2-parent");
+detach_child_2:
+	ASSERT_OK(bpf_prog_detach2(prog_c2_fd, cg_child, prog_c2_atype),
+		  "bpf_prog_detach2-child_2");
+detach_child:
+	ASSERT_OK(bpf_prog_detach2(prog_c_fd, cg_child, prog_c_atype),
+		  "bpf_prog_detach2-child");
+close_skel:
+	cgroup_preorder__destroy(skel);
+	return err;
+}
+
+void test_cgroup_preorder(void)
+{
+	int cg_parent = -1, cg_child = -1, sock_fd = -1;
+
+	cg_parent = test__join_cgroup("/parent");
+	if (!ASSERT_GE(cg_parent, 0, "join_cgroup /parent"))
+		goto out;
+
+	cg_child = test__join_cgroup("/parent/child");
+	if (!ASSERT_GE(cg_child, 0, "join_cgroup /parent/child"))
+		goto out;
+
+	sock_fd = socket(AF_INET, SOCK_STREAM, 0);
+	if (!ASSERT_GE(sock_fd, 0, "socket"))
+		goto out;
+
+	ASSERT_OK(run_getsockopt_test(cg_parent, cg_child, sock_fd, false), "getsockopt_test_1");
+	ASSERT_OK(run_getsockopt_test(cg_parent, cg_child, sock_fd, true), "getsockopt_test_2");
+
+out:
+	close(sock_fd);
+	close(cg_child);
+	close(cg_parent);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_skb_direct_packet_access.c b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_direct_packet_access.c
new file mode 100644
index 000000000000..e1a90c10db8c
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_direct_packet_access.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "cgroup_skb_direct_packet_access.skel.h"
+
+void test_cgroup_skb_prog_run_direct_packet_access(void)
+{
+	int err;
+	struct cgroup_skb_direct_packet_access *skel;
+	char test_skb[64] = {};
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = test_skb,
+		.data_size_in = sizeof(test_skb),
+	);
+
+	skel = cgroup_skb_direct_packet_access__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "cgroup_skb_direct_packet_access__open_and_load"))
+		return;
+
+	err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.direct_packet_access), &topts);
+	ASSERT_OK(err, "bpf_prog_test_run_opts err");
+	ASSERT_EQ(topts.retval, 1, "retval");
+
+	ASSERT_NEQ(skel->bss->data_end, 0, "data_end");
+
+	cgroup_skb_direct_packet_access__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_storage.c b/tools/testing/selftests/bpf/prog_tests/cgroup_storage.c
new file mode 100644
index 000000000000..cf395715ced4
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_storage.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+#include "network_helpers.h"
+#include "cgroup_storage.skel.h"
+
+#define TEST_CGROUP "/test-bpf-cgroup-storage-buf/"
+#define TEST_NS "cgroup_storage_ns"
+#define PING_CMD "ping localhost -c 1 -W 1 -q"
+
+static int setup_network(struct nstoken **token)
+{
+	SYS(fail, "ip netns add %s", TEST_NS);
+	*token = open_netns(TEST_NS);
+	if (!ASSERT_OK_PTR(*token, "open netns"))
+		goto cleanup_ns;
+	SYS(cleanup_ns, "ip link set lo up");
+
+	return 0;
+
+cleanup_ns:
+	SYS_NOFAIL("ip netns del %s", TEST_NS);
+fail:
+	return -1;
+}
+
+static void cleanup_network(struct nstoken *ns)
+{
+	close_netns(ns);
+	SYS_NOFAIL("ip netns del %s", TEST_NS);
+}
+
+void test_cgroup_storage(void)
+{
+	struct bpf_cgroup_storage_key key;
+	struct cgroup_storage *skel;
+	struct nstoken *ns = NULL;
+	unsigned long long value;
+	int cgroup_fd;
+	int err;
+
+	cgroup_fd = cgroup_setup_and_join(TEST_CGROUP);
+	if (!ASSERT_OK_FD(cgroup_fd, "create cgroup"))
+		return;
+
+	if (!ASSERT_OK(setup_network(&ns), "setup network"))
+		goto cleanup_cgroup;
+
+	skel = cgroup_storage__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "load program"))
+		goto cleanup_network;
+
+	skel->links.bpf_prog =
+		bpf_program__attach_cgroup(skel->progs.bpf_prog, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.bpf_prog, "attach program"))
+		goto cleanup_progs;
+
+	/* Check that one out of every two packets is dropped */
+	err = SYS_NOFAIL(PING_CMD);
+	ASSERT_OK(err, "first ping");
+	err = SYS_NOFAIL(PING_CMD);
+	ASSERT_NEQ(err, 0, "second ping");
+	err = SYS_NOFAIL(PING_CMD);
+	ASSERT_OK(err, "third ping");
+
+	err = bpf_map__get_next_key(skel->maps.cgroup_storage, NULL, &key,
+				    sizeof(key));
+	if (!ASSERT_OK(err, "get first key"))
+		goto cleanup_progs;
+	err = bpf_map__lookup_elem(skel->maps.cgroup_storage, &key, sizeof(key),
+				   &value, sizeof(value), 0);
+	if (!ASSERT_OK(err, "first packet count read"))
+		goto cleanup_progs;
+
+	/* Add one to the packet counter, check again packet filtering */
+	value++;
+	err = bpf_map__update_elem(skel->maps.cgroup_storage, &key, sizeof(key),
+				   &value, sizeof(value), 0);
+	if (!ASSERT_OK(err, "increment packet counter"))
+		goto cleanup_progs;
+	err = SYS_NOFAIL(PING_CMD);
+	ASSERT_OK(err, "fourth ping");
+	err = SYS_NOFAIL(PING_CMD);
+	ASSERT_NEQ(err, 0, "fifth ping");
+	err = SYS_NOFAIL(PING_CMD);
+	ASSERT_OK(err, "sixth ping");
+
+cleanup_progs:
+	cgroup_storage__destroy(skel);
+cleanup_network:
+	cleanup_network(ns);
+cleanup_cgroup:
+	close(cgroup_fd);
+	cleanup_cgroup_environment();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c b/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c
new file mode 100644
index 000000000000..a1542faf7873
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c
@@ -0,0 +1,344 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Facebook */
+#include <test_progs.h>
+#include <linux/in6.h>
+#include <sys/socket.h>
+#include <sched.h>
+#include <unistd.h>
+#include "cgroup_helpers.h"
+#include "testing_helpers.h"
+#include "cgroup_tcp_skb.skel.h"
+#include "cgroup_tcp_skb.h"
+#include "network_helpers.h"
+
+#define CGROUP_TCP_SKB_PATH "/test_cgroup_tcp_skb"
+
+static int install_filters(int cgroup_fd,
+			   struct bpf_link **egress_link,
+			   struct bpf_link **ingress_link,
+			   struct bpf_program *egress_prog,
+			   struct bpf_program *ingress_prog,
+			   struct cgroup_tcp_skb *skel)
+{
+	/* Prepare filters */
+	skel->bss->g_sock_state = 0;
+	skel->bss->g_unexpected = 0;
+	*egress_link =
+		bpf_program__attach_cgroup(egress_prog,
+					   cgroup_fd);
+	if (!ASSERT_OK_PTR(egress_link, "egress_link"))
+		return -1;
+	*ingress_link =
+		bpf_program__attach_cgroup(ingress_prog,
+					   cgroup_fd);
+	if (!ASSERT_OK_PTR(ingress_link, "ingress_link"))
+		return -1;
+
+	return 0;
+}
+
+static void uninstall_filters(struct bpf_link **egress_link,
+			      struct bpf_link **ingress_link)
+{
+	bpf_link__destroy(*egress_link);
+	*egress_link = NULL;
+	bpf_link__destroy(*ingress_link);
+	*ingress_link = NULL;
+}
+
+static int create_client_sock_v6(void)
+{
+	int fd;
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (fd < 0) {
+		perror("socket");
+		return -1;
+	}
+
+	return fd;
+}
+
+/* Connect to the server in a cgroup from the outside of the cgroup. */
+static int talk_to_cgroup(int *client_fd, int *listen_fd, int *service_fd,
+			  struct cgroup_tcp_skb *skel)
+{
+	int err, cp;
+	char buf[5];
+	int port;
+
+	/* Create client & server socket */
+	err = join_root_cgroup();
+	if (!ASSERT_OK(err, "join_root_cgroup"))
+		return -1;
+	*client_fd = create_client_sock_v6();
+	if (!ASSERT_GE(*client_fd, 0, "client_fd"))
+		return -1;
+	err = join_cgroup(CGROUP_TCP_SKB_PATH);
+	if (!ASSERT_OK(err, "join_cgroup"))
+		return -1;
+	*listen_fd = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
+	if (!ASSERT_GE(*listen_fd, 0, "listen_fd"))
+		return -1;
+	port = get_socket_local_port(*listen_fd);
+	if (!ASSERT_GE(port, 0, "get_socket_local_port"))
+		return -1;
+	skel->bss->g_sock_port = ntohs(port);
+
+	/* Connect client to server */
+	err = connect_fd_to_fd(*client_fd, *listen_fd, 0);
+	if (!ASSERT_OK(err, "connect_fd_to_fd"))
+		return -1;
+	*service_fd = accept(*listen_fd, NULL, NULL);
+	if (!ASSERT_GE(*service_fd, 0, "service_fd"))
+		return -1;
+	err = join_root_cgroup();
+	if (!ASSERT_OK(err, "join_root_cgroup"))
+		return -1;
+	cp = write(*client_fd, "hello", 5);
+	if (!ASSERT_EQ(cp, 5, "write"))
+		return -1;
+	cp = read(*service_fd, buf, 5);
+	if (!ASSERT_EQ(cp, 5, "read"))
+		return -1;
+
+	return 0;
+}
+
+/* Connect to the server out of a cgroup from inside the cgroup. */
+static int talk_to_outside(int *client_fd, int *listen_fd, int *service_fd,
+			   struct cgroup_tcp_skb *skel)
+
+{
+	int err, cp;
+	char buf[5];
+	int port;
+
+	/* Create client & server socket */
+	err = join_root_cgroup();
+	if (!ASSERT_OK(err, "join_root_cgroup"))
+		return -1;
+	*listen_fd = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
+	if (!ASSERT_GE(*listen_fd, 0, "listen_fd"))
+		return -1;
+	err = join_cgroup(CGROUP_TCP_SKB_PATH);
+	if (!ASSERT_OK(err, "join_cgroup"))
+		return -1;
+	*client_fd = create_client_sock_v6();
+	if (!ASSERT_GE(*client_fd, 0, "client_fd"))
+		return -1;
+	err = join_root_cgroup();
+	if (!ASSERT_OK(err, "join_root_cgroup"))
+		return -1;
+	port = get_socket_local_port(*listen_fd);
+	if (!ASSERT_GE(port, 0, "get_socket_local_port"))
+		return -1;
+	skel->bss->g_sock_port = ntohs(port);
+
+	/* Connect client to server */
+	err = connect_fd_to_fd(*client_fd, *listen_fd, 0);
+	if (!ASSERT_OK(err, "connect_fd_to_fd"))
+		return -1;
+	*service_fd = accept(*listen_fd, NULL, NULL);
+	if (!ASSERT_GE(*service_fd, 0, "service_fd"))
+		return -1;
+	cp = write(*client_fd, "hello", 5);
+	if (!ASSERT_EQ(cp, 5, "write"))
+		return -1;
+	cp = read(*service_fd, buf, 5);
+	if (!ASSERT_EQ(cp, 5, "read"))
+		return -1;
+
+	return 0;
+}
+
+static int close_connection(int *closing_fd, int *peer_fd, int *listen_fd,
+			    struct cgroup_tcp_skb *skel)
+{
+	__u32 saved_packet_count = 0;
+	int err;
+	int i;
+
+	/* Wait for ACKs to be sent */
+	saved_packet_count = skel->bss->g_packet_count;
+	usleep(100000);		/* 0.1s */
+	for (i = 0;
+	     skel->bss->g_packet_count != saved_packet_count && i < 10;
+	     i++) {
+		saved_packet_count = skel->bss->g_packet_count;
+		usleep(100000);	/* 0.1s */
+	}
+	if (!ASSERT_EQ(skel->bss->g_packet_count, saved_packet_count,
+		       "packet_count"))
+		return -1;
+
+	skel->bss->g_packet_count = 0;
+	saved_packet_count = 0;
+
+	/* Half shutdown to make sure the closing socket having a chance to
+	 * receive a FIN from the peer.
+	 */
+	err = shutdown(*closing_fd, SHUT_WR);
+	if (!ASSERT_OK(err, "shutdown closing_fd"))
+		return -1;
+
+	/* Wait for FIN and the ACK of the FIN to be observed */
+	for (i = 0;
+	     skel->bss->g_packet_count < saved_packet_count + 2 && i < 10;
+	     i++)
+		usleep(100000);	/* 0.1s */
+	if (!ASSERT_GE(skel->bss->g_packet_count, saved_packet_count + 2,
+		       "packet_count"))
+		return -1;
+
+	saved_packet_count = skel->bss->g_packet_count;
+
+	/* Fully shutdown the connection */
+	err = close(*peer_fd);
+	if (!ASSERT_OK(err, "close peer_fd"))
+		return -1;
+	*peer_fd = -1;
+
+	/* Wait for FIN and the ACK of the FIN to be observed */
+	for (i = 0;
+	     skel->bss->g_packet_count < saved_packet_count + 2 && i < 10;
+	     i++)
+		usleep(100000);	/* 0.1s */
+	if (!ASSERT_GE(skel->bss->g_packet_count, saved_packet_count + 2,
+		       "packet_count"))
+		return -1;
+
+	err = close(*closing_fd);
+	if (!ASSERT_OK(err, "close closing_fd"))
+		return -1;
+	*closing_fd = -1;
+
+	close(*listen_fd);
+	*listen_fd = -1;
+
+	return 0;
+}
+
+/* This test case includes four scenarios:
+ * 1. Connect to the server from outside the cgroup and close the connection
+ *    from outside the cgroup.
+ * 2. Connect to the server from outside the cgroup and close the connection
+ *    from inside the cgroup.
+ * 3. Connect to the server from inside the cgroup and close the connection
+ *    from outside the cgroup.
+ * 4. Connect to the server from inside the cgroup and close the connection
+ *    from inside the cgroup.
+ *
+ * The test case is to verify that cgroup_skb/{egress,ingress} filters
+ * receive expected packets including SYN, SYN/ACK, ACK, FIN, and FIN/ACK.
+ */
+void test_cgroup_tcp_skb(void)
+{
+	struct bpf_link *ingress_link = NULL;
+	struct bpf_link *egress_link = NULL;
+	int client_fd = -1, listen_fd = -1;
+	struct cgroup_tcp_skb *skel;
+	int service_fd = -1;
+	int cgroup_fd = -1;
+	int err;
+
+	skel = cgroup_tcp_skb__open_and_load();
+	if (!ASSERT_OK(!skel, "skel_open_load"))
+		return;
+
+	err = setup_cgroup_environment();
+	if (!ASSERT_OK(err, "setup_cgroup_environment"))
+		goto cleanup;
+
+	cgroup_fd = create_and_get_cgroup(CGROUP_TCP_SKB_PATH);
+	if (!ASSERT_GE(cgroup_fd, 0, "cgroup_fd"))
+		goto cleanup;
+
+	/* Scenario 1 */
+	err = install_filters(cgroup_fd, &egress_link, &ingress_link,
+			      skel->progs.server_egress,
+			      skel->progs.server_ingress,
+			      skel);
+	if (!ASSERT_OK(err, "install_filters"))
+		goto cleanup;
+
+	err = talk_to_cgroup(&client_fd, &listen_fd, &service_fd, skel);
+	if (!ASSERT_OK(err, "talk_to_cgroup"))
+		goto cleanup;
+
+	err = close_connection(&client_fd, &service_fd, &listen_fd, skel);
+	if (!ASSERT_OK(err, "close_connection"))
+		goto cleanup;
+
+	ASSERT_EQ(skel->bss->g_unexpected, 0, "g_unexpected");
+	ASSERT_EQ(skel->bss->g_sock_state, CLOSED, "g_sock_state");
+
+	uninstall_filters(&egress_link, &ingress_link);
+
+	/* Scenario 2 */
+	err = install_filters(cgroup_fd, &egress_link, &ingress_link,
+			      skel->progs.server_egress_srv,
+			      skel->progs.server_ingress_srv,
+			      skel);
+
+	err = talk_to_cgroup(&client_fd, &listen_fd, &service_fd, skel);
+	if (!ASSERT_OK(err, "talk_to_cgroup"))
+		goto cleanup;
+
+	err = close_connection(&service_fd, &client_fd, &listen_fd, skel);
+	if (!ASSERT_OK(err, "close_connection"))
+		goto cleanup;
+
+	ASSERT_EQ(skel->bss->g_unexpected, 0, "g_unexpected");
+	ASSERT_EQ(skel->bss->g_sock_state, TIME_WAIT, "g_sock_state");
+
+	uninstall_filters(&egress_link, &ingress_link);
+
+	/* Scenario 3 */
+	err = install_filters(cgroup_fd, &egress_link, &ingress_link,
+			      skel->progs.client_egress_srv,
+			      skel->progs.client_ingress_srv,
+			      skel);
+
+	err = talk_to_outside(&client_fd, &listen_fd, &service_fd, skel);
+	if (!ASSERT_OK(err, "talk_to_outside"))
+		goto cleanup;
+
+	err = close_connection(&service_fd, &client_fd, &listen_fd, skel);
+	if (!ASSERT_OK(err, "close_connection"))
+		goto cleanup;
+
+	ASSERT_EQ(skel->bss->g_unexpected, 0, "g_unexpected");
+	ASSERT_EQ(skel->bss->g_sock_state, CLOSED, "g_sock_state");
+
+	uninstall_filters(&egress_link, &ingress_link);
+
+	/* Scenario 4 */
+	err = install_filters(cgroup_fd, &egress_link, &ingress_link,
+			      skel->progs.client_egress,
+			      skel->progs.client_ingress,
+			      skel);
+
+	err = talk_to_outside(&client_fd, &listen_fd, &service_fd, skel);
+	if (!ASSERT_OK(err, "talk_to_outside"))
+		goto cleanup;
+
+	err = close_connection(&client_fd, &service_fd, &listen_fd, skel);
+	if (!ASSERT_OK(err, "close_connection"))
+		goto cleanup;
+
+	ASSERT_EQ(skel->bss->g_unexpected, 0, "g_unexpected");
+	ASSERT_EQ(skel->bss->g_sock_state, TIME_WAIT, "g_sock_state");
+
+	uninstall_filters(&egress_link, &ingress_link);
+
+cleanup:
+	close(client_fd);
+	close(listen_fd);
+	close(service_fd);
+	close(cgroup_fd);
+	bpf_link__destroy(egress_link);
+	bpf_link__destroy(ingress_link);
+	cleanup_cgroup_environment();
+	cgroup_tcp_skb__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
index 9026b42914d3..37c1cc52ed98 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
@@ -9,16 +9,19 @@
 
 static int run_test(int cgroup_fd, int server_fd, bool classid)
 {
-	struct network_helper_opts opts = {
-		.must_fail = true,
-	};
 	struct connect4_dropper *skel;
-	int fd, err = 0;
+	int fd, err = 0, port;
 
 	skel = connect4_dropper__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
 		return -1;
 
+	port = get_socket_local_port(server_fd);
+	if (!ASSERT_GE(port, 0, "get_socket_local_port"))
+		return -1;
+
+	skel->bss->port = ntohs(port);
+
 	skel->links.connect_v4_dropper =
 		bpf_program__attach_cgroup(skel->progs.connect_v4_dropper,
 					   cgroup_fd);
@@ -32,11 +35,16 @@ static int run_test(int cgroup_fd, int server_fd, bool classid)
 		goto out;
 	}
 
-	fd = connect_to_fd_opts(server_fd, &opts);
-	if (fd < 0)
+	errno = 0;
+	fd = connect_to_fd_opts(server_fd, NULL);
+	if (fd >= 0) {
+		log_err("Unexpected success to connect to server");
 		err = -1;
-	else
 		close(fd);
+	} else if (errno != EPERM) {
+		log_err("Unexpected errno from connect to server");
+		err = -1;
+	}
 out:
 	connect4_dropper__destroy(skel);
 	return err;
@@ -46,10 +54,9 @@ void test_cgroup_v1v2(void)
 {
 	struct network_helper_opts opts = {};
 	int server_fd, client_fd, cgroup_fd;
-	static const int port = 60120;
 
 	/* Step 1: Check base connectivity works without any BPF. */
-	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, port, 0);
+	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0);
 	if (!ASSERT_GE(server_fd, 0, "server_fd"))
 		return;
 	client_fd = connect_to_fd_opts(server_fd, &opts);
@@ -64,14 +71,14 @@ void test_cgroup_v1v2(void)
 	cgroup_fd = test__join_cgroup("/connect_dropper");
 	if (!ASSERT_GE(cgroup_fd, 0, "cgroup_fd"))
 		return;
-	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, port, 0);
+	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0);
 	if (!ASSERT_GE(server_fd, 0, "server_fd")) {
 		close(cgroup_fd);
 		return;
 	}
 	ASSERT_OK(run_test(cgroup_fd, server_fd, false), "cgroup-v2-only");
 	setup_classid_environment();
-	set_classid(42);
+	set_classid();
 	ASSERT_OK(run_test(cgroup_fd, server_fd, true), "cgroup-v1v2");
 	cleanup_classid_environment();
 	close(server_fd);
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_xattr.c b/tools/testing/selftests/bpf/prog_tests/cgroup_xattr.c
new file mode 100644
index 000000000000..5ad904e9d15d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_xattr.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <errno.h>
+#include <fcntl.h>
+#include <sys/stat.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/socket.h>
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+
+#include "read_cgroupfs_xattr.skel.h"
+#include "cgroup_read_xattr.skel.h"
+
+#define CGROUP_FS_PARENT "foo/"
+#define CGROUP_FS_CHILD CGROUP_FS_PARENT "bar/"
+#define TMP_FILE "/tmp/selftests_cgroup_xattr"
+
+static const char xattr_value_a[] = "bpf_selftest_value_a";
+static const char xattr_value_b[] = "bpf_selftest_value_b";
+static const char xattr_name[] = "user.bpf_test";
+
+static void test_read_cgroup_xattr(void)
+{
+	int tmp_fd, parent_cgroup_fd = -1, child_cgroup_fd = -1;
+	struct read_cgroupfs_xattr *skel = NULL;
+
+	parent_cgroup_fd = test__join_cgroup(CGROUP_FS_PARENT);
+	if (!ASSERT_OK_FD(parent_cgroup_fd, "create parent cgroup"))
+		return;
+	if (!ASSERT_OK(set_cgroup_xattr(CGROUP_FS_PARENT, xattr_name, xattr_value_a),
+		       "set parent xattr"))
+		goto out;
+
+	child_cgroup_fd = test__join_cgroup(CGROUP_FS_CHILD);
+	if (!ASSERT_OK_FD(child_cgroup_fd, "create child cgroup"))
+		goto out;
+	if (!ASSERT_OK(set_cgroup_xattr(CGROUP_FS_CHILD, xattr_name, xattr_value_b),
+		       "set child xattr"))
+		goto out;
+
+	skel = read_cgroupfs_xattr__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "read_cgroupfs_xattr__open_and_load"))
+		goto out;
+
+	skel->bss->target_pid = sys_gettid();
+
+	if (!ASSERT_OK(read_cgroupfs_xattr__attach(skel), "read_cgroupfs_xattr__attach"))
+		goto out;
+
+	tmp_fd = open(TMP_FILE, O_RDONLY | O_CREAT);
+	ASSERT_OK_FD(tmp_fd, "open tmp file");
+	close(tmp_fd);
+
+	ASSERT_TRUE(skel->bss->found_value_a, "found_value_a");
+	ASSERT_TRUE(skel->bss->found_value_b, "found_value_b");
+
+out:
+	close(child_cgroup_fd);
+	close(parent_cgroup_fd);
+	read_cgroupfs_xattr__destroy(skel);
+	unlink(TMP_FILE);
+}
+
+void test_cgroup_xattr(void)
+{
+	RUN_TESTS(cgroup_read_xattr);
+
+	if (test__start_subtest("read_cgroupfs_xattr"))
+		test_read_cgroup_xattr();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c b/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c
index 973f0c5af965..4b42fbc96efc 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgrp_kfunc.c
@@ -4,13 +4,12 @@
 #define _GNU_SOURCE
 #include <cgroup_helpers.h>
 #include <test_progs.h>
+#include <sched.h>
+#include <sys/wait.h>
 
 #include "cgrp_kfunc_failure.skel.h"
 #include "cgrp_kfunc_success.skel.h"
 
-static size_t log_buf_sz = 1 << 20; /* 1 MB */
-static char obj_log_buf[1048576];
-
 static struct cgrp_kfunc_success *open_load_cgrp_kfunc_skel(void)
 {
 	struct cgrp_kfunc_success *skel;
@@ -87,65 +86,73 @@ static const char * const success_tests[] = {
 	"test_cgrp_xchg_release",
 	"test_cgrp_get_release",
 	"test_cgrp_get_ancestors",
+	"test_cgrp_from_id",
 };
 
-static struct {
-	const char *prog_name;
-	const char *expected_err_msg;
-} failure_tests[] = {
-	{"cgrp_kfunc_acquire_untrusted", "R1 must be referenced or trusted"},
-	{"cgrp_kfunc_acquire_fp", "arg#0 pointer type STRUCT cgroup must point"},
-	{"cgrp_kfunc_acquire_unsafe_kretprobe", "reg type unsupported for arg#0 function"},
-	{"cgrp_kfunc_acquire_trusted_walked", "R1 must be referenced or trusted"},
-	{"cgrp_kfunc_acquire_null", "arg#0 pointer type STRUCT cgroup must point"},
-	{"cgrp_kfunc_acquire_unreleased", "Unreleased reference"},
-	{"cgrp_kfunc_get_non_kptr_param", "arg#0 expected pointer to map value"},
-	{"cgrp_kfunc_get_non_kptr_acquired", "arg#0 expected pointer to map value"},
-	{"cgrp_kfunc_get_null", "arg#0 expected pointer to map value"},
-	{"cgrp_kfunc_xchg_unreleased", "Unreleased reference"},
-	{"cgrp_kfunc_get_unreleased", "Unreleased reference"},
-	{"cgrp_kfunc_release_untrusted", "arg#0 is untrusted_ptr_or_null_ expected ptr_ or socket"},
-	{"cgrp_kfunc_release_fp", "arg#0 pointer type STRUCT cgroup must point"},
-	{"cgrp_kfunc_release_null", "arg#0 is ptr_or_null_ expected ptr_ or socket"},
-	{"cgrp_kfunc_release_unacquired", "release kernel function bpf_cgroup_release expects"},
-};
-
-static void verify_fail(const char *prog_name, const char *expected_err_msg)
+static void test_cgrp_from_id_ns(void)
 {
-	LIBBPF_OPTS(bpf_object_open_opts, opts);
-	struct cgrp_kfunc_failure *skel;
-	int err, i;
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	struct cgrp_kfunc_success *skel;
+	struct bpf_program *prog;
+	int pid, pipe_fd[2];
 
-	opts.kernel_log_buf = obj_log_buf;
-	opts.kernel_log_size = log_buf_sz;
-	opts.kernel_log_level = 1;
+	skel = open_load_cgrp_kfunc_skel();
+	if (!ASSERT_OK_PTR(skel, "open_load_skel"))
+		return;
 
-	skel = cgrp_kfunc_failure__open_opts(&opts);
-	if (!ASSERT_OK_PTR(skel, "cgrp_kfunc_failure__open_opts"))
+	if (!ASSERT_OK(skel->bss->err, "pre_mkdir_err"))
 		goto cleanup;
 
-	for (i = 0; i < ARRAY_SIZE(failure_tests); i++) {
-		struct bpf_program *prog;
-		const char *curr_name = failure_tests[i].prog_name;
+	prog = skel->progs.test_cgrp_from_id_ns;
 
-		prog = bpf_object__find_program_by_name(skel->obj, curr_name);
-		if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
-			goto cleanup;
+	if (!ASSERT_OK(pipe(pipe_fd), "pipe"))
+		goto cleanup;
 
-		bpf_program__set_autoload(prog, !strcmp(curr_name, prog_name));
+	pid = fork();
+	if (!ASSERT_GE(pid, 0, "fork result")) {
+		close(pipe_fd[0]);
+		close(pipe_fd[1]);
+		goto cleanup;
 	}
 
-	err = cgrp_kfunc_failure__load(skel);
-	if (!ASSERT_ERR(err, "unexpected load success"))
-		goto cleanup;
+	if (pid == 0) {
+		int ret = 0;
+
+		close(pipe_fd[0]);
 
-	if (!ASSERT_OK_PTR(strstr(obj_log_buf, expected_err_msg), "expected_err_msg")) {
-		fprintf(stderr, "Expected err_msg: %s\n", expected_err_msg);
-		fprintf(stderr, "Verifier output: %s\n", obj_log_buf);
+		if (!ASSERT_GE(cgroup_setup_and_join("cgrp_from_id_ns"), 0, "join cgroup"))
+			exit(1);
+
+		if (!ASSERT_OK(unshare(CLONE_NEWCGROUP), "unshare cgns"))
+			exit(1);
+
+		ret = bpf_prog_test_run_opts(bpf_program__fd(prog), &opts);
+		if (!ASSERT_OK(ret, "test run ret"))
+			exit(1);
+
+		if (!ASSERT_OK(opts.retval, "test run retval"))
+			exit(1);
+
+		if (!ASSERT_EQ(write(pipe_fd[1], &ret, sizeof(ret)), sizeof(ret), "write pipe"))
+			exit(1);
+
+		exit(0);
+	} else {
+		int res;
+
+		close(pipe_fd[1]);
+
+		ASSERT_EQ(read(pipe_fd[0], &res, sizeof(res)), sizeof(res), "read res");
+		ASSERT_EQ(waitpid(pid, NULL, 0), pid, "wait on child");
+
+		remove_cgroup_pid("cgrp_from_id_ns", pid);
+
+		ASSERT_OK(res, "result from run");
 	}
 
+	close(pipe_fd[0]);
 cleanup:
-	cgrp_kfunc_failure__destroy(skel);
+	cgrp_kfunc_success__destroy(skel);
 }
 
 void test_cgrp_kfunc(void)
@@ -163,12 +170,10 @@ void test_cgrp_kfunc(void)
 		run_success_test(success_tests[i]);
 	}
 
-	for (i = 0; i < ARRAY_SIZE(failure_tests); i++) {
-		if (!test__start_subtest(failure_tests[i].prog_name))
-			continue;
+	if (test__start_subtest("test_cgrp_from_id_ns"))
+		test_cgrp_from_id_ns();
 
-		verify_fail(failure_tests[i].prog_name, failure_tests[i].expected_err_msg);
-	}
+	RUN_TESTS(cgrp_kfunc_failure);
 
 cleanup:
 	cleanup_cgroup_environment();
diff --git a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c
index 33a2776737e7..9015e2c2ab12 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c
@@ -16,9 +16,24 @@
 
 struct socket_cookie {
 	__u64 cookie_key;
-	__u32 cookie_value;
+	__u64 cookie_value;
 };
 
+static bool is_cgroup1;
+static int target_hid;
+
+#define CGROUP_MODE_SET(skel)			\
+{						\
+	skel->bss->is_cgroup1 = is_cgroup1;	\
+	skel->bss->target_hid = target_hid;	\
+}
+
+static void cgroup_mode_value_init(bool cgroup, int hid)
+{
+	is_cgroup1 = cgroup;
+	target_hid = hid;
+}
+
 static void test_tp_btf(int cgroup_fd)
 {
 	struct cgrp_ls_tp_btf *skel;
@@ -29,6 +44,8 @@ static void test_tp_btf(int cgroup_fd)
 	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
 		return;
 
+	CGROUP_MODE_SET(skel);
+
 	/* populate a value in map_b */
 	err = bpf_map_update_elem(bpf_map__fd(skel->maps.map_b), &cgroup_fd, &val1, BPF_ANY);
 	if (!ASSERT_OK(err, "map_update_elem"))
@@ -46,14 +63,14 @@ static void test_tp_btf(int cgroup_fd)
 	if (!ASSERT_OK(err, "map_delete_elem"))
 		goto out;
 
-	skel->bss->target_pid = syscall(SYS_gettid);
+	skel->bss->target_pid = sys_gettid();
 
 	err = cgrp_ls_tp_btf__attach(skel);
 	if (!ASSERT_OK(err, "skel_attach"))
 		goto out;
 
-	syscall(SYS_gettid);
-	syscall(SYS_gettid);
+	sys_gettid();
+	sys_gettid();
 
 	skel->bss->target_pid = 0;
 
@@ -130,12 +147,14 @@ static void test_recursion(int cgroup_fd)
 	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
 		return;
 
+	CGROUP_MODE_SET(skel);
+
 	err = cgrp_ls_recursion__attach(skel);
 	if (!ASSERT_OK(err, "skel_attach"))
 		goto out;
 
 	/* trigger sys_enter, make sure it does not cause deadlock */
-	syscall(SYS_gettid);
+	sys_gettid();
 
 out:
 	cgrp_ls_recursion__destroy(skel);
@@ -165,6 +184,8 @@ static void test_cgroup_iter_sleepable(int cgroup_fd, __u64 cgroup_id)
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
 		return;
 
+	CGROUP_MODE_SET(skel);
+
 	bpf_program__set_autoload(skel->progs.cgroup_iter, true);
 	err = cgrp_ls_sleepable__load(skel);
 	if (!ASSERT_OK(err, "skel_load"))
@@ -193,7 +214,7 @@ out:
 	cgrp_ls_sleepable__destroy(skel);
 }
 
-static void test_no_rcu_lock(__u64 cgroup_id)
+static void test_yes_rcu_lock(__u64 cgroup_id)
 {
 	struct cgrp_ls_sleepable *skel;
 	int err;
@@ -202,9 +223,10 @@ static void test_no_rcu_lock(__u64 cgroup_id)
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
 		return;
 
-	skel->bss->target_pid = syscall(SYS_gettid);
+	CGROUP_MODE_SET(skel);
+	skel->bss->target_pid = sys_gettid();
 
-	bpf_program__set_autoload(skel->progs.no_rcu_lock, true);
+	bpf_program__set_autoload(skel->progs.yes_rcu_lock, true);
 	err = cgrp_ls_sleepable__load(skel);
 	if (!ASSERT_OK(err, "skel_load"))
 		goto out;
@@ -220,7 +242,7 @@ out:
 	cgrp_ls_sleepable__destroy(skel);
 }
 
-static void test_rcu_lock(void)
+static void test_no_rcu_lock(void)
 {
 	struct cgrp_ls_sleepable *skel;
 	int err;
@@ -229,14 +251,34 @@ static void test_rcu_lock(void)
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
 		return;
 
-	bpf_program__set_autoload(skel->progs.yes_rcu_lock, true);
+	CGROUP_MODE_SET(skel);
+
+	bpf_program__set_autoload(skel->progs.no_rcu_lock, true);
 	err = cgrp_ls_sleepable__load(skel);
 	ASSERT_ERR(err, "skel_load");
 
 	cgrp_ls_sleepable__destroy(skel);
 }
 
-void test_cgrp_local_storage(void)
+static void test_cgrp1_no_rcu_lock(void)
+{
+	struct cgrp_ls_sleepable *skel;
+	int err;
+
+	skel = cgrp_ls_sleepable__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	CGROUP_MODE_SET(skel);
+
+	bpf_program__set_autoload(skel->progs.cgrp1_no_rcu_lock, true);
+	err = cgrp_ls_sleepable__load(skel);
+	ASSERT_OK(err, "skel_load");
+
+	cgrp_ls_sleepable__destroy(skel);
+}
+
+static void cgrp2_local_storage(void)
 {
 	__u64 cgroup_id;
 	int cgroup_fd;
@@ -245,6 +287,8 @@ void test_cgrp_local_storage(void)
 	if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup /cgrp_local_storage"))
 		return;
 
+	cgroup_mode_value_init(0, -1);
+
 	cgroup_id = get_cgroup_id("/cgrp_local_storage");
 	if (test__start_subtest("tp_btf"))
 		test_tp_btf(cgroup_fd);
@@ -256,10 +300,62 @@ void test_cgrp_local_storage(void)
 		test_negative();
 	if (test__start_subtest("cgroup_iter_sleepable"))
 		test_cgroup_iter_sleepable(cgroup_fd, cgroup_id);
+	if (test__start_subtest("yes_rcu_lock"))
+		test_yes_rcu_lock(cgroup_id);
 	if (test__start_subtest("no_rcu_lock"))
-		test_no_rcu_lock(cgroup_id);
-	if (test__start_subtest("rcu_lock"))
-		test_rcu_lock();
+		test_no_rcu_lock();
 
 	close(cgroup_fd);
 }
+
+static void cgrp1_local_storage(void)
+{
+	int cgrp1_fd, cgrp1_hid, cgrp1_id, err;
+
+	/* Setup cgroup1 hierarchy */
+	err = setup_classid_environment();
+	if (!ASSERT_OK(err, "setup_classid_environment"))
+		return;
+
+	err = join_classid();
+	if (!ASSERT_OK(err, "join_cgroup1"))
+		goto cleanup;
+
+	cgrp1_fd = open_classid();
+	if (!ASSERT_GE(cgrp1_fd, 0, "cgroup1 fd"))
+		goto cleanup;
+
+	cgrp1_id = get_classid_cgroup_id();
+	if (!ASSERT_GE(cgrp1_id, 0, "cgroup1 id"))
+		goto close_fd;
+
+	cgrp1_hid = get_cgroup1_hierarchy_id("net_cls");
+	if (!ASSERT_GE(cgrp1_hid, 0, "cgroup1 hid"))
+		goto close_fd;
+
+	cgroup_mode_value_init(1, cgrp1_hid);
+
+	if (test__start_subtest("cgrp1_tp_btf"))
+		test_tp_btf(cgrp1_fd);
+	if (test__start_subtest("cgrp1_recursion"))
+		test_recursion(cgrp1_fd);
+	if (test__start_subtest("cgrp1_negative"))
+		test_negative();
+	if (test__start_subtest("cgrp1_iter_sleepable"))
+		test_cgroup_iter_sleepable(cgrp1_fd, cgrp1_id);
+	if (test__start_subtest("cgrp1_yes_rcu_lock"))
+		test_yes_rcu_lock(cgrp1_id);
+	if (test__start_subtest("cgrp1_no_rcu_lock"))
+		test_cgrp1_no_rcu_lock();
+
+close_fd:
+	close(cgrp1_fd);
+cleanup:
+	cleanup_classid_environment();
+}
+
+void test_cgrp_local_storage(void)
+{
+	cgrp2_local_storage();
+	cgrp1_local_storage();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/check_mtu.c b/tools/testing/selftests/bpf/prog_tests/check_mtu.c
index 12f4395f18b3..65b4512967e7 100644
--- a/tools/testing/selftests/bpf/prog_tests/check_mtu.c
+++ b/tools/testing/selftests/bpf/prog_tests/check_mtu.c
@@ -59,7 +59,7 @@ static void test_check_mtu_xdp_attach(void)
 
 	memset(&link_info, 0, sizeof(link_info));
 	fd = bpf_link__fd(link);
-	err = bpf_obj_get_info_by_fd(fd, &link_info, &link_info_len);
+	err = bpf_link_get_info_by_fd(fd, &link_info, &link_info_len);
 	if (CHECK(err, "link_info", "failed: %d\n", err))
 		goto out;
 
@@ -153,6 +153,26 @@ static void test_check_mtu_run_tc(struct test_check_mtu *skel,
 	ASSERT_EQ(mtu_result, mtu_expect, "MTU-compare-user");
 }
 
+static void test_chk_segs_flag(struct test_check_mtu *skel, __u32 mtu)
+{
+	int err, prog_fd = bpf_program__fd(skel->progs.tc_chk_segs_flag);
+	struct __sk_buff skb = {
+		.gso_size = 10,
+	};
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .ctx_in = &skb,
+		    .ctx_size_in = sizeof(skb),
+	);
+
+	/* Lower the mtu to test the BPF_MTU_CHK_SEGS */
+	SYS_NOFAIL("ip link set dev lo mtu 10");
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	SYS_NOFAIL("ip link set dev lo mtu %u", mtu);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(topts.retval, BPF_OK, "retval");
+}
 
 static void test_check_mtu_tc(__u32 mtu, __u32 ifindex)
 {
@@ -177,13 +197,14 @@ static void test_check_mtu_tc(__u32 mtu, __u32 ifindex)
 	test_check_mtu_run_tc(skel, skel->progs.tc_minus_delta, mtu);
 	test_check_mtu_run_tc(skel, skel->progs.tc_input_len, mtu);
 	test_check_mtu_run_tc(skel, skel->progs.tc_input_len_exceed, mtu);
+	test_chk_segs_flag(skel, mtu);
 cleanup:
 	test_check_mtu__destroy(skel);
 }
 
-void serial_test_check_mtu(void)
+void test_ns_check_mtu(void)
 {
-	__u32 mtu_lo;
+	int mtu_lo;
 
 	if (test__start_subtest("bpf_check_mtu XDP-attach"))
 		test_check_mtu_xdp_attach();
diff --git a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c
index 224f016b0a53..7488a7606e6a 100644
--- a/tools/testing/selftests/bpf/prog_tests/cls_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/cls_redirect.c
@@ -10,9 +10,11 @@
 #include <netinet/tcp.h>
 
 #include <test_progs.h>
+#include "network_helpers.h"
 
 #include "progs/test_cls_redirect.h"
 #include "test_cls_redirect.skel.h"
+#include "test_cls_redirect_dynptr.skel.h"
 #include "test_cls_redirect_subprogs.skel.h"
 
 #define ENCAP_IP INADDR_LOOPBACK
@@ -20,112 +22,37 @@
 
 static int duration = 0;
 
-struct addr_port {
-	in_port_t port;
-	union {
-		struct in_addr in_addr;
-		struct in6_addr in6_addr;
-	};
-};
-
-struct tuple {
-	int family;
-	struct addr_port src;
-	struct addr_port dst;
-};
-
-static int start_server(const struct sockaddr *addr, socklen_t len, int type)
-{
-	int fd = socket(addr->sa_family, type, 0);
-	if (CHECK_FAIL(fd == -1))
-		return -1;
-	if (CHECK_FAIL(bind(fd, addr, len) == -1))
-		goto err;
-	if (type == SOCK_STREAM && CHECK_FAIL(listen(fd, 128) == -1))
-		goto err;
-
-	return fd;
-
-err:
-	close(fd);
-	return -1;
-}
-
-static int connect_to_server(const struct sockaddr *addr, socklen_t len,
-			     int type)
-{
-	int fd = socket(addr->sa_family, type, 0);
-	if (CHECK_FAIL(fd == -1))
-		return -1;
-	if (CHECK_FAIL(connect(fd, addr, len)))
-		goto err;
-
-	return fd;
-
-err:
-	close(fd);
-	return -1;
-}
-
-static bool fill_addr_port(const struct sockaddr *sa, struct addr_port *ap)
-{
-	const struct sockaddr_in6 *in6;
-	const struct sockaddr_in *in;
-
-	switch (sa->sa_family) {
-	case AF_INET:
-		in = (const struct sockaddr_in *)sa;
-		ap->in_addr = in->sin_addr;
-		ap->port = in->sin_port;
-		return true;
-
-	case AF_INET6:
-		in6 = (const struct sockaddr_in6 *)sa;
-		ap->in6_addr = in6->sin6_addr;
-		ap->port = in6->sin6_port;
-		return true;
-
-	default:
-		return false;
-	}
-}
 
-static bool set_up_conn(const struct sockaddr *addr, socklen_t len, int type,
-			int *server, int *conn, struct tuple *tuple)
+static bool set_up_conn(const struct sockaddr_storage *addr, socklen_t len, int type,
+			int *server, int *conn,
+			struct sockaddr_storage *src,
+			struct sockaddr_storage *dst)
 {
 	struct sockaddr_storage ss;
 	socklen_t slen = sizeof(ss);
-	struct sockaddr *sa = (struct sockaddr *)&ss;
 
-	*server = start_server(addr, len, type);
+	*server = start_server_addr(type, addr, len, NULL);
 	if (*server < 0)
 		return false;
 
-	if (CHECK_FAIL(getsockname(*server, sa, &slen)))
+	if (CHECK_FAIL(getsockname(*server, (struct sockaddr *)&ss, &slen)))
 		goto close_server;
 
-	*conn = connect_to_server(sa, slen, type);
+	*conn = connect_to_addr(type, &ss, slen, NULL);
 	if (*conn < 0)
 		goto close_server;
 
 	/* We want to simulate packets arriving at conn, so we have to
 	 * swap src and dst.
 	 */
-	slen = sizeof(ss);
-	if (CHECK_FAIL(getsockname(*conn, sa, &slen)))
+	slen = sizeof(*dst);
+	if (CHECK_FAIL(getsockname(*conn, (struct sockaddr *)dst, &slen)))
 		goto close_conn;
 
-	if (CHECK_FAIL(!fill_addr_port(sa, &tuple->dst)))
+	slen = sizeof(*src);
+	if (CHECK_FAIL(getpeername(*conn, (struct sockaddr *)src, &slen)))
 		goto close_conn;
 
-	slen = sizeof(ss);
-	if (CHECK_FAIL(getpeername(*conn, sa, &slen)))
-		goto close_conn;
-
-	if (CHECK_FAIL(!fill_addr_port(sa, &tuple->src)))
-		goto close_conn;
-
-	tuple->family = ss.ss_family;
 	return true;
 
 close_conn:
@@ -141,17 +68,16 @@ static socklen_t prepare_addr(struct sockaddr_storage *addr, int family)
 {
 	struct sockaddr_in *addr4;
 	struct sockaddr_in6 *addr6;
+	memset(addr, 0, sizeof(*addr));
 
 	switch (family) {
 	case AF_INET:
 		addr4 = (struct sockaddr_in *)addr;
-		memset(addr4, 0, sizeof(*addr4));
 		addr4->sin_family = family;
 		addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK);
 		return sizeof(*addr4);
 	case AF_INET6:
 		addr6 = (struct sockaddr_in6 *)addr;
-		memset(addr6, 0, sizeof(*addr6));
 		addr6->sin6_family = family;
 		addr6->sin6_addr = in6addr_loopback;
 		return sizeof(*addr6);
@@ -273,9 +199,15 @@ static void encap_init(encap_headers_t *encap, uint8_t hop_count, uint8_t proto)
 }
 
 static size_t build_input(const struct test_cfg *test, void *const buf,
-			  const struct tuple *tuple)
+			  const struct sockaddr_storage *src,
+			  const struct sockaddr_storage *dst)
 {
-	in_port_t sport = tuple->src.port;
+	struct sockaddr_in6 *src_in6 = (struct sockaddr_in6 *)src;
+	struct sockaddr_in6 *dst_in6 = (struct sockaddr_in6 *)dst;
+	struct sockaddr_in *src_in = (struct sockaddr_in *)src;
+	struct sockaddr_in *dst_in = (struct sockaddr_in *)dst;
+	sa_family_t family = src->ss_family;
+	in_port_t sport, dport;
 	encap_headers_t encap;
 	struct iphdr ip;
 	struct ipv6hdr ipv6;
@@ -285,8 +217,11 @@ static size_t build_input(const struct test_cfg *test, void *const buf,
 	uint8_t *p = buf;
 	int proto;
 
+	sport = (family == AF_INET) ? src_in->sin_port : src_in6->sin6_port;
+	dport = (family == AF_INET) ? dst_in->sin_port : dst_in6->sin6_port;
+
 	proto = IPPROTO_IPIP;
-	if (tuple->family == AF_INET6)
+	if (family == AF_INET6)
 		proto = IPPROTO_IPV6;
 
 	encap_init(&encap, test->hops == ONE_HOP ? 1 : 0, proto);
@@ -301,15 +236,15 @@ static size_t build_input(const struct test_cfg *test, void *const buf,
 	if (test->type == UDP)
 		proto = IPPROTO_UDP;
 
-	switch (tuple->family) {
+	switch (family) {
 	case AF_INET:
 		ip = (struct iphdr){
 			.ihl = 5,
 			.version = 4,
 			.ttl = IPDEFTTL,
 			.protocol = proto,
-			.saddr = tuple->src.in_addr.s_addr,
-			.daddr = tuple->dst.in_addr.s_addr,
+			.saddr = src_in->sin_addr.s_addr,
+			.daddr = dst_in->sin_addr.s_addr,
 		};
 		p = mempcpy(p, &ip, sizeof(ip));
 		break;
@@ -318,8 +253,8 @@ static size_t build_input(const struct test_cfg *test, void *const buf,
 			.version = 6,
 			.hop_limit = IPDEFTTL,
 			.nexthdr = proto,
-			.saddr = tuple->src.in6_addr,
-			.daddr = tuple->dst.in6_addr,
+			.saddr = src_in6->sin6_addr,
+			.daddr = dst_in6->sin6_addr,
 		};
 		p = mempcpy(p, &ipv6, sizeof(ipv6));
 		break;
@@ -334,18 +269,16 @@ static size_t build_input(const struct test_cfg *test, void *const buf,
 	case TCP:
 		tcp = (struct tcphdr){
 			.source = sport,
-			.dest = tuple->dst.port,
+			.dest = dport,
+			.syn = (test->flags == SYN),
+			.ack = (test->flags == ACK),
 		};
-		if (test->flags == SYN)
-			tcp.syn = true;
-		if (test->flags == ACK)
-			tcp.ack = true;
 		p = mempcpy(p, &tcp, sizeof(tcp));
 		break;
 	case UDP:
 		udp = (struct udphdr){
 			.source = sport,
-			.dest = tuple->dst.port,
+			.dest = dport,
 		};
 		p = mempcpy(p, &udp, sizeof(udp));
 		break;
@@ -370,27 +303,26 @@ static void test_cls_redirect_common(struct bpf_program *prog)
 	LIBBPF_OPTS(bpf_test_run_opts, tattr);
 	int families[] = { AF_INET, AF_INET6 };
 	struct sockaddr_storage ss;
-	struct sockaddr *addr;
 	socklen_t slen;
 	int i, j, err, prog_fd;
 	int servers[__NR_KIND][ARRAY_SIZE(families)] = {};
 	int conns[__NR_KIND][ARRAY_SIZE(families)] = {};
-	struct tuple tuples[__NR_KIND][ARRAY_SIZE(families)];
+	struct sockaddr_storage srcs[__NR_KIND][ARRAY_SIZE(families)];
+	struct sockaddr_storage dsts[__NR_KIND][ARRAY_SIZE(families)];
 
-	addr = (struct sockaddr *)&ss;
 	for (i = 0; i < ARRAY_SIZE(families); i++) {
 		slen = prepare_addr(&ss, families[i]);
 		if (CHECK_FAIL(!slen))
 			goto cleanup;
 
-		if (CHECK_FAIL(!set_up_conn(addr, slen, SOCK_DGRAM,
+		if (CHECK_FAIL(!set_up_conn(&ss, slen, SOCK_DGRAM,
 					    &servers[UDP][i], &conns[UDP][i],
-					    &tuples[UDP][i])))
+					    &srcs[UDP][i], &dsts[UDP][i])))
 			goto cleanup;
 
-		if (CHECK_FAIL(!set_up_conn(addr, slen, SOCK_STREAM,
+		if (CHECK_FAIL(!set_up_conn(&ss, slen, SOCK_STREAM,
 					    &servers[TCP][i], &conns[TCP][i],
-					    &tuples[TCP][i])))
+					    &srcs[TCP][i], &dsts[TCP][i])))
 			goto cleanup;
 	}
 
@@ -399,11 +331,12 @@ static void test_cls_redirect_common(struct bpf_program *prog)
 		struct test_cfg *test = &tests[i];
 
 		for (j = 0; j < ARRAY_SIZE(families); j++) {
-			struct tuple *tuple = &tuples[test->type][j];
+			struct sockaddr_storage *src = &srcs[test->type][j];
+			struct sockaddr_storage *dst = &dsts[test->type][j];
 			char input[256];
 			char tmp[256];
 
-			test_str(tmp, sizeof(tmp), test, tuple->family);
+			test_str(tmp, sizeof(tmp), test, families[j]);
 			if (!test__start_subtest(tmp))
 				continue;
 
@@ -411,7 +344,7 @@ static void test_cls_redirect_common(struct bpf_program *prog)
 			tattr.data_size_out = sizeof(tmp);
 
 			tattr.data_in = input;
-			tattr.data_size_in = build_input(test, input, tuple);
+			tattr.data_size_in = build_input(test, input, src, dst);
 			if (CHECK_FAIL(!tattr.data_size_in))
 				continue;
 
@@ -446,6 +379,28 @@ cleanup:
 	close_fds((int *)conns, sizeof(conns) / sizeof(conns[0][0]));
 }
 
+static void test_cls_redirect_dynptr(void)
+{
+	struct test_cls_redirect_dynptr *skel;
+	int err;
+
+	skel = test_cls_redirect_dynptr__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	skel->rodata->ENCAPSULATION_IP = htonl(ENCAP_IP);
+	skel->rodata->ENCAPSULATION_PORT = htons(ENCAP_PORT);
+
+	err = test_cls_redirect_dynptr__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	test_cls_redirect_common(skel->progs.cls_redirect);
+
+cleanup:
+	test_cls_redirect_dynptr__destroy(skel);
+}
+
 static void test_cls_redirect_inlined(void)
 {
 	struct test_cls_redirect *skel;
@@ -496,4 +451,6 @@ void test_cls_redirect(void)
 		test_cls_redirect_inlined();
 	if (test__start_subtest("cls_redirect_subprogs"))
 		test_cls_redirect_subprogs();
+	if (test__start_subtest("cls_redirect_dynptr"))
+		test_cls_redirect_dynptr();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/compute_live_registers.c b/tools/testing/selftests/bpf/prog_tests/compute_live_registers.c
new file mode 100644
index 000000000000..285f20241fe1
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/compute_live_registers.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "compute_live_registers.skel.h"
+#include "test_progs.h"
+
+void test_compute_live_registers(void)
+{
+	RUN_TESTS(compute_live_registers);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/connect_ping.c b/tools/testing/selftests/bpf/prog_tests/connect_ping.c
index 289218c2216c..40fe571f2fe7 100644
--- a/tools/testing/selftests/bpf/prog_tests/connect_ping.c
+++ b/tools/testing/selftests/bpf/prog_tests/connect_ping.c
@@ -28,9 +28,9 @@ static void subtest(int cgroup_fd, struct connect_ping *skel,
 		.sin6_family = AF_INET6,
 		.sin6_addr = IN6ADDR_LOOPBACK_INIT,
 	};
-	struct sockaddr *sa;
+	struct sockaddr *sa = NULL;
 	socklen_t sa_len;
-	int protocol;
+	int protocol = -1;
 	int sock_fd;
 
 	switch (family) {
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 47f42e680105..08963c82f30b 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
 #include <test_progs.h>
 #include "progs/core_reloc_types.h"
-#include "bpf_testmod/bpf_testmod.h"
+#include "test_kmods/bpf_testmod.h"
 #include <linux/limits.h>
 #include <sys/mman.h>
 #include <sys/syscall.h>
@@ -84,11 +85,11 @@ static int duration = 0;
 #define NESTING_ERR_CASE(name) {					\
 	NESTING_CASE_COMMON(name),					\
 	.fails = true,							\
-	.run_btfgen_fails = true,							\
+	.run_btfgen_fails = true,					\
 }
 
 #define ARRAYS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) {	\
-	.a = { [2] = 1 },						\
+	.a = { [2] = 1, [3] = 11 },					\
 	.b = { [1] = { [2] = { [3] = 2 } } },				\
 	.c = { [1] = { .c =  3 } },					\
 	.d = { [0] = { [0] = { .d = 4 } } },				\
@@ -107,6 +108,7 @@ static int duration = 0;
 	.input_len = sizeof(struct core_reloc_##name),			\
 	.output = STRUCT_TO_CHAR_PTR(core_reloc_arrays_output) {	\
 		.a2   = 1,						\
+		.a3   = 12,						\
 		.b123 = 2,						\
 		.c1c  = 3,						\
 		.d00d = 4,						\
@@ -601,6 +603,7 @@ static const struct core_reloc_test_case test_cases[] = {
 	ARRAYS_ERR_CASE(arrays___err_non_array),
 	ARRAYS_ERR_CASE(arrays___err_wrong_val_type),
 	ARRAYS_ERR_CASE(arrays___err_bad_zero_sz_arr),
+	ARRAYS_ERR_CASE(arrays___err_bad_signed_arr_elem_sz),
 
 	/* enum/ptr/int handling scenarios */
 	PRIMITIVES_CASE(primitives),
@@ -1009,7 +1012,7 @@ static void run_core_reloc_tests(bool use_btfgen)
 	struct data *data;
 	void *mmap_data = NULL;
 
-	my_pid_tgid = getpid() | ((uint64_t)syscall(SYS_gettid) << 32);
+	my_pid_tgid = getpid() | ((uint64_t)sys_gettid() << 32);
 
 	for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
 		char btf_file[] = "/tmp/core_reloc.btf.XXXXXX";
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc_raw.c b/tools/testing/selftests/bpf/prog_tests/core_reloc_raw.c
new file mode 100644
index 000000000000..a18d3680fb16
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc_raw.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Test cases that can't load programs using libbpf and need direct
+ * BPF syscall access
+ */
+
+#include <sys/syscall.h>
+#include <bpf/libbpf.h>
+#include <bpf/btf.h>
+
+#include "test_progs.h"
+#include "test_btf.h"
+#include "bpf/libbpf_internal.h"
+
+static char log[16 * 1024];
+
+/* Check that verifier rejects BPF program containing relocation
+ * pointing to non-existent BTF type.
+ */
+static void test_bad_local_id(void)
+{
+	struct test_btf {
+		struct btf_header hdr;
+		__u32 types[15];
+		char strings[128];
+	} raw_btf = {
+		.hdr = {
+			.magic = BTF_MAGIC,
+			.version = BTF_VERSION,
+			.hdr_len = sizeof(struct btf_header),
+			.type_off = 0,
+			.type_len = sizeof(raw_btf.types),
+			.str_off = offsetof(struct test_btf, strings) -
+				   offsetof(struct test_btf, types),
+			.str_len = sizeof(raw_btf.strings),
+		},
+		.types = {
+			BTF_PTR_ENC(0),					/* [1] void*  */
+			BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4),	/* [2] int    */
+			BTF_FUNC_PROTO_ENC(2, 1),			/* [3] int (*)(void*) */
+			BTF_FUNC_PROTO_ARG_ENC(8, 1),
+			BTF_FUNC_ENC(8, 3)			/* [4] FUNC 'foo' type_id=2   */
+		},
+		.strings = "\0int\0 0\0foo\0"
+	};
+	__u32 log_level = 1 | 2 | 4;
+	LIBBPF_OPTS(bpf_btf_load_opts, opts,
+		    .log_buf = log,
+		    .log_size = sizeof(log),
+		    .log_level = log_level,
+	);
+	struct bpf_insn insns[] = {
+		BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	struct bpf_func_info funcs[] = {
+		{
+			.insn_off = 0,
+			.type_id = 4,
+		}
+	};
+	struct bpf_core_relo relos[] = {
+		{
+			.insn_off = 0,		/* patch first instruction (r0 = 0) */
+			.type_id = 100500,	/* !!! this type id does not exist */
+			.access_str_off = 6,	/* offset of "0" */
+			.kind = BPF_CORE_TYPE_ID_LOCAL,
+		}
+	};
+	union bpf_attr attr;
+	int saved_errno;
+	int prog_fd = -1;
+	int btf_fd = -1;
+
+	btf_fd = bpf_btf_load(&raw_btf, sizeof(raw_btf), &opts);
+	saved_errno = errno;
+	if (btf_fd < 0 || env.verbosity > VERBOSE_NORMAL) {
+		printf("-------- BTF load log start --------\n");
+		printf("%s", log);
+		printf("-------- BTF load log end ----------\n");
+	}
+	if (btf_fd < 0) {
+		PRINT_FAIL("bpf_btf_load() failed, errno=%d\n", saved_errno);
+		return;
+	}
+
+	log[0] = 0;
+	memset(&attr, 0, sizeof(attr));
+	attr.prog_btf_fd = btf_fd;
+	attr.prog_type = BPF_TRACE_RAW_TP;
+	attr.license = (__u64)"GPL";
+	attr.insns = (__u64)&insns;
+	attr.insn_cnt = sizeof(insns) / sizeof(*insns);
+	attr.log_buf = (__u64)log;
+	attr.log_size = sizeof(log);
+	attr.log_level = log_level;
+	attr.func_info = (__u64)funcs;
+	attr.func_info_cnt = sizeof(funcs) / sizeof(*funcs);
+	attr.func_info_rec_size = sizeof(*funcs);
+	attr.core_relos = (__u64)relos;
+	attr.core_relo_cnt = sizeof(relos) / sizeof(*relos);
+	attr.core_relo_rec_size = sizeof(*relos);
+	prog_fd = sys_bpf_prog_load(&attr, sizeof(attr), 1);
+	saved_errno = errno;
+	if (prog_fd < 0 || env.verbosity > VERBOSE_NORMAL) {
+		printf("-------- program load log start --------\n");
+		printf("%s", log);
+		printf("-------- program load log end ----------\n");
+	}
+	if (prog_fd >= 0) {
+		PRINT_FAIL("sys_bpf_prog_load() expected to fail\n");
+		goto out;
+	}
+	ASSERT_HAS_SUBSTR(log, "relo #0: bad type id 100500", "program load log");
+
+out:
+	close(prog_fd);
+	close(btf_fd);
+}
+
+void test_core_reloc_raw(void)
+{
+	if (test__start_subtest("bad_local_id"))
+		test_bad_local_id();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cpumask.c b/tools/testing/selftests/bpf/prog_tests/cpumask.c
new file mode 100644
index 000000000000..6c45330a5ca3
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cpumask.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <test_progs.h>
+#include "cpumask_failure.skel.h"
+#include "cpumask_success.skel.h"
+
+static const char * const cpumask_success_testcases[] = {
+	"test_alloc_free_cpumask",
+	"test_set_clear_cpu",
+	"test_setall_clear_cpu",
+	"test_first_firstzero_cpu",
+	"test_firstand_nocpu",
+	"test_test_and_set_clear",
+	"test_and_or_xor",
+	"test_intersects_subset",
+	"test_copy_any_anyand",
+	"test_insert_leave",
+	"test_insert_remove_release",
+	"test_global_mask_rcu",
+	"test_global_mask_array_one_rcu",
+	"test_global_mask_array_rcu",
+	"test_global_mask_array_l2_rcu",
+	"test_global_mask_nested_rcu",
+	"test_global_mask_nested_deep_rcu",
+	"test_global_mask_nested_deep_array_rcu",
+	"test_cpumask_weight",
+	"test_refcount_null_tracking",
+	"test_populate_reject_small_mask",
+	"test_populate_reject_unaligned",
+	"test_populate",
+};
+
+static void verify_success(const char *prog_name)
+{
+	struct cpumask_success *skel;
+	struct bpf_program *prog;
+	struct bpf_link *link = NULL;
+	pid_t child_pid;
+	int status, err;
+
+	skel = cpumask_success__open();
+	if (!ASSERT_OK_PTR(skel, "cpumask_success__open"))
+		return;
+
+	skel->bss->pid = getpid();
+	skel->bss->nr_cpus = libbpf_num_possible_cpus();
+
+	err = cpumask_success__load(skel);
+	if (!ASSERT_OK(err, "cpumask_success__load"))
+		goto cleanup;
+
+	prog = bpf_object__find_program_by_name(skel->obj, prog_name);
+	if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
+		goto cleanup;
+
+	link = bpf_program__attach(prog);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach"))
+		goto cleanup;
+
+	child_pid = fork();
+	if (!ASSERT_GT(child_pid, -1, "child_pid"))
+		goto cleanup;
+	if (child_pid == 0)
+		_exit(0);
+	waitpid(child_pid, &status, 0);
+	ASSERT_OK(skel->bss->err, "post_wait_err");
+
+cleanup:
+	bpf_link__destroy(link);
+	cpumask_success__destroy(skel);
+}
+
+void test_cpumask(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(cpumask_success_testcases); i++) {
+		if (!test__start_subtest(cpumask_success_testcases[i]))
+			continue;
+
+		verify_success(cpumask_success_testcases[i]);
+	}
+
+	RUN_TESTS(cpumask_failure);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/crypto_sanity.c b/tools/testing/selftests/bpf/prog_tests/crypto_sanity.c
new file mode 100644
index 000000000000..42bd07f7218d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/crypto_sanity.c
@@ -0,0 +1,196 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <net/if.h>
+#include <linux/if_alg.h>
+
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "crypto_sanity.skel.h"
+#include "crypto_basic.skel.h"
+
+#define NS_TEST "crypto_sanity_ns"
+#define IPV6_IFACE_ADDR "face::1"
+static const unsigned char crypto_key[] = "testtest12345678";
+static const char plain_text[] = "stringtoencrypt0";
+static int opfd = -1, tfmfd = -1;
+static const char algo[] = "ecb(aes)";
+static int init_afalg(void)
+{
+	struct sockaddr_alg sa = {
+		.salg_family = AF_ALG,
+		.salg_type = "skcipher",
+		.salg_name = "ecb(aes)"
+	};
+
+	tfmfd = socket(AF_ALG, SOCK_SEQPACKET, 0);
+	if (tfmfd == -1)
+		return errno;
+	if (bind(tfmfd, (struct sockaddr *)&sa, sizeof(sa)) == -1)
+		return errno;
+	if (setsockopt(tfmfd, SOL_ALG, ALG_SET_KEY, crypto_key, 16) == -1)
+		return errno;
+	opfd = accept(tfmfd, NULL, 0);
+	if (opfd == -1)
+		return errno;
+	return 0;
+}
+
+static void deinit_afalg(void)
+{
+	if (tfmfd != -1)
+		close(tfmfd);
+	if (opfd != -1)
+		close(opfd);
+}
+
+static void do_crypt_afalg(const void *src, void *dst, int size, bool encrypt)
+{
+	struct msghdr msg = {};
+	struct cmsghdr *cmsg;
+	char cbuf[CMSG_SPACE(4)] = {0};
+	struct iovec iov;
+
+	msg.msg_control = cbuf;
+	msg.msg_controllen = sizeof(cbuf);
+
+	cmsg = CMSG_FIRSTHDR(&msg);
+	cmsg->cmsg_level = SOL_ALG;
+	cmsg->cmsg_type = ALG_SET_OP;
+	cmsg->cmsg_len = CMSG_LEN(4);
+	*(__u32 *)CMSG_DATA(cmsg) = encrypt ? ALG_OP_ENCRYPT : ALG_OP_DECRYPT;
+
+	iov.iov_base = (char *)src;
+	iov.iov_len = size;
+
+	msg.msg_iov = &iov;
+	msg.msg_iovlen = 1;
+
+	sendmsg(opfd, &msg, 0);
+	read(opfd, dst, size);
+}
+
+void test_crypto_basic(void)
+{
+	RUN_TESTS(crypto_basic);
+}
+
+void test_crypto_sanity(void)
+{
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_hook, .attach_point = BPF_TC_EGRESS);
+	LIBBPF_OPTS(bpf_tc_opts, tc_attach_enc);
+	LIBBPF_OPTS(bpf_tc_opts, tc_attach_dec);
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	struct nstoken *nstoken = NULL;
+	struct crypto_sanity *skel;
+	char afalg_plain[16] = {0};
+	char afalg_dst[16] = {0};
+	struct sockaddr_in6 addr;
+	int sockfd, err, pfd;
+	socklen_t addrlen;
+	u16 udp_test_port;
+
+	skel = crypto_sanity__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel open"))
+		return;
+
+	SYS(fail, "ip netns add %s", NS_TEST);
+	SYS(fail, "ip -net %s -6 addr add %s/128 dev lo nodad", NS_TEST, IPV6_IFACE_ADDR);
+	SYS(fail, "ip -net %s link set dev lo up", NS_TEST);
+
+	nstoken = open_netns(NS_TEST);
+	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+		goto fail;
+
+	err = init_afalg();
+	if (!ASSERT_OK(err, "AF_ALG init fail"))
+		goto fail;
+
+	qdisc_hook.ifindex = if_nametoindex("lo");
+	if (!ASSERT_GT(qdisc_hook.ifindex, 0, "if_nametoindex lo"))
+		goto fail;
+
+	skel->bss->key_len = 16;
+	skel->bss->authsize = 0;
+	udp_test_port = skel->data->udp_test_port;
+	memcpy(skel->bss->key, crypto_key, sizeof(crypto_key));
+	snprintf(skel->bss->algo, 128, "%s", algo);
+	pfd = bpf_program__fd(skel->progs.skb_crypto_setup);
+	if (!ASSERT_GT(pfd, 0, "skb_crypto_setup fd"))
+		goto fail;
+
+	err = bpf_prog_test_run_opts(pfd, &opts);
+	if (!ASSERT_OK(err, "skb_crypto_setup") ||
+	    !ASSERT_OK(opts.retval, "skb_crypto_setup retval"))
+		goto fail;
+
+	if (!ASSERT_OK(skel->bss->status, "skb_crypto_setup status"))
+		goto fail;
+
+	err = bpf_tc_hook_create(&qdisc_hook);
+	if (!ASSERT_OK(err, "create qdisc hook"))
+		goto fail;
+
+	addrlen = sizeof(addr);
+	err = make_sockaddr(AF_INET6, IPV6_IFACE_ADDR, udp_test_port,
+			    (void *)&addr, &addrlen);
+	if (!ASSERT_OK(err, "make_sockaddr"))
+		goto fail;
+
+	tc_attach_enc.prog_fd = bpf_program__fd(skel->progs.encrypt_sanity);
+	err = bpf_tc_attach(&qdisc_hook, &tc_attach_enc);
+	if (!ASSERT_OK(err, "attach encrypt filter"))
+		goto fail;
+
+	sockfd = socket(AF_INET6, SOCK_DGRAM, 0);
+	if (!ASSERT_NEQ(sockfd, -1, "encrypt socket"))
+		goto fail;
+	err = sendto(sockfd, plain_text, sizeof(plain_text), 0, (void *)&addr, addrlen);
+	close(sockfd);
+	if (!ASSERT_EQ(err, sizeof(plain_text), "encrypt send"))
+		goto fail;
+
+	do_crypt_afalg(plain_text, afalg_dst, sizeof(afalg_dst), true);
+
+	if (!ASSERT_OK(skel->bss->status, "encrypt status"))
+		goto fail;
+	if (!ASSERT_STRNEQ(skel->bss->dst, afalg_dst, sizeof(afalg_dst), "encrypt AF_ALG"))
+		goto fail;
+
+	tc_attach_enc.flags = tc_attach_enc.prog_fd = tc_attach_enc.prog_id = 0;
+	err = bpf_tc_detach(&qdisc_hook, &tc_attach_enc);
+	if (!ASSERT_OK(err, "bpf_tc_detach encrypt"))
+		goto fail;
+
+	tc_attach_dec.prog_fd = bpf_program__fd(skel->progs.decrypt_sanity);
+	err = bpf_tc_attach(&qdisc_hook, &tc_attach_dec);
+	if (!ASSERT_OK(err, "attach decrypt filter"))
+		goto fail;
+
+	sockfd = socket(AF_INET6, SOCK_DGRAM, 0);
+	if (!ASSERT_NEQ(sockfd, -1, "decrypt socket"))
+		goto fail;
+	err = sendto(sockfd, afalg_dst, sizeof(afalg_dst), 0, (void *)&addr, addrlen);
+	close(sockfd);
+	if (!ASSERT_EQ(err, sizeof(afalg_dst), "decrypt send"))
+		goto fail;
+
+	do_crypt_afalg(afalg_dst, afalg_plain, sizeof(afalg_plain), false);
+
+	if (!ASSERT_OK(skel->bss->status, "decrypt status"))
+		goto fail;
+	if (!ASSERT_STRNEQ(skel->bss->dst, afalg_plain, sizeof(afalg_plain), "decrypt AF_ALG"))
+		goto fail;
+
+	tc_attach_dec.flags = tc_attach_dec.prog_fd = tc_attach_dec.prog_id = 0;
+	err = bpf_tc_detach(&qdisc_hook, &tc_attach_dec);
+	ASSERT_OK(err, "bpf_tc_detach decrypt");
+
+fail:
+	close_netns(nstoken);
+	deinit_afalg();
+	SYS_NOFAIL("ip netns del " NS_TEST " &> /dev/null");
+	crypto_sanity__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c
new file mode 100644
index 000000000000..dd75ccb03770
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c
@@ -0,0 +1,821 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <limits.h>
+#include <stdio.h>
+#include <string.h>
+#include <ctype.h>
+#include <regex.h>
+#include <test_progs.h>
+
+#include "bpf/btf.h"
+#include "bpf_util.h"
+#include "linux/filter.h"
+#include "linux/kernel.h"
+#include "disasm_helpers.h"
+
+#define MAX_PROG_TEXT_SZ (32 * 1024)
+
+/* The code in this file serves the sole purpose of executing test cases
+ * specified in the test_cases array. Each test case specifies a program
+ * type, context field offset, and disassembly patterns that correspond
+ * to read and write instructions generated by
+ * verifier.c:convert_ctx_access() for accessing that field.
+ *
+ * For each test case, up to three programs are created:
+ * - One that uses BPF_LDX_MEM to read the context field.
+ * - One that uses BPF_STX_MEM to write to the context field.
+ * - One that uses BPF_ST_MEM to write to the context field.
+ *
+ * The disassembly of each program is then compared with the pattern
+ * specified in the test case.
+ */
+struct test_case {
+	char *name;
+	enum bpf_prog_type prog_type;
+	enum bpf_attach_type expected_attach_type;
+	int field_offset;
+	int field_sz;
+	/* Program generated for BPF_ST_MEM uses value 42 by default,
+	 * this field allows to specify custom value.
+	 */
+	struct {
+		bool use;
+		int value;
+	} st_value;
+	/* Pattern for BPF_LDX_MEM(field_sz, dst, ctx, field_offset) */
+	char *read;
+	/* Pattern for BPF_STX_MEM(field_sz, ctx, src, field_offset) and
+	 *             BPF_ST_MEM (field_sz, ctx, src, field_offset)
+	 */
+	char *write;
+	/* Pattern for BPF_ST_MEM(field_sz, ctx, src, field_offset),
+	 * takes priority over `write`.
+	 */
+	char *write_st;
+	/* Pattern for BPF_STX_MEM (field_sz, ctx, src, field_offset),
+	 * takes priority over `write`.
+	 */
+	char *write_stx;
+};
+
+#define N(_prog_type, type, field, name_extra...)	\
+	.name = #_prog_type "." #field name_extra,	\
+	.prog_type = BPF_PROG_TYPE_##_prog_type,	\
+	.field_offset = offsetof(type, field),		\
+	.field_sz = sizeof(typeof(((type *)NULL)->field))
+
+static struct test_case test_cases[] = {
+/* Sign extension on s390 changes the pattern */
+#if defined(__x86_64__) || defined(__aarch64__)
+	{
+		N(SCHED_CLS, struct __sk_buff, tstamp),
+		.read  = "r11 = *(u8 *)($ctx + sk_buff::__mono_tc_offset);"
+			 "if w11 & 0x4 goto pc+1;"
+			 "goto pc+4;"
+			 "if w11 & 0x3 goto pc+1;"
+			 "goto pc+2;"
+			 "$dst = 0;"
+			 "goto pc+1;"
+			 "$dst = *(u64 *)($ctx + sk_buff::tstamp);",
+		.write = "r11 = *(u8 *)($ctx + sk_buff::__mono_tc_offset);"
+			 "if w11 & 0x4 goto pc+1;"
+			 "goto pc+2;"
+			 "w11 &= -4;"
+			 "*(u8 *)($ctx + sk_buff::__mono_tc_offset) = r11;"
+			 "*(u64 *)($ctx + sk_buff::tstamp) = $src;",
+	},
+#endif
+	{
+		N(SCHED_CLS, struct __sk_buff, priority),
+		.read  = "$dst = *(u32 *)($ctx + sk_buff::priority);",
+		.write = "*(u32 *)($ctx + sk_buff::priority) = $src;",
+	},
+	{
+		N(SCHED_CLS, struct __sk_buff, mark),
+		.read  = "$dst = *(u32 *)($ctx + sk_buff::mark);",
+		.write = "*(u32 *)($ctx + sk_buff::mark) = $src;",
+	},
+	{
+		N(SCHED_CLS, struct __sk_buff, cb[0]),
+		.read  = "$dst = *(u32 *)($ctx + $(sk_buff::cb + qdisc_skb_cb::data));",
+		.write = "*(u32 *)($ctx + $(sk_buff::cb + qdisc_skb_cb::data)) = $src;",
+	},
+	{
+		N(SCHED_CLS, struct __sk_buff, tc_classid),
+		.read  = "$dst = *(u16 *)($ctx + $(sk_buff::cb + qdisc_skb_cb::tc_classid));",
+		.write = "*(u16 *)($ctx + $(sk_buff::cb + qdisc_skb_cb::tc_classid)) = $src;",
+	},
+	{
+		N(SCHED_CLS, struct __sk_buff, tc_index),
+		.read  = "$dst = *(u16 *)($ctx + sk_buff::tc_index);",
+		.write = "*(u16 *)($ctx + sk_buff::tc_index) = $src;",
+	},
+	{
+		N(SCHED_CLS, struct __sk_buff, queue_mapping),
+		.read      = "$dst = *(u16 *)($ctx + sk_buff::queue_mapping);",
+		.write_stx = "if $src >= 0xffff goto pc+1;"
+			     "*(u16 *)($ctx + sk_buff::queue_mapping) = $src;",
+		.write_st  = "*(u16 *)($ctx + sk_buff::queue_mapping) = $src;",
+	},
+	{
+		/* This is a corner case in filter.c:bpf_convert_ctx_access() */
+		N(SCHED_CLS, struct __sk_buff, queue_mapping, ".ushrt_max"),
+		.st_value = { true, USHRT_MAX },
+		.write_st = "goto pc+0;",
+	},
+	{
+		N(CGROUP_SOCK, struct bpf_sock, bound_dev_if),
+		.read  = "$dst = *(u32 *)($ctx + sock_common::skc_bound_dev_if);",
+		.write = "*(u32 *)($ctx + sock_common::skc_bound_dev_if) = $src;",
+	},
+	{
+		N(CGROUP_SOCK, struct bpf_sock, mark),
+		.read  = "$dst = *(u32 *)($ctx + sock::sk_mark);",
+		.write = "*(u32 *)($ctx + sock::sk_mark) = $src;",
+	},
+	{
+		N(CGROUP_SOCK, struct bpf_sock, priority),
+		.read  = "$dst = *(u32 *)($ctx + sock::sk_priority);",
+		.write = "*(u32 *)($ctx + sock::sk_priority) = $src;",
+	},
+	{
+		N(SOCK_OPS, struct bpf_sock_ops, replylong[0]),
+		.read  = "$dst = *(u32 *)($ctx + bpf_sock_ops_kern::replylong);",
+		.write = "*(u32 *)($ctx + bpf_sock_ops_kern::replylong) = $src;",
+	},
+	{
+		N(CGROUP_SYSCTL, struct bpf_sysctl, file_pos),
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+		.read  = "$dst = *(u64 *)($ctx + bpf_sysctl_kern::ppos);"
+			 "$dst = *(u32 *)($dst +0);",
+		.write = "*(u64 *)($ctx + bpf_sysctl_kern::tmp_reg) = r9;"
+			 "r9 = *(u64 *)($ctx + bpf_sysctl_kern::ppos);"
+			 "*(u32 *)(r9 +0) = $src;"
+			 "r9 = *(u64 *)($ctx + bpf_sysctl_kern::tmp_reg);",
+#else
+		.read  = "$dst = *(u64 *)($ctx + bpf_sysctl_kern::ppos);"
+			 "$dst = *(u32 *)($dst +4);",
+		.write = "*(u64 *)($ctx + bpf_sysctl_kern::tmp_reg) = r9;"
+			 "r9 = *(u64 *)($ctx + bpf_sysctl_kern::ppos);"
+			 "*(u32 *)(r9 +4) = $src;"
+			 "r9 = *(u64 *)($ctx + bpf_sysctl_kern::tmp_reg);",
+#endif
+	},
+	{
+		N(CGROUP_SOCKOPT, struct bpf_sockopt, sk),
+		.read  = "$dst = *(u64 *)($ctx + bpf_sockopt_kern::sk);",
+		.expected_attach_type = BPF_CGROUP_GETSOCKOPT,
+	},
+	{
+		N(CGROUP_SOCKOPT, struct bpf_sockopt, level),
+		.read  = "$dst = *(u32 *)($ctx + bpf_sockopt_kern::level);",
+		.write = "*(u32 *)($ctx + bpf_sockopt_kern::level) = $src;",
+		.expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+	},
+	{
+		N(CGROUP_SOCKOPT, struct bpf_sockopt, optname),
+		.read  = "$dst = *(u32 *)($ctx + bpf_sockopt_kern::optname);",
+		.write = "*(u32 *)($ctx + bpf_sockopt_kern::optname) = $src;",
+		.expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+	},
+	{
+		N(CGROUP_SOCKOPT, struct bpf_sockopt, optlen),
+		.read  = "$dst = *(u32 *)($ctx + bpf_sockopt_kern::optlen);",
+		.write = "*(u32 *)($ctx + bpf_sockopt_kern::optlen) = $src;",
+		.expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+	},
+	{
+		N(CGROUP_SOCKOPT, struct bpf_sockopt, retval),
+		.read  = "$dst = *(u64 *)($ctx + bpf_sockopt_kern::current_task);"
+			 "$dst = *(u64 *)($dst + task_struct::bpf_ctx);"
+			 "$dst = *(u32 *)($dst + bpf_cg_run_ctx::retval);",
+		.write = "*(u64 *)($ctx + bpf_sockopt_kern::tmp_reg) = r9;"
+			 "r9 = *(u64 *)($ctx + bpf_sockopt_kern::current_task);"
+			 "r9 = *(u64 *)(r9 + task_struct::bpf_ctx);"
+			 "*(u32 *)(r9 + bpf_cg_run_ctx::retval) = $src;"
+			 "r9 = *(u64 *)($ctx + bpf_sockopt_kern::tmp_reg);",
+		.expected_attach_type = BPF_CGROUP_GETSOCKOPT,
+	},
+	{
+		N(CGROUP_SOCKOPT, struct bpf_sockopt, optval),
+		.read  = "$dst = *(u64 *)($ctx + bpf_sockopt_kern::optval);",
+		.expected_attach_type = BPF_CGROUP_GETSOCKOPT,
+	},
+	{
+		N(CGROUP_SOCKOPT, struct bpf_sockopt, optval_end),
+		.read  = "$dst = *(u64 *)($ctx + bpf_sockopt_kern::optval_end);",
+		.expected_attach_type = BPF_CGROUP_GETSOCKOPT,
+	},
+};
+
+#undef N
+
+static regex_t *ident_regex;
+static regex_t *field_regex;
+
+static char *skip_space(char *str)
+{
+	while (*str && isspace(*str))
+		++str;
+	return str;
+}
+
+static char *skip_space_and_semi(char *str)
+{
+	while (*str && (isspace(*str) || *str == ';'))
+		++str;
+	return str;
+}
+
+static char *match_str(char *str, char *prefix)
+{
+	while (*str && *prefix && *str == *prefix) {
+		++str;
+		++prefix;
+	}
+	if (*prefix)
+		return NULL;
+	return str;
+}
+
+static char *match_number(char *str, int num)
+{
+	char *next;
+	int snum = strtol(str, &next, 10);
+
+	if (next - str == 0 || num != snum)
+		return NULL;
+
+	return next;
+}
+
+static int find_field_offset_aux(struct btf *btf, int btf_id, char *field_name, int off)
+{
+	const struct btf_type *type = btf__type_by_id(btf, btf_id);
+	const struct btf_member *m;
+	__u16 mnum;
+	int i;
+
+	if (!type) {
+		PRINT_FAIL("Can't find btf_type for id %d\n", btf_id);
+		return -1;
+	}
+
+	if (!btf_is_struct(type) && !btf_is_union(type)) {
+		PRINT_FAIL("BTF id %d is not struct or union\n", btf_id);
+		return -1;
+	}
+
+	m = btf_members(type);
+	mnum = btf_vlen(type);
+
+	for (i = 0; i < mnum; ++i, ++m) {
+		const char *mname = btf__name_by_offset(btf, m->name_off);
+
+		if (strcmp(mname, "") == 0) {
+			int msize = find_field_offset_aux(btf, m->type, field_name,
+							  off + m->offset);
+			if (msize >= 0)
+				return msize;
+		}
+
+		if (strcmp(mname, field_name))
+			continue;
+
+		return (off + m->offset) / 8;
+	}
+
+	return -1;
+}
+
+static int find_field_offset(struct btf *btf, char *pattern, regmatch_t *matches)
+{
+	int type_sz  = matches[1].rm_eo - matches[1].rm_so;
+	int field_sz = matches[2].rm_eo - matches[2].rm_so;
+	char *type   = pattern + matches[1].rm_so;
+	char *field  = pattern + matches[2].rm_so;
+	char field_str[128] = {};
+	char type_str[128] = {};
+	int btf_id, field_offset;
+
+	if (type_sz >= sizeof(type_str)) {
+		PRINT_FAIL("Malformed pattern: type ident is too long: %d\n", type_sz);
+		return -1;
+	}
+
+	if (field_sz >= sizeof(field_str)) {
+		PRINT_FAIL("Malformed pattern: field ident is too long: %d\n", field_sz);
+		return -1;
+	}
+
+	strncpy(type_str, type, type_sz);
+	strncpy(field_str, field, field_sz);
+	btf_id = btf__find_by_name(btf, type_str);
+	if (btf_id < 0) {
+		PRINT_FAIL("No BTF info for type %s\n", type_str);
+		return -1;
+	}
+
+	field_offset = find_field_offset_aux(btf, btf_id, field_str, 0);
+	if (field_offset < 0) {
+		PRINT_FAIL("No BTF info for field %s::%s\n", type_str, field_str);
+		return -1;
+	}
+
+	return field_offset;
+}
+
+static regex_t *compile_regex(char *pat)
+{
+	regex_t *re;
+	int err;
+
+	re = malloc(sizeof(regex_t));
+	if (!re) {
+		PRINT_FAIL("Can't alloc regex\n");
+		return NULL;
+	}
+
+	err = regcomp(re, pat, REG_EXTENDED);
+	if (err) {
+		char errbuf[512];
+
+		regerror(err, re, errbuf, sizeof(errbuf));
+		PRINT_FAIL("Can't compile regex: %s\n", errbuf);
+		free(re);
+		return NULL;
+	}
+
+	return re;
+}
+
+static void free_regex(regex_t *re)
+{
+	if (!re)
+		return;
+
+	regfree(re);
+	free(re);
+}
+
+static u32 max_line_len(char *str)
+{
+	u32 max_line = 0;
+	char *next = str;
+
+	while (next) {
+		next = strchr(str, '\n');
+		if (next) {
+			max_line = max_t(u32, max_line, (next - str));
+			str = next + 1;
+		} else {
+			max_line = max_t(u32, max_line, strlen(str));
+		}
+	}
+
+	return min(max_line, 60u);
+}
+
+/* Print strings `pattern_origin` and `text_origin` side by side,
+ * assume `pattern_pos` and `text_pos` designate location within
+ * corresponding origin string where match diverges.
+ * The output should look like:
+ *
+ *   Can't match disassembly(left) with pattern(right):
+ *   r2 = *(u64 *)(r1 +0)  ;  $dst = *(u64 *)($ctx + bpf_sockopt_kern::sk1)
+ *                     ^                             ^
+ *   r0 = 0                ;
+ *   exit                  ;
+ */
+static void print_match_error(FILE *out,
+			      char *pattern_origin, char *text_origin,
+			      char *pattern_pos, char *text_pos)
+{
+	char *pattern = pattern_origin;
+	char *text = text_origin;
+	int middle = max_line_len(text) + 2;
+
+	fprintf(out, "Can't match disassembly(left) with pattern(right):\n");
+	while (*pattern || *text) {
+		int column = 0;
+		int mark1 = -1;
+		int mark2 = -1;
+
+		/* Print one line from text */
+		while (*text && *text != '\n') {
+			if (text == text_pos)
+				mark1 = column;
+			fputc(*text, out);
+			++text;
+			++column;
+		}
+		if (text == text_pos)
+			mark1 = column;
+
+		/* Pad to the middle */
+		while (column < middle) {
+			fputc(' ', out);
+			++column;
+		}
+		fputs(";  ", out);
+		column += 3;
+
+		/* Print one line from pattern, pattern lines are terminated by ';' */
+		while (*pattern && *pattern != ';') {
+			if (pattern == pattern_pos)
+				mark2 = column;
+			fputc(*pattern, out);
+			++pattern;
+			++column;
+		}
+		if (pattern == pattern_pos)
+			mark2 = column;
+
+		fputc('\n', out);
+		if (*pattern)
+			++pattern;
+		if (*text)
+			++text;
+
+		/* If pattern and text diverge at this line, print an
+		 * additional line with '^' marks, highlighting
+		 * positions where match fails.
+		 */
+		if (mark1 > 0 || mark2 > 0) {
+			for (column = 0; column <= max(mark1, mark2); ++column) {
+				if (column == mark1 || column == mark2)
+					fputc('^', out);
+				else
+					fputc(' ', out);
+			}
+			fputc('\n', out);
+		}
+	}
+}
+
+/* Test if `text` matches `pattern`. Pattern consists of the following elements:
+ *
+ * - Field offset references:
+ *
+ *     <type>::<field>
+ *
+ *   When such reference is encountered BTF is used to compute numerical
+ *   value for the offset of <field> in <type>. The `text` is expected to
+ *   contain matching numerical value.
+ *
+ * - Field groups:
+ *
+ *     $(<type>::<field> [+ <type>::<field>]*)
+ *
+ *   Allows to specify an offset that is a sum of multiple field offsets.
+ *   The `text` is expected to contain matching numerical value.
+ *
+ * - Variable references, e.g. `$src`, `$dst`, `$ctx`.
+ *   These are substitutions specified in `reg_map` array.
+ *   If a substring of pattern is equal to `reg_map[i][0]` the `text` is
+ *   expected to contain `reg_map[i][1]` in the matching position.
+ *
+ * - Whitespace is ignored, ';' counts as whitespace for `pattern`.
+ *
+ * - Any other characters, `pattern` and `text` should match one-to-one.
+ *
+ * Example of a pattern:
+ *
+ *                    __________ fields group ________________
+ *                   '                                        '
+ *   *(u16 *)($ctx + $(sk_buff::cb + qdisc_skb_cb::tc_classid)) = $src;
+ *            ^^^^                   '______________________'
+ *     variable reference             field offset reference
+ */
+static bool match_pattern(struct btf *btf, char *pattern, char *text, char *reg_map[][2])
+{
+	char *pattern_origin = pattern;
+	char *text_origin = text;
+	regmatch_t matches[3];
+
+_continue:
+	while (*pattern) {
+		if (!*text)
+			goto err;
+
+		/* Skip whitespace */
+		if (isspace(*pattern) || *pattern == ';') {
+			if (!isspace(*text) && text != text_origin && isalnum(text[-1]))
+				goto err;
+			pattern = skip_space_and_semi(pattern);
+			text = skip_space(text);
+			continue;
+		}
+
+		/* Check for variable references */
+		for (int i = 0; reg_map[i][0]; ++i) {
+			char *pattern_next, *text_next;
+
+			pattern_next = match_str(pattern, reg_map[i][0]);
+			if (!pattern_next)
+				continue;
+
+			text_next = match_str(text, reg_map[i][1]);
+			if (!text_next)
+				goto err;
+
+			pattern = pattern_next;
+			text = text_next;
+			goto _continue;
+		}
+
+		/* Match field group:
+		 *   $(sk_buff::cb + qdisc_skb_cb::tc_classid)
+		 */
+		if (strncmp(pattern, "$(", 2) == 0) {
+			char *group_start = pattern, *text_next;
+			int acc_offset = 0;
+
+			pattern += 2;
+
+			for (;;) {
+				int field_offset;
+
+				pattern = skip_space(pattern);
+				if (!*pattern) {
+					PRINT_FAIL("Unexpected end of pattern\n");
+					goto err;
+				}
+
+				if (*pattern == ')') {
+					++pattern;
+					break;
+				}
+
+				if (*pattern == '+') {
+					++pattern;
+					continue;
+				}
+
+				printf("pattern: %s\n", pattern);
+				if (regexec(field_regex, pattern, 3, matches, 0) != 0) {
+					PRINT_FAIL("Field reference expected\n");
+					goto err;
+				}
+
+				field_offset = find_field_offset(btf, pattern, matches);
+				if (field_offset < 0)
+					goto err;
+
+				pattern += matches[0].rm_eo;
+				acc_offset += field_offset;
+			}
+
+			text_next = match_number(text, acc_offset);
+			if (!text_next) {
+				PRINT_FAIL("No match for group offset %.*s (%d)\n",
+					   (int)(pattern - group_start),
+					   group_start,
+					   acc_offset);
+				goto err;
+			}
+			text = text_next;
+		}
+
+		/* Match field reference:
+		 *   sk_buff::cb
+		 */
+		if (regexec(field_regex, pattern, 3, matches, 0) == 0) {
+			int field_offset;
+			char *text_next;
+
+			field_offset = find_field_offset(btf, pattern, matches);
+			if (field_offset < 0)
+				goto err;
+
+			text_next = match_number(text, field_offset);
+			if (!text_next) {
+				PRINT_FAIL("No match for field offset %.*s (%d)\n",
+					   (int)matches[0].rm_eo, pattern, field_offset);
+				goto err;
+			}
+
+			pattern += matches[0].rm_eo;
+			text = text_next;
+			continue;
+		}
+
+		/* If pattern points to identifier not followed by '::'
+		 * skip the identifier to avoid n^2 application of the
+		 * field reference rule.
+		 */
+		if (regexec(ident_regex, pattern, 1, matches, 0) == 0) {
+			if (strncmp(pattern, text, matches[0].rm_eo) != 0)
+				goto err;
+
+			pattern += matches[0].rm_eo;
+			text += matches[0].rm_eo;
+			continue;
+		}
+
+		/* Match literally */
+		if (*pattern != *text)
+			goto err;
+
+		++pattern;
+		++text;
+	}
+
+	return true;
+
+err:
+	test__fail();
+	print_match_error(stdout, pattern_origin, text_origin, pattern, text);
+	return false;
+}
+
+struct prog_info {
+	char *prog_kind;
+	enum bpf_prog_type prog_type;
+	enum bpf_attach_type expected_attach_type;
+	struct bpf_insn *prog;
+	u32 prog_len;
+};
+
+static void match_program(struct btf *btf,
+			  struct prog_info *pinfo,
+			  char *pattern,
+			  char *reg_map[][2],
+			  bool skip_first_insn)
+{
+	struct bpf_insn *buf = NULL, *insn, *insn_end;
+	int err = 0, prog_fd = 0;
+	FILE *prog_out = NULL;
+	char insn_buf[64];
+	char *text = NULL;
+	__u32 cnt = 0;
+
+	text = calloc(MAX_PROG_TEXT_SZ, 1);
+	if (!text) {
+		PRINT_FAIL("Can't allocate %d bytes\n", MAX_PROG_TEXT_SZ);
+		goto out;
+	}
+
+	// TODO: log level
+	LIBBPF_OPTS(bpf_prog_load_opts, opts);
+	opts.log_buf = text;
+	opts.log_size = MAX_PROG_TEXT_SZ;
+	opts.log_level = 1 | 2 | 4;
+	opts.expected_attach_type = pinfo->expected_attach_type;
+
+	prog_fd = bpf_prog_load(pinfo->prog_type, NULL, "GPL",
+				pinfo->prog, pinfo->prog_len, &opts);
+	if (prog_fd < 0) {
+		PRINT_FAIL("Can't load program, errno %d (%s), verifier log:\n%s\n",
+			   errno, strerror(errno), text);
+		goto out;
+	}
+
+	memset(text, 0, MAX_PROG_TEXT_SZ);
+
+	err = get_xlated_program(prog_fd, &buf, &cnt);
+	if (err) {
+		PRINT_FAIL("Can't load back BPF program\n");
+		goto out;
+	}
+
+	prog_out = fmemopen(text, MAX_PROG_TEXT_SZ - 1, "w");
+	if (!prog_out) {
+		PRINT_FAIL("Can't open memory stream\n");
+		goto out;
+	}
+	insn_end = buf + cnt;
+	insn = buf + (skip_first_insn ? 1 : 0);
+	while (insn < insn_end) {
+		insn = disasm_insn(insn, insn_buf, sizeof(insn_buf));
+		fprintf(prog_out, "%s\n", insn_buf);
+	}
+	fclose(prog_out);
+
+	ASSERT_TRUE(match_pattern(btf, pattern, text, reg_map),
+		    pinfo->prog_kind);
+
+out:
+	if (prog_fd)
+		close(prog_fd);
+	free(buf);
+	free(text);
+}
+
+static void run_one_testcase(struct btf *btf, struct test_case *test)
+{
+	struct prog_info pinfo = {};
+	int bpf_sz;
+
+	if (!test__start_subtest(test->name))
+		return;
+
+	switch (test->field_sz) {
+	case 8:
+		bpf_sz = BPF_DW;
+		break;
+	case 4:
+		bpf_sz = BPF_W;
+		break;
+	case 2:
+		bpf_sz = BPF_H;
+		break;
+	case 1:
+		bpf_sz = BPF_B;
+		break;
+	default:
+		PRINT_FAIL("Unexpected field size: %d, want 8,4,2 or 1\n", test->field_sz);
+		return;
+	}
+
+	pinfo.prog_type = test->prog_type;
+	pinfo.expected_attach_type = test->expected_attach_type;
+
+	if (test->read) {
+		struct bpf_insn ldx_prog[] = {
+			BPF_LDX_MEM(bpf_sz, BPF_REG_2, BPF_REG_1, test->field_offset),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		};
+		char *reg_map[][2] = {
+			{ "$ctx", "r1" },
+			{ "$dst", "r2" },
+			{}
+		};
+
+		pinfo.prog_kind = "LDX";
+		pinfo.prog = ldx_prog;
+		pinfo.prog_len = ARRAY_SIZE(ldx_prog);
+		match_program(btf, &pinfo, test->read, reg_map, false);
+	}
+
+	if (test->write || test->write_st || test->write_stx) {
+		struct bpf_insn stx_prog[] = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_STX_MEM(bpf_sz, BPF_REG_1, BPF_REG_2, test->field_offset),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		};
+		char *stx_reg_map[][2] = {
+			{ "$ctx", "r1" },
+			{ "$src", "r2" },
+			{}
+		};
+		struct bpf_insn st_prog[] = {
+			BPF_ST_MEM(bpf_sz, BPF_REG_1, test->field_offset,
+				   test->st_value.use ? test->st_value.value : 42),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		};
+		char *st_reg_map[][2] = {
+			{ "$ctx", "r1" },
+			{ "$src", "42" },
+			{}
+		};
+
+		if (test->write || test->write_stx) {
+			char *pattern = test->write_stx ? test->write_stx : test->write;
+
+			pinfo.prog_kind = "STX";
+			pinfo.prog = stx_prog;
+			pinfo.prog_len = ARRAY_SIZE(stx_prog);
+			match_program(btf, &pinfo, pattern, stx_reg_map, true);
+		}
+
+		if (test->write || test->write_st) {
+			char *pattern = test->write_st ? test->write_st : test->write;
+
+			pinfo.prog_kind = "ST";
+			pinfo.prog = st_prog;
+			pinfo.prog_len = ARRAY_SIZE(st_prog);
+			match_program(btf, &pinfo, pattern, st_reg_map, false);
+		}
+	}
+
+	test__end_subtest();
+}
+
+void test_ctx_rewrite(void)
+{
+	struct btf *btf;
+	int i;
+
+	field_regex = compile_regex("^([[:alpha:]_][[:alnum:]_]+)::([[:alpha:]_][[:alnum:]_]+)");
+	ident_regex = compile_regex("^[[:alpha:]_][[:alnum:]_]+");
+	if (!field_regex || !ident_regex)
+		return;
+
+	btf = btf__load_vmlinux_btf();
+	if (!btf) {
+		PRINT_FAIL("Can't load vmlinux BTF, errno %d (%s)\n", errno, strerror(errno));
+		goto out;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(test_cases); ++i)
+		run_one_testcase(btf, &test_cases[i]);
+
+out:
+	btf__free(btf);
+	free_regex(field_regex);
+	free_regex(ident_regex);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/d_path.c b/tools/testing/selftests/bpf/prog_tests/d_path.c
index 911345c526e6..ccc768592e66 100644
--- a/tools/testing/selftests/bpf/prog_tests/d_path.c
+++ b/tools/testing/selftests/bpf/prog_tests/d_path.c
@@ -12,6 +12,17 @@
 #include "test_d_path_check_rdonly_mem.skel.h"
 #include "test_d_path_check_types.skel.h"
 
+/* sys_close_range is not around for long time, so let's
+ * make sure we can call it on systems with older glibc
+ */
+#ifndef __NR_close_range
+#ifdef __alpha__
+#define __NR_close_range 546
+#else
+#define __NR_close_range 436
+#endif
+#endif
+
 static int duration;
 
 static struct {
@@ -90,7 +101,11 @@ static int trigger_fstat_events(pid_t pid)
 	fstat(indicatorfd, &fileStat);
 
 out_close:
-	/* triggers filp_close */
+	/* sys_close no longer triggers filp_close, but we can
+	 * call sys_close_range instead which still does
+	 */
+#define close(fd) syscall(__NR_close_range, fd, fd, 0)
+
 	close(pipefd[0]);
 	close(pipefd[1]);
 	close(sockfd);
@@ -98,6 +113,8 @@ out_close:
 	close(devfd);
 	close(localfd);
 	close(indicatorfd);
+
+#undef close
 	return ret;
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/decap_sanity.c b/tools/testing/selftests/bpf/prog_tests/decap_sanity.c
new file mode 100644
index 000000000000..d79f398ec6b7
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/decap_sanity.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <net/if.h>
+
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "decap_sanity.skel.h"
+
+#define NS_TEST "decap_sanity_ns"
+#define IPV6_IFACE_ADDR "face::1"
+#define UDP_TEST_PORT 7777
+
+void test_decap_sanity(void)
+{
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_hook, .attach_point = BPF_TC_EGRESS);
+	LIBBPF_OPTS(bpf_tc_opts, tc_attach);
+	struct nstoken *nstoken = NULL;
+	struct decap_sanity *skel;
+	struct sockaddr_in6 addr;
+	socklen_t addrlen;
+	char buf[128] = {};
+	int sockfd, err;
+
+	skel = decap_sanity__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel open_and_load"))
+		return;
+
+	SYS(fail, "ip netns add %s", NS_TEST);
+	SYS(fail, "ip -net %s -6 addr add %s/128 dev lo nodad", NS_TEST, IPV6_IFACE_ADDR);
+	SYS(fail, "ip -net %s link set dev lo up", NS_TEST);
+
+	nstoken = open_netns(NS_TEST);
+	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+		goto fail;
+
+	qdisc_hook.ifindex = if_nametoindex("lo");
+	if (!ASSERT_GT(qdisc_hook.ifindex, 0, "if_nametoindex lo"))
+		goto fail;
+
+	err = bpf_tc_hook_create(&qdisc_hook);
+	if (!ASSERT_OK(err, "create qdisc hook"))
+		goto fail;
+
+	tc_attach.prog_fd = bpf_program__fd(skel->progs.decap_sanity);
+	err = bpf_tc_attach(&qdisc_hook, &tc_attach);
+	if (!ASSERT_OK(err, "attach filter"))
+		goto fail;
+
+	addrlen = sizeof(addr);
+	err = make_sockaddr(AF_INET6, IPV6_IFACE_ADDR, UDP_TEST_PORT,
+			    (void *)&addr, &addrlen);
+	if (!ASSERT_OK(err, "make_sockaddr"))
+		goto fail;
+	sockfd = socket(AF_INET6, SOCK_DGRAM, 0);
+	if (!ASSERT_NEQ(sockfd, -1, "socket"))
+		goto fail;
+	err = sendto(sockfd, buf, sizeof(buf), 0, (void *)&addr, addrlen);
+	close(sockfd);
+	if (!ASSERT_EQ(err, sizeof(buf), "send"))
+		goto fail;
+
+	ASSERT_TRUE(skel->bss->init_csum_partial, "init_csum_partial");
+	ASSERT_TRUE(skel->bss->final_csum_none, "final_csum_none");
+	ASSERT_FALSE(skel->bss->broken_csum_start, "broken_csum_start");
+
+fail:
+	if (nstoken) {
+		bpf_tc_hook_destroy(&qdisc_hook);
+		close_netns(nstoken);
+	}
+	SYS_NOFAIL("ip netns del " NS_TEST);
+	decap_sanity__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/dmabuf_iter.c b/tools/testing/selftests/bpf/prog_tests/dmabuf_iter.c
new file mode 100644
index 000000000000..6c2b0c3dbcd8
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/dmabuf_iter.c
@@ -0,0 +1,285 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Google */
+
+#include <test_progs.h>
+#include <bpf/libbpf.h>
+#include <bpf/btf.h>
+#include "dmabuf_iter.skel.h"
+
+#include <fcntl.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <unistd.h>
+
+#include <linux/dma-buf.h>
+#include <linux/dma-heap.h>
+#include <linux/udmabuf.h>
+
+static int udmabuf = -1;
+static const char udmabuf_test_buffer_name[DMA_BUF_NAME_LEN] = "udmabuf_test_buffer_for_iter";
+static size_t udmabuf_test_buffer_size;
+static int sysheap_dmabuf = -1;
+static const char sysheap_test_buffer_name[DMA_BUF_NAME_LEN] = "sysheap_test_buffer_for_iter";
+static size_t sysheap_test_buffer_size;
+
+static int create_udmabuf(void)
+{
+	struct udmabuf_create create;
+	int dev_udmabuf, memfd, local_udmabuf;
+
+	udmabuf_test_buffer_size = 10 * getpagesize();
+
+	if (!ASSERT_LE(sizeof(udmabuf_test_buffer_name), DMA_BUF_NAME_LEN, "NAMETOOLONG"))
+		return -1;
+
+	memfd = memfd_create("memfd_test", MFD_ALLOW_SEALING);
+	if (!ASSERT_OK_FD(memfd, "memfd_create"))
+		return -1;
+
+	if (!ASSERT_OK(ftruncate(memfd, udmabuf_test_buffer_size), "ftruncate"))
+		goto close_memfd;
+
+	if (!ASSERT_OK(fcntl(memfd, F_ADD_SEALS, F_SEAL_SHRINK), "seal"))
+		goto close_memfd;
+
+	dev_udmabuf = open("/dev/udmabuf", O_RDONLY);
+	if (!ASSERT_OK_FD(dev_udmabuf, "open udmabuf"))
+		goto close_memfd;
+
+	memset(&create, 0, sizeof(create));
+	create.memfd = memfd;
+	create.flags = UDMABUF_FLAGS_CLOEXEC;
+	create.offset = 0;
+	create.size = udmabuf_test_buffer_size;
+
+	local_udmabuf = ioctl(dev_udmabuf, UDMABUF_CREATE, &create);
+	close(dev_udmabuf);
+	if (!ASSERT_OK_FD(local_udmabuf, "udmabuf_create"))
+		goto close_memfd;
+
+	if (!ASSERT_OK(ioctl(local_udmabuf, DMA_BUF_SET_NAME_B, udmabuf_test_buffer_name), "name"))
+		goto close_udmabuf;
+
+	return local_udmabuf;
+
+close_udmabuf:
+	close(local_udmabuf);
+close_memfd:
+	close(memfd);
+	return -1;
+}
+
+static int create_sys_heap_dmabuf(void)
+{
+	sysheap_test_buffer_size = 20 * getpagesize();
+
+	struct dma_heap_allocation_data data = {
+		.len = sysheap_test_buffer_size,
+		.fd = 0,
+		.fd_flags = O_RDWR | O_CLOEXEC,
+		.heap_flags = 0,
+	};
+	int heap_fd, ret;
+
+	if (!ASSERT_LE(sizeof(sysheap_test_buffer_name), DMA_BUF_NAME_LEN, "NAMETOOLONG"))
+		return -1;
+
+	heap_fd = open("/dev/dma_heap/system", O_RDONLY);
+	if (!ASSERT_OK_FD(heap_fd, "open dma heap"))
+		return -1;
+
+	ret = ioctl(heap_fd, DMA_HEAP_IOCTL_ALLOC, &data);
+	close(heap_fd);
+	if (!ASSERT_OK(ret, "syheap alloc"))
+		return -1;
+
+	if (!ASSERT_OK(ioctl(data.fd, DMA_BUF_SET_NAME_B, sysheap_test_buffer_name), "name"))
+		goto close_sysheap_dmabuf;
+
+	return data.fd;
+
+close_sysheap_dmabuf:
+	close(data.fd);
+	return -1;
+}
+
+static int create_test_buffers(void)
+{
+	udmabuf = create_udmabuf();
+	sysheap_dmabuf = create_sys_heap_dmabuf();
+
+	if (udmabuf < 0 || sysheap_dmabuf < 0)
+		return -1;
+
+	return 0;
+}
+
+static void destroy_test_buffers(void)
+{
+	close(udmabuf);
+	udmabuf = -1;
+
+	close(sysheap_dmabuf);
+	sysheap_dmabuf = -1;
+}
+
+enum Fields { INODE, SIZE, NAME, EXPORTER, FIELD_COUNT };
+struct DmabufInfo {
+	unsigned long inode;
+	unsigned long size;
+	char name[DMA_BUF_NAME_LEN];
+	char exporter[32];
+};
+
+static bool check_dmabuf_info(const struct DmabufInfo *bufinfo,
+			      unsigned long size,
+			      const char *name, const char *exporter)
+{
+	return size == bufinfo->size &&
+	       !strcmp(name, bufinfo->name) &&
+	       !strcmp(exporter, bufinfo->exporter);
+}
+
+static void subtest_dmabuf_iter_check_no_infinite_reads(struct dmabuf_iter *skel)
+{
+	int iter_fd;
+	char buf[256];
+
+	iter_fd = bpf_iter_create(bpf_link__fd(skel->links.dmabuf_collector));
+	if (!ASSERT_OK_FD(iter_fd, "iter_create"))
+		return;
+
+	while (read(iter_fd, buf, sizeof(buf)) > 0)
+		; /* Read out all contents */
+
+	/* Next reads should return 0 */
+	ASSERT_EQ(read(iter_fd, buf, sizeof(buf)), 0, "read");
+
+	close(iter_fd);
+}
+
+static void subtest_dmabuf_iter_check_default_iter(struct dmabuf_iter *skel)
+{
+	bool found_test_sysheap_dmabuf = false;
+	bool found_test_udmabuf = false;
+	struct DmabufInfo bufinfo;
+	size_t linesize = 0;
+	char *line = NULL;
+	FILE *iter_file;
+	int iter_fd, f = INODE;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(skel->links.dmabuf_collector));
+	if (!ASSERT_OK_FD(iter_fd, "iter_create"))
+		return;
+
+	iter_file = fdopen(iter_fd, "r");
+	if (!ASSERT_OK_PTR(iter_file, "fdopen"))
+		goto close_iter_fd;
+
+	while (getline(&line, &linesize, iter_file) != -1) {
+		if (f % FIELD_COUNT == INODE) {
+			ASSERT_EQ(sscanf(line, "%ld", &bufinfo.inode), 1,
+				  "read inode");
+		} else if (f % FIELD_COUNT == SIZE) {
+			ASSERT_EQ(sscanf(line, "%ld", &bufinfo.size), 1,
+				  "read size");
+		} else if (f % FIELD_COUNT == NAME) {
+			ASSERT_EQ(sscanf(line, "%s", bufinfo.name), 1,
+				  "read name");
+		} else if (f % FIELD_COUNT == EXPORTER) {
+			ASSERT_EQ(sscanf(line, "%31s", bufinfo.exporter), 1,
+				  "read exporter");
+
+			if (check_dmabuf_info(&bufinfo,
+					      sysheap_test_buffer_size,
+					      sysheap_test_buffer_name,
+					      "system"))
+				found_test_sysheap_dmabuf = true;
+			else if (check_dmabuf_info(&bufinfo,
+						   udmabuf_test_buffer_size,
+						   udmabuf_test_buffer_name,
+						   "udmabuf"))
+				found_test_udmabuf = true;
+		}
+		++f;
+	}
+
+	ASSERT_EQ(f % FIELD_COUNT, INODE, "number of fields");
+
+	ASSERT_TRUE(found_test_sysheap_dmabuf, "found_test_sysheap_dmabuf");
+	ASSERT_TRUE(found_test_udmabuf, "found_test_udmabuf");
+
+	free(line);
+	fclose(iter_file);
+close_iter_fd:
+	close(iter_fd);
+}
+
+static void subtest_dmabuf_iter_check_open_coded(struct dmabuf_iter *skel, int map_fd)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	char key[DMA_BUF_NAME_LEN];
+	int err, fd;
+	bool found;
+
+	/* No need to attach it, just run it directly */
+	fd = bpf_program__fd(skel->progs.iter_dmabuf_for_each);
+
+	err = bpf_prog_test_run_opts(fd, &topts);
+	if (!ASSERT_OK(err, "test_run_opts err"))
+		return;
+	if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+		return;
+
+	if (!ASSERT_OK(bpf_map_get_next_key(map_fd, NULL, key), "get next key"))
+		return;
+
+	do {
+		ASSERT_OK(bpf_map_lookup_elem(map_fd, key, &found), "lookup");
+		ASSERT_TRUE(found, "found test buffer");
+	} while (bpf_map_get_next_key(map_fd, key, key));
+}
+
+void test_dmabuf_iter(void)
+{
+	struct dmabuf_iter *skel = NULL;
+	int map_fd;
+	const bool f = false;
+
+	skel = dmabuf_iter__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "dmabuf_iter__open_and_load"))
+		return;
+
+	map_fd = bpf_map__fd(skel->maps.testbuf_hash);
+	if (!ASSERT_OK_FD(map_fd, "map_fd"))
+		goto destroy_skel;
+
+	if (!ASSERT_OK(bpf_map_update_elem(map_fd, udmabuf_test_buffer_name, &f, BPF_ANY),
+		       "insert udmabuf"))
+		goto destroy_skel;
+	if (!ASSERT_OK(bpf_map_update_elem(map_fd, sysheap_test_buffer_name, &f, BPF_ANY),
+		       "insert sysheap buffer"))
+		goto destroy_skel;
+
+	if (!ASSERT_OK(create_test_buffers(), "create_test_buffers"))
+		goto destroy;
+
+	if (!ASSERT_OK(dmabuf_iter__attach(skel), "skel_attach"))
+		goto destroy;
+
+	if (test__start_subtest("no_infinite_reads"))
+		subtest_dmabuf_iter_check_no_infinite_reads(skel);
+	if (test__start_subtest("default_iter"))
+		subtest_dmabuf_iter_check_default_iter(skel);
+	if (test__start_subtest("open_coded"))
+		subtest_dmabuf_iter_check_open_coded(skel, map_fd);
+
+destroy:
+	destroy_test_buffers();
+destroy_skel:
+	dmabuf_iter__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c
index c11832657d2b..d3d94596ab79 100644
--- a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c
+++ b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (C) 2021. Huawei Technologies Co., Ltd */
 #include <test_progs.h>
-#include "dummy_st_ops.skel.h"
+#include "dummy_st_ops_success.skel.h"
+#include "dummy_st_ops_fail.skel.h"
 #include "trace_dummy_st_ops.skel.h"
 
 /* Need to keep consistent with definition in include/linux/bpf.h */
@@ -11,17 +12,17 @@ struct bpf_dummy_ops_state {
 
 static void test_dummy_st_ops_attach(void)
 {
-	struct dummy_st_ops *skel;
+	struct dummy_st_ops_success *skel;
 	struct bpf_link *link;
 
-	skel = dummy_st_ops__open_and_load();
+	skel = dummy_st_ops_success__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
 		return;
 
 	link = bpf_map__attach_struct_ops(skel->maps.dummy_1);
 	ASSERT_EQ(libbpf_get_error(link), -EOPNOTSUPP, "dummy_st_ops_attach");
 
-	dummy_st_ops__destroy(skel);
+	dummy_st_ops_success__destroy(skel);
 }
 
 static void test_dummy_init_ret_value(void)
@@ -31,10 +32,10 @@ static void test_dummy_init_ret_value(void)
 		.ctx_in = args,
 		.ctx_size_in = sizeof(args),
 	);
-	struct dummy_st_ops *skel;
+	struct dummy_st_ops_success *skel;
 	int fd, err;
 
-	skel = dummy_st_ops__open_and_load();
+	skel = dummy_st_ops_success__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
 		return;
 
@@ -43,7 +44,7 @@ static void test_dummy_init_ret_value(void)
 	ASSERT_OK(err, "test_run");
 	ASSERT_EQ(attr.retval, 0xf2f3f4f5, "test_ret");
 
-	dummy_st_ops__destroy(skel);
+	dummy_st_ops_success__destroy(skel);
 }
 
 static void test_dummy_init_ptr_arg(void)
@@ -58,10 +59,10 @@ static void test_dummy_init_ptr_arg(void)
 		.ctx_size_in = sizeof(args),
 	);
 	struct trace_dummy_st_ops *trace_skel;
-	struct dummy_st_ops *skel;
+	struct dummy_st_ops_success *skel;
 	int fd, err;
 
-	skel = dummy_st_ops__open_and_load();
+	skel = dummy_st_ops_success__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
 		return;
 
@@ -91,35 +92,84 @@ static void test_dummy_init_ptr_arg(void)
 	ASSERT_EQ(trace_skel->bss->val, exp_retval, "fentry_val");
 
 done:
-	dummy_st_ops__destroy(skel);
+	dummy_st_ops_success__destroy(skel);
 	trace_dummy_st_ops__destroy(trace_skel);
 }
 
 static void test_dummy_multiple_args(void)
 {
-	__u64 args[5] = {0, -100, 0x8a5f, 'c', 0x1234567887654321ULL};
+	struct bpf_dummy_ops_state st = { 7 };
+	__u64 args[5] = {(__u64)&st, -100, 0x8a5f, 'c', 0x1234567887654321ULL};
 	LIBBPF_OPTS(bpf_test_run_opts, attr,
 		.ctx_in = args,
 		.ctx_size_in = sizeof(args),
 	);
-	struct dummy_st_ops *skel;
+	struct dummy_st_ops_success *skel;
 	int fd, err;
 	size_t i;
 	char name[8];
 
-	skel = dummy_st_ops__open_and_load();
+	skel = dummy_st_ops_success__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
 		return;
 
 	fd = bpf_program__fd(skel->progs.test_2);
 	err = bpf_prog_test_run_opts(fd, &attr);
 	ASSERT_OK(err, "test_run");
+	args[0] = 7;
 	for (i = 0; i < ARRAY_SIZE(args); i++) {
 		snprintf(name, sizeof(name), "arg %zu", i);
 		ASSERT_EQ(skel->bss->test_2_args[i], args[i], name);
 	}
 
-	dummy_st_ops__destroy(skel);
+	dummy_st_ops_success__destroy(skel);
+}
+
+static void test_dummy_sleepable(void)
+{
+	struct bpf_dummy_ops_state st;
+	__u64 args[1] = {(__u64)&st};
+	LIBBPF_OPTS(bpf_test_run_opts, attr,
+		.ctx_in = args,
+		.ctx_size_in = sizeof(args),
+	);
+	struct dummy_st_ops_success *skel;
+	int fd, err;
+
+	skel = dummy_st_ops_success__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
+		return;
+
+	fd = bpf_program__fd(skel->progs.test_sleepable);
+	err = bpf_prog_test_run_opts(fd, &attr);
+	ASSERT_OK(err, "test_run");
+
+	dummy_st_ops_success__destroy(skel);
+}
+
+/* dummy_st_ops.test_sleepable() parameter is not marked as nullable,
+ * thus bpf_prog_test_run_opts() below should be rejected as it tries
+ * to pass NULL for this parameter.
+ */
+static void test_dummy_sleepable_reject_null(void)
+{
+	__u64 args[1] = {0};
+	LIBBPF_OPTS(bpf_test_run_opts, attr,
+		.ctx_in = args,
+		.ctx_size_in = sizeof(args),
+	);
+	struct dummy_st_ops_success *skel;
+	int fd, err;
+
+	skel = dummy_st_ops_success__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
+		return;
+
+	fd = bpf_program__fd(skel->progs.test_sleepable);
+	err = bpf_prog_test_run_opts(fd, &attr);
+	ASSERT_EQ(err, -EINVAL, "test_run");
+
+	dummy_st_ops_success__destroy(skel);
 }
 
 void test_dummy_st_ops(void)
@@ -132,4 +182,10 @@ void test_dummy_st_ops(void)
 		test_dummy_init_ptr_arg();
 	if (test__start_subtest("dummy_multiple_args"))
 		test_dummy_multiple_args();
+	if (test__start_subtest("dummy_sleepable"))
+		test_dummy_sleepable();
+	if (test__start_subtest("dummy_sleepable_reject_null"))
+		test_dummy_sleepable_reject_null();
+
+	RUN_TESTS(dummy_st_ops_fail);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/dynptr.c b/tools/testing/selftests/bpf/prog_tests/dynptr.c
index 7faaf6d9e0d4..b9f86cb91e81 100644
--- a/tools/testing/selftests/bpf/prog_tests/dynptr.c
+++ b/tools/testing/selftests/bpf/prog_tests/dynptr.c
@@ -2,24 +2,66 @@
 /* Copyright (c) 2022 Facebook */
 
 #include <test_progs.h>
+#include <network_helpers.h>
 #include "dynptr_fail.skel.h"
 #include "dynptr_success.skel.h"
 
+enum test_setup_type {
+	SETUP_SYSCALL_SLEEP,
+	SETUP_SKB_PROG,
+	SETUP_SKB_PROG_TP,
+	SETUP_XDP_PROG,
+};
+
 static struct {
 	const char *prog_name;
-	const char *expected_err_msg;
-} dynptr_tests[] = {
-	/* success cases */
-	{"test_read_write", NULL},
-	{"test_data_slice", NULL},
-	{"test_ringbuf", NULL},
+	enum test_setup_type type;
+} success_tests[] = {
+	{"test_read_write", SETUP_SYSCALL_SLEEP},
+	{"test_dynptr_data", SETUP_SYSCALL_SLEEP},
+	{"test_dynptr_copy", SETUP_SYSCALL_SLEEP},
+	{"test_dynptr_copy_xdp", SETUP_XDP_PROG},
+	{"test_dynptr_memset_zero", SETUP_SYSCALL_SLEEP},
+	{"test_dynptr_memset_notzero", SETUP_SYSCALL_SLEEP},
+	{"test_dynptr_memset_zero_offset", SETUP_SYSCALL_SLEEP},
+	{"test_dynptr_memset_zero_adjusted", SETUP_SYSCALL_SLEEP},
+	{"test_dynptr_memset_overflow", SETUP_SYSCALL_SLEEP},
+	{"test_dynptr_memset_overflow_offset", SETUP_SYSCALL_SLEEP},
+	{"test_dynptr_memset_readonly", SETUP_SKB_PROG},
+	{"test_dynptr_memset_xdp_chunks", SETUP_XDP_PROG},
+	{"test_ringbuf", SETUP_SYSCALL_SLEEP},
+	{"test_skb_readonly", SETUP_SKB_PROG},
+	{"test_dynptr_skb_data", SETUP_SKB_PROG},
+	{"test_dynptr_skb_meta_data", SETUP_SKB_PROG},
+	{"test_dynptr_skb_meta_flags", SETUP_SKB_PROG},
+	{"test_adjust", SETUP_SYSCALL_SLEEP},
+	{"test_adjust_err", SETUP_SYSCALL_SLEEP},
+	{"test_zero_size_dynptr", SETUP_SYSCALL_SLEEP},
+	{"test_dynptr_is_null", SETUP_SYSCALL_SLEEP},
+	{"test_dynptr_is_rdonly", SETUP_SKB_PROG},
+	{"test_dynptr_clone", SETUP_SKB_PROG},
+	{"test_dynptr_skb_no_buff", SETUP_SKB_PROG},
+	{"test_dynptr_skb_strcmp", SETUP_SKB_PROG},
+	{"test_dynptr_skb_tp_btf", SETUP_SKB_PROG_TP},
+	{"test_probe_read_user_dynptr", SETUP_XDP_PROG},
+	{"test_probe_read_kernel_dynptr", SETUP_XDP_PROG},
+	{"test_probe_read_user_str_dynptr", SETUP_XDP_PROG},
+	{"test_probe_read_kernel_str_dynptr", SETUP_XDP_PROG},
+	{"test_copy_from_user_dynptr", SETUP_SYSCALL_SLEEP},
+	{"test_copy_from_user_str_dynptr", SETUP_SYSCALL_SLEEP},
+	{"test_copy_from_user_task_dynptr", SETUP_SYSCALL_SLEEP},
+	{"test_copy_from_user_task_str_dynptr", SETUP_SYSCALL_SLEEP},
 };
 
-static void verify_success(const char *prog_name)
+#define PAGE_SIZE_64K 65536
+
+static void verify_success(const char *prog_name, enum test_setup_type setup_type)
 {
+	char user_data[384] = {[0 ... 382] = 'a', '\0'};
 	struct dynptr_success *skel;
 	struct bpf_program *prog;
 	struct bpf_link *link;
+	int err;
 
 	skel = dynptr_success__open();
 	if (!ASSERT_OK_PTR(skel, "dynptr_success__open"))
@@ -27,23 +69,110 @@ static void verify_success(const char *prog_name)
 
 	skel->bss->pid = getpid();
 
-	dynptr_success__load(skel);
-	if (!ASSERT_OK_PTR(skel, "dynptr_success__load"))
-		goto cleanup;
-
 	prog = bpf_object__find_program_by_name(skel->obj, prog_name);
 	if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
 		goto cleanup;
 
-	link = bpf_program__attach(prog);
-	if (!ASSERT_OK_PTR(link, "bpf_program__attach"))
+	bpf_program__set_autoload(prog, true);
+
+	err = dynptr_success__load(skel);
+	if (!ASSERT_OK(err, "dynptr_success__load"))
 		goto cleanup;
 
-	usleep(1);
+	skel->bss->user_ptr = user_data;
+	skel->data->test_len[0] = sizeof(user_data);
+	memcpy(skel->bss->expected_str, user_data, sizeof(user_data));
 
-	ASSERT_EQ(skel->bss->err, 0, "err");
+	switch (setup_type) {
+	case SETUP_SYSCALL_SLEEP:
+		link = bpf_program__attach(prog);
+		if (!ASSERT_OK_PTR(link, "bpf_program__attach"))
+			goto cleanup;
+
+		usleep(1);
+
+		bpf_link__destroy(link);
+		break;
+	case SETUP_SKB_PROG:
+	{
+		int prog_fd;
+		char buf[64];
+
+		LIBBPF_OPTS(bpf_test_run_opts, topts,
+			    .data_in = &pkt_v4,
+			    .data_size_in = sizeof(pkt_v4),
+			    .data_out = buf,
+			    .data_size_out = sizeof(buf),
+			    .repeat = 1,
+		);
 
-	bpf_link__destroy(link);
+		prog_fd = bpf_program__fd(prog);
+		if (!ASSERT_GE(prog_fd, 0, "prog_fd"))
+			goto cleanup;
+
+		err = bpf_prog_test_run_opts(prog_fd, &topts);
+
+		if (!ASSERT_OK(err, "test_run"))
+			goto cleanup;
+
+		break;
+	}
+	case SETUP_SKB_PROG_TP:
+	{
+		struct __sk_buff skb = {};
+		struct bpf_object *obj;
+		int aux_prog_fd;
+
+		/* Just use its test_run to trigger kfree_skb tracepoint */
+		err = bpf_prog_test_load("./test_pkt_access.bpf.o", BPF_PROG_TYPE_SCHED_CLS,
+					 &obj, &aux_prog_fd);
+		if (!ASSERT_OK(err, "prog_load sched cls"))
+			goto cleanup;
+
+		LIBBPF_OPTS(bpf_test_run_opts, topts,
+			    .data_in = &pkt_v4,
+			    .data_size_in = sizeof(pkt_v4),
+			    .ctx_in = &skb,
+			    .ctx_size_in = sizeof(skb),
+		);
+
+		link = bpf_program__attach(prog);
+		if (!ASSERT_OK_PTR(link, "bpf_program__attach"))
+			goto cleanup;
+
+		err = bpf_prog_test_run_opts(aux_prog_fd, &topts);
+		bpf_link__destroy(link);
+
+		if (!ASSERT_OK(err, "test_run"))
+			goto cleanup;
+
+		break;
+	}
+	case SETUP_XDP_PROG:
+	{
+		char data[90000];
+		int err, prog_fd;
+		LIBBPF_OPTS(bpf_test_run_opts, opts,
+			    .data_in = &data,
+			    .repeat = 1,
+		);
+
+		if (getpagesize() == PAGE_SIZE_64K)
+			opts.data_size_in = sizeof(data);
+		else
+			opts.data_size_in = 5000;
+
+		prog_fd = bpf_program__fd(prog);
+		err = bpf_prog_test_run_opts(prog_fd, &opts);
+
+		if (!ASSERT_OK(err, "test_run"))
+			goto cleanup;
+
+		break;
+	}
+	}
+
+	ASSERT_EQ(skel->bss->err, 0, "err");
 
 cleanup:
 	dynptr_success__destroy(skel);
@@ -53,11 +182,11 @@ void test_dynptr(void)
 {
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(dynptr_tests); i++) {
-		if (!test__start_subtest(dynptr_tests[i].prog_name))
+	for (i = 0; i < ARRAY_SIZE(success_tests); i++) {
+		if (!test__start_subtest(success_tests[i].prog_name))
 			continue;
 
-		verify_success(dynptr_tests[i].prog_name);
+		verify_success(success_tests[i].prog_name, success_tests[i].type);
 	}
 
 	RUN_TESTS(dynptr_fail);
diff --git a/tools/testing/selftests/bpf/prog_tests/empty_skb.c b/tools/testing/selftests/bpf/prog_tests/empty_skb.c
index 32dd731e9070..438583e1f2d1 100644
--- a/tools/testing/selftests/bpf/prog_tests/empty_skb.c
+++ b/tools/testing/selftests/bpf/prog_tests/empty_skb.c
@@ -4,11 +4,6 @@
 #include <net/if.h>
 #include "empty_skb.skel.h"
 
-#define SYS(cmd) ({ \
-	if (!ASSERT_OK(system(cmd), (cmd))) \
-		goto out; \
-})
-
 void test_empty_skb(void)
 {
 	LIBBPF_OPTS(bpf_test_run_opts, tattr);
@@ -29,6 +24,7 @@ void test_empty_skb(void)
 		int *ifindex;
 		int err;
 		int ret;
+		int lwt_egress_ret; /* expected retval at lwt/egress */
 		bool success_on_tc;
 	} tests[] = {
 		/* Empty packets are always rejected. */
@@ -62,6 +58,7 @@ void test_empty_skb(void)
 			.data_size_in = sizeof(eth_hlen),
 			.ifindex = &veth_ifindex,
 			.ret = -ERANGE,
+			.lwt_egress_ret = -ERANGE,
 			.success_on_tc = true,
 		},
 		{
@@ -75,6 +72,7 @@ void test_empty_skb(void)
 			.data_size_in = sizeof(eth_hlen),
 			.ifindex = &ipip_ifindex,
 			.ret = -ERANGE,
+			.lwt_egress_ret = -ERANGE,
 		},
 
 		/* ETH_HLEN+1-sized packet should be redirected. */
@@ -84,6 +82,7 @@ void test_empty_skb(void)
 			.data_in = eth_hlen_pp,
 			.data_size_in = sizeof(eth_hlen_pp),
 			.ifindex = &veth_ifindex,
+			.lwt_egress_ret = 1, /* veth_xmit NET_XMIT_DROP */
 		},
 		{
 			.msg = "ipip ETH_HLEN+1 packet ingress",
@@ -93,18 +92,20 @@ void test_empty_skb(void)
 		},
 	};
 
-	SYS("ip netns add empty_skb");
+	SYS(out, "ip netns add empty_skb");
 	tok = open_netns("empty_skb");
-	SYS("ip link add veth0 type veth peer veth1");
-	SYS("ip link set dev veth0 up");
-	SYS("ip link set dev veth1 up");
-	SYS("ip addr add 10.0.0.1/8 dev veth0");
-	SYS("ip addr add 10.0.0.2/8 dev veth1");
+	if (!ASSERT_OK_PTR(tok, "setns"))
+		goto out;
+	SYS(out, "ip link add veth0 type veth peer veth1");
+	SYS(out, "ip link set dev veth0 up");
+	SYS(out, "ip link set dev veth1 up");
+	SYS(out, "ip addr add 10.0.0.1/8 dev veth0");
+	SYS(out, "ip addr add 10.0.0.2/8 dev veth1");
 	veth_ifindex = if_nametoindex("veth0");
 
-	SYS("ip link add ipip0 type ipip local 10.0.0.1 remote 10.0.0.2");
-	SYS("ip link set ipip0 up");
-	SYS("ip addr add 192.168.1.1/16 dev ipip0");
+	SYS(out, "ip link add ipip0 type ipip local 10.0.0.1 remote 10.0.0.2");
+	SYS(out, "ip link set ipip0 up");
+	SYS(out, "ip addr add 192.168.1.1/16 dev ipip0");
 	ipip_ifindex = if_nametoindex("ipip0");
 
 	bpf_obj = empty_skb__open_and_load();
@@ -113,8 +114,12 @@ void test_empty_skb(void)
 
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		bpf_object__for_each_program(prog, bpf_obj->obj) {
-			char buf[128];
+			bool at_egress = strstr(bpf_program__name(prog), "egress") != NULL;
 			bool at_tc = !strncmp(bpf_program__section_name(prog), "tc", 2);
+			int expected_ret;
+			char buf[128];
+
+			expected_ret = at_egress && !at_tc ? tests[i].lwt_egress_ret : tests[i].ret;
 
 			tattr.data_in = tests[i].data_in;
 			tattr.data_size_in = tests[i].data_size_in;
@@ -133,7 +138,7 @@ void test_empty_skb(void)
 			if (at_tc && tests[i].success_on_tc)
 				ASSERT_GE(bpf_obj->bss->ret, 0, buf);
 			else
-				ASSERT_EQ(bpf_obj->bss->ret, tests[i].ret, buf);
+				ASSERT_EQ(bpf_obj->bss->ret, expected_ret, buf);
 		}
 	}
 
@@ -142,5 +147,5 @@ out:
 		empty_skb__destroy(bpf_obj);
 	if (tok)
 		close_netns(tok);
-	system("ip netns del empty_skb");
+	SYS_NOFAIL("ip netns del empty_skb");
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/enable_stats.c b/tools/testing/selftests/bpf/prog_tests/enable_stats.c
index 2cb2085917e7..75f85d0fe74a 100644
--- a/tools/testing/selftests/bpf/prog_tests/enable_stats.c
+++ b/tools/testing/selftests/bpf/prog_tests/enable_stats.c
@@ -28,7 +28,7 @@ void test_enable_stats(void)
 
 	prog_fd = bpf_program__fd(skel->progs.test_enable_stats);
 	memset(&info, 0, info_len);
-	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len);
 	if (CHECK(err, "get_prog_info",
 		  "failed to get bpf_prog_info for fd %d\n", prog_fd))
 		goto cleanup;
diff --git a/tools/testing/selftests/bpf/prog_tests/exceptions.c b/tools/testing/selftests/bpf/prog_tests/exceptions.c
new file mode 100644
index 000000000000..516f4a13013c
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/exceptions.c
@@ -0,0 +1,409 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <network_helpers.h>
+
+#include "exceptions.skel.h"
+#include "exceptions_ext.skel.h"
+#include "exceptions_fail.skel.h"
+#include "exceptions_assert.skel.h"
+
+static char log_buf[1024 * 1024];
+
+static void test_exceptions_failure(void)
+{
+	RUN_TESTS(exceptions_fail);
+}
+
+static void test_exceptions_success(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, ropts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = 1,
+	);
+	struct exceptions_ext *eskel = NULL;
+	struct exceptions *skel;
+	int ret;
+
+	skel = exceptions__open();
+	if (!ASSERT_OK_PTR(skel, "exceptions__open"))
+		return;
+
+	ret = exceptions__load(skel);
+	if (!ASSERT_OK(ret, "exceptions__load"))
+		goto done;
+
+	if (!ASSERT_OK(bpf_map_update_elem(bpf_map__fd(skel->maps.jmp_table), &(int){0},
+					   &(int){bpf_program__fd(skel->progs.exception_tail_call_target)}, BPF_ANY),
+		       "bpf_map_update_elem jmp_table"))
+		goto done;
+
+#define RUN_SUCCESS(_prog, return_val)						  \
+	if (!test__start_subtest(#_prog)) goto _prog##_##return_val;		  \
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs._prog), &ropts); \
+	ASSERT_OK(ret, #_prog " prog run ret");					  \
+	ASSERT_EQ(ropts.retval, return_val, #_prog " prog run retval");		  \
+	_prog##_##return_val:
+
+	RUN_SUCCESS(exception_throw_always_1, 64);
+	RUN_SUCCESS(exception_throw_always_2, 32);
+	RUN_SUCCESS(exception_throw_unwind_1, 16);
+	RUN_SUCCESS(exception_throw_unwind_2, 32);
+	RUN_SUCCESS(exception_throw_default, 0);
+	RUN_SUCCESS(exception_throw_default_value, 5);
+	RUN_SUCCESS(exception_tail_call, 24);
+	RUN_SUCCESS(exception_ext, 0);
+	RUN_SUCCESS(exception_ext_mod_cb_runtime, 35);
+	RUN_SUCCESS(exception_throw_subprog, 1);
+	RUN_SUCCESS(exception_assert_nz_gfunc, 1);
+	RUN_SUCCESS(exception_assert_zero_gfunc, 1);
+	RUN_SUCCESS(exception_assert_neg_gfunc, 1);
+	RUN_SUCCESS(exception_assert_pos_gfunc, 1);
+	RUN_SUCCESS(exception_assert_negeq_gfunc, 1);
+	RUN_SUCCESS(exception_assert_poseq_gfunc, 1);
+	RUN_SUCCESS(exception_assert_nz_gfunc_with, 1);
+	RUN_SUCCESS(exception_assert_zero_gfunc_with, 1);
+	RUN_SUCCESS(exception_assert_neg_gfunc_with, 1);
+	RUN_SUCCESS(exception_assert_pos_gfunc_with, 1);
+	RUN_SUCCESS(exception_assert_negeq_gfunc_with, 1);
+	RUN_SUCCESS(exception_assert_poseq_gfunc_with, 1);
+	RUN_SUCCESS(exception_bad_assert_nz_gfunc, 0);
+	RUN_SUCCESS(exception_bad_assert_zero_gfunc, 0);
+	RUN_SUCCESS(exception_bad_assert_neg_gfunc, 0);
+	RUN_SUCCESS(exception_bad_assert_pos_gfunc, 0);
+	RUN_SUCCESS(exception_bad_assert_negeq_gfunc, 0);
+	RUN_SUCCESS(exception_bad_assert_poseq_gfunc, 0);
+	RUN_SUCCESS(exception_bad_assert_nz_gfunc_with, 100);
+	RUN_SUCCESS(exception_bad_assert_zero_gfunc_with, 105);
+	RUN_SUCCESS(exception_bad_assert_neg_gfunc_with, 200);
+	RUN_SUCCESS(exception_bad_assert_pos_gfunc_with, 0);
+	RUN_SUCCESS(exception_bad_assert_negeq_gfunc_with, 101);
+	RUN_SUCCESS(exception_bad_assert_poseq_gfunc_with, 99);
+	RUN_SUCCESS(exception_assert_range, 1);
+	RUN_SUCCESS(exception_assert_range_with, 1);
+	RUN_SUCCESS(exception_bad_assert_range, 0);
+	RUN_SUCCESS(exception_bad_assert_range_with, 10);
+
+#define RUN_EXT(load_ret, attach_err, expr, msg, after_link)			  \
+	{									  \
+		LIBBPF_OPTS(bpf_object_open_opts, o, .kernel_log_buf = log_buf,		 \
+						     .kernel_log_size = sizeof(log_buf), \
+						     .kernel_log_level = 2);		 \
+		exceptions_ext__destroy(eskel);					  \
+		eskel = exceptions_ext__open_opts(&o);				  \
+		struct bpf_program *prog = NULL;				  \
+		struct bpf_link *link = NULL;					  \
+		if (!ASSERT_OK_PTR(eskel, "exceptions_ext__open"))		  \
+			goto done;						  \
+		(expr);								  \
+		ASSERT_OK_PTR(bpf_program__name(prog), bpf_program__name(prog));  \
+		if (!ASSERT_EQ(exceptions_ext__load(eskel), load_ret,		  \
+			       "exceptions_ext__load"))	{			  \
+			printf("%s\n", log_buf);				  \
+			goto done;						  \
+		}								  \
+		if (load_ret != 0) {						  \
+			if (!ASSERT_OK_PTR(strstr(log_buf, msg), "strstr")) {	  \
+				printf("%s\n", log_buf);			  \
+				goto done;					  \
+			}							  \
+		}								  \
+		if (!load_ret && attach_err) {					  \
+			if (!ASSERT_ERR_PTR(link = bpf_program__attach(prog), "attach err")) \
+				goto done;					  \
+		} else if (!load_ret) {						  \
+			if (!ASSERT_OK_PTR(link = bpf_program__attach(prog), "attach ok"))  \
+				goto done;					  \
+			(void)(after_link);					  \
+			bpf_link__destroy(link);				  \
+		}								  \
+	}
+
+	if (test__start_subtest("non-throwing fentry -> exception_cb"))
+		RUN_EXT(-EINVAL, true, ({
+			prog = eskel->progs.pfentry;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_ext_mod_cb_runtime),
+				       "exception_cb_mod"), "set_attach_target"))
+				goto done;
+		}), "FENTRY/FEXIT programs cannot attach to exception callback", 0);
+
+	if (test__start_subtest("throwing fentry -> exception_cb"))
+		RUN_EXT(-EINVAL, true, ({
+			prog = eskel->progs.throwing_fentry;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_ext_mod_cb_runtime),
+				       "exception_cb_mod"), "set_attach_target"))
+				goto done;
+		}), "FENTRY/FEXIT programs cannot attach to exception callback", 0);
+
+	if (test__start_subtest("non-throwing fexit -> exception_cb"))
+		RUN_EXT(-EINVAL, true, ({
+			prog = eskel->progs.pfexit;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_ext_mod_cb_runtime),
+				       "exception_cb_mod"), "set_attach_target"))
+				goto done;
+		}), "FENTRY/FEXIT programs cannot attach to exception callback", 0);
+
+	if (test__start_subtest("throwing fexit -> exception_cb"))
+		RUN_EXT(-EINVAL, true, ({
+			prog = eskel->progs.throwing_fexit;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_ext_mod_cb_runtime),
+				       "exception_cb_mod"), "set_attach_target"))
+				goto done;
+		}), "FENTRY/FEXIT programs cannot attach to exception callback", 0);
+
+	if (test__start_subtest("throwing extension (with custom cb) -> exception_cb"))
+		RUN_EXT(-EINVAL, true, ({
+			prog = eskel->progs.throwing_exception_cb_extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_ext_mod_cb_runtime),
+				       "exception_cb_mod"), "set_attach_target"))
+				goto done;
+		}), "Extension programs cannot attach to exception callback", 0);
+
+	if (test__start_subtest("throwing extension -> global func in exception_cb"))
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.throwing_exception_cb_extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_ext_mod_cb_runtime),
+				       "exception_cb_mod_global"), "set_attach_target"))
+				goto done;
+		}), "", ({ RUN_SUCCESS(exception_ext_mod_cb_runtime, 131); }));
+
+	if (test__start_subtest("throwing extension (with custom cb) -> global func in exception_cb"))
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.throwing_extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_ext),
+				       "exception_ext_global"), "set_attach_target"))
+				goto done;
+		}), "", ({ RUN_SUCCESS(exception_ext, 128); }));
+
+	if (test__start_subtest("non-throwing fentry -> non-throwing subprog"))
+		/* non-throwing fentry -> non-throwing subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.pfentry;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("throwing fentry -> non-throwing subprog"))
+		/* throwing fentry -> non-throwing subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.throwing_fentry;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("non-throwing fentry -> throwing subprog"))
+		/* non-throwing fentry -> throwing subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.pfentry;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "throwing_subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("throwing fentry -> throwing subprog"))
+		/* throwing fentry -> throwing subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.throwing_fentry;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "throwing_subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("non-throwing fexit -> non-throwing subprog"))
+		/* non-throwing fexit -> non-throwing subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.pfexit;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("throwing fexit -> non-throwing subprog"))
+		/* throwing fexit -> non-throwing subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.throwing_fexit;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("non-throwing fexit -> throwing subprog"))
+		/* non-throwing fexit -> throwing subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.pfexit;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "throwing_subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("throwing fexit -> throwing subprog"))
+		/* throwing fexit -> throwing subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.throwing_fexit;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "throwing_subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	/* fmod_ret not allowed for subprog - Check so we remember to handle its
+	 * throwing specification compatibility with target when supported.
+	 */
+	if (test__start_subtest("non-throwing fmod_ret -> non-throwing subprog"))
+		RUN_EXT(-EINVAL, true, ({
+			prog = eskel->progs.pfmod_ret;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "subprog"), "set_attach_target"))
+				goto done;
+		}), "can't modify return codes of BPF program", 0);
+
+	/* fmod_ret not allowed for subprog - Check so we remember to handle its
+	 * throwing specification compatibility with target when supported.
+	 */
+	if (test__start_subtest("non-throwing fmod_ret -> non-throwing global subprog"))
+		RUN_EXT(-EINVAL, true, ({
+			prog = eskel->progs.pfmod_ret;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "global_subprog"), "set_attach_target"))
+				goto done;
+		}), "can't modify return codes of BPF program", 0);
+
+	if (test__start_subtest("non-throwing extension -> non-throwing subprog"))
+		/* non-throwing extension -> non-throwing subprog : BAD (!global) */
+		RUN_EXT(-EINVAL, true, ({
+			prog = eskel->progs.extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "subprog"), "set_attach_target"))
+				goto done;
+		}), "subprog() is not a global function", 0);
+
+	if (test__start_subtest("non-throwing extension -> throwing subprog"))
+		/* non-throwing extension -> throwing subprog : BAD (!global) */
+		RUN_EXT(-EINVAL, true, ({
+			prog = eskel->progs.extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "throwing_subprog"), "set_attach_target"))
+				goto done;
+		}), "throwing_subprog() is not a global function", 0);
+
+	if (test__start_subtest("non-throwing extension -> non-throwing subprog"))
+		/* non-throwing extension -> non-throwing global subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "global_subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("non-throwing extension -> throwing global subprog"))
+		/* non-throwing extension -> throwing global subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "throwing_global_subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("throwing extension -> throwing global subprog"))
+		/* throwing extension -> throwing global subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.throwing_extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "throwing_global_subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("throwing extension -> non-throwing global subprog"))
+		/* throwing extension -> non-throwing global subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.throwing_extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "global_subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("non-throwing extension -> main subprog"))
+		/* non-throwing extension -> main subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "exception_throw_subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+	if (test__start_subtest("throwing extension -> main subprog"))
+		/* throwing extension -> main subprog : OK */
+		RUN_EXT(0, false, ({
+			prog = eskel->progs.throwing_extension;
+			bpf_program__set_autoload(prog, true);
+			if (!ASSERT_OK(bpf_program__set_attach_target(prog,
+				       bpf_program__fd(skel->progs.exception_throw_subprog),
+				       "exception_throw_subprog"), "set_attach_target"))
+				goto done;
+		}), "", 0);
+
+done:
+	exceptions_ext__destroy(eskel);
+	exceptions__destroy(skel);
+}
+
+static void test_exceptions_assertions(void)
+{
+	RUN_TESTS(exceptions_assert);
+}
+
+void test_exceptions(void)
+{
+	test_exceptions_success();
+	test_exceptions_failure();
+	test_exceptions_assertions();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/fd_array.c b/tools/testing/selftests/bpf/prog_tests/fd_array.c
new file mode 100644
index 000000000000..c534b4d5f9da
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/fd_array.c
@@ -0,0 +1,441 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+
+#include <linux/btf.h>
+#include <bpf/bpf.h>
+
+#include "../test_btf.h"
+
+static inline int new_map(void)
+{
+	const char *name = NULL;
+	__u32 max_entries = 1;
+	__u32 value_size = 8;
+	__u32 key_size = 4;
+
+	return bpf_map_create(BPF_MAP_TYPE_ARRAY, name,
+			      key_size, value_size,
+			      max_entries, NULL);
+}
+
+static int new_btf(void)
+{
+	struct btf_blob {
+		struct btf_header btf_hdr;
+		__u32 types[8];
+		__u32 str;
+	} raw_btf = {
+		.btf_hdr = {
+			.magic = BTF_MAGIC,
+			.version = BTF_VERSION,
+			.hdr_len = sizeof(struct btf_header),
+			.type_len = sizeof(raw_btf.types),
+			.str_off = offsetof(struct btf_blob, str) - offsetof(struct btf_blob, types),
+			.str_len = sizeof(raw_btf.str),
+		},
+		.types = {
+			/* long */
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 64, 8),  /* [1] */
+			/* unsigned long */
+			BTF_TYPE_INT_ENC(0, 0, 0, 64, 8),  /* [2] */
+		},
+	};
+
+	return bpf_btf_load(&raw_btf, sizeof(raw_btf), NULL);
+}
+
+#define Close(FD) do {		\
+	if ((FD) >= 0) {	\
+		close(FD);	\
+		FD = -1;	\
+	}			\
+} while(0)
+
+static bool map_exists(__u32 id)
+{
+	int fd;
+
+	fd = bpf_map_get_fd_by_id(id);
+	if (fd >= 0) {
+		close(fd);
+		return true;
+	}
+	return false;
+}
+
+static bool btf_exists(__u32 id)
+{
+	int fd;
+
+	fd = bpf_btf_get_fd_by_id(id);
+	if (fd >= 0) {
+		close(fd);
+		return true;
+	}
+	return false;
+}
+
+static inline int bpf_prog_get_map_ids(int prog_fd, __u32 *nr_map_ids, __u32 *map_ids)
+{
+	__u32 len = sizeof(struct bpf_prog_info);
+	struct bpf_prog_info info;
+	int err;
+
+	memset(&info, 0, len);
+	info.nr_map_ids = *nr_map_ids;
+	info.map_ids = ptr_to_u64(map_ids);
+
+	err = bpf_prog_get_info_by_fd(prog_fd, &info, &len);
+	if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd"))
+		return -1;
+
+	*nr_map_ids = info.nr_map_ids;
+
+	return 0;
+}
+
+static int __load_test_prog(int map_fd, const int *fd_array, int fd_array_cnt)
+{
+	/* A trivial program which uses one map */
+	struct bpf_insn insns[] = {
+		BPF_LD_MAP_FD(BPF_REG_1, map_fd),
+		BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	LIBBPF_OPTS(bpf_prog_load_opts, opts);
+
+	opts.fd_array = fd_array;
+	opts.fd_array_cnt = fd_array_cnt;
+
+	return bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "GPL", insns, ARRAY_SIZE(insns), &opts);
+}
+
+static int load_test_prog(const int *fd_array, int fd_array_cnt)
+{
+	int map_fd;
+	int ret;
+
+	map_fd = new_map();
+	if (!ASSERT_GE(map_fd, 0, "new_map"))
+		return map_fd;
+
+	ret = __load_test_prog(map_fd, fd_array, fd_array_cnt);
+	close(map_fd);
+	return ret;
+}
+
+static bool check_expected_map_ids(int prog_fd, int expected, __u32 *map_ids, __u32 *nr_map_ids)
+{
+	int err;
+
+	err = bpf_prog_get_map_ids(prog_fd, nr_map_ids, map_ids);
+	if (!ASSERT_OK(err, "bpf_prog_get_map_ids"))
+		return false;
+	if (!ASSERT_EQ(*nr_map_ids, expected, "unexpected nr_map_ids"))
+		return false;
+
+	return true;
+}
+
+/*
+ * Load a program, which uses one map. No fd_array maps are present.
+ * On return only one map is expected to be bound to prog.
+ */
+static void check_fd_array_cnt__no_fd_array(void)
+{
+	__u32 map_ids[16];
+	__u32 nr_map_ids;
+	int prog_fd = -1;
+
+	prog_fd = load_test_prog(NULL, 0);
+	if (!ASSERT_GE(prog_fd, 0, "BPF_PROG_LOAD"))
+		return;
+	nr_map_ids = ARRAY_SIZE(map_ids);
+	check_expected_map_ids(prog_fd, 1, map_ids, &nr_map_ids);
+	close(prog_fd);
+}
+
+/*
+ * Load a program, which uses one map, and pass two extra, non-equal, maps in
+ * fd_array with fd_array_cnt=2. On return three maps are expected to be bound
+ * to the program.
+ */
+static void check_fd_array_cnt__fd_array_ok(void)
+{
+	int extra_fds[2] = { -1, -1 };
+	__u32 map_ids[16];
+	__u32 nr_map_ids;
+	int prog_fd = -1;
+
+	extra_fds[0] = new_map();
+	if (!ASSERT_GE(extra_fds[0], 0, "new_map"))
+		goto cleanup;
+	extra_fds[1] = new_map();
+	if (!ASSERT_GE(extra_fds[1], 0, "new_map"))
+		goto cleanup;
+	prog_fd = load_test_prog(extra_fds, 2);
+	if (!ASSERT_GE(prog_fd, 0, "BPF_PROG_LOAD"))
+		goto cleanup;
+	nr_map_ids = ARRAY_SIZE(map_ids);
+	if (!check_expected_map_ids(prog_fd, 3, map_ids, &nr_map_ids))
+		goto cleanup;
+
+	/* maps should still exist when original file descriptors are closed */
+	Close(extra_fds[0]);
+	Close(extra_fds[1]);
+	if (!ASSERT_EQ(map_exists(map_ids[0]), true, "map_ids[0] should exist"))
+		goto cleanup;
+	if (!ASSERT_EQ(map_exists(map_ids[1]), true, "map_ids[1] should exist"))
+		goto cleanup;
+
+	/* some fds might be invalid, so ignore return codes */
+cleanup:
+	Close(extra_fds[1]);
+	Close(extra_fds[0]);
+	Close(prog_fd);
+}
+
+/*
+ * Load a program with a few extra maps duplicated in the fd_array.
+ * After the load maps should only be referenced once.
+ */
+static void check_fd_array_cnt__duplicated_maps(void)
+{
+	int extra_fds[4] = { -1, -1, -1, -1 };
+	__u32 map_ids[16];
+	__u32 nr_map_ids;
+	int prog_fd = -1;
+
+	extra_fds[0] = extra_fds[2] = new_map();
+	if (!ASSERT_GE(extra_fds[0], 0, "new_map"))
+		goto cleanup;
+	extra_fds[1] = extra_fds[3] = new_map();
+	if (!ASSERT_GE(extra_fds[1], 0, "new_map"))
+		goto cleanup;
+	prog_fd = load_test_prog(extra_fds, 4);
+	if (!ASSERT_GE(prog_fd, 0, "BPF_PROG_LOAD"))
+		goto cleanup;
+	nr_map_ids = ARRAY_SIZE(map_ids);
+	if (!check_expected_map_ids(prog_fd, 3, map_ids, &nr_map_ids))
+		goto cleanup;
+
+	/* maps should still exist when original file descriptors are closed */
+	Close(extra_fds[0]);
+	Close(extra_fds[1]);
+	if (!ASSERT_EQ(map_exists(map_ids[0]), true, "map should exist"))
+		goto cleanup;
+	if (!ASSERT_EQ(map_exists(map_ids[1]), true, "map should exist"))
+		goto cleanup;
+
+	/* some fds might be invalid, so ignore return codes */
+cleanup:
+	Close(extra_fds[1]);
+	Close(extra_fds[0]);
+	Close(prog_fd);
+}
+
+/*
+ * Check that if maps which are referenced by a program are
+ * passed in fd_array, then they will be referenced only once
+ */
+static void check_fd_array_cnt__referenced_maps_in_fd_array(void)
+{
+	int extra_fds[1] = { -1 };
+	__u32 map_ids[16];
+	__u32 nr_map_ids;
+	int prog_fd = -1;
+
+	extra_fds[0] = new_map();
+	if (!ASSERT_GE(extra_fds[0], 0, "new_map"))
+		goto cleanup;
+	prog_fd = __load_test_prog(extra_fds[0], extra_fds, 1);
+	if (!ASSERT_GE(prog_fd, 0, "BPF_PROG_LOAD"))
+		goto cleanup;
+	nr_map_ids = ARRAY_SIZE(map_ids);
+	if (!check_expected_map_ids(prog_fd, 1, map_ids, &nr_map_ids))
+		goto cleanup;
+
+	/* map should still exist when original file descriptor is closed */
+	Close(extra_fds[0]);
+	if (!ASSERT_EQ(map_exists(map_ids[0]), true, "map should exist"))
+		goto cleanup;
+
+	/* some fds might be invalid, so ignore return codes */
+cleanup:
+	Close(extra_fds[0]);
+	Close(prog_fd);
+}
+
+static int get_btf_id_by_fd(int btf_fd, __u32 *id)
+{
+	struct bpf_btf_info info;
+	__u32 info_len = sizeof(info);
+	int err;
+
+	memset(&info, 0, info_len);
+	err = bpf_btf_get_info_by_fd(btf_fd, &info, &info_len);
+	if (err)
+		return err;
+	if (id)
+		*id = info.id;
+	return 0;
+}
+
+/*
+ * Check that fd_array operates properly for btfs. Namely, to check that
+ * passing a btf fd in fd_array increases its reference count, do the
+ * following:
+ *  1) Create a new btf, it's referenced only by a file descriptor, so refcnt=1
+ *  2) Load a BPF prog with fd_array[0] = btf_fd; now btf's refcnt=2
+ *  3) Close the btf_fd, now refcnt=1
+ * Wait and check that BTF still exists.
+ */
+static void check_fd_array_cnt__referenced_btfs(void)
+{
+	int extra_fds[1] = { -1 };
+	int prog_fd = -1;
+	__u32 btf_id;
+	int tries;
+	int err;
+
+	extra_fds[0] = new_btf();
+	if (!ASSERT_GE(extra_fds[0], 0, "new_btf"))
+		goto cleanup;
+	prog_fd = load_test_prog(extra_fds, 1);
+	if (!ASSERT_GE(prog_fd, 0, "BPF_PROG_LOAD"))
+		goto cleanup;
+
+	/* btf should still exist when original file descriptor is closed */
+	err = get_btf_id_by_fd(extra_fds[0], &btf_id);
+	if (!ASSERT_EQ(err, 0, "get_btf_id_by_fd"))
+		goto cleanup;
+
+	Close(extra_fds[0]);
+
+	if (!ASSERT_GE(kern_sync_rcu(), 0, "kern_sync_rcu 1"))
+		goto cleanup;
+
+	if (!ASSERT_EQ(btf_exists(btf_id), true, "btf should exist"))
+		goto cleanup;
+
+	Close(prog_fd);
+
+	/* The program is freed by a workqueue, so no reliable
+	 * way to sync, so just wait a bit (max ~1 second). */
+	for (tries = 100; tries >= 0; tries--) {
+		usleep(1000);
+
+		if (!btf_exists(btf_id))
+			break;
+
+		if (tries)
+			continue;
+
+		PRINT_FAIL("btf should have been freed");
+	}
+
+	/* some fds might be invalid, so ignore return codes */
+cleanup:
+	Close(extra_fds[0]);
+	Close(prog_fd);
+}
+
+/*
+ * Test that a program with trash in fd_array can't be loaded:
+ * only map and BTF file descriptors should be accepted.
+ */
+static void check_fd_array_cnt__fd_array_with_trash(void)
+{
+	int extra_fds[3] = { -1, -1, -1 };
+	int prog_fd = -1;
+
+	extra_fds[0] = new_map();
+	if (!ASSERT_GE(extra_fds[0], 0, "new_map"))
+		goto cleanup;
+	extra_fds[1] = new_btf();
+	if (!ASSERT_GE(extra_fds[1], 0, "new_btf"))
+		goto cleanup;
+
+	/* trash 1: not a file descriptor */
+	extra_fds[2] = 0xbeef;
+	prog_fd = load_test_prog(extra_fds, 3);
+	if (!ASSERT_EQ(prog_fd, -EBADF, "prog should have been rejected with -EBADF"))
+		goto cleanup;
+
+	/* trash 2: not a map or btf */
+	extra_fds[2] = socket(AF_INET, SOCK_STREAM, 0);
+	if (!ASSERT_GE(extra_fds[2], 0, "socket"))
+		goto cleanup;
+
+	prog_fd = load_test_prog(extra_fds, 3);
+	if (!ASSERT_EQ(prog_fd, -EINVAL, "prog should have been rejected with -EINVAL"))
+		goto cleanup;
+
+	/* Validate that the prog is ok if trash is removed */
+	Close(extra_fds[2]);
+	extra_fds[2] = new_btf();
+	if (!ASSERT_GE(extra_fds[2], 0, "new_btf"))
+		goto cleanup;
+
+	prog_fd = load_test_prog(extra_fds, 3);
+	if (!ASSERT_GE(prog_fd, 0, "prog should have been loaded"))
+		goto cleanup;
+
+	/* some fds might be invalid, so ignore return codes */
+cleanup:
+	Close(extra_fds[2]);
+	Close(extra_fds[1]);
+	Close(extra_fds[0]);
+}
+
+/*
+ * Test that a program with too big fd_array can't be loaded.
+ */
+static void check_fd_array_cnt__fd_array_too_big(void)
+{
+	int extra_fds[65];
+	int prog_fd = -1;
+	int i;
+
+	for (i = 0; i < 65; i++) {
+		extra_fds[i] = new_map();
+		if (!ASSERT_GE(extra_fds[i], 0, "new_map"))
+			goto cleanup_fds;
+	}
+
+	prog_fd = load_test_prog(extra_fds, 65);
+	ASSERT_EQ(prog_fd, -E2BIG, "prog should have been rejected with -E2BIG");
+
+cleanup_fds:
+	while (i > 0)
+		Close(extra_fds[--i]);
+}
+
+void test_fd_array_cnt(void)
+{
+	if (test__start_subtest("no-fd-array"))
+		check_fd_array_cnt__no_fd_array();
+
+	if (test__start_subtest("fd-array-ok"))
+		check_fd_array_cnt__fd_array_ok();
+
+	if (test__start_subtest("fd-array-dup-input"))
+		check_fd_array_cnt__duplicated_maps();
+
+	if (test__start_subtest("fd-array-ref-maps-in-array"))
+		check_fd_array_cnt__referenced_maps_in_fd_array();
+
+	if (test__start_subtest("fd-array-ref-btfs"))
+		check_fd_array_cnt__referenced_btfs();
+
+	if (test__start_subtest("fd-array-trash-input"))
+		check_fd_array_cnt__fd_array_with_trash();
+
+	if (test__start_subtest("fd-array-2big"))
+		check_fd_array_cnt__fd_array_too_big();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/fd_htab_lookup.c b/tools/testing/selftests/bpf/prog_tests/fd_htab_lookup.c
new file mode 100644
index 000000000000..ca46fdd6e1ae
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/fd_htab_lookup.c
@@ -0,0 +1,192 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2025. Huawei Technologies Co., Ltd */
+#define _GNU_SOURCE
+#include <stdbool.h>
+#include <test_progs.h>
+#include "fd_htab_lookup.skel.h"
+
+struct htab_op_ctx {
+	int fd;
+	int loop;
+	unsigned int entries;
+	bool stop;
+};
+
+#define ERR_TO_RETVAL(where, err) ((void *)(long)(((where) << 12) | (-err)))
+
+static void *htab_lookup_fn(void *arg)
+{
+	struct htab_op_ctx *ctx = arg;
+	int i = 0;
+
+	while (i++ < ctx->loop && !ctx->stop) {
+		unsigned int j;
+
+		for (j = 0; j < ctx->entries; j++) {
+			unsigned int key = j, zero = 0, value;
+			int inner_fd, err;
+
+			err = bpf_map_lookup_elem(ctx->fd, &key, &value);
+			if (err) {
+				ctx->stop = true;
+				return ERR_TO_RETVAL(1, err);
+			}
+
+			inner_fd = bpf_map_get_fd_by_id(value);
+			if (inner_fd < 0) {
+				/* The old map has been freed */
+				if (inner_fd == -ENOENT)
+					continue;
+				ctx->stop = true;
+				return ERR_TO_RETVAL(2, inner_fd);
+			}
+
+			err = bpf_map_lookup_elem(inner_fd, &zero, &value);
+			if (err) {
+				close(inner_fd);
+				ctx->stop = true;
+				return ERR_TO_RETVAL(3, err);
+			}
+			close(inner_fd);
+
+			if (value != key) {
+				ctx->stop = true;
+				return ERR_TO_RETVAL(4, -EINVAL);
+			}
+		}
+	}
+
+	return NULL;
+}
+
+static void *htab_update_fn(void *arg)
+{
+	struct htab_op_ctx *ctx = arg;
+	int i = 0;
+
+	while (i++ < ctx->loop && !ctx->stop) {
+		unsigned int j;
+
+		for (j = 0; j < ctx->entries; j++) {
+			unsigned int key = j, zero = 0;
+			int inner_fd, err;
+
+			inner_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 4, 1, NULL);
+			if (inner_fd < 0) {
+				ctx->stop = true;
+				return ERR_TO_RETVAL(1, inner_fd);
+			}
+
+			err = bpf_map_update_elem(inner_fd, &zero, &key, 0);
+			if (err) {
+				close(inner_fd);
+				ctx->stop = true;
+				return ERR_TO_RETVAL(2, err);
+			}
+
+			err = bpf_map_update_elem(ctx->fd, &key, &inner_fd, BPF_EXIST);
+			if (err) {
+				close(inner_fd);
+				ctx->stop = true;
+				return ERR_TO_RETVAL(3, err);
+			}
+			close(inner_fd);
+		}
+	}
+
+	return NULL;
+}
+
+static int setup_htab(int fd, unsigned int entries)
+{
+	unsigned int i;
+
+	for (i = 0; i < entries; i++) {
+		unsigned int key = i, zero = 0;
+		int inner_fd, err;
+
+		inner_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 4, 1, NULL);
+		if (!ASSERT_OK_FD(inner_fd, "new array"))
+			return -1;
+
+		err = bpf_map_update_elem(inner_fd, &zero, &key, 0);
+		if (!ASSERT_OK(err, "init array")) {
+			close(inner_fd);
+			return -1;
+		}
+
+		err = bpf_map_update_elem(fd, &key, &inner_fd, 0);
+		if (!ASSERT_OK(err, "init outer")) {
+			close(inner_fd);
+			return -1;
+		}
+		close(inner_fd);
+	}
+
+	return 0;
+}
+
+static int get_int_from_env(const char *name, int dft)
+{
+	const char *value;
+
+	value = getenv(name);
+	if (!value)
+		return dft;
+
+	return atoi(value);
+}
+
+void test_fd_htab_lookup(void)
+{
+	unsigned int i, wr_nr = 8, rd_nr = 16;
+	pthread_t tids[wr_nr + rd_nr];
+	struct fd_htab_lookup *skel;
+	struct htab_op_ctx ctx;
+	int err;
+
+	skel = fd_htab_lookup__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "fd_htab_lookup__open_and_load"))
+		return;
+
+	ctx.fd = bpf_map__fd(skel->maps.outer_map);
+	ctx.loop = get_int_from_env("FD_HTAB_LOOP_NR", 5);
+	ctx.stop = false;
+	ctx.entries = 8;
+
+	err = setup_htab(ctx.fd, ctx.entries);
+	if (err)
+		goto destroy;
+
+	memset(tids, 0, sizeof(tids));
+	for (i = 0; i < wr_nr; i++) {
+		err = pthread_create(&tids[i], NULL, htab_update_fn, &ctx);
+		if (!ASSERT_OK(err, "pthread_create")) {
+			ctx.stop = true;
+			goto reap;
+		}
+	}
+	for (i = 0; i < rd_nr; i++) {
+		err = pthread_create(&tids[i + wr_nr], NULL, htab_lookup_fn, &ctx);
+		if (!ASSERT_OK(err, "pthread_create")) {
+			ctx.stop = true;
+			goto reap;
+		}
+	}
+
+reap:
+	for (i = 0; i < wr_nr + rd_nr; i++) {
+		void *ret = NULL;
+		char desc[32];
+
+		if (!tids[i])
+			continue;
+
+		snprintf(desc, sizeof(desc), "thread %u", i + 1);
+		err = pthread_join(tids[i], &ret);
+		ASSERT_OK(err, desc);
+		ASSERT_EQ(ret, NULL, desc);
+	}
+destroy:
+	fd_htab_lookup__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
index 130f5b82d2e6..5ef1804e44df 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
@@ -12,13 +12,24 @@ void test_fentry_fexit(void)
 	int err, prog_fd, i;
 	LIBBPF_OPTS(bpf_test_run_opts, topts);
 
-	fentry_skel = fentry_test_lskel__open_and_load();
+	fentry_skel = fentry_test_lskel__open();
 	if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load"))
 		goto close_prog;
-	fexit_skel = fexit_test_lskel__open_and_load();
+
+	fentry_skel->keyring_id	= KEY_SPEC_SESSION_KEYRING;
+	err = fentry_test_lskel__load(fentry_skel);
+	if (!ASSERT_OK(err, "fentry_skel_load"))
+		goto close_prog;
+
+	fexit_skel = fexit_test_lskel__open();
 	if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load"))
 		goto close_prog;
 
+	fexit_skel->keyring_id	= KEY_SPEC_SESSION_KEYRING;
+	err = fexit_test_lskel__load(fexit_skel);
+	if (!ASSERT_OK(err, "fexit_skel_load"))
+		goto close_prog;
+
 	err = fentry_test_lskel__attach(fentry_skel);
 	if (!ASSERT_OK(err, "fentry_attach"))
 		goto close_prog;
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
index c0d1d61d5f66..ec882328eb59 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
@@ -2,8 +2,9 @@
 /* Copyright (c) 2019 Facebook */
 #include <test_progs.h>
 #include "fentry_test.lskel.h"
+#include "fentry_many_args.skel.h"
 
-static int fentry_test(struct fentry_test_lskel *fentry_skel)
+static int fentry_test_common(struct fentry_test_lskel *fentry_skel)
 {
 	int err, prog_fd, i;
 	int link_fd;
@@ -37,22 +38,61 @@ static int fentry_test(struct fentry_test_lskel *fentry_skel)
 	return 0;
 }
 
-void test_fentry_test(void)
+static void fentry_test(void)
 {
 	struct fentry_test_lskel *fentry_skel = NULL;
 	int err;
 
-	fentry_skel = fentry_test_lskel__open_and_load();
-	if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load"))
+	fentry_skel = fentry_test_lskel__open();
+	if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_open"))
+		goto cleanup;
+
+	fentry_skel->keyring_id	= KEY_SPEC_SESSION_KEYRING;
+	err = fentry_test_lskel__load(fentry_skel);
+	if (!ASSERT_OK(err, "fentry_skel_load"))
 		goto cleanup;
 
-	err = fentry_test(fentry_skel);
+	err = fentry_test_common(fentry_skel);
 	if (!ASSERT_OK(err, "fentry_first_attach"))
 		goto cleanup;
 
-	err = fentry_test(fentry_skel);
+	err = fentry_test_common(fentry_skel);
 	ASSERT_OK(err, "fentry_second_attach");
 
 cleanup:
 	fentry_test_lskel__destroy(fentry_skel);
 }
+
+static void fentry_many_args(void)
+{
+	struct fentry_many_args *fentry_skel = NULL;
+	int err;
+
+	fentry_skel = fentry_many_args__open_and_load();
+	if (!ASSERT_OK_PTR(fentry_skel, "fentry_many_args_skel_load"))
+		goto cleanup;
+
+	err = fentry_many_args__attach(fentry_skel);
+	if (!ASSERT_OK(err, "fentry_many_args_attach"))
+		goto cleanup;
+
+	ASSERT_OK(trigger_module_test_read(1), "trigger_read");
+
+	ASSERT_EQ(fentry_skel->bss->test1_result, 1,
+		  "fentry_many_args_result1");
+	ASSERT_EQ(fentry_skel->bss->test2_result, 1,
+		  "fentry_many_args_result2");
+	ASSERT_EQ(fentry_skel->bss->test3_result, 1,
+		  "fentry_many_args_result3");
+
+cleanup:
+	fentry_many_args__destroy(fentry_skel);
+}
+
+void test_fentry_test(void)
+{
+	if (test__start_subtest("fentry"))
+		fentry_test();
+	if (test__start_subtest("fentry_many_args"))
+		fentry_many_args();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
index 20f5fa0fcec9..f29fc789c14b 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -79,7 +79,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 		return;
 
 	info_len = sizeof(prog_info);
-	err = bpf_obj_get_info_by_fd(tgt_fd, &prog_info, &info_len);
+	err = bpf_prog_get_info_by_fd(tgt_fd, &prog_info, &info_len);
 	if (!ASSERT_OK(err, "tgt_fd_get_info"))
 		goto close_prog;
 
@@ -136,8 +136,8 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 
 		info_len = sizeof(link_info);
 		memset(&link_info, 0, sizeof(link_info));
-		err = bpf_obj_get_info_by_fd(bpf_link__fd(link[i]),
-					     &link_info, &info_len);
+		err = bpf_link_get_info_by_fd(bpf_link__fd(link[i]),
+					      &link_info, &info_len);
 		ASSERT_OK(err, "link_fd_get_info");
 		ASSERT_EQ(link_info.tracing.attach_type,
 			  bpf_program__expected_attach_type(prog[i]),
@@ -348,7 +348,8 @@ static void test_func_sockmap_update(void)
 }
 
 static void test_obj_load_failure_common(const char *obj_file,
-					 const char *target_obj_file)
+					 const char *target_obj_file,
+					 const char *exp_msg)
 {
 	/*
 	 * standalone test that asserts failure to load freplace prog
@@ -356,6 +357,7 @@ static void test_obj_load_failure_common(const char *obj_file,
 	 */
 	struct bpf_object *obj = NULL, *pkt_obj;
 	struct bpf_program *prog;
+	char log_buf[64 * 1024];
 	int err, pkt_fd;
 	__u32 duration = 0;
 
@@ -374,11 +376,21 @@ static void test_obj_load_failure_common(const char *obj_file,
 	err = bpf_program__set_attach_target(prog, pkt_fd, NULL);
 	ASSERT_OK(err, "set_attach_target");
 
+	log_buf[0] = '\0';
+	if (exp_msg)
+		bpf_program__set_log_buf(prog, log_buf, sizeof(log_buf));
+	if (env.verbosity > VERBOSE_NONE)
+		bpf_program__set_log_level(prog, 2);
+
 	/* It should fail to load the program */
 	err = bpf_object__load(obj);
+	if (env.verbosity > VERBOSE_NONE && exp_msg) /* we overtook log */
+		printf("VERIFIER LOG:\n================\n%s\n================\n", log_buf);
 	if (CHECK(!err, "bpf_obj_load should fail", "err %d\n", err))
 		goto close_prog;
 
+	if (exp_msg)
+		ASSERT_HAS_SUBSTR(log_buf, exp_msg, "fail_msg");
 close_prog:
 	bpf_object__close(obj);
 	bpf_object__close(pkt_obj);
@@ -388,14 +400,24 @@ static void test_func_replace_return_code(void)
 {
 	/* test invalid return code in the replaced program */
 	test_obj_load_failure_common("./freplace_connect_v4_prog.bpf.o",
-				     "./connect4_prog.bpf.o");
+				     "./connect4_prog.bpf.o", NULL);
 }
 
 static void test_func_map_prog_compatibility(void)
 {
 	/* test with spin lock map value in the replaced program */
 	test_obj_load_failure_common("./freplace_attach_probe.bpf.o",
-				     "./test_attach_probe.bpf.o");
+				     "./test_attach_probe.bpf.o", NULL);
+}
+
+static void test_func_replace_unreliable(void)
+{
+	/* freplace'ing unreliable main prog should fail with error
+	 * "Cannot replace static functions"
+	 */
+	test_obj_load_failure_common("freplace_unreliable_prog.bpf.o",
+				     "./verifier_btf_unreliable_prog.bpf.o",
+				     "Cannot replace static functions");
 }
 
 static void test_func_replace_global_func(void)
@@ -417,7 +439,7 @@ static int find_prog_btf_id(const char *name, __u32 attach_prog_fd)
 	struct btf *btf;
 	int ret;
 
-	ret = bpf_obj_get_info_by_fd(attach_prog_fd, &info, &info_len);
+	ret = bpf_prog_get_info_by_fd(attach_prog_fd, &info, &info_len);
 	if (ret)
 		return ret;
 
@@ -483,12 +505,12 @@ static void test_fentry_to_cgroup_bpf(void)
 	if (!ASSERT_GE(fentry_fd, 0, "load_fentry"))
 		goto cleanup;
 
-	/* Make sure bpf_obj_get_info_by_fd works correctly when attaching
+	/* Make sure bpf_prog_get_info_by_fd works correctly when attaching
 	 * to another BPF program.
 	 */
 
-	ASSERT_OK(bpf_obj_get_info_by_fd(fentry_fd, &info, &info_len),
-		  "bpf_obj_get_info_by_fd");
+	ASSERT_OK(bpf_prog_get_info_by_fd(fentry_fd, &info, &info_len),
+		  "bpf_prog_get_info_by_fd");
 
 	ASSERT_EQ(info.btf_id, 0, "info.btf_id");
 	ASSERT_EQ(info.attach_btf_id, btf_id, "info.attach_btf_id");
@@ -563,6 +585,8 @@ void serial_test_fexit_bpf2bpf(void)
 		test_func_replace_return_code();
 	if (test__start_subtest("func_map_prog_compatibility"))
 		test_func_map_prog_compatibility();
+	if (test__start_subtest("func_replace_unreliable"))
+		test_func_replace_unreliable();
 	if (test__start_subtest("func_replace_multi"))
 		test_func_replace_multi();
 	if (test__start_subtest("fmod_ret_freplace"))
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
index f949647dbbc2..552a0875ca6d 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
@@ -21,13 +21,13 @@ static int do_sleep(void *skel)
 }
 
 #define STACK_SIZE (1024 * 1024)
-static char child_stack[STACK_SIZE];
 
 void test_fexit_sleep(void)
 {
 	struct fexit_sleep_lskel *fexit_skel = NULL;
 	int wstatus, duration = 0;
 	pid_t cpid;
+	char *child_stack = NULL;
 	int err, fexit_cnt;
 
 	fexit_skel = fexit_sleep_lskel__open_and_load();
@@ -38,6 +38,11 @@ void test_fexit_sleep(void)
 	if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err))
 		goto cleanup;
 
+	child_stack = mmap(NULL, STACK_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE |
+			   MAP_ANONYMOUS | MAP_STACK, -1, 0);
+	if (!ASSERT_NEQ(child_stack, MAP_FAILED, "mmap"))
+		goto cleanup;
+
 	cpid = clone(do_sleep, child_stack + STACK_SIZE, CLONE_FILES | SIGCHLD, fexit_skel);
 	if (CHECK(cpid == -1, "clone", "%s\n", strerror(errno)))
 		goto cleanup;
@@ -78,5 +83,6 @@ void test_fexit_sleep(void)
 		goto cleanup;
 
 cleanup:
+	munmap(child_stack, STACK_SIZE);
 	fexit_sleep_lskel__destroy(fexit_skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c
index 5a7e6011f6bf..14c91b6f1e83 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c
@@ -1,15 +1,21 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 Facebook */
 #include <test_progs.h>
-
-/* that's kernel internal BPF_MAX_TRAMP_PROGS define */
-#define CNT 38
+#include "bpf_util.h"
 
 void serial_test_fexit_stress(void)
 {
-	int fexit_fd[CNT] = {};
-	int link_fd[CNT] = {};
-	int err, i;
+	int bpf_max_tramp_links, err, i;
+	int *fd, *fexit_fd, *link_fd;
+
+	bpf_max_tramp_links = get_bpf_max_tramp_links();
+	if (!ASSERT_GE(bpf_max_tramp_links, 1, "bpf_max_tramp_links"))
+		return;
+	fd = calloc(bpf_max_tramp_links * 2, sizeof(*fd));
+	if (!ASSERT_OK_PTR(fd, "fd"))
+		return;
+	fexit_fd = fd;
+	link_fd = fd + bpf_max_tramp_links;
 
 	const struct bpf_insn trace_program[] = {
 		BPF_MOV64_IMM(BPF_REG_0, 0),
@@ -28,10 +34,10 @@ void serial_test_fexit_stress(void)
 		goto out;
 	trace_opts.attach_btf_id = err;
 
-	for (i = 0; i < CNT; i++) {
+	for (i = 0; i < bpf_max_tramp_links; i++) {
 		fexit_fd[i] = bpf_prog_load(BPF_PROG_TYPE_TRACING, NULL, "GPL",
 					    trace_program,
-					    sizeof(trace_program) / sizeof(struct bpf_insn),
+					    ARRAY_SIZE(trace_program),
 					    &trace_opts);
 		if (!ASSERT_GE(fexit_fd[i], 0, "fexit load"))
 			goto out;
@@ -44,10 +50,11 @@ void serial_test_fexit_stress(void)
 	ASSERT_OK(err, "bpf_prog_test_run_opts");
 
 out:
-	for (i = 0; i < CNT; i++) {
-		if (link_fd[i])
+	for (i = 0; i < bpf_max_tramp_links; i++) {
+		if (link_fd[i] > 0)
 			close(link_fd[i]);
-		if (fexit_fd[i])
+		if (fexit_fd[i] > 0)
 			close(fexit_fd[i]);
 	}
+	free(fd);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
index 101b7343036b..94eed753560c 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
@@ -2,8 +2,9 @@
 /* Copyright (c) 2019 Facebook */
 #include <test_progs.h>
 #include "fexit_test.lskel.h"
+#include "fexit_many_args.skel.h"
 
-static int fexit_test(struct fexit_test_lskel *fexit_skel)
+static int fexit_test_common(struct fexit_test_lskel *fexit_skel)
 {
 	int err, prog_fd, i;
 	int link_fd;
@@ -37,22 +38,61 @@ static int fexit_test(struct fexit_test_lskel *fexit_skel)
 	return 0;
 }
 
-void test_fexit_test(void)
+static void fexit_test(void)
 {
 	struct fexit_test_lskel *fexit_skel = NULL;
 	int err;
 
-	fexit_skel = fexit_test_lskel__open_and_load();
-	if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load"))
+	fexit_skel = fexit_test_lskel__open();
+	if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_open"))
+		goto cleanup;
+
+	fexit_skel->keyring_id	= KEY_SPEC_SESSION_KEYRING;
+	err = fexit_test_lskel__load(fexit_skel);
+	if (!ASSERT_OK(err, "fexit_skel_load"))
 		goto cleanup;
 
-	err = fexit_test(fexit_skel);
+	err = fexit_test_common(fexit_skel);
 	if (!ASSERT_OK(err, "fexit_first_attach"))
 		goto cleanup;
 
-	err = fexit_test(fexit_skel);
+	err = fexit_test_common(fexit_skel);
 	ASSERT_OK(err, "fexit_second_attach");
 
 cleanup:
 	fexit_test_lskel__destroy(fexit_skel);
 }
+
+static void fexit_many_args(void)
+{
+	struct fexit_many_args *fexit_skel = NULL;
+	int err;
+
+	fexit_skel = fexit_many_args__open_and_load();
+	if (!ASSERT_OK_PTR(fexit_skel, "fexit_many_args_skel_load"))
+		goto cleanup;
+
+	err = fexit_many_args__attach(fexit_skel);
+	if (!ASSERT_OK(err, "fexit_many_args_attach"))
+		goto cleanup;
+
+	ASSERT_OK(trigger_module_test_read(1), "trigger_read");
+
+	ASSERT_EQ(fexit_skel->bss->test1_result, 1,
+		  "fexit_many_args_result1");
+	ASSERT_EQ(fexit_skel->bss->test2_result, 1,
+		  "fexit_many_args_result2");
+	ASSERT_EQ(fexit_skel->bss->test3_result, 1,
+		  "fexit_many_args_result3");
+
+cleanup:
+	fexit_many_args__destroy(fexit_skel);
+}
+
+void test_fexit_test(void)
+{
+	if (test__start_subtest("fexit"))
+		fexit_test();
+	if (test__start_subtest("fexit_many_args"))
+		fexit_many_args();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/fib_lookup.c b/tools/testing/selftests/bpf/prog_tests/fib_lookup.c
new file mode 100644
index 000000000000..bd7658958004
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/fib_lookup.c
@@ -0,0 +1,377 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <linux/rtnetlink.h>
+#include <sys/types.h>
+#include <net/if.h>
+
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "fib_lookup.skel.h"
+
+#define NS_TEST			"fib_lookup_ns"
+#define IPV6_IFACE_ADDR		"face::face"
+#define IPV6_IFACE_ADDR_SEC	"cafe::cafe"
+#define IPV6_ADDR_DST		"face::3"
+#define IPV6_NUD_FAILED_ADDR	"face::1"
+#define IPV6_NUD_STALE_ADDR	"face::2"
+#define IPV4_IFACE_ADDR		"10.0.0.254"
+#define IPV4_IFACE_ADDR_SEC	"10.1.0.254"
+#define IPV4_ADDR_DST		"10.2.0.254"
+#define IPV4_NUD_FAILED_ADDR	"10.0.0.1"
+#define IPV4_NUD_STALE_ADDR	"10.0.0.2"
+#define IPV4_TBID_ADDR		"172.0.0.254"
+#define IPV4_TBID_NET		"172.0.0.0"
+#define IPV4_TBID_DST		"172.0.0.2"
+#define IPV6_TBID_ADDR		"fd00::FFFF"
+#define IPV6_TBID_NET		"fd00::"
+#define IPV6_TBID_DST		"fd00::2"
+#define MARK_NO_POLICY		33
+#define MARK			42
+#define MARK_TABLE		"200"
+#define IPV4_REMOTE_DST		"1.2.3.4"
+#define IPV4_LOCAL		"10.4.0.3"
+#define IPV4_GW1		"10.4.0.1"
+#define IPV4_GW2		"10.4.0.2"
+#define IPV6_REMOTE_DST		"be:ef::b0:10"
+#define IPV6_LOCAL		"fd01::3"
+#define IPV6_GW1		"fd01::1"
+#define IPV6_GW2		"fd01::2"
+#define DMAC			"11:11:11:11:11:11"
+#define DMAC_INIT { 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, }
+#define DMAC2			"01:01:01:01:01:01"
+#define DMAC_INIT2 { 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, }
+
+struct fib_lookup_test {
+	const char *desc;
+	const char *daddr;
+	int expected_ret;
+	const char *expected_src;
+	const char *expected_dst;
+	int lookup_flags;
+	__u32 tbid;
+	__u8 dmac[6];
+	__u32 mark;
+};
+
+static const struct fib_lookup_test tests[] = {
+	{ .desc = "IPv6 failed neigh",
+	  .daddr = IPV6_NUD_FAILED_ADDR, .expected_ret = BPF_FIB_LKUP_RET_NO_NEIGH, },
+	{ .desc = "IPv6 stale neigh",
+	  .daddr = IPV6_NUD_STALE_ADDR, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .dmac = DMAC_INIT, },
+	{ .desc = "IPv6 skip neigh",
+	  .daddr = IPV6_NUD_FAILED_ADDR, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .lookup_flags = BPF_FIB_LOOKUP_SKIP_NEIGH, },
+	{ .desc = "IPv4 failed neigh",
+	  .daddr = IPV4_NUD_FAILED_ADDR, .expected_ret = BPF_FIB_LKUP_RET_NO_NEIGH, },
+	{ .desc = "IPv4 stale neigh",
+	  .daddr = IPV4_NUD_STALE_ADDR, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .dmac = DMAC_INIT, },
+	{ .desc = "IPv4 skip neigh",
+	  .daddr = IPV4_NUD_FAILED_ADDR, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .lookup_flags = BPF_FIB_LOOKUP_SKIP_NEIGH, },
+	{ .desc = "IPv4 TBID lookup failure",
+	  .daddr = IPV4_TBID_DST, .expected_ret = BPF_FIB_LKUP_RET_NOT_FWDED,
+	  .lookup_flags = BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID,
+	  .tbid = RT_TABLE_MAIN, },
+	{ .desc = "IPv4 TBID lookup success",
+	  .daddr = IPV4_TBID_DST, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .lookup_flags = BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID, .tbid = 100,
+	  .dmac = DMAC_INIT2, },
+	{ .desc = "IPv6 TBID lookup failure",
+	  .daddr = IPV6_TBID_DST, .expected_ret = BPF_FIB_LKUP_RET_NOT_FWDED,
+	  .lookup_flags = BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID,
+	  .tbid = RT_TABLE_MAIN, },
+	{ .desc = "IPv6 TBID lookup success",
+	  .daddr = IPV6_TBID_DST, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .lookup_flags = BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID, .tbid = 100,
+	  .dmac = DMAC_INIT2, },
+	{ .desc = "IPv4 set src addr from netdev",
+	  .daddr = IPV4_NUD_FAILED_ADDR, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .expected_src = IPV4_IFACE_ADDR,
+	  .lookup_flags = BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_SKIP_NEIGH, },
+	{ .desc = "IPv6 set src addr from netdev",
+	  .daddr = IPV6_NUD_FAILED_ADDR, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .expected_src = IPV6_IFACE_ADDR,
+	  .lookup_flags = BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_SKIP_NEIGH, },
+	{ .desc = "IPv4 set prefsrc addr from route",
+	  .daddr = IPV4_ADDR_DST, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .expected_src = IPV4_IFACE_ADDR_SEC,
+	  .lookup_flags = BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_SKIP_NEIGH, },
+	{ .desc = "IPv6 set prefsrc addr route",
+	  .daddr = IPV6_ADDR_DST, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .expected_src = IPV6_IFACE_ADDR_SEC,
+	  .lookup_flags = BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_SKIP_NEIGH, },
+	/* policy routing */
+	{ .desc = "IPv4 policy routing, default",
+	  .daddr = IPV4_REMOTE_DST, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .expected_dst = IPV4_GW1,
+	  .lookup_flags = BPF_FIB_LOOKUP_MARK | BPF_FIB_LOOKUP_SKIP_NEIGH, },
+	{ .desc = "IPv4 policy routing, mark doesn't point to a policy",
+	  .daddr = IPV4_REMOTE_DST, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .expected_dst = IPV4_GW1,
+	  .lookup_flags = BPF_FIB_LOOKUP_MARK | BPF_FIB_LOOKUP_SKIP_NEIGH,
+	  .mark = MARK_NO_POLICY, },
+	{ .desc = "IPv4 policy routing, mark points to a policy",
+	  .daddr = IPV4_REMOTE_DST, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .expected_dst = IPV4_GW2,
+	  .lookup_flags = BPF_FIB_LOOKUP_MARK | BPF_FIB_LOOKUP_SKIP_NEIGH,
+	  .mark = MARK, },
+	{ .desc = "IPv4 policy routing, mark points to a policy, but no flag",
+	  .daddr = IPV4_REMOTE_DST, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .expected_dst = IPV4_GW1,
+	  .lookup_flags = BPF_FIB_LOOKUP_SKIP_NEIGH,
+	  .mark = MARK, },
+	{ .desc = "IPv6 policy routing, default",
+	  .daddr = IPV6_REMOTE_DST, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .expected_dst = IPV6_GW1,
+	  .lookup_flags = BPF_FIB_LOOKUP_MARK | BPF_FIB_LOOKUP_SKIP_NEIGH, },
+	{ .desc = "IPv6 policy routing, mark doesn't point to a policy",
+	  .daddr = IPV6_REMOTE_DST, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .expected_dst = IPV6_GW1,
+	  .lookup_flags = BPF_FIB_LOOKUP_MARK | BPF_FIB_LOOKUP_SKIP_NEIGH,
+	  .mark = MARK_NO_POLICY, },
+	{ .desc = "IPv6 policy routing, mark points to a policy",
+	  .daddr = IPV6_REMOTE_DST, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .expected_dst = IPV6_GW2,
+	  .lookup_flags = BPF_FIB_LOOKUP_MARK | BPF_FIB_LOOKUP_SKIP_NEIGH,
+	  .mark = MARK, },
+	{ .desc = "IPv6 policy routing, mark points to a policy, but no flag",
+	  .daddr = IPV6_REMOTE_DST, .expected_ret = BPF_FIB_LKUP_RET_SUCCESS,
+	  .expected_dst = IPV6_GW1,
+	  .lookup_flags = BPF_FIB_LOOKUP_SKIP_NEIGH,
+	  .mark = MARK, },
+};
+
+static int setup_netns(void)
+{
+	int err;
+
+	SYS(fail, "ip link add veth1 type veth peer name veth2");
+	SYS(fail, "ip link set dev veth1 up");
+	SYS(fail, "ip link set dev veth2 up");
+
+	err = write_sysctl("/proc/sys/net/ipv4/neigh/veth1/gc_stale_time", "900");
+	if (!ASSERT_OK(err, "write_sysctl(net.ipv4.neigh.veth1.gc_stale_time)"))
+		goto fail;
+
+	err = write_sysctl("/proc/sys/net/ipv6/neigh/veth1/gc_stale_time", "900");
+	if (!ASSERT_OK(err, "write_sysctl(net.ipv6.neigh.veth1.gc_stale_time)"))
+		goto fail;
+
+	SYS(fail, "ip addr add %s/64 dev veth1 nodad", IPV6_IFACE_ADDR);
+	SYS(fail, "ip neigh add %s dev veth1 nud failed", IPV6_NUD_FAILED_ADDR);
+	SYS(fail, "ip neigh add %s dev veth1 lladdr %s nud stale", IPV6_NUD_STALE_ADDR, DMAC);
+
+	SYS(fail, "ip addr add %s/24 dev veth1", IPV4_IFACE_ADDR);
+	SYS(fail, "ip neigh add %s dev veth1 nud failed", IPV4_NUD_FAILED_ADDR);
+	SYS(fail, "ip neigh add %s dev veth1 lladdr %s nud stale", IPV4_NUD_STALE_ADDR, DMAC);
+
+	/* Setup for prefsrc IP addr selection */
+	SYS(fail, "ip addr add %s/24 dev veth1", IPV4_IFACE_ADDR_SEC);
+	SYS(fail, "ip route add %s/32 dev veth1 src %s", IPV4_ADDR_DST, IPV4_IFACE_ADDR_SEC);
+
+	SYS(fail, "ip addr add %s/64 dev veth1 nodad", IPV6_IFACE_ADDR_SEC);
+	SYS(fail, "ip route add %s/128 dev veth1 src %s", IPV6_ADDR_DST, IPV6_IFACE_ADDR_SEC);
+
+	/* Setup for tbid lookup tests */
+	SYS(fail, "ip addr add %s/24 dev veth2", IPV4_TBID_ADDR);
+	SYS(fail, "ip route del %s/24 dev veth2", IPV4_TBID_NET);
+	SYS(fail, "ip route add table 100 %s/24 dev veth2", IPV4_TBID_NET);
+	SYS(fail, "ip neigh add %s dev veth2 lladdr %s nud stale", IPV4_TBID_DST, DMAC2);
+
+	SYS(fail, "ip addr add %s/64 dev veth2", IPV6_TBID_ADDR);
+	SYS(fail, "ip -6 route del %s/64 dev veth2", IPV6_TBID_NET);
+	SYS(fail, "ip -6 route add table 100 %s/64 dev veth2", IPV6_TBID_NET);
+	SYS(fail, "ip neigh add %s dev veth2 lladdr %s nud stale", IPV6_TBID_DST, DMAC2);
+
+	err = write_sysctl("/proc/sys/net/ipv4/conf/veth1/forwarding", "1");
+	if (!ASSERT_OK(err, "write_sysctl(net.ipv4.conf.veth1.forwarding)"))
+		goto fail;
+
+	err = write_sysctl("/proc/sys/net/ipv6/conf/veth1/forwarding", "1");
+	if (!ASSERT_OK(err, "write_sysctl(net.ipv6.conf.veth1.forwarding)"))
+		goto fail;
+
+	/* Setup for policy routing tests */
+	SYS(fail, "ip addr add %s/24 dev veth1", IPV4_LOCAL);
+	SYS(fail, "ip addr add %s/64 dev veth1 nodad", IPV6_LOCAL);
+	SYS(fail, "ip route add %s/32 via %s", IPV4_REMOTE_DST, IPV4_GW1);
+	SYS(fail, "ip route add %s/32 via %s table %s", IPV4_REMOTE_DST, IPV4_GW2, MARK_TABLE);
+	SYS(fail, "ip -6 route add %s/128 via %s", IPV6_REMOTE_DST, IPV6_GW1);
+	SYS(fail, "ip -6 route add %s/128 via %s table %s", IPV6_REMOTE_DST, IPV6_GW2, MARK_TABLE);
+	SYS(fail, "ip rule add prio 2 fwmark %d lookup %s", MARK, MARK_TABLE);
+	SYS(fail, "ip -6 rule add prio 2 fwmark %d lookup %s", MARK, MARK_TABLE);
+
+	return 0;
+fail:
+	return -1;
+}
+
+static int set_lookup_params(struct bpf_fib_lookup *params,
+			     const struct fib_lookup_test *test,
+			     int ifindex)
+{
+	int ret;
+
+	memset(params, 0, sizeof(*params));
+
+	params->l4_protocol = IPPROTO_TCP;
+	params->ifindex = ifindex;
+	params->tbid = test->tbid;
+	params->mark = test->mark;
+
+	if (inet_pton(AF_INET6, test->daddr, params->ipv6_dst) == 1) {
+		params->family = AF_INET6;
+		if (!(test->lookup_flags & BPF_FIB_LOOKUP_SRC)) {
+			ret = inet_pton(AF_INET6, IPV6_IFACE_ADDR, params->ipv6_src);
+			if (!ASSERT_EQ(ret, 1, "inet_pton(IPV6_IFACE_ADDR)"))
+				return -1;
+		}
+
+		return 0;
+	}
+
+	ret = inet_pton(AF_INET, test->daddr, &params->ipv4_dst);
+	if (!ASSERT_EQ(ret, 1, "convert IP[46] address"))
+		return -1;
+	params->family = AF_INET;
+
+	if (!(test->lookup_flags & BPF_FIB_LOOKUP_SRC)) {
+		ret = inet_pton(AF_INET, IPV4_IFACE_ADDR, &params->ipv4_src);
+		if (!ASSERT_EQ(ret, 1, "inet_pton(IPV4_IFACE_ADDR)"))
+			return -1;
+	}
+
+	return 0;
+}
+
+static void mac_str(char *b, const __u8 *mac)
+{
+	sprintf(b, "%02X:%02X:%02X:%02X:%02X:%02X",
+		mac[0], mac[1], mac[2], mac[3], mac[4], mac[5]);
+}
+
+static void assert_ip_address(int family, void *addr, const char *expected_str)
+{
+	char str[INET6_ADDRSTRLEN];
+	u8 expected_addr[16];
+	int addr_len = 0;
+	int ret;
+
+	switch (family) {
+	case AF_INET6:
+		ret = inet_pton(AF_INET6, expected_str, expected_addr);
+		ASSERT_EQ(ret, 1, "inet_pton(AF_INET6, expected_str)");
+		addr_len = 16;
+		break;
+	case AF_INET:
+		ret = inet_pton(AF_INET, expected_str, expected_addr);
+		ASSERT_EQ(ret, 1, "inet_pton(AF_INET, expected_str)");
+		addr_len = 4;
+		break;
+	default:
+		PRINT_FAIL("invalid address family: %d", family);
+		break;
+	}
+
+	if (memcmp(addr, expected_addr, addr_len)) {
+		inet_ntop(family, addr, str, sizeof(str));
+		PRINT_FAIL("expected %s actual %s ", expected_str, str);
+	}
+}
+
+static void assert_src_ip(struct bpf_fib_lookup *params, const char *expected)
+{
+	assert_ip_address(params->family, params->ipv6_src, expected);
+}
+
+static void assert_dst_ip(struct bpf_fib_lookup *params, const char *expected)
+{
+	assert_ip_address(params->family, params->ipv6_dst, expected);
+}
+
+void test_fib_lookup(void)
+{
+	struct bpf_fib_lookup *fib_params;
+	struct nstoken *nstoken = NULL;
+	struct __sk_buff skb = { };
+	struct fib_lookup *skel;
+	int prog_fd, err, ret, i;
+
+	/* The test does not use the skb->data, so
+	 * use pkt_v6 for both v6 and v4 test.
+	 */
+	LIBBPF_OPTS(bpf_test_run_opts, run_opts,
+		    .data_in = &pkt_v6,
+		    .data_size_in = sizeof(pkt_v6),
+		    .ctx_in = &skb,
+		    .ctx_size_in = sizeof(skb),
+	);
+
+	skel = fib_lookup__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel open_and_load"))
+		return;
+	prog_fd = bpf_program__fd(skel->progs.fib_lookup);
+
+	SYS(fail, "ip netns add %s", NS_TEST);
+
+	nstoken = open_netns(NS_TEST);
+	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+		goto fail;
+
+	if (setup_netns())
+		goto fail;
+
+	skb.ifindex = if_nametoindex("veth1");
+	if (!ASSERT_NEQ(skb.ifindex, 0, "if_nametoindex(veth1)"))
+		goto fail;
+
+	fib_params = &skel->bss->fib_params;
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		printf("Testing %s ", tests[i].desc);
+
+		if (set_lookup_params(fib_params, &tests[i], skb.ifindex))
+			continue;
+
+		skel->bss->fib_lookup_ret = -1;
+		skel->bss->lookup_flags = tests[i].lookup_flags;
+
+		err = bpf_prog_test_run_opts(prog_fd, &run_opts);
+		if (!ASSERT_OK(err, "bpf_prog_test_run_opts"))
+			continue;
+
+		ASSERT_EQ(skel->bss->fib_lookup_ret, tests[i].expected_ret,
+			  "fib_lookup_ret");
+
+		if (tests[i].expected_src)
+			assert_src_ip(fib_params, tests[i].expected_src);
+
+		if (tests[i].expected_dst)
+			assert_dst_ip(fib_params, tests[i].expected_dst);
+
+		ret = memcmp(tests[i].dmac, fib_params->dmac, sizeof(tests[i].dmac));
+		if (!ASSERT_EQ(ret, 0, "dmac not match")) {
+			char expected[18], actual[18];
+
+			mac_str(expected, tests[i].dmac);
+			mac_str(actual, fib_params->dmac);
+			printf("dmac expected %s actual %s ", expected, actual);
+		}
+
+		// ensure tbid is zero'd out after fib lookup.
+		if (tests[i].lookup_flags & BPF_FIB_LOOKUP_DIRECT) {
+			if (!ASSERT_EQ(skel->bss->fib_params.tbid, 0,
+					"expected fib_params.tbid to be zero"))
+				goto fail;
+		}
+	}
+
+fail:
+	if (nstoken)
+		close_netns(nstoken);
+	SYS_NOFAIL("ip netns del " NS_TEST);
+	fib_lookup__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/file_reader.c b/tools/testing/selftests/bpf/prog_tests/file_reader.c
new file mode 100644
index 000000000000..5cde32b35da4
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/file_reader.c
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "file_reader.skel.h"
+#include "file_reader_fail.skel.h"
+#include <dlfcn.h>
+#include <sys/mman.h>
+
+const char *user_ptr = "hello world";
+char file_contents[256000];
+
+void *get_executable_base_addr(void)
+{
+	Dl_info info;
+
+	if (!dladdr((void *)&get_executable_base_addr, &info)) {
+		fprintf(stderr, "dladdr failed\n");
+		return NULL;
+	}
+
+	return info.dli_fbase;
+}
+
+static int initialize_file_contents(void)
+{
+	int fd, page_sz = sysconf(_SC_PAGESIZE);
+	ssize_t n = 0, cur, off;
+	void *addr;
+
+	fd = open("/proc/self/exe", O_RDONLY);
+	if (!ASSERT_OK_FD(fd, "Open /proc/self/exe\n"))
+		return 1;
+
+	do {
+		cur = read(fd, file_contents + n, sizeof(file_contents) - n);
+		if (!ASSERT_GT(cur, 0, "read success"))
+			break;
+		n += cur;
+	} while (n < sizeof(file_contents));
+
+	close(fd);
+
+	if (!ASSERT_EQ(n, sizeof(file_contents), "Read /proc/self/exe\n"))
+		return 1;
+
+	addr = get_executable_base_addr();
+	if (!ASSERT_NEQ(addr, NULL, "get executable address"))
+		return 1;
+
+	/* page-align base file address */
+	addr = (void *)((unsigned long)addr & ~(page_sz - 1));
+
+	/*
+	 * Page out range 0..512K, use 0..256K for positive tests and
+	 * 256K..512K for negative tests expecting page faults
+	 */
+	for (off = 0; off < sizeof(file_contents) * 2; off += page_sz) {
+		if (!ASSERT_OK(madvise(addr + off, page_sz, MADV_PAGEOUT),
+			       "madvise pageout"))
+			return errno;
+	}
+
+	return 0;
+}
+
+static void run_test(const char *prog_name)
+{
+	struct file_reader *skel;
+	struct bpf_program *prog;
+	int err, fd;
+
+	err = initialize_file_contents();
+	if (!ASSERT_OK(err, "initialize file contents"))
+		return;
+
+	skel = file_reader__open();
+	if (!ASSERT_OK_PTR(skel, "file_reader__open"))
+		return;
+
+	bpf_object__for_each_program(prog, skel->obj) {
+		bpf_program__set_autoload(prog, strcmp(bpf_program__name(prog), prog_name) == 0);
+	}
+
+	memcpy(skel->bss->user_buf, file_contents, sizeof(file_contents));
+	skel->bss->pid = getpid();
+
+	err = file_reader__load(skel);
+	if (!ASSERT_OK(err, "file_reader__load"))
+		goto cleanup;
+
+	err = file_reader__attach(skel);
+	if (!ASSERT_OK(err, "file_reader__attach"))
+		goto cleanup;
+
+	fd = open("/proc/self/exe", O_RDONLY);
+	if (fd >= 0)
+		close(fd);
+
+	ASSERT_EQ(skel->bss->err, 0, "err");
+	ASSERT_EQ(skel->bss->run_success, 1, "run_success");
+cleanup:
+	file_reader__destroy(skel);
+}
+
+void test_file_reader(void)
+{
+	if (test__start_subtest("on_open_expect_fault"))
+		run_test("on_open_expect_fault");
+
+	if (test__start_subtest("on_open_validate_file_read"))
+		run_test("on_open_validate_file_read");
+
+	if (test__start_subtest("negative"))
+		RUN_TESTS(file_reader_fail);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
new file mode 100644
index 000000000000..e40114620751
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c
@@ -0,0 +1,652 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */
+
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/limits.h>
+#include <test_progs.h>
+#include "trace_helpers.h"
+#include "test_fill_link_info.skel.h"
+#include "bpf/libbpf_internal.h"
+
+#define TP_CAT "sched"
+#define TP_NAME "sched_switch"
+
+static const char *kmulti_syms[] = {
+	"bpf_fentry_test2",
+	"bpf_fentry_test1",
+	"bpf_fentry_test3",
+};
+#define KMULTI_CNT ARRAY_SIZE(kmulti_syms)
+static __u64 kmulti_addrs[KMULTI_CNT];
+static __u64 kmulti_cookies[] = { 3, 1, 2 };
+
+#define KPROBE_FUNC "bpf_fentry_test1"
+static __u64 kprobe_addr;
+
+#define UPROBE_FILE "/proc/self/exe"
+static ssize_t uprobe_offset;
+/* uprobe attach point */
+static noinline void uprobe_func(void)
+{
+	asm volatile ("");
+}
+
+#define PERF_EVENT_COOKIE 0xdeadbeef
+
+static int verify_perf_link_info(int fd, enum bpf_perf_event_type type, long addr,
+				 ssize_t offset, ssize_t entry_offset)
+{
+	ssize_t ref_ctr_offset = entry_offset /* ref_ctr_offset for uprobes */;
+	struct bpf_link_info info;
+	__u32 len = sizeof(info);
+	char buf[PATH_MAX];
+	int err;
+
+	memset(&info, 0, sizeof(info));
+	buf[0] = '\0';
+
+again:
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	if (!ASSERT_OK(err, "get_link_info"))
+		return -1;
+
+	if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_PERF_EVENT, "link_type"))
+		return -1;
+	if (!ASSERT_EQ(info.perf_event.type, type, "perf_type_match"))
+		return -1;
+
+	switch (info.perf_event.type) {
+	case BPF_PERF_EVENT_KPROBE:
+	case BPF_PERF_EVENT_KRETPROBE:
+		ASSERT_EQ(info.perf_event.kprobe.offset, offset, "kprobe_offset");
+
+		/* In case kernel.kptr_restrict is not permitted or MAX_SYMS is reached */
+		if (addr)
+			ASSERT_EQ(info.perf_event.kprobe.addr, addr + entry_offset,
+				  "kprobe_addr");
+
+		ASSERT_EQ(info.perf_event.kprobe.cookie, PERF_EVENT_COOKIE, "kprobe_cookie");
+
+		ASSERT_EQ(info.perf_event.kprobe.name_len, strlen(KPROBE_FUNC) + 1,
+				  "name_len");
+		if (!info.perf_event.kprobe.func_name) {
+			info.perf_event.kprobe.func_name = ptr_to_u64(&buf);
+			info.perf_event.kprobe.name_len = sizeof(buf);
+			goto again;
+		}
+
+		err = strncmp(u64_to_ptr(info.perf_event.kprobe.func_name), KPROBE_FUNC,
+			      strlen(KPROBE_FUNC));
+		ASSERT_EQ(err, 0, "cmp_kprobe_func_name");
+		break;
+	case BPF_PERF_EVENT_TRACEPOINT:
+		ASSERT_EQ(info.perf_event.tracepoint.name_len, strlen(TP_NAME) + 1,
+				  "name_len");
+		if (!info.perf_event.tracepoint.tp_name) {
+			info.perf_event.tracepoint.tp_name = ptr_to_u64(&buf);
+			info.perf_event.tracepoint.name_len = sizeof(buf);
+			goto again;
+		}
+
+		ASSERT_EQ(info.perf_event.tracepoint.cookie, PERF_EVENT_COOKIE, "tracepoint_cookie");
+
+		err = strncmp(u64_to_ptr(info.perf_event.tracepoint.tp_name), TP_NAME,
+			      strlen(TP_NAME));
+		ASSERT_EQ(err, 0, "cmp_tp_name");
+		break;
+	case BPF_PERF_EVENT_UPROBE:
+	case BPF_PERF_EVENT_URETPROBE:
+		ASSERT_EQ(info.perf_event.uprobe.offset, offset, "uprobe_offset");
+		ASSERT_EQ(info.perf_event.uprobe.ref_ctr_offset, ref_ctr_offset, "uprobe_ref_ctr_offset");
+
+		ASSERT_EQ(info.perf_event.uprobe.name_len, strlen(UPROBE_FILE) + 1,
+				  "name_len");
+		if (!info.perf_event.uprobe.file_name) {
+			info.perf_event.uprobe.file_name = ptr_to_u64(&buf);
+			info.perf_event.uprobe.name_len = sizeof(buf);
+			goto again;
+		}
+
+		ASSERT_EQ(info.perf_event.uprobe.cookie, PERF_EVENT_COOKIE, "uprobe_cookie");
+
+		err = strncmp(u64_to_ptr(info.perf_event.uprobe.file_name), UPROBE_FILE,
+			      strlen(UPROBE_FILE));
+			ASSERT_EQ(err, 0, "cmp_file_name");
+		break;
+	case BPF_PERF_EVENT_EVENT:
+		ASSERT_EQ(info.perf_event.event.type, PERF_TYPE_SOFTWARE, "event_type");
+		ASSERT_EQ(info.perf_event.event.config, PERF_COUNT_SW_PAGE_FAULTS, "event_config");
+		ASSERT_EQ(info.perf_event.event.cookie, PERF_EVENT_COOKIE, "event_cookie");
+		break;
+	default:
+		err = -1;
+		break;
+	}
+	return err;
+}
+
+static void kprobe_fill_invalid_user_buffer(int fd)
+{
+	struct bpf_link_info info;
+	__u32 len = sizeof(info);
+	int err;
+
+	memset(&info, 0, sizeof(info));
+
+	info.perf_event.kprobe.func_name = 0x1; /* invalid address */
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EINVAL, "invalid_buff_and_len");
+
+	info.perf_event.kprobe.name_len = 64;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EFAULT, "invalid_buff");
+
+	info.perf_event.kprobe.func_name = 0;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EINVAL, "invalid_len");
+
+	ASSERT_EQ(info.perf_event.kprobe.addr, 0, "func_addr");
+	ASSERT_EQ(info.perf_event.kprobe.offset, 0, "func_offset");
+	ASSERT_EQ(info.perf_event.type, 0, "type");
+}
+
+static void test_kprobe_fill_link_info(struct test_fill_link_info *skel,
+				       enum bpf_perf_event_type type,
+				       bool invalid)
+{
+	DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts,
+		.attach_mode = PROBE_ATTACH_MODE_LINK,
+		.retprobe = type == BPF_PERF_EVENT_KRETPROBE,
+		.bpf_cookie = PERF_EVENT_COOKIE,
+	);
+	ssize_t entry_offset = 0;
+	struct bpf_link *link;
+	int link_fd, err;
+
+	link = bpf_program__attach_kprobe_opts(skel->progs.kprobe_run, KPROBE_FUNC, &opts);
+	if (!ASSERT_OK_PTR(link, "attach_kprobe"))
+		return;
+
+	link_fd = bpf_link__fd(link);
+	if (!invalid) {
+		/* See also arch_adjust_kprobe_addr(). */
+		if (skel->kconfig->CONFIG_X86_KERNEL_IBT)
+			entry_offset = 4;
+		if (skel->kconfig->CONFIG_PPC64 &&
+		    skel->kconfig->CONFIG_KPROBES_ON_FTRACE &&
+		    !skel->kconfig->CONFIG_PPC_FTRACE_OUT_OF_LINE)
+			entry_offset = 4;
+		err = verify_perf_link_info(link_fd, type, kprobe_addr, 0, entry_offset);
+		ASSERT_OK(err, "verify_perf_link_info");
+	} else {
+		kprobe_fill_invalid_user_buffer(link_fd);
+	}
+	bpf_link__destroy(link);
+}
+
+static void test_tp_fill_link_info(struct test_fill_link_info *skel)
+{
+	DECLARE_LIBBPF_OPTS(bpf_tracepoint_opts, opts,
+		.bpf_cookie = PERF_EVENT_COOKIE,
+	);
+	struct bpf_link *link;
+	int link_fd, err;
+
+	link = bpf_program__attach_tracepoint_opts(skel->progs.tp_run, TP_CAT, TP_NAME, &opts);
+	if (!ASSERT_OK_PTR(link, "attach_tp"))
+		return;
+
+	link_fd = bpf_link__fd(link);
+	err = verify_perf_link_info(link_fd, BPF_PERF_EVENT_TRACEPOINT, 0, 0, 0);
+	ASSERT_OK(err, "verify_perf_link_info");
+	bpf_link__destroy(link);
+}
+
+static void test_event_fill_link_info(struct test_fill_link_info *skel)
+{
+	DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, opts,
+		.bpf_cookie = PERF_EVENT_COOKIE,
+	);
+	struct bpf_link *link;
+	int link_fd, err, pfd;
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_SOFTWARE,
+		.config = PERF_COUNT_SW_PAGE_FAULTS,
+		.freq = 1,
+		.sample_freq = 1,
+		.size = sizeof(struct perf_event_attr),
+	};
+
+	pfd = syscall(__NR_perf_event_open, &attr, -1 /* pid */, 0 /* cpu 0 */,
+		      -1 /* group id */, 0 /* flags */);
+	if (!ASSERT_GE(pfd, 0, "perf_event_open"))
+		return;
+
+	link = bpf_program__attach_perf_event_opts(skel->progs.event_run, pfd, &opts);
+	if (!ASSERT_OK_PTR(link, "attach_event"))
+		goto error;
+
+	link_fd = bpf_link__fd(link);
+	err = verify_perf_link_info(link_fd, BPF_PERF_EVENT_EVENT, 0, 0, 0);
+	ASSERT_OK(err, "verify_perf_link_info");
+	bpf_link__destroy(link);
+
+error:
+	close(pfd);
+}
+
+static void test_uprobe_fill_link_info(struct test_fill_link_info *skel,
+				       enum bpf_perf_event_type type)
+{
+	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, opts,
+		.retprobe = type == BPF_PERF_EVENT_URETPROBE,
+		.bpf_cookie = PERF_EVENT_COOKIE,
+	);
+	const char *sema[1] = {
+		"uprobe_link_info_sema_1",
+	};
+	__u64 *ref_ctr_offset;
+	struct bpf_link *link;
+	int link_fd, err;
+
+	err = elf_resolve_syms_offsets("/proc/self/exe", 1, sema,
+				       (unsigned long **) &ref_ctr_offset, STT_OBJECT);
+	if (!ASSERT_OK(err, "elf_resolve_syms_offsets_object"))
+		return;
+
+	opts.ref_ctr_offset = *ref_ctr_offset;
+	link = bpf_program__attach_uprobe_opts(skel->progs.uprobe_run,
+					       0, /* self pid */
+					       UPROBE_FILE, uprobe_offset,
+					       &opts);
+	if (!ASSERT_OK_PTR(link, "attach_uprobe"))
+		goto out;
+
+	link_fd = bpf_link__fd(link);
+	err = verify_perf_link_info(link_fd, type, 0, uprobe_offset, *ref_ctr_offset);
+	ASSERT_OK(err, "verify_perf_link_info");
+	bpf_link__destroy(link);
+out:
+	free(ref_ctr_offset);
+}
+
+static int verify_kmulti_link_info(int fd, bool retprobe, bool has_cookies)
+{
+	__u64 addrs[KMULTI_CNT], cookies[KMULTI_CNT];
+	struct bpf_link_info info;
+	__u32 len = sizeof(info);
+	int flags, i, err;
+
+	memset(&info, 0, sizeof(info));
+
+again:
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	if (!ASSERT_OK(err, "get_link_info"))
+		return -1;
+
+	if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_KPROBE_MULTI, "kmulti_type"))
+		return -1;
+
+	ASSERT_EQ(info.kprobe_multi.count, KMULTI_CNT, "func_cnt");
+	flags = info.kprobe_multi.flags & BPF_F_KPROBE_MULTI_RETURN;
+	if (!retprobe)
+		ASSERT_EQ(flags, 0, "kmulti_flags");
+	else
+		ASSERT_NEQ(flags, 0, "kretmulti_flags");
+
+	if (!info.kprobe_multi.addrs) {
+		info.kprobe_multi.addrs = ptr_to_u64(addrs);
+		info.kprobe_multi.cookies = ptr_to_u64(cookies);
+		goto again;
+	}
+	for (i = 0; i < KMULTI_CNT; i++) {
+		ASSERT_EQ(addrs[i], kmulti_addrs[i], "kmulti_addrs");
+		ASSERT_EQ(cookies[i], has_cookies ? kmulti_cookies[i] : 0,
+			  "kmulti_cookies_value");
+	}
+	return 0;
+}
+
+static void verify_kmulti_invalid_user_buffer(int fd)
+{
+	__u64 addrs[KMULTI_CNT], cookies[KMULTI_CNT];
+	struct bpf_link_info info;
+	__u32 len = sizeof(info);
+	int err, i;
+
+	memset(&info, 0, sizeof(info));
+
+	info.kprobe_multi.count = KMULTI_CNT;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EINVAL, "no_addr");
+
+	info.kprobe_multi.addrs = ptr_to_u64(addrs);
+	info.kprobe_multi.count = 0;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EINVAL, "no_cnt");
+
+	for (i = 0; i < KMULTI_CNT; i++)
+		addrs[i] = 0;
+	info.kprobe_multi.count = KMULTI_CNT - 1;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -ENOSPC, "smaller_cnt");
+	for (i = 0; i < KMULTI_CNT - 1; i++)
+		ASSERT_EQ(addrs[i], kmulti_addrs[i], "kmulti_addrs");
+	ASSERT_EQ(addrs[i], 0, "kmulti_addrs");
+
+	for (i = 0; i < KMULTI_CNT; i++)
+		addrs[i] = 0;
+	info.kprobe_multi.count = KMULTI_CNT + 1;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, 0, "bigger_cnt");
+	for (i = 0; i < KMULTI_CNT; i++)
+		ASSERT_EQ(addrs[i], kmulti_addrs[i], "kmulti_addrs");
+
+	info.kprobe_multi.count = KMULTI_CNT;
+	info.kprobe_multi.addrs = 0x1; /* invalid addr */
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EFAULT, "invalid_buff_addrs");
+
+	info.kprobe_multi.count = KMULTI_CNT;
+	info.kprobe_multi.addrs = ptr_to_u64(addrs);
+	info.kprobe_multi.cookies = 0x1; /* invalid addr */
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EFAULT, "invalid_buff_cookies");
+
+	/* cookies && !count */
+	info.kprobe_multi.count = 0;
+	info.kprobe_multi.addrs = ptr_to_u64(NULL);
+	info.kprobe_multi.cookies = ptr_to_u64(cookies);
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EINVAL, "invalid_cookies_count");
+}
+
+static int symbols_cmp_r(const void *a, const void *b)
+{
+	const char **str_a = (const char **) a;
+	const char **str_b = (const char **) b;
+
+	return strcmp(*str_a, *str_b);
+}
+
+static void test_kprobe_multi_fill_link_info(struct test_fill_link_info *skel,
+					     bool retprobe, bool cookies,
+					     bool invalid)
+{
+	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
+	struct bpf_link *link;
+	int link_fd, err;
+
+	opts.syms = kmulti_syms;
+	opts.cookies = cookies ? kmulti_cookies : NULL;
+	opts.cnt = KMULTI_CNT;
+	opts.retprobe = retprobe;
+	link = bpf_program__attach_kprobe_multi_opts(skel->progs.kmulti_run, NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "attach_kprobe_multi"))
+		return;
+
+	link_fd = bpf_link__fd(link);
+	if (!invalid) {
+		err = verify_kmulti_link_info(link_fd, retprobe, cookies);
+		ASSERT_OK(err, "verify_kmulti_link_info");
+	} else {
+		verify_kmulti_invalid_user_buffer(link_fd);
+	}
+	bpf_link__destroy(link);
+}
+
+#define SEC(name) __attribute__((section(name), used))
+
+static short uprobe_link_info_sema_1 SEC(".probes");
+static short uprobe_link_info_sema_2 SEC(".probes");
+static short uprobe_link_info_sema_3 SEC(".probes");
+
+noinline void uprobe_link_info_func_1(void)
+{
+	asm volatile ("");
+	uprobe_link_info_sema_1++;
+}
+
+noinline void uprobe_link_info_func_2(void)
+{
+	asm volatile ("");
+	uprobe_link_info_sema_2++;
+}
+
+noinline void uprobe_link_info_func_3(void)
+{
+	asm volatile ("");
+	uprobe_link_info_sema_3++;
+}
+
+static int
+verify_umulti_link_info(int fd, bool retprobe, __u64 *offsets,
+			__u64 *cookies, __u64 *ref_ctr_offsets)
+{
+	char path[PATH_MAX], path_buf[PATH_MAX];
+	struct bpf_link_info info;
+	__u32 len = sizeof(info);
+	__u64 ref_ctr_offsets_buf[3];
+	__u64 offsets_buf[3];
+	__u64 cookies_buf[3];
+	int i, err, bit;
+	__u32 count = 0;
+
+	memset(path, 0, sizeof(path));
+	err = readlink("/proc/self/exe", path, sizeof(path));
+	if (!ASSERT_NEQ(err, -1, "readlink"))
+		return -1;
+
+	memset(&info, 0, sizeof(info));
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	if (!ASSERT_OK(err, "bpf_link_get_info_by_fd"))
+		return -1;
+
+	ASSERT_EQ(info.uprobe_multi.count, 3, "info.uprobe_multi.count");
+	ASSERT_EQ(info.uprobe_multi.path_size, strlen(path) + 1,
+		  "info.uprobe_multi.path_size");
+
+	for (bit = 0; bit < 8; bit++) {
+		memset(&info, 0, sizeof(info));
+		info.uprobe_multi.path = ptr_to_u64(path_buf);
+		info.uprobe_multi.path_size = sizeof(path_buf);
+		info.uprobe_multi.count = count;
+
+		if (bit & 0x1)
+			info.uprobe_multi.offsets = ptr_to_u64(offsets_buf);
+		if (bit & 0x2)
+			info.uprobe_multi.cookies = ptr_to_u64(cookies_buf);
+		if (bit & 0x4)
+			info.uprobe_multi.ref_ctr_offsets = ptr_to_u64(ref_ctr_offsets_buf);
+
+		err = bpf_link_get_info_by_fd(fd, &info, &len);
+		if (!ASSERT_OK(err, "bpf_link_get_info_by_fd"))
+			return -1;
+
+		if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_UPROBE_MULTI, "info.type"))
+			return -1;
+
+		ASSERT_EQ(info.uprobe_multi.pid, getpid(), "info.uprobe_multi.pid");
+		ASSERT_EQ(info.uprobe_multi.count, 3, "info.uprobe_multi.count");
+		ASSERT_EQ(info.uprobe_multi.flags & BPF_F_KPROBE_MULTI_RETURN,
+			  retprobe, "info.uprobe_multi.flags.retprobe");
+		ASSERT_EQ(info.uprobe_multi.path_size, strlen(path) + 1, "info.uprobe_multi.path_size");
+		ASSERT_STREQ(path_buf, path, "info.uprobe_multi.path");
+
+		for (i = 0; i < info.uprobe_multi.count; i++) {
+			if (info.uprobe_multi.offsets)
+				ASSERT_EQ(offsets_buf[i], offsets[i], "info.uprobe_multi.offsets");
+			if (info.uprobe_multi.cookies)
+				ASSERT_EQ(cookies_buf[i], cookies[i], "info.uprobe_multi.cookies");
+			if (info.uprobe_multi.ref_ctr_offsets) {
+				ASSERT_EQ(ref_ctr_offsets_buf[i], ref_ctr_offsets[i],
+					  "info.uprobe_multi.ref_ctr_offsets");
+			}
+		}
+		count = count ?: info.uprobe_multi.count;
+	}
+
+	return 0;
+}
+
+static void verify_umulti_invalid_user_buffer(int fd)
+{
+	struct bpf_link_info info;
+	__u32 len = sizeof(info);
+	__u64 buf[3];
+	int err;
+
+	/* upath_size defined, not path */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.path_size = 3;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EINVAL, "failed_upath_size");
+
+	/* path defined, but small */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.path = ptr_to_u64(buf);
+	info.uprobe_multi.path_size = 3;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_LT(err, 0, "failed_upath_small");
+
+	/* path has wrong pointer */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.path_size = PATH_MAX;
+	info.uprobe_multi.path = 123;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EFAULT, "failed_bad_path_ptr");
+
+	/* count zero, with offsets */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.offsets = ptr_to_u64(buf);
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EINVAL, "failed_count");
+
+	/* offsets not big enough */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.offsets = ptr_to_u64(buf);
+	info.uprobe_multi.count = 2;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -ENOSPC, "failed_small_count");
+
+	/* offsets has wrong pointer */
+	memset(&info, 0, sizeof(info));
+	info.uprobe_multi.offsets = 123;
+	info.uprobe_multi.count = 3;
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_EQ(err, -EFAULT, "failed_wrong_offsets");
+}
+
+static void test_uprobe_multi_fill_link_info(struct test_fill_link_info *skel,
+					     bool retprobe, bool invalid)
+{
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts,
+		.retprobe = retprobe,
+	);
+	const char *syms[3] = {
+		"uprobe_link_info_func_1",
+		"uprobe_link_info_func_2",
+		"uprobe_link_info_func_3",
+	};
+	__u64 cookies[3] = {
+		0xdead,
+		0xbeef,
+		0xcafe,
+	};
+	const char *sema[3] = {
+		"uprobe_link_info_sema_1",
+		"uprobe_link_info_sema_2",
+		"uprobe_link_info_sema_3",
+	};
+	__u64 *offsets = NULL, *ref_ctr_offsets;
+	struct bpf_link *link;
+	int link_fd, err;
+
+	err = elf_resolve_syms_offsets("/proc/self/exe", 3, sema,
+				       (unsigned long **) &ref_ctr_offsets, STT_OBJECT);
+	if (!ASSERT_OK(err, "elf_resolve_syms_offsets_object"))
+		return;
+
+	err = elf_resolve_syms_offsets("/proc/self/exe", 3, syms,
+				       (unsigned long **) &offsets, STT_FUNC);
+	if (!ASSERT_OK(err, "elf_resolve_syms_offsets_func"))
+		goto out;
+
+	opts.syms = syms;
+	opts.cookies = &cookies[0];
+	opts.ref_ctr_offsets = (unsigned long *) &ref_ctr_offsets[0];
+	opts.cnt = ARRAY_SIZE(syms);
+
+	link = bpf_program__attach_uprobe_multi(skel->progs.umulti_run, 0,
+						"/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto out;
+
+	link_fd = bpf_link__fd(link);
+	if (invalid)
+		verify_umulti_invalid_user_buffer(link_fd);
+	else
+		verify_umulti_link_info(link_fd, retprobe, offsets, cookies, ref_ctr_offsets);
+
+	bpf_link__destroy(link);
+out:
+	free(ref_ctr_offsets);
+	free(offsets);
+}
+
+void test_fill_link_info(void)
+{
+	struct test_fill_link_info *skel;
+	int i;
+
+	skel = test_fill_link_info__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	/* load kallsyms to compare the addr */
+	if (!ASSERT_OK(load_kallsyms(), "load_kallsyms"))
+		goto cleanup;
+
+	kprobe_addr = ksym_get_addr(KPROBE_FUNC);
+	if (test__start_subtest("kprobe_link_info"))
+		test_kprobe_fill_link_info(skel, BPF_PERF_EVENT_KPROBE, false);
+	if (test__start_subtest("kretprobe_link_info"))
+		test_kprobe_fill_link_info(skel, BPF_PERF_EVENT_KRETPROBE, false);
+	if (test__start_subtest("kprobe_invalid_ubuff"))
+		test_kprobe_fill_link_info(skel, BPF_PERF_EVENT_KPROBE, true);
+	if (test__start_subtest("tracepoint_link_info"))
+		test_tp_fill_link_info(skel);
+	if (test__start_subtest("event_link_info"))
+		test_event_fill_link_info(skel);
+
+	uprobe_offset = get_uprobe_offset(&uprobe_func);
+	if (test__start_subtest("uprobe_link_info"))
+		test_uprobe_fill_link_info(skel, BPF_PERF_EVENT_UPROBE);
+	if (test__start_subtest("uretprobe_link_info"))
+		test_uprobe_fill_link_info(skel, BPF_PERF_EVENT_URETPROBE);
+
+	qsort(kmulti_syms, KMULTI_CNT, sizeof(kmulti_syms[0]), symbols_cmp_r);
+	for (i = 0; i < KMULTI_CNT; i++)
+		kmulti_addrs[i] = ksym_get_addr(kmulti_syms[i]);
+	if (test__start_subtest("kprobe_multi_link_info")) {
+		test_kprobe_multi_fill_link_info(skel, false, false, false);
+		test_kprobe_multi_fill_link_info(skel, false, true, false);
+	}
+	if (test__start_subtest("kretprobe_multi_link_info")) {
+		test_kprobe_multi_fill_link_info(skel, true, false, false);
+		test_kprobe_multi_fill_link_info(skel, true, true, false);
+	}
+	if (test__start_subtest("kprobe_multi_invalid_ubuff"))
+		test_kprobe_multi_fill_link_info(skel, true, true, true);
+
+	if (test__start_subtest("uprobe_multi_link_info"))
+		test_uprobe_multi_fill_link_info(skel, false, false);
+	if (test__start_subtest("uretprobe_multi_link_info"))
+		test_uprobe_multi_fill_link_info(skel, true, false);
+	if (test__start_subtest("uprobe_multi_invalid"))
+		test_uprobe_multi_fill_link_info(skel, false, true);
+
+cleanup:
+	test_fill_link_info__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/find_vma.c b/tools/testing/selftests/bpf/prog_tests/find_vma.c
index 5165b38f0e59..f7619e0ade10 100644
--- a/tools/testing/selftests/bpf/prog_tests/find_vma.c
+++ b/tools/testing/selftests/bpf/prog_tests/find_vma.c
@@ -29,8 +29,8 @@ static int open_pe(void)
 
 	/* create perf event */
 	attr.size = sizeof(attr);
-	attr.type = PERF_TYPE_HARDWARE;
-	attr.config = PERF_COUNT_HW_CPU_CYCLES;
+	attr.type = PERF_TYPE_SOFTWARE;
+	attr.config = PERF_COUNT_SW_CPU_CLOCK;
 	attr.freq = 1;
 	attr.sample_freq = 1000;
 	pfd = syscall(__NR_perf_event_open, &attr, 0, -1, -1, PERF_FLAG_FD_CLOEXEC);
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
index 7acca37a3d2b..08bae13248c4 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
@@ -1,46 +1,20 @@
 // SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
 #include <test_progs.h>
 #include <network_helpers.h>
-#include <error.h>
-#include <linux/if.h>
 #include <linux/if_tun.h>
 #include <sys/uio.h>
 
 #include "bpf_flow.skel.h"
 
+#define TEST_NS	"flow_dissector_ns"
 #define FLOW_CONTINUE_SADDR 0x7f00007f /* 127.0.0.127 */
+#define TEST_NAME_MAX_LEN	64
 
 #ifndef IP_MF
 #define IP_MF 0x2000
 #endif
 
-#define CHECK_FLOW_KEYS(desc, got, expected)				\
-	_CHECK(memcmp(&got, &expected, sizeof(got)) != 0,		\
-	      desc,							\
-	      topts.duration,						\
-	      "nhoff=%u/%u "						\
-	      "thoff=%u/%u "						\
-	      "addr_proto=0x%x/0x%x "					\
-	      "is_frag=%u/%u "						\
-	      "is_first_frag=%u/%u "					\
-	      "is_encap=%u/%u "						\
-	      "ip_proto=0x%x/0x%x "					\
-	      "n_proto=0x%x/0x%x "					\
-	      "flow_label=0x%x/0x%x "					\
-	      "sport=%u/%u "						\
-	      "dport=%u/%u\n",						\
-	      got.nhoff, expected.nhoff,				\
-	      got.thoff, expected.thoff,				\
-	      got.addr_proto, expected.addr_proto,			\
-	      got.is_frag, expected.is_frag,				\
-	      got.is_first_frag, expected.is_first_frag,		\
-	      got.is_encap, expected.is_encap,				\
-	      got.ip_proto, expected.ip_proto,				\
-	      got.n_proto, expected.n_proto,				\
-	      got.flow_label, expected.flow_label,			\
-	      got.sport, expected.sport,				\
-	      got.dport, expected.dport)
-
 struct ipv4_pkt {
 	struct ethhdr eth;
 	struct iphdr iph;
@@ -90,6 +64,19 @@ struct dvlan_ipv6_pkt {
 	struct tcphdr tcp;
 } __packed;
 
+struct gre_base_hdr {
+	__be16 flags;
+	__be16 protocol;
+} gre_base_hdr;
+
+struct gre_minimal_pkt {
+	struct ethhdr eth;
+	struct iphdr iph;
+	struct gre_base_hdr gre_hdr;
+	struct iphdr iph_inner;
+	struct tcphdr tcp;
+} __packed;
+
 struct test {
 	const char *name;
 	union {
@@ -99,6 +86,7 @@ struct test {
 		struct ipv6_pkt ipv6;
 		struct ipv6_frag_pkt ipv6_frag;
 		struct dvlan_ipv6_pkt dvlan_ipv6;
+		struct gre_minimal_pkt gre_minimal;
 	} pkt;
 	struct bpf_flow_keys keys;
 	__u32 flags;
@@ -107,7 +95,6 @@ struct test {
 
 #define VLAN_HLEN	4
 
-static __u32 duration;
 struct test tests[] = {
 	{
 		.name = "ipv4",
@@ -346,6 +333,30 @@ struct test tests[] = {
 		.retval = BPF_OK,
 	},
 	{
+		.name = "ipv6-empty-flow-label",
+		.pkt.ipv6 = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.iph.nexthdr = IPPROTO_TCP,
+			.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+			.iph.flow_lbl = { 0x00, 0x00, 0x00 },
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.flags = BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL,
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct ipv6hdr),
+			.addr_proto = ETH_P_IPV6,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+			.sport = 80,
+			.dport = 8080,
+		},
+		.flags = BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL,
+		.retval = BPF_OK,
+	},
+	{
 		.name = "ipip-encap",
 		.pkt.ipip = {
 			.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
@@ -355,8 +366,8 @@ struct test tests[] = {
 			.iph_inner.ihl = 5,
 			.iph_inner.protocol = IPPROTO_TCP,
 			.iph_inner.tot_len =
-				__bpf_constant_htons(MAGIC_BYTES) -
-				sizeof(struct iphdr),
+				__bpf_constant_htons(MAGIC_BYTES -
+				sizeof(struct iphdr)),
 			.tcp.doff = 5,
 			.tcp.source = 80,
 			.tcp.dest = 8080,
@@ -384,8 +395,8 @@ struct test tests[] = {
 			.iph_inner.ihl = 5,
 			.iph_inner.protocol = IPPROTO_TCP,
 			.iph_inner.tot_len =
-				__bpf_constant_htons(MAGIC_BYTES) -
-				sizeof(struct iphdr),
+				__bpf_constant_htons(MAGIC_BYTES -
+				sizeof(struct iphdr)),
 			.tcp.doff = 5,
 			.tcp.source = 80,
 			.tcp.dest = 8080,
@@ -413,16 +424,145 @@ struct test tests[] = {
 			.iph_inner.ihl = 5,
 			.iph_inner.protocol = IPPROTO_TCP,
 			.iph_inner.tot_len =
-				__bpf_constant_htons(MAGIC_BYTES) -
-				sizeof(struct iphdr),
+				__bpf_constant_htons(MAGIC_BYTES -
+				sizeof(struct iphdr)),
 			.tcp.doff = 5,
 			.tcp.source = 99,
 			.tcp.dest = 9090,
 		},
 		.retval = BPF_FLOW_DISSECTOR_CONTINUE,
 	},
+	{
+		.name = "ip-gre",
+		.pkt.gre_minimal = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
+			.iph.ihl = 5,
+			.iph.protocol = IPPROTO_GRE,
+			.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+			.gre_hdr = {
+				.flags = 0,
+				.protocol = __bpf_constant_htons(ETH_P_IP),
+			},
+			.iph_inner.ihl = 5,
+			.iph_inner.protocol = IPPROTO_TCP,
+			.iph_inner.tot_len =
+				__bpf_constant_htons(MAGIC_BYTES -
+				sizeof(struct iphdr)),
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct iphdr) * 2 +
+				 sizeof(struct gre_base_hdr),
+			.addr_proto = ETH_P_IP,
+			.ip_proto = IPPROTO_TCP,
+			.n_proto = __bpf_constant_htons(ETH_P_IP),
+			.is_encap = true,
+			.sport = 80,
+			.dport = 8080,
+		},
+		.retval = BPF_OK,
+	},
+	{
+		.name = "ip-gre-no-encap",
+		.pkt.ipip = {
+			.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
+			.iph.ihl = 5,
+			.iph.protocol = IPPROTO_GRE,
+			.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+			.iph_inner.ihl = 5,
+			.iph_inner.protocol = IPPROTO_TCP,
+			.iph_inner.tot_len =
+				__bpf_constant_htons(MAGIC_BYTES -
+				sizeof(struct iphdr)),
+			.tcp.doff = 5,
+			.tcp.source = 80,
+			.tcp.dest = 8080,
+		},
+		.keys = {
+			.flags = BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP,
+			.nhoff = ETH_HLEN,
+			.thoff = ETH_HLEN + sizeof(struct iphdr)
+				 + sizeof(struct gre_base_hdr),
+			.addr_proto = ETH_P_IP,
+			.ip_proto = IPPROTO_GRE,
+			.n_proto = __bpf_constant_htons(ETH_P_IP),
+			.is_encap = true,
+		},
+		.flags = BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP,
+		.retval = BPF_OK,
+	},
 };
 
+void serial_test_flow_dissector_namespace(void)
+{
+	struct bpf_flow *skel;
+	struct nstoken *ns;
+	int err, prog_fd;
+
+	skel = bpf_flow__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open/load skeleton"))
+		return;
+
+	prog_fd = bpf_program__fd(skel->progs._dissect);
+	if (!ASSERT_OK_FD(prog_fd, "get dissector fd"))
+		goto out_destroy_skel;
+
+	/* We must be able to attach a flow dissector to root namespace */
+	err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0);
+	if (!ASSERT_OK(err, "attach on root namespace ok"))
+		goto out_destroy_skel;
+
+	err = make_netns(TEST_NS);
+	if (!ASSERT_OK(err, "create non-root net namespace"))
+		goto out_destroy_skel;
+
+	/* We must not be able to additionally attach a flow dissector to a
+	 * non-root net namespace
+	 */
+	ns = open_netns(TEST_NS);
+	if (!ASSERT_OK_PTR(ns, "enter non-root net namespace"))
+		goto out_clean_ns;
+	err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0);
+	if (!ASSERT_ERR(err,
+			"refuse new flow dissector in non-root net namespace"))
+		bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR);
+	else
+		ASSERT_EQ(errno, EEXIST,
+			  "refused because of already attached prog");
+	close_netns(ns);
+
+	/* If no flow dissector is attached to the root namespace, we must
+	 * be able to attach one to a non-root net namespace
+	 */
+	bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR);
+	ns = open_netns(TEST_NS);
+	ASSERT_OK_PTR(ns, "enter non-root net namespace");
+	err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0);
+	close_netns(ns);
+	ASSERT_OK(err, "accept new flow dissector in non-root net namespace");
+
+	/* If a flow dissector is attached to non-root net namespace, attaching
+	 * a flow dissector to root namespace must fail
+	 */
+	err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0);
+	if (!ASSERT_ERR(err, "refuse new flow dissector on root namespace"))
+		bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR);
+	else
+		ASSERT_EQ(errno, EEXIST,
+			  "refused because of already attached prog");
+
+	ns = open_netns(TEST_NS);
+	bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR);
+	close_netns(ns);
+out_clean_ns:
+	remove_netns(TEST_NS);
+out_destroy_skel:
+	bpf_flow__destroy(skel);
+}
+
 static int create_tap(const char *ifname)
 {
 	struct ifreq ifr = {
@@ -510,22 +650,27 @@ static int init_prog_array(struct bpf_object *obj, struct bpf_map *prog_array)
 	return 0;
 }
 
-static void run_tests_skb_less(int tap_fd, struct bpf_map *keys)
+static void run_tests_skb_less(int tap_fd, struct bpf_map *keys,
+			       char *test_suffix)
 {
+	char test_name[TEST_NAME_MAX_LEN];
 	int i, err, keys_fd;
 
 	keys_fd = bpf_map__fd(keys);
-	if (CHECK(keys_fd < 0, "bpf_map__fd", "err %d\n", keys_fd))
+	if (!ASSERT_OK_FD(keys_fd, "bpf_map__fd"))
 		return;
 
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		/* Keep in sync with 'flags' from eth_get_headlen. */
 		__u32 eth_get_headlen_flags =
 			BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG;
-		LIBBPF_OPTS(bpf_test_run_opts, topts);
 		struct bpf_flow_keys flow_keys = {};
 		__u32 key = (__u32)(tests[i].keys.sport) << 16 |
 			    tests[i].keys.dport;
+		snprintf(test_name, TEST_NAME_MAX_LEN, "%s-%s", tests[i].name,
+			 test_suffix);
+		if (!test__start_subtest(test_name))
+			continue;
 
 		/* For skb-less case we can't pass input flags; run
 		 * only the tests that have a matching set of flags.
@@ -535,78 +680,139 @@ static void run_tests_skb_less(int tap_fd, struct bpf_map *keys)
 			continue;
 
 		err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt));
-		CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno);
+		if (!ASSERT_EQ(err, sizeof(tests[i].pkt), "tx_tap"))
+			continue;
 
 		/* check the stored flow_keys only if BPF_OK expected */
 		if (tests[i].retval != BPF_OK)
 			continue;
 
 		err = bpf_map_lookup_elem(keys_fd, &key, &flow_keys);
-		ASSERT_OK(err, "bpf_map_lookup_elem");
+		if (!ASSERT_OK(err, "bpf_map_lookup_elem"))
+			continue;
 
-		CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys);
+		ASSERT_MEMEQ(&flow_keys, &tests[i].keys,
+			     sizeof(struct bpf_flow_keys),
+			     "returned flow keys");
 
 		err = bpf_map_delete_elem(keys_fd, &key);
 		ASSERT_OK(err, "bpf_map_delete_elem");
 	}
 }
 
-static void test_skb_less_prog_attach(struct bpf_flow *skel, int tap_fd)
+void test_flow_dissector_skb_less_direct_attach(void)
 {
-	int err, prog_fd;
+	int err, prog_fd, tap_fd;
+	struct bpf_flow *skel;
+	struct netns_obj *ns;
 
-	prog_fd = bpf_program__fd(skel->progs._dissect);
-	if (CHECK(prog_fd < 0, "bpf_program__fd", "err %d\n", prog_fd))
+	ns = netns_new("flow_dissector_skb_less_indirect_attach_ns", true);
+	if (!ASSERT_OK_PTR(ns, "create and open netns"))
 		return;
 
+	skel = bpf_flow__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open/load skeleton"))
+		goto out_clean_ns;
+
+	err = init_prog_array(skel->obj, skel->maps.jmp_table);
+	if (!ASSERT_OK(err, "init_prog_array"))
+		goto out_destroy_skel;
+
+	prog_fd = bpf_program__fd(skel->progs._dissect);
+	if (!ASSERT_OK_FD(prog_fd, "bpf_program__fd"))
+		goto out_destroy_skel;
+
 	err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0);
-	if (CHECK(err, "bpf_prog_attach", "err %d errno %d\n", err, errno))
-		return;
+	if (!ASSERT_OK(err, "bpf_prog_attach"))
+		goto out_destroy_skel;
+
+	tap_fd = create_tap("tap0");
+	if (!ASSERT_OK_FD(tap_fd, "create_tap"))
+		goto out_destroy_skel;
+	err = ifup("tap0");
+	if (!ASSERT_OK(err, "ifup"))
+		goto out_close_tap;
 
-	run_tests_skb_less(tap_fd, skel->maps.last_dissection);
+	run_tests_skb_less(tap_fd, skel->maps.last_dissection,
+			   "non-skb-direct-attach");
 
 	err = bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR);
-	CHECK(err, "bpf_prog_detach2", "err %d errno %d\n", err, errno);
+	ASSERT_OK(err, "bpf_prog_detach2");
+
+out_close_tap:
+	close(tap_fd);
+out_destroy_skel:
+	bpf_flow__destroy(skel);
+out_clean_ns:
+	netns_free(ns);
 }
 
-static void test_skb_less_link_create(struct bpf_flow *skel, int tap_fd)
+void test_flow_dissector_skb_less_indirect_attach(void)
 {
+	int err, net_fd, tap_fd;
+	struct bpf_flow *skel;
 	struct bpf_link *link;
-	int err, net_fd;
+	struct netns_obj *ns;
 
-	net_fd = open("/proc/self/ns/net", O_RDONLY);
-	if (CHECK(net_fd < 0, "open(/proc/self/ns/net)", "err %d\n", errno))
+	ns = netns_new("flow_dissector_skb_less_indirect_attach_ns", true);
+	if (!ASSERT_OK_PTR(ns, "create and open netns"))
 		return;
 
+	skel = bpf_flow__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open/load skeleton"))
+		goto out_clean_ns;
+
+	net_fd = open("/proc/self/ns/net", O_RDONLY);
+	if (!ASSERT_OK_FD(net_fd, "open(/proc/self/ns/net"))
+		goto out_destroy_skel;
+
+	err = init_prog_array(skel->obj, skel->maps.jmp_table);
+	if (!ASSERT_OK(err, "init_prog_array"))
+		goto out_destroy_skel;
+
+	tap_fd = create_tap("tap0");
+	if (!ASSERT_OK_FD(tap_fd, "create_tap"))
+		goto out_close_ns;
+	err = ifup("tap0");
+	if (!ASSERT_OK(err, "ifup"))
+		goto out_close_tap;
+
 	link = bpf_program__attach_netns(skel->progs._dissect, net_fd);
 	if (!ASSERT_OK_PTR(link, "attach_netns"))
-		goto out_close;
+		goto out_close_tap;
 
-	run_tests_skb_less(tap_fd, skel->maps.last_dissection);
+	run_tests_skb_less(tap_fd, skel->maps.last_dissection,
+			   "non-skb-indirect-attach");
 
 	err = bpf_link__destroy(link);
-	CHECK(err, "bpf_link__destroy", "err %d\n", err);
-out_close:
+	ASSERT_OK(err, "bpf_link__destroy");
+
+out_close_tap:
+	close(tap_fd);
+out_close_ns:
 	close(net_fd);
+out_destroy_skel:
+	bpf_flow__destroy(skel);
+out_clean_ns:
+	netns_free(ns);
 }
 
-void test_flow_dissector(void)
+void test_flow_dissector_skb(void)
 {
-	int i, err, prog_fd, keys_fd = -1, tap_fd;
+	char test_name[TEST_NAME_MAX_LEN];
 	struct bpf_flow *skel;
+	int i, err, prog_fd;
 
 	skel = bpf_flow__open_and_load();
-	if (CHECK(!skel, "skel", "failed to open/load skeleton\n"))
+	if (!ASSERT_OK_PTR(skel, "open/load skeleton"))
 		return;
 
-	prog_fd = bpf_program__fd(skel->progs._dissect);
-	if (CHECK(prog_fd < 0, "bpf_program__fd", "err %d\n", prog_fd))
-		goto out_destroy_skel;
-	keys_fd = bpf_map__fd(skel->maps.last_dissection);
-	if (CHECK(keys_fd < 0, "bpf_map__fd", "err %d\n", keys_fd))
-		goto out_destroy_skel;
 	err = init_prog_array(skel->obj, skel->maps.jmp_table);
-	if (CHECK(err, "init_prog_array", "err %d\n", err))
+	if (!ASSERT_OK(err, "init_prog_array"))
+		goto out_destroy_skel;
+
+	prog_fd = bpf_program__fd(skel->progs._dissect);
+	if (!ASSERT_OK_FD(prog_fd, "bpf_program__fd"))
 		goto out_destroy_skel;
 
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
@@ -618,6 +824,10 @@ void test_flow_dissector(void)
 		);
 		static struct bpf_flow_keys ctx = {};
 
+		snprintf(test_name, TEST_NAME_MAX_LEN, "%s-skb", tests[i].name);
+		if (!test__start_subtest(test_name))
+			continue;
+
 		if (tests[i].flags) {
 			topts.ctx_in = &ctx;
 			topts.ctx_size_in = sizeof(ctx);
@@ -633,26 +843,12 @@ void test_flow_dissector(void)
 			continue;
 		ASSERT_EQ(topts.data_size_out, sizeof(flow_keys),
 			  "test_run data_size_out");
-		CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys);
+		ASSERT_MEMEQ(&flow_keys, &tests[i].keys,
+			     sizeof(struct bpf_flow_keys),
+			     "returned flow keys");
 	}
 
-	/* Do the same tests but for skb-less flow dissector.
-	 * We use a known path in the net/tun driver that calls
-	 * eth_get_headlen and we manually export bpf_flow_keys
-	 * via BPF map in this case.
-	 */
-
-	tap_fd = create_tap("tap0");
-	CHECK(tap_fd < 0, "create_tap", "tap_fd %d errno %d\n", tap_fd, errno);
-	err = ifup("tap0");
-	CHECK(err, "ifup", "err %d errno %d\n", err, errno);
-
-	/* Test direct prog attachment */
-	test_skb_less_prog_attach(skel, tap_fd);
-	/* Test indirect prog attachment via link */
-	test_skb_less_link_create(skel, tap_fd);
-
-	close(tap_fd);
 out_destroy_skel:
 	bpf_flow__destroy(skel);
 }
+
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c
new file mode 100644
index 000000000000..80b153d3ddec
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c
@@ -0,0 +1,797 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <bpf/bpf.h>
+#include <linux/bpf.h>
+#include <bpf/libbpf.h>
+#include <arpa/inet.h>
+#include <asm/byteorder.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <unistd.h>
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "bpf_util.h"
+#include "bpf_flow.skel.h"
+
+#define CFG_PORT_INNER 8000
+#define CFG_PORT_GUE 6080
+#define SUBTEST_NAME_MAX_LEN 32
+#define TEST_NAME_MAX_LEN (32 + SUBTEST_NAME_MAX_LEN)
+#define MAX_SOURCE_PORTS 3
+#define TEST_PACKETS_COUNT 10
+#define TEST_PACKET_LEN 100
+#define TEST_PACKET_PATTERN 'a'
+#define TEST_IPV4 "192.168.0.1/32"
+#define TEST_IPV6 "100::a/128"
+#define TEST_TUNNEL_REMOTE "127.0.0.2"
+#define TEST_TUNNEL_LOCAL "127.0.0.1"
+
+#define INIT_ADDR4(addr4, port)					\
+	{							\
+		.sin_family = AF_INET,				\
+		.sin_port = __constant_htons(port),		\
+		.sin_addr.s_addr = __constant_htonl(addr4),	\
+	}
+
+#define INIT_ADDR6(addr6, port)				\
+	{						\
+		.sin6_family = AF_INET6,		\
+		.sin6_port = __constant_htons(port),	\
+		.sin6_addr = addr6,			\
+	}
+#define TEST_IN4_SRC_ADDR_DEFAULT INIT_ADDR4(INADDR_LOOPBACK + 2, 0)
+#define TEST_IN4_DST_ADDR_DEFAULT INIT_ADDR4(INADDR_LOOPBACK, CFG_PORT_INNER)
+#define TEST_OUT4_SRC_ADDR_DEFAULT INIT_ADDR4(INADDR_LOOPBACK + 1, 0)
+#define TEST_OUT4_DST_ADDR_DEFAULT INIT_ADDR4(INADDR_LOOPBACK, 0)
+
+#define TEST_IN6_SRC_ADDR_DEFAULT INIT_ADDR6(IN6ADDR_LOOPBACK_INIT, 0)
+#define TEST_IN6_DST_ADDR_DEFAULT \
+	INIT_ADDR6(IN6ADDR_LOOPBACK_INIT, CFG_PORT_INNER)
+#define TEST_OUT6_SRC_ADDR_DEFAULT INIT_ADDR6(IN6ADDR_LOOPBACK_INIT, 0)
+#define TEST_OUT6_DST_ADDR_DEFAULT INIT_ADDR6(IN6ADDR_LOOPBACK_INIT, 0)
+
+#define TEST_IN4_SRC_ADDR_DISSECT_CONTINUE INIT_ADDR4(INADDR_LOOPBACK + 126, 0)
+#define TEST_IN4_SRC_ADDR_IPIP INIT_ADDR4((in_addr_t)0x01010101, 0)
+#define TEST_IN4_DST_ADDR_IPIP INIT_ADDR4((in_addr_t)0xC0A80001, CFG_PORT_INNER)
+
+struct grehdr {
+	uint16_t unused;
+	uint16_t protocol;
+} __packed;
+
+struct guehdr {
+	union {
+		struct {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+			__u8 hlen : 5, control : 1, version : 2;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+			__u8 version : 2, control : 1, hlen : 5;
+#else
+#error "Please fix <asm/byteorder.h>"
+#endif
+			__u8 proto_ctype;
+			__be16 flags;
+		};
+		__be32 word;
+	};
+};
+
+static char buf[ETH_DATA_LEN];
+
+struct test_configuration {
+	char name[SUBTEST_NAME_MAX_LEN];
+	int (*test_setup)(void);
+	void (*test_teardown)(void);
+	int source_ports[MAX_SOURCE_PORTS];
+	int cfg_l3_inner;
+	struct sockaddr_in in_saddr4;
+	struct sockaddr_in in_daddr4;
+	struct sockaddr_in6 in_saddr6;
+	struct sockaddr_in6 in_daddr6;
+	int cfg_l3_outer;
+	struct sockaddr_in out_saddr4;
+	struct sockaddr_in out_daddr4;
+	struct sockaddr_in6 out_saddr6;
+	struct sockaddr_in6 out_daddr6;
+	int cfg_encap_proto;
+	uint8_t cfg_dsfield_inner;
+	uint8_t cfg_dsfield_outer;
+	int cfg_l3_extra;
+	struct sockaddr_in extra_saddr4;
+	struct sockaddr_in extra_daddr4;
+	struct sockaddr_in6 extra_saddr6;
+	struct sockaddr_in6 extra_daddr6;
+};
+
+static unsigned long util_gettime(void)
+{
+	struct timeval tv;
+
+	gettimeofday(&tv, NULL);
+	return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
+}
+
+static void build_ipv4_header(void *header, uint8_t proto, uint32_t src,
+			      uint32_t dst, int payload_len, uint8_t tos)
+{
+	struct iphdr *iph = header;
+
+	iph->ihl = 5;
+	iph->version = 4;
+	iph->tos = tos;
+	iph->ttl = 8;
+	iph->tot_len = htons(sizeof(*iph) + payload_len);
+	iph->id = htons(1337);
+	iph->protocol = proto;
+	iph->saddr = src;
+	iph->daddr = dst;
+	iph->check = build_ip_csum((void *)iph);
+}
+
+static void ipv6_set_dsfield(struct ipv6hdr *ip6h, uint8_t dsfield)
+{
+	uint16_t val, *ptr = (uint16_t *)ip6h;
+
+	val = ntohs(*ptr);
+	val &= 0xF00F;
+	val |= ((uint16_t)dsfield) << 4;
+	*ptr = htons(val);
+}
+
+static void build_ipv6_header(void *header, uint8_t proto,
+			      const struct sockaddr_in6 *src,
+			      const struct sockaddr_in6 *dst, int payload_len,
+			      uint8_t dsfield)
+{
+	struct ipv6hdr *ip6h = header;
+
+	ip6h->version = 6;
+	ip6h->payload_len = htons(payload_len);
+	ip6h->nexthdr = proto;
+	ip6h->hop_limit = 8;
+	ipv6_set_dsfield(ip6h, dsfield);
+
+	memcpy(&ip6h->saddr, &src->sin6_addr, sizeof(ip6h->saddr));
+	memcpy(&ip6h->daddr, &dst->sin6_addr, sizeof(ip6h->daddr));
+}
+
+static void build_udp_header(void *header, int payload_len, uint16_t sport,
+			     uint16_t dport, int family)
+{
+	struct udphdr *udph = header;
+	int len = sizeof(*udph) + payload_len;
+
+	udph->source = htons(sport);
+	udph->dest = htons(dport);
+	udph->len = htons(len);
+	udph->check = 0;
+	if (family == AF_INET)
+		udph->check = build_udp_v4_csum(header - sizeof(struct iphdr),
+						udph);
+	else
+		udph->check = build_udp_v6_csum(header - sizeof(struct ipv6hdr),
+						udph);
+}
+
+static void build_gue_header(void *header, uint8_t proto)
+{
+	struct guehdr *gueh = header;
+
+	gueh->proto_ctype = proto;
+}
+
+static void build_gre_header(void *header, uint16_t proto)
+{
+	struct grehdr *greh = header;
+
+	greh->protocol = htons(proto);
+}
+
+static int l3_length(int family)
+{
+	if (family == AF_INET)
+		return sizeof(struct iphdr);
+	else
+		return sizeof(struct ipv6hdr);
+}
+
+static int build_packet(const struct test_configuration *test, uint16_t sport)
+{
+	int ol3_len = 0, ol4_len = 0, il3_len = 0, il4_len = 0;
+	int el3_len = 0, packet_len;
+
+	memset(buf, 0, ETH_DATA_LEN);
+
+	if (test->cfg_l3_extra)
+		el3_len = l3_length(test->cfg_l3_extra);
+
+	/* calculate header offsets */
+	if (test->cfg_encap_proto) {
+		ol3_len = l3_length(test->cfg_l3_outer);
+
+		if (test->cfg_encap_proto == IPPROTO_GRE)
+			ol4_len = sizeof(struct grehdr);
+		else if (test->cfg_encap_proto == IPPROTO_UDP)
+			ol4_len = sizeof(struct udphdr) + sizeof(struct guehdr);
+	}
+
+	il3_len = l3_length(test->cfg_l3_inner);
+	il4_len = sizeof(struct udphdr);
+
+	packet_len = el3_len + ol3_len + ol4_len + il3_len + il4_len +
+		     TEST_PACKET_LEN;
+	if (!ASSERT_LE(packet_len, sizeof(buf), "check packet size"))
+		return -1;
+
+	/*
+	 * Fill packet from inside out, to calculate correct checksums.
+	 * But create ip before udp headers, as udp uses ip for pseudo-sum.
+	 */
+	memset(buf + el3_len + ol3_len + ol4_len + il3_len + il4_len,
+	       TEST_PACKET_PATTERN, TEST_PACKET_LEN);
+
+	/* add zero byte for udp csum padding */
+	buf[el3_len + ol3_len + ol4_len + il3_len + il4_len + TEST_PACKET_LEN] =
+		0;
+
+	switch (test->cfg_l3_inner) {
+	case PF_INET:
+		build_ipv4_header(buf + el3_len + ol3_len + ol4_len,
+				  IPPROTO_UDP, test->in_saddr4.sin_addr.s_addr,
+				  test->in_daddr4.sin_addr.s_addr,
+				  il4_len + TEST_PACKET_LEN,
+				  test->cfg_dsfield_inner);
+		break;
+	case PF_INET6:
+		build_ipv6_header(buf + el3_len + ol3_len + ol4_len,
+				  IPPROTO_UDP, &test->in_saddr6,
+				  &test->in_daddr6, il4_len + TEST_PACKET_LEN,
+				  test->cfg_dsfield_inner);
+		break;
+	}
+
+	build_udp_header(buf + el3_len + ol3_len + ol4_len + il3_len,
+			 TEST_PACKET_LEN, sport, CFG_PORT_INNER,
+			 test->cfg_l3_inner);
+
+	if (!test->cfg_encap_proto)
+		return il3_len + il4_len + TEST_PACKET_LEN;
+
+	switch (test->cfg_l3_outer) {
+	case PF_INET:
+		build_ipv4_header(buf + el3_len, test->cfg_encap_proto,
+				  test->out_saddr4.sin_addr.s_addr,
+				  test->out_daddr4.sin_addr.s_addr,
+				  ol4_len + il3_len + il4_len + TEST_PACKET_LEN,
+				  test->cfg_dsfield_outer);
+		break;
+	case PF_INET6:
+		build_ipv6_header(buf + el3_len, test->cfg_encap_proto,
+				  &test->out_saddr6, &test->out_daddr6,
+				  ol4_len + il3_len + il4_len + TEST_PACKET_LEN,
+				  test->cfg_dsfield_outer);
+		break;
+	}
+
+	switch (test->cfg_encap_proto) {
+	case IPPROTO_UDP:
+		build_gue_header(buf + el3_len + ol3_len + ol4_len -
+					 sizeof(struct guehdr),
+				 test->cfg_l3_inner == PF_INET ? IPPROTO_IPIP :
+								 IPPROTO_IPV6);
+		build_udp_header(buf + el3_len + ol3_len,
+				 sizeof(struct guehdr) + il3_len + il4_len +
+					 TEST_PACKET_LEN,
+				 sport, CFG_PORT_GUE, test->cfg_l3_outer);
+		break;
+	case IPPROTO_GRE:
+		build_gre_header(buf + el3_len + ol3_len,
+				 test->cfg_l3_inner == PF_INET ? ETH_P_IP :
+								 ETH_P_IPV6);
+		break;
+	}
+
+	switch (test->cfg_l3_extra) {
+	case PF_INET:
+		build_ipv4_header(buf,
+				  test->cfg_l3_outer == PF_INET ? IPPROTO_IPIP :
+								  IPPROTO_IPV6,
+				  test->extra_saddr4.sin_addr.s_addr,
+				  test->extra_daddr4.sin_addr.s_addr,
+				  ol3_len + ol4_len + il3_len + il4_len +
+					  TEST_PACKET_LEN,
+				  0);
+		break;
+	case PF_INET6:
+		build_ipv6_header(buf,
+				  test->cfg_l3_outer == PF_INET ? IPPROTO_IPIP :
+								  IPPROTO_IPV6,
+				  &test->extra_saddr6, &test->extra_daddr6,
+				  ol3_len + ol4_len + il3_len + il4_len +
+					  TEST_PACKET_LEN,
+				  0);
+		break;
+	}
+
+	return el3_len + ol3_len + ol4_len + il3_len + il4_len +
+	       TEST_PACKET_LEN;
+}
+
+/* sender transmits encapsulated over RAW or unencap'd over UDP */
+static int setup_tx(const struct test_configuration *test)
+{
+	int family, fd, ret;
+
+	if (test->cfg_l3_extra)
+		family = test->cfg_l3_extra;
+	else if (test->cfg_l3_outer)
+		family = test->cfg_l3_outer;
+	else
+		family = test->cfg_l3_inner;
+
+	fd = socket(family, SOCK_RAW, IPPROTO_RAW);
+	if (!ASSERT_OK_FD(fd, "setup tx socket"))
+		return fd;
+
+	if (test->cfg_l3_extra) {
+		if (test->cfg_l3_extra == PF_INET)
+			ret = connect(fd, (void *)&test->extra_daddr4,
+				      sizeof(test->extra_daddr4));
+		else
+			ret = connect(fd, (void *)&test->extra_daddr6,
+				      sizeof(test->extra_daddr6));
+		if (!ASSERT_OK(ret, "connect")) {
+			close(fd);
+			return ret;
+		}
+	} else if (test->cfg_l3_outer) {
+		/* connect to destination if not encapsulated */
+		if (test->cfg_l3_outer == PF_INET)
+			ret = connect(fd, (void *)&test->out_daddr4,
+				      sizeof(test->out_daddr4));
+		else
+			ret = connect(fd, (void *)&test->out_daddr6,
+				      sizeof(test->out_daddr6));
+		if (!ASSERT_OK(ret, "connect")) {
+			close(fd);
+			return ret;
+		}
+	} else {
+		/* otherwise using loopback */
+		if (test->cfg_l3_inner == PF_INET)
+			ret = connect(fd, (void *)&test->in_daddr4,
+				      sizeof(test->in_daddr4));
+		else
+			ret = connect(fd, (void *)&test->in_daddr6,
+				      sizeof(test->in_daddr6));
+		if (!ASSERT_OK(ret, "connect")) {
+			close(fd);
+			return ret;
+		}
+	}
+
+	return fd;
+}
+
+/* receiver reads unencapsulated UDP */
+static int setup_rx(const struct test_configuration *test)
+{
+	int fd, ret;
+
+	fd = socket(test->cfg_l3_inner, SOCK_DGRAM, 0);
+	if (!ASSERT_OK_FD(fd, "socket rx"))
+		return fd;
+
+	if (test->cfg_l3_inner == PF_INET)
+		ret = bind(fd, (void *)&test->in_daddr4,
+			   sizeof(test->in_daddr4));
+	else
+		ret = bind(fd, (void *)&test->in_daddr6,
+			   sizeof(test->in_daddr6));
+	if (!ASSERT_OK(ret, "bind rx")) {
+		close(fd);
+		return ret;
+	}
+
+	return fd;
+}
+
+static int do_tx(int fd, const char *pkt, int len)
+{
+	int ret;
+
+	ret = write(fd, pkt, len);
+	return ret != len;
+}
+
+static int do_poll(int fd, short events, int timeout)
+{
+	struct pollfd pfd;
+	int ret;
+
+	pfd.fd = fd;
+	pfd.events = events;
+
+	ret = poll(&pfd, 1, timeout);
+	return ret;
+}
+
+static int do_rx(int fd)
+{
+	char rbuf;
+	int ret, num = 0;
+
+	while (1) {
+		ret = recv(fd, &rbuf, 1, MSG_DONTWAIT);
+		if (ret == -1 && errno == EAGAIN)
+			break;
+		if (ret < 0)
+			return -1;
+		if (!ASSERT_EQ(rbuf, TEST_PACKET_PATTERN, "check pkt pattern"))
+			return -1;
+		num++;
+	}
+
+	return num;
+}
+
+static int run_test(const struct test_configuration *test,
+		    int source_port_index)
+{
+	int fdt = -1, fdr = -1, len, tx = 0, rx = 0, err;
+	unsigned long tstop, tcur;
+
+	fdr = setup_rx(test);
+	fdt = setup_tx(test);
+	if (!ASSERT_OK_FD(fdr, "setup rx") || !ASSERT_OK_FD(fdt, "setup tx")) {
+		err = -1;
+		goto out_close_sockets;
+	}
+
+	len = build_packet(test,
+			   (uint16_t)test->source_ports[source_port_index]);
+	if (!ASSERT_GT(len, 0, "build test packet"))
+		return -1;
+
+	tcur = util_gettime();
+	tstop = tcur;
+
+	while (tx < TEST_PACKETS_COUNT) {
+		if (!ASSERT_OK(do_tx(fdt, buf, len), "do_tx"))
+			break;
+		tx++;
+		err = do_rx(fdr);
+		if (!ASSERT_GE(err, 0, "do_rx"))
+			break;
+		rx += err;
+	}
+
+	/* read straggler packets, if any */
+	if (rx < tx) {
+		tstop = util_gettime() + 100;
+		while (rx < tx) {
+			tcur = util_gettime();
+			if (tcur >= tstop)
+				break;
+
+			err = do_poll(fdr, POLLIN, tstop - tcur);
+			if (err < 0)
+				break;
+			err = do_rx(fdr);
+			if (err >= 0)
+				rx += err;
+		}
+	}
+
+out_close_sockets:
+	close(fdt);
+	close(fdr);
+	return rx;
+}
+
+static int attach_and_configure_program(struct bpf_flow *skel)
+{
+	struct bpf_map *prog_array = skel->maps.jmp_table;
+	int main_prog_fd, sub_prog_fd, map_fd, i, err;
+	struct bpf_program *prog;
+	char prog_name[32];
+
+	main_prog_fd = bpf_program__fd(skel->progs._dissect);
+	if (main_prog_fd < 0)
+		return main_prog_fd;
+
+	err = bpf_prog_attach(main_prog_fd, 0, BPF_FLOW_DISSECTOR, 0);
+	if (err)
+		return err;
+
+	map_fd = bpf_map__fd(prog_array);
+	if (map_fd < 0)
+		return map_fd;
+
+	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
+		snprintf(prog_name, sizeof(prog_name), "flow_dissector_%d", i);
+
+		prog = bpf_object__find_program_by_name(skel->obj, prog_name);
+		if (!prog)
+			return -1;
+
+		sub_prog_fd = bpf_program__fd(prog);
+		if (sub_prog_fd < 0)
+			return -1;
+
+		err = bpf_map_update_elem(map_fd, &i, &sub_prog_fd, BPF_ANY);
+		if (err)
+			return -1;
+	}
+
+	return main_prog_fd;
+}
+
+static void detach_program(struct bpf_flow *skel, int prog_fd)
+{
+	bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR);
+}
+
+static int set_port_drop(int pf, bool multi_port)
+{
+	char dst_port[16];
+
+	snprintf(dst_port, sizeof(dst_port), "%d", CFG_PORT_INNER);
+
+	SYS(fail, "tc qdisc add dev lo ingress");
+	SYS(fail_delete_qdisc, "tc filter add %s %s %s %s %s %s %s %s %s %s %s %s",
+	    "dev lo",
+	    "parent FFFF:",
+	    "protocol", pf == PF_INET6 ? "ipv6" : "ip",
+	    "pref 1337",
+	    "flower",
+	    "ip_proto udp",
+	    "src_port", multi_port ? "8-10" : "9",
+	    "dst_port", dst_port,
+	    "action drop");
+	return 0;
+
+fail_delete_qdisc:
+	SYS_NOFAIL("tc qdisc del dev lo ingress");
+fail:
+	return 1;
+}
+
+static void remove_filter(void)
+{
+	SYS_NOFAIL("tc filter del dev lo ingress");
+	SYS_NOFAIL("tc qdisc del dev lo ingress");
+}
+
+static int ipv4_setup(void)
+{
+	return set_port_drop(PF_INET, false);
+}
+
+static int ipv6_setup(void)
+{
+	return set_port_drop(PF_INET6, false);
+}
+
+static int port_range_setup(void)
+{
+	return set_port_drop(PF_INET, true);
+}
+
+static int set_addresses(void)
+{
+	SYS(out, "ip -4 addr add  %s dev lo", TEST_IPV4);
+	SYS(out_remove_ipv4, "ip -6 addr add %s dev lo", TEST_IPV6);
+	return 0;
+out_remove_ipv4:
+	SYS_NOFAIL("ip -4 addr del %s dev lo", TEST_IPV4);
+out:
+	return -1;
+}
+
+static void unset_addresses(void)
+{
+	SYS_NOFAIL("ip -4 addr del %s dev lo", TEST_IPV4);
+	SYS_NOFAIL("ip -6 addr del %s dev lo", TEST_IPV6);
+}
+
+static int ipip_setup(void)
+{
+	if (!ASSERT_OK(set_addresses(), "configure addresses"))
+		return -1;
+	if (!ASSERT_OK(set_port_drop(PF_INET, false), "set filter"))
+		goto out_unset_addresses;
+	SYS(out_remove_filter,
+	    "ip link add ipip_test type ipip remote %s local %s dev lo",
+	    TEST_TUNNEL_REMOTE, TEST_TUNNEL_LOCAL);
+	SYS(out_clean_netif, "ip link set ipip_test up");
+	return 0;
+
+out_clean_netif:
+	SYS_NOFAIL("ip link del ipip_test");
+out_remove_filter:
+	remove_filter();
+out_unset_addresses:
+	unset_addresses();
+	return -1;
+}
+
+static void ipip_shutdown(void)
+{
+	SYS_NOFAIL("ip link del ipip_test");
+	remove_filter();
+	unset_addresses();
+}
+
+static int gre_setup(void)
+{
+	if (!ASSERT_OK(set_addresses(), "configure addresses"))
+		return -1;
+	if (!ASSERT_OK(set_port_drop(PF_INET, false), "set filter"))
+		goto out_unset_addresses;
+	SYS(out_remove_filter,
+	    "ip link add gre_test type gre remote %s local %s dev lo",
+	    TEST_TUNNEL_REMOTE, TEST_TUNNEL_LOCAL);
+	SYS(out_clean_netif, "ip link set gre_test up");
+	return 0;
+
+out_clean_netif:
+	SYS_NOFAIL("ip link del ipip_test");
+out_remove_filter:
+	remove_filter();
+out_unset_addresses:
+	unset_addresses();
+	return -1;
+}
+
+static void gre_shutdown(void)
+{
+	SYS_NOFAIL("ip link del gre_test");
+	remove_filter();
+	unset_addresses();
+}
+
+static const struct test_configuration tests_input[] = {
+	{
+		.name = "ipv4",
+		.test_setup = ipv4_setup,
+		.test_teardown = remove_filter,
+		.source_ports = { 8, 9, 10 },
+		.cfg_l3_inner = PF_INET,
+		.in_saddr4 = TEST_IN4_SRC_ADDR_DEFAULT,
+		.in_daddr4 = TEST_IN4_DST_ADDR_DEFAULT
+	},
+	{
+		.name = "ipv4_continue_dissect",
+		.test_setup = ipv4_setup,
+		.test_teardown = remove_filter,
+		.source_ports = { 8, 9, 10 },
+		.cfg_l3_inner = PF_INET,
+		.in_saddr4 = TEST_IN4_SRC_ADDR_DISSECT_CONTINUE,
+		.in_daddr4 = TEST_IN4_DST_ADDR_DEFAULT },
+	{
+		.name = "ipip",
+		.test_setup = ipip_setup,
+		.test_teardown = ipip_shutdown,
+		.source_ports = { 8, 9, 10 },
+		.cfg_l3_inner = PF_INET,
+		.in_saddr4 = TEST_IN4_SRC_ADDR_IPIP,
+		.in_daddr4 = TEST_IN4_DST_ADDR_IPIP,
+		.out_saddr4 = TEST_OUT4_SRC_ADDR_DEFAULT,
+		.out_daddr4 = TEST_OUT4_DST_ADDR_DEFAULT,
+		.cfg_l3_outer = PF_INET,
+		.cfg_encap_proto = IPPROTO_IPIP,
+
+	},
+	{
+		.name = "gre",
+		.test_setup = gre_setup,
+		.test_teardown = gre_shutdown,
+		.source_ports = { 8, 9, 10 },
+		.cfg_l3_inner = PF_INET,
+		.in_saddr4 = TEST_IN4_SRC_ADDR_IPIP,
+		.in_daddr4 = TEST_IN4_DST_ADDR_IPIP,
+		.out_saddr4 = TEST_OUT4_SRC_ADDR_DEFAULT,
+		.out_daddr4 = TEST_OUT4_DST_ADDR_DEFAULT,
+		.cfg_l3_outer = PF_INET,
+		.cfg_encap_proto = IPPROTO_GRE,
+	},
+	{
+		.name = "port_range",
+		.test_setup = port_range_setup,
+		.test_teardown = remove_filter,
+		.source_ports = { 7, 9, 11 },
+		.cfg_l3_inner = PF_INET,
+		.in_saddr4 = TEST_IN4_SRC_ADDR_DEFAULT,
+		.in_daddr4 = TEST_IN4_DST_ADDR_DEFAULT },
+	{
+		.name = "ipv6",
+		.test_setup = ipv6_setup,
+		.test_teardown = remove_filter,
+		.source_ports = { 8, 9, 10 },
+		.cfg_l3_inner = PF_INET6,
+		.in_saddr6 = TEST_IN6_SRC_ADDR_DEFAULT,
+		.in_daddr6 = TEST_IN6_DST_ADDR_DEFAULT
+	},
+};
+
+struct test_ctx {
+	struct bpf_flow *skel;
+	struct netns_obj *ns;
+	int prog_fd;
+};
+
+static int test_global_init(struct test_ctx *ctx)
+{
+	int err;
+
+	ctx->skel = bpf_flow__open_and_load();
+	if (!ASSERT_OK_PTR(ctx->skel, "open and load flow_dissector"))
+		return -1;
+
+	ctx->ns = netns_new("flow_dissector_classification", true);
+	if (!ASSERT_OK_PTR(ctx->ns, "switch ns"))
+		goto out_destroy_skel;
+
+	err = write_sysctl("/proc/sys/net/ipv4/conf/default/rp_filter", "0");
+	err |= write_sysctl("/proc/sys/net/ipv4/conf/all/rp_filter", "0");
+	err |= write_sysctl("/proc/sys/net/ipv4/conf/lo/rp_filter", "0");
+	if (!ASSERT_OK(err, "configure net tunables"))
+		goto out_clean_ns;
+
+	ctx->prog_fd = attach_and_configure_program(ctx->skel);
+	if (!ASSERT_OK_FD(ctx->prog_fd, "attach and configure program"))
+		goto out_clean_ns;
+	return 0;
+out_clean_ns:
+	netns_free(ctx->ns);
+out_destroy_skel:
+	bpf_flow__destroy(ctx->skel);
+	return -1;
+}
+
+static void test_global_shutdown(struct test_ctx *ctx)
+{
+	detach_program(ctx->skel, ctx->prog_fd);
+	netns_free(ctx->ns);
+	bpf_flow__destroy(ctx->skel);
+}
+
+void test_flow_dissector_classification(void)
+{
+	struct test_ctx ctx;
+	const struct test_configuration *test;
+	int i;
+
+	if (test_global_init(&ctx))
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(tests_input); i++) {
+		if (!test__start_subtest(tests_input[i].name))
+			continue;
+		test = &tests_input[i];
+		/* All tests are expected to have one rx-ok port first,
+		 * then a non-working rx port, and finally a rx-ok port
+		 */
+		if (test->test_setup &&
+		    !ASSERT_OK(test->test_setup(), "init filter"))
+			continue;
+
+		ASSERT_EQ(run_test(test, 0), TEST_PACKETS_COUNT,
+			  "test first port");
+		ASSERT_EQ(run_test(test, 1), 0, "test second port");
+		ASSERT_EQ(run_test(test, 2), TEST_PACKETS_COUNT,
+			  "test third port");
+		if (test->test_teardown)
+			test->test_teardown();
+	}
+	test_global_shutdown(&ctx);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
index 7c79462d2702..9333f7346d15 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
@@ -60,9 +60,9 @@ static __u32 query_prog_id(int prog)
 	__u32 info_len = sizeof(info);
 	int err;
 
-	err = bpf_obj_get_info_by_fd(prog, &info, &info_len);
+	err = bpf_prog_get_info_by_fd(prog, &info, &info_len);
 	if (CHECK_FAIL(err || info_len != sizeof(info))) {
-		perror("bpf_obj_get_info_by_fd");
+		perror("bpf_prog_get_info_by_fd");
 		return 0;
 	}
 
@@ -497,7 +497,7 @@ static void test_link_get_info(int netns, int prog1, int prog2)
 	}
 
 	info_len = sizeof(info);
-	err = bpf_obj_get_info_by_fd(link, &info, &info_len);
+	err = bpf_link_get_info_by_fd(link, &info, &info_len);
 	if (CHECK_FAIL(err)) {
 		perror("bpf_obj_get_info");
 		goto out_unlink;
@@ -521,7 +521,7 @@ static void test_link_get_info(int netns, int prog1, int prog2)
 
 	link_id = info.id;
 	info_len = sizeof(info);
-	err = bpf_obj_get_info_by_fd(link, &info, &info_len);
+	err = bpf_link_get_info_by_fd(link, &info, &info_len);
 	if (CHECK_FAIL(err)) {
 		perror("bpf_obj_get_info");
 		goto out_unlink;
@@ -546,7 +546,7 @@ static void test_link_get_info(int netns, int prog1, int prog2)
 	netns = -1;
 
 	info_len = sizeof(info);
-	err = bpf_obj_get_info_by_fd(link, &info, &info_len);
+	err = bpf_link_get_info_by_fd(link, &info, &info_len);
 	if (CHECK_FAIL(err)) {
 		perror("bpf_obj_get_info");
 		goto out_unlink;
diff --git a/tools/testing/selftests/bpf/prog_tests/for_each.c b/tools/testing/selftests/bpf/prog_tests/for_each.c
index 8963f8a549f2..5fea3209566e 100644
--- a/tools/testing/selftests/bpf/prog_tests/for_each.c
+++ b/tools/testing/selftests/bpf/prog_tests/for_each.c
@@ -5,6 +5,8 @@
 #include "for_each_hash_map_elem.skel.h"
 #include "for_each_array_map_elem.skel.h"
 #include "for_each_map_elem_write_key.skel.h"
+#include "for_each_multi_maps.skel.h"
+#include "for_each_hash_modify.skel.h"
 
 static unsigned int duration;
 
@@ -143,6 +145,99 @@ static void test_write_map_key(void)
 		for_each_map_elem_write_key__destroy(skel);
 }
 
+static void test_multi_maps(void)
+{
+	struct for_each_multi_maps *skel;
+	__u64 val, array_total, hash_total;
+	__u32 key, max_entries;
+	int i, err;
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = 1,
+	);
+
+	skel = for_each_multi_maps__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "for_each_multi_maps__open_and_load"))
+		return;
+
+	array_total = 0;
+	max_entries = bpf_map__max_entries(skel->maps.arraymap);
+	for (i = 0; i < max_entries; i++) {
+		key = i;
+		val = i + 1;
+		array_total += val;
+		err = bpf_map__update_elem(skel->maps.arraymap, &key, sizeof(key),
+					   &val, sizeof(val), BPF_ANY);
+		if (!ASSERT_OK(err, "array_map_update"))
+			goto out;
+	}
+
+	hash_total = 0;
+	max_entries = bpf_map__max_entries(skel->maps.hashmap);
+	for (i = 0; i < max_entries; i++) {
+		key = i + 100;
+		val = i + 1;
+		hash_total += val;
+		err = bpf_map__update_elem(skel->maps.hashmap, &key, sizeof(key),
+					   &val, sizeof(val), BPF_ANY);
+		if (!ASSERT_OK(err, "hash_map_update"))
+			goto out;
+	}
+
+	skel->bss->data_output = 0;
+	skel->bss->use_array = 1;
+	err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_pkt_access), &topts);
+	ASSERT_OK(err, "bpf_prog_test_run_opts");
+	ASSERT_OK(topts.retval, "retval");
+	ASSERT_EQ(skel->bss->data_output, array_total, "array output");
+
+	skel->bss->data_output = 0;
+	skel->bss->use_array = 0;
+	err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_pkt_access), &topts);
+	ASSERT_OK(err, "bpf_prog_test_run_opts");
+	ASSERT_OK(topts.retval, "retval");
+	ASSERT_EQ(skel->bss->data_output, hash_total, "hash output");
+
+out:
+	for_each_multi_maps__destroy(skel);
+}
+
+static void test_hash_modify(void)
+{
+	struct for_each_hash_modify *skel;
+	int max_entries, i, err;
+	__u64 key, val;
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = 1
+	);
+
+	skel = for_each_hash_modify__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "for_each_hash_modify__open_and_load"))
+		return;
+
+	max_entries = bpf_map__max_entries(skel->maps.hashmap);
+	for (i = 0; i < max_entries; i++) {
+		key = i;
+		val = i;
+		err = bpf_map__update_elem(skel->maps.hashmap, &key, sizeof(key),
+					   &val, sizeof(val), BPF_ANY);
+		if (!ASSERT_OK(err, "map_update"))
+			goto out;
+	}
+
+	err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_pkt_access), &topts);
+	ASSERT_OK(err, "bpf_prog_test_run_opts");
+	ASSERT_OK(topts.retval, "retval");
+
+out:
+	for_each_hash_modify__destroy(skel);
+}
+
 void test_for_each(void)
 {
 	if (test__start_subtest("hash_map"))
@@ -151,4 +246,8 @@ void test_for_each(void)
 		test_array_map();
 	if (test__start_subtest("write_map_key"))
 		test_write_map_key();
+	if (test__start_subtest("multi_maps"))
+		test_multi_maps();
+	if (test__start_subtest("hash_modify"))
+		test_hash_modify();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/free_timer.c b/tools/testing/selftests/bpf/prog_tests/free_timer.c
new file mode 100644
index 000000000000..0de8facca4c5
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/free_timer.c
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2025. Huawei Technologies Co., Ltd */
+#define _GNU_SOURCE
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <test_progs.h>
+
+#include "free_timer.skel.h"
+
+struct run_ctx {
+	struct bpf_program *start_prog;
+	struct bpf_program *overwrite_prog;
+	pthread_barrier_t notify;
+	int loop;
+	bool start;
+	bool stop;
+};
+
+static void start_threads(struct run_ctx *ctx)
+{
+	ctx->start = true;
+}
+
+static void stop_threads(struct run_ctx *ctx)
+{
+	ctx->stop = true;
+	/* Guarantee the order between ->stop and ->start */
+	__atomic_store_n(&ctx->start, true, __ATOMIC_RELEASE);
+}
+
+static int wait_for_start(struct run_ctx *ctx)
+{
+	while (!__atomic_load_n(&ctx->start, __ATOMIC_ACQUIRE))
+		usleep(10);
+
+	return ctx->stop;
+}
+
+static void *overwrite_timer_fn(void *arg)
+{
+	struct run_ctx *ctx = arg;
+	int loop, fd, err;
+	cpu_set_t cpuset;
+	long ret = 0;
+
+	/* Pin on CPU 0 */
+	CPU_ZERO(&cpuset);
+	CPU_SET(0, &cpuset);
+	pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset);
+
+	/* Is the thread being stopped ? */
+	err = wait_for_start(ctx);
+	if (err)
+		return NULL;
+
+	fd = bpf_program__fd(ctx->overwrite_prog);
+	loop = ctx->loop;
+	while (loop-- > 0) {
+		LIBBPF_OPTS(bpf_test_run_opts, opts);
+
+		/* Wait for start thread to complete */
+		pthread_barrier_wait(&ctx->notify);
+
+		/* Overwrite timers */
+		err = bpf_prog_test_run_opts(fd, &opts);
+		if (err)
+			ret |= 1;
+		else if (opts.retval)
+			ret |= 2;
+
+		/* Notify start thread to start timers */
+		pthread_barrier_wait(&ctx->notify);
+	}
+
+	return (void *)ret;
+}
+
+static void *start_timer_fn(void *arg)
+{
+	struct run_ctx *ctx = arg;
+	int loop, fd, err;
+	cpu_set_t cpuset;
+	long ret = 0;
+
+	/* Pin on CPU 1 */
+	CPU_ZERO(&cpuset);
+	CPU_SET(1, &cpuset);
+	pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset);
+
+	/* Is the thread being stopped ? */
+	err = wait_for_start(ctx);
+	if (err)
+		return NULL;
+
+	fd = bpf_program__fd(ctx->start_prog);
+	loop = ctx->loop;
+	while (loop-- > 0) {
+		LIBBPF_OPTS(bpf_test_run_opts, opts);
+
+		/* Run the prog to start timer */
+		err = bpf_prog_test_run_opts(fd, &opts);
+		if (err)
+			ret |= 4;
+		else if (opts.retval)
+			ret |= 8;
+
+		/* Notify overwrite thread to do overwrite */
+		pthread_barrier_wait(&ctx->notify);
+
+		/* Wait for overwrite thread to complete */
+		pthread_barrier_wait(&ctx->notify);
+	}
+
+	return (void *)ret;
+}
+
+void test_free_timer(void)
+{
+	struct free_timer *skel;
+	struct bpf_program *prog;
+	struct run_ctx ctx;
+	pthread_t tid[2];
+	void *ret;
+	int err;
+
+	skel = free_timer__open_and_load();
+	if (!skel && errno == EOPNOTSUPP) {
+		test__skip();
+		return;
+	}
+	if (!ASSERT_OK_PTR(skel, "open_load"))
+		return;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	prog = bpf_object__find_program_by_name(skel->obj, "start_timer");
+	if (!ASSERT_OK_PTR(prog, "find start prog"))
+		goto out;
+	ctx.start_prog = prog;
+
+	prog = bpf_object__find_program_by_name(skel->obj, "overwrite_timer");
+	if (!ASSERT_OK_PTR(prog, "find overwrite prog"))
+		goto out;
+	ctx.overwrite_prog = prog;
+
+	pthread_barrier_init(&ctx.notify, NULL, 2);
+	ctx.loop = 10;
+
+	err = pthread_create(&tid[0], NULL, start_timer_fn, &ctx);
+	if (!ASSERT_OK(err, "create start_timer"))
+		goto out;
+
+	err = pthread_create(&tid[1], NULL, overwrite_timer_fn, &ctx);
+	if (!ASSERT_OK(err, "create overwrite_timer")) {
+		stop_threads(&ctx);
+		goto out;
+	}
+
+	start_threads(&ctx);
+
+	ret = NULL;
+	err = pthread_join(tid[0], &ret);
+	ASSERT_EQ(err | (long)ret, 0, "start_timer");
+	ret = NULL;
+	err = pthread_join(tid[1], &ret);
+	ASSERT_EQ(err | (long)ret, 0, "overwrite_timer");
+out:
+	free_timer__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c b/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c
new file mode 100644
index 000000000000..43a26ec69a8e
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/fs_kfuncs.c
@@ -0,0 +1,291 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <stdlib.h>
+#include <sys/types.h>
+#include <sys/xattr.h>
+#include <linux/fsverity.h>
+#include <unistd.h>
+#include <test_progs.h>
+#include "test_get_xattr.skel.h"
+#include "test_set_remove_xattr.skel.h"
+#include "test_fsverity.skel.h"
+
+static const char testfile[] = "/tmp/test_progs_fs_kfuncs";
+
+static void test_get_xattr(const char *name, const char *value, bool allow_access)
+{
+	struct test_get_xattr *skel = NULL;
+	int fd = -1, err;
+	int v[32];
+
+	fd = open(testfile, O_CREAT | O_RDONLY, 0644);
+	if (!ASSERT_GE(fd, 0, "create_file"))
+		return;
+
+	close(fd);
+	fd = -1;
+
+	err = setxattr(testfile, name, value, strlen(value) + 1, 0);
+	if (err && errno == EOPNOTSUPP) {
+		printf("%s:SKIP:local fs doesn't support xattr (%d)\n"
+		       "To run this test, make sure /tmp filesystem supports xattr.\n",
+		       __func__, errno);
+		test__skip();
+		goto out;
+	}
+
+	if (!ASSERT_OK(err, "setxattr"))
+		goto out;
+
+	skel = test_get_xattr__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_get_xattr__open_and_load"))
+		goto out;
+
+	skel->bss->monitored_pid = getpid();
+	err = test_get_xattr__attach(skel);
+
+	if (!ASSERT_OK(err, "test_get_xattr__attach"))
+		goto out;
+
+	fd = open(testfile, O_RDONLY, 0644);
+
+	if (!ASSERT_GE(fd, 0, "open_file"))
+		goto out;
+
+	/* Trigger security_inode_getxattr */
+	err = getxattr(testfile, name, v, sizeof(v));
+
+	if (allow_access) {
+		ASSERT_EQ(err, -1, "getxattr_return");
+		ASSERT_EQ(errno, EINVAL, "getxattr_errno");
+		ASSERT_EQ(skel->bss->found_xattr_from_file, 1, "found_xattr_from_file");
+		ASSERT_EQ(skel->bss->found_xattr_from_dentry, 1, "found_xattr_from_dentry");
+	} else {
+		ASSERT_EQ(err, strlen(value) + 1, "getxattr_return");
+		ASSERT_EQ(skel->bss->found_xattr_from_file, 0, "found_xattr_from_file");
+		ASSERT_EQ(skel->bss->found_xattr_from_dentry, 0, "found_xattr_from_dentry");
+	}
+
+out:
+	close(fd);
+	test_get_xattr__destroy(skel);
+	remove(testfile);
+}
+
+/* xattr value we will set to security.bpf.foo */
+static const char value_foo[] = "hello";
+
+static void read_and_validate_foo(struct test_set_remove_xattr *skel)
+{
+	char value_out[32];
+	int err;
+
+	err = getxattr(testfile, skel->rodata->xattr_foo, value_out, sizeof(value_out));
+	ASSERT_EQ(err, sizeof(value_foo), "getxattr size foo");
+	ASSERT_EQ(strncmp(value_out, value_foo, sizeof(value_foo)), 0, "strncmp value_foo");
+}
+
+static void set_foo(struct test_set_remove_xattr *skel)
+{
+	ASSERT_OK(setxattr(testfile, skel->rodata->xattr_foo, value_foo, strlen(value_foo) + 1, 0),
+		  "setxattr foo");
+}
+
+static void validate_bar_match(struct test_set_remove_xattr *skel)
+{
+	char value_out[32];
+	int err;
+
+	err = getxattr(testfile, skel->rodata->xattr_bar, value_out, sizeof(value_out));
+	ASSERT_EQ(err, sizeof(skel->data->value_bar), "getxattr size bar");
+	ASSERT_EQ(strncmp(value_out, skel->data->value_bar, sizeof(skel->data->value_bar)), 0,
+		  "strncmp value_bar");
+}
+
+static void validate_bar_removed(struct test_set_remove_xattr *skel)
+{
+	char value_out[32];
+	int err;
+
+	err = getxattr(testfile, skel->rodata->xattr_bar, value_out, sizeof(value_out));
+	ASSERT_LT(err, 0, "getxattr size bar should fail");
+}
+
+static void test_set_remove_xattr(void)
+{
+	struct test_set_remove_xattr *skel = NULL;
+	int fd = -1, err;
+
+	fd = open(testfile, O_CREAT | O_RDONLY, 0644);
+	if (!ASSERT_GE(fd, 0, "create_file"))
+		return;
+
+	close(fd);
+	fd = -1;
+
+	skel = test_set_remove_xattr__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_set_remove_xattr__open_and_load"))
+		return;
+
+	/* Set security.bpf.foo to "hello" */
+	err = setxattr(testfile, skel->rodata->xattr_foo, value_foo, strlen(value_foo) + 1, 0);
+	if (err && errno == EOPNOTSUPP) {
+		printf("%s:SKIP:local fs doesn't support xattr (%d)\n"
+		       "To run this test, make sure /tmp filesystem supports xattr.\n",
+		       __func__, errno);
+		test__skip();
+		goto out;
+	}
+
+	if (!ASSERT_OK(err, "setxattr"))
+		goto out;
+
+	skel->bss->monitored_pid = getpid();
+	err = test_set_remove_xattr__attach(skel);
+	if (!ASSERT_OK(err, "test_set_remove_xattr__attach"))
+		goto out;
+
+	/* First, test not _locked version of the kfuncs with getxattr. */
+
+	/* Read security.bpf.foo and trigger test_inode_getxattr. This
+	 * bpf program will set security.bpf.bar to "world".
+	 */
+	read_and_validate_foo(skel);
+	validate_bar_match(skel);
+
+	/* Read security.bpf.foo and trigger test_inode_getxattr again.
+	 * This will remove xattr security.bpf.bar.
+	 */
+	read_and_validate_foo(skel);
+	validate_bar_removed(skel);
+
+	ASSERT_TRUE(skel->bss->set_security_bpf_bar_success, "set_security_bpf_bar_success");
+	ASSERT_TRUE(skel->bss->remove_security_bpf_bar_success, "remove_security_bpf_bar_success");
+	ASSERT_TRUE(skel->bss->set_security_selinux_fail, "set_security_selinux_fail");
+	ASSERT_TRUE(skel->bss->remove_security_selinux_fail, "remove_security_selinux_fail");
+
+	/* Second, test _locked version of the kfuncs, with setxattr */
+
+	/* Set security.bpf.foo and trigger test_inode_setxattr. This
+	 * bpf program will set security.bpf.bar to "world".
+	 */
+	set_foo(skel);
+	validate_bar_match(skel);
+
+	/* Set security.bpf.foo and trigger test_inode_setxattr again.
+	 * This will remove xattr security.bpf.bar.
+	 */
+	set_foo(skel);
+	validate_bar_removed(skel);
+
+	ASSERT_TRUE(skel->bss->locked_set_security_bpf_bar_success,
+		    "locked_set_security_bpf_bar_success");
+	ASSERT_TRUE(skel->bss->locked_remove_security_bpf_bar_success,
+		    "locked_remove_security_bpf_bar_success");
+	ASSERT_TRUE(skel->bss->locked_set_security_selinux_fail,
+		    "locked_set_security_selinux_fail");
+	ASSERT_TRUE(skel->bss->locked_remove_security_selinux_fail,
+		    "locked_remove_security_selinux_fail");
+
+out:
+	close(fd);
+	test_set_remove_xattr__destroy(skel);
+	remove(testfile);
+}
+
+#ifndef SHA256_DIGEST_SIZE
+#define SHA256_DIGEST_SIZE      32
+#endif
+
+static void test_fsverity(void)
+{
+	struct fsverity_enable_arg arg = {0};
+	struct test_fsverity *skel = NULL;
+	struct fsverity_digest *d;
+	int fd, err;
+	char buffer[4096];
+
+	fd = open(testfile, O_CREAT | O_RDWR, 0644);
+	if (!ASSERT_GE(fd, 0, "create_file"))
+		return;
+
+	/* Write random buffer, so the file is not empty */
+	err = write(fd, buffer, 4096);
+	if (!ASSERT_EQ(err, 4096, "write_file"))
+		goto out;
+	close(fd);
+
+	/* Reopen read-only, otherwise FS_IOC_ENABLE_VERITY will fail */
+	fd = open(testfile, O_RDONLY, 0644);
+	if (!ASSERT_GE(fd, 0, "open_file1"))
+		return;
+
+	/* Enable fsverity for the file.
+	 * If the file system doesn't support verity, this will fail. Skip
+	 * the test in such case.
+	 */
+	arg.version = 1;
+	arg.hash_algorithm = FS_VERITY_HASH_ALG_SHA256;
+	arg.block_size = 4096;
+	err = ioctl(fd, FS_IOC_ENABLE_VERITY, &arg);
+	if (err) {
+		printf("%s:SKIP:local fs doesn't support fsverity (%d)\n"
+		       "To run this test, try enable CONFIG_FS_VERITY and enable FSVerity for the filesystem.\n",
+		       __func__, errno);
+		test__skip();
+		goto out;
+	}
+
+	skel = test_fsverity__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_fsverity__open_and_load"))
+		goto out;
+
+	/* Get fsverity_digest from ioctl */
+	d = (struct fsverity_digest *)skel->bss->expected_digest;
+	d->digest_algorithm = FS_VERITY_HASH_ALG_SHA256;
+	d->digest_size = SHA256_DIGEST_SIZE;
+	err = ioctl(fd, FS_IOC_MEASURE_VERITY, skel->bss->expected_digest);
+	if (!ASSERT_OK(err, "ioctl_FS_IOC_MEASURE_VERITY"))
+		goto out;
+
+	skel->bss->monitored_pid = getpid();
+	err = test_fsverity__attach(skel);
+	if (!ASSERT_OK(err, "test_fsverity__attach"))
+		goto out;
+
+	/* Reopen the file to trigger the program */
+	close(fd);
+	fd = open(testfile, O_RDONLY);
+	if (!ASSERT_GE(fd, 0, "open_file2"))
+		goto out;
+
+	ASSERT_EQ(skel->bss->got_fsverity, 1, "got_fsverity");
+	ASSERT_EQ(skel->bss->digest_matches, 1, "digest_matches");
+out:
+	close(fd);
+	test_fsverity__destroy(skel);
+	remove(testfile);
+}
+
+void test_fs_kfuncs(void)
+{
+	/* Matches xattr_names in progs/test_get_xattr.c */
+	if (test__start_subtest("user_xattr"))
+		test_get_xattr("user.kfuncs", "hello", true);
+
+	if (test__start_subtest("security_bpf_xattr"))
+		test_get_xattr("security.bpf.xxx", "hello", true);
+
+	if (test__start_subtest("security_bpf_xattr_error"))
+		test_get_xattr("security.bpf", "hello", false);
+
+	if (test__start_subtest("security_selinux_xattr_error"))
+		test_get_xattr("security.selinux", "hello", false);
+
+	if (test__start_subtest("set_remove_xattr"))
+		test_set_remove_xattr();
+
+	if (test__start_subtest("fsverity"))
+		test_fsverity();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
index 3948da12a528..0394a1156d99 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
@@ -37,8 +37,8 @@ static int create_perf_events(void)
 
 	/* create perf event */
 	attr.size = sizeof(attr);
-	attr.type = PERF_TYPE_RAW;
-	attr.config = 0x1b00;
+	attr.type = PERF_TYPE_HARDWARE;
+	attr.config = PERF_COUNT_HW_CPU_CYCLES;
 	attr.sample_type = PERF_SAMPLE_BRANCH_STACK;
 	attr.branch_sample_type = PERF_SAMPLE_BRANCH_KERNEL |
 		PERF_SAMPLE_BRANCH_USER | PERF_SAMPLE_BRANCH_ANY;
diff --git a/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c b/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c
index 28cf63963cb7..64a9c95d4acf 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c
@@ -30,7 +30,9 @@ void test_get_func_args_test(void)
 	prog_fd = bpf_program__fd(skel->progs.fmod_ret_test);
 	err = bpf_prog_test_run_opts(prog_fd, &topts);
 	ASSERT_OK(err, "test_run");
-	ASSERT_EQ(topts.retval, 1234, "test_run");
+
+	ASSERT_EQ(topts.retval >> 16, 1, "test_run");
+	ASSERT_EQ(topts.retval & 0xffff, 1234 + 29, "test_run");
 
 	ASSERT_EQ(skel->bss->test1_result, 1, "test1_result");
 	ASSERT_EQ(skel->bss->test2_result, 1, "test2_result");
diff --git a/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c b/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c
index fede8ef58b5b..c40242dfa8fb 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_func_ip_test.c
@@ -1,6 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 #include "get_func_ip_test.skel.h"
+#include "get_func_ip_uprobe_test.skel.h"
+
+static noinline void uprobe_trigger(void)
+{
+}
 
 static void test_function_entry(void)
 {
@@ -20,6 +25,8 @@ static void test_function_entry(void)
 	if (!ASSERT_OK(err, "get_func_ip_test__attach"))
 		goto cleanup;
 
+	skel->bss->uprobe_trigger = (unsigned long) uprobe_trigger;
+
 	prog_fd = bpf_program__fd(skel->progs.test1);
 	err = bpf_prog_test_run_opts(prog_fd, &topts);
 	ASSERT_OK(err, "test_run");
@@ -30,21 +37,31 @@ static void test_function_entry(void)
 
 	ASSERT_OK(err, "test_run");
 
+	uprobe_trigger();
+
 	ASSERT_EQ(skel->bss->test1_result, 1, "test1_result");
 	ASSERT_EQ(skel->bss->test2_result, 1, "test2_result");
 	ASSERT_EQ(skel->bss->test3_result, 1, "test3_result");
 	ASSERT_EQ(skel->bss->test4_result, 1, "test4_result");
 	ASSERT_EQ(skel->bss->test5_result, 1, "test5_result");
+	ASSERT_EQ(skel->bss->test7_result, 1, "test7_result");
+	ASSERT_EQ(skel->bss->test8_result, 1, "test8_result");
 
 cleanup:
 	get_func_ip_test__destroy(skel);
 }
 
-/* test6 is x86_64 specific because of the instruction
- * offset, disabling it for all other archs
- */
 #ifdef __x86_64__
-static void test_function_body(void)
+extern void uprobe_trigger_body(void);
+asm(
+".globl uprobe_trigger_body\n"
+".type uprobe_trigger_body, @function\n"
+"uprobe_trigger_body:\n"
+"	nop\n"
+"	ret\n"
+);
+
+static void test_function_body_kprobe(void)
 {
 	struct get_func_ip_test *skel = NULL;
 	LIBBPF_OPTS(bpf_test_run_opts, topts);
@@ -56,6 +73,9 @@ static void test_function_body(void)
 	if (!ASSERT_OK_PTR(skel, "get_func_ip_test__open"))
 		return;
 
+	/* test6 is x86_64 specific and is disabled by default,
+	 * enable it for body test.
+	 */
 	bpf_program__set_autoload(skel->progs.test6, true);
 
 	err = get_func_ip_test__load(skel);
@@ -79,6 +99,35 @@ cleanup:
 	bpf_link__destroy(link6);
 	get_func_ip_test__destroy(skel);
 }
+
+static void test_function_body_uprobe(void)
+{
+	struct get_func_ip_uprobe_test *skel = NULL;
+	int err;
+
+	skel = get_func_ip_uprobe_test__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "get_func_ip_uprobe_test__open_and_load"))
+		return;
+
+	err = get_func_ip_uprobe_test__attach(skel);
+	if (!ASSERT_OK(err, "get_func_ip_test__attach"))
+		goto cleanup;
+
+	skel->bss->uprobe_trigger_body = (unsigned long) uprobe_trigger_body;
+
+	uprobe_trigger_body();
+
+	ASSERT_EQ(skel->bss->test1_result, 1, "test1_result");
+
+cleanup:
+	get_func_ip_uprobe_test__destroy(skel);
+}
+
+static void test_function_body(void)
+{
+	test_function_body_kprobe();
+	test_function_body_uprobe();
+}
 #else
 #define test_function_body()
 #endif
diff --git a/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c b/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c
index 5308de1ed478..2715c68301f5 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c
@@ -65,6 +65,7 @@ void test_get_stackid_cannot_attach(void)
 	skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu,
 							   pmu_fd);
 	ASSERT_OK_PTR(skel->links.oncpu, "attach_perf_event_callchain");
+	bpf_link__destroy(skel->links.oncpu);
 	close(pmu_fd);
 
 	/* add exclude_callchain_kernel, attach should fail */
diff --git a/tools/testing/selftests/bpf/prog_tests/global_func_dead_code.c b/tools/testing/selftests/bpf/prog_tests/global_func_dead_code.c
new file mode 100644
index 000000000000..65309894b27a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/global_func_dead_code.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <test_progs.h>
+#include "verifier_global_subprogs.skel.h"
+#include "freplace_dead_global_func.skel.h"
+
+void test_global_func_dead_code(void)
+{
+	struct verifier_global_subprogs *tgt_skel = NULL;
+	struct freplace_dead_global_func *skel = NULL;
+	char log_buf[4096];
+	int err, tgt_fd;
+
+	/* first, try to load target with good global subprog */
+	tgt_skel = verifier_global_subprogs__open();
+	if (!ASSERT_OK_PTR(tgt_skel, "tgt_skel_good_open"))
+		return;
+
+	bpf_program__set_autoload(tgt_skel->progs.chained_global_func_calls_success, true);
+
+	err = verifier_global_subprogs__load(tgt_skel);
+	if (!ASSERT_OK(err, "tgt_skel_good_load"))
+		goto out;
+
+	tgt_fd = bpf_program__fd(tgt_skel->progs.chained_global_func_calls_success);
+
+	/* Attach to good non-eliminated subprog */
+	skel = freplace_dead_global_func__open();
+	if (!ASSERT_OK_PTR(skel, "skel_good_open"))
+		goto out;
+
+	err = bpf_program__set_attach_target(skel->progs.freplace_prog, tgt_fd, "global_good");
+	ASSERT_OK(err, "attach_target_good");
+
+	err = freplace_dead_global_func__load(skel);
+	if (!ASSERT_OK(err, "skel_good_load"))
+		goto out;
+
+	freplace_dead_global_func__destroy(skel);
+
+	/* Try attaching to dead code-eliminated subprog */
+	skel = freplace_dead_global_func__open();
+	if (!ASSERT_OK_PTR(skel, "skel_dead_open"))
+		goto out;
+
+	bpf_program__set_log_buf(skel->progs.freplace_prog, log_buf, sizeof(log_buf));
+	err = bpf_program__set_attach_target(skel->progs.freplace_prog, tgt_fd, "global_dead");
+	ASSERT_OK(err, "attach_target_dead");
+
+	err = freplace_dead_global_func__load(skel);
+	if (!ASSERT_ERR(err, "skel_dead_load"))
+		goto out;
+
+	ASSERT_HAS_SUBSTR(log_buf, "Subprog global_dead doesn't exist", "dead_subprog_missing_msg");
+
+out:
+	verifier_global_subprogs__destroy(tgt_skel);
+	freplace_dead_global_func__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/global_map_resize.c b/tools/testing/selftests/bpf/prog_tests/global_map_resize.c
new file mode 100644
index 000000000000..56b5baef35c8
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/global_map_resize.c
@@ -0,0 +1,235 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+#include <errno.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+#include "test_global_map_resize.skel.h"
+#include "test_progs.h"
+
+static void run_prog_bss_array_sum(void)
+{
+	(void)syscall(__NR_getpid);
+}
+
+static void run_prog_data_array_sum(void)
+{
+	(void)syscall(__NR_getuid);
+}
+
+static void global_map_resize_bss_subtest(void)
+{
+	int err;
+	struct test_global_map_resize *skel;
+	struct bpf_map *map;
+	const __u32 desired_sz = sizeof(skel->bss->sum) + sysconf(_SC_PAGE_SIZE) * 2;
+	size_t array_len, actual_sz, new_sz;
+
+	skel = test_global_map_resize__open();
+	if (!ASSERT_OK_PTR(skel, "test_global_map_resize__open"))
+		goto teardown;
+
+	/* set some initial value before resizing.
+	 * it is expected this non-zero value will be preserved
+	 * while resizing.
+	 */
+	skel->bss->array[0] = 1;
+
+	/* resize map value and verify the new size */
+	map = skel->maps.bss;
+	err = bpf_map__set_value_size(map, desired_sz);
+	if (!ASSERT_OK(err, "bpf_map__set_value_size"))
+		goto teardown;
+	if (!ASSERT_EQ(bpf_map__value_size(map), desired_sz, "resize"))
+		goto teardown;
+
+	new_sz = sizeof(skel->data_percpu_arr->percpu_arr[0]) * libbpf_num_possible_cpus();
+	err = bpf_map__set_value_size(skel->maps.data_percpu_arr, new_sz);
+	ASSERT_OK(err, "percpu_arr_resize");
+
+	/* set the expected number of elements based on the resized array */
+	array_len = (desired_sz - sizeof(skel->bss->sum)) / sizeof(skel->bss->array[0]);
+	if (!ASSERT_GT(array_len, 1, "array_len"))
+		goto teardown;
+
+	skel->bss = bpf_map__initial_value(skel->maps.bss, &actual_sz);
+	if (!ASSERT_OK_PTR(skel->bss, "bpf_map__initial_value (ptr)"))
+		goto teardown;
+	if (!ASSERT_EQ(actual_sz, desired_sz, "bpf_map__initial_value (size)"))
+		goto teardown;
+
+	/* fill the newly resized array with ones,
+	 * skipping the first element which was previously set
+	 */
+	for (int i = 1; i < array_len; i++)
+		skel->bss->array[i] = 1;
+
+	/* set global const values before loading */
+	skel->rodata->pid = getpid();
+	skel->rodata->bss_array_len = array_len;
+	skel->rodata->data_array_len = 1;
+
+	err = test_global_map_resize__load(skel);
+	if (!ASSERT_OK(err, "test_global_map_resize__load"))
+		goto teardown;
+	err = test_global_map_resize__attach(skel);
+	if (!ASSERT_OK(err, "test_global_map_resize__attach"))
+		goto teardown;
+
+	/* run the bpf program which will sum the contents of the array.
+	 * since the array was filled with ones,verify the sum equals array_len
+	 */
+	run_prog_bss_array_sum();
+	if (!ASSERT_EQ(skel->bss->sum, array_len, "sum"))
+		goto teardown;
+
+teardown:
+	test_global_map_resize__destroy(skel);
+}
+
+static void global_map_resize_data_subtest(void)
+{
+	struct test_global_map_resize *skel;
+	struct bpf_map *map;
+	const __u32 desired_sz = sysconf(_SC_PAGE_SIZE) * 2;
+	size_t array_len, actual_sz, new_sz;
+	int err;
+
+	skel = test_global_map_resize__open();
+	if (!ASSERT_OK_PTR(skel, "test_global_map_resize__open"))
+		goto teardown;
+
+	/* set some initial value before resizing.
+	 * it is expected this non-zero value will be preserved
+	 * while resizing.
+	 */
+	skel->data_custom->my_array[0] = 1;
+
+	/* resize map value and verify the new size */
+	map = skel->maps.data_custom;
+	err = bpf_map__set_value_size(map, desired_sz);
+	if (!ASSERT_OK(err, "bpf_map__set_value_size"))
+		goto teardown;
+	if (!ASSERT_EQ(bpf_map__value_size(map), desired_sz, "resize"))
+		goto teardown;
+
+	new_sz = sizeof(skel->data_percpu_arr->percpu_arr[0]) * libbpf_num_possible_cpus();
+	err = bpf_map__set_value_size(skel->maps.data_percpu_arr, new_sz);
+	ASSERT_OK(err, "percpu_arr_resize");
+
+	/* set the expected number of elements based on the resized array */
+	array_len = (desired_sz - sizeof(skel->bss->sum)) / sizeof(skel->data_custom->my_array[0]);
+	if (!ASSERT_GT(array_len, 1, "array_len"))
+		goto teardown;
+
+	skel->data_custom = bpf_map__initial_value(skel->maps.data_custom, &actual_sz);
+	if (!ASSERT_OK_PTR(skel->data_custom, "bpf_map__initial_value (ptr)"))
+		goto teardown;
+	if (!ASSERT_EQ(actual_sz, desired_sz, "bpf_map__initial_value (size)"))
+		goto teardown;
+
+	/* fill the newly resized array with ones,
+	 * skipping the first element which was previously set
+	 */
+	for (int i = 1; i < array_len; i++)
+		skel->data_custom->my_array[i] = 1;
+
+	/* set global const values before loading */
+	skel->rodata->pid = getpid();
+	skel->rodata->bss_array_len = 1;
+	skel->rodata->data_array_len = array_len;
+
+	err = test_global_map_resize__load(skel);
+	if (!ASSERT_OK(err, "test_global_map_resize__load"))
+		goto teardown;
+	err = test_global_map_resize__attach(skel);
+	if (!ASSERT_OK(err, "test_global_map_resize__attach"))
+		goto teardown;
+
+	/* run the bpf program which will sum the contents of the array.
+	 * since the array was filled with ones,verify the sum equals array_len
+	 */
+	run_prog_data_array_sum();
+	if (!ASSERT_EQ(skel->bss->sum, array_len, "sum"))
+		goto teardown;
+
+teardown:
+	test_global_map_resize__destroy(skel);
+}
+
+static void global_map_resize_invalid_subtest(void)
+{
+	int err;
+	struct test_global_map_resize *skel;
+	struct bpf_map *map;
+	__u32 element_sz, desired_sz;
+
+	skel = test_global_map_resize__open();
+	if (!ASSERT_OK_PTR(skel, "test_global_map_resize__open"))
+		return;
+
+	 /* attempt to resize a global datasec map to size
+	  * which does NOT align with array
+	  */
+	map = skel->maps.data_custom;
+	if (!ASSERT_NEQ(bpf_map__btf_value_type_id(map), 0, ".data.custom initial btf"))
+		goto teardown;
+	/* set desired size a fraction of element size beyond an aligned size */
+	element_sz = sizeof(skel->data_custom->my_array[0]);
+	desired_sz = element_sz + element_sz / 2;
+	/* confirm desired size does NOT align with array */
+	if (!ASSERT_NEQ(desired_sz % element_sz, 0, "my_array alignment"))
+		goto teardown;
+	err = bpf_map__set_value_size(map, desired_sz);
+	/* confirm resize is OK but BTF info is cleared */
+	if (!ASSERT_OK(err, ".data.custom bpf_map__set_value_size") ||
+	    !ASSERT_EQ(bpf_map__btf_key_type_id(map), 0, ".data.custom clear btf key") ||
+	    !ASSERT_EQ(bpf_map__btf_value_type_id(map), 0, ".data.custom clear btf val"))
+		goto teardown;
+
+	/* attempt to resize a global datasec map whose only var is NOT an array */
+	map = skel->maps.data_non_array;
+	if (!ASSERT_NEQ(bpf_map__btf_value_type_id(map), 0, ".data.non_array initial btf"))
+		goto teardown;
+	/* set desired size to arbitrary value */
+	desired_sz = 1024;
+	err = bpf_map__set_value_size(map, desired_sz);
+	/* confirm resize is OK but BTF info is cleared */
+	if (!ASSERT_OK(err, ".data.non_array bpf_map__set_value_size") ||
+	    !ASSERT_EQ(bpf_map__btf_key_type_id(map), 0, ".data.non_array clear btf key") ||
+	    !ASSERT_EQ(bpf_map__btf_value_type_id(map), 0, ".data.non_array clear btf val"))
+		goto teardown;
+
+	/* attempt to resize a global datasec map
+	 * whose last var is NOT an array
+	 */
+	map = skel->maps.data_array_not_last;
+	if (!ASSERT_NEQ(bpf_map__btf_value_type_id(map), 0, ".data.array_not_last initial btf"))
+		goto teardown;
+	/* set desired size to a multiple of element size */
+	element_sz = sizeof(skel->data_array_not_last->my_array_first[0]);
+	desired_sz = element_sz * 8;
+	/* confirm desired size aligns with array */
+	if (!ASSERT_EQ(desired_sz % element_sz, 0, "my_array_first alignment"))
+		goto teardown;
+	err = bpf_map__set_value_size(map, desired_sz);
+	/* confirm resize is OK but BTF info is cleared */
+	if (!ASSERT_OK(err, ".data.array_not_last bpf_map__set_value_size") ||
+	    !ASSERT_EQ(bpf_map__btf_key_type_id(map), 0, ".data.array_not_last clear btf key") ||
+	    !ASSERT_EQ(bpf_map__btf_value_type_id(map), 0, ".data.array_not_last clear btf val"))
+		goto teardown;
+
+teardown:
+	test_global_map_resize__destroy(skel);
+}
+
+void test_global_map_resize(void)
+{
+	if (test__start_subtest("global_map_resize_bss"))
+		global_map_resize_bss_subtest();
+
+	if (test__start_subtest("global_map_resize_data"))
+		global_map_resize_data_subtest();
+
+	if (test__start_subtest("global_map_resize_invalid"))
+		global_map_resize_invalid_subtest();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/htab_reuse.c b/tools/testing/selftests/bpf/prog_tests/htab_reuse.c
new file mode 100644
index 000000000000..a742dd994d60
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/htab_reuse.c
@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#define _GNU_SOURCE
+#include <sched.h>
+#include <stdbool.h>
+#include <test_progs.h>
+#include "htab_reuse.skel.h"
+
+struct htab_op_ctx {
+	int fd;
+	int loop;
+	bool stop;
+};
+
+struct htab_val {
+	unsigned int lock;
+	unsigned int data;
+};
+
+static void *htab_lookup_fn(void *arg)
+{
+	struct htab_op_ctx *ctx = arg;
+	int i = 0;
+
+	while (i++ < ctx->loop && !ctx->stop) {
+		struct htab_val value;
+		unsigned int key;
+
+		/* Use BPF_F_LOCK to use spin-lock in map value. */
+		key = 7;
+		bpf_map_lookup_elem_flags(ctx->fd, &key, &value, BPF_F_LOCK);
+	}
+
+	return NULL;
+}
+
+static void *htab_update_fn(void *arg)
+{
+	struct htab_op_ctx *ctx = arg;
+	int i = 0;
+
+	while (i++ < ctx->loop && !ctx->stop) {
+		struct htab_val value;
+		unsigned int key;
+
+		key = 7;
+		value.lock = 0;
+		value.data = key;
+		bpf_map_update_elem(ctx->fd, &key, &value, BPF_F_LOCK);
+		bpf_map_delete_elem(ctx->fd, &key);
+
+		key = 24;
+		value.lock = 0;
+		value.data = key;
+		bpf_map_update_elem(ctx->fd, &key, &value, BPF_F_LOCK);
+		bpf_map_delete_elem(ctx->fd, &key);
+	}
+
+	return NULL;
+}
+
+void test_htab_reuse(void)
+{
+	unsigned int i, wr_nr = 1, rd_nr = 4;
+	pthread_t tids[wr_nr + rd_nr];
+	struct htab_reuse *skel;
+	struct htab_op_ctx ctx;
+	int err;
+
+	skel = htab_reuse__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "htab_reuse__open_and_load"))
+		return;
+
+	ctx.fd = bpf_map__fd(skel->maps.htab);
+	ctx.loop = 500;
+	ctx.stop = false;
+
+	memset(tids, 0, sizeof(tids));
+	for (i = 0; i < wr_nr; i++) {
+		err = pthread_create(&tids[i], NULL, htab_update_fn, &ctx);
+		if (!ASSERT_OK(err, "pthread_create")) {
+			ctx.stop = true;
+			goto reap;
+		}
+	}
+	for (i = 0; i < rd_nr; i++) {
+		err = pthread_create(&tids[i + wr_nr], NULL, htab_lookup_fn, &ctx);
+		if (!ASSERT_OK(err, "pthread_create")) {
+			ctx.stop = true;
+			goto reap;
+		}
+	}
+
+reap:
+	for (i = 0; i < wr_nr + rd_nr; i++) {
+		if (!tids[i])
+			continue;
+		pthread_join(tids[i], NULL);
+	}
+	htab_reuse__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/htab_update.c b/tools/testing/selftests/bpf/prog_tests/htab_update.c
index 2bc85f4814f4..d0b405eb2966 100644
--- a/tools/testing/selftests/bpf/prog_tests/htab_update.c
+++ b/tools/testing/selftests/bpf/prog_tests/htab_update.c
@@ -15,17 +15,17 @@ struct htab_update_ctx {
 static void test_reenter_update(void)
 {
 	struct htab_update *skel;
-	unsigned int key, value;
+	void *value = NULL;
+	unsigned int key, value_size;
 	int err;
 
 	skel = htab_update__open();
 	if (!ASSERT_OK_PTR(skel, "htab_update__open"))
 		return;
 
-	/* lookup_elem_raw() may be inlined and find_kernel_btf_id() will return -ESRCH */
-	bpf_program__set_autoload(skel->progs.lookup_elem_raw, true);
+	bpf_program__set_autoload(skel->progs.bpf_obj_free_fields, true);
 	err = htab_update__load(skel);
-	if (!ASSERT_TRUE(!err || err == -ESRCH, "htab_update__load") || err)
+	if (!ASSERT_TRUE(!err, "htab_update__load") || err)
 		goto out;
 
 	skel->bss->pid = getpid();
@@ -33,14 +33,33 @@ static void test_reenter_update(void)
 	if (!ASSERT_OK(err, "htab_update__attach"))
 		goto out;
 
-	/* Will trigger the reentrancy of bpf_map_update_elem() */
+	value_size = bpf_map__value_size(skel->maps.htab);
+
+	value = calloc(1, value_size);
+	if (!ASSERT_OK_PTR(value, "calloc value"))
+		goto out;
+	/*
+	 * First update: plain insert. This should NOT trigger the re-entrancy
+	 * path, because there is no old element to free yet.
+	 */
 	key = 0;
-	value = 0;
-	err = bpf_map_update_elem(bpf_map__fd(skel->maps.htab), &key, &value, 0);
-	if (!ASSERT_OK(err, "add element"))
+	err = bpf_map_update_elem(bpf_map__fd(skel->maps.htab), &key, value, BPF_ANY);
+	if (!ASSERT_OK(err, "first update (insert)"))
+		goto out;
+
+	/*
+	 * Second update: replace existing element with same key and trigger
+	 * the reentrancy of bpf_map_update_elem().
+	 * check_and_free_fields() calls bpf_obj_free_fields() on the old
+	 * value, which is where fentry program runs and performs a nested
+	 * bpf_map_update_elem(), triggering -EDEADLK.
+	 */
+	memset(value, 0, value_size);
+	err = bpf_map_update_elem(bpf_map__fd(skel->maps.htab), &key, value, BPF_ANY);
+	if (!ASSERT_OK(err, "second update (replace)"))
 		goto out;
 
-	ASSERT_EQ(skel->bss->update_err, -EBUSY, "no reentrancy");
+	ASSERT_EQ(skel->bss->update_err, -EDEADLK, "no reentrancy");
 out:
 	htab_update__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/inner_array_lookup.c b/tools/testing/selftests/bpf/prog_tests/inner_array_lookup.c
new file mode 100644
index 000000000000..9ab4cd195108
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/inner_array_lookup.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <test_progs.h>
+
+#include "inner_array_lookup.skel.h"
+
+void test_inner_array_lookup(void)
+{
+	int map1_fd, err;
+	int key = 3;
+	int val = 1;
+	struct inner_array_lookup *skel;
+
+	skel = inner_array_lookup__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_load_skeleton"))
+		return;
+
+	err = inner_array_lookup__attach(skel);
+	if (!ASSERT_OK(err, "skeleton_attach"))
+		goto cleanup;
+
+	map1_fd = bpf_map__fd(skel->maps.inner_map1);
+	bpf_map_update_elem(map1_fd, &key, &val, 0);
+
+	/* Probe should have set the element at index 3 to 2 */
+	bpf_map_lookup_elem(map1_fd, &key, &val);
+	ASSERT_EQ(val, 2, "value_is_2");
+
+cleanup:
+	inner_array_lookup__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/ip_check_defrag.c b/tools/testing/selftests/bpf/prog_tests/ip_check_defrag.c
new file mode 100644
index 000000000000..4ddb8a5fece8
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/ip_check_defrag.c
@@ -0,0 +1,283 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <net/if.h>
+#include <linux/netfilter.h>
+#include <network_helpers.h>
+#include "ip_check_defrag.skel.h"
+#include "ip_check_defrag_frags.h"
+
+/*
+ * This selftest spins up a client and an echo server, each in their own
+ * network namespace. The client will send a fragmented message to the server.
+ * The prog attached to the server will shoot down any fragments. Thus, if
+ * the server is able to correctly echo back the message to the client, we will
+ * have verified that netfilter is reassembling packets for us.
+ *
+ * Topology:
+ * =========
+ *           NS0         |         NS1
+ *                       |
+ *         client        |       server
+ *       ----------      |     ----------
+ *       |  veth0  | --------- |  veth1  |
+ *       ----------    peer    ----------
+ *                       |
+ *                       |       with bpf
+ */
+
+#define NS0		"defrag_ns0"
+#define NS1		"defrag_ns1"
+#define VETH0		"veth0"
+#define VETH1		"veth1"
+#define VETH0_ADDR	"172.16.1.100"
+#define VETH0_ADDR6	"fc00::100"
+/* The following constants must stay in sync with `generate_udp_fragments.py` */
+#define VETH1_ADDR	"172.16.1.200"
+#define VETH1_ADDR6	"fc00::200"
+#define CLIENT_PORT	48878
+#define SERVER_PORT	48879
+#define MAGIC_MESSAGE	"THIS IS THE ORIGINAL MESSAGE, PLEASE REASSEMBLE ME"
+
+static int setup_topology(bool ipv6)
+{
+	bool up;
+	int i;
+
+	SYS(fail, "ip netns add " NS0);
+	SYS(fail, "ip netns add " NS1);
+	SYS(fail, "ip link add " VETH0 " netns " NS0 " type veth peer name " VETH1 " netns " NS1);
+	if (ipv6) {
+		SYS(fail, "ip -6 -net " NS0 " addr add " VETH0_ADDR6 "/64 dev " VETH0 " nodad");
+		SYS(fail, "ip -6 -net " NS1 " addr add " VETH1_ADDR6 "/64 dev " VETH1 " nodad");
+	} else {
+		SYS(fail, "ip -net " NS0 " addr add " VETH0_ADDR "/24 dev " VETH0);
+		SYS(fail, "ip -net " NS1 " addr add " VETH1_ADDR "/24 dev " VETH1);
+	}
+	SYS(fail, "ip -net " NS0 " link set dev " VETH0 " up");
+	SYS(fail, "ip -net " NS1 " link set dev " VETH1 " up");
+
+	/* Wait for up to 5s for links to come up */
+	for (i = 0; i < 5; ++i) {
+		if (ipv6)
+			up = !SYS_NOFAIL("ip netns exec " NS0 " ping -6 -c 1 -W 1 " VETH1_ADDR6);
+		else
+			up = !SYS_NOFAIL("ip netns exec " NS0 " ping -c 1 -W 1 " VETH1_ADDR);
+
+		if (up)
+			break;
+	}
+
+	return 0;
+fail:
+	return -1;
+}
+
+static void cleanup_topology(void)
+{
+	SYS_NOFAIL("test -f /var/run/netns/" NS0 " && ip netns delete " NS0);
+	SYS_NOFAIL("test -f /var/run/netns/" NS1 " && ip netns delete " NS1);
+}
+
+static int attach(struct ip_check_defrag *skel, bool ipv6)
+{
+	LIBBPF_OPTS(bpf_netfilter_opts, opts,
+		    .pf = ipv6 ? NFPROTO_IPV6 : NFPROTO_IPV4,
+		    .priority = 42,
+		    .flags = BPF_F_NETFILTER_IP_DEFRAG);
+	struct nstoken *nstoken;
+	int err = -1;
+
+	nstoken = open_netns(NS1);
+	if (!ASSERT_OK_PTR(nstoken, "setns"))
+		goto out;
+
+	skel->links.defrag = bpf_program__attach_netfilter(skel->progs.defrag, &opts);
+	if (!ASSERT_OK_PTR(skel->links.defrag, "program attach"))
+		goto out;
+
+	err = 0;
+out:
+	close_netns(nstoken);
+	return err;
+}
+
+static int send_frags(int client)
+{
+	struct sockaddr_storage saddr;
+	struct sockaddr *saddr_p;
+	socklen_t saddr_len;
+	int err;
+
+	saddr_p = (struct sockaddr *)&saddr;
+	err = make_sockaddr(AF_INET, VETH1_ADDR, SERVER_PORT, &saddr, &saddr_len);
+	if (!ASSERT_OK(err, "make_sockaddr"))
+		return -1;
+
+	err = sendto(client, frag_0, sizeof(frag_0), 0, saddr_p, saddr_len);
+	if (!ASSERT_GE(err, 0, "sendto frag_0"))
+		return -1;
+
+	err = sendto(client, frag_1, sizeof(frag_1), 0, saddr_p, saddr_len);
+	if (!ASSERT_GE(err, 0, "sendto frag_1"))
+		return -1;
+
+	err = sendto(client, frag_2, sizeof(frag_2), 0, saddr_p, saddr_len);
+	if (!ASSERT_GE(err, 0, "sendto frag_2"))
+		return -1;
+
+	return 0;
+}
+
+static int send_frags6(int client)
+{
+	struct sockaddr_storage saddr;
+	struct sockaddr *saddr_p;
+	socklen_t saddr_len;
+	int err;
+
+	saddr_p = (struct sockaddr *)&saddr;
+	/* Port needs to be set to 0 for raw ipv6 socket for some reason */
+	err = make_sockaddr(AF_INET6, VETH1_ADDR6, 0, &saddr, &saddr_len);
+	if (!ASSERT_OK(err, "make_sockaddr"))
+		return -1;
+
+	err = sendto(client, frag6_0, sizeof(frag6_0), 0, saddr_p, saddr_len);
+	if (!ASSERT_GE(err, 0, "sendto frag6_0"))
+		return -1;
+
+	err = sendto(client, frag6_1, sizeof(frag6_1), 0, saddr_p, saddr_len);
+	if (!ASSERT_GE(err, 0, "sendto frag6_1"))
+		return -1;
+
+	err = sendto(client, frag6_2, sizeof(frag6_2), 0, saddr_p, saddr_len);
+	if (!ASSERT_GE(err, 0, "sendto frag6_2"))
+		return -1;
+
+	return 0;
+}
+
+void test_bpf_ip_check_defrag_ok(bool ipv6)
+{
+	int family = ipv6 ? AF_INET6 : AF_INET;
+	struct network_helper_opts rx_opts = {
+		.timeout_ms = 1000,
+	};
+	struct network_helper_opts tx_ops = {
+		.timeout_ms = 1000,
+		.proto = IPPROTO_RAW,
+	};
+	struct sockaddr_storage caddr;
+	struct ip_check_defrag *skel;
+	struct nstoken *nstoken;
+	int client_tx_fd = -1;
+	int client_rx_fd = -1;
+	socklen_t caddr_len;
+	int srv_fd = -1;
+	char buf[1024];
+	int len, err;
+
+	skel = ip_check_defrag__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	if (!ASSERT_OK(setup_topology(ipv6), "setup_topology"))
+		goto out;
+
+	if (!ASSERT_OK(attach(skel, ipv6), "attach"))
+		goto out;
+
+	/* Start server in ns1 */
+	nstoken = open_netns(NS1);
+	if (!ASSERT_OK_PTR(nstoken, "setns ns1"))
+		goto out;
+	srv_fd = start_server(family, SOCK_DGRAM, NULL, SERVER_PORT, 0);
+	close_netns(nstoken);
+	if (!ASSERT_GE(srv_fd, 0, "start_server"))
+		goto out;
+
+	/* Open tx raw socket in ns0 */
+	nstoken = open_netns(NS0);
+	if (!ASSERT_OK_PTR(nstoken, "setns ns0"))
+		goto out;
+	client_tx_fd = client_socket(family, SOCK_RAW, &tx_ops);
+	close_netns(nstoken);
+	if (!ASSERT_GE(client_tx_fd, 0, "client_socket"))
+		goto out;
+
+	/* Open rx socket in ns0 */
+	nstoken = open_netns(NS0);
+	if (!ASSERT_OK_PTR(nstoken, "setns ns0"))
+		goto out;
+	client_rx_fd = client_socket(family, SOCK_DGRAM, &rx_opts);
+	close_netns(nstoken);
+	if (!ASSERT_GE(client_rx_fd, 0, "client_socket"))
+		goto out;
+
+	/* Bind rx socket to a premeditated port */
+	memset(&caddr, 0, sizeof(caddr));
+	nstoken = open_netns(NS0);
+	if (!ASSERT_OK_PTR(nstoken, "setns ns0"))
+		goto out;
+	if (ipv6) {
+		struct sockaddr_in6 *c = (struct sockaddr_in6 *)&caddr;
+
+		c->sin6_family = AF_INET6;
+		inet_pton(AF_INET6, VETH0_ADDR6, &c->sin6_addr);
+		c->sin6_port = htons(CLIENT_PORT);
+		err = bind(client_rx_fd, (struct sockaddr *)c, sizeof(*c));
+	} else {
+		struct sockaddr_in *c = (struct sockaddr_in *)&caddr;
+
+		c->sin_family = AF_INET;
+		inet_pton(AF_INET, VETH0_ADDR, &c->sin_addr);
+		c->sin_port = htons(CLIENT_PORT);
+		err = bind(client_rx_fd, (struct sockaddr *)c, sizeof(*c));
+	}
+	close_netns(nstoken);
+	if (!ASSERT_OK(err, "bind"))
+		goto out;
+
+	/* Send message in fragments */
+	if (ipv6) {
+		if (!ASSERT_OK(send_frags6(client_tx_fd), "send_frags6"))
+			goto out;
+	} else {
+		if (!ASSERT_OK(send_frags(client_tx_fd), "send_frags"))
+			goto out;
+	}
+
+	if (!ASSERT_EQ(skel->bss->shootdowns, 0, "shootdowns"))
+		goto out;
+
+	/* Receive reassembled msg on server and echo back to client */
+	caddr_len = sizeof(caddr);
+	len = recvfrom(srv_fd, buf, sizeof(buf), 0, (struct sockaddr *)&caddr, &caddr_len);
+	if (!ASSERT_GE(len, 0, "server recvfrom"))
+		goto out;
+	len = sendto(srv_fd, buf, len, 0, (struct sockaddr *)&caddr, caddr_len);
+	if (!ASSERT_GE(len, 0, "server sendto"))
+		goto out;
+
+	/* Expect reassembed message to be echoed back */
+	len = recvfrom(client_rx_fd, buf, sizeof(buf), 0, NULL, NULL);
+	if (!ASSERT_EQ(len, sizeof(MAGIC_MESSAGE) - 1, "client short read"))
+		goto out;
+
+out:
+	if (client_rx_fd != -1)
+		close(client_rx_fd);
+	if (client_tx_fd != -1)
+		close(client_tx_fd);
+	if (srv_fd != -1)
+		close(srv_fd);
+	cleanup_topology();
+	ip_check_defrag__destroy(skel);
+}
+
+void test_bpf_ip_check_defrag(void)
+{
+	if (test__start_subtest("v4"))
+		test_bpf_ip_check_defrag_ok(false);
+	if (test__start_subtest("v6"))
+		test_bpf_ip_check_defrag_ok(true);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/iters.c b/tools/testing/selftests/bpf/prog_tests/iters.c
new file mode 100644
index 000000000000..3cea71f9c500
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/iters.c
@@ -0,0 +1,319 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <sys/syscall.h>
+#include <sys/mman.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <malloc.h>
+#include <stdlib.h>
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+
+#include "iters.skel.h"
+#include "iters_state_safety.skel.h"
+#include "iters_looping.skel.h"
+#include "iters_num.skel.h"
+#include "iters_testmod.skel.h"
+#include "iters_testmod_seq.skel.h"
+#include "iters_task_vma.skel.h"
+#include "iters_task.skel.h"
+#include "iters_css_task.skel.h"
+#include "iters_css.skel.h"
+#include "iters_task_failure.skel.h"
+
+static void subtest_num_iters(void)
+{
+	struct iters_num *skel;
+	int err;
+
+	skel = iters_num__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return;
+
+	err = iters_num__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	usleep(1);
+	iters_num__detach(skel);
+
+#define VALIDATE_CASE(case_name)					\
+	ASSERT_EQ(skel->bss->res_##case_name,				\
+		  skel->rodata->exp_##case_name,			\
+		  #case_name)
+
+	VALIDATE_CASE(empty_zero);
+	VALIDATE_CASE(empty_int_min);
+	VALIDATE_CASE(empty_int_max);
+	VALIDATE_CASE(empty_minus_one);
+
+	VALIDATE_CASE(simple_sum);
+	VALIDATE_CASE(neg_sum);
+	VALIDATE_CASE(very_neg_sum);
+	VALIDATE_CASE(neg_pos_sum);
+
+	VALIDATE_CASE(invalid_range);
+	VALIDATE_CASE(max_range);
+	VALIDATE_CASE(e2big_range);
+
+	VALIDATE_CASE(succ_elem_cnt);
+	VALIDATE_CASE(overfetched_elem_cnt);
+	VALIDATE_CASE(fail_elem_cnt);
+
+#undef VALIDATE_CASE
+
+cleanup:
+	iters_num__destroy(skel);
+}
+
+static void subtest_testmod_seq_iters(void)
+{
+	struct iters_testmod_seq *skel;
+	int err;
+
+	if (!env.has_testmod) {
+		test__skip();
+		return;
+	}
+
+	skel = iters_testmod_seq__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return;
+
+	err = iters_testmod_seq__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	usleep(1);
+	iters_testmod_seq__detach(skel);
+
+#define VALIDATE_CASE(case_name)					\
+	ASSERT_EQ(skel->bss->res_##case_name,				\
+		  skel->rodata->exp_##case_name,			\
+		  #case_name)
+
+	VALIDATE_CASE(empty);
+	VALIDATE_CASE(full);
+	VALIDATE_CASE(truncated);
+
+#undef VALIDATE_CASE
+
+cleanup:
+	iters_testmod_seq__destroy(skel);
+}
+
+static void subtest_task_vma_iters(void)
+{
+	unsigned long start, end, bpf_iter_start, bpf_iter_end;
+	struct iters_task_vma *skel;
+	char rest_of_line[1000];
+	unsigned int seen;
+	FILE *f = NULL;
+	int err;
+
+	skel = iters_task_vma__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return;
+
+	skel->bss->target_pid = getpid();
+
+	err = iters_task_vma__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	getpgid(skel->bss->target_pid);
+	iters_task_vma__detach(skel);
+
+	if (!ASSERT_GT(skel->bss->vmas_seen, 0, "vmas_seen_gt_zero"))
+		goto cleanup;
+
+	f = fopen("/proc/self/maps", "r");
+	if (!ASSERT_OK_PTR(f, "proc_maps_fopen"))
+		goto cleanup;
+
+	seen = 0;
+	while (fscanf(f, "%lx-%lx %[^\n]\n", &start, &end, rest_of_line) == 3) {
+		/* [vsyscall] vma isn't _really_ part of task->mm vmas.
+		 * /proc/PID/maps returns it when out of vmas - see get_gate_vma
+		 * calls in fs/proc/task_mmu.c
+		 */
+		if (strstr(rest_of_line, "[vsyscall]"))
+			continue;
+
+		bpf_iter_start = skel->bss->vm_ranges[seen].vm_start;
+		bpf_iter_end = skel->bss->vm_ranges[seen].vm_end;
+
+		ASSERT_EQ(bpf_iter_start, start, "vma->vm_start match");
+		ASSERT_EQ(bpf_iter_end, end, "vma->vm_end match");
+		seen++;
+	}
+
+	if (!ASSERT_EQ(skel->bss->vmas_seen, seen, "vmas_seen_eq"))
+		goto cleanup;
+
+cleanup:
+	if (f)
+		fclose(f);
+	iters_task_vma__destroy(skel);
+}
+
+static pthread_mutex_t do_nothing_mutex;
+
+static void *do_nothing_wait(void *arg)
+{
+	pthread_mutex_lock(&do_nothing_mutex);
+	pthread_mutex_unlock(&do_nothing_mutex);
+
+	pthread_exit(arg);
+}
+
+#define thread_num 2
+
+static void subtest_task_iters(void)
+{
+	struct iters_task *skel = NULL;
+	pthread_t thread_ids[thread_num];
+	void *ret;
+	int err;
+
+	skel = iters_task__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		goto cleanup;
+	skel->bss->target_pid = getpid();
+	err = iters_task__attach(skel);
+	if (!ASSERT_OK(err, "iters_task__attach"))
+		goto cleanup;
+	pthread_mutex_lock(&do_nothing_mutex);
+	for (int i = 0; i < thread_num; i++)
+		ASSERT_OK(pthread_create(&thread_ids[i], NULL, &do_nothing_wait, NULL),
+			"pthread_create");
+
+	syscall(SYS_getpgid);
+	iters_task__detach(skel);
+	ASSERT_EQ(skel->bss->procs_cnt, 1, "procs_cnt");
+	ASSERT_EQ(skel->bss->threads_cnt, thread_num + 2, "threads_cnt");
+	ASSERT_EQ(skel->bss->proc_threads_cnt, thread_num + 2, "proc_threads_cnt");
+	ASSERT_EQ(skel->bss->invalid_cnt, 0, "invalid_cnt");
+	pthread_mutex_unlock(&do_nothing_mutex);
+	for (int i = 0; i < thread_num; i++)
+		ASSERT_OK(pthread_join(thread_ids[i], &ret), "pthread_join");
+cleanup:
+	iters_task__destroy(skel);
+}
+
+extern int stack_mprotect(void);
+
+static void subtest_css_task_iters(void)
+{
+	struct iters_css_task *skel = NULL;
+	int err, cg_fd, cg_id;
+	const char *cgrp_path = "/cg1";
+
+	err = setup_cgroup_environment();
+	if (!ASSERT_OK(err, "setup_cgroup_environment"))
+		goto cleanup;
+	cg_fd = create_and_get_cgroup(cgrp_path);
+	if (!ASSERT_GE(cg_fd, 0, "create_and_get_cgroup"))
+		goto cleanup;
+	cg_id = get_cgroup_id(cgrp_path);
+	err = join_cgroup(cgrp_path);
+	if (!ASSERT_OK(err, "join_cgroup"))
+		goto cleanup;
+
+	skel = iters_css_task__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		goto cleanup;
+
+	skel->bss->target_pid = getpid();
+	skel->bss->cg_id = cg_id;
+	err = iters_css_task__attach(skel);
+	if (!ASSERT_OK(err, "iters_task__attach"))
+		goto cleanup;
+	err = stack_mprotect();
+	if (!ASSERT_EQ(err, -1, "stack_mprotect") ||
+	    !ASSERT_EQ(errno, EPERM, "stack_mprotect"))
+		goto cleanup;
+	iters_css_task__detach(skel);
+	ASSERT_EQ(skel->bss->css_task_cnt, 1, "css_task_cnt");
+
+cleanup:
+	cleanup_cgroup_environment();
+	iters_css_task__destroy(skel);
+}
+
+static void subtest_css_iters(void)
+{
+	struct iters_css *skel = NULL;
+	struct {
+		const char *path;
+		int fd;
+	} cgs[] = {
+		{ "/cg1" },
+		{ "/cg1/cg2" },
+		{ "/cg1/cg2/cg3" },
+		{ "/cg1/cg2/cg3/cg4" },
+	};
+	int err, cg_nr = ARRAY_SIZE(cgs);
+	int i;
+
+	err = setup_cgroup_environment();
+	if (!ASSERT_OK(err, "setup_cgroup_environment"))
+		goto cleanup;
+	for (i = 0; i < cg_nr; i++) {
+		cgs[i].fd = create_and_get_cgroup(cgs[i].path);
+		if (!ASSERT_GE(cgs[i].fd, 0, "create_and_get_cgroup"))
+			goto cleanup;
+	}
+
+	skel = iters_css__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		goto cleanup;
+
+	skel->bss->target_pid = getpid();
+	skel->bss->root_cg_id = get_cgroup_id(cgs[0].path);
+	skel->bss->leaf_cg_id = get_cgroup_id(cgs[cg_nr - 1].path);
+	err = iters_css__attach(skel);
+
+	if (!ASSERT_OK(err, "iters_task__attach"))
+		goto cleanup;
+
+	syscall(SYS_getpgid);
+	ASSERT_EQ(skel->bss->pre_order_cnt, cg_nr, "pre_order_cnt");
+	ASSERT_EQ(skel->bss->first_cg_id, get_cgroup_id(cgs[0].path), "first_cg_id");
+
+	ASSERT_EQ(skel->bss->post_order_cnt, cg_nr, "post_order_cnt");
+	ASSERT_EQ(skel->bss->last_cg_id, get_cgroup_id(cgs[0].path), "last_cg_id");
+	ASSERT_EQ(skel->bss->tree_high, cg_nr - 1, "tree_high");
+	iters_css__detach(skel);
+cleanup:
+	cleanup_cgroup_environment();
+	iters_css__destroy(skel);
+}
+
+void test_iters(void)
+{
+	RUN_TESTS(iters_state_safety);
+	RUN_TESTS(iters_looping);
+	RUN_TESTS(iters);
+	RUN_TESTS(iters_css_task);
+
+	if (env.has_testmod) {
+		RUN_TESTS(iters_testmod);
+		RUN_TESTS(iters_testmod_seq);
+	}
+
+	if (test__start_subtest("num"))
+		subtest_num_iters();
+	if (test__start_subtest("testmod_seq"))
+		subtest_testmod_seq_iters();
+	if (test__start_subtest("task_vma"))
+		subtest_task_vma_iters();
+	if (test__start_subtest("task"))
+		subtest_task_iters();
+	if (test__start_subtest("css_task"))
+		subtest_css_task_iters();
+	if (test__start_subtest("css"))
+		subtest_css_iters();
+	RUN_TESTS(iters_task_failure);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/jeq_infer_not_null.c b/tools/testing/selftests/bpf/prog_tests/jeq_infer_not_null.c
new file mode 100644
index 000000000000..3add34df5767
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/jeq_infer_not_null.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "jeq_infer_not_null_fail.skel.h"
+
+void test_jeq_infer_not_null(void)
+{
+	RUN_TESTS(jeq_infer_not_null_fail);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/jit_probe_mem.c b/tools/testing/selftests/bpf/prog_tests/jit_probe_mem.c
new file mode 100644
index 000000000000..5639428607e6
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/jit_probe_mem.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <network_helpers.h>
+
+#include "jit_probe_mem.skel.h"
+
+void test_jit_probe_mem(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = 1,
+	);
+	struct jit_probe_mem *skel;
+	int ret;
+
+	skel = jit_probe_mem__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "jit_probe_mem__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_jit_probe_mem), &opts);
+	ASSERT_OK(ret, "jit_probe_mem ret");
+	ASSERT_OK(opts.retval, "jit_probe_mem opts.retval");
+	ASSERT_EQ(skel->data->total_sum, 192, "jit_probe_mem total_sum");
+
+	jit_probe_mem__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/kernel_flag.c b/tools/testing/selftests/bpf/prog_tests/kernel_flag.c
new file mode 100644
index 000000000000..97b00c7efe94
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/kernel_flag.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Microsoft */
+#include <test_progs.h>
+#include "kfunc_call_test.skel.h"
+#include "kfunc_call_test.lskel.h"
+#include "test_kernel_flag.skel.h"
+
+void test_kernel_flag(void)
+{
+	struct test_kernel_flag *lsm_skel;
+	struct kfunc_call_test *skel = NULL;
+	struct kfunc_call_test_lskel *lskel = NULL;
+	int ret;
+
+	lsm_skel = test_kernel_flag__open_and_load();
+	if (!ASSERT_OK_PTR(lsm_skel, "lsm_skel"))
+		return;
+
+	lsm_skel->bss->monitored_tid = sys_gettid();
+
+	ret = test_kernel_flag__attach(lsm_skel);
+	if (!ASSERT_OK(ret, "test_kernel_flag__attach"))
+		goto close_prog;
+
+	/* Test with skel. This should pass the gatekeeper */
+	skel = kfunc_call_test__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel"))
+		goto close_prog;
+
+	/* Test with lskel. This should fail due to blocking kernel-based bpf() invocations */
+	lskel = kfunc_call_test_lskel__open_and_load();
+	if (!ASSERT_ERR_PTR(lskel, "lskel"))
+		goto close_prog;
+
+close_prog:
+	if (skel)
+		kfunc_call_test__destroy(skel);
+	if (lskel)
+		kfunc_call_test_lskel__destroy(lskel);
+
+	lsm_skel->bss->monitored_tid = 0;
+	test_kernel_flag__destroy(lsm_skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
index 73579370bfbd..34f8822fd221 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
 #include <test_progs.h>
 #include <network_helpers.h>
 #include "kfree_skb.skel.h"
@@ -36,7 +37,7 @@ static void on_sample(void *ctx, int cpu, void *data, __u32 size)
 		  "cb32_0 %x != %x\n",
 		  meta->cb32_0, cb.cb32[0]))
 		return;
-	if (CHECK(pkt_v6->eth.h_proto != 0xdd86, "check_eth",
+	if (CHECK(pkt_v6->eth.h_proto != htons(ETH_P_IPV6), "check_eth",
 		  "h_proto %x\n", pkt_v6->eth.h_proto))
 		return;
 	if (CHECK(pkt_v6->iph.nexthdr != 6, "check_ip",
diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
index 5af1ee8f0e6e..f79c8e53cb3e 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
@@ -68,14 +68,18 @@ static struct kfunc_test_params kfunc_tests[] = {
 	TC_FAIL(kfunc_call_test_get_mem_fail_oob, 0, "min value is outside of the allowed memory range"),
 	TC_FAIL(kfunc_call_test_get_mem_fail_not_const, 0, "is not a const"),
 	TC_FAIL(kfunc_call_test_mem_acquire_fail, 0, "acquire kernel function does not return PTR_TO_BTF_ID"),
+	TC_FAIL(kfunc_call_test_pointer_arg_type_mismatch, 0, "arg#0 expected pointer to ctx, but got scalar"),
 
 	/* success cases */
 	TC_TEST(kfunc_call_test1, 12),
 	TC_TEST(kfunc_call_test2, 3),
+	TC_TEST(kfunc_call_test4, -1234),
 	TC_TEST(kfunc_call_test_ref_btf_id, 0),
 	TC_TEST(kfunc_call_test_get_mem, 42),
 	SYSCALL_TEST(kfunc_syscall_test, 0),
 	SYSCALL_NULL_CTX_TEST(kfunc_syscall_test_null, 0),
+	TC_TEST(kfunc_call_test_static_unused_arg, 0),
+	TC_TEST(kfunc_call_ctx, 0),
 };
 
 struct syscall_test_args {
@@ -171,8 +175,8 @@ static void verify_fail(struct kfunc_test_params *param)
 	case tc_test:
 		topts.data_in = &pkt_v4;
 		topts.data_size_in = sizeof(pkt_v4);
-		break;
 		topts.repeat = 1;
+		break;
 	}
 
 	skel = kfunc_call_fail__open_opts(&opts);
diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c b/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c
index a9229260a6ce..8cd298b78e44 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfunc_dynptr_param.c
@@ -10,17 +10,11 @@
 #include <test_progs.h>
 #include "test_kfunc_dynptr_param.skel.h"
 
-static size_t log_buf_sz = 1048576; /* 1 MB */
-static char obj_log_buf[1048576];
-
 static struct {
 	const char *prog_name;
-	const char *expected_verifier_err_msg;
 	int expected_runtime_err;
 } kfunc_dynptr_tests[] = {
-	{"not_valid_dynptr", "Expected an initialized dynptr as arg #1", 0},
-	{"not_ptr_to_stack", "arg#0 expected pointer to stack or dynptr_ptr", 0},
-	{"dynptr_data_null", NULL, -EBADMSG},
+	{"dynptr_data_null", -EBADMSG},
 };
 
 static bool kfunc_not_supported;
@@ -38,29 +32,15 @@ static int libbpf_print_cb(enum libbpf_print_level level, const char *fmt,
 	return 0;
 }
 
-static void verify_fail(const char *prog_name, const char *expected_err_msg)
+static bool has_pkcs7_kfunc_support(void)
 {
 	struct test_kfunc_dynptr_param *skel;
-	LIBBPF_OPTS(bpf_object_open_opts, opts);
 	libbpf_print_fn_t old_print_cb;
-	struct bpf_program *prog;
 	int err;
 
-	opts.kernel_log_buf = obj_log_buf;
-	opts.kernel_log_size = log_buf_sz;
-	opts.kernel_log_level = 1;
-
-	skel = test_kfunc_dynptr_param__open_opts(&opts);
-	if (!ASSERT_OK_PTR(skel, "test_kfunc_dynptr_param__open_opts"))
-		goto cleanup;
-
-	prog = bpf_object__find_program_by_name(skel->obj, prog_name);
-	if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
-		goto cleanup;
-
-	bpf_program__set_autoload(prog, true);
-
-	bpf_map__set_max_entries(skel->maps.ringbuf, getpagesize());
+	skel = test_kfunc_dynptr_param__open();
+	if (!ASSERT_OK_PTR(skel, "test_kfunc_dynptr_param__open"))
+		return false;
 
 	kfunc_not_supported = false;
 
@@ -72,26 +52,18 @@ static void verify_fail(const char *prog_name, const char *expected_err_msg)
 		fprintf(stderr,
 		  "%s:SKIP:bpf_verify_pkcs7_signature() kfunc not supported\n",
 		  __func__);
-		test__skip();
-		goto cleanup;
-	}
-
-	if (!ASSERT_ERR(err, "unexpected load success"))
-		goto cleanup;
-
-	if (!ASSERT_OK_PTR(strstr(obj_log_buf, expected_err_msg), "expected_err_msg")) {
-		fprintf(stderr, "Expected err_msg: %s\n", expected_err_msg);
-		fprintf(stderr, "Verifier output: %s\n", obj_log_buf);
+		test_kfunc_dynptr_param__destroy(skel);
+		return false;
 	}
 
-cleanup:
 	test_kfunc_dynptr_param__destroy(skel);
+
+	return true;
 }
 
 static void verify_success(const char *prog_name, int expected_runtime_err)
 {
 	struct test_kfunc_dynptr_param *skel;
-	libbpf_print_fn_t old_print_cb;
 	struct bpf_program *prog;
 	struct bpf_link *link;
 	__u32 next_id;
@@ -103,21 +75,7 @@ static void verify_success(const char *prog_name, int expected_runtime_err)
 
 	skel->bss->pid = getpid();
 
-	bpf_map__set_max_entries(skel->maps.ringbuf, getpagesize());
-
-	kfunc_not_supported = false;
-
-	old_print_cb = libbpf_set_print(libbpf_print_cb);
 	err = test_kfunc_dynptr_param__load(skel);
-	libbpf_set_print(old_print_cb);
-
-	if (err < 0 && kfunc_not_supported) {
-		fprintf(stderr,
-		  "%s:SKIP:bpf_verify_pkcs7_signature() kfunc not supported\n",
-		  __func__);
-		test__skip();
-		goto cleanup;
-	}
 
 	if (!ASSERT_OK(err, "test_kfunc_dynptr_param__load"))
 		goto cleanup;
@@ -147,15 +105,15 @@ void test_kfunc_dynptr_param(void)
 {
 	int i;
 
+	if (!has_pkcs7_kfunc_support())
+		return;
+
 	for (i = 0; i < ARRAY_SIZE(kfunc_dynptr_tests); i++) {
 		if (!test__start_subtest(kfunc_dynptr_tests[i].prog_name))
 			continue;
 
-		if (kfunc_dynptr_tests[i].expected_verifier_err_msg)
-			verify_fail(kfunc_dynptr_tests[i].prog_name,
-			  kfunc_dynptr_tests[i].expected_verifier_err_msg);
-		else
-			verify_success(kfunc_dynptr_tests[i].prog_name,
-				kfunc_dynptr_tests[i].expected_runtime_err);
+		verify_success(kfunc_dynptr_tests[i].prog_name,
+			kfunc_dynptr_tests[i].expected_runtime_err);
 	}
+	RUN_TESTS(test_kfunc_dynptr_param);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_module_order.c b/tools/testing/selftests/bpf/prog_tests/kfunc_module_order.c
new file mode 100644
index 000000000000..48c0560d398e
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/kfunc_module_order.c
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <testing_helpers.h>
+
+#include "kfunc_module_order.skel.h"
+
+static int test_run_prog(const struct bpf_program *prog,
+			 struct bpf_test_run_opts *opts)
+{
+	int err;
+
+	err = bpf_prog_test_run_opts(bpf_program__fd(prog), opts);
+	if (!ASSERT_OK(err, "bpf_prog_test_run_opts"))
+		return err;
+
+	if (!ASSERT_EQ((int)opts->retval, 0, bpf_program__name(prog)))
+		return -EINVAL;
+
+	return 0;
+}
+
+void test_kfunc_module_order(void)
+{
+	struct kfunc_module_order *skel;
+	char pkt_data[64] = {};
+	int err = 0;
+
+	DECLARE_LIBBPF_OPTS(bpf_test_run_opts, test_opts, .data_in = pkt_data,
+			    .data_size_in = sizeof(pkt_data));
+
+	err = load_module("bpf_test_modorder_x.ko",
+			  env_verbosity > VERBOSE_NONE);
+	if (!ASSERT_OK(err, "load bpf_test_modorder_x.ko"))
+		return;
+
+	err = load_module("bpf_test_modorder_y.ko",
+			  env_verbosity > VERBOSE_NONE);
+	if (!ASSERT_OK(err, "load bpf_test_modorder_y.ko"))
+		goto exit_modx;
+
+	skel = kfunc_module_order__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "kfunc_module_order__open_and_load()")) {
+		err = -EINVAL;
+		goto exit_mods;
+	}
+
+	test_run_prog(skel->progs.call_kfunc_xy, &test_opts);
+	test_run_prog(skel->progs.call_kfunc_yx, &test_opts);
+
+	kfunc_module_order__destroy(skel);
+exit_mods:
+	unload_module("bpf_test_modorder_y", env_verbosity > VERBOSE_NONE);
+exit_modx:
+	unload_module("bpf_test_modorder_x", env_verbosity > VERBOSE_NONE);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_param_nullable.c b/tools/testing/selftests/bpf/prog_tests/kfunc_param_nullable.c
new file mode 100644
index 000000000000..c8f4dcaac7c7
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/kfunc_param_nullable.c
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Copyright (c) 2024 Meta Platforms, Inc */
+
+#include <test_progs.h>
+#include "test_kfunc_param_nullable.skel.h"
+
+void test_kfunc_param_nullable(void)
+{
+	RUN_TESTS(test_kfunc_param_nullable);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c
new file mode 100644
index 000000000000..6e35e13c2022
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c
@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Google */
+
+#include <test_progs.h>
+#include <bpf/libbpf.h>
+#include <bpf/btf.h>
+#include "kmem_cache_iter.skel.h"
+
+#define SLAB_NAME_MAX  32
+
+struct kmem_cache_result {
+	char name[SLAB_NAME_MAX];
+	long obj_size;
+};
+
+static void subtest_kmem_cache_iter_check_task_struct(struct kmem_cache_iter *skel)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		.flags = 0,  /* Run it with the current task */
+	);
+	int prog_fd = bpf_program__fd(skel->progs.check_task_struct);
+
+	/* Get task_struct and check it if's from a slab cache */
+	ASSERT_OK(bpf_prog_test_run_opts(prog_fd, &opts), "prog_test_run");
+
+	/* The BPF program should set 'found' variable */
+	ASSERT_EQ(skel->bss->task_struct_found, 1, "task_struct_found");
+}
+
+static void subtest_kmem_cache_iter_check_slabinfo(struct kmem_cache_iter *skel)
+{
+	FILE *fp;
+	int map_fd;
+	char name[SLAB_NAME_MAX];
+	unsigned long objsize;
+	char rest_of_line[1000];
+	struct kmem_cache_result r;
+	int seen = 0;
+
+	fp = fopen("/proc/slabinfo", "r");
+	if (fp == NULL) {
+		/* CONFIG_SLUB_DEBUG is not enabled */
+		return;
+	}
+
+	map_fd = bpf_map__fd(skel->maps.slab_result);
+
+	/* Ignore first two lines for header */
+	fscanf(fp, "slabinfo - version: %*d.%*d\n");
+	fscanf(fp, "# %*s %*s %*s %*s %*s %*s : %[^\n]\n", rest_of_line);
+
+	/* Compare name and objsize only - others can be changes frequently */
+	while (fscanf(fp, "%s %*u %*u %lu %*u %*u : %[^\n]\n",
+		      name, &objsize, rest_of_line) == 3) {
+		int ret = bpf_map_lookup_elem(map_fd, &seen, &r);
+
+		if (!ASSERT_OK(ret, "kmem_cache_lookup"))
+			break;
+
+		ASSERT_STRNEQ(r.name, name, sizeof(r.name) - 1,
+			      "kmem_cache_name");
+		ASSERT_EQ(r.obj_size, objsize, "kmem_cache_objsize");
+
+		seen++;
+	}
+
+	ASSERT_EQ(skel->bss->kmem_cache_seen, seen, "kmem_cache_seen_eq");
+
+	fclose(fp);
+}
+
+static void subtest_kmem_cache_iter_open_coded(struct kmem_cache_iter *skel)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	int err, fd;
+
+	/* No need to attach it, just run it directly */
+	fd = bpf_program__fd(skel->progs.open_coded_iter);
+
+	err = bpf_prog_test_run_opts(fd, &topts);
+	if (!ASSERT_OK(err, "test_run_opts err"))
+		return;
+	if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+		return;
+
+	/* It should be same as we've seen from the explicit iterator */
+	ASSERT_EQ(skel->bss->open_coded_seen, skel->bss->kmem_cache_seen, "open_code_seen_eq");
+}
+
+void test_kmem_cache_iter(void)
+{
+	struct kmem_cache_iter *skel = NULL;
+	char buf[256];
+	int iter_fd;
+
+	skel = kmem_cache_iter__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "kmem_cache_iter__open_and_load"))
+		return;
+
+	if (!ASSERT_OK(kmem_cache_iter__attach(skel), "skel_attach"))
+		goto destroy;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(skel->links.slab_info_collector));
+	if (!ASSERT_GE(iter_fd, 0, "iter_create"))
+		goto destroy;
+
+	memset(buf, 0, sizeof(buf));
+	while (read(iter_fd, buf, sizeof(buf)) > 0) {
+		/* Read out all contents */
+		printf("%s", buf);
+	}
+
+	/* Next reads should return 0 */
+	ASSERT_EQ(read(iter_fd, buf, sizeof(buf)), 0, "read");
+
+	if (test__start_subtest("check_task_struct"))
+		subtest_kmem_cache_iter_check_task_struct(skel);
+	if (test__start_subtest("check_slabinfo"))
+		subtest_kmem_cache_iter_check_slabinfo(skel);
+	if (test__start_subtest("open_coded_iter"))
+		subtest_kmem_cache_iter_open_coded(skel);
+
+	close(iter_fd);
+
+destroy:
+	kmem_cache_iter__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
index c6f37e825f11..6cfaa978bc9a 100644
--- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c
@@ -3,6 +3,11 @@
 #include "kprobe_multi.skel.h"
 #include "trace_helpers.h"
 #include "kprobe_multi_empty.skel.h"
+#include "kprobe_multi_override.skel.h"
+#include "kprobe_multi_session.skel.h"
+#include "kprobe_multi_session_cookie.skel.h"
+#include "kprobe_multi_verifier.skel.h"
+#include "kprobe_write_ctx.skel.h"
 #include "bpf/libbpf_internal.h"
 #include "bpf/hashmap.h"
 
@@ -221,6 +226,7 @@ static void test_attach_api_fails(void)
 		"bpf_fentry_test2",
 	};
 	__u64 cookies[2];
+	int saved_error;
 
 	addrs[0] = ksym_get_addr("bpf_fentry_test1");
 	addrs[1] = ksym_get_addr("bpf_fentry_test2");
@@ -237,10 +243,11 @@ static void test_attach_api_fails(void)
 	/* fail_1 - pattern and opts NULL */
 	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
 						     NULL, NULL);
+	saved_error = -errno;
 	if (!ASSERT_ERR_PTR(link, "fail_1"))
 		goto cleanup;
 
-	if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_1_error"))
+	if (!ASSERT_EQ(saved_error, -EINVAL, "fail_1_error"))
 		goto cleanup;
 
 	/* fail_2 - both addrs and syms set */
@@ -251,10 +258,11 @@ static void test_attach_api_fails(void)
 
 	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
 						     NULL, &opts);
+	saved_error = -errno;
 	if (!ASSERT_ERR_PTR(link, "fail_2"))
 		goto cleanup;
 
-	if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_2_error"))
+	if (!ASSERT_EQ(saved_error, -EINVAL, "fail_2_error"))
 		goto cleanup;
 
 	/* fail_3 - pattern and addrs set */
@@ -265,10 +273,11 @@ static void test_attach_api_fails(void)
 
 	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
 						     "ksys_*", &opts);
+	saved_error = -errno;
 	if (!ASSERT_ERR_PTR(link, "fail_3"))
 		goto cleanup;
 
-	if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_3_error"))
+	if (!ASSERT_EQ(saved_error, -EINVAL, "fail_3_error"))
 		goto cleanup;
 
 	/* fail_4 - pattern and cnt set */
@@ -279,10 +288,11 @@ static void test_attach_api_fails(void)
 
 	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
 						     "ksys_*", &opts);
+	saved_error = -errno;
 	if (!ASSERT_ERR_PTR(link, "fail_4"))
 		goto cleanup;
 
-	if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_4_error"))
+	if (!ASSERT_EQ(saved_error, -EINVAL, "fail_4_error"))
 		goto cleanup;
 
 	/* fail_5 - pattern and cookies */
@@ -293,10 +303,26 @@ static void test_attach_api_fails(void)
 
 	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
 						     "ksys_*", &opts);
+	saved_error = -errno;
 	if (!ASSERT_ERR_PTR(link, "fail_5"))
 		goto cleanup;
 
-	if (!ASSERT_EQ(libbpf_get_error(link), -EINVAL, "fail_5_error"))
+	if (!ASSERT_EQ(saved_error, -EINVAL, "fail_5_error"))
+		goto cleanup;
+
+	/* fail_6 - abnormal cnt */
+	opts.addrs = (const unsigned long *) addrs;
+	opts.syms = NULL;
+	opts.cnt = INT_MAX;
+	opts.cookies = NULL;
+
+	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
+						     NULL, &opts);
+	saved_error = -errno;
+	if (!ASSERT_ERR_PTR(link, "fail_6"))
+		goto cleanup;
+
+	if (!ASSERT_EQ(saved_error, -E2BIG, "fail_6_error"))
 		goto cleanup;
 
 cleanup:
@@ -304,134 +330,113 @@ cleanup:
 	kprobe_multi__destroy(skel);
 }
 
-static inline __u64 get_time_ns(void)
+static void test_session_skel_api(void)
 {
-	struct timespec t;
+	struct kprobe_multi_session *skel = NULL;
+	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	struct bpf_link *link = NULL;
+	int i, err, prog_fd;
 
-	clock_gettime(CLOCK_MONOTONIC, &t);
-	return (__u64) t.tv_sec * 1000000000 + t.tv_nsec;
-}
+	skel = kprobe_multi_session__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "kprobe_multi_session__open_and_load"))
+		return;
 
-static size_t symbol_hash(long key, void *ctx __maybe_unused)
-{
-	return str_hash((const char *) key);
-}
+	skel->bss->pid = getpid();
 
-static bool symbol_equal(long key1, long key2, void *ctx __maybe_unused)
-{
-	return strcmp((const char *) key1, (const char *) key2) == 0;
+	err = kprobe_multi_session__attach(skel);
+	if (!ASSERT_OK(err, " kprobe_multi_session__attach"))
+		goto cleanup;
+
+	prog_fd = bpf_program__fd(skel->progs.trigger);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(topts.retval, 0, "test_run");
+
+	/* bpf_fentry_test1-4 trigger return probe, result is 2 */
+	for (i = 0; i < 4; i++)
+		ASSERT_EQ(skel->bss->kprobe_session_result[i], 2, "kprobe_session_result");
+
+	/* bpf_fentry_test5-8 trigger only entry probe, result is 1 */
+	for (i = 4; i < 8; i++)
+		ASSERT_EQ(skel->bss->kprobe_session_result[i], 1, "kprobe_session_result");
+
+cleanup:
+	bpf_link__destroy(link);
+	kprobe_multi_session__destroy(skel);
 }
 
-static int get_syms(char ***symsp, size_t *cntp)
+static void test_session_cookie_skel_api(void)
 {
-	size_t cap = 0, cnt = 0, i;
-	char *name = NULL, **syms = NULL;
-	struct hashmap *map;
-	char buf[256];
-	FILE *f;
-	int err = 0;
-
-	/*
-	 * The available_filter_functions contains many duplicates,
-	 * but other than that all symbols are usable in kprobe multi
-	 * interface.
-	 * Filtering out duplicates by using hashmap__add, which won't
-	 * add existing entry.
-	 */
-	f = fopen("/sys/kernel/debug/tracing/available_filter_functions", "r");
-	if (!f)
-		return -EINVAL;
-
-	map = hashmap__new(symbol_hash, symbol_equal, NULL);
-	if (IS_ERR(map)) {
-		err = libbpf_get_error(map);
-		goto error;
-	}
+	struct kprobe_multi_session_cookie *skel = NULL;
+	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	struct bpf_link *link = NULL;
+	int err, prog_fd;
 
-	while (fgets(buf, sizeof(buf), f)) {
-		/* skip modules */
-		if (strchr(buf, '['))
-			continue;
-
-		free(name);
-		if (sscanf(buf, "%ms$*[^\n]\n", &name) != 1)
-			continue;
-		/*
-		 * We attach to almost all kernel functions and some of them
-		 * will cause 'suspicious RCU usage' when fprobe is attached
-		 * to them. Filter out the current culprits - arch_cpu_idle
-		 * default_idle and rcu_* functions.
-		 */
-		if (!strcmp(name, "arch_cpu_idle"))
-			continue;
-		if (!strcmp(name, "default_idle"))
-			continue;
-		if (!strncmp(name, "rcu_", 4))
-			continue;
-		if (!strcmp(name, "bpf_dispatcher_xdp_func"))
-			continue;
-		if (!strncmp(name, "__ftrace_invalid_address__",
-			     sizeof("__ftrace_invalid_address__") - 1))
-			continue;
-
-		err = hashmap__add(map, name, 0);
-		if (err == -EEXIST)
-			continue;
-		if (err)
-			goto error;
-
-		err = libbpf_ensure_mem((void **) &syms, &cap,
-					sizeof(*syms), cnt + 1);
-		if (err)
-			goto error;
-
-		syms[cnt++] = name;
-		name = NULL;
-	}
+	skel = kprobe_multi_session_cookie__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "fentry_raw_skel_load"))
+		return;
 
-	*symsp = syms;
-	*cntp = cnt;
+	skel->bss->pid = getpid();
 
-error:
-	free(name);
-	fclose(f);
-	hashmap__free(map);
-	if (err) {
-		for (i = 0; i < cnt; i++)
-			free(syms[i]);
-		free(syms);
-	}
-	return err;
+	err = kprobe_multi_session_cookie__attach(skel);
+	if (!ASSERT_OK(err, " kprobe_multi_wrapper__attach"))
+		goto cleanup;
+
+	prog_fd = bpf_program__fd(skel->progs.trigger);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(topts.retval, 0, "test_run");
+
+	ASSERT_EQ(skel->bss->test_kprobe_1_result, 1, "test_kprobe_1_result");
+	ASSERT_EQ(skel->bss->test_kprobe_2_result, 2, "test_kprobe_2_result");
+	ASSERT_EQ(skel->bss->test_kprobe_3_result, 3, "test_kprobe_3_result");
+
+cleanup:
+	bpf_link__destroy(link);
+	kprobe_multi_session_cookie__destroy(skel);
 }
 
-void serial_test_kprobe_multi_bench_attach(void)
+static void test_unique_match(void)
 {
 	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
-	struct kprobe_multi_empty *skel = NULL;
-	long attach_start_ns, attach_end_ns;
-	long detach_start_ns, detach_end_ns;
-	double attach_delta, detach_delta;
+	struct kprobe_multi *skel = NULL;
 	struct bpf_link *link = NULL;
-	char **syms = NULL;
-	size_t cnt = 0, i;
 
-	if (!ASSERT_OK(get_syms(&syms, &cnt), "get_syms"))
+	skel = kprobe_multi__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "kprobe_multi__open_and_load"))
 		return;
 
-	skel = kprobe_multi_empty__open_and_load();
-	if (!ASSERT_OK_PTR(skel, "kprobe_multi_empty__open_and_load"))
-		goto cleanup;
+	opts.unique_match = true;
+	skel->bss->pid = getpid();
+	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
+						     "bpf_fentry_test*", &opts);
+	if (!ASSERT_ERR_PTR(link, "bpf_program__attach_kprobe_multi_opts"))
+		bpf_link__destroy(link);
 
-	opts.syms = (const char **) syms;
-	opts.cnt = cnt;
+	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual,
+						     "bpf_fentry_test8*", &opts);
+	if (ASSERT_OK_PTR(link, "bpf_program__attach_kprobe_multi_opts"))
+		bpf_link__destroy(link);
+
+	kprobe_multi__destroy(skel);
+}
+
+static void do_bench_test(struct kprobe_multi_empty *skel, struct bpf_kprobe_multi_opts *opts)
+{
+	long attach_start_ns, attach_end_ns;
+	long detach_start_ns, detach_end_ns;
+	double attach_delta, detach_delta;
+	struct bpf_link *link = NULL;
 
 	attach_start_ns = get_time_ns();
 	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_empty,
-						     NULL, &opts);
+						     NULL, opts);
 	attach_end_ns = get_time_ns();
 
 	if (!ASSERT_OK_PTR(link, "bpf_program__attach_kprobe_multi_opts"))
-		goto cleanup;
+		return;
 
 	detach_start_ns = get_time_ns();
 	bpf_link__destroy(link);
@@ -440,17 +445,135 @@ void serial_test_kprobe_multi_bench_attach(void)
 	attach_delta = (attach_end_ns - attach_start_ns) / 1000000000.0;
 	detach_delta = (detach_end_ns - detach_start_ns) / 1000000000.0;
 
-	printf("%s: found %lu functions\n", __func__, cnt);
+	printf("%s: found %lu functions\n", __func__, opts->cnt);
 	printf("%s: attached in %7.3lfs\n", __func__, attach_delta);
 	printf("%s: detached in %7.3lfs\n", __func__, detach_delta);
+}
+
+static void test_kprobe_multi_bench_attach(bool kernel)
+{
+	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
+	struct kprobe_multi_empty *skel = NULL;
+	char **syms = NULL;
+	size_t cnt = 0;
+
+	if (!ASSERT_OK(bpf_get_ksyms(&syms, &cnt, kernel), "bpf_get_ksyms"))
+		return;
+
+	skel = kprobe_multi_empty__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "kprobe_multi_empty__open_and_load"))
+		goto cleanup;
+
+	opts.syms = (const char **) syms;
+	opts.cnt = cnt;
+
+	do_bench_test(skel, &opts);
 
 cleanup:
 	kprobe_multi_empty__destroy(skel);
-	if (syms) {
-		for (i = 0; i < cnt; i++)
-			free(syms[i]);
+	if (syms)
 		free(syms);
+}
+
+static void test_kprobe_multi_bench_attach_addr(bool kernel)
+{
+	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
+	struct kprobe_multi_empty *skel = NULL;
+	unsigned long *addrs = NULL;
+	size_t cnt = 0;
+	int err;
+
+	err = bpf_get_addrs(&addrs, &cnt, kernel);
+	if (err == -ENOENT) {
+		test__skip();
+		return;
+	}
+
+	if (!ASSERT_OK(err, "bpf_get_addrs"))
+		return;
+
+	skel = kprobe_multi_empty__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "kprobe_multi_empty__open_and_load"))
+		goto cleanup;
+
+	opts.addrs = addrs;
+	opts.cnt = cnt;
+
+	do_bench_test(skel, &opts);
+
+cleanup:
+	kprobe_multi_empty__destroy(skel);
+	free(addrs);
+}
+
+static void test_attach_override(void)
+{
+	struct kprobe_multi_override *skel = NULL;
+	struct bpf_link *link = NULL;
+
+	skel = kprobe_multi_override__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "kprobe_multi_empty__open_and_load"))
+		goto cleanup;
+
+	/* The test_override calls bpf_override_return so it should fail
+	 * to attach to bpf_fentry_test1 function, which is not on error
+	 * injection list.
+	 */
+	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_override,
+						     "bpf_fentry_test1", NULL);
+	if (!ASSERT_ERR_PTR(link, "override_attached_bpf_fentry_test1")) {
+		bpf_link__destroy(link);
+		goto cleanup;
 	}
+
+	/* The should_fail_bio function is on error injection list,
+	 * attach should succeed.
+	 */
+	link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_override,
+						     "should_fail_bio", NULL);
+	if (!ASSERT_OK_PTR(link, "override_attached_should_fail_bio"))
+		goto cleanup;
+
+	bpf_link__destroy(link);
+
+cleanup:
+	kprobe_multi_override__destroy(skel);
+}
+
+#ifdef __x86_64__
+static void test_attach_write_ctx(void)
+{
+	struct kprobe_write_ctx *skel = NULL;
+	struct bpf_link *link = NULL;
+
+	skel = kprobe_write_ctx__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "kprobe_write_ctx__open_and_load"))
+		return;
+
+	link = bpf_program__attach_kprobe_opts(skel->progs.kprobe_multi_write_ctx,
+						     "bpf_fentry_test1", NULL);
+	if (!ASSERT_ERR_PTR(link, "bpf_program__attach_kprobe_opts"))
+		bpf_link__destroy(link);
+
+	kprobe_write_ctx__destroy(skel);
+}
+#else
+static void test_attach_write_ctx(void)
+{
+	test__skip();
+}
+#endif
+
+void serial_test_kprobe_multi_bench_attach(void)
+{
+	if (test__start_subtest("kernel"))
+		test_kprobe_multi_bench_attach(true);
+	if (test__start_subtest("modules"))
+		test_kprobe_multi_bench_attach(false);
+	if (test__start_subtest("kernel"))
+		test_kprobe_multi_bench_attach_addr(true);
+	if (test__start_subtest("modules"))
+		test_kprobe_multi_bench_attach_addr(false);
 }
 
 void test_kprobe_multi_test(void)
@@ -472,4 +595,15 @@ void test_kprobe_multi_test(void)
 		test_attach_api_syms();
 	if (test__start_subtest("attach_api_fails"))
 		test_attach_api_fails();
+	if (test__start_subtest("attach_override"))
+		test_attach_override();
+	if (test__start_subtest("session"))
+		test_session_skel_api();
+	if (test__start_subtest("session_cookie"))
+		test_session_cookie_skel_api();
+	if (test__start_subtest("unique_match"))
+		test_unique_match();
+	if (test__start_subtest("attach_write_ctx"))
+		test_attach_write_ctx();
+	RUN_TESTS(kprobe_multi_verifier);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_testmod_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_testmod_test.c
index 1fbe7e4ac00a..9d03528f05db 100644
--- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_testmod_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_testmod_test.c
@@ -4,6 +4,8 @@
 #include "trace_helpers.h"
 #include "bpf/libbpf_internal.h"
 
+static struct ksyms *ksyms;
+
 static void kprobe_multi_testmod_check(struct kprobe_multi *skel)
 {
 	ASSERT_EQ(skel->bss->kprobe_testmod_test1_result, 1, "kprobe_test1_result");
@@ -50,12 +52,12 @@ static void test_testmod_attach_api_addrs(void)
 	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
 	unsigned long long addrs[3];
 
-	addrs[0] = ksym_get_addr("bpf_testmod_fentry_test1");
-	ASSERT_NEQ(addrs[0], 0, "ksym_get_addr");
-	addrs[1] = ksym_get_addr("bpf_testmod_fentry_test2");
-	ASSERT_NEQ(addrs[1], 0, "ksym_get_addr");
-	addrs[2] = ksym_get_addr("bpf_testmod_fentry_test3");
-	ASSERT_NEQ(addrs[2], 0, "ksym_get_addr");
+	addrs[0] = ksym_get_addr_local(ksyms, "bpf_testmod_fentry_test1");
+	ASSERT_NEQ(addrs[0], 0, "ksym_get_addr_local");
+	addrs[1] = ksym_get_addr_local(ksyms, "bpf_testmod_fentry_test2");
+	ASSERT_NEQ(addrs[1], 0, "ksym_get_addr_local");
+	addrs[2] = ksym_get_addr_local(ksyms, "bpf_testmod_fentry_test3");
+	ASSERT_NEQ(addrs[2], 0, "ksym_get_addr_local");
 
 	opts.addrs = (const unsigned long *) addrs;
 	opts.cnt = ARRAY_SIZE(addrs);
@@ -79,11 +81,15 @@ static void test_testmod_attach_api_syms(void)
 
 void serial_test_kprobe_multi_testmod_test(void)
 {
-	if (!ASSERT_OK(load_kallsyms_refresh(), "load_kallsyms_refresh"))
+	ksyms = load_kallsyms_local();
+	if (!ASSERT_OK_PTR(ksyms, "load_kallsyms_local"))
 		return;
 
 	if (test__start_subtest("testmod_attach_api_syms"))
 		test_testmod_attach_api_syms();
+
 	if (test__start_subtest("testmod_attach_api_addrs"))
 		test_testmod_attach_api_addrs();
+
+	free_kallsyms_local(ksyms);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/kptr_xchg_inline.c b/tools/testing/selftests/bpf/prog_tests/kptr_xchg_inline.c
new file mode 100644
index 000000000000..7def158da9eb
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/kptr_xchg_inline.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <test_progs.h>
+
+#include "linux/filter.h"
+#include "kptr_xchg_inline.skel.h"
+
+void test_kptr_xchg_inline(void)
+{
+	struct kptr_xchg_inline *skel;
+	struct bpf_insn *insn = NULL;
+	struct bpf_insn exp;
+	unsigned int cnt;
+	int err;
+
+#if !(defined(__x86_64__) || defined(__aarch64__) || \
+      (defined(__riscv) && __riscv_xlen == 64))
+	test__skip();
+	return;
+#endif
+
+	skel = kptr_xchg_inline__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_load"))
+		return;
+
+	err = get_xlated_program(bpf_program__fd(skel->progs.kptr_xchg_inline), &insn, &cnt);
+	if (!ASSERT_OK(err, "prog insn"))
+		goto out;
+
+	/* The original instructions are:
+	 * r1 = map[id:xxx][0]+0
+	 * r2 = 0
+	 * call bpf_kptr_xchg#yyy
+	 *
+	 * call bpf_kptr_xchg#yyy will be inlined as:
+	 * r0 = r2
+	 * r0 = atomic64_xchg((u64 *)(r1 +0), r0)
+	 */
+	if (!ASSERT_GT(cnt, 5, "insn cnt"))
+		goto out;
+
+	exp = BPF_MOV64_REG(BPF_REG_0, BPF_REG_2);
+	if (!ASSERT_OK(memcmp(&insn[3], &exp, sizeof(exp)), "mov"))
+		goto out;
+
+	exp = BPF_ATOMIC_OP(BPF_DW, BPF_XCHG, BPF_REG_1, BPF_REG_0, 0);
+	if (!ASSERT_OK(memcmp(&insn[4], &exp, sizeof(exp)), "xchg"))
+		goto out;
+out:
+	free(insn);
+	kptr_xchg_inline__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms.c b/tools/testing/selftests/bpf/prog_tests/ksyms.c
index b295969b263b..dc7aab532fb1 100644
--- a/tools/testing/selftests/bpf/prog_tests/ksyms.c
+++ b/tools/testing/selftests/bpf/prog_tests/ksyms.c
@@ -5,8 +5,6 @@
 #include "test_ksyms.skel.h"
 #include <sys/stat.h>
 
-static int duration;
-
 void test_ksyms(void)
 {
 	const char *btf_path = "/sys/kernel/btf/vmlinux";
@@ -18,43 +16,37 @@ void test_ksyms(void)
 	int err;
 
 	err = kallsyms_find("bpf_link_fops", &link_fops_addr);
-	if (CHECK(err == -EINVAL, "kallsyms_fopen", "failed to open: %d\n", errno))
+	if (!ASSERT_NEQ(err, -EINVAL, "bpf_link_fops: kallsyms_fopen"))
 		return;
-	if (CHECK(err == -ENOENT, "ksym_find", "symbol 'bpf_link_fops' not found\n"))
+	if (!ASSERT_NEQ(err, -ENOENT, "bpf_link_fops: ksym_find"))
 		return;
 
 	err = kallsyms_find("__per_cpu_start", &per_cpu_start_addr);
-	if (CHECK(err == -EINVAL, "kallsyms_fopen", "failed to open: %d\n", errno))
+	if (!ASSERT_NEQ(err, -EINVAL, "__per_cpu_start: kallsyms_fopen"))
 		return;
-	if (CHECK(err == -ENOENT, "ksym_find", "symbol 'per_cpu_start' not found\n"))
+	if (!ASSERT_NEQ(err, -ENOENT, "__per_cpu_start: ksym_find"))
 		return;
 
-	if (CHECK(stat(btf_path, &st), "stat_btf", "err %d\n", errno))
+	if (!ASSERT_OK(stat(btf_path, &st), "stat_btf"))
 		return;
 	btf_size = st.st_size;
 
 	skel = test_ksyms__open_and_load();
-	if (CHECK(!skel, "skel_open", "failed to open and load skeleton\n"))
+	if (!ASSERT_OK_PTR(skel, "test_ksyms__open_and_load"))
 		return;
 
 	err = test_ksyms__attach(skel);
-	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+	if (!ASSERT_OK(err, "test_ksyms__attach"))
 		goto cleanup;
 
 	/* trigger tracepoint */
 	usleep(1);
 
 	data = skel->data;
-	CHECK(data->out__bpf_link_fops != link_fops_addr, "bpf_link_fops",
-	      "got 0x%llx, exp 0x%llx\n",
-	      data->out__bpf_link_fops, link_fops_addr);
-	CHECK(data->out__bpf_link_fops1 != 0, "bpf_link_fops1",
-	      "got %llu, exp %llu\n", data->out__bpf_link_fops1, (__u64)0);
-	CHECK(data->out__btf_size != btf_size, "btf_size",
-	      "got %llu, exp %llu\n", data->out__btf_size, btf_size);
-	CHECK(data->out__per_cpu_start != per_cpu_start_addr, "__per_cpu_start",
-	      "got %llu, exp %llu\n", data->out__per_cpu_start,
-	      per_cpu_start_addr);
+	ASSERT_EQ(data->out__bpf_link_fops, link_fops_addr, "bpf_link_fops");
+	ASSERT_EQ(data->out__bpf_link_fops1, 0, "bpf_link_fops1");
+	ASSERT_EQ(data->out__btf_size, btf_size, "btf_size");
+	ASSERT_EQ(data->out__per_cpu_start, per_cpu_start_addr, "__per_cpu_start");
 
 cleanup:
 	test_ksyms__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/l4lb_all.c b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c
index 9c1a18573ffd..1eab286b14fe 100644
--- a/tools/testing/selftests/bpf/prog_tests/l4lb_all.c
+++ b/tools/testing/selftests/bpf/prog_tests/l4lb_all.c
@@ -93,4 +93,6 @@ void test_l4lb_all(void)
 		test_l4lb("test_l4lb.bpf.o");
 	if (test__start_subtest("l4lb_noinline"))
 		test_l4lb("test_l4lb_noinline.bpf.o");
+	if (test__start_subtest("l4lb_noinline_dynptr"))
+		test_l4lb("test_l4lb_noinline_dynptr.bpf.o");
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_get_fd_by_id_opts.c b/tools/testing/selftests/bpf/prog_tests/libbpf_get_fd_by_id_opts.c
index 25e5dfa9c315..a3f238f51d05 100644
--- a/tools/testing/selftests/bpf/prog_tests/libbpf_get_fd_by_id_opts.c
+++ b/tools/testing/selftests/bpf/prog_tests/libbpf_get_fd_by_id_opts.c
@@ -29,9 +29,9 @@ void test_libbpf_get_fd_by_id_opts(void)
 	if (!ASSERT_OK(ret, "test_libbpf_get_fd_by_id_opts__attach"))
 		goto close_prog;
 
-	ret = bpf_obj_get_info_by_fd(bpf_map__fd(skel->maps.data_input),
+	ret = bpf_map_get_info_by_fd(bpf_map__fd(skel->maps.data_input),
 				     &info_m, &len);
-	if (!ASSERT_OK(ret, "bpf_obj_get_info_by_fd"))
+	if (!ASSERT_OK(ret, "bpf_map_get_info_by_fd"))
 		goto close_prog;
 
 	fd = bpf_map_get_fd_by_id(info_m.id);
diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c
index 9f766ddd946a..4ed46ed58a7b 100644
--- a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c
+++ b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c
@@ -30,6 +30,8 @@ void test_libbpf_probe_prog_types(void)
 
 		if (prog_type == BPF_PROG_TYPE_UNSPEC)
 			continue;
+		if (strcmp(prog_type_name, "__MAX_BPF_PROG_TYPE") == 0)
+			continue;
 
 		if (!test__start_subtest(prog_type_name))
 			continue;
@@ -68,6 +70,8 @@ void test_libbpf_probe_map_types(void)
 
 		if (map_type == BPF_MAP_TYPE_UNSPEC)
 			continue;
+		if (strcmp(map_type_name, "__MAX_BPF_MAP_TYPE") == 0)
+			continue;
 
 		if (!test__start_subtest(map_type_name))
 			continue;
diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
index efb8bd43653c..62ea855ec4d0 100644
--- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
+++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
@@ -87,7 +87,7 @@ static void test_libbpf_bpf_link_type_str(void)
 		const char *link_type_str;
 		char buf[256];
 
-		if (link_type == MAX_BPF_LINK_TYPE)
+		if (link_type == __MAX_BPF_LINK_TYPE)
 			continue;
 
 		link_type_name = btf__str_by_offset(btf, e->name_off);
@@ -132,6 +132,9 @@ static void test_libbpf_bpf_map_type_str(void)
 		const char *map_type_str;
 		char buf[256];
 
+		if (map_type == __MAX_BPF_MAP_TYPE)
+			continue;
+
 		map_type_name = btf__str_by_offset(btf, e->name_off);
 		map_type_str = libbpf_bpf_map_type_str(map_type);
 		ASSERT_OK_PTR(map_type_str, map_type_name);
@@ -142,10 +145,14 @@ static void test_libbpf_bpf_map_type_str(void)
 		/* Special case for map_type_name BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED
 		 * where it and BPF_MAP_TYPE_CGROUP_STORAGE have the same enum value
 		 * (map_type). For this enum value, libbpf_bpf_map_type_str() picks
-		 * BPF_MAP_TYPE_CGROUP_STORAGE.
+		 * BPF_MAP_TYPE_CGROUP_STORAGE. The same for
+		 * BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED and
+		 * BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE.
 		 */
 		if (strcmp(map_type_name, "BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED") == 0)
 			continue;
+		if (strcmp(map_type_name, "BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED") == 0)
+			continue;
 
 		ASSERT_STREQ(buf, map_type_name, "exp_str_value");
 	}
@@ -182,6 +189,9 @@ static void test_libbpf_bpf_prog_type_str(void)
 		const char *prog_type_str;
 		char buf[256];
 
+		if (prog_type == __MAX_BPF_PROG_TYPE)
+			continue;
+
 		prog_type_name = btf__str_by_offset(btf, e->name_off);
 		prog_type_str = libbpf_bpf_prog_type_str(prog_type);
 		ASSERT_OK_PTR(prog_type_str, prog_type_name);
diff --git a/tools/testing/selftests/bpf/prog_tests/linked_funcs.c b/tools/testing/selftests/bpf/prog_tests/linked_funcs.c
index cad664546912..fa639b021f7e 100644
--- a/tools/testing/selftests/bpf/prog_tests/linked_funcs.c
+++ b/tools/testing/selftests/bpf/prog_tests/linked_funcs.c
@@ -20,7 +20,7 @@ void test_linked_funcs(void)
 	bpf_program__set_autoload(skel->progs.handler1, true);
 	bpf_program__set_autoload(skel->progs.handler2, true);
 
-	skel->rodata->my_tid = syscall(SYS_gettid);
+	skel->rodata->my_tid = sys_gettid();
 	skel->bss->syscall_id = SYS_getpgid;
 
 	err = linked_funcs__load(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/linked_list.c b/tools/testing/selftests/bpf/prog_tests/linked_list.c
index 9a7d4c47af63..14c5a7ef0e87 100644
--- a/tools/testing/selftests/bpf/prog_tests/linked_list.c
+++ b/tools/testing/selftests/bpf/prog_tests/linked_list.c
@@ -7,6 +7,7 @@
 
 #include "linked_list.skel.h"
 #include "linked_list_fail.skel.h"
+#include "linked_list_peek.skel.h"
 
 static char log_buf[1024 * 1024];
 
@@ -23,7 +24,7 @@ static struct {
 	  "bpf_spin_lock at off=" #off " must be held for bpf_list_head" }, \
 	{ #test "_missing_lock_pop_back", \
 	  "bpf_spin_lock at off=" #off " must be held for bpf_list_head" },
-	TEST(kptr, 32)
+	TEST(kptr, 40)
 	TEST(global, 16)
 	TEST(map, 0)
 	TEST(inner_map, 0)
@@ -31,7 +32,7 @@ static struct {
 #define TEST(test, op) \
 	{ #test "_kptr_incorrect_lock_" #op, \
 	  "held lock and object are not in the same allocation\n" \
-	  "bpf_spin_lock at off=32 must be held for bpf_list_head" }, \
+	  "bpf_spin_lock at off=40 must be held for bpf_list_head" }, \
 	{ #test "_global_incorrect_lock_" #op, \
 	  "held lock and object are not in the same allocation\n" \
 	  "bpf_spin_lock at off=16 must be held for bpf_list_head" }, \
@@ -58,52 +59,44 @@ static struct {
 	TEST(inner_map, pop_front)
 	TEST(inner_map, pop_back)
 #undef TEST
-	{ "map_compat_kprobe", "tracing progs cannot use bpf_list_head yet" },
-	{ "map_compat_kretprobe", "tracing progs cannot use bpf_list_head yet" },
-	{ "map_compat_tp", "tracing progs cannot use bpf_list_head yet" },
-	{ "map_compat_perf", "tracing progs cannot use bpf_list_head yet" },
-	{ "map_compat_raw_tp", "tracing progs cannot use bpf_list_head yet" },
-	{ "map_compat_raw_tp_w", "tracing progs cannot use bpf_list_head yet" },
+	{ "map_compat_kprobe", "tracing progs cannot use bpf_{list_head,rb_root} yet" },
+	{ "map_compat_kretprobe", "tracing progs cannot use bpf_{list_head,rb_root} yet" },
+	{ "map_compat_tp", "tracing progs cannot use bpf_{list_head,rb_root} yet" },
+	{ "map_compat_perf", "tracing progs cannot use bpf_{list_head,rb_root} yet" },
+	{ "map_compat_raw_tp", "tracing progs cannot use bpf_{list_head,rb_root} yet" },
+	{ "map_compat_raw_tp_w", "tracing progs cannot use bpf_{list_head,rb_root} yet" },
 	{ "obj_type_id_oor", "local type ID argument must be in range [0, U32_MAX]" },
-	{ "obj_new_no_composite", "bpf_obj_new type ID argument must be of a struct" },
-	{ "obj_new_no_struct", "bpf_obj_new type ID argument must be of a struct" },
+	{ "obj_new_no_composite", "bpf_obj_new/bpf_percpu_obj_new type ID argument must be of a struct" },
+	{ "obj_new_no_struct", "bpf_obj_new/bpf_percpu_obj_new type ID argument must be of a struct" },
 	{ "obj_drop_non_zero_off", "R1 must have zero offset when passed to release func" },
 	{ "new_null_ret", "R0 invalid mem access 'ptr_or_null_'" },
 	{ "obj_new_acq", "Unreleased reference id=" },
 	{ "use_after_drop", "invalid mem access 'scalar'" },
-	{ "ptr_walk_scalar", "type=scalar expected=percpu_ptr_" },
+	{ "ptr_walk_scalar", "type=rdonly_untrusted_mem expected=percpu_ptr_" },
 	{ "direct_read_lock", "direct access to bpf_spin_lock is disallowed" },
 	{ "direct_write_lock", "direct access to bpf_spin_lock is disallowed" },
 	{ "direct_read_head", "direct access to bpf_list_head is disallowed" },
 	{ "direct_write_head", "direct access to bpf_list_head is disallowed" },
 	{ "direct_read_node", "direct access to bpf_list_node is disallowed" },
 	{ "direct_write_node", "direct access to bpf_list_node is disallowed" },
-	{ "write_after_push_front", "only read is supported" },
-	{ "write_after_push_back", "only read is supported" },
 	{ "use_after_unlock_push_front", "invalid mem access 'scalar'" },
 	{ "use_after_unlock_push_back", "invalid mem access 'scalar'" },
 	{ "double_push_front", "arg#1 expected pointer to allocated object" },
 	{ "double_push_back", "arg#1 expected pointer to allocated object" },
 	{ "no_node_value_type", "bpf_list_node not found at offset=0" },
 	{ "incorrect_value_type",
-	  "operation on bpf_list_head expects arg#1 bpf_list_node at offset=0 in struct foo, "
+	  "operation on bpf_list_head expects arg#1 bpf_list_node at offset=48 in struct foo, "
 	  "but arg is at offset=0 in struct bar" },
 	{ "incorrect_node_var_off", "variable ptr_ access var_off=(0x0; 0xffffffff) disallowed" },
-	{ "incorrect_node_off1", "bpf_list_node not found at offset=1" },
-	{ "incorrect_node_off2", "arg#1 offset=40, but expected bpf_list_node at offset=0 in struct foo" },
+	{ "incorrect_node_off1", "bpf_list_node not found at offset=49" },
+	{ "incorrect_node_off2", "arg#1 offset=0, but expected bpf_list_node at offset=48 in struct foo" },
 	{ "no_head_type", "bpf_list_head not found at offset=0" },
 	{ "incorrect_head_var_off1", "R1 doesn't have constant offset" },
 	{ "incorrect_head_var_off2", "variable ptr_ access var_off=(0x0; 0xffffffff) disallowed" },
-	{ "incorrect_head_off1", "bpf_list_head not found at offset=17" },
+	{ "incorrect_head_off1", "bpf_list_head not found at offset=25" },
 	{ "incorrect_head_off2", "bpf_list_head not found at offset=1" },
-	{ "pop_front_off",
-	  "15: (bf) r1 = r6                      ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=40,imm=0) "
-	  "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=40,imm=0) refs=2,4\n"
-	  "16: (85) call bpf_this_cpu_ptr#154\nR1 type=ptr_or_null_ expected=percpu_ptr_" },
-	{ "pop_back_off",
-	  "15: (bf) r1 = r6                      ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=40,imm=0) "
-	  "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=40,imm=0) refs=2,4\n"
-	  "16: (85) call bpf_this_cpu_ptr#154\nR1 type=ptr_or_null_ expected=percpu_ptr_" },
+	{ "pop_front_off", "off 48 doesn't point to 'struct bpf_spin_lock' that is at 40" },
+	{ "pop_back_off", "off 48 doesn't point to 'struct bpf_spin_lock' that is at 40" },
 };
 
 static void test_linked_list_fail_prog(const char *prog_name, const char *err_msg)
@@ -191,6 +184,18 @@ static void test_linked_list_success(int mode, bool leave_in_map)
 	if (!leave_in_map)
 		clear_fields(skel->maps.bss_A);
 
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.global_list_push_pop_nested), &opts);
+	ASSERT_OK(ret, "global_list_push_pop_nested");
+	ASSERT_OK(opts.retval, "global_list_push_pop_nested retval");
+	if (!leave_in_map)
+		clear_fields(skel->maps.bss_A);
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.global_list_array_push_pop), &opts);
+	ASSERT_OK(ret, "global_list_array_push_pop");
+	ASSERT_OK(opts.retval, "global_list_array_push_pop retval");
+	if (!leave_in_map)
+		clear_fields(skel->maps.bss_A);
+
 	if (mode == PUSH_POP)
 		goto end;
 
@@ -259,7 +264,7 @@ static struct btf *init_btf(void)
 	hid = btf__add_struct(btf, "bpf_list_head", 16);
 	if (!ASSERT_EQ(hid, LIST_HEAD, "btf__add_struct bpf_list_head"))
 		goto end;
-	nid = btf__add_struct(btf, "bpf_list_node", 16);
+	nid = btf__add_struct(btf, "bpf_list_node", 24);
 	if (!ASSERT_EQ(nid, LIST_NODE, "btf__add_struct bpf_list_node"))
 		goto end;
 	return btf;
@@ -268,6 +273,59 @@ end:
 	return NULL;
 }
 
+static void list_and_rb_node_same_struct(bool refcount_field)
+{
+	int bpf_rb_node_btf_id, bpf_refcount_btf_id = 0, foo_btf_id;
+	struct btf *btf;
+	int id, err;
+
+	btf = init_btf();
+	if (!ASSERT_OK_PTR(btf, "init_btf"))
+		return;
+
+	bpf_rb_node_btf_id = btf__add_struct(btf, "bpf_rb_node", 32);
+	if (!ASSERT_GT(bpf_rb_node_btf_id, 0, "btf__add_struct bpf_rb_node"))
+		return;
+
+	if (refcount_field) {
+		bpf_refcount_btf_id = btf__add_struct(btf, "bpf_refcount", 4);
+		if (!ASSERT_GT(bpf_refcount_btf_id, 0, "btf__add_struct bpf_refcount"))
+			return;
+	}
+
+	id = btf__add_struct(btf, "bar", refcount_field ? 60 : 56);
+	if (!ASSERT_GT(id, 0, "btf__add_struct bar"))
+		return;
+	err = btf__add_field(btf, "a", LIST_NODE, 0, 0);
+	if (!ASSERT_OK(err, "btf__add_field bar::a"))
+		return;
+	err = btf__add_field(btf, "c", bpf_rb_node_btf_id, 192, 0);
+	if (!ASSERT_OK(err, "btf__add_field bar::c"))
+		return;
+	if (refcount_field) {
+		err = btf__add_field(btf, "ref", bpf_refcount_btf_id, 448, 0);
+		if (!ASSERT_OK(err, "btf__add_field bar::ref"))
+			return;
+	}
+
+	foo_btf_id = btf__add_struct(btf, "foo", 20);
+	if (!ASSERT_GT(foo_btf_id, 0, "btf__add_struct foo"))
+		return;
+	err = btf__add_field(btf, "a", LIST_HEAD, 0, 0);
+	if (!ASSERT_OK(err, "btf__add_field foo::a"))
+		return;
+	err = btf__add_field(btf, "b", SPIN_LOCK, 128, 0);
+	if (!ASSERT_OK(err, "btf__add_field foo::b"))
+		return;
+	id = btf__add_decl_tag(btf, "contains:bar:a", foo_btf_id, 0);
+	if (!ASSERT_GT(id, 0, "btf__add_decl_tag contains:bar:a"))
+		return;
+
+	err = btf__load_into_kernel(btf);
+	ASSERT_EQ(err, refcount_field ? 0 : -EINVAL, "check btf");
+	btf__free(btf);
+}
+
 static void test_btf(void)
 {
 	struct btf *btf = NULL;
@@ -476,7 +534,7 @@ static void test_btf(void)
 		btf = init_btf();
 		if (!ASSERT_OK_PTR(btf, "init_btf"))
 			break;
-		id = btf__add_struct(btf, "foo", 36);
+		id = btf__add_struct(btf, "foo", 44);
 		if (!ASSERT_EQ(id, 5, "btf__add_struct foo"))
 			break;
 		err = btf__add_field(btf, "a", LIST_HEAD, 0, 0);
@@ -485,7 +543,7 @@ static void test_btf(void)
 		err = btf__add_field(btf, "b", LIST_NODE, 128, 0);
 		if (!ASSERT_OK(err, "btf__add_field foo::b"))
 			break;
-		err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0);
+		err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0);
 		if (!ASSERT_OK(err, "btf__add_field foo::c"))
 			break;
 		id = btf__add_decl_tag(btf, "contains:foo:b", 5, 0);
@@ -502,7 +560,7 @@ static void test_btf(void)
 		btf = init_btf();
 		if (!ASSERT_OK_PTR(btf, "init_btf"))
 			break;
-		id = btf__add_struct(btf, "foo", 36);
+		id = btf__add_struct(btf, "foo", 44);
 		if (!ASSERT_EQ(id, 5, "btf__add_struct foo"))
 			break;
 		err = btf__add_field(btf, "a", LIST_HEAD, 0, 0);
@@ -511,13 +569,13 @@ static void test_btf(void)
 		err = btf__add_field(btf, "b", LIST_NODE, 128, 0);
 		if (!ASSERT_OK(err, "btf__add_field foo::b"))
 			break;
-		err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0);
+		err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0);
 		if (!ASSERT_OK(err, "btf__add_field foo::c"))
 			break;
 		id = btf__add_decl_tag(btf, "contains:bar:b", 5, 0);
 		if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:b"))
 			break;
-		id = btf__add_struct(btf, "bar", 36);
+		id = btf__add_struct(btf, "bar", 44);
 		if (!ASSERT_EQ(id, 7, "btf__add_struct bar"))
 			break;
 		err = btf__add_field(btf, "a", LIST_HEAD, 0, 0);
@@ -526,7 +584,7 @@ static void test_btf(void)
 		err = btf__add_field(btf, "b", LIST_NODE, 128, 0);
 		if (!ASSERT_OK(err, "btf__add_field bar::b"))
 			break;
-		err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0);
+		err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0);
 		if (!ASSERT_OK(err, "btf__add_field bar::c"))
 			break;
 		id = btf__add_decl_tag(btf, "contains:foo:b", 7, 0);
@@ -543,19 +601,19 @@ static void test_btf(void)
 		btf = init_btf();
 		if (!ASSERT_OK_PTR(btf, "init_btf"))
 			break;
-		id = btf__add_struct(btf, "foo", 20);
+		id = btf__add_struct(btf, "foo", 28);
 		if (!ASSERT_EQ(id, 5, "btf__add_struct foo"))
 			break;
 		err = btf__add_field(btf, "a", LIST_HEAD, 0, 0);
 		if (!ASSERT_OK(err, "btf__add_field foo::a"))
 			break;
-		err = btf__add_field(btf, "b", SPIN_LOCK, 128, 0);
+		err = btf__add_field(btf, "b", SPIN_LOCK, 192, 0);
 		if (!ASSERT_OK(err, "btf__add_field foo::b"))
 			break;
 		id = btf__add_decl_tag(btf, "contains:bar:a", 5, 0);
 		if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:a"))
 			break;
-		id = btf__add_struct(btf, "bar", 16);
+		id = btf__add_struct(btf, "bar", 24);
 		if (!ASSERT_EQ(id, 7, "btf__add_struct bar"))
 			break;
 		err = btf__add_field(btf, "a", LIST_NODE, 0, 0);
@@ -572,19 +630,19 @@ static void test_btf(void)
 		btf = init_btf();
 		if (!ASSERT_OK_PTR(btf, "init_btf"))
 			break;
-		id = btf__add_struct(btf, "foo", 20);
+		id = btf__add_struct(btf, "foo", 28);
 		if (!ASSERT_EQ(id, 5, "btf__add_struct foo"))
 			break;
 		err = btf__add_field(btf, "a", LIST_HEAD, 0, 0);
 		if (!ASSERT_OK(err, "btf__add_field foo::a"))
 			break;
-		err = btf__add_field(btf, "b", SPIN_LOCK, 128, 0);
+		err = btf__add_field(btf, "b", SPIN_LOCK, 192, 0);
 		if (!ASSERT_OK(err, "btf__add_field foo::b"))
 			break;
 		id = btf__add_decl_tag(btf, "contains:bar:b", 5, 0);
 		if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:b"))
 			break;
-		id = btf__add_struct(btf, "bar", 36);
+		id = btf__add_struct(btf, "bar", 44);
 		if (!ASSERT_EQ(id, 7, "btf__add_struct bar"))
 			break;
 		err = btf__add_field(btf, "a", LIST_HEAD, 0, 0);
@@ -593,13 +651,13 @@ static void test_btf(void)
 		err = btf__add_field(btf, "b", LIST_NODE, 128, 0);
 		if (!ASSERT_OK(err, "btf__add_field bar::b"))
 			break;
-		err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0);
+		err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0);
 		if (!ASSERT_OK(err, "btf__add_field bar::c"))
 			break;
 		id = btf__add_decl_tag(btf, "contains:baz:a", 7, 0);
 		if (!ASSERT_EQ(id, 8, "btf__add_decl_tag contains:baz:a"))
 			break;
-		id = btf__add_struct(btf, "baz", 16);
+		id = btf__add_struct(btf, "baz", 24);
 		if (!ASSERT_EQ(id, 9, "btf__add_struct baz"))
 			break;
 		err = btf__add_field(btf, "a", LIST_NODE, 0, 0);
@@ -616,7 +674,7 @@ static void test_btf(void)
 		btf = init_btf();
 		if (!ASSERT_OK_PTR(btf, "init_btf"))
 			break;
-		id = btf__add_struct(btf, "foo", 36);
+		id = btf__add_struct(btf, "foo", 44);
 		if (!ASSERT_EQ(id, 5, "btf__add_struct foo"))
 			break;
 		err = btf__add_field(btf, "a", LIST_HEAD, 0, 0);
@@ -625,13 +683,13 @@ static void test_btf(void)
 		err = btf__add_field(btf, "b", LIST_NODE, 128, 0);
 		if (!ASSERT_OK(err, "btf__add_field foo::b"))
 			break;
-		err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0);
+		err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0);
 		if (!ASSERT_OK(err, "btf__add_field foo::c"))
 			break;
 		id = btf__add_decl_tag(btf, "contains:bar:b", 5, 0);
 		if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:b"))
 			break;
-		id = btf__add_struct(btf, "bar", 36);
+		id = btf__add_struct(btf, "bar", 44);
 		if (!ASSERT_EQ(id, 7, "btf__add_struct bar"))
 			break;
 		err = btf__add_field(btf, "a", LIST_HEAD, 0, 0);
@@ -640,13 +698,13 @@ static void test_btf(void)
 		err = btf__add_field(btf, "b", LIST_NODE, 128, 0);
 		if (!ASSERT_OK(err, "btf__add_field bar:b"))
 			break;
-		err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0);
+		err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0);
 		if (!ASSERT_OK(err, "btf__add_field bar:c"))
 			break;
 		id = btf__add_decl_tag(btf, "contains:baz:a", 7, 0);
 		if (!ASSERT_EQ(id, 8, "btf__add_decl_tag contains:baz:a"))
 			break;
-		id = btf__add_struct(btf, "baz", 16);
+		id = btf__add_struct(btf, "baz", 24);
 		if (!ASSERT_EQ(id, 9, "btf__add_struct baz"))
 			break;
 		err = btf__add_field(btf, "a", LIST_NODE, 0, 0);
@@ -675,7 +733,7 @@ static void test_btf(void)
 		id = btf__add_decl_tag(btf, "contains:bar:b", 5, 0);
 		if (!ASSERT_EQ(id, 6, "btf__add_decl_tag contains:bar:b"))
 			break;
-		id = btf__add_struct(btf, "bar", 36);
+		id = btf__add_struct(btf, "bar", 44);
 		if (!ASSERT_EQ(id, 7, "btf__add_struct bar"))
 			break;
 		err = btf__add_field(btf, "a", LIST_HEAD, 0, 0);
@@ -684,13 +742,13 @@ static void test_btf(void)
 		err = btf__add_field(btf, "b", LIST_NODE, 128, 0);
 		if (!ASSERT_OK(err, "btf__add_field bar::b"))
 			break;
-		err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0);
+		err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0);
 		if (!ASSERT_OK(err, "btf__add_field bar::c"))
 			break;
 		id = btf__add_decl_tag(btf, "contains:baz:b", 7, 0);
 		if (!ASSERT_EQ(id, 8, "btf__add_decl_tag"))
 			break;
-		id = btf__add_struct(btf, "baz", 36);
+		id = btf__add_struct(btf, "baz", 44);
 		if (!ASSERT_EQ(id, 9, "btf__add_struct baz"))
 			break;
 		err = btf__add_field(btf, "a", LIST_HEAD, 0, 0);
@@ -699,13 +757,13 @@ static void test_btf(void)
 		err = btf__add_field(btf, "b", LIST_NODE, 128, 0);
 		if (!ASSERT_OK(err, "btf__add_field bar::b"))
 			break;
-		err = btf__add_field(btf, "c", SPIN_LOCK, 256, 0);
+		err = btf__add_field(btf, "c", SPIN_LOCK, 320, 0);
 		if (!ASSERT_OK(err, "btf__add_field bar::c"))
 			break;
 		id = btf__add_decl_tag(btf, "contains:bam:a", 9, 0);
 		if (!ASSERT_EQ(id, 10, "btf__add_decl_tag contains:bam:a"))
 			break;
-		id = btf__add_struct(btf, "bam", 16);
+		id = btf__add_struct(btf, "bam", 24);
 		if (!ASSERT_EQ(id, 11, "btf__add_struct bam"))
 			break;
 		err = btf__add_field(btf, "a", LIST_NODE, 0, 0);
@@ -717,6 +775,16 @@ static void test_btf(void)
 		btf__free(btf);
 		break;
 	}
+
+	while (test__start_subtest("btf: list_node and rb_node in same struct")) {
+		list_and_rb_node_same_struct(true);
+		break;
+	}
+
+	while (test__start_subtest("btf: list_node and rb_node in same struct, no bpf_refcount")) {
+		list_and_rb_node_same_struct(false);
+		break;
+	}
 }
 
 void test_linked_list(void)
@@ -738,3 +806,8 @@ void test_linked_list(void)
 	test_linked_list_success(LIST_IN_LIST, true);
 	test_linked_list_success(TEST_ALL, false);
 }
+
+void test_linked_list_peek(void)
+{
+	RUN_TESTS(linked_list_peek);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/livepatch_trampoline.c b/tools/testing/selftests/bpf/prog_tests/livepatch_trampoline.c
new file mode 100644
index 000000000000..72aa5376c30e
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/livepatch_trampoline.c
@@ -0,0 +1,107 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <test_progs.h>
+#include "testing_helpers.h"
+#include "livepatch_trampoline.skel.h"
+
+static int load_livepatch(void)
+{
+	char path[4096];
+
+	/* CI will set KBUILD_OUTPUT */
+	snprintf(path, sizeof(path), "%s/samples/livepatch/livepatch-sample.ko",
+		 getenv("KBUILD_OUTPUT") ? : "../../../..");
+
+	return load_module(path, env_verbosity > VERBOSE_NONE);
+}
+
+static void unload_livepatch(void)
+{
+	/* Disable the livepatch before unloading the module */
+	system("echo 0 > /sys/kernel/livepatch/livepatch_sample/enabled");
+
+	unload_module("livepatch_sample", env_verbosity > VERBOSE_NONE);
+}
+
+static void read_proc_cmdline(void)
+{
+	char buf[4096];
+	int fd, ret;
+
+	fd = open("/proc/cmdline", O_RDONLY);
+	if (!ASSERT_OK_FD(fd, "open /proc/cmdline"))
+		return;
+
+	ret = read(fd, buf, sizeof(buf));
+	if (!ASSERT_GT(ret, 0, "read /proc/cmdline"))
+		goto out;
+
+	ASSERT_OK(strncmp(buf, "this has been live patched", 26), "strncmp");
+
+out:
+	close(fd);
+}
+
+static void __test_livepatch_trampoline(bool fexit_first)
+{
+	struct livepatch_trampoline *skel = NULL;
+	int err;
+
+	skel = livepatch_trampoline__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		goto out;
+
+	skel->bss->my_pid = getpid();
+
+	if (!fexit_first) {
+		/* fentry program is loaded first by default */
+		err = livepatch_trampoline__attach(skel);
+		if (!ASSERT_OK(err, "skel_attach"))
+			goto out;
+	} else {
+		/* Manually load fexit program first. */
+		skel->links.fexit_cmdline = bpf_program__attach(skel->progs.fexit_cmdline);
+		if (!ASSERT_OK_PTR(skel->links.fexit_cmdline, "attach_fexit"))
+			goto out;
+
+		skel->links.fentry_cmdline = bpf_program__attach(skel->progs.fentry_cmdline);
+		if (!ASSERT_OK_PTR(skel->links.fentry_cmdline, "attach_fentry"))
+			goto out;
+	}
+
+	read_proc_cmdline();
+
+	ASSERT_EQ(skel->bss->fentry_hit, 1, "fentry_hit");
+	ASSERT_EQ(skel->bss->fexit_hit, 1, "fexit_hit");
+out:
+	livepatch_trampoline__destroy(skel);
+}
+
+void test_livepatch_trampoline(void)
+{
+	int retry_cnt = 0;
+
+retry:
+	if (load_livepatch()) {
+		if (retry_cnt) {
+			ASSERT_OK(1, "load_livepatch");
+			goto out;
+		}
+		/*
+		 * Something else (previous run of the same test?) loaded
+		 * the KLP module. Unload the KLP module and retry.
+		 */
+		unload_livepatch();
+		retry_cnt++;
+		goto retry;
+	}
+
+	if (test__start_subtest("fentry_first"))
+		__test_livepatch_trampoline(false);
+
+	if (test__start_subtest("fexit_first"))
+		__test_livepatch_trampoline(true);
+out:
+	unload_livepatch();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c b/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c
new file mode 100644
index 000000000000..827e713f6cf1
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/local_kptr_stash.c
@@ -0,0 +1,147 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <test_progs.h>
+#include <network_helpers.h>
+
+#include "local_kptr_stash.skel.h"
+#include "local_kptr_stash_fail.skel.h"
+static void test_local_kptr_stash_simple(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+	struct local_kptr_stash *skel;
+	int ret;
+
+	skel = local_kptr_stash__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "local_kptr_stash__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.stash_rb_nodes), &opts);
+	ASSERT_OK(ret, "local_kptr_stash_add_nodes run");
+	ASSERT_OK(opts.retval, "local_kptr_stash_add_nodes retval");
+
+	local_kptr_stash__destroy(skel);
+}
+
+static void test_local_kptr_stash_plain(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+	struct local_kptr_stash *skel;
+	int ret;
+
+	skel = local_kptr_stash__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "local_kptr_stash__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.stash_plain), &opts);
+	ASSERT_OK(ret, "local_kptr_stash_add_plain run");
+	ASSERT_OK(opts.retval, "local_kptr_stash_add_plain retval");
+
+	local_kptr_stash__destroy(skel);
+}
+
+static void test_local_kptr_stash_local_with_root(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+	struct local_kptr_stash *skel;
+	int ret;
+
+	skel = local_kptr_stash__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "local_kptr_stash__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.stash_local_with_root), &opts);
+	ASSERT_OK(ret, "local_kptr_stash_add_local_with_root run");
+	ASSERT_OK(opts.retval, "local_kptr_stash_add_local_with_root retval");
+
+	local_kptr_stash__destroy(skel);
+}
+
+static void test_local_kptr_stash_unstash(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+	struct local_kptr_stash *skel;
+	int ret;
+
+	skel = local_kptr_stash__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "local_kptr_stash__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.stash_rb_nodes), &opts);
+	ASSERT_OK(ret, "local_kptr_stash_add_nodes run");
+	ASSERT_OK(opts.retval, "local_kptr_stash_add_nodes retval");
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.unstash_rb_node), &opts);
+	ASSERT_OK(ret, "local_kptr_stash_add_nodes run");
+	ASSERT_EQ(opts.retval, 42, "local_kptr_stash_add_nodes retval");
+
+	local_kptr_stash__destroy(skel);
+}
+
+static void test_refcount_acquire_without_unstash(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+	struct local_kptr_stash *skel;
+	int ret;
+
+	skel = local_kptr_stash__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "local_kptr_stash__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.refcount_acquire_without_unstash),
+				     &opts);
+	ASSERT_OK(ret, "refcount_acquire_without_unstash run");
+	ASSERT_EQ(opts.retval, 2, "refcount_acquire_without_unstash retval");
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.stash_refcounted_node), &opts);
+	ASSERT_OK(ret, "stash_refcounted_node run");
+	ASSERT_OK(opts.retval, "stash_refcounted_node retval");
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.refcount_acquire_without_unstash),
+				     &opts);
+	ASSERT_OK(ret, "refcount_acquire_without_unstash (2) run");
+	ASSERT_EQ(opts.retval, 42, "refcount_acquire_without_unstash (2) retval");
+
+	local_kptr_stash__destroy(skel);
+}
+
+static void test_local_kptr_stash_fail(void)
+{
+	RUN_TESTS(local_kptr_stash_fail);
+}
+
+void test_local_kptr_stash(void)
+{
+	if (test__start_subtest("local_kptr_stash_simple"))
+		test_local_kptr_stash_simple();
+	if (test__start_subtest("local_kptr_stash_plain"))
+		test_local_kptr_stash_plain();
+	if (test__start_subtest("local_kptr_stash_local_with_root"))
+		test_local_kptr_stash_local_with_root();
+	if (test__start_subtest("local_kptr_stash_unstash"))
+		test_local_kptr_stash_unstash();
+	if (test__start_subtest("refcount_acquire_without_unstash"))
+		test_refcount_acquire_without_unstash();
+	if (test__start_subtest("local_kptr_stash_fail"))
+		test_local_kptr_stash_fail();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/log_buf.c b/tools/testing/selftests/bpf/prog_tests/log_buf.c
index fe9a23e65ef4..d6f14a232002 100644
--- a/tools/testing/selftests/bpf/prog_tests/log_buf.c
+++ b/tools/testing/selftests/bpf/prog_tests/log_buf.c
@@ -5,6 +5,11 @@
 #include <bpf/btf.h>
 
 #include "test_log_buf.skel.h"
+#include "bpf_util.h"
+
+#if !defined(__clang__)
+#pragma GCC diagnostic ignored "-Wmaybe-uninitialized"
+#endif
 
 static size_t libbpf_log_pos;
 static char libbpf_log_buf[1024 * 1024];
@@ -78,7 +83,7 @@ static void obj_load_log_buf(void)
 	ASSERT_OK_PTR(strstr(libbpf_log_buf, "prog 'bad_prog': BPF program load failed"),
 		      "libbpf_log_not_empty");
 	ASSERT_OK_PTR(strstr(obj_log_buf, "DATASEC license"), "obj_log_not_empty");
-	ASSERT_OK_PTR(strstr(good_log_buf, "0: R1=ctx(off=0,imm=0) R10=fp0"),
+	ASSERT_OK_PTR(strstr(good_log_buf, "0: R1=ctx() R10=fp0"),
 		      "good_log_verbose");
 	ASSERT_OK_PTR(strstr(bad_log_buf, "invalid access to map value, value_size=16 off=16000 size=4"),
 		      "bad_log_not_empty");
@@ -143,11 +148,11 @@ static void bpf_prog_load_log_buf(void)
 		BPF_MOV64_IMM(BPF_REG_0, 0),
 		BPF_EXIT_INSN(),
 	};
-	const size_t good_prog_insn_cnt = sizeof(good_prog_insns) / sizeof(struct bpf_insn);
+	const size_t good_prog_insn_cnt = ARRAY_SIZE(good_prog_insns);
 	const struct bpf_insn bad_prog_insns[] = {
 		BPF_EXIT_INSN(),
 	};
-	size_t bad_prog_insn_cnt = sizeof(bad_prog_insns) / sizeof(struct bpf_insn);
+	size_t bad_prog_insn_cnt = ARRAY_SIZE(bad_prog_insns);
 	LIBBPF_OPTS(bpf_prog_load_opts, opts);
 	const size_t log_buf_sz = 1024 * 1024;
 	char *log_buf;
@@ -159,7 +164,7 @@ static void bpf_prog_load_log_buf(void)
 	opts.log_buf = log_buf;
 	opts.log_size = log_buf_sz;
 
-	/* with log_level == 0 log_buf shoud stay empty for good prog */
+	/* with log_level == 0 log_buf should stay empty for good prog */
 	log_buf[0] = '\0';
 	opts.log_level = 0;
 	fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "good_prog", "GPL",
@@ -168,18 +173,16 @@ static void bpf_prog_load_log_buf(void)
 	ASSERT_GE(fd, 0, "good_fd1");
 	if (fd >= 0)
 		close(fd);
-	fd = -1;
 
 	/* log_level == 2 should always fill log_buf, even for good prog */
 	log_buf[0] = '\0';
 	opts.log_level = 2;
 	fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "good_prog", "GPL",
 			   good_prog_insns, good_prog_insn_cnt, &opts);
-	ASSERT_OK_PTR(strstr(log_buf, "0: R1=ctx(off=0,imm=0) R10=fp0"), "good_log_2");
+	ASSERT_OK_PTR(strstr(log_buf, "0: R1=ctx() R10=fp0"), "good_log_2");
 	ASSERT_GE(fd, 0, "good_fd2");
 	if (fd >= 0)
 		close(fd);
-	fd = -1;
 
 	/* log_level == 0 should fill log_buf for bad prog */
 	log_buf[0] = '\0';
@@ -190,7 +193,6 @@ static void bpf_prog_load_log_buf(void)
 	ASSERT_LT(fd, 0, "bad_fd");
 	if (fd >= 0)
 		close(fd);
-	fd = -1;
 
 	free(log_buf);
 }
@@ -221,7 +223,7 @@ static void bpf_btf_load_log_buf(void)
 	opts.log_buf = log_buf;
 	opts.log_size = log_buf_sz;
 
-	/* with log_level == 0 log_buf shoud stay empty for good BTF */
+	/* with log_level == 0 log_buf should stay empty for good BTF */
 	log_buf[0] = '\0';
 	opts.log_level = 0;
 	fd = bpf_btf_load(raw_btf_data, raw_btf_size, &opts);
diff --git a/tools/testing/selftests/bpf/prog_tests/log_fixup.c b/tools/testing/selftests/bpf/prog_tests/log_fixup.c
index f4ffdcabf4e4..90a98e23be61 100644
--- a/tools/testing/selftests/bpf/prog_tests/log_fixup.c
+++ b/tools/testing/selftests/bpf/prog_tests/log_fixup.c
@@ -24,6 +24,7 @@ static void bad_core_relo(size_t log_buf_size, enum trunc_type trunc_type)
 	bpf_program__set_autoload(skel->progs.bad_relo, true);
 	memset(log_buf, 0, sizeof(log_buf));
 	bpf_program__set_log_buf(skel->progs.bad_relo, log_buf, log_buf_size ?: sizeof(log_buf));
+	bpf_program__set_log_level(skel->progs.bad_relo, 1 | 8); /* BPF_LOG_FIXED to force truncation */
 
 	err = test_log_fixup__load(skel);
 	if (!ASSERT_ERR(err, "load_fail"))
@@ -123,7 +124,7 @@ static void missing_map(void)
 	ASSERT_FALSE(bpf_map__autocreate(skel->maps.missing_map), "missing_map_autocreate");
 
 	ASSERT_HAS_SUBSTR(log_buf,
-			  "8: <invalid BPF map reference>\n"
+			  ": <invalid BPF map reference>\n"
 			  "BPF map 'missing_map' is referenced but wasn't created\n",
 			  "log_buf");
 
@@ -134,6 +135,35 @@ cleanup:
 	test_log_fixup__destroy(skel);
 }
 
+static void missing_kfunc(void)
+{
+	char log_buf[8 * 1024];
+	struct test_log_fixup* skel;
+	int err;
+
+	skel = test_log_fixup__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	bpf_program__set_autoload(skel->progs.use_missing_kfunc, true);
+	bpf_program__set_log_buf(skel->progs.use_missing_kfunc, log_buf, sizeof(log_buf));
+
+	err = test_log_fixup__load(skel);
+	if (!ASSERT_ERR(err, "load_fail"))
+		goto cleanup;
+
+	ASSERT_HAS_SUBSTR(log_buf,
+			  "0: <invalid kfunc call>\n"
+			  "kfunc 'bpf_nonexistent_kfunc' is referenced but wasn't resolved\n",
+			  "log_buf");
+
+	if (env.verbosity > VERBOSE_NONE)
+		printf("LOG:   \n=================\n%s=================\n", log_buf);
+
+cleanup:
+	test_log_fixup__destroy(skel);
+}
+
 void test_log_fixup(void)
 {
 	if (test__start_subtest("bad_core_relo_trunc_none"))
@@ -141,9 +171,11 @@ void test_log_fixup(void)
 	if (test__start_subtest("bad_core_relo_trunc_partial"))
 		bad_core_relo(300, TRUNC_PARTIAL /* truncate original log a bit */);
 	if (test__start_subtest("bad_core_relo_trunc_full"))
-		bad_core_relo(250, TRUNC_FULL  /* truncate also libbpf's message patch */);
+		bad_core_relo(240, TRUNC_FULL  /* truncate also libbpf's message patch */);
 	if (test__start_subtest("bad_core_relo_subprog"))
 		bad_core_relo_subprog();
 	if (test__start_subtest("missing_map"))
 		missing_map();
+	if (test__start_subtest("missing_kfunc"))
+		missing_kfunc();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/lsm_cgroup.c b/tools/testing/selftests/bpf/prog_tests/lsm_cgroup.c
index f117bfef68a1..6df25de8f080 100644
--- a/tools/testing/selftests/bpf/prog_tests/lsm_cgroup.c
+++ b/tools/testing/selftests/bpf/prog_tests/lsm_cgroup.c
@@ -10,10 +10,6 @@
 #include "cgroup_helpers.h"
 #include "network_helpers.h"
 
-#ifndef ENOTSUPP
-#define ENOTSUPP 524
-#endif
-
 static struct btf *btf;
 
 static __u32 query_prog_cnt(int cgroup_fd, const char *attach_func)
@@ -47,7 +43,8 @@ static __u32 query_prog_cnt(int cgroup_fd, const char *attach_func)
 
 		fd = bpf_prog_get_fd_by_id(p.prog_ids[i]);
 		ASSERT_GE(fd, 0, "prog_get_fd_by_id");
-		ASSERT_OK(bpf_obj_get_info_by_fd(fd, &info, &info_len), "prog_info_by_fd");
+		ASSERT_OK(bpf_prog_get_info_by_fd(fd, &info, &info_len),
+			  "prog_info_by_fd");
 		close(fd);
 
 		if (info.attach_btf_id ==
diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h b/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h
new file mode 100644
index 000000000000..ccec0fcdabc1
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h
@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __LWT_HELPERS_H
+#define __LWT_HELPERS_H
+
+#include <time.h>
+#include <net/if.h>
+#include <linux/icmp.h>
+
+#include "test_progs.h"
+
+#define log_err(MSG, ...) \
+	fprintf(stderr, "(%s:%d: errno: %s) " MSG "\n", \
+		__FILE__, __LINE__, strerror(errno), ##__VA_ARGS__)
+
+#define RUN_TEST(name)                                                        \
+	({                                                                    \
+		if (test__start_subtest(#name))                               \
+			if (ASSERT_OK(netns_create(), "netns_create")) {      \
+				struct nstoken *token = open_netns(NETNS);    \
+				if (ASSERT_OK_PTR(token, "setns")) {          \
+					test_ ## name();                      \
+					close_netns(token);                   \
+				}                                             \
+				netns_delete();                               \
+			}                                                     \
+	})
+
+static inline int netns_create(void)
+{
+	return system("ip netns add " NETNS);
+}
+
+static inline int netns_delete(void)
+{
+	return system("ip netns del " NETNS ">/dev/null 2>&1");
+}
+
+#define ICMP_PAYLOAD_SIZE     100
+
+/* Match an ICMP packet with payload len ICMP_PAYLOAD_SIZE */
+static int __expect_icmp_ipv4(char *buf, ssize_t len)
+{
+	struct iphdr *ip = (struct iphdr *)buf;
+	struct icmphdr *icmp = (struct icmphdr *)(ip + 1);
+	ssize_t min_header_len = sizeof(*ip) + sizeof(*icmp);
+
+	if (len < min_header_len)
+		return -1;
+
+	if (ip->protocol != IPPROTO_ICMP)
+		return -1;
+
+	if (icmp->type != ICMP_ECHO)
+		return -1;
+
+	return len == ICMP_PAYLOAD_SIZE + min_header_len;
+}
+
+typedef int (*filter_t) (char *, ssize_t);
+
+/* wait_for_packet - wait for a packet that matches the filter
+ *
+ * @fd: tun fd/packet socket to read packet
+ * @filter: filter function, returning 1 if matches
+ * @timeout: timeout to wait for the packet
+ *
+ * Returns 1 if a matching packet is read, 0 if timeout expired, -1 on error.
+ */
+static int wait_for_packet(int fd, filter_t filter, struct timeval *timeout)
+{
+	char buf[4096];
+	int max_retry = 5; /* in case we read some spurious packets */
+	fd_set fds;
+
+	FD_ZERO(&fds);
+	while (max_retry--) {
+		/* Linux modifies timeout arg... So make a copy */
+		struct timeval copied_timeout = *timeout;
+		ssize_t ret = -1;
+
+		FD_SET(fd, &fds);
+
+		ret = select(1 + fd, &fds, NULL, NULL, &copied_timeout);
+		if (ret <= 0) {
+			if (errno == EINTR)
+				continue;
+			else if (errno == EAGAIN || ret == 0)
+				return 0;
+
+			log_err("select failed");
+			return -1;
+		}
+
+		ret = read(fd, buf, sizeof(buf));
+
+		if (ret <= 0) {
+			log_err("read(dev): %ld", ret);
+			return -1;
+		}
+
+		if (filter && filter(buf, ret) > 0)
+			return 1;
+	}
+
+	return 0;
+}
+
+#endif /* __LWT_HELPERS_H */
diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_ip_encap.c b/tools/testing/selftests/bpf/prog_tests/lwt_ip_encap.c
new file mode 100644
index 000000000000..b6391af5f6f9
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_ip_encap.c
@@ -0,0 +1,540 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <netinet/in.h>
+
+#include "network_helpers.h"
+#include "test_progs.h"
+
+#define BPF_FILE "test_lwt_ip_encap.bpf.o"
+
+#define NETNS_NAME_SIZE	32
+#define NETNS_BASE	"ns-lwt-ip-encap"
+
+#define IP4_ADDR_1 "172.16.1.100"
+#define IP4_ADDR_2 "172.16.2.100"
+#define IP4_ADDR_3 "172.16.3.100"
+#define IP4_ADDR_4 "172.16.4.100"
+#define IP4_ADDR_5 "172.16.5.100"
+#define IP4_ADDR_6 "172.16.6.100"
+#define IP4_ADDR_7 "172.16.7.100"
+#define IP4_ADDR_8 "172.16.8.100"
+#define IP4_ADDR_GRE "172.16.16.100"
+
+#define IP4_ADDR_SRC IP4_ADDR_1
+#define IP4_ADDR_DST IP4_ADDR_4
+
+#define IP6_ADDR_1 "fb01::1"
+#define IP6_ADDR_2 "fb02::1"
+#define IP6_ADDR_3 "fb03::1"
+#define IP6_ADDR_4 "fb04::1"
+#define IP6_ADDR_5 "fb05::1"
+#define IP6_ADDR_6 "fb06::1"
+#define IP6_ADDR_7 "fb07::1"
+#define IP6_ADDR_8 "fb08::1"
+#define IP6_ADDR_GRE "fb10::1"
+
+#define IP6_ADDR_SRC IP6_ADDR_1
+#define IP6_ADDR_DST IP6_ADDR_4
+
+/* Setup/topology:
+ *
+ *    NS1             NS2             NS3
+ *   veth1 <---> veth2   veth3 <---> veth4 (the top route)
+ *   veth5 <---> veth6   veth7 <---> veth8 (the bottom route)
+ *
+ *   Each vethN gets IP[4|6]_ADDR_N address.
+ *
+ *   IP*_ADDR_SRC = IP*_ADDR_1
+ *   IP*_ADDR_DST = IP*_ADDR_4
+ *
+ *   All tests test pings from IP*_ADDR__SRC to IP*_ADDR_DST.
+ *
+ *   By default, routes are configured to allow packets to go
+ *   IP*_ADDR_1 <=> IP*_ADDR_2 <=> IP*_ADDR_3 <=> IP*_ADDR_4 (the top route).
+ *
+ *   A GRE device is installed in NS3 with IP*_ADDR_GRE, and
+ *   NS1/NS2 are configured to route packets to IP*_ADDR_GRE via IP*_ADDR_8
+ *   (the bottom route).
+ *
+ * Tests:
+ *
+ *   1. Routes NS2->IP*_ADDR_DST are brought down, so the only way a ping
+ *      from IP*_ADDR_SRC to IP*_ADDR_DST can work is via IP*_ADDR_GRE.
+ *
+ *   2a. In an egress test, a bpf LWT_XMIT program is installed on veth1
+ *       that encaps the packets with an IP/GRE header to route to IP*_ADDR_GRE.
+ *
+ *       ping: SRC->[encap at veth1:egress]->GRE:decap->DST
+ *       ping replies go DST->SRC directly
+ *
+ *   2b. In an ingress test, a bpf LWT_IN program is installed on veth2
+ *       that encaps the packets with an IP/GRE header to route to IP*_ADDR_GRE.
+ *
+ *       ping: SRC->[encap at veth2:ingress]->GRE:decap->DST
+ *       ping replies go DST->SRC directly
+ */
+
+static int create_ns(char *name, size_t name_sz)
+{
+	if (!name)
+		goto fail;
+
+	if (!ASSERT_OK(append_tid(name, name_sz), "append TID"))
+		goto fail;
+
+	SYS(fail, "ip netns add %s", name);
+
+	/* rp_filter gets confused by what these tests are doing, so disable it */
+	SYS(fail, "ip netns exec %s sysctl -wq net.ipv4.conf.all.rp_filter=0", name);
+	SYS(fail, "ip netns exec %s sysctl -wq net.ipv4.conf.default.rp_filter=0", name);
+	/* Disable IPv6 DAD because it sometimes takes too long and fails tests */
+	SYS(fail, "ip netns exec %s sysctl -wq net.ipv6.conf.all.accept_dad=0", name);
+	SYS(fail, "ip netns exec %s sysctl -wq net.ipv6.conf.default.accept_dad=0", name);
+
+	return 0;
+fail:
+	return -1;
+}
+
+static int set_top_addr(const char *ns1, const char *ns2, const char *ns3)
+{
+	SYS(fail, "ip -n %s    a add %s/24  dev veth1", ns1, IP4_ADDR_1);
+	SYS(fail, "ip -n %s    a add %s/24  dev veth2", ns2, IP4_ADDR_2);
+	SYS(fail, "ip -n %s    a add %s/24  dev veth3", ns2, IP4_ADDR_3);
+	SYS(fail, "ip -n %s    a add %s/24  dev veth4", ns3, IP4_ADDR_4);
+	SYS(fail, "ip -n %s -6 a add %s/128 dev veth1", ns1, IP6_ADDR_1);
+	SYS(fail, "ip -n %s -6 a add %s/128 dev veth2", ns2, IP6_ADDR_2);
+	SYS(fail, "ip -n %s -6 a add %s/128 dev veth3", ns2, IP6_ADDR_3);
+	SYS(fail, "ip -n %s -6 a add %s/128 dev veth4", ns3, IP6_ADDR_4);
+
+	SYS(fail, "ip -n %s link set dev veth1 up", ns1);
+	SYS(fail, "ip -n %s link set dev veth2 up", ns2);
+	SYS(fail, "ip -n %s link set dev veth3 up", ns2);
+	SYS(fail, "ip -n %s link set dev veth4 up", ns3);
+
+	return 0;
+fail:
+	return 1;
+}
+
+static int set_bottom_addr(const char *ns1, const char *ns2, const char *ns3)
+{
+	SYS(fail, "ip -n %s    a add %s/24  dev veth5", ns1, IP4_ADDR_5);
+	SYS(fail, "ip -n %s    a add %s/24  dev veth6", ns2, IP4_ADDR_6);
+	SYS(fail, "ip -n %s    a add %s/24  dev veth7", ns2, IP4_ADDR_7);
+	SYS(fail, "ip -n %s    a add %s/24  dev veth8", ns3, IP4_ADDR_8);
+	SYS(fail, "ip -n %s -6 a add %s/128 dev veth5", ns1, IP6_ADDR_5);
+	SYS(fail, "ip -n %s -6 a add %s/128 dev veth6", ns2, IP6_ADDR_6);
+	SYS(fail, "ip -n %s -6 a add %s/128 dev veth7", ns2, IP6_ADDR_7);
+	SYS(fail, "ip -n %s -6 a add %s/128 dev veth8", ns3, IP6_ADDR_8);
+
+	SYS(fail, "ip -n %s link set dev veth5 up", ns1);
+	SYS(fail, "ip -n %s link set dev veth6 up", ns2);
+	SYS(fail, "ip -n %s link set dev veth7 up", ns2);
+	SYS(fail, "ip -n %s link set dev veth8 up", ns3);
+
+	return 0;
+fail:
+	return 1;
+}
+
+static int configure_vrf(const char *ns1, const char *ns2)
+{
+	if (!ns1 || !ns2)
+		goto fail;
+
+	SYS(fail, "ip -n %s link add red type vrf table 1001", ns1);
+	SYS(fail, "ip -n %s link set red up", ns1);
+	SYS(fail, "ip -n %s route add table 1001 unreachable default metric 8192", ns1);
+	SYS(fail, "ip -n %s -6 route add table 1001 unreachable default metric 8192", ns1);
+	SYS(fail, "ip -n %s link set veth1 vrf red", ns1);
+	SYS(fail, "ip -n %s link set veth5 vrf red", ns1);
+
+	SYS(fail, "ip -n %s link add red type vrf table 1001", ns2);
+	SYS(fail, "ip -n %s link set red up", ns2);
+	SYS(fail, "ip -n %s route add table 1001 unreachable default metric 8192", ns2);
+	SYS(fail, "ip -n %s -6 route add table 1001 unreachable default metric 8192", ns2);
+	SYS(fail, "ip -n %s link set veth2 vrf red", ns2);
+	SYS(fail, "ip -n %s link set veth3 vrf red", ns2);
+	SYS(fail, "ip -n %s link set veth6 vrf red", ns2);
+	SYS(fail, "ip -n %s link set veth7 vrf red", ns2);
+
+	return 0;
+fail:
+	return -1;
+}
+
+static int configure_ns1(const char *ns1, const char *vrf)
+{
+	struct nstoken *nstoken = NULL;
+
+	if (!ns1 || !vrf)
+		goto fail;
+
+	nstoken = open_netns(ns1);
+	if (!ASSERT_OK_PTR(nstoken, "open ns1"))
+		goto fail;
+
+	/* Top route */
+	SYS(fail, "ip    route add %s/32  dev veth1 %s", IP4_ADDR_2, vrf);
+	SYS(fail, "ip    route add default dev veth1 via %s %s", IP4_ADDR_2, vrf);
+	SYS(fail, "ip -6 route add %s/128 dev veth1 %s", IP6_ADDR_2, vrf);
+	SYS(fail, "ip -6 route add default dev veth1 via %s %s", IP6_ADDR_2, vrf);
+	/* Bottom route */
+	SYS(fail, "ip    route add %s/32  dev veth5 %s", IP4_ADDR_6, vrf);
+	SYS(fail, "ip    route add %s/32  dev veth5 via  %s %s", IP4_ADDR_7, IP4_ADDR_6, vrf);
+	SYS(fail, "ip    route add %s/32  dev veth5 via  %s %s", IP4_ADDR_8, IP4_ADDR_6, vrf);
+	SYS(fail, "ip -6 route add %s/128 dev veth5 %s", IP6_ADDR_6, vrf);
+	SYS(fail, "ip -6 route add %s/128 dev veth5 via  %s %s", IP6_ADDR_7, IP6_ADDR_6, vrf);
+	SYS(fail, "ip -6 route add %s/128 dev veth5 via  %s %s", IP6_ADDR_8, IP6_ADDR_6, vrf);
+
+	close_netns(nstoken);
+	return 0;
+fail:
+	close_netns(nstoken);
+	return -1;
+}
+
+static int configure_ns2(const char *ns2, const char *vrf)
+{
+	struct nstoken *nstoken = NULL;
+
+	if (!ns2 || !vrf)
+		goto fail;
+
+	nstoken = open_netns(ns2);
+	if (!ASSERT_OK_PTR(nstoken, "open ns2"))
+		goto fail;
+
+	SYS(fail, "ip netns exec %s sysctl -wq net.ipv4.ip_forward=1", ns2);
+	SYS(fail, "ip netns exec %s sysctl -wq net.ipv6.conf.all.forwarding=1", ns2);
+
+	/* Top route */
+	SYS(fail, "ip    route add %s/32  dev veth2 %s", IP4_ADDR_1, vrf);
+	SYS(fail, "ip    route add %s/32  dev veth3 %s", IP4_ADDR_4, vrf);
+	SYS(fail, "ip -6 route add %s/128 dev veth2 %s", IP6_ADDR_1, vrf);
+	SYS(fail, "ip -6 route add %s/128 dev veth3 %s", IP6_ADDR_4, vrf);
+	/* Bottom route */
+	SYS(fail, "ip    route add %s/32  dev veth6 %s", IP4_ADDR_5, vrf);
+	SYS(fail, "ip    route add %s/32  dev veth7 %s", IP4_ADDR_8, vrf);
+	SYS(fail, "ip -6 route add %s/128 dev veth6 %s", IP6_ADDR_5, vrf);
+	SYS(fail, "ip -6 route add %s/128 dev veth7 %s", IP6_ADDR_8, vrf);
+
+	close_netns(nstoken);
+	return 0;
+fail:
+	close_netns(nstoken);
+	return -1;
+}
+
+static int configure_ns3(const char *ns3)
+{
+	struct nstoken *nstoken = NULL;
+
+	if (!ns3)
+		goto fail;
+
+	nstoken = open_netns(ns3);
+	if (!ASSERT_OK_PTR(nstoken, "open ns3"))
+		goto fail;
+
+	/* Top route */
+	SYS(fail, "ip    route add %s/32  dev veth4", IP4_ADDR_3);
+	SYS(fail, "ip    route add %s/32  dev veth4 via  %s", IP4_ADDR_1, IP4_ADDR_3);
+	SYS(fail, "ip    route add %s/32  dev veth4 via  %s", IP4_ADDR_2, IP4_ADDR_3);
+	SYS(fail, "ip -6 route add %s/128 dev veth4", IP6_ADDR_3);
+	SYS(fail, "ip -6 route add %s/128 dev veth4 via  %s", IP6_ADDR_1, IP6_ADDR_3);
+	SYS(fail, "ip -6 route add %s/128 dev veth4 via  %s", IP6_ADDR_2, IP6_ADDR_3);
+	/* Bottom route */
+	SYS(fail, "ip    route add %s/32  dev veth8", IP4_ADDR_7);
+	SYS(fail, "ip    route add %s/32  dev veth8 via  %s", IP4_ADDR_5, IP4_ADDR_7);
+	SYS(fail, "ip    route add %s/32  dev veth8 via  %s", IP4_ADDR_6, IP4_ADDR_7);
+	SYS(fail, "ip -6 route add %s/128 dev veth8", IP6_ADDR_7);
+	SYS(fail, "ip -6 route add %s/128 dev veth8 via  %s", IP6_ADDR_5, IP6_ADDR_7);
+	SYS(fail, "ip -6 route add %s/128 dev veth8 via  %s", IP6_ADDR_6, IP6_ADDR_7);
+
+	/* Configure IPv4 GRE device */
+	SYS(fail, "ip tunnel add gre_dev mode gre remote %s local %s ttl 255",
+	    IP4_ADDR_1, IP4_ADDR_GRE);
+	SYS(fail, "ip link set gre_dev up");
+	SYS(fail, "ip a add %s dev gre_dev", IP4_ADDR_GRE);
+
+	/* Configure IPv6 GRE device */
+	SYS(fail, "ip tunnel add gre6_dev mode ip6gre remote %s local %s ttl 255",
+	    IP6_ADDR_1, IP6_ADDR_GRE);
+	SYS(fail, "ip link set gre6_dev up");
+	SYS(fail, "ip a add %s dev gre6_dev", IP6_ADDR_GRE);
+
+	close_netns(nstoken);
+	return 0;
+fail:
+	close_netns(nstoken);
+	return -1;
+}
+
+static int setup_network(char *ns1, char *ns2, char *ns3, const char *vrf)
+{
+	if (!ns1 || !ns2 || !ns3 || !vrf)
+		goto fail;
+
+	SYS(fail, "ip -n %s link add veth1 type veth peer name veth2 netns %s", ns1, ns2);
+	SYS(fail, "ip -n %s link add veth3 type veth peer name veth4 netns %s", ns2, ns3);
+	SYS(fail, "ip -n %s link add veth5 type veth peer name veth6 netns %s", ns1, ns2);
+	SYS(fail, "ip -n %s link add veth7 type veth peer name veth8 netns %s", ns2, ns3);
+
+	if (vrf[0]) {
+		if (!ASSERT_OK(configure_vrf(ns1, ns2), "configure vrf"))
+			goto fail;
+	}
+	if (!ASSERT_OK(set_top_addr(ns1, ns2, ns3), "set top addresses"))
+		goto fail;
+
+	if (!ASSERT_OK(set_bottom_addr(ns1, ns2, ns3), "set bottom addresses"))
+		goto fail;
+
+	if (!ASSERT_OK(configure_ns1(ns1, vrf), "configure ns1 routes"))
+		goto fail;
+
+	if (!ASSERT_OK(configure_ns2(ns2, vrf), "configure ns2 routes"))
+		goto fail;
+
+	if (!ASSERT_OK(configure_ns3(ns3), "configure ns3 routes"))
+		goto fail;
+
+	/* Link bottom route to the GRE tunnels */
+	SYS(fail, "ip -n %s route add %s/32 dev veth5 via %s %s",
+	    ns1, IP4_ADDR_GRE, IP4_ADDR_6, vrf);
+	SYS(fail, "ip -n %s route add %s/32 dev veth7 via %s %s",
+	    ns2, IP4_ADDR_GRE, IP4_ADDR_8, vrf);
+	SYS(fail, "ip -n %s -6 route add %s/128 dev veth5 via %s %s",
+	    ns1, IP6_ADDR_GRE, IP6_ADDR_6, vrf);
+	SYS(fail, "ip -n %s -6 route add %s/128 dev veth7 via %s %s",
+	    ns2, IP6_ADDR_GRE, IP6_ADDR_8, vrf);
+
+	return 0;
+fail:
+	return -1;
+}
+
+static int remove_routes_to_gredev(const char *ns1, const char *ns2, const char *vrf)
+{
+	SYS(fail, "ip -n %s route del %s dev veth5 %s", ns1, IP4_ADDR_GRE, vrf);
+	SYS(fail, "ip -n %s route del %s dev veth7 %s", ns2, IP4_ADDR_GRE, vrf);
+	SYS(fail, "ip -n %s -6 route del %s/128 dev veth5 %s", ns1, IP6_ADDR_GRE, vrf);
+	SYS(fail, "ip -n %s -6 route del %s/128 dev veth7 %s", ns2, IP6_ADDR_GRE, vrf);
+
+	return 0;
+fail:
+	return -1;
+}
+
+static int add_unreachable_routes_to_gredev(const char *ns1, const char *ns2, const char *vrf)
+{
+	SYS(fail, "ip -n %s route add unreachable %s/32 %s", ns1, IP4_ADDR_GRE, vrf);
+	SYS(fail, "ip -n %s route add unreachable %s/32 %s", ns2, IP4_ADDR_GRE, vrf);
+	SYS(fail, "ip -n %s -6 route add unreachable %s/128 %s", ns1, IP6_ADDR_GRE, vrf);
+	SYS(fail, "ip -n %s -6 route add unreachable %s/128 %s", ns2, IP6_ADDR_GRE, vrf);
+
+	return 0;
+fail:
+	return -1;
+}
+
+#define GSO_SIZE 5000
+#define GSO_TCP_PORT 9000
+/* This tests the fix from commit ea0371f78799 ("net: fix GSO in bpf_lwt_push_ip_encap") */
+static int test_gso_fix(const char *ns1, const char *ns3, int family)
+{
+	const char *ip_addr = family == AF_INET ? IP4_ADDR_DST : IP6_ADDR_DST;
+	char gso_packet[GSO_SIZE] = {};
+	struct nstoken *nstoken = NULL;
+	int sfd, cfd, afd;
+	ssize_t bytes;
+	int ret = -1;
+
+	if (!ns1 || !ns3)
+		return ret;
+
+	nstoken = open_netns(ns3);
+	if (!ASSERT_OK_PTR(nstoken, "open ns3"))
+		return ret;
+
+	sfd = start_server_str(family, SOCK_STREAM, ip_addr, GSO_TCP_PORT, NULL);
+	if (!ASSERT_OK_FD(sfd, "start server"))
+		goto close_netns;
+
+	close_netns(nstoken);
+
+	nstoken = open_netns(ns1);
+	if (!ASSERT_OK_PTR(nstoken, "open ns1"))
+		goto close_server;
+
+	cfd = connect_to_addr_str(family, SOCK_STREAM, ip_addr, GSO_TCP_PORT, NULL);
+	if (!ASSERT_OK_FD(cfd, "connect to server"))
+		goto close_server;
+
+	close_netns(nstoken);
+	nstoken = NULL;
+
+	afd = accept(sfd, NULL, NULL);
+	if (!ASSERT_OK_FD(afd, "accept"))
+		goto close_client;
+
+	/* Send a packet larger than MTU */
+	bytes = send(cfd, gso_packet, GSO_SIZE, 0);
+	if (!ASSERT_EQ(bytes, GSO_SIZE, "send packet"))
+		goto close_accept;
+
+	/* Verify we received all expected bytes */
+	bytes = read(afd, gso_packet, GSO_SIZE);
+	if (!ASSERT_EQ(bytes, GSO_SIZE, "receive packet"))
+		goto close_accept;
+
+	ret = 0;
+
+close_accept:
+	close(afd);
+close_client:
+	close(cfd);
+close_server:
+	close(sfd);
+close_netns:
+	close_netns(nstoken);
+
+	return ret;
+}
+
+static int check_ping_ok(const char *ns1)
+{
+	SYS(fail, "ip netns exec %s ping -c 1 -W1 -I veth1 %s > /dev/null", ns1, IP4_ADDR_DST);
+	SYS(fail, "ip netns exec %s ping6 -c 1 -W1 -I veth1 %s > /dev/null", ns1, IP6_ADDR_DST);
+	return 0;
+fail:
+	return -1;
+}
+
+static int check_ping_fails(const char *ns1)
+{
+	int ret;
+
+	ret = SYS_NOFAIL("ip netns exec %s ping -c 1 -W1 -I veth1 %s", ns1, IP4_ADDR_DST);
+	if (!ret)
+		return -1;
+
+	ret = SYS_NOFAIL("ip netns exec %s ping6 -c 1 -W1 -I veth1 %s", ns1, IP6_ADDR_DST);
+	if (!ret)
+		return -1;
+
+	return 0;
+}
+
+#define EGRESS true
+#define INGRESS false
+#define IPV4_ENCAP true
+#define IPV6_ENCAP false
+static void lwt_ip_encap(bool ipv4_encap, bool egress, const char *vrf)
+{
+	char ns1[NETNS_NAME_SIZE] = NETNS_BASE "-1-";
+	char ns2[NETNS_NAME_SIZE] = NETNS_BASE "-2-";
+	char ns3[NETNS_NAME_SIZE] = NETNS_BASE "-3-";
+	char *sec = ipv4_encap ?  "encap_gre" : "encap_gre6";
+
+	if (!vrf)
+		return;
+
+	if (!ASSERT_OK(create_ns(ns1, NETNS_NAME_SIZE), "create ns1"))
+		goto out;
+	if (!ASSERT_OK(create_ns(ns2, NETNS_NAME_SIZE), "create ns2"))
+		goto out;
+	if (!ASSERT_OK(create_ns(ns3, NETNS_NAME_SIZE), "create ns3"))
+		goto out;
+
+	if (!ASSERT_OK(setup_network(ns1, ns2, ns3, vrf), "setup network"))
+		goto out;
+
+	/* By default, pings work */
+	if (!ASSERT_OK(check_ping_ok(ns1), "ping OK"))
+		goto out;
+
+	/* Remove NS2->DST routes, ping fails */
+	SYS(out, "ip -n %s    route del %s/32  dev veth3 %s", ns2, IP4_ADDR_DST, vrf);
+	SYS(out, "ip -n %s -6 route del %s/128 dev veth3 %s", ns2, IP6_ADDR_DST, vrf);
+	if (!ASSERT_OK(check_ping_fails(ns1), "ping expected fail"))
+		goto out;
+
+	/* Install replacement routes (LWT/eBPF), pings succeed */
+	if (egress) {
+		SYS(out, "ip -n %s route add %s encap bpf xmit obj %s sec %s dev veth1 %s",
+		    ns1, IP4_ADDR_DST, BPF_FILE, sec, vrf);
+		SYS(out, "ip -n %s -6 route add %s encap bpf xmit obj %s sec %s dev veth1 %s",
+		    ns1, IP6_ADDR_DST, BPF_FILE, sec, vrf);
+	} else {
+		SYS(out, "ip -n %s route add %s encap bpf in obj %s sec %s dev veth2 %s",
+		    ns2, IP4_ADDR_DST, BPF_FILE, sec, vrf);
+		SYS(out, "ip -n %s -6 route add %s encap bpf in obj %s sec %s dev veth2 %s",
+		    ns2, IP6_ADDR_DST, BPF_FILE, sec, vrf);
+	}
+
+	if (!ASSERT_OK(check_ping_ok(ns1), "ping OK"))
+		goto out;
+
+	/* Skip GSO tests with VRF: VRF routing needs properly assigned
+	 * source IP/device, which is easy to do with ping but hard with TCP.
+	 */
+	if (egress && !vrf[0]) {
+		if (!ASSERT_OK(test_gso_fix(ns1, ns3, AF_INET), "test GSO"))
+			goto out;
+	}
+
+	/* Negative test: remove routes to GRE devices: ping fails */
+	if (!ASSERT_OK(remove_routes_to_gredev(ns1, ns2, vrf), "remove routes to gredev"))
+		goto out;
+	if (!ASSERT_OK(check_ping_fails(ns1), "ping expected fail"))
+		goto out;
+
+	/* Another negative test */
+	if (!ASSERT_OK(add_unreachable_routes_to_gredev(ns1, ns2, vrf),
+		       "add unreachable routes"))
+		goto out;
+	ASSERT_OK(check_ping_fails(ns1), "ping expected fail");
+
+out:
+	SYS_NOFAIL("ip netns del %s", ns1);
+	SYS_NOFAIL("ip netns del %s", ns2);
+	SYS_NOFAIL("ip netns del %s", ns3);
+}
+
+void test_lwt_ip_encap_vrf_ipv6(void)
+{
+	if (test__start_subtest("egress"))
+		lwt_ip_encap(IPV6_ENCAP, EGRESS, "vrf red");
+
+	if (test__start_subtest("ingress"))
+		lwt_ip_encap(IPV6_ENCAP, INGRESS, "vrf red");
+}
+
+void test_lwt_ip_encap_vrf_ipv4(void)
+{
+	if (test__start_subtest("egress"))
+		lwt_ip_encap(IPV4_ENCAP, EGRESS, "vrf red");
+
+	if (test__start_subtest("ingress"))
+		lwt_ip_encap(IPV4_ENCAP, INGRESS, "vrf red");
+}
+
+void test_lwt_ip_encap_ipv6(void)
+{
+	if (test__start_subtest("egress"))
+		lwt_ip_encap(IPV6_ENCAP, EGRESS, "");
+
+	if (test__start_subtest("ingress"))
+		lwt_ip_encap(IPV6_ENCAP, INGRESS, "");
+}
+
+void test_lwt_ip_encap_ipv4(void)
+{
+	if (test__start_subtest("egress"))
+		lwt_ip_encap(IPV4_ENCAP, EGRESS, "");
+
+	if (test__start_subtest("ingress"))
+		lwt_ip_encap(IPV4_ENCAP, INGRESS, "");
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c b/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c
new file mode 100644
index 000000000000..b6e8d822e8e9
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c
@@ -0,0 +1,331 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+
+/*
+ * Test suite of lwt_xmit BPF programs that redirect packets
+ *   The file tests focus not only if these programs work as expected normally,
+ *   but also if they can handle abnormal situations gracefully.
+ *
+ * WARNING
+ * -------
+ *  This test suite may crash the kernel, thus should be run in a VM.
+ *
+ * Setup:
+ * ---------
+ *  All tests are performed in a single netns. Two lwt encap routes are setup for
+ *  each subtest:
+ *
+ *    ip route add 10.0.0.0/24 encap bpf xmit <obj> sec "<ingress_sec>" dev link_err
+ *    ip route add 20.0.0.0/24 encap bpf xmit <obj> sec "<egress_sec>" dev link_err
+ *
+ *  Here <obj> is statically defined to test_lwt_redirect.bpf.o, and each section
+ *  of this object holds a program entry to test. The BPF object is built from
+ *  progs/test_lwt_redirect.c. We didn't use generated BPF skeleton since the
+ *  attachment for lwt programs are not supported by libbpf yet.
+ *
+ *  For testing, ping commands are run in the test netns:
+ *
+ *    ping 10.0.0.<ifindex> -c 1 -w 1 -s 100
+ *    ping 20.0.0.<ifindex> -c 1 -w 1 -s 100
+ *
+ * Scenarios:
+ * --------------------------------
+ *  1. Redirect to a running tap/tun device
+ *  2. Redirect to a down tap/tun device
+ *  3. Redirect to a vlan device with lower layer down
+ *
+ *  Case 1, ping packets should be received by packet socket on target device
+ *  when redirected to ingress, and by tun/tap fd when redirected to egress.
+ *
+ *  Case 2,3 are considered successful as long as they do not crash the kernel
+ *  as a regression.
+ *
+ *  Case 1,2 use tap device to test redirect to device that requires MAC
+ *  header, and tun device to test the case with no MAC header added.
+ */
+#include <sys/socket.h>
+#include <net/if.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/if_tun.h>
+#include <arpa/inet.h>
+#include <unistd.h>
+#include <errno.h>
+#include <stdbool.h>
+#include <stdlib.h>
+
+#define NETNS "ns_lwt_redirect"
+#include "lwt_helpers.h"
+#include "test_progs.h"
+#include "network_helpers.h"
+
+#define BPF_OBJECT            "test_lwt_redirect.bpf.o"
+#define INGRESS_SEC(need_mac) ((need_mac) ? "redir_ingress" : "redir_ingress_nomac")
+#define EGRESS_SEC(need_mac)  ((need_mac) ? "redir_egress" : "redir_egress_nomac")
+#define LOCAL_SRC             "10.0.0.1"
+#define CIDR_TO_INGRESS       "10.0.0.0/24"
+#define CIDR_TO_EGRESS        "20.0.0.0/24"
+
+/* ping to redirect toward given dev, with last byte of dest IP being the target
+ * device index.
+ *
+ * Note: ping command inside BPF-CI is busybox version, so it does not have certain
+ * function, such like -m option to set packet mark.
+ */
+static void ping_dev(const char *dev, bool is_ingress)
+{
+	int link_index = if_nametoindex(dev);
+	char ip[256];
+
+	if (!ASSERT_GE(link_index, 0, "if_nametoindex"))
+		return;
+
+	if (is_ingress)
+		snprintf(ip, sizeof(ip), "10.0.0.%d", link_index);
+	else
+		snprintf(ip, sizeof(ip), "20.0.0.%d", link_index);
+
+	/* We won't get a reply. Don't fail here */
+	SYS_NOFAIL("ping %s -c1 -W1 -s %d",
+		   ip, ICMP_PAYLOAD_SIZE);
+}
+
+static int new_packet_sock(const char *ifname)
+{
+	int err = 0;
+	int ignore_outgoing = 1;
+	int ifindex = -1;
+	int s = -1;
+
+	s = socket(AF_PACKET, SOCK_RAW, 0);
+	if (!ASSERT_GE(s, 0, "socket(AF_PACKET)"))
+		return -1;
+
+	ifindex = if_nametoindex(ifname);
+	if (!ASSERT_GE(ifindex, 0, "if_nametoindex")) {
+		close(s);
+		return -1;
+	}
+
+	struct sockaddr_ll addr = {
+		.sll_family = AF_PACKET,
+		.sll_protocol = htons(ETH_P_IP),
+		.sll_ifindex = ifindex,
+	};
+
+	err = bind(s, (struct sockaddr *)&addr, sizeof(addr));
+	if (!ASSERT_OK(err, "bind(AF_PACKET)")) {
+		close(s);
+		return -1;
+	}
+
+	/* Use packet socket to capture only the ingress, so we can distinguish
+	 * the case where a regression that actually redirects the packet to
+	 * the egress.
+	 */
+	err = setsockopt(s, SOL_PACKET, PACKET_IGNORE_OUTGOING,
+			 &ignore_outgoing, sizeof(ignore_outgoing));
+	if (!ASSERT_OK(err, "setsockopt(PACKET_IGNORE_OUTGOING)")) {
+		close(s);
+		return -1;
+	}
+
+	err = fcntl(s, F_SETFL, O_NONBLOCK);
+	if (!ASSERT_OK(err, "fcntl(O_NONBLOCK)")) {
+		close(s);
+		return -1;
+	}
+
+	return s;
+}
+
+static int expect_icmp(char *buf, ssize_t len)
+{
+	struct ethhdr *eth = (struct ethhdr *)buf;
+
+	if (len < (ssize_t)sizeof(*eth))
+		return -1;
+
+	if (eth->h_proto == htons(ETH_P_IP))
+		return __expect_icmp_ipv4((char *)(eth + 1), len - sizeof(*eth));
+
+	return -1;
+}
+
+static int expect_icmp_nomac(char *buf, ssize_t len)
+{
+	return __expect_icmp_ipv4(buf, len);
+}
+
+static void send_and_capture_test_packets(const char *test_name, int tap_fd,
+					  const char *target_dev, bool need_mac)
+{
+	int psock = -1;
+	struct timeval timeo = {
+		.tv_sec = 0,
+		.tv_usec = 250000,
+	};
+	int ret = -1;
+
+	filter_t filter = need_mac ? expect_icmp : expect_icmp_nomac;
+
+	ping_dev(target_dev, false);
+
+	ret = wait_for_packet(tap_fd, filter, &timeo);
+	if (!ASSERT_EQ(ret, 1, "wait_for_epacket")) {
+		log_err("%s egress test fails", test_name);
+		goto out;
+	}
+
+	psock = new_packet_sock(target_dev);
+	ping_dev(target_dev, true);
+
+	ret = wait_for_packet(psock, filter, &timeo);
+	if (!ASSERT_EQ(ret, 1, "wait_for_ipacket")) {
+		log_err("%s ingress test fails", test_name);
+		goto out;
+	}
+
+out:
+	if (psock >= 0)
+		close(psock);
+}
+
+static int setup_redirect_target(const char *target_dev, bool need_mac)
+{
+	int target_index = -1;
+	int tap_fd = -1;
+
+	tap_fd = open_tuntap(target_dev, need_mac);
+	if (!ASSERT_GE(tap_fd, 0, "open_tuntap"))
+		goto fail;
+
+	target_index = if_nametoindex(target_dev);
+	if (!ASSERT_GE(target_index, 0, "if_nametoindex"))
+		goto fail;
+
+	SYS(fail, "sysctl -w net.ipv6.conf.all.disable_ipv6=1");
+	SYS(fail, "ip link add link_err type dummy");
+	SYS(fail, "ip link set lo up");
+	SYS(fail, "ip addr add dev lo " LOCAL_SRC "/32");
+	SYS(fail, "ip link set link_err up");
+	SYS(fail, "ip link set %s up", target_dev);
+
+	SYS(fail, "ip route add %s dev link_err encap bpf xmit obj %s sec %s",
+	    CIDR_TO_INGRESS, BPF_OBJECT, INGRESS_SEC(need_mac));
+
+	SYS(fail, "ip route add %s dev link_err encap bpf xmit obj %s sec %s",
+	    CIDR_TO_EGRESS, BPF_OBJECT, EGRESS_SEC(need_mac));
+
+	return tap_fd;
+
+fail:
+	if (tap_fd >= 0)
+		close(tap_fd);
+	return -1;
+}
+
+static void test_lwt_redirect_normal(void)
+{
+	const char *target_dev = "tap0";
+	int tap_fd = -1;
+	bool need_mac = true;
+
+	tap_fd = setup_redirect_target(target_dev, need_mac);
+	if (!ASSERT_GE(tap_fd, 0, "setup_redirect_target"))
+		return;
+
+	send_and_capture_test_packets(__func__, tap_fd, target_dev, need_mac);
+	close(tap_fd);
+}
+
+static void test_lwt_redirect_normal_nomac(void)
+{
+	const char *target_dev = "tun0";
+	int tap_fd = -1;
+	bool need_mac = false;
+
+	tap_fd = setup_redirect_target(target_dev, need_mac);
+	if (!ASSERT_GE(tap_fd, 0, "setup_redirect_target"))
+		return;
+
+	send_and_capture_test_packets(__func__, tap_fd, target_dev, need_mac);
+	close(tap_fd);
+}
+
+/* This test aims to prevent regression of future. As long as the kernel does
+ * not panic, it is considered as success.
+ */
+static void __test_lwt_redirect_dev_down(bool need_mac)
+{
+	const char *target_dev = "tap0";
+	int tap_fd = -1;
+
+	tap_fd = setup_redirect_target(target_dev, need_mac);
+	if (!ASSERT_GE(tap_fd, 0, "setup_redirect_target"))
+		return;
+
+	SYS(out, "ip link set %s down", target_dev);
+	ping_dev(target_dev, true);
+	ping_dev(target_dev, false);
+
+out:
+	close(tap_fd);
+}
+
+static void test_lwt_redirect_dev_down(void)
+{
+	__test_lwt_redirect_dev_down(true);
+}
+
+static void test_lwt_redirect_dev_down_nomac(void)
+{
+	__test_lwt_redirect_dev_down(false);
+}
+
+/* This test aims to prevent regression of future. As long as the kernel does
+ * not panic, it is considered as success.
+ */
+static void test_lwt_redirect_dev_carrier_down(void)
+{
+	const char *lower_dev = "tap0";
+	const char *vlan_dev = "vlan100";
+	int tap_fd = -1;
+
+	tap_fd = setup_redirect_target(lower_dev, true);
+	if (!ASSERT_GE(tap_fd, 0, "setup_redirect_target"))
+		return;
+
+	SYS(out, "ip link add vlan100 link %s type vlan id 100", lower_dev);
+	SYS(out, "ip link set %s up", vlan_dev);
+	SYS(out, "ip link set %s down", lower_dev);
+	ping_dev(vlan_dev, true);
+	ping_dev(vlan_dev, false);
+
+out:
+	close(tap_fd);
+}
+
+static void *test_lwt_redirect_run(void *arg)
+{
+	netns_delete();
+	RUN_TEST(lwt_redirect_normal);
+	RUN_TEST(lwt_redirect_normal_nomac);
+	RUN_TEST(lwt_redirect_dev_down);
+	RUN_TEST(lwt_redirect_dev_down_nomac);
+	RUN_TEST(lwt_redirect_dev_carrier_down);
+	return NULL;
+}
+
+void test_lwt_redirect(void)
+{
+	pthread_t test_thread;
+	int err;
+
+	/* Run the tests in their own thread to isolate the namespace changes
+	 * so they do not affect the environment of other tests.
+	 * (specifically needed because of unshare(CLONE_NEWNS) in open_netns())
+	 */
+	err = pthread_create(&test_thread, NULL, &test_lwt_redirect_run, NULL);
+	if (ASSERT_OK(err, "pthread_create"))
+		ASSERT_OK(pthread_join(test_thread, NULL), "pthread_join");
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c b/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c
new file mode 100644
index 000000000000..6c50c0f63f43
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c
@@ -0,0 +1,264 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+
+/*
+ * Test suite of lwt BPF programs that reroutes packets
+ *   The file tests focus not only if these programs work as expected normally,
+ *   but also if they can handle abnormal situations gracefully. This test
+ *   suite currently only covers lwt_xmit hook. lwt_in tests have not been
+ *   implemented.
+ *
+ * WARNING
+ * -------
+ *  This test suite can crash the kernel, thus should be run in a VM.
+ *
+ * Setup:
+ * ---------
+ *  all tests are performed in a single netns. A lwt encap route is setup for
+ *  each subtest:
+ *
+ *    ip route add 10.0.0.0/24 encap bpf xmit <obj> sec "<section_N>" dev link_err
+ *
+ *  Here <obj> is statically defined to test_lwt_reroute.bpf.o, and it contains
+ *  a single test program entry. This program sets packet mark by last byte of
+ *  the IPv4 daddr. For example, a packet going to 1.2.3.4 will receive a skb
+ *  mark 4. A packet will only be marked once, and IP x.x.x.0 will be skipped
+ *  to avoid route loop. We didn't use generated BPF skeleton since the
+ *  attachment for lwt programs are not supported by libbpf yet.
+ *
+ *  The test program will bring up a tun device, and sets up the following
+ *  routes:
+ *
+ *    ip rule add pref 100 from all fwmark <tun_index> lookup 100
+ *    ip route add table 100 default dev tun0
+ *
+ *  For normal testing, a ping command is running in the test netns:
+ *
+ *    ping 10.0.0.<tun_index> -c 1 -w 1 -s 100
+ *
+ *  For abnormal testing, fq is used as the qdisc of the tun device. Then a UDP
+ *  socket will try to overflow the fq queue and trigger qdisc drop error.
+ *
+ * Scenarios:
+ * --------------------------------
+ *  1. Reroute to a running tun device
+ *  2. Reroute to a device where qdisc drop
+ *
+ *  For case 1, ping packets should be received by the tun device.
+ *
+ *  For case 2, force UDP packets to overflow fq limit. As long as kernel
+ *  is not crashed, it is considered successful.
+ */
+#define NETNS "ns_lwt_reroute"
+#include <netinet/in.h>
+#include "lwt_helpers.h"
+#include "network_helpers.h"
+#include <linux/net_tstamp.h>
+
+#define BPF_OBJECT            "test_lwt_reroute.bpf.o"
+#define LOCAL_SRC             "10.0.0.1"
+#define TEST_CIDR             "10.0.0.0/24"
+#define XMIT_HOOK             "xmit"
+#define XMIT_SECTION          "lwt_xmit"
+#define NSEC_PER_SEC          1000000000ULL
+
+/* send a ping to be rerouted to the target device */
+static void ping_once(const char *ip)
+{
+	/* We won't get a reply. Don't fail here */
+	SYS_NOFAIL("ping %s -c1 -W1 -s %d",
+		   ip, ICMP_PAYLOAD_SIZE);
+}
+
+/* Send snd_target UDP packets to overflow the fq queue and trigger qdisc drop
+ * error. This is done via TX tstamp to force buffering delayed packets.
+ */
+static int overflow_fq(int snd_target, const char *target_ip)
+{
+	struct sockaddr_in addr = {
+		.sin_family = AF_INET,
+		.sin_port = htons(1234),
+	};
+
+	char data_buf[8]; /* only #pkts matter, so use a random small buffer */
+	char control_buf[CMSG_SPACE(sizeof(uint64_t))];
+	struct iovec iov = {
+		.iov_base = data_buf,
+		.iov_len = sizeof(data_buf),
+	};
+	int err = -1;
+	int s = -1;
+	struct sock_txtime txtime_on = {
+		.clockid = CLOCK_MONOTONIC,
+		.flags = 0,
+	};
+	struct msghdr msg = {
+		.msg_name = &addr,
+		.msg_namelen = sizeof(addr),
+		.msg_control = control_buf,
+		.msg_controllen = sizeof(control_buf),
+		.msg_iovlen = 1,
+		.msg_iov = &iov,
+	};
+	struct cmsghdr *cmsg = CMSG_FIRSTHDR(&msg);
+
+	memset(data_buf, 0, sizeof(data_buf));
+
+	s = socket(AF_INET, SOCK_DGRAM, 0);
+	if (!ASSERT_GE(s, 0, "socket"))
+		goto out;
+
+	err = setsockopt(s, SOL_SOCKET, SO_TXTIME, &txtime_on, sizeof(txtime_on));
+	if (!ASSERT_OK(err, "setsockopt(SO_TXTIME)"))
+		goto out;
+
+	err = inet_pton(AF_INET, target_ip, &addr.sin_addr);
+	if (!ASSERT_EQ(err, 1, "inet_pton"))
+		goto out;
+
+	while (snd_target > 0) {
+		struct timespec now;
+
+		memset(control_buf, 0, sizeof(control_buf));
+		cmsg->cmsg_type = SCM_TXTIME;
+		cmsg->cmsg_level = SOL_SOCKET;
+		cmsg->cmsg_len = CMSG_LEN(sizeof(uint64_t));
+
+		err = clock_gettime(CLOCK_MONOTONIC, &now);
+		if (!ASSERT_OK(err, "clock_gettime(CLOCK_MONOTONIC)")) {
+			err = -1;
+			goto out;
+		}
+
+		*(uint64_t *)CMSG_DATA(cmsg) = (now.tv_nsec + 1) * NSEC_PER_SEC +
+					       now.tv_nsec;
+
+		/* we will intentionally send more than fq limit, so ignore
+		 * the error here.
+		 */
+		sendmsg(s, &msg, MSG_NOSIGNAL);
+		snd_target--;
+	}
+
+	/* no kernel crash so far is considered success */
+	err = 0;
+
+out:
+	if (s >= 0)
+		close(s);
+
+	return err;
+}
+
+static int setup(const char *tun_dev)
+{
+	int target_index = -1;
+	int tap_fd = -1;
+
+	tap_fd = open_tuntap(tun_dev, false);
+	if (!ASSERT_GE(tap_fd, 0, "open_tun"))
+		return -1;
+
+	target_index = if_nametoindex(tun_dev);
+	if (!ASSERT_GE(target_index, 0, "if_nametoindex"))
+		return -1;
+
+	SYS(fail, "ip link add link_err type dummy");
+	SYS(fail, "ip link set lo up");
+	SYS(fail, "ip addr add dev lo " LOCAL_SRC "/32");
+	SYS(fail, "ip link set link_err up");
+	SYS(fail, "ip link set %s up", tun_dev);
+
+	SYS(fail, "ip route add %s dev link_err encap bpf xmit obj %s sec lwt_xmit",
+	    TEST_CIDR, BPF_OBJECT);
+
+	SYS(fail, "ip rule add pref 100 from all fwmark %d lookup 100",
+	    target_index);
+	SYS(fail, "ip route add t 100 default dev %s", tun_dev);
+
+	return tap_fd;
+
+fail:
+	if (tap_fd >= 0)
+		close(tap_fd);
+	return -1;
+}
+
+static void test_lwt_reroute_normal_xmit(void)
+{
+	const char *tun_dev = "tun0";
+	int tun_fd = -1;
+	int ifindex = -1;
+	char ip[256];
+	struct timeval timeo = {
+		.tv_sec = 0,
+		.tv_usec = 250000,
+	};
+
+	tun_fd = setup(tun_dev);
+	if (!ASSERT_GE(tun_fd, 0, "setup_reroute"))
+		return;
+
+	ifindex = if_nametoindex(tun_dev);
+	if (!ASSERT_GE(ifindex, 0, "if_nametoindex"))
+		return;
+
+	snprintf(ip, 256, "10.0.0.%d", ifindex);
+
+	/* ping packets should be received by the tun device */
+	ping_once(ip);
+
+	if (!ASSERT_EQ(wait_for_packet(tun_fd, __expect_icmp_ipv4, &timeo), 1,
+		       "wait_for_packet"))
+		log_err("%s xmit", __func__);
+}
+
+/*
+ * Test the failure case when the skb is dropped at the qdisc. This is a
+ * regression prevention at the xmit hook only.
+ */
+static void test_lwt_reroute_qdisc_dropped(void)
+{
+	const char *tun_dev = "tun0";
+	int tun_fd = -1;
+	int ifindex = -1;
+	char ip[256];
+
+	tun_fd = setup(tun_dev);
+	if (!ASSERT_GE(tun_fd, 0, "setup_reroute"))
+		goto fail;
+
+	SYS(fail, "tc qdisc replace dev %s root fq limit 5 flow_limit 5", tun_dev);
+
+	ifindex = if_nametoindex(tun_dev);
+	if (!ASSERT_GE(ifindex, 0, "if_nametoindex"))
+		return;
+
+	snprintf(ip, 256, "10.0.0.%d", ifindex);
+	ASSERT_EQ(overflow_fq(10, ip), 0, "overflow_fq");
+
+fail:
+	if (tun_fd >= 0)
+		close(tun_fd);
+}
+
+static void *test_lwt_reroute_run(void *arg)
+{
+	netns_delete();
+	RUN_TEST(lwt_reroute_normal_xmit);
+	RUN_TEST(lwt_reroute_qdisc_dropped);
+	return NULL;
+}
+
+void test_lwt_reroute(void)
+{
+	pthread_t test_thread;
+	int err;
+
+	/* Run the tests in their own thread to isolate the namespace changes
+	 * so they do not affect the environment of other tests.
+	 * (specifically needed because of unshare(CLONE_NEWNS) in open_netns())
+	 */
+	err = pthread_create(&test_thread, NULL, &test_lwt_reroute_run, NULL);
+	if (ASSERT_OK(err, "pthread_create"))
+		ASSERT_OK(pthread_join(test_thread, NULL), "pthread_join");
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c b/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c
new file mode 100644
index 000000000000..3bc730b7c7fa
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c
@@ -0,0 +1,176 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/* Connects 6 network namespaces through veths.
+ * Each NS may have different IPv6 global scope addresses :
+ *
+ *          NS1            NS2             NS3              NS4               NS5             NS6
+ *      lo  veth1 <-> veth2 veth3 <-> veth4 veth5 <-> veth6 lo veth7 <-> veth8 veth9 <-> veth10 lo
+ * fb00 ::1  ::12      ::21  ::34      ::43  ::56      ::65     ::78      ::87  ::910     ::109  ::6
+ * fd00                                                                                          ::4
+ * fc42                                                     ::1
+ *
+ * All IPv6 packets going to fb00::/16 through NS2 will be encapsulated in a
+ * IPv6 header with a Segment Routing Header, with segments :
+ *	fd00::1 -> fd00::2 -> fd00::3 -> fd00::4
+ *
+ * 3 fd00::/16 IPv6 addresses are binded to seg6local End.BPF actions :
+ * - fd00::1 : add a TLV, change the flags and apply a End.X action to fc42::1
+ * - fd00::2 : remove the TLV, change the flags, add a tag
+ * - fd00::3 : apply an End.T action to fd00::4, through routing table 117
+ *
+ * fd00::4 is a simple Segment Routing node decapsulating the inner IPv6 packet.
+ * Each End.BPF action will validate the operations applied on the SRH by the
+ * previous BPF program in the chain, otherwise the packet is dropped.
+ *
+ * An UDP datagram is sent from fb00::1 to fb00::6. The test succeeds if this
+ * datagram can be read on NS6 when binding to fb00::6.
+ */
+
+#include "network_helpers.h"
+#include "test_progs.h"
+
+#define NETNS_BASE "lwt-seg6local-"
+#define BPF_FILE "test_lwt_seg6local.bpf.o"
+
+static void cleanup(void)
+{
+	int ns;
+
+	for (ns = 1; ns < 7; ns++)
+		SYS_NOFAIL("ip netns del %s%d", NETNS_BASE, ns);
+}
+
+static int setup(void)
+{
+	int ns;
+
+	for (ns = 1; ns < 7; ns++)
+		SYS(fail, "ip netns add %s%d", NETNS_BASE, ns);
+
+	SYS(fail, "ip -n %s6 link set dev lo up", NETNS_BASE);
+
+	for (ns = 1; ns < 6; ns++) {
+		int local_id = ns * 2 - 1;
+		int peer_id = ns * 2;
+		int next_ns = ns + 1;
+
+		SYS(fail, "ip -n %s%d link add veth%d type veth peer name veth%d netns %s%d",
+		    NETNS_BASE, ns, local_id, peer_id, NETNS_BASE, next_ns);
+
+		SYS(fail, "ip -n %s%d link set dev veth%d up", NETNS_BASE, ns, local_id);
+		SYS(fail, "ip -n %s%d link set dev veth%d up", NETNS_BASE, next_ns, peer_id);
+
+		/* All link scope addresses to veths */
+		SYS(fail, "ip -n %s%d -6 addr add fb00::%d%d/16 dev veth%d scope link",
+		    NETNS_BASE, ns, local_id, peer_id, local_id);
+		SYS(fail, "ip -n %s%d -6 addr add fb00::%d%d/16 dev veth%d scope link",
+		    NETNS_BASE, next_ns, peer_id, local_id, peer_id);
+	}
+
+
+	SYS(fail, "ip -n %s5 -6 route add fb00::109 table 117 dev veth9 scope link", NETNS_BASE);
+
+	SYS(fail, "ip -n %s1 -6 addr add fb00::1/16 dev lo", NETNS_BASE);
+	SYS(fail, "ip -n %s1 -6 route add fb00::6 dev veth1 via fb00::21", NETNS_BASE);
+
+	SYS(fail, "ip -n %s2 -6 route add fb00::6 encap bpf in obj %s sec encap_srh dev veth2",
+	    NETNS_BASE, BPF_FILE);
+	SYS(fail, "ip -n %s2 -6 route add fd00::1 dev veth3 via fb00::43 scope link", NETNS_BASE);
+
+	SYS(fail, "ip -n %s3 -6 route add fc42::1 dev veth5 via fb00::65", NETNS_BASE);
+	SYS(fail,
+	    "ip -n %s3 -6 route add fd00::1 encap seg6local action End.BPF endpoint obj %s sec add_egr_x dev veth4",
+	    NETNS_BASE, BPF_FILE);
+
+	SYS(fail,
+	    "ip -n %s4 -6 route add fd00::2 encap seg6local action End.BPF endpoint obj %s sec pop_egr dev veth6",
+	    NETNS_BASE, BPF_FILE);
+	SYS(fail, "ip -n %s4 -6 addr add fc42::1 dev lo", NETNS_BASE);
+	SYS(fail, "ip -n %s4 -6 route add fd00::3 dev veth7 via fb00::87", NETNS_BASE);
+
+	SYS(fail, "ip -n %s5 -6 route add fd00::4 table 117 dev veth9 via fb00::109", NETNS_BASE);
+	SYS(fail,
+	    "ip -n %s5 -6 route add fd00::3 encap seg6local action End.BPF endpoint obj %s sec inspect_t dev veth8",
+	    NETNS_BASE, BPF_FILE);
+
+	SYS(fail, "ip -n %s6 -6 addr add fb00::6/16 dev lo", NETNS_BASE);
+	SYS(fail, "ip -n %s6 -6 addr add fd00::4/16 dev lo", NETNS_BASE);
+
+	for (ns = 1; ns < 6; ns++)
+		SYS(fail, "ip netns exec %s%d sysctl -wq net.ipv6.conf.all.forwarding=1",
+		    NETNS_BASE, ns);
+
+	SYS(fail, "ip netns exec %s6 sysctl -wq net.ipv6.conf.all.seg6_enabled=1", NETNS_BASE);
+	SYS(fail, "ip netns exec %s6 sysctl -wq net.ipv6.conf.lo.seg6_enabled=1", NETNS_BASE);
+	SYS(fail, "ip netns exec %s6 sysctl -wq net.ipv6.conf.veth10.seg6_enabled=1", NETNS_BASE);
+
+	return 0;
+fail:
+	return -1;
+}
+
+#define SERVER_PORT 7330
+#define CLIENT_PORT 2121
+void test_lwt_seg6local(void)
+{
+	struct sockaddr_in6 server_addr = {};
+	const char *ns1 = NETNS_BASE "1";
+	const char *ns6 = NETNS_BASE "6";
+	struct nstoken *nstoken = NULL;
+	const char *foobar = "foobar";
+	ssize_t bytes;
+	int sfd, cfd;
+	char buf[7];
+
+	if (!ASSERT_OK(setup(), "setup"))
+		goto out;
+
+	nstoken = open_netns(ns6);
+	if (!ASSERT_OK_PTR(nstoken, "open ns6"))
+		goto out;
+
+	sfd = start_server_str(AF_INET6, SOCK_DGRAM, "fb00::6", SERVER_PORT, NULL);
+	if (!ASSERT_OK_FD(sfd, "start server"))
+		goto close_netns;
+
+	close_netns(nstoken);
+
+	nstoken = open_netns(ns1);
+	if (!ASSERT_OK_PTR(nstoken, "open ns1"))
+		goto close_server;
+
+	cfd = start_server_str(AF_INET6, SOCK_DGRAM, "fb00::1", CLIENT_PORT, NULL);
+	if (!ASSERT_OK_FD(cfd, "start client"))
+		goto close_server;
+
+	close_netns(nstoken);
+	nstoken = NULL;
+
+	/* Send a packet larger than MTU */
+	server_addr.sin6_family = AF_INET6;
+	server_addr.sin6_port = htons(SERVER_PORT);
+	if (!ASSERT_EQ(inet_pton(AF_INET6, "fb00::6", &server_addr.sin6_addr), 1,
+		       "build target addr"))
+		goto close_client;
+
+	bytes = sendto(cfd, foobar, sizeof(foobar), 0,
+		       (struct sockaddr *)&server_addr, sizeof(server_addr));
+	if (!ASSERT_EQ(bytes, sizeof(foobar), "send packet"))
+		goto close_client;
+
+	/* Verify we received all expected bytes */
+	bytes = read(sfd, buf, sizeof(buf));
+	if (!ASSERT_EQ(bytes, sizeof(buf), "receive packet"))
+		goto close_client;
+	ASSERT_STREQ(buf, foobar, "check udp packet");
+
+close_client:
+	close(cfd);
+close_server:
+	close(sfd);
+close_netns:
+	close_netns(nstoken);
+
+out:
+	cleanup();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/map_btf.c b/tools/testing/selftests/bpf/prog_tests/map_btf.c
new file mode 100644
index 000000000000..2c4ef6037573
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/map_btf.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <test_progs.h>
+
+#include "normal_map_btf.skel.h"
+#include "map_in_map_btf.skel.h"
+
+static void do_test_normal_map_btf(void)
+{
+	struct normal_map_btf *skel;
+	int i, err, new_fd = -1;
+	int map_fd_arr[64];
+
+	skel = normal_map_btf__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_load"))
+		return;
+
+	err = normal_map_btf__attach(skel);
+	if (!ASSERT_OK(err, "attach"))
+		goto out;
+
+	skel->bss->pid = getpid();
+	usleep(1);
+	ASSERT_TRUE(skel->bss->done, "done");
+
+	/* Use percpu_array to slow bpf_map_free_deferred() down.
+	 * The memory allocation may fail, so doesn't check the returned fd.
+	 */
+	for (i = 0; i < ARRAY_SIZE(map_fd_arr); i++)
+		map_fd_arr[i] = bpf_map_create(BPF_MAP_TYPE_PERCPU_ARRAY, NULL, 4, 4, 256, NULL);
+
+	/* Close array fd later */
+	new_fd = dup(bpf_map__fd(skel->maps.array));
+out:
+	normal_map_btf__destroy(skel);
+	if (new_fd < 0)
+		return;
+	/* Use kern_sync_rcu() to wait for the start of the free of the bpf
+	 * program and use an assumed delay to wait for the release of the map
+	 * btf which is held by other maps (e.g, bss). After that, array map
+	 * holds the last reference of map btf.
+	 */
+	kern_sync_rcu();
+	usleep(4000);
+	/* Spawn multiple kworkers to delay the invocation of
+	 * bpf_map_free_deferred() for array map.
+	 */
+	for (i = 0; i < ARRAY_SIZE(map_fd_arr); i++) {
+		if (map_fd_arr[i] < 0)
+			continue;
+		close(map_fd_arr[i]);
+	}
+	close(new_fd);
+}
+
+static void do_test_map_in_map_btf(void)
+{
+	int err, zero = 0, new_fd = -1;
+	struct map_in_map_btf *skel;
+
+	skel = map_in_map_btf__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_load"))
+		return;
+
+	err = map_in_map_btf__attach(skel);
+	if (!ASSERT_OK(err, "attach"))
+		goto out;
+
+	skel->bss->pid = getpid();
+	usleep(1);
+	ASSERT_TRUE(skel->bss->done, "done");
+
+	/* Close inner_array fd later */
+	new_fd = dup(bpf_map__fd(skel->maps.inner_array));
+	/* Defer the free of inner_array */
+	err = bpf_map__delete_elem(skel->maps.outer_array, &zero, sizeof(zero), 0);
+	ASSERT_OK(err, "delete inner map");
+out:
+	map_in_map_btf__destroy(skel);
+	if (new_fd < 0)
+		return;
+	/* Use kern_sync_rcu() to wait for the start of the free of the bpf
+	 * program and use an assumed delay to wait for the free of the outer
+	 * map and the release of map btf. After that, inner map holds the last
+	 * reference of map btf.
+	 */
+	kern_sync_rcu();
+	usleep(10000);
+	close(new_fd);
+}
+
+void test_map_btf(void)
+{
+	if (test__start_subtest("array_btf"))
+		do_test_normal_map_btf();
+	if (test__start_subtest("inner_array_btf"))
+		do_test_map_in_map_btf();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/map_excl.c b/tools/testing/selftests/bpf/prog_tests/map_excl.c
new file mode 100644
index 000000000000..6bdc6d6de0da
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/map_excl.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2025 Google LLC. */
+#define _GNU_SOURCE
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <test_progs.h>
+#include <bpf/btf.h>
+
+#include "map_excl.skel.h"
+
+static void test_map_excl_allowed(void)
+{
+	struct map_excl *skel = map_excl__open();
+	int err;
+
+	err = bpf_map__set_exclusive_program(skel->maps.excl_map, skel->progs.should_have_access);
+	if (!ASSERT_OK(err, "bpf_map__set_exclusive_program"))
+		goto out;
+
+	bpf_program__set_autoload(skel->progs.should_have_access, true);
+	bpf_program__set_autoload(skel->progs.should_not_have_access, false);
+
+	err = map_excl__load(skel);
+	ASSERT_OK(err, "map_excl__load");
+out:
+	map_excl__destroy(skel);
+}
+
+static void test_map_excl_denied(void)
+{
+	struct map_excl *skel = map_excl__open();
+	int err;
+
+	err = bpf_map__set_exclusive_program(skel->maps.excl_map, skel->progs.should_have_access);
+	if (!ASSERT_OK(err, "bpf_map__make_exclusive"))
+		goto out;
+
+	bpf_program__set_autoload(skel->progs.should_have_access, false);
+	bpf_program__set_autoload(skel->progs.should_not_have_access, true);
+
+	err = map_excl__load(skel);
+	ASSERT_EQ(err, -EACCES, "exclusive map access not denied\n");
+out:
+	map_excl__destroy(skel);
+
+}
+
+void test_map_excl(void)
+{
+	if (test__start_subtest("map_excl_allowed"))
+		test_map_excl_allowed();
+	if (test__start_subtest("map_excl_denied"))
+		test_map_excl_denied();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/map_in_map.c b/tools/testing/selftests/bpf/prog_tests/map_in_map.c
new file mode 100644
index 000000000000..286a9fb469e2
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/map_in_map.c
@@ -0,0 +1,271 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#define _GNU_SOURCE
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <test_progs.h>
+#include <bpf/btf.h>
+
+#include "access_map_in_map.skel.h"
+#include "update_map_in_htab.skel.h"
+
+struct thread_ctx {
+	pthread_barrier_t barrier;
+	int outer_map_fd;
+	int start, abort;
+	int loop, err;
+};
+
+static int wait_for_start_or_abort(struct thread_ctx *ctx)
+{
+	while (!ctx->start && !ctx->abort)
+		usleep(1);
+	return ctx->abort ? -1 : 0;
+}
+
+static void *update_map_fn(void *data)
+{
+	struct thread_ctx *ctx = data;
+	int loop = ctx->loop, err = 0;
+
+	if (wait_for_start_or_abort(ctx) < 0)
+		return NULL;
+	pthread_barrier_wait(&ctx->barrier);
+
+	while (loop-- > 0) {
+		int fd, zero = 0;
+
+		fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 4, 1, NULL);
+		if (fd < 0) {
+			err |= 1;
+			pthread_barrier_wait(&ctx->barrier);
+			continue;
+		}
+
+		/* Remove the old inner map */
+		if (bpf_map_update_elem(ctx->outer_map_fd, &zero, &fd, 0) < 0)
+			err |= 2;
+		close(fd);
+		pthread_barrier_wait(&ctx->barrier);
+	}
+
+	ctx->err = err;
+
+	return NULL;
+}
+
+static void *access_map_fn(void *data)
+{
+	struct thread_ctx *ctx = data;
+	int loop = ctx->loop;
+
+	if (wait_for_start_or_abort(ctx) < 0)
+		return NULL;
+	pthread_barrier_wait(&ctx->barrier);
+
+	while (loop-- > 0) {
+		/* Access the old inner map */
+		syscall(SYS_getpgid);
+		pthread_barrier_wait(&ctx->barrier);
+	}
+
+	return NULL;
+}
+
+static void test_map_in_map_access(const char *prog_name, const char *map_name)
+{
+	struct access_map_in_map *skel;
+	struct bpf_map *outer_map;
+	struct bpf_program *prog;
+	struct thread_ctx ctx;
+	pthread_t tid[2];
+	int err;
+
+	skel = access_map_in_map__open();
+	if (!ASSERT_OK_PTR(skel, "access_map_in_map open"))
+		return;
+
+	prog = bpf_object__find_program_by_name(skel->obj, prog_name);
+	if (!ASSERT_OK_PTR(prog, "find program"))
+		goto out;
+	bpf_program__set_autoload(prog, true);
+
+	outer_map = bpf_object__find_map_by_name(skel->obj, map_name);
+	if (!ASSERT_OK_PTR(outer_map, "find map"))
+		goto out;
+
+	err = access_map_in_map__load(skel);
+	if (!ASSERT_OK(err, "access_map_in_map load"))
+		goto out;
+
+	err = access_map_in_map__attach(skel);
+	if (!ASSERT_OK(err, "access_map_in_map attach"))
+		goto out;
+
+	skel->bss->tgid = getpid();
+
+	memset(&ctx, 0, sizeof(ctx));
+	pthread_barrier_init(&ctx.barrier, NULL, 2);
+	ctx.outer_map_fd = bpf_map__fd(outer_map);
+	ctx.loop = 4;
+
+	err = pthread_create(&tid[0], NULL, update_map_fn, &ctx);
+	if (!ASSERT_OK(err, "close_thread"))
+		goto out;
+
+	err = pthread_create(&tid[1], NULL, access_map_fn, &ctx);
+	if (!ASSERT_OK(err, "read_thread")) {
+		ctx.abort = 1;
+		pthread_join(tid[0], NULL);
+		goto out;
+	}
+
+	ctx.start = 1;
+	pthread_join(tid[0], NULL);
+	pthread_join(tid[1], NULL);
+
+	ASSERT_OK(ctx.err, "err");
+out:
+	access_map_in_map__destroy(skel);
+}
+
+static void add_del_fd_htab(int outer_fd)
+{
+	int inner_fd, err;
+	int key = 1;
+
+	inner_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "arr1", 4, 4, 1, NULL);
+	if (!ASSERT_OK_FD(inner_fd, "inner1"))
+		return;
+	err = bpf_map_update_elem(outer_fd, &key, &inner_fd, BPF_NOEXIST);
+	close(inner_fd);
+	if (!ASSERT_OK(err, "add"))
+		return;
+
+	/* Delete */
+	err = bpf_map_delete_elem(outer_fd, &key);
+	ASSERT_OK(err, "del");
+}
+
+static void overwrite_fd_htab(int outer_fd)
+{
+	int inner_fd, err;
+	int key = 1;
+
+	inner_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "arr1", 4, 4, 1, NULL);
+	if (!ASSERT_OK_FD(inner_fd, "inner1"))
+		return;
+	err = bpf_map_update_elem(outer_fd, &key, &inner_fd, BPF_NOEXIST);
+	close(inner_fd);
+	if (!ASSERT_OK(err, "add"))
+		return;
+
+	/* Overwrite */
+	inner_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "arr2", 4, 4, 1, NULL);
+	if (!ASSERT_OK_FD(inner_fd, "inner2"))
+		goto out;
+	err = bpf_map_update_elem(outer_fd, &key, &inner_fd, BPF_EXIST);
+	close(inner_fd);
+	if (!ASSERT_OK(err, "overwrite"))
+		goto out;
+
+	err = bpf_map_delete_elem(outer_fd, &key);
+	ASSERT_OK(err, "del");
+	return;
+out:
+	bpf_map_delete_elem(outer_fd, &key);
+}
+
+static void lookup_delete_fd_htab(int outer_fd)
+{
+	int key = 1, value;
+	int inner_fd, err;
+
+	inner_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "arr1", 4, 4, 1, NULL);
+	if (!ASSERT_OK_FD(inner_fd, "inner1"))
+		return;
+	err = bpf_map_update_elem(outer_fd, &key, &inner_fd, BPF_NOEXIST);
+	close(inner_fd);
+	if (!ASSERT_OK(err, "add"))
+		return;
+
+	/* lookup_and_delete is not supported for htab of maps */
+	err = bpf_map_lookup_and_delete_elem(outer_fd, &key, &value);
+	ASSERT_EQ(err, -ENOTSUPP, "lookup_del");
+
+	err = bpf_map_delete_elem(outer_fd, &key);
+	ASSERT_OK(err, "del");
+}
+
+static void batched_lookup_delete_fd_htab(int outer_fd)
+{
+	int keys[2] = {1, 2}, values[2];
+	unsigned int cnt, batch;
+	int inner_fd, err;
+
+	inner_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "arr1", 4, 4, 1, NULL);
+	if (!ASSERT_OK_FD(inner_fd, "inner1"))
+		return;
+
+	err = bpf_map_update_elem(outer_fd, &keys[0], &inner_fd, BPF_NOEXIST);
+	close(inner_fd);
+	if (!ASSERT_OK(err, "add1"))
+		return;
+
+	inner_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "arr2", 4, 4, 1, NULL);
+	if (!ASSERT_OK_FD(inner_fd, "inner2"))
+		goto out;
+	err = bpf_map_update_elem(outer_fd, &keys[1], &inner_fd, BPF_NOEXIST);
+	close(inner_fd);
+	if (!ASSERT_OK(err, "add2"))
+		goto out;
+
+	/* batched lookup_and_delete */
+	cnt = ARRAY_SIZE(keys);
+	err = bpf_map_lookup_and_delete_batch(outer_fd, NULL, &batch, keys, values, &cnt, NULL);
+	ASSERT_TRUE((!err || err == -ENOENT), "delete_batch ret");
+	ASSERT_EQ(cnt, ARRAY_SIZE(keys), "delete_batch cnt");
+
+out:
+	bpf_map_delete_elem(outer_fd, &keys[0]);
+}
+
+static void test_update_map_in_htab(bool preallocate)
+{
+	struct update_map_in_htab *skel;
+	int err, fd;
+
+	skel = update_map_in_htab__open();
+	if (!ASSERT_OK_PTR(skel, "open"))
+		return;
+
+	err = update_map_in_htab__load(skel);
+	if (!ASSERT_OK(err, "load"))
+		goto out;
+
+	fd = preallocate ? bpf_map__fd(skel->maps.outer_htab_map) :
+			   bpf_map__fd(skel->maps.outer_alloc_htab_map);
+
+	add_del_fd_htab(fd);
+	overwrite_fd_htab(fd);
+	lookup_delete_fd_htab(fd);
+	batched_lookup_delete_fd_htab(fd);
+out:
+	update_map_in_htab__destroy(skel);
+}
+
+void test_map_in_map(void)
+{
+	if (test__start_subtest("acc_map_in_array"))
+		test_map_in_map_access("access_map_in_array", "outer_array_map");
+	if (test__start_subtest("sleepable_acc_map_in_array"))
+		test_map_in_map_access("sleepable_access_map_in_array", "outer_array_map");
+	if (test__start_subtest("acc_map_in_htab"))
+		test_map_in_map_access("access_map_in_htab", "outer_htab_map");
+	if (test__start_subtest("sleepable_acc_map_in_htab"))
+		test_map_in_map_access("sleepable_access_map_in_htab", "outer_htab_map");
+	if (test__start_subtest("update_map_in_htab"))
+		test_update_map_in_htab(true);
+	if (test__start_subtest("update_map_in_alloc_htab"))
+		test_update_map_in_htab(false);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/map_kptr.c b/tools/testing/selftests/bpf/prog_tests/map_kptr.c
index 3533a4ecad01..8743df599567 100644
--- a/tools/testing/selftests/bpf/prog_tests/map_kptr.c
+++ b/tools/testing/selftests/bpf/prog_tests/map_kptr.c
@@ -4,70 +4,160 @@
 
 #include "map_kptr.skel.h"
 #include "map_kptr_fail.skel.h"
+#include "rcu_tasks_trace_gp.skel.h"
 
 static void test_map_kptr_success(bool test_run)
 {
+	LIBBPF_OPTS(bpf_test_run_opts, lopts);
 	LIBBPF_OPTS(bpf_test_run_opts, opts,
 		.data_in = &pkt_v4,
 		.data_size_in = sizeof(pkt_v4),
 		.repeat = 1,
 	);
+	int key = 0, ret, cpu;
 	struct map_kptr *skel;
-	int key = 0, ret;
-	char buf[16];
+	char buf[16], *pbuf;
 
 	skel = map_kptr__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "map_kptr__open_and_load"))
 		return;
 
-	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_map_kptr_ref), &opts);
-	ASSERT_OK(ret, "test_map_kptr_ref refcount");
-	ASSERT_OK(opts.retval, "test_map_kptr_ref retval");
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_map_kptr_ref1), &opts);
+	ASSERT_OK(ret, "test_map_kptr_ref1 refcount");
+	ASSERT_OK(opts.retval, "test_map_kptr_ref1 retval");
 	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_map_kptr_ref2), &opts);
 	ASSERT_OK(ret, "test_map_kptr_ref2 refcount");
 	ASSERT_OK(opts.retval, "test_map_kptr_ref2 retval");
 
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_ls_map_kptr_ref1), &lopts);
+	ASSERT_OK(ret, "test_ls_map_kptr_ref1 refcount");
+	ASSERT_OK(lopts.retval, "test_ls_map_kptr_ref1 retval");
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_ls_map_kptr_ref2), &lopts);
+	ASSERT_OK(ret, "test_ls_map_kptr_ref2 refcount");
+	ASSERT_OK(lopts.retval, "test_ls_map_kptr_ref2 retval");
+
 	if (test_run)
 		goto exit;
 
+	cpu = libbpf_num_possible_cpus();
+	if (!ASSERT_GT(cpu, 0, "libbpf_num_possible_cpus"))
+		goto exit;
+
+	pbuf = calloc(cpu, sizeof(buf));
+	if (!ASSERT_OK_PTR(pbuf, "calloc(pbuf)"))
+		goto exit;
+
 	ret = bpf_map__update_elem(skel->maps.array_map,
 				   &key, sizeof(key), buf, sizeof(buf), 0);
 	ASSERT_OK(ret, "array_map update");
-	ret = bpf_map__update_elem(skel->maps.array_map,
-				   &key, sizeof(key), buf, sizeof(buf), 0);
-	ASSERT_OK(ret, "array_map update2");
+	skel->data->ref--;
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_map_kptr_ref3), &opts);
+	ASSERT_OK(ret, "test_map_kptr_ref3 refcount");
+	ASSERT_OK(opts.retval, "test_map_kptr_ref3 retval");
+
+	ret = bpf_map__update_elem(skel->maps.pcpu_array_map,
+				   &key, sizeof(key), pbuf, cpu * sizeof(buf), 0);
+	ASSERT_OK(ret, "pcpu_array_map update");
+	skel->data->ref--;
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_map_kptr_ref3), &opts);
+	ASSERT_OK(ret, "test_map_kptr_ref3 refcount");
+	ASSERT_OK(opts.retval, "test_map_kptr_ref3 retval");
 
-	ret = bpf_map__update_elem(skel->maps.hash_map,
-				   &key, sizeof(key), buf, sizeof(buf), 0);
-	ASSERT_OK(ret, "hash_map update");
 	ret = bpf_map__delete_elem(skel->maps.hash_map, &key, sizeof(key), 0);
 	ASSERT_OK(ret, "hash_map delete");
+	skel->data->ref--;
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_map_kptr_ref3), &opts);
+	ASSERT_OK(ret, "test_map_kptr_ref3 refcount");
+	ASSERT_OK(opts.retval, "test_map_kptr_ref3 retval");
+
+	ret = bpf_map__delete_elem(skel->maps.pcpu_hash_map, &key, sizeof(key), 0);
+	ASSERT_OK(ret, "pcpu_hash_map delete");
+	skel->data->ref--;
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_map_kptr_ref3), &opts);
+	ASSERT_OK(ret, "test_map_kptr_ref3 refcount");
+	ASSERT_OK(opts.retval, "test_map_kptr_ref3 retval");
 
-	ret = bpf_map__update_elem(skel->maps.hash_malloc_map,
-				   &key, sizeof(key), buf, sizeof(buf), 0);
-	ASSERT_OK(ret, "hash_malloc_map update");
 	ret = bpf_map__delete_elem(skel->maps.hash_malloc_map, &key, sizeof(key), 0);
 	ASSERT_OK(ret, "hash_malloc_map delete");
+	skel->data->ref--;
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_map_kptr_ref3), &opts);
+	ASSERT_OK(ret, "test_map_kptr_ref3 refcount");
+	ASSERT_OK(opts.retval, "test_map_kptr_ref3 retval");
+
+	ret = bpf_map__delete_elem(skel->maps.pcpu_hash_malloc_map, &key, sizeof(key), 0);
+	ASSERT_OK(ret, "pcpu_hash_malloc_map delete");
+	skel->data->ref--;
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_map_kptr_ref3), &opts);
+	ASSERT_OK(ret, "test_map_kptr_ref3 refcount");
+	ASSERT_OK(opts.retval, "test_map_kptr_ref3 retval");
 
-	ret = bpf_map__update_elem(skel->maps.lru_hash_map,
-				   &key, sizeof(key), buf, sizeof(buf), 0);
-	ASSERT_OK(ret, "lru_hash_map update");
 	ret = bpf_map__delete_elem(skel->maps.lru_hash_map, &key, sizeof(key), 0);
 	ASSERT_OK(ret, "lru_hash_map delete");
+	skel->data->ref--;
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_map_kptr_ref3), &opts);
+	ASSERT_OK(ret, "test_map_kptr_ref3 refcount");
+	ASSERT_OK(opts.retval, "test_map_kptr_ref3 retval");
+
+	ret = bpf_map__delete_elem(skel->maps.lru_pcpu_hash_map, &key, sizeof(key), 0);
+	ASSERT_OK(ret, "lru_pcpu_hash_map delete");
+	skel->data->ref--;
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_map_kptr_ref3), &opts);
+	ASSERT_OK(ret, "test_map_kptr_ref3 refcount");
+	ASSERT_OK(opts.retval, "test_map_kptr_ref3 retval");
 
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_ls_map_kptr_ref_del), &lopts);
+	ASSERT_OK(ret, "test_ls_map_kptr_ref_del delete");
+	skel->data->ref--;
+	ASSERT_OK(lopts.retval, "test_ls_map_kptr_ref_del retval");
+
+	free(pbuf);
 exit:
 	map_kptr__destroy(skel);
 }
 
-void test_map_kptr(void)
+static int kern_sync_rcu_tasks_trace(struct rcu_tasks_trace_gp *rcu)
 {
-	if (test__start_subtest("success")) {
+	long gp_seq = READ_ONCE(rcu->bss->gp_seq);
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+
+	if (!ASSERT_OK(bpf_prog_test_run_opts(bpf_program__fd(rcu->progs.do_call_rcu_tasks_trace),
+					      &opts), "do_call_rcu_tasks_trace"))
+		return -EFAULT;
+	if (!ASSERT_OK(opts.retval, "opts.retval == 0"))
+		return -EFAULT;
+	while (gp_seq == READ_ONCE(rcu->bss->gp_seq))
+		sched_yield();
+	return 0;
+}
+
+void serial_test_map_kptr(void)
+{
+	struct rcu_tasks_trace_gp *skel;
+
+	RUN_TESTS(map_kptr_fail);
+
+	skel = rcu_tasks_trace_gp__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "rcu_tasks_trace_gp__open_and_load"))
+		return;
+	if (!ASSERT_OK(rcu_tasks_trace_gp__attach(skel), "rcu_tasks_trace_gp__attach"))
+		goto end;
+
+	if (test__start_subtest("success-map")) {
+		test_map_kptr_success(true);
+
+		ASSERT_OK(kern_sync_rcu_tasks_trace(skel), "sync rcu_tasks_trace");
+		ASSERT_OK(kern_sync_rcu(), "sync rcu");
+		/* Observe refcount dropping to 1 on bpf_map_free_deferred */
 		test_map_kptr_success(false);
-		/* Do test_run twice, so that we see refcount going back to 1
-		 * after we leave it in map from first iteration.
-		 */
+
+		ASSERT_OK(kern_sync_rcu_tasks_trace(skel), "sync rcu_tasks_trace");
+		ASSERT_OK(kern_sync_rcu(), "sync rcu");
+		/* Observe refcount dropping to 1 on synchronous delete elem */
 		test_map_kptr_success(true);
 	}
 
-	RUN_TESTS(map_kptr_fail);
+end:
+	rcu_tasks_trace_gp__destroy(skel);
+	return;
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/map_ops.c b/tools/testing/selftests/bpf/prog_tests/map_ops.c
new file mode 100644
index 000000000000..be5e42a413b4
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/map_ops.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <errno.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+#include "test_map_ops.skel.h"
+#include "test_progs.h"
+
+static void map_update(void)
+{
+	(void)syscall(__NR_getpid);
+}
+
+static void map_delete(void)
+{
+	(void)syscall(__NR_getppid);
+}
+
+static void map_push(void)
+{
+	(void)syscall(__NR_getuid);
+}
+
+static void map_pop(void)
+{
+	(void)syscall(__NR_geteuid);
+}
+
+static void map_peek(void)
+{
+	(void)syscall(__NR_getgid);
+}
+
+static void map_for_each_pass(void)
+{
+	(void)syscall(__NR_gettid);
+}
+
+static void map_for_each_fail(void)
+{
+	(void)syscall(__NR_getpgid);
+}
+
+static int setup(struct test_map_ops **skel)
+{
+	int err = 0;
+
+	if (!skel)
+		return -1;
+
+	*skel = test_map_ops__open();
+	if (!ASSERT_OK_PTR(*skel, "test_map_ops__open"))
+		return -1;
+
+	(*skel)->rodata->pid = getpid();
+
+	err = test_map_ops__load(*skel);
+	if (!ASSERT_OK(err, "test_map_ops__load"))
+		return err;
+
+	err = test_map_ops__attach(*skel);
+	if (!ASSERT_OK(err, "test_map_ops__attach"))
+		return err;
+
+	return err;
+}
+
+static void teardown(struct test_map_ops **skel)
+{
+	if (skel && *skel)
+		test_map_ops__destroy(*skel);
+}
+
+static void map_ops_update_delete_subtest(void)
+{
+	struct test_map_ops *skel;
+
+	if (setup(&skel))
+		goto teardown;
+
+	map_update();
+	ASSERT_OK(skel->bss->err, "map_update_initial");
+
+	map_update();
+	ASSERT_LT(skel->bss->err, 0, "map_update_existing");
+	ASSERT_EQ(skel->bss->err, -EEXIST, "map_update_existing");
+
+	map_delete();
+	ASSERT_OK(skel->bss->err, "map_delete_existing");
+
+	map_delete();
+	ASSERT_LT(skel->bss->err, 0, "map_delete_non_existing");
+	ASSERT_EQ(skel->bss->err, -ENOENT, "map_delete_non_existing");
+
+teardown:
+	teardown(&skel);
+}
+
+static void map_ops_push_peek_pop_subtest(void)
+{
+	struct test_map_ops *skel;
+
+	if (setup(&skel))
+		goto teardown;
+
+	map_push();
+	ASSERT_OK(skel->bss->err, "map_push_initial");
+
+	map_push();
+	ASSERT_LT(skel->bss->err, 0, "map_push_when_full");
+	ASSERT_EQ(skel->bss->err, -E2BIG, "map_push_when_full");
+
+	map_peek();
+	ASSERT_OK(skel->bss->err, "map_peek");
+
+	map_pop();
+	ASSERT_OK(skel->bss->err, "map_pop");
+
+	map_peek();
+	ASSERT_LT(skel->bss->err, 0, "map_peek_when_empty");
+	ASSERT_EQ(skel->bss->err, -ENOENT, "map_peek_when_empty");
+
+	map_pop();
+	ASSERT_LT(skel->bss->err, 0, "map_pop_when_empty");
+	ASSERT_EQ(skel->bss->err, -ENOENT, "map_pop_when_empty");
+
+teardown:
+	teardown(&skel);
+}
+
+static void map_ops_for_each_subtest(void)
+{
+	struct test_map_ops *skel;
+
+	if (setup(&skel))
+		goto teardown;
+
+	map_for_each_pass();
+	/* expect to iterate over 1 element */
+	ASSERT_EQ(skel->bss->err, 1, "map_for_each_no_flags");
+
+	map_for_each_fail();
+	ASSERT_LT(skel->bss->err, 0, "map_for_each_with_flags");
+	ASSERT_EQ(skel->bss->err, -EINVAL, "map_for_each_with_flags");
+
+teardown:
+	teardown(&skel);
+}
+
+void test_map_ops(void)
+{
+	if (test__start_subtest("map_ops_update_delete"))
+		map_ops_update_delete_subtest();
+
+	if (test__start_subtest("map_ops_push_peek_pop"))
+		map_ops_push_peek_pop_subtest();
+
+	if (test__start_subtest("map_ops_for_each"))
+		map_ops_for_each_subtest();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/mem_rdonly_untrusted.c b/tools/testing/selftests/bpf/prog_tests/mem_rdonly_untrusted.c
new file mode 100644
index 000000000000..40d4f687bd9c
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/mem_rdonly_untrusted.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <test_progs.h>
+#include "mem_rdonly_untrusted.skel.h"
+
+void test_mem_rdonly_untrusted(void)
+{
+	RUN_TESTS(mem_rdonly_untrusted);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/metadata.c b/tools/testing/selftests/bpf/prog_tests/metadata.c
index 2c53eade88e3..8b67dfc10f5c 100644
--- a/tools/testing/selftests/bpf/prog_tests/metadata.c
+++ b/tools/testing/selftests/bpf/prog_tests/metadata.c
@@ -16,7 +16,7 @@ static int duration;
 static int prog_holds_map(int prog_fd, int map_fd)
 {
 	struct bpf_prog_info prog_info = {};
-	struct bpf_prog_info map_info = {};
+	struct bpf_map_info map_info = {};
 	__u32 prog_info_len;
 	__u32 map_info_len;
 	__u32 *map_ids;
@@ -25,12 +25,12 @@ static int prog_holds_map(int prog_fd, int map_fd)
 	int i;
 
 	map_info_len = sizeof(map_info);
-	ret = bpf_obj_get_info_by_fd(map_fd, &map_info, &map_info_len);
+	ret = bpf_map_get_info_by_fd(map_fd, &map_info, &map_info_len);
 	if (ret)
 		return -errno;
 
 	prog_info_len = sizeof(prog_info);
-	ret = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &prog_info_len);
+	ret = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &prog_info_len);
 	if (ret)
 		return -errno;
 
@@ -44,7 +44,7 @@ static int prog_holds_map(int prog_fd, int map_fd)
 	prog_info.map_ids = ptr_to_u64(map_ids);
 	prog_info_len = sizeof(prog_info);
 
-	ret = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &prog_info_len);
+	ret = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &prog_info_len);
 	if (ret) {
 		ret = -errno;
 		goto free_map_ids;
diff --git a/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c b/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c
index eb2feaac81fe..653b0a20fab9 100644
--- a/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c
+++ b/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c
@@ -488,7 +488,7 @@ static void run_test(struct migrate_reuseport_test_case *test_case,
 			goto close_servers;
 	}
 
-	/* Tie requests to the first four listners */
+	/* Tie requests to the first four listeners */
 	err = start_clients(test_case);
 	if (!ASSERT_OK(err, "start_clients"))
 		goto close_clients;
diff --git a/tools/testing/selftests/bpf/prog_tests/missed.c b/tools/testing/selftests/bpf/prog_tests/missed.c
new file mode 100644
index 000000000000..ed8857ae914a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/missed.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include "missed_kprobe.skel.h"
+#include "missed_kprobe_recursion.skel.h"
+#include "missed_tp_recursion.skel.h"
+
+/*
+ * Putting kprobe on bpf_fentry_test1 that calls bpf_kfunc_common_test
+ * kfunc, which has also kprobe on. The latter won't get triggered due
+ * to kprobe recursion check and kprobe missed counter is incremented.
+ */
+static void test_missed_perf_kprobe(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	struct bpf_link_info info = {};
+	struct missed_kprobe *skel;
+	__u32 len = sizeof(info);
+	int err, prog_fd;
+
+	skel = missed_kprobe__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "missed_kprobe__open_and_load"))
+		goto cleanup;
+
+	err = missed_kprobe__attach(skel);
+	if (!ASSERT_OK(err, "missed_kprobe__attach"))
+		goto cleanup;
+
+	prog_fd = bpf_program__fd(skel->progs.trigger);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(topts.retval, 0, "test_run");
+
+	err = bpf_link_get_info_by_fd(bpf_link__fd(skel->links.test2), &info, &len);
+	if (!ASSERT_OK(err, "bpf_link_get_info_by_fd"))
+		goto cleanup;
+
+	ASSERT_EQ(info.type, BPF_LINK_TYPE_PERF_EVENT, "info.type");
+	ASSERT_EQ(info.perf_event.type, BPF_PERF_EVENT_KPROBE, "info.perf_event.type");
+	ASSERT_EQ(info.perf_event.kprobe.missed, 1, "info.perf_event.kprobe.missed");
+
+cleanup:
+	missed_kprobe__destroy(skel);
+}
+
+static __u64 get_missed_count(int fd)
+{
+	struct bpf_prog_info info = {};
+	__u32 len = sizeof(info);
+	int err;
+
+	err = bpf_prog_get_info_by_fd(fd, &info, &len);
+	if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd"))
+		return (__u64) -1;
+	return info.recursion_misses;
+}
+
+/*
+ * Putting kprobe.multi on bpf_fentry_test1 that calls bpf_kfunc_common_test
+ * kfunc which has 3 perf event kprobes and 1 kprobe.multi attached.
+ *
+ * Because fprobe (kprobe.multi attach layear) does not have strict recursion
+ * check the kprobe's bpf_prog_active check is hit for test2-5.
+ */
+static void test_missed_kprobe_recursion(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	struct missed_kprobe_recursion *skel;
+	int err, prog_fd;
+
+	skel = missed_kprobe_recursion__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "missed_kprobe_recursion__open_and_load"))
+		goto cleanup;
+
+	err = missed_kprobe_recursion__attach(skel);
+	if (!ASSERT_OK(err, "missed_kprobe_recursion__attach"))
+		goto cleanup;
+
+	prog_fd = bpf_program__fd(skel->progs.trigger);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(topts.retval, 0, "test_run");
+
+	ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test1)), 0, "test1_recursion_misses");
+	ASSERT_GE(get_missed_count(bpf_program__fd(skel->progs.test2)), 1, "test2_recursion_misses");
+	ASSERT_GE(get_missed_count(bpf_program__fd(skel->progs.test3)), 1, "test3_recursion_misses");
+	ASSERT_GE(get_missed_count(bpf_program__fd(skel->progs.test4)), 1, "test4_recursion_misses");
+	ASSERT_GE(get_missed_count(bpf_program__fd(skel->progs.test5)), 1, "test5_recursion_misses");
+	ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test6)), 1, "test6_recursion_misses");
+
+cleanup:
+	missed_kprobe_recursion__destroy(skel);
+}
+
+/*
+ * Putting kprobe on bpf_fentry_test1 that calls bpf_printk and invokes
+ * bpf_trace_printk tracepoint. The bpf_trace_printk tracepoint has test[234]
+ * programs attached to it.
+ *
+ * Because kprobe execution goes through bpf_prog_active check, programs
+ * attached to the tracepoint will fail the recursion check and increment
+ * the recursion_misses stats.
+ */
+static void test_missed_tp_recursion(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	struct missed_tp_recursion *skel;
+	int err, prog_fd;
+
+	skel = missed_tp_recursion__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "missed_tp_recursion__open_and_load"))
+		goto cleanup;
+
+	err = missed_tp_recursion__attach(skel);
+	if (!ASSERT_OK(err, "missed_tp_recursion__attach"))
+		goto cleanup;
+
+	prog_fd = bpf_program__fd(skel->progs.trigger);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(topts.retval, 0, "test_run");
+
+	ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test1)), 0, "test1_recursion_misses");
+	ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test2)), 1, "test2_recursion_misses");
+	ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test3)), 1, "test3_recursion_misses");
+	ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test4)), 1, "test4_recursion_misses");
+
+cleanup:
+	missed_tp_recursion__destroy(skel);
+}
+
+void test_missed(void)
+{
+	if (test__start_subtest("perf_kprobe"))
+		test_missed_perf_kprobe();
+	if (test__start_subtest("kprobe_recursion"))
+		test_missed_kprobe_recursion();
+	if (test__start_subtest("tp_recursion"))
+		test_missed_tp_recursion();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c
index 37b002ca1167..a271d5a0f7ab 100644
--- a/tools/testing/selftests/bpf/prog_tests/mmap.c
+++ b/tools/testing/selftests/bpf/prog_tests/mmap.c
@@ -64,7 +64,7 @@ void test_mmap(void)
 
 	/* get map's ID */
 	memset(&map_info, 0, map_info_sz);
-	err = bpf_obj_get_info_by_fd(data_map_fd, &map_info, &map_info_sz);
+	err = bpf_map_get_info_by_fd(data_map_fd, &map_info, &map_info_sz);
 	if (CHECK(err, "map_get_info", "failed %d\n", errno))
 		goto cleanup;
 	data_map_id = map_info.id;
diff --git a/tools/testing/selftests/bpf/prog_tests/modify_return.c b/tools/testing/selftests/bpf/prog_tests/modify_return.c
index 5d9955af6247..a70c99c2f8c8 100644
--- a/tools/testing/selftests/bpf/prog_tests/modify_return.c
+++ b/tools/testing/selftests/bpf/prog_tests/modify_return.c
@@ -41,6 +41,10 @@ static void run_test(__u32 input_retval, __u16 want_side_effect, __s16 want_ret)
 	ASSERT_EQ(skel->bss->fexit_result, 1, "modify_return fexit_result");
 	ASSERT_EQ(skel->bss->fmod_ret_result, 1, "modify_return fmod_ret_result");
 
+	ASSERT_EQ(skel->bss->fentry_result2, 1, "modify_return fentry_result2");
+	ASSERT_EQ(skel->bss->fexit_result2, 1, "modify_return fexit_result2");
+	ASSERT_EQ(skel->bss->fmod_ret_result2, 1, "modify_return fmod_ret_result2");
+
 cleanup:
 	modify_return__destroy(skel);
 }
@@ -49,9 +53,9 @@ cleanup:
 void serial_test_modify_return(void)
 {
 	run_test(0 /* input_retval */,
-		 1 /* want_side_effect */,
-		 4 /* want_ret */);
+		 2 /* want_side_effect */,
+		 33 /* want_ret */);
 	run_test(-EINVAL /* input_retval */,
 		 0 /* want_side_effect */,
-		 -EINVAL /* want_ret */);
+		 -EINVAL * 2 /* want_ret */);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/module_attach.c b/tools/testing/selftests/bpf/prog_tests/module_attach.c
index 7fc01ff490db..70fa7ae93173 100644
--- a/tools/testing/selftests/bpf/prog_tests/module_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/module_attach.c
@@ -4,6 +4,7 @@
 #include <test_progs.h>
 #include <stdbool.h>
 #include "test_module_attach.skel.h"
+#include "testing_helpers.h"
 
 static int duration;
 
@@ -32,11 +33,6 @@ static int trigger_module_test_writable(int *val)
 	return 0;
 }
 
-static int delete_module(const char *name, int flags)
-{
-	return syscall(__NR_delete_module, name, flags);
-}
-
 void test_module_attach(void)
 {
 	const int READ_SZ = 456;
@@ -55,6 +51,10 @@ void test_module_attach(void)
 					     0, "bpf_testmod_test_read");
 	ASSERT_OK(err, "set_attach_target");
 
+	err = bpf_program__set_attach_target(skel->progs.handle_fentry_explicit_manual,
+					     0, "bpf_testmod:bpf_testmod_test_read");
+	ASSERT_OK(err, "set_attach_target_explicit");
+
 	err = test_module_attach__load(skel);
 	if (CHECK(err, "skel_load", "failed to load skeleton\n"))
 		return;
@@ -74,6 +74,8 @@ void test_module_attach(void)
 	ASSERT_EQ(bss->tp_btf_read_sz, READ_SZ, "tp_btf");
 	ASSERT_EQ(bss->fentry_read_sz, READ_SZ, "fentry");
 	ASSERT_EQ(bss->fentry_manual_read_sz, READ_SZ, "fentry_manual");
+	ASSERT_EQ(bss->fentry_explicit_read_sz, READ_SZ, "fentry_explicit");
+	ASSERT_EQ(bss->fentry_explicit_manual_read_sz, READ_SZ, "fentry_explicit_manual");
 	ASSERT_EQ(bss->fexit_read_sz, READ_SZ, "fexit");
 	ASSERT_EQ(bss->fexit_ret, -EIO, "fexit_tet");
 	ASSERT_EQ(bss->fmod_ret_read_sz, READ_SZ, "fmod_ret");
@@ -88,26 +90,26 @@ void test_module_attach(void)
 
 	test_module_attach__detach(skel);
 
-	/* attach fentry/fexit and make sure it get's module reference */
+	/* attach fentry/fexit and make sure it gets module reference */
 	link = bpf_program__attach(skel->progs.handle_fentry);
 	if (!ASSERT_OK_PTR(link, "attach_fentry"))
 		goto cleanup;
 
-	ASSERT_ERR(delete_module("bpf_testmod", 0), "delete_module");
+	ASSERT_ERR(unload_bpf_testmod(false), "unload_bpf_testmod");
 	bpf_link__destroy(link);
 
 	link = bpf_program__attach(skel->progs.handle_fexit);
 	if (!ASSERT_OK_PTR(link, "attach_fexit"))
 		goto cleanup;
 
-	ASSERT_ERR(delete_module("bpf_testmod", 0), "delete_module");
+	ASSERT_ERR(unload_bpf_testmod(false), "unload_bpf_testmod");
 	bpf_link__destroy(link);
 
 	link = bpf_program__attach(skel->progs.kprobe_multi);
 	if (!ASSERT_OK_PTR(link, "attach_kprobe_multi"))
 		goto cleanup;
 
-	ASSERT_ERR(delete_module("bpf_testmod", 0), "delete_module");
+	ASSERT_ERR(unload_bpf_testmod(false), "unload_bpf_testmod");
 	bpf_link__destroy(link);
 
 cleanup:
diff --git a/tools/testing/selftests/bpf/prog_tests/module_fentry_shadow.c b/tools/testing/selftests/bpf/prog_tests/module_fentry_shadow.c
new file mode 100644
index 000000000000..bea05f78de5f
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/module_fentry_shadow.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Red Hat */
+#include <test_progs.h>
+#include <bpf/btf.h>
+#include "bpf/libbpf_internal.h"
+#include "cgroup_helpers.h"
+#include "bpf_util.h"
+
+static const char *module_name = "bpf_testmod";
+static const char *symbol_name = "bpf_fentry_shadow_test";
+
+static int get_bpf_testmod_btf_fd(void)
+{
+	struct bpf_btf_info info;
+	char name[64];
+	__u32 id = 0, len;
+	int err, fd;
+
+	while (true) {
+		err = bpf_btf_get_next_id(id, &id);
+		if (err) {
+			log_err("failed to iterate BTF objects");
+			return err;
+		}
+
+		fd = bpf_btf_get_fd_by_id(id);
+		if (fd < 0) {
+			if (errno == ENOENT)
+				continue; /* expected race: BTF was unloaded */
+			err = -errno;
+			log_err("failed to get FD for BTF object #%d", id);
+			return err;
+		}
+
+		len = sizeof(info);
+		memset(&info, 0, sizeof(info));
+		info.name = ptr_to_u64(name);
+		info.name_len = sizeof(name);
+
+		err = bpf_obj_get_info_by_fd(fd, &info, &len);
+		if (err) {
+			err = -errno;
+			log_err("failed to get info for BTF object #%d", id);
+			close(fd);
+			return err;
+		}
+
+		if (strcmp(name, module_name) == 0)
+			return fd;
+
+		close(fd);
+	}
+	return -ENOENT;
+}
+
+void test_module_fentry_shadow(void)
+{
+	struct btf *vmlinux_btf = NULL, *mod_btf = NULL;
+	int err, i;
+	int btf_fd[2] = {};
+	int prog_fd[2] = {};
+	int link_fd[2] = {};
+	__s32 btf_id[2] = {};
+
+	if (!env.has_testmod) {
+		test__skip();
+		return;
+	}
+
+	LIBBPF_OPTS(bpf_prog_load_opts, load_opts,
+		.expected_attach_type = BPF_TRACE_FENTRY,
+	);
+
+	const struct bpf_insn trace_program[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+
+	vmlinux_btf = btf__load_vmlinux_btf();
+	if (!ASSERT_OK_PTR(vmlinux_btf, "load_vmlinux_btf"))
+		return;
+
+	btf_fd[1] = get_bpf_testmod_btf_fd();
+	if (!ASSERT_GE(btf_fd[1], 0, "get_bpf_testmod_btf_fd"))
+		goto out;
+
+	mod_btf = btf_get_from_fd(btf_fd[1], vmlinux_btf);
+	if (!ASSERT_OK_PTR(mod_btf, "btf_get_from_fd"))
+		goto out;
+
+	btf_id[0] = btf__find_by_name_kind(vmlinux_btf, symbol_name, BTF_KIND_FUNC);
+	if (!ASSERT_GT(btf_id[0], 0, "btf_find_by_name"))
+		goto out;
+
+	btf_id[1] = btf__find_by_name_kind(mod_btf, symbol_name, BTF_KIND_FUNC);
+	if (!ASSERT_GT(btf_id[1], 0, "btf_find_by_name"))
+		goto out;
+
+	for (i = 0; i < 2; i++) {
+		load_opts.attach_btf_id = btf_id[i];
+		load_opts.attach_btf_obj_fd = btf_fd[i];
+		prog_fd[i] = bpf_prog_load(BPF_PROG_TYPE_TRACING, NULL, "GPL",
+					   trace_program,
+					   ARRAY_SIZE(trace_program),
+					   &load_opts);
+		if (!ASSERT_GE(prog_fd[i], 0, "bpf_prog_load"))
+			goto out;
+
+		/* If the verifier incorrectly resolves addresses of the
+		 * shadowed functions and uses the same address for both the
+		 * vmlinux and the bpf_testmod functions, this will fail on
+		 * attempting to create two trampolines for the same address,
+		 * which is forbidden.
+		 */
+		link_fd[i] = bpf_link_create(prog_fd[i], 0, BPF_TRACE_FENTRY, NULL);
+		if (!ASSERT_GE(link_fd[i], 0, "bpf_link_create"))
+			goto out;
+	}
+
+	err = bpf_prog_test_run_opts(prog_fd[0], NULL);
+	ASSERT_OK(err, "running test");
+
+out:
+	btf__free(vmlinux_btf);
+	btf__free(mod_btf);
+	for (i = 0; i < 2; i++) {
+		if (btf_fd[i])
+			close(btf_fd[i]);
+		if (prog_fd[i] > 0)
+			close(prog_fd[i]);
+		if (link_fd[i] > 0)
+			close(link_fd[i]);
+	}
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/mptcp.c b/tools/testing/selftests/bpf/prog_tests/mptcp.c
index 59f08d6d1d53..8fade8bdc451 100644
--- a/tools/testing/selftests/bpf/prog_tests/mptcp.c
+++ b/tools/testing/selftests/bpf/prog_tests/mptcp.c
@@ -2,15 +2,66 @@
 /* Copyright (c) 2020, Tessares SA. */
 /* Copyright (c) 2022, SUSE. */
 
+#include <linux/const.h>
+#include <netinet/in.h>
 #include <test_progs.h>
+#include <unistd.h>
+#include <errno.h>
 #include "cgroup_helpers.h"
 #include "network_helpers.h"
 #include "mptcp_sock.skel.h"
+#include "mptcpify.skel.h"
+#include "mptcp_subflow.skel.h"
+#include "mptcp_sockmap.skel.h"
+
+#define NS_TEST "mptcp_ns"
+#define ADDR_1	"10.0.1.1"
+#define ADDR_2	"10.0.1.2"
+#define PORT_1	10001
+
+#ifndef IPPROTO_MPTCP
+#define IPPROTO_MPTCP 262
+#endif
+
+#ifndef SOL_MPTCP
+#define SOL_MPTCP 284
+#endif
+#ifndef MPTCP_INFO
+#define MPTCP_INFO		1
+#endif
+#ifndef MPTCP_INFO_FLAG_FALLBACK
+#define MPTCP_INFO_FLAG_FALLBACK		_BITUL(0)
+#endif
+#ifndef MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED
+#define MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED	_BITUL(1)
+#endif
 
 #ifndef TCP_CA_NAME_MAX
 #define TCP_CA_NAME_MAX	16
 #endif
 
+struct __mptcp_info {
+	__u8	mptcpi_subflows;
+	__u8	mptcpi_add_addr_signal;
+	__u8	mptcpi_add_addr_accepted;
+	__u8	mptcpi_subflows_max;
+	__u8	mptcpi_add_addr_signal_max;
+	__u8	mptcpi_add_addr_accepted_max;
+	__u32	mptcpi_flags;
+	__u32	mptcpi_token;
+	__u64	mptcpi_write_seq;
+	__u64	mptcpi_snd_una;
+	__u64	mptcpi_rcv_nxt;
+	__u8	mptcpi_local_addr_used;
+	__u8	mptcpi_local_addr_max;
+	__u8	mptcpi_csum_enabled;
+	__u32	mptcpi_retransmits;
+	__u64	mptcpi_bytes_retrans;
+	__u64	mptcpi_bytes_sent;
+	__u64	mptcpi_bytes_received;
+	__u64	mptcpi_bytes_acked;
+};
+
 struct mptcp_storage {
 	__u32 invoked;
 	__u32 is_mptcp;
@@ -20,6 +71,17 @@ struct mptcp_storage {
 	char ca_name[TCP_CA_NAME_MAX];
 };
 
+static int start_mptcp_server(int family, const char *addr_str, __u16 port,
+			      int timeout_ms)
+{
+	struct network_helper_opts opts = {
+		.timeout_ms	= timeout_ms,
+		.proto		= IPPROTO_MPTCP,
+	};
+
+	return start_server_str(family, SOCK_STREAM, addr_str, port, &opts);
+}
+
 static int verify_tsk(int map_fd, int client_fd)
 {
 	int err, cfd = client_fd;
@@ -98,24 +160,14 @@ static int run_test(int cgroup_fd, int server_fd, bool is_mptcp)
 
 	sock_skel = mptcp_sock__open_and_load();
 	if (!ASSERT_OK_PTR(sock_skel, "skel_open_load"))
-		return -EIO;
+		return libbpf_get_error(sock_skel);
 
 	err = mptcp_sock__attach(sock_skel);
 	if (!ASSERT_OK(err, "skel_attach"))
 		goto out;
 
 	prog_fd = bpf_program__fd(sock_skel->progs._sockops);
-	if (!ASSERT_GE(prog_fd, 0, "bpf_program__fd")) {
-		err = -EIO;
-		goto out;
-	}
-
 	map_fd = bpf_map__fd(sock_skel->maps.socket_storage_map);
-	if (!ASSERT_GE(map_fd, 0, "bpf_map__fd")) {
-		err = -EIO;
-		goto out;
-	}
-
 	err = bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_SOCK_OPS, 0);
 	if (!ASSERT_OK(err, "bpf_prog_attach"))
 		goto out;
@@ -138,12 +190,17 @@ out:
 
 static void test_base(void)
 {
+	struct netns_obj *netns = NULL;
 	int server_fd, cgroup_fd;
 
 	cgroup_fd = test__join_cgroup("/mptcp");
 	if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup"))
 		return;
 
+	netns = netns_new(NS_TEST, true);
+	if (!ASSERT_OK_PTR(netns, "netns_new"))
+		goto fail;
+
 	/* without MPTCP */
 	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0);
 	if (!ASSERT_GE(server_fd, 0, "start_server"))
@@ -157,13 +214,363 @@ with_mptcp:
 	/* with MPTCP */
 	server_fd = start_mptcp_server(AF_INET, NULL, 0, 0);
 	if (!ASSERT_GE(server_fd, 0, "start_mptcp_server"))
-		goto close_cgroup_fd;
+		goto fail;
 
 	ASSERT_OK(run_test(cgroup_fd, server_fd, true), "run_test mptcp");
 
 	close(server_fd);
 
-close_cgroup_fd:
+fail:
+	netns_free(netns);
+	close(cgroup_fd);
+}
+
+static void send_byte(int fd)
+{
+	char b = 0x55;
+
+	ASSERT_EQ(write(fd, &b, sizeof(b)), 1, "send single byte");
+}
+
+static int verify_mptcpify(int server_fd, int client_fd)
+{
+	struct __mptcp_info info;
+	socklen_t optlen;
+	int protocol;
+	int err = 0;
+
+	optlen = sizeof(protocol);
+	if (!ASSERT_OK(getsockopt(server_fd, SOL_SOCKET, SO_PROTOCOL, &protocol, &optlen),
+		       "getsockopt(SOL_PROTOCOL)"))
+		return -1;
+
+	if (!ASSERT_EQ(protocol, IPPROTO_MPTCP, "protocol isn't MPTCP"))
+		err++;
+
+	optlen = sizeof(info);
+	if (!ASSERT_OK(getsockopt(client_fd, SOL_MPTCP, MPTCP_INFO, &info, &optlen),
+		       "getsockopt(MPTCP_INFO)"))
+		return -1;
+
+	if (!ASSERT_GE(info.mptcpi_flags, 0, "unexpected mptcpi_flags"))
+		err++;
+	if (!ASSERT_FALSE(info.mptcpi_flags & MPTCP_INFO_FLAG_FALLBACK,
+			  "MPTCP fallback"))
+		err++;
+	if (!ASSERT_TRUE(info.mptcpi_flags & MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED,
+			 "no remote key received"))
+		err++;
+
+	return err;
+}
+
+static int run_mptcpify(int cgroup_fd)
+{
+	int server_fd, client_fd, err = 0;
+	struct mptcpify *mptcpify_skel;
+
+	mptcpify_skel = mptcpify__open_and_load();
+	if (!ASSERT_OK_PTR(mptcpify_skel, "skel_open_load"))
+		return libbpf_get_error(mptcpify_skel);
+
+	mptcpify_skel->bss->pid = getpid();
+
+	err = mptcpify__attach(mptcpify_skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto out;
+
+	/* without MPTCP */
+	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0);
+	if (!ASSERT_GE(server_fd, 0, "start_server")) {
+		err = -EIO;
+		goto out;
+	}
+
+	client_fd = connect_to_fd(server_fd, 0);
+	if (!ASSERT_GE(client_fd, 0, "connect to fd")) {
+		err = -EIO;
+		goto close_server;
+	}
+
+	send_byte(client_fd);
+
+	err = verify_mptcpify(server_fd, client_fd);
+
+	close(client_fd);
+close_server:
+	close(server_fd);
+out:
+	mptcpify__destroy(mptcpify_skel);
+	return err;
+}
+
+static void test_mptcpify(void)
+{
+	struct netns_obj *netns = NULL;
+	int cgroup_fd;
+
+	cgroup_fd = test__join_cgroup("/mptcpify");
+	if (!ASSERT_GE(cgroup_fd, 0, "test__join_cgroup"))
+		return;
+
+	netns = netns_new(NS_TEST, true);
+	if (!ASSERT_OK_PTR(netns, "netns_new"))
+		goto fail;
+
+	ASSERT_OK(run_mptcpify(cgroup_fd), "run_mptcpify");
+
+fail:
+	netns_free(netns);
+	close(cgroup_fd);
+}
+
+static int endpoint_init(char *flags)
+{
+	SYS(fail, "ip -net %s link add veth1 type veth peer name veth2", NS_TEST);
+	SYS(fail, "ip -net %s addr add %s/24 dev veth1", NS_TEST, ADDR_1);
+	SYS(fail, "ip -net %s link set dev veth1 up", NS_TEST);
+	SYS(fail, "ip -net %s addr add %s/24 dev veth2", NS_TEST, ADDR_2);
+	SYS(fail, "ip -net %s link set dev veth2 up", NS_TEST);
+	if (SYS_NOFAIL("ip -net %s mptcp endpoint add %s %s", NS_TEST, ADDR_2, flags)) {
+		printf("'ip mptcp' not supported, skip this test.\n");
+		test__skip();
+		goto fail;
+	}
+
+	return 0;
+fail:
+	return -1;
+}
+
+static void wait_for_new_subflows(int fd)
+{
+	socklen_t len;
+	u8 subflows;
+	int err, i;
+
+	len = sizeof(subflows);
+	/* Wait max 5 sec for new subflows to be created */
+	for (i = 0; i < 50; i++) {
+		err = getsockopt(fd, SOL_MPTCP, MPTCP_INFO, &subflows, &len);
+		if (!err && subflows > 0)
+			break;
+
+		usleep(100000); /* 0.1s */
+	}
+}
+
+static void run_subflow(void)
+{
+	int server_fd, client_fd, err;
+	char new[TCP_CA_NAME_MAX];
+	char cc[TCP_CA_NAME_MAX];
+	unsigned int mark;
+	socklen_t len;
+
+	server_fd = start_mptcp_server(AF_INET, ADDR_1, PORT_1, 0);
+	if (!ASSERT_OK_FD(server_fd, "start_mptcp_server"))
+		return;
+
+	client_fd = connect_to_fd(server_fd, 0);
+	if (!ASSERT_OK_FD(client_fd, "connect_to_fd"))
+		goto close_server;
+
+	send_byte(client_fd);
+	wait_for_new_subflows(client_fd);
+
+	len = sizeof(mark);
+	err = getsockopt(client_fd, SOL_SOCKET, SO_MARK, &mark, &len);
+	if (ASSERT_OK(err, "getsockopt(client_fd, SO_MARK)"))
+		ASSERT_EQ(mark, 0, "mark");
+
+	len = sizeof(new);
+	err = getsockopt(client_fd, SOL_TCP, TCP_CONGESTION, new, &len);
+	if (ASSERT_OK(err, "getsockopt(client_fd, TCP_CONGESTION)")) {
+		get_msk_ca_name(cc);
+		ASSERT_STREQ(new, cc, "cc");
+	}
+
+	close(client_fd);
+close_server:
+	close(server_fd);
+}
+
+static void test_subflow(void)
+{
+	struct mptcp_subflow *skel;
+	struct netns_obj *netns;
+	int cgroup_fd;
+
+	cgroup_fd = test__join_cgroup("/mptcp_subflow");
+	if (!ASSERT_OK_FD(cgroup_fd, "join_cgroup: mptcp_subflow"))
+		return;
+
+	skel = mptcp_subflow__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_load: mptcp_subflow"))
+		goto close_cgroup;
+
+	skel->bss->pid = getpid();
+
+	skel->links.mptcp_subflow =
+		bpf_program__attach_cgroup(skel->progs.mptcp_subflow, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.mptcp_subflow, "attach mptcp_subflow"))
+		goto skel_destroy;
+
+	skel->links._getsockopt_subflow =
+		bpf_program__attach_cgroup(skel->progs._getsockopt_subflow, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links._getsockopt_subflow, "attach _getsockopt_subflow"))
+		goto skel_destroy;
+
+	netns = netns_new(NS_TEST, true);
+	if (!ASSERT_OK_PTR(netns, "netns_new: mptcp_subflow"))
+		goto skel_destroy;
+
+	if (endpoint_init("subflow") < 0)
+		goto close_netns;
+
+	run_subflow();
+
+close_netns:
+	netns_free(netns);
+skel_destroy:
+	mptcp_subflow__destroy(skel);
+close_cgroup:
+	close(cgroup_fd);
+}
+
+/* Test sockmap on MPTCP server handling non-mp-capable clients. */
+static void test_sockmap_with_mptcp_fallback(struct mptcp_sockmap *skel)
+{
+	int listen_fd = -1, client_fd1 = -1, client_fd2 = -1;
+	int server_fd1 = -1, server_fd2 = -1, sent, recvd;
+	char snd[9] = "123456789";
+	char rcv[10];
+
+	/* start server with MPTCP enabled */
+	listen_fd = start_mptcp_server(AF_INET, NULL, 0, 0);
+	if (!ASSERT_OK_FD(listen_fd, "sockmap-fb:start_mptcp_server"))
+		return;
+
+	skel->bss->trace_port = ntohs(get_socket_local_port(listen_fd));
+	skel->bss->sk_index = 0;
+	/* create client without MPTCP enabled */
+	client_fd1 = connect_to_fd_opts(listen_fd, NULL);
+	if (!ASSERT_OK_FD(client_fd1, "sockmap-fb:connect_to_fd"))
+		goto end;
+
+	server_fd1 = accept(listen_fd, NULL, 0);
+	skel->bss->sk_index = 1;
+	client_fd2 = connect_to_fd_opts(listen_fd, NULL);
+	if (!ASSERT_OK_FD(client_fd2, "sockmap-fb:connect_to_fd"))
+		goto end;
+
+	server_fd2 = accept(listen_fd, NULL, 0);
+	/* test normal redirect behavior: data sent by client_fd1 can be
+	 * received by client_fd2
+	 */
+	skel->bss->redirect_idx = 1;
+	sent = send(client_fd1, snd, sizeof(snd), 0);
+	if (!ASSERT_EQ(sent, sizeof(snd), "sockmap-fb:send(client_fd1)"))
+		goto end;
+
+	/* try to recv more bytes to avoid truncation check */
+	recvd = recv(client_fd2, rcv, sizeof(rcv), 0);
+	if (!ASSERT_EQ(recvd, sizeof(snd), "sockmap-fb:recv(client_fd2)"))
+		goto end;
+
+end:
+	if (client_fd1 >= 0)
+		close(client_fd1);
+	if (client_fd2 >= 0)
+		close(client_fd2);
+	if (server_fd1 >= 0)
+		close(server_fd1);
+	if (server_fd2 >= 0)
+		close(server_fd2);
+	close(listen_fd);
+}
+
+/* Test sockmap rejection of MPTCP sockets - both server and client sides. */
+static void test_sockmap_reject_mptcp(struct mptcp_sockmap *skel)
+{
+	int listen_fd = -1, server_fd = -1, client_fd1 = -1;
+	int err, zero = 0;
+
+	/* start server with MPTCP enabled */
+	listen_fd = start_mptcp_server(AF_INET, NULL, 0, 0);
+	if (!ASSERT_OK_FD(listen_fd, "start_mptcp_server"))
+		return;
+
+	skel->bss->trace_port = ntohs(get_socket_local_port(listen_fd));
+	skel->bss->sk_index = 0;
+	/* create client with MPTCP enabled */
+	client_fd1 = connect_to_fd(listen_fd, 0);
+	if (!ASSERT_OK_FD(client_fd1, "connect_to_fd client_fd1"))
+		goto end;
+
+	/* bpf_sock_map_update() called from sockops should reject MPTCP sk */
+	if (!ASSERT_EQ(skel->bss->helper_ret, -EOPNOTSUPP, "should reject"))
+		goto end;
+
+	server_fd = accept(listen_fd, NULL, 0);
+	err = bpf_map_update_elem(bpf_map__fd(skel->maps.sock_map),
+				  &zero, &server_fd, BPF_NOEXIST);
+	if (!ASSERT_EQ(err, -EOPNOTSUPP, "server should be disallowed"))
+		goto end;
+
+	/* MPTCP client should also be disallowed */
+	err = bpf_map_update_elem(bpf_map__fd(skel->maps.sock_map),
+				  &zero, &client_fd1, BPF_NOEXIST);
+	if (!ASSERT_EQ(err, -EOPNOTSUPP, "client should be disallowed"))
+		goto end;
+end:
+	if (client_fd1 >= 0)
+		close(client_fd1);
+	if (server_fd >= 0)
+		close(server_fd);
+	close(listen_fd);
+}
+
+static void test_mptcp_sockmap(void)
+{
+	struct mptcp_sockmap *skel;
+	struct netns_obj *netns;
+	int cgroup_fd, err;
+
+	cgroup_fd = test__join_cgroup("/mptcp_sockmap");
+	if (!ASSERT_OK_FD(cgroup_fd, "join_cgroup: mptcp_sockmap"))
+		return;
+
+	skel = mptcp_sockmap__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_load: mptcp_sockmap"))
+		goto close_cgroup;
+
+	skel->links.mptcp_sockmap_inject =
+		bpf_program__attach_cgroup(skel->progs.mptcp_sockmap_inject, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.mptcp_sockmap_inject, "attach sockmap"))
+		goto skel_destroy;
+
+	err = bpf_prog_attach(bpf_program__fd(skel->progs.mptcp_sockmap_redirect),
+			      bpf_map__fd(skel->maps.sock_map),
+			      BPF_SK_SKB_STREAM_VERDICT, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach stream verdict"))
+		goto skel_destroy;
+
+	netns = netns_new(NS_TEST, true);
+	if (!ASSERT_OK_PTR(netns, "netns_new: mptcp_sockmap"))
+		goto skel_destroy;
+
+	if (endpoint_init("subflow") < 0)
+		goto close_netns;
+
+	test_sockmap_with_mptcp_fallback(skel);
+	test_sockmap_reject_mptcp(skel);
+
+close_netns:
+	netns_free(netns);
+skel_destroy:
+	mptcp_sockmap__destroy(skel);
+close_cgroup:
 	close(cgroup_fd);
 }
 
@@ -171,4 +578,10 @@ void test_mptcp(void)
 {
 	if (test__start_subtest("base"))
 		test_base();
+	if (test__start_subtest("mptcpify"))
+		test_mptcpify();
+	if (test__start_subtest("subflow"))
+		test_subflow();
+	if (test__start_subtest("sockmap"))
+		test_mptcp_sockmap();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/nested_trust.c b/tools/testing/selftests/bpf/prog_tests/nested_trust.c
new file mode 100644
index 000000000000..54a112ad5f9c
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/nested_trust.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <test_progs.h>
+#include "nested_trust_failure.skel.h"
+#include "nested_trust_success.skel.h"
+#include "nested_acquire.skel.h"
+
+void test_nested_trust(void)
+{
+	RUN_TESTS(nested_trust_success);
+	RUN_TESTS(nested_trust_failure);
+
+	if (env.has_testmod)
+		RUN_TESTS(nested_acquire);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/net_timestamping.c b/tools/testing/selftests/bpf/prog_tests/net_timestamping.c
new file mode 100644
index 000000000000..dbfd87499b6b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/net_timestamping.c
@@ -0,0 +1,239 @@
+#include <linux/net_tstamp.h>
+#include <sys/time.h>
+#include <linux/errqueue.h>
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "net_timestamping.skel.h"
+
+#define CG_NAME "/net-timestamping-test"
+#define NSEC_PER_SEC    1000000000LL
+
+static const char addr4_str[] = "127.0.0.1";
+static const char addr6_str[] = "::1";
+static struct net_timestamping *skel;
+static const int cfg_payload_len = 30;
+static struct timespec usr_ts;
+static u64 delay_tolerance_nsec = 10000000000; /* 10 seconds */
+int SK_TS_SCHED;
+int SK_TS_TXSW;
+int SK_TS_ACK;
+
+static int64_t timespec_to_ns64(struct timespec *ts)
+{
+	return ts->tv_sec * NSEC_PER_SEC + ts->tv_nsec;
+}
+
+static void validate_key(int tskey, int tstype)
+{
+	static int expected_tskey = -1;
+
+	if (tstype == SCM_TSTAMP_SCHED)
+		expected_tskey = cfg_payload_len - 1;
+
+	ASSERT_EQ(expected_tskey, tskey, "tskey mismatch");
+
+	expected_tskey = tskey;
+}
+
+static void validate_timestamp(struct timespec *cur, struct timespec *prev)
+{
+	int64_t cur_ns, prev_ns;
+
+	cur_ns = timespec_to_ns64(cur);
+	prev_ns = timespec_to_ns64(prev);
+
+	ASSERT_LT(cur_ns - prev_ns, delay_tolerance_nsec, "latency");
+}
+
+static void test_socket_timestamp(struct scm_timestamping *tss, int tstype,
+				  int tskey)
+{
+	static struct timespec prev_ts;
+
+	validate_key(tskey, tstype);
+
+	switch (tstype) {
+	case SCM_TSTAMP_SCHED:
+		validate_timestamp(&tss->ts[0], &usr_ts);
+		SK_TS_SCHED += 1;
+		break;
+	case SCM_TSTAMP_SND:
+		validate_timestamp(&tss->ts[0], &prev_ts);
+		SK_TS_TXSW += 1;
+		break;
+	case SCM_TSTAMP_ACK:
+		validate_timestamp(&tss->ts[0], &prev_ts);
+		SK_TS_ACK += 1;
+		break;
+	}
+
+	prev_ts = tss->ts[0];
+}
+
+static void test_recv_errmsg_cmsg(struct msghdr *msg)
+{
+	struct sock_extended_err *serr = NULL;
+	struct scm_timestamping *tss = NULL;
+	struct cmsghdr *cm;
+
+	for (cm = CMSG_FIRSTHDR(msg);
+	     cm && cm->cmsg_len;
+	     cm = CMSG_NXTHDR(msg, cm)) {
+		if (cm->cmsg_level == SOL_SOCKET &&
+		    cm->cmsg_type == SCM_TIMESTAMPING) {
+			tss = (void *)CMSG_DATA(cm);
+		} else if ((cm->cmsg_level == SOL_IP &&
+			    cm->cmsg_type == IP_RECVERR) ||
+			   (cm->cmsg_level == SOL_IPV6 &&
+			    cm->cmsg_type == IPV6_RECVERR) ||
+			   (cm->cmsg_level == SOL_PACKET &&
+			    cm->cmsg_type == PACKET_TX_TIMESTAMP)) {
+			serr = (void *)CMSG_DATA(cm);
+			ASSERT_EQ(serr->ee_origin, SO_EE_ORIGIN_TIMESTAMPING,
+				  "cmsg type");
+		}
+
+		if (serr && tss)
+			test_socket_timestamp(tss, serr->ee_info,
+					      serr->ee_data);
+	}
+}
+
+static bool socket_recv_errmsg(int fd)
+{
+	static char ctrl[1024 /* overprovision*/];
+	char data[cfg_payload_len];
+	static struct msghdr msg;
+	struct iovec entry;
+	int n = 0;
+
+	memset(&msg, 0, sizeof(msg));
+	memset(&entry, 0, sizeof(entry));
+	memset(ctrl, 0, sizeof(ctrl));
+
+	entry.iov_base = data;
+	entry.iov_len = cfg_payload_len;
+	msg.msg_iov = &entry;
+	msg.msg_iovlen = 1;
+	msg.msg_name = NULL;
+	msg.msg_namelen = 0;
+	msg.msg_control = ctrl;
+	msg.msg_controllen = sizeof(ctrl);
+
+	n = recvmsg(fd, &msg, MSG_ERRQUEUE);
+	if (n == -1)
+		ASSERT_EQ(errno, EAGAIN, "recvmsg MSG_ERRQUEUE");
+
+	if (n >= 0)
+		test_recv_errmsg_cmsg(&msg);
+
+	return n == -1;
+}
+
+static void test_socket_timestamping(int fd)
+{
+	while (!socket_recv_errmsg(fd));
+
+	ASSERT_EQ(SK_TS_SCHED, 1, "SCM_TSTAMP_SCHED");
+	ASSERT_EQ(SK_TS_TXSW, 1, "SCM_TSTAMP_SND");
+	ASSERT_EQ(SK_TS_ACK, 1, "SCM_TSTAMP_ACK");
+
+	SK_TS_SCHED = 0;
+	SK_TS_TXSW = 0;
+	SK_TS_ACK = 0;
+}
+
+static void test_tcp(int family, bool enable_socket_timestamping)
+{
+	struct net_timestamping__bss *bss;
+	char buf[cfg_payload_len];
+	int sfd = -1, cfd = -1;
+	unsigned int sock_opt;
+	struct netns_obj *ns;
+	int cg_fd;
+	int ret;
+
+	cg_fd = test__join_cgroup(CG_NAME);
+	if (!ASSERT_OK_FD(cg_fd, "join cgroup"))
+		return;
+
+	ns = netns_new("net_timestamping_ns", true);
+	if (!ASSERT_OK_PTR(ns, "create ns"))
+		goto out;
+
+	skel = net_timestamping__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open and load skel"))
+		goto out;
+
+	if (!ASSERT_OK(net_timestamping__attach(skel), "attach skel"))
+		goto out;
+
+	skel->links.skops_sockopt =
+		bpf_program__attach_cgroup(skel->progs.skops_sockopt, cg_fd);
+	if (!ASSERT_OK_PTR(skel->links.skops_sockopt, "attach cgroup"))
+		goto out;
+
+	bss = skel->bss;
+	memset(bss, 0, sizeof(*bss));
+
+	skel->bss->monitored_pid = getpid();
+
+	sfd = start_server(family, SOCK_STREAM,
+			   family == AF_INET6 ? addr6_str : addr4_str, 0, 0);
+	if (!ASSERT_OK_FD(sfd, "start_server"))
+		goto out;
+
+	cfd = connect_to_fd(sfd, 0);
+	if (!ASSERT_OK_FD(cfd, "connect_to_fd_server"))
+		goto out;
+
+	if (enable_socket_timestamping) {
+		sock_opt = SOF_TIMESTAMPING_SOFTWARE |
+			   SOF_TIMESTAMPING_OPT_ID |
+			   SOF_TIMESTAMPING_TX_SCHED |
+			   SOF_TIMESTAMPING_TX_SOFTWARE |
+			   SOF_TIMESTAMPING_TX_ACK;
+		ret = setsockopt(cfd, SOL_SOCKET, SO_TIMESTAMPING,
+				 (char *) &sock_opt, sizeof(sock_opt));
+		if (!ASSERT_OK(ret, "setsockopt SO_TIMESTAMPING"))
+			goto out;
+
+		ret = clock_gettime(CLOCK_REALTIME, &usr_ts);
+		if (!ASSERT_OK(ret, "get user time"))
+			goto out;
+	}
+
+	ret = write(cfd, buf, sizeof(buf));
+	if (!ASSERT_EQ(ret, sizeof(buf), "send to server"))
+		goto out;
+
+	if (enable_socket_timestamping)
+		test_socket_timestamping(cfd);
+
+	ASSERT_EQ(bss->nr_active, 1, "nr_active");
+	ASSERT_EQ(bss->nr_snd, 2, "nr_snd");
+	ASSERT_EQ(bss->nr_sched, 1, "nr_sched");
+	ASSERT_EQ(bss->nr_txsw, 1, "nr_txsw");
+	ASSERT_EQ(bss->nr_ack, 1, "nr_ack");
+
+out:
+	if (sfd >= 0)
+		close(sfd);
+	if (cfd >= 0)
+		close(cfd);
+	net_timestamping__destroy(skel);
+	netns_free(ns);
+	close(cg_fd);
+}
+
+void test_net_timestamping(void)
+{
+	if (test__start_subtest("INET4: bpf timestamping"))
+		test_tcp(AF_INET, false);
+	if (test__start_subtest("INET4: bpf and socket timestamping"))
+		test_tcp(AF_INET, true);
+	if (test__start_subtest("INET6: bpf timestamping"))
+		test_tcp(AF_INET6, false);
+	if (test__start_subtest("INET6: bpf and socket timestamping"))
+		test_tcp(AF_INET6, true);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/netcnt.c b/tools/testing/selftests/bpf/prog_tests/netcnt.c
index d3915c58d0e1..c3333edd029f 100644
--- a/tools/testing/selftests/bpf/prog_tests/netcnt.c
+++ b/tools/testing/selftests/bpf/prog_tests/netcnt.c
@@ -67,12 +67,12 @@ void serial_test_netcnt(void)
 	}
 
 	/* No packets should be lost */
-	ASSERT_EQ(packets, 10000, "packets");
+	ASSERT_GE(packets, 10000, "packets");
 
 	/* Let's check that bytes counter matches the number of packets
 	 * multiplied by the size of ipv6 ICMP packet.
 	 */
-	ASSERT_EQ(bytes, packets * 104, "bytes");
+	ASSERT_GE(bytes, packets * 104, "bytes");
 
 err:
 	if (cg_fd != -1)
diff --git a/tools/testing/selftests/bpf/prog_tests/netfilter_link_attach.c b/tools/testing/selftests/bpf/prog_tests/netfilter_link_attach.c
new file mode 100644
index 000000000000..2f52fa2641ba
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/netfilter_link_attach.c
@@ -0,0 +1,124 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <netinet/in.h>
+#include <linux/netfilter.h>
+
+#include "test_progs.h"
+#include "test_netfilter_link_attach.skel.h"
+
+struct nf_link_test {
+	__u32 pf;
+	__u32 hooknum;
+	__s32 priority;
+	__u32 flags;
+
+	bool expect_success;
+	const char * const name;
+};
+
+static const struct nf_link_test nf_hook_link_tests[] = {
+	{ .name = "allzero", },
+	{ .pf = NFPROTO_NUMPROTO, .name = "invalid-pf", },
+	{ .pf = NFPROTO_IPV4, .hooknum = 42, .name = "invalid-hooknum", },
+	{ .pf = NFPROTO_IPV4, .priority = INT_MIN, .name = "invalid-priority-min", },
+	{ .pf = NFPROTO_IPV4, .priority = INT_MAX, .name = "invalid-priority-max", },
+	{ .pf = NFPROTO_IPV4, .flags = UINT_MAX, .name = "invalid-flags", },
+
+	{ .pf = NFPROTO_INET, .priority = 1, .name = "invalid-inet-not-supported", },
+
+	{
+		.pf = NFPROTO_IPV4,
+		.hooknum = NF_INET_POST_ROUTING,
+		.priority = -10000,
+		.flags = 0,
+		.expect_success = true,
+		.name = "attach ipv4",
+	},
+	{
+		.pf = NFPROTO_IPV6,
+		.hooknum = NF_INET_FORWARD,
+		.priority =  10001,
+		.flags = BPF_F_NETFILTER_IP_DEFRAG,
+		.expect_success = true,
+		.name = "attach ipv6",
+	},
+};
+
+static void verify_netfilter_link_info(struct bpf_link *link, const struct nf_link_test nf_expected)
+{
+	struct bpf_link_info info;
+	__u32 len = sizeof(info);
+	int err, fd;
+
+	memset(&info, 0, len);
+
+	fd = bpf_link__fd(link);
+	err = bpf_link_get_info_by_fd(fd, &info, &len);
+	ASSERT_OK(err, "get_link_info");
+
+	ASSERT_EQ(info.type, BPF_LINK_TYPE_NETFILTER, "info link type");
+	ASSERT_EQ(info.netfilter.pf, nf_expected.pf, "info nf protocol family");
+	ASSERT_EQ(info.netfilter.hooknum, nf_expected.hooknum, "info nf hooknum");
+	ASSERT_EQ(info.netfilter.priority, nf_expected.priority, "info nf priority");
+	ASSERT_EQ(info.netfilter.flags, nf_expected.flags, "info nf flags");
+}
+
+void test_netfilter_link_attach(void)
+{
+	struct test_netfilter_link_attach *skel;
+	struct bpf_program *prog;
+	LIBBPF_OPTS(bpf_netfilter_opts, opts);
+	int i;
+
+	skel = test_netfilter_link_attach__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_netfilter_link_attach__open_and_load"))
+		goto out;
+
+	prog = skel->progs.nf_link_attach_test;
+	if (!ASSERT_OK_PTR(prog, "attach program"))
+		goto out;
+
+	for (i = 0; i < ARRAY_SIZE(nf_hook_link_tests); i++) {
+		struct bpf_link *link;
+
+		if (!test__start_subtest(nf_hook_link_tests[i].name))
+			continue;
+
+#define X(opts, m, i)	opts.m = nf_hook_link_tests[(i)].m
+		X(opts, pf, i);
+		X(opts, hooknum, i);
+		X(opts, priority, i);
+		X(opts, flags, i);
+#undef X
+		link = bpf_program__attach_netfilter(prog, &opts);
+		if (nf_hook_link_tests[i].expect_success) {
+			struct bpf_link *link2;
+
+			if (!ASSERT_OK_PTR(link, "program attach successful"))
+				continue;
+
+			verify_netfilter_link_info(link, nf_hook_link_tests[i]);
+
+			link2 = bpf_program__attach_netfilter(prog, &opts);
+			ASSERT_ERR_PTR(link2, "attach program with same pf/hook/priority");
+
+			if (!ASSERT_OK(bpf_link__destroy(link), "link destroy"))
+				break;
+
+			link2 = bpf_program__attach_netfilter(prog, &opts);
+			if (!ASSERT_OK_PTR(link2, "program reattach successful"))
+				continue;
+
+			verify_netfilter_link_info(link2, nf_hook_link_tests[i]);
+
+			if (!ASSERT_OK(bpf_link__destroy(link2), "link destroy"))
+				break;
+		} else {
+			ASSERT_ERR_PTR(link, "program load failure");
+		}
+	}
+
+out:
+	test_netfilter_link_attach__destroy(skel);
+}
+
diff --git a/tools/testing/selftests/bpf/prog_tests/netns_cookie.c b/tools/testing/selftests/bpf/prog_tests/netns_cookie.c
index 71d8f3ba7d6b..e00cd34586dd 100644
--- a/tools/testing/selftests/bpf/prog_tests/netns_cookie.c
+++ b/tools/testing/selftests/bpf/prog_tests/netns_cookie.c
@@ -8,12 +8,16 @@
 #define SO_NETNS_COOKIE 71
 #endif
 
+#define loopback 1
+
 static int duration;
 
 void test_netns_cookie(void)
 {
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
 	int server_fd = -1, client_fd = -1, cgroup_fd = -1;
-	int err, val, ret, map, verdict;
+	int err, val, ret, map, verdict, tc_fd;
 	struct netns_cookie_prog *skel;
 	uint64_t cookie_expected_value;
 	socklen_t vallen = sizeof(cookie_expected_value);
@@ -29,45 +33,63 @@ void test_netns_cookie(void)
 
 	skel->links.get_netns_cookie_sockops = bpf_program__attach_cgroup(
 		skel->progs.get_netns_cookie_sockops, cgroup_fd);
-	if (!ASSERT_OK_PTR(skel->links.get_netns_cookie_sockops, "prog_attach"))
+	if (!ASSERT_OK_PTR(skel->links.get_netns_cookie_sockops, "prog_attach_sockops"))
 		goto done;
 
 	verdict = bpf_program__fd(skel->progs.get_netns_cookie_sk_msg);
 	map = bpf_map__fd(skel->maps.sock_map);
 	err = bpf_prog_attach(verdict, map, BPF_SK_MSG_VERDICT, 0);
-	if (!ASSERT_OK(err, "prog_attach"))
+	if (!ASSERT_OK(err, "prog_attach_sk_msg"))
+		goto done;
+
+	tc_fd = bpf_program__fd(skel->progs.get_netns_cookie_tcx);
+	err = bpf_prog_attach_opts(tc_fd, loopback, BPF_TCX_INGRESS, &opta);
+	if (!ASSERT_OK(err, "prog_attach_tcx"))
 		goto done;
 
+	skel->links.get_netns_cookie_cgroup_skb = bpf_program__attach_cgroup(
+		skel->progs.get_netns_cookie_cgroup_skb, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.get_netns_cookie_cgroup_skb, "prog_attach_cgroup_skb"))
+		goto cleanup_tc;
+
 	server_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
 	if (CHECK(server_fd < 0, "start_server", "errno %d\n", errno))
-		goto done;
+		goto cleanup_tc;
 
 	client_fd = connect_to_fd(server_fd, 0);
 	if (CHECK(client_fd < 0, "connect_to_fd", "errno %d\n", errno))
-		goto done;
+		goto cleanup_tc;
 
 	ret = send(client_fd, send_msg, sizeof(send_msg), 0);
 	if (CHECK(ret != sizeof(send_msg), "send(msg)", "ret:%d\n", ret))
-		goto done;
+		goto cleanup_tc;
 
 	err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.sockops_netns_cookies),
 				  &client_fd, &val);
 	if (!ASSERT_OK(err, "map_lookup(sockops_netns_cookies)"))
-		goto done;
+		goto cleanup_tc;
 
 	err = getsockopt(client_fd, SOL_SOCKET, SO_NETNS_COOKIE,
 			 &cookie_expected_value, &vallen);
 	if (!ASSERT_OK(err, "getsockopt"))
-		goto done;
+		goto cleanup_tc;
 
-	ASSERT_EQ(val, cookie_expected_value, "cookie_value");
+	ASSERT_EQ(val, cookie_expected_value, "cookie_value_sockops");
 
 	err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.sk_msg_netns_cookies),
 				  &client_fd, &val);
 	if (!ASSERT_OK(err, "map_lookup(sk_msg_netns_cookies)"))
-		goto done;
+		goto cleanup_tc;
+
+	ASSERT_EQ(val, cookie_expected_value, "cookie_value_sk_msg");
+	ASSERT_EQ(skel->bss->tcx_init_netns_cookie, cookie_expected_value, "cookie_value_init_tcx");
+	ASSERT_EQ(skel->bss->tcx_netns_cookie, cookie_expected_value, "cookie_value_tcx");
+	ASSERT_EQ(skel->bss->cgroup_skb_init_netns_cookie, cookie_expected_value, "cookie_value_init_cgroup_skb");
+	ASSERT_EQ(skel->bss->cgroup_skb_netns_cookie, cookie_expected_value, "cookie_value_cgroup_skb");
 
-	ASSERT_EQ(val, cookie_expected_value, "cookie_value");
+cleanup_tc:
+	err = bpf_prog_detach_opts(tc_fd, loopback, BPF_TCX_INGRESS, &optd);
+	ASSERT_OK(err, "prog_detach");
 
 done:
 	if (server_fd != -1)
diff --git a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
index 24d493482ffc..99c953f2be21 100644
--- a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
+++ b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
@@ -11,78 +11,217 @@
 #include <sched.h>
 #include <sys/wait.h>
 #include <sys/mount.h>
-#include <sys/fcntl.h>
+#include <fcntl.h>
+#include "network_helpers.h"
 
 #define STACK_SIZE (1024 * 1024)
 static char child_stack[STACK_SIZE];
 
-static int test_current_pid_tgid(void *args)
+static int get_pid_tgid(pid_t *pid, pid_t *tgid,
+			struct test_ns_current_pid_tgid__bss *bss)
 {
-	struct test_ns_current_pid_tgid__bss  *bss;
-	struct test_ns_current_pid_tgid *skel;
-	int err = -1, duration = 0;
-	pid_t tgid, pid;
 	struct stat st;
+	int err;
 
-	skel = test_ns_current_pid_tgid__open_and_load();
-	if (CHECK(!skel, "skel_open_load", "failed to load skeleton\n"))
-		goto cleanup;
-
-	pid = syscall(SYS_gettid);
-	tgid = getpid();
+	*pid = sys_gettid();
+	*tgid = getpid();
 
 	err = stat("/proc/self/ns/pid", &st);
-	if (CHECK(err, "stat", "failed /proc/self/ns/pid: %d\n", err))
-		goto cleanup;
+	if (!ASSERT_OK(err, "stat /proc/self/ns/pid"))
+		return err;
 
-	bss = skel->bss;
 	bss->dev = st.st_dev;
 	bss->ino = st.st_ino;
 	bss->user_pid = 0;
 	bss->user_tgid = 0;
+	return 0;
+}
+
+static int test_current_pid_tgid_tp(void *args)
+{
+	struct test_ns_current_pid_tgid__bss  *bss;
+	struct test_ns_current_pid_tgid *skel;
+	int ret = -1, err;
+	pid_t tgid, pid;
+
+	skel = test_ns_current_pid_tgid__open();
+	if (!ASSERT_OK_PTR(skel, "test_ns_current_pid_tgid__open"))
+		return ret;
+
+	bpf_program__set_autoload(skel->progs.tp_handler, true);
+
+	err = test_ns_current_pid_tgid__load(skel);
+	if (!ASSERT_OK(err, "test_ns_current_pid_tgid__load"))
+		goto cleanup;
+
+	bss = skel->bss;
+	if (get_pid_tgid(&pid, &tgid, bss))
+		goto cleanup;
 
 	err = test_ns_current_pid_tgid__attach(skel);
-	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+	if (!ASSERT_OK(err, "test_ns_current_pid_tgid__attach"))
 		goto cleanup;
 
 	/* trigger tracepoint */
 	usleep(1);
-	ASSERT_EQ(bss->user_pid, pid, "pid");
-	ASSERT_EQ(bss->user_tgid, tgid, "tgid");
-	err = 0;
+	if (!ASSERT_EQ(bss->user_pid, pid, "pid"))
+		goto cleanup;
+	if (!ASSERT_EQ(bss->user_tgid, tgid, "tgid"))
+		goto cleanup;
+	ret = 0;
+
+cleanup:
+	test_ns_current_pid_tgid__destroy(skel);
+	return ret;
+}
+
+static int test_current_pid_tgid_cgrp(void *args)
+{
+	struct test_ns_current_pid_tgid__bss *bss;
+	struct test_ns_current_pid_tgid *skel;
+	int server_fd = -1, ret = -1, err;
+	int cgroup_fd = *(int *)args;
+	pid_t tgid, pid;
+
+	skel = test_ns_current_pid_tgid__open();
+	if (!ASSERT_OK_PTR(skel, "test_ns_current_pid_tgid__open"))
+		return ret;
+
+	bpf_program__set_autoload(skel->progs.cgroup_bind4, true);
+
+	err = test_ns_current_pid_tgid__load(skel);
+	if (!ASSERT_OK(err, "test_ns_current_pid_tgid__load"))
+		goto cleanup;
+
+	bss = skel->bss;
+	if (get_pid_tgid(&pid, &tgid, bss))
+		goto cleanup;
+
+	skel->links.cgroup_bind4 = bpf_program__attach_cgroup(
+		skel->progs.cgroup_bind4, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.cgroup_bind4, "bpf_program__attach_cgroup"))
+		goto cleanup;
+
+	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, 0, 0);
+	if (!ASSERT_GE(server_fd, 0, "start_server"))
+		goto cleanup;
+
+	if (!ASSERT_EQ(bss->user_pid, pid, "pid"))
+		goto cleanup;
+	if (!ASSERT_EQ(bss->user_tgid, tgid, "tgid"))
+		goto cleanup;
+	ret = 0;
 
 cleanup:
-	 test_ns_current_pid_tgid__destroy(skel);
+	if (server_fd >= 0)
+		close(server_fd);
+	test_ns_current_pid_tgid__destroy(skel);
+	return ret;
+}
+
+static int test_current_pid_tgid_sk_msg(void *args)
+{
+	int verdict, map, server_fd = -1, client_fd = -1;
+	struct test_ns_current_pid_tgid__bss *bss;
+	static const char send_msg[] = "message";
+	struct test_ns_current_pid_tgid *skel;
+	int ret = -1, err, key = 0;
+	pid_t tgid, pid;
+
+	skel = test_ns_current_pid_tgid__open();
+	if (!ASSERT_OK_PTR(skel, "test_ns_current_pid_tgid__open"))
+		return ret;
+
+	bpf_program__set_autoload(skel->progs.sk_msg, true);
+
+	err = test_ns_current_pid_tgid__load(skel);
+	if (!ASSERT_OK(err, "test_ns_current_pid_tgid__load"))
+		goto cleanup;
+
+	bss = skel->bss;
+	if (get_pid_tgid(&pid, &tgid, skel->bss))
+		goto cleanup;
+
+	verdict = bpf_program__fd(skel->progs.sk_msg);
+	map = bpf_map__fd(skel->maps.sock_map);
+	err = bpf_prog_attach(verdict, map, BPF_SK_MSG_VERDICT, 0);
+	if (!ASSERT_OK(err, "prog_attach"))
+		goto cleanup;
+
+	server_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
+	if (!ASSERT_GE(server_fd, 0, "start_server"))
+		goto cleanup;
 
-	return err;
+	client_fd = connect_to_fd(server_fd, 0);
+	if (!ASSERT_GE(client_fd, 0, "connect_to_fd"))
+		goto cleanup;
+
+	err = bpf_map_update_elem(map, &key, &client_fd, BPF_ANY);
+	if (!ASSERT_OK(err, "bpf_map_update_elem"))
+		goto cleanup;
+
+	err = send(client_fd, send_msg, sizeof(send_msg), 0);
+	if (!ASSERT_EQ(err, sizeof(send_msg), "send(msg)"))
+		goto cleanup;
+
+	if (!ASSERT_EQ(bss->user_pid, pid, "pid"))
+		goto cleanup;
+	if (!ASSERT_EQ(bss->user_tgid, tgid, "tgid"))
+		goto cleanup;
+	ret = 0;
+
+cleanup:
+	if (server_fd >= 0)
+		close(server_fd);
+	if (client_fd >= 0)
+		close(client_fd);
+	test_ns_current_pid_tgid__destroy(skel);
+	return ret;
 }
 
-static void test_ns_current_pid_tgid_new_ns(void)
+static void test_ns_current_pid_tgid_new_ns(int (*fn)(void *), void *arg)
 {
-	int wstatus, duration = 0;
+	int wstatus;
 	pid_t cpid;
 
 	/* Create a process in a new namespace, this process
 	 * will be the init process of this new namespace hence will be pid 1.
 	 */
-	cpid = clone(test_current_pid_tgid, child_stack + STACK_SIZE,
-		     CLONE_NEWPID | SIGCHLD, NULL);
+	cpid = clone(fn, child_stack + STACK_SIZE,
+		     CLONE_NEWPID | SIGCHLD, arg);
 
-	if (CHECK(cpid == -1, "clone", "%s\n", strerror(errno)))
+	if (!ASSERT_NEQ(cpid, -1, "clone"))
 		return;
 
-	if (CHECK(waitpid(cpid, &wstatus, 0) == -1, "waitpid", "%s\n", strerror(errno)))
+	if (!ASSERT_NEQ(waitpid(cpid, &wstatus, 0), -1, "waitpid"))
 		return;
 
-	if (CHECK(WEXITSTATUS(wstatus) != 0, "newns_pidtgid", "failed"))
+	if (!ASSERT_OK(WEXITSTATUS(wstatus), "newns_pidtgid"))
 		return;
 }
 
 /* TODO: use a different tracepoint */
-void serial_test_ns_current_pid_tgid(void)
+void serial_test_current_pid_tgid(void)
 {
-	if (test__start_subtest("ns_current_pid_tgid_root_ns"))
-		test_current_pid_tgid(NULL);
-	if (test__start_subtest("ns_current_pid_tgid_new_ns"))
-		test_ns_current_pid_tgid_new_ns();
+	if (test__start_subtest("root_ns_tp"))
+		test_current_pid_tgid_tp(NULL);
+	if (test__start_subtest("new_ns_tp"))
+		test_ns_current_pid_tgid_new_ns(test_current_pid_tgid_tp, NULL);
 }
+
+void test_ns_current_pid_tgid_cgrp(void)
+{
+	int cgroup_fd = test__join_cgroup("/sock_addr");
+
+	if (ASSERT_OK_FD(cgroup_fd, "join_cgroup")) {
+		test_ns_current_pid_tgid_new_ns(test_current_pid_tgid_cgrp, &cgroup_fd);
+		close(cgroup_fd);
+	}
+}
+
+void test_ns_current_pid_tgid_sk_msg(void)
+{
+	test_ns_current_pid_tgid_new_ns(test_current_pid_tgid_sk_msg, NULL);
+}
+
+
diff --git a/tools/testing/selftests/bpf/prog_tests/parse_tcp_hdr_opt.c b/tools/testing/selftests/bpf/prog_tests/parse_tcp_hdr_opt.c
new file mode 100644
index 000000000000..e9c07d561ded
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/parse_tcp_hdr_opt.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "test_parse_tcp_hdr_opt.skel.h"
+#include "test_parse_tcp_hdr_opt_dynptr.skel.h"
+#include "test_tcp_hdr_options.h"
+
+struct test_pkt {
+	struct ipv6_packet pk6_v6;
+	u8 options[16];
+} __packed;
+
+struct test_pkt pkt = {
+	.pk6_v6.eth.h_proto = __bpf_constant_htons(ETH_P_IPV6),
+	.pk6_v6.iph.nexthdr = IPPROTO_TCP,
+	.pk6_v6.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+	.pk6_v6.tcp.urg_ptr = 123,
+	.pk6_v6.tcp.doff = 9, /* 16 bytes of options */
+
+	.options = {
+		TCPOPT_MSS, 4, 0x05, 0xB4, TCPOPT_NOP, TCPOPT_NOP,
+		0, 6, 0xBB, 0xBB, 0xBB, 0xBB, TCPOPT_EOL
+	},
+};
+
+static void test_parse_opt(void)
+{
+	struct test_parse_tcp_hdr_opt *skel;
+	struct bpf_program *prog;
+	char buf[128];
+	int err;
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		    .data_in = &pkt,
+		    .data_size_in = sizeof(pkt),
+		    .data_out = buf,
+		    .data_size_out = sizeof(buf),
+		    .repeat = 3,
+	);
+
+	skel = test_parse_tcp_hdr_opt__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return;
+
+	pkt.options[6] = skel->rodata->tcp_hdr_opt_kind_tpr;
+	prog = skel->progs.xdp_ingress_v6;
+
+	err = bpf_prog_test_run_opts(bpf_program__fd(prog), &topts);
+	ASSERT_OK(err, "ipv6 test_run");
+	ASSERT_EQ(topts.retval, XDP_PASS, "ipv6 test_run retval");
+	ASSERT_EQ(skel->bss->server_id, 0xBBBBBBBB, "server id");
+
+	test_parse_tcp_hdr_opt__destroy(skel);
+}
+
+static void test_parse_opt_dynptr(void)
+{
+	struct test_parse_tcp_hdr_opt_dynptr *skel;
+	struct bpf_program *prog;
+	char buf[128];
+	int err;
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		    .data_in = &pkt,
+		    .data_size_in = sizeof(pkt),
+		    .data_out = buf,
+		    .data_size_out = sizeof(buf),
+		    .repeat = 3,
+	);
+
+	skel = test_parse_tcp_hdr_opt_dynptr__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return;
+
+	pkt.options[6] = skel->rodata->tcp_hdr_opt_kind_tpr;
+	prog = skel->progs.xdp_ingress_v6;
+
+	err = bpf_prog_test_run_opts(bpf_program__fd(prog), &topts);
+	ASSERT_OK(err, "ipv6 test_run");
+	ASSERT_EQ(topts.retval, XDP_PASS, "ipv6 test_run retval");
+	ASSERT_EQ(skel->bss->server_id, 0xBBBBBBBB, "server id");
+
+	test_parse_tcp_hdr_opt_dynptr__destroy(skel);
+}
+
+void test_parse_tcp_hdr_opt(void)
+{
+	if (test__start_subtest("parse_tcp_hdr_opt"))
+		test_parse_opt();
+	if (test__start_subtest("parse_tcp_hdr_opt_dynptr"))
+		test_parse_opt_dynptr();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c b/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
new file mode 100644
index 000000000000..343da65864d6
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/percpu_alloc.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include "percpu_alloc_array.skel.h"
+#include "percpu_alloc_cgrp_local_storage.skel.h"
+#include "percpu_alloc_fail.skel.h"
+
+static void test_array(void)
+{
+	struct percpu_alloc_array *skel;
+	int err, prog_fd;
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+
+	skel = percpu_alloc_array__open();
+	if (!ASSERT_OK_PTR(skel, "percpu_alloc_array__open"))
+		return;
+
+	bpf_program__set_autoload(skel->progs.test_array_map_1, true);
+	bpf_program__set_autoload(skel->progs.test_array_map_2, true);
+	bpf_program__set_autoload(skel->progs.test_array_map_3, true);
+	bpf_program__set_autoload(skel->progs.test_array_map_4, true);
+
+	skel->bss->my_pid = getpid();
+	skel->rodata->nr_cpus = libbpf_num_possible_cpus();
+
+	err = percpu_alloc_array__load(skel);
+	if (!ASSERT_OK(err, "percpu_alloc_array__load"))
+		goto out;
+
+	err = percpu_alloc_array__attach(skel);
+	if (!ASSERT_OK(err, "percpu_alloc_array__attach"))
+		goto out;
+
+	prog_fd = bpf_program__fd(skel->progs.test_array_map_1);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run array_map 1-4");
+	ASSERT_EQ(topts.retval, 0, "test_run array_map 1-4");
+	ASSERT_EQ(skel->bss->cpu0_field_d, 2, "cpu0_field_d");
+	ASSERT_EQ(skel->bss->sum_field_c, 1, "sum_field_c");
+out:
+	percpu_alloc_array__destroy(skel);
+}
+
+static void test_array_sleepable(void)
+{
+	struct percpu_alloc_array *skel;
+	int err, prog_fd;
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+
+	skel = percpu_alloc_array__open();
+	if (!ASSERT_OK_PTR(skel, "percpu_alloc__open"))
+		return;
+
+	bpf_program__set_autoload(skel->progs.test_array_map_10, true);
+
+	skel->bss->my_pid = getpid();
+	skel->rodata->nr_cpus = libbpf_num_possible_cpus();
+
+	err = percpu_alloc_array__load(skel);
+	if (!ASSERT_OK(err, "percpu_alloc_array__load"))
+		goto out;
+
+	err = percpu_alloc_array__attach(skel);
+	if (!ASSERT_OK(err, "percpu_alloc_array__attach"))
+		goto out;
+
+	prog_fd = bpf_program__fd(skel->progs.test_array_map_10);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run array_map_10");
+	ASSERT_EQ(topts.retval, 0, "test_run array_map_10");
+	ASSERT_EQ(skel->bss->cpu0_field_d, 2, "cpu0_field_d");
+	ASSERT_EQ(skel->bss->sum_field_c, 1, "sum_field_c");
+out:
+	percpu_alloc_array__destroy(skel);
+}
+
+static void test_cgrp_local_storage(void)
+{
+	struct percpu_alloc_cgrp_local_storage *skel;
+	int err, cgroup_fd, prog_fd;
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+
+	cgroup_fd = test__join_cgroup("/percpu_alloc");
+	if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup /percpu_alloc"))
+		return;
+
+	skel = percpu_alloc_cgrp_local_storage__open();
+	if (!ASSERT_OK_PTR(skel, "percpu_alloc_cgrp_local_storage__open"))
+		goto close_fd;
+
+	skel->bss->my_pid = getpid();
+	skel->rodata->nr_cpus = libbpf_num_possible_cpus();
+
+	err = percpu_alloc_cgrp_local_storage__load(skel);
+	if (!ASSERT_OK(err, "percpu_alloc_cgrp_local_storage__load"))
+		goto destroy_skel;
+
+	err = percpu_alloc_cgrp_local_storage__attach(skel);
+	if (!ASSERT_OK(err, "percpu_alloc_cgrp_local_storage__attach"))
+		goto destroy_skel;
+
+	prog_fd = bpf_program__fd(skel->progs.test_cgrp_local_storage_1);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run cgrp_local_storage 1-3");
+	ASSERT_EQ(topts.retval, 0, "test_run cgrp_local_storage 1-3");
+	ASSERT_EQ(skel->bss->cpu0_field_d, 2, "cpu0_field_d");
+	ASSERT_EQ(skel->bss->sum_field_c, 1, "sum_field_c");
+
+destroy_skel:
+	percpu_alloc_cgrp_local_storage__destroy(skel);
+close_fd:
+	close(cgroup_fd);
+}
+
+static void test_failure(void) {
+	RUN_TESTS(percpu_alloc_fail);
+}
+
+void test_percpu_alloc(void)
+{
+	if (test__start_subtest("array"))
+		test_array();
+	if (test__start_subtest("array_sleepable"))
+		test_array_sleepable();
+	if (test__start_subtest("cgrp_local_storage"))
+		test_cgrp_local_storage();
+	if (test__start_subtest("failure_tests"))
+		test_failure();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_branches.c b/tools/testing/selftests/bpf/prog_tests/perf_branches.c
index bc24f83339d6..0a7ef770c487 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_branches.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_branches.c
@@ -15,6 +15,10 @@ static void check_good_sample(struct test_perf_branches *skel)
 	int pbe_size = sizeof(struct perf_branch_entry);
 	int duration = 0;
 
+	if (CHECK(!skel->bss->run_cnt, "invalid run_cnt",
+		  "checked sample validity before prog run"))
+		return;
+
 	if (CHECK(!skel->bss->valid, "output not valid",
 		 "no valid sample from prog"))
 		return;
@@ -45,6 +49,10 @@ static void check_bad_sample(struct test_perf_branches *skel)
 	int written_stack = skel->bss->written_stack_out;
 	int duration = 0;
 
+	if (CHECK(!skel->bss->run_cnt, "invalid run_cnt",
+		  "checked sample validity before prog run"))
+		return;
+
 	if (CHECK(!skel->bss->valid, "output not valid",
 		 "no valid sample from prog"))
 		return;
@@ -83,8 +91,12 @@ static void test_perf_branches_common(int perf_fd,
 	err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), &cpu_set);
 	if (CHECK(err, "set_affinity", "cpu #0, err %d\n", err))
 		goto out_destroy;
-	/* spin the loop for a while (random high number) */
-	for (i = 0; i < 1000000; ++i)
+
+	/* Spin the loop for a while by using a high iteration count, and by
+	 * checking whether the specific run count marker has been explicitly
+	 * incremented at least once by the backing perf_event BPF program.
+	 */
+	for (i = 0; i < 100000000 && !*(volatile int *)&skel->bss->run_cnt; ++i)
 		++j;
 
 	test_perf_branches__detach(skel);
@@ -116,11 +128,11 @@ static void test_perf_branches_hw(void)
 	pfd = syscall(__NR_perf_event_open, &attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC);
 
 	/*
-	 * Some setups don't support branch records (virtual machines, !x86),
-	 * so skip test in this case.
+	 * Some setups don't support LBR (virtual machines, !x86, AMD Milan Zen
+	 * 3 which only supports BRS), so skip test in this case.
 	 */
 	if (pfd < 0) {
-		if (errno == ENOENT || errno == EOPNOTSUPP) {
+		if (errno == ENOENT || errno == EOPNOTSUPP || errno == EINVAL) {
 			printf("%s:SKIP:no PERF_SAMPLE_BRANCH_STACK\n",
 			       __func__);
 			test__skip();
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c b/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c
index 33144c9432ae..f4aad35afae1 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c
@@ -63,7 +63,8 @@ void test_perf_event_stackmap(void)
 			PERF_SAMPLE_BRANCH_NO_FLAGS |
 			PERF_SAMPLE_BRANCH_NO_CYCLES |
 			PERF_SAMPLE_BRANCH_CALL_STACK,
-		.sample_period = 5000,
+		.freq = 1,
+		.sample_freq = read_perf_max_sample_freq(),
 		.size = sizeof(struct perf_event_attr),
 	};
 	struct perf_event_stackmap *skel;
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_link.c b/tools/testing/selftests/bpf/prog_tests/perf_link.c
index 224eba6fef2e..d940ff87fa08 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_link.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_link.c
@@ -4,8 +4,12 @@
 #include <pthread.h>
 #include <sched.h>
 #include <test_progs.h>
+#include "testing_helpers.h"
 #include "test_perf_link.skel.h"
 
+#define BURN_TIMEOUT_MS 100
+#define BURN_TIMEOUT_NS BURN_TIMEOUT_MS * 1000000
+
 static void burn_cpu(void)
 {
 	volatile int j = 0;
@@ -32,6 +36,7 @@ void serial_test_perf_link(void)
 	int run_cnt_before, run_cnt_after;
 	struct bpf_link_info info;
 	__u32 info_len = sizeof(info);
+	__u64 timeout_time_ns;
 
 	/* create perf event */
 	memset(&attr, 0, sizeof(attr));
@@ -54,7 +59,7 @@ void serial_test_perf_link(void)
 		goto cleanup;
 
 	memset(&info, 0, sizeof(info));
-	err = bpf_obj_get_info_by_fd(link_fd, &info, &info_len);
+	err = bpf_link_get_info_by_fd(link_fd, &info, &info_len);
 	if (!ASSERT_OK(err, "link_get_info"))
 		goto cleanup;
 
@@ -63,8 +68,14 @@ void serial_test_perf_link(void)
 	ASSERT_GT(info.prog_id, 0, "link_prog_id");
 
 	/* ensure we get at least one perf_event prog execution */
-	burn_cpu();
-	ASSERT_GT(skel->bss->run_cnt, 0, "run_cnt");
+	timeout_time_ns = get_time_ns() + BURN_TIMEOUT_NS;
+	while (true) {
+		burn_cpu();
+		if (skel->bss->run_cnt > 0)
+			break;
+	        if (!ASSERT_LT(get_time_ns(), timeout_time_ns, "run_cnt_timeout"))
+			break;
+	}
 
 	/* perf_event is still active, but we close link and BPF program
 	 * shouldn't be executed anymore
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_skip.c b/tools/testing/selftests/bpf/prog_tests/perf_skip.c
new file mode 100644
index 000000000000..37d8618800e4
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/perf_skip.c
@@ -0,0 +1,137 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <test_progs.h>
+#include "test_perf_skip.skel.h"
+#include <linux/compiler.h>
+#include <linux/hw_breakpoint.h>
+#include <sys/mman.h>
+
+#ifndef TRAP_PERF
+#define TRAP_PERF 6
+#endif
+
+int sigio_count, sigtrap_count;
+
+static void handle_sigio(int sig __always_unused)
+{
+	++sigio_count;
+}
+
+static void handle_sigtrap(int signum __always_unused,
+			   siginfo_t *info,
+			   void *ucontext __always_unused)
+{
+	ASSERT_EQ(info->si_code, TRAP_PERF, "si_code");
+	++sigtrap_count;
+}
+
+static noinline int test_function(void)
+{
+	asm volatile ("");
+	return 0;
+}
+
+void serial_test_perf_skip(void)
+{
+	struct sigaction action = {};
+	struct sigaction previous_sigtrap;
+	sighandler_t previous_sigio = SIG_ERR;
+	struct test_perf_skip *skel = NULL;
+	struct perf_event_attr attr = {};
+	int perf_fd = -1;
+	int err;
+	struct f_owner_ex owner;
+	struct bpf_link *prog_link = NULL;
+
+	action.sa_flags = SA_SIGINFO | SA_NODEFER;
+	action.sa_sigaction = handle_sigtrap;
+	sigemptyset(&action.sa_mask);
+	if (!ASSERT_OK(sigaction(SIGTRAP, &action, &previous_sigtrap), "sigaction"))
+		return;
+
+	previous_sigio = signal(SIGIO, handle_sigio);
+	if (!ASSERT_NEQ(previous_sigio, SIG_ERR, "signal"))
+		goto cleanup;
+
+	skel = test_perf_skip__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	attr.type = PERF_TYPE_BREAKPOINT;
+	attr.size = sizeof(attr);
+	attr.bp_type = HW_BREAKPOINT_X;
+	attr.bp_addr = (uintptr_t)test_function;
+	attr.bp_len = sizeof(long);
+	attr.sample_period = 1;
+	attr.sample_type = PERF_SAMPLE_IP;
+	attr.pinned = 1;
+	attr.exclude_kernel = 1;
+	attr.exclude_hv = 1;
+	attr.precise_ip = 3;
+	attr.sigtrap = 1;
+	attr.remove_on_exec = 1;
+
+	perf_fd = syscall(__NR_perf_event_open, &attr, 0, -1, -1, 0);
+	if (perf_fd < 0 && (errno == ENOENT || errno == EOPNOTSUPP)) {
+		printf("SKIP:no PERF_TYPE_BREAKPOINT/HW_BREAKPOINT_X\n");
+		test__skip();
+		goto cleanup;
+	}
+	if (!ASSERT_OK(perf_fd < 0, "perf_event_open"))
+		goto cleanup;
+
+	/* Configure the perf event to signal on sample. */
+	err = fcntl(perf_fd, F_SETFL, O_ASYNC);
+	if (!ASSERT_OK(err, "fcntl(F_SETFL, O_ASYNC)"))
+		goto cleanup;
+
+	owner.type = F_OWNER_TID;
+	owner.pid = syscall(__NR_gettid);
+	err = fcntl(perf_fd, F_SETOWN_EX, &owner);
+	if (!ASSERT_OK(err, "fcntl(F_SETOWN_EX)"))
+		goto cleanup;
+
+	/* Allow at most one sample. A sample rejected by bpf should
+	 * not count against this.
+	 */
+	err = ioctl(perf_fd, PERF_EVENT_IOC_REFRESH, 1);
+	if (!ASSERT_OK(err, "ioctl(PERF_EVENT_IOC_REFRESH)"))
+		goto cleanup;
+
+	prog_link = bpf_program__attach_perf_event(skel->progs.handler, perf_fd);
+	if (!ASSERT_OK_PTR(prog_link, "bpf_program__attach_perf_event"))
+		goto cleanup;
+
+	/* Configure the bpf program to suppress the sample. */
+	skel->bss->ip = (uintptr_t)test_function;
+	test_function();
+
+	ASSERT_EQ(sigio_count, 0, "sigio_count");
+	ASSERT_EQ(sigtrap_count, 0, "sigtrap_count");
+
+	/* Configure the bpf program to allow the sample. */
+	skel->bss->ip = 0;
+	test_function();
+
+	ASSERT_EQ(sigio_count, 1, "sigio_count");
+	ASSERT_EQ(sigtrap_count, 1, "sigtrap_count");
+
+	/* Test that the sample above is the only one allowed (by perf, not
+	 * by bpf)
+	 */
+	test_function();
+
+	ASSERT_EQ(sigio_count, 1, "sigio_count");
+	ASSERT_EQ(sigtrap_count, 1, "sigtrap_count");
+
+cleanup:
+	bpf_link__destroy(prog_link);
+	if (perf_fd >= 0)
+		close(perf_fd);
+	test_perf_skip__destroy(skel);
+
+	if (previous_sigio != SIG_ERR)
+		signal(SIGIO, previous_sigio);
+	sigaction(SIGTRAP, &previous_sigtrap, NULL);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/pinning.c b/tools/testing/selftests/bpf/prog_tests/pinning.c
index d95cee5867b7..c799a3c5ad1f 100644
--- a/tools/testing/selftests/bpf/prog_tests/pinning.c
+++ b/tools/testing/selftests/bpf/prog_tests/pinning.c
@@ -18,7 +18,7 @@ __u32 get_map_id(struct bpf_object *obj, const char *name)
 	if (CHECK(!map, "find map", "NULL map"))
 		return 0;
 
-	err = bpf_obj_get_info_by_fd(bpf_map__fd(map),
+	err = bpf_map_get_info_by_fd(bpf_map__fd(map),
 				     &map_info, &map_info_len);
 	CHECK(err, "get map info", "err %d errno %d", err, errno);
 	return map_info.id;
diff --git a/tools/testing/selftests/bpf/prog_tests/pinning_devmap_reuse.c b/tools/testing/selftests/bpf/prog_tests/pinning_devmap_reuse.c
new file mode 100644
index 000000000000..9ae49b587f3e
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/pinning_devmap_reuse.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <test_progs.h>
+
+
+#include "test_pinning_devmap.skel.h"
+
+void test_pinning_devmap_reuse(void)
+{
+	const char *pinpath1 = "/sys/fs/bpf/pinmap1";
+	const char *pinpath2 = "/sys/fs/bpf/pinmap2";
+	struct test_pinning_devmap *skel1 = NULL, *skel2 = NULL;
+	int err;
+	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts);
+
+	/* load the object a first time */
+	skel1 = test_pinning_devmap__open_and_load();
+	if (!ASSERT_OK_PTR(skel1, "skel_load1"))
+		goto out;
+
+	/* load the object a second time, re-using the pinned map */
+	skel2 = test_pinning_devmap__open_and_load();
+	if (!ASSERT_OK_PTR(skel2, "skel_load2"))
+		goto out;
+
+	/* we can close the reference safely without
+	 * the map's refcount falling to 0
+	 */
+	test_pinning_devmap__destroy(skel1);
+	skel1 = NULL;
+
+	/* now, swap the pins */
+	err = renameat2(0, pinpath1, 0, pinpath2, RENAME_EXCHANGE);
+	if (!ASSERT_OK(err, "swap pins"))
+		goto out;
+
+	/* load the object again, this time the re-use should fail */
+	skel1 = test_pinning_devmap__open_and_load();
+	if (!ASSERT_ERR_PTR(skel1, "skel_load3"))
+		goto out;
+
+out:
+	unlink(pinpath1);
+	unlink(pinpath2);
+	test_pinning_devmap__destroy(skel1);
+	test_pinning_devmap__destroy(skel2);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/pinning_htab.c b/tools/testing/selftests/bpf/prog_tests/pinning_htab.c
new file mode 100644
index 000000000000..16bd74be3dbe
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/pinning_htab.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "test_pinning_htab.skel.h"
+
+static void unpin_map(const char *map_name, const char *pin_path)
+{
+	struct test_pinning_htab *skel;
+	struct bpf_map *map;
+	int err;
+
+	skel = test_pinning_htab__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel open_and_load"))
+		return;
+
+	map = bpf_object__find_map_by_name(skel->obj, map_name);
+	if (!ASSERT_OK_PTR(map, "bpf_object__find_map_by_name"))
+		goto out;
+
+	err = bpf_map__pin(map, pin_path);
+	if (!ASSERT_OK(err, "bpf_map__pin"))
+		goto out;
+
+	err = bpf_map__unpin(map, pin_path);
+	ASSERT_OK(err, "bpf_map__unpin");
+out:
+	test_pinning_htab__destroy(skel);
+}
+
+void test_pinning_htab(void)
+{
+	if (test__start_subtest("timer_prealloc"))
+		unpin_map("timer_prealloc", "/sys/fs/bpf/timer_prealloc");
+	if (test__start_subtest("timer_no_prealloc"))
+		unpin_map("timer_no_prealloc", "/sys/fs/bpf/timer_no_prealloc");
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/preempt_lock.c b/tools/testing/selftests/bpf/prog_tests/preempt_lock.c
new file mode 100644
index 000000000000..02917c672441
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/preempt_lock.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <network_helpers.h>
+#include <preempt_lock.skel.h>
+
+void test_preempt_lock(void)
+{
+	RUN_TESTS(preempt_lock);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/preempted_bpf_ma_op.c b/tools/testing/selftests/bpf/prog_tests/preempted_bpf_ma_op.c
new file mode 100644
index 000000000000..3a2ec3923fca
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/preempted_bpf_ma_op.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#define _GNU_SOURCE
+#include <sched.h>
+#include <pthread.h>
+#include <stdbool.h>
+#include <test_progs.h>
+
+#include "preempted_bpf_ma_op.skel.h"
+
+#define ALLOC_THREAD_NR 4
+#define ALLOC_LOOP_NR 512
+
+struct alloc_ctx {
+	/* output */
+	int run_err;
+	/* input */
+	int fd;
+	bool *nomem_err;
+};
+
+static void *run_alloc_prog(void *data)
+{
+	struct alloc_ctx *ctx = data;
+	cpu_set_t cpu_set;
+	int i;
+
+	CPU_ZERO(&cpu_set);
+	CPU_SET(0, &cpu_set);
+	pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), &cpu_set);
+
+	for (i = 0; i < ALLOC_LOOP_NR && !*ctx->nomem_err; i++) {
+		LIBBPF_OPTS(bpf_test_run_opts, topts);
+		int err;
+
+		err = bpf_prog_test_run_opts(ctx->fd, &topts);
+		ctx->run_err |= err | topts.retval;
+	}
+
+	return NULL;
+}
+
+void test_preempted_bpf_ma_op(void)
+{
+	struct alloc_ctx ctx[ALLOC_THREAD_NR];
+	struct preempted_bpf_ma_op *skel;
+	pthread_t tid[ALLOC_THREAD_NR];
+	int i, err;
+
+	skel = preempted_bpf_ma_op__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	err = preempted_bpf_ma_op__attach(skel);
+	if (!ASSERT_OK(err, "attach"))
+		goto out;
+
+	for (i = 0; i < ARRAY_SIZE(ctx); i++) {
+		struct bpf_program *prog;
+		char name[8];
+
+		snprintf(name, sizeof(name), "test%d", i);
+		prog = bpf_object__find_program_by_name(skel->obj, name);
+		if (!ASSERT_OK_PTR(prog, "no test prog"))
+			goto out;
+
+		ctx[i].run_err = 0;
+		ctx[i].fd = bpf_program__fd(prog);
+		ctx[i].nomem_err = &skel->bss->nomem_err;
+	}
+
+	memset(tid, 0, sizeof(tid));
+	for (i = 0; i < ARRAY_SIZE(tid); i++) {
+		err = pthread_create(&tid[i], NULL, run_alloc_prog, &ctx[i]);
+		if (!ASSERT_OK(err, "pthread_create"))
+			break;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(tid); i++) {
+		if (!tid[i])
+			break;
+		pthread_join(tid[i], NULL);
+		ASSERT_EQ(ctx[i].run_err, 0, "run prog err");
+	}
+
+	ASSERT_FALSE(skel->bss->nomem_err, "ENOMEM");
+out:
+	preempted_bpf_ma_op__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/prepare.c b/tools/testing/selftests/bpf/prog_tests/prepare.c
new file mode 100644
index 000000000000..fb5cdad97116
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/prepare.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta */
+
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "prepare.skel.h"
+
+static bool check_prepared(struct bpf_object *obj)
+{
+	bool is_prepared = true;
+	const struct bpf_map *map;
+
+	bpf_object__for_each_map(map, obj) {
+		if (bpf_map__fd(map) < 0)
+			is_prepared = false;
+	}
+
+	return is_prepared;
+}
+
+static void test_prepare_no_load(void)
+{
+	struct prepare *skel;
+	int err;
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+	);
+
+	skel = prepare__open();
+	if (!ASSERT_OK_PTR(skel, "prepare__open"))
+		return;
+
+	if (!ASSERT_FALSE(check_prepared(skel->obj), "not check_prepared"))
+		goto cleanup;
+
+	err = bpf_object__prepare(skel->obj);
+
+	if (!ASSERT_TRUE(check_prepared(skel->obj), "check_prepared"))
+		goto cleanup;
+
+	if (!ASSERT_OK(err, "bpf_object__prepare"))
+		goto cleanup;
+
+cleanup:
+	prepare__destroy(skel);
+}
+
+static void test_prepare_load(void)
+{
+	struct prepare *skel;
+	int err, prog_fd;
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+	);
+
+	skel = prepare__open();
+	if (!ASSERT_OK_PTR(skel, "prepare__open"))
+		return;
+
+	if (!ASSERT_FALSE(check_prepared(skel->obj), "not check_prepared"))
+		goto cleanup;
+
+	err = bpf_object__prepare(skel->obj);
+	if (!ASSERT_OK(err, "bpf_object__prepare"))
+		goto cleanup;
+
+	err = prepare__load(skel);
+	if (!ASSERT_OK(err, "prepare__load"))
+		goto cleanup;
+
+	if (!ASSERT_TRUE(check_prepared(skel->obj), "check_prepared"))
+		goto cleanup;
+
+	prog_fd = bpf_program__fd(skel->progs.program);
+	if (!ASSERT_GE(prog_fd, 0, "prog_fd"))
+		goto cleanup;
+
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	if (!ASSERT_OK(err, "test_run_opts err"))
+		goto cleanup;
+
+	if (!ASSERT_OK(topts.retval, "test_run_opts retval"))
+		goto cleanup;
+
+	ASSERT_EQ(skel->bss->err, 0, "err");
+
+cleanup:
+	prepare__destroy(skel);
+}
+
+void test_prepare(void)
+{
+	if (test__start_subtest("prepare_load"))
+		test_prepare_load();
+	if (test__start_subtest("prepare_no_load"))
+		test_prepare_no_load();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/pro_epilogue.c b/tools/testing/selftests/bpf/prog_tests/pro_epilogue.c
new file mode 100644
index 000000000000..5d3c00a08a88
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/pro_epilogue.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <test_progs.h>
+#include "pro_epilogue.skel.h"
+#include "epilogue_tailcall.skel.h"
+#include "pro_epilogue_goto_start.skel.h"
+#include "epilogue_exit.skel.h"
+#include "pro_epilogue_with_kfunc.skel.h"
+
+struct st_ops_args {
+	__u64 a;
+};
+
+static void test_tailcall(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	struct epilogue_tailcall *skel;
+	struct st_ops_args args;
+	int err, prog_fd;
+
+	skel = epilogue_tailcall__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "epilogue_tailcall__open_and_load"))
+		return;
+
+	topts.ctx_in = &args;
+	topts.ctx_size_in = sizeof(args);
+
+	skel->links.epilogue_tailcall =
+		bpf_map__attach_struct_ops(skel->maps.epilogue_tailcall);
+	if (!ASSERT_OK_PTR(skel->links.epilogue_tailcall, "attach_struct_ops"))
+		goto done;
+
+	/* Both test_epilogue_tailcall and test_epilogue_subprog are
+	 * patched with epilogue. When syscall_epilogue_tailcall()
+	 * is run, test_epilogue_tailcall() is triggered.
+	 * It executes a tail call and control is transferred to
+	 * test_epilogue_subprog(). Only test_epilogue_subprog()
+	 * does args->a += 1, thus final args.a value of 10001
+	 * guarantees that only the epilogue of the
+	 * test_epilogue_subprog is executed.
+	 */
+	memset(&args, 0, sizeof(args));
+	prog_fd = bpf_program__fd(skel->progs.syscall_epilogue_tailcall);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "bpf_prog_test_run_opts");
+	ASSERT_EQ(args.a, 10001, "args.a");
+	ASSERT_EQ(topts.retval, 10001 * 2, "topts.retval");
+
+done:
+	epilogue_tailcall__destroy(skel);
+}
+
+void test_pro_epilogue(void)
+{
+	RUN_TESTS(pro_epilogue);
+	RUN_TESTS(pro_epilogue_goto_start);
+	RUN_TESTS(epilogue_exit);
+	RUN_TESTS(pro_epilogue_with_kfunc);
+	if (test__start_subtest("tailcall"))
+		test_tailcall();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/prog_run_opts.c b/tools/testing/selftests/bpf/prog_tests/prog_run_opts.c
index 1ccd2bdf8fa8..01f1d1b6715a 100644
--- a/tools/testing/selftests/bpf/prog_tests/prog_run_opts.c
+++ b/tools/testing/selftests/bpf/prog_tests/prog_run_opts.c
@@ -12,7 +12,7 @@ static void check_run_cnt(int prog_fd, __u64 run_cnt)
 	__u32 info_len = sizeof(info);
 	int err;
 
-	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len);
 	if (CHECK(err, "get_prog_info", "failed to get bpf_prog_info for fd %d\n", prog_fd))
 		return;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/prog_tests_framework.c b/tools/testing/selftests/bpf/prog_tests/prog_tests_framework.c
index 14f2796076e0..7607cfc2408c 100644
--- a/tools/testing/selftests/bpf/prog_tests/prog_tests_framework.c
+++ b/tools/testing/selftests/bpf/prog_tests/prog_tests_framework.c
@@ -54,3 +54,128 @@ void test_prog_tests_framework(void)
 		return;
 	clear_test_state(state);
 }
+
+static void dummy_emit(const char *buf, bool force) {}
+
+void test_prog_tests_framework_expected_msgs(void)
+{
+	struct expected_msgs msgs;
+	int i, j, error_cnt;
+	const struct {
+		const char *name;
+		const char *log;
+		const char *expected;
+		struct expect_msg *pats;
+	} cases[] = {
+		{
+			.name = "simple-ok",
+			.log = "aaabbbccc",
+			.pats = (struct expect_msg[]) {
+				{ .substr = "aaa" },
+				{ .substr = "ccc" },
+				{}
+			}
+		},
+		{
+			.name = "simple-fail",
+			.log = "aaabbbddd",
+			.expected = "MATCHED    SUBSTR: 'aaa'\n"
+				    "EXPECTED   SUBSTR: 'ccc'\n",
+			.pats = (struct expect_msg[]) {
+				{ .substr = "aaa" },
+				{ .substr = "ccc" },
+				{}
+			}
+		},
+		{
+			.name = "negative-ok-mid",
+			.log = "aaabbbccc",
+			.pats = (struct expect_msg[]) {
+				{ .substr = "aaa" },
+				{ .substr = "foo", .negative = true },
+				{ .substr = "bar", .negative = true },
+				{ .substr = "ccc" },
+				{}
+			}
+		},
+		{
+			.name = "negative-ok-tail",
+			.log = "aaabbbccc",
+			.pats = (struct expect_msg[]) {
+				{ .substr = "aaa" },
+				{ .substr = "foo", .negative = true },
+				{}
+			}
+		},
+		{
+			.name = "negative-ok-head",
+			.log = "aaabbbccc",
+			.pats = (struct expect_msg[]) {
+				{ .substr = "foo", .negative = true },
+				{ .substr = "ccc" },
+				{}
+			}
+		},
+		{
+			.name = "negative-fail-head",
+			.log = "aaabbbccc",
+			.expected = "UNEXPECTED SUBSTR: 'aaa'\n",
+			.pats = (struct expect_msg[]) {
+				{ .substr = "aaa", .negative = true },
+				{ .substr = "bbb" },
+				{}
+			}
+		},
+		{
+			.name = "negative-fail-tail",
+			.log = "aaabbbccc",
+			.expected = "UNEXPECTED SUBSTR: 'ccc'\n",
+			.pats = (struct expect_msg[]) {
+				{ .substr = "bbb" },
+				{ .substr = "ccc", .negative = true },
+				{}
+			}
+		},
+		{
+			.name = "negative-fail-mid-1",
+			.log = "aaabbbccc",
+			.expected = "UNEXPECTED SUBSTR: 'bbb'\n",
+			.pats = (struct expect_msg[]) {
+				{ .substr = "aaa" },
+				{ .substr = "bbb", .negative = true },
+				{ .substr = "ccc" },
+				{}
+			}
+		},
+		{
+			.name = "negative-fail-mid-2",
+			.log = "aaabbb222ccc",
+			.expected = "UNEXPECTED SUBSTR: '222'\n",
+			.pats = (struct expect_msg[]) {
+				{ .substr = "aaa" },
+				{ .substr = "222", .negative = true },
+				{ .substr = "bbb", .negative = true },
+				{ .substr = "ccc" },
+				{}
+			}
+		}
+	};
+
+	for (i = 0; i < ARRAY_SIZE(cases); i++) {
+		if (test__start_subtest(cases[i].name)) {
+			error_cnt = env.subtest_state->error_cnt;
+			msgs.patterns = cases[i].pats;
+			msgs.cnt = 0;
+			for (j = 0; cases[i].pats[j].substr; j++)
+				msgs.cnt++;
+			validate_msgs(cases[i].log, &msgs, dummy_emit);
+			fflush(stderr);
+			env.subtest_state->error_cnt = error_cnt;
+			if (cases[i].expected)
+				ASSERT_HAS_SUBSTR(env.subtest_state->log_buf, cases[i].expected, "expected output");
+			else
+				ASSERT_STREQ(env.subtest_state->log_buf, "", "expected no output");
+			test__end_subtest();
+		}
+	}
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/ptr_untrusted.c b/tools/testing/selftests/bpf/prog_tests/ptr_untrusted.c
new file mode 100644
index 000000000000..8d077d150c56
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/ptr_untrusted.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */
+
+#include <string.h>
+#include <linux/bpf.h>
+#include <test_progs.h>
+#include "test_ptr_untrusted.skel.h"
+
+#define TP_NAME "sched_switch"
+
+void serial_test_ptr_untrusted(void)
+{
+	struct test_ptr_untrusted *skel;
+	int err;
+
+	skel = test_ptr_untrusted__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	/* First, attach lsm prog */
+	skel->links.lsm_run = bpf_program__attach_lsm(skel->progs.lsm_run);
+	if (!ASSERT_OK_PTR(skel->links.lsm_run, "lsm_attach"))
+		goto cleanup;
+
+	/* Second, attach raw_tp prog. The lsm prog will be triggered. */
+	skel->links.raw_tp_run = bpf_program__attach_raw_tracepoint(skel->progs.raw_tp_run,
+								    TP_NAME);
+	if (!ASSERT_OK_PTR(skel->links.raw_tp_run, "raw_tp_attach"))
+		goto cleanup;
+
+	err = strncmp(skel->bss->tp_name, TP_NAME, strlen(TP_NAME));
+	ASSERT_EQ(err, 0, "cmp_tp_name");
+
+cleanup:
+	test_ptr_untrusted__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c
index 722c5f2a7776..a043af9cd6d9 100644
--- a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c
@@ -14,7 +14,7 @@ static void test_queue_stack_map_by_type(int type)
 	int i, err, prog_fd, map_in_fd, map_out_fd;
 	char file[32], buf[128];
 	struct bpf_object *obj;
-	struct iphdr iph;
+	struct iphdr iph = {};
 	LIBBPF_OPTS(bpf_test_run_opts, topts,
 		.data_in = &pkt_v4,
 		.data_size_in = sizeof(pkt_v4),
diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c
new file mode 100644
index 000000000000..43676a9922dc
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_null.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <test_progs.h>
+#include "raw_tp_null.skel.h"
+#include "raw_tp_null_fail.skel.h"
+
+void test_raw_tp_null(void)
+{
+	struct raw_tp_null *skel;
+
+	RUN_TESTS(raw_tp_null_fail);
+
+	skel = raw_tp_null__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "raw_tp_null__open_and_load"))
+		return;
+
+	skel->bss->tid = sys_gettid();
+
+	if (!ASSERT_OK(raw_tp_null__attach(skel), "raw_tp_null__attach"))
+		goto end;
+
+	ASSERT_OK(trigger_module_test_read(2), "trigger testmod read");
+	ASSERT_EQ(skel->bss->i, 3, "invocations");
+
+end:
+	raw_tp_null__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c
index e2f1445b0e10..216b0dfac0fe 100644
--- a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c
+++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_reject_nbd_invalid.c
@@ -2,6 +2,7 @@
 
 #include <test_progs.h>
 #include <linux/nbd.h>
+#include "bpf_util.h"
 
 void test_raw_tp_writable_reject_nbd_invalid(void)
 {
@@ -25,7 +26,7 @@ void test_raw_tp_writable_reject_nbd_invalid(void)
 	);
 
 	bpf_fd = bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, NULL, "GPL v2",
-			       program, sizeof(program) / sizeof(struct bpf_insn),
+			       program, ARRAY_SIZE(program),
 			       &opts);
 	if (CHECK(bpf_fd < 0, "bpf_raw_tracepoint_writable load",
 		  "failed: %d errno %d\n", bpf_fd, errno))
diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c
index f4aa7dab4766..e3668058b7bb 100644
--- a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c
+++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c
@@ -2,6 +2,7 @@
 
 #include <test_progs.h>
 #include <linux/nbd.h>
+#include "bpf_util.h"
 
 /* NOTE: conflict with other tests. */
 void serial_test_raw_tp_writable_test_run(void)
@@ -24,7 +25,7 @@ void serial_test_raw_tp_writable_test_run(void)
 	);
 
 	int bpf_fd = bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, NULL, "GPL v2",
-				   trace_program, sizeof(trace_program) / sizeof(struct bpf_insn),
+				   trace_program, ARRAY_SIZE(trace_program),
 				   &trace_opts);
 	if (CHECK(bpf_fd < 0, "bpf_raw_tracepoint_writable loaded",
 		  "failed: %d errno %d\n", bpf_fd, errno))
@@ -41,7 +42,7 @@ void serial_test_raw_tp_writable_test_run(void)
 	);
 
 	int filter_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL v2",
-				      skb_program, sizeof(skb_program) / sizeof(struct bpf_insn),
+				      skb_program, ARRAY_SIZE(skb_program),
 				      &skb_opts);
 	if (CHECK(filter_fd < 0, "test_program_loaded", "failed: %d errno %d\n",
 		  filter_fd, errno))
diff --git a/tools/testing/selftests/bpf/prog_tests/rbtree.c b/tools/testing/selftests/bpf/prog_tests/rbtree.c
new file mode 100644
index 000000000000..d8f3d7a45fe9
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/rbtree.c
@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include <test_progs.h>
+#include <network_helpers.h>
+
+#include "rbtree.skel.h"
+#include "rbtree_fail.skel.h"
+#include "rbtree_btf_fail__wrong_node_type.skel.h"
+#include "rbtree_btf_fail__add_wrong_type.skel.h"
+#include "rbtree_search.skel.h"
+
+static void test_rbtree_add_nodes(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+	struct rbtree *skel;
+	int ret;
+
+	skel = rbtree__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "rbtree__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_add_nodes), &opts);
+	ASSERT_OK(ret, "rbtree_add_nodes run");
+	ASSERT_OK(opts.retval, "rbtree_add_nodes retval");
+	ASSERT_EQ(skel->data->less_callback_ran, 1, "rbtree_add_nodes less_callback_ran");
+
+	rbtree__destroy(skel);
+}
+
+static void test_rbtree_add_nodes_nested(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+	struct rbtree *skel;
+	int ret;
+
+	skel = rbtree__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "rbtree__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_add_nodes_nested), &opts);
+	ASSERT_OK(ret, "rbtree_add_nodes_nested run");
+	ASSERT_OK(opts.retval, "rbtree_add_nodes_nested retval");
+	ASSERT_EQ(skel->data->less_callback_ran, 1, "rbtree_add_nodes_nested less_callback_ran");
+
+	rbtree__destroy(skel);
+}
+
+static void test_rbtree_add_and_remove(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+	struct rbtree *skel;
+	int ret;
+
+	skel = rbtree__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "rbtree__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_add_and_remove), &opts);
+	ASSERT_OK(ret, "rbtree_add_and_remove");
+	ASSERT_OK(opts.retval, "rbtree_add_and_remove retval");
+	ASSERT_EQ(skel->data->removed_key, 5, "rbtree_add_and_remove first removed key");
+
+	rbtree__destroy(skel);
+}
+
+static void test_rbtree_add_and_remove_array(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+	struct rbtree *skel;
+	int ret;
+
+	skel = rbtree__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "rbtree__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_add_and_remove_array), &opts);
+	ASSERT_OK(ret, "rbtree_add_and_remove_array");
+	ASSERT_OK(opts.retval, "rbtree_add_and_remove_array retval");
+
+	rbtree__destroy(skel);
+}
+
+static void test_rbtree_first_and_remove(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+	struct rbtree *skel;
+	int ret;
+
+	skel = rbtree__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "rbtree__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_first_and_remove), &opts);
+	ASSERT_OK(ret, "rbtree_first_and_remove");
+	ASSERT_OK(opts.retval, "rbtree_first_and_remove retval");
+	ASSERT_EQ(skel->data->first_data[0], 2, "rbtree_first_and_remove first rbtree_first()");
+	ASSERT_EQ(skel->data->removed_key, 1, "rbtree_first_and_remove first removed key");
+	ASSERT_EQ(skel->data->first_data[1], 4, "rbtree_first_and_remove second rbtree_first()");
+
+	rbtree__destroy(skel);
+}
+
+static void test_rbtree_api_release_aliasing(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+	struct rbtree *skel;
+	int ret;
+
+	skel = rbtree__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "rbtree__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_api_release_aliasing), &opts);
+	ASSERT_OK(ret, "rbtree_api_release_aliasing");
+	ASSERT_OK(opts.retval, "rbtree_api_release_aliasing retval");
+	ASSERT_EQ(skel->data->first_data[0], 42, "rbtree_api_release_aliasing first rbtree_remove()");
+	ASSERT_EQ(skel->data->first_data[1], -1, "rbtree_api_release_aliasing second rbtree_remove()");
+
+	rbtree__destroy(skel);
+}
+
+void test_rbtree_success(void)
+{
+	if (test__start_subtest("rbtree_add_nodes"))
+		test_rbtree_add_nodes();
+	if (test__start_subtest("rbtree_add_nodes_nested"))
+		test_rbtree_add_nodes_nested();
+	if (test__start_subtest("rbtree_add_and_remove"))
+		test_rbtree_add_and_remove();
+	if (test__start_subtest("rbtree_add_and_remove_array"))
+		test_rbtree_add_and_remove_array();
+	if (test__start_subtest("rbtree_first_and_remove"))
+		test_rbtree_first_and_remove();
+	if (test__start_subtest("rbtree_api_release_aliasing"))
+		test_rbtree_api_release_aliasing();
+}
+
+#define BTF_FAIL_TEST(suffix)									\
+void test_rbtree_btf_fail__##suffix(void)							\
+{												\
+	struct rbtree_btf_fail__##suffix *skel;							\
+												\
+	skel = rbtree_btf_fail__##suffix##__open_and_load();					\
+	if (!ASSERT_ERR_PTR(skel,								\
+			    "rbtree_btf_fail__" #suffix "__open_and_load unexpected success"))	\
+		rbtree_btf_fail__##suffix##__destroy(skel);					\
+}
+
+#define RUN_BTF_FAIL_TEST(suffix)				\
+	if (test__start_subtest("rbtree_btf_fail__" #suffix))	\
+		test_rbtree_btf_fail__##suffix();
+
+BTF_FAIL_TEST(wrong_node_type);
+BTF_FAIL_TEST(add_wrong_type);
+
+void test_rbtree_btf_fail(void)
+{
+	RUN_BTF_FAIL_TEST(wrong_node_type);
+	RUN_BTF_FAIL_TEST(add_wrong_type);
+}
+
+void test_rbtree_fail(void)
+{
+	RUN_TESTS(rbtree_fail);
+}
+
+void test_rbtree_search(void)
+{
+	RUN_TESTS(rbtree_search);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c b/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c
index 447d8560ecb6..246eb259c08a 100644
--- a/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c
@@ -21,14 +21,19 @@ static void test_success(void)
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
 		return;
 
-	skel->bss->target_pid = syscall(SYS_gettid);
+	skel->bss->target_pid = sys_gettid();
 
 	bpf_program__set_autoload(skel->progs.get_cgroup_id, true);
 	bpf_program__set_autoload(skel->progs.task_succ, true);
-	bpf_program__set_autoload(skel->progs.no_lock, true);
 	bpf_program__set_autoload(skel->progs.two_regions, true);
 	bpf_program__set_autoload(skel->progs.non_sleepable_1, true);
 	bpf_program__set_autoload(skel->progs.non_sleepable_2, true);
+	bpf_program__set_autoload(skel->progs.nested_rcu_region, true);
+	bpf_program__set_autoload(skel->progs.task_trusted_non_rcuptr, true);
+	bpf_program__set_autoload(skel->progs.rcu_read_lock_subprog, true);
+	bpf_program__set_autoload(skel->progs.rcu_read_lock_global_subprog, true);
+	bpf_program__set_autoload(skel->progs.rcu_read_lock_subprog_lock, true);
+	bpf_program__set_autoload(skel->progs.rcu_read_lock_subprog_unlock, true);
 	err = rcu_read_lock__load(skel);
 	if (!ASSERT_OK(err, "skel_load"))
 		goto out;
@@ -54,7 +59,7 @@ static void test_rcuptr_acquire(void)
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
 		return;
 
-	skel->bss->target_pid = syscall(SYS_gettid);
+	skel->bss->target_pid = sys_gettid();
 
 	bpf_program__set_autoload(skel->progs.task_acquire, true);
 	err = rcu_read_lock__load(skel);
@@ -69,11 +74,18 @@ out:
 
 static const char * const inproper_region_tests[] = {
 	"miss_lock",
+	"no_lock",
 	"miss_unlock",
 	"non_sleepable_rcu_mismatch",
 	"inproper_sleepable_helper",
 	"inproper_sleepable_kfunc",
-	"nested_rcu_region",
+	"nested_rcu_region_unbalanced_1",
+	"nested_rcu_region_unbalanced_2",
+	"rcu_read_lock_global_subprog_lock",
+	"rcu_read_lock_global_subprog_unlock",
+	"rcu_read_lock_sleepable_helper_global_subprog",
+	"rcu_read_lock_sleepable_kfunc_global_subprog",
+	"rcu_read_lock_sleepable_global_subprog_indirect",
 };
 
 static void test_inproper_region(void)
@@ -99,7 +111,6 @@ out:
 }
 
 static const char * const rcuptr_misuse_tests[] = {
-	"task_untrusted_non_rcuptr",
 	"task_untrusted_rcuptr",
 	"cross_rcu_region",
 };
@@ -128,17 +139,8 @@ out:
 
 void test_rcu_read_lock(void)
 {
-	struct btf *vmlinux_btf;
 	int cgroup_fd;
 
-	vmlinux_btf = btf__load_vmlinux_btf();
-	if (!ASSERT_OK_PTR(vmlinux_btf, "could not load vmlinux BTF"))
-		return;
-	if (btf__find_by_name_kind(vmlinux_btf, "rcu", BTF_KIND_TYPE_TAG) < 0) {
-		test__skip();
-		goto out;
-	}
-
 	cgroup_fd = test__join_cgroup("/rcu_read_lock");
 	if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup /rcu_read_lock"))
 		goto out;
@@ -153,6 +155,5 @@ void test_rcu_read_lock(void)
 	if (test__start_subtest("negative_tests_rcuptr_misuse"))
 		test_rcuptr_misuse();
 	close(cgroup_fd);
-out:
-	btf__free(vmlinux_btf);
+out:;
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c b/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c
new file mode 100644
index 000000000000..a8d1eaa67020
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2024. Huawei Technologies Co., Ltd */
+#include "test_progs.h"
+#include "read_vsyscall.skel.h"
+
+#if defined(__x86_64__)
+/* For VSYSCALL_ADDR */
+#include <asm/vsyscall.h>
+#else
+/* To prevent build failure on non-x86 arch */
+#define VSYSCALL_ADDR 0UL
+#endif
+
+struct read_ret_desc {
+	const char *name;
+	int ret;
+} all_read[] = {
+	{ .name = "probe_read_kernel", .ret = -ERANGE },
+	{ .name = "probe_read_kernel_str", .ret = -ERANGE },
+	{ .name = "probe_read", .ret = -ERANGE },
+	{ .name = "probe_read_str", .ret = -ERANGE },
+	{ .name = "probe_read_user", .ret = -EFAULT },
+	{ .name = "probe_read_user_str", .ret = -EFAULT },
+	{ .name = "copy_from_user", .ret = -EFAULT },
+	{ .name = "copy_from_user_task", .ret = -EFAULT },
+	{ .name = "copy_from_user_str", .ret = -EFAULT },
+	{ .name = "copy_from_user_task_str", .ret = -EFAULT },
+};
+
+void test_read_vsyscall(void)
+{
+	struct read_vsyscall *skel;
+	unsigned int i;
+	int err;
+
+#if !defined(__x86_64__)
+	test__skip();
+	return;
+#endif
+	skel = read_vsyscall__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "read_vsyscall open_load"))
+		return;
+
+	skel->bss->target_pid = getpid();
+	err = read_vsyscall__attach(skel);
+	if (!ASSERT_EQ(err, 0, "read_vsyscall attach"))
+		goto out;
+
+	/* userspace may don't have vsyscall page due to LEGACY_VSYSCALL_NONE,
+	 * but it doesn't affect the returned error codes.
+	 */
+	skel->bss->user_ptr = (void *)VSYSCALL_ADDR;
+	usleep(1);
+
+	for (i = 0; i < ARRAY_SIZE(all_read); i++)
+		ASSERT_EQ(skel->bss->read_ret[i], all_read[i].ret, all_read[i].name);
+out:
+	read_vsyscall__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/recursion.c b/tools/testing/selftests/bpf/prog_tests/recursion.c
index f3af2627b599..23552d3e3365 100644
--- a/tools/testing/selftests/bpf/prog_tests/recursion.c
+++ b/tools/testing/selftests/bpf/prog_tests/recursion.c
@@ -31,8 +31,8 @@ void test_recursion(void)
 	bpf_map_delete_elem(bpf_map__fd(skel->maps.hash2), &key);
 	ASSERT_EQ(skel->bss->pass2, 2, "pass2 == 2");
 
-	err = bpf_obj_get_info_by_fd(bpf_program__fd(skel->progs.on_delete),
-				     &prog_info, &prog_info_len);
+	err = bpf_prog_get_info_by_fd(bpf_program__fd(skel->progs.on_delete),
+				      &prog_info, &prog_info_len);
 	if (!ASSERT_OK(err, "get_prog_info"))
 		goto out;
 	ASSERT_EQ(prog_info.recursion_misses, 2, "recursion_misses");
diff --git a/tools/testing/selftests/bpf/prog_tests/recursive_attach.c b/tools/testing/selftests/bpf/prog_tests/recursive_attach.c
new file mode 100644
index 000000000000..0ffa01d54ce2
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/recursive_attach.c
@@ -0,0 +1,218 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Red Hat, Inc. */
+#include <test_progs.h>
+#include "fentry_recursive.skel.h"
+#include "fentry_recursive_target.skel.h"
+#include <bpf/btf.h>
+#include "bpf/libbpf_internal.h"
+
+/* Test recursive attachment of tracing progs with more than one nesting level
+ * is not possible. Create a chain of attachment, verify that the last prog
+ * will fail. Depending on the arguments, following cases are tested:
+ *
+ * - Recursive loading of tracing progs, without attaching (attach = false,
+ *   detach = false). The chain looks like this:
+ *       load target
+ *       load fentry1 -> target
+ *       load fentry2 -> fentry1 (fail)
+ *
+ * - Recursive attach of tracing progs (attach = true, detach = false). The
+ *   chain looks like this:
+ *       load target
+ *       load fentry1 -> target
+ *       attach fentry1 -> target
+ *       load fentry2 -> fentry1 (fail)
+ *
+ * - Recursive attach and detach of tracing progs (attach = true, detach =
+ *   true). This validates that attach_tracing_prog flag will be set throughout
+ *   the whole lifecycle of an fentry prog, independently from whether it's
+ *   detached. The chain looks like this:
+ *       load target
+ *       load fentry1 -> target
+ *       attach fentry1 -> target
+ *       detach fentry1
+ *       load fentry2 -> fentry1 (fail)
+ */
+static void test_recursive_fentry_chain(bool attach, bool detach)
+{
+	struct fentry_recursive_target *target_skel = NULL;
+	struct fentry_recursive *tracing_chain[2] = {};
+	struct bpf_program *prog;
+	int prev_fd, err;
+
+	target_skel = fentry_recursive_target__open_and_load();
+	if (!ASSERT_OK_PTR(target_skel, "fentry_recursive_target__open_and_load"))
+		return;
+
+	/* Create an attachment chain with two fentry progs */
+	for (int i = 0; i < 2; i++) {
+		tracing_chain[i] = fentry_recursive__open();
+		if (!ASSERT_OK_PTR(tracing_chain[i], "fentry_recursive__open"))
+			goto close_prog;
+
+		/* The first prog in the chain is going to be attached to the target
+		 * fentry program, the second one to the previous in the chain.
+		 */
+		prog = tracing_chain[i]->progs.recursive_attach;
+		if (i == 0) {
+			prev_fd = bpf_program__fd(target_skel->progs.test1);
+			err = bpf_program__set_attach_target(prog, prev_fd, "test1");
+		} else {
+			prev_fd = bpf_program__fd(tracing_chain[i-1]->progs.recursive_attach);
+			err = bpf_program__set_attach_target(prog, prev_fd, "recursive_attach");
+		}
+
+		if (!ASSERT_OK(err, "bpf_program__set_attach_target"))
+			goto close_prog;
+
+		err = fentry_recursive__load(tracing_chain[i]);
+		/* The first attach should succeed, the second fail */
+		if (i == 0) {
+			if (!ASSERT_OK(err, "fentry_recursive__load"))
+				goto close_prog;
+
+			if (attach) {
+				err = fentry_recursive__attach(tracing_chain[i]);
+				if (!ASSERT_OK(err, "fentry_recursive__attach"))
+					goto close_prog;
+			}
+
+			if (detach) {
+				/* Flag attach_tracing_prog should still be set, preventing
+				 * attachment of the following prog.
+				 */
+				fentry_recursive__detach(tracing_chain[i]);
+			}
+		} else {
+			if (!ASSERT_ERR(err, "fentry_recursive__load"))
+				goto close_prog;
+		}
+	}
+
+close_prog:
+	fentry_recursive_target__destroy(target_skel);
+	for (int i = 0; i < 2; i++) {
+		fentry_recursive__destroy(tracing_chain[i]);
+	}
+}
+
+void test_recursive_fentry(void)
+{
+	if (test__start_subtest("attach"))
+		test_recursive_fentry_chain(true, false);
+	if (test__start_subtest("load"))
+		test_recursive_fentry_chain(false, false);
+	if (test__start_subtest("detach"))
+		test_recursive_fentry_chain(true, true);
+}
+
+/* Test that a tracing prog reattachment (when we land in
+ * "prog->aux->dst_trampoline and tgt_prog is NULL" branch in
+ * bpf_tracing_prog_attach) does not lead to a crash due to missing attach_btf
+ */
+void test_fentry_attach_btf_presence(void)
+{
+	struct fentry_recursive_target *target_skel = NULL;
+	struct fentry_recursive *tracing_skel = NULL;
+	struct bpf_program *prog;
+	int err, link_fd, tgt_prog_fd;
+
+	target_skel = fentry_recursive_target__open_and_load();
+	if (!ASSERT_OK_PTR(target_skel, "fentry_recursive_target__open_and_load"))
+		goto close_prog;
+
+	tracing_skel = fentry_recursive__open();
+	if (!ASSERT_OK_PTR(tracing_skel, "fentry_recursive__open"))
+		goto close_prog;
+
+	prog = tracing_skel->progs.recursive_attach;
+	tgt_prog_fd = bpf_program__fd(target_skel->progs.fentry_target);
+	err = bpf_program__set_attach_target(prog, tgt_prog_fd, "fentry_target");
+	if (!ASSERT_OK(err, "bpf_program__set_attach_target"))
+		goto close_prog;
+
+	err = fentry_recursive__load(tracing_skel);
+	if (!ASSERT_OK(err, "fentry_recursive__load"))
+		goto close_prog;
+
+	tgt_prog_fd = bpf_program__fd(tracing_skel->progs.recursive_attach);
+	link_fd = bpf_link_create(tgt_prog_fd, 0, BPF_TRACE_FENTRY, NULL);
+	if (!ASSERT_GE(link_fd, 0, "link_fd"))
+		goto close_prog;
+
+	fentry_recursive__detach(tracing_skel);
+
+	err = fentry_recursive__attach(tracing_skel);
+	ASSERT_ERR(err, "fentry_recursive__attach");
+
+close_prog:
+	fentry_recursive_target__destroy(target_skel);
+	fentry_recursive__destroy(tracing_skel);
+}
+
+static void *fentry_target_test_run(void *arg)
+{
+	for (;;) {
+		int prog_fd = __atomic_load_n((int *)arg, __ATOMIC_SEQ_CST);
+		LIBBPF_OPTS(bpf_test_run_opts, topts);
+		int err;
+
+		if (prog_fd == -1)
+			break;
+		err = bpf_prog_test_run_opts(prog_fd, &topts);
+		if (!ASSERT_OK(err, "fentry_target test_run"))
+			break;
+	}
+
+	return NULL;
+}
+
+void test_fentry_attach_stress(void)
+{
+	struct fentry_recursive_target *target_skel = NULL;
+	struct fentry_recursive *tracing_skel = NULL;
+	struct bpf_program *prog;
+	int err, i, tgt_prog_fd;
+	pthread_t thread;
+
+	target_skel = fentry_recursive_target__open_and_load();
+	if (!ASSERT_OK_PTR(target_skel,
+			   "fentry_recursive_target__open_and_load"))
+		goto close_prog;
+	tgt_prog_fd = bpf_program__fd(target_skel->progs.fentry_target);
+	err = pthread_create(&thread, NULL,
+			     fentry_target_test_run, &tgt_prog_fd);
+	if (!ASSERT_OK(err, "bpf_program__set_attach_target"))
+		goto close_prog;
+
+	for (i = 0; i < 1000; i++) {
+		tracing_skel = fentry_recursive__open();
+		if (!ASSERT_OK_PTR(tracing_skel, "fentry_recursive__open"))
+			goto stop_thread;
+
+		prog = tracing_skel->progs.recursive_attach;
+		err = bpf_program__set_attach_target(prog, tgt_prog_fd,
+						     "fentry_target");
+		if (!ASSERT_OK(err, "bpf_program__set_attach_target"))
+			goto stop_thread;
+
+		err = fentry_recursive__load(tracing_skel);
+		if (!ASSERT_OK(err, "fentry_recursive__load"))
+			goto stop_thread;
+
+		err = fentry_recursive__attach(tracing_skel);
+		if (!ASSERT_OK(err, "fentry_recursive__attach"))
+			goto stop_thread;
+
+		fentry_recursive__destroy(tracing_skel);
+		tracing_skel = NULL;
+	}
+
+stop_thread:
+	__atomic_store_n(&tgt_prog_fd, -1, __ATOMIC_SEQ_CST);
+	err = pthread_join(thread, NULL);
+	ASSERT_OK(err, "pthread_join");
+close_prog:
+	fentry_recursive__destroy(tracing_skel);
+	fentry_recursive_target__destroy(target_skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c b/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c
new file mode 100644
index 000000000000..d2c0542716a8
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/refcounted_kptr.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <test_progs.h>
+#include <network_helpers.h>
+
+#include "refcounted_kptr.skel.h"
+#include "refcounted_kptr_fail.skel.h"
+
+void test_refcounted_kptr(void)
+{
+	RUN_TESTS(refcounted_kptr);
+}
+
+void test_refcounted_kptr_fail(void)
+{
+	RUN_TESTS(refcounted_kptr_fail);
+}
+
+void test_refcounted_kptr_wrong_owner(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+	struct refcounted_kptr *skel;
+	int ret;
+
+	skel = refcounted_kptr__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "refcounted_kptr__open_and_load"))
+		return;
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_wrong_owner_remove_fail_a1), &opts);
+	ASSERT_OK(ret, "rbtree_wrong_owner_remove_fail_a1");
+	ASSERT_OK(opts.retval, "rbtree_wrong_owner_remove_fail_a1 retval");
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_wrong_owner_remove_fail_b), &opts);
+	ASSERT_OK(ret, "rbtree_wrong_owner_remove_fail_b");
+	ASSERT_OK(opts.retval, "rbtree_wrong_owner_remove_fail_b retval");
+
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.rbtree_wrong_owner_remove_fail_a2), &opts);
+	ASSERT_OK(ret, "rbtree_wrong_owner_remove_fail_a2");
+	ASSERT_OK(opts.retval, "rbtree_wrong_owner_remove_fail_a2 retval");
+	refcounted_kptr__destroy(skel);
+}
+
+void test_percpu_hash_refcounted_kptr_refcount_leak(void)
+{
+	struct refcounted_kptr *skel;
+	int cpu_nr, fd, err, key = 0;
+	struct bpf_map *map;
+	size_t values_sz;
+	u64 *values;
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .repeat = 1,
+	);
+
+	cpu_nr = libbpf_num_possible_cpus();
+	if (!ASSERT_GT(cpu_nr, 0, "libbpf_num_possible_cpus"))
+		return;
+
+	values = calloc(cpu_nr, sizeof(u64));
+	if (!ASSERT_OK_PTR(values, "calloc values"))
+		return;
+
+	skel = refcounted_kptr__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "refcounted_kptr__open_and_load")) {
+		free(values);
+		return;
+	}
+
+	values_sz = cpu_nr * sizeof(u64);
+	memset(values, 0, values_sz);
+
+	map = skel->maps.percpu_hash;
+	err = bpf_map__update_elem(map, &key, sizeof(key), values, values_sz, 0);
+	if (!ASSERT_OK(err, "bpf_map__update_elem"))
+		goto out;
+
+	fd = bpf_program__fd(skel->progs.percpu_hash_refcount_leak);
+	err = bpf_prog_test_run_opts(fd, &opts);
+	if (!ASSERT_OK(err, "bpf_prog_test_run_opts"))
+		goto out;
+	if (!ASSERT_EQ(opts.retval, 2, "opts.retval"))
+		goto out;
+
+	err = bpf_map__update_elem(map, &key, sizeof(key), values, values_sz, 0);
+	if (!ASSERT_OK(err, "bpf_map__update_elem"))
+		goto out;
+
+	fd = bpf_program__fd(skel->progs.check_percpu_hash_refcount);
+	err = bpf_prog_test_run_opts(fd, &opts);
+	ASSERT_OK(err, "bpf_prog_test_run_opts");
+	ASSERT_EQ(opts.retval, 1, "opts.retval");
+
+out:
+	refcounted_kptr__destroy(skel);
+	free(values);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
new file mode 100644
index 000000000000..d93a0c7b1786
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c
@@ -0,0 +1,2161 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#define _GNU_SOURCE
+#include <limits.h>
+#include <test_progs.h>
+#include <linux/filter.h>
+#include <linux/bpf.h>
+
+/* =================================
+ * SHORT AND CONSISTENT NUMBER TYPES
+ * =================================
+ */
+#define U64_MAX ((u64)UINT64_MAX)
+#define U32_MAX ((u32)UINT_MAX)
+#define U16_MAX ((u32)UINT_MAX)
+#define S64_MIN ((s64)INT64_MIN)
+#define S64_MAX ((s64)INT64_MAX)
+#define S32_MIN ((s32)INT_MIN)
+#define S32_MAX ((s32)INT_MAX)
+#define S16_MIN ((s16)0x80000000)
+#define S16_MAX ((s16)0x7fffffff)
+
+typedef unsigned long long ___u64;
+typedef unsigned int ___u32;
+typedef long long ___s64;
+typedef int ___s32;
+
+/* avoid conflicts with already defined types in kernel headers */
+#define u64 ___u64
+#define u32 ___u32
+#define s64 ___s64
+#define s32 ___s32
+
+/* ==================================
+ * STRING BUF ABSTRACTION AND HELPERS
+ * ==================================
+ */
+struct strbuf {
+	size_t buf_sz;
+	int pos;
+	char buf[0];
+};
+
+#define DEFINE_STRBUF(name, N)						\
+	struct { struct strbuf buf; char data[(N)]; } ___##name;	\
+	struct strbuf *name = (___##name.buf.buf_sz = (N), ___##name.buf.pos = 0, &___##name.buf)
+
+__printf(2, 3)
+static inline void snappendf(struct strbuf *s, const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	s->pos += vsnprintf(s->buf + s->pos,
+			    s->pos < s->buf_sz ? s->buf_sz - s->pos : 0,
+			    fmt, args);
+	va_end(args);
+}
+
+/* ==================================
+ * GENERIC NUMBER TYPE AND OPERATIONS
+ * ==================================
+ */
+enum num_t { U64, first_t = U64, U32, S64, S32, last_t = S32 };
+
+static __always_inline u64 min_t(enum num_t t, u64 x, u64 y)
+{
+	switch (t) {
+	case U64: return (u64)x < (u64)y ? (u64)x : (u64)y;
+	case U32: return (u32)x < (u32)y ? (u32)x : (u32)y;
+	case S64: return (s64)x < (s64)y ? (s64)x : (s64)y;
+	case S32: return (s32)x < (s32)y ? (s32)x : (s32)y;
+	default: printf("min_t!\n"); exit(1);
+	}
+}
+
+static __always_inline u64 max_t(enum num_t t, u64 x, u64 y)
+{
+	switch (t) {
+	case U64: return (u64)x > (u64)y ? (u64)x : (u64)y;
+	case U32: return (u32)x > (u32)y ? (u32)x : (u32)y;
+	case S64: return (s64)x > (s64)y ? (s64)x : (s64)y;
+	case S32: return (s32)x > (s32)y ? (u32)(s32)x : (u32)(s32)y;
+	default: printf("max_t!\n"); exit(1);
+	}
+}
+
+static __always_inline u64 cast_t(enum num_t t, u64 x)
+{
+	switch (t) {
+	case U64: return (u64)x;
+	case U32: return (u32)x;
+	case S64: return (s64)x;
+	case S32: return (u32)(s32)x;
+	default: printf("cast_t!\n"); exit(1);
+	}
+}
+
+static const char *t_str(enum num_t t)
+{
+	switch (t) {
+	case U64: return "u64";
+	case U32: return "u32";
+	case S64: return "s64";
+	case S32: return "s32";
+	default: printf("t_str!\n"); exit(1);
+	}
+}
+
+static enum num_t t_is_32(enum num_t t)
+{
+	switch (t) {
+	case U64: return false;
+	case U32: return true;
+	case S64: return false;
+	case S32: return true;
+	default: printf("t_is_32!\n"); exit(1);
+	}
+}
+
+static enum num_t t_signed(enum num_t t)
+{
+	switch (t) {
+	case U64: return S64;
+	case U32: return S32;
+	case S64: return S64;
+	case S32: return S32;
+	default: printf("t_signed!\n"); exit(1);
+	}
+}
+
+static enum num_t t_unsigned(enum num_t t)
+{
+	switch (t) {
+	case U64: return U64;
+	case U32: return U32;
+	case S64: return U64;
+	case S32: return U32;
+	default: printf("t_unsigned!\n"); exit(1);
+	}
+}
+
+#define UNUM_MAX_DECIMAL U16_MAX
+#define SNUM_MAX_DECIMAL S16_MAX
+#define SNUM_MIN_DECIMAL S16_MIN
+
+static bool num_is_small(enum num_t t, u64 x)
+{
+	switch (t) {
+	case U64: return (u64)x <= UNUM_MAX_DECIMAL;
+	case U32: return (u32)x <= UNUM_MAX_DECIMAL;
+	case S64: return (s64)x >= SNUM_MIN_DECIMAL && (s64)x <= SNUM_MAX_DECIMAL;
+	case S32: return (s32)x >= SNUM_MIN_DECIMAL && (s32)x <= SNUM_MAX_DECIMAL;
+	default: printf("num_is_small!\n"); exit(1);
+	}
+}
+
+static void snprintf_num(enum num_t t, struct strbuf *sb, u64 x)
+{
+	bool is_small = num_is_small(t, x);
+
+	if (is_small) {
+		switch (t) {
+		case U64: return snappendf(sb, "%llu", (u64)x);
+		case U32: return snappendf(sb, "%u", (u32)x);
+		case S64: return snappendf(sb, "%lld", (s64)x);
+		case S32: return snappendf(sb, "%d", (s32)x);
+		default: printf("snprintf_num!\n"); exit(1);
+		}
+	} else {
+		switch (t) {
+		case U64:
+			if (x == U64_MAX)
+				return snappendf(sb, "U64_MAX");
+			else if (x >= U64_MAX - 256)
+				return snappendf(sb, "U64_MAX-%llu", U64_MAX - x);
+			else
+				return snappendf(sb, "%#llx", (u64)x);
+		case U32:
+			if ((u32)x == U32_MAX)
+				return snappendf(sb, "U32_MAX");
+			else if ((u32)x >= U32_MAX - 256)
+				return snappendf(sb, "U32_MAX-%u", U32_MAX - (u32)x);
+			else
+				return snappendf(sb, "%#x", (u32)x);
+		case S64:
+			if ((s64)x == S64_MAX)
+				return snappendf(sb, "S64_MAX");
+			else if ((s64)x >= S64_MAX - 256)
+				return snappendf(sb, "S64_MAX-%lld", S64_MAX - (s64)x);
+			else if ((s64)x == S64_MIN)
+				return snappendf(sb, "S64_MIN");
+			else if ((s64)x <= S64_MIN + 256)
+				return snappendf(sb, "S64_MIN+%lld", (s64)x - S64_MIN);
+			else
+				return snappendf(sb, "%#llx", (s64)x);
+		case S32:
+			if ((s32)x == S32_MAX)
+				return snappendf(sb, "S32_MAX");
+			else if ((s32)x >= S32_MAX - 256)
+				return snappendf(sb, "S32_MAX-%d", S32_MAX - (s32)x);
+			else if ((s32)x == S32_MIN)
+				return snappendf(sb, "S32_MIN");
+			else if ((s32)x <= S32_MIN + 256)
+				return snappendf(sb, "S32_MIN+%d", (s32)x - S32_MIN);
+			else
+				return snappendf(sb, "%#x", (s32)x);
+		default: printf("snprintf_num!\n"); exit(1);
+		}
+	}
+}
+
+/* ===================================
+ * GENERIC RANGE STRUCT AND OPERATIONS
+ * ===================================
+ */
+struct range {
+	u64 a, b;
+};
+
+static void snprintf_range(enum num_t t, struct strbuf *sb, struct range x)
+{
+	if (x.a == x.b)
+		return snprintf_num(t, sb, x.a);
+
+	snappendf(sb, "[");
+	snprintf_num(t, sb, x.a);
+	snappendf(sb, "; ");
+	snprintf_num(t, sb, x.b);
+	snappendf(sb, "]");
+}
+
+static void print_range(enum num_t t, struct range x, const char *sfx)
+{
+	DEFINE_STRBUF(sb, 128);
+
+	snprintf_range(t, sb, x);
+	printf("%s%s", sb->buf, sfx);
+}
+
+static const struct range unkn[] = {
+	[U64] = { 0, U64_MAX },
+	[U32] = { 0, U32_MAX },
+	[S64] = { (u64)S64_MIN, (u64)S64_MAX },
+	[S32] = { (u64)(u32)S32_MIN, (u64)(u32)S32_MAX },
+};
+
+static struct range unkn_subreg(enum num_t t)
+{
+	switch (t) {
+	case U64: return unkn[U32];
+	case U32: return unkn[U32];
+	case S64: return unkn[U32];
+	case S32: return unkn[S32];
+	default: printf("unkn_subreg!\n"); exit(1);
+	}
+}
+
+static struct range range(enum num_t t, u64 a, u64 b)
+{
+	switch (t) {
+	case U64: return (struct range){ (u64)a, (u64)b };
+	case U32: return (struct range){ (u32)a, (u32)b };
+	case S64: return (struct range){ (s64)a, (s64)b };
+	case S32: return (struct range){ (u32)(s32)a, (u32)(s32)b };
+	default: printf("range!\n"); exit(1);
+	}
+}
+
+static __always_inline u32 sign64(u64 x) { return (x >> 63) & 1; }
+static __always_inline u32 sign32(u64 x) { return ((u32)x >> 31) & 1; }
+static __always_inline u32 upper32(u64 x) { return (u32)(x >> 32); }
+static __always_inline u64 swap_low32(u64 x, u32 y) { return (x & 0xffffffff00000000ULL) | y; }
+
+static bool range_eq(struct range x, struct range y)
+{
+	return x.a == y.a && x.b == y.b;
+}
+
+static struct range range_cast_to_s32(struct range x)
+{
+	u64 a = x.a, b = x.b;
+
+	/* if upper 32 bits are constant, lower 32 bits should form a proper
+	 * s32 range to be correct
+	 */
+	if (upper32(a) == upper32(b) && (s32)a <= (s32)b)
+		return range(S32, a, b);
+
+	/* Special case where upper bits form a small sequence of two
+	 * sequential numbers (in 32-bit unsigned space, so 0xffffffff to
+	 * 0x00000000 is also valid), while lower bits form a proper s32 range
+	 * going from negative numbers to positive numbers.
+	 *
+	 * E.g.: [0xfffffff0ffffff00; 0xfffffff100000010]. Iterating
+	 * over full 64-bit numbers range will form a proper [-16, 16]
+	 * ([0xffffff00; 0x00000010]) range in its lower 32 bits.
+	 */
+	if (upper32(a) + 1 == upper32(b) && (s32)a < 0 && (s32)b >= 0)
+		return range(S32, a, b);
+
+	/* otherwise we can't derive much meaningful information */
+	return unkn[S32];
+}
+
+static struct range range_cast_u64(enum num_t to_t, struct range x)
+{
+	u64 a = (u64)x.a, b = (u64)x.b;
+
+	switch (to_t) {
+	case U64:
+		return x;
+	case U32:
+		if (upper32(a) != upper32(b))
+			return unkn[U32];
+		return range(U32, a, b);
+	case S64:
+		if (sign64(a) != sign64(b))
+			return unkn[S64];
+		return range(S64, a, b);
+	case S32:
+		return range_cast_to_s32(x);
+	default: printf("range_cast_u64!\n"); exit(1);
+	}
+}
+
+static struct range range_cast_s64(enum num_t to_t, struct range x)
+{
+	s64 a = (s64)x.a, b = (s64)x.b;
+
+	switch (to_t) {
+	case U64:
+		/* equivalent to (s64)a <= (s64)b check */
+		if (sign64(a) != sign64(b))
+			return unkn[U64];
+		return range(U64, a, b);
+	case U32:
+		if (upper32(a) != upper32(b) || sign32(a) != sign32(b))
+			return unkn[U32];
+		return range(U32, a, b);
+	case S64:
+		return x;
+	case S32:
+		return range_cast_to_s32(x);
+	default: printf("range_cast_s64!\n"); exit(1);
+	}
+}
+
+static struct range range_cast_u32(enum num_t to_t, struct range x)
+{
+	u32 a = (u32)x.a, b = (u32)x.b;
+
+	switch (to_t) {
+	case U64:
+	case S64:
+		/* u32 is always a valid zero-extended u64/s64 */
+		return range(to_t, a, b);
+	case U32:
+		return x;
+	case S32:
+		return range_cast_to_s32(range(U32, a, b));
+	default: printf("range_cast_u32!\n"); exit(1);
+	}
+}
+
+static struct range range_cast_s32(enum num_t to_t, struct range x)
+{
+	s32 a = (s32)x.a, b = (s32)x.b;
+
+	switch (to_t) {
+	case U64:
+	case U32:
+	case S64:
+		if (sign32(a) != sign32(b))
+			return unkn[to_t];
+		return range(to_t, a, b);
+	case S32:
+		return x;
+	default: printf("range_cast_s32!\n"); exit(1);
+	}
+}
+
+/* Reinterpret range in *from_t* domain as a range in *to_t* domain preserving
+ * all possible information. Worst case, it will be unknown range within
+ * *to_t* domain, if nothing more specific can be guaranteed during the
+ * conversion
+ */
+static struct range range_cast(enum num_t from_t, enum num_t to_t, struct range from)
+{
+	switch (from_t) {
+	case U64: return range_cast_u64(to_t, from);
+	case U32: return range_cast_u32(to_t, from);
+	case S64: return range_cast_s64(to_t, from);
+	case S32: return range_cast_s32(to_t, from);
+	default: printf("range_cast!\n"); exit(1);
+	}
+}
+
+static bool is_valid_num(enum num_t t, u64 x)
+{
+	switch (t) {
+	case U64: return true;
+	case U32: return upper32(x) == 0;
+	case S64: return true;
+	case S32: return upper32(x) == 0;
+	default: printf("is_valid_num!\n"); exit(1);
+	}
+}
+
+static bool is_valid_range(enum num_t t, struct range x)
+{
+	if (!is_valid_num(t, x.a) || !is_valid_num(t, x.b))
+		return false;
+
+	switch (t) {
+	case U64: return (u64)x.a <= (u64)x.b;
+	case U32: return (u32)x.a <= (u32)x.b;
+	case S64: return (s64)x.a <= (s64)x.b;
+	case S32: return (s32)x.a <= (s32)x.b;
+	default: printf("is_valid_range!\n"); exit(1);
+	}
+}
+
+static struct range range_improve(enum num_t t, struct range old, struct range new)
+{
+	return range(t, max_t(t, old.a, new.a), min_t(t, old.b, new.b));
+}
+
+static struct range range_refine(enum num_t x_t, struct range x, enum num_t y_t, struct range y)
+{
+	struct range y_cast;
+
+	y_cast = range_cast(y_t, x_t, y);
+
+	/* If we know that
+	 *   - *x* is in the range of signed 32bit value, and
+	 *   - *y_cast* range is 32-bit signed non-negative
+	 * then *x* range can be improved with *y_cast* such that *x* range
+	 * is 32-bit signed non-negative. Otherwise, if the new range for *x*
+	 * allows upper 32-bit * 0xffffffff then the eventual new range for
+	 * *x* will be out of signed 32-bit range which violates the origin
+	 * *x* range.
+	 */
+	if (x_t == S64 && y_t == S32 && y_cast.a <= S32_MAX  && y_cast.b <= S32_MAX &&
+	    (s64)x.a >= S32_MIN && (s64)x.b <= S32_MAX)
+		return range_improve(x_t, x, y_cast);
+
+	/* the case when new range knowledge, *y*, is a 32-bit subregister
+	 * range, while previous range knowledge, *x*, is a full register
+	 * 64-bit range, needs special treatment to take into account upper 32
+	 * bits of full register range
+	 */
+	if (t_is_32(y_t) && !t_is_32(x_t)) {
+		struct range x_swap;
+
+		/* some combinations of upper 32 bits and sign bit can lead to
+		 * invalid ranges, in such cases it's easier to detect them
+		 * after cast/swap than try to enumerate all the conditions
+		 * under which transformation and knowledge transfer is valid
+		 */
+		x_swap = range(x_t, swap_low32(x.a, y_cast.a), swap_low32(x.b, y_cast.b));
+		if (!is_valid_range(x_t, x_swap))
+			return x;
+		return range_improve(x_t, x, x_swap);
+	}
+
+	if (!t_is_32(x_t) && !t_is_32(y_t) && x_t != y_t) {
+		if (x_t == S64 && x.a > x.b) {
+			if (x.b < y.a && x.a <= y.b)
+				return range(x_t, x.a, y.b);
+			if (x.a > y.b && x.b >= y.a)
+				return range(x_t, y.a, x.b);
+		} else if (x_t == U64 && y.a > y.b) {
+			if (y.b < x.a && y.a <= x.b)
+				return range(x_t, y.a, x.b);
+			if (y.a > x.b && y.b >= x.a)
+				return range(x_t, x.a, y.b);
+		}
+	}
+
+	/* otherwise, plain range cast and intersection works */
+	return range_improve(x_t, x, y_cast);
+}
+
+/* =======================
+ * GENERIC CONDITIONAL OPS
+ * =======================
+ */
+enum op { OP_LT, OP_LE, OP_GT, OP_GE, OP_EQ, OP_NE, first_op = OP_LT, last_op = OP_NE };
+
+static enum op complement_op(enum op op)
+{
+	switch (op) {
+	case OP_LT: return OP_GE;
+	case OP_LE: return OP_GT;
+	case OP_GT: return OP_LE;
+	case OP_GE: return OP_LT;
+	case OP_EQ: return OP_NE;
+	case OP_NE: return OP_EQ;
+	default: printf("complement_op!\n"); exit(1);
+	}
+}
+
+static const char *op_str(enum op op)
+{
+	switch (op) {
+	case OP_LT: return "<";
+	case OP_LE: return "<=";
+	case OP_GT: return ">";
+	case OP_GE: return ">=";
+	case OP_EQ: return "==";
+	case OP_NE: return "!=";
+	default: printf("op_str!\n"); exit(1);
+	}
+}
+
+/* Can register with range [x.a, x.b] *EVER* satisfy
+ * OP (<, <=, >, >=, ==, !=) relation to
+ * a register with range [y.a, y.b]
+ * _in *num_t* domain_
+ */
+static bool range_canbe_op(enum num_t t, struct range x, struct range y, enum op op)
+{
+#define range_canbe(T) do {									\
+	switch (op) {										\
+	case OP_LT: return (T)x.a < (T)y.b;							\
+	case OP_LE: return (T)x.a <= (T)y.b;							\
+	case OP_GT: return (T)x.b > (T)y.a;							\
+	case OP_GE: return (T)x.b >= (T)y.a;							\
+	case OP_EQ: return (T)max_t(t, x.a, y.a) <= (T)min_t(t, x.b, y.b);			\
+	case OP_NE: return !((T)x.a == (T)x.b && (T)y.a == (T)y.b && (T)x.a == (T)y.a);		\
+	default: printf("range_canbe op %d\n", op); exit(1);					\
+	}											\
+} while (0)
+
+	switch (t) {
+	case U64: { range_canbe(u64); }
+	case U32: { range_canbe(u32); }
+	case S64: { range_canbe(s64); }
+	case S32: { range_canbe(s32); }
+	default: printf("range_canbe!\n"); exit(1);
+	}
+#undef range_canbe
+}
+
+/* Does register with range [x.a, x.b] *ALWAYS* satisfy
+ * OP (<, <=, >, >=, ==, !=) relation to
+ * a register with range [y.a, y.b]
+ * _in *num_t* domain_
+ */
+static bool range_always_op(enum num_t t, struct range x, struct range y, enum op op)
+{
+	/* always op <=> ! canbe complement(op) */
+	return !range_canbe_op(t, x, y, complement_op(op));
+}
+
+/* Does register with range [x.a, x.b] *NEVER* satisfy
+ * OP (<, <=, >, >=, ==, !=) relation to
+ * a register with range [y.a, y.b]
+ * _in *num_t* domain_
+ */
+static bool range_never_op(enum num_t t, struct range x, struct range y, enum op op)
+{
+	return !range_canbe_op(t, x, y, op);
+}
+
+/* similar to verifier's is_branch_taken():
+ *    1 - always taken;
+ *    0 - never taken,
+ *   -1 - unsure.
+ */
+static int range_branch_taken_op(enum num_t t, struct range x, struct range y, enum op op)
+{
+	if (range_always_op(t, x, y, op))
+		return 1;
+	if (range_never_op(t, x, y, op))
+		return 0;
+	return -1;
+}
+
+/* What would be the new estimates for register x and y ranges assuming truthful
+ * OP comparison between them. I.e., (x OP y == true) => x <- newx, y <- newy.
+ *
+ * We assume "interesting" cases where ranges overlap. Cases where it's
+ * obvious that (x OP y) is either always true or false should be filtered with
+ * range_never and range_always checks.
+ */
+static void range_cond(enum num_t t, struct range x, struct range y,
+		       enum op op, struct range *newx, struct range *newy)
+{
+	if (!range_canbe_op(t, x, y, op)) {
+		/* nothing to adjust, can't happen, return original values */
+		*newx = x;
+		*newy = y;
+		return;
+	}
+	switch (op) {
+	case OP_LT:
+		*newx = range(t, x.a, min_t(t, x.b, y.b - 1));
+		*newy = range(t, max_t(t, x.a + 1, y.a), y.b);
+		break;
+	case OP_LE:
+		*newx = range(t, x.a, min_t(t, x.b, y.b));
+		*newy = range(t, max_t(t, x.a, y.a), y.b);
+		break;
+	case OP_GT:
+		*newx = range(t, max_t(t, x.a, y.a + 1), x.b);
+		*newy = range(t, y.a, min_t(t, x.b - 1, y.b));
+		break;
+	case OP_GE:
+		*newx = range(t, max_t(t, x.a, y.a), x.b);
+		*newy = range(t, y.a, min_t(t, x.b, y.b));
+		break;
+	case OP_EQ:
+		*newx = range(t, max_t(t, x.a, y.a), min_t(t, x.b, y.b));
+		*newy = range(t, max_t(t, x.a, y.a), min_t(t, x.b, y.b));
+		break;
+	case OP_NE:
+		/* below logic is supported by the verifier now */
+		if (x.a == x.b && x.a == y.a) {
+			/* X is a constant matching left side of Y */
+			*newx = range(t, x.a, x.b);
+			*newy = range(t, y.a + 1, y.b);
+		} else if (x.a == x.b && x.b == y.b) {
+			/* X is a constant matching right side of Y */
+			*newx = range(t, x.a, x.b);
+			*newy = range(t, y.a, y.b - 1);
+		} else if (y.a == y.b && x.a == y.a) {
+			/* Y is a constant matching left side of X */
+			*newx = range(t, x.a + 1, x.b);
+			*newy = range(t, y.a, y.b);
+		} else if (y.a == y.b && x.b == y.b) {
+			/* Y is a constant matching right side of X */
+			*newx = range(t, x.a, x.b - 1);
+			*newy = range(t, y.a, y.b);
+		} else {
+			/* generic case, can't derive more information */
+			*newx = range(t, x.a, x.b);
+			*newy = range(t, y.a, y.b);
+		}
+
+		break;
+	default:
+		break;
+	}
+}
+
+/* =======================
+ * REGISTER STATE HANDLING
+ * =======================
+ */
+struct reg_state {
+	struct range r[4]; /* indexed by enum num_t: U64, U32, S64, S32 */
+	bool valid;
+};
+
+static void print_reg_state(struct reg_state *r, const char *sfx)
+{
+	DEFINE_STRBUF(sb, 512);
+	enum num_t t;
+	int cnt = 0;
+
+	if (!r->valid) {
+		printf("<not found>%s", sfx);
+		return;
+	}
+
+	snappendf(sb, "scalar(");
+	for (t = first_t; t <= last_t; t++) {
+		snappendf(sb, "%s%s=", cnt++ ? "," : "", t_str(t));
+		snprintf_range(t, sb, r->r[t]);
+	}
+	snappendf(sb, ")");
+
+	printf("%s%s", sb->buf, sfx);
+}
+
+static void print_refinement(enum num_t s_t, struct range src,
+			     enum num_t d_t, struct range old, struct range new,
+			     const char *ctx)
+{
+	printf("REFINING (%s) (%s)SRC=", ctx, t_str(s_t));
+	print_range(s_t, src, "");
+	printf(" (%s)DST_OLD=", t_str(d_t));
+	print_range(d_t, old, "");
+	printf(" (%s)DST_NEW=", t_str(d_t));
+	print_range(d_t, new, "\n");
+}
+
+static void reg_state_refine(struct reg_state *r, enum num_t t, struct range x, const char *ctx)
+{
+	enum num_t d_t, s_t;
+	struct range old;
+	bool keep_going = false;
+
+again:
+	/* try to derive new knowledge from just learned range x of type t */
+	for (d_t = first_t; d_t <= last_t; d_t++) {
+		old = r->r[d_t];
+		r->r[d_t] = range_refine(d_t, r->r[d_t], t, x);
+		if (!range_eq(r->r[d_t], old)) {
+			keep_going = true;
+			if (env.verbosity >= VERBOSE_VERY)
+				print_refinement(t, x, d_t, old, r->r[d_t], ctx);
+		}
+	}
+
+	/* now see if we can derive anything new from updated reg_state's ranges */
+	for (s_t = first_t; s_t <= last_t; s_t++) {
+		for (d_t = first_t; d_t <= last_t; d_t++) {
+			old = r->r[d_t];
+			r->r[d_t] = range_refine(d_t, r->r[d_t], s_t, r->r[s_t]);
+			if (!range_eq(r->r[d_t], old)) {
+				keep_going = true;
+				if (env.verbosity >= VERBOSE_VERY)
+					print_refinement(s_t, r->r[s_t], d_t, old, r->r[d_t], ctx);
+			}
+		}
+	}
+
+	/* keep refining until we converge */
+	if (keep_going) {
+		keep_going = false;
+		goto again;
+	}
+}
+
+static void reg_state_set_const(struct reg_state *rs, enum num_t t, u64 val)
+{
+	enum num_t tt;
+
+	rs->valid = true;
+	for (tt = first_t; tt <= last_t; tt++)
+		rs->r[tt] = tt == t ? range(t, val, val) : unkn[tt];
+
+	reg_state_refine(rs, t, rs->r[t], "CONST");
+}
+
+static void reg_state_cond(enum num_t t, struct reg_state *x, struct reg_state *y, enum op op,
+			   struct reg_state *newx, struct reg_state *newy, const char *ctx)
+{
+	char buf[32];
+	enum num_t ts[2];
+	struct reg_state xx = *x, yy = *y;
+	int i, t_cnt;
+	struct range z1, z2;
+
+	if (op == OP_EQ || op == OP_NE) {
+		/* OP_EQ and OP_NE are sign-agnostic, so we need to process
+		 * both signed and unsigned domains at the same time
+		 */
+		ts[0] = t_unsigned(t);
+		ts[1] = t_signed(t);
+		t_cnt = 2;
+	} else {
+		ts[0] = t;
+		t_cnt = 1;
+	}
+
+	for (i = 0; i < t_cnt; i++) {
+		t = ts[i];
+		z1 = x->r[t];
+		z2 = y->r[t];
+
+		range_cond(t, z1, z2, op, &z1, &z2);
+
+		if (newx) {
+			snprintf(buf, sizeof(buf), "%s R1", ctx);
+			reg_state_refine(&xx, t, z1, buf);
+		}
+		if (newy) {
+			snprintf(buf, sizeof(buf), "%s R2", ctx);
+			reg_state_refine(&yy, t, z2, buf);
+		}
+	}
+
+	if (newx)
+		*newx = xx;
+	if (newy)
+		*newy = yy;
+}
+
+static int reg_state_branch_taken_op(enum num_t t, struct reg_state *x, struct reg_state *y,
+				     enum op op)
+{
+	if (op == OP_EQ || op == OP_NE) {
+		/* OP_EQ and OP_NE are sign-agnostic */
+		enum num_t tu = t_unsigned(t);
+		enum num_t ts = t_signed(t);
+		int br_u, br_s, br;
+
+		br_u = range_branch_taken_op(tu, x->r[tu], y->r[tu], op);
+		br_s = range_branch_taken_op(ts, x->r[ts], y->r[ts], op);
+
+		if (br_u >= 0 && br_s >= 0 && br_u != br_s)
+			ASSERT_FALSE(true, "branch taken inconsistency!\n");
+
+		/* if 64-bit ranges are indecisive, use 32-bit subranges to
+		 * eliminate always/never taken branches, if possible
+		 */
+		if (br_u == -1 && (t == U64 || t == S64)) {
+			br = range_branch_taken_op(U32, x->r[U32], y->r[U32], op);
+			/* we can only reject for OP_EQ, never take branch
+			 * based on lower 32 bits
+			 */
+			if (op == OP_EQ && br == 0)
+				return 0;
+			/* for OP_NEQ we can be conclusive only if lower 32 bits
+			 * differ and thus inequality branch is always taken
+			 */
+			if (op == OP_NE && br == 1)
+				return 1;
+
+			br = range_branch_taken_op(S32, x->r[S32], y->r[S32], op);
+			if (op == OP_EQ && br == 0)
+				return 0;
+			if (op == OP_NE && br == 1)
+				return 1;
+		}
+
+		return br_u >= 0 ? br_u : br_s;
+	}
+	return range_branch_taken_op(t, x->r[t], y->r[t], op);
+}
+
+/* =====================================
+ * BPF PROGS GENERATION AND VERIFICATION
+ * =====================================
+ */
+struct case_spec {
+	/* whether to init full register (r1) or sub-register (w1) */
+	bool init_subregs;
+	/* whether to establish initial value range on full register (r1) or
+	 * sub-register (w1)
+	 */
+	bool setup_subregs;
+	/* whether to establish initial value range using signed or unsigned
+	 * comparisons (i.e., initialize umin/umax or smin/smax directly)
+	 */
+	bool setup_signed;
+	/* whether to perform comparison on full registers or sub-registers */
+	bool compare_subregs;
+	/* whether to perform comparison using signed or unsigned operations */
+	bool compare_signed;
+};
+
+/* Generate test BPF program based on provided test ranges, operation, and
+ * specifications about register bitness and signedness.
+ */
+static int load_range_cmp_prog(struct range x, struct range y, enum op op,
+			       int branch_taken, struct case_spec spec,
+			       char *log_buf, size_t log_sz,
+			       int *false_pos, int *true_pos)
+{
+#define emit(insn) ({							\
+	struct bpf_insn __insns[] = { insn };				\
+	int __i;							\
+	for (__i = 0; __i < ARRAY_SIZE(__insns); __i++)			\
+		insns[cur_pos + __i] = __insns[__i];			\
+	cur_pos += __i;							\
+})
+#define JMP_TO(target) (target - cur_pos - 1)
+	int cur_pos = 0, exit_pos, fd, op_code;
+	struct bpf_insn insns[64];
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		.log_level = 2,
+		.log_buf = log_buf,
+		.log_size = log_sz,
+		.prog_flags = testing_prog_flags(),
+	);
+
+	/* ; skip exit block below
+	 * goto +2;
+	 */
+	emit(BPF_JMP_A(2));
+	exit_pos = cur_pos;
+	/* ; exit block for all the preparatory conditionals
+	 * out:
+	 * r0 = 0;
+	 * exit;
+	 */
+	emit(BPF_MOV64_IMM(BPF_REG_0, 0));
+	emit(BPF_EXIT_INSN());
+	/*
+	 * ; assign r6/w6 and r7/w7 unpredictable u64/u32 value
+	 * call bpf_get_current_pid_tgid;
+	 * r6 = r0;               | w6 = w0;
+	 * call bpf_get_current_pid_tgid;
+	 * r7 = r0;               | w7 = w0;
+	 */
+	emit(BPF_EMIT_CALL(BPF_FUNC_get_current_pid_tgid));
+	if (spec.init_subregs)
+		emit(BPF_MOV32_REG(BPF_REG_6, BPF_REG_0));
+	else
+		emit(BPF_MOV64_REG(BPF_REG_6, BPF_REG_0));
+	emit(BPF_EMIT_CALL(BPF_FUNC_get_current_pid_tgid));
+	if (spec.init_subregs)
+		emit(BPF_MOV32_REG(BPF_REG_7, BPF_REG_0));
+	else
+		emit(BPF_MOV64_REG(BPF_REG_7, BPF_REG_0));
+	/* ; setup initial r6/w6 possible value range ([x.a, x.b])
+	 * r1 = %[x.a] ll;        | w1 = %[x.a];
+	 * r2 = %[x.b] ll;        | w2 = %[x.b];
+	 * if r6 < r1 goto out;   | if w6 < w1 goto out;
+	 * if r6 > r2 goto out;   | if w6 > w2 goto out;
+	 */
+	if (spec.setup_subregs) {
+		emit(BPF_MOV32_IMM(BPF_REG_1, (s32)x.a));
+		emit(BPF_MOV32_IMM(BPF_REG_2, (s32)x.b));
+		emit(BPF_JMP32_REG(spec.setup_signed ? BPF_JSLT : BPF_JLT,
+				   BPF_REG_6, BPF_REG_1, JMP_TO(exit_pos)));
+		emit(BPF_JMP32_REG(spec.setup_signed ? BPF_JSGT : BPF_JGT,
+				   BPF_REG_6, BPF_REG_2, JMP_TO(exit_pos)));
+	} else {
+		emit(BPF_LD_IMM64(BPF_REG_1, x.a));
+		emit(BPF_LD_IMM64(BPF_REG_2, x.b));
+		emit(BPF_JMP_REG(spec.setup_signed ? BPF_JSLT : BPF_JLT,
+				 BPF_REG_6, BPF_REG_1, JMP_TO(exit_pos)));
+		emit(BPF_JMP_REG(spec.setup_signed ? BPF_JSGT : BPF_JGT,
+				 BPF_REG_6, BPF_REG_2, JMP_TO(exit_pos)));
+	}
+	/* ; setup initial r7/w7 possible value range ([y.a, y.b])
+	 * r1 = %[y.a] ll;        | w1 = %[y.a];
+	 * r2 = %[y.b] ll;        | w2 = %[y.b];
+	 * if r7 < r1 goto out;   | if w7 < w1 goto out;
+	 * if r7 > r2 goto out;   | if w7 > w2 goto out;
+	 */
+	if (spec.setup_subregs) {
+		emit(BPF_MOV32_IMM(BPF_REG_1, (s32)y.a));
+		emit(BPF_MOV32_IMM(BPF_REG_2, (s32)y.b));
+		emit(BPF_JMP32_REG(spec.setup_signed ? BPF_JSLT : BPF_JLT,
+				   BPF_REG_7, BPF_REG_1, JMP_TO(exit_pos)));
+		emit(BPF_JMP32_REG(spec.setup_signed ? BPF_JSGT : BPF_JGT,
+				   BPF_REG_7, BPF_REG_2, JMP_TO(exit_pos)));
+	} else {
+		emit(BPF_LD_IMM64(BPF_REG_1, y.a));
+		emit(BPF_LD_IMM64(BPF_REG_2, y.b));
+		emit(BPF_JMP_REG(spec.setup_signed ? BPF_JSLT : BPF_JLT,
+				 BPF_REG_7, BPF_REG_1, JMP_TO(exit_pos)));
+		emit(BPF_JMP_REG(spec.setup_signed ? BPF_JSGT : BPF_JGT,
+				 BPF_REG_7, BPF_REG_2, JMP_TO(exit_pos)));
+	}
+	/* ; range test instruction
+	 * if r6 <op> r7 goto +3; | if w6 <op> w7 goto +3;
+	 */
+	switch (op) {
+	case OP_LT: op_code = spec.compare_signed ? BPF_JSLT : BPF_JLT; break;
+	case OP_LE: op_code = spec.compare_signed ? BPF_JSLE : BPF_JLE; break;
+	case OP_GT: op_code = spec.compare_signed ? BPF_JSGT : BPF_JGT; break;
+	case OP_GE: op_code = spec.compare_signed ? BPF_JSGE : BPF_JGE; break;
+	case OP_EQ: op_code = BPF_JEQ; break;
+	case OP_NE: op_code = BPF_JNE; break;
+	default:
+		printf("unrecognized op %d\n", op);
+		return -ENOTSUP;
+	}
+	/* ; BEFORE conditional, r0/w0 = {r6/w6,r7/w7} is to extract verifier state reliably
+	 * ; this is used for debugging, as verifier doesn't always print
+	 * ; registers states as of condition jump instruction (e.g., when
+	 * ; precision marking happens)
+	 * r0 = r6;               | w0 = w6;
+	 * r0 = r7;               | w0 = w7;
+	 */
+	if (spec.compare_subregs) {
+		emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_6));
+		emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_7));
+	} else {
+		emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_6));
+		emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_7));
+	}
+	if (spec.compare_subregs)
+		emit(BPF_JMP32_REG(op_code, BPF_REG_6, BPF_REG_7, 3));
+	else
+		emit(BPF_JMP_REG(op_code, BPF_REG_6, BPF_REG_7, 3));
+	/* ; FALSE branch, r0/w0 = {r6/w6,r7/w7} is to extract verifier state reliably
+	 * r0 = r6;               | w0 = w6;
+	 * r0 = r7;               | w0 = w7;
+	 * exit;
+	 */
+	*false_pos = cur_pos;
+	if (spec.compare_subregs) {
+		emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_6));
+		emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_7));
+	} else {
+		emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_6));
+		emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_7));
+	}
+	if (branch_taken == 1) /* false branch is never taken */
+		emit(BPF_EMIT_CALL(0xDEAD)); /* poison this branch */
+	else
+		emit(BPF_EXIT_INSN());
+	/* ; TRUE branch, r0/w0 = {r6/w6,r7/w7} is to extract verifier state reliably
+	 * r0 = r6;               | w0 = w6;
+	 * r0 = r7;               | w0 = w7;
+	 * exit;
+	 */
+	*true_pos = cur_pos;
+	if (spec.compare_subregs) {
+		emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_6));
+		emit(BPF_MOV32_REG(BPF_REG_0, BPF_REG_7));
+	} else {
+		emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_6));
+		emit(BPF_MOV64_REG(BPF_REG_0, BPF_REG_7));
+	}
+	if (branch_taken == 0) /* true branch is never taken */
+		emit(BPF_EMIT_CALL(0xDEAD)); /* poison this branch */
+	emit(BPF_EXIT_INSN()); /* last instruction has to be exit */
+
+	fd = bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT, "reg_bounds_test",
+			   "GPL", insns, cur_pos, &opts);
+	if (fd < 0)
+		return fd;
+
+	close(fd);
+	return 0;
+#undef emit
+#undef JMP_TO
+}
+
+#define str_has_pfx(str, pfx) (strncmp(str, pfx, strlen(pfx)) == 0)
+
+/* Parse register state from verifier log.
+ * `s` should point to the start of "Rx = ..." substring in the verifier log.
+ */
+static int parse_reg_state(const char *s, struct reg_state *reg)
+{
+	/* There are two generic forms for SCALAR register:
+	 * - known constant: R6_rwD=P%lld
+	 * - range: R6_rwD=scalar(id=1,...), where "..." is a comma-separated
+	 *   list of optional range specifiers:
+	 *     - umin=%llu, if missing, assumed 0;
+	 *     - umax=%llu, if missing, assumed U64_MAX;
+	 *     - smin=%lld, if missing, assumed S64_MIN;
+	 *     - smax=%lld, if missing, assumed S64_MAX;
+	 *     - umin32=%d, if missing, assumed 0;
+	 *     - umax32=%d, if missing, assumed U32_MAX;
+	 *     - smin32=%d, if missing, assumed S32_MIN;
+	 *     - smax32=%d, if missing, assumed S32_MAX;
+	 *     - var_off=(%#llx; %#llx), tnum part, we don't care about it.
+	 *
+	 * If some of the values are equal, they will be grouped (but min/max
+	 * are not mixed together, and similarly negative values are not
+	 * grouped with non-negative ones). E.g.:
+	 *
+	 *   R6_w=Pscalar(smin=smin32=0, smax=umax=umax32=1000)
+	 *
+	 * _rwD part is optional (and any of the letters can be missing).
+	 * P (precision mark) is optional as well.
+	 *
+	 * Anything inside scalar() is optional, including id, of course.
+	 */
+	struct {
+		const char *pfx;
+		u64 *dst, def;
+		bool is_32, is_set;
+	} *f, fields[8] = {
+		{"smin=", &reg->r[S64].a, S64_MIN},
+		{"smax=", &reg->r[S64].b, S64_MAX},
+		{"umin=", &reg->r[U64].a, 0},
+		{"umax=", &reg->r[U64].b, U64_MAX},
+		{"smin32=", &reg->r[S32].a, (u32)S32_MIN, true},
+		{"smax32=", &reg->r[S32].b, (u32)S32_MAX, true},
+		{"umin32=", &reg->r[U32].a, 0,            true},
+		{"umax32=", &reg->r[U32].b, U32_MAX,      true},
+	};
+	const char *p;
+	int i;
+
+	p = strchr(s, '=');
+	if (!p)
+		return -EINVAL;
+	p++;
+	if (*p == 'P')
+		p++;
+
+	if (!str_has_pfx(p, "scalar(")) {
+		long long sval;
+		enum num_t t;
+
+		if (p[0] == '0' && p[1] == 'x') {
+			if (sscanf(p, "%llx", &sval) != 1)
+				return -EINVAL;
+		} else {
+			if (sscanf(p, "%lld", &sval) != 1)
+				return -EINVAL;
+		}
+
+		reg->valid = true;
+		for (t = first_t; t <= last_t; t++) {
+			reg->r[t] = range(t, sval, sval);
+		}
+		return 0;
+	}
+
+	p += sizeof("scalar");
+	while (p) {
+		int midxs[ARRAY_SIZE(fields)], mcnt = 0;
+		u64 val;
+
+		for (i = 0; i < ARRAY_SIZE(fields); i++) {
+			f = &fields[i];
+			if (!str_has_pfx(p, f->pfx))
+				continue;
+			midxs[mcnt++] = i;
+			p += strlen(f->pfx);
+		}
+
+		if (mcnt) {
+			/* populate all matched fields */
+			if (p[0] == '0' && p[1] == 'x') {
+				if (sscanf(p, "%llx", &val) != 1)
+					return -EINVAL;
+			} else {
+				if (sscanf(p, "%lld", &val) != 1)
+					return -EINVAL;
+			}
+
+			for (i = 0; i < mcnt; i++) {
+				f = &fields[midxs[i]];
+				f->is_set = true;
+				*f->dst = f->is_32 ? (u64)(u32)val : val;
+			}
+		} else if (str_has_pfx(p, "var_off")) {
+			/* skip "var_off=(0x0; 0x3f)" part completely */
+			p = strchr(p, ')');
+			if (!p)
+				return -EINVAL;
+			p++;
+		}
+
+		p = strpbrk(p, ",)");
+		if (*p == ')')
+			break;
+		if (p)
+			p++;
+	}
+
+	reg->valid = true;
+
+	for (i = 0; i < ARRAY_SIZE(fields); i++) {
+		f = &fields[i];
+		if (!f->is_set)
+			*f->dst = f->def;
+	}
+
+	return 0;
+}
+
+
+/* Parse all register states (TRUE/FALSE branches and DST/SRC registers)
+ * out of the verifier log for a corresponding test case BPF program.
+ */
+static int parse_range_cmp_log(const char *log_buf, struct case_spec spec,
+			       int false_pos, int true_pos,
+			       struct reg_state *false1_reg, struct reg_state *false2_reg,
+			       struct reg_state *true1_reg, struct reg_state *true2_reg)
+{
+	struct {
+		int insn_idx;
+		int reg_idx;
+		const char *reg_upper;
+		struct reg_state *state;
+	} specs[] = {
+		{false_pos,     6, "R6=", false1_reg},
+		{false_pos + 1, 7, "R7=", false2_reg},
+		{true_pos,      6, "R6=", true1_reg},
+		{true_pos + 1,  7, "R7=", true2_reg},
+	};
+	char buf[32];
+	const char *p = log_buf, *q;
+	int i, err;
+
+	for (i = 0; i < 4; i++) {
+		sprintf(buf, "%d: (%s) %s = %s%d", specs[i].insn_idx,
+			spec.compare_subregs ? "bc" : "bf",
+			spec.compare_subregs ? "w0" : "r0",
+			spec.compare_subregs ? "w" : "r", specs[i].reg_idx);
+
+		q = strstr(p, buf);
+		if (!q) {
+			*specs[i].state = (struct reg_state){.valid = false};
+			continue;
+		}
+		p = strstr(q, specs[i].reg_upper);
+		if (!p)
+			return -EINVAL;
+		err = parse_reg_state(p, specs[i].state);
+		if (err)
+			return -EINVAL;
+	}
+	return 0;
+}
+
+/* Validate ranges match, and print details if they don't */
+static bool assert_range_eq(enum num_t t, struct range x, struct range y,
+			    const char *ctx1, const char *ctx2)
+{
+	DEFINE_STRBUF(sb, 512);
+
+	if (range_eq(x, y))
+		return true;
+
+	snappendf(sb, "MISMATCH %s.%s: ", ctx1, ctx2);
+	snprintf_range(t, sb, x);
+	snappendf(sb, " != ");
+	snprintf_range(t, sb, y);
+
+	printf("%s\n", sb->buf);
+
+	return false;
+}
+
+/* Validate that register states match, and print details if they don't */
+static bool assert_reg_state_eq(struct reg_state *r, struct reg_state *e, const char *ctx)
+{
+	bool ok = true;
+	enum num_t t;
+
+	if (r->valid != e->valid) {
+		printf("MISMATCH %s: actual %s != expected %s\n", ctx,
+		       r->valid ? "<valid>" : "<invalid>",
+		       e->valid ? "<valid>" : "<invalid>");
+		return false;
+	}
+
+	if (!r->valid)
+		return true;
+
+	for (t = first_t; t <= last_t; t++) {
+		if (!assert_range_eq(t, r->r[t], e->r[t], ctx, t_str(t)))
+			ok = false;
+	}
+
+	return ok;
+}
+
+/* Printf verifier log, filtering out irrelevant noise */
+static void print_verifier_log(const char *buf)
+{
+	const char *p;
+
+	while (buf[0]) {
+		p = strchrnul(buf, '\n');
+
+		/* filter out irrelevant precision backtracking logs */
+		if (str_has_pfx(buf, "mark_precise: "))
+			goto skip_line;
+
+		printf("%.*s\n", (int)(p - buf), buf);
+
+skip_line:
+		buf = *p == '\0' ? p : p + 1;
+	}
+}
+
+/* Simulate provided test case purely with our own range-based logic.
+ * This is done to set up expectations for verifier's branch_taken logic and
+ * verifier's register states in the verifier log.
+ */
+static void sim_case(enum num_t init_t, enum num_t cond_t,
+		     struct range x, struct range y, enum op op,
+		     struct reg_state *fr1, struct reg_state *fr2,
+		     struct reg_state *tr1, struct reg_state *tr2,
+		     int *branch_taken)
+{
+	const u64 A = x.a;
+	const u64 B = x.b;
+	const u64 C = y.a;
+	const u64 D = y.b;
+	struct reg_state rc;
+	enum op rev_op = complement_op(op);
+	enum num_t t;
+
+	fr1->valid = fr2->valid = true;
+	tr1->valid = tr2->valid = true;
+	for (t = first_t; t <= last_t; t++) {
+		/* if we are initializing using 32-bit subregisters,
+		 * full registers get upper 32 bits zeroed automatically
+		 */
+		struct range z = t_is_32(init_t) ? unkn_subreg(t) : unkn[t];
+
+		fr1->r[t] = fr2->r[t] = tr1->r[t] = tr2->r[t] = z;
+	}
+
+	/* step 1: r1 >= A, r2 >= C */
+	reg_state_set_const(&rc, init_t, A);
+	reg_state_cond(init_t, fr1, &rc, OP_GE, fr1, NULL, "r1>=A");
+	reg_state_set_const(&rc, init_t, C);
+	reg_state_cond(init_t, fr2, &rc, OP_GE, fr2, NULL, "r2>=C");
+	*tr1 = *fr1;
+	*tr2 = *fr2;
+	if (env.verbosity >= VERBOSE_VERY) {
+		printf("STEP1 (%s) R1: ", t_str(init_t)); print_reg_state(fr1, "\n");
+		printf("STEP1 (%s) R2: ", t_str(init_t)); print_reg_state(fr2, "\n");
+	}
+
+	/* step 2: r1 <= B, r2 <= D */
+	reg_state_set_const(&rc, init_t, B);
+	reg_state_cond(init_t, fr1, &rc, OP_LE, fr1, NULL, "r1<=B");
+	reg_state_set_const(&rc, init_t, D);
+	reg_state_cond(init_t, fr2, &rc, OP_LE, fr2, NULL, "r2<=D");
+	*tr1 = *fr1;
+	*tr2 = *fr2;
+	if (env.verbosity >= VERBOSE_VERY) {
+		printf("STEP2 (%s) R1: ", t_str(init_t)); print_reg_state(fr1, "\n");
+		printf("STEP2 (%s) R2: ", t_str(init_t)); print_reg_state(fr2, "\n");
+	}
+
+	/* step 3: r1 <op> r2 */
+	*branch_taken = reg_state_branch_taken_op(cond_t, fr1, fr2, op);
+	fr1->valid = fr2->valid = false;
+	tr1->valid = tr2->valid = false;
+	if (*branch_taken != 1) { /* FALSE is possible */
+		fr1->valid = fr2->valid = true;
+		reg_state_cond(cond_t, fr1, fr2, rev_op, fr1, fr2, "FALSE");
+	}
+	if (*branch_taken != 0) { /* TRUE is possible */
+		tr1->valid = tr2->valid = true;
+		reg_state_cond(cond_t, tr1, tr2, op, tr1, tr2, "TRUE");
+	}
+	if (env.verbosity >= VERBOSE_VERY) {
+		printf("STEP3 (%s) FALSE R1:", t_str(cond_t)); print_reg_state(fr1, "\n");
+		printf("STEP3 (%s) FALSE R2:", t_str(cond_t)); print_reg_state(fr2, "\n");
+		printf("STEP3 (%s) TRUE  R1:", t_str(cond_t)); print_reg_state(tr1, "\n");
+		printf("STEP3 (%s) TRUE  R2:", t_str(cond_t)); print_reg_state(tr2, "\n");
+	}
+}
+
+/* ===============================
+ * HIGH-LEVEL TEST CASE VALIDATION
+ * ===============================
+ */
+static u32 upper_seeds[] = {
+	0,
+	1,
+	U32_MAX,
+	U32_MAX - 1,
+	S32_MAX,
+	(u32)S32_MIN,
+};
+
+static u32 lower_seeds[] = {
+	0,
+	1,
+	2, (u32)-2,
+	255, (u32)-255,
+	UINT_MAX,
+	UINT_MAX - 1,
+	INT_MAX,
+	(u32)INT_MIN,
+};
+
+struct ctx {
+	int val_cnt, subval_cnt, range_cnt, subrange_cnt;
+	u64 uvals[ARRAY_SIZE(upper_seeds) * ARRAY_SIZE(lower_seeds)];
+	s64 svals[ARRAY_SIZE(upper_seeds) * ARRAY_SIZE(lower_seeds)];
+	u32 usubvals[ARRAY_SIZE(lower_seeds)];
+	s32 ssubvals[ARRAY_SIZE(lower_seeds)];
+	struct range *uranges, *sranges;
+	struct range *usubranges, *ssubranges;
+	int max_failure_cnt, cur_failure_cnt;
+	int total_case_cnt, case_cnt;
+	int rand_case_cnt;
+	unsigned rand_seed;
+	__u64 start_ns;
+	char progress_ctx[64];
+};
+
+static void cleanup_ctx(struct ctx *ctx)
+{
+	free(ctx->uranges);
+	free(ctx->sranges);
+	free(ctx->usubranges);
+	free(ctx->ssubranges);
+}
+
+struct subtest_case {
+	enum num_t init_t;
+	enum num_t cond_t;
+	struct range x;
+	struct range y;
+	enum op op;
+};
+
+static void subtest_case_str(struct strbuf *sb, struct subtest_case *t, bool use_op)
+{
+	snappendf(sb, "(%s)", t_str(t->init_t));
+	snprintf_range(t->init_t, sb, t->x);
+	snappendf(sb, " (%s)%s ", t_str(t->cond_t), use_op ? op_str(t->op) : "<op>");
+	snprintf_range(t->init_t, sb, t->y);
+}
+
+/* Generate and validate test case based on specific combination of setup
+ * register ranges (including their expected num_t domain), and conditional
+ * operation to perform (including num_t domain in which it has to be
+ * performed)
+ */
+static int verify_case_op(enum num_t init_t, enum num_t cond_t,
+			  struct range x, struct range y, enum op op)
+{
+	char log_buf[256 * 1024];
+	size_t log_sz = sizeof(log_buf);
+	int err, false_pos = 0, true_pos = 0, branch_taken;
+	struct reg_state fr1, fr2, tr1, tr2;
+	struct reg_state fe1, fe2, te1, te2;
+	bool failed = false;
+	struct case_spec spec = {
+		.init_subregs = (init_t == U32 || init_t == S32),
+		.setup_subregs = (init_t == U32 || init_t == S32),
+		.setup_signed = (init_t == S64 || init_t == S32),
+		.compare_subregs = (cond_t == U32 || cond_t == S32),
+		.compare_signed = (cond_t == S64 || cond_t == S32),
+	};
+
+	log_buf[0] = '\0';
+
+	sim_case(init_t, cond_t, x, y, op, &fe1, &fe2, &te1, &te2, &branch_taken);
+
+	err = load_range_cmp_prog(x, y, op, branch_taken, spec,
+				  log_buf, log_sz, &false_pos, &true_pos);
+	if (err) {
+		ASSERT_OK(err, "load_range_cmp_prog");
+		failed = true;
+	}
+
+	err = parse_range_cmp_log(log_buf, spec, false_pos, true_pos,
+				  &fr1, &fr2, &tr1, &tr2);
+	if (err) {
+		ASSERT_OK(err, "parse_range_cmp_log");
+		failed = true;
+	}
+
+	if (!assert_reg_state_eq(&fr1, &fe1, "false_reg1") ||
+	    !assert_reg_state_eq(&fr2, &fe2, "false_reg2") ||
+	    !assert_reg_state_eq(&tr1, &te1, "true_reg1") ||
+	    !assert_reg_state_eq(&tr2, &te2, "true_reg2")) {
+		failed = true;
+	}
+
+	if (failed || env.verbosity >= VERBOSE_NORMAL) {
+		if (failed || env.verbosity >= VERBOSE_VERY) {
+			printf("VERIFIER LOG:\n========================\n");
+			print_verifier_log(log_buf);
+			printf("=====================\n");
+		}
+		printf("ACTUAL   FALSE1: "); print_reg_state(&fr1, "\n");
+		printf("EXPECTED FALSE1: "); print_reg_state(&fe1, "\n");
+		printf("ACTUAL   FALSE2: "); print_reg_state(&fr2, "\n");
+		printf("EXPECTED FALSE2: "); print_reg_state(&fe2, "\n");
+		printf("ACTUAL   TRUE1:  "); print_reg_state(&tr1, "\n");
+		printf("EXPECTED TRUE1:  "); print_reg_state(&te1, "\n");
+		printf("ACTUAL   TRUE2:  "); print_reg_state(&tr2, "\n");
+		printf("EXPECTED TRUE2:  "); print_reg_state(&te2, "\n");
+
+		return failed ? -EINVAL : 0;
+	}
+
+	return 0;
+}
+
+/* Given setup ranges and number types, go over all supported operations,
+ * generating individual subtest for each allowed combination
+ */
+static int verify_case_opt(struct ctx *ctx, enum num_t init_t, enum num_t cond_t,
+			   struct range x, struct range y, bool is_subtest)
+{
+	DEFINE_STRBUF(sb, 256);
+	int err;
+	struct subtest_case sub = {
+		.init_t = init_t,
+		.cond_t = cond_t,
+		.x = x,
+		.y = y,
+	};
+
+	sb->pos = 0; /* reset position in strbuf */
+	subtest_case_str(sb, &sub, false /* ignore op */);
+	if (is_subtest && !test__start_subtest(sb->buf))
+		return 0;
+
+	for (sub.op = first_op; sub.op <= last_op; sub.op++) {
+		sb->pos = 0; /* reset position in strbuf */
+		subtest_case_str(sb, &sub, true /* print op */);
+
+		if (env.verbosity >= VERBOSE_NORMAL) /* this speeds up debugging */
+			printf("TEST CASE: %s\n", sb->buf);
+
+		err = verify_case_op(init_t, cond_t, x, y, sub.op);
+		if (err || env.verbosity >= VERBOSE_NORMAL)
+			ASSERT_OK(err, sb->buf);
+		if (err) {
+			ctx->cur_failure_cnt++;
+			if (ctx->cur_failure_cnt > ctx->max_failure_cnt)
+				return err;
+			return 0; /* keep testing other cases */
+		}
+		ctx->case_cnt++;
+		if ((ctx->case_cnt % 10000) == 0) {
+			double progress = (ctx->case_cnt + 0.0) / ctx->total_case_cnt;
+			u64 elapsed_ns = get_time_ns() - ctx->start_ns;
+			double remain_ns = elapsed_ns / progress * (1 - progress);
+
+			fprintf(env.stderr_saved, "PROGRESS (%s): %d/%d (%.2lf%%), "
+					    "elapsed %llu mins (%.2lf hrs), "
+					    "ETA %.0lf mins (%.2lf hrs)\n",
+				ctx->progress_ctx,
+				ctx->case_cnt, ctx->total_case_cnt, 100.0 * progress,
+				elapsed_ns / 1000000000 / 60,
+				elapsed_ns / 1000000000.0 / 3600,
+				remain_ns / 1000000000.0 / 60,
+				remain_ns / 1000000000.0 / 3600);
+		}
+	}
+
+	return 0;
+}
+
+static int verify_case(struct ctx *ctx, enum num_t init_t, enum num_t cond_t,
+		       struct range x, struct range y)
+{
+	return verify_case_opt(ctx, init_t, cond_t, x, y, true /* is_subtest */);
+}
+
+/* ================================
+ * GENERATED CASES FROM SEED VALUES
+ * ================================
+ */
+static int u64_cmp(const void *p1, const void *p2)
+{
+	u64 x1 = *(const u64 *)p1, x2 = *(const u64 *)p2;
+
+	return x1 != x2 ? (x1 < x2 ? -1 : 1) : 0;
+}
+
+static int u32_cmp(const void *p1, const void *p2)
+{
+	u32 x1 = *(const u32 *)p1, x2 = *(const u32 *)p2;
+
+	return x1 != x2 ? (x1 < x2 ? -1 : 1) : 0;
+}
+
+static int s64_cmp(const void *p1, const void *p2)
+{
+	s64 x1 = *(const s64 *)p1, x2 = *(const s64 *)p2;
+
+	return x1 != x2 ? (x1 < x2 ? -1 : 1) : 0;
+}
+
+static int s32_cmp(const void *p1, const void *p2)
+{
+	s32 x1 = *(const s32 *)p1, x2 = *(const s32 *)p2;
+
+	return x1 != x2 ? (x1 < x2 ? -1 : 1) : 0;
+}
+
+/* Generate valid unique constants from seeds, both signed and unsigned */
+static void gen_vals(struct ctx *ctx)
+{
+	int i, j, cnt = 0;
+
+	for (i = 0; i < ARRAY_SIZE(upper_seeds); i++) {
+		for (j = 0; j < ARRAY_SIZE(lower_seeds); j++) {
+			ctx->uvals[cnt++] = (((u64)upper_seeds[i]) << 32) | lower_seeds[j];
+		}
+	}
+
+	/* sort and compact uvals (i.e., it's `sort | uniq`) */
+	qsort(ctx->uvals, cnt, sizeof(*ctx->uvals), u64_cmp);
+	for (i = 1, j = 0; i < cnt; i++) {
+		if (ctx->uvals[j] == ctx->uvals[i])
+			continue;
+		j++;
+		ctx->uvals[j] = ctx->uvals[i];
+	}
+	ctx->val_cnt = j + 1;
+
+	/* we have exactly the same number of s64 values, they are just in
+	 * a different order than u64s, so just sort them differently
+	 */
+	for (i = 0; i < ctx->val_cnt; i++)
+		ctx->svals[i] = ctx->uvals[i];
+	qsort(ctx->svals, ctx->val_cnt, sizeof(*ctx->svals), s64_cmp);
+
+	if (env.verbosity >= VERBOSE_SUPER) {
+		DEFINE_STRBUF(sb1, 256);
+		DEFINE_STRBUF(sb2, 256);
+
+		for (i = 0; i < ctx->val_cnt; i++) {
+			sb1->pos = sb2->pos = 0;
+			snprintf_num(U64, sb1, ctx->uvals[i]);
+			snprintf_num(S64, sb2, ctx->svals[i]);
+			printf("SEED #%d: u64=%-20s s64=%-20s\n", i, sb1->buf, sb2->buf);
+		}
+	}
+
+	/* 32-bit values are generated separately */
+	cnt = 0;
+	for (i = 0; i < ARRAY_SIZE(lower_seeds); i++) {
+		ctx->usubvals[cnt++] = lower_seeds[i];
+	}
+
+	/* sort and compact usubvals (i.e., it's `sort | uniq`) */
+	qsort(ctx->usubvals, cnt, sizeof(*ctx->usubvals), u32_cmp);
+	for (i = 1, j = 0; i < cnt; i++) {
+		if (ctx->usubvals[j] == ctx->usubvals[i])
+			continue;
+		j++;
+		ctx->usubvals[j] = ctx->usubvals[i];
+	}
+	ctx->subval_cnt = j + 1;
+
+	for (i = 0; i < ctx->subval_cnt; i++)
+		ctx->ssubvals[i] = ctx->usubvals[i];
+	qsort(ctx->ssubvals, ctx->subval_cnt, sizeof(*ctx->ssubvals), s32_cmp);
+
+	if (env.verbosity >= VERBOSE_SUPER) {
+		DEFINE_STRBUF(sb1, 256);
+		DEFINE_STRBUF(sb2, 256);
+
+		for (i = 0; i < ctx->subval_cnt; i++) {
+			sb1->pos = sb2->pos = 0;
+			snprintf_num(U32, sb1, ctx->usubvals[i]);
+			snprintf_num(S32, sb2, ctx->ssubvals[i]);
+			printf("SUBSEED #%d: u32=%-10s s32=%-10s\n", i, sb1->buf, sb2->buf);
+		}
+	}
+}
+
+/* Generate valid ranges from upper/lower seeds */
+static int gen_ranges(struct ctx *ctx)
+{
+	int i, j, cnt = 0;
+
+	for (i = 0; i < ctx->val_cnt; i++) {
+		for (j = i; j < ctx->val_cnt; j++) {
+			if (env.verbosity >= VERBOSE_SUPER) {
+				DEFINE_STRBUF(sb1, 256);
+				DEFINE_STRBUF(sb2, 256);
+
+				sb1->pos = sb2->pos = 0;
+				snprintf_range(U64, sb1, range(U64, ctx->uvals[i], ctx->uvals[j]));
+				snprintf_range(S64, sb2, range(S64, ctx->svals[i], ctx->svals[j]));
+				printf("RANGE #%d: u64=%-40s s64=%-40s\n", cnt, sb1->buf, sb2->buf);
+			}
+			cnt++;
+		}
+	}
+	ctx->range_cnt = cnt;
+
+	ctx->uranges = calloc(ctx->range_cnt, sizeof(*ctx->uranges));
+	if (!ASSERT_OK_PTR(ctx->uranges, "uranges_calloc"))
+		return -EINVAL;
+	ctx->sranges = calloc(ctx->range_cnt, sizeof(*ctx->sranges));
+	if (!ASSERT_OK_PTR(ctx->sranges, "sranges_calloc"))
+		return -EINVAL;
+
+	cnt = 0;
+	for (i = 0; i < ctx->val_cnt; i++) {
+		for (j = i; j < ctx->val_cnt; j++) {
+			ctx->uranges[cnt] = range(U64, ctx->uvals[i], ctx->uvals[j]);
+			ctx->sranges[cnt] = range(S64, ctx->svals[i], ctx->svals[j]);
+			cnt++;
+		}
+	}
+
+	cnt = 0;
+	for (i = 0; i < ctx->subval_cnt; i++) {
+		for (j = i; j < ctx->subval_cnt; j++) {
+			if (env.verbosity >= VERBOSE_SUPER) {
+				DEFINE_STRBUF(sb1, 256);
+				DEFINE_STRBUF(sb2, 256);
+
+				sb1->pos = sb2->pos = 0;
+				snprintf_range(U32, sb1, range(U32, ctx->usubvals[i], ctx->usubvals[j]));
+				snprintf_range(S32, sb2, range(S32, ctx->ssubvals[i], ctx->ssubvals[j]));
+				printf("SUBRANGE #%d: u32=%-20s s32=%-20s\n", cnt, sb1->buf, sb2->buf);
+			}
+			cnt++;
+		}
+	}
+	ctx->subrange_cnt = cnt;
+
+	ctx->usubranges = calloc(ctx->subrange_cnt, sizeof(*ctx->usubranges));
+	if (!ASSERT_OK_PTR(ctx->usubranges, "usubranges_calloc"))
+		return -EINVAL;
+	ctx->ssubranges = calloc(ctx->subrange_cnt, sizeof(*ctx->ssubranges));
+	if (!ASSERT_OK_PTR(ctx->ssubranges, "ssubranges_calloc"))
+		return -EINVAL;
+
+	cnt = 0;
+	for (i = 0; i < ctx->subval_cnt; i++) {
+		for (j = i; j < ctx->subval_cnt; j++) {
+			ctx->usubranges[cnt] = range(U32, ctx->usubvals[i], ctx->usubvals[j]);
+			ctx->ssubranges[cnt] = range(S32, ctx->ssubvals[i], ctx->ssubvals[j]);
+			cnt++;
+		}
+	}
+
+	return 0;
+}
+
+static int parse_env_vars(struct ctx *ctx)
+{
+	const char *s;
+
+	if ((s = getenv("REG_BOUNDS_MAX_FAILURE_CNT"))) {
+		errno = 0;
+		ctx->max_failure_cnt = strtol(s, NULL, 10);
+		if (errno || ctx->max_failure_cnt < 0) {
+			ASSERT_OK(-errno, "REG_BOUNDS_MAX_FAILURE_CNT");
+			return -EINVAL;
+		}
+	}
+
+	if ((s = getenv("REG_BOUNDS_RAND_CASE_CNT"))) {
+		errno = 0;
+		ctx->rand_case_cnt = strtol(s, NULL, 10);
+		if (errno || ctx->rand_case_cnt < 0) {
+			ASSERT_OK(-errno, "REG_BOUNDS_RAND_CASE_CNT");
+			return -EINVAL;
+		}
+	}
+
+	if ((s = getenv("REG_BOUNDS_RAND_SEED"))) {
+		errno = 0;
+		ctx->rand_seed = strtoul(s, NULL, 10);
+		if (errno) {
+			ASSERT_OK(-errno, "REG_BOUNDS_RAND_SEED");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int prepare_gen_tests(struct ctx *ctx)
+{
+	const char *s;
+	int err;
+
+	if (!(s = getenv("SLOW_TESTS")) || strcmp(s, "1") != 0) {
+		test__skip();
+		return -ENOTSUP;
+	}
+
+	err = parse_env_vars(ctx);
+	if (err)
+		return err;
+
+	gen_vals(ctx);
+	err = gen_ranges(ctx);
+	if (err) {
+		ASSERT_OK(err, "gen_ranges");
+		return err;
+	}
+
+	return 0;
+}
+
+/* Go over generated constants and ranges and validate various supported
+ * combinations of them
+ */
+static void validate_gen_range_vs_const_64(enum num_t init_t, enum num_t cond_t)
+{
+	struct ctx ctx;
+	struct range rconst;
+	const struct range *ranges;
+	const u64 *vals;
+	int i, j;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	if (prepare_gen_tests(&ctx))
+		goto cleanup;
+
+	ranges = init_t == U64 ? ctx.uranges : ctx.sranges;
+	vals = init_t == U64 ? ctx.uvals : (const u64 *)ctx.svals;
+
+	ctx.total_case_cnt = (last_op - first_op + 1) * (2 * ctx.range_cnt * ctx.val_cnt);
+	ctx.start_ns = get_time_ns();
+	snprintf(ctx.progress_ctx, sizeof(ctx.progress_ctx),
+		 "RANGE x CONST, %s -> %s",
+		 t_str(init_t), t_str(cond_t));
+
+	for (i = 0; i < ctx.val_cnt; i++) {
+		for (j = 0; j < ctx.range_cnt; j++) {
+			rconst = range(init_t, vals[i], vals[i]);
+
+			/* (u64|s64)(<range> x <const>) */
+			if (verify_case(&ctx, init_t, cond_t, ranges[j], rconst))
+				goto cleanup;
+			/* (u64|s64)(<const> x <range>) */
+			if (verify_case(&ctx, init_t, cond_t, rconst, ranges[j]))
+				goto cleanup;
+		}
+	}
+
+cleanup:
+	cleanup_ctx(&ctx);
+}
+
+static void validate_gen_range_vs_const_32(enum num_t init_t, enum num_t cond_t)
+{
+	struct ctx ctx;
+	struct range rconst;
+	const struct range *ranges;
+	const u32 *vals;
+	int i, j;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	if (prepare_gen_tests(&ctx))
+		goto cleanup;
+
+	ranges = init_t == U32 ? ctx.usubranges : ctx.ssubranges;
+	vals = init_t == U32 ? ctx.usubvals : (const u32 *)ctx.ssubvals;
+
+	ctx.total_case_cnt = (last_op - first_op + 1) * (2 * ctx.subrange_cnt * ctx.subval_cnt);
+	ctx.start_ns = get_time_ns();
+	snprintf(ctx.progress_ctx, sizeof(ctx.progress_ctx),
+		 "RANGE x CONST, %s -> %s",
+		 t_str(init_t), t_str(cond_t));
+
+	for (i = 0; i < ctx.subval_cnt; i++) {
+		for (j = 0; j < ctx.subrange_cnt; j++) {
+			rconst = range(init_t, vals[i], vals[i]);
+
+			/* (u32|s32)(<range> x <const>) */
+			if (verify_case(&ctx, init_t, cond_t, ranges[j], rconst))
+				goto cleanup;
+			/* (u32|s32)(<const> x <range>) */
+			if (verify_case(&ctx, init_t, cond_t, rconst, ranges[j]))
+				goto cleanup;
+		}
+	}
+
+cleanup:
+	cleanup_ctx(&ctx);
+}
+
+static void validate_gen_range_vs_range(enum num_t init_t, enum num_t cond_t)
+{
+	struct ctx ctx;
+	const struct range *ranges;
+	int i, j, rcnt;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	if (prepare_gen_tests(&ctx))
+		goto cleanup;
+
+	switch (init_t)
+	{
+	case U64:
+		ranges = ctx.uranges;
+		rcnt = ctx.range_cnt;
+		break;
+	case U32:
+		ranges = ctx.usubranges;
+		rcnt = ctx.subrange_cnt;
+		break;
+	case S64:
+		ranges = ctx.sranges;
+		rcnt = ctx.range_cnt;
+		break;
+	case S32:
+		ranges = ctx.ssubranges;
+		rcnt = ctx.subrange_cnt;
+		break;
+	default:
+		printf("validate_gen_range_vs_range!\n");
+		exit(1);
+	}
+
+	ctx.total_case_cnt = (last_op - first_op + 1) * (2 * rcnt * (rcnt + 1) / 2);
+	ctx.start_ns = get_time_ns();
+	snprintf(ctx.progress_ctx, sizeof(ctx.progress_ctx),
+		 "RANGE x RANGE, %s -> %s",
+		 t_str(init_t), t_str(cond_t));
+
+	for (i = 0; i < rcnt; i++) {
+		for (j = i; j < rcnt; j++) {
+			/* (<range> x <range>) */
+			if (verify_case(&ctx, init_t, cond_t, ranges[i], ranges[j]))
+				goto cleanup;
+			if (verify_case(&ctx, init_t, cond_t, ranges[j], ranges[i]))
+				goto cleanup;
+		}
+	}
+
+cleanup:
+	cleanup_ctx(&ctx);
+}
+
+/* Go over thousands of test cases generated from initial seed values.
+ * Given this take a long time, guard this begind SLOW_TESTS=1 envvar. If
+ * envvar is not set, this test is skipped during test_progs testing.
+ *
+ * We split this up into smaller subsets based on initialization and
+ * conditional numeric domains to get an easy parallelization with test_progs'
+ * -j argument.
+ */
+
+/* RANGE x CONST, U64 initial range */
+void test_reg_bounds_gen_consts_u64_u64(void) { validate_gen_range_vs_const_64(U64, U64); }
+void test_reg_bounds_gen_consts_u64_s64(void) { validate_gen_range_vs_const_64(U64, S64); }
+void test_reg_bounds_gen_consts_u64_u32(void) { validate_gen_range_vs_const_64(U64, U32); }
+void test_reg_bounds_gen_consts_u64_s32(void) { validate_gen_range_vs_const_64(U64, S32); }
+/* RANGE x CONST, S64 initial range */
+void test_reg_bounds_gen_consts_s64_u64(void) { validate_gen_range_vs_const_64(S64, U64); }
+void test_reg_bounds_gen_consts_s64_s64(void) { validate_gen_range_vs_const_64(S64, S64); }
+void test_reg_bounds_gen_consts_s64_u32(void) { validate_gen_range_vs_const_64(S64, U32); }
+void test_reg_bounds_gen_consts_s64_s32(void) { validate_gen_range_vs_const_64(S64, S32); }
+/* RANGE x CONST, U32 initial range */
+void test_reg_bounds_gen_consts_u32_u64(void) { validate_gen_range_vs_const_32(U32, U64); }
+void test_reg_bounds_gen_consts_u32_s64(void) { validate_gen_range_vs_const_32(U32, S64); }
+void test_reg_bounds_gen_consts_u32_u32(void) { validate_gen_range_vs_const_32(U32, U32); }
+void test_reg_bounds_gen_consts_u32_s32(void) { validate_gen_range_vs_const_32(U32, S32); }
+/* RANGE x CONST, S32 initial range */
+void test_reg_bounds_gen_consts_s32_u64(void) { validate_gen_range_vs_const_32(S32, U64); }
+void test_reg_bounds_gen_consts_s32_s64(void) { validate_gen_range_vs_const_32(S32, S64); }
+void test_reg_bounds_gen_consts_s32_u32(void) { validate_gen_range_vs_const_32(S32, U32); }
+void test_reg_bounds_gen_consts_s32_s32(void) { validate_gen_range_vs_const_32(S32, S32); }
+
+/* RANGE x RANGE, U64 initial range */
+void test_reg_bounds_gen_ranges_u64_u64(void) { validate_gen_range_vs_range(U64, U64); }
+void test_reg_bounds_gen_ranges_u64_s64(void) { validate_gen_range_vs_range(U64, S64); }
+void test_reg_bounds_gen_ranges_u64_u32(void) { validate_gen_range_vs_range(U64, U32); }
+void test_reg_bounds_gen_ranges_u64_s32(void) { validate_gen_range_vs_range(U64, S32); }
+/* RANGE x RANGE, S64 initial range */
+void test_reg_bounds_gen_ranges_s64_u64(void) { validate_gen_range_vs_range(S64, U64); }
+void test_reg_bounds_gen_ranges_s64_s64(void) { validate_gen_range_vs_range(S64, S64); }
+void test_reg_bounds_gen_ranges_s64_u32(void) { validate_gen_range_vs_range(S64, U32); }
+void test_reg_bounds_gen_ranges_s64_s32(void) { validate_gen_range_vs_range(S64, S32); }
+/* RANGE x RANGE, U32 initial range */
+void test_reg_bounds_gen_ranges_u32_u64(void) { validate_gen_range_vs_range(U32, U64); }
+void test_reg_bounds_gen_ranges_u32_s64(void) { validate_gen_range_vs_range(U32, S64); }
+void test_reg_bounds_gen_ranges_u32_u32(void) { validate_gen_range_vs_range(U32, U32); }
+void test_reg_bounds_gen_ranges_u32_s32(void) { validate_gen_range_vs_range(U32, S32); }
+/* RANGE x RANGE, S32 initial range */
+void test_reg_bounds_gen_ranges_s32_u64(void) { validate_gen_range_vs_range(S32, U64); }
+void test_reg_bounds_gen_ranges_s32_s64(void) { validate_gen_range_vs_range(S32, S64); }
+void test_reg_bounds_gen_ranges_s32_u32(void) { validate_gen_range_vs_range(S32, U32); }
+void test_reg_bounds_gen_ranges_s32_s32(void) { validate_gen_range_vs_range(S32, S32); }
+
+#define DEFAULT_RAND_CASE_CNT 100
+
+#define RAND_21BIT_MASK ((1 << 22) - 1)
+
+static u64 rand_u64()
+{
+	/* RAND_MAX is guaranteed to be at least 1<<15, but in practice it
+	 * seems to be 1<<31, so we need to call it thrice to get full u64;
+	 * we'll use roughly equal split: 22 + 21 + 21 bits
+	 */
+	return ((u64)random() << 42) |
+	       (((u64)random() & RAND_21BIT_MASK) << 21) |
+	       (random() & RAND_21BIT_MASK);
+}
+
+static u64 rand_const(enum num_t t)
+{
+	return cast_t(t, rand_u64());
+}
+
+static struct range rand_range(enum num_t t)
+{
+	u64 x = rand_const(t), y = rand_const(t);
+
+	return range(t, min_t(t, x, y), max_t(t, x, y));
+}
+
+static void validate_rand_ranges(enum num_t init_t, enum num_t cond_t, bool const_range)
+{
+	struct ctx ctx;
+	struct range range1, range2;
+	int err, i;
+	u64 t;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	err = parse_env_vars(&ctx);
+	if (err) {
+		ASSERT_OK(err, "parse_env_vars");
+		return;
+	}
+
+	if (ctx.rand_case_cnt == 0)
+		ctx.rand_case_cnt = DEFAULT_RAND_CASE_CNT;
+	if (ctx.rand_seed == 0)
+		ctx.rand_seed = (unsigned)get_time_ns();
+
+	srandom(ctx.rand_seed);
+
+	ctx.total_case_cnt = (last_op - first_op + 1) * (2 * ctx.rand_case_cnt);
+	ctx.start_ns = get_time_ns();
+	snprintf(ctx.progress_ctx, sizeof(ctx.progress_ctx),
+		 "[RANDOM SEED %u] RANGE x %s, %s -> %s",
+		 ctx.rand_seed, const_range ? "CONST" : "RANGE",
+		 t_str(init_t), t_str(cond_t));
+
+	for (i = 0; i < ctx.rand_case_cnt; i++) {
+		range1 = rand_range(init_t);
+		if (const_range) {
+			t = rand_const(init_t);
+			range2 = range(init_t, t, t);
+		} else {
+			range2 = rand_range(init_t);
+		}
+
+		/* <range1> x <range2> */
+		if (verify_case_opt(&ctx, init_t, cond_t, range1, range2, false /* !is_subtest */))
+			goto cleanup;
+		/* <range2> x <range1> */
+		if (verify_case_opt(&ctx, init_t, cond_t, range2, range1, false /* !is_subtest */))
+			goto cleanup;
+	}
+
+cleanup:
+	/* make sure we report random seed for reproducing */
+	ASSERT_TRUE(true, ctx.progress_ctx);
+	cleanup_ctx(&ctx);
+}
+
+/* [RANDOM] RANGE x CONST, U64 initial range */
+void test_reg_bounds_rand_consts_u64_u64(void) { validate_rand_ranges(U64, U64, true /* const */); }
+void test_reg_bounds_rand_consts_u64_s64(void) { validate_rand_ranges(U64, S64, true /* const */); }
+void test_reg_bounds_rand_consts_u64_u32(void) { validate_rand_ranges(U64, U32, true /* const */); }
+void test_reg_bounds_rand_consts_u64_s32(void) { validate_rand_ranges(U64, S32, true /* const */); }
+/* [RANDOM] RANGE x CONST, S64 initial range */
+void test_reg_bounds_rand_consts_s64_u64(void) { validate_rand_ranges(S64, U64, true /* const */); }
+void test_reg_bounds_rand_consts_s64_s64(void) { validate_rand_ranges(S64, S64, true /* const */); }
+void test_reg_bounds_rand_consts_s64_u32(void) { validate_rand_ranges(S64, U32, true /* const */); }
+void test_reg_bounds_rand_consts_s64_s32(void) { validate_rand_ranges(S64, S32, true /* const */); }
+/* [RANDOM] RANGE x CONST, U32 initial range */
+void test_reg_bounds_rand_consts_u32_u64(void) { validate_rand_ranges(U32, U64, true /* const */); }
+void test_reg_bounds_rand_consts_u32_s64(void) { validate_rand_ranges(U32, S64, true /* const */); }
+void test_reg_bounds_rand_consts_u32_u32(void) { validate_rand_ranges(U32, U32, true /* const */); }
+void test_reg_bounds_rand_consts_u32_s32(void) { validate_rand_ranges(U32, S32, true /* const */); }
+/* [RANDOM] RANGE x CONST, S32 initial range */
+void test_reg_bounds_rand_consts_s32_u64(void) { validate_rand_ranges(S32, U64, true /* const */); }
+void test_reg_bounds_rand_consts_s32_s64(void) { validate_rand_ranges(S32, S64, true /* const */); }
+void test_reg_bounds_rand_consts_s32_u32(void) { validate_rand_ranges(S32, U32, true /* const */); }
+void test_reg_bounds_rand_consts_s32_s32(void) { validate_rand_ranges(S32, S32, true /* const */); }
+
+/* [RANDOM] RANGE x RANGE, U64 initial range */
+void test_reg_bounds_rand_ranges_u64_u64(void) { validate_rand_ranges(U64, U64, false /* range */); }
+void test_reg_bounds_rand_ranges_u64_s64(void) { validate_rand_ranges(U64, S64, false /* range */); }
+void test_reg_bounds_rand_ranges_u64_u32(void) { validate_rand_ranges(U64, U32, false /* range */); }
+void test_reg_bounds_rand_ranges_u64_s32(void) { validate_rand_ranges(U64, S32, false /* range */); }
+/* [RANDOM] RANGE x RANGE, S64 initial range */
+void test_reg_bounds_rand_ranges_s64_u64(void) { validate_rand_ranges(S64, U64, false /* range */); }
+void test_reg_bounds_rand_ranges_s64_s64(void) { validate_rand_ranges(S64, S64, false /* range */); }
+void test_reg_bounds_rand_ranges_s64_u32(void) { validate_rand_ranges(S64, U32, false /* range */); }
+void test_reg_bounds_rand_ranges_s64_s32(void) { validate_rand_ranges(S64, S32, false /* range */); }
+/* [RANDOM] RANGE x RANGE, U32 initial range */
+void test_reg_bounds_rand_ranges_u32_u64(void) { validate_rand_ranges(U32, U64, false /* range */); }
+void test_reg_bounds_rand_ranges_u32_s64(void) { validate_rand_ranges(U32, S64, false /* range */); }
+void test_reg_bounds_rand_ranges_u32_u32(void) { validate_rand_ranges(U32, U32, false /* range */); }
+void test_reg_bounds_rand_ranges_u32_s32(void) { validate_rand_ranges(U32, S32, false /* range */); }
+/* [RANDOM] RANGE x RANGE, S32 initial range */
+void test_reg_bounds_rand_ranges_s32_u64(void) { validate_rand_ranges(S32, U64, false /* range */); }
+void test_reg_bounds_rand_ranges_s32_s64(void) { validate_rand_ranges(S32, S64, false /* range */); }
+void test_reg_bounds_rand_ranges_s32_u32(void) { validate_rand_ranges(S32, U32, false /* range */); }
+void test_reg_bounds_rand_ranges_s32_s32(void) { validate_rand_ranges(S32, S32, false /* range */); }
+
+/* A set of hard-coded "interesting" cases to validate as part of normal
+ * test_progs test runs
+ */
+static struct subtest_case crafted_cases[] = {
+	{U64, U64, {0, 0xffffffff}, {0, 0}},
+	{U64, U64, {0, 0x80000000}, {0, 0}},
+	{U64, U64, {0x100000000ULL, 0x100000100ULL}, {0, 0}},
+	{U64, U64, {0x100000000ULL, 0x180000000ULL}, {0, 0}},
+	{U64, U64, {0x100000000ULL, 0x1ffffff00ULL}, {0, 0}},
+	{U64, U64, {0x100000000ULL, 0x1ffffff01ULL}, {0, 0}},
+	{U64, U64, {0x100000000ULL, 0x1fffffffeULL}, {0, 0}},
+	{U64, U64, {0x100000001ULL, 0x1000000ffULL}, {0, 0}},
+
+	/* single point overlap, interesting BPF_EQ and BPF_NE interactions */
+	{U64, U64, {0, 1}, {1, 0x80000000}},
+	{U64, S64, {0, 1}, {1, 0x80000000}},
+	{U64, U32, {0, 1}, {1, 0x80000000}},
+	{U64, S32, {0, 1}, {1, 0x80000000}},
+
+	{U64, S64, {0, 0xffffffff00000000ULL}, {0, 0}},
+	{U64, S64, {0x7fffffffffffffffULL, 0xffffffff00000000ULL}, {0, 0}},
+	{U64, S64, {0x7fffffff00000001ULL, 0xffffffff00000000ULL}, {0, 0}},
+	{U64, S64, {0, 0xffffffffULL}, {1, 1}},
+	{U64, S64, {0, 0xffffffffULL}, {0x7fffffff, 0x7fffffff}},
+
+	{U64, U32, {0, 0x100000000}, {0, 0}},
+	{U64, U32, {0xfffffffe, 0x100000000}, {0x80000000, 0x80000000}},
+
+	{U64, S32, {0, 0xffffffff00000000ULL}, {0, 0}},
+	/* these are tricky cases where lower 32 bits allow to tighten 64
+	 * bit boundaries based on tightened lower 32 bit boundaries
+	 */
+	{U64, S32, {0, 0x0ffffffffULL}, {0, 0}},
+	{U64, S32, {0, 0x100000000ULL}, {0, 0}},
+	{U64, S32, {0, 0x100000001ULL}, {0, 0}},
+	{U64, S32, {0, 0x180000000ULL}, {0, 0}},
+	{U64, S32, {0, 0x17fffffffULL}, {0, 0}},
+	{U64, S32, {0, 0x180000001ULL}, {0, 0}},
+
+	/* verifier knows about [-1, 0] range for s32 for this case already */
+	{S64, S64, {0xffffffffffffffffULL, 0}, {0xffffffff00000000ULL, 0xffffffff00000000ULL}},
+	/* but didn't know about these cases initially */
+	{U64, U64, {0xffffffff, 0x100000000ULL}, {0, 0}}, /* s32: [-1, 0] */
+	{U64, U64, {0xffffffff, 0x100000001ULL}, {0, 0}}, /* s32: [-1, 1] */
+
+	/* longer convergence case: learning from u64 -> s64 -> u64 -> u32,
+	 * arriving at u32: [1, U32_MAX] (instead of more pessimistic [0, U32_MAX])
+	 */
+	{S64, U64, {0xffffffff00000001ULL, 0}, {0xffffffff00000000ULL, 0xffffffff00000000ULL}},
+
+	{U32, U32, {1, U32_MAX}, {0, 0}},
+
+	{U32, S32, {0, U32_MAX}, {U32_MAX, U32_MAX}},
+
+	{S32, U64, {(u32)S32_MIN, (u32)S32_MIN}, {(u32)(s32)-255, 0}},
+	{S32, S64, {(u32)S32_MIN, (u32)(s32)-255}, {(u32)(s32)-2, 0}},
+	{S32, S64, {0, 1}, {(u32)S32_MIN, (u32)S32_MIN}},
+	{S32, U32, {(u32)S32_MIN, (u32)S32_MIN}, {(u32)S32_MIN, (u32)S32_MIN}},
+
+	/* edge overlap testings for BPF_NE */
+	{U64, U64, {0, U64_MAX}, {U64_MAX, U64_MAX}},
+	{U64, U64, {0, U64_MAX}, {0, 0}},
+	{S64, U64, {S64_MIN, 0}, {S64_MIN, S64_MIN}},
+	{S64, U64, {S64_MIN, 0}, {0, 0}},
+	{S64, U64, {S64_MIN, S64_MAX}, {S64_MAX, S64_MAX}},
+	{U32, U32, {0, U32_MAX}, {0, 0}},
+	{U32, U32, {0, U32_MAX}, {U32_MAX, U32_MAX}},
+	{S32, U32, {(u32)S32_MIN, 0}, {0, 0}},
+	{S32, U32, {(u32)S32_MIN, 0}, {(u32)S32_MIN, (u32)S32_MIN}},
+	{S32, U32, {(u32)S32_MIN, S32_MAX}, {S32_MAX, S32_MAX}},
+	{S64, U32, {0x0, 0x1f}, {0xffffffff80000000ULL, 0x000000007fffffffULL}},
+	{S64, U32, {0x0, 0x1f}, {0xffffffffffff8000ULL, 0x0000000000007fffULL}},
+	{S64, U32, {0x0, 0x1f}, {0xffffffffffffff80ULL, 0x000000000000007fULL}},
+};
+
+/* Go over crafted hard-coded cases. This is fast, so we do it as part of
+ * normal test_progs run.
+ */
+void test_reg_bounds_crafted(void)
+{
+	struct ctx ctx;
+	int i;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	for (i = 0; i < ARRAY_SIZE(crafted_cases); i++) {
+		struct subtest_case *c = &crafted_cases[i];
+
+		verify_case(&ctx, c->init_t, c->cond_t, c->x, c->y);
+		verify_case(&ctx, c->init_t, c->cond_t, c->y, c->x);
+	}
+
+	cleanup_ctx(&ctx);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c b/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c
new file mode 100644
index 000000000000..f0a8c828f8f1
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/res_spin_lock.c
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024-2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <network_helpers.h>
+#include <sys/sysinfo.h>
+
+#include "res_spin_lock.skel.h"
+#include "res_spin_lock_fail.skel.h"
+
+void test_res_spin_lock_failure(void)
+{
+	RUN_TESTS(res_spin_lock_fail);
+}
+
+static volatile int skip;
+
+static void *spin_lock_thread(void *arg)
+{
+	int err, prog_fd = *(u32 *) arg;
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = 10000,
+	);
+
+	while (!READ_ONCE(skip)) {
+		err = bpf_prog_test_run_opts(prog_fd, &topts);
+		if (err || topts.retval) {
+			ASSERT_OK(err, "test_run");
+			ASSERT_OK(topts.retval, "test_run retval");
+			break;
+		}
+	}
+	pthread_exit(arg);
+}
+
+void test_res_spin_lock_success(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.repeat = 1,
+	);
+	struct res_spin_lock *skel;
+	pthread_t thread_id[16];
+	int prog_fd, i, err;
+	void *ret;
+
+	if (get_nprocs() < 2) {
+		test__skip();
+		return;
+	}
+
+	skel = res_spin_lock__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "res_spin_lock__open_and_load"))
+		return;
+	/* AA deadlock */
+	prog_fd = bpf_program__fd(skel->progs.res_spin_lock_test);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "error");
+	ASSERT_OK(topts.retval, "retval");
+
+	prog_fd = bpf_program__fd(skel->progs.res_spin_lock_test_held_lock_max);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "error");
+	ASSERT_OK(topts.retval, "retval");
+
+	/* Multi-threaded ABBA deadlock. */
+
+	prog_fd = bpf_program__fd(skel->progs.res_spin_lock_test_AB);
+	for (i = 0; i < 16; i++) {
+		int err;
+
+		err = pthread_create(&thread_id[i], NULL, &spin_lock_thread, &prog_fd);
+		if (!ASSERT_OK(err, "pthread_create"))
+			goto end;
+	}
+
+	topts.retval = 0;
+	topts.repeat = 1000;
+	int fd = bpf_program__fd(skel->progs.res_spin_lock_test_BA);
+	while (!topts.retval && !err && !READ_ONCE(skel->bss->err)) {
+		err = bpf_prog_test_run_opts(fd, &topts);
+	}
+
+	WRITE_ONCE(skip, true);
+
+	for (i = 0; i < 16; i++) {
+		if (!ASSERT_OK(pthread_join(thread_id[i], &ret), "pthread_join"))
+			goto end;
+		if (!ASSERT_EQ(ret, &prog_fd, "ret == prog_fd"))
+			goto end;
+	}
+
+	ASSERT_EQ(READ_ONCE(skel->bss->err), -EDEADLK, "timeout err");
+	ASSERT_OK(err, "err");
+	ASSERT_EQ(topts.retval, -EDEADLK, "timeout");
+end:
+	res_spin_lock__destroy(skel);
+	return;
+}
+
+void serial_test_res_spin_lock_stress(void)
+{
+	if (libbpf_num_possible_cpus() < 3) {
+		test__skip();
+		return;
+	}
+
+	ASSERT_OK(load_module("bpf_test_rqspinlock.ko", false), "load module AA");
+	sleep(5);
+	unload_module("bpf_test_rqspinlock", false);
+	/*
+	 * Insert bpf_test_rqspinlock.ko manually with test_mode=[1|2] to test
+	 * other cases (ABBA, ABBCCA).
+	 */
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
index f81d08d429a2..51544372f52e 100644
--- a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
+++ b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
@@ -103,7 +103,7 @@ static int resolve_symbols(void)
 
 	btf = btf__parse_elf("btf_data.bpf.o", NULL);
 	if (CHECK(libbpf_get_error(btf), "resolve",
-		  "Failed to load BTF from btf_data.o\n"))
+		  "Failed to load BTF from btf_data.bpf.o\n"))
 		return -1;
 
 	nr = btf__type_cnt(btf);
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
index ac104dc652e3..64520684d2cb 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -12,8 +12,12 @@
 #include <sys/sysinfo.h>
 #include <linux/perf_event.h>
 #include <linux/ring_buffer.h>
+
 #include "test_ringbuf.lskel.h"
+#include "test_ringbuf_n.lskel.h"
 #include "test_ringbuf_map_key.lskel.h"
+#include "test_ringbuf_write.lskel.h"
+#include "test_ringbuf_overwrite.lskel.h"
 
 #define EDONE 7777
 
@@ -83,6 +87,58 @@ static void *poll_thread(void *input)
 	return (void *)(long)ring_buffer__poll(ringbuf, timeout);
 }
 
+static void ringbuf_write_subtest(void)
+{
+	struct test_ringbuf_write_lskel *skel;
+	int page_size = getpagesize();
+	size_t *mmap_ptr;
+	int err, rb_fd;
+
+	skel = test_ringbuf_write_lskel__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	skel->maps.ringbuf.max_entries = 0x40000;
+
+	err = test_ringbuf_write_lskel__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	rb_fd = skel->maps.ringbuf.map_fd;
+
+	mmap_ptr = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, rb_fd, 0);
+	if (!ASSERT_OK_PTR(mmap_ptr, "rw_cons_pos"))
+		goto cleanup;
+	*mmap_ptr = 0x30000;
+	ASSERT_OK(munmap(mmap_ptr, page_size), "unmap_rw");
+
+	skel->bss->pid = getpid();
+
+	ringbuf = ring_buffer__new(rb_fd, process_sample, NULL, NULL);
+	if (!ASSERT_OK_PTR(ringbuf, "ringbuf_new"))
+		goto cleanup;
+
+	err = test_ringbuf_write_lskel__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup_ringbuf;
+
+	skel->bss->discarded = 0;
+	skel->bss->passed = 0;
+
+	/* trigger exactly two samples */
+	syscall(__NR_getpgid);
+	syscall(__NR_getpgid);
+
+	ASSERT_EQ(skel->bss->discarded, 2, "discarded");
+	ASSERT_EQ(skel->bss->passed, 0, "passed");
+
+	test_ringbuf_write_lskel__detach(skel);
+cleanup_ringbuf:
+	ring_buffer__free(ringbuf);
+cleanup:
+	test_ringbuf_write_lskel__destroy(skel);
+}
+
 static void ringbuf_subtest(void)
 {
 	const size_t rec_sz = BPF_RINGBUF_HDR_SZ + sizeof(struct sample);
@@ -91,6 +147,9 @@ static void ringbuf_subtest(void)
 	int err, cnt, rb_fd;
 	int page_size = getpagesize();
 	void *mmap_ptr, *tmp_ptr;
+	struct ring *ring;
+	int map_fd;
+	unsigned long avail_data, ring_size, cons_pos, prod_pos;
 
 	skel = test_ringbuf_lskel__open();
 	if (CHECK(!skel, "skel_open", "skeleton open failed\n"))
@@ -162,6 +221,13 @@ static void ringbuf_subtest(void)
 
 	trigger_samples();
 
+	ring = ring_buffer__ring(ringbuf, 0);
+	if (!ASSERT_OK_PTR(ring, "ring_buffer__ring_idx_0"))
+		goto cleanup;
+
+	map_fd = ring__map_fd(ring);
+	ASSERT_EQ(map_fd, skel->maps.ringbuf.map_fd, "ring_map_fd");
+
 	/* 2 submitted + 1 discarded records */
 	CHECK(skel->bss->avail_data != 3 * rec_sz,
 	      "err_avail_size", "exp %ld, got %ld\n",
@@ -176,6 +242,18 @@ static void ringbuf_subtest(void)
 	      "err_prod_pos", "exp %ld, got %ld\n",
 	      3L * rec_sz, skel->bss->prod_pos);
 
+	/* verify getting this data directly via the ring object yields the same
+	 * results
+	 */
+	avail_data = ring__avail_data_size(ring);
+	ASSERT_EQ(avail_data, 3 * rec_sz, "ring_avail_size");
+	ring_size = ring__size(ring);
+	ASSERT_EQ(ring_size, page_size, "ring_ring_size");
+	cons_pos = ring__consumer_pos(ring);
+	ASSERT_EQ(cons_pos, 0, "ring_cons_pos");
+	prod_pos = ring__producer_pos(ring);
+	ASSERT_EQ(prod_pos, 3 * rec_sz, "ring_prod_pos");
+
 	/* poll for samples */
 	err = ring_buffer__poll(ringbuf, -1);
 
@@ -282,6 +360,10 @@ static void ringbuf_subtest(void)
 	err = ring_buffer__consume(ringbuf);
 	CHECK(err < 0, "rb_consume", "failed: %d\b", err);
 
+	/* also consume using ring__consume to make sure it works the same */
+	err = ring__consume(ring);
+	ASSERT_GE(err, 0, "ring_consume");
+
 	/* 3 rounds, 2 samples each */
 	cnt = atomic_xchg(&sample_cnt, 0);
 	CHECK(cnt != 6, "cnt", "exp %d samples, got %d\n", 6, cnt);
@@ -300,6 +382,68 @@ cleanup:
 	test_ringbuf_lskel__destroy(skel);
 }
 
+/*
+ * Test ring_buffer__consume_n() by producing N_TOT_SAMPLES samples in the ring
+ * buffer, via getpid(), and consuming them in chunks of N_SAMPLES.
+ */
+#define N_TOT_SAMPLES	32
+#define N_SAMPLES	4
+
+/* Sample value to verify the callback validity */
+#define SAMPLE_VALUE	42L
+
+static int process_n_sample(void *ctx, void *data, size_t len)
+{
+	struct sample *s = data;
+
+	ASSERT_EQ(s->value, SAMPLE_VALUE, "sample_value");
+
+	return 0;
+}
+
+static void ringbuf_n_subtest(void)
+{
+	struct test_ringbuf_n_lskel *skel_n;
+	int err, i;
+
+	skel_n = test_ringbuf_n_lskel__open();
+	if (!ASSERT_OK_PTR(skel_n, "test_ringbuf_n_lskel__open"))
+		return;
+
+	skel_n->maps.ringbuf.max_entries = getpagesize();
+	skel_n->bss->pid = getpid();
+
+	err = test_ringbuf_n_lskel__load(skel_n);
+	if (!ASSERT_OK(err, "test_ringbuf_n_lskel__load"))
+		goto cleanup;
+
+	ringbuf = ring_buffer__new(skel_n->maps.ringbuf.map_fd,
+				   process_n_sample, NULL, NULL);
+	if (!ASSERT_OK_PTR(ringbuf, "ring_buffer__new"))
+		goto cleanup;
+
+	err = test_ringbuf_n_lskel__attach(skel_n);
+	if (!ASSERT_OK(err, "test_ringbuf_n_lskel__attach"))
+		goto cleanup_ringbuf;
+
+	/* Produce N_TOT_SAMPLES samples in the ring buffer by calling getpid() */
+	skel_n->bss->value = SAMPLE_VALUE;
+	for (i = 0; i < N_TOT_SAMPLES; i++)
+		syscall(__NR_getpgid);
+
+	/* Consume all samples from the ring buffer in batches of N_SAMPLES */
+	for (i = 0; i < N_TOT_SAMPLES; i += err) {
+		err = ring_buffer__consume_n(ringbuf, N_SAMPLES);
+		if (!ASSERT_EQ(err, N_SAMPLES, "rb_consume"))
+			goto cleanup_ringbuf;
+	}
+
+cleanup_ringbuf:
+	ring_buffer__free(ringbuf);
+cleanup:
+	test_ringbuf_n_lskel__destroy(skel_n);
+}
+
 static int process_map_key_sample(void *ctx, void *data, size_t len)
 {
 	struct sample *s;
@@ -354,10 +498,78 @@ cleanup:
 	test_ringbuf_map_key_lskel__destroy(skel_map_key);
 }
 
+static void ringbuf_overwrite_mode_subtest(void)
+{
+	unsigned long size, len1, len2, len3, len4, len5;
+	unsigned long expect_avail_data, expect_prod_pos, expect_over_pos;
+	struct test_ringbuf_overwrite_lskel *skel;
+	int page_size = getpagesize();
+	int err;
+
+	skel = test_ringbuf_overwrite_lskel__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	size = page_size;
+	len1 = page_size / 2;
+	len2 = page_size / 4;
+	len3 = size - len1 - len2 - BPF_RINGBUF_HDR_SZ * 3;
+	len4 = len3 - 8;
+	len5 = len3; /* retry with len3 */
+
+	skel->maps.ringbuf.max_entries = size;
+	skel->rodata->LEN1 = len1;
+	skel->rodata->LEN2 = len2;
+	skel->rodata->LEN3 = len3;
+	skel->rodata->LEN4 = len4;
+	skel->rodata->LEN5 = len5;
+
+	skel->bss->pid = getpid();
+
+	err = test_ringbuf_overwrite_lskel__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	err = test_ringbuf_overwrite_lskel__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	syscall(__NR_getpgid);
+
+	ASSERT_EQ(skel->bss->reserve1_fail, 0, "reserve 1");
+	ASSERT_EQ(skel->bss->reserve2_fail, 0, "reserve 2");
+	ASSERT_EQ(skel->bss->reserve3_fail, 1, "reserve 3");
+	ASSERT_EQ(skel->bss->reserve4_fail, 0, "reserve 4");
+	ASSERT_EQ(skel->bss->reserve5_fail, 0, "reserve 5");
+
+	ASSERT_EQ(skel->bss->ring_size, size, "check_ring_size");
+
+	expect_avail_data = len2 + len4 + len5 + 3 * BPF_RINGBUF_HDR_SZ;
+	ASSERT_EQ(skel->bss->avail_data, expect_avail_data, "check_avail_size");
+
+	ASSERT_EQ(skel->bss->cons_pos, 0, "check_cons_pos");
+
+	expect_prod_pos = len1 + len2 + len4 + len5 + 4 * BPF_RINGBUF_HDR_SZ;
+	ASSERT_EQ(skel->bss->prod_pos, expect_prod_pos, "check_prod_pos");
+
+	expect_over_pos = len1 + BPF_RINGBUF_HDR_SZ;
+	ASSERT_EQ(skel->bss->over_pos, expect_over_pos, "check_over_pos");
+
+	test_ringbuf_overwrite_lskel__detach(skel);
+cleanup:
+	test_ringbuf_overwrite_lskel__destroy(skel);
+}
+
 void test_ringbuf(void)
 {
 	if (test__start_subtest("ringbuf"))
 		ringbuf_subtest();
+	if (test__start_subtest("ringbuf_n"))
+		ringbuf_n_subtest();
 	if (test__start_subtest("ringbuf_map_key"))
 		ringbuf_map_key_subtest();
+	if (test__start_subtest("ringbuf_write"))
+		ringbuf_write_subtest();
+	if (test__start_subtest("ringbuf_overwrite_mode"))
+		ringbuf_overwrite_mode_subtest();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
index 1455911d9fcb..58522195081b 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
@@ -42,6 +42,8 @@ void test_ringbuf_multi(void)
 {
 	struct test_ringbuf_multi *skel;
 	struct ring_buffer *ringbuf = NULL;
+	struct ring *ring_old;
+	struct ring *ring;
 	int err;
 	int page_size = getpagesize();
 	int proto_fd = -1;
@@ -84,11 +86,24 @@ void test_ringbuf_multi(void)
 	if (CHECK(!ringbuf, "ringbuf_create", "failed to create ringbuf\n"))
 		goto cleanup;
 
+	/* verify ring_buffer__ring returns expected results */
+	ring = ring_buffer__ring(ringbuf, 0);
+	if (!ASSERT_OK_PTR(ring, "ring_buffer__ring_idx_0"))
+		goto cleanup;
+	ring_old = ring;
+	ring = ring_buffer__ring(ringbuf, 1);
+	ASSERT_ERR_PTR(ring, "ring_buffer__ring_idx_1");
+
 	err = ring_buffer__add(ringbuf, bpf_map__fd(skel->maps.ringbuf2),
 			      process_sample, (void *)(long)2);
 	if (CHECK(err, "ringbuf_add", "failed to add another ring\n"))
 		goto cleanup;
 
+	/* verify adding a new ring didn't invalidate our older pointer */
+	ring = ring_buffer__ring(ringbuf, 0);
+	if (!ASSERT_EQ(ring, ring_old, "ring_buffer__ring_again"))
+		goto cleanup;
+
 	err = test_ringbuf_multi__attach(skel);
 	if (CHECK(err, "skel_attach", "skeleton attachment failed: %d\n", err))
 		goto cleanup;
diff --git a/tools/testing/selftests/bpf/prog_tests/section_names.c b/tools/testing/selftests/bpf/prog_tests/section_names.c
index 8b571890c57e..c3d78846f31a 100644
--- a/tools/testing/selftests/bpf/prog_tests/section_names.c
+++ b/tools/testing/selftests/bpf/prog_tests/section_names.c
@@ -124,6 +124,11 @@ static struct sec_name_test tests[] = {
 		{0, BPF_CGROUP_INET6_CONNECT},
 	},
 	{
+		"cgroup/connect_unix",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UNIX_CONNECT},
+		{0, BPF_CGROUP_UNIX_CONNECT},
+	},
+	{
 		"cgroup/sendmsg4",
 		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG},
 		{0, BPF_CGROUP_UDP4_SENDMSG},
@@ -134,6 +139,11 @@ static struct sec_name_test tests[] = {
 		{0, BPF_CGROUP_UDP6_SENDMSG},
 	},
 	{
+		"cgroup/sendmsg_unix",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UNIX_SENDMSG},
+		{0, BPF_CGROUP_UNIX_SENDMSG},
+	},
+	{
 		"cgroup/recvmsg4",
 		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_RECVMSG},
 		{0, BPF_CGROUP_UDP4_RECVMSG},
@@ -144,6 +154,11 @@ static struct sec_name_test tests[] = {
 		{0, BPF_CGROUP_UDP6_RECVMSG},
 	},
 	{
+		"cgroup/recvmsg_unix",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UNIX_RECVMSG},
+		{0, BPF_CGROUP_UNIX_RECVMSG},
+	},
+	{
 		"cgroup/sysctl",
 		{0, BPF_PROG_TYPE_CGROUP_SYSCTL, BPF_CGROUP_SYSCTL},
 		{0, BPF_CGROUP_SYSCTL},
@@ -158,6 +173,36 @@ static struct sec_name_test tests[] = {
 		{0, BPF_PROG_TYPE_CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT},
 		{0, BPF_CGROUP_SETSOCKOPT},
 	},
+	{
+		"cgroup/getpeername4",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETPEERNAME},
+		{0, BPF_CGROUP_INET4_GETPEERNAME},
+	},
+	{
+		"cgroup/getpeername6",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETPEERNAME},
+		{0, BPF_CGROUP_INET6_GETPEERNAME},
+	},
+	{
+		"cgroup/getpeername_unix",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UNIX_GETPEERNAME},
+		{0, BPF_CGROUP_UNIX_GETPEERNAME},
+	},
+	{
+		"cgroup/getsockname4",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETSOCKNAME},
+		{0, BPF_CGROUP_INET4_GETSOCKNAME},
+	},
+	{
+		"cgroup/getsockname6",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETSOCKNAME},
+		{0, BPF_CGROUP_INET6_GETSOCKNAME},
+	},
+	{
+		"cgroup/getsockname_unix",
+		{0, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_UNIX_GETSOCKNAME},
+		{0, BPF_CGROUP_UNIX_GETSOCKNAME},
+	},
 };
 
 static void test_prog_type_by_name(const struct sec_name_test *test)
diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
index 64c5f5eb2994..3dbcc091f16c 100644
--- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
+++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
@@ -37,17 +37,11 @@ static int sk_fds[REUSEPORT_ARRAY_SIZE];
 static int reuseport_array = -1, outer_map = -1;
 static enum bpf_map_type inner_map_type;
 static int select_by_skb_data_prog;
-static int saved_tcp_syncookie = -1;
 static struct bpf_object *obj;
-static int saved_tcp_fo = -1;
 static __u32 index_zero;
 static int epfd;
 
-static union sa46 {
-	struct sockaddr_in6 v6;
-	struct sockaddr_in v4;
-	sa_family_t family;
-} srv_sa;
+static struct sockaddr_storage srv_sa;
 
 #define RET_IF(condition, tag, format...) ({				\
 	if (CHECK_FAIL(condition)) {					\
@@ -137,24 +131,24 @@ static int prepare_bpf_obj(void)
 	return 0;
 }
 
-static void sa46_init_loopback(union sa46 *sa, sa_family_t family)
+static void ss_init_loopback(struct sockaddr_storage *sa, sa_family_t family)
 {
 	memset(sa, 0, sizeof(*sa));
-	sa->family = family;
-	if (sa->family == AF_INET6)
-		sa->v6.sin6_addr = in6addr_loopback;
+	sa->ss_family = family;
+	if (sa->ss_family == AF_INET6)
+		((struct sockaddr_in6 *)sa)->sin6_addr = in6addr_loopback;
 	else
-		sa->v4.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+		((struct sockaddr_in *)sa)->sin_addr.s_addr = htonl(INADDR_LOOPBACK);
 }
 
-static void sa46_init_inany(union sa46 *sa, sa_family_t family)
+static void ss_init_inany(struct sockaddr_storage *sa, sa_family_t family)
 {
 	memset(sa, 0, sizeof(*sa));
-	sa->family = family;
-	if (sa->family == AF_INET6)
-		sa->v6.sin6_addr = in6addr_any;
+	sa->ss_family = family;
+	if (sa->ss_family == AF_INET6)
+		((struct sockaddr_in6 *)sa)->sin6_addr = in6addr_any;
 	else
-		sa->v4.sin_addr.s_addr = INADDR_ANY;
+		((struct sockaddr_in *)sa)->sin_addr.s_addr = INADDR_ANY;
 }
 
 static int read_int_sysctl(const char *sysctl)
@@ -193,14 +187,6 @@ static int write_int_sysctl(const char *sysctl, int v)
 	return 0;
 }
 
-static void restore_sysctls(void)
-{
-	if (saved_tcp_fo != -1)
-		write_int_sysctl(TCP_FO_SYSCTL, saved_tcp_fo);
-	if (saved_tcp_syncookie != -1)
-		write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, saved_tcp_syncookie);
-}
-
 static int enable_fastopen(void)
 {
 	int fo;
@@ -238,7 +224,7 @@ static void check_data(int type, sa_family_t family, const struct cmd *cmd,
 		       int cli_fd)
 {
 	struct data_check expected = {}, result;
-	union sa46 cli_sa;
+	struct sockaddr_storage cli_sa;
 	socklen_t addrlen;
 	int err;
 
@@ -261,26 +247,32 @@ static void check_data(int type, sa_family_t family, const struct cmd *cmd,
 	}
 
 	if (family == AF_INET6) {
+		struct sockaddr_in6 *srv_v6 = (struct sockaddr_in6 *)&srv_sa;
+		struct sockaddr_in6 *cli_v6 = (struct sockaddr_in6 *)&cli_sa;
+
 		expected.eth_protocol = htons(ETH_P_IPV6);
-		expected.bind_inany = !srv_sa.v6.sin6_addr.s6_addr32[3] &&
-			!srv_sa.v6.sin6_addr.s6_addr32[2] &&
-			!srv_sa.v6.sin6_addr.s6_addr32[1] &&
-			!srv_sa.v6.sin6_addr.s6_addr32[0];
+		expected.bind_inany = !srv_v6->sin6_addr.s6_addr32[3] &&
+			!srv_v6->sin6_addr.s6_addr32[2] &&
+			!srv_v6->sin6_addr.s6_addr32[1] &&
+			!srv_v6->sin6_addr.s6_addr32[0];
 
-		memcpy(&expected.skb_addrs[0], cli_sa.v6.sin6_addr.s6_addr32,
-		       sizeof(cli_sa.v6.sin6_addr));
+		memcpy(&expected.skb_addrs[0], cli_v6->sin6_addr.s6_addr32,
+		       sizeof(cli_v6->sin6_addr));
 		memcpy(&expected.skb_addrs[4], &in6addr_loopback,
 		       sizeof(in6addr_loopback));
-		expected.skb_ports[0] = cli_sa.v6.sin6_port;
-		expected.skb_ports[1] = srv_sa.v6.sin6_port;
+		expected.skb_ports[0] = cli_v6->sin6_port;
+		expected.skb_ports[1] = srv_v6->sin6_port;
 	} else {
+		struct sockaddr_in *srv_v4 = (struct sockaddr_in *)&srv_sa;
+		struct sockaddr_in *cli_v4 = (struct sockaddr_in *)&cli_sa;
+
 		expected.eth_protocol = htons(ETH_P_IP);
-		expected.bind_inany = !srv_sa.v4.sin_addr.s_addr;
+		expected.bind_inany = !srv_v4->sin_addr.s_addr;
 
-		expected.skb_addrs[0] = cli_sa.v4.sin_addr.s_addr;
+		expected.skb_addrs[0] = cli_v4->sin_addr.s_addr;
 		expected.skb_addrs[1] = htonl(INADDR_LOOPBACK);
-		expected.skb_ports[0] = cli_sa.v4.sin_port;
-		expected.skb_ports[1] = srv_sa.v4.sin_port;
+		expected.skb_ports[0] = cli_v4->sin_port;
+		expected.skb_ports[1] = srv_v4->sin_port;
 	}
 
 	if (memcmp(&result, &expected, offsetof(struct data_check,
@@ -374,16 +366,15 @@ static void check_results(void)
 static int send_data(int type, sa_family_t family, void *data, size_t len,
 		     enum result expected)
 {
-	union sa46 cli_sa;
+	struct sockaddr_storage cli_sa;
 	int fd, err;
 
 	fd = socket(family, type, 0);
 	RET_ERR(fd == -1, "socket()", "fd:%d errno:%d\n", fd, errno);
 
-	sa46_init_loopback(&cli_sa, family);
+	ss_init_loopback(&cli_sa, family);
 	err = bind(fd, (struct sockaddr *)&cli_sa, sizeof(cli_sa));
 	RET_ERR(fd == -1, "bind(cli_sa)", "err:%d errno:%d\n", err, errno);
-
 	err = sendto(fd, data, len, MSG_FASTOPEN, (struct sockaddr *)&srv_sa,
 		     sizeof(srv_sa));
 	RET_ERR(err != len && expected >= PASS,
@@ -599,9 +590,9 @@ static void prepare_sk_fds(int type, sa_family_t family, bool inany)
 	socklen_t addrlen;
 
 	if (inany)
-		sa46_init_inany(&srv_sa, family);
+		ss_init_inany(&srv_sa, family);
 	else
-		sa46_init_loopback(&srv_sa, family);
+		ss_init_loopback(&srv_sa, family);
 	addrlen = sizeof(srv_sa);
 
 	/*
@@ -793,6 +784,7 @@ static void test_config(int sotype, sa_family_t family, bool inany)
 		TEST_INIT(test_pass_on_err),
 		TEST_INIT(test_detach_bpf),
 	};
+	struct netns_obj *netns;
 	char s[MAX_TEST_NAME];
 	const struct test *t;
 
@@ -808,9 +800,21 @@ static void test_config(int sotype, sa_family_t family, bool inany)
 		if (!test__start_subtest(s))
 			continue;
 
+		netns = netns_new("select_reuseport", true);
+		if (!ASSERT_OK_PTR(netns, "netns_new"))
+			continue;
+
+		if (CHECK_FAIL(enable_fastopen()))
+			goto out;
+		if (CHECK_FAIL(disable_syncookie()))
+			goto out;
+
 		setup_per_test(sotype, family, inany, t->no_inner_map);
 		t->fn(sotype, family);
 		cleanup_per_test(t->no_inner_map);
+
+out:
+		netns_free(netns);
 	}
 }
 
@@ -850,21 +854,7 @@ out:
 
 void serial_test_select_reuseport(void)
 {
-	saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL);
-	if (saved_tcp_fo < 0)
-		goto out;
-	saved_tcp_syncookie = read_int_sysctl(TCP_SYNCOOKIE_SYSCTL);
-	if (saved_tcp_syncookie < 0)
-		goto out;
-
-	if (enable_fastopen())
-		goto out;
-	if (disable_syncookie())
-		goto out;
-
 	test_map_type(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY);
 	test_map_type(BPF_MAP_TYPE_SOCKMAP);
 	test_map_type(BPF_MAP_TYPE_SOCKHASH);
-out:
-	restore_sysctls();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c
index d63a20fbed33..7ac4d5a488aa 100644
--- a/tools/testing/selftests/bpf/prog_tests/send_signal.c
+++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c
@@ -3,22 +3,32 @@
 #include <sys/time.h>
 #include <sys/resource.h>
 #include "test_send_signal_kern.skel.h"
+#include "io_helpers.h"
 
 static int sigusr1_received;
 
 static void sigusr1_handler(int signum)
 {
-	sigusr1_received = 1;
+	sigusr1_received = 8;
+}
+
+static void sigusr1_siginfo_handler(int s, siginfo_t *i, void *v)
+{
+	sigusr1_received = (int)(long long)i->si_value.sival_ptr;
 }
 
 static void test_send_signal_common(struct perf_event_attr *attr,
-				    bool signal_thread)
+				    bool signal_thread, bool remote)
 {
 	struct test_send_signal_kern *skel;
+	struct sigaction sa;
 	int pipe_c2p[2], pipe_p2c[2];
 	int err = -1, pmu_fd = -1;
+	volatile int j = 0;
+	int retry_count;
 	char buf[256];
 	pid_t pid;
+	int old_prio;
 
 	if (!ASSERT_OK(pipe(pipe_c2p), "pipe_c2p"))
 		return;
@@ -39,11 +49,14 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 	}
 
 	if (pid == 0) {
-		int old_prio;
-		volatile int j = 0;
-
 		/* install signal handler and notify parent */
-		ASSERT_NEQ(signal(SIGUSR1, sigusr1_handler), SIG_ERR, "signal");
+		if (remote) {
+			sa.sa_sigaction = sigusr1_siginfo_handler;
+			sa.sa_flags = SA_RESTART | SA_SIGINFO;
+			ASSERT_NEQ(sigaction(SIGUSR1, &sa, NULL), -1, "sigaction");
+		} else {
+			ASSERT_NEQ(signal(SIGUSR1, sigusr1_handler), SIG_ERR, "signal");
+		}
 
 		close(pipe_c2p[0]); /* close read */
 		close(pipe_p2c[1]); /* close write */
@@ -52,10 +65,12 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 		 * that if an interrupt happens, the underlying task
 		 * is this process.
 		 */
-		errno = 0;
-		old_prio = getpriority(PRIO_PROCESS, 0);
-		ASSERT_OK(errno, "getpriority");
-		ASSERT_OK(setpriority(PRIO_PROCESS, 0, -20), "setpriority");
+		if (!remote) {
+			errno = 0;
+			old_prio = getpriority(PRIO_PROCESS, 0);
+			ASSERT_OK(errno, "getpriority");
+			ASSERT_OK(setpriority(PRIO_PROCESS, 0, -20), "setpriority");
+		}
 
 		/* notify parent signal handler is installed */
 		ASSERT_EQ(write(pipe_c2p[1], buf, 1), 1, "pipe_write");
@@ -64,18 +79,27 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 		ASSERT_EQ(read(pipe_p2c[0], buf, 1), 1, "pipe_read");
 
 		/* wait a little for signal handler */
-		for (int i = 0; i < 1000000000 && !sigusr1_received; i++)
+		for (int i = 0; i < 1000000000 && !sigusr1_received; i++) {
 			j /= i + j + 1;
+			if (remote)
+				sleep(1);
+			else
+				if (!attr)
+					/* trigger the nanosleep tracepoint program. */
+					usleep(1);
+		}
 
-		buf[0] = sigusr1_received ? '2' : '0';
-		ASSERT_EQ(sigusr1_received, 1, "sigusr1_received");
+		buf[0] = sigusr1_received;
+
+		ASSERT_EQ(sigusr1_received, 8, "sigusr1_received");
 		ASSERT_EQ(write(pipe_c2p[1], buf, 1), 1, "pipe_write");
 
 		/* wait for parent notification and exit */
 		ASSERT_EQ(read(pipe_p2c[0], buf, 1), 1, "pipe_read");
 
 		/* restore the old priority */
-		ASSERT_OK(setpriority(PRIO_PROCESS, 0, old_prio), "setpriority");
+		if (!remote)
+			ASSERT_OK(setpriority(PRIO_PROCESS, 0, old_prio), "setpriority");
 
 		close(pipe_c2p[1]);
 		close(pipe_p2c[0]);
@@ -89,6 +113,17 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
 		goto skel_open_load_failure;
 
+	/* boost with a high priority so we got a higher chance
+	 * that if an interrupt happens, the underlying task
+	 * is this process.
+	 */
+	if (remote) {
+		errno = 0;
+		old_prio = getpriority(PRIO_PROCESS, 0);
+		ASSERT_OK(errno, "getpriority");
+		ASSERT_OK(setpriority(PRIO_PROCESS, 0, -20), "setpriority");
+	}
+
 	if (!attr) {
 		err = test_send_signal_kern__attach(skel);
 		if (!ASSERT_OK(err, "skel_attach")) {
@@ -96,8 +131,12 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 			goto destroy_skel;
 		}
 	} else {
-		pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1 /* cpu */,
-				 -1 /* group id */, 0 /* flags */);
+		if (!remote)
+			pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1 /* cpu */,
+					 -1 /* group id */, 0 /* flags */);
+		else
+			pmu_fd = syscall(__NR_perf_event_open, attr, getpid(), -1 /* cpu */,
+					 -1 /* group id */, 0 /* flags */);
 		if (!ASSERT_GE(pmu_fd, 0, "perf_event_open")) {
 			err = -1;
 			goto destroy_skel;
@@ -115,13 +154,36 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 	/* trigger the bpf send_signal */
 	skel->bss->signal_thread = signal_thread;
 	skel->bss->sig = SIGUSR1;
-	skel->bss->pid = pid;
+	if (!remote) {
+		skel->bss->target_pid = 0;
+		skel->bss->pid = pid;
+	} else {
+		skel->bss->target_pid = pid;
+		skel->bss->pid = getpid();
+	}
 
 	/* notify child that bpf program can send_signal now */
 	ASSERT_EQ(write(pipe_p2c[1], buf, 1), 1, "pipe_write");
 
-	/* wait for result */
-	err = read(pipe_c2p[0], buf, 1);
+	for (retry_count = 0;;) {
+		/* For the remote test, the BPF program is triggered from this
+		 * process but the other process/thread is signaled.
+		 */
+		if (remote) {
+			if (!attr) {
+				for (int i = 0; i < 10; i++)
+					usleep(1);
+			} else {
+				for (int i = 0; i < 100000000; i++)
+					j /= i + 1;
+			}
+		}
+		/* wait for result */
+		err = read_with_timeout(pipe_c2p[0], buf, 1, 100);
+		if (err == -EAGAIN && retry_count++ < 10000)
+			continue;
+		break;
+	}
 	if (!ASSERT_GE(err, 0, "reading pipe"))
 		goto disable_pmu;
 	if (!ASSERT_GT(err, 0, "reading pipe error: size 0")) {
@@ -129,7 +191,7 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 		goto disable_pmu;
 	}
 
-	ASSERT_EQ(buf[0], '2', "incorrect result");
+	ASSERT_EQ(buf[0], 8, "incorrect result");
 
 	/* notify child safe to exit */
 	ASSERT_EQ(write(pipe_p2c[1], buf, 1), 1, "pipe_write");
@@ -138,32 +200,42 @@ disable_pmu:
 	close(pmu_fd);
 destroy_skel:
 	test_send_signal_kern__destroy(skel);
+	/* restore the old priority */
+	if (remote)
+		ASSERT_OK(setpriority(PRIO_PROCESS, 0, old_prio), "setpriority");
 skel_open_load_failure:
 	close(pipe_c2p[0]);
 	close(pipe_p2c[1]);
+	/*
+	 * Child is either about to exit cleanly or stuck in case of errors.
+	 * Nudge it to exit.
+	 */
+	kill(pid, SIGKILL);
 	wait(NULL);
 }
 
-static void test_send_signal_tracepoint(bool signal_thread)
+static void test_send_signal_tracepoint(bool signal_thread, bool remote)
 {
-	test_send_signal_common(NULL, signal_thread);
+	test_send_signal_common(NULL, signal_thread, remote);
 }
 
-static void test_send_signal_perf(bool signal_thread)
+static void test_send_signal_perf(bool signal_thread, bool remote)
 {
 	struct perf_event_attr attr = {
-		.sample_period = 1,
+		.freq = 1,
+		.sample_freq = 1000,
 		.type = PERF_TYPE_SOFTWARE,
 		.config = PERF_COUNT_SW_CPU_CLOCK,
 	};
 
-	test_send_signal_common(&attr, signal_thread);
+	test_send_signal_common(&attr, signal_thread, remote);
 }
 
-static void test_send_signal_nmi(bool signal_thread)
+static void test_send_signal_nmi(bool signal_thread, bool remote)
 {
 	struct perf_event_attr attr = {
-		.sample_period = 1,
+		.freq = 1,
+		.sample_freq = 1000,
 		.type = PERF_TYPE_HARDWARE,
 		.config = PERF_COUNT_HW_CPU_CYCLES,
 	};
@@ -175,7 +247,7 @@ static void test_send_signal_nmi(bool signal_thread)
 	pmu_fd = syscall(__NR_perf_event_open, &attr, 0 /* pid */,
 			 -1 /* cpu */, -1 /* group_fd */, 0 /* flags */);
 	if (pmu_fd == -1) {
-		if (errno == ENOENT) {
+		if (errno == ENOENT || errno == EOPNOTSUPP) {
 			printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n",
 			       __func__);
 			test__skip();
@@ -186,21 +258,35 @@ static void test_send_signal_nmi(bool signal_thread)
 		close(pmu_fd);
 	}
 
-	test_send_signal_common(&attr, signal_thread);
+	test_send_signal_common(&attr, signal_thread, remote);
 }
 
 void test_send_signal(void)
 {
 	if (test__start_subtest("send_signal_tracepoint"))
-		test_send_signal_tracepoint(false);
+		test_send_signal_tracepoint(false, false);
 	if (test__start_subtest("send_signal_perf"))
-		test_send_signal_perf(false);
+		test_send_signal_perf(false, false);
 	if (test__start_subtest("send_signal_nmi"))
-		test_send_signal_nmi(false);
+		test_send_signal_nmi(false, false);
 	if (test__start_subtest("send_signal_tracepoint_thread"))
-		test_send_signal_tracepoint(true);
+		test_send_signal_tracepoint(true, false);
 	if (test__start_subtest("send_signal_perf_thread"))
-		test_send_signal_perf(true);
+		test_send_signal_perf(true, false);
 	if (test__start_subtest("send_signal_nmi_thread"))
-		test_send_signal_nmi(true);
+		test_send_signal_nmi(true, false);
+
+	/* Signal remote thread and thread group */
+	if (test__start_subtest("send_signal_tracepoint_remote"))
+		test_send_signal_tracepoint(false, true);
+	if (test__start_subtest("send_signal_perf_remote"))
+		test_send_signal_perf(false, true);
+	if (test__start_subtest("send_signal_nmi_remote"))
+		test_send_signal_nmi(false, true);
+	if (test__start_subtest("send_signal_tracepoint_thread_remote"))
+		test_send_signal_tracepoint(true, true);
+	if (test__start_subtest("send_signal_perf_thread_remote"))
+		test_send_signal_perf(true, true);
+	if (test__start_subtest("send_signal_nmi_thread_remote"))
+		test_send_signal_nmi(true, true);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c
index 018611e6b248..e4dac529d424 100644
--- a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c
+++ b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c
@@ -4,6 +4,7 @@
 #define _GNU_SOURCE
 #include <sched.h>
 #include <linux/socket.h>
+#include <linux/tls.h>
 #include <net/if.h>
 
 #include "test_progs.h"
@@ -83,10 +84,125 @@ static void test_udp(int family)
 	ASSERT_EQ(bss->nr_binddev, 1, "nr_bind");
 }
 
+static void test_ktls(int family)
+{
+	struct tls12_crypto_info_aes_gcm_128 aes128;
+	struct setget_sockopt__bss *bss = skel->bss;
+	int cfd = -1, sfd = -1, fd = -1, ret;
+	char buf;
+
+	memset(bss, 0, sizeof(*bss));
+
+	sfd = start_server(family, SOCK_STREAM,
+			   family == AF_INET6 ? addr6_str : addr4_str, 0, 0);
+	if (!ASSERT_GE(sfd, 0, "start_server"))
+		return;
+	fd = connect_to_fd(sfd, 0);
+	if (!ASSERT_GE(fd, 0, "connect_to_fd"))
+		goto err_out;
+
+	cfd = accept(sfd, NULL, 0);
+	if (!ASSERT_GE(cfd, 0, "accept"))
+		goto err_out;
+
+	close(sfd);
+	sfd = -1;
+
+	/* Setup KTLS */
+	ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+	if (!ASSERT_OK(ret, "setsockopt"))
+		goto err_out;
+	ret = setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+	if (!ASSERT_OK(ret, "setsockopt"))
+		goto err_out;
+
+	memset(&aes128, 0, sizeof(aes128));
+	aes128.info.version = TLS_1_2_VERSION;
+	aes128.info.cipher_type = TLS_CIPHER_AES_GCM_128;
+
+	ret = setsockopt(fd, SOL_TLS, TLS_TX, &aes128, sizeof(aes128));
+	if (!ASSERT_OK(ret, "setsockopt"))
+		goto err_out;
+
+	ret = setsockopt(cfd, SOL_TLS, TLS_RX, &aes128, sizeof(aes128));
+	if (!ASSERT_OK(ret, "setsockopt"))
+		goto err_out;
+
+	/* KTLS is enabled */
+
+	close(fd);
+	/* At this point, the cfd socket is at the CLOSE_WAIT state
+	 * and still run TLS protocol.  The test for
+	 * BPF_TCP_CLOSE_WAIT should be run at this point.
+	 */
+	ret = read(cfd, &buf, sizeof(buf));
+	ASSERT_EQ(ret, 0, "read");
+	close(cfd);
+
+	ASSERT_EQ(bss->nr_listen, 1, "nr_listen");
+	ASSERT_EQ(bss->nr_connect, 1, "nr_connect");
+	ASSERT_EQ(bss->nr_active, 1, "nr_active");
+	ASSERT_EQ(bss->nr_passive, 1, "nr_passive");
+	ASSERT_EQ(bss->nr_socket_post_create, 2, "nr_socket_post_create");
+	ASSERT_EQ(bss->nr_binddev, 2, "nr_bind");
+	ASSERT_EQ(bss->nr_fin_wait1, 1, "nr_fin_wait1");
+	return;
+
+err_out:
+	close(fd);
+	close(cfd);
+	close(sfd);
+}
+
+static void test_nonstandard_opt(int family)
+{
+	struct setget_sockopt__bss *bss = skel->bss;
+	struct bpf_link *getsockopt_link = NULL;
+	int sfd = -1, fd = -1, cfd = -1, flags;
+	socklen_t flagslen = sizeof(flags);
+
+	memset(bss, 0, sizeof(*bss));
+
+	sfd = start_server(family, SOCK_STREAM,
+			   family == AF_INET6 ? addr6_str : addr4_str, 0, 0);
+	if (!ASSERT_GE(sfd, 0, "start_server"))
+		return;
+
+	fd = connect_to_fd(sfd, 0);
+	if (!ASSERT_GE(fd, 0, "connect_to_fd_server"))
+		goto err_out;
+
+	/* cgroup/getsockopt prog will intercept getsockopt() below and
+	 * retrieve the tcp socket bpf_sock_ops_cb_flags value for the
+	 * accept()ed socket; this was set earlier in the passive established
+	 * callback for the accept()ed socket via bpf_setsockopt().
+	 */
+	getsockopt_link = bpf_program__attach_cgroup(skel->progs._getsockopt, cg_fd);
+	if (!ASSERT_OK_PTR(getsockopt_link, "getsockopt prog"))
+		goto err_out;
+
+	cfd = accept(sfd, NULL, 0);
+	if (!ASSERT_GE(cfd, 0, "accept"))
+		goto err_out;
+
+	if (!ASSERT_OK(getsockopt(cfd, SOL_TCP, TCP_BPF_SOCK_OPS_CB_FLAGS, &flags, &flagslen),
+		       "getsockopt_flags"))
+		goto err_out;
+	ASSERT_EQ(flags & BPF_SOCK_OPS_STATE_CB_FLAG, BPF_SOCK_OPS_STATE_CB_FLAG,
+		  "cb_flags_set");
+err_out:
+	close(sfd);
+	if (fd != -1)
+		close(fd);
+	if (cfd != -1)
+		close(cfd);
+	bpf_link__destroy(getsockopt_link);
+}
+
 void test_setget_sockopt(void)
 {
 	cg_fd = test__join_cgroup(CG_NAME);
-	if (cg_fd < 0)
+	if (!ASSERT_OK_FD(cg_fd, "join cgroup"))
 		return;
 
 	if (create_netns())
@@ -118,6 +234,10 @@ void test_setget_sockopt(void)
 	test_tcp(AF_INET);
 	test_udp(AF_INET6);
 	test_udp(AF_INET);
+	test_ktls(AF_INET6);
+	test_ktls(AF_INET);
+	test_nonstandard_opt(AF_INET);
+	test_nonstandard_opt(AF_INET6);
 
 done:
 	setget_sockopt__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/sha256.c b/tools/testing/selftests/bpf/prog_tests/sha256.c
new file mode 100644
index 000000000000..604a0b1423d5
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sha256.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright 2025 Google LLC */
+
+#include <test_progs.h>
+#include "bpf/libbpf_internal.h"
+
+#define MAX_LEN 4096
+
+/* Test libbpf_sha256() for all lengths from 0 to MAX_LEN inclusively. */
+void test_sha256(void)
+{
+	/*
+	 * The correctness of this value was verified by running this test with
+	 * libbpf_sha256() replaced by OpenSSL's SHA256().
+	 */
+	static const __u8 expected_digest_of_digests[SHA256_DIGEST_LENGTH] = {
+		0x62, 0x30, 0x0e, 0x1d, 0xea, 0x7f, 0xc4, 0x74,
+		0xfd, 0x8e, 0x64, 0x0b, 0xd8, 0x5f, 0xea, 0x04,
+		0xf3, 0xef, 0x77, 0x42, 0xc2, 0x01, 0xb8, 0x90,
+		0x6e, 0x19, 0x91, 0x1b, 0xca, 0xb3, 0x28, 0x42,
+	};
+	__u64 seed = 0;
+	__u8 *data = NULL, *digests = NULL;
+	__u8 digest_of_digests[SHA256_DIGEST_LENGTH];
+	size_t i;
+
+	data = malloc(MAX_LEN);
+	if (!ASSERT_OK_PTR(data, "malloc"))
+		goto out;
+	digests = malloc((MAX_LEN + 1) * SHA256_DIGEST_LENGTH);
+	if (!ASSERT_OK_PTR(digests, "malloc"))
+		goto out;
+
+	/* Generate MAX_LEN bytes of "random" data deterministically. */
+	for (i = 0; i < MAX_LEN; i++) {
+		seed = (seed * 25214903917 + 11) & ((1ULL << 48) - 1);
+		data[i] = (__u8)(seed >> 16);
+	}
+
+	/* Calculate a digest for each length 0 through MAX_LEN inclusively. */
+	for (i = 0; i <= MAX_LEN; i++)
+		libbpf_sha256(data, i, &digests[i * SHA256_DIGEST_LENGTH]);
+
+	/* Calculate and verify the digest of all the digests. */
+	libbpf_sha256(digests, (MAX_LEN + 1) * SHA256_DIGEST_LENGTH,
+		      digest_of_digests);
+	ASSERT_MEMEQ(digest_of_digests, expected_digest_of_digests,
+		     SHA256_DIGEST_LENGTH, "digest_of_digests");
+out:
+	free(data);
+	free(digests);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sk_assign.c b/tools/testing/selftests/bpf/prog_tests/sk_assign.c
index 3e190ed63976..10a0ab954b8a 100644
--- a/tools/testing/selftests/bpf/prog_tests/sk_assign.c
+++ b/tools/testing/selftests/bpf/prog_tests/sk_assign.c
@@ -15,6 +15,7 @@
 #include <unistd.h>
 
 #include "test_progs.h"
+#include "network_helpers.h"
 
 #define BIND_PORT 1234
 #define CONNECT_PORT 4321
@@ -22,14 +23,30 @@
 #define NS_SELF "/proc/self/ns/net"
 #define SERVER_MAP_PATH "/sys/fs/bpf/tc/globals/server_map"
 
-static const struct timeval timeo_sec = { .tv_sec = 3 };
-static const size_t timeo_optlen = sizeof(timeo_sec);
 static int stop, duration;
 
 static bool
 configure_stack(void)
 {
+	char tc_version[128];
 	char tc_cmd[BUFSIZ];
+	char *prog;
+	FILE *tc;
+
+	/* Check whether tc is built with libbpf. */
+	tc = popen("tc -V", "r");
+	if (CHECK_FAIL(!tc))
+		return false;
+	if (CHECK_FAIL(!fgets(tc_version, sizeof(tc_version), tc))) {
+		pclose(tc);
+		return false;
+	}
+	if (strstr(tc_version, ", libbpf "))
+		prog = "test_sk_assign_libbpf.bpf.o";
+	else
+		prog = "test_sk_assign.bpf.o";
+	if (CHECK_FAIL(pclose(tc)))
+		return false;
 
 	/* Move to a new networking namespace */
 	if (CHECK_FAIL(unshare(CLONE_NEWNET)))
@@ -46,8 +63,8 @@ configure_stack(void)
 	/* Load qdisc, BPF program */
 	if (CHECK_FAIL(system("tc qdisc add dev lo clsact")))
 		return false;
-	sprintf(tc_cmd, "%s %s %s %s", "tc filter add dev lo ingress bpf",
-		       "direct-action object-file ./test_sk_assign.bpf.o",
+	sprintf(tc_cmd, "%s %s %s %s %s", "tc filter add dev lo ingress bpf",
+		       "direct-action object-file", prog,
 		       "section tc",
 		       (env.verbosity < VERBOSE_VERY) ? " 2>/dev/null" : "verbose");
 	if (CHECK(system(tc_cmd), "BPF load failed;",
@@ -57,52 +74,6 @@ configure_stack(void)
 	return true;
 }
 
-static int
-start_server(const struct sockaddr *addr, socklen_t len, int type)
-{
-	int fd;
-
-	fd = socket(addr->sa_family, type, 0);
-	if (CHECK_FAIL(fd == -1))
-		goto out;
-	if (CHECK_FAIL(setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &timeo_sec,
-				  timeo_optlen)))
-		goto close_out;
-	if (CHECK_FAIL(bind(fd, addr, len) == -1))
-		goto close_out;
-	if (type == SOCK_STREAM && CHECK_FAIL(listen(fd, 128) == -1))
-		goto close_out;
-
-	goto out;
-close_out:
-	close(fd);
-	fd = -1;
-out:
-	return fd;
-}
-
-static int
-connect_to_server(const struct sockaddr *addr, socklen_t len, int type)
-{
-	int fd = -1;
-
-	fd = socket(addr->sa_family, type, 0);
-	if (CHECK_FAIL(fd == -1))
-		goto out;
-	if (CHECK_FAIL(setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, &timeo_sec,
-				  timeo_optlen)))
-		goto close_out;
-	if (CHECK_FAIL(connect(fd, addr, len)))
-		goto close_out;
-
-	goto out;
-close_out:
-	close(fd);
-	fd = -1;
-out:
-	return fd;
-}
-
 static in_port_t
 get_port(int fd)
 {
@@ -129,15 +100,12 @@ get_port(int fd)
 static ssize_t
 rcv_msg(int srv_client, int type)
 {
-	struct sockaddr_storage ss;
 	char buf[BUFSIZ];
-	socklen_t slen;
 
 	if (type == SOCK_STREAM)
 		return read(srv_client, &buf, sizeof(buf));
 	else
-		return recvfrom(srv_client, &buf, sizeof(buf), 0,
-				(struct sockaddr *)&ss, &slen);
+		return recvfrom(srv_client, &buf, sizeof(buf), 0, NULL, NULL);
 }
 
 static int
@@ -148,7 +116,7 @@ run_test(int server_fd, const struct sockaddr *addr, socklen_t len, int type)
 	in_port_t port;
 	int ret = 1;
 
-	client = connect_to_server(addr, len, type);
+	client = connect_to_addr(type, (struct sockaddr_storage *)addr, len, NULL);
 	if (client == -1) {
 		perror("Cannot connect to server");
 		goto out;
@@ -297,7 +265,9 @@ void test_sk_assign(void)
 			continue;
 		prepare_addr(test->addr, test->family, BIND_PORT, false);
 		addr = (const struct sockaddr *)test->addr;
-		server = start_server(addr, test->len, test->type);
+		server = start_server_addr(test->type,
+					   (const struct sockaddr_storage *)addr,
+					   test->len, NULL);
 		if (server == -1)
 			goto close;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/sk_bypass_prot_mem.c b/tools/testing/selftests/bpf/prog_tests/sk_bypass_prot_mem.c
new file mode 100644
index 000000000000..e4940583924b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sk_bypass_prot_mem.c
@@ -0,0 +1,292 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright 2025 Google LLC */
+
+#include <test_progs.h>
+#include "sk_bypass_prot_mem.skel.h"
+#include "network_helpers.h"
+
+#define NR_PAGES	32
+#define NR_SOCKETS	2
+#define BUF_TOTAL	(NR_PAGES * 4096 / NR_SOCKETS)
+#define BUF_SINGLE	1024
+#define NR_SEND		(BUF_TOTAL / BUF_SINGLE)
+
+struct test_case {
+	char name[8];
+	int family;
+	int type;
+	int (*create_sockets)(struct test_case *test_case, int sk[], int len);
+	long (*get_memory_allocated)(struct test_case *test_case, struct sk_bypass_prot_mem *skel);
+};
+
+static int tcp_create_sockets(struct test_case *test_case, int sk[], int len)
+{
+	int server, i, err = 0;
+
+	server = start_server(test_case->family, test_case->type, NULL, 0, 0);
+	if (!ASSERT_GE(server, 0, "start_server_str"))
+		return server;
+
+	/* Keep for-loop so we can change NR_SOCKETS easily. */
+	for (i = 0; i < len; i += 2) {
+		sk[i] = connect_to_fd(server, 0);
+		if (sk[i] < 0) {
+			ASSERT_GE(sk[i], 0, "connect_to_fd");
+			err = sk[i];
+			break;
+		}
+
+		sk[i + 1] = accept(server, NULL, NULL);
+		if (sk[i + 1] < 0) {
+			ASSERT_GE(sk[i + 1], 0, "accept");
+			err = sk[i + 1];
+			break;
+		}
+	}
+
+	close(server);
+
+	return err;
+}
+
+static int udp_create_sockets(struct test_case *test_case, int sk[], int len)
+{
+	int i, j, err, rcvbuf = BUF_TOTAL;
+
+	/* Keep for-loop so we can change NR_SOCKETS easily. */
+	for (i = 0; i < len; i += 2) {
+		sk[i] = start_server(test_case->family, test_case->type, NULL, 0, 0);
+		if (sk[i] < 0) {
+			ASSERT_GE(sk[i], 0, "start_server");
+			return sk[i];
+		}
+
+		sk[i + 1] = connect_to_fd(sk[i], 0);
+		if (sk[i + 1] < 0) {
+			ASSERT_GE(sk[i + 1], 0, "connect_to_fd");
+			return sk[i + 1];
+		}
+
+		err = connect_fd_to_fd(sk[i], sk[i + 1], 0);
+		if (err) {
+			ASSERT_EQ(err, 0, "connect_fd_to_fd");
+			return err;
+		}
+
+		for (j = 0; j < 2; j++) {
+			err = setsockopt(sk[i + j], SOL_SOCKET, SO_RCVBUF, &rcvbuf, sizeof(int));
+			if (err) {
+				ASSERT_EQ(err, 0, "setsockopt(SO_RCVBUF)");
+				return err;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static long get_memory_allocated(struct test_case *test_case,
+				 bool *activated, long *memory_allocated)
+{
+	int sk;
+
+	*activated = true;
+
+	/* AF_INET and AF_INET6 share the same memory_allocated.
+	 * tcp_init_sock() is called by AF_INET and AF_INET6,
+	 * but udp_lib_init_sock() is inline.
+	 */
+	sk = socket(AF_INET, test_case->type, 0);
+	if (!ASSERT_GE(sk, 0, "get_memory_allocated"))
+		return -1;
+
+	close(sk);
+
+	return *memory_allocated;
+}
+
+static long tcp_get_memory_allocated(struct test_case *test_case, struct sk_bypass_prot_mem *skel)
+{
+	return get_memory_allocated(test_case,
+				    &skel->bss->tcp_activated,
+				    &skel->bss->tcp_memory_allocated);
+}
+
+static long udp_get_memory_allocated(struct test_case *test_case, struct sk_bypass_prot_mem *skel)
+{
+	return get_memory_allocated(test_case,
+				    &skel->bss->udp_activated,
+				    &skel->bss->udp_memory_allocated);
+}
+
+static int check_bypass(struct test_case *test_case,
+			struct sk_bypass_prot_mem *skel, bool bypass)
+{
+	char buf[BUF_SINGLE] = {};
+	long memory_allocated[2];
+	int sk[NR_SOCKETS];
+	int err, i, j;
+
+	for (i = 0; i < ARRAY_SIZE(sk); i++)
+		sk[i] = -1;
+
+	err = test_case->create_sockets(test_case, sk, ARRAY_SIZE(sk));
+	if (err)
+		goto close;
+
+	memory_allocated[0] = test_case->get_memory_allocated(test_case, skel);
+
+	/* allocate pages >= NR_PAGES */
+	for (i = 0; i < ARRAY_SIZE(sk); i++) {
+		for (j = 0; j < NR_SEND; j++) {
+			int bytes = send(sk[i], buf, sizeof(buf), 0);
+
+			/* Avoid too noisy logs when something failed. */
+			if (bytes != sizeof(buf)) {
+				ASSERT_EQ(bytes, sizeof(buf), "send");
+				if (bytes < 0) {
+					err = bytes;
+					goto drain;
+				}
+			}
+		}
+	}
+
+	memory_allocated[1] = test_case->get_memory_allocated(test_case, skel);
+
+	if (bypass)
+		ASSERT_LE(memory_allocated[1], memory_allocated[0] + 10, "bypass");
+	else
+		ASSERT_GT(memory_allocated[1], memory_allocated[0] + NR_PAGES, "no bypass");
+
+drain:
+	if (test_case->type == SOCK_DGRAM) {
+		/* UDP starts purging sk->sk_receive_queue after one RCU
+		 * grace period, then udp_memory_allocated goes down,
+		 * so drain the queue before close().
+		 */
+		for (i = 0; i < ARRAY_SIZE(sk); i++) {
+			for (j = 0; j < NR_SEND; j++) {
+				int bytes = recv(sk[i], buf, 1, MSG_DONTWAIT | MSG_TRUNC);
+
+				if (bytes == sizeof(buf))
+					continue;
+				if (bytes != -1 || errno != EAGAIN)
+					PRINT_FAIL("bytes: %d, errno: %s\n", bytes, strerror(errno));
+				break;
+			}
+		}
+	}
+
+close:
+	for (i = 0; i < ARRAY_SIZE(sk); i++) {
+		if (sk[i] < 0)
+			break;
+
+		close(sk[i]);
+	}
+
+	return err;
+}
+
+static void run_test(struct test_case *test_case)
+{
+	struct sk_bypass_prot_mem *skel;
+	struct nstoken *nstoken;
+	int cgroup, err;
+
+	skel = sk_bypass_prot_mem__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	skel->bss->nr_cpus = libbpf_num_possible_cpus();
+
+	err = sk_bypass_prot_mem__attach(skel);
+	if (!ASSERT_OK(err, "attach"))
+		goto destroy_skel;
+
+	cgroup = test__join_cgroup("/sk_bypass_prot_mem");
+	if (!ASSERT_GE(cgroup, 0, "join_cgroup"))
+		goto destroy_skel;
+
+	err = make_netns("sk_bypass_prot_mem");
+	if (!ASSERT_EQ(err, 0, "make_netns"))
+		goto close_cgroup;
+
+	nstoken = open_netns("sk_bypass_prot_mem");
+	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+		goto remove_netns;
+
+	err = check_bypass(test_case, skel, false);
+	if (!ASSERT_EQ(err, 0, "test_bypass(false)"))
+		goto close_netns;
+
+	err = write_sysctl("/proc/sys/net/core/bypass_prot_mem", "1");
+	if (!ASSERT_EQ(err, 0, "write_sysctl(1)"))
+		goto close_netns;
+
+	err = check_bypass(test_case, skel, true);
+	if (!ASSERT_EQ(err, 0, "test_bypass(true by sysctl)"))
+		goto close_netns;
+
+	err = write_sysctl("/proc/sys/net/core/bypass_prot_mem", "0");
+	if (!ASSERT_EQ(err, 0, "write_sysctl(0)"))
+		goto close_netns;
+
+	skel->links.sock_create = bpf_program__attach_cgroup(skel->progs.sock_create, cgroup);
+	if (!ASSERT_OK_PTR(skel->links.sock_create, "attach_cgroup(sock_create)"))
+		goto close_netns;
+
+	err = check_bypass(test_case, skel, true);
+	ASSERT_EQ(err, 0, "test_bypass(true by bpf)");
+
+close_netns:
+	close_netns(nstoken);
+remove_netns:
+	remove_netns("sk_bypass_prot_mem");
+close_cgroup:
+	close(cgroup);
+destroy_skel:
+	sk_bypass_prot_mem__destroy(skel);
+}
+
+static struct test_case test_cases[] = {
+	{
+		.name = "TCP  ",
+		.family = AF_INET,
+		.type = SOCK_STREAM,
+		.create_sockets = tcp_create_sockets,
+		.get_memory_allocated = tcp_get_memory_allocated,
+	},
+	{
+		.name = "UDP  ",
+		.family = AF_INET,
+		.type = SOCK_DGRAM,
+		.create_sockets = udp_create_sockets,
+		.get_memory_allocated = udp_get_memory_allocated,
+	},
+	{
+		.name = "TCPv6",
+		.family = AF_INET6,
+		.type = SOCK_STREAM,
+		.create_sockets = tcp_create_sockets,
+		.get_memory_allocated = tcp_get_memory_allocated,
+	},
+	{
+		.name = "UDPv6",
+		.family = AF_INET6,
+		.type = SOCK_DGRAM,
+		.create_sockets = udp_create_sockets,
+		.get_memory_allocated = udp_get_memory_allocated,
+	},
+};
+
+void serial_test_sk_bypass_prot_mem(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
+		if (test__start_subtest(test_cases[i].name))
+			run_test(&test_cases[i]);
+	}
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
index 597d0467a926..023c31bde229 100644
--- a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
+++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
@@ -18,7 +18,6 @@
 #include <arpa/inet.h>
 #include <assert.h>
 #include <errno.h>
-#include <error.h>
 #include <fcntl.h>
 #include <sched.h>
 #include <stdio.h>
@@ -47,8 +46,6 @@
 #define INT_IP6		"fd00::2"
 #define INT_PORT	8008
 
-#define IO_TIMEOUT_SEC	3
-
 enum server {
 	SERVER_A = 0,
 	SERVER_B = 1,
@@ -77,6 +74,12 @@ struct test {
 	bool reuseport_has_conns; /* Add a connected socket to reuseport group */
 };
 
+struct cb_opts {
+	int family;
+	int sotype;
+	bool reuseport;
+};
+
 static __u32 duration;		/* for CHECK macro */
 
 static bool is_ipv6(const char *ip)
@@ -102,59 +105,14 @@ static int attach_reuseport(int sock_fd, struct bpf_program *reuseport_prog)
 	return 0;
 }
 
-static socklen_t inetaddr_len(const struct sockaddr_storage *addr)
-{
-	return (addr->ss_family == AF_INET ? sizeof(struct sockaddr_in) :
-		addr->ss_family == AF_INET6 ? sizeof(struct sockaddr_in6) : 0);
-}
-
-static int make_socket(int sotype, const char *ip, int port,
-		       struct sockaddr_storage *addr)
-{
-	struct timeval timeo = { .tv_sec = IO_TIMEOUT_SEC };
-	int err, family, fd;
-
-	family = is_ipv6(ip) ? AF_INET6 : AF_INET;
-	err = make_sockaddr(family, ip, port, addr, NULL);
-	if (CHECK(err, "make_address", "failed\n"))
-		return -1;
-
-	fd = socket(addr->ss_family, sotype, 0);
-	if (CHECK(fd < 0, "socket", "failed\n")) {
-		log_err("failed to make socket");
-		return -1;
-	}
-
-	err = setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, &timeo, sizeof(timeo));
-	if (CHECK(err, "setsockopt(SO_SNDTIMEO)", "failed\n")) {
-		log_err("failed to set SNDTIMEO");
-		close(fd);
-		return -1;
-	}
-
-	err = setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &timeo, sizeof(timeo));
-	if (CHECK(err, "setsockopt(SO_RCVTIMEO)", "failed\n")) {
-		log_err("failed to set RCVTIMEO");
-		close(fd);
-		return -1;
-	}
-
-	return fd;
-}
-
-static int make_server(int sotype, const char *ip, int port,
-		       struct bpf_program *reuseport_prog)
+static int setsockopts(int fd, void *opts)
 {
-	struct sockaddr_storage addr = {0};
+	struct cb_opts *co = (struct cb_opts *)opts;
 	const int one = 1;
-	int err, fd = -1;
-
-	fd = make_socket(sotype, ip, port, &addr);
-	if (fd < 0)
-		return -1;
+	int err = 0;
 
 	/* Enabled for UDPv6 sockets for IPv4-mapped IPv6 to work. */
-	if (sotype == SOCK_DGRAM) {
+	if (co->sotype == SOCK_DGRAM) {
 		err = setsockopt(fd, SOL_IP, IP_RECVORIGDSTADDR, &one,
 				 sizeof(one));
 		if (CHECK(err, "setsockopt(IP_RECVORIGDSTADDR)", "failed\n")) {
@@ -163,7 +121,7 @@ static int make_server(int sotype, const char *ip, int port,
 		}
 	}
 
-	if (sotype == SOCK_DGRAM && addr.ss_family == AF_INET6) {
+	if (co->sotype == SOCK_DGRAM && co->family == AF_INET6) {
 		err = setsockopt(fd, SOL_IPV6, IPV6_RECVORIGDSTADDR, &one,
 				 sizeof(one));
 		if (CHECK(err, "setsockopt(IPV6_RECVORIGDSTADDR)", "failed\n")) {
@@ -172,7 +130,7 @@ static int make_server(int sotype, const char *ip, int port,
 		}
 	}
 
-	if (sotype == SOCK_STREAM) {
+	if (co->sotype == SOCK_STREAM) {
 		err = setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &one,
 				 sizeof(one));
 		if (CHECK(err, "setsockopt(SO_REUSEADDR)", "failed\n")) {
@@ -181,7 +139,7 @@ static int make_server(int sotype, const char *ip, int port,
 		}
 	}
 
-	if (reuseport_prog) {
+	if (co->reuseport) {
 		err = setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &one,
 				 sizeof(one));
 		if (CHECK(err, "setsockopt(SO_REUSEPORT)", "failed\n")) {
@@ -190,19 +148,28 @@ static int make_server(int sotype, const char *ip, int port,
 		}
 	}
 
-	err = bind(fd, (void *)&addr, inetaddr_len(&addr));
-	if (CHECK(err, "bind", "failed\n")) {
-		log_err("failed to bind listen socket");
-		goto fail;
-	}
+fail:
+	return err;
+}
 
-	if (sotype == SOCK_STREAM) {
-		err = listen(fd, SOMAXCONN);
-		if (CHECK(err, "make_server", "listen")) {
-			log_err("failed to listen on port %d", port);
-			goto fail;
-		}
-	}
+static int make_server(int sotype, const char *ip, int port,
+		       struct bpf_program *reuseport_prog)
+{
+	struct cb_opts cb_opts = {
+		.family = is_ipv6(ip) ? AF_INET6 : AF_INET,
+		.sotype = sotype,
+		.reuseport = reuseport_prog,
+	};
+	struct network_helper_opts opts = {
+		.backlog	= SOMAXCONN,
+		.post_socket_cb = setsockopts,
+		.cb_opts	= &cb_opts,
+	};
+	int err, fd;
+
+	fd = start_server_str(cb_opts.family, sotype, ip, port, &opts);
+	if (!ASSERT_OK_FD(fd, "start_server_str"))
+		return -1;
 
 	/* Late attach reuseport prog so we can have one init path */
 	if (reuseport_prog) {
@@ -219,27 +186,6 @@ fail:
 	return -1;
 }
 
-static int make_client(int sotype, const char *ip, int port)
-{
-	struct sockaddr_storage addr = {0};
-	int err, fd;
-
-	fd = make_socket(sotype, ip, port, &addr);
-	if (fd < 0)
-		return -1;
-
-	err = connect(fd, (void *)&addr, inetaddr_len(&addr));
-	if (CHECK(err, "make_client", "connect")) {
-		log_err("failed to connect client socket");
-		goto fail;
-	}
-
-	return fd;
-fail:
-	close(fd);
-	return -1;
-}
-
 static __u64 socket_cookie(int fd)
 {
 	__u64 cookie;
@@ -406,18 +352,12 @@ static int udp_recv_send(int server_fd)
 	}
 
 	/* Reply from original destination address. */
-	fd = socket(dst_addr->ss_family, SOCK_DGRAM, 0);
-	if (CHECK(fd < 0, "socket", "failed\n")) {
+	fd = start_server_addr(SOCK_DGRAM, dst_addr, sizeof(*dst_addr), NULL);
+	if (!ASSERT_OK_FD(fd, "start_server_addr")) {
 		log_err("failed to create tx socket");
 		return -1;
 	}
 
-	ret = bind(fd, (struct sockaddr *)dst_addr, sizeof(*dst_addr));
-	if (CHECK(ret, "bind", "failed\n")) {
-		log_err("failed to bind tx socket");
-		goto out;
-	}
-
 	msg.msg_control = NULL;
 	msg.msg_controllen = 0;
 	n = sendmsg(fd, &msg, 0);
@@ -629,9 +569,6 @@ static void run_lookup_prog(const struct test *t)
 	 * BPF socket lookup.
 	 */
 	if (t->reuseport_has_conns) {
-		struct sockaddr_storage addr = {};
-		socklen_t len = sizeof(addr);
-
 		/* Add an extra socket to reuseport group */
 		reuse_conn_fd = make_server(t->sotype, t->listen_at.ip,
 					    t->listen_at.port,
@@ -639,17 +576,15 @@ static void run_lookup_prog(const struct test *t)
 		if (reuse_conn_fd < 0)
 			goto close;
 
-		/* Connect the extra socket to itself */
-		err = getsockname(reuse_conn_fd, (void *)&addr, &len);
-		if (CHECK(err, "getsockname", "errno %d\n", errno))
-			goto close;
-		err = connect(reuse_conn_fd, (void *)&addr, len);
-		if (CHECK(err, "connect", "errno %d\n", errno))
+		 /* Connect the extra socket to itself */
+		err = connect_fd_to_fd(reuse_conn_fd, reuse_conn_fd, 0);
+		if (!ASSERT_OK(err, "connect_fd_to_fd"))
 			goto close;
 	}
 
-	client_fd = make_client(t->sotype, t->connect_to.ip, t->connect_to.port);
-	if (client_fd < 0)
+	client_fd = connect_to_addr_str(is_ipv6(t->connect_to.ip) ? AF_INET6 : AF_INET,
+					t->sotype, t->connect_to.ip, t->connect_to.port, NULL);
+	if (!ASSERT_OK_FD(client_fd, "connect_to_addr_str"))
 		goto close;
 
 	if (t->sotype == SOCK_STREAM)
@@ -864,9 +799,11 @@ static void test_redirect_lookup(struct test_sk_lookup *skel)
 
 static void drop_on_lookup(const struct test *t)
 {
+	int family = is_ipv6(t->connect_to.ip) ? AF_INET6 : AF_INET;
 	struct sockaddr_storage dst = {};
 	int client_fd, server_fd, err;
 	struct bpf_link *lookup_link;
+	socklen_t len;
 	ssize_t n;
 
 	lookup_link = attach_lookup_prog(t->lookup_prog);
@@ -878,12 +815,14 @@ static void drop_on_lookup(const struct test *t)
 	if (server_fd < 0)
 		goto detach;
 
-	client_fd = make_socket(t->sotype, t->connect_to.ip,
-				t->connect_to.port, &dst);
-	if (client_fd < 0)
+	client_fd = client_socket(family, t->sotype, NULL);
+	if (!ASSERT_OK_FD(client_fd, "client_socket"))
 		goto close_srv;
 
-	err = connect(client_fd, (void *)&dst, inetaddr_len(&dst));
+	err = make_sockaddr(family, t->connect_to.ip, t->connect_to.port, &dst, &len);
+	if (!ASSERT_OK(err, "make_sockaddr"))
+		goto close_all;
+	err = connect(client_fd, (void *)&dst, len);
 	if (t->sotype == SOCK_DGRAM) {
 		err = send_byte(client_fd);
 		if (err)
@@ -978,9 +917,11 @@ static void test_drop_on_lookup(struct test_sk_lookup *skel)
 
 static void drop_on_reuseport(const struct test *t)
 {
+	int family = is_ipv6(t->connect_to.ip) ? AF_INET6 : AF_INET;
 	struct sockaddr_storage dst = { 0 };
 	int client, server1, server2, err;
 	struct bpf_link *lookup_link;
+	socklen_t len;
 	ssize_t n;
 
 	lookup_link = attach_lookup_prog(t->lookup_prog);
@@ -994,7 +935,7 @@ static void drop_on_reuseport(const struct test *t)
 
 	err = update_lookup_map(t->sock_map, SERVER_A, server1);
 	if (err)
-		goto detach;
+		goto close_srv1;
 
 	/* second server on destination address we should never reach */
 	server2 = make_server(t->sotype, t->connect_to.ip, t->connect_to.port,
@@ -1002,12 +943,14 @@ static void drop_on_reuseport(const struct test *t)
 	if (server2 < 0)
 		goto close_srv1;
 
-	client = make_socket(t->sotype, t->connect_to.ip,
-			     t->connect_to.port, &dst);
-	if (client < 0)
+	client = client_socket(family, t->sotype, NULL);
+	if (!ASSERT_OK_FD(client, "client_socket"))
 		goto close_srv2;
 
-	err = connect(client, (void *)&dst, inetaddr_len(&dst));
+	err = make_sockaddr(family, t->connect_to.ip, t->connect_to.port, &dst, &len);
+	if (!ASSERT_OK(err, "make_sockaddr"))
+		goto close_all;
+	err = connect(client, (void *)&dst, len);
 	if (t->sotype == SOCK_DGRAM) {
 		err = send_byte(client);
 		if (err)
@@ -1154,8 +1097,8 @@ static void run_sk_assign_connected(struct test_sk_lookup *skel,
 	if (server_fd < 0)
 		return;
 
-	connected_fd = make_client(sotype, EXT_IP4, EXT_PORT);
-	if (connected_fd < 0)
+	connected_fd = connect_to_addr_str(AF_INET, sotype, EXT_IP4, EXT_PORT, NULL);
+	if (!ASSERT_OK_FD(connected_fd, "connect_to_addr_str"))
 		goto out_close_server;
 
 	/* Put a connected socket in redirect map */
@@ -1168,8 +1111,8 @@ static void run_sk_assign_connected(struct test_sk_lookup *skel,
 		goto out_close_connected;
 
 	/* Try to redirect TCP SYN / UDP packet to a connected socket */
-	client_fd = make_client(sotype, EXT_IP4, EXT_PORT);
-	if (client_fd < 0)
+	client_fd = connect_to_addr_str(AF_INET, sotype, EXT_IP4, EXT_PORT, NULL);
+	if (!ASSERT_OK_FD(client_fd, "connect_to_addr_str"))
 		goto out_unlink_prog;
 	if (sotype == SOCK_DGRAM) {
 		send_byte(client_fd);
@@ -1221,6 +1164,7 @@ static void run_multi_prog_lookup(const struct test_multi_prog *t)
 	int map_fd, server_fd, client_fd;
 	struct bpf_link *link1, *link2;
 	int prog_idx, done, err;
+	socklen_t len;
 
 	map_fd = bpf_map__fd(t->run_map);
 
@@ -1250,11 +1194,14 @@ static void run_multi_prog_lookup(const struct test_multi_prog *t)
 	if (err)
 		goto out_close_server;
 
-	client_fd = make_socket(SOCK_STREAM, EXT_IP4, EXT_PORT, &dst);
-	if (client_fd < 0)
+	client_fd = client_socket(AF_INET, SOCK_STREAM, NULL);
+	if (!ASSERT_OK_FD(client_fd, "client_socket"))
 		goto out_close_server;
 
-	err = connect(client_fd, (void *)&dst, inetaddr_len(&dst));
+	err = make_sockaddr(AF_INET, EXT_IP4, EXT_PORT, &dst, &len);
+	if (!ASSERT_OK(err, "make_sockaddr"))
+		goto out_close_client;
+	err = connect(client_fd, (void *)&dst, len);
 	if (CHECK(err && !t->expect_errno, "connect",
 		  "unexpected error %d\n", errno))
 		goto out_close_client;
diff --git a/tools/testing/selftests/bpf/prog_tests/sk_storage_omem_uncharge.c b/tools/testing/selftests/bpf/prog_tests/sk_storage_omem_uncharge.c
new file mode 100644
index 000000000000..f35852d245e3
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sk_storage_omem_uncharge.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Facebook */
+#include <test_progs.h>
+#include <bpf/libbpf.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include "sk_storage_omem_uncharge.skel.h"
+
+void test_sk_storage_omem_uncharge(void)
+{
+	struct sk_storage_omem_uncharge *skel;
+	int sk_fd = -1, map_fd, err, value;
+	socklen_t optlen;
+
+	skel = sk_storage_omem_uncharge__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel open_and_load"))
+		return;
+	map_fd = bpf_map__fd(skel->maps.sk_storage);
+
+	/* A standalone socket not binding to addr:port,
+	 * so nentns is not needed.
+	 */
+	sk_fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (!ASSERT_GE(sk_fd, 0, "socket"))
+		goto done;
+
+	optlen = sizeof(skel->bss->cookie);
+	err = getsockopt(sk_fd, SOL_SOCKET, SO_COOKIE, &skel->bss->cookie, &optlen);
+	if (!ASSERT_OK(err, "getsockopt(SO_COOKIE)"))
+		goto done;
+
+	value = 0;
+	err = bpf_map_update_elem(map_fd, &sk_fd, &value, 0);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(value=0)"))
+		goto done;
+
+	value = 0xdeadbeef;
+	err = bpf_map_update_elem(map_fd, &sk_fd, &value, 0);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(value=0xdeadbeef)"))
+		goto done;
+
+	err = sk_storage_omem_uncharge__attach(skel);
+	if (!ASSERT_OK(err, "attach"))
+		goto done;
+
+	close(sk_fd);
+	sk_fd = -1;
+
+	ASSERT_EQ(skel->bss->cookie_found, 2, "cookie_found");
+	ASSERT_EQ(skel->bss->omem, 0, "omem");
+
+done:
+	sk_storage_omem_uncharge__destroy(skel);
+	if (sk_fd != -1)
+		close(sk_fd);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/snprintf.c b/tools/testing/selftests/bpf/prog_tests/snprintf.c
index 4be6fdb78c6a..594441acb707 100644
--- a/tools/testing/selftests/bpf/prog_tests/snprintf.c
+++ b/tools/testing/selftests/bpf/prog_tests/snprintf.c
@@ -116,6 +116,8 @@ static void test_snprintf_negative(void)
 	ASSERT_ERR(load_single_snprintf("%llc"), "invalid specifier 7");
 	ASSERT_ERR(load_single_snprintf("\x80"), "non ascii character");
 	ASSERT_ERR(load_single_snprintf("\x1"), "non printable character");
+	ASSERT_ERR(load_single_snprintf("%p%"), "invalid specifier 8");
+	ASSERT_ERR(load_single_snprintf("%s%"), "invalid specifier 9");
 }
 
 void test_snprintf(void)
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_addr.c b/tools/testing/selftests/bpf/prog_tests/sock_addr.c
new file mode 100644
index 000000000000..b2efabbed220
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sock_addr.c
@@ -0,0 +1,2660 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <sys/un.h>
+
+#include "test_progs.h"
+
+#include "sock_addr_kern.skel.h"
+#include "bind4_prog.skel.h"
+#include "bind6_prog.skel.h"
+#include "connect_unix_prog.skel.h"
+#include "connect4_prog.skel.h"
+#include "connect6_prog.skel.h"
+#include "sendmsg4_prog.skel.h"
+#include "sendmsg6_prog.skel.h"
+#include "recvmsg4_prog.skel.h"
+#include "recvmsg6_prog.skel.h"
+#include "sendmsg_unix_prog.skel.h"
+#include "recvmsg_unix_prog.skel.h"
+#include "getsockname4_prog.skel.h"
+#include "getsockname6_prog.skel.h"
+#include "getsockname_unix_prog.skel.h"
+#include "getpeername4_prog.skel.h"
+#include "getpeername6_prog.skel.h"
+#include "getpeername_unix_prog.skel.h"
+#include "network_helpers.h"
+
+#define TEST_NS                 "sock_addr"
+#define TEST_IF_PREFIX          "test_sock_addr"
+#define TEST_IPV4               "127.0.0.4"
+#define TEST_IPV6               "::6"
+
+#define SERV4_IP                "192.168.1.254"
+#define SERV4_REWRITE_IP        "127.0.0.1"
+#define SRC4_IP                 "172.16.0.1"
+#define SRC4_REWRITE_IP         TEST_IPV4
+#define SERV4_PORT              4040
+#define SERV4_REWRITE_PORT      4444
+
+#define SERV6_IP                "face:b00c:1234:5678::abcd"
+#define SERV6_REWRITE_IP        "::1"
+#define SERV6_V4MAPPED_IP       "::ffff:192.168.0.4"
+#define SRC6_IP                 "::1"
+#define SRC6_REWRITE_IP         TEST_IPV6
+#define WILDCARD6_IP            "::"
+#define SERV6_PORT              6060
+#define SERV6_REWRITE_PORT      6666
+
+#define SERVUN_ADDRESS         "bpf_cgroup_unix_test"
+#define SERVUN_REWRITE_ADDRESS "bpf_cgroup_unix_test_rewrite"
+#define SRCUN_ADDRESS          "bpf_cgroup_unix_test_src"
+
+#define save_errno_do(op) ({ int __save = errno; op; errno = __save; })
+
+enum sock_addr_test_type {
+	SOCK_ADDR_TEST_BIND,
+	SOCK_ADDR_TEST_CONNECT,
+	SOCK_ADDR_TEST_SENDMSG,
+	SOCK_ADDR_TEST_RECVMSG,
+	SOCK_ADDR_TEST_GETSOCKNAME,
+	SOCK_ADDR_TEST_GETPEERNAME,
+};
+
+typedef void *(*load_fn)(int cgroup_fd,
+			 enum bpf_attach_type attach_type,
+			 bool expect_reject);
+typedef void (*destroy_fn)(void *skel);
+
+static int cmp_addr(const struct sockaddr_storage *addr1, socklen_t addr1_len,
+		    const struct sockaddr_storage *addr2, socklen_t addr2_len,
+		    bool cmp_port);
+
+struct init_sock_args {
+	int af;
+	int type;
+};
+
+struct addr_args {
+	char addr[sizeof(struct sockaddr_storage)];
+	int addrlen;
+};
+
+struct sendmsg_args {
+	struct addr_args addr;
+	char msg[10];
+	int msglen;
+};
+
+static struct sock_addr_kern *skel;
+
+static int run_bpf_prog(const char *prog_name, void *ctx, int ctx_size)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	struct bpf_program *prog;
+	int prog_fd, err;
+
+	topts.ctx_in = ctx;
+	topts.ctx_size_in = ctx_size;
+
+	prog = bpf_object__find_program_by_name(skel->obj, prog_name);
+	if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
+		goto err;
+
+	prog_fd = bpf_program__fd(prog);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	if (!ASSERT_OK(err, prog_name))
+		goto err;
+
+	err = topts.retval;
+	errno = -topts.retval;
+	goto out;
+err:
+	err = -1;
+out:
+	return err;
+}
+
+static int kernel_init_sock(int af, int type, int protocol)
+{
+	struct init_sock_args args = {
+		.af = af,
+		.type = type,
+	};
+
+	return run_bpf_prog("init_sock", &args, sizeof(args));
+}
+
+static int kernel_close_sock(int fd)
+{
+	return run_bpf_prog("close_sock", NULL, 0);
+}
+
+static int sock_addr_op(const char *name, struct sockaddr *addr,
+			socklen_t *addrlen, bool expect_change)
+{
+	struct addr_args args;
+	int err;
+
+	if (addrlen)
+		args.addrlen = *addrlen;
+
+	if (addr)
+		memcpy(&args.addr, addr, *addrlen);
+
+	err = run_bpf_prog(name, &args, sizeof(args));
+
+	if (!expect_change && addr)
+		if (!ASSERT_EQ(cmp_addr((struct sockaddr_storage *)addr,
+					*addrlen,
+					(struct sockaddr_storage *)&args.addr,
+					args.addrlen, 1),
+			       0, "address_param_modified"))
+			return -1;
+
+	if (addrlen)
+		*addrlen = args.addrlen;
+
+	if (addr)
+		memcpy(addr, &args.addr, *addrlen);
+
+	return err;
+}
+
+static int send_msg_op(const char *name, struct sockaddr *addr,
+		       socklen_t addrlen, const char *msg, int msglen)
+{
+	struct sendmsg_args args;
+	int err;
+
+	memset(&args, 0, sizeof(args));
+	memcpy(&args.addr.addr, addr, addrlen);
+	args.addr.addrlen = addrlen;
+	memcpy(args.msg, msg, msglen);
+	args.msglen = msglen;
+
+	err = run_bpf_prog(name, &args, sizeof(args));
+
+	if (!ASSERT_EQ(cmp_addr((struct sockaddr_storage *)addr,
+				addrlen,
+				(struct sockaddr_storage *)&args.addr.addr,
+				args.addr.addrlen, 1),
+		       0, "address_param_modified"))
+		return -1;
+
+	return err;
+}
+
+static int kernel_connect(struct sockaddr *addr, socklen_t addrlen)
+{
+	return sock_addr_op("kernel_connect", addr, &addrlen, false);
+}
+
+static int kernel_bind(int fd, struct sockaddr *addr, socklen_t addrlen)
+{
+	return sock_addr_op("kernel_bind", addr, &addrlen, false);
+}
+
+static int kernel_listen(void)
+{
+	return sock_addr_op("kernel_listen", NULL, NULL, false);
+}
+
+static int kernel_sendmsg(int fd, struct sockaddr *addr, socklen_t addrlen,
+			  char *msg, int msglen)
+{
+	return send_msg_op("kernel_sendmsg", addr, addrlen, msg, msglen);
+}
+
+static int sock_sendmsg(int fd, struct sockaddr *addr, socklen_t addrlen,
+			char *msg, int msglen)
+{
+	return send_msg_op("sock_sendmsg", addr, addrlen, msg, msglen);
+}
+
+static int kernel_getsockname(int fd, struct sockaddr *addr, socklen_t *addrlen)
+{
+	return sock_addr_op("kernel_getsockname", addr, addrlen, true);
+}
+
+static int kernel_getpeername(int fd, struct sockaddr *addr, socklen_t *addrlen)
+{
+	return sock_addr_op("kernel_getpeername", addr, addrlen, true);
+}
+
+int kernel_connect_to_addr(int type, const struct sockaddr_storage *addr, socklen_t addrlen,
+			   const struct network_helper_opts *opts)
+{
+	int err;
+
+	if (!ASSERT_OK(kernel_init_sock(addr->ss_family, type, 0),
+		       "kernel_init_sock"))
+		goto err;
+
+	if (kernel_connect((struct sockaddr *)addr, addrlen) < 0)
+		goto err;
+
+	/* Test code expects a "file descriptor" on success. */
+	err = 1;
+	goto out;
+err:
+	err = -1;
+	save_errno_do(ASSERT_OK(kernel_close_sock(0), "kernel_close_sock"));
+out:
+	return err;
+}
+
+int kernel_start_server(int family, int type, const char *addr_str, __u16 port,
+			int timeout_ms)
+{
+	struct sockaddr_storage addr;
+	socklen_t addrlen;
+	int err;
+
+	if (!ASSERT_OK(kernel_init_sock(family, type, 0), "kernel_init_sock"))
+		goto err;
+
+	if (make_sockaddr(family, addr_str, port, &addr, &addrlen))
+		goto err;
+
+	if (kernel_bind(0, (struct sockaddr *)&addr, addrlen) < 0)
+		goto err;
+
+	if (type == SOCK_STREAM) {
+		if (!ASSERT_OK(kernel_listen(), "kernel_listen"))
+			goto err;
+	}
+
+	/* Test code expects a "file descriptor" on success. */
+	err = 1;
+	goto out;
+err:
+	err = -1;
+	save_errno_do(ASSERT_OK(kernel_close_sock(0), "kernel_close_sock"));
+out:
+	return err;
+}
+
+struct sock_ops {
+	int (*connect_to_addr)(int type, const struct sockaddr_storage *addr,
+			       socklen_t addrlen,
+			       const struct network_helper_opts *opts);
+	int (*start_server)(int family, int type, const char *addr_str,
+			    __u16 port, int timeout_ms);
+	int (*socket)(int famil, int type, int protocol);
+	int (*bind)(int fd, struct sockaddr *addr, socklen_t addrlen);
+	int (*getsockname)(int fd, struct sockaddr *addr, socklen_t *addrlen);
+	int (*getpeername)(int fd, struct sockaddr *addr, socklen_t *addrlen);
+	int (*sendmsg)(int fd, struct sockaddr *addr, socklen_t addrlen,
+		       char *msg, int msglen);
+	int (*close)(int fd);
+};
+
+static int user_sendmsg(int fd, struct sockaddr *addr, socklen_t addrlen,
+			char *msg, int msglen)
+{
+	struct msghdr hdr;
+	struct iovec iov;
+
+	memset(&iov, 0, sizeof(iov));
+	iov.iov_base = msg;
+	iov.iov_len = msglen;
+
+	memset(&hdr, 0, sizeof(hdr));
+	hdr.msg_name = (void *)addr;
+	hdr.msg_namelen = addrlen;
+	hdr.msg_iov = &iov;
+	hdr.msg_iovlen = 1;
+
+	return sendmsg(fd, &hdr, 0);
+}
+
+static int user_bind(int fd, struct sockaddr *addr, socklen_t addrlen)
+{
+	return bind(fd, (const struct sockaddr *)addr, addrlen);
+}
+
+struct sock_ops user_ops = {
+	.connect_to_addr = connect_to_addr,
+	.start_server = start_server,
+	.socket = socket,
+	.bind = user_bind,
+	.getsockname = getsockname,
+	.getpeername = getpeername,
+	.sendmsg = user_sendmsg,
+	.close = close,
+};
+
+struct sock_ops kern_ops_sock_sendmsg = {
+	.connect_to_addr = kernel_connect_to_addr,
+	.start_server = kernel_start_server,
+	.socket = kernel_init_sock,
+	.bind = kernel_bind,
+	.getsockname = kernel_getsockname,
+	.getpeername = kernel_getpeername,
+	.sendmsg = sock_sendmsg,
+	.close = kernel_close_sock,
+};
+
+struct sock_ops kern_ops_kernel_sendmsg = {
+	.connect_to_addr = kernel_connect_to_addr,
+	.start_server = kernel_start_server,
+	.socket = kernel_init_sock,
+	.bind = kernel_bind,
+	.getsockname = kernel_getsockname,
+	.getpeername = kernel_getpeername,
+	.sendmsg = kernel_sendmsg,
+	.close = kernel_close_sock,
+};
+
+struct sock_addr_test {
+	enum sock_addr_test_type type;
+	const char *name;
+	/* BPF prog properties */
+	load_fn loadfn;
+	destroy_fn destroyfn;
+	enum bpf_attach_type attach_type;
+	/* Socket operations */
+	struct sock_ops *ops;
+	/* Socket properties */
+	int socket_family;
+	int socket_type;
+	/* IP:port pairs for BPF prog to override */
+	const char *requested_addr;
+	unsigned short requested_port;
+	const char *expected_addr;
+	unsigned short expected_port;
+	const char *expected_src_addr;
+	/* Expected test result */
+	enum {
+		LOAD_REJECT,
+		ATTACH_REJECT,
+		SYSCALL_EPERM,
+		SYSCALL_ENOTSUPP,
+		SUCCESS,
+	} expected_result;
+};
+
+#define BPF_SKEL_FUNCS_RAW(skel_name, prog_name) \
+static void *prog_name##_load_raw(int cgroup_fd, \
+				  enum bpf_attach_type attach_type, \
+				  bool expect_reject) \
+{ \
+	struct skel_name *skel = skel_name##__open(); \
+	int prog_fd = -1; \
+	if (!ASSERT_OK_PTR(skel, "skel_open")) \
+		goto cleanup; \
+	if (!ASSERT_OK(skel_name##__load(skel), "load")) \
+		goto cleanup; \
+	prog_fd = bpf_program__fd(skel->progs.prog_name); \
+	if (!ASSERT_GT(prog_fd, 0, "prog_fd")) \
+		goto cleanup; \
+	if (bpf_prog_attach(prog_fd, cgroup_fd, attach_type, \
+			      BPF_F_ALLOW_OVERRIDE), "bpf_prog_attach") { \
+		ASSERT_TRUE(expect_reject, "unexpected rejection"); \
+		goto cleanup; \
+	} \
+	if (!ASSERT_FALSE(expect_reject, "expected rejection")) \
+		goto cleanup; \
+cleanup: \
+	if (prog_fd > 0) \
+		bpf_prog_detach(cgroup_fd, attach_type); \
+	skel_name##__destroy(skel); \
+	return NULL; \
+} \
+static void prog_name##_destroy_raw(void *progfd) \
+{ \
+	/* No-op. *_load_raw does all cleanup. */ \
+} \
+
+#define BPF_SKEL_FUNCS(skel_name, prog_name) \
+static void *prog_name##_load(int cgroup_fd, \
+			      enum bpf_attach_type attach_type, \
+			      bool expect_reject) \
+{ \
+	struct skel_name *skel = skel_name##__open(); \
+	if (!ASSERT_OK_PTR(skel, "skel_open")) \
+		goto cleanup; \
+	if (!ASSERT_OK(bpf_program__set_expected_attach_type(skel->progs.prog_name, \
+							     attach_type), \
+		       "set_expected_attach_type")) \
+		goto cleanup; \
+	if (skel_name##__load(skel)) { \
+		ASSERT_TRUE(expect_reject, "unexpected rejection"); \
+		goto cleanup; \
+	} \
+	if (!ASSERT_FALSE(expect_reject, "expected rejection")) \
+		goto cleanup; \
+	skel->links.prog_name = bpf_program__attach_cgroup( \
+		skel->progs.prog_name, cgroup_fd); \
+	if (!ASSERT_OK_PTR(skel->links.prog_name, "prog_attach")) \
+		goto cleanup; \
+	return skel; \
+cleanup: \
+	skel_name##__destroy(skel); \
+	return NULL; \
+} \
+static void prog_name##_destroy(void *skel) \
+{ \
+	skel_name##__destroy(skel); \
+}
+
+BPF_SKEL_FUNCS(bind4_prog, bind_v4_prog);
+BPF_SKEL_FUNCS_RAW(bind4_prog, bind_v4_prog);
+BPF_SKEL_FUNCS(bind4_prog, bind_v4_deny_prog);
+BPF_SKEL_FUNCS(bind6_prog, bind_v6_prog);
+BPF_SKEL_FUNCS_RAW(bind6_prog, bind_v6_prog);
+BPF_SKEL_FUNCS(bind6_prog, bind_v6_deny_prog);
+BPF_SKEL_FUNCS(connect4_prog, connect_v4_prog);
+BPF_SKEL_FUNCS_RAW(connect4_prog, connect_v4_prog);
+BPF_SKEL_FUNCS(connect4_prog, connect_v4_deny_prog);
+BPF_SKEL_FUNCS(connect6_prog, connect_v6_prog);
+BPF_SKEL_FUNCS_RAW(connect6_prog, connect_v6_prog);
+BPF_SKEL_FUNCS(connect6_prog, connect_v6_deny_prog);
+BPF_SKEL_FUNCS(connect_unix_prog, connect_unix_prog);
+BPF_SKEL_FUNCS_RAW(connect_unix_prog, connect_unix_prog);
+BPF_SKEL_FUNCS(connect_unix_prog, connect_unix_deny_prog);
+BPF_SKEL_FUNCS(sendmsg4_prog, sendmsg_v4_prog);
+BPF_SKEL_FUNCS_RAW(sendmsg4_prog, sendmsg_v4_prog);
+BPF_SKEL_FUNCS(sendmsg4_prog, sendmsg_v4_deny_prog);
+BPF_SKEL_FUNCS(sendmsg6_prog, sendmsg_v6_prog);
+BPF_SKEL_FUNCS_RAW(sendmsg6_prog, sendmsg_v6_prog);
+BPF_SKEL_FUNCS(sendmsg6_prog, sendmsg_v6_deny_prog);
+BPF_SKEL_FUNCS(sendmsg6_prog, sendmsg_v6_preserve_dst_prog);
+BPF_SKEL_FUNCS(sendmsg6_prog, sendmsg_v6_v4mapped_prog);
+BPF_SKEL_FUNCS(sendmsg6_prog, sendmsg_v6_wildcard_prog);
+BPF_SKEL_FUNCS(sendmsg_unix_prog, sendmsg_unix_prog);
+BPF_SKEL_FUNCS_RAW(sendmsg_unix_prog, sendmsg_unix_prog);
+BPF_SKEL_FUNCS(sendmsg_unix_prog, sendmsg_unix_deny_prog);
+BPF_SKEL_FUNCS(recvmsg4_prog, recvmsg4_prog);
+BPF_SKEL_FUNCS_RAW(recvmsg4_prog, recvmsg4_prog);
+BPF_SKEL_FUNCS(recvmsg6_prog, recvmsg6_prog);
+BPF_SKEL_FUNCS_RAW(recvmsg6_prog, recvmsg6_prog);
+BPF_SKEL_FUNCS(recvmsg_unix_prog, recvmsg_unix_prog);
+BPF_SKEL_FUNCS_RAW(recvmsg_unix_prog, recvmsg_unix_prog);
+BPF_SKEL_FUNCS(getsockname_unix_prog, getsockname_unix_prog);
+BPF_SKEL_FUNCS_RAW(getsockname_unix_prog, getsockname_unix_prog);
+BPF_SKEL_FUNCS(getsockname4_prog, getsockname_v4_prog);
+BPF_SKEL_FUNCS_RAW(getsockname4_prog, getsockname_v4_prog);
+BPF_SKEL_FUNCS(getsockname6_prog, getsockname_v6_prog);
+BPF_SKEL_FUNCS_RAW(getsockname6_prog, getsockname_v6_prog);
+BPF_SKEL_FUNCS(getpeername_unix_prog, getpeername_unix_prog);
+BPF_SKEL_FUNCS_RAW(getpeername_unix_prog, getpeername_unix_prog);
+BPF_SKEL_FUNCS(getpeername4_prog, getpeername_v4_prog);
+BPF_SKEL_FUNCS_RAW(getpeername4_prog, getpeername_v4_prog);
+BPF_SKEL_FUNCS(getpeername6_prog, getpeername_v6_prog);
+BPF_SKEL_FUNCS_RAW(getpeername6_prog, getpeername_v6_prog);
+
+static struct sock_addr_test tests[] = {
+	/* bind - system calls */
+	{
+		SOCK_ADDR_TEST_BIND,
+		"bind4: bind (stream)",
+		bind_v4_prog_load,
+		bind_v4_prog_destroy,
+		BPF_CGROUP_INET4_BIND,
+		&user_ops,
+		AF_INET,
+		SOCK_STREAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_BIND,
+		"bind4: bind deny (stream)",
+		bind_v4_deny_prog_load,
+		bind_v4_deny_prog_destroy,
+		BPF_CGROUP_INET4_BIND,
+		&user_ops,
+		AF_INET,
+		SOCK_STREAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		NULL,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_BIND,
+		"bind4: bind (dgram)",
+		bind_v4_prog_load,
+		bind_v4_prog_destroy,
+		BPF_CGROUP_INET4_BIND,
+		&user_ops,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_BIND,
+		"bind4: bind deny (dgram)",
+		bind_v4_deny_prog_load,
+		bind_v4_deny_prog_destroy,
+		BPF_CGROUP_INET4_BIND,
+		&user_ops,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		NULL,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_BIND,
+		"bind4: load prog with wrong expected attach type",
+		bind_v4_prog_load,
+		bind_v4_prog_destroy,
+		BPF_CGROUP_INET6_BIND,
+		&user_ops,
+		AF_INET,
+		SOCK_STREAM,
+		NULL,
+		0,
+		NULL,
+		0,
+		NULL,
+		LOAD_REJECT,
+	},
+	{
+		SOCK_ADDR_TEST_BIND,
+		"bind4: attach prog with wrong attach type",
+		bind_v4_prog_load_raw,
+		bind_v4_prog_destroy_raw,
+		BPF_CGROUP_INET6_BIND,
+		&user_ops,
+		AF_INET,
+		SOCK_STREAM,
+		NULL,
+		0,
+		NULL,
+		0,
+		NULL,
+		ATTACH_REJECT,
+	},
+	{
+		SOCK_ADDR_TEST_BIND,
+		"bind6: bind (stream)",
+		bind_v6_prog_load,
+		bind_v6_prog_destroy,
+		BPF_CGROUP_INET6_BIND,
+		&user_ops,
+		AF_INET6,
+		SOCK_STREAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_BIND,
+		"bind6: bind deny (stream)",
+		bind_v6_deny_prog_load,
+		bind_v6_deny_prog_destroy,
+		BPF_CGROUP_INET6_BIND,
+		&user_ops,
+		AF_INET6,
+		SOCK_STREAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		NULL,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_BIND,
+		"bind6: bind (dgram)",
+		bind_v6_prog_load,
+		bind_v6_prog_destroy,
+		BPF_CGROUP_INET6_BIND,
+		&user_ops,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_BIND,
+		"bind6: bind deny (dgram)",
+		bind_v6_deny_prog_load,
+		bind_v6_deny_prog_destroy,
+		BPF_CGROUP_INET6_BIND,
+		&user_ops,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		NULL,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_BIND,
+		"bind6: load prog with wrong expected attach type",
+		bind_v6_prog_load,
+		bind_v6_prog_destroy,
+		BPF_CGROUP_INET4_BIND,
+		&user_ops,
+		AF_INET6,
+		SOCK_STREAM,
+		NULL,
+		0,
+		NULL,
+		0,
+		NULL,
+		LOAD_REJECT,
+	},
+	{
+		SOCK_ADDR_TEST_BIND,
+		"bind6: attach prog with wrong attach type",
+		bind_v6_prog_load_raw,
+		bind_v6_prog_destroy_raw,
+		BPF_CGROUP_INET4_BIND,
+		&user_ops,
+		AF_INET,
+		SOCK_STREAM,
+		NULL,
+		0,
+		NULL,
+		0,
+		NULL,
+		ATTACH_REJECT,
+	},
+
+	/* bind - kernel calls */
+	{
+		SOCK_ADDR_TEST_BIND,
+		"bind4: kernel_bind (stream)",
+		bind_v4_prog_load,
+		bind_v4_prog_destroy,
+		BPF_CGROUP_INET4_BIND,
+		&kern_ops_sock_sendmsg,
+		AF_INET,
+		SOCK_STREAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_BIND,
+		"bind4: kernel_bind deny (stream)",
+		bind_v4_deny_prog_load,
+		bind_v4_deny_prog_destroy,
+		BPF_CGROUP_INET4_BIND,
+		&kern_ops_sock_sendmsg,
+		AF_INET,
+		SOCK_STREAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		NULL,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_BIND,
+		"bind4: kernel_bind (dgram)",
+		bind_v4_prog_load,
+		bind_v4_prog_destroy,
+		BPF_CGROUP_INET4_BIND,
+		&kern_ops_sock_sendmsg,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_BIND,
+		"bind4: kernel_bind deny (dgram)",
+		bind_v4_deny_prog_load,
+		bind_v4_deny_prog_destroy,
+		BPF_CGROUP_INET4_BIND,
+		&kern_ops_sock_sendmsg,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		NULL,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_BIND,
+		"bind6: kernel_bind (stream)",
+		bind_v6_prog_load,
+		bind_v6_prog_destroy,
+		BPF_CGROUP_INET6_BIND,
+		&kern_ops_sock_sendmsg,
+		AF_INET6,
+		SOCK_STREAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_BIND,
+		"bind6: kernel_bind deny (stream)",
+		bind_v6_deny_prog_load,
+		bind_v6_deny_prog_destroy,
+		BPF_CGROUP_INET6_BIND,
+		&kern_ops_sock_sendmsg,
+		AF_INET6,
+		SOCK_STREAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		NULL,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_BIND,
+		"bind6: kernel_bind (dgram)",
+		bind_v6_prog_load,
+		bind_v6_prog_destroy,
+		BPF_CGROUP_INET6_BIND,
+		&kern_ops_sock_sendmsg,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_BIND,
+		"bind6: kernel_bind deny (dgram)",
+		bind_v6_deny_prog_load,
+		bind_v6_deny_prog_destroy,
+		BPF_CGROUP_INET6_BIND,
+		&kern_ops_sock_sendmsg,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		NULL,
+		SYSCALL_EPERM,
+	},
+
+	/* connect - system calls */
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect4: connect (stream)",
+		connect_v4_prog_load,
+		connect_v4_prog_destroy,
+		BPF_CGROUP_INET4_CONNECT,
+		&user_ops,
+		AF_INET,
+		SOCK_STREAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SRC4_REWRITE_IP,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect4: connect deny (stream)",
+		connect_v4_deny_prog_load,
+		connect_v4_deny_prog_destroy,
+		BPF_CGROUP_INET4_CONNECT,
+		&user_ops,
+		AF_INET,
+		SOCK_STREAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SRC4_REWRITE_IP,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect4: connect (dgram)",
+		connect_v4_prog_load,
+		connect_v4_prog_destroy,
+		BPF_CGROUP_INET4_CONNECT,
+		&user_ops,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SRC4_REWRITE_IP,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect4: connect deny (dgram)",
+		connect_v4_deny_prog_load,
+		connect_v4_deny_prog_destroy,
+		BPF_CGROUP_INET4_CONNECT,
+		&user_ops,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SRC4_REWRITE_IP,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect4: load prog with wrong expected attach type",
+		connect_v4_prog_load,
+		connect_v4_prog_destroy,
+		BPF_CGROUP_INET6_CONNECT,
+		&user_ops,
+		AF_INET,
+		SOCK_STREAM,
+		NULL,
+		0,
+		NULL,
+		0,
+		NULL,
+		LOAD_REJECT,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect4: attach prog with wrong attach type",
+		connect_v4_prog_load_raw,
+		connect_v4_prog_destroy_raw,
+		BPF_CGROUP_INET6_CONNECT,
+		&user_ops,
+		AF_INET,
+		SOCK_STREAM,
+		NULL,
+		0,
+		NULL,
+		0,
+		NULL,
+		ATTACH_REJECT,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect6: connect (stream)",
+		connect_v6_prog_load,
+		connect_v6_prog_destroy,
+		BPF_CGROUP_INET6_CONNECT,
+		&user_ops,
+		AF_INET6,
+		SOCK_STREAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SRC6_REWRITE_IP,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect6: connect deny (stream)",
+		connect_v6_deny_prog_load,
+		connect_v6_deny_prog_destroy,
+		BPF_CGROUP_INET6_CONNECT,
+		&user_ops,
+		AF_INET6,
+		SOCK_STREAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SRC6_REWRITE_IP,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect6: connect (dgram)",
+		connect_v6_prog_load,
+		connect_v6_prog_destroy,
+		BPF_CGROUP_INET6_CONNECT,
+		&user_ops,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SRC6_REWRITE_IP,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect6: connect deny (dgram)",
+		connect_v6_deny_prog_load,
+		connect_v6_deny_prog_destroy,
+		BPF_CGROUP_INET6_CONNECT,
+		&user_ops,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SRC6_REWRITE_IP,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect6: load prog with wrong expected attach type",
+		connect_v6_prog_load,
+		connect_v6_prog_destroy,
+		BPF_CGROUP_INET4_CONNECT,
+		&user_ops,
+		AF_INET6,
+		SOCK_STREAM,
+		NULL,
+		0,
+		NULL,
+		0,
+		NULL,
+		LOAD_REJECT,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect6: attach prog with wrong attach type",
+		connect_v6_prog_load_raw,
+		connect_v6_prog_destroy_raw,
+		BPF_CGROUP_INET4_CONNECT,
+		&user_ops,
+		AF_INET,
+		SOCK_STREAM,
+		NULL,
+		0,
+		NULL,
+		0,
+		NULL,
+		ATTACH_REJECT,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect_unix: connect (stream)",
+		connect_unix_prog_load,
+		connect_unix_prog_destroy,
+		BPF_CGROUP_UNIX_CONNECT,
+		&user_ops,
+		AF_UNIX,
+		SOCK_STREAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect_unix: connect deny (stream)",
+		connect_unix_deny_prog_load,
+		connect_unix_deny_prog_destroy,
+		BPF_CGROUP_UNIX_CONNECT,
+		&user_ops,
+		AF_UNIX,
+		SOCK_STREAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect_unix: attach prog with wrong attach type",
+		connect_unix_prog_load_raw,
+		connect_unix_prog_destroy_raw,
+		BPF_CGROUP_INET4_CONNECT,
+		&user_ops,
+		AF_UNIX,
+		SOCK_STREAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+		ATTACH_REJECT,
+	},
+
+	/* connect - kernel calls */
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect4: kernel_connect (stream)",
+		connect_v4_prog_load,
+		connect_v4_prog_destroy,
+		BPF_CGROUP_INET4_CONNECT,
+		&kern_ops_sock_sendmsg,
+		AF_INET,
+		SOCK_STREAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SRC4_REWRITE_IP,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect4: kernel_connect deny (stream)",
+		connect_v4_deny_prog_load,
+		connect_v4_deny_prog_destroy,
+		BPF_CGROUP_INET4_CONNECT,
+		&kern_ops_sock_sendmsg,
+		AF_INET,
+		SOCK_STREAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SRC4_REWRITE_IP,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect4: kernel_connect (dgram)",
+		connect_v4_prog_load,
+		connect_v4_prog_destroy,
+		BPF_CGROUP_INET4_CONNECT,
+		&kern_ops_sock_sendmsg,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SRC4_REWRITE_IP,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect4: kernel_connect deny (dgram)",
+		connect_v4_deny_prog_load,
+		connect_v4_deny_prog_destroy,
+		BPF_CGROUP_INET4_CONNECT,
+		&kern_ops_sock_sendmsg,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SRC4_REWRITE_IP,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect6: kernel_connect (stream)",
+		connect_v6_prog_load,
+		connect_v6_prog_destroy,
+		BPF_CGROUP_INET6_CONNECT,
+		&kern_ops_sock_sendmsg,
+		AF_INET6,
+		SOCK_STREAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SRC6_REWRITE_IP,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect6: kernel_connect deny (stream)",
+		connect_v6_deny_prog_load,
+		connect_v6_deny_prog_destroy,
+		BPF_CGROUP_INET6_CONNECT,
+		&kern_ops_sock_sendmsg,
+		AF_INET6,
+		SOCK_STREAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SRC6_REWRITE_IP,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect6: kernel_connect (dgram)",
+		connect_v6_prog_load,
+		connect_v6_prog_destroy,
+		BPF_CGROUP_INET6_CONNECT,
+		&kern_ops_sock_sendmsg,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SRC6_REWRITE_IP,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect6: kernel_connect deny (dgram)",
+		connect_v6_deny_prog_load,
+		connect_v6_deny_prog_destroy,
+		BPF_CGROUP_INET6_CONNECT,
+		&kern_ops_sock_sendmsg,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SRC6_REWRITE_IP,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect_unix: kernel_connect (dgram)",
+		connect_unix_prog_load,
+		connect_unix_prog_destroy,
+		BPF_CGROUP_UNIX_CONNECT,
+		&kern_ops_sock_sendmsg,
+		AF_UNIX,
+		SOCK_STREAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_CONNECT,
+		"connect_unix: kernel_connect deny (dgram)",
+		connect_unix_deny_prog_load,
+		connect_unix_deny_prog_destroy,
+		BPF_CGROUP_UNIX_CONNECT,
+		&kern_ops_sock_sendmsg,
+		AF_UNIX,
+		SOCK_STREAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+		SYSCALL_EPERM,
+	},
+
+	/* sendmsg - system calls */
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg4: sendmsg (dgram)",
+		sendmsg_v4_prog_load,
+		sendmsg_v4_prog_destroy,
+		BPF_CGROUP_UDP4_SENDMSG,
+		&user_ops,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SRC4_REWRITE_IP,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg4: sendmsg deny (dgram)",
+		sendmsg_v4_deny_prog_load,
+		sendmsg_v4_deny_prog_destroy,
+		BPF_CGROUP_UDP4_SENDMSG,
+		&user_ops,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SRC4_REWRITE_IP,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg4: load prog with wrong expected attach type",
+		sendmsg_v4_prog_load,
+		sendmsg_v4_prog_destroy,
+		BPF_CGROUP_UDP6_SENDMSG,
+		&user_ops,
+		AF_INET,
+		SOCK_DGRAM,
+		NULL,
+		0,
+		NULL,
+		0,
+		NULL,
+		LOAD_REJECT,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg4: attach prog with wrong attach type",
+		sendmsg_v4_prog_load_raw,
+		sendmsg_v4_prog_destroy_raw,
+		BPF_CGROUP_UDP6_SENDMSG,
+		&user_ops,
+		AF_INET,
+		SOCK_DGRAM,
+		NULL,
+		0,
+		NULL,
+		0,
+		NULL,
+		ATTACH_REJECT,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg6: sendmsg (dgram)",
+		sendmsg_v6_prog_load,
+		sendmsg_v6_prog_destroy,
+		BPF_CGROUP_UDP6_SENDMSG,
+		&user_ops,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SRC6_REWRITE_IP,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg6: sendmsg [::] (BSD'ism) (dgram)",
+		sendmsg_v6_preserve_dst_prog_load,
+		sendmsg_v6_preserve_dst_prog_destroy,
+		BPF_CGROUP_UDP6_SENDMSG,
+		&user_ops,
+		AF_INET6,
+		SOCK_DGRAM,
+		WILDCARD6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_PORT,
+		SRC6_IP,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg6: sendmsg deny (dgram)",
+		sendmsg_v6_deny_prog_load,
+		sendmsg_v6_deny_prog_destroy,
+		BPF_CGROUP_UDP6_SENDMSG,
+		&user_ops,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SRC6_REWRITE_IP,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg6: sendmsg IPv4-mapped IPv6 (dgram)",
+		sendmsg_v6_v4mapped_prog_load,
+		sendmsg_v6_v4mapped_prog_destroy,
+		BPF_CGROUP_UDP6_SENDMSG,
+		&user_ops,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SRC6_REWRITE_IP,
+		SYSCALL_ENOTSUPP,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg6: sendmsg dst IP = [::] (BSD'ism) (dgram)",
+		sendmsg_v6_wildcard_prog_load,
+		sendmsg_v6_wildcard_prog_destroy,
+		BPF_CGROUP_UDP6_SENDMSG,
+		&user_ops,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SRC6_REWRITE_IP,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg6: load prog with wrong expected attach type",
+		sendmsg_v6_prog_load,
+		sendmsg_v6_prog_destroy,
+		BPF_CGROUP_UDP4_SENDMSG,
+		&user_ops,
+		AF_INET6,
+		SOCK_DGRAM,
+		NULL,
+		0,
+		NULL,
+		0,
+		NULL,
+		LOAD_REJECT,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg6: attach prog with wrong attach type",
+		sendmsg_v6_prog_load_raw,
+		sendmsg_v6_prog_destroy_raw,
+		BPF_CGROUP_UDP4_SENDMSG,
+		&user_ops,
+		AF_INET6,
+		SOCK_DGRAM,
+		NULL,
+		0,
+		NULL,
+		0,
+		NULL,
+		ATTACH_REJECT,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg_unix: sendmsg (dgram)",
+		sendmsg_unix_prog_load,
+		sendmsg_unix_prog_destroy,
+		BPF_CGROUP_UNIX_SENDMSG,
+		&user_ops,
+		AF_UNIX,
+		SOCK_DGRAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg_unix: sendmsg deny (dgram)",
+		sendmsg_unix_deny_prog_load,
+		sendmsg_unix_deny_prog_destroy,
+		BPF_CGROUP_UNIX_SENDMSG,
+		&user_ops,
+		AF_UNIX,
+		SOCK_DGRAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg_unix: attach prog with wrong attach type",
+		sendmsg_unix_prog_load_raw,
+		sendmsg_unix_prog_destroy_raw,
+		BPF_CGROUP_UDP4_SENDMSG,
+		&user_ops,
+		AF_UNIX,
+		SOCK_DGRAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+		ATTACH_REJECT,
+	},
+
+	/* sendmsg - kernel calls (sock_sendmsg) */
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg4: sock_sendmsg (dgram)",
+		sendmsg_v4_prog_load,
+		sendmsg_v4_prog_destroy,
+		BPF_CGROUP_UDP4_SENDMSG,
+		&kern_ops_sock_sendmsg,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SRC4_REWRITE_IP,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg4: sock_sendmsg deny (dgram)",
+		sendmsg_v4_deny_prog_load,
+		sendmsg_v4_deny_prog_destroy,
+		BPF_CGROUP_UDP4_SENDMSG,
+		&kern_ops_sock_sendmsg,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SRC4_REWRITE_IP,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg6: sock_sendmsg (dgram)",
+		sendmsg_v6_prog_load,
+		sendmsg_v6_prog_destroy,
+		BPF_CGROUP_UDP6_SENDMSG,
+		&kern_ops_sock_sendmsg,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SRC6_REWRITE_IP,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg6: sock_sendmsg [::] (BSD'ism) (dgram)",
+		sendmsg_v6_preserve_dst_prog_load,
+		sendmsg_v6_preserve_dst_prog_destroy,
+		BPF_CGROUP_UDP6_SENDMSG,
+		&kern_ops_sock_sendmsg,
+		AF_INET6,
+		SOCK_DGRAM,
+		WILDCARD6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_PORT,
+		SRC6_IP,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg6: sock_sendmsg deny (dgram)",
+		sendmsg_v6_deny_prog_load,
+		sendmsg_v6_deny_prog_destroy,
+		BPF_CGROUP_UDP6_SENDMSG,
+		&kern_ops_sock_sendmsg,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SRC6_REWRITE_IP,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg_unix: sock_sendmsg (dgram)",
+		sendmsg_unix_prog_load,
+		sendmsg_unix_prog_destroy,
+		BPF_CGROUP_UNIX_SENDMSG,
+		&kern_ops_sock_sendmsg,
+		AF_UNIX,
+		SOCK_DGRAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg_unix: sock_sendmsg deny (dgram)",
+		sendmsg_unix_deny_prog_load,
+		sendmsg_unix_deny_prog_destroy,
+		BPF_CGROUP_UNIX_SENDMSG,
+		&kern_ops_sock_sendmsg,
+		AF_UNIX,
+		SOCK_DGRAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+		SYSCALL_EPERM,
+	},
+
+	/* sendmsg - kernel calls (kernel_sendmsg) */
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg4: kernel_sendmsg (dgram)",
+		sendmsg_v4_prog_load,
+		sendmsg_v4_prog_destroy,
+		BPF_CGROUP_UDP4_SENDMSG,
+		&kern_ops_kernel_sendmsg,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SRC4_REWRITE_IP,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg4: kernel_sendmsg deny (dgram)",
+		sendmsg_v4_deny_prog_load,
+		sendmsg_v4_deny_prog_destroy,
+		BPF_CGROUP_UDP4_SENDMSG,
+		&kern_ops_kernel_sendmsg,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_IP,
+		SERV4_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SRC4_REWRITE_IP,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg6: kernel_sendmsg (dgram)",
+		sendmsg_v6_prog_load,
+		sendmsg_v6_prog_destroy,
+		BPF_CGROUP_UDP6_SENDMSG,
+		&kern_ops_kernel_sendmsg,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SRC6_REWRITE_IP,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg6: kernel_sendmsg [::] (BSD'ism) (dgram)",
+		sendmsg_v6_preserve_dst_prog_load,
+		sendmsg_v6_preserve_dst_prog_destroy,
+		BPF_CGROUP_UDP6_SENDMSG,
+		&kern_ops_kernel_sendmsg,
+		AF_INET6,
+		SOCK_DGRAM,
+		WILDCARD6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_PORT,
+		SRC6_IP,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg6: kernel_sendmsg deny (dgram)",
+		sendmsg_v6_deny_prog_load,
+		sendmsg_v6_deny_prog_destroy,
+		BPF_CGROUP_UDP6_SENDMSG,
+		&kern_ops_kernel_sendmsg,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_IP,
+		SERV6_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SRC6_REWRITE_IP,
+		SYSCALL_EPERM,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg_unix: sock_sendmsg (dgram)",
+		sendmsg_unix_prog_load,
+		sendmsg_unix_prog_destroy,
+		BPF_CGROUP_UNIX_SENDMSG,
+		&kern_ops_kernel_sendmsg,
+		AF_UNIX,
+		SOCK_DGRAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_SENDMSG,
+		"sendmsg_unix: kernel_sendmsg deny (dgram)",
+		sendmsg_unix_deny_prog_load,
+		sendmsg_unix_deny_prog_destroy,
+		BPF_CGROUP_UNIX_SENDMSG,
+		&kern_ops_kernel_sendmsg,
+		AF_UNIX,
+		SOCK_DGRAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+		SYSCALL_EPERM,
+	},
+
+	/* recvmsg - system calls */
+	{
+		SOCK_ADDR_TEST_RECVMSG,
+		"recvmsg4: recvfrom (dgram)",
+		recvmsg4_prog_load,
+		recvmsg4_prog_destroy,
+		BPF_CGROUP_UDP4_RECVMSG,
+		&user_ops,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SERV4_IP,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_RECVMSG,
+		"recvmsg4: attach prog with wrong attach type",
+		recvmsg4_prog_load_raw,
+		recvmsg4_prog_destroy_raw,
+		BPF_CGROUP_UDP6_RECVMSG,
+		&user_ops,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SERV4_IP,
+		ATTACH_REJECT,
+	},
+	{
+		SOCK_ADDR_TEST_RECVMSG,
+		"recvmsg6: recvfrom (dgram)",
+		recvmsg6_prog_load,
+		recvmsg6_prog_destroy,
+		BPF_CGROUP_UDP6_RECVMSG,
+		&user_ops,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SERV6_IP,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_RECVMSG,
+		"recvmsg6: attach prog with wrong attach type",
+		recvmsg6_prog_load_raw,
+		recvmsg6_prog_destroy_raw,
+		BPF_CGROUP_UDP4_RECVMSG,
+		&user_ops,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SERV6_IP,
+		ATTACH_REJECT,
+	},
+	{
+		SOCK_ADDR_TEST_RECVMSG,
+		"recvmsg_unix: recvfrom (dgram)",
+		recvmsg_unix_prog_load,
+		recvmsg_unix_prog_destroy,
+		BPF_CGROUP_UNIX_RECVMSG,
+		&user_ops,
+		AF_UNIX,
+		SOCK_DGRAM,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		SERVUN_ADDRESS,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_RECVMSG,
+		"recvmsg_unix: recvfrom (stream)",
+		recvmsg_unix_prog_load,
+		recvmsg_unix_prog_destroy,
+		BPF_CGROUP_UNIX_RECVMSG,
+		&user_ops,
+		AF_UNIX,
+		SOCK_STREAM,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		SERVUN_ADDRESS,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_RECVMSG,
+		"recvmsg_unix: attach prog with wrong attach type",
+		recvmsg_unix_prog_load_raw,
+		recvmsg_unix_prog_destroy_raw,
+		BPF_CGROUP_UDP4_RECVMSG,
+		&user_ops,
+		AF_INET6,
+		SOCK_STREAM,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		SERVUN_ADDRESS,
+		ATTACH_REJECT,
+	},
+
+	/* getsockname - system calls */
+	{
+		SOCK_ADDR_TEST_GETSOCKNAME,
+		"getsockname4: getsockname (stream)",
+		getsockname_v4_prog_load,
+		getsockname_v4_prog_destroy,
+		BPF_CGROUP_INET4_GETSOCKNAME,
+		&user_ops,
+		AF_INET,
+		SOCK_STREAM,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SERV4_IP,
+		SERV4_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_GETSOCKNAME,
+		"getsockname4: getsockname (dgram)",
+		getsockname_v4_prog_load,
+		getsockname_v4_prog_destroy,
+		BPF_CGROUP_INET4_GETSOCKNAME,
+		&user_ops,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SERV4_IP,
+		SERV4_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_GETSOCKNAME,
+		"getsockname4: attach prog with wrong attach type",
+		getsockname_v4_prog_load_raw,
+		getsockname_v4_prog_destroy_raw,
+		BPF_CGROUP_INET6_GETSOCKNAME,
+		&user_ops,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SERV4_IP,
+		SERV4_PORT,
+		NULL,
+		ATTACH_REJECT,
+	},
+	{
+		SOCK_ADDR_TEST_GETSOCKNAME,
+		"getsockname6: getsockname (stream)",
+		getsockname_v6_prog_load,
+		getsockname_v6_prog_destroy,
+		BPF_CGROUP_INET6_GETSOCKNAME,
+		&user_ops,
+		AF_INET6,
+		SOCK_STREAM,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SERV6_IP,
+		SERV6_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_GETSOCKNAME,
+		"getsockname6: getsockname (dgram)",
+		getsockname_v6_prog_load,
+		getsockname_v6_prog_destroy,
+		BPF_CGROUP_INET6_GETSOCKNAME,
+		&user_ops,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SERV6_IP,
+		SERV6_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_GETSOCKNAME,
+		"getsockname6: attach prog with wrong attach type",
+		getsockname_v6_prog_load_raw,
+		getsockname_v6_prog_destroy_raw,
+		BPF_CGROUP_INET4_GETSOCKNAME,
+		&user_ops,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SERV6_IP,
+		SERV6_PORT,
+		NULL,
+		ATTACH_REJECT,
+	},
+	{
+		SOCK_ADDR_TEST_GETSOCKNAME,
+		"getsockname_unix: getsockname",
+		getsockname_unix_prog_load,
+		getsockname_unix_prog_destroy,
+		BPF_CGROUP_UNIX_GETSOCKNAME,
+		&user_ops,
+		AF_UNIX,
+		SOCK_STREAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_GETSOCKNAME,
+		"getsockname_unix: attach prog with wrong attach type",
+		getsockname_unix_prog_load_raw,
+		getsockname_unix_prog_destroy_raw,
+		BPF_CGROUP_INET4_GETSOCKNAME,
+		&user_ops,
+		AF_UNIX,
+		SOCK_STREAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+		ATTACH_REJECT,
+	},
+
+	/* getsockname - kernel calls */
+	{
+		SOCK_ADDR_TEST_GETSOCKNAME,
+		"getsockname4: kernel_getsockname (stream)",
+		getsockname_v4_prog_load,
+		getsockname_v4_prog_destroy,
+		BPF_CGROUP_INET4_GETSOCKNAME,
+		&kern_ops_kernel_sendmsg,
+		AF_INET,
+		SOCK_STREAM,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SERV4_IP,
+		SERV4_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_GETSOCKNAME,
+		"getsockname4: kernel_getsockname (dgram)",
+		getsockname_v4_prog_load,
+		getsockname_v4_prog_destroy,
+		BPF_CGROUP_INET4_GETSOCKNAME,
+		&kern_ops_kernel_sendmsg,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SERV4_IP,
+		SERV4_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_GETSOCKNAME,
+		"getsockname6: kernel_getsockname (stream)",
+		getsockname_v6_prog_load,
+		getsockname_v6_prog_destroy,
+		BPF_CGROUP_INET6_GETSOCKNAME,
+		&kern_ops_kernel_sendmsg,
+		AF_INET6,
+		SOCK_STREAM,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SERV6_IP,
+		SERV6_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_GETSOCKNAME,
+		"getsockname6: kernel_getsockname (dgram)",
+		getsockname_v6_prog_load,
+		getsockname_v6_prog_destroy,
+		BPF_CGROUP_INET6_GETSOCKNAME,
+		&kern_ops_kernel_sendmsg,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SERV6_IP,
+		SERV6_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_GETSOCKNAME,
+		"getsockname_unix: kernel_getsockname",
+		getsockname_unix_prog_load,
+		getsockname_unix_prog_destroy,
+		BPF_CGROUP_UNIX_GETSOCKNAME,
+		&kern_ops_kernel_sendmsg,
+		AF_UNIX,
+		SOCK_STREAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+		SUCCESS,
+	},
+
+	/* getpeername - system calls */
+	{
+		SOCK_ADDR_TEST_GETPEERNAME,
+		"getpeername4: getpeername (stream)",
+		getpeername_v4_prog_load,
+		getpeername_v4_prog_destroy,
+		BPF_CGROUP_INET4_GETPEERNAME,
+		&user_ops,
+		AF_INET,
+		SOCK_STREAM,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SERV4_IP,
+		SERV4_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_GETPEERNAME,
+		"getpeername4: getpeername (dgram)",
+		getpeername_v4_prog_load,
+		getpeername_v4_prog_destroy,
+		BPF_CGROUP_INET4_GETPEERNAME,
+		&user_ops,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SERV4_IP,
+		SERV4_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_GETPEERNAME,
+		"getpeername4: attach prog with wrong attach type",
+		getpeername_v4_prog_load_raw,
+		getpeername_v4_prog_destroy_raw,
+		BPF_CGROUP_INET6_GETSOCKNAME,
+		&user_ops,
+		AF_UNIX,
+		SOCK_DGRAM,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SERV4_IP,
+		SERV4_PORT,
+		NULL,
+		ATTACH_REJECT,
+	},
+	{
+		SOCK_ADDR_TEST_GETPEERNAME,
+		"getpeername6: getpeername (stream)",
+		getpeername_v6_prog_load,
+		getpeername_v6_prog_destroy,
+		BPF_CGROUP_INET6_GETPEERNAME,
+		&user_ops,
+		AF_INET6,
+		SOCK_STREAM,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SERV6_IP,
+		SERV6_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_GETPEERNAME,
+		"getpeername6: getpeername (dgram)",
+		getpeername_v6_prog_load,
+		getpeername_v6_prog_destroy,
+		BPF_CGROUP_INET6_GETPEERNAME,
+		&user_ops,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SERV6_IP,
+		SERV6_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_GETPEERNAME,
+		"getpeername6: attach prog with wrong attach type",
+		getpeername_v6_prog_load_raw,
+		getpeername_v6_prog_destroy_raw,
+		BPF_CGROUP_INET4_GETSOCKNAME,
+		&user_ops,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SERV6_IP,
+		SERV6_PORT,
+		NULL,
+		ATTACH_REJECT,
+	},
+	{
+		SOCK_ADDR_TEST_GETPEERNAME,
+		"getpeername_unix: getpeername",
+		getpeername_unix_prog_load,
+		getpeername_unix_prog_destroy,
+		BPF_CGROUP_UNIX_GETPEERNAME,
+		&user_ops,
+		AF_UNIX,
+		SOCK_STREAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_GETPEERNAME,
+		"getpeername_unix: attach prog with wrong attach type",
+		getpeername_unix_prog_load_raw,
+		getpeername_unix_prog_destroy_raw,
+		BPF_CGROUP_INET4_GETSOCKNAME,
+		&user_ops,
+		AF_UNIX,
+		SOCK_STREAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+		ATTACH_REJECT,
+	},
+
+	/* getpeername - kernel calls */
+	{
+		SOCK_ADDR_TEST_GETPEERNAME,
+		"getpeername4: kernel_getpeername (stream)",
+		getpeername_v4_prog_load,
+		getpeername_v4_prog_destroy,
+		BPF_CGROUP_INET4_GETPEERNAME,
+		&kern_ops_kernel_sendmsg,
+		AF_INET,
+		SOCK_STREAM,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SERV4_IP,
+		SERV4_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_GETPEERNAME,
+		"getpeername4: kernel_getpeername (dgram)",
+		getpeername_v4_prog_load,
+		getpeername_v4_prog_destroy,
+		BPF_CGROUP_INET4_GETPEERNAME,
+		&kern_ops_kernel_sendmsg,
+		AF_INET,
+		SOCK_DGRAM,
+		SERV4_REWRITE_IP,
+		SERV4_REWRITE_PORT,
+		SERV4_IP,
+		SERV4_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_GETPEERNAME,
+		"getpeername6: kernel_getpeername (stream)",
+		getpeername_v6_prog_load,
+		getpeername_v6_prog_destroy,
+		BPF_CGROUP_INET6_GETPEERNAME,
+		&kern_ops_kernel_sendmsg,
+		AF_INET6,
+		SOCK_STREAM,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SERV6_IP,
+		SERV6_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_GETPEERNAME,
+		"getpeername6: kernel_getpeername (dgram)",
+		getpeername_v6_prog_load,
+		getpeername_v6_prog_destroy,
+		BPF_CGROUP_INET6_GETPEERNAME,
+		&kern_ops_kernel_sendmsg,
+		AF_INET6,
+		SOCK_DGRAM,
+		SERV6_REWRITE_IP,
+		SERV6_REWRITE_PORT,
+		SERV6_IP,
+		SERV6_PORT,
+		NULL,
+		SUCCESS,
+	},
+	{
+		SOCK_ADDR_TEST_GETPEERNAME,
+		"getpeername_unix: kernel_getpeername",
+		getpeername_unix_prog_load,
+		getpeername_unix_prog_destroy,
+		BPF_CGROUP_UNIX_GETPEERNAME,
+		&kern_ops_kernel_sendmsg,
+		AF_UNIX,
+		SOCK_STREAM,
+		SERVUN_ADDRESS,
+		0,
+		SERVUN_REWRITE_ADDRESS,
+		0,
+		NULL,
+		SUCCESS,
+	},
+};
+
+typedef int (*info_fn)(int, struct sockaddr *, socklen_t *);
+
+static int cmp_addr(const struct sockaddr_storage *addr1, socklen_t addr1_len,
+		    const struct sockaddr_storage *addr2, socklen_t addr2_len,
+		    bool cmp_port)
+{
+	const struct sockaddr_in *four1, *four2;
+	const struct sockaddr_in6 *six1, *six2;
+	const struct sockaddr_un *un1, *un2;
+
+	if (addr1->ss_family != addr2->ss_family)
+		return -1;
+
+	if (addr1_len != addr2_len)
+		return -1;
+
+	if (addr1->ss_family == AF_INET) {
+		four1 = (const struct sockaddr_in *)addr1;
+		four2 = (const struct sockaddr_in *)addr2;
+		return !((four1->sin_port == four2->sin_port || !cmp_port) &&
+			 four1->sin_addr.s_addr == four2->sin_addr.s_addr);
+	} else if (addr1->ss_family == AF_INET6) {
+		six1 = (const struct sockaddr_in6 *)addr1;
+		six2 = (const struct sockaddr_in6 *)addr2;
+		return !((six1->sin6_port == six2->sin6_port || !cmp_port) &&
+			 !memcmp(&six1->sin6_addr, &six2->sin6_addr,
+				 sizeof(struct in6_addr)));
+	} else if (addr1->ss_family == AF_UNIX) {
+		un1 = (const struct sockaddr_un *)addr1;
+		un2 = (const struct sockaddr_un *)addr2;
+		return memcmp(un1, un2, addr1_len);
+	}
+
+	return -1;
+}
+
+static int cmp_sock_addr(info_fn fn, int sock1,
+			 const struct sockaddr_storage *addr2,
+			 socklen_t addr2_len, bool cmp_port)
+{
+	struct sockaddr_storage addr1;
+	socklen_t len1 = sizeof(addr1);
+
+	memset(&addr1, 0, len1);
+	if (fn(sock1, (struct sockaddr *)&addr1, (socklen_t *)&len1) != 0)
+		return -1;
+
+	return cmp_addr(&addr1, len1, addr2, addr2_len, cmp_port);
+}
+
+static int load_sock_addr_kern(void)
+{
+	int err;
+
+	skel = sock_addr_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel"))
+		goto err;
+
+	err = 0;
+	goto out;
+err:
+	err = -1;
+out:
+	return err;
+}
+
+static void unload_sock_addr_kern(void)
+{
+	sock_addr_kern__destroy(skel);
+}
+
+static int test_bind(struct sock_addr_test *test)
+{
+	struct sockaddr_storage expected_addr;
+	socklen_t expected_addr_len = sizeof(struct sockaddr_storage);
+	int serv = -1, client = -1, err;
+
+	serv = test->ops->start_server(test->socket_family, test->socket_type,
+				       test->requested_addr,
+				       test->requested_port, 0);
+	if (serv < 0) {
+		err = errno;
+		goto err;
+	}
+
+	err = make_sockaddr(test->socket_family,
+			    test->expected_addr, test->expected_port,
+			    &expected_addr, &expected_addr_len);
+	if (!ASSERT_EQ(err, 0, "make_sockaddr"))
+		goto cleanup;
+
+	err = cmp_sock_addr(test->ops->getsockname, serv, &expected_addr,
+			    expected_addr_len, true);
+	if (!ASSERT_EQ(err, 0, "cmp_local_addr"))
+		goto cleanup;
+
+	/* Try to connect to server just in case */
+	client = connect_to_addr(test->socket_type, &expected_addr, expected_addr_len, NULL);
+	if (!ASSERT_GE(client, 0, "connect_to_addr"))
+		goto cleanup;
+
+cleanup:
+	err = 0;
+err:
+	if (client != -1)
+		close(client);
+	if (serv != -1)
+		test->ops->close(serv);
+
+	return err;
+}
+
+static int test_connect(struct sock_addr_test *test)
+{
+	struct sockaddr_storage addr, expected_addr, expected_src_addr;
+	socklen_t addr_len = sizeof(struct sockaddr_storage),
+		  expected_addr_len = sizeof(struct sockaddr_storage),
+		  expected_src_addr_len = sizeof(struct sockaddr_storage);
+	int serv = -1, client = -1, err;
+
+	serv = start_server(test->socket_family, test->socket_type,
+			    test->expected_addr, test->expected_port, 0);
+	if (!ASSERT_GE(serv, 0, "start_server"))
+		goto cleanup;
+
+	err = make_sockaddr(test->socket_family, test->requested_addr, test->requested_port,
+			    &addr, &addr_len);
+	if (!ASSERT_EQ(err, 0, "make_sockaddr"))
+		goto cleanup;
+
+	client = test->ops->connect_to_addr(test->socket_type, &addr, addr_len,
+					    NULL);
+	if (client < 0) {
+		err = errno;
+		goto err;
+	}
+
+	err = make_sockaddr(test->socket_family, test->expected_addr, test->expected_port,
+			    &expected_addr, &expected_addr_len);
+	if (!ASSERT_EQ(err, 0, "make_sockaddr"))
+		goto cleanup;
+
+	if (test->expected_src_addr) {
+		err = make_sockaddr(test->socket_family, test->expected_src_addr, 0,
+				    &expected_src_addr, &expected_src_addr_len);
+		if (!ASSERT_EQ(err, 0, "make_sockaddr"))
+			goto cleanup;
+	}
+
+	err = cmp_sock_addr(test->ops->getpeername, client, &expected_addr,
+			    expected_addr_len, true);
+	if (!ASSERT_EQ(err, 0, "cmp_peer_addr"))
+		goto cleanup;
+
+	if (test->expected_src_addr) {
+		err = cmp_sock_addr(test->ops->getsockname, client,
+				    &expected_src_addr, expected_src_addr_len,
+				    false);
+		if (!ASSERT_EQ(err, 0, "cmp_local_addr"))
+			goto cleanup;
+	}
+cleanup:
+	err = 0;
+err:
+	if (client != -1)
+		test->ops->close(client);
+	if (serv != -1)
+		close(serv);
+
+	return err;
+}
+
+static int test_xmsg(struct sock_addr_test *test)
+{
+	struct sockaddr_storage addr, src_addr;
+	socklen_t addr_len = sizeof(struct sockaddr_storage),
+		  src_addr_len = sizeof(struct sockaddr_storage);
+	char data = 'a';
+	int serv = -1, client = -1, err;
+
+	/* Unlike the other tests, here we test that we can rewrite the src addr
+	 * with a recvmsg() hook.
+	 */
+
+	serv = start_server(test->socket_family, test->socket_type,
+			    test->expected_addr, test->expected_port, 0);
+	if (!ASSERT_GE(serv, 0, "start_server"))
+		goto cleanup;
+
+	client = test->ops->socket(test->socket_family, test->socket_type, 0);
+	if (!ASSERT_GE(client, 0, "socket"))
+		goto cleanup;
+
+	/* AF_UNIX sockets have to be bound to something to trigger the recvmsg bpf program. */
+	if (test->socket_family == AF_UNIX) {
+		err = make_sockaddr(AF_UNIX, SRCUN_ADDRESS, 0, &src_addr, &src_addr_len);
+		if (!ASSERT_EQ(err, 0, "make_sockaddr"))
+			goto cleanup;
+
+		err = test->ops->bind(client, (struct sockaddr *)&src_addr,
+				      src_addr_len);
+		if (!ASSERT_OK(err, "bind"))
+			goto cleanup;
+	}
+
+	err = make_sockaddr(test->socket_family, test->requested_addr, test->requested_port,
+			    &addr, &addr_len);
+	if (!ASSERT_EQ(err, 0, "make_sockaddr"))
+		goto cleanup;
+
+	if (test->socket_type == SOCK_DGRAM) {
+		err = test->ops->sendmsg(client, (struct sockaddr *)&addr,
+					 addr_len, &data, sizeof(data));
+		if (err < 0) {
+			err = errno;
+			goto err;
+		}
+
+		if (!ASSERT_EQ(err, sizeof(data), "sendmsg"))
+			goto cleanup;
+	} else {
+		/* Testing with connection-oriented sockets is only valid for
+		 * recvmsg() tests.
+		 */
+		if (!ASSERT_EQ(test->type, SOCK_ADDR_TEST_RECVMSG, "recvmsg"))
+			goto cleanup;
+
+		err = connect(client, (const struct sockaddr *)&addr, addr_len);
+		if (!ASSERT_OK(err, "connect"))
+			goto cleanup;
+
+		err = send(client, &data, sizeof(data), 0);
+		if (!ASSERT_EQ(err, sizeof(data), "send"))
+			goto cleanup;
+
+		err = listen(serv, 0);
+		if (!ASSERT_OK(err, "listen"))
+			goto cleanup;
+
+		err = accept(serv, NULL, NULL);
+		if (!ASSERT_GE(err, 0, "accept"))
+			goto cleanup;
+
+		close(serv);
+		serv = err;
+	}
+
+	addr_len = src_addr_len = sizeof(struct sockaddr_storage);
+
+	err = recvfrom(serv, &data, sizeof(data), 0, (struct sockaddr *) &src_addr, &src_addr_len);
+	if (!ASSERT_EQ(err, sizeof(data), "recvfrom"))
+		goto cleanup;
+
+	ASSERT_EQ(data, 'a', "data mismatch");
+
+	if (test->expected_src_addr) {
+		err = make_sockaddr(test->socket_family, test->expected_src_addr, 0,
+				    &addr, &addr_len);
+		if (!ASSERT_EQ(err, 0, "make_sockaddr"))
+			goto cleanup;
+
+		err = cmp_addr(&src_addr, src_addr_len, &addr, addr_len, false);
+		if (!ASSERT_EQ(err, 0, "cmp_addr"))
+			goto cleanup;
+	}
+
+cleanup:
+	err = 0;
+err:
+	if (client != -1)
+		test->ops->close(client);
+	if (serv != -1)
+		close(serv);
+
+	return err;
+}
+
+static int test_getsockname(struct sock_addr_test *test)
+{
+	struct sockaddr_storage expected_addr;
+	socklen_t expected_addr_len = sizeof(struct sockaddr_storage);
+	int serv = -1, err;
+
+	serv = test->ops->start_server(test->socket_family, test->socket_type,
+			    test->requested_addr, test->requested_port, 0);
+	if (!ASSERT_GE(serv, 0, "start_server"))
+		goto cleanup;
+
+	err = make_sockaddr(test->socket_family,
+			    test->expected_addr, test->expected_port,
+			    &expected_addr, &expected_addr_len);
+	if (!ASSERT_EQ(err, 0, "make_sockaddr"))
+		goto cleanup;
+
+	err = cmp_sock_addr(test->ops->getsockname, serv, &expected_addr, expected_addr_len, true);
+	if (!ASSERT_EQ(err, 0, "cmp_local_addr"))
+		goto cleanup;
+
+cleanup:
+	if (serv != -1)
+		test->ops->close(serv);
+
+	return 0;
+}
+
+static int test_getpeername(struct sock_addr_test *test)
+{
+	struct sockaddr_storage addr, expected_addr;
+	socklen_t addr_len = sizeof(struct sockaddr_storage),
+		  expected_addr_len = sizeof(struct sockaddr_storage);
+	int serv = -1, client = -1, err;
+
+	serv = start_server(test->socket_family, test->socket_type,
+			    test->requested_addr, test->requested_port, 0);
+	if (!ASSERT_GE(serv, 0, "start_server"))
+		goto cleanup;
+
+	err = make_sockaddr(test->socket_family, test->requested_addr, test->requested_port,
+			    &addr, &addr_len);
+	if (!ASSERT_EQ(err, 0, "make_sockaddr"))
+		goto cleanup;
+
+	client = test->ops->connect_to_addr(test->socket_type, &addr, addr_len,
+					    NULL);
+	if (!ASSERT_GE(client, 0, "connect_to_addr"))
+		goto cleanup;
+
+	err = make_sockaddr(test->socket_family, test->expected_addr, test->expected_port,
+			    &expected_addr, &expected_addr_len);
+	if (!ASSERT_EQ(err, 0, "make_sockaddr"))
+		goto cleanup;
+
+	err = cmp_sock_addr(test->ops->getpeername, client, &expected_addr,
+			    expected_addr_len, true);
+	if (!ASSERT_EQ(err, 0, "cmp_peer_addr"))
+		goto cleanup;
+
+cleanup:
+	if (client != -1)
+		test->ops->close(client);
+	if (serv != -1)
+		close(serv);
+
+	return 0;
+}
+
+static int setup_test_env(struct nstoken **tok)
+{
+	int err;
+
+	SYS_NOFAIL("ip netns delete %s", TEST_NS);
+	SYS(fail, "ip netns add %s", TEST_NS);
+	*tok = open_netns(TEST_NS);
+	if (!ASSERT_OK_PTR(*tok, "netns token"))
+		goto fail;
+
+	SYS(fail, "ip link add dev %s1 type veth peer name %s2", TEST_IF_PREFIX,
+	    TEST_IF_PREFIX);
+	SYS(fail, "ip link set lo up");
+	SYS(fail, "ip link set %s1 up", TEST_IF_PREFIX);
+	SYS(fail, "ip link set %s2 up", TEST_IF_PREFIX);
+	SYS(fail, "ip -4 addr add %s/8 dev %s1", TEST_IPV4, TEST_IF_PREFIX);
+	SYS(fail, "ip -6 addr add %s/128 nodad dev %s1", TEST_IPV6, TEST_IF_PREFIX);
+
+	err = 0;
+	goto out;
+fail:
+	err = -1;
+	close_netns(*tok);
+	*tok = NULL;
+	SYS_NOFAIL("ip netns delete %s", TEST_NS);
+out:
+	return err;
+}
+
+static void cleanup_test_env(struct nstoken *tok)
+{
+	close_netns(tok);
+	SYS_NOFAIL("ip netns delete %s", TEST_NS);
+}
+
+void test_sock_addr(void)
+{
+	struct nstoken *tok = NULL;
+	int cgroup_fd = -1;
+	void *skel;
+
+	cgroup_fd = test__join_cgroup("/sock_addr");
+	if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup"))
+		goto cleanup;
+
+	if (!ASSERT_OK(setup_test_env(&tok), "setup_test_env"))
+		goto cleanup;
+
+	if (!ASSERT_OK(load_sock_addr_kern(), "load_sock_addr_kern"))
+		goto cleanup;
+
+	for (size_t i = 0; i < ARRAY_SIZE(tests); ++i) {
+		struct sock_addr_test *test = &tests[i];
+		int err;
+
+		if (!test__start_subtest(test->name))
+			continue;
+
+		skel = test->loadfn(cgroup_fd, test->attach_type,
+				    test->expected_result == LOAD_REJECT ||
+					test->expected_result == ATTACH_REJECT);
+		if (!skel)
+			continue;
+
+		switch (test->type) {
+		/* Not exercised yet but we leave this code here for when the
+		 * INET and INET6 sockaddr tests are migrated to this file in
+		 * the future.
+		 */
+		case SOCK_ADDR_TEST_BIND:
+			err = test_bind(test);
+			break;
+		case SOCK_ADDR_TEST_CONNECT:
+			err = test_connect(test);
+			break;
+		case SOCK_ADDR_TEST_SENDMSG:
+		case SOCK_ADDR_TEST_RECVMSG:
+			err = test_xmsg(test);
+			break;
+		case SOCK_ADDR_TEST_GETSOCKNAME:
+			err = test_getsockname(test);
+			break;
+		case SOCK_ADDR_TEST_GETPEERNAME:
+			err = test_getpeername(test);
+			break;
+		default:
+			ASSERT_TRUE(false, "Unknown sock addr test type");
+			err = -EINVAL;
+			break;
+		}
+
+		if (test->expected_result == SYSCALL_EPERM)
+			ASSERT_EQ(err, EPERM, "socket operation returns EPERM");
+		else if (test->expected_result == SYSCALL_ENOTSUPP)
+			ASSERT_EQ(err, ENOTSUPP, "socket operation returns ENOTSUPP");
+		else if (test->expected_result == SUCCESS)
+			ASSERT_OK(err, "socket operation succeeds");
+
+		test->destroyfn(skel);
+	}
+
+cleanup:
+	unload_sock_addr_kern();
+	cleanup_test_env(tok);
+	if (cgroup_fd >= 0)
+		close(cgroup_fd);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_create.c b/tools/testing/selftests/bpf/prog_tests/sock_create.c
new file mode 100644
index 000000000000..187ffc5e60c4
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sock_create.c
@@ -0,0 +1,348 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+
+static char bpf_log_buf[4096];
+static bool verbose;
+
+enum sock_create_test_error {
+	OK = 0,
+	DENY_CREATE,
+};
+
+static struct sock_create_test {
+	const char			*descr;
+	const struct bpf_insn		insns[64];
+	enum bpf_attach_type		attach_type;
+	enum bpf_attach_type		expected_attach_type;
+
+	int				domain;
+	int				type;
+	int				protocol;
+
+	int				optname;
+	int				optval;
+	enum sock_create_test_error	error;
+} tests[] = {
+	{
+		.descr = "AF_INET set priority",
+		.insns = {
+			/* r3 = 123 (priority) */
+			BPF_MOV64_IMM(BPF_REG_3, 123),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3,
+				    offsetof(struct bpf_sock, priority)),
+
+			/* return 1 */
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE,
+		.attach_type = BPF_CGROUP_INET_SOCK_CREATE,
+
+		.domain = AF_INET,
+		.type = SOCK_DGRAM,
+
+		.optname = SO_PRIORITY,
+		.optval = 123,
+	},
+	{
+		.descr = "AF_INET6 set priority",
+		.insns = {
+			/* r3 = 123 (priority) */
+			BPF_MOV64_IMM(BPF_REG_3, 123),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3,
+				    offsetof(struct bpf_sock, priority)),
+
+			/* return 1 */
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE,
+		.attach_type = BPF_CGROUP_INET_SOCK_CREATE,
+
+		.domain = AF_INET6,
+		.type = SOCK_DGRAM,
+
+		.optname = SO_PRIORITY,
+		.optval = 123,
+	},
+	{
+		.descr = "AF_INET set mark",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+
+			/* get uid of process */
+			BPF_EMIT_CALL(BPF_FUNC_get_current_uid_gid),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xffffffff),
+
+			/* if uid is 0, use given mark(666), else use uid as the mark */
+			BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+			BPF_MOV64_IMM(BPF_REG_3, 666),
+
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3,
+				    offsetof(struct bpf_sock, mark)),
+
+			/* return 1 */
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE,
+		.attach_type = BPF_CGROUP_INET_SOCK_CREATE,
+
+		.domain = AF_INET,
+		.type = SOCK_DGRAM,
+
+		.optname = SO_MARK,
+		.optval = 666,
+	},
+	{
+		.descr = "AF_INET6 set mark",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+
+			/* get uid of process */
+			BPF_EMIT_CALL(BPF_FUNC_get_current_uid_gid),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xffffffff),
+
+			/* if uid is 0, use given mark(666), else use uid as the mark */
+			BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+			BPF_MOV64_IMM(BPF_REG_3, 666),
+
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3,
+				    offsetof(struct bpf_sock, mark)),
+
+			/* return 1 */
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE,
+		.attach_type = BPF_CGROUP_INET_SOCK_CREATE,
+
+		.domain = AF_INET6,
+		.type = SOCK_DGRAM,
+
+		.optname = SO_MARK,
+		.optval = 666,
+	},
+	{
+		.descr = "AF_INET bound to iface",
+		.insns = {
+			/* r3 = 1 (lo interface) */
+			BPF_MOV64_IMM(BPF_REG_3, 1),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3,
+				    offsetof(struct bpf_sock, bound_dev_if)),
+
+			/* return 1 */
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE,
+		.attach_type = BPF_CGROUP_INET_SOCK_CREATE,
+
+		.domain = AF_INET,
+		.type = SOCK_DGRAM,
+
+		.optname = SO_BINDTOIFINDEX,
+		.optval = 1,
+	},
+	{
+		.descr = "AF_INET6 bound to iface",
+		.insns = {
+			/* r3 = 1 (lo interface) */
+			BPF_MOV64_IMM(BPF_REG_3, 1),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3,
+				    offsetof(struct bpf_sock, bound_dev_if)),
+
+			/* return 1 */
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE,
+		.attach_type = BPF_CGROUP_INET_SOCK_CREATE,
+
+		.domain = AF_INET6,
+		.type = SOCK_DGRAM,
+
+		.optname = SO_BINDTOIFINDEX,
+		.optval = 1,
+	},
+	{
+		.descr = "block AF_INET, SOCK_DGRAM, IPPROTO_ICMP socket",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 1),	/* r0 = verdict */
+
+			/* sock->family == AF_INET */
+			BPF_LDX_MEM(BPF_H, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct bpf_sock, family)),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_2, AF_INET, 5),
+
+			/* sock->type == SOCK_DGRAM */
+			BPF_LDX_MEM(BPF_H, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct bpf_sock, type)),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_2, SOCK_DGRAM, 3),
+
+			/* sock->protocol == IPPROTO_ICMP */
+			BPF_LDX_MEM(BPF_H, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct bpf_sock, protocol)),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_2, IPPROTO_ICMP, 1),
+
+			/* return 0 (block) */
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE,
+		.attach_type = BPF_CGROUP_INET_SOCK_CREATE,
+
+		.domain = AF_INET,
+		.type = SOCK_DGRAM,
+		.protocol = IPPROTO_ICMP,
+
+		.error = DENY_CREATE,
+	},
+	{
+		.descr = "block AF_INET6, SOCK_DGRAM, IPPROTO_ICMPV6 socket",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 1),	/* r0 = verdict */
+
+			/* sock->family == AF_INET6 */
+			BPF_LDX_MEM(BPF_H, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct bpf_sock, family)),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_2, AF_INET6, 5),
+
+			/* sock->type == SOCK_DGRAM */
+			BPF_LDX_MEM(BPF_H, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct bpf_sock, type)),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_2, SOCK_DGRAM, 3),
+
+			/* sock->protocol == IPPROTO_ICMPV6 */
+			BPF_LDX_MEM(BPF_H, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct bpf_sock, protocol)),
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_2, IPPROTO_ICMPV6, 1),
+
+			/* return 0 (block) */
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE,
+		.attach_type = BPF_CGROUP_INET_SOCK_CREATE,
+
+		.domain = AF_INET,
+		.type = SOCK_DGRAM,
+		.protocol = IPPROTO_ICMPV6,
+
+		.error = DENY_CREATE,
+	},
+	{
+		.descr = "load w/o expected_attach_type (compat mode)",
+		.insns = {
+			/* return 1 */
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.expected_attach_type = 0,
+		.attach_type = BPF_CGROUP_INET_SOCK_CREATE,
+
+		.domain = AF_INET,
+		.type = SOCK_STREAM,
+	},
+};
+
+static int load_prog(const struct bpf_insn *insns,
+		     enum bpf_attach_type expected_attach_type)
+{
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		    .expected_attach_type = expected_attach_type,
+		    .log_level = 2,
+		    .log_buf = bpf_log_buf,
+		    .log_size = sizeof(bpf_log_buf),
+	);
+	int fd, insns_cnt = 0;
+
+	for (;
+	     insns[insns_cnt].code != (BPF_JMP | BPF_EXIT);
+	     insns_cnt++) {
+	}
+	insns_cnt++;
+
+	fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns,
+			   insns_cnt, &opts);
+	if (verbose && fd < 0)
+		fprintf(stderr, "%s\n", bpf_log_buf);
+
+	return fd;
+}
+
+static int run_test(int cgroup_fd, struct sock_create_test *test)
+{
+	int sock_fd, err, prog_fd, optval, ret = -1;
+	socklen_t optlen = sizeof(optval);
+
+	prog_fd = load_prog(test->insns, test->expected_attach_type);
+	if (prog_fd < 0) {
+		log_err("Failed to load BPF program");
+		return -1;
+	}
+
+	err = bpf_prog_attach(prog_fd, cgroup_fd, test->attach_type, 0);
+	if (err < 0) {
+		log_err("Failed to attach BPF program");
+		goto close_prog_fd;
+	}
+
+	sock_fd = socket(test->domain, test->type, test->protocol);
+	if (sock_fd < 0) {
+		if (test->error == DENY_CREATE)
+			ret = 0;
+		else
+			log_err("Failed to create socket");
+
+		goto detach_prog;
+	}
+
+	if (test->optname) {
+		err = getsockopt(sock_fd, SOL_SOCKET, test->optname, &optval, &optlen);
+		if (err) {
+			log_err("Failed to call getsockopt");
+			goto cleanup;
+		}
+
+		if (optval != test->optval) {
+			errno = 0;
+			log_err("getsockopt returned unexpected optval");
+			goto cleanup;
+		}
+	}
+
+	ret = test->error != OK;
+
+cleanup:
+	close(sock_fd);
+detach_prog:
+	bpf_prog_detach2(prog_fd, cgroup_fd, test->attach_type);
+close_prog_fd:
+	close(prog_fd);
+	return ret;
+}
+
+void test_sock_create(void)
+{
+	int cgroup_fd, i;
+
+	cgroup_fd = test__join_cgroup("/sock_create");
+	if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup"))
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		if (!test__start_subtest(tests[i].descr))
+			continue;
+
+		ASSERT_OK(run_test(cgroup_fd, &tests[i]), tests[i].descr);
+	}
+
+	close(cgroup_fd);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_destroy.c b/tools/testing/selftests/bpf/prog_tests/sock_destroy.c
new file mode 100644
index 000000000000..9c11938fe597
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sock_destroy.c
@@ -0,0 +1,221 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <bpf/bpf_endian.h>
+
+#include "sock_destroy_prog.skel.h"
+#include "sock_destroy_prog_fail.skel.h"
+#include "network_helpers.h"
+
+#define TEST_NS "sock_destroy_netns"
+
+static void start_iter_sockets(struct bpf_program *prog)
+{
+	struct bpf_link *link;
+	char buf[50] = {};
+	int iter_fd, len;
+
+	link = bpf_program__attach_iter(prog, NULL);
+	if (!ASSERT_OK_PTR(link, "attach_iter"))
+		return;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (!ASSERT_GE(iter_fd, 0, "create_iter"))
+		goto free_link;
+
+	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
+		;
+	ASSERT_GE(len, 0, "read");
+
+	close(iter_fd);
+
+free_link:
+	bpf_link__destroy(link);
+}
+
+static void test_tcp_client(struct sock_destroy_prog *skel)
+{
+	int serv = -1, clien = -1, accept_serv = -1, n;
+
+	serv = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
+	if (!ASSERT_GE(serv, 0, "start_server"))
+		goto cleanup;
+
+	clien = connect_to_fd(serv, 0);
+	if (!ASSERT_GE(clien, 0, "connect_to_fd"))
+		goto cleanup;
+
+	accept_serv = accept(serv, NULL, NULL);
+	if (!ASSERT_GE(accept_serv, 0, "serv accept"))
+		goto cleanup;
+
+	n = send(clien, "t", 1, 0);
+	if (!ASSERT_EQ(n, 1, "client send"))
+		goto cleanup;
+
+	/* Run iterator program that destroys connected client sockets. */
+	start_iter_sockets(skel->progs.iter_tcp6_client);
+
+	n = send(clien, "t", 1, 0);
+	if (!ASSERT_LT(n, 0, "client_send on destroyed socket"))
+		goto cleanup;
+	ASSERT_EQ(errno, ECONNABORTED, "error code on destroyed socket");
+
+cleanup:
+	if (clien != -1)
+		close(clien);
+	if (accept_serv != -1)
+		close(accept_serv);
+	if (serv != -1)
+		close(serv);
+}
+
+static void test_tcp_server(struct sock_destroy_prog *skel)
+{
+	int serv = -1, clien = -1, accept_serv = -1, n, serv_port;
+
+	serv = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
+	if (!ASSERT_GE(serv, 0, "start_server"))
+		goto cleanup;
+	serv_port = get_socket_local_port(serv);
+	if (!ASSERT_GE(serv_port, 0, "get_sock_local_port"))
+		goto cleanup;
+	skel->bss->serv_port = (__be16) serv_port;
+
+	clien = connect_to_fd(serv, 0);
+	if (!ASSERT_GE(clien, 0, "connect_to_fd"))
+		goto cleanup;
+
+	accept_serv = accept(serv, NULL, NULL);
+	if (!ASSERT_GE(accept_serv, 0, "serv accept"))
+		goto cleanup;
+
+	n = send(clien, "t", 1, 0);
+	if (!ASSERT_EQ(n, 1, "client send"))
+		goto cleanup;
+
+	/* Run iterator program that destroys server sockets. */
+	start_iter_sockets(skel->progs.iter_tcp6_server);
+
+	n = send(clien, "t", 1, 0);
+	if (!ASSERT_LT(n, 0, "client_send on destroyed socket"))
+		goto cleanup;
+	ASSERT_EQ(errno, ECONNRESET, "error code on destroyed socket");
+
+cleanup:
+	if (clien != -1)
+		close(clien);
+	if (accept_serv != -1)
+		close(accept_serv);
+	if (serv != -1)
+		close(serv);
+}
+
+static void test_udp_client(struct sock_destroy_prog *skel)
+{
+	int serv = -1, clien = -1, n = 0;
+
+	serv = start_server(AF_INET6, SOCK_DGRAM, NULL, 0, 0);
+	if (!ASSERT_GE(serv, 0, "start_server"))
+		goto cleanup;
+
+	clien = connect_to_fd(serv, 0);
+	if (!ASSERT_GE(clien, 0, "connect_to_fd"))
+		goto cleanup;
+
+	n = send(clien, "t", 1, 0);
+	if (!ASSERT_EQ(n, 1, "client send"))
+		goto cleanup;
+
+	/* Run iterator program that destroys sockets. */
+	start_iter_sockets(skel->progs.iter_udp6_client);
+
+	n = send(clien, "t", 1, 0);
+	if (!ASSERT_LT(n, 0, "client_send on destroyed socket"))
+		goto cleanup;
+	/* UDP sockets have an overriding error code after they are disconnected,
+	 * so we don't check for ECONNABORTED error code.
+	 */
+
+cleanup:
+	if (clien != -1)
+		close(clien);
+	if (serv != -1)
+		close(serv);
+}
+
+static void test_udp_server(struct sock_destroy_prog *skel)
+{
+	int *listen_fds = NULL, n, i, serv_port;
+	unsigned int num_listens = 5;
+	char buf[1];
+
+	/* Start reuseport servers. */
+	listen_fds = start_reuseport_server(AF_INET6, SOCK_DGRAM,
+					    "::1", 0, 0, num_listens);
+	if (!ASSERT_OK_PTR(listen_fds, "start_reuseport_server"))
+		goto cleanup;
+	serv_port = get_socket_local_port(listen_fds[0]);
+	if (!ASSERT_GE(serv_port, 0, "get_sock_local_port"))
+		goto cleanup;
+	skel->bss->serv_port = (__be16) serv_port;
+
+	/* Run iterator program that destroys server sockets. */
+	start_iter_sockets(skel->progs.iter_udp6_server);
+
+	for (i = 0; i < num_listens; ++i) {
+		n = read(listen_fds[i], buf, sizeof(buf));
+		if (!ASSERT_EQ(n, -1, "read") ||
+		    !ASSERT_EQ(errno, ECONNABORTED, "error code on destroyed socket"))
+			break;
+	}
+	ASSERT_EQ(i, num_listens, "server socket");
+
+cleanup:
+	free_fds(listen_fds, num_listens);
+}
+
+void test_sock_destroy(void)
+{
+	struct sock_destroy_prog *skel;
+	struct nstoken *nstoken = NULL;
+	int cgroup_fd;
+
+	skel = sock_destroy_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	cgroup_fd = test__join_cgroup("/sock_destroy");
+	if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup"))
+		goto cleanup;
+
+	skel->links.sock_connect = bpf_program__attach_cgroup(
+		skel->progs.sock_connect, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.sock_connect, "prog_attach"))
+		goto cleanup;
+
+	SYS(cleanup, "ip netns add %s", TEST_NS);
+	SYS(cleanup, "ip -net %s link set dev lo up", TEST_NS);
+
+	nstoken = open_netns(TEST_NS);
+	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+		goto cleanup;
+
+	if (test__start_subtest("tcp_client"))
+		test_tcp_client(skel);
+	if (test__start_subtest("tcp_server"))
+		test_tcp_server(skel);
+	if (test__start_subtest("udp_client"))
+		test_udp_client(skel);
+	if (test__start_subtest("udp_server"))
+		test_udp_server(skel);
+
+	RUN_TESTS(sock_destroy_prog_fail);
+
+cleanup:
+	if (nstoken)
+		close_netns(nstoken);
+	SYS_NOFAIL("ip netns del " TEST_NS);
+	if (cgroup_fd >= 0)
+		close(cgroup_fd);
+	sock_destroy_prog__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c
new file mode 100644
index 000000000000..27781df8f2fb
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c
@@ -0,0 +1,994 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2024 Meta
+
+#include <poll.h>
+#include <test_progs.h>
+#include "network_helpers.h"
+#include "sock_iter_batch.skel.h"
+
+#define TEST_NS "sock_iter_batch_netns"
+#define TEST_CHILD_NS "sock_iter_batch_child_netns"
+
+static const int init_batch_size = 16;
+static const int nr_soreuse = 4;
+
+struct iter_out {
+	int idx;
+	__u64 cookie;
+} __packed;
+
+struct sock_count {
+	__u64 cookie;
+	int count;
+};
+
+static int insert(__u64 cookie, struct sock_count counts[], int counts_len)
+{
+	int insert = -1;
+	int i = 0;
+
+	for (; i < counts_len; i++) {
+		if (!counts[i].cookie) {
+			insert = i;
+		} else if (counts[i].cookie == cookie) {
+			insert = i;
+			break;
+		}
+	}
+	if (insert < 0)
+		return insert;
+
+	counts[insert].cookie = cookie;
+	counts[insert].count++;
+
+	return counts[insert].count;
+}
+
+static int read_n(int iter_fd, int n, struct sock_count counts[],
+		  int counts_len)
+{
+	struct iter_out out;
+	int nread = 1;
+	int i = 0;
+
+	for (; nread > 0 && (n < 0 || i < n); i++) {
+		nread = read(iter_fd, &out, sizeof(out));
+		if (!nread || !ASSERT_EQ(nread, sizeof(out), "nread"))
+			break;
+		ASSERT_GE(insert(out.cookie, counts, counts_len), 0, "insert");
+	}
+
+	ASSERT_TRUE(n < 0 || i == n, "n < 0 || i == n");
+
+	return i;
+}
+
+static __u64 socket_cookie(int fd)
+{
+	__u64 cookie;
+	socklen_t cookie_len = sizeof(cookie);
+
+	if (!ASSERT_OK(getsockopt(fd, SOL_SOCKET, SO_COOKIE, &cookie,
+				  &cookie_len), "getsockopt(SO_COOKIE)"))
+		return 0;
+	return cookie;
+}
+
+static bool was_seen(int fd, struct sock_count counts[], int counts_len)
+{
+	__u64 cookie = socket_cookie(fd);
+	int i = 0;
+
+	for (; cookie && i < counts_len; i++)
+		if (cookie == counts[i].cookie)
+			return true;
+
+	return false;
+}
+
+static int get_seen_socket(int *fds, struct sock_count counts[], int n)
+{
+	int i = 0;
+
+	for (; i < n; i++)
+		if (was_seen(fds[i], counts, n))
+			return i;
+	return -1;
+}
+
+static int get_nth_socket(int *fds, int fds_len, struct bpf_link *link, int n)
+{
+	int i, nread, iter_fd;
+	int nth_sock_idx = -1;
+	struct iter_out out;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (!ASSERT_OK_FD(iter_fd, "bpf_iter_create"))
+		return -1;
+
+	for (; n >= 0; n--) {
+		nread = read(iter_fd, &out, sizeof(out));
+		if (!nread || !ASSERT_GE(nread, 1, "nread"))
+			goto done;
+	}
+
+	for (i = 0; i < fds_len && nth_sock_idx < 0; i++)
+		if (fds[i] >= 0 && socket_cookie(fds[i]) == out.cookie)
+			nth_sock_idx = i;
+done:
+	close(iter_fd);
+	return nth_sock_idx;
+}
+
+static void destroy(int fd)
+{
+	struct sock_iter_batch *skel = NULL;
+	__u64 cookie = socket_cookie(fd);
+	struct bpf_link *link = NULL;
+	int iter_fd = -1;
+	int nread;
+	__u64 out;
+
+	skel = sock_iter_batch__open();
+	if (!ASSERT_OK_PTR(skel, "sock_iter_batch__open"))
+		goto done;
+
+	skel->rodata->destroy_cookie = cookie;
+
+	if (!ASSERT_OK(sock_iter_batch__load(skel), "sock_iter_batch__load"))
+		goto done;
+
+	link = bpf_program__attach_iter(skel->progs.iter_tcp_destroy, NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_iter"))
+		goto done;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (!ASSERT_OK_FD(iter_fd, "bpf_iter_create"))
+		goto done;
+
+	/* Delete matching socket. */
+	nread = read(iter_fd, &out, sizeof(out));
+	ASSERT_GE(nread, 0, "nread");
+	if (nread)
+		ASSERT_EQ(out, cookie, "cookie matches");
+done:
+	if (iter_fd >= 0)
+		close(iter_fd);
+	bpf_link__destroy(link);
+	sock_iter_batch__destroy(skel);
+	close(fd);
+}
+
+static int get_seen_count(int fd, struct sock_count counts[], int n)
+{
+	__u64 cookie = socket_cookie(fd);
+	int count = 0;
+	int i = 0;
+
+	for (; cookie && !count && i < n; i++)
+		if (cookie == counts[i].cookie)
+			count = counts[i].count;
+
+	return count;
+}
+
+static void check_n_were_seen_once(int *fds, int fds_len, int n,
+				   struct sock_count counts[], int counts_len)
+{
+	int seen_once = 0;
+	int seen_cnt;
+	int i = 0;
+
+	for (; i < fds_len; i++) {
+		/* Skip any sockets that were closed or that weren't seen
+		 * exactly once.
+		 */
+		if (fds[i] < 0)
+			continue;
+		seen_cnt = get_seen_count(fds[i], counts, counts_len);
+		if (seen_cnt && ASSERT_EQ(seen_cnt, 1, "seen_cnt"))
+			seen_once++;
+	}
+
+	ASSERT_EQ(seen_once, n, "seen_once");
+}
+
+static int accept_from_one(struct pollfd *server_poll_fds,
+			   int server_poll_fds_len)
+{
+	static const int poll_timeout_ms = 5000; /* 5s */
+	int ret;
+	int i;
+
+	ret = poll(server_poll_fds, server_poll_fds_len, poll_timeout_ms);
+	if (!ASSERT_EQ(ret, 1, "poll"))
+		return -1;
+
+	for (i = 0; i < server_poll_fds_len; i++)
+		if (server_poll_fds[i].revents & POLLIN)
+			return accept(server_poll_fds[i].fd, NULL, NULL);
+
+	return -1;
+}
+
+static int *connect_to_server(int family, int sock_type, const char *addr,
+			      __u16 port, int nr_connects, int *server_fds,
+			      int server_fds_len)
+{
+	struct pollfd *server_poll_fds = NULL;
+	int *established_socks = NULL;
+	int i;
+
+	server_poll_fds = calloc(server_fds_len, sizeof(*server_poll_fds));
+	if (!ASSERT_OK_PTR(server_poll_fds, "server_poll_fds"))
+		return NULL;
+
+	for (i = 0; i < server_fds_len; i++) {
+		server_poll_fds[i].fd = server_fds[i];
+		server_poll_fds[i].events = POLLIN;
+	}
+
+	i = 0;
+
+	established_socks = malloc(sizeof(*established_socks) * nr_connects*2);
+	if (!ASSERT_OK_PTR(established_socks, "established_socks"))
+		goto error;
+
+	while (nr_connects--) {
+		established_socks[i] = connect_to_addr_str(family, sock_type,
+							   addr, port, NULL);
+		if (!ASSERT_OK_FD(established_socks[i], "connect_to_addr_str"))
+			goto error;
+		i++;
+		established_socks[i] = accept_from_one(server_poll_fds,
+						       server_fds_len);
+		if (!ASSERT_OK_FD(established_socks[i], "accept_from_one"))
+			goto error;
+		i++;
+	}
+
+	free(server_poll_fds);
+	return established_socks;
+error:
+	free_fds(established_socks, i);
+	free(server_poll_fds);
+	return NULL;
+}
+
+static void remove_seen(int family, int sock_type, const char *addr, __u16 port,
+			int *socks, int socks_len, int *established_socks,
+			int established_socks_len, struct sock_count *counts,
+			int counts_len, struct bpf_link *link, int iter_fd)
+{
+	int close_idx;
+
+	/* Iterate through the first socks_len - 1 sockets. */
+	read_n(iter_fd, socks_len - 1, counts, counts_len);
+
+	/* Make sure we saw socks_len - 1 sockets exactly once. */
+	check_n_were_seen_once(socks, socks_len, socks_len - 1, counts,
+			       counts_len);
+
+	/* Close a socket we've already seen to remove it from the bucket. */
+	close_idx = get_seen_socket(socks, counts, counts_len);
+	if (!ASSERT_GE(close_idx, 0, "close_idx"))
+		return;
+	close(socks[close_idx]);
+	socks[close_idx] = -1;
+
+	/* Iterate through the rest of the sockets. */
+	read_n(iter_fd, -1, counts, counts_len);
+
+	/* Make sure the last socket wasn't skipped and that there were no
+	 * repeats.
+	 */
+	check_n_were_seen_once(socks, socks_len, socks_len - 1, counts,
+			       counts_len);
+}
+
+static void remove_seen_established(int family, int sock_type, const char *addr,
+				    __u16 port, int *listen_socks,
+				    int listen_socks_len, int *established_socks,
+				    int established_socks_len,
+				    struct sock_count *counts, int counts_len,
+				    struct bpf_link *link, int iter_fd)
+{
+	int close_idx;
+
+	/* Iterate through all listening sockets. */
+	read_n(iter_fd, listen_socks_len, counts, counts_len);
+
+	/* Make sure we saw all listening sockets exactly once. */
+	check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len,
+			       counts, counts_len);
+
+	/* Leave one established socket. */
+	read_n(iter_fd, established_socks_len - 1, counts, counts_len);
+
+	/* Close a socket we've already seen to remove it from the bucket. */
+	close_idx = get_nth_socket(established_socks, established_socks_len,
+				   link, listen_socks_len + 1);
+	if (!ASSERT_GE(close_idx, 0, "close_idx"))
+		return;
+	destroy(established_socks[close_idx]);
+	established_socks[close_idx] = -1;
+
+	/* Iterate through the rest of the sockets. */
+	read_n(iter_fd, -1, counts, counts_len);
+
+	/* Make sure the last socket wasn't skipped and that there were no
+	 * repeats.
+	 */
+	check_n_were_seen_once(established_socks, established_socks_len,
+			       established_socks_len - 1, counts, counts_len);
+}
+
+static void remove_unseen(int family, int sock_type, const char *addr,
+			  __u16 port, int *socks, int socks_len,
+			  int *established_socks, int established_socks_len,
+			  struct sock_count *counts, int counts_len,
+			  struct bpf_link *link, int iter_fd)
+{
+	int close_idx;
+
+	/* Iterate through the first socket. */
+	read_n(iter_fd, 1, counts, counts_len);
+
+	/* Make sure we saw a socket from fds. */
+	check_n_were_seen_once(socks, socks_len, 1, counts, counts_len);
+
+	/* Close what would be the next socket in the bucket to exercise the
+	 * condition where we need to skip past the first cookie we remembered.
+	 */
+	close_idx = get_nth_socket(socks, socks_len, link, 1);
+	if (!ASSERT_GE(close_idx, 0, "close_idx"))
+		return;
+	close(socks[close_idx]);
+	socks[close_idx] = -1;
+
+	/* Iterate through the rest of the sockets. */
+	read_n(iter_fd, -1, counts, counts_len);
+
+	/* Make sure the remaining sockets were seen exactly once and that we
+	 * didn't repeat the socket that was already seen.
+	 */
+	check_n_were_seen_once(socks, socks_len, socks_len - 1, counts,
+			       counts_len);
+}
+
+static void remove_unseen_established(int family, int sock_type,
+				      const char *addr, __u16 port,
+				      int *listen_socks, int listen_socks_len,
+				      int *established_socks,
+				      int established_socks_len,
+				      struct sock_count *counts, int counts_len,
+				      struct bpf_link *link, int iter_fd)
+{
+	int close_idx;
+
+	/* Iterate through all listening sockets. */
+	read_n(iter_fd, listen_socks_len, counts, counts_len);
+
+	/* Make sure we saw all listening sockets exactly once. */
+	check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len,
+			       counts, counts_len);
+
+	/* Iterate through the first established socket. */
+	read_n(iter_fd, 1, counts, counts_len);
+
+	/* Make sure we saw one established socks. */
+	check_n_were_seen_once(established_socks, established_socks_len, 1,
+			       counts, counts_len);
+
+	/* Close what would be the next socket in the bucket to exercise the
+	 * condition where we need to skip past the first cookie we remembered.
+	 */
+	close_idx = get_nth_socket(established_socks, established_socks_len,
+				   link, listen_socks_len + 1);
+	if (!ASSERT_GE(close_idx, 0, "close_idx"))
+		return;
+
+	destroy(established_socks[close_idx]);
+	established_socks[close_idx] = -1;
+
+	/* Iterate through the rest of the sockets. */
+	read_n(iter_fd, -1, counts, counts_len);
+
+	/* Make sure the remaining sockets were seen exactly once and that we
+	 * didn't repeat the socket that was already seen.
+	 */
+	check_n_were_seen_once(established_socks, established_socks_len,
+			       established_socks_len - 1, counts, counts_len);
+}
+
+static void remove_all(int family, int sock_type, const char *addr,
+		       __u16 port, int *socks, int socks_len,
+		       int *established_socks, int established_socks_len,
+		       struct sock_count *counts, int counts_len,
+		       struct bpf_link *link, int iter_fd)
+{
+	int close_idx, i;
+
+	/* Iterate through the first socket. */
+	read_n(iter_fd, 1, counts, counts_len);
+
+	/* Make sure we saw a socket from fds. */
+	check_n_were_seen_once(socks, socks_len, 1, counts, counts_len);
+
+	/* Close all remaining sockets to exhaust the list of saved cookies and
+	 * exit without putting any sockets into the batch on the next read.
+	 */
+	for (i = 0; i < socks_len - 1; i++) {
+		close_idx = get_nth_socket(socks, socks_len, link, 1);
+		if (!ASSERT_GE(close_idx, 0, "close_idx"))
+			return;
+		close(socks[close_idx]);
+		socks[close_idx] = -1;
+	}
+
+	/* Make sure there are no more sockets returned */
+	ASSERT_EQ(read_n(iter_fd, -1, counts, counts_len), 0, "read_n");
+}
+
+static void remove_all_established(int family, int sock_type, const char *addr,
+				   __u16 port, int *listen_socks,
+				   int listen_socks_len, int *established_socks,
+				   int established_socks_len,
+				   struct sock_count *counts, int counts_len,
+				   struct bpf_link *link, int iter_fd)
+{
+	int *close_idx = NULL;
+	int i;
+
+	/* Iterate through all listening sockets. */
+	read_n(iter_fd, listen_socks_len, counts, counts_len);
+
+	/* Make sure we saw all listening sockets exactly once. */
+	check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len,
+			       counts, counts_len);
+
+	/* Iterate through the first established socket. */
+	read_n(iter_fd, 1, counts, counts_len);
+
+	/* Make sure we saw one established socks. */
+	check_n_were_seen_once(established_socks, established_socks_len, 1,
+			       counts, counts_len);
+
+	/* Close all remaining sockets to exhaust the list of saved cookies and
+	 * exit without putting any sockets into the batch on the next read.
+	 */
+	close_idx = malloc(sizeof(int) * (established_socks_len - 1));
+	if (!ASSERT_OK_PTR(close_idx, "close_idx malloc"))
+		return;
+	for (i = 0; i < established_socks_len - 1; i++) {
+		close_idx[i] = get_nth_socket(established_socks,
+					      established_socks_len, link,
+					      listen_socks_len + i);
+		if (!ASSERT_GE(close_idx[i], 0, "close_idx"))
+			return;
+	}
+
+	for (i = 0; i < established_socks_len - 1; i++) {
+		destroy(established_socks[close_idx[i]]);
+		established_socks[close_idx[i]] = -1;
+	}
+
+	/* Make sure there are no more sockets returned */
+	ASSERT_EQ(read_n(iter_fd, -1, counts, counts_len), 0, "read_n");
+	free(close_idx);
+}
+
+static void add_some(int family, int sock_type, const char *addr, __u16 port,
+		     int *socks, int socks_len, int *established_socks,
+		     int established_socks_len, struct sock_count *counts,
+		     int counts_len, struct bpf_link *link, int iter_fd)
+{
+	int *new_socks = NULL;
+
+	/* Iterate through the first socks_len - 1 sockets. */
+	read_n(iter_fd, socks_len - 1, counts, counts_len);
+
+	/* Make sure we saw socks_len - 1 sockets exactly once. */
+	check_n_were_seen_once(socks, socks_len, socks_len - 1, counts,
+			       counts_len);
+
+	/* Double the number of sockets in the bucket. */
+	new_socks = start_reuseport_server(family, sock_type, addr, port, 0,
+					   socks_len);
+	if (!ASSERT_OK_PTR(new_socks, "start_reuseport_server"))
+		goto done;
+
+	/* Iterate through the rest of the sockets. */
+	read_n(iter_fd, -1, counts, counts_len);
+
+	/* Make sure each of the original sockets was seen exactly once. */
+	check_n_were_seen_once(socks, socks_len, socks_len, counts,
+			       counts_len);
+done:
+	free_fds(new_socks, socks_len);
+}
+
+static void add_some_established(int family, int sock_type, const char *addr,
+				 __u16 port, int *listen_socks,
+				 int listen_socks_len, int *established_socks,
+				 int established_socks_len,
+				 struct sock_count *counts,
+				 int counts_len, struct bpf_link *link,
+				 int iter_fd)
+{
+	int *new_socks = NULL;
+
+	/* Iterate through all listening sockets. */
+	read_n(iter_fd, listen_socks_len, counts, counts_len);
+
+	/* Make sure we saw all listening sockets exactly once. */
+	check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len,
+			       counts, counts_len);
+
+	/* Iterate through the first established_socks_len - 1 sockets. */
+	read_n(iter_fd, established_socks_len - 1, counts, counts_len);
+
+	/* Make sure we saw established_socks_len - 1 sockets exactly once. */
+	check_n_were_seen_once(established_socks, established_socks_len,
+			       established_socks_len - 1, counts, counts_len);
+
+	/* Double the number of established sockets in the bucket. */
+	new_socks = connect_to_server(family, sock_type, addr, port,
+				      established_socks_len / 2, listen_socks,
+				      listen_socks_len);
+	if (!ASSERT_OK_PTR(new_socks, "connect_to_server"))
+		goto done;
+
+	/* Iterate through the rest of the sockets. */
+	read_n(iter_fd, -1, counts, counts_len);
+
+	/* Make sure each of the original sockets was seen exactly once. */
+	check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len,
+			       counts, counts_len);
+	check_n_were_seen_once(established_socks, established_socks_len,
+			       established_socks_len, counts, counts_len);
+done:
+	free_fds(new_socks, established_socks_len);
+}
+
+static void force_realloc(int family, int sock_type, const char *addr,
+			  __u16 port, int *socks, int socks_len,
+			  int *established_socks, int established_socks_len,
+			  struct sock_count *counts, int counts_len,
+			  struct bpf_link *link, int iter_fd)
+{
+	int *new_socks = NULL;
+
+	/* Iterate through the first socket just to initialize the batch. */
+	read_n(iter_fd, 1, counts, counts_len);
+
+	/* Double the number of sockets in the bucket to force a realloc on the
+	 * next read.
+	 */
+	new_socks = start_reuseport_server(family, sock_type, addr, port, 0,
+					   socks_len);
+	if (!ASSERT_OK_PTR(new_socks, "start_reuseport_server"))
+		goto done;
+
+	/* Iterate through the rest of the sockets. */
+	read_n(iter_fd, -1, counts, counts_len);
+
+	/* Make sure each socket from the first set was seen exactly once. */
+	check_n_were_seen_once(socks, socks_len, socks_len, counts,
+			       counts_len);
+done:
+	free_fds(new_socks, socks_len);
+}
+
+static void force_realloc_established(int family, int sock_type,
+				      const char *addr, __u16 port,
+				      int *listen_socks, int listen_socks_len,
+				      int *established_socks,
+				      int established_socks_len,
+				      struct sock_count *counts, int counts_len,
+				      struct bpf_link *link, int iter_fd)
+{
+	/* Iterate through all sockets to trigger a realloc. */
+	read_n(iter_fd, -1, counts, counts_len);
+
+	/* Make sure each socket was seen exactly once. */
+	check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len,
+			       counts, counts_len);
+	check_n_were_seen_once(established_socks, established_socks_len,
+			       established_socks_len, counts, counts_len);
+}
+
+struct test_case {
+	void (*test)(int family, int sock_type, const char *addr, __u16 port,
+		     int *socks, int socks_len, int *established_socks,
+		     int established_socks_len, struct sock_count *counts,
+		     int counts_len, struct bpf_link *link, int iter_fd);
+	const char *description;
+	int ehash_buckets;
+	int connections;
+	int init_socks;
+	int max_socks;
+	int sock_type;
+	int family;
+};
+
+static struct test_case resume_tests[] = {
+	{
+		.description = "udp: resume after removing a seen socket",
+		.init_socks = nr_soreuse,
+		.max_socks = nr_soreuse,
+		.sock_type = SOCK_DGRAM,
+		.family = AF_INET6,
+		.test = remove_seen,
+	},
+	{
+		.description = "udp: resume after removing one unseen socket",
+		.init_socks = nr_soreuse,
+		.max_socks = nr_soreuse,
+		.sock_type = SOCK_DGRAM,
+		.family = AF_INET6,
+		.test = remove_unseen,
+	},
+	{
+		.description = "udp: resume after removing all unseen sockets",
+		.init_socks = nr_soreuse,
+		.max_socks = nr_soreuse,
+		.sock_type = SOCK_DGRAM,
+		.family = AF_INET6,
+		.test = remove_all,
+	},
+	{
+		.description = "udp: resume after adding a few sockets",
+		.init_socks = nr_soreuse,
+		.max_socks = nr_soreuse,
+		.sock_type = SOCK_DGRAM,
+		/* Use AF_INET so that new sockets are added to the head of the
+		 * bucket's list.
+		 */
+		.family = AF_INET,
+		.test = add_some,
+	},
+	{
+		.description = "udp: force a realloc to occur",
+		.init_socks = init_batch_size,
+		.max_socks = init_batch_size * 2,
+		.sock_type = SOCK_DGRAM,
+		/* Use AF_INET6 so that new sockets are added to the tail of the
+		 * bucket's list, needing to be added to the next batch to force
+		 * a realloc.
+		 */
+		.family = AF_INET6,
+		.test = force_realloc,
+	},
+	{
+		.description = "tcp: resume after removing a seen socket (listening)",
+		.init_socks = nr_soreuse,
+		.max_socks = nr_soreuse,
+		.sock_type = SOCK_STREAM,
+		.family = AF_INET6,
+		.test = remove_seen,
+	},
+	{
+		.description = "tcp: resume after removing one unseen socket (listening)",
+		.init_socks = nr_soreuse,
+		.max_socks = nr_soreuse,
+		.sock_type = SOCK_STREAM,
+		.family = AF_INET6,
+		.test = remove_unseen,
+	},
+	{
+		.description = "tcp: resume after removing all unseen sockets (listening)",
+		.init_socks = nr_soreuse,
+		.max_socks = nr_soreuse,
+		.sock_type = SOCK_STREAM,
+		.family = AF_INET6,
+		.test = remove_all,
+	},
+	{
+		.description = "tcp: resume after adding a few sockets (listening)",
+		.init_socks = nr_soreuse,
+		.max_socks = nr_soreuse,
+		.sock_type = SOCK_STREAM,
+		/* Use AF_INET so that new sockets are added to the head of the
+		 * bucket's list.
+		 */
+		.family = AF_INET,
+		.test = add_some,
+	},
+	{
+		.description = "tcp: force a realloc to occur (listening)",
+		.init_socks = init_batch_size,
+		.max_socks = init_batch_size * 2,
+		.sock_type = SOCK_STREAM,
+		/* Use AF_INET6 so that new sockets are added to the tail of the
+		 * bucket's list, needing to be added to the next batch to force
+		 * a realloc.
+		 */
+		.family = AF_INET6,
+		.test = force_realloc,
+	},
+	{
+		.description = "tcp: resume after removing a seen socket (established)",
+		/* Force all established sockets into one bucket */
+		.ehash_buckets = 1,
+		.connections = nr_soreuse,
+		.init_socks = nr_soreuse,
+		/* Room for connect()ed and accept()ed sockets */
+		.max_socks = nr_soreuse * 3,
+		.sock_type = SOCK_STREAM,
+		.family = AF_INET6,
+		.test = remove_seen_established,
+	},
+	{
+		.description = "tcp: resume after removing one unseen socket (established)",
+		/* Force all established sockets into one bucket */
+		.ehash_buckets = 1,
+		.connections = nr_soreuse,
+		.init_socks = nr_soreuse,
+		/* Room for connect()ed and accept()ed sockets */
+		.max_socks = nr_soreuse * 3,
+		.sock_type = SOCK_STREAM,
+		.family = AF_INET6,
+		.test = remove_unseen_established,
+	},
+	{
+		.description = "tcp: resume after removing all unseen sockets (established)",
+		/* Force all established sockets into one bucket */
+		.ehash_buckets = 1,
+		.connections = nr_soreuse,
+		.init_socks = nr_soreuse,
+		/* Room for connect()ed and accept()ed sockets */
+		.max_socks = nr_soreuse * 3,
+		.sock_type = SOCK_STREAM,
+		.family = AF_INET6,
+		.test = remove_all_established,
+	},
+	{
+		.description = "tcp: resume after adding a few sockets (established)",
+		/* Force all established sockets into one bucket */
+		.ehash_buckets = 1,
+		.connections = nr_soreuse,
+		.init_socks = nr_soreuse,
+		/* Room for connect()ed and accept()ed sockets */
+		.max_socks = nr_soreuse * 3,
+		.sock_type = SOCK_STREAM,
+		.family = AF_INET6,
+		.test = add_some_established,
+	},
+	{
+		.description = "tcp: force a realloc to occur (established)",
+		/* Force all established sockets into one bucket */
+		.ehash_buckets = 1,
+		/* Bucket size will need to double when going from listening to
+		 * established sockets.
+		 */
+		.connections = init_batch_size,
+		.init_socks = nr_soreuse,
+		/* Room for connect()ed and accept()ed sockets */
+		.max_socks = nr_soreuse + (init_batch_size * 2),
+		.sock_type = SOCK_STREAM,
+		.family = AF_INET6,
+		.test = force_realloc_established,
+	},
+};
+
+static void do_resume_test(struct test_case *tc)
+{
+	struct sock_iter_batch *skel = NULL;
+	struct sock_count *counts = NULL;
+	static const __u16 port = 10001;
+	struct nstoken *nstoken = NULL;
+	struct bpf_link *link = NULL;
+	int *established_fds = NULL;
+	int err, iter_fd = -1;
+	const char *addr;
+	int *fds = NULL;
+
+	if (tc->ehash_buckets) {
+		SYS_NOFAIL("ip netns del " TEST_CHILD_NS);
+		SYS(done, "sysctl -wq net.ipv4.tcp_child_ehash_entries=%d",
+		    tc->ehash_buckets);
+		SYS(done, "ip netns add %s", TEST_CHILD_NS);
+		SYS(done, "ip -net %s link set dev lo up", TEST_CHILD_NS);
+		nstoken = open_netns(TEST_CHILD_NS);
+		if (!ASSERT_OK_PTR(nstoken, "open_child_netns"))
+			goto done;
+	}
+
+	counts = calloc(tc->max_socks, sizeof(*counts));
+	if (!ASSERT_OK_PTR(counts, "counts"))
+		goto done;
+	skel = sock_iter_batch__open();
+	if (!ASSERT_OK_PTR(skel, "sock_iter_batch__open"))
+		goto done;
+
+	/* Prepare a bucket of sockets in the kernel hashtable */
+	addr = tc->family == AF_INET6 ? "::1" : "127.0.0.1";
+	fds = start_reuseport_server(tc->family, tc->sock_type, addr, port, 0,
+				     tc->init_socks);
+	if (!ASSERT_OK_PTR(fds, "start_reuseport_server"))
+		goto done;
+	if (tc->connections) {
+		established_fds = connect_to_server(tc->family, tc->sock_type,
+						    addr, port,
+						    tc->connections, fds,
+						    tc->init_socks);
+		if (!ASSERT_OK_PTR(established_fds, "connect_to_server"))
+			goto done;
+	}
+	skel->rodata->ports[0] = 0;
+	skel->rodata->ports[1] = 0;
+	skel->rodata->sf = tc->family;
+	skel->rodata->ss = 0;
+
+	err = sock_iter_batch__load(skel);
+	if (!ASSERT_OK(err, "sock_iter_batch__load"))
+		goto done;
+
+	link = bpf_program__attach_iter(tc->sock_type == SOCK_STREAM ?
+					skel->progs.iter_tcp_soreuse :
+					skel->progs.iter_udp_soreuse,
+					NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_iter"))
+		goto done;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (!ASSERT_OK_FD(iter_fd, "bpf_iter_create"))
+		goto done;
+
+	tc->test(tc->family, tc->sock_type, addr, port, fds, tc->init_socks,
+		 established_fds, tc->connections*2, counts, tc->max_socks,
+		 link, iter_fd);
+done:
+	close_netns(nstoken);
+	SYS_NOFAIL("ip netns del " TEST_CHILD_NS);
+	SYS_NOFAIL("sysctl -w net.ipv4.tcp_child_ehash_entries=0");
+	free(counts);
+	free_fds(fds, tc->init_socks);
+	free_fds(established_fds, tc->connections*2);
+	if (iter_fd >= 0)
+		close(iter_fd);
+	bpf_link__destroy(link);
+	sock_iter_batch__destroy(skel);
+}
+
+static void do_resume_tests(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(resume_tests); i++) {
+		if (test__start_subtest(resume_tests[i].description)) {
+			do_resume_test(&resume_tests[i]);
+		}
+	}
+}
+
+static void do_test(int sock_type, bool onebyone)
+{
+	int err, i, nread, to_read, total_read, iter_fd = -1;
+	struct iter_out outputs[nr_soreuse];
+	struct bpf_link *link = NULL;
+	struct sock_iter_batch *skel;
+	int first_idx, second_idx;
+	int *fds[2] = {};
+
+	skel = sock_iter_batch__open();
+	if (!ASSERT_OK_PTR(skel, "sock_iter_batch__open"))
+		return;
+
+	/* Prepare 2 buckets of sockets in the kernel hashtable */
+	for (i = 0; i < ARRAY_SIZE(fds); i++) {
+		int local_port;
+
+		fds[i] = start_reuseport_server(AF_INET6, sock_type, "::1", 0, 0,
+						nr_soreuse);
+		if (!ASSERT_OK_PTR(fds[i], "start_reuseport_server"))
+			goto done;
+		local_port = get_socket_local_port(*fds[i]);
+		if (!ASSERT_GE(local_port, 0, "get_socket_local_port"))
+			goto done;
+		skel->rodata->ports[i] = ntohs(local_port);
+	}
+	skel->rodata->sf = AF_INET6;
+	if (sock_type == SOCK_STREAM)
+		skel->rodata->ss = TCP_LISTEN;
+
+	err = sock_iter_batch__load(skel);
+	if (!ASSERT_OK(err, "sock_iter_batch__load"))
+		goto done;
+
+	link = bpf_program__attach_iter(sock_type == SOCK_STREAM ?
+					skel->progs.iter_tcp_soreuse :
+					skel->progs.iter_udp_soreuse,
+					NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_iter"))
+		goto done;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (!ASSERT_GE(iter_fd, 0, "bpf_iter_create"))
+		goto done;
+
+	/* Test reading a bucket (either from fds[0] or fds[1]).
+	 * Only read "nr_soreuse - 1" number of sockets
+	 * from a bucket and leave one socket out from
+	 * that bucket on purpose.
+	 */
+	to_read = (nr_soreuse - 1) * sizeof(*outputs);
+	total_read = 0;
+	first_idx = -1;
+	do {
+		nread = read(iter_fd, outputs, onebyone ? sizeof(*outputs) : to_read);
+		if (nread <= 0 || nread % sizeof(*outputs))
+			break;
+		total_read += nread;
+
+		if (first_idx == -1)
+			first_idx = outputs[0].idx;
+		for (i = 0; i < nread / sizeof(*outputs); i++)
+			ASSERT_EQ(outputs[i].idx, first_idx, "first_idx");
+	} while (total_read < to_read);
+	ASSERT_EQ(nread, onebyone ? sizeof(*outputs) : to_read, "nread");
+	ASSERT_EQ(total_read, to_read, "total_read");
+
+	free_fds(fds[first_idx], nr_soreuse);
+	fds[first_idx] = NULL;
+
+	/* Read the "whole" second bucket */
+	to_read = nr_soreuse * sizeof(*outputs);
+	total_read = 0;
+	second_idx = !first_idx;
+	do {
+		nread = read(iter_fd, outputs, onebyone ? sizeof(*outputs) : to_read);
+		if (nread <= 0 || nread % sizeof(*outputs))
+			break;
+		total_read += nread;
+
+		for (i = 0; i < nread / sizeof(*outputs); i++)
+			ASSERT_EQ(outputs[i].idx, second_idx, "second_idx");
+	} while (total_read <= to_read);
+	ASSERT_EQ(nread, 0, "nread");
+	/* Both so_reuseport ports should be in different buckets, so
+	 * total_read must equal to the expected to_read.
+	 *
+	 * For a very unlikely case, both ports collide at the same bucket,
+	 * the bucket offset (i.e. 3) will be skipped and it cannot
+	 * expect the to_read number of bytes.
+	 */
+	if (skel->bss->bucket[0] != skel->bss->bucket[1])
+		ASSERT_EQ(total_read, to_read, "total_read");
+
+done:
+	for (i = 0; i < ARRAY_SIZE(fds); i++)
+		free_fds(fds[i], nr_soreuse);
+	if (iter_fd < 0)
+		close(iter_fd);
+	bpf_link__destroy(link);
+	sock_iter_batch__destroy(skel);
+}
+
+void test_sock_iter_batch(void)
+{
+	struct nstoken *nstoken = NULL;
+
+	SYS_NOFAIL("ip netns del " TEST_NS);
+	SYS(done, "ip netns add %s", TEST_NS);
+	SYS(done, "ip -net %s link set dev lo up", TEST_NS);
+
+	nstoken = open_netns(TEST_NS);
+	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+		goto done;
+
+	if (test__start_subtest("tcp")) {
+		do_test(SOCK_STREAM, true);
+		do_test(SOCK_STREAM, false);
+	}
+	if (test__start_subtest("udp")) {
+		do_test(SOCK_DGRAM, true);
+		do_test(SOCK_DGRAM, false);
+	}
+	do_resume_tests();
+	close_netns(nstoken);
+
+done:
+	SYS_NOFAIL("ip netns del " TEST_NS);
+}
diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/prog_tests/sock_post_bind.c
index 810c3740b2cc..788135c9c673 100644
--- a/tools/testing/selftests/bpf/test_sock.c
+++ b/tools/testing/selftests/bpf/prog_tests/sock_post_bind.c
@@ -1,132 +1,35 @@
 // SPDX-License-Identifier: GPL-2.0
-// Copyright (c) 2018 Facebook
-
-#include <stdio.h>
-#include <unistd.h>
-
-#include <arpa/inet.h>
-#include <sys/types.h>
-#include <sys/socket.h>
-
-#include <linux/filter.h>
-
-#include <bpf/bpf.h>
-
+#include <linux/bpf.h>
+#include <test_progs.h>
 #include "cgroup_helpers.h"
-#include <bpf/bpf_endian.h>
-#include "bpf_util.h"
 
-#define CG_PATH		"/foo"
-#define MAX_INSNS	512
+#define TEST_NS "sock_post_bind"
 
-char bpf_log_buf[BPF_LOG_BUF_SIZE];
-static bool verbose = false;
+static char bpf_log_buf[4096];
 
-struct sock_test {
-	const char *descr;
+static struct sock_post_bind_test {
+	const char			*descr;
 	/* BPF prog properties */
-	struct bpf_insn	insns[MAX_INSNS];
-	enum bpf_attach_type expected_attach_type;
-	enum bpf_attach_type attach_type;
+	const struct bpf_insn		insns[64];
+	enum bpf_attach_type		attach_type;
+	enum bpf_attach_type		expected_attach_type;
 	/* Socket properties */
-	int domain;
-	int type;
+	int				domain;
+	int				type;
 	/* Endpoint to bind() to */
 	const char *ip;
 	unsigned short port;
 	unsigned short port_retry;
+
 	/* Expected test result */
 	enum {
-		LOAD_REJECT,
 		ATTACH_REJECT,
 		BIND_REJECT,
 		SUCCESS,
 		RETRY_SUCCESS,
 		RETRY_REJECT
 	} result;
-};
-
-static struct sock_test tests[] = {
-	{
-		.descr = "bind4 load with invalid access: src_ip6",
-		.insns = {
-			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
-				    offsetof(struct bpf_sock, src_ip6[0])),
-			BPF_MOV64_IMM(BPF_REG_0, 1),
-			BPF_EXIT_INSN(),
-		},
-		.expected_attach_type = BPF_CGROUP_INET4_POST_BIND,
-		.attach_type = BPF_CGROUP_INET4_POST_BIND,
-		.result = LOAD_REJECT,
-	},
-	{
-		.descr = "bind4 load with invalid access: mark",
-		.insns = {
-			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
-				    offsetof(struct bpf_sock, mark)),
-			BPF_MOV64_IMM(BPF_REG_0, 1),
-			BPF_EXIT_INSN(),
-		},
-		.expected_attach_type = BPF_CGROUP_INET4_POST_BIND,
-		.attach_type = BPF_CGROUP_INET4_POST_BIND,
-		.result = LOAD_REJECT,
-	},
-	{
-		.descr = "bind6 load with invalid access: src_ip4",
-		.insns = {
-			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
-				    offsetof(struct bpf_sock, src_ip4)),
-			BPF_MOV64_IMM(BPF_REG_0, 1),
-			BPF_EXIT_INSN(),
-		},
-		.expected_attach_type = BPF_CGROUP_INET6_POST_BIND,
-		.attach_type = BPF_CGROUP_INET6_POST_BIND,
-		.result = LOAD_REJECT,
-	},
-	{
-		.descr = "sock_create load with invalid access: src_port",
-		.insns = {
-			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
-				    offsetof(struct bpf_sock, src_port)),
-			BPF_MOV64_IMM(BPF_REG_0, 1),
-			BPF_EXIT_INSN(),
-		},
-		.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE,
-		.attach_type = BPF_CGROUP_INET_SOCK_CREATE,
-		.result = LOAD_REJECT,
-	},
-	{
-		.descr = "sock_create load w/o expected_attach_type (compat mode)",
-		.insns = {
-			BPF_MOV64_IMM(BPF_REG_0, 1),
-			BPF_EXIT_INSN(),
-		},
-		.expected_attach_type = 0,
-		.attach_type = BPF_CGROUP_INET_SOCK_CREATE,
-		.domain = AF_INET,
-		.type = SOCK_STREAM,
-		.ip = "127.0.0.1",
-		.port = 8097,
-		.result = SUCCESS,
-	},
-	{
-		.descr = "sock_create load w/ expected_attach_type",
-		.insns = {
-			BPF_MOV64_IMM(BPF_REG_0, 1),
-			BPF_EXIT_INSN(),
-		},
-		.expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE,
-		.attach_type = BPF_CGROUP_INET_SOCK_CREATE,
-		.domain = AF_INET,
-		.type = SOCK_STREAM,
-		.ip = "127.0.0.1",
-		.port = 8097,
-		.result = SUCCESS,
-	},
+} tests[] = {
 	{
 		.descr = "attach type mismatch bind4 vs bind6",
 		.insns = {
@@ -374,40 +277,29 @@ static struct sock_test tests[] = {
 	},
 };
 
-static size_t probe_prog_length(const struct bpf_insn *fp)
-{
-	size_t len;
-
-	for (len = MAX_INSNS - 1; len > 0; --len)
-		if (fp[len].code != 0 || fp[len].imm != 0)
-			break;
-	return len + 1;
-}
-
-static int load_sock_prog(const struct bpf_insn *prog,
-			  enum bpf_attach_type attach_type)
+static int load_prog(const struct bpf_insn *insns,
+		     enum bpf_attach_type expected_attach_type)
 {
-	LIBBPF_OPTS(bpf_prog_load_opts, opts);
-	int ret, insn_cnt;
-
-	insn_cnt = probe_prog_length(prog);
-
-	opts.expected_attach_type = attach_type;
-	opts.log_buf = bpf_log_buf;
-	opts.log_size = BPF_LOG_BUF_SIZE;
-	opts.log_level = 2;
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		    .expected_attach_type = expected_attach_type,
+		    .log_level = 2,
+		    .log_buf = bpf_log_buf,
+		    .log_size = sizeof(bpf_log_buf),
+	);
+	int fd, insns_cnt = 0;
+
+	for (;
+	     insns[insns_cnt].code != (BPF_JMP | BPF_EXIT);
+	     insns_cnt++) {
+	}
+	insns_cnt++;
 
-	ret = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", prog, insn_cnt, &opts);
-	if (verbose && ret < 0)
+	fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, NULL, "GPL", insns,
+			   insns_cnt, &opts);
+	if (fd < 0)
 		fprintf(stderr, "%s\n", bpf_log_buf);
 
-	return ret;
-}
-
-static int attach_sock_prog(int cgfd, int progfd,
-			    enum bpf_attach_type attach_type)
-{
-	return bpf_prog_attach(progfd, cgfd, attach_type, BPF_F_ALLOW_OVERRIDE);
+	return fd;
 }
 
 static int bind_sock(int domain, int type, const char *ip,
@@ -477,22 +369,16 @@ out:
 	return res;
 }
 
-static int run_test_case(int cgfd, const struct sock_test *test)
+static int run_test(int cgroup_fd, struct sock_post_bind_test *test)
 {
-	int progfd = -1;
-	int err = 0;
-	int res;
-
-	printf("Test case: %s .. ", test->descr);
-	progfd = load_sock_prog(test->insns, test->expected_attach_type);
-	if (progfd < 0) {
-		if (test->result == LOAD_REJECT)
-			goto out;
-		else
-			goto err;
-	}
+	int err, prog_fd, res, ret = 0;
 
-	if (attach_sock_prog(cgfd, progfd, test->attach_type) < 0) {
+	prog_fd = load_prog(test->insns, test->expected_attach_type);
+	if (prog_fd < 0)
+		goto err;
+
+	err = bpf_prog_attach(prog_fd, cgroup_fd, test->attach_type, 0);
+	if (err < 0) {
 		if (test->result == ATTACH_REJECT)
 			goto out;
 		else
@@ -503,54 +389,38 @@ static int run_test_case(int cgfd, const struct sock_test *test)
 			test->port_retry);
 	if (res > 0 && test->result == res)
 		goto out;
-
 err:
-	err = -1;
+	ret = -1;
 out:
 	/* Detaching w/o checking return code: best effort attempt. */
-	if (progfd != -1)
-		bpf_prog_detach(cgfd, test->attach_type);
-	close(progfd);
-	printf("[%s]\n", err ? "FAIL" : "PASS");
-	return err;
+	if (prog_fd != -1)
+		bpf_prog_detach(cgroup_fd, test->attach_type);
+	close(prog_fd);
+	return ret;
 }
 
-static int run_tests(int cgfd)
+void test_sock_post_bind(void)
 {
-	int passes = 0;
-	int fails = 0;
+	struct netns_obj *ns;
+	int cgroup_fd;
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(tests); ++i) {
-		if (run_test_case(cgfd, &tests[i]))
-			++fails;
-		else
-			++passes;
-	}
-	printf("Summary: %d PASSED, %d FAILED\n", passes, fails);
-	return fails ? -1 : 0;
-}
-
-int main(int argc, char **argv)
-{
-	int cgfd = -1;
-	int err = 0;
+	cgroup_fd = test__join_cgroup("/post_bind");
+	if (!ASSERT_OK_FD(cgroup_fd, "join_cgroup"))
+		return;
 
-	cgfd = cgroup_setup_and_join(CG_PATH);
-	if (cgfd < 0)
-		goto err;
+	ns = netns_new(TEST_NS, true);
+	if (!ASSERT_OK_PTR(ns, "netns_new"))
+		goto cleanup;
 
-	/* Use libbpf 1.0 API mode */
-	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		if (!test__start_subtest(tests[i].descr))
+			continue;
 
-	if (run_tests(cgfd))
-		goto err;
+		ASSERT_OK(run_test(cgroup_fd, &tests[i]), tests[i].descr);
+	}
 
-	goto out;
-err:
-	err = -1;
-out:
-	close(cgfd);
-	cleanup_cgroup_environment();
-	return err;
+cleanup:
+	netns_free(ns);
+	close(cgroup_fd);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/socket_helpers.h b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h
new file mode 100644
index 000000000000..0d59503a0c73
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/socket_helpers.h
@@ -0,0 +1,473 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __SOCKET_HELPERS__
+#define __SOCKET_HELPERS__
+
+#include <sys/un.h>
+#include <linux/vm_sockets.h>
+
+/* include/linux/net.h */
+#define SOCK_TYPE_MASK 0xf
+
+#define IO_TIMEOUT_SEC 30
+#define MAX_STRERR_LEN 256
+
+/* workaround for older vm_sockets.h */
+#ifndef VMADDR_CID_LOCAL
+#define VMADDR_CID_LOCAL 1
+#endif
+
+/* include/linux/compiler_types.h */
+#if __STDC_VERSION__ < 202311L && !defined(auto)
+# define auto __auto_type
+#endif
+
+/* include/linux/cleanup.h */
+#define __get_and_null(p, nullvalue)                                           \
+	({                                                                     \
+		auto __ptr = &(p);					       \
+		auto __val = *__ptr;                                           \
+		*__ptr = nullvalue;                                            \
+		__val;                                                         \
+	})
+
+#define take_fd(fd) __get_and_null(fd, -EBADF)
+
+/* Wrappers that fail the test on error and report it. */
+
+#define _FAIL(errnum, fmt...)                                                  \
+	({                                                                     \
+		error_at_line(0, (errnum), __func__, __LINE__, fmt);           \
+		CHECK_FAIL(true);                                              \
+	})
+#define FAIL(fmt...) _FAIL(0, fmt)
+#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt)
+#define FAIL_LIBBPF(err, msg)                                                  \
+	({                                                                     \
+		char __buf[MAX_STRERR_LEN];                                    \
+		libbpf_strerror((err), __buf, sizeof(__buf));                  \
+		FAIL("%s: %s", (msg), __buf);                                  \
+	})
+
+
+#define xaccept_nonblock(fd, addr, len)                                        \
+	({                                                                     \
+		int __ret =                                                    \
+			accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC);   \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("accept");                                  \
+		__ret;                                                         \
+	})
+
+#define xbind(fd, addr, len)                                                   \
+	({                                                                     \
+		int __ret = bind((fd), (addr), (len));                         \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("bind");                                    \
+		__ret;                                                         \
+	})
+
+#define xclose(fd)                                                             \
+	({                                                                     \
+		int __ret = close((fd));                                       \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("close");                                   \
+		__ret;                                                         \
+	})
+
+#define xconnect(fd, addr, len)                                                \
+	({                                                                     \
+		int __ret = connect((fd), (addr), (len));                      \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("connect");                                 \
+		__ret;                                                         \
+	})
+
+#define xgetsockname(fd, addr, len)                                            \
+	({                                                                     \
+		int __ret = getsockname((fd), (addr), (len));                  \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("getsockname");                             \
+		__ret;                                                         \
+	})
+
+#define xgetsockopt(fd, level, name, val, len)                                 \
+	({                                                                     \
+		int __ret = getsockopt((fd), (level), (name), (val), (len));   \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("getsockopt(" #name ")");                   \
+		__ret;                                                         \
+	})
+
+#define xlisten(fd, backlog)                                                   \
+	({                                                                     \
+		int __ret = listen((fd), (backlog));                           \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("listen");                                  \
+		__ret;                                                         \
+	})
+
+#define xsetsockopt(fd, level, name, val, len)                                 \
+	({                                                                     \
+		int __ret = setsockopt((fd), (level), (name), (val), (len));   \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("setsockopt(" #name ")");                   \
+		__ret;                                                         \
+	})
+
+#define xsend(fd, buf, len, flags)                                             \
+	({                                                                     \
+		ssize_t __ret = send((fd), (buf), (len), (flags));             \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("send");                                    \
+		__ret;                                                         \
+	})
+
+#define xrecv_nonblock(fd, buf, len, flags)                                    \
+	({                                                                     \
+		ssize_t __ret = recv_timeout((fd), (buf), (len), (flags),      \
+					     IO_TIMEOUT_SEC);                  \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("recv");                                    \
+		__ret;                                                         \
+	})
+
+#define xsocket(family, sotype, flags)                                         \
+	({                                                                     \
+		int __ret = socket(family, sotype, flags);                     \
+		if (__ret == -1)                                               \
+			FAIL_ERRNO("socket");                                  \
+		__ret;                                                         \
+	})
+
+static inline void close_fd(int *fd)
+{
+	if (*fd >= 0)
+		xclose(*fd);
+}
+
+#define __close_fd __attribute__((cleanup(close_fd)))
+
+static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss)
+{
+	return (struct sockaddr *)ss;
+}
+
+static inline void init_addr_loopback4(struct sockaddr_storage *ss,
+				       socklen_t *len)
+{
+	struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss));
+
+	addr4->sin_family = AF_INET;
+	addr4->sin_port = 0;
+	addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+	*len = sizeof(*addr4);
+}
+
+static inline void init_addr_loopback6(struct sockaddr_storage *ss,
+				       socklen_t *len)
+{
+	struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss));
+
+	addr6->sin6_family = AF_INET6;
+	addr6->sin6_port = 0;
+	addr6->sin6_addr = in6addr_loopback;
+	*len = sizeof(*addr6);
+}
+
+static inline void init_addr_loopback_unix(struct sockaddr_storage *ss,
+					   socklen_t *len)
+{
+	struct sockaddr_un *addr = memset(ss, 0, sizeof(*ss));
+
+	addr->sun_family = AF_UNIX;
+	*len = sizeof(sa_family_t);
+}
+
+static inline void init_addr_loopback_vsock(struct sockaddr_storage *ss,
+					    socklen_t *len)
+{
+	struct sockaddr_vm *addr = memset(ss, 0, sizeof(*ss));
+
+	addr->svm_family = AF_VSOCK;
+	addr->svm_port = VMADDR_PORT_ANY;
+	addr->svm_cid = VMADDR_CID_LOCAL;
+	*len = sizeof(*addr);
+}
+
+static inline void init_addr_loopback(int family, struct sockaddr_storage *ss,
+				      socklen_t *len)
+{
+	switch (family) {
+	case AF_INET:
+		init_addr_loopback4(ss, len);
+		return;
+	case AF_INET6:
+		init_addr_loopback6(ss, len);
+		return;
+	case AF_UNIX:
+		init_addr_loopback_unix(ss, len);
+		return;
+	case AF_VSOCK:
+		init_addr_loopback_vsock(ss, len);
+		return;
+	default:
+		FAIL("unsupported address family %d", family);
+	}
+}
+
+static inline int enable_reuseport(int s, int progfd)
+{
+	int err, one = 1;
+
+	err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one));
+	if (err)
+		return -1;
+	err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd,
+			  sizeof(progfd));
+	if (err)
+		return -1;
+
+	return 0;
+}
+
+static inline int socket_loopback_reuseport(int family, int sotype, int progfd)
+{
+	struct sockaddr_storage addr;
+	socklen_t len = 0;
+	int err, s;
+
+	init_addr_loopback(family, &addr, &len);
+
+	s = xsocket(family, sotype, 0);
+	if (s == -1)
+		return -1;
+
+	if (progfd >= 0)
+		enable_reuseport(s, progfd);
+
+	err = xbind(s, sockaddr(&addr), len);
+	if (err)
+		goto close;
+
+	if (sotype & SOCK_DGRAM)
+		return s;
+
+	err = xlisten(s, SOMAXCONN);
+	if (err)
+		goto close;
+
+	return s;
+close:
+	xclose(s);
+	return -1;
+}
+
+static inline int socket_loopback(int family, int sotype)
+{
+	return socket_loopback_reuseport(family, sotype, -1);
+}
+
+static inline int poll_connect(int fd, unsigned int timeout_sec)
+{
+	struct timeval timeout = { .tv_sec = timeout_sec };
+	fd_set wfds;
+	int r, eval;
+	socklen_t esize = sizeof(eval);
+
+	FD_ZERO(&wfds);
+	FD_SET(fd, &wfds);
+
+	r = select(fd + 1, NULL, &wfds, NULL, &timeout);
+	if (r == 0)
+		errno = ETIME;
+	if (r != 1)
+		return -1;
+
+	if (getsockopt(fd, SOL_SOCKET, SO_ERROR, &eval, &esize) < 0)
+		return -1;
+	if (eval != 0) {
+		errno = eval;
+		return -1;
+	}
+
+	return 0;
+}
+
+static inline int poll_read(int fd, unsigned int timeout_sec)
+{
+	struct timeval timeout = { .tv_sec = timeout_sec };
+	fd_set rfds;
+	int r;
+
+	FD_ZERO(&rfds);
+	FD_SET(fd, &rfds);
+
+	r = select(fd + 1, &rfds, NULL, NULL, &timeout);
+	if (r == 0)
+		errno = ETIME;
+
+	return r == 1 ? 0 : -1;
+}
+
+static inline int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len,
+				 unsigned int timeout_sec)
+{
+	if (poll_read(fd, timeout_sec))
+		return -1;
+
+	return accept(fd, addr, len);
+}
+
+static inline int recv_timeout(int fd, void *buf, size_t len, int flags,
+			       unsigned int timeout_sec)
+{
+	if (poll_read(fd, timeout_sec))
+		return -1;
+
+	return recv(fd, buf, len, flags);
+}
+
+
+static inline int create_pair(int family, int sotype, int *p0, int *p1)
+{
+	__close_fd int s, c = -1, p = -1;
+	struct sockaddr_storage addr;
+	socklen_t len;
+	int err;
+
+	s = socket_loopback(family, sotype);
+	if (s < 0)
+		return s;
+
+	c = xsocket(family, sotype, 0);
+	if (c < 0)
+		return c;
+
+	init_addr_loopback(family, &addr, &len);
+	err = xbind(c, sockaddr(&addr), len);
+	if (err)
+		return err;
+
+	len = sizeof(addr);
+	err = xgetsockname(s, sockaddr(&addr), &len);
+	if (err)
+		return err;
+
+	err = connect(c, sockaddr(&addr), len);
+	if (err) {
+		if (errno != EINPROGRESS) {
+			FAIL_ERRNO("connect");
+			return err;
+		}
+
+		err = poll_connect(c, IO_TIMEOUT_SEC);
+		if (err) {
+			FAIL_ERRNO("poll_connect");
+			return err;
+		}
+	}
+
+	switch (sotype & SOCK_TYPE_MASK) {
+	case SOCK_DGRAM:
+		err = xgetsockname(c, sockaddr(&addr), &len);
+		if (err)
+			return err;
+
+		err = xconnect(s, sockaddr(&addr), len);
+		if (err)
+			return err;
+
+		*p0 = take_fd(s);
+		break;
+	case SOCK_STREAM:
+	case SOCK_SEQPACKET:
+		p = xaccept_nonblock(s, NULL, NULL);
+		if (p < 0)
+			return p;
+
+		*p0 = take_fd(p);
+		break;
+	default:
+		FAIL("Unsupported socket type %#x", sotype);
+		return -EOPNOTSUPP;
+	}
+
+	*p1 = take_fd(c);
+	return 0;
+}
+
+static inline int create_socket_pairs(int family, int sotype, int *c0, int *c1,
+				      int *p0, int *p1)
+{
+	int err;
+
+	err = create_pair(family, sotype, c0, p0);
+	if (err)
+		return err;
+
+	err = create_pair(family, sotype, c1, p1);
+	if (err) {
+		close(*c0);
+		close(*p0);
+	}
+
+	return err;
+}
+
+static inline const char *socket_kind_to_str(int sock_fd)
+{
+	socklen_t opt_len;
+	int domain, type;
+
+	opt_len = sizeof(domain);
+	if (getsockopt(sock_fd, SOL_SOCKET, SO_DOMAIN, &domain, &opt_len))
+		FAIL_ERRNO("getsockopt(SO_DOMAIN)");
+
+	opt_len = sizeof(type);
+	if (getsockopt(sock_fd, SOL_SOCKET, SO_TYPE, &type, &opt_len))
+		FAIL_ERRNO("getsockopt(SO_TYPE)");
+
+	switch (domain) {
+	case AF_INET:
+		switch (type) {
+		case SOCK_STREAM:
+			return "tcp4";
+		case SOCK_DGRAM:
+			return "udp4";
+		}
+		break;
+	case AF_INET6:
+		switch (type) {
+		case SOCK_STREAM:
+			return "tcp6";
+		case SOCK_DGRAM:
+			return "udp6";
+		}
+		break;
+	case AF_UNIX:
+		switch (type) {
+		case SOCK_STREAM:
+			return "u_str";
+		case SOCK_DGRAM:
+			return "u_dgr";
+		case SOCK_SEQPACKET:
+			return "u_seq";
+		}
+		break;
+	case AF_VSOCK:
+		switch (type) {
+		case SOCK_STREAM:
+			return "v_str";
+		case SOCK_DGRAM:
+			return "v_dgr";
+		case SOCK_SEQPACKET:
+			return "v_seq";
+		}
+		break;
+	}
+
+	return "???";
+}
+
+#endif // __SOCKET_HELPERS__
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 0aa088900699..1e3e4392dcca 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -2,6 +2,7 @@
 // Copyright (c) 2020 Cloudflare
 #include <error.h>
 #include <netinet/tcp.h>
+#include <sys/epoll.h>
 
 #include "test_progs.h"
 #include "test_skmsg_load_helpers.skel.h"
@@ -9,8 +10,13 @@
 #include "test_sockmap_invalid_update.skel.h"
 #include "test_sockmap_skb_verdict_attach.skel.h"
 #include "test_sockmap_progs_query.skel.h"
+#include "test_sockmap_pass_prog.skel.h"
+#include "test_sockmap_drop_prog.skel.h"
+#include "test_sockmap_change_tail.skel.h"
 #include "bpf_iter_sockmap.skel.h"
 
+#include "sockmap_helpers.h"
+
 #define TCP_REPAIR		19	/* TCP sock is under repair right now */
 
 #define TCP_REPAIR_ON		1
@@ -103,6 +109,39 @@ out:
 	close(s);
 }
 
+static void test_sockmap_vsock_delete_on_close(void)
+{
+	int map, c, p, err, zero = 0;
+
+	map = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(int),
+			     sizeof(int), 1, NULL);
+	if (!ASSERT_OK_FD(map, "bpf_map_create"))
+		return;
+
+	err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p);
+	if (!ASSERT_OK(err, "create_pair"))
+		goto close_map;
+
+	if (xbpf_map_update_elem(map, &zero, &c, BPF_NOEXIST))
+		goto close_socks;
+
+	xclose(c);
+	xclose(p);
+
+	err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p);
+	if (!ASSERT_OK(err, "create_pair"))
+		goto close_map;
+
+	err = bpf_map_update_elem(map, &zero, &c, BPF_NOEXIST);
+	ASSERT_OK(err, "after close(), bpf_map_update");
+
+close_socks:
+	xclose(c);
+	xclose(p);
+close_map:
+	xclose(map);
+}
+
 static void test_skmsg_helpers(enum bpf_map_type map_type)
 {
 	struct test_skmsg_load_helpers *skel;
@@ -126,6 +165,65 @@ out:
 	test_skmsg_load_helpers__destroy(skel);
 }
 
+static void test_skmsg_helpers_with_link(enum bpf_map_type map_type)
+{
+	struct bpf_program *prog, *prog_clone, *prog_clone2;
+	DECLARE_LIBBPF_OPTS(bpf_link_update_opts, opts);
+	struct test_skmsg_load_helpers *skel;
+	struct bpf_link *link, *link2;
+	int err, map;
+
+	skel = test_skmsg_load_helpers__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_skmsg_load_helpers__open_and_load"))
+		return;
+
+	prog = skel->progs.prog_msg_verdict;
+	prog_clone = skel->progs.prog_msg_verdict_clone;
+	prog_clone2 = skel->progs.prog_msg_verdict_clone2;
+	map = bpf_map__fd(skel->maps.sock_map);
+
+	link = bpf_program__attach_sockmap(prog, map);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_sockmap"))
+		goto out;
+
+	/* Fail since bpf_link for the same prog has been created. */
+	err = bpf_prog_attach(bpf_program__fd(prog), map, BPF_SK_MSG_VERDICT, 0);
+	if (!ASSERT_ERR(err, "bpf_prog_attach"))
+		goto out;
+
+	/* Fail since bpf_link for the same prog type has been created. */
+	link2 = bpf_program__attach_sockmap(prog_clone, map);
+	if (!ASSERT_ERR_PTR(link2, "bpf_program__attach_sockmap")) {
+		bpf_link__detach(link2);
+		goto out;
+	}
+
+	err = bpf_link__update_program(link, prog_clone);
+	if (!ASSERT_OK(err, "bpf_link__update_program"))
+		goto out;
+
+	/* Fail since a prog with different type attempts to do update. */
+	err = bpf_link__update_program(link, skel->progs.prog_skb_verdict);
+	if (!ASSERT_ERR(err, "bpf_link__update_program"))
+		goto out;
+
+	/* Fail since the old prog does not match the one in the kernel. */
+	opts.old_prog_fd = bpf_program__fd(prog_clone2);
+	opts.flags = BPF_F_REPLACE;
+	err = bpf_link_update(bpf_link__fd(link), bpf_program__fd(prog), &opts);
+	if (!ASSERT_ERR(err, "bpf_link_update"))
+		goto out;
+
+	opts.old_prog_fd = bpf_program__fd(prog_clone);
+	opts.flags = BPF_F_REPLACE;
+	err = bpf_link_update(bpf_link__fd(link), bpf_program__fd(prog), &opts);
+	if (!ASSERT_OK(err, "bpf_link_update"))
+		goto out;
+out:
+	bpf_link__detach(link);
+	test_skmsg_load_helpers__destroy(skel);
+}
+
 static void test_sockmap_update(enum bpf_map_type map_type)
 {
 	int err, prog, src;
@@ -293,15 +391,49 @@ out:
 	test_sockmap_skb_verdict_attach__destroy(skel);
 }
 
+static void test_sockmap_skb_verdict_attach_with_link(void)
+{
+	struct test_sockmap_skb_verdict_attach *skel;
+	struct bpf_program *prog;
+	struct bpf_link *link;
+	int err, map;
+
+	skel = test_sockmap_skb_verdict_attach__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+	prog = skel->progs.prog_skb_verdict;
+	map = bpf_map__fd(skel->maps.sock_map);
+	link = bpf_program__attach_sockmap(prog, map);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_sockmap"))
+		goto out;
+
+	bpf_link__detach(link);
+
+	err = bpf_prog_attach(bpf_program__fd(prog), map, BPF_SK_SKB_STREAM_VERDICT, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach"))
+		goto out;
+
+	/* Fail since attaching with the same prog/map has been done. */
+	link = bpf_program__attach_sockmap(prog, map);
+	if (!ASSERT_ERR_PTR(link, "bpf_program__attach_sockmap"))
+		bpf_link__detach(link);
+
+	err = bpf_prog_detach2(bpf_program__fd(prog), map, BPF_SK_SKB_STREAM_VERDICT);
+	if (!ASSERT_OK(err, "bpf_prog_detach2"))
+		goto out;
+out:
+	test_sockmap_skb_verdict_attach__destroy(skel);
+}
+
 static __u32 query_prog_id(int prog_fd)
 {
 	struct bpf_prog_info info = {};
 	__u32 info_len = sizeof(info);
 	int err;
 
-	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
-	if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd") ||
-	    !ASSERT_EQ(info_len, sizeof(info), "bpf_obj_get_info_by_fd"))
+	err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len);
+	if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd") ||
+	    !ASSERT_EQ(info_len, sizeof(info), "bpf_prog_get_info_by_fd"))
 		return 0;
 
 	return info.id;
@@ -350,12 +482,574 @@ out:
 	test_sockmap_progs_query__destroy(skel);
 }
 
+#define MAX_EVENTS 10
+static void test_sockmap_skb_verdict_shutdown(void)
+{
+	int n, err, map, verdict, c1 = -1, p1 = -1;
+	struct epoll_event ev, events[MAX_EVENTS];
+	struct test_sockmap_pass_prog *skel;
+	int zero = 0;
+	int epollfd;
+	char b;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+	map = bpf_map__fd(skel->maps.sock_map_rx);
+
+	err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach"))
+		goto out;
+
+	err = create_pair(AF_INET, SOCK_STREAM, &c1, &p1);
+	if (err < 0)
+		goto out;
+
+	err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST);
+	if (err < 0)
+		goto out_close;
+
+	shutdown(p1, SHUT_WR);
+
+	ev.events = EPOLLIN;
+	ev.data.fd = c1;
+
+	epollfd = epoll_create1(0);
+	if (!ASSERT_GT(epollfd, -1, "epoll_create(0)"))
+		goto out_close;
+	err = epoll_ctl(epollfd, EPOLL_CTL_ADD, c1, &ev);
+	if (!ASSERT_OK(err, "epoll_ctl(EPOLL_CTL_ADD)"))
+		goto out_close;
+	err = epoll_wait(epollfd, events, MAX_EVENTS, -1);
+	if (!ASSERT_EQ(err, 1, "epoll_wait(fd)"))
+		goto out_close;
+
+	n = recv(c1, &b, 1, MSG_DONTWAIT);
+	ASSERT_EQ(n, 0, "recv(fin)");
+out_close:
+	close(c1);
+	close(p1);
+out:
+	test_sockmap_pass_prog__destroy(skel);
+}
+
+
+static void test_sockmap_skb_verdict_fionread(bool pass_prog)
+{
+	int err, map, verdict, c0 = -1, c1 = -1, p0 = -1, p1 = -1;
+	int expected, zero = 0, sent, recvd, avail;
+	struct test_sockmap_pass_prog *pass = NULL;
+	struct test_sockmap_drop_prog *drop = NULL;
+	char buf[256] = "0123456789";
+
+	if (pass_prog) {
+		pass = test_sockmap_pass_prog__open_and_load();
+		if (!ASSERT_OK_PTR(pass, "open_and_load"))
+			return;
+		verdict = bpf_program__fd(pass->progs.prog_skb_verdict);
+		map = bpf_map__fd(pass->maps.sock_map_rx);
+		expected = sizeof(buf);
+	} else {
+		drop = test_sockmap_drop_prog__open_and_load();
+		if (!ASSERT_OK_PTR(drop, "open_and_load"))
+			return;
+		verdict = bpf_program__fd(drop->progs.prog_skb_verdict);
+		map = bpf_map__fd(drop->maps.sock_map_rx);
+		/* On drop data is consumed immediately and copied_seq inc'd */
+		expected = 0;
+	}
+
+
+	err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach"))
+		goto out;
+
+	err = create_socket_pairs(AF_INET, SOCK_STREAM, &c0, &c1, &p0, &p1);
+	if (!ASSERT_OK(err, "create_socket_pairs()"))
+		goto out;
+
+	err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(c1)"))
+		goto out_close;
+
+	sent = xsend(p1, &buf, sizeof(buf), 0);
+	ASSERT_EQ(sent, sizeof(buf), "xsend(p0)");
+	err = ioctl(c1, FIONREAD, &avail);
+	ASSERT_OK(err, "ioctl(FIONREAD) error");
+	ASSERT_EQ(avail, expected, "ioctl(FIONREAD)");
+	/* On DROP test there will be no data to read */
+	if (pass_prog) {
+		recvd = recv_timeout(c1, &buf, sizeof(buf), MSG_DONTWAIT, IO_TIMEOUT_SEC);
+		ASSERT_EQ(recvd, sizeof(buf), "recv_timeout(c0)");
+	}
+
+out_close:
+	close(c0);
+	close(p0);
+	close(c1);
+	close(p1);
+out:
+	if (pass_prog)
+		test_sockmap_pass_prog__destroy(pass);
+	else
+		test_sockmap_drop_prog__destroy(drop);
+}
+
+static void test_sockmap_skb_verdict_change_tail(void)
+{
+	struct test_sockmap_change_tail *skel;
+	int err, map, verdict;
+	int c1, p1, sent, recvd;
+	int zero = 0;
+	char buf[2];
+
+	skel = test_sockmap_change_tail__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+	verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+	map = bpf_map__fd(skel->maps.sock_map_rx);
+
+	err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach"))
+		goto out;
+	err = create_pair(AF_INET, SOCK_STREAM, &c1, &p1);
+	if (!ASSERT_OK(err, "create_pair()"))
+		goto out;
+	err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(c1)"))
+		goto out_close;
+	sent = xsend(p1, "Tr", 2, 0);
+	ASSERT_EQ(sent, 2, "xsend(p1)");
+	recvd = recv(c1, buf, 2, 0);
+	ASSERT_EQ(recvd, 1, "recv(c1)");
+	ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret");
+
+	sent = xsend(p1, "G", 1, 0);
+	ASSERT_EQ(sent, 1, "xsend(p1)");
+	recvd = recv(c1, buf, 2, 0);
+	ASSERT_EQ(recvd, 2, "recv(c1)");
+	ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret");
+
+	sent = xsend(p1, "E", 1, 0);
+	ASSERT_EQ(sent, 1, "xsend(p1)");
+	recvd = recv(c1, buf, 1, 0);
+	ASSERT_EQ(recvd, 1, "recv(c1)");
+	ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret");
+
+out_close:
+	close(c1);
+	close(p1);
+out:
+	test_sockmap_change_tail__destroy(skel);
+}
+
+static void test_sockmap_skb_verdict_peek_helper(int map)
+{
+	int err, c1, p1, zero = 0, sent, recvd, avail;
+	char snd[256] = "0123456789";
+	char rcv[256] = "0";
+
+	err = create_pair(AF_INET, SOCK_STREAM, &c1, &p1);
+	if (!ASSERT_OK(err, "create_pair()"))
+		return;
+
+	err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(c1)"))
+		goto out_close;
+
+	sent = xsend(p1, snd, sizeof(snd), 0);
+	ASSERT_EQ(sent, sizeof(snd), "xsend(p1)");
+	recvd = recv(c1, rcv, sizeof(rcv), MSG_PEEK);
+	ASSERT_EQ(recvd, sizeof(rcv), "recv(c1)");
+	err = ioctl(c1, FIONREAD, &avail);
+	ASSERT_OK(err, "ioctl(FIONREAD) error");
+	ASSERT_EQ(avail, sizeof(snd), "after peek ioctl(FIONREAD)");
+	recvd = recv(c1, rcv, sizeof(rcv), 0);
+	ASSERT_EQ(recvd, sizeof(rcv), "recv(p0)");
+	err = ioctl(c1, FIONREAD, &avail);
+	ASSERT_OK(err, "ioctl(FIONREAD) error");
+	ASSERT_EQ(avail, 0, "after read ioctl(FIONREAD)");
+
+out_close:
+	close(c1);
+	close(p1);
+}
+
+static void test_sockmap_skb_verdict_peek(void)
+{
+	struct test_sockmap_pass_prog *pass;
+	int err, map, verdict;
+
+	pass = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(pass, "open_and_load"))
+		return;
+	verdict = bpf_program__fd(pass->progs.prog_skb_verdict);
+	map = bpf_map__fd(pass->maps.sock_map_rx);
+
+	err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach"))
+		goto out;
+
+	test_sockmap_skb_verdict_peek_helper(map);
+
+out:
+	test_sockmap_pass_prog__destroy(pass);
+}
+
+static void test_sockmap_skb_verdict_peek_with_link(void)
+{
+	struct test_sockmap_pass_prog *pass;
+	struct bpf_program *prog;
+	struct bpf_link *link;
+	int err, map;
+
+	pass = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(pass, "open_and_load"))
+		return;
+	prog = pass->progs.prog_skb_verdict;
+	map = bpf_map__fd(pass->maps.sock_map_rx);
+	link = bpf_program__attach_sockmap(prog, map);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_sockmap"))
+		goto out;
+
+	err = bpf_link__update_program(link, pass->progs.prog_skb_verdict_clone);
+	if (!ASSERT_OK(err, "bpf_link__update_program"))
+		goto out;
+
+	/* Fail since a prog with different attach type attempts to do update. */
+	err = bpf_link__update_program(link, pass->progs.prog_skb_parser);
+	if (!ASSERT_ERR(err, "bpf_link__update_program"))
+		goto out;
+
+	test_sockmap_skb_verdict_peek_helper(map);
+	ASSERT_EQ(pass->bss->clone_called, 1, "clone_called");
+out:
+	bpf_link__detach(link);
+	test_sockmap_pass_prog__destroy(pass);
+}
+
+static void test_sockmap_unconnected_unix(void)
+{
+	int err, map, stream = 0, dgram = 0, zero = 0;
+	struct test_sockmap_pass_prog *skel;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	map = bpf_map__fd(skel->maps.sock_map_rx);
+
+	stream = xsocket(AF_UNIX, SOCK_STREAM, 0);
+	if (stream < 0)
+		return;
+
+	dgram = xsocket(AF_UNIX, SOCK_DGRAM, 0);
+	if (dgram < 0) {
+		close(stream);
+		return;
+	}
+
+	err = bpf_map_update_elem(map, &zero, &stream, BPF_ANY);
+	ASSERT_ERR(err, "bpf_map_update_elem(stream)");
+
+	err = bpf_map_update_elem(map, &zero, &dgram, BPF_ANY);
+	ASSERT_OK(err, "bpf_map_update_elem(dgram)");
+
+	close(stream);
+	close(dgram);
+}
+
+static void test_sockmap_many_socket(void)
+{
+	struct test_sockmap_pass_prog *skel;
+	int stream[2], dgram, udp, tcp;
+	int i, err, map, entry = 0;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	map = bpf_map__fd(skel->maps.sock_map_rx);
+
+	dgram = xsocket(AF_UNIX, SOCK_DGRAM, 0);
+	if (dgram < 0) {
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	tcp = connected_socket_v4();
+	if (!ASSERT_GE(tcp, 0, "connected_socket_v4")) {
+		close(dgram);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0);
+	if (udp < 0) {
+		close(dgram);
+		close(tcp);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	err = socketpair(AF_UNIX, SOCK_STREAM, 0, stream);
+	ASSERT_OK(err, "socketpair(af_unix, sock_stream)");
+	if (err)
+		goto out;
+
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map, &entry, &stream[0], BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(stream)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map, &entry, &dgram, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(dgram)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map, &entry, &udp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(udp)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map, &entry, &tcp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(tcp)");
+	}
+	for (entry--; entry >= 0; entry--) {
+		err = bpf_map_delete_elem(map, &entry);
+		ASSERT_OK(err, "bpf_map_delete_elem(entry)");
+	}
+
+	close(stream[0]);
+	close(stream[1]);
+out:
+	close(dgram);
+	close(tcp);
+	close(udp);
+	test_sockmap_pass_prog__destroy(skel);
+}
+
+static void test_sockmap_many_maps(void)
+{
+	struct test_sockmap_pass_prog *skel;
+	int stream[2], dgram, udp, tcp;
+	int i, err, map[2], entry = 0;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	map[0] = bpf_map__fd(skel->maps.sock_map_rx);
+	map[1] = bpf_map__fd(skel->maps.sock_map_tx);
+
+	dgram = xsocket(AF_UNIX, SOCK_DGRAM, 0);
+	if (dgram < 0) {
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	tcp = connected_socket_v4();
+	if (!ASSERT_GE(tcp, 0, "connected_socket_v4")) {
+		close(dgram);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0);
+	if (udp < 0) {
+		close(dgram);
+		close(tcp);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	err = socketpair(AF_UNIX, SOCK_STREAM, 0, stream);
+	ASSERT_OK(err, "socketpair(af_unix, sock_stream)");
+	if (err)
+		goto out;
+
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map[i], &entry, &stream[0], BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(stream)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map[i], &entry, &dgram, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(dgram)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map[i], &entry, &udp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(udp)");
+	}
+	for (i = 0; i < 2; i++, entry++) {
+		err = bpf_map_update_elem(map[i], &entry, &tcp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(tcp)");
+	}
+	for (entry--; entry >= 0; entry--) {
+		err = bpf_map_delete_elem(map[1], &entry);
+		entry--;
+		ASSERT_OK(err, "bpf_map_delete_elem(entry)");
+		err = bpf_map_delete_elem(map[0], &entry);
+		ASSERT_OK(err, "bpf_map_delete_elem(entry)");
+	}
+
+	close(stream[0]);
+	close(stream[1]);
+out:
+	close(dgram);
+	close(tcp);
+	close(udp);
+	test_sockmap_pass_prog__destroy(skel);
+}
+
+static void test_sockmap_same_sock(void)
+{
+	struct test_sockmap_pass_prog *skel;
+	int stream[2], dgram, udp, tcp;
+	int i, err, map, zero = 0;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	map = bpf_map__fd(skel->maps.sock_map_rx);
+
+	dgram = xsocket(AF_UNIX, SOCK_DGRAM, 0);
+	if (dgram < 0) {
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	tcp = connected_socket_v4();
+	if (!ASSERT_GE(tcp, 0, "connected_socket_v4")) {
+		close(dgram);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	udp = xsocket(AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, 0);
+	if (udp < 0) {
+		close(dgram);
+		close(tcp);
+		test_sockmap_pass_prog__destroy(skel);
+		return;
+	}
+
+	err = socketpair(AF_UNIX, SOCK_STREAM, 0, stream);
+	ASSERT_OK(err, "socketpair(af_unix, sock_stream)");
+	if (err) {
+		close(tcp);
+		goto out;
+	}
+
+	for (i = 0; i < 2; i++) {
+		err = bpf_map_update_elem(map, &zero, &stream[0], BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(stream)");
+	}
+	for (i = 0; i < 2; i++) {
+		err = bpf_map_update_elem(map, &zero, &dgram, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(dgram)");
+	}
+	for (i = 0; i < 2; i++) {
+		err = bpf_map_update_elem(map, &zero, &udp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(udp)");
+	}
+	for (i = 0; i < 2; i++) {
+		err = bpf_map_update_elem(map, &zero, &tcp, BPF_ANY);
+		ASSERT_OK(err, "bpf_map_update_elem(tcp)");
+	}
+
+	close(tcp);
+	err = bpf_map_delete_elem(map, &zero);
+	ASSERT_ERR(err, "bpf_map_delete_elem(entry)");
+
+	close(stream[0]);
+	close(stream[1]);
+out:
+	close(dgram);
+	close(udp);
+	test_sockmap_pass_prog__destroy(skel);
+}
+
+static void test_sockmap_skb_verdict_vsock_poll(void)
+{
+	struct test_sockmap_pass_prog *skel;
+	int err, map, conn, peer;
+	struct bpf_program *prog;
+	struct bpf_link *link;
+	char buf = 'x';
+	int zero = 0;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	if (create_pair(AF_VSOCK, SOCK_STREAM, &conn, &peer))
+		goto destroy;
+
+	prog = skel->progs.prog_skb_verdict;
+	map = bpf_map__fd(skel->maps.sock_map_rx);
+	link = bpf_program__attach_sockmap(prog, map);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_sockmap"))
+		goto close;
+
+	err = bpf_map_update_elem(map, &zero, &conn, BPF_ANY);
+	if (!ASSERT_OK(err, "bpf_map_update_elem"))
+		goto detach;
+
+	if (xsend(peer, &buf, 1, 0) != 1)
+		goto detach;
+
+	err = poll_read(conn, IO_TIMEOUT_SEC);
+	if (!ASSERT_OK(err, "poll"))
+		goto detach;
+
+	if (xrecv_nonblock(conn, &buf, 1, 0) != 1)
+		FAIL("xrecv_nonblock");
+detach:
+	bpf_link__detach(link);
+close:
+	xclose(conn);
+	xclose(peer);
+destroy:
+	test_sockmap_pass_prog__destroy(skel);
+}
+
+static void test_sockmap_vsock_unconnected(void)
+{
+	struct sockaddr_storage addr;
+	int map, s, zero = 0;
+	socklen_t alen;
+
+	map = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(int),
+			     sizeof(int), 1, NULL);
+	if (!ASSERT_OK_FD(map, "bpf_map_create"))
+		return;
+
+	s = xsocket(AF_VSOCK, SOCK_STREAM, 0);
+	if (s < 0)
+		goto close_map;
+
+	/* Fail connect(), but trigger transport assignment. */
+	init_addr_loopback(AF_VSOCK, &addr, &alen);
+	if (!ASSERT_ERR(connect(s, sockaddr(&addr), alen), "connect"))
+		goto close_sock;
+
+	ASSERT_ERR(bpf_map_update_elem(map, &zero, &s, BPF_ANY), "map_update");
+
+close_sock:
+	xclose(s);
+close_map:
+	xclose(map);
+}
+
 void test_sockmap_basic(void)
 {
 	if (test__start_subtest("sockmap create_update_free"))
 		test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKMAP);
 	if (test__start_subtest("sockhash create_update_free"))
 		test_sockmap_create_update_free(BPF_MAP_TYPE_SOCKHASH);
+	if (test__start_subtest("sockmap vsock delete on close"))
+		test_sockmap_vsock_delete_on_close();
 	if (test__start_subtest("sockmap sk_msg load helpers"))
 		test_skmsg_helpers(BPF_MAP_TYPE_SOCKMAP);
 	if (test__start_subtest("sockhash sk_msg load helpers"))
@@ -376,6 +1070,8 @@ void test_sockmap_basic(void)
 		test_sockmap_skb_verdict_attach(BPF_SK_SKB_STREAM_VERDICT,
 						BPF_SK_SKB_VERDICT);
 	}
+	if (test__start_subtest("sockmap skb_verdict attach_with_link"))
+		test_sockmap_skb_verdict_attach_with_link();
 	if (test__start_subtest("sockmap msg_verdict progs query"))
 		test_sockmap_progs_query(BPF_SK_MSG_VERDICT);
 	if (test__start_subtest("sockmap stream_parser progs query"))
@@ -384,4 +1080,32 @@ void test_sockmap_basic(void)
 		test_sockmap_progs_query(BPF_SK_SKB_STREAM_VERDICT);
 	if (test__start_subtest("sockmap skb_verdict progs query"))
 		test_sockmap_progs_query(BPF_SK_SKB_VERDICT);
+	if (test__start_subtest("sockmap skb_verdict shutdown"))
+		test_sockmap_skb_verdict_shutdown();
+	if (test__start_subtest("sockmap skb_verdict fionread"))
+		test_sockmap_skb_verdict_fionread(true);
+	if (test__start_subtest("sockmap skb_verdict fionread on drop"))
+		test_sockmap_skb_verdict_fionread(false);
+	if (test__start_subtest("sockmap skb_verdict change tail"))
+		test_sockmap_skb_verdict_change_tail();
+	if (test__start_subtest("sockmap skb_verdict msg_f_peek"))
+		test_sockmap_skb_verdict_peek();
+	if (test__start_subtest("sockmap skb_verdict msg_f_peek with link"))
+		test_sockmap_skb_verdict_peek_with_link();
+	if (test__start_subtest("sockmap unconnected af_unix"))
+		test_sockmap_unconnected_unix();
+	if (test__start_subtest("sockmap one socket to many map entries"))
+		test_sockmap_many_socket();
+	if (test__start_subtest("sockmap one socket to many maps"))
+		test_sockmap_many_maps();
+	if (test__start_subtest("sockmap same socket replace"))
+		test_sockmap_same_sock();
+	if (test__start_subtest("sockmap sk_msg attach sockmap helpers with link"))
+		test_skmsg_helpers_with_link(BPF_MAP_TYPE_SOCKMAP);
+	if (test__start_subtest("sockhash sk_msg attach sockhash helpers with link"))
+		test_skmsg_helpers_with_link(BPF_MAP_TYPE_SOCKHASH);
+	if (test__start_subtest("sockmap skb_verdict vsock poll"))
+		test_sockmap_skb_verdict_vsock_poll();
+	if (test__start_subtest("sockmap vsock unconnected"))
+		test_sockmap_vsock_unconnected();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
new file mode 100644
index 000000000000..d815efac52fd
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
@@ -0,0 +1,83 @@
+#ifndef __SOCKMAP_HELPERS__
+#define __SOCKMAP_HELPERS__
+
+#include "socket_helpers.h"
+
+#define MAX_TEST_NAME 80
+
+#define u32(v) ((u32){(v)})
+#define u64(v) ((u64){(v)})
+
+#define __always_unused	__attribute__((__unused__))
+
+#define xbpf_map_delete_elem(fd, key)                                          \
+	({                                                                     \
+		int __ret = bpf_map_delete_elem((fd), (key));                  \
+		if (__ret < 0)                                                 \
+			FAIL_ERRNO("map_delete");                              \
+		__ret;                                                         \
+	})
+
+#define xbpf_map_lookup_elem(fd, key, val)                                     \
+	({                                                                     \
+		int __ret = bpf_map_lookup_elem((fd), (key), (val));           \
+		if (__ret < 0)                                                 \
+			FAIL_ERRNO("map_lookup");                              \
+		__ret;                                                         \
+	})
+
+#define xbpf_map_update_elem(fd, key, val, flags)                              \
+	({                                                                     \
+		int __ret = bpf_map_update_elem((fd), (key), (val), (flags));  \
+		if (__ret < 0)                                                 \
+			FAIL_ERRNO("map_update");                              \
+		__ret;                                                         \
+	})
+
+#define xbpf_prog_attach(prog, target, type, flags)                            \
+	({                                                                     \
+		int __ret =                                                    \
+			bpf_prog_attach((prog), (target), (type), (flags));    \
+		if (__ret < 0)                                                 \
+			FAIL_ERRNO("prog_attach(" #type ")");                  \
+		__ret;                                                         \
+	})
+
+#define xbpf_prog_detach2(prog, target, type)                                  \
+	({                                                                     \
+		int __ret = bpf_prog_detach2((prog), (target), (type));        \
+		if (__ret < 0)                                                 \
+			FAIL_ERRNO("prog_detach2(" #type ")");                 \
+		__ret;                                                         \
+	})
+
+#define xpthread_create(thread, attr, func, arg)                               \
+	({                                                                     \
+		int __ret = pthread_create((thread), (attr), (func), (arg));   \
+		errno = __ret;                                                 \
+		if (__ret)                                                     \
+			FAIL_ERRNO("pthread_create");                          \
+		__ret;                                                         \
+	})
+
+#define xpthread_join(thread, retval)                                          \
+	({                                                                     \
+		int __ret = pthread_join((thread), (retval));                  \
+		errno = __ret;                                                 \
+		if (__ret)                                                     \
+			FAIL_ERRNO("pthread_join");                            \
+		__ret;                                                         \
+	})
+
+static inline int add_to_sockmap(int mapfd, int fd1, int fd2)
+{
+	int err;
+
+	err = xbpf_map_update_elem(mapfd, &u32(0), &u64(fd1), BPF_NOEXIST);
+	if (err)
+		return err;
+
+	return xbpf_map_update_elem(mapfd, &u32(1), &u64(fd2), BPF_NOEXIST);
+}
+
+#endif // __SOCKMAP_HELPERS__
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
index 2d0796314862..b87e7f39e15a 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c
@@ -3,77 +3,62 @@
 /*
  * Tests for sockmap/sockhash holding kTLS sockets.
  */
-
+#include <error.h>
 #include <netinet/tcp.h>
+#include <linux/tls.h>
 #include "test_progs.h"
+#include "sockmap_helpers.h"
+#include "test_skmsg_load_helpers.skel.h"
+#include "test_sockmap_ktls.skel.h"
 
 #define MAX_TEST_NAME 80
 #define TCP_ULP 31
 
-static int tcp_server(int family)
+static int init_ktls_pairs(int c, int p)
 {
-	int err, s;
-
-	s = socket(family, SOCK_STREAM, 0);
-	if (!ASSERT_GE(s, 0, "socket"))
-		return -1;
-
-	err = listen(s, SOMAXCONN);
-	if (!ASSERT_OK(err, "listen"))
-		return -1;
-
-	return s;
-}
+	int err;
+	struct tls12_crypto_info_aes_gcm_128 crypto_rx;
+	struct tls12_crypto_info_aes_gcm_128 crypto_tx;
 
-static int disconnect(int fd)
-{
-	struct sockaddr unspec = { AF_UNSPEC };
+	err = setsockopt(c, IPPROTO_TCP, TCP_ULP, "tls", strlen("tls"));
+	if (!ASSERT_OK(err, "setsockopt(TCP_ULP)"))
+		goto out;
 
-	return connect(fd, &unspec, sizeof(unspec));
+	err = setsockopt(p, IPPROTO_TCP, TCP_ULP, "tls", strlen("tls"));
+	if (!ASSERT_OK(err, "setsockopt(TCP_ULP)"))
+		goto out;
+
+	memset(&crypto_rx, 0, sizeof(crypto_rx));
+	memset(&crypto_tx, 0, sizeof(crypto_tx));
+	crypto_rx.info.version = TLS_1_2_VERSION;
+	crypto_tx.info.version = TLS_1_2_VERSION;
+	crypto_rx.info.cipher_type = TLS_CIPHER_AES_GCM_128;
+	crypto_tx.info.cipher_type = TLS_CIPHER_AES_GCM_128;
+
+	err = setsockopt(c, SOL_TLS, TLS_TX, &crypto_tx, sizeof(crypto_tx));
+	if (!ASSERT_OK(err, "setsockopt(TLS_TX)"))
+		goto out;
+
+	err = setsockopt(p, SOL_TLS, TLS_RX, &crypto_rx, sizeof(crypto_rx));
+	if (!ASSERT_OK(err, "setsockopt(TLS_RX)"))
+		goto out;
+	return 0;
+out:
+	return -1;
 }
 
-/* Disconnect (unhash) a kTLS socket after removing it from sockmap. */
-static void test_sockmap_ktls_disconnect_after_delete(int family, int map)
+static int create_ktls_pairs(int family, int sotype, int *c, int *p)
 {
-	struct sockaddr_storage addr = {0};
-	socklen_t len = sizeof(addr);
-	int err, cli, srv, zero = 0;
-
-	srv = tcp_server(family);
-	if (srv == -1)
-		return;
-
-	err = getsockname(srv, (struct sockaddr *)&addr, &len);
-	if (!ASSERT_OK(err, "getsockopt"))
-		goto close_srv;
-
-	cli = socket(family, SOCK_STREAM, 0);
-	if (!ASSERT_GE(cli, 0, "socket"))
-		goto close_srv;
+	int err;
 
-	err = connect(cli, (struct sockaddr *)&addr, len);
-	if (!ASSERT_OK(err, "connect"))
-		goto close_cli;
-
-	err = bpf_map_update_elem(map, &zero, &cli, 0);
-	if (!ASSERT_OK(err, "bpf_map_update_elem"))
-		goto close_cli;
-
-	err = setsockopt(cli, IPPROTO_TCP, TCP_ULP, "tls", strlen("tls"));
-	if (!ASSERT_OK(err, "setsockopt(TCP_ULP)"))
-		goto close_cli;
-
-	err = bpf_map_delete_elem(map, &zero);
-	if (!ASSERT_OK(err, "bpf_map_delete_elem"))
-		goto close_cli;
-
-	err = disconnect(cli);
-	ASSERT_OK(err, "disconnect");
+	err = create_pair(family, sotype, c, p);
+	if (!ASSERT_OK(err, "create_pair()"))
+		return -1;
 
-close_cli:
-	close(cli);
-close_srv:
-	close(srv);
+	err = init_ktls_pairs(*c, *p);
+	if (!ASSERT_OK(err, "init_ktls_pairs(c, p)"))
+		return -1;
+	return 0;
 }
 
 static void test_sockmap_ktls_update_fails_when_sock_has_ulp(int family, int map)
@@ -146,6 +131,278 @@ static const char *fmt_test_name(const char *subtest_name, int family,
 	return test_name;
 }
 
+static void test_sockmap_ktls_offload(int family, int sotype)
+{
+	int err;
+	int c = 0, p = 0, sent, recvd;
+	char msg[12] = "hello world\0";
+	char rcv[13];
+
+	err = create_ktls_pairs(family, sotype, &c, &p);
+	if (!ASSERT_OK(err, "create_ktls_pairs()"))
+		goto out;
+
+	sent = send(c, msg, sizeof(msg), 0);
+	if (!ASSERT_OK(err, "send(msg)"))
+		goto out;
+
+	recvd = recv(p, rcv, sizeof(rcv), 0);
+	if (!ASSERT_OK(err, "recv(msg)") ||
+	    !ASSERT_EQ(recvd, sent, "length mismatch"))
+		goto out;
+
+	ASSERT_OK(memcmp(msg, rcv, sizeof(msg)), "data mismatch");
+
+out:
+	if (c)
+		close(c);
+	if (p)
+		close(p);
+}
+
+static void test_sockmap_ktls_tx_cork(int family, int sotype, bool push)
+{
+	int err, off;
+	int i, j;
+	int start_push = 0, push_len = 0;
+	int c = 0, p = 0, one = 1, sent, recvd;
+	int prog_fd, map_fd;
+	char msg[12] = "hello world\0";
+	char rcv[20] = {0};
+	struct test_sockmap_ktls *skel;
+
+	skel = test_sockmap_ktls__open_and_load();
+	if (!ASSERT_TRUE(skel, "open ktls skel"))
+		return;
+
+	err = create_pair(family, sotype, &c, &p);
+	if (!ASSERT_OK(err, "create_pair()"))
+		goto out;
+
+	prog_fd = bpf_program__fd(skel->progs.prog_sk_policy);
+	map_fd = bpf_map__fd(skel->maps.sock_map);
+
+	err = bpf_prog_attach(prog_fd, map_fd, BPF_SK_MSG_VERDICT, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach sk msg"))
+		goto out;
+
+	err = bpf_map_update_elem(map_fd, &one, &c, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(c)"))
+		goto out;
+
+	err = init_ktls_pairs(c, p);
+	if (!ASSERT_OK(err, "init_ktls_pairs(c, p)"))
+		goto out;
+
+	skel->bss->cork_byte = sizeof(msg);
+	if (push) {
+		start_push = 1;
+		push_len = 2;
+	}
+	skel->bss->push_start = start_push;
+	skel->bss->push_end = push_len;
+
+	off = sizeof(msg) / 2;
+	sent = send(c, msg, off, 0);
+	if (!ASSERT_EQ(sent, off, "send(msg)"))
+		goto out;
+
+	recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1);
+	if (!ASSERT_EQ(-1, recvd, "expected no data"))
+		goto out;
+
+	/* send remaining msg */
+	sent = send(c, msg + off, sizeof(msg) - off, 0);
+	if (!ASSERT_EQ(sent, sizeof(msg) - off, "send remaining data"))
+		goto out;
+
+	recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1);
+	if (!ASSERT_OK(err, "recv(msg)") ||
+	    !ASSERT_EQ(recvd, sizeof(msg) + push_len, "check length mismatch"))
+		goto out;
+
+	for (i = 0, j = 0; i < recvd;) {
+		/* skip checking the data that has been pushed in */
+		if (i >= start_push && i <= start_push + push_len - 1) {
+			i++;
+			continue;
+		}
+		if (!ASSERT_EQ(rcv[i], msg[j], "data mismatch"))
+			goto out;
+		i++;
+		j++;
+	}
+out:
+	if (c)
+		close(c);
+	if (p)
+		close(p);
+	test_sockmap_ktls__destroy(skel);
+}
+
+static void test_sockmap_ktls_tx_no_buf(int family, int sotype, bool push)
+{
+	int c = -1, p = -1, one = 1, two = 2;
+	struct test_sockmap_ktls *skel;
+	unsigned char *data = NULL;
+	struct msghdr msg = {0};
+	struct iovec iov[2];
+	int prog_fd, map_fd;
+	int txrx_buf = 1024;
+	int iov_length = 8192;
+	int err;
+
+	skel = test_sockmap_ktls__open_and_load();
+	if (!ASSERT_TRUE(skel, "open ktls skel"))
+		return;
+
+	err = create_pair(family, sotype, &c, &p);
+	if (!ASSERT_OK(err, "create_pair()"))
+		goto out;
+
+	err = setsockopt(c, SOL_SOCKET, SO_RCVBUFFORCE, &txrx_buf, sizeof(int));
+	err |= setsockopt(p, SOL_SOCKET, SO_SNDBUFFORCE, &txrx_buf, sizeof(int));
+	if (!ASSERT_OK(err, "set buf limit"))
+		goto out;
+
+	prog_fd = bpf_program__fd(skel->progs.prog_sk_policy_redir);
+	map_fd = bpf_map__fd(skel->maps.sock_map);
+
+	err = bpf_prog_attach(prog_fd, map_fd, BPF_SK_MSG_VERDICT, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach sk msg"))
+		goto out;
+
+	err = bpf_map_update_elem(map_fd, &one, &c, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(c)"))
+		goto out;
+
+	err = bpf_map_update_elem(map_fd, &two, &p, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(p)"))
+		goto out;
+
+	skel->bss->apply_bytes = 1024;
+
+	err = init_ktls_pairs(c, p);
+	if (!ASSERT_OK(err, "init_ktls_pairs(c, p)"))
+		goto out;
+
+	data = calloc(iov_length, sizeof(char));
+	if (!data)
+		goto out;
+
+	iov[0].iov_base = data;
+	iov[0].iov_len = iov_length;
+	iov[1].iov_base = data;
+	iov[1].iov_len = iov_length;
+	msg.msg_iov = iov;
+	msg.msg_iovlen = 2;
+
+	for (;;) {
+		err = sendmsg(c, &msg, MSG_DONTWAIT);
+		if (err <= 0)
+			break;
+	}
+
+out:
+	if (data)
+		free(data);
+	if (c != -1)
+		close(c);
+	if (p != -1)
+		close(p);
+
+	test_sockmap_ktls__destroy(skel);
+}
+
+static void test_sockmap_ktls_tx_pop(int family, int sotype)
+{
+	char msg[37] = "0123456789abcdefghijklmnopqrstuvwxyz\0";
+	int c = 0, p = 0, one = 1, sent, recvd;
+	struct test_sockmap_ktls *skel;
+	int prog_fd, map_fd;
+	char rcv[50] = {0};
+	int err;
+	int i, m, r;
+
+	skel = test_sockmap_ktls__open_and_load();
+	if (!ASSERT_TRUE(skel, "open ktls skel"))
+		return;
+
+	err = create_pair(family, sotype, &c, &p);
+	if (!ASSERT_OK(err, "create_pair()"))
+		goto out;
+
+	prog_fd = bpf_program__fd(skel->progs.prog_sk_policy);
+	map_fd = bpf_map__fd(skel->maps.sock_map);
+
+	err = bpf_prog_attach(prog_fd, map_fd, BPF_SK_MSG_VERDICT, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach sk msg"))
+		goto out;
+
+	err = bpf_map_update_elem(map_fd, &one, &c, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(c)"))
+		goto out;
+
+	err = init_ktls_pairs(c, p);
+	if (!ASSERT_OK(err, "init_ktls_pairs(c, p)"))
+		goto out;
+
+	struct {
+		int	pop_start;
+		int	pop_len;
+	} pop_policy[] = {
+		/* trim the start */
+		{0, 2},
+		{0, 10},
+		{1, 2},
+		{1, 10},
+		/* trim the end */
+		{35, 2},
+		/* New entries should be added before this line */
+		{-1, -1},
+	};
+
+	i = 0;
+	while (pop_policy[i].pop_start >= 0) {
+		skel->bss->pop_start = pop_policy[i].pop_start;
+		skel->bss->pop_end =  pop_policy[i].pop_len;
+
+		sent = send(c, msg, sizeof(msg), 0);
+		if (!ASSERT_EQ(sent, sizeof(msg), "send(msg)"))
+			goto out;
+
+		recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1);
+		if (!ASSERT_EQ(recvd, sizeof(msg) - pop_policy[i].pop_len, "pop len mismatch"))
+			goto out;
+
+		/* verify the data
+		 * msg: 0123456789a bcdefghij klmnopqrstuvwxyz
+		 *                  |       |
+		 *                  popped data
+		 */
+		for (m = 0, r = 0; m < sizeof(msg);) {
+			/* skip checking the data that has been popped */
+			if (m >= pop_policy[i].pop_start &&
+			    m <= pop_policy[i].pop_start + pop_policy[i].pop_len - 1) {
+				m++;
+				continue;
+			}
+
+			if (!ASSERT_EQ(msg[m], rcv[r], "data mismatch"))
+				goto out;
+			m++;
+			r++;
+		}
+		i++;
+	}
+out:
+	if (c)
+		close(c);
+	if (p)
+		close(p);
+	test_sockmap_ktls__destroy(skel);
+}
+
 static void run_tests(int family, enum bpf_map_type map_type)
 {
 	int map;
@@ -154,18 +411,32 @@ static void run_tests(int family, enum bpf_map_type map_type)
 	if (!ASSERT_GE(map, 0, "bpf_map_create"))
 		return;
 
-	if (test__start_subtest(fmt_test_name("disconnect_after_delete", family, map_type)))
-		test_sockmap_ktls_disconnect_after_delete(family, map);
 	if (test__start_subtest(fmt_test_name("update_fails_when_sock_has_ulp", family, map_type)))
 		test_sockmap_ktls_update_fails_when_sock_has_ulp(family, map);
 
 	close(map);
 }
 
+static void run_ktls_test(int family, int sotype)
+{
+	if (test__start_subtest("tls simple offload"))
+		test_sockmap_ktls_offload(family, sotype);
+	if (test__start_subtest("tls tx cork"))
+		test_sockmap_ktls_tx_cork(family, sotype, false);
+	if (test__start_subtest("tls tx cork with push"))
+		test_sockmap_ktls_tx_cork(family, sotype, true);
+	if (test__start_subtest("tls tx egress with no buf"))
+		test_sockmap_ktls_tx_no_buf(family, sotype, true);
+	if (test__start_subtest("tls tx with pop"))
+		test_sockmap_ktls_tx_pop(family, sotype);
+}
+
 void test_sockmap_ktls(void)
 {
 	run_tests(AF_INET, BPF_MAP_TYPE_SOCKMAP);
 	run_tests(AF_INET, BPF_MAP_TYPE_SOCKHASH);
 	run_tests(AF_INET6, BPF_MAP_TYPE_SOCKMAP);
 	run_tests(AF_INET6, BPF_MAP_TYPE_SOCKHASH);
+	run_ktls_test(AF_INET, SOCK_STREAM);
+	run_ktls_test(AF_INET6, SOCK_STREAM);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index 2cf0c7a3fe23..f1bdccc7e4e7 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -18,6 +18,7 @@
 #include <string.h>
 #include <sys/select.h>
 #include <unistd.h>
+#include <linux/vm_sockets.h>
 
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
@@ -26,302 +27,12 @@
 #include "test_progs.h"
 #include "test_sockmap_listen.skel.h"
 
-#define IO_TIMEOUT_SEC 30
-#define MAX_STRERR_LEN 256
-#define MAX_TEST_NAME 80
-
-#define _FAIL(errnum, fmt...)                                                  \
-	({                                                                     \
-		error_at_line(0, (errnum), __func__, __LINE__, fmt);           \
-		CHECK_FAIL(true);                                              \
-	})
-#define FAIL(fmt...) _FAIL(0, fmt)
-#define FAIL_ERRNO(fmt...) _FAIL(errno, fmt)
-#define FAIL_LIBBPF(err, msg)                                                  \
-	({                                                                     \
-		char __buf[MAX_STRERR_LEN];                                    \
-		libbpf_strerror((err), __buf, sizeof(__buf));                  \
-		FAIL("%s: %s", (msg), __buf);                                  \
-	})
-
-/* Wrappers that fail the test on error and report it. */
-
-#define xaccept_nonblock(fd, addr, len)                                        \
-	({                                                                     \
-		int __ret =                                                    \
-			accept_timeout((fd), (addr), (len), IO_TIMEOUT_SEC);   \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("accept");                                  \
-		__ret;                                                         \
-	})
-
-#define xbind(fd, addr, len)                                                   \
-	({                                                                     \
-		int __ret = bind((fd), (addr), (len));                         \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("bind");                                    \
-		__ret;                                                         \
-	})
-
-#define xclose(fd)                                                             \
-	({                                                                     \
-		int __ret = close((fd));                                       \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("close");                                   \
-		__ret;                                                         \
-	})
-
-#define xconnect(fd, addr, len)                                                \
-	({                                                                     \
-		int __ret = connect((fd), (addr), (len));                      \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("connect");                                 \
-		__ret;                                                         \
-	})
-
-#define xgetsockname(fd, addr, len)                                            \
-	({                                                                     \
-		int __ret = getsockname((fd), (addr), (len));                  \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("getsockname");                             \
-		__ret;                                                         \
-	})
-
-#define xgetsockopt(fd, level, name, val, len)                                 \
-	({                                                                     \
-		int __ret = getsockopt((fd), (level), (name), (val), (len));   \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("getsockopt(" #name ")");                   \
-		__ret;                                                         \
-	})
-
-#define xlisten(fd, backlog)                                                   \
-	({                                                                     \
-		int __ret = listen((fd), (backlog));                           \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("listen");                                  \
-		__ret;                                                         \
-	})
-
-#define xsetsockopt(fd, level, name, val, len)                                 \
-	({                                                                     \
-		int __ret = setsockopt((fd), (level), (name), (val), (len));   \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("setsockopt(" #name ")");                   \
-		__ret;                                                         \
-	})
-
-#define xsend(fd, buf, len, flags)                                             \
-	({                                                                     \
-		ssize_t __ret = send((fd), (buf), (len), (flags));             \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("send");                                    \
-		__ret;                                                         \
-	})
-
-#define xrecv_nonblock(fd, buf, len, flags)                                    \
-	({                                                                     \
-		ssize_t __ret = recv_timeout((fd), (buf), (len), (flags),      \
-					     IO_TIMEOUT_SEC);                  \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("recv");                                    \
-		__ret;                                                         \
-	})
-
-#define xsocket(family, sotype, flags)                                         \
-	({                                                                     \
-		int __ret = socket(family, sotype, flags);                     \
-		if (__ret == -1)                                               \
-			FAIL_ERRNO("socket");                                  \
-		__ret;                                                         \
-	})
-
-#define xbpf_map_delete_elem(fd, key)                                          \
-	({                                                                     \
-		int __ret = bpf_map_delete_elem((fd), (key));                  \
-		if (__ret < 0)                                               \
-			FAIL_ERRNO("map_delete");                              \
-		__ret;                                                         \
-	})
-
-#define xbpf_map_lookup_elem(fd, key, val)                                     \
-	({                                                                     \
-		int __ret = bpf_map_lookup_elem((fd), (key), (val));           \
-		if (__ret < 0)                                               \
-			FAIL_ERRNO("map_lookup");                              \
-		__ret;                                                         \
-	})
-
-#define xbpf_map_update_elem(fd, key, val, flags)                              \
-	({                                                                     \
-		int __ret = bpf_map_update_elem((fd), (key), (val), (flags));  \
-		if (__ret < 0)                                               \
-			FAIL_ERRNO("map_update");                              \
-		__ret;                                                         \
-	})
-
-#define xbpf_prog_attach(prog, target, type, flags)                            \
-	({                                                                     \
-		int __ret =                                                    \
-			bpf_prog_attach((prog), (target), (type), (flags));    \
-		if (__ret < 0)                                               \
-			FAIL_ERRNO("prog_attach(" #type ")");                  \
-		__ret;                                                         \
-	})
-
-#define xbpf_prog_detach2(prog, target, type)                                  \
-	({                                                                     \
-		int __ret = bpf_prog_detach2((prog), (target), (type));        \
-		if (__ret < 0)                                               \
-			FAIL_ERRNO("prog_detach2(" #type ")");                 \
-		__ret;                                                         \
-	})
-
-#define xpthread_create(thread, attr, func, arg)                               \
-	({                                                                     \
-		int __ret = pthread_create((thread), (attr), (func), (arg));   \
-		errno = __ret;                                                 \
-		if (__ret)                                                     \
-			FAIL_ERRNO("pthread_create");                          \
-		__ret;                                                         \
-	})
-
-#define xpthread_join(thread, retval)                                          \
-	({                                                                     \
-		int __ret = pthread_join((thread), (retval));                  \
-		errno = __ret;                                                 \
-		if (__ret)                                                     \
-			FAIL_ERRNO("pthread_join");                            \
-		__ret;                                                         \
-	})
-
-static int poll_read(int fd, unsigned int timeout_sec)
-{
-	struct timeval timeout = { .tv_sec = timeout_sec };
-	fd_set rfds;
-	int r;
-
-	FD_ZERO(&rfds);
-	FD_SET(fd, &rfds);
-
-	r = select(fd + 1, &rfds, NULL, NULL, &timeout);
-	if (r == 0)
-		errno = ETIME;
-
-	return r == 1 ? 0 : -1;
-}
-
-static int accept_timeout(int fd, struct sockaddr *addr, socklen_t *len,
-			  unsigned int timeout_sec)
-{
-	if (poll_read(fd, timeout_sec))
-		return -1;
-
-	return accept(fd, addr, len);
-}
-
-static int recv_timeout(int fd, void *buf, size_t len, int flags,
-			unsigned int timeout_sec)
-{
-	if (poll_read(fd, timeout_sec))
-		return -1;
-
-	return recv(fd, buf, len, flags);
-}
-
-static void init_addr_loopback4(struct sockaddr_storage *ss, socklen_t *len)
-{
-	struct sockaddr_in *addr4 = memset(ss, 0, sizeof(*ss));
+#include "sockmap_helpers.h"
 
-	addr4->sin_family = AF_INET;
-	addr4->sin_port = 0;
-	addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK);
-	*len = sizeof(*addr4);
-}
-
-static void init_addr_loopback6(struct sockaddr_storage *ss, socklen_t *len)
-{
-	struct sockaddr_in6 *addr6 = memset(ss, 0, sizeof(*ss));
-
-	addr6->sin6_family = AF_INET6;
-	addr6->sin6_port = 0;
-	addr6->sin6_addr = in6addr_loopback;
-	*len = sizeof(*addr6);
-}
-
-static void init_addr_loopback(int family, struct sockaddr_storage *ss,
-			       socklen_t *len)
-{
-	switch (family) {
-	case AF_INET:
-		init_addr_loopback4(ss, len);
-		return;
-	case AF_INET6:
-		init_addr_loopback6(ss, len);
-		return;
-	default:
-		FAIL("unsupported address family %d", family);
-	}
-}
+#define NO_FLAGS 0
 
-static inline struct sockaddr *sockaddr(struct sockaddr_storage *ss)
-{
-	return (struct sockaddr *)ss;
-}
-
-static int enable_reuseport(int s, int progfd)
-{
-	int err, one = 1;
-
-	err = xsetsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one));
-	if (err)
-		return -1;
-	err = xsetsockopt(s, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &progfd,
-			  sizeof(progfd));
-	if (err)
-		return -1;
-
-	return 0;
-}
-
-static int socket_loopback_reuseport(int family, int sotype, int progfd)
-{
-	struct sockaddr_storage addr;
-	socklen_t len;
-	int err, s;
-
-	init_addr_loopback(family, &addr, &len);
-
-	s = xsocket(family, sotype, 0);
-	if (s == -1)
-		return -1;
-
-	if (progfd >= 0)
-		enable_reuseport(s, progfd);
-
-	err = xbind(s, sockaddr(&addr), len);
-	if (err)
-		goto close;
-
-	if (sotype & SOCK_DGRAM)
-		return s;
-
-	err = xlisten(s, SOMAXCONN);
-	if (err)
-		goto close;
-
-	return s;
-close:
-	xclose(s);
-	return -1;
-}
-
-static int socket_loopback(int family, int sotype)
-{
-	return socket_loopback_reuseport(family, sotype, -1);
-}
-
-static void test_insert_invalid(int family, int sotype, int mapfd)
+static void test_insert_invalid(struct test_sockmap_listen *skel __always_unused,
+				int family, int sotype, int mapfd)
 {
 	u32 key = 0;
 	u64 value;
@@ -338,7 +49,8 @@ static void test_insert_invalid(int family, int sotype, int mapfd)
 		FAIL_ERRNO("map_update: expected EBADF");
 }
 
-static void test_insert_opened(int family, int sotype, int mapfd)
+static void test_insert_opened(struct test_sockmap_listen *skel __always_unused,
+			       int family, int sotype, int mapfd)
 {
 	u32 key = 0;
 	u64 value;
@@ -359,10 +71,11 @@ static void test_insert_opened(int family, int sotype, int mapfd)
 	xclose(s);
 }
 
-static void test_insert_bound(int family, int sotype, int mapfd)
+static void test_insert_bound(struct test_sockmap_listen *skel __always_unused,
+			      int family, int sotype, int mapfd)
 {
 	struct sockaddr_storage addr;
-	socklen_t len;
+	socklen_t len = 0;
 	u32 key = 0;
 	u64 value;
 	int err, s;
@@ -386,7 +99,8 @@ close:
 	xclose(s);
 }
 
-static void test_insert(int family, int sotype, int mapfd)
+static void test_insert(struct test_sockmap_listen *skel __always_unused,
+			int family, int sotype, int mapfd)
 {
 	u64 value;
 	u32 key;
@@ -402,7 +116,8 @@ static void test_insert(int family, int sotype, int mapfd)
 	xclose(s);
 }
 
-static void test_delete_after_insert(int family, int sotype, int mapfd)
+static void test_delete_after_insert(struct test_sockmap_listen *skel __always_unused,
+				     int family, int sotype, int mapfd)
 {
 	u64 value;
 	u32 key;
@@ -419,7 +134,8 @@ static void test_delete_after_insert(int family, int sotype, int mapfd)
 	xclose(s);
 }
 
-static void test_delete_after_close(int family, int sotype, int mapfd)
+static void test_delete_after_close(struct test_sockmap_listen *skel __always_unused,
+				    int family, int sotype, int mapfd)
 {
 	int err, s;
 	u64 value;
@@ -442,7 +158,8 @@ static void test_delete_after_close(int family, int sotype, int mapfd)
 		FAIL_ERRNO("map_delete: expected EINVAL/EINVAL");
 }
 
-static void test_lookup_after_insert(int family, int sotype, int mapfd)
+static void test_lookup_after_insert(struct test_sockmap_listen *skel __always_unused,
+				     int family, int sotype, int mapfd)
 {
 	u64 cookie, value;
 	socklen_t len;
@@ -470,7 +187,8 @@ static void test_lookup_after_insert(int family, int sotype, int mapfd)
 	xclose(s);
 }
 
-static void test_lookup_after_delete(int family, int sotype, int mapfd)
+static void test_lookup_after_delete(struct test_sockmap_listen *skel __always_unused,
+				     int family, int sotype, int mapfd)
 {
 	int err, s;
 	u64 value;
@@ -493,7 +211,8 @@ static void test_lookup_after_delete(int family, int sotype, int mapfd)
 	xclose(s);
 }
 
-static void test_lookup_32_bit_value(int family, int sotype, int mapfd)
+static void test_lookup_32_bit_value(struct test_sockmap_listen *skel __always_unused,
+				     int family, int sotype, int mapfd)
 {
 	u32 key, value32;
 	int err, s;
@@ -523,7 +242,8 @@ close:
 	xclose(s);
 }
 
-static void test_update_existing(int family, int sotype, int mapfd)
+static void test_update_existing(struct test_sockmap_listen *skel __always_unused,
+				 int family, int sotype, int mapfd)
 {
 	int s1, s2;
 	u64 value;
@@ -551,7 +271,7 @@ close_s1:
 /* Exercise the code path where we destroy child sockets that never
  * got accept()'ed, aka orphans, when parent socket gets closed.
  */
-static void test_destroy_orphan_child(int family, int sotype, int mapfd)
+static void do_destroy_orphan_child(int family, int sotype, int mapfd)
 {
 	struct sockaddr_storage addr;
 	socklen_t len;
@@ -582,10 +302,38 @@ close_srv:
 	xclose(s);
 }
 
+static void test_destroy_orphan_child(struct test_sockmap_listen *skel,
+				      int family, int sotype, int mapfd)
+{
+	int msg_verdict = bpf_program__fd(skel->progs.prog_msg_verdict);
+	int skb_verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+	const struct test {
+		int progfd;
+		enum bpf_attach_type atype;
+	} tests[] = {
+		{ -1, -1 },
+		{ msg_verdict, BPF_SK_MSG_VERDICT },
+		{ skb_verdict, BPF_SK_SKB_VERDICT },
+	};
+	const struct test *t;
+
+	for (t = tests; t < tests + ARRAY_SIZE(tests); t++) {
+		if (t->progfd != -1 &&
+		    xbpf_prog_attach(t->progfd, mapfd, t->atype, 0) != 0)
+			return;
+
+		do_destroy_orphan_child(family, sotype, mapfd);
+
+		if (t->progfd != -1)
+			xbpf_prog_detach2(t->progfd, mapfd, t->atype);
+	}
+}
+
 /* Perform a passive open after removing listening socket from SOCKMAP
  * to ensure that callbacks get restored properly.
  */
-static void test_clone_after_delete(int family, int sotype, int mapfd)
+static void test_clone_after_delete(struct test_sockmap_listen *skel __always_unused,
+				    int family, int sotype, int mapfd)
 {
 	struct sockaddr_storage addr;
 	socklen_t len;
@@ -621,7 +369,8 @@ close_srv:
  * SOCKMAP, but got accept()'ed only after the parent has been removed
  * from SOCKMAP, gets cloned without parent psock state or callbacks.
  */
-static void test_accept_after_delete(int family, int sotype, int mapfd)
+static void test_accept_after_delete(struct test_sockmap_listen *skel __always_unused,
+				     int family, int sotype, int mapfd)
 {
 	struct sockaddr_storage addr;
 	const u32 zero = 0;
@@ -675,7 +424,8 @@ close_srv:
 /* Check that child socket that got created and accepted while parent
  * was in a SOCKMAP is cloned without parent psock state or callbacks.
  */
-static void test_accept_before_delete(int family, int sotype, int mapfd)
+static void test_accept_before_delete(struct test_sockmap_listen *skel __always_unused,
+				      int family, int sotype, int mapfd)
 {
 	struct sockaddr_storage addr;
 	const u32 zero = 0, one = 1;
@@ -784,7 +534,8 @@ done:
 	return NULL;
 }
 
-static void test_syn_recv_insert_delete(int family, int sotype, int mapfd)
+static void test_syn_recv_insert_delete(struct test_sockmap_listen *skel __always_unused,
+					int family, int sotype, int mapfd)
 {
 	struct connect_accept_ctx ctx = { 0 };
 	struct sockaddr_storage addr;
@@ -847,7 +598,8 @@ static void *listen_thread(void *arg)
 	return NULL;
 }
 
-static void test_race_insert_listen(int family, int socktype, int mapfd)
+static void test_race_insert_listen(struct test_sockmap_listen *skel __always_unused,
+				    int family, int socktype, int mapfd)
 {
 	struct connect_accept_ctx ctx = { 0 };
 	const u32 zero = 0;
@@ -921,71 +673,26 @@ static const char *redir_mode_str(enum redir_mode mode)
 	}
 }
 
-static int add_to_sockmap(int sock_mapfd, int fd1, int fd2)
-{
-	u64 value;
-	u32 key;
-	int err;
-
-	key = 0;
-	value = fd1;
-	err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
-	if (err)
-		return err;
-
-	key = 1;
-	value = fd2;
-	return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
-}
-
 static void redir_to_connected(int family, int sotype, int sock_mapfd,
 			       int verd_mapfd, enum redir_mode mode)
 {
 	const char *log_prefix = redir_mode_str(mode);
-	struct sockaddr_storage addr;
-	int s, c0, c1, p0, p1;
+	int c0, c1, p0, p1;
 	unsigned int pass;
-	socklen_t len;
 	int err, n;
 	u32 key;
 	char b;
 
 	zero_verdict_count(verd_mapfd);
 
-	s = socket_loopback(family, sotype | SOCK_NONBLOCK);
-	if (s < 0)
-		return;
-
-	len = sizeof(addr);
-	err = xgetsockname(s, sockaddr(&addr), &len);
-	if (err)
-		goto close_srv;
-
-	c0 = xsocket(family, sotype, 0);
-	if (c0 < 0)
-		goto close_srv;
-	err = xconnect(c0, sockaddr(&addr), len);
+	err = create_socket_pairs(family, sotype | SOCK_NONBLOCK, &c0, &c1,
+				  &p0, &p1);
 	if (err)
-		goto close_cli0;
-
-	p0 = xaccept_nonblock(s, NULL, NULL);
-	if (p0 < 0)
-		goto close_cli0;
-
-	c1 = xsocket(family, sotype, 0);
-	if (c1 < 0)
-		goto close_peer0;
-	err = xconnect(c1, sockaddr(&addr), len);
-	if (err)
-		goto close_cli1;
-
-	p1 = xaccept_nonblock(s, NULL, NULL);
-	if (p1 < 0)
-		goto close_cli1;
+		return;
 
 	err = add_to_sockmap(sock_mapfd, p0, p1);
 	if (err)
-		goto close_peer1;
+		goto close;
 
 	n = write(mode == REDIR_INGRESS ? c1 : p1, "a", 1);
 	if (n < 0)
@@ -993,12 +700,12 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd,
 	if (n == 0)
 		FAIL("%s: incomplete write", log_prefix);
 	if (n < 1)
-		goto close_peer1;
+		goto close;
 
 	key = SK_PASS;
 	err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass);
 	if (err)
-		goto close_peer1;
+		goto close;
 	if (pass != 1)
 		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
 	n = recv_timeout(c0, &b, 1, 0, IO_TIMEOUT_SEC);
@@ -1007,16 +714,11 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd,
 	if (n == 0)
 		FAIL("%s: incomplete recv", log_prefix);
 
-close_peer1:
+close:
 	xclose(p1);
-close_cli1:
 	xclose(c1);
-close_peer0:
 	xclose(p0);
-close_cli0:
 	xclose(c0);
-close_srv:
-	xclose(s);
 }
 
 static void test_skb_redir_to_connected(struct test_sockmap_listen *skel,
@@ -1062,6 +764,24 @@ static void test_msg_redir_to_connected(struct test_sockmap_listen *skel,
 	xbpf_prog_detach2(verdict, sock_map, BPF_SK_MSG_VERDICT);
 }
 
+static void test_msg_redir_to_connected_with_link(struct test_sockmap_listen *skel,
+						  struct bpf_map *inner_map, int family,
+						  int sotype)
+{
+	int prog_msg_verdict = bpf_program__fd(skel->progs.prog_msg_verdict);
+	int verdict_map = bpf_map__fd(skel->maps.verdict_map);
+	int sock_map = bpf_map__fd(inner_map);
+	int link_fd;
+
+	link_fd = bpf_link_create(prog_msg_verdict, sock_map, BPF_SK_MSG_VERDICT, NULL);
+	if (!ASSERT_GE(link_fd, 0, "bpf_link_create"))
+		return;
+
+	redir_to_connected(family, sotype, sock_map, verdict_map, REDIR_EGRESS);
+
+	close(link_fd);
+}
+
 static void redir_to_listening(int family, int sotype, int sock_mapfd,
 			       int verd_mapfd, enum redir_mode mode)
 {
@@ -1164,6 +884,92 @@ static void test_msg_redir_to_listening(struct test_sockmap_listen *skel,
 	xbpf_prog_detach2(verdict, sock_map, BPF_SK_MSG_VERDICT);
 }
 
+static void test_msg_redir_to_listening_with_link(struct test_sockmap_listen *skel,
+						  struct bpf_map *inner_map, int family,
+						  int sotype)
+{
+	struct bpf_program *verdict = skel->progs.prog_msg_verdict;
+	int verdict_map = bpf_map__fd(skel->maps.verdict_map);
+	int sock_map = bpf_map__fd(inner_map);
+	struct bpf_link *link;
+
+	link = bpf_program__attach_sockmap(verdict, sock_map);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_sockmap"))
+		return;
+
+	redir_to_listening(family, sotype, sock_map, verdict_map, REDIR_EGRESS);
+
+	bpf_link__detach(link);
+}
+
+static void redir_partial(int family, int sotype, int sock_map, int parser_map)
+{
+	int c0 = -1, c1 = -1, p0 = -1, p1 = -1;
+	int err, n, key, value;
+	char buf[] = "abc";
+
+	key = 0;
+	value = sizeof(buf) - 1;
+	err = xbpf_map_update_elem(parser_map, &key, &value, 0);
+	if (err)
+		return;
+
+	err = create_socket_pairs(family, sotype | SOCK_NONBLOCK, &c0, &c1,
+				  &p0, &p1);
+	if (err)
+		goto clean_parser_map;
+
+	err = add_to_sockmap(sock_map, p0, p1);
+	if (err)
+		goto close;
+
+	n = xsend(c1, buf, sizeof(buf), 0);
+	if (n == -1)
+		goto close;
+	if (n < sizeof(buf))
+		FAIL("incomplete write");
+
+	n = xrecv_nonblock(c0, buf, sizeof(buf), 0);
+	if (n != sizeof(buf) - 1)
+		FAIL("expect %zu, received %d", sizeof(buf) - 1, n);
+
+close:
+	xclose(c0);
+	xclose(p0);
+	xclose(c1);
+	xclose(p1);
+
+clean_parser_map:
+	key = 0;
+	value = 0;
+	xbpf_map_update_elem(parser_map, &key, &value, 0);
+}
+
+static void test_skb_redir_partial(struct test_sockmap_listen *skel,
+				   struct bpf_map *inner_map, int family,
+				   int sotype)
+{
+	int verdict = bpf_program__fd(skel->progs.prog_stream_verdict);
+	int parser = bpf_program__fd(skel->progs.prog_stream_parser);
+	int parser_map = bpf_map__fd(skel->maps.parser_map);
+	int sock_map = bpf_map__fd(inner_map);
+	int err;
+
+	err = xbpf_prog_attach(parser, sock_map, BPF_SK_SKB_STREAM_PARSER, 0);
+	if (err)
+		return;
+
+	err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_STREAM_VERDICT, 0);
+	if (err)
+		goto detach;
+
+	redir_partial(family, sotype, sock_map, parser_map);
+
+	xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_STREAM_VERDICT);
+detach:
+	xbpf_prog_detach2(parser, sock_map, BPF_SK_SKB_STREAM_PARSER);
+}
+
 static void test_reuseport_select_listening(int family, int sotype,
 					    int sock_map, int verd_map,
 					    int reuseport_prog)
@@ -1434,6 +1240,8 @@ static const char *family_str(sa_family_t family)
 		return "IPv6";
 	case AF_UNIX:
 		return "Unix";
+	case AF_VSOCK:
+		return "VSOCK";
 	default:
 		return "unknown";
 	}
@@ -1473,7 +1281,8 @@ static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map,
 		     int family, int sotype)
 {
 	const struct op_test {
-		void (*fn)(int family, int sotype, int mapfd);
+		void (*fn)(struct test_sockmap_listen *skel,
+			   int family, int sotype, int mapfd);
 		const char *name;
 		int sotype;
 	} tests[] = {
@@ -1520,7 +1329,7 @@ static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map,
 		if (!test__start_subtest(s))
 			continue;
 
-		t->fn(family, sotype, map_fd);
+		t->fn(skel, family, sotype, map_fd);
 		test_ops_cleanup(map);
 	}
 }
@@ -1535,8 +1344,11 @@ static void test_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
 	} tests[] = {
 		TEST(test_skb_redir_to_connected),
 		TEST(test_skb_redir_to_listening),
+		TEST(test_skb_redir_partial),
 		TEST(test_msg_redir_to_connected),
+		TEST(test_msg_redir_to_connected_with_link),
 		TEST(test_msg_redir_to_listening),
+		TEST(test_msg_redir_to_listening_with_link),
 	};
 	const char *family_name, *map_name;
 	const struct redir_test *t;
@@ -1556,94 +1368,6 @@ static void test_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
 	}
 }
 
-static void unix_redir_to_connected(int sotype, int sock_mapfd,
-			       int verd_mapfd, enum redir_mode mode)
-{
-	const char *log_prefix = redir_mode_str(mode);
-	int c0, c1, p0, p1;
-	unsigned int pass;
-	int err, n;
-	int sfd[2];
-	u32 key;
-	char b;
-
-	zero_verdict_count(verd_mapfd);
-
-	if (socketpair(AF_UNIX, sotype | SOCK_NONBLOCK, 0, sfd))
-		return;
-	c0 = sfd[0], p0 = sfd[1];
-
-	if (socketpair(AF_UNIX, sotype | SOCK_NONBLOCK, 0, sfd))
-		goto close0;
-	c1 = sfd[0], p1 = sfd[1];
-
-	err = add_to_sockmap(sock_mapfd, p0, p1);
-	if (err)
-		goto close;
-
-	n = write(c1, "a", 1);
-	if (n < 0)
-		FAIL_ERRNO("%s: write", log_prefix);
-	if (n == 0)
-		FAIL("%s: incomplete write", log_prefix);
-	if (n < 1)
-		goto close;
-
-	key = SK_PASS;
-	err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass);
-	if (err)
-		goto close;
-	if (pass != 1)
-		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-
-	n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
-	if (n < 0)
-		FAIL_ERRNO("%s: recv_timeout", log_prefix);
-	if (n == 0)
-		FAIL("%s: incomplete recv", log_prefix);
-
-close:
-	xclose(c1);
-	xclose(p1);
-close0:
-	xclose(c0);
-	xclose(p0);
-}
-
-static void unix_skb_redir_to_connected(struct test_sockmap_listen *skel,
-					struct bpf_map *inner_map, int sotype)
-{
-	int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
-	int verdict_map = bpf_map__fd(skel->maps.verdict_map);
-	int sock_map = bpf_map__fd(inner_map);
-	int err;
-
-	err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0);
-	if (err)
-		return;
-
-	skel->bss->test_ingress = false;
-	unix_redir_to_connected(sotype, sock_map, verdict_map, REDIR_EGRESS);
-	skel->bss->test_ingress = true;
-	unix_redir_to_connected(sotype, sock_map, verdict_map, REDIR_INGRESS);
-
-	xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
-}
-
-static void test_unix_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
-			    int sotype)
-{
-	const char *family_name, *map_name;
-	char s[MAX_TEST_NAME];
-
-	family_name = family_str(AF_UNIX);
-	map_name = map_type_str(map);
-	snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, __func__);
-	if (!test__start_subtest(s))
-		return;
-	unix_skb_redir_to_connected(skel, map, sotype);
-}
-
 static void test_reuseport(struct test_sockmap_listen *skel,
 			   struct bpf_map *map, int family, int sotype)
 {
@@ -1684,310 +1408,6 @@ static void test_reuseport(struct test_sockmap_listen *skel,
 	}
 }
 
-static int inet_socketpair(int family, int type, int *s, int *c)
-{
-	struct sockaddr_storage addr;
-	socklen_t len;
-	int p0, c0;
-	int err;
-
-	p0 = socket_loopback(family, type | SOCK_NONBLOCK);
-	if (p0 < 0)
-		return p0;
-
-	len = sizeof(addr);
-	err = xgetsockname(p0, sockaddr(&addr), &len);
-	if (err)
-		goto close_peer0;
-
-	c0 = xsocket(family, type | SOCK_NONBLOCK, 0);
-	if (c0 < 0) {
-		err = c0;
-		goto close_peer0;
-	}
-	err = xconnect(c0, sockaddr(&addr), len);
-	if (err)
-		goto close_cli0;
-	err = xgetsockname(c0, sockaddr(&addr), &len);
-	if (err)
-		goto close_cli0;
-	err = xconnect(p0, sockaddr(&addr), len);
-	if (err)
-		goto close_cli0;
-
-	*s = p0;
-	*c = c0;
-	return 0;
-
-close_cli0:
-	xclose(c0);
-close_peer0:
-	xclose(p0);
-	return err;
-}
-
-static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd,
-				   enum redir_mode mode)
-{
-	const char *log_prefix = redir_mode_str(mode);
-	int c0, c1, p0, p1;
-	unsigned int pass;
-	int err, n;
-	u32 key;
-	char b;
-
-	zero_verdict_count(verd_mapfd);
-
-	err = inet_socketpair(family, SOCK_DGRAM, &p0, &c0);
-	if (err)
-		return;
-	err = inet_socketpair(family, SOCK_DGRAM, &p1, &c1);
-	if (err)
-		goto close_cli0;
-
-	err = add_to_sockmap(sock_mapfd, p0, p1);
-	if (err)
-		goto close_cli1;
-
-	n = write(c1, "a", 1);
-	if (n < 0)
-		FAIL_ERRNO("%s: write", log_prefix);
-	if (n == 0)
-		FAIL("%s: incomplete write", log_prefix);
-	if (n < 1)
-		goto close_cli1;
-
-	key = SK_PASS;
-	err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass);
-	if (err)
-		goto close_cli1;
-	if (pass != 1)
-		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-
-	n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
-	if (n < 0)
-		FAIL_ERRNO("%s: recv_timeout", log_prefix);
-	if (n == 0)
-		FAIL("%s: incomplete recv", log_prefix);
-
-close_cli1:
-	xclose(c1);
-	xclose(p1);
-close_cli0:
-	xclose(c0);
-	xclose(p0);
-}
-
-static void udp_skb_redir_to_connected(struct test_sockmap_listen *skel,
-				       struct bpf_map *inner_map, int family)
-{
-	int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
-	int verdict_map = bpf_map__fd(skel->maps.verdict_map);
-	int sock_map = bpf_map__fd(inner_map);
-	int err;
-
-	err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0);
-	if (err)
-		return;
-
-	skel->bss->test_ingress = false;
-	udp_redir_to_connected(family, sock_map, verdict_map, REDIR_EGRESS);
-	skel->bss->test_ingress = true;
-	udp_redir_to_connected(family, sock_map, verdict_map, REDIR_INGRESS);
-
-	xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
-}
-
-static void test_udp_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
-			   int family)
-{
-	const char *family_name, *map_name;
-	char s[MAX_TEST_NAME];
-
-	family_name = family_str(family);
-	map_name = map_type_str(map);
-	snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, __func__);
-	if (!test__start_subtest(s))
-		return;
-	udp_skb_redir_to_connected(skel, map, family);
-}
-
-static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd,
-					int verd_mapfd, enum redir_mode mode)
-{
-	const char *log_prefix = redir_mode_str(mode);
-	int c0, c1, p0, p1;
-	unsigned int pass;
-	int err, n;
-	int sfd[2];
-	u32 key;
-	char b;
-
-	zero_verdict_count(verd_mapfd);
-
-	if (socketpair(AF_UNIX, SOCK_DGRAM | SOCK_NONBLOCK, 0, sfd))
-		return;
-	c0 = sfd[0], p0 = sfd[1];
-
-	err = inet_socketpair(family, SOCK_DGRAM, &p1, &c1);
-	if (err)
-		goto close;
-
-	err = add_to_sockmap(sock_mapfd, p0, p1);
-	if (err)
-		goto close_cli1;
-
-	n = write(c1, "a", 1);
-	if (n < 0)
-		FAIL_ERRNO("%s: write", log_prefix);
-	if (n == 0)
-		FAIL("%s: incomplete write", log_prefix);
-	if (n < 1)
-		goto close_cli1;
-
-	key = SK_PASS;
-	err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass);
-	if (err)
-		goto close_cli1;
-	if (pass != 1)
-		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-
-	n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
-	if (n < 0)
-		FAIL_ERRNO("%s: recv_timeout", log_prefix);
-	if (n == 0)
-		FAIL("%s: incomplete recv", log_prefix);
-
-close_cli1:
-	xclose(c1);
-	xclose(p1);
-close:
-	xclose(c0);
-	xclose(p0);
-}
-
-static void inet_unix_skb_redir_to_connected(struct test_sockmap_listen *skel,
-					    struct bpf_map *inner_map, int family)
-{
-	int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
-	int verdict_map = bpf_map__fd(skel->maps.verdict_map);
-	int sock_map = bpf_map__fd(inner_map);
-	int err;
-
-	err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0);
-	if (err)
-		return;
-
-	skel->bss->test_ingress = false;
-	inet_unix_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
-				    REDIR_EGRESS);
-	inet_unix_redir_to_connected(family, SOCK_STREAM, sock_map, verdict_map,
-				    REDIR_EGRESS);
-	skel->bss->test_ingress = true;
-	inet_unix_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
-				    REDIR_INGRESS);
-	inet_unix_redir_to_connected(family, SOCK_STREAM, sock_map, verdict_map,
-				    REDIR_INGRESS);
-
-	xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
-}
-
-static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd,
-					int verd_mapfd, enum redir_mode mode)
-{
-	const char *log_prefix = redir_mode_str(mode);
-	int c0, c1, p0, p1;
-	unsigned int pass;
-	int err, n;
-	int sfd[2];
-	u32 key;
-	char b;
-
-	zero_verdict_count(verd_mapfd);
-
-	err = inet_socketpair(family, SOCK_DGRAM, &p0, &c0);
-	if (err)
-		return;
-
-	if (socketpair(AF_UNIX, SOCK_DGRAM | SOCK_NONBLOCK, 0, sfd))
-		goto close_cli0;
-	c1 = sfd[0], p1 = sfd[1];
-
-	err = add_to_sockmap(sock_mapfd, p0, p1);
-	if (err)
-		goto close;
-
-	n = write(c1, "a", 1);
-	if (n < 0)
-		FAIL_ERRNO("%s: write", log_prefix);
-	if (n == 0)
-		FAIL("%s: incomplete write", log_prefix);
-	if (n < 1)
-		goto close;
-
-	key = SK_PASS;
-	err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass);
-	if (err)
-		goto close;
-	if (pass != 1)
-		FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-
-	n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
-	if (n < 0)
-		FAIL_ERRNO("%s: recv_timeout", log_prefix);
-	if (n == 0)
-		FAIL("%s: incomplete recv", log_prefix);
-
-close:
-	xclose(c1);
-	xclose(p1);
-close_cli0:
-	xclose(c0);
-	xclose(p0);
-
-}
-
-static void unix_inet_skb_redir_to_connected(struct test_sockmap_listen *skel,
-					    struct bpf_map *inner_map, int family)
-{
-	int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
-	int verdict_map = bpf_map__fd(skel->maps.verdict_map);
-	int sock_map = bpf_map__fd(inner_map);
-	int err;
-
-	err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0);
-	if (err)
-		return;
-
-	skel->bss->test_ingress = false;
-	unix_inet_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
-				     REDIR_EGRESS);
-	unix_inet_redir_to_connected(family, SOCK_STREAM, sock_map, verdict_map,
-				     REDIR_EGRESS);
-	skel->bss->test_ingress = true;
-	unix_inet_redir_to_connected(family, SOCK_DGRAM, sock_map, verdict_map,
-				     REDIR_INGRESS);
-	unix_inet_redir_to_connected(family, SOCK_STREAM, sock_map, verdict_map,
-				     REDIR_INGRESS);
-
-	xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
-}
-
-static void test_udp_unix_redir(struct test_sockmap_listen *skel, struct bpf_map *map,
-				int family)
-{
-	const char *family_name, *map_name;
-	char s[MAX_TEST_NAME];
-
-	family_name = family_str(family);
-	map_name = map_type_str(map);
-	snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, __func__);
-	if (!test__start_subtest(s))
-		return;
-	inet_unix_skb_redir_to_connected(skel, map, family);
-	unix_inet_skb_redir_to_connected(skel, map, family);
-}
-
 static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map,
 		      int family)
 {
@@ -1996,8 +1416,6 @@ static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map,
 	test_redir(skel, map, family, SOCK_STREAM);
 	test_reuseport(skel, map, family, SOCK_STREAM);
 	test_reuseport(skel, map, family, SOCK_DGRAM);
-	test_udp_redir(skel, map, family);
-	test_udp_unix_redir(skel, map, family);
 }
 
 void serial_test_sockmap_listen(void)
@@ -2013,14 +1431,10 @@ void serial_test_sockmap_listen(void)
 	skel->bss->test_sockmap = true;
 	run_tests(skel, skel->maps.sock_map, AF_INET);
 	run_tests(skel, skel->maps.sock_map, AF_INET6);
-	test_unix_redir(skel, skel->maps.sock_map, SOCK_DGRAM);
-	test_unix_redir(skel, skel->maps.sock_map, SOCK_STREAM);
 
 	skel->bss->test_sockmap = false;
 	run_tests(skel, skel->maps.sock_hash, AF_INET);
 	run_tests(skel, skel->maps.sock_hash, AF_INET6);
-	test_unix_redir(skel, skel->maps.sock_hash, SOCK_DGRAM);
-	test_unix_redir(skel, skel->maps.sock_hash, SOCK_STREAM);
 
 	test_sockmap_listen__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_redir.c b/tools/testing/selftests/bpf/prog_tests/sockmap_redir.c
new file mode 100644
index 000000000000..9c461d93113d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_redir.c
@@ -0,0 +1,465 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test for sockmap/sockhash redirection.
+ *
+ * BPF_MAP_TYPE_SOCKMAP
+ * BPF_MAP_TYPE_SOCKHASH
+ *	x
+ * sk_msg-to-egress
+ * sk_msg-to-ingress
+ * sk_skb-to-egress
+ * sk_skb-to-ingress
+ *	x
+ * AF_INET, SOCK_STREAM
+ * AF_INET6, SOCK_STREAM
+ * AF_INET, SOCK_DGRAM
+ * AF_INET6, SOCK_DGRAM
+ * AF_UNIX, SOCK_STREAM
+ * AF_UNIX, SOCK_DGRAM
+ * AF_VSOCK, SOCK_STREAM
+ * AF_VSOCK, SOCK_SEQPACKET
+ */
+
+#include <errno.h>
+#include <error.h>
+#include <sched.h>
+#include <stdio.h>
+#include <unistd.h>
+
+#include <netinet/in.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <sys/un.h>
+#include <linux/string.h>
+#include <linux/vm_sockets.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "linux/const.h"
+#include "test_progs.h"
+#include "sockmap_helpers.h"
+#include "test_sockmap_redir.skel.h"
+
+/* The meaning of SUPPORTED is "will redirect packet as expected".
+ */
+#define SUPPORTED		_BITUL(0)
+
+/* Note on sk_skb-to-ingress ->af_vsock:
+ *
+ * Peer socket may receive the packet some time after the return from sendmsg().
+ * In a typical usage scenario, recvmsg() will block until the redirected packet
+ * appears in the destination queue, or timeout if the packet was dropped. By
+ * that point, the verdict map has already been updated to reflect what has
+ * happened.
+ *
+ * But sk_skb-to-ingress/af_vsock is an unsupported combination, so no recvmsg()
+ * takes place. Which means we may race the execution of the verdict logic and
+ * read map_verd before it has been updated, i.e. we might observe
+ * map_verd[SK_DROP]=0 instead of map_verd[SK_DROP]=1.
+ *
+ * This confuses the selftest logic: if there was no packet dropped, where's the
+ * packet? So here's a heuristic: on map_verd[SK_DROP]=map_verd[SK_PASS]=0
+ * (which implies the verdict program has not been ran) just re-read the verdict
+ * map again.
+ */
+#define UNSUPPORTED_RACY_VERD	_BITUL(1)
+
+enum prog_type {
+	SK_MSG_EGRESS,
+	SK_MSG_INGRESS,
+	SK_SKB_EGRESS,
+	SK_SKB_INGRESS,
+};
+
+enum {
+	SEND_INNER = 0,
+	SEND_OUTER,
+};
+
+enum {
+	RECV_INNER = 0,
+	RECV_OUTER,
+};
+
+struct maps {
+	int in;
+	int out;
+	int verd;
+};
+
+struct combo_spec {
+	enum prog_type prog_type;
+	const char *in, *out;
+};
+
+struct redir_spec {
+	const char *name;
+	int idx_send;
+	int idx_recv;
+	enum prog_type prog_type;
+};
+
+struct socket_spec {
+	int family;
+	int sotype;
+	int send_flags;
+	int in[2];
+	int out[2];
+};
+
+static int socket_spec_pairs(struct socket_spec *s)
+{
+	return create_socket_pairs(s->family, s->sotype,
+				   &s->in[0], &s->out[0],
+				   &s->in[1], &s->out[1]);
+}
+
+static void socket_spec_close(struct socket_spec *s)
+{
+	xclose(s->in[0]);
+	xclose(s->in[1]);
+	xclose(s->out[0]);
+	xclose(s->out[1]);
+}
+
+static void get_redir_params(struct redir_spec *redir,
+			     struct test_sockmap_redir *skel, int *prog_fd,
+			     enum bpf_attach_type *attach_type,
+			     int *redirect_flags)
+{
+	enum prog_type type = redir->prog_type;
+	struct bpf_program *prog;
+	bool sk_msg;
+
+	sk_msg = type == SK_MSG_INGRESS || type == SK_MSG_EGRESS;
+	prog = sk_msg ? skel->progs.prog_msg_verdict : skel->progs.prog_skb_verdict;
+
+	*prog_fd = bpf_program__fd(prog);
+	*attach_type = sk_msg ? BPF_SK_MSG_VERDICT : BPF_SK_SKB_VERDICT;
+
+	if (type == SK_MSG_INGRESS || type == SK_SKB_INGRESS)
+		*redirect_flags = BPF_F_INGRESS;
+	else
+		*redirect_flags = 0;
+}
+
+static void try_recv(const char *prefix, int fd, int flags, bool expect_success)
+{
+	ssize_t n;
+	char buf;
+
+	errno = 0;
+	n = recv(fd, &buf, 1, flags);
+	if (n < 0 && expect_success)
+		FAIL_ERRNO("%s: unexpected failure: retval=%zd", prefix, n);
+	if (!n && !expect_success)
+		FAIL("%s: expected failure: retval=%zd", prefix, n);
+}
+
+static void handle_unsupported(int sd_send, int sd_peer, int sd_in, int sd_out,
+			       int sd_recv, int map_verd, int status)
+{
+	unsigned int drop, pass;
+	char recv_buf;
+	ssize_t n;
+
+get_verdict:
+	if (xbpf_map_lookup_elem(map_verd, &u32(SK_DROP), &drop) ||
+	    xbpf_map_lookup_elem(map_verd, &u32(SK_PASS), &pass))
+		return;
+
+	if (pass == 0 && drop == 0 && (status & UNSUPPORTED_RACY_VERD)) {
+		sched_yield();
+		goto get_verdict;
+	}
+
+	if (pass != 0) {
+		FAIL("unsupported: wanted verdict pass 0, have %u", pass);
+		return;
+	}
+
+	/* If nothing was dropped, packet should have reached the peer */
+	if (drop == 0) {
+		errno = 0;
+		n = recv_timeout(sd_peer, &recv_buf, 1, 0, IO_TIMEOUT_SEC);
+		if (n != 1)
+			FAIL_ERRNO("unsupported: packet missing, retval=%zd", n);
+	}
+
+	/* Ensure queues are empty */
+	try_recv("bpf.recv(sd_send)", sd_send, MSG_DONTWAIT, false);
+	if (sd_in != sd_send)
+		try_recv("bpf.recv(sd_in)", sd_in, MSG_DONTWAIT, false);
+
+	try_recv("bpf.recv(sd_out)", sd_out, MSG_DONTWAIT, false);
+	if (sd_recv != sd_out)
+		try_recv("bpf.recv(sd_recv)", sd_recv, MSG_DONTWAIT, false);
+}
+
+static void test_send_redir_recv(int sd_send, int send_flags, int sd_peer,
+				 int sd_in, int sd_out, int sd_recv,
+				 struct maps *maps, int status)
+{
+	unsigned int drop, pass;
+	char *send_buf = "ab";
+	char recv_buf = '\0';
+	ssize_t n, len = 1;
+
+	/* Zero out the verdict map */
+	if (xbpf_map_update_elem(maps->verd, &u32(SK_DROP), &u32(0), BPF_ANY) ||
+	    xbpf_map_update_elem(maps->verd, &u32(SK_PASS), &u32(0), BPF_ANY))
+		return;
+
+	if (xbpf_map_update_elem(maps->in, &u32(0), &u64(sd_in), BPF_NOEXIST))
+		return;
+
+	if (xbpf_map_update_elem(maps->out, &u32(0), &u64(sd_out), BPF_NOEXIST))
+		goto del_in;
+
+	/* Last byte is OOB data when send_flags has MSG_OOB bit set */
+	if (send_flags & MSG_OOB)
+		len++;
+	n = send(sd_send, send_buf, len, send_flags);
+	if (n >= 0 && n < len)
+		FAIL("incomplete send");
+	if (n < 0) {
+		/* sk_msg redirect combo not supported? */
+		if (status & SUPPORTED || errno != EACCES)
+			FAIL_ERRNO("send");
+		goto out;
+	}
+
+	if (!(status & SUPPORTED)) {
+		handle_unsupported(sd_send, sd_peer, sd_in, sd_out, sd_recv,
+				   maps->verd, status);
+		goto out;
+	}
+
+	errno = 0;
+	n = recv_timeout(sd_recv, &recv_buf, 1, 0, IO_TIMEOUT_SEC);
+	if (n != 1) {
+		FAIL_ERRNO("recv_timeout()");
+		goto out;
+	}
+
+	/* Check verdict _after_ recv(); af_vsock may need time to catch up */
+	if (xbpf_map_lookup_elem(maps->verd, &u32(SK_DROP), &drop) ||
+	    xbpf_map_lookup_elem(maps->verd, &u32(SK_PASS), &pass))
+		goto out;
+
+	if (drop != 0 || pass != 1)
+		FAIL("unexpected verdict drop/pass: wanted 0/1, have %u/%u",
+		     drop, pass);
+
+	if (recv_buf != send_buf[0])
+		FAIL("recv(): payload check, %02x != %02x", recv_buf, send_buf[0]);
+
+	if (send_flags & MSG_OOB) {
+		/* Fail reading OOB while in sockmap */
+		try_recv("bpf.recv(sd_out, MSG_OOB)", sd_out,
+			 MSG_OOB | MSG_DONTWAIT, false);
+
+		/* Remove sd_out from sockmap */
+		xbpf_map_delete_elem(maps->out, &u32(0));
+
+		/* Check that OOB was dropped on redirect */
+		try_recv("recv(sd_out, MSG_OOB)", sd_out,
+			 MSG_OOB | MSG_DONTWAIT, false);
+
+		goto del_in;
+	}
+out:
+	xbpf_map_delete_elem(maps->out, &u32(0));
+del_in:
+	xbpf_map_delete_elem(maps->in, &u32(0));
+}
+
+static int is_redir_supported(enum prog_type type, const char *in,
+			      const char *out)
+{
+	/* Matching based on strings returned by socket_kind_to_str():
+	 * tcp4, udp4, tcp6, udp6, u_str, u_dgr, v_str, v_seq
+	 * Plus a wildcard: any
+	 * Not in use: u_seq, v_dgr
+	 */
+	struct combo_spec *c, combos[] = {
+		/* Send to local: TCP -> any, but vsock */
+		{ SK_MSG_INGRESS,	"tcp",	"tcp"	},
+		{ SK_MSG_INGRESS,	"tcp",	"udp"	},
+		{ SK_MSG_INGRESS,	"tcp",	"u_str"	},
+		{ SK_MSG_INGRESS,	"tcp",	"u_dgr"	},
+
+		/* Send to egress: TCP -> TCP */
+		{ SK_MSG_EGRESS,	"tcp",	"tcp"	},
+
+		/* Ingress to egress: any -> any */
+		{ SK_SKB_EGRESS,	"any",	"any"	},
+
+		/* Ingress to local: any -> any, but vsock */
+		{ SK_SKB_INGRESS,	"any",	"tcp"	},
+		{ SK_SKB_INGRESS,	"any",	"udp"	},
+		{ SK_SKB_INGRESS,	"any",	"u_str"	},
+		{ SK_SKB_INGRESS,	"any",	"u_dgr"	},
+	};
+
+	for (c = combos; c < combos + ARRAY_SIZE(combos); c++) {
+		if (c->prog_type == type &&
+		    (!strcmp(c->in, "any") || strstarts(in, c->in)) &&
+		    (!strcmp(c->out, "any") || strstarts(out, c->out)))
+			return SUPPORTED;
+	}
+
+	return 0;
+}
+
+static int get_support_status(enum prog_type type, const char *in,
+			      const char *out)
+{
+	int status = is_redir_supported(type, in, out);
+
+	if (type == SK_SKB_INGRESS && strstarts(out, "v_"))
+		status |= UNSUPPORTED_RACY_VERD;
+
+	return status;
+}
+
+static void test_socket(enum bpf_map_type type, struct redir_spec *redir,
+			struct maps *maps, struct socket_spec *s_in,
+			struct socket_spec *s_out)
+{
+	int fd_in, fd_out, fd_send, fd_peer, fd_recv, flags, status;
+	const char *in_str, *out_str;
+	char s[MAX_TEST_NAME];
+
+	fd_in = s_in->in[0];
+	fd_out = s_out->out[0];
+	fd_send = s_in->in[redir->idx_send];
+	fd_peer = s_in->in[redir->idx_send ^ 1];
+	fd_recv = s_out->out[redir->idx_recv];
+	flags = s_in->send_flags;
+
+	in_str = socket_kind_to_str(fd_in);
+	out_str = socket_kind_to_str(fd_out);
+	status = get_support_status(redir->prog_type, in_str, out_str);
+
+	snprintf(s, sizeof(s),
+		 "%-4s %-17s %-5s %s %-5s%6s",
+		 /* hash sk_skb-to-ingress u_str → v_str (OOB) */
+		 type == BPF_MAP_TYPE_SOCKMAP ? "map" : "hash",
+		 redir->name,
+		 in_str,
+		 status & SUPPORTED ? "→" : " ",
+		 out_str,
+		 (flags & MSG_OOB) ? "(OOB)" : "");
+
+	if (!test__start_subtest(s))
+		return;
+
+	test_send_redir_recv(fd_send, flags, fd_peer, fd_in, fd_out, fd_recv,
+			     maps, status);
+}
+
+static void test_redir(enum bpf_map_type type, struct redir_spec *redir,
+		       struct maps *maps)
+{
+	struct socket_spec *s, sockets[] = {
+		{ AF_INET, SOCK_STREAM },
+		// { AF_INET, SOCK_STREAM, MSG_OOB }, /* Known to be broken */
+		{ AF_INET6, SOCK_STREAM },
+		{ AF_INET, SOCK_DGRAM },
+		{ AF_INET6, SOCK_DGRAM },
+		{ AF_UNIX, SOCK_STREAM },
+		{ AF_UNIX, SOCK_STREAM, MSG_OOB },
+		{ AF_UNIX, SOCK_DGRAM },
+		// { AF_UNIX, SOCK_SEQPACKET},	/* Unsupported BPF_MAP_UPDATE_ELEM */
+		{ AF_VSOCK, SOCK_STREAM },
+		// { AF_VSOCK, SOCK_DGRAM },	/* Unsupported socket() */
+		{ AF_VSOCK, SOCK_SEQPACKET },
+	};
+
+	for (s = sockets; s < sockets + ARRAY_SIZE(sockets); s++)
+		if (socket_spec_pairs(s))
+			goto out;
+
+	/* Intra-proto */
+	for (s = sockets; s < sockets + ARRAY_SIZE(sockets); s++)
+		test_socket(type, redir, maps, s, s);
+
+	/* Cross-proto */
+	for (int i = 0; i < ARRAY_SIZE(sockets); i++) {
+		for (int j = 0; j < ARRAY_SIZE(sockets); j++) {
+			struct socket_spec *out = &sockets[j];
+			struct socket_spec *in = &sockets[i];
+
+			/* Skip intra-proto and between variants */
+			if (out->send_flags ||
+			    (in->family == out->family &&
+			     in->sotype == out->sotype))
+				continue;
+
+			test_socket(type, redir, maps, in, out);
+		}
+	}
+out:
+	while (--s >= sockets)
+		socket_spec_close(s);
+}
+
+static void test_map(enum bpf_map_type type)
+{
+	struct redir_spec *r, redirs[] = {
+		{ "sk_msg-to-ingress", SEND_INNER, RECV_INNER, SK_MSG_INGRESS },
+		{ "sk_msg-to-egress", SEND_INNER, RECV_OUTER, SK_MSG_EGRESS },
+		{ "sk_skb-to-egress", SEND_OUTER, RECV_OUTER, SK_SKB_EGRESS },
+		{ "sk_skb-to-ingress", SEND_OUTER, RECV_INNER, SK_SKB_INGRESS },
+	};
+
+	for (r = redirs; r < redirs + ARRAY_SIZE(redirs); r++) {
+		enum bpf_attach_type attach_type;
+		struct test_sockmap_redir *skel;
+		struct maps maps;
+		int prog_fd;
+
+		skel = test_sockmap_redir__open_and_load();
+		if (!skel) {
+			FAIL("open_and_load");
+			return;
+		}
+
+		switch (type) {
+		case BPF_MAP_TYPE_SOCKMAP:
+			maps.in = bpf_map__fd(skel->maps.nop_map);
+			maps.out = bpf_map__fd(skel->maps.sock_map);
+			break;
+		case BPF_MAP_TYPE_SOCKHASH:
+			maps.in = bpf_map__fd(skel->maps.nop_hash);
+			maps.out = bpf_map__fd(skel->maps.sock_hash);
+			break;
+		default:
+			FAIL("Unsupported bpf_map_type");
+			return;
+		}
+
+		skel->bss->redirect_type = type;
+		maps.verd = bpf_map__fd(skel->maps.verdict_map);
+		get_redir_params(r, skel, &prog_fd, &attach_type,
+				 &skel->bss->redirect_flags);
+
+		if (xbpf_prog_attach(prog_fd, maps.in, attach_type, 0))
+			return;
+
+		test_redir(type, r, &maps);
+
+		if (xbpf_prog_detach2(prog_fd, maps.in, attach_type))
+			return;
+
+		test_sockmap_redir__destroy(skel);
+	}
+}
+
+void serial_test_sockmap_redir(void)
+{
+	test_map(BPF_MAP_TYPE_SOCKMAP);
+	test_map(BPF_MAP_TYPE_SOCKHASH);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_strp.c b/tools/testing/selftests/bpf/prog_tests/sockmap_strp.c
new file mode 100644
index 000000000000..621b3b71888e
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_strp.c
@@ -0,0 +1,454 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <error.h>
+#include <netinet/tcp.h>
+#include <test_progs.h>
+#include "sockmap_helpers.h"
+#include "test_skmsg_load_helpers.skel.h"
+#include "test_sockmap_strp.skel.h"
+
+#define STRP_PKT_HEAD_LEN 4
+#define STRP_PKT_BODY_LEN 6
+#define STRP_PKT_FULL_LEN (STRP_PKT_HEAD_LEN + STRP_PKT_BODY_LEN)
+
+static const char packet[STRP_PKT_FULL_LEN] = "head+body\0";
+static const int test_packet_num = 100;
+
+/* Current implementation of tcp_bpf_recvmsg_parser() invokes data_ready
+ * with sk held if an skb exists in sk_receive_queue. Then for the
+ * data_ready implementation of strparser, it will delay the read
+ * operation if sk is held and EAGAIN is returned.
+ */
+static int sockmap_strp_consume_pre_data(int p)
+{
+	int recvd;
+	bool retried = false;
+	char rcv[10];
+
+retry:
+	errno = 0;
+	recvd = recv_timeout(p, rcv, sizeof(rcv), 0, 1);
+	if (recvd < 0 && errno == EAGAIN && retried == false) {
+		/* On the first call, EAGAIN will certainly be returned.
+		 * A 1-second wait is enough for the workqueue to finish.
+		 */
+		sleep(1);
+		retried = true;
+		goto retry;
+	}
+
+	if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "recv error or truncated data") ||
+	    !ASSERT_OK(memcmp(packet, rcv, STRP_PKT_FULL_LEN),
+				"data mismatch"))
+		return -1;
+	return 0;
+}
+
+static struct test_sockmap_strp *sockmap_strp_init(int *out_map, bool pass,
+						   bool need_parser)
+{
+	struct test_sockmap_strp *strp = NULL;
+	int verdict, parser;
+	int err;
+
+	strp = test_sockmap_strp__open_and_load();
+	*out_map = bpf_map__fd(strp->maps.sock_map);
+
+	if (need_parser)
+		parser = bpf_program__fd(strp->progs.prog_skb_parser_partial);
+	else
+		parser = bpf_program__fd(strp->progs.prog_skb_parser);
+
+	if (pass)
+		verdict = bpf_program__fd(strp->progs.prog_skb_verdict_pass);
+	else
+		verdict = bpf_program__fd(strp->progs.prog_skb_verdict);
+
+	err = bpf_prog_attach(parser, *out_map, BPF_SK_SKB_STREAM_PARSER, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach stream parser"))
+		goto err;
+
+	err = bpf_prog_attach(verdict, *out_map, BPF_SK_SKB_STREAM_VERDICT, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach stream verdict"))
+		goto err;
+
+	return strp;
+err:
+	test_sockmap_strp__destroy(strp);
+	return NULL;
+}
+
+/* Dispatch packets to different socket by packet size:
+ *
+ *                      ------  ------
+ *                     | pkt4 || pkt1 |... > remote socket
+ *  ------ ------     / ------  ------
+ * | pkt8 | pkt7 |...
+ *  ------ ------     \ ------  ------
+ *                     | pkt3 || pkt2 |... > local socket
+ *                      ------  ------
+ */
+static void test_sockmap_strp_dispatch_pkt(int family, int sotype)
+{
+	int i, j, zero = 0, one = 1, recvd;
+	int err, map;
+	int c0 = -1, p0 = -1, c1 = -1, p1 = -1;
+	struct test_sockmap_strp *strp = NULL;
+	int test_cnt = 6;
+	char rcv[10];
+	struct {
+		char	data[7];
+		int	data_len;
+		int	send_cnt;
+		int	*receiver;
+	} send_dir[2] = {
+		/* data expected to deliver to local */
+		{"llllll", 6, 0, &p0},
+		/* data expected to deliver to remote */
+		{"rrrrr",  5, 0, &c1}
+	};
+
+	strp = sockmap_strp_init(&map, false, false);
+	if (!ASSERT_TRUE(strp, "sockmap_strp_init"))
+		return;
+
+	err = create_socket_pairs(family, sotype, &c0, &c1, &p0, &p1);
+	if (!ASSERT_OK(err, "create_socket_pairs()"))
+		goto out;
+
+	err = bpf_map_update_elem(map, &zero, &p0, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(p0)"))
+		goto out_close;
+
+	err = bpf_map_update_elem(map, &one, &p1, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(p1)"))
+		goto out_close;
+
+	err = setsockopt(c1, IPPROTO_TCP, TCP_NODELAY, &zero, sizeof(zero));
+	if (!ASSERT_OK(err, "setsockopt(TCP_NODELAY)"))
+		goto out_close;
+
+	/* deliver data with data size greater than 5 to local */
+	strp->data->verdict_max_size = 5;
+
+	for (i = 0; i < test_cnt; i++) {
+		int d = i % 2;
+
+		xsend(c0, send_dir[d].data, send_dir[d].data_len, 0);
+		send_dir[d].send_cnt++;
+	}
+
+	for (i = 0; i < 2; i++) {
+		for (j = 0; j < send_dir[i].send_cnt; j++) {
+			int expected = send_dir[i].data_len;
+
+			recvd = recv_timeout(*send_dir[i].receiver, rcv,
+					     expected, MSG_DONTWAIT,
+					     IO_TIMEOUT_SEC);
+			if (!ASSERT_EQ(recvd, expected, "recv_timeout()"))
+				goto out_close;
+			if (!ASSERT_OK(memcmp(send_dir[i].data, rcv, recvd),
+				       "data mismatch"))
+				goto out_close;
+		}
+	}
+out_close:
+	close(c0);
+	close(c1);
+	close(p0);
+	close(p1);
+out:
+	test_sockmap_strp__destroy(strp);
+}
+
+/* We have multiple packets in one skb
+ * ------------ ------------ ------------
+ * |  packet1  |   packet2  |  ...
+ * ------------ ------------ ------------
+ */
+static void test_sockmap_strp_multiple_pkt(int family, int sotype)
+{
+	int i, zero = 0;
+	int sent, recvd, total;
+	int err, map;
+	int c = -1, p = -1;
+	struct test_sockmap_strp *strp = NULL;
+	char *snd = NULL, *rcv = NULL;
+
+	strp = sockmap_strp_init(&map, true, true);
+	if (!ASSERT_TRUE(strp, "sockmap_strp_init"))
+		return;
+
+	err = create_pair(family, sotype, &c, &p);
+	if (err)
+		goto out;
+
+	err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(zero, p)"))
+		goto out_close;
+
+	/* construct multiple packets in one buffer */
+	total = test_packet_num * STRP_PKT_FULL_LEN;
+	snd = malloc(total);
+	rcv = malloc(total + 1);
+	if (!ASSERT_TRUE(snd, "malloc(snd)") ||
+	    !ASSERT_TRUE(rcv, "malloc(rcv)"))
+		goto out_close;
+
+	for (i = 0; i < test_packet_num; i++) {
+		memcpy(snd + i * STRP_PKT_FULL_LEN,
+		       packet, STRP_PKT_FULL_LEN);
+	}
+
+	sent = xsend(c, snd, total, 0);
+	if (!ASSERT_EQ(sent, total, "xsend(c)"))
+		goto out_close;
+
+	/* try to recv one more byte to avoid truncation check */
+	recvd = recv_timeout(p, rcv, total + 1, MSG_DONTWAIT, IO_TIMEOUT_SEC);
+	if (!ASSERT_EQ(recvd, total, "recv(rcv)"))
+		goto out_close;
+
+	/* we sent TCP segment with multiple encapsulation
+	 * then check whether packets are handled correctly
+	 */
+	if (!ASSERT_OK(memcmp(snd, rcv, total), "data mismatch"))
+		goto out_close;
+
+out_close:
+	close(c);
+	close(p);
+	if (snd)
+		free(snd);
+	if (rcv)
+		free(rcv);
+out:
+	test_sockmap_strp__destroy(strp);
+}
+
+/* Test strparser with partial read */
+static void test_sockmap_strp_partial_read(int family, int sotype)
+{
+	int zero = 0, recvd, off;
+	int err, map;
+	int c = -1, p = -1;
+	struct test_sockmap_strp *strp = NULL;
+	char rcv[STRP_PKT_FULL_LEN + 1] = "0";
+
+	strp = sockmap_strp_init(&map, true, true);
+	if (!ASSERT_TRUE(strp, "sockmap_strp_init"))
+		return;
+
+	err = create_pair(family, sotype, &c, &p);
+	if (err)
+		goto out;
+
+	/* sk_data_ready of 'p' will be replaced by strparser handler */
+	err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(zero, p)"))
+		goto out_close;
+
+	/* 1.1 send partial head, 1 byte header left */
+	off = STRP_PKT_HEAD_LEN - 1;
+	xsend(c, packet, off, 0);
+	recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1);
+	if (!ASSERT_EQ(-1, recvd, "partial head sent, expected no data"))
+		goto out_close;
+
+	/* 1.2 send remaining head and body */
+	xsend(c, packet + off, STRP_PKT_FULL_LEN - off, 0);
+	recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, IO_TIMEOUT_SEC);
+	if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "expected full data"))
+		goto out_close;
+
+	/* 2.1 send partial head, 1 byte header left */
+	off = STRP_PKT_HEAD_LEN - 1;
+	xsend(c, packet, off, 0);
+
+	/* 2.2 send remaining head and partial body, 1 byte body left */
+	xsend(c, packet + off, STRP_PKT_FULL_LEN - off - 1, 0);
+	off = STRP_PKT_FULL_LEN - 1;
+	recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1);
+	if (!ASSERT_EQ(-1, recvd, "partial body sent, expected no data"))
+		goto out_close;
+
+	/* 2.3 send remaining body */
+	xsend(c, packet + off, STRP_PKT_FULL_LEN - off, 0);
+	recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, IO_TIMEOUT_SEC);
+	if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "expected full data"))
+		goto out_close;
+
+out_close:
+	close(c);
+	close(p);
+
+out:
+	test_sockmap_strp__destroy(strp);
+}
+
+/* Test simple socket read/write with strparser + FIONREAD */
+static void test_sockmap_strp_pass(int family, int sotype, bool fionread)
+{
+	int zero = 0, pkt_size = STRP_PKT_FULL_LEN, sent, recvd, avail;
+	int err, map;
+	int c = -1, p = -1;
+	int test_cnt = 10, i;
+	struct test_sockmap_strp *strp = NULL;
+	char rcv[STRP_PKT_FULL_LEN + 1] = "0";
+
+	strp = sockmap_strp_init(&map, true, true);
+	if (!ASSERT_TRUE(strp, "sockmap_strp_init"))
+		return;
+
+	err = create_pair(family, sotype, &c, &p);
+	if (err)
+		goto out;
+
+	/* inject some data before bpf process, it should be read
+	 * correctly because we check sk_receive_queue in
+	 * tcp_bpf_recvmsg_parser().
+	 */
+	sent = xsend(c, packet, pkt_size, 0);
+	if (!ASSERT_EQ(sent, pkt_size, "xsend(pre-data)"))
+		goto out_close;
+
+	/* sk_data_ready of 'p' will be replaced by strparser handler */
+	err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(p)"))
+		goto out_close;
+
+	/* consume previous data we injected */
+	if (sockmap_strp_consume_pre_data(p))
+		goto out_close;
+
+	/* Previously, we encountered issues such as deadlocks and
+	 * sequence errors that resulted in the inability to read
+	 * continuously. Therefore, we perform multiple iterations
+	 * of testing here.
+	 */
+	for (i = 0; i < test_cnt; i++) {
+		sent = xsend(c, packet, pkt_size, 0);
+		if (!ASSERT_EQ(sent, pkt_size, "xsend(c)"))
+			goto out_close;
+
+		recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT,
+				     IO_TIMEOUT_SEC);
+		if (!ASSERT_EQ(recvd, pkt_size, "recv_timeout(p)") ||
+		    !ASSERT_OK(memcmp(packet, rcv, pkt_size),
+				  "memcmp, data mismatch"))
+			goto out_close;
+	}
+
+	if (fionread) {
+		sent = xsend(c, packet, pkt_size, 0);
+		if (!ASSERT_EQ(sent, pkt_size, "second xsend(c)"))
+			goto out_close;
+
+		err = ioctl(p, FIONREAD, &avail);
+		if (!ASSERT_OK(err, "ioctl(FIONREAD) error") ||
+		    !ASSERT_EQ(avail, pkt_size, "ioctl(FIONREAD)"))
+			goto out_close;
+
+		recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT,
+				     IO_TIMEOUT_SEC);
+		if (!ASSERT_EQ(recvd, pkt_size, "second recv_timeout(p)") ||
+		    !ASSERT_OK(memcmp(packet, rcv, pkt_size),
+			      "second memcmp, data mismatch"))
+			goto out_close;
+	}
+
+out_close:
+	close(c);
+	close(p);
+
+out:
+	test_sockmap_strp__destroy(strp);
+}
+
+/* Test strparser with verdict mode */
+static void test_sockmap_strp_verdict(int family, int sotype)
+{
+	int zero = 0, one = 1, sent, recvd, off;
+	int err, map;
+	int c0 = -1, p0 = -1, c1 = -1, p1 = -1;
+	struct test_sockmap_strp *strp = NULL;
+	char rcv[STRP_PKT_FULL_LEN + 1] = "0";
+
+	strp = sockmap_strp_init(&map, false, true);
+	if (!ASSERT_TRUE(strp, "sockmap_strp_init"))
+		return;
+
+	/* We simulate a reverse proxy server.
+	 * When p0 receives data from c0, we forward it to c1.
+	 * From c1's perspective, it will consider this data
+	 * as being sent by p1.
+	 */
+	err = create_socket_pairs(family, sotype, &c0, &c1, &p0, &p1);
+	if (!ASSERT_OK(err, "create_socket_pairs()"))
+		goto out;
+
+	err = bpf_map_update_elem(map, &zero, &p0, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(p0)"))
+		goto out_close;
+
+	err = bpf_map_update_elem(map, &one, &p1, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "bpf_map_update_elem(p1)"))
+		goto out_close;
+
+	sent = xsend(c0, packet, STRP_PKT_FULL_LEN, 0);
+	if (!ASSERT_EQ(sent, STRP_PKT_FULL_LEN, "xsend(c0)"))
+		goto out_close;
+
+	recvd = recv_timeout(c1, rcv, sizeof(rcv), MSG_DONTWAIT,
+			     IO_TIMEOUT_SEC);
+	if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "recv_timeout(c1)") ||
+	    !ASSERT_OK(memcmp(packet, rcv, STRP_PKT_FULL_LEN),
+			  "received data does not match the sent data"))
+		goto out_close;
+
+	/* send again to ensure the stream is functioning correctly. */
+	sent = xsend(c0, packet, STRP_PKT_FULL_LEN, 0);
+	if (!ASSERT_EQ(sent, STRP_PKT_FULL_LEN, "second xsend(c0)"))
+		goto out_close;
+
+	/* partial read */
+	off = STRP_PKT_FULL_LEN / 2;
+	recvd = recv_timeout(c1, rcv, off, MSG_DONTWAIT,
+			     IO_TIMEOUT_SEC);
+	recvd += recv_timeout(c1, rcv + off, sizeof(rcv) - off, MSG_DONTWAIT,
+			      IO_TIMEOUT_SEC);
+
+	if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "partial recv_timeout(c1)") ||
+	    !ASSERT_OK(memcmp(packet, rcv, STRP_PKT_FULL_LEN),
+			  "partial received data does not match the sent data"))
+		goto out_close;
+
+out_close:
+	close(c0);
+	close(c1);
+	close(p0);
+	close(p1);
+out:
+	test_sockmap_strp__destroy(strp);
+}
+
+void test_sockmap_strp(void)
+{
+	if (test__start_subtest("sockmap strp tcp pass"))
+		test_sockmap_strp_pass(AF_INET, SOCK_STREAM, false);
+	if (test__start_subtest("sockmap strp tcp v6 pass"))
+		test_sockmap_strp_pass(AF_INET6, SOCK_STREAM, false);
+	if (test__start_subtest("sockmap strp tcp pass fionread"))
+		test_sockmap_strp_pass(AF_INET, SOCK_STREAM, true);
+	if (test__start_subtest("sockmap strp tcp v6 pass fionread"))
+		test_sockmap_strp_pass(AF_INET6, SOCK_STREAM, true);
+	if (test__start_subtest("sockmap strp tcp verdict"))
+		test_sockmap_strp_verdict(AF_INET, SOCK_STREAM);
+	if (test__start_subtest("sockmap strp tcp v6 verdict"))
+		test_sockmap_strp_verdict(AF_INET6, SOCK_STREAM);
+	if (test__start_subtest("sockmap strp tcp partial read"))
+		test_sockmap_strp_partial_read(AF_INET, SOCK_STREAM);
+	if (test__start_subtest("sockmap strp tcp multiple packets"))
+		test_sockmap_strp_multiple_pkt(AF_INET, SOCK_STREAM);
+	if (test__start_subtest("sockmap strp tcp dispatch"))
+		test_sockmap_strp_dispatch_pkt(AF_INET, SOCK_STREAM);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt.c b/tools/testing/selftests/bpf/prog_tests/sockopt.c
index aa4debf62fc6..eaac83a7f388 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt.c
@@ -1,14 +1,20 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include <io_uring/mini_liburing.h>
 #include "cgroup_helpers.h"
 
 static char bpf_log_buf[4096];
 static bool verbose;
 
+#ifndef PAGE_SIZE
+#define PAGE_SIZE 4096
+#endif
+
 enum sockopt_test_error {
 	OK = 0,
 	DENY_LOAD,
 	DENY_ATTACH,
+	EOPNOTSUPP_GETSOCKOPT,
 	EPERM_GETSOCKOPT,
 	EFAULT_GETSOCKOPT,
 	EPERM_SETSOCKOPT,
@@ -18,6 +24,7 @@ enum sockopt_test_error {
 static struct sockopt_test {
 	const char			*descr;
 	const struct bpf_insn		insns[64];
+	enum bpf_prog_type		prog_type;
 	enum bpf_attach_type		attach_type;
 	enum bpf_attach_type		expected_attach_type;
 
@@ -33,6 +40,7 @@ static struct sockopt_test {
 	socklen_t			get_optlen_ret;
 
 	enum sockopt_test_error		error;
+	bool				io_uring_support;
 } tests[] = {
 
 	/* ==================== getsockopt ====================  */
@@ -246,7 +254,9 @@ static struct sockopt_test {
 		.attach_type = BPF_CGROUP_GETSOCKOPT,
 		.expected_attach_type = BPF_CGROUP_GETSOCKOPT,
 
+		.get_level = SOL_SOCKET,
 		.get_optlen = 64,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "getsockopt: deny bigger ctx->optlen",
@@ -271,12 +281,34 @@ static struct sockopt_test {
 		.get_optlen = 64,
 
 		.error = EFAULT_GETSOCKOPT,
+		.io_uring_support = true,
 	},
 	{
-		.descr = "getsockopt: deny arbitrary ctx->retval",
+		.descr = "getsockopt: ignore >PAGE_SIZE optlen",
 		.insns = {
-			/* ctx->retval = 123 */
-			BPF_MOV64_IMM(BPF_REG_0, 123),
+			/* write 0xFF to the first optval byte */
+
+			/* r6 = ctx->optval */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct bpf_sockopt, optval)),
+			/* r2 = ctx->optval */
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
+			/* r6 = ctx->optval + 1 */
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1),
+
+			/* r7 = ctx->optval_end */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct bpf_sockopt, optval_end)),
+
+			/* if (ctx->optval + 1 <= ctx->optval_end) { */
+			BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_7, 1),
+			/* ctx->optval[0] = 0xF0 */
+			BPF_ST_MEM(BPF_B, BPF_REG_2, 0, 0xFF),
+			/* } */
+
+			/* retval changes are ignored */
+			/* ctx->retval = 5 */
+			BPF_MOV64_IMM(BPF_REG_0, 5),
 			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
 				    offsetof(struct bpf_sockopt, retval)),
 
@@ -287,9 +319,12 @@ static struct sockopt_test {
 		.attach_type = BPF_CGROUP_GETSOCKOPT,
 		.expected_attach_type = BPF_CGROUP_GETSOCKOPT,
 
-		.get_optlen = 64,
-
-		.error = EFAULT_GETSOCKOPT,
+		.get_level = 1234,
+		.get_optname = 5678,
+		.get_optval = {}, /* the changes are ignored */
+		.get_optlen = PAGE_SIZE + 1,
+		.error = EOPNOTSUPP_GETSOCKOPT,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "getsockopt: support smaller ctx->optlen",
@@ -309,8 +344,10 @@ static struct sockopt_test {
 		.attach_type = BPF_CGROUP_GETSOCKOPT,
 		.expected_attach_type = BPF_CGROUP_GETSOCKOPT,
 
+		.get_level = SOL_SOCKET,
 		.get_optlen = 64,
 		.get_optlen_ret = 32,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "getsockopt: deny writing to ctx->optval",
@@ -490,6 +527,7 @@ static struct sockopt_test {
 		.set_level = 123,
 
 		.set_optlen = 1,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: allow changing ctx->level",
@@ -544,6 +582,7 @@ static struct sockopt_test {
 		.set_optname = 123,
 
 		.set_optlen = 1,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: allow changing ctx->optname",
@@ -596,6 +635,7 @@ static struct sockopt_test {
 		.expected_attach_type = BPF_CGROUP_SETSOCKOPT,
 
 		.set_optlen = 64,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: ctx->optlen == -1 is ok",
@@ -612,6 +652,7 @@ static struct sockopt_test {
 		.expected_attach_type = BPF_CGROUP_SETSOCKOPT,
 
 		.set_optlen = 64,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: deny ctx->optlen < 0 (except -1)",
@@ -630,6 +671,7 @@ static struct sockopt_test {
 		.set_optlen = 4,
 
 		.error = EFAULT_SETSOCKOPT,
+		.io_uring_support = true,
 	},
 	{
 		.descr = "setsockopt: deny ctx->optlen > input optlen",
@@ -647,6 +689,46 @@ static struct sockopt_test {
 		.set_optlen = 64,
 
 		.error = EFAULT_SETSOCKOPT,
+		.io_uring_support = true,
+	},
+	{
+		.descr = "setsockopt: ignore >PAGE_SIZE optlen",
+		.insns = {
+			/* write 0xFF to the first optval byte */
+
+			/* r6 = ctx->optval */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct bpf_sockopt, optval)),
+			/* r2 = ctx->optval */
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
+			/* r6 = ctx->optval + 1 */
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1),
+
+			/* r7 = ctx->optval_end */
+			BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct bpf_sockopt, optval_end)),
+
+			/* if (ctx->optval + 1 <= ctx->optval_end) { */
+			BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_7, 1),
+			/* ctx->optval[0] = 0xF0 */
+			BPF_ST_MEM(BPF_B, BPF_REG_2, 0, 0xF0),
+			/* } */
+
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.attach_type = BPF_CGROUP_SETSOCKOPT,
+		.expected_attach_type = BPF_CGROUP_SETSOCKOPT,
+
+		.set_level = SOL_IP,
+		.set_optname = IP_TOS,
+		.set_optval = {},
+		.set_optlen = PAGE_SIZE + 1,
+
+		.get_level = SOL_IP,
+		.get_optname = IP_TOS,
+		.get_optval = {}, /* the changes are ignored */
+		.get_optlen = 4,
 	},
 	{
 		.descr = "setsockopt: allow changing ctx->optlen within bounds",
@@ -847,9 +929,40 @@ static struct sockopt_test {
 
 		.error = EPERM_SETSOCKOPT,
 	},
+
+	/* ==================== prog_type ====================  */
+
+	{
+		.descr = "can attach only BPF_CGROUP_SETSOCKOP",
+		.insns = {
+			/* return 1 */
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+
+		},
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+		.attach_type = BPF_CGROUP_SETSOCKOPT,
+		.expected_attach_type = 0,
+		.error = DENY_ATTACH,
+	},
+
+	{
+		.descr = "can attach only BPF_CGROUP_GETSOCKOP",
+		.insns = {
+			/* return 1 */
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+
+		},
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+		.attach_type = BPF_CGROUP_GETSOCKOPT,
+		.expected_attach_type = 0,
+		.error = DENY_ATTACH,
+	},
 };
 
 static int load_prog(const struct bpf_insn *insns,
+		     enum bpf_prog_type prog_type,
 		     enum bpf_attach_type expected_attach_type)
 {
 	LIBBPF_OPTS(bpf_prog_load_opts, opts,
@@ -866,20 +979,107 @@ static int load_prog(const struct bpf_insn *insns,
 	}
 	insns_cnt++;
 
-	fd = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCKOPT, NULL, "GPL", insns, insns_cnt, &opts);
+	fd = bpf_prog_load(prog_type, NULL, "GPL", insns, insns_cnt, &opts);
 	if (verbose && fd < 0)
 		fprintf(stderr, "%s\n", bpf_log_buf);
 
 	return fd;
 }
 
-static int run_test(int cgroup_fd, struct sockopt_test *test)
+/* Core function that handles io_uring ring initialization,
+ * sending SQE with sockopt command and waiting for the CQE.
+ */
+static int uring_sockopt(int op, int fd, int level, int optname,
+			 const void *optval, socklen_t optlen)
+{
+	struct io_uring_cqe *cqe;
+	struct io_uring_sqe *sqe;
+	struct io_uring ring;
+	int err;
+
+	err = io_uring_queue_init(1, &ring, 0);
+	if (!ASSERT_OK(err, "io_uring initialization"))
+		return err;
+
+	sqe = io_uring_get_sqe(&ring);
+	if (!ASSERT_NEQ(sqe, NULL, "Get an SQE")) {
+		err = -1;
+		goto fail;
+	}
+
+	io_uring_prep_cmd(sqe, op, fd, level, optname, optval, optlen);
+
+	err = io_uring_submit(&ring);
+	if (!ASSERT_EQ(err, 1, "Submit SQE"))
+		goto fail;
+
+	err = io_uring_wait_cqe(&ring, &cqe);
+	if (!ASSERT_OK(err, "Wait for CQE"))
+		goto fail;
+
+	err = cqe->res;
+
+fail:
+	io_uring_queue_exit(&ring);
+
+	return err;
+}
+
+static int uring_setsockopt(int fd, int level, int optname, const void *optval,
+			    socklen_t optlen)
+{
+	return uring_sockopt(SOCKET_URING_OP_SETSOCKOPT, fd, level, optname,
+			     optval, optlen);
+}
+
+static int uring_getsockopt(int fd, int level, int optname, void *optval,
+			    socklen_t *optlen)
+{
+	int ret = uring_sockopt(SOCKET_URING_OP_GETSOCKOPT, fd, level, optname,
+				optval, *optlen);
+	if (ret < 0)
+		return ret;
+
+	/* Populate optlen back to be compatible with systemcall interface,
+	 * and simplify the test.
+	 */
+	*optlen = ret;
+
+	return 0;
+}
+
+/* Execute the setsocktopt operation */
+static int call_setsockopt(bool use_io_uring, int fd, int level, int optname,
+			   const void *optval, socklen_t optlen)
+{
+	if (use_io_uring)
+		return uring_setsockopt(fd, level, optname, optval, optlen);
+
+	return setsockopt(fd, level, optname, optval, optlen);
+}
+
+/* Execute the getsocktopt operation */
+static int call_getsockopt(bool use_io_uring, int fd, int level, int optname,
+			   void *optval, socklen_t *optlen)
 {
-	int sock_fd, err, prog_fd;
+	if (use_io_uring)
+		return uring_getsockopt(fd, level, optname, optval, optlen);
+
+	return getsockopt(fd, level, optname, optval, optlen);
+}
+
+static int run_test(int cgroup_fd, struct sockopt_test *test, bool use_io_uring,
+		    bool use_link)
+{
+	int prog_type = BPF_PROG_TYPE_CGROUP_SOCKOPT;
+	int sock_fd, err, prog_fd, link_fd = -1;
 	void *optval = NULL;
 	int ret = 0;
 
-	prog_fd = load_prog(test->insns, test->expected_attach_type);
+	if (test->prog_type)
+		prog_type = test->prog_type;
+
+	prog_fd = load_prog(test->insns, prog_type, test->expected_attach_type);
 	if (prog_fd < 0) {
 		if (test->error == DENY_LOAD)
 			return 0;
@@ -888,7 +1088,12 @@ static int run_test(int cgroup_fd, struct sockopt_test *test)
 		return -1;
 	}
 
-	err = bpf_prog_attach(prog_fd, cgroup_fd, test->attach_type, 0);
+	if (use_link) {
+		err = bpf_link_create(prog_fd, cgroup_fd, test->attach_type, NULL);
+		link_fd = err;
+	} else {
+		err = bpf_prog_attach(prog_fd, cgroup_fd, test->attach_type, 0);
+	}
 	if (err < 0) {
 		if (test->error == DENY_ATTACH)
 			goto close_prog_fd;
@@ -906,8 +1111,16 @@ static int run_test(int cgroup_fd, struct sockopt_test *test)
 	}
 
 	if (test->set_optlen) {
-		err = setsockopt(sock_fd, test->set_level, test->set_optname,
-				 test->set_optval, test->set_optlen);
+		if (test->set_optlen >= PAGE_SIZE) {
+			int num_pages = test->set_optlen / PAGE_SIZE;
+			int remainder = test->set_optlen % PAGE_SIZE;
+
+			test->set_optlen = num_pages * sysconf(_SC_PAGESIZE) + remainder;
+		}
+
+		err = call_setsockopt(use_io_uring, sock_fd, test->set_level,
+				      test->set_optname, test->set_optval,
+				      test->set_optlen);
 		if (err) {
 			if (errno == EPERM && test->error == EPERM_SETSOCKOPT)
 				goto close_sock_fd;
@@ -921,14 +1134,24 @@ static int run_test(int cgroup_fd, struct sockopt_test *test)
 	}
 
 	if (test->get_optlen) {
+		if (test->get_optlen >= PAGE_SIZE) {
+			int num_pages = test->get_optlen / PAGE_SIZE;
+			int remainder = test->get_optlen % PAGE_SIZE;
+
+			test->get_optlen = num_pages * sysconf(_SC_PAGESIZE) + remainder;
+		}
+
 		optval = malloc(test->get_optlen);
+		memset(optval, 0, test->get_optlen);
 		socklen_t optlen = test->get_optlen;
 		socklen_t expected_get_optlen = test->get_optlen_ret ?:
 			test->get_optlen;
 
-		err = getsockopt(sock_fd, test->get_level, test->get_optname,
-				 optval, &optlen);
+		err = call_getsockopt(use_io_uring, sock_fd, test->get_level,
+				      test->get_optname, optval, &optlen);
 		if (err) {
+			if (errno == EOPNOTSUPP && test->error == EOPNOTSUPP_GETSOCKOPT)
+				goto free_optval;
 			if (errno == EPERM && test->error == EPERM_GETSOCKOPT)
 				goto free_optval;
 			if (errno == EFAULT && test->error == EFAULT_GETSOCKOPT)
@@ -961,7 +1184,12 @@ free_optval:
 close_sock_fd:
 	close(sock_fd);
 detach_prog:
-	bpf_prog_detach2(prog_fd, cgroup_fd, test->attach_type);
+	if (use_link) {
+		if (link_fd >= 0)
+			close(link_fd);
+	} else {
+		bpf_prog_detach2(prog_fd, cgroup_fd, test->attach_type);
+	}
 close_prog_fd:
 	close(prog_fd);
 	return ret;
@@ -976,8 +1204,16 @@ void test_sockopt(void)
 		return;
 
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
-		test__start_subtest(tests[i].descr);
-		ASSERT_OK(run_test(cgroup_fd, &tests[i]), tests[i].descr);
+		if (!test__start_subtest(tests[i].descr))
+			continue;
+
+		ASSERT_OK(run_test(cgroup_fd, &tests[i], false, false),
+			  tests[i].descr);
+		ASSERT_OK(run_test(cgroup_fd, &tests[i], false, true),
+			  tests[i].descr);
+		if (tests[i].io_uring_support)
+			ASSERT_OK(run_test(cgroup_fd, &tests[i], true, false),
+				  tests[i].descr);
 	}
 
 	close(cgroup_fd);
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
index 60c17a8e2789..7cd8be2780ca 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_inherit.c
@@ -1,41 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 #include "cgroup_helpers.h"
+#include "network_helpers.h"
+
+#include "sockopt_inherit.skel.h"
 
 #define SOL_CUSTOM			0xdeadbeef
 #define CUSTOM_INHERIT1			0
 #define CUSTOM_INHERIT2			1
 #define CUSTOM_LISTENER			2
 
-static int connect_to_server(int server_fd)
-{
-	struct sockaddr_storage addr;
-	socklen_t len = sizeof(addr);
-	int fd;
-
-	fd = socket(AF_INET, SOCK_STREAM, 0);
-	if (fd < 0) {
-		log_err("Failed to create client socket");
-		return -1;
-	}
-
-	if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) {
-		log_err("Failed to get server addr");
-		goto out;
-	}
-
-	if (connect(fd, (const struct sockaddr *)&addr, len) < 0) {
-		log_err("Fail to connect to server");
-		goto out;
-	}
-
-	return fd;
-
-out:
-	close(fd);
-	return -1;
-}
-
 static int verify_sockopt(int fd, int optname, const char *msg, char expected)
 {
 	socklen_t optlen = 1;
@@ -96,97 +70,59 @@ static void *server_thread(void *arg)
 	return (void *)(long)err;
 }
 
-static int start_server(void)
+static int custom_cb(int fd, void *opts)
 {
-	struct sockaddr_in addr = {
-		.sin_family = AF_INET,
-		.sin_addr.s_addr = htonl(INADDR_LOOPBACK),
-	};
 	char buf;
 	int err;
-	int fd;
 	int i;
 
-	fd = socket(AF_INET, SOCK_STREAM, 0);
-	if (fd < 0) {
-		log_err("Failed to create server socket");
-		return -1;
-	}
-
 	for (i = CUSTOM_INHERIT1; i <= CUSTOM_LISTENER; i++) {
 		buf = 0x01;
 		err = setsockopt(fd, SOL_CUSTOM, i, &buf, 1);
 		if (err) {
 			log_err("Failed to call setsockopt(%d)", i);
-			close(fd);
 			return -1;
 		}
 	}
 
-	if (bind(fd, (const struct sockaddr *)&addr, sizeof(addr)) < 0) {
-		log_err("Failed to bind socket");
-		close(fd);
-		return -1;
-	}
-
-	return fd;
-}
-
-static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title,
-		       const char *prog_name)
-{
-	enum bpf_attach_type attach_type;
-	enum bpf_prog_type prog_type;
-	struct bpf_program *prog;
-	int err;
-
-	err = libbpf_prog_type_by_name(title, &prog_type, &attach_type);
-	if (err) {
-		log_err("Failed to deduct types for %s BPF program", prog_name);
-		return -1;
-	}
-
-	prog = bpf_object__find_program_by_name(obj, prog_name);
-	if (!prog) {
-		log_err("Failed to find %s BPF program", prog_name);
-		return -1;
-	}
-
-	err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd,
-			      attach_type, 0);
-	if (err) {
-		log_err("Failed to attach %s BPF program", prog_name);
-		return -1;
-	}
-
 	return 0;
 }
 
 static void run_test(int cgroup_fd)
 {
+	struct bpf_link *link_getsockopt = NULL;
+	struct bpf_link *link_setsockopt = NULL;
+	struct network_helper_opts opts = {
+		.post_socket_cb = custom_cb,
+	};
 	int server_fd = -1, client_fd;
-	struct bpf_object *obj;
+	struct sockaddr_in addr = {
+		.sin_family = AF_INET,
+		.sin_addr.s_addr = htonl(INADDR_LOOPBACK),
+	};
+	struct sockopt_inherit *obj;
 	void *server_err;
 	pthread_t tid;
 	int err;
 
-	obj = bpf_object__open_file("sockopt_inherit.bpf.o", NULL);
-	if (!ASSERT_OK_PTR(obj, "obj_open"))
+	obj = sockopt_inherit__open_and_load();
+	if (!ASSERT_OK_PTR(obj, "skel-load"))
 		return;
 
-	err = bpf_object__load(obj);
-	if (!ASSERT_OK(err, "obj_load"))
-		goto close_bpf_object;
+	obj->bss->page_size = sysconf(_SC_PAGESIZE);
 
-	err = prog_attach(obj, cgroup_fd, "cgroup/getsockopt", "_getsockopt");
-	if (!ASSERT_OK(err, "prog_attach _getsockopt"))
+	link_getsockopt = bpf_program__attach_cgroup(obj->progs._getsockopt,
+						     cgroup_fd);
+	if (!ASSERT_OK_PTR(link_getsockopt, "cg-attach-getsockopt"))
 		goto close_bpf_object;
 
-	err = prog_attach(obj, cgroup_fd, "cgroup/setsockopt", "_setsockopt");
-	if (!ASSERT_OK(err, "prog_attach _setsockopt"))
+	link_setsockopt = bpf_program__attach_cgroup(obj->progs._setsockopt,
+						     cgroup_fd);
+	if (!ASSERT_OK_PTR(link_setsockopt, "cg-attach-setsockopt"))
 		goto close_bpf_object;
 
-	server_fd = start_server();
+	server_fd = start_server_addr(SOCK_STREAM, (struct sockaddr_storage *)&addr,
+				      sizeof(addr), &opts);
 	if (!ASSERT_GE(server_fd, 0, "start_server"))
 		goto close_bpf_object;
 
@@ -199,7 +135,7 @@ static void run_test(int cgroup_fd)
 	pthread_cond_wait(&server_started, &server_started_mtx);
 	pthread_mutex_unlock(&server_started_mtx);
 
-	client_fd = connect_to_server(server_fd);
+	client_fd = connect_to_fd(server_fd, 0);
 	if (!ASSERT_GE(client_fd, 0, "connect_to_server"))
 		goto close_server_fd;
 
@@ -217,7 +153,10 @@ static void run_test(int cgroup_fd)
 close_server_fd:
 	close(server_fd);
 close_bpf_object:
-	bpf_object__close(obj);
+	bpf_link__destroy(link_getsockopt);
+	bpf_link__destroy(link_setsockopt);
+
+	sockopt_inherit__destroy(obj);
 }
 
 void test_sockopt_inherit(void)
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c
index 7f5659349011..759bbb6f8c5f 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c
@@ -2,61 +2,13 @@
 #include <test_progs.h>
 #include "cgroup_helpers.h"
 
-static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title, const char *name)
-{
-	enum bpf_attach_type attach_type;
-	enum bpf_prog_type prog_type;
-	struct bpf_program *prog;
-	int err;
-
-	err = libbpf_prog_type_by_name(title, &prog_type, &attach_type);
-	if (err) {
-		log_err("Failed to deduct types for %s BPF program", title);
-		return -1;
-	}
-
-	prog = bpf_object__find_program_by_name(obj, name);
-	if (!prog) {
-		log_err("Failed to find %s BPF program", name);
-		return -1;
-	}
-
-	err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd,
-			      attach_type, BPF_F_ALLOW_MULTI);
-	if (err) {
-		log_err("Failed to attach %s BPF program", name);
-		return -1;
-	}
-
-	return 0;
-}
+#include "sockopt_multi.skel.h"
 
-static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title, const char *name)
-{
-	enum bpf_attach_type attach_type;
-	enum bpf_prog_type prog_type;
-	struct bpf_program *prog;
-	int err;
-
-	err = libbpf_prog_type_by_name(title, &prog_type, &attach_type);
-	if (err)
-		return -1;
-
-	prog = bpf_object__find_program_by_name(obj, name);
-	if (!prog)
-		return -1;
-
-	err = bpf_prog_detach2(bpf_program__fd(prog), cgroup_fd,
-			       attach_type);
-	if (err)
-		return -1;
-
-	return 0;
-}
-
-static int run_getsockopt_test(struct bpf_object *obj, int cg_parent,
+static int run_getsockopt_test(struct sockopt_multi *obj, int cg_parent,
 			       int cg_child, int sock_fd)
 {
+	struct bpf_link *link_parent = NULL;
+	struct bpf_link *link_child = NULL;
 	socklen_t optlen;
 	__u8 buf;
 	int err;
@@ -89,8 +41,9 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent,
 	 * - child:  0x80 -> 0x90
 	 */
 
-	err = prog_attach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child");
-	if (err)
+	link_child = bpf_program__attach_cgroup(obj->progs._getsockopt_child,
+						cg_child);
+	if (!ASSERT_OK_PTR(link_child, "cg-attach-getsockopt_child"))
 		goto detach;
 
 	buf = 0x00;
@@ -113,8 +66,9 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent,
 	 * - parent: 0x90 -> 0xA0
 	 */
 
-	err = prog_attach(obj, cg_parent, "cgroup/getsockopt", "_getsockopt_parent");
-	if (err)
+	link_parent = bpf_program__attach_cgroup(obj->progs._getsockopt_parent,
+						 cg_parent);
+	if (!ASSERT_OK_PTR(link_parent, "cg-attach-getsockopt_parent"))
 		goto detach;
 
 	buf = 0x00;
@@ -157,11 +111,8 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent,
 	 * - parent: unexpected 0x40, EPERM
 	 */
 
-	err = prog_detach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child");
-	if (err) {
-		log_err("Failed to detach child program");
-		goto detach;
-	}
+	bpf_link__destroy(link_child);
+	link_child = NULL;
 
 	buf = 0x00;
 	optlen = 1;
@@ -198,15 +149,17 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent,
 	}
 
 detach:
-	prog_detach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child");
-	prog_detach(obj, cg_parent, "cgroup/getsockopt", "_getsockopt_parent");
+	bpf_link__destroy(link_child);
+	bpf_link__destroy(link_parent);
 
 	return err;
 }
 
-static int run_setsockopt_test(struct bpf_object *obj, int cg_parent,
+static int run_setsockopt_test(struct sockopt_multi *obj, int cg_parent,
 			       int cg_child, int sock_fd)
 {
+	struct bpf_link *link_parent = NULL;
+	struct bpf_link *link_child = NULL;
 	socklen_t optlen;
 	__u8 buf;
 	int err;
@@ -236,8 +189,9 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent,
 
 	/* Attach child program and make sure it adds 0x10. */
 
-	err = prog_attach(obj, cg_child, "cgroup/setsockopt", "_setsockopt");
-	if (err)
+	link_child = bpf_program__attach_cgroup(obj->progs._setsockopt,
+						cg_child);
+	if (!ASSERT_OK_PTR(link_child, "cg-attach-setsockopt_child"))
 		goto detach;
 
 	buf = 0x80;
@@ -263,8 +217,9 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent,
 
 	/* Attach parent program and make sure it adds another 0x10. */
 
-	err = prog_attach(obj, cg_parent, "cgroup/setsockopt", "_setsockopt");
-	if (err)
+	link_parent = bpf_program__attach_cgroup(obj->progs._setsockopt,
+						 cg_parent);
+	if (!ASSERT_OK_PTR(link_parent, "cg-attach-setsockopt_parent"))
 		goto detach;
 
 	buf = 0x80;
@@ -289,8 +244,8 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent,
 	}
 
 detach:
-	prog_detach(obj, cg_child, "cgroup/setsockopt", "_setsockopt");
-	prog_detach(obj, cg_parent, "cgroup/setsockopt", "_setsockopt");
+	bpf_link__destroy(link_child);
+	bpf_link__destroy(link_parent);
 
 	return err;
 }
@@ -298,9 +253,8 @@ detach:
 void test_sockopt_multi(void)
 {
 	int cg_parent = -1, cg_child = -1;
-	struct bpf_object *obj = NULL;
+	struct sockopt_multi *obj = NULL;
 	int sock_fd = -1;
-	int err = -1;
 
 	cg_parent = test__join_cgroup("/parent");
 	if (!ASSERT_GE(cg_parent, 0, "join_cgroup /parent"))
@@ -310,13 +264,11 @@ void test_sockopt_multi(void)
 	if (!ASSERT_GE(cg_child, 0, "join_cgroup /parent/child"))
 		goto out;
 
-	obj = bpf_object__open_file("sockopt_multi.bpf.o", NULL);
-	if (!ASSERT_OK_PTR(obj, "obj_load"))
+	obj = sockopt_multi__open_and_load();
+	if (!ASSERT_OK_PTR(obj, "skel-load"))
 		goto out;
 
-	err = bpf_object__load(obj);
-	if (!ASSERT_OK(err, "obj_load"))
-		goto out;
+	obj->bss->page_size = sysconf(_SC_PAGESIZE);
 
 	sock_fd = socket(AF_INET, SOCK_STREAM, 0);
 	if (!ASSERT_GE(sock_fd, 0, "socket"))
@@ -327,7 +279,7 @@ void test_sockopt_multi(void)
 
 out:
 	close(sock_fd);
-	bpf_object__close(obj);
+	sockopt_multi__destroy(obj);
 	close(cg_child);
 	close(cg_parent);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c b/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c
index 6b53b3cb8dad..6b2d300e9fd4 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_qos_to_cc.c
@@ -42,6 +42,8 @@ void test_sockopt_qos_to_cc(void)
 	if (!ASSERT_OK_PTR(skel, "skel"))
 		goto done;
 
+	skel->bss->page_size = sysconf(_SC_PAGESIZE);
+
 	sock_fd = socket(AF_INET6, SOCK_STREAM, 0);
 	if (!ASSERT_GE(sock_fd, 0, "v6 socket open"))
 		goto done;
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
index 60d952719d27..ba6b3ec1156a 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
@@ -2,7 +2,8 @@
 #include <test_progs.h>
 #include "cgroup_helpers.h"
 
-#include <linux/tcp.h>
+#include <netinet/tcp.h>
+#include <linux/netlink.h>
 #include "sockopt_sk.skel.h"
 
 #ifndef SOL_TCP
@@ -183,6 +184,33 @@ static int getsetsockopt(void)
 		goto err;
 	}
 
+	/* optval=NULL case is handled correctly */
+
+	close(fd);
+	fd = socket(AF_NETLINK, SOCK_RAW, 0);
+	if (fd < 0) {
+		log_err("Failed to create AF_NETLINK socket");
+		return -1;
+	}
+
+	buf.u32 = 1;
+	optlen = sizeof(__u32);
+	err = setsockopt(fd, SOL_NETLINK, NETLINK_ADD_MEMBERSHIP, &buf, optlen);
+	if (err) {
+		log_err("Unexpected getsockopt(NETLINK_ADD_MEMBERSHIP) err=%d errno=%d",
+			err, errno);
+		goto err;
+	}
+
+	optlen = 0;
+	err = getsockopt(fd, SOL_NETLINK, NETLINK_LIST_MEMBERSHIPS, NULL, &optlen);
+	if (err) {
+		log_err("Unexpected getsockopt(NETLINK_LIST_MEMBERSHIPS) err=%d errno=%d",
+			err, errno);
+		goto err;
+	}
+	ASSERT_EQ(optlen, 8, "Unexpected NETLINK_LIST_MEMBERSHIPS value");
+
 	free(big_buf);
 	close(fd);
 	return 0;
diff --git a/tools/testing/selftests/bpf/prog_tests/spin_lock.c b/tools/testing/selftests/bpf/prog_tests/spin_lock.c
index d9270bd3d920..254fbfeab06a 100644
--- a/tools/testing/selftests/bpf/prog_tests/spin_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/spin_lock.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <regex.h>
 #include <test_progs.h>
 #include <network_helpers.h>
 
@@ -12,19 +13,23 @@ static struct {
 	const char *err_msg;
 } spin_lock_fail_tests[] = {
 	{ "lock_id_kptr_preserve",
-	  "5: (bf) r1 = r0                       ; R0_w=ptr_foo(id=2,ref_obj_id=2,off=0,imm=0) "
-	  "R1_w=ptr_foo(id=2,ref_obj_id=2,off=0,imm=0) refs=2\n6: (85) call bpf_this_cpu_ptr#154\n"
+	  "5: (bf) r1 = r0                       ; R0=ptr_foo(id=2,ref_obj_id=2) "
+	  "R1=ptr_foo(id=2,ref_obj_id=2) refs=2\n6: (85) call bpf_this_cpu_ptr#154\n"
 	  "R1 type=ptr_ expected=percpu_ptr_" },
 	{ "lock_id_global_zero",
-	  "; R1_w=map_value(off=0,ks=4,vs=4,imm=0)\n2: (85) call bpf_this_cpu_ptr#154\n"
+	  "; R1=map_value(map=.data.A,ks=4,vs=4)\n2: (85) call bpf_this_cpu_ptr#154\n"
 	  "R1 type=map_value expected=percpu_ptr_" },
 	{ "lock_id_mapval_preserve",
-	  "8: (bf) r1 = r0                       ; R0_w=map_value(id=1,off=0,ks=4,vs=8,imm=0) "
-	  "R1_w=map_value(id=1,off=0,ks=4,vs=8,imm=0)\n9: (85) call bpf_this_cpu_ptr#154\n"
+	  "[0-9]\\+: (bf) r1 = r0                       ;"
+	  " R0=map_value(id=1,map=array_map,ks=4,vs=8)"
+	  " R1=map_value(id=1,map=array_map,ks=4,vs=8)\n"
+	  "[0-9]\\+: (85) call bpf_this_cpu_ptr#154\n"
 	  "R1 type=map_value expected=percpu_ptr_" },
 	{ "lock_id_innermapval_preserve",
-	  "13: (bf) r1 = r0                      ; R0=map_value(id=2,off=0,ks=4,vs=8,imm=0) "
-	  "R1_w=map_value(id=2,off=0,ks=4,vs=8,imm=0)\n14: (85) call bpf_this_cpu_ptr#154\n"
+	  "[0-9]\\+: (bf) r1 = r0                      ;"
+	  " R0=map_value(id=2,ks=4,vs=8)"
+	  " R1=map_value(id=2,ks=4,vs=8)\n"
+	  "[0-9]\\+: (85) call bpf_this_cpu_ptr#154\n"
 	  "R1 type=map_value expected=percpu_ptr_" },
 	{ "lock_id_mismatch_kptr_kptr", "bpf_spin_unlock of different lock" },
 	{ "lock_id_mismatch_kptr_global", "bpf_spin_unlock of different lock" },
@@ -43,8 +48,31 @@ static struct {
 	{ "lock_id_mismatch_innermapval_kptr", "bpf_spin_unlock of different lock" },
 	{ "lock_id_mismatch_innermapval_global", "bpf_spin_unlock of different lock" },
 	{ "lock_id_mismatch_innermapval_mapval", "bpf_spin_unlock of different lock" },
+	{ "lock_global_subprog_call1", "global function calls are not allowed while holding a lock" },
+	{ "lock_global_subprog_call2", "global function calls are not allowed while holding a lock" },
+	{ "lock_global_sleepable_helper_subprog", "global function calls are not allowed while holding a lock" },
+	{ "lock_global_sleepable_kfunc_subprog", "global function calls are not allowed while holding a lock" },
+	{ "lock_global_sleepable_subprog_indirect", "global function calls are not allowed while holding a lock" },
 };
 
+static int match_regex(const char *pattern, const char *string)
+{
+	int err, rc;
+	regex_t re;
+
+	err = regcomp(&re, pattern, REG_NOSUB);
+	if (err) {
+		char errbuf[512];
+
+		regerror(err, &re, errbuf, sizeof(errbuf));
+		PRINT_FAIL("Can't compile regex: %s\n", errbuf);
+		return -1;
+	}
+	rc = regexec(&re, string, 0, NULL, 0);
+	regfree(&re);
+	return rc == 0 ? 1 : 0;
+}
+
 static void test_spin_lock_fail_prog(const char *prog_name, const char *err_msg)
 {
 	LIBBPF_OPTS(bpf_object_open_opts, opts, .kernel_log_buf = log_buf,
@@ -74,7 +102,11 @@ static void test_spin_lock_fail_prog(const char *prog_name, const char *err_msg)
 		goto end;
 	}
 
-	if (!ASSERT_OK_PTR(strstr(log_buf, err_msg), "expected error message")) {
+	ret = match_regex(err_msg, log_buf);
+	if (!ASSERT_GE(ret, 0, "match_regex"))
+		goto end;
+
+	if (!ASSERT_TRUE(ret, "no match for expected error message")) {
 		fprintf(stderr, "Expected: %s\n", err_msg);
 		fprintf(stderr, "Verifier: %s\n", log_buf);
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c
index 9ad09a6c538a..271b5cc9fc01 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c
@@ -7,13 +7,12 @@ void test_stacktrace_build_id(void)
 
 	int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd;
 	struct test_stacktrace_build_id *skel;
-	int err, stack_trace_len;
+	int err, stack_trace_len, build_id_size;
 	__u32 key, prev_key, val, duration = 0;
-	char buf[256];
-	int i, j;
+	char buf[BPF_BUILD_ID_SIZE];
 	struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH];
 	int build_id_matches = 0;
-	int retry = 1;
+	int i, retry = 1;
 
 retry:
 	skel = test_stacktrace_build_id__open_and_load();
@@ -40,7 +39,7 @@ retry:
 	bpf_map_update_elem(control_map_fd, &key, &val, 0);
 
 	/* for every element in stackid_hmap, we can find a corresponding one
-	 * in stackmap, and vise versa.
+	 * in stackmap, and vice versa.
 	 */
 	err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
 	if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
@@ -52,9 +51,10 @@ retry:
 		  "err %d errno %d\n", err, errno))
 		goto cleanup;
 
-	err = extract_build_id(buf, 256);
+	build_id_size = read_build_id("urandom_read", buf, sizeof(buf));
+	err = build_id_size < 0 ? build_id_size : 0;
 
-	if (CHECK(err, "get build_id with readelf",
+	if (CHECK(err, "read_build_id",
 		  "err %d errno %d\n", err, errno))
 		goto cleanup;
 
@@ -64,8 +64,6 @@ retry:
 		goto cleanup;
 
 	do {
-		char build_id[64];
-
 		err = bpf_map_lookup_elem(stackmap_fd, &key, id_offs);
 		if (CHECK(err, "lookup_elem from stackmap",
 			  "err %d, errno %d\n", err, errno))
@@ -73,10 +71,7 @@ retry:
 		for (i = 0; i < PERF_MAX_STACK_DEPTH; ++i)
 			if (id_offs[i].status == BPF_STACK_BUILD_ID_VALID &&
 			    id_offs[i].offset != 0) {
-				for (j = 0; j < 20; ++j)
-					sprintf(build_id + 2 * j, "%02x",
-						id_offs[i].build_id[j] & 0xff);
-				if (strstr(buf, build_id) != NULL)
+				if (memcmp(buf, id_offs[i].build_id, build_id_size) == 0)
 					build_id_matches = 1;
 			}
 		prev_key = key;
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
index f4ea1a215ce4..b277dddd5af7 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
@@ -2,21 +2,6 @@
 #include <test_progs.h>
 #include "test_stacktrace_build_id.skel.h"
 
-static __u64 read_perf_max_sample_freq(void)
-{
-	__u64 sample_freq = 5000; /* fallback to 5000 on error */
-	FILE *f;
-	__u32 duration = 0;
-
-	f = fopen("/proc/sys/kernel/perf_event_max_sample_rate", "r");
-	if (f == NULL)
-		return sample_freq;
-	CHECK(fscanf(f, "%llu", &sample_freq) != 1, "Get max sample rate",
-		  "return default value: 5000,err %d\n", -errno);
-	fclose(f);
-	return sample_freq;
-}
-
 void test_stacktrace_build_id_nmi(void)
 {
 	int control_map_fd, stackid_hmap_fd, stackmap_fd;
@@ -28,11 +13,10 @@ void test_stacktrace_build_id_nmi(void)
 		.config = PERF_COUNT_HW_CPU_CYCLES,
 	};
 	__u32 key, prev_key, val, duration = 0;
-	char buf[256];
-	int i, j;
+	char buf[BPF_BUILD_ID_SIZE];
 	struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH];
-	int build_id_matches = 0;
-	int retry = 1;
+	int build_id_matches = 0, build_id_size;
+	int i, retry = 1;
 
 	attr.sample_freq = read_perf_max_sample_freq();
 
@@ -51,7 +35,7 @@ retry:
 	pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
 			 0 /* cpu 0 */, -1 /* group id */,
 			 0 /* flags */);
-	if (pmu_fd < 0 && errno == ENOENT) {
+	if (pmu_fd < 0 && (errno == ENOENT || errno == EOPNOTSUPP)) {
 		printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n", __func__);
 		test__skip();
 		goto cleanup;
@@ -82,7 +66,7 @@ retry:
 	bpf_map_update_elem(control_map_fd, &key, &val, 0);
 
 	/* for every element in stackid_hmap, we can find a corresponding one
-	 * in stackmap, and vise versa.
+	 * in stackmap, and vice versa.
 	 */
 	err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
 	if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
@@ -94,7 +78,8 @@ retry:
 		  "err %d errno %d\n", err, errno))
 		goto cleanup;
 
-	err = extract_build_id(buf, 256);
+	build_id_size = read_build_id("urandom_read", buf, sizeof(buf));
+	err = build_id_size < 0 ? build_id_size : 0;
 
 	if (CHECK(err, "get build_id with readelf",
 		  "err %d errno %d\n", err, errno))
@@ -106,8 +91,6 @@ retry:
 		goto cleanup;
 
 	do {
-		char build_id[64];
-
 		err = bpf_map__lookup_elem(skel->maps.stackmap, &key, sizeof(key),
 					   id_offs, sizeof(id_offs), 0);
 		if (CHECK(err, "lookup_elem from stackmap",
@@ -116,10 +99,7 @@ retry:
 		for (i = 0; i < PERF_MAX_STACK_DEPTH; ++i)
 			if (id_offs[i].status == BPF_STACK_BUILD_ID_VALID &&
 			    id_offs[i].offset != 0) {
-				for (j = 0; j < 20; ++j)
-					sprintf(build_id + 2 * j, "%02x",
-						id_offs[i].build_id[j] & 0xff);
-				if (strstr(buf, build_id) != NULL)
+				if (memcmp(buf, id_offs[i].build_id, build_id_size) == 0)
 					build_id_matches = 1;
 			}
 		prev_key = key;
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_ips.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_ips.c
new file mode 100644
index 000000000000..c9efdd2a5b18
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_ips.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include "stacktrace_ips.skel.h"
+
+#ifdef __x86_64__
+static int check_stacktrace_ips(int fd, __u32 key, int cnt, ...)
+{
+	__u64 ips[PERF_MAX_STACK_DEPTH];
+	struct ksyms *ksyms = NULL;
+	int i, err = 0;
+	va_list args;
+
+	/* sorted by addr */
+	ksyms = load_kallsyms_local();
+	if (!ASSERT_OK_PTR(ksyms, "load_kallsyms_local"))
+		return -1;
+
+	/* unlikely, but... */
+	if (!ASSERT_LT(cnt, PERF_MAX_STACK_DEPTH, "check_max"))
+		return -1;
+
+	err = bpf_map_lookup_elem(fd, &key, ips);
+	if (err)
+		goto out;
+
+	/*
+	 * Compare all symbols provided via arguments with stacktrace ips,
+	 * and their related symbol addresses.t
+	 */
+	va_start(args, cnt);
+
+	for (i = 0; i < cnt; i++) {
+		unsigned long val;
+		struct ksym *ksym;
+
+		val = va_arg(args, unsigned long);
+		ksym = ksym_search_local(ksyms, ips[i]);
+		if (!ASSERT_OK_PTR(ksym, "ksym_search_local"))
+			break;
+		ASSERT_EQ(ksym->addr, val, "stack_cmp");
+	}
+
+	va_end(args);
+
+out:
+	free_kallsyms_local(ksyms);
+	return err;
+}
+
+static void test_stacktrace_ips_kprobe_multi(bool retprobe)
+{
+	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts,
+		.retprobe = retprobe
+	);
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	struct stacktrace_ips *skel;
+
+	skel = stacktrace_ips__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "stacktrace_ips__open_and_load"))
+		return;
+
+	if (!skel->kconfig->CONFIG_UNWINDER_ORC) {
+		test__skip();
+		goto cleanup;
+	}
+
+	skel->links.kprobe_multi_test = bpf_program__attach_kprobe_multi_opts(
+							skel->progs.kprobe_multi_test,
+							"bpf_testmod_stacktrace_test", &opts);
+	if (!ASSERT_OK_PTR(skel->links.kprobe_multi_test, "bpf_program__attach_kprobe_multi_opts"))
+		goto cleanup;
+
+	trigger_module_test_read(1);
+
+	load_kallsyms();
+
+	check_stacktrace_ips(bpf_map__fd(skel->maps.stackmap), skel->bss->stack_key, 4,
+			     ksym_get_addr("bpf_testmod_stacktrace_test_3"),
+			     ksym_get_addr("bpf_testmod_stacktrace_test_2"),
+			     ksym_get_addr("bpf_testmod_stacktrace_test_1"),
+			     ksym_get_addr("bpf_testmod_test_read"));
+
+cleanup:
+	stacktrace_ips__destroy(skel);
+}
+
+static void test_stacktrace_ips_raw_tp(void)
+{
+	__u32 info_len = sizeof(struct bpf_prog_info);
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	struct bpf_prog_info info = {};
+	struct stacktrace_ips *skel;
+	__u64 bpf_prog_ksym = 0;
+	int err;
+
+	skel = stacktrace_ips__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "stacktrace_ips__open_and_load"))
+		return;
+
+	if (!skel->kconfig->CONFIG_UNWINDER_ORC) {
+		test__skip();
+		goto cleanup;
+	}
+
+	skel->links.rawtp_test = bpf_program__attach_raw_tracepoint(
+							skel->progs.rawtp_test,
+							"bpf_testmod_test_read");
+	if (!ASSERT_OK_PTR(skel->links.rawtp_test, "bpf_program__attach_raw_tracepoint"))
+		goto cleanup;
+
+	/* get bpf program address */
+	info.jited_ksyms = ptr_to_u64(&bpf_prog_ksym);
+	info.nr_jited_ksyms = 1;
+	err = bpf_prog_get_info_by_fd(bpf_program__fd(skel->progs.rawtp_test),
+				      &info, &info_len);
+	if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd"))
+		goto cleanup;
+
+	trigger_module_test_read(1);
+
+	load_kallsyms();
+
+	check_stacktrace_ips(bpf_map__fd(skel->maps.stackmap), skel->bss->stack_key, 2,
+			     bpf_prog_ksym,
+			     ksym_get_addr("bpf_trace_run2"));
+
+cleanup:
+	stacktrace_ips__destroy(skel);
+}
+
+static void __test_stacktrace_ips(void)
+{
+	if (test__start_subtest("kprobe_multi"))
+		test_stacktrace_ips_kprobe_multi(false);
+	if (test__start_subtest("kretprobe_multi"))
+		test_stacktrace_ips_kprobe_multi(true);
+	if (test__start_subtest("raw_tp"))
+		test_stacktrace_ips_raw_tp();
+}
+#else
+static void __test_stacktrace_ips(void)
+{
+	test__skip();
+}
+#endif
+
+void test_stacktrace_ips(void)
+{
+	__test_stacktrace_ips();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
index df59e4ae2951..c23b97414813 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map.c
@@ -1,46 +1,27 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include "stacktrace_map.skel.h"
 
 void test_stacktrace_map(void)
 {
+	struct stacktrace_map *skel;
 	int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd;
-	const char *prog_name = "oncpu";
-	int err, prog_fd, stack_trace_len;
-	const char *file = "./test_stacktrace_map.bpf.o";
-	__u32 key, val, duration = 0;
-	struct bpf_program *prog;
-	struct bpf_object *obj;
-	struct bpf_link *link;
+	int err, stack_trace_len;
+	__u32 key, val, stack_id, duration = 0;
+	__u64 stack[PERF_MAX_STACK_DEPTH];
 
-	err = bpf_prog_test_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd);
-	if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
+	skel = stacktrace_map__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
 		return;
 
-	prog = bpf_object__find_program_by_name(obj, prog_name);
-	if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name))
-		goto close_prog;
-
-	link = bpf_program__attach_tracepoint(prog, "sched", "sched_switch");
-	if (!ASSERT_OK_PTR(link, "attach_tp"))
-		goto close_prog;
-
-	/* find map fds */
-	control_map_fd = bpf_find_map(__func__, obj, "control_map");
-	if (CHECK_FAIL(control_map_fd < 0))
-		goto disable_pmu;
-
-	stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap");
-	if (CHECK_FAIL(stackid_hmap_fd < 0))
-		goto disable_pmu;
-
-	stackmap_fd = bpf_find_map(__func__, obj, "stackmap");
-	if (CHECK_FAIL(stackmap_fd < 0))
-		goto disable_pmu;
-
-	stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap");
-	if (CHECK_FAIL(stack_amap_fd < 0))
-		goto disable_pmu;
+	control_map_fd = bpf_map__fd(skel->maps.control_map);
+	stackid_hmap_fd = bpf_map__fd(skel->maps.stackid_hmap);
+	stackmap_fd = bpf_map__fd(skel->maps.stackmap);
+	stack_amap_fd = bpf_map__fd(skel->maps.stack_amap);
 
+	err = stacktrace_map__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto out;
 	/* give some time for bpf program run */
 	sleep(1);
 
@@ -50,26 +31,32 @@ void test_stacktrace_map(void)
 	bpf_map_update_elem(control_map_fd, &key, &val, 0);
 
 	/* for every element in stackid_hmap, we can find a corresponding one
-	 * in stackmap, and vise versa.
+	 * in stackmap, and vice versa.
 	 */
 	err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
 	if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
 		  "err %d errno %d\n", err, errno))
-		goto disable_pmu;
+		goto out;
 
 	err = compare_map_keys(stackmap_fd, stackid_hmap_fd);
 	if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap",
 		  "err %d errno %d\n", err, errno))
-		goto disable_pmu;
+		goto out;
 
 	stack_trace_len = PERF_MAX_STACK_DEPTH * sizeof(__u64);
 	err = compare_stack_ips(stackmap_fd, stack_amap_fd, stack_trace_len);
 	if (CHECK(err, "compare_stack_ips stackmap vs. stack_amap",
 		  "err %d errno %d\n", err, errno))
-		goto disable_pmu;
-
-disable_pmu:
-	bpf_link__destroy(link);
-close_prog:
-	bpf_object__close(obj);
+		goto out;
+
+	stack_id = skel->bss->stack_id;
+	err = bpf_map_lookup_and_delete_elem(stackmap_fd, &stack_id,  stack);
+	if (!ASSERT_OK(err, "lookup and delete target stack_id"))
+		goto out;
+
+	err = bpf_map_lookup_elem(stackmap_fd, &stack_id, stack);
+	if (!ASSERT_EQ(err, -ENOENT, "lookup deleted stack_id"))
+		goto out;
+out:
+	stacktrace_map__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
index c6ef06f55cdb..e985d51d3d47 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_raw_tp.c
@@ -5,7 +5,7 @@ void test_stacktrace_map_raw_tp(void)
 {
 	const char *prog_name = "oncpu";
 	int control_map_fd, stackid_hmap_fd, stackmap_fd;
-	const char *file = "./test_stacktrace_map.bpf.o";
+	const char *file = "./stacktrace_map.bpf.o";
 	__u32 key, val, duration = 0;
 	int err, prog_fd;
 	struct bpf_program *prog;
@@ -46,7 +46,7 @@ void test_stacktrace_map_raw_tp(void)
 	bpf_map_update_elem(control_map_fd, &key, &val, 0);
 
 	/* for every element in stackid_hmap, we can find a corresponding one
-	 * in stackmap, and vise versa.
+	 * in stackmap, and vice versa.
 	 */
 	err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
 	if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c
index 1932b1e0685c..dc2ccf6a14d1 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_map_skip.c
@@ -40,7 +40,7 @@ void test_stacktrace_map_skip(void)
 	skel->bss->control = 1;
 
 	/* for every element in stackid_hmap, we can find a corresponding one
-	 * in stackmap, and vise versa.
+	 * in stackmap, and vice versa.
 	 */
 	err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
 	if (!ASSERT_OK(err, "compare_map_keys stackid_hmap vs. stackmap"))
diff --git a/tools/testing/selftests/bpf/prog_tests/stream.c b/tools/testing/selftests/bpf/prog_tests/stream.c
new file mode 100644
index 000000000000..c3cce5c292bd
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/stream.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <sys/mman.h>
+
+#include "stream.skel.h"
+#include "stream_fail.skel.h"
+
+void test_stream_failure(void)
+{
+	RUN_TESTS(stream_fail);
+}
+
+void test_stream_success(void)
+{
+	RUN_TESTS(stream);
+	return;
+}
+
+void test_stream_syscall(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	LIBBPF_OPTS(bpf_prog_stream_read_opts, ropts);
+	struct stream *skel;
+	int ret, prog_fd;
+	char buf[64];
+
+	skel = stream__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "stream__open_and_load"))
+		return;
+
+	prog_fd = bpf_program__fd(skel->progs.stream_syscall);
+	ret = bpf_prog_test_run_opts(prog_fd, &opts);
+	ASSERT_OK(ret, "ret");
+	ASSERT_OK(opts.retval, "retval");
+
+	ASSERT_LT(bpf_prog_stream_read(0, BPF_STREAM_STDOUT, buf, sizeof(buf), &ropts), 0, "error");
+	ret = -errno;
+	ASSERT_EQ(ret, -EINVAL, "bad prog_fd");
+
+	ASSERT_LT(bpf_prog_stream_read(prog_fd, 0, buf, sizeof(buf), &ropts), 0, "error");
+	ret = -errno;
+	ASSERT_EQ(ret, -ENOENT, "bad stream id");
+
+	ASSERT_LT(bpf_prog_stream_read(prog_fd, BPF_STREAM_STDOUT, NULL, sizeof(buf), NULL), 0, "error");
+	ret = -errno;
+	ASSERT_EQ(ret, -EFAULT, "bad stream buf");
+
+	ret = bpf_prog_stream_read(prog_fd, BPF_STREAM_STDOUT, buf, 2, NULL);
+	ASSERT_EQ(ret, 2, "bytes");
+	ret = bpf_prog_stream_read(prog_fd, BPF_STREAM_STDOUT, buf, 2, NULL);
+	ASSERT_EQ(ret, 1, "bytes");
+	ret = bpf_prog_stream_read(prog_fd, BPF_STREAM_STDOUT, buf, 1, &ropts);
+	ASSERT_EQ(ret, 0, "no bytes stdout");
+	ret = bpf_prog_stream_read(prog_fd, BPF_STREAM_STDERR, buf, 1, &ropts);
+	ASSERT_EQ(ret, 0, "no bytes stderr");
+
+	stream__destroy(skel);
+}
+
+static void test_address(struct bpf_program *prog, unsigned long *fault_addr_p)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	LIBBPF_OPTS(bpf_prog_stream_read_opts, ropts);
+	int ret, prog_fd;
+	char fault_addr[64];
+	char buf[1024];
+
+	prog_fd = bpf_program__fd(prog);
+
+	ret = bpf_prog_test_run_opts(prog_fd, &opts);
+	ASSERT_OK(ret, "ret");
+	ASSERT_OK(opts.retval, "retval");
+
+	sprintf(fault_addr, "0x%lx", *fault_addr_p);
+
+	ret = bpf_prog_stream_read(prog_fd, BPF_STREAM_STDERR, buf, sizeof(buf), &ropts);
+	ASSERT_GT(ret, 0, "stream read");
+	ASSERT_LE(ret, 1023, "len for buf");
+	buf[ret] = '\0';
+
+	if (!ASSERT_HAS_SUBSTR(buf, fault_addr, "fault_addr")) {
+		fprintf(stderr, "Output from stream:\n%s\n", buf);
+		fprintf(stderr, "Fault Addr: %s\n", fault_addr);
+	}
+}
+
+void test_stream_arena_fault_address(void)
+{
+	struct stream *skel;
+
+#if !defined(__x86_64__) && !defined(__aarch64__)
+	printf("%s:SKIP: arena fault reporting not supported\n", __func__);
+	test__skip();
+	return;
+#endif
+
+	skel = stream__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "stream__open_and_load"))
+		return;
+
+	if (test__start_subtest("read_fault"))
+		test_address(skel->progs.stream_arena_read_fault, &skel->bss->fault_addr);
+	if (test__start_subtest("write_fault"))
+		test_address(skel->progs.stream_arena_write_fault, &skel->bss->fault_addr);
+
+	stream__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c b/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c
new file mode 100644
index 000000000000..0f3bf594e7a5
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2025 Red Hat, Inc.*/
+#include <test_progs.h>
+#include "string_kfuncs_success.skel.h"
+#include "string_kfuncs_failure1.skel.h"
+#include "string_kfuncs_failure2.skel.h"
+#include <sys/mman.h>
+
+static const char * const test_cases[] = {
+	"strcmp",
+	"strcasecmp",
+	"strchr",
+	"strchrnul",
+	"strnchr",
+	"strrchr",
+	"strlen",
+	"strnlen",
+	"strspn_str",
+	"strspn_accept",
+	"strcspn_str",
+	"strcspn_reject",
+	"strstr",
+	"strcasestr",
+	"strnstr",
+	"strncasestr",
+};
+
+void run_too_long_tests(void)
+{
+	struct string_kfuncs_failure2 *skel;
+	struct bpf_program *prog;
+	char test_name[256];
+	int err, i;
+
+	skel = string_kfuncs_failure2__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "string_kfuncs_failure2__open_and_load"))
+		return;
+
+	memset(skel->bss->long_str, 'a', sizeof(skel->bss->long_str));
+
+	for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
+		sprintf(test_name, "test_%s_too_long", test_cases[i]);
+		if (!test__start_subtest(test_name))
+			continue;
+
+		prog = bpf_object__find_program_by_name(skel->obj, test_name);
+		if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
+			goto cleanup;
+
+		LIBBPF_OPTS(bpf_test_run_opts, topts);
+		err = bpf_prog_test_run_opts(bpf_program__fd(prog), &topts);
+		if (!ASSERT_OK(err, "bpf_prog_test_run"))
+			goto cleanup;
+
+		ASSERT_EQ(topts.retval, -E2BIG, "reading too long string fails with -E2BIG");
+	}
+
+cleanup:
+	string_kfuncs_failure2__destroy(skel);
+}
+
+void test_string_kfuncs(void)
+{
+	RUN_TESTS(string_kfuncs_success);
+	RUN_TESTS(string_kfuncs_failure1);
+
+	run_too_long_tests();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/struct_ops_autocreate.c b/tools/testing/selftests/bpf/prog_tests/struct_ops_autocreate.c
new file mode 100644
index 000000000000..a5cc593c1e1d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/struct_ops_autocreate.c
@@ -0,0 +1,159 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "struct_ops_autocreate.skel.h"
+#include "struct_ops_autocreate2.skel.h"
+
+static void cant_load_full_object(void)
+{
+	struct struct_ops_autocreate *skel;
+	char *log = NULL;
+	int err;
+
+	skel = struct_ops_autocreate__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_autocreate__open"))
+		return;
+
+	if (start_libbpf_log_capture())
+		goto cleanup;
+	/* The testmod_2 map BTF type (struct bpf_testmod_ops___v2) doesn't
+	 * match the BTF of the actual struct bpf_testmod_ops defined in the
+	 * kernel, so we should fail to load it if we don't disable autocreate
+	 * for that map.
+	 */
+	err = struct_ops_autocreate__load(skel);
+	log = stop_libbpf_log_capture();
+	if (!ASSERT_ERR(err, "struct_ops_autocreate__load"))
+		goto cleanup;
+
+	ASSERT_HAS_SUBSTR(log, "libbpf: struct_ops init_kern", "init_kern message");
+	ASSERT_EQ(err, -ENOTSUP, "errno should be ENOTSUP");
+
+cleanup:
+	free(log);
+	struct_ops_autocreate__destroy(skel);
+}
+
+static int check_test_1_link(struct struct_ops_autocreate *skel, struct bpf_map *map)
+{
+	struct bpf_link *link;
+	int err;
+
+	link = bpf_map__attach_struct_ops(skel->maps.testmod_1);
+	if (!ASSERT_OK_PTR(link, "bpf_map__attach_struct_ops"))
+		return -1;
+
+	/* test_1() would be called from bpf_dummy_reg2() in bpf_testmod.c */
+	err = ASSERT_EQ(skel->bss->test_1_result, 42, "test_1_result");
+	bpf_link__destroy(link);
+	return err;
+}
+
+static void can_load_partial_object(void)
+{
+	struct struct_ops_autocreate *skel;
+	int err;
+
+	skel = struct_ops_autocreate__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_autocreate__open_opts"))
+		return;
+
+	err = bpf_map__set_autocreate(skel->maps.testmod_2, false);
+	if (!ASSERT_OK(err, "bpf_map__set_autocreate"))
+		goto cleanup;
+
+	ASSERT_TRUE(bpf_program__autoload(skel->progs.test_1), "test_1 default autoload");
+	ASSERT_TRUE(bpf_program__autoload(skel->progs.test_2), "test_2 default autoload");
+
+	err = struct_ops_autocreate__load(skel);
+	if (ASSERT_OK(err, "struct_ops_autocreate__load"))
+		goto cleanup;
+
+	ASSERT_TRUE(bpf_program__autoload(skel->progs.test_1), "test_1 actual autoload");
+	ASSERT_FALSE(bpf_program__autoload(skel->progs.test_2), "test_2 actual autoload");
+
+	check_test_1_link(skel, skel->maps.testmod_1);
+
+cleanup:
+	struct_ops_autocreate__destroy(skel);
+}
+
+static void optional_maps(void)
+{
+	struct struct_ops_autocreate *skel;
+	int err;
+
+	skel = struct_ops_autocreate__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_autocreate__open"))
+		return;
+
+	ASSERT_TRUE(bpf_map__autocreate(skel->maps.testmod_1), "testmod_1 autocreate");
+	ASSERT_TRUE(bpf_map__autocreate(skel->maps.testmod_2), "testmod_2 autocreate");
+	ASSERT_FALSE(bpf_map__autocreate(skel->maps.optional_map), "optional_map autocreate");
+	ASSERT_FALSE(bpf_map__autocreate(skel->maps.optional_map2), "optional_map2 autocreate");
+
+	err  = bpf_map__set_autocreate(skel->maps.testmod_1, false);
+	err |= bpf_map__set_autocreate(skel->maps.testmod_2, false);
+	err |= bpf_map__set_autocreate(skel->maps.optional_map2, true);
+	if (!ASSERT_OK(err, "bpf_map__set_autocreate"))
+		goto cleanup;
+
+	err = struct_ops_autocreate__load(skel);
+	if (ASSERT_OK(err, "struct_ops_autocreate__load"))
+		goto cleanup;
+
+	check_test_1_link(skel, skel->maps.optional_map2);
+
+cleanup:
+	struct_ops_autocreate__destroy(skel);
+}
+
+/* Swap test_mod1->test_1 program from 'bar' to 'foo' using shadow vars.
+ * test_mod1 load should enable autoload for 'foo'.
+ */
+static void autoload_and_shadow_vars(void)
+{
+	struct struct_ops_autocreate2 *skel = NULL;
+	struct bpf_link *link = NULL;
+	int err;
+
+	skel = struct_ops_autocreate2__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_autocreate__open_opts"))
+		return;
+
+	ASSERT_FALSE(bpf_program__autoload(skel->progs.foo), "foo default autoload");
+	ASSERT_FALSE(bpf_program__autoload(skel->progs.bar), "bar default autoload");
+
+	/* loading map testmod_1 would switch foo's autoload to true */
+	skel->struct_ops.testmod_1->test_1 = skel->progs.foo;
+
+	err = struct_ops_autocreate2__load(skel);
+	if (ASSERT_OK(err, "struct_ops_autocreate__load"))
+		goto cleanup;
+
+	ASSERT_TRUE(bpf_program__autoload(skel->progs.foo), "foo actual autoload");
+	ASSERT_FALSE(bpf_program__autoload(skel->progs.bar), "bar actual autoload");
+
+	link = bpf_map__attach_struct_ops(skel->maps.testmod_1);
+	if (!ASSERT_OK_PTR(link, "bpf_map__attach_struct_ops"))
+		goto cleanup;
+
+	/* test_1() would be called from bpf_dummy_reg2() in bpf_testmod.c */
+	err = ASSERT_EQ(skel->bss->test_1_result, 42, "test_1_result");
+
+cleanup:
+	bpf_link__destroy(link);
+	struct_ops_autocreate2__destroy(skel);
+}
+
+void test_struct_ops_autocreate(void)
+{
+	if (test__start_subtest("cant_load_full_object"))
+		cant_load_full_object();
+	if (test__start_subtest("can_load_partial_object"))
+		can_load_partial_object();
+	if (test__start_subtest("autoload_and_shadow_vars"))
+		autoload_and_shadow_vars();
+	if (test__start_subtest("optional_maps"))
+		optional_maps();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c b/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c
new file mode 100644
index 000000000000..4006879ca3fe
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c
@@ -0,0 +1,106 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "struct_ops_private_stack.skel.h"
+#include "struct_ops_private_stack_fail.skel.h"
+#include "struct_ops_private_stack_recur.skel.h"
+
+static void test_private_stack(void)
+{
+	struct struct_ops_private_stack *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = struct_ops_private_stack__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_private_stack__open"))
+		return;
+
+	if (skel->data->skip) {
+		test__skip();
+		goto cleanup;
+	}
+
+	err = struct_ops_private_stack__load(skel);
+	if (!ASSERT_OK(err, "struct_ops_private_stack__load"))
+		goto cleanup;
+
+	link = bpf_map__attach_struct_ops(skel->maps.testmod_1);
+	if (!ASSERT_OK_PTR(link, "attach_struct_ops"))
+		goto cleanup;
+
+	ASSERT_OK(trigger_module_test_read(256), "trigger_read");
+
+	ASSERT_EQ(skel->bss->val_i, 3, "val_i");
+	ASSERT_EQ(skel->bss->val_j, 8, "val_j");
+
+	bpf_link__destroy(link);
+
+cleanup:
+	struct_ops_private_stack__destroy(skel);
+}
+
+static void test_private_stack_fail(void)
+{
+	struct struct_ops_private_stack_fail *skel;
+	int err;
+
+	skel = struct_ops_private_stack_fail__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_private_stack_fail__open"))
+		return;
+
+	if (skel->data->skip) {
+		test__skip();
+		goto cleanup;
+	}
+
+	err = struct_ops_private_stack_fail__load(skel);
+	if (!ASSERT_ERR(err, "struct_ops_private_stack_fail__load"))
+		goto cleanup;
+	return;
+
+cleanup:
+	struct_ops_private_stack_fail__destroy(skel);
+}
+
+static void test_private_stack_recur(void)
+{
+	struct struct_ops_private_stack_recur *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = struct_ops_private_stack_recur__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_private_stack_recur__open"))
+		return;
+
+	if (skel->data->skip) {
+		test__skip();
+		goto cleanup;
+	}
+
+	err = struct_ops_private_stack_recur__load(skel);
+	if (!ASSERT_OK(err, "struct_ops_private_stack_recur__load"))
+		goto cleanup;
+
+	link = bpf_map__attach_struct_ops(skel->maps.testmod_1);
+	if (!ASSERT_OK_PTR(link, "attach_struct_ops"))
+		goto cleanup;
+
+	ASSERT_OK(trigger_module_test_read(256), "trigger_read");
+
+	ASSERT_EQ(skel->bss->val_j, 3, "val_j");
+
+	bpf_link__destroy(link);
+
+cleanup:
+	struct_ops_private_stack_recur__destroy(skel);
+}
+
+void test_struct_ops_private_stack(void)
+{
+	if (test__start_subtest("private_stack"))
+		test_private_stack();
+	if (test__start_subtest("private_stack_fail"))
+		test_private_stack_fail();
+	if (test__start_subtest("private_stack_recur"))
+		test_private_stack_recur();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/subprogs_extable.c b/tools/testing/selftests/bpf/prog_tests/subprogs_extable.c
new file mode 100644
index 000000000000..3afd9f775f68
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/subprogs_extable.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "test_subprogs_extable.skel.h"
+
+void test_subprogs_extable(void)
+{
+	const int read_sz = 456;
+	struct test_subprogs_extable *skel;
+	int err;
+
+	skel = test_subprogs_extable__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return;
+
+	err = test_subprogs_extable__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	/* trigger tracepoint */
+	ASSERT_OK(trigger_module_test_read(read_sz), "trigger_read");
+
+	ASSERT_NEQ(skel->bss->triggered, 0, "verify at least one program ran");
+
+	test_subprogs_extable__detach(skel);
+
+cleanup:
+	test_subprogs_extable__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/subskeleton.c b/tools/testing/selftests/bpf/prog_tests/subskeleton.c
index 9c31b7004f9c..fdf13ed0152a 100644
--- a/tools/testing/selftests/bpf/prog_tests/subskeleton.c
+++ b/tools/testing/selftests/bpf/prog_tests/subskeleton.c
@@ -46,7 +46,8 @@ static int subskeleton_lib_subresult(struct bpf_object *obj)
 	return result;
 }
 
-void test_subskeleton(void)
+/* initialize and load through skeleton, then instantiate subskeleton out of it */
+static void subtest_skel_subskeleton(void)
 {
 	int err, result;
 	struct test_subskeleton *skel;
@@ -76,3 +77,76 @@ void test_subskeleton(void)
 cleanup:
 	test_subskeleton__destroy(skel);
 }
+
+/* initialize and load through generic bpf_object API, then instantiate subskeleton out of it */
+static void subtest_obj_subskeleton(void)
+{
+	int err, result;
+	const void *elf_bytes;
+	size_t elf_bytes_sz = 0, rodata_sz = 0, bss_sz = 0;
+	struct bpf_object *obj;
+	const struct bpf_map *map;
+	const struct bpf_program *prog;
+	struct bpf_link *link = NULL;
+	struct test_subskeleton__rodata *rodata;
+	struct test_subskeleton__bss *bss;
+
+	elf_bytes = test_subskeleton__elf_bytes(&elf_bytes_sz);
+	if (!ASSERT_OK_PTR(elf_bytes, "elf_bytes"))
+		return;
+
+	obj = bpf_object__open_mem(elf_bytes, elf_bytes_sz, NULL);
+	if (!ASSERT_OK_PTR(obj, "obj_open_mem"))
+		return;
+
+	map = bpf_object__find_map_by_name(obj, ".rodata");
+	if (!ASSERT_OK_PTR(map, "rodata_map_by_name"))
+		goto cleanup;
+
+	rodata = bpf_map__initial_value(map, &rodata_sz);
+	if (!ASSERT_OK_PTR(rodata, "rodata_get"))
+		goto cleanup;
+
+	rodata->rovar1 = 10;
+	rodata->var1 = 1;
+	subskeleton_lib_setup(obj);
+
+	err = bpf_object__load(obj);
+	if (!ASSERT_OK(err, "obj_load"))
+		goto cleanup;
+
+	prog = bpf_object__find_program_by_name(obj, "handler1");
+	if (!ASSERT_OK_PTR(prog, "prog_by_name"))
+		goto cleanup;
+
+	link = bpf_program__attach(prog);
+	if (!ASSERT_OK_PTR(link, "prog_attach"))
+		goto cleanup;
+
+	/* trigger tracepoint */
+	usleep(1);
+
+	map = bpf_object__find_map_by_name(obj, ".bss");
+	if (!ASSERT_OK_PTR(map, "bss_map_by_name"))
+		goto cleanup;
+
+	bss = bpf_map__initial_value(map, &bss_sz);
+	if (!ASSERT_OK_PTR(rodata, "rodata_get"))
+		goto cleanup;
+
+	result = subskeleton_lib_subresult(obj) * 10;
+	ASSERT_EQ(bss->out1, result, "out1");
+
+cleanup:
+	bpf_link__destroy(link);
+	bpf_object__close(obj);
+}
+
+
+void test_subskeleton(void)
+{
+	if (test__start_subtest("skel_subskel"))
+		subtest_skel_subskeleton();
+	if (test__start_subtest("obj_subskel"))
+		subtest_obj_subskeleton();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/summarization.c b/tools/testing/selftests/bpf/prog_tests/summarization.c
new file mode 100644
index 000000000000..5dd6c120a838
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/summarization.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "bpf/libbpf.h"
+#include "summarization_freplace.skel.h"
+#include "summarization.skel.h"
+#include <test_progs.h>
+
+static void print_verifier_log(const char *log)
+{
+	if (env.verbosity >= VERBOSE_VERY)
+		fprintf(stdout, "VERIFIER LOG:\n=============\n%s=============\n", log);
+}
+
+static void test_aux(const char *main_prog_name,
+		     const char *to_be_replaced,
+		     const char *replacement,
+		     bool expect_load,
+		     const char *err_msg)
+{
+	struct summarization_freplace *freplace = NULL;
+	struct bpf_program *freplace_prog = NULL;
+	struct bpf_program *main_prog = NULL;
+	LIBBPF_OPTS(bpf_object_open_opts, opts);
+	struct summarization *main = NULL;
+	char log[16*1024];
+	int err;
+
+	opts.kernel_log_buf = log;
+	opts.kernel_log_size = sizeof(log);
+	if (env.verbosity >= VERBOSE_SUPER)
+		opts.kernel_log_level = 1 | 2 | 4;
+	main = summarization__open_opts(&opts);
+	if (!ASSERT_OK_PTR(main, "summarization__open"))
+		goto out;
+	main_prog = bpf_object__find_program_by_name(main->obj, main_prog_name);
+	if (!ASSERT_OK_PTR(main_prog, "main_prog"))
+		goto out;
+	bpf_program__set_autoload(main_prog, true);
+	err = summarization__load(main);
+	print_verifier_log(log);
+	if (!ASSERT_OK(err, "summarization__load"))
+		goto out;
+	freplace = summarization_freplace__open_opts(&opts);
+	if (!ASSERT_OK_PTR(freplace, "summarization_freplace__open"))
+		goto out;
+	freplace_prog = bpf_object__find_program_by_name(freplace->obj, replacement);
+	if (!ASSERT_OK_PTR(freplace_prog, "freplace_prog"))
+		goto out;
+	bpf_program__set_autoload(freplace_prog, true);
+	bpf_program__set_autoattach(freplace_prog, true);
+	bpf_program__set_attach_target(freplace_prog,
+				       bpf_program__fd(main_prog),
+				       to_be_replaced);
+	err = summarization_freplace__load(freplace);
+	print_verifier_log(log);
+
+	/* The might_sleep extension doesn't work yet as sleepable calls are not
+	 * allowed, but preserve the check in case it's supported later and then
+	 * this particular combination can be enabled.
+	 */
+	if (!strcmp("might_sleep", replacement) && err) {
+		ASSERT_HAS_SUBSTR(log, "helper call might sleep in a non-sleepable prog", "error log");
+		ASSERT_EQ(err, -EINVAL, "err");
+		test__skip();
+		goto out;
+	}
+
+	if (expect_load) {
+		ASSERT_OK(err, "summarization_freplace__load");
+	} else {
+		ASSERT_ERR(err, "summarization_freplace__load");
+		ASSERT_HAS_SUBSTR(log, err_msg, "error log");
+	}
+
+out:
+	summarization_freplace__destroy(freplace);
+	summarization__destroy(main);
+}
+
+/* There are two global subprograms in both summarization.skel.h:
+ * - one changes packet data;
+ * - another does not.
+ * It is ok to freplace subprograms that change packet data with those
+ * that either do or do not. It is only ok to freplace subprograms
+ * that do not change packet data with those that do not as well.
+ * The below tests check outcomes for each combination of such freplace.
+ * Also test a case when main subprogram itself is replaced and is a single
+ * subprogram in a program.
+ *
+ * This holds for might_sleep programs. It is ok to replace might_sleep with
+ * might_sleep and with does_not_sleep, but does_not_sleep cannot be replaced
+ * with might_sleep.
+ */
+void test_summarization_freplace(void)
+{
+	struct {
+		const char *main;
+		const char *to_be_replaced;
+		bool has_side_effect;
+	} mains[2][4] = {
+		{
+			{ "main_changes_with_subprogs",		"changes_pkt_data",	    true },
+			{ "main_changes_with_subprogs",		"does_not_change_pkt_data", false },
+			{ "main_changes",			"main_changes",             true },
+			{ "main_does_not_change",		"main_does_not_change",     false },
+		},
+		{
+			{ "main_might_sleep_with_subprogs",	"might_sleep",		    true },
+			{ "main_might_sleep_with_subprogs",	"does_not_sleep",	    false },
+			{ "main_might_sleep",			"main_might_sleep",	    true },
+			{ "main_does_not_sleep",		"main_does_not_sleep",	    false },
+		},
+	};
+	const char *pkt_err = "Extension program changes packet data";
+	const char *slp_err = "Extension program may sleep";
+	struct {
+		const char *func;
+		bool has_side_effect;
+		const char *err_msg;
+	} replacements[2][2] = {
+		{
+			{ "changes_pkt_data",	      true,	pkt_err },
+			{ "does_not_change_pkt_data", false,	pkt_err },
+		},
+		{
+			{ "might_sleep",	      true,	slp_err },
+			{ "does_not_sleep",	      false,	slp_err },
+		},
+	};
+	char buf[64];
+
+	for (int t = 0; t < 2; t++) {
+		for (int i = 0; i < ARRAY_SIZE(mains); ++i) {
+			for (int j = 0; j < ARRAY_SIZE(replacements); ++j) {
+				snprintf(buf, sizeof(buf), "%s_with_%s",
+					 mains[t][i].to_be_replaced, replacements[t][j].func);
+				if (!test__start_subtest(buf))
+					continue;
+				test_aux(mains[t][i].main, mains[t][i].to_be_replaced, replacements[t][j].func,
+					 mains[t][i].has_side_effect || !replacements[t][j].has_side_effect,
+					 replacements[t][j].err_msg);
+			}
+		}
+	}
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/syscall.c b/tools/testing/selftests/bpf/prog_tests/syscall.c
index f4d40001155a..0be8301c0ffd 100644
--- a/tools/testing/selftests/bpf/prog_tests/syscall.c
+++ b/tools/testing/selftests/bpf/prog_tests/syscall.c
@@ -12,7 +12,7 @@ struct args {
 	int btf_fd;
 };
 
-void test_syscall(void)
+static void test_syscall_load_prog(void)
 {
 	static char verifier_log[8192];
 	struct args ctx = {
@@ -32,7 +32,7 @@ void test_syscall(void)
 	if (!ASSERT_OK_PTR(skel, "skel_load"))
 		goto cleanup;
 
-	prog_fd = bpf_program__fd(skel->progs.bpf_prog);
+	prog_fd = bpf_program__fd(skel->progs.load_prog);
 	err = bpf_prog_test_run_opts(prog_fd, &tattr);
 	ASSERT_EQ(err, 0, "err");
 	ASSERT_EQ(tattr.retval, 1, "retval");
@@ -53,3 +53,29 @@ cleanup:
 	if (ctx.btf_fd > 0)
 		close(ctx.btf_fd);
 }
+
+static void test_syscall_update_outer_map(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	struct syscall *skel;
+	int err, prog_fd;
+
+	skel = syscall__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	prog_fd = bpf_program__fd(skel->progs.update_outer_map);
+	err = bpf_prog_test_run_opts(prog_fd, &opts);
+	ASSERT_EQ(err, 0, "err");
+	ASSERT_EQ(opts.retval, 1, "retval");
+cleanup:
+	syscall__destroy(skel);
+}
+
+void test_syscall(void)
+{
+	if (test__start_subtest("load_prog"))
+		test_syscall_load_prog();
+	if (test__start_subtest("update_outer_map"))
+		test_syscall_update_outer_map();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
index 58fe2c586ed7..0ab36503c3b2 100644
--- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c
+++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
@@ -1,6 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <unistd.h>
 #include <test_progs.h>
 #include <network_helpers.h>
+#include "tailcall_poke.skel.h"
+#include "tailcall_bpf2bpf_hierarchy2.skel.h"
+#include "tailcall_bpf2bpf_hierarchy3.skel.h"
+#include "tailcall_freplace.skel.h"
+#include "tc_bpf2bpf.skel.h"
+#include "tailcall_fail.skel.h"
 
 /* test_tailcall_1 checks basic functionality by patching multiple locations
  * in a single program for a single tail call slot with nop->jmp, jmp->nop
@@ -218,12 +225,14 @@ out:
 	bpf_object__close(obj);
 }
 
-static void test_tailcall_count(const char *which)
+static void test_tailcall_count(const char *which, bool test_fentry,
+				bool test_fexit)
 {
+	struct bpf_object *obj = NULL, *fentry_obj = NULL, *fexit_obj = NULL;
+	struct bpf_link *fentry_link = NULL, *fexit_link = NULL;
 	int err, map_fd, prog_fd, main_fd, data_fd, i, val;
 	struct bpf_map *prog_array, *data_map;
 	struct bpf_program *prog;
-	struct bpf_object *obj;
 	char buff[128] = {};
 	LIBBPF_OPTS(bpf_test_run_opts, topts,
 		.data_in = buff,
@@ -265,23 +274,105 @@ static void test_tailcall_count(const char *which)
 	if (CHECK_FAIL(err))
 		goto out;
 
+	if (test_fentry) {
+		fentry_obj = bpf_object__open_file("tailcall_bpf2bpf_fentry.bpf.o",
+						   NULL);
+		if (!ASSERT_OK_PTR(fentry_obj, "open fentry_obj file"))
+			goto out;
+
+		prog = bpf_object__find_program_by_name(fentry_obj, "fentry");
+		if (!ASSERT_OK_PTR(prog, "find fentry prog"))
+			goto out;
+
+		err = bpf_program__set_attach_target(prog, prog_fd,
+						     "subprog_tail");
+		if (!ASSERT_OK(err, "set_attach_target subprog_tail"))
+			goto out;
+
+		err = bpf_object__load(fentry_obj);
+		if (!ASSERT_OK(err, "load fentry_obj"))
+			goto out;
+
+		fentry_link = bpf_program__attach_trace(prog);
+		if (!ASSERT_OK_PTR(fentry_link, "attach_trace"))
+			goto out;
+	}
+
+	if (test_fexit) {
+		fexit_obj = bpf_object__open_file("tailcall_bpf2bpf_fexit.bpf.o",
+						  NULL);
+		if (!ASSERT_OK_PTR(fexit_obj, "open fexit_obj file"))
+			goto out;
+
+		prog = bpf_object__find_program_by_name(fexit_obj, "fexit");
+		if (!ASSERT_OK_PTR(prog, "find fexit prog"))
+			goto out;
+
+		err = bpf_program__set_attach_target(prog, prog_fd,
+						     "subprog_tail");
+		if (!ASSERT_OK(err, "set_attach_target subprog_tail"))
+			goto out;
+
+		err = bpf_object__load(fexit_obj);
+		if (!ASSERT_OK(err, "load fexit_obj"))
+			goto out;
+
+		fexit_link = bpf_program__attach_trace(prog);
+		if (!ASSERT_OK_PTR(fexit_link, "attach_trace"))
+			goto out;
+	}
+
 	err = bpf_prog_test_run_opts(main_fd, &topts);
 	ASSERT_OK(err, "tailcall");
 	ASSERT_EQ(topts.retval, 1, "tailcall retval");
 
 	data_map = bpf_object__find_map_by_name(obj, "tailcall.bss");
 	if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map)))
-		return;
+		goto out;
 
 	data_fd = bpf_map__fd(data_map);
-	if (CHECK_FAIL(map_fd < 0))
-		return;
+	if (CHECK_FAIL(data_fd < 0))
+		goto out;
 
 	i = 0;
 	err = bpf_map_lookup_elem(data_fd, &i, &val);
 	ASSERT_OK(err, "tailcall count");
 	ASSERT_EQ(val, 33, "tailcall count");
 
+	if (test_fentry) {
+		data_map = bpf_object__find_map_by_name(fentry_obj, ".bss");
+		if (!ASSERT_FALSE(!data_map || !bpf_map__is_internal(data_map),
+				  "find tailcall_bpf2bpf_fentry.bss map"))
+			goto out;
+
+		data_fd = bpf_map__fd(data_map);
+		if (!ASSERT_FALSE(data_fd < 0,
+				  "find tailcall_bpf2bpf_fentry.bss map fd"))
+			goto out;
+
+		i = 0;
+		err = bpf_map_lookup_elem(data_fd, &i, &val);
+		ASSERT_OK(err, "fentry count");
+		ASSERT_EQ(val, 33, "fentry count");
+	}
+
+	if (test_fexit) {
+		data_map = bpf_object__find_map_by_name(fexit_obj, ".bss");
+		if (!ASSERT_FALSE(!data_map || !bpf_map__is_internal(data_map),
+				  "find tailcall_bpf2bpf_fexit.bss map"))
+			goto out;
+
+		data_fd = bpf_map__fd(data_map);
+		if (!ASSERT_FALSE(data_fd < 0,
+				  "find tailcall_bpf2bpf_fexit.bss map fd"))
+			goto out;
+
+		i = 0;
+		err = bpf_map_lookup_elem(data_fd, &i, &val);
+		ASSERT_OK(err, "fexit count");
+		ASSERT_EQ(val, 33, "fexit count");
+	}
+
 	i = 0;
 	err = bpf_map_delete_elem(map_fd, &i);
 	if (CHECK_FAIL(err))
@@ -291,6 +382,10 @@ static void test_tailcall_count(const char *which)
 	ASSERT_OK(err, "tailcall");
 	ASSERT_OK(topts.retval, "tailcall retval");
 out:
+	bpf_link__destroy(fentry_link);
+	bpf_link__destroy(fexit_link);
+	bpf_object__close(fentry_obj);
+	bpf_object__close(fexit_obj);
 	bpf_object__close(obj);
 }
 
@@ -299,7 +394,7 @@ out:
  */
 static void test_tailcall_3(void)
 {
-	test_tailcall_count("tailcall3.bpf.o");
+	test_tailcall_count("tailcall3.bpf.o", false, false);
 }
 
 /* test_tailcall_6 checks that the count value of the tail call limit
@@ -307,7 +402,7 @@ static void test_tailcall_3(void)
  */
 static void test_tailcall_6(void)
 {
-	test_tailcall_count("tailcall6.bpf.o");
+	test_tailcall_count("tailcall6.bpf.o", false, false);
 }
 
 /* test_tailcall_4 checks that the kernel properly selects indirect jump
@@ -352,11 +447,11 @@ static void test_tailcall_4(void)
 
 	data_map = bpf_object__find_map_by_name(obj, "tailcall.bss");
 	if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map)))
-		return;
+		goto out;
 
 	data_fd = bpf_map__fd(data_map);
-	if (CHECK_FAIL(map_fd < 0))
-		return;
+	if (CHECK_FAIL(data_fd < 0))
+		goto out;
 
 	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
 		snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
@@ -442,11 +537,11 @@ static void test_tailcall_5(void)
 
 	data_map = bpf_object__find_map_by_name(obj, "tailcall.bss");
 	if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map)))
-		return;
+		goto out;
 
 	data_fd = bpf_map__fd(data_map);
-	if (CHECK_FAIL(map_fd < 0))
-		return;
+	if (CHECK_FAIL(data_fd < 0))
+		goto out;
 
 	for (i = 0; i < bpf_map__max_entries(prog_array); i++) {
 		snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
@@ -631,11 +726,11 @@ static void test_tailcall_bpf2bpf_2(void)
 
 	data_map = bpf_object__find_map_by_name(obj, "tailcall.bss");
 	if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map)))
-		return;
+		goto out;
 
 	data_fd = bpf_map__fd(data_map);
-	if (CHECK_FAIL(map_fd < 0))
-		return;
+	if (CHECK_FAIL(data_fd < 0))
+		goto out;
 
 	i = 0;
 	err = bpf_map_lookup_elem(data_fd, &i, &val);
@@ -805,11 +900,11 @@ static void test_tailcall_bpf2bpf_4(bool noise)
 
 	data_map = bpf_object__find_map_by_name(obj, "tailcall.bss");
 	if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map)))
-		return;
+		goto out;
 
 	data_fd = bpf_map__fd(data_map);
-	if (CHECK_FAIL(map_fd < 0))
-		return;
+	if (CHECK_FAIL(data_fd < 0))
+		goto out;
 
 	i = 0;
 	val.noise = noise;
@@ -872,7 +967,7 @@ static void test_tailcall_bpf2bpf_6(void)
 	ASSERT_EQ(topts.retval, 0, "tailcall retval");
 
 	data_fd = bpf_map__fd(obj->maps.bss);
-	if (!ASSERT_GE(map_fd, 0, "bss map fd"))
+	if (!ASSERT_GE(data_fd, 0, "bss map fd"))
 		goto out;
 
 	i = 0;
@@ -884,6 +979,680 @@ out:
 	tailcall_bpf2bpf6__destroy(obj);
 }
 
+/* test_tailcall_bpf2bpf_fentry checks that the count value of the tail call
+ * limit enforcement matches with expectations when tailcall is preceded with
+ * bpf2bpf call, and the bpf2bpf call is traced by fentry.
+ */
+static void test_tailcall_bpf2bpf_fentry(void)
+{
+	test_tailcall_count("tailcall_bpf2bpf2.bpf.o", true, false);
+}
+
+/* test_tailcall_bpf2bpf_fexit checks that the count value of the tail call
+ * limit enforcement matches with expectations when tailcall is preceded with
+ * bpf2bpf call, and the bpf2bpf call is traced by fexit.
+ */
+static void test_tailcall_bpf2bpf_fexit(void)
+{
+	test_tailcall_count("tailcall_bpf2bpf2.bpf.o", false, true);
+}
+
+/* test_tailcall_bpf2bpf_fentry_fexit checks that the count value of the tail
+ * call limit enforcement matches with expectations when tailcall is preceded
+ * with bpf2bpf call, and the bpf2bpf call is traced by both fentry and fexit.
+ */
+static void test_tailcall_bpf2bpf_fentry_fexit(void)
+{
+	test_tailcall_count("tailcall_bpf2bpf2.bpf.o", true, true);
+}
+
+/* test_tailcall_bpf2bpf_fentry_entry checks that the count value of the tail
+ * call limit enforcement matches with expectations when tailcall is preceded
+ * with bpf2bpf call, and the bpf2bpf caller is traced by fentry.
+ */
+static void test_tailcall_bpf2bpf_fentry_entry(void)
+{
+	struct bpf_object *tgt_obj = NULL, *fentry_obj = NULL;
+	int err, map_fd, prog_fd, data_fd, i, val;
+	struct bpf_map *prog_array, *data_map;
+	struct bpf_link *fentry_link = NULL;
+	struct bpf_program *prog;
+	char buff[128] = {};
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = buff,
+		.data_size_in = sizeof(buff),
+		.repeat = 1,
+	);
+
+	err = bpf_prog_test_load("tailcall_bpf2bpf2.bpf.o",
+				 BPF_PROG_TYPE_SCHED_CLS,
+				 &tgt_obj, &prog_fd);
+	if (!ASSERT_OK(err, "load tgt_obj"))
+		return;
+
+	prog_array = bpf_object__find_map_by_name(tgt_obj, "jmp_table");
+	if (!ASSERT_OK_PTR(prog_array, "find jmp_table map"))
+		goto out;
+
+	map_fd = bpf_map__fd(prog_array);
+	if (!ASSERT_FALSE(map_fd < 0, "find jmp_table map fd"))
+		goto out;
+
+	prog = bpf_object__find_program_by_name(tgt_obj, "classifier_0");
+	if (!ASSERT_OK_PTR(prog, "find classifier_0 prog"))
+		goto out;
+
+	prog_fd = bpf_program__fd(prog);
+	if (!ASSERT_FALSE(prog_fd < 0, "find classifier_0 prog fd"))
+		goto out;
+
+	i = 0;
+	err = bpf_map_update_elem(map_fd, &i, &prog_fd, BPF_ANY);
+	if (!ASSERT_OK(err, "update jmp_table"))
+		goto out;
+
+	fentry_obj = bpf_object__open_file("tailcall_bpf2bpf_fentry.bpf.o",
+					   NULL);
+	if (!ASSERT_OK_PTR(fentry_obj, "open fentry_obj file"))
+		goto out;
+
+	prog = bpf_object__find_program_by_name(fentry_obj, "fentry");
+	if (!ASSERT_OK_PTR(prog, "find fentry prog"))
+		goto out;
+
+	err = bpf_program__set_attach_target(prog, prog_fd, "classifier_0");
+	if (!ASSERT_OK(err, "set_attach_target classifier_0"))
+		goto out;
+
+	err = bpf_object__load(fentry_obj);
+	if (!ASSERT_OK(err, "load fentry_obj"))
+		goto out;
+
+	fentry_link = bpf_program__attach_trace(prog);
+	if (!ASSERT_OK_PTR(fentry_link, "attach_trace"))
+		goto out;
+
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_EQ(topts.retval, 1, "tailcall retval");
+
+	data_map = bpf_object__find_map_by_name(tgt_obj, "tailcall.bss");
+	if (!ASSERT_FALSE(!data_map || !bpf_map__is_internal(data_map),
+			  "find tailcall.bss map"))
+		goto out;
+
+	data_fd = bpf_map__fd(data_map);
+	if (!ASSERT_FALSE(data_fd < 0, "find tailcall.bss map fd"))
+		goto out;
+
+	i = 0;
+	err = bpf_map_lookup_elem(data_fd, &i, &val);
+	ASSERT_OK(err, "tailcall count");
+	ASSERT_EQ(val, 34, "tailcall count");
+
+	data_map = bpf_object__find_map_by_name(fentry_obj, ".bss");
+	if (!ASSERT_FALSE(!data_map || !bpf_map__is_internal(data_map),
+			  "find tailcall_bpf2bpf_fentry.bss map"))
+		goto out;
+
+	data_fd = bpf_map__fd(data_map);
+	if (!ASSERT_FALSE(data_fd < 0,
+			  "find tailcall_bpf2bpf_fentry.bss map fd"))
+		goto out;
+
+	i = 0;
+	err = bpf_map_lookup_elem(data_fd, &i, &val);
+	ASSERT_OK(err, "fentry count");
+	ASSERT_EQ(val, 1, "fentry count");
+
+out:
+	bpf_link__destroy(fentry_link);
+	bpf_object__close(fentry_obj);
+	bpf_object__close(tgt_obj);
+}
+
+#define JMP_TABLE "/sys/fs/bpf/jmp_table"
+
+static int poke_thread_exit;
+
+static void *poke_update(void *arg)
+{
+	__u32 zero = 0, prog1_fd, prog2_fd, map_fd;
+	struct tailcall_poke *call = arg;
+
+	map_fd = bpf_map__fd(call->maps.jmp_table);
+	prog1_fd = bpf_program__fd(call->progs.call1);
+	prog2_fd = bpf_program__fd(call->progs.call2);
+
+	while (!poke_thread_exit) {
+		bpf_map_update_elem(map_fd, &zero, &prog1_fd, BPF_ANY);
+		bpf_map_update_elem(map_fd, &zero, &prog2_fd, BPF_ANY);
+	}
+
+	return NULL;
+}
+
+/*
+ * We are trying to hit prog array update during another program load
+ * that shares the same prog array map.
+ *
+ * For that we share the jmp_table map between two skeleton instances
+ * by pinning the jmp_table to same path. Then first skeleton instance
+ * periodically updates jmp_table in 'poke update' thread while we load
+ * the second skeleton instance in the main thread.
+ */
+static void test_tailcall_poke(void)
+{
+	struct tailcall_poke *call, *test;
+	int err, cnt = 10;
+	pthread_t thread;
+
+	unlink(JMP_TABLE);
+
+	call = tailcall_poke__open_and_load();
+	if (!ASSERT_OK_PTR(call, "tailcall_poke__open"))
+		return;
+
+	err = bpf_map__pin(call->maps.jmp_table, JMP_TABLE);
+	if (!ASSERT_OK(err, "bpf_map__pin"))
+		goto out;
+
+	err = pthread_create(&thread, NULL, poke_update, call);
+	if (!ASSERT_OK(err, "new toggler"))
+		goto out;
+
+	while (cnt--) {
+		test = tailcall_poke__open();
+		if (!ASSERT_OK_PTR(test, "tailcall_poke__open"))
+			break;
+
+		err = bpf_map__set_pin_path(test->maps.jmp_table, JMP_TABLE);
+		if (!ASSERT_OK(err, "bpf_map__pin")) {
+			tailcall_poke__destroy(test);
+			break;
+		}
+
+		bpf_program__set_autoload(test->progs.test, true);
+		bpf_program__set_autoload(test->progs.call1, false);
+		bpf_program__set_autoload(test->progs.call2, false);
+
+		err = tailcall_poke__load(test);
+		tailcall_poke__destroy(test);
+		if (!ASSERT_OK(err, "tailcall_poke__load"))
+			break;
+	}
+
+	poke_thread_exit = 1;
+	ASSERT_OK(pthread_join(thread, NULL), "pthread_join");
+
+out:
+	bpf_map__unpin(call->maps.jmp_table, JMP_TABLE);
+	tailcall_poke__destroy(call);
+}
+
+static void test_tailcall_hierarchy_count(const char *which, bool test_fentry,
+					  bool test_fexit,
+					  bool test_fentry_entry)
+{
+	int err, map_fd, prog_fd, main_data_fd, fentry_data_fd = 0, fexit_data_fd = 0, i, val;
+	struct bpf_object *obj = NULL, *fentry_obj = NULL, *fexit_obj = NULL;
+	struct bpf_link *fentry_link = NULL, *fexit_link = NULL;
+	struct bpf_program *prog, *fentry_prog;
+	struct bpf_map *prog_array, *data_map;
+	int fentry_prog_fd;
+	char buff[128] = {};
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = buff,
+		.data_size_in = sizeof(buff),
+		.repeat = 1,
+	);
+
+	err = bpf_prog_test_load(which, BPF_PROG_TYPE_SCHED_CLS, &obj,
+				 &prog_fd);
+	if (!ASSERT_OK(err, "load obj"))
+		return;
+
+	prog = bpf_object__find_program_by_name(obj, "entry");
+	if (!ASSERT_OK_PTR(prog, "find entry prog"))
+		goto out;
+
+	prog_fd = bpf_program__fd(prog);
+	if (!ASSERT_GE(prog_fd, 0, "prog_fd"))
+		goto out;
+
+	if (test_fentry_entry) {
+		fentry_obj = bpf_object__open_file("tailcall_bpf2bpf_hierarchy_fentry.bpf.o",
+						   NULL);
+		if (!ASSERT_OK_PTR(fentry_obj, "open fentry_obj file"))
+			goto out;
+
+		fentry_prog = bpf_object__find_program_by_name(fentry_obj,
+							       "fentry");
+		if (!ASSERT_OK_PTR(prog, "find fentry prog"))
+			goto out;
+
+		err = bpf_program__set_attach_target(fentry_prog, prog_fd,
+						     "entry");
+		if (!ASSERT_OK(err, "set_attach_target entry"))
+			goto out;
+
+		err = bpf_object__load(fentry_obj);
+		if (!ASSERT_OK(err, "load fentry_obj"))
+			goto out;
+
+		fentry_link = bpf_program__attach_trace(fentry_prog);
+		if (!ASSERT_OK_PTR(fentry_link, "attach_trace"))
+			goto out;
+
+		fentry_prog_fd = bpf_program__fd(fentry_prog);
+		if (!ASSERT_GE(fentry_prog_fd, 0, "fentry_prog_fd"))
+			goto out;
+
+		prog_array = bpf_object__find_map_by_name(fentry_obj, "jmp_table");
+		if (!ASSERT_OK_PTR(prog_array, "find jmp_table"))
+			goto out;
+
+		map_fd = bpf_map__fd(prog_array);
+		if (!ASSERT_GE(map_fd, 0, "map_fd"))
+			goto out;
+
+		i = 0;
+		err = bpf_map_update_elem(map_fd, &i, &fentry_prog_fd, BPF_ANY);
+		if (!ASSERT_OK(err, "update jmp_table"))
+			goto out;
+
+		data_map = bpf_object__find_map_by_name(fentry_obj, ".bss");
+		if (!ASSERT_FALSE(!data_map || !bpf_map__is_internal(data_map),
+				  "find data_map"))
+			goto out;
+
+	} else {
+		prog_array = bpf_object__find_map_by_name(obj, "jmp_table");
+		if (!ASSERT_OK_PTR(prog_array, "find jmp_table"))
+			goto out;
+
+		map_fd = bpf_map__fd(prog_array);
+		if (!ASSERT_GE(map_fd, 0, "map_fd"))
+			goto out;
+
+		i = 0;
+		err = bpf_map_update_elem(map_fd, &i, &prog_fd, BPF_ANY);
+		if (!ASSERT_OK(err, "update jmp_table"))
+			goto out;
+
+		data_map = bpf_object__find_map_by_name(obj, ".bss");
+		if (!ASSERT_FALSE(!data_map || !bpf_map__is_internal(data_map),
+				  "find data_map"))
+			goto out;
+	}
+
+	if (test_fentry) {
+		fentry_obj = bpf_object__open_file("tailcall_bpf2bpf_fentry.bpf.o",
+						   NULL);
+		if (!ASSERT_OK_PTR(fentry_obj, "open fentry_obj file"))
+			goto out;
+
+		prog = bpf_object__find_program_by_name(fentry_obj, "fentry");
+		if (!ASSERT_OK_PTR(prog, "find fentry prog"))
+			goto out;
+
+		err = bpf_program__set_attach_target(prog, prog_fd,
+						     "subprog_tail");
+		if (!ASSERT_OK(err, "set_attach_target subprog_tail"))
+			goto out;
+
+		err = bpf_object__load(fentry_obj);
+		if (!ASSERT_OK(err, "load fentry_obj"))
+			goto out;
+
+		fentry_link = bpf_program__attach_trace(prog);
+		if (!ASSERT_OK_PTR(fentry_link, "attach_trace"))
+			goto out;
+	}
+
+	if (test_fexit) {
+		fexit_obj = bpf_object__open_file("tailcall_bpf2bpf_fexit.bpf.o",
+						  NULL);
+		if (!ASSERT_OK_PTR(fexit_obj, "open fexit_obj file"))
+			goto out;
+
+		prog = bpf_object__find_program_by_name(fexit_obj, "fexit");
+		if (!ASSERT_OK_PTR(prog, "find fexit prog"))
+			goto out;
+
+		err = bpf_program__set_attach_target(prog, prog_fd,
+						     "subprog_tail");
+		if (!ASSERT_OK(err, "set_attach_target subprog_tail"))
+			goto out;
+
+		err = bpf_object__load(fexit_obj);
+		if (!ASSERT_OK(err, "load fexit_obj"))
+			goto out;
+
+		fexit_link = bpf_program__attach_trace(prog);
+		if (!ASSERT_OK_PTR(fexit_link, "attach_trace"))
+			goto out;
+	}
+
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_EQ(topts.retval, 1, "tailcall retval");
+
+	main_data_fd = bpf_map__fd(data_map);
+	if (!ASSERT_GE(main_data_fd, 0, "main_data_fd"))
+		goto out;
+
+	i = 0;
+	err = bpf_map_lookup_elem(main_data_fd, &i, &val);
+	ASSERT_OK(err, "tailcall count");
+	ASSERT_EQ(val, 34, "tailcall count");
+
+	if (test_fentry) {
+		data_map = bpf_object__find_map_by_name(fentry_obj, ".bss");
+		if (!ASSERT_FALSE(!data_map || !bpf_map__is_internal(data_map),
+				  "find tailcall_bpf2bpf_fentry.bss map"))
+			goto out;
+
+		fentry_data_fd = bpf_map__fd(data_map);
+		if (!ASSERT_GE(fentry_data_fd, 0,
+				  "find tailcall_bpf2bpf_fentry.bss map fd"))
+			goto out;
+
+		i = 0;
+		err = bpf_map_lookup_elem(fentry_data_fd, &i, &val);
+		ASSERT_OK(err, "fentry count");
+		ASSERT_EQ(val, 68, "fentry count");
+	}
+
+	if (test_fexit) {
+		data_map = bpf_object__find_map_by_name(fexit_obj, ".bss");
+		if (!ASSERT_FALSE(!data_map || !bpf_map__is_internal(data_map),
+				  "find tailcall_bpf2bpf_fexit.bss map"))
+			goto out;
+
+		fexit_data_fd = bpf_map__fd(data_map);
+		if (!ASSERT_GE(fexit_data_fd, 0,
+				  "find tailcall_bpf2bpf_fexit.bss map fd"))
+			goto out;
+
+		i = 0;
+		err = bpf_map_lookup_elem(fexit_data_fd, &i, &val);
+		ASSERT_OK(err, "fexit count");
+		ASSERT_EQ(val, 68, "fexit count");
+	}
+
+	i = 0;
+	err = bpf_map_delete_elem(map_fd, &i);
+	if (!ASSERT_OK(err, "delete_elem from jmp_table"))
+		goto out;
+
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "tailcall");
+	ASSERT_EQ(topts.retval, 1, "tailcall retval");
+
+	i = 0;
+	err = bpf_map_lookup_elem(main_data_fd, &i, &val);
+	ASSERT_OK(err, "tailcall count");
+	ASSERT_EQ(val, 35, "tailcall count");
+
+	if (test_fentry) {
+		i = 0;
+		err = bpf_map_lookup_elem(fentry_data_fd, &i, &val);
+		ASSERT_OK(err, "fentry count");
+		ASSERT_EQ(val, 70, "fentry count");
+	}
+
+	if (test_fexit) {
+		i = 0;
+		err = bpf_map_lookup_elem(fexit_data_fd, &i, &val);
+		ASSERT_OK(err, "fexit count");
+		ASSERT_EQ(val, 70, "fexit count");
+	}
+
+out:
+	bpf_link__destroy(fentry_link);
+	bpf_link__destroy(fexit_link);
+	bpf_object__close(fentry_obj);
+	bpf_object__close(fexit_obj);
+	bpf_object__close(obj);
+}
+
+/* test_tailcall_bpf2bpf_hierarchy_1 checks that the count value of the tail
+ * call limit enforcement matches with expectations when tailcalls are preceded
+ * with two bpf2bpf calls.
+ *
+ *         subprog --tailcall-> entry
+ * entry <
+ *         subprog --tailcall-> entry
+ */
+static void test_tailcall_bpf2bpf_hierarchy_1(void)
+{
+	test_tailcall_hierarchy_count("tailcall_bpf2bpf_hierarchy1.bpf.o",
+				      false, false, false);
+}
+
+/* test_tailcall_bpf2bpf_hierarchy_fentry checks that the count value of the
+ * tail call limit enforcement matches with expectations when tailcalls are
+ * preceded with two bpf2bpf calls, and the two subprogs are traced by fentry.
+ */
+static void test_tailcall_bpf2bpf_hierarchy_fentry(void)
+{
+	test_tailcall_hierarchy_count("tailcall_bpf2bpf_hierarchy1.bpf.o",
+				      true, false, false);
+}
+
+/* test_tailcall_bpf2bpf_hierarchy_fexit checks that the count value of the tail
+ * call limit enforcement matches with expectations when tailcalls are preceded
+ * with two bpf2bpf calls, and the two subprogs are traced by fexit.
+ */
+static void test_tailcall_bpf2bpf_hierarchy_fexit(void)
+{
+	test_tailcall_hierarchy_count("tailcall_bpf2bpf_hierarchy1.bpf.o",
+				      false, true, false);
+}
+
+/* test_tailcall_bpf2bpf_hierarchy_fentry_fexit checks that the count value of
+ * the tail call limit enforcement matches with expectations when tailcalls are
+ * preceded with two bpf2bpf calls, and the two subprogs are traced by both
+ * fentry and fexit.
+ */
+static void test_tailcall_bpf2bpf_hierarchy_fentry_fexit(void)
+{
+	test_tailcall_hierarchy_count("tailcall_bpf2bpf_hierarchy1.bpf.o",
+				      true, true, false);
+}
+
+/* test_tailcall_bpf2bpf_hierarchy_fentry_entry checks that the count value of
+ * the tail call limit enforcement matches with expectations when tailcalls are
+ * preceded with two bpf2bpf calls in fentry.
+ */
+static void test_tailcall_bpf2bpf_hierarchy_fentry_entry(void)
+{
+	test_tailcall_hierarchy_count("tc_dummy.bpf.o", false, false, true);
+}
+
+/* test_tailcall_bpf2bpf_hierarchy_2 checks that the count value of the tail
+ * call limit enforcement matches with expectations:
+ *
+ *         subprog_tail0 --tailcall-> classifier_0 -> subprog_tail0
+ * entry <
+ *         subprog_tail1 --tailcall-> classifier_1 -> subprog_tail1
+ */
+static void test_tailcall_bpf2bpf_hierarchy_2(void)
+{
+	RUN_TESTS(tailcall_bpf2bpf_hierarchy2);
+}
+
+/* test_tailcall_bpf2bpf_hierarchy_3 checks that the count value of the tail
+ * call limit enforcement matches with expectations:
+ *
+ *                                   subprog with jmp_table0 to classifier_0
+ * entry --tailcall-> classifier_0 <
+ *                                   subprog with jmp_table1 to classifier_0
+ */
+static void test_tailcall_bpf2bpf_hierarchy_3(void)
+{
+	RUN_TESTS(tailcall_bpf2bpf_hierarchy3);
+}
+
+/* test_tailcall_freplace checks that the freplace prog fails to update the
+ * prog_array map, no matter whether the freplace prog attaches to its target.
+ */
+static void test_tailcall_freplace(void)
+{
+	struct tailcall_freplace *freplace_skel = NULL;
+	struct bpf_link *freplace_link = NULL;
+	struct bpf_program *freplace_prog;
+	struct tc_bpf2bpf *tc_skel = NULL;
+	int prog_fd, tc_prog_fd, map_fd;
+	char buff[128] = {};
+	int err, key;
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		    .data_in = buff,
+		    .data_size_in = sizeof(buff),
+		    .repeat = 1,
+	);
+
+	freplace_skel = tailcall_freplace__open();
+	if (!ASSERT_OK_PTR(freplace_skel, "tailcall_freplace__open"))
+		return;
+
+	tc_skel = tc_bpf2bpf__open_and_load();
+	if (!ASSERT_OK_PTR(tc_skel, "tc_bpf2bpf__open_and_load"))
+		goto out;
+
+	tc_prog_fd = bpf_program__fd(tc_skel->progs.entry_tc);
+	freplace_prog = freplace_skel->progs.entry_freplace;
+	err = bpf_program__set_attach_target(freplace_prog, tc_prog_fd,
+					     "subprog_tc");
+	if (!ASSERT_OK(err, "set_attach_target"))
+		goto out;
+
+	err = tailcall_freplace__load(freplace_skel);
+	if (!ASSERT_OK(err, "tailcall_freplace__load"))
+		goto out;
+
+	map_fd = bpf_map__fd(freplace_skel->maps.jmp_table);
+	prog_fd = bpf_program__fd(freplace_prog);
+	key = 0;
+	err = bpf_map_update_elem(map_fd, &key, &prog_fd, BPF_ANY);
+	ASSERT_ERR(err, "update jmp_table failure");
+
+	freplace_link = bpf_program__attach_freplace(freplace_prog, tc_prog_fd,
+						     "subprog_tc");
+	if (!ASSERT_OK_PTR(freplace_link, "attach_freplace"))
+		goto out;
+
+	err = bpf_map_update_elem(map_fd, &key, &prog_fd, BPF_ANY);
+	ASSERT_ERR(err, "update jmp_table failure");
+
+out:
+	bpf_link__destroy(freplace_link);
+	tailcall_freplace__destroy(freplace_skel);
+	tc_bpf2bpf__destroy(tc_skel);
+}
+
+/* test_tailcall_bpf2bpf_freplace checks the failure that fails to attach a tail
+ * callee prog with freplace prog or fails to update an extended prog to
+ * prog_array map.
+ */
+static void test_tailcall_bpf2bpf_freplace(void)
+{
+	struct tailcall_freplace *freplace_skel = NULL;
+	struct bpf_link *freplace_link = NULL;
+	struct tc_bpf2bpf *tc_skel = NULL;
+	char buff[128] = {};
+	int prog_fd, map_fd;
+	int err, key;
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		    .data_in = buff,
+		    .data_size_in = sizeof(buff),
+		    .repeat = 1,
+	);
+
+	tc_skel = tc_bpf2bpf__open_and_load();
+	if (!ASSERT_OK_PTR(tc_skel, "tc_bpf2bpf__open_and_load"))
+		goto out;
+
+	prog_fd = bpf_program__fd(tc_skel->progs.entry_tc);
+	freplace_skel = tailcall_freplace__open();
+	if (!ASSERT_OK_PTR(freplace_skel, "tailcall_freplace__open"))
+		goto out;
+
+	err = bpf_program__set_attach_target(freplace_skel->progs.entry_freplace,
+					     prog_fd, "subprog_tc");
+	if (!ASSERT_OK(err, "set_attach_target"))
+		goto out;
+
+	err = tailcall_freplace__load(freplace_skel);
+	if (!ASSERT_OK(err, "tailcall_freplace__load"))
+		goto out;
+
+	/* OK to attach then detach freplace prog. */
+
+	freplace_link = bpf_program__attach_freplace(freplace_skel->progs.entry_freplace,
+						     prog_fd, "subprog_tc");
+	if (!ASSERT_OK_PTR(freplace_link, "attach_freplace"))
+		goto out;
+
+	err = bpf_link__destroy(freplace_link);
+	freplace_link = NULL;
+	if (!ASSERT_OK(err, "destroy link"))
+		goto out;
+
+	/* OK to update prog_array map then delete element from the map. */
+
+	key = 0;
+	map_fd = bpf_map__fd(freplace_skel->maps.jmp_table);
+	err = bpf_map_update_elem(map_fd, &key, &prog_fd, BPF_ANY);
+	if (!ASSERT_OK(err, "update jmp_table"))
+		goto out;
+
+	err = bpf_map_delete_elem(map_fd, &key);
+	if (!ASSERT_OK(err, "delete_elem from jmp_table"))
+		goto out;
+
+	/* Fail to attach a tail callee prog with freplace prog. */
+
+	err = bpf_map_update_elem(map_fd, &key, &prog_fd, BPF_ANY);
+	if (!ASSERT_OK(err, "update jmp_table"))
+		goto out;
+
+	freplace_link = bpf_program__attach_freplace(freplace_skel->progs.entry_freplace,
+						     prog_fd, "subprog_tc");
+	if (!ASSERT_ERR_PTR(freplace_link, "attach_freplace failure"))
+		goto out;
+
+	err = bpf_map_delete_elem(map_fd, &key);
+	if (!ASSERT_OK(err, "delete_elem from jmp_table"))
+		goto out;
+
+	/* Fail to update an extended prog to prog_array map. */
+
+	freplace_link = bpf_program__attach_freplace(freplace_skel->progs.entry_freplace,
+						     prog_fd, "subprog_tc");
+	if (!ASSERT_OK_PTR(freplace_link, "attach_freplace"))
+		goto out;
+
+	err = bpf_map_update_elem(map_fd, &key, &prog_fd, BPF_ANY);
+	if (!ASSERT_ERR(err, "update jmp_table failure"))
+		goto out;
+
+out:
+	bpf_link__destroy(freplace_link);
+	tailcall_freplace__destroy(freplace_skel);
+	tc_bpf2bpf__destroy(tc_skel);
+}
+
+static void test_tailcall_failure()
+{
+	RUN_TESTS(tailcall_fail);
+}
+
 void test_tailcalls(void)
 {
 	if (test__start_subtest("tailcall_1"))
@@ -910,4 +1679,32 @@ void test_tailcalls(void)
 		test_tailcall_bpf2bpf_4(true);
 	if (test__start_subtest("tailcall_bpf2bpf_6"))
 		test_tailcall_bpf2bpf_6();
+	if (test__start_subtest("tailcall_bpf2bpf_fentry"))
+		test_tailcall_bpf2bpf_fentry();
+	if (test__start_subtest("tailcall_bpf2bpf_fexit"))
+		test_tailcall_bpf2bpf_fexit();
+	if (test__start_subtest("tailcall_bpf2bpf_fentry_fexit"))
+		test_tailcall_bpf2bpf_fentry_fexit();
+	if (test__start_subtest("tailcall_bpf2bpf_fentry_entry"))
+		test_tailcall_bpf2bpf_fentry_entry();
+	if (test__start_subtest("tailcall_poke"))
+		test_tailcall_poke();
+	if (test__start_subtest("tailcall_bpf2bpf_hierarchy_1"))
+		test_tailcall_bpf2bpf_hierarchy_1();
+	if (test__start_subtest("tailcall_bpf2bpf_hierarchy_fentry"))
+		test_tailcall_bpf2bpf_hierarchy_fentry();
+	if (test__start_subtest("tailcall_bpf2bpf_hierarchy_fexit"))
+		test_tailcall_bpf2bpf_hierarchy_fexit();
+	if (test__start_subtest("tailcall_bpf2bpf_hierarchy_fentry_fexit"))
+		test_tailcall_bpf2bpf_hierarchy_fentry_fexit();
+	if (test__start_subtest("tailcall_bpf2bpf_hierarchy_fentry_entry"))
+		test_tailcall_bpf2bpf_hierarchy_fentry_entry();
+	test_tailcall_bpf2bpf_hierarchy_2();
+	test_tailcall_bpf2bpf_hierarchy_3();
+	if (test__start_subtest("tailcall_freplace"))
+		test_tailcall_freplace();
+	if (test__start_subtest("tailcall_bpf2bpf_freplace"))
+		test_tailcall_bpf2bpf_freplace();
+	if (test__start_subtest("tailcall_failure"))
+		test_tailcall_failure();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/task_fd_query_tp.c b/tools/testing/selftests/bpf/prog_tests/task_fd_query_tp.c
index c717741bf8b6..c91eda624657 100644
--- a/tools/testing/selftests/bpf/prog_tests/task_fd_query_tp.c
+++ b/tools/testing/selftests/bpf/prog_tests/task_fd_query_tp.c
@@ -17,8 +17,13 @@ static void test_task_fd_query_tp_core(const char *probe_name,
 	if (CHECK(err, "bpf_prog_test_load", "err %d errno %d\n", err, errno))
 		goto close_prog;
 
-	snprintf(buf, sizeof(buf),
-		 "/sys/kernel/debug/tracing/events/%s/id", probe_name);
+	if (access("/sys/kernel/tracing/trace", F_OK) == 0) {
+		snprintf(buf, sizeof(buf),
+			 "/sys/kernel/tracing/events/%s/id", probe_name);
+	} else {
+		snprintf(buf, sizeof(buf),
+			 "/sys/kernel/debug/tracing/events/%s/id", probe_name);
+	}
 	efd = open(buf, O_RDONLY, 0);
 	if (CHECK(efd < 0, "open", "err %d errno %d\n", efd, errno))
 		goto close_prog;
diff --git a/tools/testing/selftests/bpf/prog_tests/task_kfunc.c b/tools/testing/selftests/bpf/prog_tests/task_kfunc.c
index 18848c31e36f..83b90335967a 100644
--- a/tools/testing/selftests/bpf/prog_tests/task_kfunc.c
+++ b/tools/testing/selftests/bpf/prog_tests/task_kfunc.c
@@ -9,9 +9,6 @@
 #include "task_kfunc_failure.skel.h"
 #include "task_kfunc_success.skel.h"
 
-static size_t log_buf_sz = 1 << 20; /* 1 MB */
-static char obj_log_buf[1048576];
-
 static struct task_kfunc_success *open_load_task_kfunc_skel(void)
 {
 	struct task_kfunc_success *skel;
@@ -71,79 +68,94 @@ cleanup:
 	task_kfunc_success__destroy(skel);
 }
 
-static const char * const success_tests[] = {
-	"test_task_acquire_release_argument",
-	"test_task_acquire_release_current",
-	"test_task_acquire_leave_in_map",
-	"test_task_xchg_release",
-	"test_task_get_release",
-	"test_task_current_acquire_release",
-	"test_task_from_pid_arg",
-	"test_task_from_pid_current",
-	"test_task_from_pid_invalid",
-};
-
-static struct {
-	const char *prog_name;
-	const char *expected_err_msg;
-} failure_tests[] = {
-	{"task_kfunc_acquire_untrusted", "R1 must be referenced or trusted"},
-	{"task_kfunc_acquire_fp", "arg#0 pointer type STRUCT task_struct must point"},
-	{"task_kfunc_acquire_unsafe_kretprobe", "reg type unsupported for arg#0 function"},
-	{"task_kfunc_acquire_trusted_walked", "R1 must be referenced or trusted"},
-	{"task_kfunc_acquire_null", "arg#0 pointer type STRUCT task_struct must point"},
-	{"task_kfunc_acquire_unreleased", "Unreleased reference"},
-	{"task_kfunc_get_non_kptr_param", "arg#0 expected pointer to map value"},
-	{"task_kfunc_get_non_kptr_acquired", "arg#0 expected pointer to map value"},
-	{"task_kfunc_get_null", "arg#0 expected pointer to map value"},
-	{"task_kfunc_xchg_unreleased", "Unreleased reference"},
-	{"task_kfunc_get_unreleased", "Unreleased reference"},
-	{"task_kfunc_release_untrusted", "arg#0 is untrusted_ptr_or_null_ expected ptr_ or socket"},
-	{"task_kfunc_release_fp", "arg#0 pointer type STRUCT task_struct must point"},
-	{"task_kfunc_release_null", "arg#0 is ptr_or_null_ expected ptr_ or socket"},
-	{"task_kfunc_release_unacquired", "release kernel function bpf_task_release expects"},
-	{"task_kfunc_from_pid_no_null_check", "arg#0 is ptr_or_null_ expected ptr_ or socket"},
-	{"task_kfunc_from_lsm_task_free", "reg type unsupported for arg#0 function"},
-};
-
-static void verify_fail(const char *prog_name, const char *expected_err_msg)
+static int run_vpid_test(void *prog_name)
 {
-	LIBBPF_OPTS(bpf_object_open_opts, opts);
-	struct task_kfunc_failure *skel;
-	int err, i;
+	struct task_kfunc_success *skel;
+	struct bpf_program *prog;
+	int prog_fd, err = 0;
 
-	opts.kernel_log_buf = obj_log_buf;
-	opts.kernel_log_size = log_buf_sz;
-	opts.kernel_log_level = 1;
+	if (getpid() != 1)
+		return 1;
 
-	skel = task_kfunc_failure__open_opts(&opts);
-	if (!ASSERT_OK_PTR(skel, "task_kfunc_failure__open_opts"))
+	skel = open_load_task_kfunc_skel();
+	if (!skel)
+		return 2;
+
+	if (skel->bss->err) {
+		err = 3;
 		goto cleanup;
+	}
 
-	for (i = 0; i < ARRAY_SIZE(failure_tests); i++) {
-		struct bpf_program *prog;
-		const char *curr_name = failure_tests[i].prog_name;
+	prog = bpf_object__find_program_by_name(skel->obj, prog_name);
+	if (!prog) {
+		err = 4;
+		goto cleanup;
+	}
 
-		prog = bpf_object__find_program_by_name(skel->obj, curr_name);
-		if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
-			goto cleanup;
+	prog_fd = bpf_program__fd(prog);
+	if (prog_fd < 0) {
+		err = 5;
+		goto cleanup;
+	}
 
-		bpf_program__set_autoload(prog, !strcmp(curr_name, prog_name));
+	if (bpf_prog_test_run_opts(prog_fd, NULL)) {
+		err = 6;
+		goto cleanup;
 	}
 
-	err = task_kfunc_failure__load(skel);
-	if (!ASSERT_ERR(err, "unexpected load success"))
+	if (skel->bss->err)
+		err = 7 + skel->bss->err;
+cleanup:
+	task_kfunc_success__destroy(skel);
+	return err;
+}
+
+static void run_vpid_success_test(const char *prog_name)
+{
+	const int stack_size = 1024 * 1024;
+	int child_pid, wstatus;
+	char *stack;
+
+	stack = (char *)malloc(stack_size);
+	if (!ASSERT_OK_PTR(stack, "clone_stack"))
+		return;
+
+	child_pid = clone(run_vpid_test, stack + stack_size,
+			  CLONE_NEWPID | SIGCHLD, (void *)prog_name);
+	if (!ASSERT_GT(child_pid, -1, "child_pid"))
 		goto cleanup;
 
-	if (!ASSERT_OK_PTR(strstr(obj_log_buf, expected_err_msg), "expected_err_msg")) {
-		fprintf(stderr, "Expected err_msg: %s\n", expected_err_msg);
-		fprintf(stderr, "Verifier output: %s\n", obj_log_buf);
-	}
+	if (!ASSERT_GT(waitpid(child_pid, &wstatus, 0), -1, "waitpid"))
+		goto cleanup;
 
+	if (WEXITSTATUS(wstatus) > 7)
+		ASSERT_OK(WEXITSTATUS(wstatus) - 7, "vpid_test_failure");
+	else
+		ASSERT_OK(WEXITSTATUS(wstatus), "run_vpid_test_err");
 cleanup:
-	task_kfunc_failure__destroy(skel);
+	free(stack);
 }
 
+static const char * const success_tests[] = {
+	"test_task_acquire_release_argument",
+	"test_task_acquire_release_current",
+	"test_task_acquire_leave_in_map",
+	"test_task_xchg_release",
+	"test_task_map_acquire_release",
+	"test_task_current_acquire_release",
+	"test_task_from_pid_arg",
+	"test_task_from_pid_current",
+	"test_task_from_pid_invalid",
+	"task_kfunc_acquire_trusted_walked",
+	"test_task_kfunc_flavor_relo",
+	"test_task_kfunc_flavor_relo_not_found",
+};
+
+static const char * const vpid_success_tests[] = {
+	"test_task_from_vpid_current",
+	"test_task_from_vpid_invalid",
+};
+
 void test_task_kfunc(void)
 {
 	int i;
@@ -155,10 +167,12 @@ void test_task_kfunc(void)
 		run_success_test(success_tests[i]);
 	}
 
-	for (i = 0; i < ARRAY_SIZE(failure_tests); i++) {
-		if (!test__start_subtest(failure_tests[i].prog_name))
+	for (i = 0; i < ARRAY_SIZE(vpid_success_tests); i++) {
+		if (!test__start_subtest(vpid_success_tests[i]))
 			continue;
 
-		verify_fail(failure_tests[i].prog_name, failure_tests[i].expected_err_msg);
+		run_vpid_success_test(vpid_success_tests[i]);
 	}
+
+	RUN_TESTS(task_kfunc_failure);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/task_local_data.h b/tools/testing/selftests/bpf/prog_tests/task_local_data.h
new file mode 100644
index 000000000000..2de38776a2d4
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/task_local_data.h
@@ -0,0 +1,386 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TASK_LOCAL_DATA_H
+#define __TASK_LOCAL_DATA_H
+
+#include <errno.h>
+#include <fcntl.h>
+#include <sched.h>
+#include <stdatomic.h>
+#include <stddef.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+
+#ifdef TLD_FREE_DATA_ON_THREAD_EXIT
+#include <pthread.h>
+#endif
+
+#include <bpf/bpf.h>
+
+/*
+ * OPTIONS
+ *
+ *   Define the option before including the header
+ *
+ *   TLD_FREE_DATA_ON_THREAD_EXIT - Frees memory on thread exit automatically
+ *
+ *   Thread-specific memory for storing TLD is allocated lazily on the first call to
+ *   tld_get_data(). The thread that calls it must also call tld_free() on thread exit
+ *   to prevent memory leak. Pthread will be included if the option is defined. A pthread
+ *   key will be registered with a destructor that calls tld_free().
+ *
+ *
+ *   TLD_DYN_DATA_SIZE - The maximum size of memory allocated for TLDs created dynamically
+ *   (default: 64 bytes)
+ *
+ *   A TLD can be defined statically using TLD_DEFINE_KEY() or created on the fly using
+ *   tld_create_key(). As the total size of TLDs created with tld_create_key() cannot be
+ *   possibly known statically, a memory area of size TLD_DYN_DATA_SIZE will be allocated
+ *   for these TLDs. This additional memory is allocated for every thread that calls
+ *   tld_get_data() even if no tld_create_key are actually called, so be mindful of
+ *   potential memory wastage. Use TLD_DEFINE_KEY() whenever possible as just enough memory
+ *   will be allocated for TLDs created with it.
+ *
+ *
+ *   TLD_NAME_LEN - The maximum length of the name of a TLD (default: 62)
+ *
+ *   Setting TLD_NAME_LEN will affect the maximum number of TLDs a process can store,
+ *   TLD_MAX_DATA_CNT.
+ *
+ *
+ *   TLD_DATA_USE_ALIGNED_ALLOC - Always use aligned_alloc() instead of malloc()
+ *
+ *   When allocating the memory for storing TLDs, we need to make sure there is a memory
+ *   region of the X bytes within a page. This is due to the limit posed by UPTR: memory
+ *   pinned to the kernel cannot exceed a page nor can it cross the page boundary. The
+ *   library normally calls malloc(2*X) given X bytes of total TLDs, and only uses
+ *   aligned_alloc(PAGE_SIZE, X) when X >= PAGE_SIZE / 2. This is to reduce memory wastage
+ *   as not all memory allocator can use the exact amount of memory requested to fulfill
+ *   aligned_alloc(). For example, some may round the size up to the alignment. Enable the
+ *   option to always use aligned_alloc() if the implementation has low memory overhead.
+ */
+
+#define TLD_PAGE_SIZE getpagesize()
+#define TLD_PAGE_MASK (~(TLD_PAGE_SIZE - 1))
+
+#define TLD_ROUND_MASK(x, y) ((__typeof__(x))((y) - 1))
+#define TLD_ROUND_UP(x, y) ((((x) - 1) | TLD_ROUND_MASK(x, y)) + 1)
+
+#define TLD_READ_ONCE(x) (*(volatile typeof(x) *)&(x))
+
+#ifndef TLD_DYN_DATA_SIZE
+#define TLD_DYN_DATA_SIZE 64
+#endif
+
+#define TLD_MAX_DATA_CNT (TLD_PAGE_SIZE / sizeof(struct tld_metadata) - 1)
+
+#ifndef TLD_NAME_LEN
+#define TLD_NAME_LEN 62
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+typedef struct {
+	__s16 off;
+} tld_key_t;
+
+struct tld_metadata {
+	char name[TLD_NAME_LEN];
+	_Atomic __u16 size;
+};
+
+struct tld_meta_u {
+	_Atomic __u8 cnt;
+	__u16 size;
+	struct tld_metadata metadata[];
+};
+
+struct tld_data_u {
+	__u64 start; /* offset of tld_data_u->data in a page */
+	char data[];
+};
+
+struct tld_map_value {
+	void *data;
+	struct tld_meta_u *meta;
+};
+
+struct tld_meta_u * _Atomic tld_meta_p __attribute__((weak));
+__thread struct tld_data_u *tld_data_p __attribute__((weak));
+__thread void *tld_data_alloc_p __attribute__((weak));
+
+#ifdef TLD_FREE_DATA_ON_THREAD_EXIT
+pthread_key_t tld_pthread_key __attribute__((weak));
+
+static void tld_free(void);
+
+static void __tld_thread_exit_handler(void *unused)
+{
+	tld_free();
+}
+#endif
+
+static int __tld_init_meta_p(void)
+{
+	struct tld_meta_u *meta, *uninit = NULL;
+	int err = 0;
+
+	meta = (struct tld_meta_u *)aligned_alloc(TLD_PAGE_SIZE, TLD_PAGE_SIZE);
+	if (!meta) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	memset(meta, 0, TLD_PAGE_SIZE);
+	meta->size = TLD_DYN_DATA_SIZE;
+
+	if (!atomic_compare_exchange_strong(&tld_meta_p, &uninit, meta)) {
+		free(meta);
+		goto out;
+	}
+
+#ifdef TLD_FREE_DATA_ON_THREAD_EXIT
+	pthread_key_create(&tld_pthread_key, __tld_thread_exit_handler);
+#endif
+out:
+	return err;
+}
+
+static int __tld_init_data_p(int map_fd)
+{
+	bool use_aligned_alloc = false;
+	struct tld_map_value map_val;
+	struct tld_data_u *data;
+	void *data_alloc = NULL;
+	int err, tid_fd = -1;
+
+	tid_fd = syscall(SYS_pidfd_open, sys_gettid(), O_EXCL);
+	if (tid_fd < 0) {
+		err = -errno;
+		goto out;
+	}
+
+#ifdef TLD_DATA_USE_ALIGNED_ALLOC
+	use_aligned_alloc = true;
+#endif
+
+	/*
+	 * tld_meta_p->size = TLD_DYN_DATA_SIZE +
+	 *          total size of TLDs defined via TLD_DEFINE_KEY()
+	 */
+	data_alloc = (use_aligned_alloc || tld_meta_p->size * 2 >= TLD_PAGE_SIZE) ?
+		aligned_alloc(TLD_PAGE_SIZE, tld_meta_p->size) :
+		malloc(tld_meta_p->size * 2);
+	if (!data_alloc) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	/*
+	 * Always pass a page-aligned address to UPTR since the size of tld_map_value::data
+	 * is a page in BTF. If data_alloc spans across two pages, use the page that contains large
+	 * enough memory.
+	 */
+	if (TLD_PAGE_SIZE - (~TLD_PAGE_MASK & (intptr_t)data_alloc) >= tld_meta_p->size) {
+		map_val.data = (void *)(TLD_PAGE_MASK & (intptr_t)data_alloc);
+		data = data_alloc;
+		data->start = (~TLD_PAGE_MASK & (intptr_t)data_alloc) +
+			      offsetof(struct tld_data_u, data);
+	} else {
+		map_val.data = (void *)(TLD_ROUND_UP((intptr_t)data_alloc, TLD_PAGE_SIZE));
+		data = (void *)(TLD_ROUND_UP((intptr_t)data_alloc, TLD_PAGE_SIZE));
+		data->start = offsetof(struct tld_data_u, data);
+	}
+	map_val.meta = TLD_READ_ONCE(tld_meta_p);
+
+	err = bpf_map_update_elem(map_fd, &tid_fd, &map_val, 0);
+	if (err) {
+		free(data_alloc);
+		goto out;
+	}
+
+	tld_data_p = data;
+	tld_data_alloc_p = data_alloc;
+#ifdef TLD_FREE_DATA_ON_THREAD_EXIT
+	pthread_setspecific(tld_pthread_key, (void *)1);
+#endif
+out:
+	if (tid_fd >= 0)
+		close(tid_fd);
+	return err;
+}
+
+static tld_key_t __tld_create_key(const char *name, size_t size, bool dyn_data)
+{
+	int err, i, sz, off = 0;
+	__u8 cnt;
+
+	if (!TLD_READ_ONCE(tld_meta_p)) {
+		err = __tld_init_meta_p();
+		if (err)
+			return (tld_key_t){err};
+	}
+
+	for (i = 0; i < TLD_MAX_DATA_CNT; i++) {
+retry:
+		cnt = atomic_load(&tld_meta_p->cnt);
+		if (i < cnt) {
+			/* A metadata is not ready until size is updated with a non-zero value */
+			while (!(sz = atomic_load(&tld_meta_p->metadata[i].size)))
+				sched_yield();
+
+			if (!strncmp(tld_meta_p->metadata[i].name, name, TLD_NAME_LEN))
+				return (tld_key_t){-EEXIST};
+
+			off += TLD_ROUND_UP(sz, 8);
+			continue;
+		}
+
+		/*
+		 * TLD_DEFINE_KEY() is given memory upto a page while at most
+		 * TLD_DYN_DATA_SIZE is allocated for tld_create_key()
+		 */
+		if (dyn_data) {
+			if (off + TLD_ROUND_UP(size, 8) > tld_meta_p->size)
+				return (tld_key_t){-E2BIG};
+		} else {
+			if (off + TLD_ROUND_UP(size, 8) > TLD_PAGE_SIZE - sizeof(struct tld_data_u))
+				return (tld_key_t){-E2BIG};
+			tld_meta_p->size += TLD_ROUND_UP(size, 8);
+		}
+
+		/*
+		 * Only one tld_create_key() can increase the current cnt by one and
+		 * takes the latest available slot. Other threads will check again if a new
+		 * TLD can still be added, and then compete for the new slot after the
+		 * succeeding thread update the size.
+		 */
+		if (!atomic_compare_exchange_strong(&tld_meta_p->cnt, &cnt, cnt + 1))
+			goto retry;
+
+		strncpy(tld_meta_p->metadata[i].name, name, TLD_NAME_LEN);
+		atomic_store(&tld_meta_p->metadata[i].size, size);
+		return (tld_key_t){(__s16)off};
+	}
+
+	return (tld_key_t){-ENOSPC};
+}
+
+/**
+ * TLD_DEFINE_KEY() - Define a TLD and a global variable key associated with the TLD.
+ *
+ * @name: The name of the TLD
+ * @size: The size of the TLD
+ * @key: The variable name of the key. Cannot exceed TLD_NAME_LEN
+ *
+ * The macro can only be used in file scope.
+ *
+ * A global variable key of opaque type, tld_key_t, will be declared and initialized before
+ * main() starts. Use tld_key_is_err() or tld_key_err_or_zero() later to check if the key
+ * creation succeeded. Pass the key to tld_get_data() to get a pointer to the TLD.
+ * bpf programs can also fetch the same key by name.
+ *
+ * The total size of TLDs created using TLD_DEFINE_KEY() cannot exceed a page. Just
+ * enough memory will be allocated for each thread on the first call to tld_get_data().
+ */
+#define TLD_DEFINE_KEY(key, name, size)			\
+tld_key_t key;						\
+							\
+__attribute__((constructor))				\
+void __tld_define_key_##key(void)			\
+{							\
+	key = __tld_create_key(name, size, false);	\
+}
+
+/**
+ * tld_create_key() - Create a TLD and return a key associated with the TLD.
+ *
+ * @name: The name the TLD
+ * @size: The size of the TLD
+ *
+ * Return an opaque object key. Use tld_key_is_err() or tld_key_err_or_zero() to check
+ * if the key creation succeeded. Pass the key to tld_get_data() to get a pointer to
+ * locate the TLD. bpf programs can also fetch the same key by name.
+ *
+ * Use tld_create_key() only when a TLD needs to be created dynamically (e.g., @name is
+ * not known statically or a TLD needs to be created conditionally)
+ *
+ * An additional TLD_DYN_DATA_SIZE bytes are allocated per-thread to accommodate TLDs
+ * created dynamically with tld_create_key(). Since only a user page is pinned to the
+ * kernel, when TLDs created with TLD_DEFINE_KEY() uses more than TLD_PAGE_SIZE -
+ * TLD_DYN_DATA_SIZE, the buffer size will be limited to the rest of the page.
+ */
+__attribute__((unused))
+static tld_key_t tld_create_key(const char *name, size_t size)
+{
+	return __tld_create_key(name, size, true);
+}
+
+__attribute__((unused))
+static inline bool tld_key_is_err(tld_key_t key)
+{
+	return key.off < 0;
+}
+
+__attribute__((unused))
+static inline int tld_key_err_or_zero(tld_key_t key)
+{
+	return tld_key_is_err(key) ? key.off : 0;
+}
+
+/**
+ * tld_get_data() - Get a pointer to the TLD associated with the given key of the
+ * calling thread.
+ *
+ * @map_fd: A file descriptor of tld_data_map, the underlying BPF task local storage map
+ * of task local data.
+ * @key: A key object created by TLD_DEFINE_KEY() or tld_create_key().
+ *
+ * Return a pointer to the TLD if the key is valid; NULL if not enough memory for TLD
+ * for this thread, or the key is invalid. The returned pointer is guaranteed to be 8-byte
+ * aligned.
+ *
+ * Threads that call tld_get_data() must call tld_free() on exit to prevent
+ * memory leak if TLD_FREE_DATA_ON_THREAD_EXIT is not defined.
+ */
+__attribute__((unused))
+static void *tld_get_data(int map_fd, tld_key_t key)
+{
+	if (!TLD_READ_ONCE(tld_meta_p))
+		return NULL;
+
+	/* tld_data_p is allocated on the first invocation of tld_get_data() */
+	if (!tld_data_p && __tld_init_data_p(map_fd))
+		return NULL;
+
+	return tld_data_p->data + key.off;
+}
+
+/**
+ * tld_free() - Free task local data memory of the calling thread
+ *
+ * For the calling thread, all pointers to TLDs acquired before will become invalid.
+ *
+ * Users must call tld_free() on thread exit to prevent memory leak. Alternatively,
+ * define TLD_FREE_DATA_ON_THREAD_EXIT and a thread exit handler will be registered
+ * to free the memory automatically.
+ */
+__attribute__((unused))
+static void tld_free(void)
+{
+	if (tld_data_alloc_p) {
+		free(tld_data_alloc_p);
+		tld_data_alloc_p = NULL;
+		tld_data_p = NULL;
+	}
+}
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
+#endif /* __TASK_LOCAL_DATA_H */
diff --git a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c
index a176bd75a748..42e822ea352f 100644
--- a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c
+++ b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c
@@ -7,12 +7,20 @@
 #include <pthread.h>
 #include <sys/syscall.h>   /* For SYS_xxx definitions */
 #include <sys/types.h>
+#include <sys/eventfd.h>
+#include <sys/mman.h>
 #include <test_progs.h>
+#include <bpf/btf.h>
 #include "task_local_storage_helpers.h"
 #include "task_local_storage.skel.h"
 #include "task_local_storage_exit_creds.skel.h"
 #include "task_ls_recursion.skel.h"
 #include "task_storage_nodeadlock.skel.h"
+#include "uptr_test_common.h"
+#include "task_ls_uptr.skel.h"
+#include "uptr_update_failure.skel.h"
+#include "uptr_failure.skel.h"
+#include "uptr_map_failure.skel.h"
 
 static void test_sys_enter_exit(void)
 {
@@ -23,14 +31,14 @@ static void test_sys_enter_exit(void)
 	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
 		return;
 
-	skel->bss->target_pid = syscall(SYS_gettid);
+	skel->bss->target_pid = sys_gettid();
 
 	err = task_local_storage__attach(skel);
 	if (!ASSERT_OK(err, "skel_attach"))
 		goto out;
 
-	syscall(SYS_gettid);
-	syscall(SYS_gettid);
+	sys_gettid();
+	sys_gettid();
 
 	/* 3x syscalls: 1x attach and 2x gettid */
 	ASSERT_EQ(skel->bss->enter_cnt, 3, "enter_cnt");
@@ -99,7 +107,7 @@ static void test_recursion(void)
 
 	/* trigger sys_enter, make sure it does not cause deadlock */
 	skel->bss->test_pid = getpid();
-	syscall(SYS_gettid);
+	sys_gettid();
 	skel->bss->test_pid = 0;
 	task_ls_recursion__detach(skel);
 
@@ -117,21 +125,15 @@ static void test_recursion(void)
 	ASSERT_OK(err, "lookup map_b");
 	ASSERT_EQ(value, 100, "map_b value");
 
-	prog_fd = bpf_program__fd(skel->progs.on_lookup);
-	memset(&info, 0, sizeof(info));
-	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
-	ASSERT_OK(err, "get prog info");
-	ASSERT_GT(info.recursion_misses, 0, "on_lookup prog recursion");
-
 	prog_fd = bpf_program__fd(skel->progs.on_update);
 	memset(&info, 0, sizeof(info));
-	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len);
 	ASSERT_OK(err, "get prog info");
 	ASSERT_EQ(info.recursion_misses, 0, "on_update prog recursion");
 
 	prog_fd = bpf_program__fd(skel->progs.on_enter);
 	memset(&info, 0, sizeof(info));
-	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len);
 	ASSERT_OK(err, "get prog info");
 	ASSERT_EQ(info.recursion_misses, 0, "on_enter prog recursion");
 
@@ -195,7 +197,7 @@ static void test_nodeadlock(void)
 	/* Unnecessary recursion and deadlock detection are reproducible
 	 * in the preemptible kernel.
 	 */
-	if (!skel->kconfig->CONFIG_PREEMPT) {
+	if (!skel->kconfig->CONFIG_PREEMPTION) {
 		test__skip();
 		goto done;
 	}
@@ -221,7 +223,7 @@ static void test_nodeadlock(void)
 
 	info_len = sizeof(info);
 	prog_fd = bpf_program__fd(skel->progs.socket_post_create);
-	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len);
 	ASSERT_OK(err, "get prog info");
 	ASSERT_EQ(info.recursion_misses, 0, "prog recursion");
 
@@ -233,6 +235,259 @@ done:
 	sched_setaffinity(getpid(), sizeof(old), &old);
 }
 
+static struct user_data udata __attribute__((aligned(16))) = {
+	.a = 1,
+	.b = 2,
+};
+
+static struct user_data udata2 __attribute__((aligned(16))) = {
+	.a = 3,
+	.b = 4,
+};
+
+static void check_udata2(int expected)
+{
+	udata2.result = udata2.nested_result = 0;
+	usleep(1);
+	ASSERT_EQ(udata2.result, expected, "udata2.result");
+	ASSERT_EQ(udata2.nested_result, expected, "udata2.nested_result");
+}
+
+static void test_uptr_basic(void)
+{
+	int map_fd, parent_task_fd, ev_fd;
+	struct value_type value = {};
+	struct task_ls_uptr *skel;
+	pid_t child_pid, my_tid;
+	__u64 ev_dummy_data = 1;
+	int err;
+
+	my_tid = sys_gettid();
+	parent_task_fd = sys_pidfd_open(my_tid, 0);
+	if (!ASSERT_OK_FD(parent_task_fd, "parent_task_fd"))
+		return;
+
+	ev_fd = eventfd(0, 0);
+	if (!ASSERT_OK_FD(ev_fd, "ev_fd")) {
+		close(parent_task_fd);
+		return;
+	}
+
+	skel = task_ls_uptr__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		goto out;
+
+	map_fd = bpf_map__fd(skel->maps.datamap);
+	value.udata = &udata;
+	value.nested.udata = &udata;
+	err = bpf_map_update_elem(map_fd, &parent_task_fd, &value, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "update_elem(udata)"))
+		goto out;
+
+	err = task_ls_uptr__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto out;
+
+	child_pid = fork();
+	if (!ASSERT_NEQ(child_pid, -1, "fork"))
+		goto out;
+
+	/* Call syscall in the child process, but access the map value of
+	 * the parent process in the BPF program to check if the user kptr
+	 * is translated/mapped correctly.
+	 */
+	if (child_pid == 0) {
+		/* child */
+
+		/* Overwrite the user_data in the child process to check if
+		 * the BPF program accesses the user_data of the parent.
+		 */
+		udata.a = 0;
+		udata.b = 0;
+
+		/* Wait for the parent to set child_pid */
+		read(ev_fd, &ev_dummy_data, sizeof(ev_dummy_data));
+		exit(0);
+	}
+
+	skel->bss->parent_pid = my_tid;
+	skel->bss->target_pid = child_pid;
+
+	write(ev_fd, &ev_dummy_data, sizeof(ev_dummy_data));
+
+	err = waitpid(child_pid, NULL, 0);
+	ASSERT_EQ(err, child_pid, "waitpid");
+	ASSERT_EQ(udata.result, MAGIC_VALUE + udata.a + udata.b, "udata.result");
+	ASSERT_EQ(udata.nested_result, MAGIC_VALUE + udata.a + udata.b, "udata.nested_result");
+
+	skel->bss->target_pid = my_tid;
+
+	/* update_elem: uptr changes from udata1 to udata2 */
+	value.udata = &udata2;
+	value.nested.udata = &udata2;
+	err = bpf_map_update_elem(map_fd, &parent_task_fd, &value, BPF_EXIST);
+	if (!ASSERT_OK(err, "update_elem(udata2)"))
+		goto out;
+	check_udata2(MAGIC_VALUE + udata2.a + udata2.b);
+
+	/* update_elem: uptr changes from udata2 uptr to NULL */
+	memset(&value, 0, sizeof(value));
+	err = bpf_map_update_elem(map_fd, &parent_task_fd, &value, BPF_EXIST);
+	if (!ASSERT_OK(err, "update_elem(udata2)"))
+		goto out;
+	check_udata2(0);
+
+	/* update_elem: uptr changes from NULL to udata2 */
+	value.udata = &udata2;
+	value.nested.udata = &udata2;
+	err = bpf_map_update_elem(map_fd, &parent_task_fd, &value, BPF_EXIST);
+	if (!ASSERT_OK(err, "update_elem(udata2)"))
+		goto out;
+	check_udata2(MAGIC_VALUE + udata2.a + udata2.b);
+
+	/* Check if user programs can access the value of user kptrs
+	 * through bpf_map_lookup_elem(). Make sure the kernel value is not
+	 * leaked.
+	 */
+	err = bpf_map_lookup_elem(map_fd, &parent_task_fd, &value);
+	if (!ASSERT_OK(err, "bpf_map_lookup_elem"))
+		goto out;
+	ASSERT_EQ(value.udata, NULL, "value.udata");
+	ASSERT_EQ(value.nested.udata, NULL, "value.nested.udata");
+
+	/* delete_elem */
+	err = bpf_map_delete_elem(map_fd, &parent_task_fd);
+	ASSERT_OK(err, "delete_elem(udata2)");
+	check_udata2(0);
+
+	/* update_elem: add uptr back to test map_free */
+	value.udata = &udata2;
+	value.nested.udata = &udata2;
+	err = bpf_map_update_elem(map_fd, &parent_task_fd, &value, BPF_NOEXIST);
+	ASSERT_OK(err, "update_elem(udata2)");
+
+out:
+	task_ls_uptr__destroy(skel);
+	close(ev_fd);
+	close(parent_task_fd);
+}
+
+static void test_uptr_across_pages(void)
+{
+	int page_size = getpagesize();
+	struct value_type value = {};
+	struct task_ls_uptr *skel;
+	int err, task_fd, map_fd;
+	void *mem;
+
+	task_fd = sys_pidfd_open(getpid(), 0);
+	if (!ASSERT_OK_FD(task_fd, "task_fd"))
+		return;
+
+	mem = mmap(NULL, page_size * 2, PROT_READ | PROT_WRITE,
+		   MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	if (!ASSERT_OK_PTR(mem, "mmap(page_size * 2)")) {
+		close(task_fd);
+		return;
+	}
+
+	skel = task_ls_uptr__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		goto out;
+
+	map_fd = bpf_map__fd(skel->maps.datamap);
+	value.udata = mem + page_size - offsetof(struct user_data, b);
+	err = bpf_map_update_elem(map_fd, &task_fd, &value, 0);
+	if (!ASSERT_ERR(err, "update_elem(udata)"))
+		goto out;
+	ASSERT_EQ(errno, EOPNOTSUPP, "errno");
+
+	value.udata = mem + page_size - sizeof(struct user_data);
+	err = bpf_map_update_elem(map_fd, &task_fd, &value, 0);
+	ASSERT_OK(err, "update_elem(udata)");
+
+out:
+	task_ls_uptr__destroy(skel);
+	close(task_fd);
+	munmap(mem, page_size * 2);
+}
+
+static void test_uptr_update_failure(void)
+{
+	struct value_lock_type value = {};
+	struct uptr_update_failure *skel;
+	int err, task_fd, map_fd;
+
+	task_fd = sys_pidfd_open(getpid(), 0);
+	if (!ASSERT_OK_FD(task_fd, "task_fd"))
+		return;
+
+	skel = uptr_update_failure__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		goto out;
+
+	map_fd = bpf_map__fd(skel->maps.datamap);
+
+	value.udata = &udata;
+	err = bpf_map_update_elem(map_fd, &task_fd, &value, BPF_F_LOCK);
+	if (!ASSERT_ERR(err, "update_elem(udata, BPF_F_LOCK)"))
+		goto out;
+	ASSERT_EQ(errno, EOPNOTSUPP, "errno");
+
+	err = bpf_map_update_elem(map_fd, &task_fd, &value, BPF_EXIST);
+	if (!ASSERT_ERR(err, "update_elem(udata, BPF_EXIST)"))
+		goto out;
+	ASSERT_EQ(errno, ENOENT, "errno");
+
+	err = bpf_map_update_elem(map_fd, &task_fd, &value, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "update_elem(udata, BPF_NOEXIST)"))
+		goto out;
+
+	value.udata = &udata2;
+	err = bpf_map_update_elem(map_fd, &task_fd, &value, BPF_NOEXIST);
+	if (!ASSERT_ERR(err, "update_elem(udata2, BPF_NOEXIST)"))
+		goto out;
+	ASSERT_EQ(errno, EEXIST, "errno");
+
+out:
+	uptr_update_failure__destroy(skel);
+	close(task_fd);
+}
+
+static void test_uptr_map_failure(const char *map_name, int expected_errno)
+{
+	LIBBPF_OPTS(bpf_map_create_opts, create_attr);
+	struct uptr_map_failure *skel;
+	struct bpf_map *map;
+	struct btf *btf;
+	int map_fd, err;
+
+	skel = uptr_map_failure__open();
+	if (!ASSERT_OK_PTR(skel, "uptr_map_failure__open"))
+		return;
+
+	map = bpf_object__find_map_by_name(skel->obj, map_name);
+	btf = bpf_object__btf(skel->obj);
+	err = btf__load_into_kernel(btf);
+	if (!ASSERT_OK(err, "btf__load_into_kernel"))
+		goto done;
+
+	create_attr.map_flags = bpf_map__map_flags(map);
+	create_attr.btf_fd = btf__fd(btf);
+	create_attr.btf_key_type_id = bpf_map__btf_key_type_id(map);
+	create_attr.btf_value_type_id = bpf_map__btf_value_type_id(map);
+	map_fd = bpf_map_create(bpf_map__type(map), map_name,
+				bpf_map__key_size(map), bpf_map__value_size(map),
+				0, &create_attr);
+	if (ASSERT_ERR_FD(map_fd, "map_create"))
+		ASSERT_EQ(errno, expected_errno, "errno");
+	else
+		close(map_fd);
+
+done:
+	uptr_map_failure__destroy(skel);
+}
+
 void test_task_local_storage(void)
 {
 	if (test__start_subtest("sys_enter_exit"))
@@ -243,4 +498,21 @@ void test_task_local_storage(void)
 		test_recursion();
 	if (test__start_subtest("nodeadlock"))
 		test_nodeadlock();
+	if (test__start_subtest("uptr_basic"))
+		test_uptr_basic();
+	if (test__start_subtest("uptr_across_pages"))
+		test_uptr_across_pages();
+	if (test__start_subtest("uptr_update_failure"))
+		test_uptr_update_failure();
+	if (test__start_subtest("uptr_map_failure_e2big")) {
+		if (getpagesize() == PAGE_SIZE)
+			test_uptr_map_failure("large_uptr_map", E2BIG);
+		else
+			test__skip();
+	}
+	if (test__start_subtest("uptr_map_failure_size0"))
+		test_uptr_map_failure("empty_uptr_map", EINVAL);
+	if (test__start_subtest("uptr_map_failure_kstruct"))
+		test_uptr_map_failure("kstruct_uptr_map", EINVAL);
+	RUN_TESTS(uptr_failure);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c b/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c
new file mode 100644
index 000000000000..626d76fe43a2
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Bytedance */
+
+#include <sys/syscall.h>
+#include <test_progs.h>
+#include <cgroup_helpers.h>
+#include "test_task_under_cgroup.skel.h"
+
+#define FOO	"/foo"
+
+void test_task_under_cgroup(void)
+{
+	struct test_task_under_cgroup *skel;
+	int ret, foo;
+	pid_t pid;
+
+	foo = test__join_cgroup(FOO);
+	if (!ASSERT_OK(foo < 0, "cgroup_join_foo"))
+		return;
+
+	skel = test_task_under_cgroup__open();
+	if (!ASSERT_OK_PTR(skel, "test_task_under_cgroup__open"))
+		goto cleanup;
+
+	skel->rodata->local_pid = getpid();
+	skel->bss->remote_pid = getpid();
+	skel->rodata->cgid = get_cgroup_id(FOO);
+
+	ret = test_task_under_cgroup__load(skel);
+	if (!ASSERT_OK(ret, "test_task_under_cgroup__load"))
+		goto cleanup;
+
+	/* First, attach the LSM program, and then it will be triggered when the
+	 * TP_BTF program is attached.
+	 */
+	skel->links.lsm_run = bpf_program__attach_lsm(skel->progs.lsm_run);
+	if (!ASSERT_OK_PTR(skel->links.lsm_run, "attach_lsm"))
+		goto cleanup;
+
+	skel->links.tp_btf_run = bpf_program__attach_trace(skel->progs.tp_btf_run);
+	if (!ASSERT_OK_PTR(skel->links.tp_btf_run, "attach_tp_btf"))
+		goto cleanup;
+
+	pid = fork();
+	if (pid == 0)
+		exit(0);
+
+	ret = (pid == -1);
+	if (ASSERT_OK(ret, "fork process"))
+		wait(NULL);
+
+	test_task_under_cgroup__detach(skel);
+
+	ASSERT_NEQ(skel->bss->remote_pid, skel->rodata->local_pid,
+		   "test task_under_cgroup");
+
+cleanup:
+	test_task_under_cgroup__destroy(skel);
+	close(foo);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/task_work_stress.c b/tools/testing/selftests/bpf/prog_tests/task_work_stress.c
new file mode 100644
index 000000000000..450d17d91a56
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/task_work_stress.c
@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <string.h>
+#include <stdio.h>
+#include "task_work_stress.skel.h"
+#include <linux/bpf.h>
+#include <linux/perf_event.h>
+#include <sys/syscall.h>
+#include <time.h>
+#include <stdlib.h>
+#include <stdatomic.h>
+
+struct test_data {
+	int prog_fd;
+	atomic_int exit;
+};
+
+void *runner(void *test_data)
+{
+	struct test_data *td = test_data;
+	int err = 0;
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+
+	while (!err && !atomic_load(&td->exit))
+		err = bpf_prog_test_run_opts(td->prog_fd, &opts);
+
+	return NULL;
+}
+
+static int get_env_int(const char *str, int def)
+{
+	const char *s = getenv(str);
+	char *end;
+	int retval;
+
+	if (!s || !*s)
+		return def;
+	errno = 0;
+	retval = strtol(s, &end, 10);
+	if (errno || *end || retval < 0)
+		return def;
+	return retval;
+}
+
+static void task_work_run(bool enable_delete)
+{
+	struct task_work_stress *skel;
+	struct bpf_program *scheduler, *deleter;
+	int nthreads = 16;
+	int test_time_s = get_env_int("BPF_TASK_WORK_TEST_TIME", 1);
+	pthread_t tid[nthreads], tid_del;
+	bool started[nthreads], started_del = false;
+	struct test_data td_sched = { .exit = 0 }, td_del = { .exit = 1 };
+	int i, err;
+
+	skel = task_work_stress__open();
+	if (!ASSERT_OK_PTR(skel, "task_work__open"))
+		return;
+
+	scheduler = bpf_object__find_program_by_name(skel->obj, "schedule_task_work");
+	bpf_program__set_autoload(scheduler, true);
+
+	deleter = bpf_object__find_program_by_name(skel->obj, "delete_task_work");
+	bpf_program__set_autoload(deleter, true);
+
+	err = task_work_stress__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	for (i = 0; i < nthreads; ++i)
+		started[i] = false;
+
+	td_sched.prog_fd = bpf_program__fd(scheduler);
+	for (i = 0; i < nthreads; ++i) {
+		if (pthread_create(&tid[i], NULL, runner, &td_sched) != 0) {
+			fprintf(stderr, "could not start thread");
+			goto cancel;
+		}
+		started[i] = true;
+	}
+
+	if (enable_delete)
+		atomic_store(&td_del.exit, 0);
+
+	td_del.prog_fd = bpf_program__fd(deleter);
+	if (pthread_create(&tid_del, NULL, runner, &td_del) != 0) {
+		fprintf(stderr, "could not start thread");
+		goto cancel;
+	}
+	started_del = true;
+
+	/* Run stress test for some time */
+	sleep(test_time_s);
+
+cancel:
+	atomic_store(&td_sched.exit, 1);
+	atomic_store(&td_del.exit, 1);
+	for (i = 0; i < nthreads; ++i) {
+		if (started[i])
+			pthread_join(tid[i], NULL);
+	}
+
+	if (started_del)
+		pthread_join(tid_del, NULL);
+
+	ASSERT_GT(skel->bss->callback_scheduled, 0, "work scheduled");
+	/* Some scheduling attempts should have failed due to contention */
+	ASSERT_GT(skel->bss->schedule_error, 0, "schedule error");
+
+	if (enable_delete) {
+		/* If delete thread is enabled, it has cancelled some callbacks */
+		ASSERT_GT(skel->bss->delete_success, 0, "delete success");
+		ASSERT_LT(skel->bss->callback_success, skel->bss->callback_scheduled, "callbacks");
+	} else {
+		/* Without delete thread number of scheduled callbacks is the same as fired */
+		ASSERT_EQ(skel->bss->callback_success, skel->bss->callback_scheduled, "callbacks");
+	}
+
+cleanup:
+	task_work_stress__destroy(skel);
+}
+
+void test_task_work_stress(void)
+{
+	if (test__start_subtest("no_delete"))
+		task_work_run(false);
+	if (test__start_subtest("with_delete"))
+		task_work_run(true);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_bpf.c b/tools/testing/selftests/bpf/prog_tests/tc_bpf.c
index 4a505a5adf4d..48b55539331e 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_bpf.c
@@ -3,6 +3,7 @@
 #include <test_progs.h>
 #include <linux/pkt_cls.h>
 
+#include "cap_helpers.h"
 #include "test_tc_bpf.skel.h"
 
 #define LO_IFINDEX 1
@@ -29,8 +30,8 @@ static int test_tc_bpf_basic(const struct bpf_tc_hook *hook, int fd)
 	__u32 info_len = sizeof(info);
 	int ret;
 
-	ret = bpf_obj_get_info_by_fd(fd, &info, &info_len);
-	if (!ASSERT_OK(ret, "bpf_obj_get_info_by_fd"))
+	ret = bpf_prog_get_info_by_fd(fd, &info, &info_len);
+	if (!ASSERT_OK(ret, "bpf_prog_get_info_by_fd"))
 		return ret;
 
 	ret = bpf_tc_attach(hook, &opts);
@@ -327,7 +328,7 @@ static int test_tc_bpf_api(struct bpf_tc_hook *hook, int fd)
 	return 0;
 }
 
-void test_tc_bpf(void)
+void tc_bpf_root(void)
 {
 	DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = LO_IFINDEX,
 			    .attach_point = BPF_TC_INGRESS);
@@ -393,3 +394,36 @@ end:
 	}
 	test_tc_bpf__destroy(skel);
 }
+
+void tc_bpf_non_root(void)
+{
+	struct test_tc_bpf *skel = NULL;
+	__u64 caps = 0;
+	int ret;
+
+	/* In case CAP_BPF and CAP_PERFMON is not set */
+	ret = cap_enable_effective(1ULL << CAP_BPF | 1ULL << CAP_NET_ADMIN, &caps);
+	if (!ASSERT_OK(ret, "set_cap_bpf_cap_net_admin"))
+		return;
+	ret = cap_disable_effective(1ULL << CAP_SYS_ADMIN | 1ULL << CAP_PERFMON, NULL);
+	if (!ASSERT_OK(ret, "disable_cap_sys_admin"))
+		goto restore_cap;
+
+	skel = test_tc_bpf__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tc_bpf__open_and_load"))
+		goto restore_cap;
+
+	test_tc_bpf__destroy(skel);
+
+restore_cap:
+	if (caps)
+		cap_enable_effective(caps, NULL);
+}
+
+void test_tc_bpf(void)
+{
+	if (test__start_subtest("tc_bpf_root"))
+		tc_bpf_root();
+	if (test__start_subtest("tc_bpf_non_root"))
+		tc_bpf_non_root();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c b/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c
new file mode 100644
index 000000000000..74752233e779
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tc_change_tail.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <error.h>
+#include <test_progs.h>
+#include <linux/pkt_cls.h>
+
+#include "test_tc_change_tail.skel.h"
+#include "socket_helpers.h"
+
+#define LO_IFINDEX 1
+
+void test_tc_change_tail(void)
+{
+	LIBBPF_OPTS(bpf_tcx_opts, tcx_opts);
+	struct test_tc_change_tail *skel = NULL;
+	struct bpf_link *link;
+	int c1, p1;
+	char buf[2];
+	int ret;
+
+	skel = test_tc_change_tail__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tc_change_tail__open_and_load"))
+		return;
+
+	link = bpf_program__attach_tcx(skel->progs.change_tail, LO_IFINDEX,
+				     &tcx_opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_tcx"))
+		goto destroy;
+
+	skel->links.change_tail = link;
+	ret = create_pair(AF_INET, SOCK_DGRAM, &c1, &p1);
+	if (!ASSERT_OK(ret, "create_pair"))
+		goto destroy;
+
+	ret = xsend(p1, "Tr", 2, 0);
+	ASSERT_EQ(ret, 2, "xsend(p1)");
+	ret = recv(c1, buf, 2, 0);
+	ASSERT_EQ(ret, 2, "recv(c1)");
+	ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret");
+
+	ret = xsend(p1, "G", 1, 0);
+	ASSERT_EQ(ret, 1, "xsend(p1)");
+	ret = recv(c1, buf, 2, 0);
+	ASSERT_EQ(ret, 1, "recv(c1)");
+	ASSERT_EQ(skel->data->change_tail_ret, 0, "change_tail_ret");
+
+	ret = xsend(p1, "E", 1, 0);
+	ASSERT_EQ(ret, 1, "xsend(p1)");
+	ret = recv(c1, buf, 1, 0);
+	ASSERT_EQ(ret, 1, "recv(c1)");
+	ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret");
+
+	ret = xsend(p1, "Z", 1, 0);
+	ASSERT_EQ(ret, 1, "xsend(p1)");
+	ret = recv(c1, buf, 1, 0);
+	ASSERT_EQ(ret, 1, "recv(c1)");
+	ASSERT_EQ(skel->data->change_tail_ret, -EINVAL, "change_tail_ret");
+
+	close(c1);
+	close(p1);
+destroy:
+	test_tc_change_tail__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_helpers.h b/tools/testing/selftests/bpf/prog_tests/tc_helpers.h
new file mode 100644
index 000000000000..d52a62af77bf
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tc_helpers.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2023 Isovalent */
+#ifndef TC_HELPERS
+#define TC_HELPERS
+#include <test_progs.h>
+
+#ifndef loopback
+# define loopback 1
+#endif
+
+static inline __u32 ifindex_from_link_fd(int fd)
+{
+	struct bpf_link_info link_info = {};
+	__u32 link_info_len = sizeof(link_info);
+	int err;
+
+	err = bpf_link_get_info_by_fd(fd, &link_info, &link_info_len);
+	if (!ASSERT_OK(err, "id_from_link_fd"))
+		return 0;
+
+	return link_info.tcx.ifindex;
+}
+
+static inline void __assert_mprog_count(int target, int expected, int ifindex)
+{
+	__u32 count = 0, attach_flags = 0;
+	int err;
+
+	err = bpf_prog_query(ifindex, target, 0, &attach_flags,
+			     NULL, &count);
+	ASSERT_EQ(count, expected, "count");
+	ASSERT_EQ(err, 0, "prog_query");
+}
+
+static inline void assert_mprog_count(int target, int expected)
+{
+	__assert_mprog_count(target, expected, loopback);
+}
+
+static inline void assert_mprog_count_ifindex(int ifindex, int target, int expected)
+{
+	__assert_mprog_count(target, expected, ifindex);
+}
+
+static inline void tc_skel_reset_all_seen(struct test_tc_link *skel)
+{
+	memset(skel->bss, 0, sizeof(*skel->bss));
+}
+
+#endif /* TC_HELPERS */
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_links.c b/tools/testing/selftests/bpf/prog_tests/tc_links.c
new file mode 100644
index 000000000000..2186a24e7d8a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tc_links.c
@@ -0,0 +1,1962 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+#include <uapi/linux/if_link.h>
+#include <uapi/linux/pkt_sched.h>
+#include <net/if.h>
+#include <test_progs.h>
+
+#define loopback 1
+#define ping_cmd "ping -q -c1 -w1 127.0.0.1 > /dev/null"
+
+#include "test_tc_link.skel.h"
+
+#include "netlink_helpers.h"
+#include "tc_helpers.h"
+
+void test_ns_tc_links_basic(void)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 prog_ids[2], link_ids[2];
+	__u32 pid1, pid2, lid1, lid2;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+
+	assert_mprog_count(BPF_TCX_INGRESS, 0);
+	assert_mprog_count(BPF_TCX_EGRESS, 0);
+
+	ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count(BPF_TCX_INGRESS, 1);
+	assert_mprog_count(BPF_TCX_EGRESS, 0);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, BPF_TCX_INGRESS, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 2, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
+	ASSERT_NEQ(lid1, lid2, "link_ids_1_2");
+
+	assert_mprog_count(BPF_TCX_INGRESS, 1);
+	assert_mprog_count(BPF_TCX_EGRESS, 1);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, BPF_TCX_EGRESS, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 2, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+cleanup:
+	test_tc_link__destroy(skel);
+
+	assert_mprog_count(BPF_TCX_INGRESS, 0);
+	assert_mprog_count(BPF_TCX_EGRESS, 0);
+}
+
+static void test_tc_links_before_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 prog_ids[5], link_ids[5];
+	__u32 pid1, pid2, pid3, pid4;
+	__u32 lid1, lid2, lid3, lid4;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target),
+		  0, "tc3_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target),
+		  0, "tc4_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+	pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid3, pid4, "prog_ids_3_4");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count(target, 1);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid2, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid2, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = bpf_program__fd(skel->progs.tc2),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc3, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc3 = link;
+
+	lid3 = id_from_link_fd(bpf_link__fd(skel->links.tc3));
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE | BPF_F_LINK,
+		.relative_id = lid1,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc4, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc4 = link;
+
+	lid4 = id_from_link_fd(bpf_link__fd(skel->links.tc4));
+
+	assert_mprog_count(target, 4);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid4, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid4, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid1, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], pid3, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], lid3, "link_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], pid2, "prog_ids[3]");
+	ASSERT_EQ(optq.link_ids[3], lid2, "link_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+	ASSERT_EQ(optq.link_ids[4], 0, "link_ids[4]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+cleanup:
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void test_ns_tc_links_before(void)
+{
+	test_tc_links_before_target(BPF_TCX_INGRESS);
+	test_tc_links_before_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_links_after_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 prog_ids[5], link_ids[5];
+	__u32 pid1, pid2, pid3, pid4;
+	__u32 lid1, lid2, lid3, lid4;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target),
+		  0, "tc3_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target),
+		  0, "tc4_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+	pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid3, pid4, "prog_ids_3_4");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count(target, 1);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid2, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid2, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_AFTER,
+		.relative_fd = bpf_program__fd(skel->progs.tc1),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc3, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc3 = link;
+
+	lid3 = id_from_link_fd(bpf_link__fd(skel->links.tc3));
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_AFTER | BPF_F_LINK,
+		.relative_fd = bpf_link__fd(skel->links.tc2),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc4, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc4 = link;
+
+	lid4 = id_from_link_fd(bpf_link__fd(skel->links.tc4));
+
+	assert_mprog_count(target, 4);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid3, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid3, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], pid2, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], lid2, "link_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], pid4, "prog_ids[3]");
+	ASSERT_EQ(optq.link_ids[3], lid4, "link_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+	ASSERT_EQ(optq.link_ids[4], 0, "link_ids[4]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+cleanup:
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void test_ns_tc_links_after(void)
+{
+	test_tc_links_after_target(BPF_TCX_INGRESS);
+	test_tc_links_after_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_links_revision_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 prog_ids[3], link_ids[3];
+	__u32 pid1, pid2, lid1, lid2;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+
+	assert_mprog_count(target, 0);
+
+	optl.expected_revision = 1;
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count(target, 1);
+
+	optl.expected_revision = 1;
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 1);
+
+	optl.expected_revision = 2;
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid2, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid2, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], 0, "prog_ids[2]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+cleanup:
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void test_ns_tc_links_revision(void)
+{
+	test_tc_links_revision_target(BPF_TCX_INGRESS);
+	test_tc_links_revision_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_chain_classic(int target, bool chain_tc_old)
+{
+	LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+	LIBBPF_OPTS(bpf_tc_hook, tc_hook, .ifindex = loopback);
+	bool hook_created = false, tc_attached = false;
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 pid1, pid2, pid3;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	if (chain_tc_old) {
+		tc_hook.attach_point = target == BPF_TCX_INGRESS ?
+				       BPF_TC_INGRESS : BPF_TC_EGRESS;
+		err = bpf_tc_hook_create(&tc_hook);
+		if (err == 0)
+			hook_created = true;
+		err = err == -EEXIST ? 0 : err;
+		if (!ASSERT_OK(err, "bpf_tc_hook_create"))
+			goto cleanup;
+
+		tc_opts.prog_fd = bpf_program__fd(skel->progs.tc3);
+		err = bpf_tc_attach(&tc_hook, &tc_opts);
+		if (!ASSERT_OK(err, "bpf_tc_attach"))
+			goto cleanup;
+		tc_attached = true;
+	}
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	assert_mprog_count(target, 2);
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, chain_tc_old, "seen_tc3");
+
+	err = bpf_link__detach(skel->links.tc2);
+	if (!ASSERT_OK(err, "prog_detach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, chain_tc_old, "seen_tc3");
+cleanup:
+	if (tc_attached) {
+		tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0;
+		err = bpf_tc_detach(&tc_hook, &tc_opts);
+		ASSERT_OK(err, "bpf_tc_detach");
+	}
+	if (hook_created) {
+		tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS;
+		bpf_tc_hook_destroy(&tc_hook);
+	}
+	assert_mprog_count(target, 1);
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void test_ns_tc_links_chain_classic(void)
+{
+	test_tc_chain_classic(BPF_TCX_INGRESS, false);
+	test_tc_chain_classic(BPF_TCX_EGRESS, false);
+	test_tc_chain_classic(BPF_TCX_INGRESS, true);
+	test_tc_chain_classic(BPF_TCX_EGRESS, true);
+}
+
+static void test_tc_links_replace_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 pid1, pid2, pid3, lid1, lid2;
+	__u32 prog_ids[4], link_ids[4];
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target),
+		  0, "tc3_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	optl.expected_revision = 1;
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE,
+		.relative_id = pid1,
+		.expected_revision = 2,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid1, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_REPLACE,
+		.relative_fd = bpf_program__fd(skel->progs.tc2),
+		.expected_revision = 3,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc3, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_REPLACE | BPF_F_LINK,
+		.relative_fd = bpf_link__fd(skel->links.tc2),
+		.expected_revision = 3,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc3, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_REPLACE | BPF_F_LINK | BPF_F_AFTER,
+		.relative_id = lid2,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc3, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 2);
+
+	err = bpf_link__update_program(skel->links.tc2, skel->progs.tc3);
+	if (!ASSERT_OK(err, "link_update"))
+		goto cleanup;
+
+	assert_mprog_count(target, 2);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 4, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid3, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid1, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3");
+
+	err = bpf_link__detach(skel->links.tc2);
+	if (!ASSERT_OK(err, "link_detach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+
+	err = bpf_link__update_program(skel->links.tc1, skel->progs.tc1);
+	if (!ASSERT_OK(err, "link_update_self"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+cleanup:
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void test_ns_tc_links_replace(void)
+{
+	test_tc_links_replace_target(BPF_TCX_INGRESS);
+	test_tc_links_replace_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_links_invalid_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 pid1, pid2, lid1;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+
+	assert_mprog_count(target, 0);
+
+	optl.flags = BPF_F_BEFORE | BPF_F_AFTER;
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE | BPF_F_ID,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_AFTER | BPF_F_ID,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_ID,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_LINK,
+		.relative_fd = bpf_program__fd(skel->progs.tc2),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_LINK,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.relative_fd = bpf_program__fd(skel->progs.tc2),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE | BPF_F_AFTER,
+		.relative_fd = bpf_program__fd(skel->progs.tc2),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = bpf_program__fd(skel->progs.tc1),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_ID,
+		.relative_id = pid2,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_ID,
+		.relative_id = 42,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = bpf_program__fd(skel->progs.tc1),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE | BPF_F_LINK,
+		.relative_fd = bpf_program__fd(skel->progs.tc1),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_AFTER,
+		.relative_fd = bpf_program__fd(skel->progs.tc1),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, 0, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_AFTER | BPF_F_LINK,
+		.relative_fd = bpf_program__fd(skel->progs.tc1),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optl);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_AFTER | BPF_F_LINK,
+		.relative_fd = bpf_program__fd(skel->progs.tc1),
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE | BPF_F_LINK | BPF_F_ID,
+		.relative_id = ~0,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE | BPF_F_LINK | BPF_F_ID,
+		.relative_id = lid1,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE | BPF_F_ID,
+		.relative_id = pid1,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE | BPF_F_LINK | BPF_F_ID,
+		.relative_id = lid1,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	assert_mprog_count(target, 2);
+cleanup:
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void test_ns_tc_links_invalid(void)
+{
+	test_tc_links_invalid_target(BPF_TCX_INGRESS);
+	test_tc_links_invalid_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_links_prepend_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 prog_ids[5], link_ids[5];
+	__u32 pid1, pid2, pid3, pid4;
+	__u32 lid1, lid2, lid3, lid4;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target),
+		  0, "tc3_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target),
+		  0, "tc4_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+	pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid3, pid4, "prog_ids_3_4");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid1, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc3, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc3 = link;
+
+	lid3 = id_from_link_fd(bpf_link__fd(skel->links.tc3));
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc4, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc4 = link;
+
+	lid4 = id_from_link_fd(bpf_link__fd(skel->links.tc4));
+
+	assert_mprog_count(target, 4);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid4, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid4, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid3, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid3, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], pid2, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], lid2, "link_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], pid1, "prog_ids[3]");
+	ASSERT_EQ(optq.link_ids[3], lid1, "link_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+	ASSERT_EQ(optq.link_ids[4], 0, "link_ids[4]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+cleanup:
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void test_ns_tc_links_prepend(void)
+{
+	test_tc_links_prepend_target(BPF_TCX_INGRESS);
+	test_tc_links_prepend_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_links_append_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 prog_ids[5], link_ids[5];
+	__u32 pid1, pid2, pid3, pid4;
+	__u32 lid1, lid2, lid3, lid4;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target),
+		  0, "tc3_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target),
+		  0, "tc4_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+	pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid3, pid4, "prog_ids_3_4");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_AFTER,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid2, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid2, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_AFTER,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc3, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc3 = link;
+
+	lid3 = id_from_link_fd(bpf_link__fd(skel->links.tc3));
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_AFTER,
+	);
+
+	link = bpf_program__attach_tcx(skel->progs.tc4, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc4 = link;
+
+	lid4 = id_from_link_fd(bpf_link__fd(skel->links.tc4));
+
+	assert_mprog_count(target, 4);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid2, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid2, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], pid3, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], lid3, "link_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], pid4, "prog_ids[3]");
+	ASSERT_EQ(optq.link_ids[3], lid4, "link_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+	ASSERT_EQ(optq.link_ids[4], 0, "link_ids[4]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+cleanup:
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void test_ns_tc_links_append(void)
+{
+	test_tc_links_append_target(BPF_TCX_INGRESS);
+	test_tc_links_append_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_links_dev_cleanup_target(int target)
+{
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 pid1, pid2, pid3, pid4;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err, ifindex;
+
+	ASSERT_OK(system("ip link add dev tcx_opts1 type veth peer name tcx_opts2"), "add veth");
+	ifindex = if_nametoindex("tcx_opts1");
+	ASSERT_NEQ(ifindex, 0, "non_zero_ifindex");
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target),
+		  0, "tc3_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target),
+		  0, "tc4_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+	pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid3, pid4, "prog_ids_3_4");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	assert_mprog_count_ifindex(ifindex, target, 1);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	assert_mprog_count_ifindex(ifindex, target, 2);
+
+	link = bpf_program__attach_tcx(skel->progs.tc3, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc3 = link;
+
+	assert_mprog_count_ifindex(ifindex, target, 3);
+
+	link = bpf_program__attach_tcx(skel->progs.tc4, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc4 = link;
+
+	assert_mprog_count_ifindex(ifindex, target, 4);
+
+	ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth");
+	ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed");
+	ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
+
+	ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc1)), 0, "tc1_ifindex");
+	ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc2)), 0, "tc2_ifindex");
+	ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc3)), 0, "tc3_ifindex");
+	ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc4)), 0, "tc4_ifindex");
+
+	test_tc_link__destroy(skel);
+	return;
+cleanup:
+	test_tc_link__destroy(skel);
+
+	ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth");
+	ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed");
+	ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
+}
+
+void test_ns_tc_links_dev_cleanup(void)
+{
+	test_tc_links_dev_cleanup_target(BPF_TCX_INGRESS);
+	test_tc_links_dev_cleanup_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_chain_mixed(int target)
+{
+	LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+	LIBBPF_OPTS(bpf_tc_hook, tc_hook, .ifindex = loopback);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	__u32 pid1, pid2, pid3;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target),
+		  0, "tc4_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc5, target),
+		  0, "tc5_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc6, target),
+		  0, "tc6_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc5));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc6));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	tc_hook.attach_point = target == BPF_TCX_INGRESS ?
+			       BPF_TC_INGRESS : BPF_TC_EGRESS;
+	err = bpf_tc_hook_create(&tc_hook);
+	err = err == -EEXIST ? 0 : err;
+	if (!ASSERT_OK(err, "bpf_tc_hook_create"))
+		goto cleanup;
+
+	tc_opts.prog_fd = bpf_program__fd(skel->progs.tc5);
+	err = bpf_tc_attach(&tc_hook, &tc_opts);
+	if (!ASSERT_OK(err, "bpf_tc_attach"))
+		goto cleanup;
+
+	link = bpf_program__attach_tcx(skel->progs.tc6, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc6 = link;
+
+	assert_mprog_count(target, 1);
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+	ASSERT_EQ(skel->bss->seen_tc5, false, "seen_tc5");
+	ASSERT_EQ(skel->bss->seen_tc6, true, "seen_tc6");
+
+	err = bpf_link__update_program(skel->links.tc6, skel->progs.tc4);
+	if (!ASSERT_OK(err, "link_update"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+	ASSERT_EQ(skel->bss->seen_tc5, true, "seen_tc5");
+	ASSERT_EQ(skel->bss->seen_tc6, false, "seen_tc6");
+
+	err = bpf_link__detach(skel->links.tc6);
+	if (!ASSERT_OK(err, "prog_detach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 0);
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+	ASSERT_EQ(skel->bss->seen_tc5, true, "seen_tc5");
+	ASSERT_EQ(skel->bss->seen_tc6, false, "seen_tc6");
+
+cleanup:
+	tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0;
+	err = bpf_tc_detach(&tc_hook, &tc_opts);
+	ASSERT_OK(err, "bpf_tc_detach");
+
+	tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS;
+	bpf_tc_hook_destroy(&tc_hook);
+
+	test_tc_link__destroy(skel);
+}
+
+void test_ns_tc_links_chain_mixed(void)
+{
+	test_tc_chain_mixed(BPF_TCX_INGRESS);
+	test_tc_chain_mixed(BPF_TCX_EGRESS);
+}
+
+static void test_tc_links_ingress(int target, bool chain_tc_old,
+				  bool tcx_teardown_first)
+{
+	LIBBPF_OPTS(bpf_tc_opts, tc_opts,
+		.handle		= 1,
+		.priority	= 1,
+	);
+	LIBBPF_OPTS(bpf_tc_hook, tc_hook,
+		.ifindex	= loopback,
+		.attach_point	= BPF_TC_CUSTOM,
+		.parent		= TC_H_INGRESS,
+	);
+	bool hook_created = false, tc_attached = false;
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 pid1, pid2, pid3;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	if (chain_tc_old) {
+		ASSERT_OK(system("tc qdisc add dev lo ingress"), "add_ingress");
+		hook_created = true;
+
+		tc_opts.prog_fd = bpf_program__fd(skel->progs.tc3);
+		err = bpf_tc_attach(&tc_hook, &tc_opts);
+		if (!ASSERT_OK(err, "bpf_tc_attach"))
+			goto cleanup;
+		tc_attached = true;
+	}
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	assert_mprog_count(target, 2);
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, chain_tc_old, "seen_tc3");
+
+	err = bpf_link__detach(skel->links.tc2);
+	if (!ASSERT_OK(err, "prog_detach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, chain_tc_old, "seen_tc3");
+cleanup:
+	if (tc_attached) {
+		tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0;
+		err = bpf_tc_detach(&tc_hook, &tc_opts);
+		ASSERT_OK(err, "bpf_tc_detach");
+	}
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+	assert_mprog_count(target, 1);
+	if (hook_created && tcx_teardown_first)
+		ASSERT_OK(system("tc qdisc del dev lo ingress"), "del_ingress");
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+	test_tc_link__destroy(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+	if (hook_created && !tcx_teardown_first)
+		ASSERT_OK(system("tc qdisc del dev lo ingress"), "del_ingress");
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+	assert_mprog_count(target, 0);
+}
+
+void test_ns_tc_links_ingress(void)
+{
+	test_tc_links_ingress(BPF_TCX_INGRESS, true, true);
+	test_tc_links_ingress(BPF_TCX_INGRESS, true, false);
+	test_tc_links_ingress(BPF_TCX_INGRESS, false, false);
+}
+
+struct qdisc_req {
+	struct nlmsghdr  n;
+	struct tcmsg     t;
+	char             buf[1024];
+};
+
+static int qdisc_replace(int ifindex, const char *kind, bool block)
+{
+	struct rtnl_handle rth = { .fd = -1 };
+	struct qdisc_req req;
+	int err;
+
+	err = rtnl_open(&rth, 0);
+	if (!ASSERT_OK(err, "open_rtnetlink"))
+		return err;
+
+	memset(&req, 0, sizeof(req));
+	req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg));
+	req.n.nlmsg_flags = NLM_F_CREATE | NLM_F_REPLACE | NLM_F_REQUEST;
+	req.n.nlmsg_type = RTM_NEWQDISC;
+	req.t.tcm_family = AF_UNSPEC;
+	req.t.tcm_ifindex = ifindex;
+	req.t.tcm_parent = 0xfffffff1;
+
+	addattr_l(&req.n, sizeof(req), TCA_KIND, kind, strlen(kind) + 1);
+	if (block)
+		addattr32(&req.n, sizeof(req), TCA_INGRESS_BLOCK, 1);
+
+	err = rtnl_talk(&rth, &req.n, NULL);
+	ASSERT_OK(err, "talk_rtnetlink");
+	rtnl_close(&rth);
+	return err;
+}
+
+void test_ns_tc_links_dev_chain0(void)
+{
+	int err, ifindex;
+
+	ASSERT_OK(system("ip link add dev foo type veth peer name bar"), "add veth");
+	ifindex = if_nametoindex("foo");
+	ASSERT_NEQ(ifindex, 0, "non_zero_ifindex");
+	err = qdisc_replace(ifindex, "ingress", true);
+	if (!ASSERT_OK(err, "attaching ingress"))
+		goto cleanup;
+	ASSERT_OK(system("tc filter add block 1 matchall action skbmod swap mac"), "add block");
+	err = qdisc_replace(ifindex, "clsact", false);
+	if (!ASSERT_OK(err, "attaching clsact"))
+		goto cleanup;
+	/* Heuristic: kern_sync_rcu() alone does not work; a wait-time of ~5s
+	 * triggered the issue without the fix reliably 100% of the time.
+	 */
+	sleep(5);
+	ASSERT_OK(system("tc filter add dev foo ingress matchall action skbmod swap mac"), "add filter");
+cleanup:
+	ASSERT_OK(system("ip link del dev foo"), "del veth");
+	ASSERT_EQ(if_nametoindex("foo"), 0, "foo removed");
+	ASSERT_EQ(if_nametoindex("bar"), 0, "bar removed");
+}
+
+static void test_tc_links_dev_mixed(int target)
+{
+	LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+	LIBBPF_OPTS(bpf_tc_hook, tc_hook);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 pid1, pid2, pid3, pid4;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err, ifindex;
+
+	ASSERT_OK(system("ip link add dev tcx_opts1 type veth peer name tcx_opts2"), "add veth");
+	ifindex = if_nametoindex("tcx_opts1");
+	ASSERT_NEQ(ifindex, 0, "non_zero_ifindex");
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target),
+		  0, "tc3_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target),
+		  0, "tc4_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+	pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid3, pid4, "prog_ids_3_4");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	link = bpf_program__attach_tcx(skel->progs.tc1, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	assert_mprog_count_ifindex(ifindex, target, 1);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	assert_mprog_count_ifindex(ifindex, target, 2);
+
+	link = bpf_program__attach_tcx(skel->progs.tc3, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc3 = link;
+
+	assert_mprog_count_ifindex(ifindex, target, 3);
+
+	link = bpf_program__attach_tcx(skel->progs.tc4, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc4 = link;
+
+	assert_mprog_count_ifindex(ifindex, target, 4);
+
+	tc_hook.ifindex = ifindex;
+	tc_hook.attach_point = target == BPF_TCX_INGRESS ?
+			       BPF_TC_INGRESS : BPF_TC_EGRESS;
+
+	err = bpf_tc_hook_create(&tc_hook);
+	err = err == -EEXIST ? 0 : err;
+	if (!ASSERT_OK(err, "bpf_tc_hook_create"))
+		goto cleanup;
+
+	tc_opts.prog_fd = bpf_program__fd(skel->progs.tc5);
+	err = bpf_tc_attach(&tc_hook, &tc_opts);
+	if (!ASSERT_OK(err, "bpf_tc_attach"))
+		goto cleanup;
+
+	ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth");
+	ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed");
+	ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
+
+	ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc1)), 0, "tc1_ifindex");
+	ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc2)), 0, "tc2_ifindex");
+	ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc3)), 0, "tc3_ifindex");
+	ASSERT_EQ(ifindex_from_link_fd(bpf_link__fd(skel->links.tc4)), 0, "tc4_ifindex");
+
+	test_tc_link__destroy(skel);
+	return;
+cleanup:
+	test_tc_link__destroy(skel);
+
+	ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth");
+	ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed");
+	ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
+}
+
+void test_ns_tc_links_dev_mixed(void)
+{
+	test_tc_links_dev_mixed(BPF_TCX_INGRESS);
+	test_tc_links_dev_mixed(BPF_TCX_EGRESS);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
new file mode 100644
index 000000000000..2461d183dee5
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
@@ -0,0 +1,870 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+#include <uapi/linux/if_link.h>
+#include <net/if.h>
+#include <test_progs.h>
+
+#define netkit_peer "nk0"
+#define netkit_name "nk1"
+
+#define ping_addr_neigh		0x0a000002 /* 10.0.0.2 */
+#define ping_addr_noneigh	0x0a000003 /* 10.0.0.3 */
+
+#include "test_tc_link.skel.h"
+#include "netlink_helpers.h"
+#include "tc_helpers.h"
+
+#define NETKIT_HEADROOM	32
+#define NETKIT_TAILROOM	8
+
+#define MARK		42
+#define PRIO		0xeb9f
+#define ICMP_ECHO	8
+
+#define FLAG_ADJUST_ROOM (1 << 0)
+#define FLAG_SAME_NETNS  (1 << 1)
+
+struct icmphdr {
+	__u8		type;
+	__u8		code;
+	__sum16		checksum;
+	struct {
+		__be16	id;
+		__be16	sequence;
+	} echo;
+};
+
+struct iplink_req {
+	struct nlmsghdr  n;
+	struct ifinfomsg i;
+	char             buf[1024];
+};
+
+static int create_netkit(int mode, int policy, int peer_policy, int *ifindex,
+			 int scrub, int peer_scrub, __u32 flags)
+{
+	struct rtnl_handle rth = { .fd = -1 };
+	struct iplink_req req = {};
+	struct rtattr *linkinfo, *data;
+	const char *type = "netkit";
+	int err;
+
+	err = rtnl_open(&rth, 0);
+	if (!ASSERT_OK(err, "open_rtnetlink"))
+		return err;
+
+	memset(&req, 0, sizeof(req));
+	req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+	req.n.nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE | NLM_F_EXCL;
+	req.n.nlmsg_type = RTM_NEWLINK;
+	req.i.ifi_family = AF_UNSPEC;
+
+	addattr_l(&req.n, sizeof(req), IFLA_IFNAME, netkit_name,
+		  strlen(netkit_name));
+	linkinfo = addattr_nest(&req.n, sizeof(req), IFLA_LINKINFO);
+	addattr_l(&req.n, sizeof(req), IFLA_INFO_KIND, type, strlen(type));
+	data = addattr_nest(&req.n, sizeof(req), IFLA_INFO_DATA);
+	addattr32(&req.n, sizeof(req), IFLA_NETKIT_POLICY, policy);
+	addattr32(&req.n, sizeof(req), IFLA_NETKIT_PEER_POLICY, peer_policy);
+	addattr32(&req.n, sizeof(req), IFLA_NETKIT_SCRUB, scrub);
+	addattr32(&req.n, sizeof(req), IFLA_NETKIT_PEER_SCRUB, peer_scrub);
+	addattr32(&req.n, sizeof(req), IFLA_NETKIT_MODE, mode);
+	if (flags & FLAG_ADJUST_ROOM) {
+		addattr16(&req.n, sizeof(req), IFLA_NETKIT_HEADROOM, NETKIT_HEADROOM);
+		addattr16(&req.n, sizeof(req), IFLA_NETKIT_TAILROOM, NETKIT_TAILROOM);
+	}
+	addattr_nest_end(&req.n, data);
+	addattr_nest_end(&req.n, linkinfo);
+
+	err = rtnl_talk(&rth, &req.n, NULL);
+	ASSERT_OK(err, "talk_rtnetlink");
+	rtnl_close(&rth);
+	*ifindex = if_nametoindex(netkit_name);
+
+	ASSERT_GT(*ifindex, 0, "retrieve_ifindex");
+	ASSERT_OK(system("ip netns add foo"), "create netns");
+	ASSERT_OK(system("ip link set dev " netkit_name " up"),
+			 "up primary");
+	ASSERT_OK(system("ip addr add dev " netkit_name " 10.0.0.1/24"),
+			 "addr primary");
+
+	if (mode == NETKIT_L3) {
+		ASSERT_EQ(system("ip link set dev " netkit_name
+				 " addr ee:ff:bb:cc:aa:dd 2> /dev/null"), 512,
+				 "set hwaddress");
+	} else {
+		ASSERT_OK(system("ip link set dev " netkit_name
+				 " addr ee:ff:bb:cc:aa:dd"),
+				 "set hwaddress");
+	}
+	if (flags & FLAG_SAME_NETNS) {
+		ASSERT_OK(system("ip link set dev " netkit_peer " up"),
+				 "up peer");
+		ASSERT_OK(system("ip addr add dev " netkit_peer " 10.0.0.2/24"),
+				 "addr peer");
+	} else {
+		ASSERT_OK(system("ip link set " netkit_peer " netns foo"),
+				 "move peer");
+		ASSERT_OK(system("ip netns exec foo ip link set dev "
+				 netkit_peer " up"), "up peer");
+		ASSERT_OK(system("ip netns exec foo ip addr add dev "
+				 netkit_peer " 10.0.0.2/24"), "addr peer");
+	}
+	return err;
+}
+
+static void move_netkit(void)
+{
+	ASSERT_OK(system("ip link set " netkit_peer " netns foo"),
+			 "move peer");
+	ASSERT_OK(system("ip netns exec foo ip link set dev "
+			 netkit_peer " up"), "up peer");
+	ASSERT_OK(system("ip netns exec foo ip addr add dev "
+			 netkit_peer " 10.0.0.2/24"), "addr peer");
+}
+
+static void destroy_netkit(void)
+{
+	ASSERT_OK(system("ip link del dev " netkit_name), "del primary");
+	ASSERT_OK(system("ip netns del foo"), "delete netns");
+	ASSERT_EQ(if_nametoindex(netkit_name), 0, netkit_name "_ifindex");
+}
+
+static int __send_icmp(__u32 dest)
+{
+	int sock, ret, mark = MARK, prio = PRIO;
+	struct sockaddr_in addr;
+	struct icmphdr icmp;
+
+	ret = write_sysctl("/proc/sys/net/ipv4/ping_group_range", "0 0");
+	if (!ASSERT_OK(ret, "write_sysctl(net.ipv4.ping_group_range)"))
+		return ret;
+
+	sock = socket(AF_INET, SOCK_DGRAM, IPPROTO_ICMP);
+	if (!ASSERT_GE(sock, 0, "icmp_socket"))
+		return -errno;
+
+	ret = setsockopt(sock, SOL_SOCKET, SO_BINDTODEVICE,
+			 netkit_name, strlen(netkit_name) + 1);
+	if (!ASSERT_OK(ret, "setsockopt(SO_BINDTODEVICE)"))
+		goto out;
+
+	ret = setsockopt(sock, SOL_SOCKET, SO_MARK, &mark, sizeof(mark));
+	if (!ASSERT_OK(ret, "setsockopt(SO_MARK)"))
+		goto out;
+
+	ret = setsockopt(sock, SOL_SOCKET, SO_PRIORITY,
+			 &prio, sizeof(prio));
+	if (!ASSERT_OK(ret, "setsockopt(SO_PRIORITY)"))
+		goto out;
+
+	memset(&addr, 0, sizeof(addr));
+	addr.sin_family = AF_INET;
+	addr.sin_addr.s_addr = htonl(dest);
+
+	memset(&icmp, 0, sizeof(icmp));
+	icmp.type = ICMP_ECHO;
+	icmp.echo.id = 1234;
+	icmp.echo.sequence = 1;
+
+	ret = sendto(sock, &icmp, sizeof(icmp), 0,
+		     (struct sockaddr *)&addr, sizeof(addr));
+	if (!ASSERT_GE(ret, 0, "icmp_sendto"))
+		ret = -errno;
+	else
+		ret = 0;
+out:
+	close(sock);
+	return ret;
+}
+
+static int send_icmp(void)
+{
+	return __send_icmp(ping_addr_neigh);
+}
+
+void serial_test_tc_netkit_basic(void)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_netkit_opts, optl);
+	__u32 prog_ids[2], link_ids[2];
+	__u32 pid1, pid2, lid1, lid2;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err, ifindex;
+
+	err = create_netkit(NETKIT_L2, NETKIT_PASS, NETKIT_PASS,
+			    &ifindex, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT, 0);
+	if (err)
+		return;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1,
+		  BPF_NETKIT_PRIMARY), 0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2,
+		  BPF_NETKIT_PEER), 0, "tc2_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+
+	ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(ifindex, BPF_NETKIT_PRIMARY, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 2, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	link = bpf_program__attach_netkit(skel->progs.tc2, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
+	ASSERT_NEQ(lid1, lid2, "link_ids_1_2");
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 1);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(ifindex, BPF_NETKIT_PEER, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 2, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+cleanup:
+	test_tc_link__destroy(skel);
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+	destroy_netkit();
+}
+
+static void serial_test_tc_netkit_multi_links_target(int mode, int target)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_netkit_opts, optl);
+	__u32 prog_ids[3], link_ids[3];
+	__u32 pid1, pid2, lid1, lid2;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err, ifindex;
+
+	err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
+			    &ifindex, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT, 0);
+	if (err)
+		return;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1,
+		  target), 0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2,
+		  target), 0, "tc2_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+
+	assert_mprog_count_ifindex(ifindex, target, 0);
+
+	ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_eth, false, "seen_eth");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count_ifindex(ifindex, target, 1);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(ifindex, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 2, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_eth, true, "seen_eth");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	LIBBPF_OPTS_RESET(optl,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = bpf_program__fd(skel->progs.tc1),
+	);
+
+	link = bpf_program__attach_netkit(skel->progs.tc2, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc2 = link;
+
+	lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
+	ASSERT_NEQ(lid1, lid2, "link_ids_1_2");
+
+	assert_mprog_count_ifindex(ifindex, target, 2);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(ifindex, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], lid1, "link_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_eth, true, "seen_eth");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+cleanup:
+	test_tc_link__destroy(skel);
+
+	assert_mprog_count_ifindex(ifindex, target, 0);
+	destroy_netkit();
+}
+
+void serial_test_tc_netkit_multi_links(void)
+{
+	serial_test_tc_netkit_multi_links_target(NETKIT_L2, BPF_NETKIT_PRIMARY);
+	serial_test_tc_netkit_multi_links_target(NETKIT_L3, BPF_NETKIT_PRIMARY);
+	serial_test_tc_netkit_multi_links_target(NETKIT_L2, BPF_NETKIT_PEER);
+	serial_test_tc_netkit_multi_links_target(NETKIT_L3, BPF_NETKIT_PEER);
+}
+
+static void serial_test_tc_netkit_multi_opts_target(int mode, int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 pid1, pid2, fd1, fd2;
+	__u32 prog_ids[3];
+	struct test_tc_link *skel;
+	int err, ifindex;
+
+	err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
+			    &ifindex, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT, 0);
+	if (err)
+		return;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+
+	pid1 = id_from_prog_fd(fd1);
+	pid2 = id_from_prog_fd(fd2);
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+
+	assert_mprog_count_ifindex(ifindex, target, 0);
+
+	ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_eth, false, "seen_eth");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	err = bpf_prog_attach_opts(fd1, ifindex, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count_ifindex(ifindex, target, 1);
+
+	optq.prog_ids = prog_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(ifindex, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_fd1;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 2, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_eth, true, "seen_eth");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_attach_opts(fd2, ifindex, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_fd1;
+
+	assert_mprog_count_ifindex(ifindex, target, 2);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(ifindex, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_fd2;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_eth, true, "seen_eth");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+
+cleanup_fd2:
+	err = bpf_prog_detach_opts(fd2, ifindex, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count_ifindex(ifindex, target, 1);
+cleanup_fd1:
+	err = bpf_prog_detach_opts(fd1, ifindex, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count_ifindex(ifindex, target, 0);
+cleanup:
+	test_tc_link__destroy(skel);
+
+	assert_mprog_count_ifindex(ifindex, target, 0);
+	destroy_netkit();
+}
+
+void serial_test_tc_netkit_multi_opts(void)
+{
+	serial_test_tc_netkit_multi_opts_target(NETKIT_L2, BPF_NETKIT_PRIMARY);
+	serial_test_tc_netkit_multi_opts_target(NETKIT_L3, BPF_NETKIT_PRIMARY);
+	serial_test_tc_netkit_multi_opts_target(NETKIT_L2, BPF_NETKIT_PEER);
+	serial_test_tc_netkit_multi_opts_target(NETKIT_L3, BPF_NETKIT_PEER);
+}
+
+void serial_test_tc_netkit_device(void)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_netkit_opts, optl);
+	__u32 prog_ids[2], link_ids[2];
+	__u32 pid1, pid2, lid1;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err, ifindex, ifindex2;
+
+	err = create_netkit(NETKIT_L3, NETKIT_PASS, NETKIT_PASS,
+			    &ifindex, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT, FLAG_SAME_NETNS);
+	if (err)
+		return;
+
+	ifindex2 = if_nametoindex(netkit_peer);
+	ASSERT_NEQ(ifindex, ifindex2, "ifindex_1_2");
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1,
+		  BPF_NETKIT_PRIMARY), 0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2,
+		  BPF_NETKIT_PEER), 0, "tc2_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3,
+		  BPF_NETKIT_PRIMARY), 0, "tc3_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+
+	ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(ifindex, BPF_NETKIT_PRIMARY, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 2, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(ifindex2, BPF_NETKIT_PRIMARY, &optq);
+	ASSERT_EQ(err, -EACCES, "prog_query_should_fail");
+
+	err = bpf_prog_query_opts(ifindex2, BPF_NETKIT_PEER, &optq);
+	ASSERT_EQ(err, -EACCES, "prog_query_should_fail");
+
+	link = bpf_program__attach_netkit(skel->progs.tc2, ifindex2, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	link = bpf_program__attach_netkit(skel->progs.tc3, ifindex2, &optl);
+	if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+cleanup:
+	test_tc_link__destroy(skel);
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+	destroy_netkit();
+}
+
+static void serial_test_tc_netkit_neigh_links_target(int mode, int target)
+{
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_netkit_opts, optl);
+	__u32 prog_ids[2], link_ids[2];
+	__u32 pid1, lid1;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err, ifindex;
+
+	err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
+			    &ifindex, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT, 0);
+	if (err)
+		return;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1,
+		  BPF_NETKIT_PRIMARY), 0, "tc1_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+
+	assert_mprog_count_ifindex(ifindex, target, 0);
+
+	ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_eth, false, "seen_eth");
+
+	link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1));
+
+	assert_mprog_count_ifindex(ifindex, target, 1);
+
+	optq.prog_ids = prog_ids;
+	optq.link_ids = link_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(link_ids, 0, sizeof(link_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(ifindex, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 2, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]");
+	ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_EQ(__send_icmp(ping_addr_noneigh), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc1, true /* L2: ARP */, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_eth, mode == NETKIT_L3, "seen_eth");
+cleanup:
+	test_tc_link__destroy(skel);
+
+	assert_mprog_count_ifindex(ifindex, target, 0);
+	destroy_netkit();
+}
+
+void serial_test_tc_netkit_neigh_links(void)
+{
+	serial_test_tc_netkit_neigh_links_target(NETKIT_L2, BPF_NETKIT_PRIMARY);
+	serial_test_tc_netkit_neigh_links_target(NETKIT_L3, BPF_NETKIT_PRIMARY);
+}
+
+static void serial_test_tc_netkit_pkt_type_mode(int mode)
+{
+	LIBBPF_OPTS(bpf_netkit_opts, optl_nk);
+	LIBBPF_OPTS(bpf_tcx_opts, optl_tcx);
+	int err, ifindex, ifindex2;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+
+	err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
+			    &ifindex, NETKIT_SCRUB_DEFAULT,
+			    NETKIT_SCRUB_DEFAULT, FLAG_SAME_NETNS);
+	if (err)
+		return;
+
+	ifindex2 = if_nametoindex(netkit_peer);
+	ASSERT_NEQ(ifindex, ifindex2, "ifindex_1_2");
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1,
+		  BPF_NETKIT_PRIMARY), 0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc7,
+		  BPF_TCX_INGRESS), 0, "tc7_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	assert_mprog_count_ifindex(ifindex,  BPF_NETKIT_PRIMARY, 0);
+	assert_mprog_count_ifindex(ifindex2, BPF_TCX_INGRESS, 0);
+
+	link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl_nk);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	assert_mprog_count_ifindex(ifindex,  BPF_NETKIT_PRIMARY, 1);
+	assert_mprog_count_ifindex(ifindex2, BPF_TCX_INGRESS, 0);
+
+	link = bpf_program__attach_tcx(skel->progs.tc7, ifindex2, &optl_tcx);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc7 = link;
+
+	assert_mprog_count_ifindex(ifindex,  BPF_NETKIT_PRIMARY, 1);
+	assert_mprog_count_ifindex(ifindex2, BPF_TCX_INGRESS, 1);
+
+	move_netkit();
+
+	tc_skel_reset_all_seen(skel);
+	skel->bss->set_type = true;
+	ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc7, true, "seen_tc7");
+
+	ASSERT_EQ(skel->bss->seen_host,  true, "seen_host");
+	ASSERT_EQ(skel->bss->seen_mcast, true, "seen_mcast");
+cleanup:
+	test_tc_link__destroy(skel);
+
+	assert_mprog_count_ifindex(ifindex,  BPF_NETKIT_PRIMARY, 0);
+	destroy_netkit();
+}
+
+void serial_test_tc_netkit_pkt_type(void)
+{
+	serial_test_tc_netkit_pkt_type_mode(NETKIT_L2);
+	serial_test_tc_netkit_pkt_type_mode(NETKIT_L3);
+}
+
+static void serial_test_tc_netkit_scrub_type(int scrub, bool room)
+{
+	LIBBPF_OPTS(bpf_netkit_opts, optl);
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err, ifindex;
+
+	err = create_netkit(NETKIT_L2, NETKIT_PASS, NETKIT_PASS,
+			    &ifindex, scrub, scrub,
+			    room ? FLAG_ADJUST_ROOM : 0);
+	if (err)
+		return;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc8,
+		  BPF_NETKIT_PRIMARY), 0, "tc8_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+
+	ASSERT_EQ(skel->bss->seen_tc8, false, "seen_tc8");
+
+	link = bpf_program__attach_netkit(skel->progs.tc8, ifindex, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc8 = link;
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc8, true, "seen_tc8");
+	ASSERT_EQ(skel->bss->mark, scrub == NETKIT_SCRUB_NONE ? MARK : 0, "mark");
+	ASSERT_EQ(skel->bss->prio, scrub == NETKIT_SCRUB_NONE ? PRIO : 0, "prio");
+	ASSERT_EQ(skel->bss->headroom, room ? NETKIT_HEADROOM : 0, "headroom");
+	ASSERT_EQ(skel->bss->tailroom, room ? NETKIT_TAILROOM : 0, "tailroom");
+cleanup:
+	test_tc_link__destroy(skel);
+
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0);
+	assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0);
+	destroy_netkit();
+}
+
+void serial_test_tc_netkit_scrub(void)
+{
+	serial_test_tc_netkit_scrub_type(NETKIT_SCRUB_DEFAULT, false);
+	serial_test_tc_netkit_scrub_type(NETKIT_SCRUB_NONE, true);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_opts.c b/tools/testing/selftests/bpf/prog_tests/tc_opts.c
new file mode 100644
index 000000000000..dd7a138d8c3d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tc_opts.c
@@ -0,0 +1,2814 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+#include <uapi/linux/if_link.h>
+#include <net/if.h>
+#include <test_progs.h>
+
+#define loopback 1
+#define ping_cmd "ping -q -c1 -w1 127.0.0.1 > /dev/null"
+
+#include "test_tc_link.skel.h"
+#include "tc_helpers.h"
+
+void test_ns_tc_opts_basic(void)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, id1, id2;
+	struct test_tc_link *skel;
+	__u32 prog_ids[2];
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+
+	assert_mprog_count(BPF_TCX_INGRESS, 0);
+	assert_mprog_count(BPF_TCX_EGRESS, 0);
+
+	ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	err = bpf_prog_attach_opts(fd1, loopback, BPF_TCX_INGRESS, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(BPF_TCX_INGRESS, 1);
+	assert_mprog_count(BPF_TCX_EGRESS, 0);
+
+	optq.prog_ids = prog_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, BPF_TCX_INGRESS, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_in;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 2, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+
+	err = bpf_prog_attach_opts(fd2, loopback, BPF_TCX_EGRESS, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_in;
+
+	assert_mprog_count(BPF_TCX_INGRESS, 1);
+	assert_mprog_count(BPF_TCX_EGRESS, 1);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, BPF_TCX_EGRESS, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_eg;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 2, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+
+cleanup_eg:
+	err = bpf_prog_detach_opts(fd2, loopback, BPF_TCX_EGRESS, &optd);
+	ASSERT_OK(err, "prog_detach_eg");
+
+	assert_mprog_count(BPF_TCX_INGRESS, 1);
+	assert_mprog_count(BPF_TCX_EGRESS, 0);
+
+cleanup_in:
+	err = bpf_prog_detach_opts(fd1, loopback, BPF_TCX_INGRESS, &optd);
+	ASSERT_OK(err, "prog_detach_in");
+
+	assert_mprog_count(BPF_TCX_INGRESS, 0);
+	assert_mprog_count(BPF_TCX_EGRESS, 0);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+static void test_tc_opts_before_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+	struct test_tc_link *skel;
+	__u32 prog_ids[5];
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+	fd3 = bpf_program__fd(skel->progs.tc3);
+	fd4 = bpf_program__fd(skel->progs.tc4);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+	id4 = id_from_prog_fd(fd4);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id3, id4, "prog_ids_3_4");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target;
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target2;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = fd2,
+	);
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target2;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target3;
+
+	ASSERT_EQ(optq.count, 3, "count");
+	ASSERT_EQ(optq.revision, 4, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id2, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], 0, "prog_ids[3]");
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE,
+		.relative_id = id1,
+	);
+
+	err = bpf_prog_attach_opts(fd4, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target3;
+
+	assert_mprog_count(target, 4);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target4;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id4, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id1, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id3, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], id2, "prog_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+
+cleanup_target4:
+	err = bpf_prog_detach_opts(fd4, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 3);
+
+cleanup_target3:
+	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 2);
+
+cleanup_target2:
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 1);
+
+cleanup_target:
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void test_ns_tc_opts_before(void)
+{
+	test_tc_opts_before_target(BPF_TCX_INGRESS);
+	test_tc_opts_before_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_after_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+	struct test_tc_link *skel;
+	__u32 prog_ids[5];
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+	fd3 = bpf_program__fd(skel->progs.tc3);
+	fd4 = bpf_program__fd(skel->progs.tc4);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+	id4 = id_from_prog_fd(fd4);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id3, id4, "prog_ids_3_4");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target;
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target2;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_AFTER,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target2;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target3;
+
+	ASSERT_EQ(optq.count, 3, "count");
+	ASSERT_EQ(optq.revision, 4, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id2, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], 0, "prog_ids[3]");
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_AFTER,
+		.relative_id = id2,
+	);
+
+	err = bpf_prog_attach_opts(fd4, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target3;
+
+	assert_mprog_count(target, 4);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target4;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id2, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+
+cleanup_target4:
+	err = bpf_prog_detach_opts(fd4, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 3);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target3;
+
+	ASSERT_EQ(optq.count, 3, "count");
+	ASSERT_EQ(optq.revision, 6, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id2, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], 0, "prog_ids[3]");
+
+cleanup_target3:
+	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 2);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target2;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 7, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+cleanup_target2:
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 1);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 8, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+
+cleanup_target:
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void test_ns_tc_opts_after(void)
+{
+	test_tc_opts_after_target(BPF_TCX_INGRESS);
+	test_tc_opts_after_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_revision_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, id1, id2;
+	struct test_tc_link *skel;
+	__u32 prog_ids[3];
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.expected_revision = 1,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.expected_revision = 1,
+	);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, -ESTALE, "prog_attach"))
+		goto cleanup_target;
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.expected_revision = 2,
+	);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target;
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target2;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+
+	LIBBPF_OPTS_RESET(optd,
+		.expected_revision = 2,
+	);
+
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_EQ(err, -ESTALE, "prog_detach");
+	assert_mprog_count(target, 2);
+
+cleanup_target2:
+	LIBBPF_OPTS_RESET(optd,
+		.expected_revision = 3,
+	);
+
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 1);
+
+cleanup_target:
+	LIBBPF_OPTS_RESET(optd);
+
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void test_ns_tc_opts_revision(void)
+{
+	test_tc_opts_revision_target(BPF_TCX_INGRESS);
+	test_tc_opts_revision_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_chain_classic(int target, bool chain_tc_old)
+{
+	LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+	LIBBPF_OPTS(bpf_tc_hook, tc_hook, .ifindex = loopback);
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	bool hook_created = false, tc_attached = false;
+	__u32 fd1, fd2, fd3, id1, id2, id3;
+	struct test_tc_link *skel;
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+	fd3 = bpf_program__fd(skel->progs.tc3);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	if (chain_tc_old) {
+		tc_hook.attach_point = target == BPF_TCX_INGRESS ?
+				       BPF_TC_INGRESS : BPF_TC_EGRESS;
+		err = bpf_tc_hook_create(&tc_hook);
+		if (err == 0)
+			hook_created = true;
+		err = err == -EEXIST ? 0 : err;
+		if (!ASSERT_OK(err, "bpf_tc_hook_create"))
+			goto cleanup;
+
+		tc_opts.prog_fd = fd3;
+		err = bpf_tc_attach(&tc_hook, &tc_opts);
+		if (!ASSERT_OK(err, "bpf_tc_attach"))
+			goto cleanup;
+		tc_attached = true;
+	}
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_detach;
+
+	assert_mprog_count(target, 2);
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, chain_tc_old, "seen_tc3");
+
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	if (!ASSERT_OK(err, "prog_detach"))
+		goto cleanup_detach;
+
+	assert_mprog_count(target, 1);
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, chain_tc_old, "seen_tc3");
+
+cleanup_detach:
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	if (!ASSERT_OK(err, "prog_detach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 0);
+cleanup:
+	if (tc_attached) {
+		tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0;
+		err = bpf_tc_detach(&tc_hook, &tc_opts);
+		ASSERT_OK(err, "bpf_tc_detach");
+	}
+	if (hook_created) {
+		tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS;
+		bpf_tc_hook_destroy(&tc_hook);
+	}
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void test_ns_tc_opts_chain_classic(void)
+{
+	test_tc_chain_classic(BPF_TCX_INGRESS, false);
+	test_tc_chain_classic(BPF_TCX_EGRESS, false);
+	test_tc_chain_classic(BPF_TCX_INGRESS, true);
+	test_tc_chain_classic(BPF_TCX_EGRESS, true);
+}
+
+static void test_tc_opts_replace_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, fd3, id1, id2, id3, detach_fd;
+	__u32 prog_ids[4], prog_flags[4];
+	struct test_tc_link *skel;
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+	fd3 = bpf_program__fd(skel->progs.tc3);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.expected_revision = 1,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE,
+		.relative_id = id1,
+		.expected_revision = 2,
+	);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target;
+
+	detach_fd = fd2;
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_attach_flags = prog_flags;
+	optq.prog_ids = prog_ids;
+
+	memset(prog_flags, 0, sizeof(prog_flags));
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target2;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id1, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	ASSERT_EQ(optq.prog_attach_flags[0], 0, "prog_flags[0]");
+	ASSERT_EQ(optq.prog_attach_flags[1], 0, "prog_flags[1]");
+	ASSERT_EQ(optq.prog_attach_flags[2], 0, "prog_flags[2]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE,
+		.replace_prog_fd = fd2,
+		.expected_revision = 3,
+	);
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target2;
+
+	detach_fd = fd3;
+
+	assert_mprog_count(target, 2);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target2;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 4, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id3, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id1, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3");
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE | BPF_F_BEFORE,
+		.replace_prog_fd = fd3,
+		.relative_fd = fd1,
+		.expected_revision = 4,
+	);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target2;
+
+	detach_fd = fd2;
+
+	assert_mprog_count(target, 2);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target2;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id1, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE,
+		.replace_prog_fd = fd2,
+	);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	ASSERT_EQ(err, -EEXIST, "prog_attach");
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE | BPF_F_AFTER,
+		.replace_prog_fd = fd2,
+		.relative_fd = fd1,
+		.expected_revision = 5,
+	);
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	ASSERT_EQ(err, -ERANGE, "prog_attach");
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE | BPF_F_AFTER | BPF_F_REPLACE,
+		.replace_prog_fd = fd2,
+		.relative_fd = fd1,
+		.expected_revision = 5,
+	);
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	ASSERT_EQ(err, -ERANGE, "prog_attach");
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+		.relative_id = id1,
+		.expected_revision = 5,
+	);
+
+cleanup_target2:
+	err = bpf_prog_detach_opts(detach_fd, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 1);
+
+cleanup_target:
+	LIBBPF_OPTS_RESET(optd);
+
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void test_ns_tc_opts_replace(void)
+{
+	test_tc_opts_replace_target(BPF_TCX_INGRESS);
+	test_tc_opts_replace_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_invalid_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	__u32 fd1, fd2, id1, id2;
+	struct test_tc_link *skel;
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE | BPF_F_AFTER,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -ERANGE, "prog_attach");
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE | BPF_F_ID,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -ENOENT, "prog_attach");
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_AFTER | BPF_F_ID,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -ENOENT, "prog_attach");
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.relative_fd = fd2,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -EINVAL, "prog_attach");
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE | BPF_F_AFTER,
+		.relative_fd = fd2,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -ENOENT, "prog_attach");
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_ID,
+		.relative_id = id2,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -EINVAL, "prog_attach");
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -ENOENT, "prog_attach");
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_AFTER,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -ENOENT, "prog_attach");
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(opta);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -EEXIST, "prog_attach");
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -EEXIST, "prog_attach");
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_AFTER,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -EEXIST, "prog_attach");
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -EINVAL, "prog_attach_x1");
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE,
+		.replace_prog_fd = fd1,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	ASSERT_EQ(err, -EEXIST, "prog_attach");
+	assert_mprog_count(target, 1);
+
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void test_ns_tc_opts_invalid(void)
+{
+	test_tc_opts_invalid_target(BPF_TCX_INGRESS);
+	test_tc_opts_invalid_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_prepend_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+	struct test_tc_link *skel;
+	__u32 prog_ids[5];
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+	fd3 = bpf_program__fd(skel->progs.tc3);
+	fd4 = bpf_program__fd(skel->progs.tc4);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+	id4 = id_from_prog_fd(fd4);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id3, id4, "prog_ids_3_4");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE,
+	);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target;
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target2;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id1, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE,
+	);
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target2;
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_BEFORE,
+	);
+
+	err = bpf_prog_attach_opts(fd4, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target3;
+
+	assert_mprog_count(target, 4);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target4;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id4, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id2, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], id1, "prog_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+
+cleanup_target4:
+	err = bpf_prog_detach_opts(fd4, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 3);
+
+cleanup_target3:
+	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 2);
+
+cleanup_target2:
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 1);
+
+cleanup_target:
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void test_ns_tc_opts_prepend(void)
+{
+	test_tc_opts_prepend_target(BPF_TCX_INGRESS);
+	test_tc_opts_prepend_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_append_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+	struct test_tc_link *skel;
+	__u32 prog_ids[5];
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+	fd3 = bpf_program__fd(skel->progs.tc3);
+	fd4 = bpf_program__fd(skel->progs.tc4);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+	id4 = id_from_prog_fd(fd4);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id3, id4, "prog_ids_3_4");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_AFTER,
+	);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target;
+
+	assert_mprog_count(target, 2);
+
+	optq.prog_ids = prog_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target2;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 3, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, false, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_AFTER,
+	);
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target2;
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_AFTER,
+	);
+
+	err = bpf_prog_attach_opts(fd4, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_target3;
+
+	assert_mprog_count(target, 4);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup_target4;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id3, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2");
+	ASSERT_EQ(skel->bss->seen_tc3, true, "seen_tc3");
+	ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+
+cleanup_target4:
+	err = bpf_prog_detach_opts(fd4, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 3);
+
+cleanup_target3:
+	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 2);
+
+cleanup_target2:
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 1);
+
+cleanup_target:
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void test_ns_tc_opts_append(void)
+{
+	test_tc_opts_append_target(BPF_TCX_INGRESS);
+	test_tc_opts_append_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_dev_cleanup_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+	struct test_tc_link *skel;
+	int err, ifindex;
+
+	ASSERT_OK(system("ip link add dev tcx_opts1 type veth peer name tcx_opts2"), "add veth");
+	ifindex = if_nametoindex("tcx_opts1");
+	ASSERT_NEQ(ifindex, 0, "non_zero_ifindex");
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+	fd3 = bpf_program__fd(skel->progs.tc3);
+	fd4 = bpf_program__fd(skel->progs.tc4);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+	id4 = id_from_prog_fd(fd4);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id3, id4, "prog_ids_3_4");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count_ifindex(ifindex, target, 0);
+
+	err = bpf_prog_attach_opts(fd1, ifindex, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count_ifindex(ifindex, target, 1);
+
+	err = bpf_prog_attach_opts(fd2, ifindex, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup1;
+
+	assert_mprog_count_ifindex(ifindex, target, 2);
+
+	err = bpf_prog_attach_opts(fd3, ifindex, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup2;
+
+	assert_mprog_count_ifindex(ifindex, target, 3);
+
+	err = bpf_prog_attach_opts(fd4, ifindex, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup3;
+
+	assert_mprog_count_ifindex(ifindex, target, 4);
+
+	ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth");
+	ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed");
+	ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
+	return;
+cleanup3:
+	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count_ifindex(ifindex, target, 2);
+cleanup2:
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count_ifindex(ifindex, target, 1);
+cleanup1:
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count_ifindex(ifindex, target, 0);
+cleanup:
+	test_tc_link__destroy(skel);
+
+	ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth");
+	ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed");
+	ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
+}
+
+void test_ns_tc_opts_dev_cleanup(void)
+{
+	test_tc_opts_dev_cleanup_target(BPF_TCX_INGRESS);
+	test_tc_opts_dev_cleanup_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_mixed_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	__u32 pid1, pid2, pid3, pid4, lid2, lid4;
+	__u32 prog_flags[4], link_flags[4];
+	__u32 prog_ids[4], link_ids[4];
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	int err, detach_fd;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, target),
+		  0, "tc3_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc4, target),
+		  0, "tc4_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	pid3 = id_from_prog_fd(bpf_program__fd(skel->progs.tc3));
+	pid4 = id_from_prog_fd(bpf_program__fd(skel->progs.tc4));
+
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+	ASSERT_NEQ(pid3, pid4, "prog_ids_3_4");
+	ASSERT_NEQ(pid2, pid3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	err = bpf_prog_attach_opts(bpf_program__fd(skel->progs.tc1),
+				   loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	detach_fd = bpf_program__fd(skel->progs.tc1);
+
+	assert_mprog_count(target, 1);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup1;
+	skel->links.tc2 = link;
+
+	lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2));
+
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE,
+		.replace_prog_fd = bpf_program__fd(skel->progs.tc1),
+	);
+
+	err = bpf_prog_attach_opts(bpf_program__fd(skel->progs.tc2),
+				   loopback, target, &opta);
+	ASSERT_EQ(err, -EEXIST, "prog_attach");
+
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE,
+		.replace_prog_fd = bpf_program__fd(skel->progs.tc2),
+	);
+
+	err = bpf_prog_attach_opts(bpf_program__fd(skel->progs.tc1),
+				   loopback, target, &opta);
+	ASSERT_EQ(err, -EEXIST, "prog_attach");
+
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE,
+		.replace_prog_fd = bpf_program__fd(skel->progs.tc2),
+	);
+
+	err = bpf_prog_attach_opts(bpf_program__fd(skel->progs.tc3),
+				   loopback, target, &opta);
+	ASSERT_EQ(err, -EBUSY, "prog_attach");
+
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE,
+		.replace_prog_fd = bpf_program__fd(skel->progs.tc1),
+	);
+
+	err = bpf_prog_attach_opts(bpf_program__fd(skel->progs.tc3),
+				   loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup1;
+
+	detach_fd = bpf_program__fd(skel->progs.tc3);
+
+	assert_mprog_count(target, 2);
+
+	link = bpf_program__attach_tcx(skel->progs.tc4, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup1;
+	skel->links.tc4 = link;
+
+	lid4 = id_from_link_fd(bpf_link__fd(skel->links.tc4));
+
+	assert_mprog_count(target, 3);
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE,
+		.replace_prog_fd = bpf_program__fd(skel->progs.tc4),
+	);
+
+	err = bpf_prog_attach_opts(bpf_program__fd(skel->progs.tc2),
+				   loopback, target, &opta);
+	ASSERT_EQ(err, -EEXIST, "prog_attach");
+
+	optq.prog_ids = prog_ids;
+	optq.prog_attach_flags = prog_flags;
+	optq.link_ids = link_ids;
+	optq.link_attach_flags = link_flags;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	memset(prog_flags, 0, sizeof(prog_flags));
+	memset(link_ids, 0, sizeof(link_ids));
+	memset(link_flags, 0, sizeof(link_flags));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup1;
+
+	ASSERT_EQ(optq.count, 3, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], pid3, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_attach_flags[0], 0, "prog_flags[0]");
+	ASSERT_EQ(optq.link_ids[0], 0, "link_ids[0]");
+	ASSERT_EQ(optq.link_attach_flags[0], 0, "link_flags[0]");
+	ASSERT_EQ(optq.prog_ids[1], pid2, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_attach_flags[1], 0, "prog_flags[1]");
+	ASSERT_EQ(optq.link_ids[1], lid2, "link_ids[1]");
+	ASSERT_EQ(optq.link_attach_flags[1], 0, "link_flags[1]");
+	ASSERT_EQ(optq.prog_ids[2], pid4, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_attach_flags[2], 0, "prog_flags[2]");
+	ASSERT_EQ(optq.link_ids[2], lid4, "link_ids[2]");
+	ASSERT_EQ(optq.link_attach_flags[2], 0, "link_flags[2]");
+	ASSERT_EQ(optq.prog_ids[3], 0, "prog_ids[3]");
+	ASSERT_EQ(optq.prog_attach_flags[3], 0, "prog_flags[3]");
+	ASSERT_EQ(optq.link_ids[3], 0, "link_ids[3]");
+	ASSERT_EQ(optq.link_attach_flags[3], 0, "link_flags[3]");
+
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+cleanup1:
+	err = bpf_prog_detach_opts(detach_fd, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 2);
+
+cleanup:
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void test_ns_tc_opts_mixed(void)
+{
+	test_tc_opts_mixed_target(BPF_TCX_INGRESS);
+	test_tc_opts_mixed_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_demixed_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_tcx_opts, optl);
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+	__u32 pid1, pid2;
+	int err;
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, target),
+		  0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, target),
+		  0, "tc2_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1));
+	pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2));
+	ASSERT_NEQ(pid1, pid2, "prog_ids_1_2");
+
+	assert_mprog_count(target, 0);
+
+	err = bpf_prog_attach_opts(bpf_program__fd(skel->progs.tc1),
+				   loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	link = bpf_program__attach_tcx(skel->progs.tc2, loopback, &optl);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup1;
+	skel->links.tc2 = link;
+
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+	);
+
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_EQ(err, -EBUSY, "prog_detach");
+
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+	);
+
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 1);
+	goto cleanup;
+
+cleanup1:
+	err = bpf_prog_detach_opts(bpf_program__fd(skel->progs.tc1),
+				   loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 2);
+
+cleanup:
+	test_tc_link__destroy(skel);
+	assert_mprog_count(target, 0);
+}
+
+void test_ns_tc_opts_demixed(void)
+{
+	test_tc_opts_demixed_target(BPF_TCX_INGRESS);
+	test_tc_opts_demixed_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_detach_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+	struct test_tc_link *skel;
+	__u32 prog_ids[5];
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+	fd3 = bpf_program__fd(skel->progs.tc3);
+	fd4 = bpf_program__fd(skel->progs.tc4);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+	id4 = id_from_prog_fd(fd4);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id3, id4, "prog_ids_3_4");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup1;
+
+	assert_mprog_count(target, 2);
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup2;
+
+	assert_mprog_count(target, 3);
+
+	err = bpf_prog_attach_opts(fd4, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup3;
+
+	assert_mprog_count(target, 4);
+
+	optq.prog_ids = prog_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id3, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+	);
+
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 3);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 3, "count");
+	ASSERT_EQ(optq.revision, 6, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id4, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], 0, "prog_ids[3]");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+	);
+
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 2);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 7, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	LIBBPF_OPTS_RESET(optd);
+
+	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 1);
+
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+	);
+
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_EQ(err, -ENOENT, "prog_detach");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+	);
+
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_EQ(err, -ENOENT, "prog_detach");
+	goto cleanup;
+
+cleanup4:
+	err = bpf_prog_detach_opts(fd4, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 3);
+
+cleanup3:
+	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 2);
+
+cleanup2:
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 1);
+
+cleanup1:
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void test_ns_tc_opts_detach(void)
+{
+	test_tc_opts_detach_target(BPF_TCX_INGRESS);
+	test_tc_opts_detach_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_detach_before_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+	struct test_tc_link *skel;
+	__u32 prog_ids[5];
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+	fd3 = bpf_program__fd(skel->progs.tc3);
+	fd4 = bpf_program__fd(skel->progs.tc4);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+	id4 = id_from_prog_fd(fd4);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id3, id4, "prog_ids_3_4");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup1;
+
+	assert_mprog_count(target, 2);
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup2;
+
+	assert_mprog_count(target, 3);
+
+	err = bpf_prog_attach_opts(fd4, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup3;
+
+	assert_mprog_count(target, 4);
+
+	optq.prog_ids = prog_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id3, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = fd2,
+	);
+
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 3);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 3, "count");
+	ASSERT_EQ(optq.revision, 6, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id4, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], 0, "prog_ids[3]");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = fd2,
+	);
+
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_EQ(err, -ENOENT, "prog_detach");
+	assert_mprog_count(target, 3);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = fd4,
+	);
+
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_EQ(err, -ERANGE, "prog_detach");
+	assert_mprog_count(target, 3);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_EQ(err, -ENOENT, "prog_detach");
+	assert_mprog_count(target, 3);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = fd3,
+	);
+
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 2);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 7, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id3, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id4, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+		.relative_fd = fd4,
+	);
+
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 1);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 8, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id4, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_BEFORE,
+	);
+
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 0);
+	goto cleanup;
+
+cleanup4:
+	err = bpf_prog_detach_opts(fd4, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 3);
+
+cleanup3:
+	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 2);
+
+cleanup2:
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 1);
+
+cleanup1:
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void test_ns_tc_opts_detach_before(void)
+{
+	test_tc_opts_detach_before_target(BPF_TCX_INGRESS);
+	test_tc_opts_detach_before_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_detach_after_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+	struct test_tc_link *skel;
+	__u32 prog_ids[5];
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+	fd3 = bpf_program__fd(skel->progs.tc3);
+	fd4 = bpf_program__fd(skel->progs.tc4);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+	id4 = id_from_prog_fd(fd4);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id3, id4, "prog_ids_3_4");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup1;
+
+	assert_mprog_count(target, 2);
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup2;
+
+	assert_mprog_count(target, 3);
+
+	err = bpf_prog_attach_opts(fd4, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup3;
+
+	assert_mprog_count(target, 4);
+
+	optq.prog_ids = prog_ids;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id3, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 3);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 3, "count");
+	ASSERT_EQ(optq.revision, 6, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id4, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], 0, "prog_ids[3]");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_EQ(err, -ENOENT, "prog_detach");
+	assert_mprog_count(target, 3);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+		.relative_fd = fd4,
+	);
+
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_EQ(err, -ERANGE, "prog_detach");
+	assert_mprog_count(target, 3);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+		.relative_fd = fd3,
+	);
+
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_EQ(err, -ERANGE, "prog_detach");
+	assert_mprog_count(target, 3);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_EQ(err, -ERANGE, "prog_detach");
+	assert_mprog_count(target, 3);
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 2);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 2, "count");
+	ASSERT_EQ(optq.revision, 7, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id4, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+		.relative_fd = fd1,
+	);
+
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 1);
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 8, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+
+	LIBBPF_OPTS_RESET(optd,
+		.flags = BPF_F_AFTER,
+	);
+
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+
+	assert_mprog_count(target, 0);
+	goto cleanup;
+
+cleanup4:
+	err = bpf_prog_detach_opts(fd4, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 3);
+
+cleanup3:
+	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 2);
+
+cleanup2:
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 1);
+
+cleanup1:
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void test_ns_tc_opts_detach_after(void)
+{
+	test_tc_opts_detach_after_target(BPF_TCX_INGRESS);
+	test_tc_opts_detach_after_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_delete_empty(int target, bool chain_tc_old)
+{
+	LIBBPF_OPTS(bpf_tc_hook, tc_hook, .ifindex = loopback);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	int err;
+
+	assert_mprog_count(target, 0);
+	if (chain_tc_old) {
+		tc_hook.attach_point = target == BPF_TCX_INGRESS ?
+				       BPF_TC_INGRESS : BPF_TC_EGRESS;
+		err = bpf_tc_hook_create(&tc_hook);
+		ASSERT_OK(err, "bpf_tc_hook_create");
+		assert_mprog_count(target, 0);
+	}
+	err = bpf_prog_detach_opts(0, loopback, target, &optd);
+	ASSERT_EQ(err, -ENOENT, "prog_detach");
+	if (chain_tc_old) {
+		tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS;
+		bpf_tc_hook_destroy(&tc_hook);
+	}
+	assert_mprog_count(target, 0);
+}
+
+void test_ns_tc_opts_delete_empty(void)
+{
+	test_tc_opts_delete_empty(BPF_TCX_INGRESS, false);
+	test_tc_opts_delete_empty(BPF_TCX_EGRESS, false);
+	test_tc_opts_delete_empty(BPF_TCX_INGRESS, true);
+	test_tc_opts_delete_empty(BPF_TCX_EGRESS, true);
+}
+
+static void test_tc_chain_mixed(int target)
+{
+	LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+	LIBBPF_OPTS(bpf_tc_hook, tc_hook, .ifindex = loopback);
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	__u32 fd1, fd2, fd3, id1, id2, id3;
+	struct test_tc_link *skel;
+	int err, detach_fd;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc4);
+	fd2 = bpf_program__fd(skel->progs.tc5);
+	fd3 = bpf_program__fd(skel->progs.tc6);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+
+	ASSERT_NEQ(id1, id2, "prog_ids_1_2");
+	ASSERT_NEQ(id2, id3, "prog_ids_2_3");
+
+	assert_mprog_count(target, 0);
+
+	tc_hook.attach_point = target == BPF_TCX_INGRESS ?
+			       BPF_TC_INGRESS : BPF_TC_EGRESS;
+	err = bpf_tc_hook_create(&tc_hook);
+	err = err == -EEXIST ? 0 : err;
+	if (!ASSERT_OK(err, "bpf_tc_hook_create"))
+		goto cleanup;
+
+	tc_opts.prog_fd = fd2;
+	err = bpf_tc_attach(&tc_hook, &tc_opts);
+	if (!ASSERT_OK(err, "bpf_tc_attach"))
+		goto cleanup_hook;
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_filter;
+
+	detach_fd = fd3;
+
+	assert_mprog_count(target, 1);
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+	ASSERT_EQ(skel->bss->seen_tc5, false, "seen_tc5");
+	ASSERT_EQ(skel->bss->seen_tc6, true, "seen_tc6");
+
+	LIBBPF_OPTS_RESET(opta,
+		.flags = BPF_F_REPLACE,
+		.replace_prog_fd = fd3,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup_opts;
+
+	detach_fd = fd1;
+
+	assert_mprog_count(target, 1);
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc4, true, "seen_tc4");
+	ASSERT_EQ(skel->bss->seen_tc5, true, "seen_tc5");
+	ASSERT_EQ(skel->bss->seen_tc6, false, "seen_tc6");
+
+cleanup_opts:
+	err = bpf_prog_detach_opts(detach_fd, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+	tc_skel_reset_all_seen(skel);
+	ASSERT_OK(system(ping_cmd), ping_cmd);
+
+	ASSERT_EQ(skel->bss->seen_tc4, false, "seen_tc4");
+	ASSERT_EQ(skel->bss->seen_tc5, true, "seen_tc5");
+	ASSERT_EQ(skel->bss->seen_tc6, false, "seen_tc6");
+
+cleanup_filter:
+	tc_opts.flags = tc_opts.prog_fd = tc_opts.prog_id = 0;
+	err = bpf_tc_detach(&tc_hook, &tc_opts);
+	ASSERT_OK(err, "bpf_tc_detach");
+
+cleanup_hook:
+	tc_hook.attach_point = BPF_TC_INGRESS | BPF_TC_EGRESS;
+	bpf_tc_hook_destroy(&tc_hook);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void test_ns_tc_opts_chain_mixed(void)
+{
+	test_tc_chain_mixed(BPF_TCX_INGRESS);
+	test_tc_chain_mixed(BPF_TCX_EGRESS);
+}
+
+static int generate_dummy_prog(void)
+{
+	const struct bpf_insn prog_insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	const size_t prog_insn_cnt = ARRAY_SIZE(prog_insns);
+	LIBBPF_OPTS(bpf_prog_load_opts, opts);
+	const size_t log_buf_sz = 256;
+	char log_buf[log_buf_sz];
+	int fd = -1;
+
+	opts.log_buf = log_buf;
+	opts.log_size = log_buf_sz;
+
+	log_buf[0] = '\0';
+	opts.log_level = 0;
+	fd = bpf_prog_load(BPF_PROG_TYPE_SCHED_CLS, "tcx_prog", "GPL",
+			   prog_insns, prog_insn_cnt, &opts);
+	ASSERT_STREQ(log_buf, "", "log_0");
+	ASSERT_GE(fd, 0, "prog_fd");
+	return fd;
+}
+
+static void test_tc_opts_max_target(int target, int flags, bool relative)
+{
+	int err, ifindex, i, prog_fd, last_fd = -1;
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	const int max_progs = 63;
+
+	ASSERT_OK(system("ip link add dev tcx_opts1 type veth peer name tcx_opts2"), "add veth");
+	ifindex = if_nametoindex("tcx_opts1");
+	ASSERT_NEQ(ifindex, 0, "non_zero_ifindex");
+
+	assert_mprog_count_ifindex(ifindex, target, 0);
+
+	for (i = 0; i < max_progs; i++) {
+		prog_fd = generate_dummy_prog();
+		if (!ASSERT_GE(prog_fd, 0, "dummy_prog"))
+			goto cleanup;
+		err = bpf_prog_attach_opts(prog_fd, ifindex, target, &opta);
+		if (!ASSERT_EQ(err, 0, "prog_attach"))
+			goto cleanup;
+		assert_mprog_count_ifindex(ifindex, target, i + 1);
+		if (i == max_progs - 1 && relative)
+			last_fd = prog_fd;
+		else
+			close(prog_fd);
+	}
+
+	prog_fd = generate_dummy_prog();
+	if (!ASSERT_GE(prog_fd, 0, "dummy_prog"))
+		goto cleanup;
+	opta.flags = flags;
+	if (last_fd > 0)
+		opta.relative_fd = last_fd;
+	err = bpf_prog_attach_opts(prog_fd, ifindex, target, &opta);
+	ASSERT_EQ(err, -ERANGE, "prog_64_attach");
+	assert_mprog_count_ifindex(ifindex, target, max_progs);
+	close(prog_fd);
+cleanup:
+	if (last_fd > 0)
+		close(last_fd);
+	ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth");
+	ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed");
+	ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed");
+}
+
+void test_ns_tc_opts_max(void)
+{
+	test_tc_opts_max_target(BPF_TCX_INGRESS, 0, false);
+	test_tc_opts_max_target(BPF_TCX_EGRESS, 0, false);
+
+	test_tc_opts_max_target(BPF_TCX_INGRESS, BPF_F_BEFORE, false);
+	test_tc_opts_max_target(BPF_TCX_EGRESS, BPF_F_BEFORE, true);
+
+	test_tc_opts_max_target(BPF_TCX_INGRESS, BPF_F_AFTER, true);
+	test_tc_opts_max_target(BPF_TCX_EGRESS, BPF_F_AFTER, false);
+}
+
+static void test_tc_opts_query_target(int target)
+{
+	const size_t attr_size = offsetofend(union bpf_attr, query);
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	__u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+	struct test_tc_link *skel;
+	union bpf_attr attr;
+	__u32 prog_ids[10];
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	fd2 = bpf_program__fd(skel->progs.tc2);
+	fd3 = bpf_program__fd(skel->progs.tc3);
+	fd4 = bpf_program__fd(skel->progs.tc4);
+
+	id1 = id_from_prog_fd(fd1);
+	id2 = id_from_prog_fd(fd2);
+	id3 = id_from_prog_fd(fd3);
+	id4 = id_from_prog_fd(fd4);
+
+	assert_mprog_count(target, 0);
+
+	LIBBPF_OPTS_RESET(opta,
+		.expected_revision = 1,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	assert_mprog_count(target, 1);
+
+	LIBBPF_OPTS_RESET(opta,
+		.expected_revision = 2,
+	);
+
+	err = bpf_prog_attach_opts(fd2, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup1;
+
+	assert_mprog_count(target, 2);
+
+	LIBBPF_OPTS_RESET(opta,
+		.expected_revision = 3,
+	);
+
+	err = bpf_prog_attach_opts(fd3, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup2;
+
+	assert_mprog_count(target, 3);
+
+	LIBBPF_OPTS_RESET(opta,
+		.expected_revision = 4,
+	);
+
+	err = bpf_prog_attach_opts(fd4, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup3;
+
+	assert_mprog_count(target, 4);
+
+	/* Test 1: Double query via libbpf API */
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids, NULL, "prog_ids");
+	ASSERT_EQ(optq.link_ids, NULL, "link_ids");
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.prog_ids = prog_ids;
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(optq.count, 4, "count");
+	ASSERT_EQ(optq.revision, 5, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(optq.prog_ids[2], id3, "prog_ids[2]");
+	ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]");
+	ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+	ASSERT_EQ(optq.link_ids, NULL, "link_ids");
+
+	/* Test 2: Double query via bpf_attr & bpf(2) directly */
+	memset(&attr, 0, attr_size);
+	attr.query.target_ifindex = loopback;
+	attr.query.attach_type = target;
+
+	err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(attr.query.count, 4, "count");
+	ASSERT_EQ(attr.query.revision, 5, "revision");
+	ASSERT_EQ(attr.query.query_flags, 0, "query_flags");
+	ASSERT_EQ(attr.query.attach_flags, 0, "attach_flags");
+	ASSERT_EQ(attr.query.target_ifindex, loopback, "target_ifindex");
+	ASSERT_EQ(attr.query.attach_type, target, "attach_type");
+	ASSERT_EQ(attr.query.prog_ids, 0, "prog_ids");
+	ASSERT_EQ(attr.query.prog_attach_flags, 0, "prog_attach_flags");
+	ASSERT_EQ(attr.query.link_ids, 0, "link_ids");
+	ASSERT_EQ(attr.query.link_attach_flags, 0, "link_attach_flags");
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	attr.query.prog_ids = ptr_to_u64(prog_ids);
+
+	err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(attr.query.count, 4, "count");
+	ASSERT_EQ(attr.query.revision, 5, "revision");
+	ASSERT_EQ(attr.query.query_flags, 0, "query_flags");
+	ASSERT_EQ(attr.query.attach_flags, 0, "attach_flags");
+	ASSERT_EQ(attr.query.target_ifindex, loopback, "target_ifindex");
+	ASSERT_EQ(attr.query.attach_type, target, "attach_type");
+	ASSERT_EQ(attr.query.prog_ids, ptr_to_u64(prog_ids), "prog_ids");
+	ASSERT_EQ(prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(prog_ids[2], id3, "prog_ids[2]");
+	ASSERT_EQ(prog_ids[3], id4, "prog_ids[3]");
+	ASSERT_EQ(prog_ids[4], 0, "prog_ids[4]");
+	ASSERT_EQ(attr.query.prog_attach_flags, 0, "prog_attach_flags");
+	ASSERT_EQ(attr.query.link_ids, 0, "link_ids");
+	ASSERT_EQ(attr.query.link_attach_flags, 0, "link_attach_flags");
+
+	/* Test 3: Query with smaller prog_ids array */
+	memset(&attr, 0, attr_size);
+	attr.query.target_ifindex = loopback;
+	attr.query.attach_type = target;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	attr.query.prog_ids = ptr_to_u64(prog_ids);
+	attr.query.count = 2;
+
+	err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size);
+	ASSERT_EQ(err, -1, "prog_query_should_fail");
+	ASSERT_EQ(errno, ENOSPC, "prog_query_should_fail");
+
+	ASSERT_EQ(attr.query.count, 4, "count");
+	ASSERT_EQ(attr.query.revision, 5, "revision");
+	ASSERT_EQ(attr.query.query_flags, 0, "query_flags");
+	ASSERT_EQ(attr.query.attach_flags, 0, "attach_flags");
+	ASSERT_EQ(attr.query.target_ifindex, loopback, "target_ifindex");
+	ASSERT_EQ(attr.query.attach_type, target, "attach_type");
+	ASSERT_EQ(attr.query.prog_ids, ptr_to_u64(prog_ids), "prog_ids");
+	ASSERT_EQ(prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(prog_ids[3], 0, "prog_ids[3]");
+	ASSERT_EQ(prog_ids[4], 0, "prog_ids[4]");
+	ASSERT_EQ(attr.query.prog_attach_flags, 0, "prog_attach_flags");
+	ASSERT_EQ(attr.query.link_ids, 0, "link_ids");
+	ASSERT_EQ(attr.query.link_attach_flags, 0, "link_attach_flags");
+
+	/* Test 4: Query with larger prog_ids array */
+	memset(&attr, 0, attr_size);
+	attr.query.target_ifindex = loopback;
+	attr.query.attach_type = target;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	attr.query.prog_ids = ptr_to_u64(prog_ids);
+	attr.query.count = 10;
+
+	err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(attr.query.count, 4, "count");
+	ASSERT_EQ(attr.query.revision, 5, "revision");
+	ASSERT_EQ(attr.query.query_flags, 0, "query_flags");
+	ASSERT_EQ(attr.query.attach_flags, 0, "attach_flags");
+	ASSERT_EQ(attr.query.target_ifindex, loopback, "target_ifindex");
+	ASSERT_EQ(attr.query.attach_type, target, "attach_type");
+	ASSERT_EQ(attr.query.prog_ids, ptr_to_u64(prog_ids), "prog_ids");
+	ASSERT_EQ(prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(prog_ids[1], id2, "prog_ids[1]");
+	ASSERT_EQ(prog_ids[2], id3, "prog_ids[2]");
+	ASSERT_EQ(prog_ids[3], id4, "prog_ids[3]");
+	ASSERT_EQ(prog_ids[4], 0, "prog_ids[4]");
+	ASSERT_EQ(attr.query.prog_attach_flags, 0, "prog_attach_flags");
+	ASSERT_EQ(attr.query.link_ids, 0, "link_ids");
+	ASSERT_EQ(attr.query.link_attach_flags, 0, "link_attach_flags");
+
+	/* Test 5: Query with NULL prog_ids array but with count > 0 */
+	memset(&attr, 0, attr_size);
+	attr.query.target_ifindex = loopback;
+	attr.query.attach_type = target;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	attr.query.count = sizeof(prog_ids);
+
+	err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(attr.query.count, 4, "count");
+	ASSERT_EQ(attr.query.revision, 5, "revision");
+	ASSERT_EQ(attr.query.query_flags, 0, "query_flags");
+	ASSERT_EQ(attr.query.attach_flags, 0, "attach_flags");
+	ASSERT_EQ(attr.query.target_ifindex, loopback, "target_ifindex");
+	ASSERT_EQ(attr.query.attach_type, target, "attach_type");
+	ASSERT_EQ(prog_ids[0], 0, "prog_ids[0]");
+	ASSERT_EQ(prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(prog_ids[3], 0, "prog_ids[3]");
+	ASSERT_EQ(prog_ids[4], 0, "prog_ids[4]");
+	ASSERT_EQ(attr.query.prog_ids, 0, "prog_ids");
+	ASSERT_EQ(attr.query.prog_attach_flags, 0, "prog_attach_flags");
+	ASSERT_EQ(attr.query.link_ids, 0, "link_ids");
+	ASSERT_EQ(attr.query.link_attach_flags, 0, "link_attach_flags");
+
+	/* Test 6: Query with non-NULL prog_ids array but with count == 0 */
+	memset(&attr, 0, attr_size);
+	attr.query.target_ifindex = loopback;
+	attr.query.attach_type = target;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	attr.query.prog_ids = ptr_to_u64(prog_ids);
+
+	err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup4;
+
+	ASSERT_EQ(attr.query.count, 4, "count");
+	ASSERT_EQ(attr.query.revision, 5, "revision");
+	ASSERT_EQ(attr.query.query_flags, 0, "query_flags");
+	ASSERT_EQ(attr.query.attach_flags, 0, "attach_flags");
+	ASSERT_EQ(attr.query.target_ifindex, loopback, "target_ifindex");
+	ASSERT_EQ(attr.query.attach_type, target, "attach_type");
+	ASSERT_EQ(prog_ids[0], 0, "prog_ids[0]");
+	ASSERT_EQ(prog_ids[1], 0, "prog_ids[1]");
+	ASSERT_EQ(prog_ids[2], 0, "prog_ids[2]");
+	ASSERT_EQ(prog_ids[3], 0, "prog_ids[3]");
+	ASSERT_EQ(prog_ids[4], 0, "prog_ids[4]");
+	ASSERT_EQ(attr.query.prog_ids, ptr_to_u64(prog_ids), "prog_ids");
+	ASSERT_EQ(attr.query.prog_attach_flags, 0, "prog_attach_flags");
+	ASSERT_EQ(attr.query.link_ids, 0, "link_ids");
+	ASSERT_EQ(attr.query.link_attach_flags, 0, "link_attach_flags");
+
+	/* Test 7: Query with invalid flags */
+	attr.query.attach_flags = 0;
+	attr.query.query_flags = 1;
+
+	err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size);
+	ASSERT_EQ(err, -1, "prog_query_should_fail");
+	ASSERT_EQ(errno, EINVAL, "prog_query_should_fail");
+
+	attr.query.attach_flags = 1;
+	attr.query.query_flags = 0;
+
+	err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size);
+	ASSERT_EQ(err, -1, "prog_query_should_fail");
+	ASSERT_EQ(errno, EINVAL, "prog_query_should_fail");
+
+cleanup4:
+	err = bpf_prog_detach_opts(fd4, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 3);
+
+cleanup3:
+	err = bpf_prog_detach_opts(fd3, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 2);
+
+cleanup2:
+	err = bpf_prog_detach_opts(fd2, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 1);
+
+cleanup1:
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void test_ns_tc_opts_query(void)
+{
+	test_tc_opts_query_target(BPF_TCX_INGRESS);
+	test_tc_opts_query_target(BPF_TCX_EGRESS);
+}
+
+static void test_tc_opts_query_attach_target(int target)
+{
+	LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+	LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+	LIBBPF_OPTS(bpf_prog_query_opts, optq);
+	struct test_tc_link *skel;
+	__u32 prog_ids[2];
+	__u32 fd1, id1;
+	int err;
+
+	skel = test_tc_link__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	fd1 = bpf_program__fd(skel->progs.tc1);
+	id1 = id_from_prog_fd(fd1);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup;
+
+	ASSERT_EQ(optq.count, 0, "count");
+	ASSERT_EQ(optq.revision, 1, "revision");
+
+	LIBBPF_OPTS_RESET(opta,
+		.expected_revision = optq.revision,
+	);
+
+	err = bpf_prog_attach_opts(fd1, loopback, target, &opta);
+	if (!ASSERT_EQ(err, 0, "prog_attach"))
+		goto cleanup;
+
+	memset(prog_ids, 0, sizeof(prog_ids));
+	optq.prog_ids = prog_ids;
+	optq.count = ARRAY_SIZE(prog_ids);
+
+	err = bpf_prog_query_opts(loopback, target, &optq);
+	if (!ASSERT_OK(err, "prog_query"))
+		goto cleanup1;
+
+	ASSERT_EQ(optq.count, 1, "count");
+	ASSERT_EQ(optq.revision, 2, "revision");
+	ASSERT_EQ(optq.prog_ids[0], id1, "prog_ids[0]");
+	ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]");
+
+cleanup1:
+	err = bpf_prog_detach_opts(fd1, loopback, target, &optd);
+	ASSERT_OK(err, "prog_detach");
+	assert_mprog_count(target, 0);
+cleanup:
+	test_tc_link__destroy(skel);
+}
+
+void test_ns_tc_opts_query_attach(void)
+{
+	test_tc_opts_query_attach_target(BPF_TCX_INGRESS);
+	test_tc_opts_query_attach_target(BPF_TCX_EGRESS);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
index bca5e6839ac4..76d72a59365e 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
@@ -24,6 +24,7 @@
 
 #include "test_progs.h"
 #include "network_helpers.h"
+#include "netlink_helpers.h"
 #include "test_tc_neigh_fib.skel.h"
 #include "test_tc_neigh.skel.h"
 #include "test_tc_peer.skel.h"
@@ -55,6 +56,8 @@
 
 #define MAC_DST_FWD "00:11:22:33:44:55"
 #define MAC_DST "00:22:33:44:55:66"
+#define MAC_SRC_FWD "00:33:44:55:66:77"
+#define MAC_SRC "00:44:55:66:77:88"
 
 #define IFADDR_STR_LEN 18
 #define PING_ARGS "-i 0.2 -c 3 -w 10 -q"
@@ -67,6 +70,7 @@
 		__FILE__, __LINE__, strerror(errno), ##__VA_ARGS__)
 
 static const char * const namespaces[] = {NS_SRC, NS_FWD, NS_DST, NULL};
+static struct netns_obj *netns_objs[3];
 
 static int write_file(const char *path, const char *newval)
 {
@@ -86,35 +90,55 @@ static int write_file(const char *path, const char *newval)
 
 static int netns_setup_namespaces(const char *verb)
 {
+	struct netns_obj **ns_obj = netns_objs;
 	const char * const *ns = namespaces;
-	char cmd[128];
 
 	while (*ns) {
-		snprintf(cmd, sizeof(cmd), "ip netns %s %s", verb, *ns);
-		if (!ASSERT_OK(system(cmd), cmd))
-			return -1;
+		if (strcmp(verb, "add") == 0) {
+			*ns_obj = netns_new(*ns, false);
+			if (!ASSERT_OK_PTR(*ns_obj, "netns_new"))
+				return -1;
+		} else {
+			if (!ASSERT_OK_PTR(*ns_obj, "netns_obj is NULL"))
+				return -1;
+			netns_free(*ns_obj);
+			*ns_obj = NULL;
+		}
 		ns++;
+		ns_obj++;
 	}
 	return 0;
 }
 
 static void netns_setup_namespaces_nofail(const char *verb)
 {
+	struct netns_obj **ns_obj = netns_objs;
 	const char * const *ns = namespaces;
-	char cmd[128];
 
 	while (*ns) {
-		snprintf(cmd, sizeof(cmd), "ip netns %s %s > /dev/null 2>&1", verb, *ns);
-		system(cmd);
+		if (strcmp(verb, "add") == 0) {
+			*ns_obj = netns_new(*ns, false);
+		} else {
+			if (*ns_obj)
+				netns_free(*ns_obj);
+			*ns_obj = NULL;
+		}
 		ns++;
+		ns_obj++;
 	}
 }
 
+enum dev_mode {
+	MODE_VETH,
+	MODE_NETKIT,
+};
+
 struct netns_setup_result {
-	int ifindex_veth_src;
-	int ifindex_veth_src_fwd;
-	int ifindex_veth_dst;
-	int ifindex_veth_dst_fwd;
+	enum dev_mode dev_mode;
+	int ifindex_src;
+	int ifindex_src_fwd;
+	int ifindex_dst;
+	int ifindex_dst_fwd;
 };
 
 static int get_ifaddr(const char *name, char *ifaddr)
@@ -137,66 +161,113 @@ static int get_ifaddr(const char *name, char *ifaddr)
 	return 0;
 }
 
-#define SYS(fmt, ...)						\
-	({							\
-		char cmd[1024];					\
-		snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__);	\
-		if (!ASSERT_OK(system(cmd), cmd))		\
-			goto fail;				\
-	})
+static int create_netkit(int mode, char *prim, char *peer)
+{
+	struct rtattr *linkinfo, *data, *peer_info;
+	struct rtnl_handle rth = { .fd = -1 };
+	const char *type = "netkit";
+	struct {
+		struct nlmsghdr n;
+		struct ifinfomsg i;
+		char buf[1024];
+	} req = {};
+	int err;
+
+	err = rtnl_open(&rth, 0);
+	if (!ASSERT_OK(err, "open_rtnetlink"))
+		return err;
+
+	memset(&req, 0, sizeof(req));
+	req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+	req.n.nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE | NLM_F_EXCL;
+	req.n.nlmsg_type = RTM_NEWLINK;
+	req.i.ifi_family = AF_UNSPEC;
+
+	addattr_l(&req.n, sizeof(req), IFLA_IFNAME, prim, strlen(prim));
+	linkinfo = addattr_nest(&req.n, sizeof(req), IFLA_LINKINFO);
+	addattr_l(&req.n, sizeof(req), IFLA_INFO_KIND, type, strlen(type));
+	data = addattr_nest(&req.n, sizeof(req), IFLA_INFO_DATA);
+	addattr32(&req.n, sizeof(req), IFLA_NETKIT_MODE, mode);
+	peer_info = addattr_nest(&req.n, sizeof(req), IFLA_NETKIT_PEER_INFO);
+	req.n.nlmsg_len += sizeof(struct ifinfomsg);
+	addattr_l(&req.n, sizeof(req), IFLA_IFNAME, peer, strlen(peer));
+	addattr_nest_end(&req.n, peer_info);
+	addattr_nest_end(&req.n, data);
+	addattr_nest_end(&req.n, linkinfo);
+
+	err = rtnl_talk(&rth, &req.n, NULL);
+	ASSERT_OK(err, "talk_rtnetlink");
+	rtnl_close(&rth);
+	return err;
+}
 
 static int netns_setup_links_and_routes(struct netns_setup_result *result)
 {
 	struct nstoken *nstoken = NULL;
-	char veth_src_fwd_addr[IFADDR_STR_LEN+1] = {};
+	char src_fwd_addr[IFADDR_STR_LEN+1] = {};
+	char src_addr[IFADDR_STR_LEN + 1] = {};
+	int err;
 
-	SYS("ip link add veth_src type veth peer name veth_src_fwd");
-	SYS("ip link add veth_dst type veth peer name veth_dst_fwd");
+	if (result->dev_mode == MODE_VETH) {
+		SYS(fail, "ip link add src address " MAC_SRC " type veth "
+			  "peer name src_fwd address " MAC_SRC_FWD);
+		SYS(fail, "ip link add dst address " MAC_DST " type veth "
+			  "peer name dst_fwd address " MAC_DST_FWD);
+	} else if (result->dev_mode == MODE_NETKIT) {
+		err = create_netkit(NETKIT_L3, "src", "src_fwd");
+		if (!ASSERT_OK(err, "create_ifindex_src"))
+			goto fail;
+		err = create_netkit(NETKIT_L3, "dst", "dst_fwd");
+		if (!ASSERT_OK(err, "create_ifindex_dst"))
+			goto fail;
+	}
 
-	SYS("ip link set veth_dst_fwd address " MAC_DST_FWD);
-	SYS("ip link set veth_dst address " MAC_DST);
+	if (get_ifaddr("src_fwd", src_fwd_addr))
+		goto fail;
 
-	if (get_ifaddr("veth_src_fwd", veth_src_fwd_addr))
+	if (get_ifaddr("src", src_addr))
 		goto fail;
 
-	result->ifindex_veth_src = if_nametoindex("veth_src");
-	if (!ASSERT_GT(result->ifindex_veth_src, 0, "ifindex_veth_src"))
+	result->ifindex_src = if_nametoindex("src");
+	if (!ASSERT_GT(result->ifindex_src, 0, "ifindex_src"))
 		goto fail;
 
-	result->ifindex_veth_src_fwd = if_nametoindex("veth_src_fwd");
-	if (!ASSERT_GT(result->ifindex_veth_src_fwd, 0, "ifindex_veth_src_fwd"))
+	result->ifindex_src_fwd = if_nametoindex("src_fwd");
+	if (!ASSERT_GT(result->ifindex_src_fwd, 0, "ifindex_src_fwd"))
 		goto fail;
 
-	result->ifindex_veth_dst = if_nametoindex("veth_dst");
-	if (!ASSERT_GT(result->ifindex_veth_dst, 0, "ifindex_veth_dst"))
+	result->ifindex_dst = if_nametoindex("dst");
+	if (!ASSERT_GT(result->ifindex_dst, 0, "ifindex_dst"))
 		goto fail;
 
-	result->ifindex_veth_dst_fwd = if_nametoindex("veth_dst_fwd");
-	if (!ASSERT_GT(result->ifindex_veth_dst_fwd, 0, "ifindex_veth_dst_fwd"))
+	result->ifindex_dst_fwd = if_nametoindex("dst_fwd");
+	if (!ASSERT_GT(result->ifindex_dst_fwd, 0, "ifindex_dst_fwd"))
 		goto fail;
 
-	SYS("ip link set veth_src netns " NS_SRC);
-	SYS("ip link set veth_src_fwd netns " NS_FWD);
-	SYS("ip link set veth_dst_fwd netns " NS_FWD);
-	SYS("ip link set veth_dst netns " NS_DST);
+	SYS(fail, "ip link set src netns " NS_SRC);
+	SYS(fail, "ip link set src_fwd netns " NS_FWD);
+	SYS(fail, "ip link set dst_fwd netns " NS_FWD);
+	SYS(fail, "ip link set dst netns " NS_DST);
 
 	/** setup in 'src' namespace */
 	nstoken = open_netns(NS_SRC);
 	if (!ASSERT_OK_PTR(nstoken, "setns src"))
 		goto fail;
 
-	SYS("ip addr add " IP4_SRC "/32 dev veth_src");
-	SYS("ip addr add " IP6_SRC "/128 dev veth_src nodad");
-	SYS("ip link set dev veth_src up");
+	SYS(fail, "ip addr add " IP4_SRC "/32 dev src");
+	SYS(fail, "ip addr add " IP6_SRC "/128 dev src nodad");
+	SYS(fail, "ip link set dev src up");
 
-	SYS("ip route add " IP4_DST "/32 dev veth_src scope global");
-	SYS("ip route add " IP4_NET "/16 dev veth_src scope global");
-	SYS("ip route add " IP6_DST "/128 dev veth_src scope global");
+	SYS(fail, "ip route add " IP4_DST "/32 dev src scope global");
+	SYS(fail, "ip route add " IP4_NET "/16 dev src scope global");
+	SYS(fail, "ip route add " IP6_DST "/128 dev src scope global");
 
-	SYS("ip neigh add " IP4_DST " dev veth_src lladdr %s",
-	    veth_src_fwd_addr);
-	SYS("ip neigh add " IP6_DST " dev veth_src lladdr %s",
-	    veth_src_fwd_addr);
+	if (result->dev_mode == MODE_VETH) {
+		SYS(fail, "ip neigh add " IP4_DST " dev src lladdr %s",
+		    src_fwd_addr);
+		SYS(fail, "ip neigh add " IP6_DST " dev src lladdr %s",
+		    src_fwd_addr);
+	}
 
 	close_netns(nstoken);
 
@@ -209,15 +280,22 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result)
 	 * needs v4 one in order to start ARP probing. IP4_NET route is added
 	 * to the endpoints so that the ARP processing will reply.
 	 */
-	SYS("ip addr add " IP4_SLL "/32 dev veth_src_fwd");
-	SYS("ip addr add " IP4_DLL "/32 dev veth_dst_fwd");
-	SYS("ip link set dev veth_src_fwd up");
-	SYS("ip link set dev veth_dst_fwd up");
-
-	SYS("ip route add " IP4_SRC "/32 dev veth_src_fwd scope global");
-	SYS("ip route add " IP6_SRC "/128 dev veth_src_fwd scope global");
-	SYS("ip route add " IP4_DST "/32 dev veth_dst_fwd scope global");
-	SYS("ip route add " IP6_DST "/128 dev veth_dst_fwd scope global");
+	SYS(fail, "ip addr add " IP4_SLL "/32 dev src_fwd");
+	SYS(fail, "ip addr add " IP4_DLL "/32 dev dst_fwd");
+	SYS(fail, "ip link set dev src_fwd up");
+	SYS(fail, "ip link set dev dst_fwd up");
+
+	SYS(fail, "ip route add " IP4_SRC "/32 dev src_fwd scope global");
+	SYS(fail, "ip route add " IP6_SRC "/128 dev src_fwd scope global");
+	SYS(fail, "ip route add " IP4_DST "/32 dev dst_fwd scope global");
+	SYS(fail, "ip route add " IP6_DST "/128 dev dst_fwd scope global");
+
+	if (result->dev_mode == MODE_VETH) {
+		SYS(fail, "ip neigh add " IP4_SRC " dev src_fwd lladdr %s", src_addr);
+		SYS(fail, "ip neigh add " IP6_SRC " dev src_fwd lladdr %s", src_addr);
+		SYS(fail, "ip neigh add " IP4_DST " dev dst_fwd lladdr %s", MAC_DST);
+		SYS(fail, "ip neigh add " IP6_DST " dev dst_fwd lladdr %s", MAC_DST);
+	}
 
 	close_netns(nstoken);
 
@@ -226,16 +304,19 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result)
 	if (!ASSERT_OK_PTR(nstoken, "setns dst"))
 		goto fail;
 
-	SYS("ip addr add " IP4_DST "/32 dev veth_dst");
-	SYS("ip addr add " IP6_DST "/128 dev veth_dst nodad");
-	SYS("ip link set dev veth_dst up");
+	SYS(fail, "ip addr add " IP4_DST "/32 dev dst");
+	SYS(fail, "ip addr add " IP6_DST "/128 dev dst nodad");
+	SYS(fail, "ip link set dev dst up");
+	SYS(fail, "ip link set dev lo up");
 
-	SYS("ip route add " IP4_SRC "/32 dev veth_dst scope global");
-	SYS("ip route add " IP4_NET "/16 dev veth_dst scope global");
-	SYS("ip route add " IP6_SRC "/128 dev veth_dst scope global");
+	SYS(fail, "ip route add " IP4_SRC "/32 dev dst scope global");
+	SYS(fail, "ip route add " IP4_NET "/16 dev dst scope global");
+	SYS(fail, "ip route add " IP6_SRC "/128 dev dst scope global");
 
-	SYS("ip neigh add " IP4_SRC " dev veth_dst lladdr " MAC_DST_FWD);
-	SYS("ip neigh add " IP6_SRC " dev veth_dst lladdr " MAC_DST_FWD);
+	if (result->dev_mode == MODE_VETH) {
+		SYS(fail, "ip neigh add " IP4_SRC " dev dst lladdr " MAC_DST_FWD);
+		SYS(fail, "ip neigh add " IP6_SRC " dev dst lladdr " MAC_DST_FWD);
+	}
 
 	close_netns(nstoken);
 
@@ -301,23 +382,23 @@ static int netns_load_bpf(const struct bpf_program *src_prog,
 			  const struct bpf_program *chk_prog,
 			  const struct netns_setup_result *setup_result)
 {
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_src_fwd);
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_dst_fwd);
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_src_fwd);
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_dst_fwd);
 	int err;
 
-	/* tc qdisc add dev veth_src_fwd clsact */
-	QDISC_CLSACT_CREATE(&qdisc_veth_src_fwd, setup_result->ifindex_veth_src_fwd);
-	/* tc filter add dev veth_src_fwd ingress bpf da src_prog */
-	XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_INGRESS, src_prog, 0);
-	/* tc filter add dev veth_src_fwd egress bpf da chk_prog */
-	XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_EGRESS, chk_prog, 0);
+	/* tc qdisc add dev src_fwd clsact */
+	QDISC_CLSACT_CREATE(&qdisc_src_fwd, setup_result->ifindex_src_fwd);
+	/* tc filter add dev src_fwd ingress bpf da src_prog */
+	XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_INGRESS, src_prog, 0);
+	/* tc filter add dev src_fwd egress bpf da chk_prog */
+	XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_EGRESS, chk_prog, 0);
 
-	/* tc qdisc add dev veth_dst_fwd clsact */
-	QDISC_CLSACT_CREATE(&qdisc_veth_dst_fwd, setup_result->ifindex_veth_dst_fwd);
-	/* tc filter add dev veth_dst_fwd ingress bpf da dst_prog */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_INGRESS, dst_prog, 0);
-	/* tc filter add dev veth_dst_fwd egress bpf da chk_prog */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_EGRESS, chk_prog, 0);
+	/* tc qdisc add dev dst_fwd clsact */
+	QDISC_CLSACT_CREATE(&qdisc_dst_fwd, setup_result->ifindex_dst_fwd);
+	/* tc filter add dev dst_fwd ingress bpf da dst_prog */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_INGRESS, dst_prog, 0);
+	/* tc filter add dev dst_fwd egress bpf da chk_prog */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_EGRESS, chk_prog, 0);
 
 	return 0;
 fail:
@@ -375,7 +456,7 @@ done:
 
 static int test_ping(int family, const char *addr)
 {
-	SYS("ip netns exec " NS_SRC " %s " PING_ARGS " %s > /dev/null", ping_command(family), addr);
+	SYS(fail, "ip netns exec " NS_SRC " %s " PING_ARGS " %s > /dev/null", ping_command(family), addr);
 	return 0;
 fail:
 	return -1;
@@ -404,9 +485,9 @@ static int set_forwarding(bool enable)
 	return 0;
 }
 
-static void rcv_tstamp(int fd, const char *expected, size_t s)
+static int __rcv_tstamp(int fd, const char *expected, size_t s, __u64 *tstamp)
 {
-	struct __kernel_timespec pkt_ts = {};
+	struct timespec pkt_ts = {};
 	char ctl[CMSG_SPACE(sizeof(pkt_ts))];
 	struct timespec now_ts;
 	struct msghdr msg = {};
@@ -425,15 +506,21 @@ static void rcv_tstamp(int fd, const char *expected, size_t s)
 
 	ret = recvmsg(fd, &msg, 0);
 	if (!ASSERT_EQ(ret, s, "recvmsg"))
-		return;
+		return -1;
 	ASSERT_STRNEQ(data, expected, s, "expected rcv data");
 
 	cmsg = CMSG_FIRSTHDR(&msg);
 	if (cmsg && cmsg->cmsg_level == SOL_SOCKET &&
-	    cmsg->cmsg_type == SO_TIMESTAMPNS_NEW)
+	    cmsg->cmsg_type == SO_TIMESTAMPNS)
 		memcpy(&pkt_ts, CMSG_DATA(cmsg), sizeof(pkt_ts));
 
 	pkt_ns = pkt_ts.tv_sec * NSEC_PER_SEC + pkt_ts.tv_nsec;
+	if (tstamp) {
+		/* caller will check the tstamp itself */
+		*tstamp = pkt_ns;
+		return 0;
+	}
+
 	ASSERT_NEQ(pkt_ns, 0, "pkt rcv tstamp");
 
 	ret = clock_gettime(CLOCK_REALTIME, &now_ts);
@@ -443,6 +530,60 @@ static void rcv_tstamp(int fd, const char *expected, size_t s)
 	if (ASSERT_GE(now_ns, pkt_ns, "check rcv tstamp"))
 		ASSERT_LT(now_ns - pkt_ns, 5 * NSEC_PER_SEC,
 			  "check rcv tstamp");
+	return 0;
+}
+
+static void rcv_tstamp(int fd, const char *expected, size_t s)
+{
+	__rcv_tstamp(fd, expected, s, NULL);
+}
+
+static int wait_netstamp_needed_key(void)
+{
+	int opt = 1, srv_fd = -1, cli_fd = -1, nretries = 0, err, n;
+	char buf[] = "testing testing";
+	struct nstoken *nstoken;
+	__u64 tstamp = 0;
+
+	nstoken = open_netns(NS_DST);
+	if (!ASSERT_OK_PTR(nstoken, "setns dst"))
+		return -1;
+
+	srv_fd = start_server(AF_INET6, SOCK_DGRAM, "::1", 0, 0);
+	if (!ASSERT_GE(srv_fd, 0, "start_server"))
+		goto done;
+
+	err = setsockopt(srv_fd, SOL_SOCKET, SO_TIMESTAMPNS,
+			 &opt, sizeof(opt));
+	if (!ASSERT_OK(err, "setsockopt(SO_TIMESTAMPNS)"))
+		goto done;
+
+	cli_fd = connect_to_fd(srv_fd, TIMEOUT_MILLIS);
+	if (!ASSERT_GE(cli_fd, 0, "connect_to_fd"))
+		goto done;
+
+again:
+	n = write(cli_fd, buf, sizeof(buf));
+	if (!ASSERT_EQ(n, sizeof(buf), "send to server"))
+		goto done;
+	err = __rcv_tstamp(srv_fd, buf, sizeof(buf), &tstamp);
+	if (!ASSERT_OK(err, "__rcv_tstamp"))
+		goto done;
+	if (!tstamp && nretries++ < 5) {
+		sleep(1);
+		printf("netstamp_needed_key retry#%d\n", nretries);
+		goto again;
+	}
+
+done:
+	if (!tstamp && srv_fd != -1) {
+		close(srv_fd);
+		srv_fd = -1;
+	}
+	if (cli_fd != -1)
+		close(cli_fd);
+	close_netns(nstoken);
+	return srv_fd;
 }
 
 static void snd_tstamp(int fd, char *b, size_t s)
@@ -496,9 +637,9 @@ static void test_inet_dtime(int family, int type, const char *addr, __u16 port)
 		return;
 
 	/* Ensure the kernel puts the (rcv) timestamp for all skb */
-	err = setsockopt(listen_fd, SOL_SOCKET, SO_TIMESTAMPNS_NEW,
+	err = setsockopt(listen_fd, SOL_SOCKET, SO_TIMESTAMPNS,
 			 &opt, sizeof(opt));
-	if (!ASSERT_OK(err, "setsockopt(SO_TIMESTAMPNS_NEW)"))
+	if (!ASSERT_OK(err, "setsockopt(SO_TIMESTAMPNS)"))
 		goto done;
 
 	if (type == SOCK_STREAM) {
@@ -547,10 +688,10 @@ done:
 static int netns_load_dtime_bpf(struct test_tc_dtime *skel,
 				const struct netns_setup_result *setup_result)
 {
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_src_fwd);
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_dst_fwd);
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_src);
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_dst);
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_src_fwd);
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_dst_fwd);
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_src);
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_dst);
 	struct nstoken *nstoken;
 	int err;
 
@@ -558,58 +699,58 @@ static int netns_load_dtime_bpf(struct test_tc_dtime *skel,
 	nstoken = open_netns(NS_SRC);
 	if (!ASSERT_OK_PTR(nstoken, "setns " NS_SRC))
 		return -1;
-	/* tc qdisc add dev veth_src clsact */
-	QDISC_CLSACT_CREATE(&qdisc_veth_src, setup_result->ifindex_veth_src);
-	/* tc filter add dev veth_src ingress bpf da ingress_host */
-	XGRESS_FILTER_ADD(&qdisc_veth_src, BPF_TC_INGRESS, skel->progs.ingress_host, 0);
-	/* tc filter add dev veth_src egress bpf da egress_host */
-	XGRESS_FILTER_ADD(&qdisc_veth_src, BPF_TC_EGRESS, skel->progs.egress_host, 0);
+	/* tc qdisc add dev src clsact */
+	QDISC_CLSACT_CREATE(&qdisc_src, setup_result->ifindex_src);
+	/* tc filter add dev src ingress bpf da ingress_host */
+	XGRESS_FILTER_ADD(&qdisc_src, BPF_TC_INGRESS, skel->progs.ingress_host, 0);
+	/* tc filter add dev src egress bpf da egress_host */
+	XGRESS_FILTER_ADD(&qdisc_src, BPF_TC_EGRESS, skel->progs.egress_host, 0);
 	close_netns(nstoken);
 
 	/* setup ns_dst tc progs */
 	nstoken = open_netns(NS_DST);
 	if (!ASSERT_OK_PTR(nstoken, "setns " NS_DST))
 		return -1;
-	/* tc qdisc add dev veth_dst clsact */
-	QDISC_CLSACT_CREATE(&qdisc_veth_dst, setup_result->ifindex_veth_dst);
-	/* tc filter add dev veth_dst ingress bpf da ingress_host */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst, BPF_TC_INGRESS, skel->progs.ingress_host, 0);
-	/* tc filter add dev veth_dst egress bpf da egress_host */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst, BPF_TC_EGRESS, skel->progs.egress_host, 0);
+	/* tc qdisc add dev dst clsact */
+	QDISC_CLSACT_CREATE(&qdisc_dst, setup_result->ifindex_dst);
+	/* tc filter add dev dst ingress bpf da ingress_host */
+	XGRESS_FILTER_ADD(&qdisc_dst, BPF_TC_INGRESS, skel->progs.ingress_host, 0);
+	/* tc filter add dev dst egress bpf da egress_host */
+	XGRESS_FILTER_ADD(&qdisc_dst, BPF_TC_EGRESS, skel->progs.egress_host, 0);
 	close_netns(nstoken);
 
 	/* setup ns_fwd tc progs */
 	nstoken = open_netns(NS_FWD);
 	if (!ASSERT_OK_PTR(nstoken, "setns " NS_FWD))
 		return -1;
-	/* tc qdisc add dev veth_dst_fwd clsact */
-	QDISC_CLSACT_CREATE(&qdisc_veth_dst_fwd, setup_result->ifindex_veth_dst_fwd);
-	/* tc filter add dev veth_dst_fwd ingress prio 100 bpf da ingress_fwdns_prio100 */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_INGRESS,
+	/* tc qdisc add dev dst_fwd clsact */
+	QDISC_CLSACT_CREATE(&qdisc_dst_fwd, setup_result->ifindex_dst_fwd);
+	/* tc filter add dev dst_fwd ingress prio 100 bpf da ingress_fwdns_prio100 */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_INGRESS,
 			  skel->progs.ingress_fwdns_prio100, 100);
-	/* tc filter add dev veth_dst_fwd ingress prio 101 bpf da ingress_fwdns_prio101 */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_INGRESS,
+	/* tc filter add dev dst_fwd ingress prio 101 bpf da ingress_fwdns_prio101 */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_INGRESS,
 			  skel->progs.ingress_fwdns_prio101, 101);
-	/* tc filter add dev veth_dst_fwd egress prio 100 bpf da egress_fwdns_prio100 */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_EGRESS,
+	/* tc filter add dev dst_fwd egress prio 100 bpf da egress_fwdns_prio100 */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_EGRESS,
 			  skel->progs.egress_fwdns_prio100, 100);
-	/* tc filter add dev veth_dst_fwd egress prio 101 bpf da egress_fwdns_prio101 */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_EGRESS,
+	/* tc filter add dev dst_fwd egress prio 101 bpf da egress_fwdns_prio101 */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_EGRESS,
 			  skel->progs.egress_fwdns_prio101, 101);
 
-	/* tc qdisc add dev veth_src_fwd clsact */
-	QDISC_CLSACT_CREATE(&qdisc_veth_src_fwd, setup_result->ifindex_veth_src_fwd);
-	/* tc filter add dev veth_src_fwd ingress prio 100 bpf da ingress_fwdns_prio100 */
-	XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_INGRESS,
+	/* tc qdisc add dev src_fwd clsact */
+	QDISC_CLSACT_CREATE(&qdisc_src_fwd, setup_result->ifindex_src_fwd);
+	/* tc filter add dev src_fwd ingress prio 100 bpf da ingress_fwdns_prio100 */
+	XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_INGRESS,
 			  skel->progs.ingress_fwdns_prio100, 100);
-	/* tc filter add dev veth_src_fwd ingress prio 101 bpf da ingress_fwdns_prio101 */
-	XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_INGRESS,
+	/* tc filter add dev src_fwd ingress prio 101 bpf da ingress_fwdns_prio101 */
+	XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_INGRESS,
 			  skel->progs.ingress_fwdns_prio101, 101);
-	/* tc filter add dev veth_src_fwd egress prio 100 bpf da egress_fwdns_prio100 */
-	XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_EGRESS,
+	/* tc filter add dev src_fwd egress prio 100 bpf da egress_fwdns_prio100 */
+	XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_EGRESS,
 			  skel->progs.egress_fwdns_prio100, 100);
-	/* tc filter add dev veth_src_fwd egress prio 101 bpf da egress_fwdns_prio101 */
-	XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_EGRESS,
+	/* tc filter add dev src_fwd egress prio 101 bpf da egress_fwdns_prio101 */
+	XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_EGRESS,
 			  skel->progs.egress_fwdns_prio101, 101);
 	close_netns(nstoken);
 	return 0;
@@ -732,7 +873,7 @@ static void test_tcp_dtime(struct test_tc_dtime *skel, int family, bool bpf_fwd)
 	test_inet_dtime(family, SOCK_STREAM, addr, 50000 + t);
 
 	/* fwdns_prio100 prog does not read delivery_time_type, so
-	 * kernel puts the (rcv) timetamp in __sk_buff->tstamp
+	 * kernel puts the (rcv) timestamp in __sk_buff->tstamp
 	 */
 	ASSERT_EQ(dtimes[INGRESS_FWDNS_P100], 0,
 		  dtime_cnt_str(t, INGRESS_FWDNS_P100));
@@ -765,9 +906,6 @@ static void test_udp_dtime(struct test_tc_dtime *skel, int family, bool bpf_fwd)
 
 	ASSERT_EQ(dtimes[INGRESS_FWDNS_P100], 0,
 		  dtime_cnt_str(t, INGRESS_FWDNS_P100));
-	/* non mono delivery time is not forwarded */
-	ASSERT_EQ(dtimes[INGRESS_FWDNS_P101], 0,
-		  dtime_cnt_str(t, INGRESS_FWDNS_P101));
 	for (i = EGRESS_FWDNS_P100; i < SET_DTIME; i++)
 		ASSERT_GT(dtimes[i], 0, dtime_cnt_str(t, i));
 
@@ -779,14 +917,23 @@ static void test_tc_redirect_dtime(struct netns_setup_result *setup_result)
 {
 	struct test_tc_dtime *skel;
 	struct nstoken *nstoken;
-	int err;
+	int hold_tstamp_fd, err;
+
+	/* Hold a sk with the SOCK_TIMESTAMP set to ensure there
+	 * is no delay in the kernel net_enable_timestamp().
+	 * This ensures the following tests must have
+	 * non zero rcv tstamp in the recvmsg().
+	 */
+	hold_tstamp_fd = wait_netstamp_needed_key();
+	if (!ASSERT_GE(hold_tstamp_fd, 0, "wait_netstamp_needed_key"))
+		return;
 
 	skel = test_tc_dtime__open();
 	if (!ASSERT_OK_PTR(skel, "test_tc_dtime__open"))
-		return;
+		goto done;
 
-	skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd;
-	skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd;
+	skel->rodata->IFINDEX_SRC = setup_result->ifindex_src_fwd;
+	skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd;
 
 	err = test_tc_dtime__load(skel);
 	if (!ASSERT_OK(err, "test_tc_dtime__load"))
@@ -828,6 +975,7 @@ static void test_tc_redirect_dtime(struct netns_setup_result *setup_result)
 
 done:
 	test_tc_dtime__destroy(skel);
+	close(hold_tstamp_fd);
 }
 
 static void test_tc_redirect_neigh_fib(struct netns_setup_result *setup_result)
@@ -876,8 +1024,8 @@ static void test_tc_redirect_neigh(struct netns_setup_result *setup_result)
 	if (!ASSERT_OK_PTR(skel, "test_tc_neigh__open"))
 		goto done;
 
-	skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd;
-	skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd;
+	skel->rodata->IFINDEX_SRC = setup_result->ifindex_src_fwd;
+	skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd;
 
 	err = test_tc_neigh__load(skel);
 	if (!ASSERT_OK(err, "test_tc_neigh__load"))
@@ -912,8 +1060,8 @@ static void test_tc_redirect_peer(struct netns_setup_result *setup_result)
 	if (!ASSERT_OK_PTR(skel, "test_tc_peer__open"))
 		goto done;
 
-	skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd;
-	skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd;
+	skel->rodata->IFINDEX_SRC = setup_result->ifindex_src_fwd;
+	skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd;
 
 	err = test_tc_peer__load(skel);
 	if (!ASSERT_OK(err, "test_tc_peer__load"))
@@ -953,7 +1101,7 @@ static int tun_open(char *name)
 	if (!ASSERT_OK(err, "ioctl TUNSETIFF"))
 		goto fail;
 
-	SYS("ip link set dev %s up", name);
+	SYS(fail, "ip link set dev %s up", name);
 
 	return fd;
 fail:
@@ -1004,7 +1152,7 @@ static int tun_relay_loop(int src_fd, int target_fd)
 static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result)
 {
 	LIBBPF_OPTS(bpf_tc_hook, qdisc_tun_fwd);
-	LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_dst_fwd);
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_dst_fwd);
 	struct test_tc_peer *skel = NULL;
 	struct nstoken *nstoken = NULL;
 	int err;
@@ -1053,7 +1201,7 @@ static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result)
 		goto fail;
 
 	skel->rodata->IFINDEX_SRC = ifindex;
-	skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd;
+	skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd;
 
 	err = test_tc_peer__load(skel);
 	if (!ASSERT_OK(err, "test_tc_peer__load"))
@@ -1061,38 +1209,38 @@ static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result)
 
 	/* Load "tc_src_l3" to the tun_fwd interface to redirect packets
 	 * towards dst, and "tc_dst" to redirect packets
-	 * and "tc_chk" on veth_dst_fwd to drop non-redirected packets.
+	 * and "tc_chk" on dst_fwd to drop non-redirected packets.
 	 */
 	/* tc qdisc add dev tun_fwd clsact */
 	QDISC_CLSACT_CREATE(&qdisc_tun_fwd, ifindex);
 	/* tc filter add dev tun_fwd ingress bpf da tc_src_l3 */
 	XGRESS_FILTER_ADD(&qdisc_tun_fwd, BPF_TC_INGRESS, skel->progs.tc_src_l3, 0);
 
-	/* tc qdisc add dev veth_dst_fwd clsact */
-	QDISC_CLSACT_CREATE(&qdisc_veth_dst_fwd, setup_result->ifindex_veth_dst_fwd);
-	/* tc filter add dev veth_dst_fwd ingress bpf da tc_dst_l3 */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_INGRESS, skel->progs.tc_dst_l3, 0);
-	/* tc filter add dev veth_dst_fwd egress bpf da tc_chk */
-	XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_EGRESS, skel->progs.tc_chk, 0);
+	/* tc qdisc add dev dst_fwd clsact */
+	QDISC_CLSACT_CREATE(&qdisc_dst_fwd, setup_result->ifindex_dst_fwd);
+	/* tc filter add dev dst_fwd ingress bpf da tc_dst_l3 */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_INGRESS, skel->progs.tc_dst_l3, 0);
+	/* tc filter add dev dst_fwd egress bpf da tc_chk */
+	XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_EGRESS, skel->progs.tc_chk, 0);
 
 	/* Setup route and neigh tables */
-	SYS("ip -netns " NS_SRC " addr add dev tun_src " IP4_TUN_SRC "/24");
-	SYS("ip -netns " NS_FWD " addr add dev tun_fwd " IP4_TUN_FWD "/24");
+	SYS(fail, "ip -netns " NS_SRC " addr add dev tun_src " IP4_TUN_SRC "/24");
+	SYS(fail, "ip -netns " NS_FWD " addr add dev tun_fwd " IP4_TUN_FWD "/24");
 
-	SYS("ip -netns " NS_SRC " addr add dev tun_src " IP6_TUN_SRC "/64 nodad");
-	SYS("ip -netns " NS_FWD " addr add dev tun_fwd " IP6_TUN_FWD "/64 nodad");
+	SYS(fail, "ip -netns " NS_SRC " addr add dev tun_src " IP6_TUN_SRC "/64 nodad");
+	SYS(fail, "ip -netns " NS_FWD " addr add dev tun_fwd " IP6_TUN_FWD "/64 nodad");
 
-	SYS("ip -netns " NS_SRC " route del " IP4_DST "/32 dev veth_src scope global");
-	SYS("ip -netns " NS_SRC " route add " IP4_DST "/32 via " IP4_TUN_FWD
+	SYS(fail, "ip -netns " NS_SRC " route del " IP4_DST "/32 dev src scope global");
+	SYS(fail, "ip -netns " NS_SRC " route add " IP4_DST "/32 via " IP4_TUN_FWD
 	    " dev tun_src scope global");
-	SYS("ip -netns " NS_DST " route add " IP4_TUN_SRC "/32 dev veth_dst scope global");
-	SYS("ip -netns " NS_SRC " route del " IP6_DST "/128 dev veth_src scope global");
-	SYS("ip -netns " NS_SRC " route add " IP6_DST "/128 via " IP6_TUN_FWD
+	SYS(fail, "ip -netns " NS_DST " route add " IP4_TUN_SRC "/32 dev dst scope global");
+	SYS(fail, "ip -netns " NS_SRC " route del " IP6_DST "/128 dev src scope global");
+	SYS(fail, "ip -netns " NS_SRC " route add " IP6_DST "/128 via " IP6_TUN_FWD
 	    " dev tun_src scope global");
-	SYS("ip -netns " NS_DST " route add " IP6_TUN_SRC "/128 dev veth_dst scope global");
+	SYS(fail, "ip -netns " NS_DST " route add " IP6_TUN_SRC "/128 dev dst scope global");
 
-	SYS("ip -netns " NS_DST " neigh add " IP4_TUN_SRC " dev veth_dst lladdr " MAC_DST_FWD);
-	SYS("ip -netns " NS_DST " neigh add " IP6_TUN_SRC " dev veth_dst lladdr " MAC_DST_FWD);
+	SYS(fail, "ip -netns " NS_DST " neigh add " IP4_TUN_SRC " dev dst lladdr " MAC_DST_FWD);
+	SYS(fail, "ip -netns " NS_DST " neigh add " IP6_TUN_SRC " dev dst lladdr " MAC_DST_FWD);
 
 	if (!ASSERT_OK(set_forwarding(false), "disable forwarding"))
 		goto fail;
@@ -1114,9 +1262,9 @@ fail:
 		close_netns(nstoken);
 }
 
-#define RUN_TEST(name)                                                                      \
+#define RUN_TEST(name, mode)                                                                \
 	({                                                                                  \
-		struct netns_setup_result setup_result;                                     \
+		struct netns_setup_result setup_result = { .dev_mode = mode, };             \
 		if (test__start_subtest(#name))                                             \
 			if (ASSERT_OK(netns_setup_namespaces("add"), "setup namespaces")) { \
 				if (ASSERT_OK(netns_setup_links_and_routes(&setup_result),  \
@@ -1130,11 +1278,13 @@ static void *test_tc_redirect_run_tests(void *arg)
 {
 	netns_setup_namespaces_nofail("delete");
 
-	RUN_TEST(tc_redirect_peer);
-	RUN_TEST(tc_redirect_peer_l3);
-	RUN_TEST(tc_redirect_neigh);
-	RUN_TEST(tc_redirect_neigh_fib);
-	RUN_TEST(tc_redirect_dtime);
+	RUN_TEST(tc_redirect_peer, MODE_VETH);
+	RUN_TEST(tc_redirect_peer, MODE_NETKIT);
+	RUN_TEST(tc_redirect_peer_l3, MODE_VETH);
+	RUN_TEST(tc_redirect_peer_l3, MODE_NETKIT);
+	RUN_TEST(tc_redirect_neigh, MODE_VETH);
+	RUN_TEST(tc_redirect_neigh_fib, MODE_VETH);
+	RUN_TEST(tc_redirect_dtime, MODE_VETH);
 	return NULL;
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_custom_syncookie.c b/tools/testing/selftests/bpf/prog_tests/tcp_custom_syncookie.c
new file mode 100644
index 000000000000..eaf441dc7e79
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_custom_syncookie.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+
+#define _GNU_SOURCE
+#include <sched.h>
+#include <stdlib.h>
+#include <net/if.h>
+
+#include "test_progs.h"
+#include "cgroup_helpers.h"
+#include "network_helpers.h"
+#include "test_tcp_custom_syncookie.skel.h"
+
+static struct test_tcp_custom_syncookie_case {
+	int family, type;
+	char addr[16];
+	char name[10];
+} test_cases[] = {
+	{
+		.name = "IPv4 TCP",
+		.family = AF_INET,
+		.type = SOCK_STREAM,
+		.addr = "127.0.0.1",
+	},
+	{
+		.name = "IPv6 TCP",
+		.family = AF_INET6,
+		.type = SOCK_STREAM,
+		.addr = "::1",
+	},
+};
+
+static int setup_netns(void)
+{
+	if (!ASSERT_OK(unshare(CLONE_NEWNET), "create netns"))
+		return -1;
+
+	if (!ASSERT_OK(system("ip link set dev lo up"), "ip"))
+		goto err;
+
+	if (!ASSERT_OK(write_sysctl("/proc/sys/net/ipv4/tcp_ecn", "1"),
+		       "write_sysctl"))
+		goto err;
+
+	return 0;
+err:
+	return -1;
+}
+
+static int setup_tc(struct test_tcp_custom_syncookie *skel)
+{
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_lo, .attach_point = BPF_TC_INGRESS);
+	LIBBPF_OPTS(bpf_tc_opts, tc_attach,
+		    .prog_fd = bpf_program__fd(skel->progs.tcp_custom_syncookie));
+
+	qdisc_lo.ifindex = if_nametoindex("lo");
+	if (!ASSERT_OK(bpf_tc_hook_create(&qdisc_lo), "qdisc add dev lo clsact"))
+		goto err;
+
+	if (!ASSERT_OK(bpf_tc_attach(&qdisc_lo, &tc_attach),
+		       "filter add dev lo ingress"))
+		goto err;
+
+	return 0;
+err:
+	return -1;
+}
+
+#define msg "Hello World"
+#define msglen 11
+
+static void transfer_message(int sender, int receiver)
+{
+	char buf[msglen];
+	int ret;
+
+	ret = send(sender, msg, msglen, 0);
+	if (!ASSERT_EQ(ret, msglen, "send"))
+		return;
+
+	memset(buf, 0, sizeof(buf));
+
+	ret = recv(receiver, buf, msglen, 0);
+	if (!ASSERT_EQ(ret, msglen, "recv"))
+		return;
+
+	ret = strncmp(buf, msg, msglen);
+	if (!ASSERT_EQ(ret, 0, "strncmp"))
+		return;
+}
+
+static void create_connection(struct test_tcp_custom_syncookie_case *test_case)
+{
+	int server, client, child;
+
+	server = start_server(test_case->family, test_case->type, test_case->addr, 0, 0);
+	if (!ASSERT_NEQ(server, -1, "start_server"))
+		return;
+
+	client = connect_to_fd(server, 0);
+	if (!ASSERT_NEQ(client, -1, "connect_to_fd"))
+		goto close_server;
+
+	child = accept(server, NULL, 0);
+	if (!ASSERT_NEQ(child, -1, "accept"))
+		goto close_client;
+
+	transfer_message(client, child);
+	transfer_message(child, client);
+
+	close(child);
+close_client:
+	close(client);
+close_server:
+	close(server);
+}
+
+void test_tcp_custom_syncookie(void)
+{
+	struct test_tcp_custom_syncookie *skel;
+	int i;
+
+	if (setup_netns())
+		return;
+
+	skel = test_tcp_custom_syncookie__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	if (setup_tc(skel))
+		goto destroy_skel;
+
+	for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
+		if (!test__start_subtest(test_cases[i].name))
+			continue;
+
+		skel->bss->handled_syn = false;
+		skel->bss->handled_ack = false;
+
+		create_connection(&test_cases[i]);
+
+		ASSERT_EQ(skel->bss->handled_syn, true, "SYN is not handled at tc.");
+		ASSERT_EQ(skel->bss->handled_ack, true, "ACK is not handled at tc");
+	}
+
+destroy_skel:
+	system("tc qdisc del dev lo clsact");
+
+	test_tcp_custom_syncookie__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
index 5cf85d0f9827..56685fc03c7e 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
@@ -151,7 +151,7 @@ static int check_hdr_opt(const struct bpf_test_option *exp,
 			 const struct bpf_test_option *act,
 			 const char *hdr_desc)
 {
-	if (!ASSERT_OK(memcmp(exp, act, sizeof(*exp)), hdr_desc)) {
+	if (!ASSERT_EQ(memcmp(exp, act, sizeof(*exp)), 0, hdr_desc)) {
 		print_option(exp, "expected: ");
 		print_option(act, "  actual: ");
 		return -1;
@@ -169,7 +169,7 @@ static int check_hdr_stg(const struct hdr_stg *exp, int fd,
 		  "map_lookup(hdr_stg_map_fd)"))
 		return -1;
 
-	if (!ASSERT_OK(memcmp(exp, &act, sizeof(*exp)), stg_desc)) {
+	if (!ASSERT_EQ(memcmp(exp, &act, sizeof(*exp)), 0, stg_desc)) {
 		print_hdr_stg(exp, "expected: ");
 		print_hdr_stg(&act, "  actual: ");
 		return -1;
@@ -347,7 +347,7 @@ static void syncookie_estab(void)
 	exp_active_estab_in.max_delack_ms = 22;
 
 	exp_passive_hdr_stg.syncookie = true;
-	exp_active_hdr_stg.resend_syn = true,
+	exp_active_hdr_stg.resend_syn = true;
 
 	prepare_out();
 
diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
index 8fe84da1b9b4..c38784c1c066 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
 #include <test_progs.h>
 #include "cgroup_helpers.h"
 #include "network_helpers.h"
@@ -10,6 +11,9 @@ struct tcp_rtt_storage {
 	__u32 delivered;
 	__u32 delivered_ce;
 	__u32 icsk_retransmits;
+
+	__u32 mrtt_us;	/* args[0] */
+	__u32 srtt;	/* args[1] */
 };
 
 static void send_byte(int fd)
@@ -83,6 +87,17 @@ static int verify_sk(int map_fd, int client_fd, const char *msg, __u32 invoked,
 		err++;
 	}
 
+	/* Precise values of mrtt and srtt are unavailable, just make sure they are nonzero */
+	if (val.mrtt_us == 0) {
+		log_err("%s: unexpected bpf_tcp_sock.args[0] (mrtt_us) %u == 0", msg, val.mrtt_us);
+		err++;
+	}
+
+	if (val.srtt == 0) {
+		log_err("%s: unexpected bpf_tcp_sock.args[1] (srtt) %u == 0", msg, val.srtt);
+		err++;
+	}
+
 	return err;
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c b/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c
new file mode 100644
index 000000000000..ccae0b31ac6c
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#define _GNU_SOURCE
+#include <sched.h>
+#include <pthread.h>
+#include <stdbool.h>
+#include <bpf/btf.h>
+#include <test_progs.h>
+
+#include "test_bpf_ma.skel.h"
+
+static void do_bpf_ma_test(const char *name)
+{
+	struct test_bpf_ma *skel;
+	struct bpf_program *prog;
+	struct btf *btf;
+	int i, err, id;
+	char tname[32];
+
+	skel = test_bpf_ma__open();
+	if (!ASSERT_OK_PTR(skel, "open"))
+		return;
+
+	btf = bpf_object__btf(skel->obj);
+	if (!ASSERT_OK_PTR(btf, "btf"))
+		goto out;
+
+	for (i = 0; i < ARRAY_SIZE(skel->rodata->data_sizes); i++) {
+		snprintf(tname, sizeof(tname), "bin_data_%u", skel->rodata->data_sizes[i]);
+		id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT);
+		if (!ASSERT_GT(id, 0, tname))
+			goto out;
+		skel->rodata->data_btf_ids[i] = id;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(skel->rodata->percpu_data_sizes); i++) {
+		snprintf(tname, sizeof(tname), "percpu_bin_data_%u", skel->rodata->percpu_data_sizes[i]);
+		id = btf__find_by_name_kind(btf, tname, BTF_KIND_STRUCT);
+		if (!ASSERT_GT(id, 0, tname))
+			goto out;
+		skel->rodata->percpu_data_btf_ids[i] = id;
+	}
+
+	prog = bpf_object__find_program_by_name(skel->obj, name);
+	if (!ASSERT_OK_PTR(prog, "invalid prog name"))
+		goto out;
+	bpf_program__set_autoload(prog, true);
+
+	err = test_bpf_ma__load(skel);
+	if (!ASSERT_OK(err, "load"))
+		goto out;
+
+	err = test_bpf_ma__attach(skel);
+	if (!ASSERT_OK(err, "attach"))
+		goto out;
+
+	skel->bss->pid = getpid();
+	usleep(1);
+	ASSERT_OK(skel->bss->err, "test error");
+out:
+	test_bpf_ma__destroy(skel);
+}
+
+void test_test_bpf_ma(void)
+{
+	if (test__start_subtest("batch_alloc_free"))
+		do_bpf_ma_test("test_batch_alloc_free");
+	if (test__start_subtest("free_through_map_free"))
+		do_bpf_ma_test("test_free_through_map_free");
+	if (test__start_subtest("batch_percpu_alloc_free"))
+		do_bpf_ma_test("test_batch_percpu_alloc_free");
+	if (test__start_subtest("percpu_free_through_map_free"))
+		do_bpf_ma_test("test_percpu_free_through_map_free");
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpf_smc.c b/tools/testing/selftests/bpf/prog_tests/test_bpf_smc.c
new file mode 100644
index 000000000000..de22734abc4d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_bpf_smc.c
@@ -0,0 +1,390 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <linux/genetlink.h>
+#include "network_helpers.h"
+#include "bpf_smc.skel.h"
+
+#ifndef IPPROTO_SMC
+#define IPPROTO_SMC 256
+#endif
+
+#define CLIENT_IP			"127.0.0.1"
+#define SERVER_IP			"127.0.1.0"
+#define SERVER_IP_VIA_RISK_PATH	"127.0.2.0"
+
+#define SERVICE_1	80
+#define SERVICE_2	443
+#define SERVICE_3	8443
+
+#define TEST_NS	"bpf_smc_netns"
+
+static struct netns_obj *test_netns;
+
+struct smc_policy_ip_key {
+	__u32  sip;
+	__u32  dip;
+};
+
+struct smc_policy_ip_value {
+	__u8	mode;
+};
+
+#if defined(__s390x__)
+/* s390x has default seid  */
+static bool setup_ueid(void) { return true; }
+static void cleanup_ueid(void) {}
+#else
+enum {
+	SMC_NETLINK_ADD_UEID = 10,
+	SMC_NETLINK_REMOVE_UEID
+};
+
+enum {
+	SMC_NLA_EID_TABLE_UNSPEC,
+	SMC_NLA_EID_TABLE_ENTRY,    /* string */
+};
+
+struct msgtemplate {
+	struct nlmsghdr n;
+	struct genlmsghdr g;
+	char buf[1024];
+};
+
+#define GENLMSG_DATA(glh)	((void *)(NLMSG_DATA(glh) + GENL_HDRLEN))
+#define GENLMSG_PAYLOAD(glh)	(NLMSG_PAYLOAD(glh, 0) - GENL_HDRLEN)
+#define NLA_DATA(na)		((void *)((char *)(na) + NLA_HDRLEN))
+#define NLA_PAYLOAD(len)	((len) - NLA_HDRLEN)
+
+#define SMC_GENL_FAMILY_NAME	"SMC_GEN_NETLINK"
+#define SMC_BPFTEST_UEID	"SMC-BPFTEST-UEID"
+
+static uint16_t smc_nl_family_id = -1;
+
+static int send_cmd(int fd, __u16 nlmsg_type, __u32 nlmsg_pid,
+		    __u16 nlmsg_flags, __u8 genl_cmd, __u16 nla_type,
+		    void *nla_data, int nla_len)
+{
+	struct nlattr *na;
+	struct sockaddr_nl nladdr;
+	int r, buflen;
+	char *buf;
+
+	struct msgtemplate msg = {0};
+
+	msg.n.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN);
+	msg.n.nlmsg_type = nlmsg_type;
+	msg.n.nlmsg_flags = nlmsg_flags;
+	msg.n.nlmsg_seq = 0;
+	msg.n.nlmsg_pid = nlmsg_pid;
+	msg.g.cmd = genl_cmd;
+	msg.g.version = 1;
+	na = (struct nlattr *)GENLMSG_DATA(&msg);
+	na->nla_type = nla_type;
+	na->nla_len = nla_len + 1 + NLA_HDRLEN;
+	memcpy(NLA_DATA(na), nla_data, nla_len);
+	msg.n.nlmsg_len += NLMSG_ALIGN(na->nla_len);
+
+	buf = (char *)&msg;
+	buflen = msg.n.nlmsg_len;
+	memset(&nladdr, 0, sizeof(nladdr));
+	nladdr.nl_family = AF_NETLINK;
+
+	while ((r = sendto(fd, buf, buflen, 0, (struct sockaddr *)&nladdr,
+			   sizeof(nladdr))) < buflen) {
+		if (r > 0) {
+			buf += r;
+			buflen -= r;
+		} else if (errno != EAGAIN) {
+			return -1;
+		}
+	}
+	return 0;
+}
+
+static bool get_smc_nl_family_id(void)
+{
+	struct sockaddr_nl nl_src;
+	struct msgtemplate msg;
+	struct nlattr *nl;
+	int fd, ret;
+	pid_t pid;
+
+	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC);
+	if (!ASSERT_OK_FD(fd, "nl_family socket"))
+		return false;
+
+	pid = getpid();
+
+	memset(&nl_src, 0, sizeof(nl_src));
+	nl_src.nl_family = AF_NETLINK;
+	nl_src.nl_pid = pid;
+
+	ret = bind(fd, (struct sockaddr *)&nl_src, sizeof(nl_src));
+	if (!ASSERT_OK(ret, "nl_family bind"))
+		goto fail;
+
+	ret = send_cmd(fd, GENL_ID_CTRL, pid,
+		       NLM_F_REQUEST, CTRL_CMD_GETFAMILY,
+		       CTRL_ATTR_FAMILY_NAME, (void *)SMC_GENL_FAMILY_NAME,
+		       strlen(SMC_GENL_FAMILY_NAME));
+	if (!ASSERT_OK(ret, "nl_family query"))
+		goto fail;
+
+	ret = recv(fd, &msg, sizeof(msg), 0);
+	if (!ASSERT_FALSE(msg.n.nlmsg_type == NLMSG_ERROR || ret < 0 ||
+			  !NLMSG_OK(&msg.n, ret), "nl_family response"))
+		goto fail;
+
+	nl = (struct nlattr *)GENLMSG_DATA(&msg);
+	nl = (struct nlattr *)((char *)nl + NLA_ALIGN(nl->nla_len));
+	if (!ASSERT_EQ(nl->nla_type, CTRL_ATTR_FAMILY_ID, "nl_family nla type"))
+		goto fail;
+
+	smc_nl_family_id = *(uint16_t *)NLA_DATA(nl);
+	close(fd);
+	return true;
+fail:
+	close(fd);
+	return false;
+}
+
+static bool smc_ueid(int op)
+{
+	struct sockaddr_nl nl_src;
+	struct msgtemplate msg;
+	struct nlmsgerr *err;
+	char test_ueid[32];
+	int fd, ret;
+	pid_t pid;
+
+	/* UEID required */
+	memset(test_ueid, '\x20', sizeof(test_ueid));
+	memcpy(test_ueid, SMC_BPFTEST_UEID, strlen(SMC_BPFTEST_UEID));
+	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC);
+	if (!ASSERT_OK_FD(fd, "ueid socket"))
+		return false;
+
+	pid = getpid();
+	memset(&nl_src, 0, sizeof(nl_src));
+	nl_src.nl_family = AF_NETLINK;
+	nl_src.nl_pid = pid;
+
+	ret = bind(fd, (struct sockaddr *)&nl_src, sizeof(nl_src));
+	if (!ASSERT_OK(ret, "ueid bind"))
+		goto fail;
+
+	ret = send_cmd(fd, smc_nl_family_id, pid,
+		       NLM_F_REQUEST | NLM_F_ACK, op, SMC_NLA_EID_TABLE_ENTRY,
+		       (void *)test_ueid, sizeof(test_ueid));
+	if (!ASSERT_OK(ret, "ueid cmd"))
+		goto fail;
+
+	ret = recv(fd, &msg, sizeof(msg), 0);
+	if (!ASSERT_FALSE(ret < 0 ||
+			  !NLMSG_OK(&msg.n, ret), "ueid response"))
+		goto fail;
+
+	if (msg.n.nlmsg_type == NLMSG_ERROR) {
+		err = NLMSG_DATA(&msg);
+		switch (op) {
+		case SMC_NETLINK_REMOVE_UEID:
+			if (!ASSERT_FALSE((err->error && err->error != -ENOENT),
+					  "ueid remove"))
+				goto fail;
+			break;
+		case SMC_NETLINK_ADD_UEID:
+			if (!ASSERT_OK(err->error, "ueid add"))
+				goto fail;
+			break;
+		default:
+			break;
+		}
+	}
+	close(fd);
+	return true;
+fail:
+	close(fd);
+	return false;
+}
+
+static bool setup_ueid(void)
+{
+	/* get smc nl id */
+	if (!get_smc_nl_family_id())
+		return false;
+	/* clear old ueid for bpftest */
+	smc_ueid(SMC_NETLINK_REMOVE_UEID);
+	/* smc-loopback required ueid */
+	return smc_ueid(SMC_NETLINK_ADD_UEID);
+}
+
+static void cleanup_ueid(void)
+{
+	smc_ueid(SMC_NETLINK_REMOVE_UEID);
+}
+#endif /* __s390x__ */
+
+static bool setup_netns(void)
+{
+	test_netns = netns_new(TEST_NS, true);
+	if (!ASSERT_OK_PTR(test_netns, "open net namespace"))
+		goto fail_netns;
+
+	SYS(fail_ip, "ip addr add 127.0.1.0/8 dev lo");
+	SYS(fail_ip, "ip addr add 127.0.2.0/8 dev lo");
+
+	return true;
+fail_ip:
+	netns_free(test_netns);
+fail_netns:
+	return false;
+}
+
+static void cleanup_netns(void)
+{
+	netns_free(test_netns);
+}
+
+static bool setup_smc(void)
+{
+	if (!setup_ueid())
+		return false;
+
+	if (!setup_netns())
+		goto fail_netns;
+
+	return true;
+fail_netns:
+	cleanup_ueid();
+	return false;
+}
+
+static int set_client_addr_cb(int fd, void *opts)
+{
+	const char *src = (const char *)opts;
+	struct sockaddr_in localaddr;
+
+	localaddr.sin_family = AF_INET;
+	localaddr.sin_port = htons(0);
+	localaddr.sin_addr.s_addr = inet_addr(src);
+	return !ASSERT_OK(bind(fd, &localaddr, sizeof(localaddr)), "client bind");
+}
+
+static void run_link(const char *src, const char *dst, int port)
+{
+	struct network_helper_opts opts = {0};
+	int server, client;
+
+	server = start_server_str(AF_INET, SOCK_STREAM, dst, port, NULL);
+	if (!ASSERT_OK_FD(server, "start service_1"))
+		return;
+
+	opts.proto = IPPROTO_TCP;
+	opts.post_socket_cb = set_client_addr_cb;
+	opts.cb_opts = (void *)src;
+
+	client = connect_to_fd_opts(server, &opts);
+	if (!ASSERT_OK_FD(client, "start connect"))
+		goto fail_client;
+
+	close(client);
+fail_client:
+	close(server);
+}
+
+static void block_link(int map_fd, const char *src, const char *dst)
+{
+	struct smc_policy_ip_value val = { .mode = /* block */ 0 };
+	struct smc_policy_ip_key key = {
+		.sip = inet_addr(src),
+		.dip = inet_addr(dst),
+	};
+
+	bpf_map_update_elem(map_fd, &key, &val, BPF_ANY);
+}
+
+/*
+ * This test describes a real-life service topology as follows:
+ *
+ *                             +-------------> service_1
+ *            link 1           |                     |
+ *   +--------------------> server                   |  link 2
+ *   |                         |                     V
+ *   |                         +-------------> service_2
+ *   |        link 3
+ *  client -------------------> server_via_unsafe_path -> service_3
+ *
+ * Among them,
+ * 1. link-1 is very suitable for using SMC.
+ * 2. link-2 is not suitable for using SMC, because the mode of this link is
+ *    kind of short-link services.
+ * 3. link-3 is also not suitable for using SMC, because the RDMA link is
+ *    unavailable and needs to go through a long timeout before it can fallback
+ *    to TCP.
+ * To achieve this goal, we use a customized SMC ip strategy via smc_hs_ctrl.
+ */
+static void test_topo(void)
+{
+	struct bpf_smc *skel;
+	int rc, map_fd;
+
+	skel = bpf_smc__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "bpf_smc__open_and_load"))
+		return;
+
+	rc = bpf_smc__attach(skel);
+	if (!ASSERT_OK(rc, "bpf_smc__attach"))
+		goto fail;
+
+	map_fd = bpf_map__fd(skel->maps.smc_policy_ip);
+	if (!ASSERT_OK_FD(map_fd, "bpf_map__fd"))
+		goto fail;
+
+	/* Mock the process of transparent replacement, since we will modify
+	 * protocol to ipproto_smc accropding to it via
+	 * fmod_ret/update_socket_protocol.
+	 */
+	write_sysctl("/proc/sys/net/smc/hs_ctrl", "linkcheck");
+
+	/* Configure ip strat */
+	block_link(map_fd, CLIENT_IP, SERVER_IP_VIA_RISK_PATH);
+	block_link(map_fd, SERVER_IP, SERVER_IP);
+
+	/* should go with smc */
+	run_link(CLIENT_IP, SERVER_IP, SERVICE_1);
+	/* should go with smc fallback */
+	run_link(SERVER_IP, SERVER_IP, SERVICE_2);
+
+	ASSERT_EQ(skel->bss->smc_cnt, 2, "smc count");
+	ASSERT_EQ(skel->bss->fallback_cnt, 1, "fallback count");
+
+	/* should go with smc */
+	run_link(CLIENT_IP, SERVER_IP, SERVICE_2);
+
+	ASSERT_EQ(skel->bss->smc_cnt, 3, "smc count");
+	ASSERT_EQ(skel->bss->fallback_cnt, 1, "fallback count");
+
+	/* should go with smc fallback */
+	run_link(CLIENT_IP, SERVER_IP_VIA_RISK_PATH, SERVICE_3);
+
+	ASSERT_EQ(skel->bss->smc_cnt, 4, "smc count");
+	ASSERT_EQ(skel->bss->fallback_cnt, 2, "fallback count");
+
+fail:
+	bpf_smc__destroy(skel);
+}
+
+void test_bpf_smc(void)
+{
+	if (!setup_smc()) {
+		printf("setup for smc test failed, test SKIP:\n");
+		test__skip();
+		return;
+	}
+
+	if (test__start_subtest("topo"))
+		test_topo();
+
+	cleanup_ueid();
+	cleanup_netns();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c b/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c
index c381faaae741..1750c29b94f8 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_bpf_syscall_macro.c
@@ -1,5 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright 2022 Sony Group Corporation */
+#define _GNU_SOURCE
+#include <fcntl.h>
 #include <sys/prctl.h>
 #include <test_progs.h>
 #include "bpf_syscall_macro.skel.h"
@@ -13,6 +15,8 @@ void test_bpf_syscall_macro(void)
 	unsigned long exp_arg3 = 13;
 	unsigned long exp_arg4 = 14;
 	unsigned long exp_arg5 = 15;
+	loff_t off_in, off_out;
+	ssize_t r;
 
 	/* check whether it can open program */
 	skel = bpf_syscall_macro__open();
@@ -33,11 +37,8 @@ void test_bpf_syscall_macro(void)
 
 	/* check whether args of syscall are copied correctly */
 	prctl(exp_arg1, exp_arg2, exp_arg3, exp_arg4, exp_arg5);
-#if defined(__aarch64__) || defined(__s390__)
-	ASSERT_NEQ(skel->bss->arg1, exp_arg1, "syscall_arg1");
-#else
+
 	ASSERT_EQ(skel->bss->arg1, exp_arg1, "syscall_arg1");
-#endif
 	ASSERT_EQ(skel->bss->arg2, exp_arg2, "syscall_arg2");
 	ASSERT_EQ(skel->bss->arg3, exp_arg3, "syscall_arg3");
 	/* it cannot copy arg4 when uses PT_REGS_PARM4 on x86_64 */
@@ -68,6 +69,18 @@ void test_bpf_syscall_macro(void)
 	ASSERT_EQ(skel->bss->arg4_syscall, exp_arg4, "BPF_KPROBE_SYSCALL_arg4");
 	ASSERT_EQ(skel->bss->arg5_syscall, exp_arg5, "BPF_KPROBE_SYSCALL_arg5");
 
+	r = splice(-42, &off_in, 42, &off_out, 0x12340000, SPLICE_F_NONBLOCK);
+	err = -errno;
+	ASSERT_EQ(r, -1, "splice_res");
+	ASSERT_EQ(err, -EBADF, "splice_err");
+
+	ASSERT_EQ(skel->bss->splice_fd_in, -42, "splice_arg1");
+	ASSERT_EQ(skel->bss->splice_off_in, (__u64)&off_in, "splice_arg2");
+	ASSERT_EQ(skel->bss->splice_fd_out, 42, "splice_arg3");
+	ASSERT_EQ(skel->bss->splice_off_out, (__u64)&off_out, "splice_arg4");
+	ASSERT_EQ(skel->bss->splice_len, 0x12340000, "splice_arg5");
+	ASSERT_EQ(skel->bss->splice_flags, SPLICE_F_NONBLOCK, "splice_arg6");
+
 cleanup:
 	bpf_syscall_macro__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpffs.c b/tools/testing/selftests/bpf/prog_tests/test_bpffs.c
index 214d9f4a94a5..ea933fd151c3 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_bpffs.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_bpffs.c
@@ -8,7 +8,8 @@
 #include <sys/types.h>
 #include <test_progs.h>
 
-#define TDIR "/sys/kernel/debug"
+/* TDIR must be in a location we can create a directory in. */
+#define TDIR "/tmp/test_bpffs_testdir"
 
 static int read_iter(char *file)
 {
@@ -43,8 +44,11 @@ static int fn(void)
 	if (!ASSERT_OK(err, "mount /"))
 		goto out;
 
-	err = umount(TDIR);
-	if (!ASSERT_OK(err, "umount " TDIR))
+	err =  mkdir(TDIR, 0777);
+	/* If the directory already exists we can carry on. It may be left over
+	 * from a previous run.
+	 */
+	if ((err && errno != EEXIST) && !ASSERT_OK(err, "mkdir " TDIR))
 		goto out;
 
 	err = mount("none", TDIR, "tmpfs", 0, NULL);
@@ -138,6 +142,7 @@ out:
 	rmdir(TDIR "/fs1");
 	rmdir(TDIR "/fs2");
 	umount(TDIR);
+	rmdir(TDIR);
 	exit(err);
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/test_bprm_opts.c b/tools/testing/selftests/bpf/prog_tests/test_bprm_opts.c
index a0054019e677..9c0200c132d9 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_bprm_opts.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_bprm_opts.c
@@ -51,7 +51,7 @@ static int run_set_secureexec(int map_fd, int secureexec)
 			exit(ret);
 
 		/* If the binary is executed with securexec=1, the dynamic
-		 * loader ingores and unsets certain variables like LD_PRELOAD,
+		 * loader ignores and unsets certain variables like LD_PRELOAD,
 		 * TMPDIR etc. TMPDIR is used here to simplify the example, as
 		 * LD_PRELOAD requires a real .so file.
 		 *
diff --git a/tools/testing/selftests/bpf/prog_tests/test_btf_ext.c b/tools/testing/selftests/bpf/prog_tests/test_btf_ext.c
new file mode 100644
index 000000000000..7d1b478c99a0
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_btf_ext.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms Inc. */
+#include <test_progs.h>
+#include "test_btf_ext.skel.h"
+#include "btf_helpers.h"
+
+static void subtest_line_func_info(void)
+{
+	struct test_btf_ext *skel;
+	struct bpf_prog_info info;
+	struct bpf_line_info line_info[128], *libbpf_line_info;
+	struct bpf_func_info func_info[128], *libbpf_func_info;
+	__u32 info_len = sizeof(info), libbbpf_line_info_cnt, libbbpf_func_info_cnt;
+	int err, fd;
+
+	skel = test_btf_ext__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return;
+
+	fd = bpf_program__fd(skel->progs.global_func);
+
+	memset(&info, 0, sizeof(info));
+	info.line_info = ptr_to_u64(&line_info);
+	info.nr_line_info = sizeof(line_info);
+	info.line_info_rec_size = sizeof(*line_info);
+	err = bpf_prog_get_info_by_fd(fd, &info, &info_len);
+	if (!ASSERT_OK(err, "prog_line_info"))
+		goto out;
+
+	libbpf_line_info = bpf_program__line_info(skel->progs.global_func);
+	libbbpf_line_info_cnt = bpf_program__line_info_cnt(skel->progs.global_func);
+
+	memset(&info, 0, sizeof(info));
+	info.func_info = ptr_to_u64(&func_info);
+	info.nr_func_info = sizeof(func_info);
+	info.func_info_rec_size = sizeof(*func_info);
+	err = bpf_prog_get_info_by_fd(fd, &info, &info_len);
+	if (!ASSERT_OK(err, "prog_func_info"))
+		goto out;
+
+	libbpf_func_info = bpf_program__func_info(skel->progs.global_func);
+	libbbpf_func_info_cnt = bpf_program__func_info_cnt(skel->progs.global_func);
+
+	if (!ASSERT_OK_PTR(libbpf_line_info, "bpf_program__line_info"))
+		goto out;
+	if (!ASSERT_EQ(libbbpf_line_info_cnt, info.nr_line_info, "line_info_cnt"))
+		goto out;
+	if (!ASSERT_OK_PTR(libbpf_func_info, "bpf_program__func_info"))
+		goto out;
+	if (!ASSERT_EQ(libbbpf_func_info_cnt, info.nr_func_info, "func_info_cnt"))
+		goto out;
+	ASSERT_MEMEQ(libbpf_line_info, line_info, libbbpf_line_info_cnt * sizeof(*line_info),
+		     "line_info");
+	ASSERT_MEMEQ(libbpf_func_info, func_info, libbbpf_func_info_cnt * sizeof(*func_info),
+		     "func_info");
+out:
+	test_btf_ext__destroy(skel);
+}
+
+void test_btf_ext(void)
+{
+	if (test__start_subtest("line_func_info"))
+		subtest_line_func_info();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_csum_diff.c b/tools/testing/selftests/bpf/prog_tests/test_csum_diff.c
new file mode 100644
index 000000000000..107b20d43e83
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_csum_diff.c
@@ -0,0 +1,408 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates */
+#include <test_progs.h>
+#include "csum_diff_test.skel.h"
+
+#define BUFF_SZ 512
+
+struct testcase {
+	unsigned long long to_buff[BUFF_SZ / 8];
+	unsigned int to_buff_len;
+	unsigned long long from_buff[BUFF_SZ / 8];
+	unsigned int from_buff_len;
+	unsigned short seed;
+	unsigned short result;
+};
+
+#define NUM_PUSH_TESTS 4
+
+struct testcase push_tests[NUM_PUSH_TESTS] = {
+	{
+		.to_buff = {
+			0xdeadbeefdeadbeef,
+		},
+		.to_buff_len = 8,
+		.from_buff = {},
+		.from_buff_len = 0,
+		.seed = 0,
+		.result = 0x3b3b
+	},
+	{
+		.to_buff = {
+			0xdeadbeefdeadbeef,
+			0xbeefdeadbeefdead,
+		},
+		.to_buff_len = 16,
+		.from_buff = {},
+		.from_buff_len = 0,
+		.seed = 0x1234,
+		.result = 0x88aa
+	},
+	{
+		.to_buff = {
+			0xdeadbeefdeadbeef,
+			0xbeefdeadbeefdead,
+		},
+		.to_buff_len = 15,
+		.from_buff = {},
+		.from_buff_len = 0,
+		.seed = 0x1234,
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+		.result = 0xcaa9
+#else
+		.result = 0x87fd
+#endif
+	},
+	{
+		.to_buff = {
+			0x327b23c66b8b4567,
+			0x66334873643c9869,
+			0x19495cff74b0dc51,
+			0x625558ec2ae8944a,
+			0x46e87ccd238e1f29,
+			0x507ed7ab3d1b58ba,
+			0x41b71efb2eb141f2,
+			0x7545e14679e2a9e3,
+			0x5bd062c2515f007c,
+			0x4db127f812200854,
+			0x1f16e9e80216231b,
+			0x66ef438d1190cde7,
+			0x3352255a140e0f76,
+			0x0ded7263109cf92e,
+			0x1befd79f7fdcc233,
+			0x6b68079a41a7c4c9,
+			0x25e45d324e6afb66,
+			0x431bd7b7519b500d,
+			0x7c83e4583f2dba31,
+			0x62bbd95a257130a3,
+			0x628c895d436c6125,
+			0x721da317333ab105,
+			0x2d1d5ae92443a858,
+			0x75a2a8d46763845e,
+			0x79838cb208edbdab,
+			0x0b03e0c64353d0cd,
+			0x54e49eb4189a769b,
+			0x2ca8861171f32454,
+			0x02901d820836c40e,
+			0x081386413a95f874,
+			0x7c3dbd3d1e7ff521,
+			0x6ceaf087737b8ddc,
+			0x4516dde922221a70,
+			0x614fd4a13006c83e,
+			0x5577f8e1419ac241,
+			0x05072367440badfc,
+			0x77465f013804823e,
+			0x5c482a977724c67e,
+			0x5e884adc2463b9ea,
+			0x2d51779651ead36b,
+			0x153ea438580bd78f,
+			0x70a64e2a3855585c,
+			0x2a487cb06a2342ec,
+			0x725a06fb1d4ed43b,
+			0x57e4ccaf2cd89a32,
+			0x4b588f547a6d8d3c,
+			0x6de91b18542289ec,
+			0x7644a45c38437fdb,
+			0x684a481a32fff902,
+			0x749abb43579478fe,
+			0x1ba026fa3dc240fb,
+			0x75c6c33a79a1deaa,
+			0x70c6a52912e685fb,
+			0x374a3fe6520eedd1,
+			0x23f9c13c4f4ef005,
+			0x275ac794649bb77c,
+			0x1cf10fd839386575,
+			0x235ba861180115be,
+			0x354fe9f947398c89,
+			0x741226bb15b5af5c,
+			0x10233c990d34b6a8,
+			0x615740953f6ab60f,
+			0x77ae35eb7e0c57b1,
+			0x310c50b3579be4f1,
+		},
+		.to_buff_len = 512,
+		.from_buff = {},
+		.from_buff_len = 0,
+		.seed = 0xffff,
+		.result = 0xca45
+	},
+};
+
+#define NUM_PULL_TESTS 4
+
+struct testcase pull_tests[NUM_PULL_TESTS] = {
+	{
+		.from_buff = {
+			0xdeadbeefdeadbeef,
+		},
+		.from_buff_len = 8,
+		.to_buff = {},
+		.to_buff_len = 0,
+		.seed = 0,
+		.result = 0xc4c4
+	},
+	{
+		.from_buff = {
+			0xdeadbeefdeadbeef,
+			0xbeefdeadbeefdead,
+		},
+		.from_buff_len = 16,
+		.to_buff = {},
+		.to_buff_len = 0,
+		.seed = 0x1234,
+		.result = 0x9bbd
+	},
+	{
+		.from_buff = {
+			0xdeadbeefdeadbeef,
+			0xbeefdeadbeefdead,
+		},
+		.from_buff_len = 15,
+		.to_buff = {},
+		.to_buff_len = 0,
+		.seed = 0x1234,
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+		.result = 0x59be
+#else
+		.result = 0x9c6a
+#endif
+	},
+	{
+		.from_buff = {
+			0x327b23c66b8b4567,
+			0x66334873643c9869,
+			0x19495cff74b0dc51,
+			0x625558ec2ae8944a,
+			0x46e87ccd238e1f29,
+			0x507ed7ab3d1b58ba,
+			0x41b71efb2eb141f2,
+			0x7545e14679e2a9e3,
+			0x5bd062c2515f007c,
+			0x4db127f812200854,
+			0x1f16e9e80216231b,
+			0x66ef438d1190cde7,
+			0x3352255a140e0f76,
+			0x0ded7263109cf92e,
+			0x1befd79f7fdcc233,
+			0x6b68079a41a7c4c9,
+			0x25e45d324e6afb66,
+			0x431bd7b7519b500d,
+			0x7c83e4583f2dba31,
+			0x62bbd95a257130a3,
+			0x628c895d436c6125,
+			0x721da317333ab105,
+			0x2d1d5ae92443a858,
+			0x75a2a8d46763845e,
+			0x79838cb208edbdab,
+			0x0b03e0c64353d0cd,
+			0x54e49eb4189a769b,
+			0x2ca8861171f32454,
+			0x02901d820836c40e,
+			0x081386413a95f874,
+			0x7c3dbd3d1e7ff521,
+			0x6ceaf087737b8ddc,
+			0x4516dde922221a70,
+			0x614fd4a13006c83e,
+			0x5577f8e1419ac241,
+			0x05072367440badfc,
+			0x77465f013804823e,
+			0x5c482a977724c67e,
+			0x5e884adc2463b9ea,
+			0x2d51779651ead36b,
+			0x153ea438580bd78f,
+			0x70a64e2a3855585c,
+			0x2a487cb06a2342ec,
+			0x725a06fb1d4ed43b,
+			0x57e4ccaf2cd89a32,
+			0x4b588f547a6d8d3c,
+			0x6de91b18542289ec,
+			0x7644a45c38437fdb,
+			0x684a481a32fff902,
+			0x749abb43579478fe,
+			0x1ba026fa3dc240fb,
+			0x75c6c33a79a1deaa,
+			0x70c6a52912e685fb,
+			0x374a3fe6520eedd1,
+			0x23f9c13c4f4ef005,
+			0x275ac794649bb77c,
+			0x1cf10fd839386575,
+			0x235ba861180115be,
+			0x354fe9f947398c89,
+			0x741226bb15b5af5c,
+			0x10233c990d34b6a8,
+			0x615740953f6ab60f,
+			0x77ae35eb7e0c57b1,
+			0x310c50b3579be4f1,
+		},
+		.from_buff_len = 512,
+		.to_buff = {},
+		.to_buff_len = 0,
+		.seed = 0xffff,
+		.result = 0x35ba
+	},
+};
+
+#define NUM_DIFF_TESTS 4
+
+struct testcase diff_tests[NUM_DIFF_TESTS] = {
+	{
+		.from_buff = {
+			0xdeadbeefdeadbeef,
+		},
+		.from_buff_len = 8,
+		.to_buff = {
+			0xabababababababab,
+		},
+		.to_buff_len = 8,
+		.seed = 0,
+		.result = 0x7373
+	},
+	{
+		.from_buff = {
+			0xdeadbeefdeadbeef,
+		},
+		.from_buff_len = 7,
+		.to_buff = {
+			0xabababababababab,
+		},
+		.to_buff_len = 7,
+		.seed = 0,
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+		.result = 0xa673
+#else
+		.result = 0x73b7
+#endif
+	},
+	{
+		.from_buff = {
+			0,
+		},
+		.from_buff_len = 8,
+		.to_buff = {
+			0xabababababababab,
+		},
+		.to_buff_len = 8,
+		.seed = 0,
+		.result = 0xaeae
+	},
+	{
+		.from_buff = {
+			0xdeadbeefdeadbeef
+		},
+		.from_buff_len = 8,
+		.to_buff = {
+			0,
+		},
+		.to_buff_len = 8,
+		.seed = 0xffff,
+		.result = 0xc4c4
+	},
+};
+
+#define NUM_EDGE_TESTS 4
+
+struct testcase edge_tests[NUM_EDGE_TESTS] = {
+	{
+		.from_buff = {},
+		.from_buff_len = 0,
+		.to_buff = {},
+		.to_buff_len = 0,
+		.seed = 0,
+		.result = 0
+	},
+	{
+		.from_buff = {
+			0x1234
+		},
+		.from_buff_len = 0,
+		.to_buff = {
+			0x1234
+		},
+		.to_buff_len = 0,
+		.seed = 0,
+		.result = 0
+	},
+	{
+		.from_buff = {},
+		.from_buff_len = 0,
+		.to_buff = {},
+		.to_buff_len = 0,
+		.seed = 0x1234,
+		.result = 0x1234
+	},
+	{
+		.from_buff = {},
+		.from_buff_len = 512,
+		.to_buff = {},
+		.to_buff_len = 0,
+		.seed = 0xffff,
+		.result = 0xffff
+	},
+};
+
+static unsigned short trigger_csum_diff(const struct csum_diff_test *skel)
+{
+	u8 tmp_out[64 << 2] = {};
+	u8 tmp_in[64] = {};
+	int err;
+	int pfd;
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = tmp_in,
+		.data_size_in = sizeof(tmp_in),
+		.data_out = tmp_out,
+		.data_size_out = sizeof(tmp_out),
+		.repeat = 1,
+	);
+	pfd = bpf_program__fd(skel->progs.compute_checksum);
+	err = bpf_prog_test_run_opts(pfd, &topts);
+	if (err)
+		return -1;
+
+	return skel->bss->result;
+}
+
+static void test_csum_diff(struct testcase *tests, int num_tests)
+{
+	struct csum_diff_test *skel;
+	unsigned short got;
+	int err;
+
+	for (int i = 0; i < num_tests; i++) {
+		skel = csum_diff_test__open();
+		if (!ASSERT_OK_PTR(skel, "csum_diff_test open"))
+			return;
+
+		skel->rodata->to_buff_len = tests[i].to_buff_len;
+		skel->rodata->from_buff_len = tests[i].from_buff_len;
+
+		err = csum_diff_test__load(skel);
+		if (!ASSERT_EQ(err, 0, "csum_diff_test load"))
+			goto out;
+
+		memcpy(skel->bss->to_buff, tests[i].to_buff, tests[i].to_buff_len);
+		memcpy(skel->bss->from_buff, tests[i].from_buff, tests[i].from_buff_len);
+		skel->bss->seed = tests[i].seed;
+
+		got = trigger_csum_diff(skel);
+		ASSERT_EQ(got, tests[i].result, "csum_diff result");
+
+		csum_diff_test__destroy(skel);
+	}
+
+	return;
+out:
+	csum_diff_test__destroy(skel);
+}
+
+void test_test_csum_diff(void)
+{
+	if (test__start_subtest("csum_diff_push"))
+		test_csum_diff(push_tests, NUM_PUSH_TESTS);
+	if (test__start_subtest("csum_diff_pull"))
+		test_csum_diff(pull_tests, NUM_PULL_TESTS);
+	if (test__start_subtest("csum_diff_diff"))
+		test_csum_diff(diff_tests, NUM_DIFF_TESTS);
+	if (test__start_subtest("csum_diff_edge"))
+		test_csum_diff(edge_tests, NUM_EDGE_TESTS);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
index 7295cc60f724..e905cbaf6b3d 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
@@ -1,104 +1,162 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
 #include <test_progs.h>
+#include "test_global_func1.skel.h"
+#include "test_global_func2.skel.h"
+#include "test_global_func3.skel.h"
+#include "test_global_func4.skel.h"
+#include "test_global_func5.skel.h"
+#include "test_global_func6.skel.h"
+#include "test_global_func7.skel.h"
+#include "test_global_func8.skel.h"
+#include "test_global_func9.skel.h"
+#include "test_global_func10.skel.h"
+#include "test_global_func11.skel.h"
+#include "test_global_func12.skel.h"
+#include "test_global_func13.skel.h"
+#include "test_global_func14.skel.h"
+#include "test_global_func15.skel.h"
+#include "test_global_func16.skel.h"
+#include "test_global_func17.skel.h"
+#include "test_global_func_ctx_args.skel.h"
+
+#include "bpf/libbpf_internal.h"
+#include "btf_helpers.h"
+
+static void check_ctx_arg_type(const struct btf *btf, const struct btf_param *p)
+{
+	const struct btf_type *t;
+	const char *s;
 
-const char *err_str;
-bool found;
+	t = btf__type_by_id(btf, p->type);
+	if (!ASSERT_EQ(btf_kind(t), BTF_KIND_PTR, "ptr_t"))
+		return;
 
-static int libbpf_debug_print(enum libbpf_print_level level,
-			      const char *format, va_list args)
-{
-	char *log_buf;
+	s = btf_type_raw_dump(btf, t->type);
+	if (!ASSERT_HAS_SUBSTR(s, "STRUCT 'bpf_perf_event_data' size=0 vlen=0",
+			       "ctx_struct_t"))
+		return;
+}
 
-	if (level != LIBBPF_WARN ||
-	    strcmp(format, "libbpf: \n%s\n")) {
-		vprintf(format, args);
-		return 0;
+static void subtest_ctx_arg_rewrite(void)
+{
+	struct test_global_func_ctx_args *skel = NULL;
+	struct bpf_prog_info info;
+	char func_info_buf[1024] __attribute__((aligned(8)));
+	struct bpf_func_info_min *rec;
+	struct btf *btf = NULL;
+	__u32 info_len = sizeof(info);
+	int err, fd, i;
+	struct btf *kern_btf = NULL;
+
+	kern_btf = btf__load_vmlinux_btf();
+	if (!ASSERT_OK_PTR(kern_btf, "kern_btf_load"))
+		return;
+
+	/* simple detection of kernel native arg:ctx tag support */
+	if (btf__find_by_name_kind(kern_btf, "bpf_subprog_arg_info", BTF_KIND_STRUCT) > 0) {
+		test__skip();
+		btf__free(kern_btf);
+		return;
 	}
+	btf__free(kern_btf);
 
-	log_buf = va_arg(args, char *);
-	if (!log_buf)
-		goto out;
-	if (err_str && strstr(log_buf, err_str) == 0)
-		found = true;
-out:
-	printf(format, log_buf);
-	return 0;
-}
+	skel = test_global_func_ctx_args__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
 
-extern int extra_prog_load_log_flags;
+	bpf_program__set_autoload(skel->progs.arg_tag_ctx_perf, true);
 
-static int check_load(const char *file)
-{
-	struct bpf_object *obj = NULL;
-	struct bpf_program *prog;
-	int err;
+	err = test_global_func_ctx_args__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto out;
 
-	found = false;
+	memset(&info, 0, sizeof(info));
+	info.func_info = ptr_to_u64(&func_info_buf);
+	info.nr_func_info = 3;
+	info.func_info_rec_size = sizeof(struct bpf_func_info_min);
 
-	obj = bpf_object__open_file(file, NULL);
-	err = libbpf_get_error(obj);
-	if (err)
-		return err;
+	fd = bpf_program__fd(skel->progs.arg_tag_ctx_perf);
+	err = bpf_prog_get_info_by_fd(fd, &info, &info_len);
+	if (!ASSERT_OK(err, "prog_info"))
+		goto out;
 
-	prog = bpf_object__next_program(obj, NULL);
-	if (!prog) {
-		err = -ENOENT;
-		goto err_out;
-	}
+	if (!ASSERT_EQ(info.nr_func_info, 3, "nr_func_info"))
+		goto out;
 
-	bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32);
-	bpf_program__set_log_level(prog, extra_prog_load_log_flags);
+	btf = btf__load_from_kernel_by_id(info.btf_id);
+	if (!ASSERT_OK_PTR(btf, "obj_kern_btf"))
+		goto out;
 
-	err = bpf_object__load(obj);
+	rec = (struct bpf_func_info_min *)func_info_buf;
+	for (i = 0; i < info.nr_func_info; i++, rec = (void *)rec + info.func_info_rec_size) {
+		const struct btf_type *fn_t, *proto_t;
+		const char *name;
+
+		if (rec->insn_off == 0)
+			continue; /* main prog, skip */
+
+		fn_t = btf__type_by_id(btf, rec->type_id);
+		if (!ASSERT_OK_PTR(fn_t, "fn_type"))
+			goto out;
+		if (!ASSERT_EQ(btf_kind(fn_t), BTF_KIND_FUNC, "fn_type_kind"))
+			goto out;
+		proto_t = btf__type_by_id(btf, fn_t->type);
+		if (!ASSERT_OK_PTR(proto_t, "proto_type"))
+			goto out;
+
+		name = btf__name_by_offset(btf, fn_t->name_off);
+		if (strcmp(name, "subprog_ctx_tag") == 0) {
+			/* int subprog_ctx_tag(void *ctx __arg_ctx) */
+			if (!ASSERT_EQ(btf_vlen(proto_t), 1, "arg_cnt"))
+				goto out;
+
+			/* arg 0 is PTR -> STRUCT bpf_perf_event_data */
+			check_ctx_arg_type(btf, &btf_params(proto_t)[0]);
+		} else if (strcmp(name, "subprog_multi_ctx_tags") == 0) {
+			/* int subprog_multi_ctx_tags(void *ctx1 __arg_ctx,
+			 *			      struct my_struct *mem,
+			 *			      void *ctx2 __arg_ctx)
+			 */
+			if (!ASSERT_EQ(btf_vlen(proto_t), 3, "arg_cnt"))
+				goto out;
+
+			/* arg 0 is PTR -> STRUCT bpf_perf_event_data */
+			check_ctx_arg_type(btf, &btf_params(proto_t)[0]);
+			/* arg 2 is PTR -> STRUCT bpf_perf_event_data */
+			check_ctx_arg_type(btf, &btf_params(proto_t)[2]);
+		} else {
+			ASSERT_FAIL("unexpected subprog %s", name);
+			goto out;
+		}
+	}
 
-err_out:
-	bpf_object__close(obj);
-	return err;
+out:
+	btf__free(btf);
+	test_global_func_ctx_args__destroy(skel);
 }
 
-struct test_def {
-	const char *file;
-	const char *err_str;
-};
-
 void test_test_global_funcs(void)
 {
-	struct test_def tests[] = {
-		{ "test_global_func1.bpf.o", "combined stack size of 4 calls is 544" },
-		{ "test_global_func2.bpf.o" },
-		{ "test_global_func3.bpf.o", "the call stack of 8 frames" },
-		{ "test_global_func4.bpf.o" },
-		{ "test_global_func5.bpf.o", "expected pointer to ctx, but got PTR" },
-		{ "test_global_func6.bpf.o", "modified ctx ptr R2" },
-		{ "test_global_func7.bpf.o", "foo() doesn't return scalar" },
-		{ "test_global_func8.bpf.o" },
-		{ "test_global_func9.bpf.o" },
-		{ "test_global_func10.bpf.o", "invalid indirect read from stack" },
-		{ "test_global_func11.bpf.o", "Caller passes invalid args into func#1" },
-		{ "test_global_func12.bpf.o", "invalid mem access 'mem_or_null'" },
-		{ "test_global_func13.bpf.o", "Caller passes invalid args into func#1" },
-		{ "test_global_func14.bpf.o", "reference type('FWD S') size cannot be determined" },
-		{ "test_global_func15.bpf.o", "At program exit the register R0 has value" },
-		{ "test_global_func16.bpf.o", "invalid indirect read from stack" },
-		{ "test_global_func17.bpf.o", "Caller passes invalid args into func#1" },
-	};
-	libbpf_print_fn_t old_print_fn = NULL;
-	int err, i, duration = 0;
-
-	old_print_fn = libbpf_set_print(libbpf_debug_print);
-
-	for (i = 0; i < ARRAY_SIZE(tests); i++) {
-		const struct test_def *test = &tests[i];
-
-		if (!test__start_subtest(test->file))
-			continue;
-
-		err_str = test->err_str;
-		err = check_load(test->file);
-		CHECK_FAIL(!!err ^ !!err_str);
-		if (err_str)
-			CHECK(found, "", "expected string '%s'", err_str);
-	}
-	libbpf_set_print(old_print_fn);
+	RUN_TESTS(test_global_func1);
+	RUN_TESTS(test_global_func2);
+	RUN_TESTS(test_global_func3);
+	RUN_TESTS(test_global_func4);
+	RUN_TESTS(test_global_func5);
+	RUN_TESTS(test_global_func6);
+	RUN_TESTS(test_global_func7);
+	RUN_TESTS(test_global_func8);
+	RUN_TESTS(test_global_func9);
+	RUN_TESTS(test_global_func10);
+	RUN_TESTS(test_global_func11);
+	RUN_TESTS(test_global_func12);
+	RUN_TESTS(test_global_func13);
+	RUN_TESTS(test_global_func14);
+	RUN_TESTS(test_global_func15);
+	RUN_TESTS(test_global_func16);
+	RUN_TESTS(test_global_func17);
+	RUN_TESTS(test_global_func_ctx_args);
+
+	if (test__start_subtest("ctx_arg_rewrite"))
+		subtest_ctx_arg_rewrite();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/test_ima.c b/tools/testing/selftests/bpf/prog_tests/test_ima.c
index b13feceb38f1..810b14981c2e 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_ima.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_ima.c
@@ -70,7 +70,7 @@ void test_test_ima(void)
 	u64 bin_true_sample;
 	char cmd[256];
 
-	int err, duration = 0;
+	int err, duration = 0, fresh_digest_idx = 0;
 	struct ima *skel = NULL;
 
 	skel = ima__open_and_load();
@@ -129,7 +129,15 @@ void test_test_ima(void)
 	/*
 	 * Test #3
 	 * - Goal: confirm that bpf_ima_inode_hash() returns a non-fresh digest
-	 * - Expected result: 2 samples (/bin/true: non-fresh, fresh)
+	 * - Expected result:
+	 *   1 sample (/bin/true: fresh) if commit 62622dab0a28 applied
+	 *   2 samples (/bin/true: non-fresh, fresh) if commit 62622dab0a28 is
+	 *     not applied
+	 *
+	 * If commit 62622dab0a28 ("ima: return IMA digest value only when
+	 * IMA_COLLECTED flag is set") is applied, bpf_ima_inode_hash() refuses
+	 * to give a non-fresh digest, hence the correct result is 1 instead of
+	 * 2.
 	 */
 	test_init(skel->bss);
 
@@ -144,13 +152,18 @@ void test_test_ima(void)
 		goto close_clean;
 
 	err = ring_buffer__consume(ringbuf);
-	ASSERT_EQ(err, 2, "num_samples_or_err");
-	ASSERT_NEQ(ima_hash_from_bpf[0], 0, "ima_hash");
-	ASSERT_NEQ(ima_hash_from_bpf[1], 0, "ima_hash");
-	ASSERT_EQ(ima_hash_from_bpf[0], bin_true_sample, "sample_equal_or_err");
+	ASSERT_GE(err, 1, "num_samples_or_err");
+	if (err == 2) {
+		ASSERT_NEQ(ima_hash_from_bpf[0], 0, "ima_hash");
+		ASSERT_EQ(ima_hash_from_bpf[0], bin_true_sample,
+			  "sample_equal_or_err");
+		fresh_digest_idx = 1;
+	}
+
+	ASSERT_NEQ(ima_hash_from_bpf[fresh_digest_idx], 0, "ima_hash");
 	/* IMA refreshed the digest. */
-	ASSERT_NEQ(ima_hash_from_bpf[1], bin_true_sample,
-		   "sample_different_or_err");
+	ASSERT_NEQ(ima_hash_from_bpf[fresh_digest_idx], bin_true_sample,
+		   "sample_equal_or_err");
 
 	/*
 	 * Test #4
diff --git a/tools/testing/selftests/bpf/prog_tests/test_ldsx_insn.c b/tools/testing/selftests/bpf/prog_tests/test_ldsx_insn.c
new file mode 100644
index 000000000000..375677c19146
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_ldsx_insn.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates.*/
+
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "test_ldsx_insn.skel.h"
+
+static void test_map_val_and_probed_memory(void)
+{
+	struct test_ldsx_insn *skel;
+	int err;
+
+	skel = test_ldsx_insn__open();
+	if (!ASSERT_OK_PTR(skel, "test_ldsx_insn__open"))
+		return;
+
+	if (skel->rodata->skip) {
+		test__skip();
+		goto out;
+	}
+
+	bpf_program__set_autoload(skel->progs.rdonly_map_prog, true);
+	bpf_program__set_autoload(skel->progs.map_val_prog, true);
+	bpf_program__set_autoload(skel->progs.test_ptr_struct_arg, true);
+
+	err = test_ldsx_insn__load(skel);
+	if (!ASSERT_OK(err, "test_ldsx_insn__load"))
+		goto out;
+
+	err = test_ldsx_insn__attach(skel);
+	if (!ASSERT_OK(err, "test_ldsx_insn__attach"))
+		goto out;
+
+	ASSERT_OK(trigger_module_test_read(256), "trigger_read");
+
+	ASSERT_EQ(skel->bss->done1, 1, "done1");
+	ASSERT_EQ(skel->bss->ret1, 1, "ret1");
+	ASSERT_EQ(skel->bss->done2, 1, "done2");
+	ASSERT_EQ(skel->bss->ret2, 1, "ret2");
+	ASSERT_EQ(skel->bss->int_member, -1, "int_member");
+
+out:
+	test_ldsx_insn__destroy(skel);
+}
+
+static void test_ctx_member_sign_ext(void)
+{
+	struct test_ldsx_insn *skel;
+	int err, fd, cgroup_fd;
+	char buf[16] = {0};
+	socklen_t optlen;
+
+	cgroup_fd = test__join_cgroup("/ldsx_test");
+	if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup /ldsx_test"))
+		return;
+
+	skel = test_ldsx_insn__open();
+	if (!ASSERT_OK_PTR(skel, "test_ldsx_insn__open"))
+		goto close_cgroup_fd;
+
+	if (skel->rodata->skip) {
+		test__skip();
+		goto destroy_skel;
+	}
+
+	bpf_program__set_autoload(skel->progs._getsockopt, true);
+
+	err = test_ldsx_insn__load(skel);
+	if (!ASSERT_OK(err, "test_ldsx_insn__load"))
+		goto destroy_skel;
+
+	skel->links._getsockopt =
+		bpf_program__attach_cgroup(skel->progs._getsockopt, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links._getsockopt, "getsockopt_link"))
+		goto destroy_skel;
+
+	fd = socket(AF_INET, SOCK_STREAM, 0);
+	if (!ASSERT_GE(fd, 0, "socket"))
+		goto destroy_skel;
+
+	optlen = sizeof(buf);
+	(void)getsockopt(fd, SOL_IP, IP_TTL, buf, &optlen);
+
+	ASSERT_EQ(skel->bss->set_optlen, -1, "optlen");
+	ASSERT_EQ(skel->bss->set_retval, -1, "retval");
+
+	close(fd);
+destroy_skel:
+	test_ldsx_insn__destroy(skel);
+close_cgroup_fd:
+	close(cgroup_fd);
+}
+
+static void test_ctx_member_narrow_sign_ext(void)
+{
+	struct test_ldsx_insn *skel;
+	struct __sk_buff skb = {};
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		    .data_in = &pkt_v4,
+		    .data_size_in = sizeof(pkt_v4),
+		    .ctx_in = &skb,
+		    .ctx_size_in = sizeof(skb),
+	);
+	int err, prog_fd;
+
+	skel = test_ldsx_insn__open();
+	if (!ASSERT_OK_PTR(skel, "test_ldsx_insn__open"))
+		return;
+
+	if (skel->rodata->skip) {
+		test__skip();
+		goto out;
+	}
+
+	bpf_program__set_autoload(skel->progs._tc, true);
+
+	err = test_ldsx_insn__load(skel);
+	if (!ASSERT_OK(err, "test_ldsx_insn__load"))
+		goto out;
+
+	prog_fd = bpf_program__fd(skel->progs._tc);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run");
+
+	ASSERT_EQ(skel->bss->set_mark, -2, "set_mark");
+
+out:
+	test_ldsx_insn__destroy(skel);
+}
+
+void test_ldsx_insn(void)
+{
+	if (test__start_subtest("map_val and probed_memory"))
+		test_map_val_and_probed_memory();
+	if (test__start_subtest("ctx_member_sign_ext"))
+		test_ctx_member_sign_ext();
+	if (test__start_subtest("ctx_member_narrow_sign_ext"))
+		test_ctx_member_narrow_sign_ext();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_local_storage.c b/tools/testing/selftests/bpf/prog_tests/test_local_storage.c
index 9c77cd6b1eaf..bcf2e1905ed7 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_local_storage.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_local_storage.c
@@ -13,8 +13,6 @@
 #include "network_helpers.h"
 #include "task_local_storage_helpers.h"
 
-static unsigned int duration;
-
 #define TEST_STORAGE_VALUE 0xbeefdead
 
 struct storage {
@@ -25,7 +23,7 @@ struct storage {
 /* Fork and exec the provided rm binary and return the exit code of the
  * forked process and its pid.
  */
-static int run_self_unlink(int *monitored_pid, const char *rm_path)
+static int run_self_unlink(struct local_storage *skel, const char *rm_path)
 {
 	int child_pid, child_status, ret;
 	int null_fd;
@@ -37,7 +35,7 @@ static int run_self_unlink(int *monitored_pid, const char *rm_path)
 		dup2(null_fd, STDERR_FILENO);
 		close(null_fd);
 
-		*monitored_pid = getpid();
+		skel->bss->monitored_pid = getpid();
 		/* Use the copied /usr/bin/rm to delete itself
 		 * /tmp/copy_of_rm /tmp/copy_of_rm.
 		 */
@@ -46,6 +44,7 @@ static int run_self_unlink(int *monitored_pid, const char *rm_path)
 			exit(errno);
 	} else if (child_pid > 0) {
 		waitpid(child_pid, &child_status, 0);
+		ASSERT_EQ(skel->data->task_storage_result, 0, "task_storage_result");
 		return WEXITSTATUS(child_status);
 	}
 
@@ -60,36 +59,30 @@ static bool check_syscall_operations(int map_fd, int obj_fd)
 
 	/* Looking up an existing element should fail initially */
 	err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val, 0);
-	if (CHECK(!err || errno != ENOENT, "bpf_map_lookup_elem",
-		  "err:%d errno:%d\n", err, errno))
+	if (!ASSERT_EQ(err, -ENOENT, "bpf_map_lookup_elem"))
 		return false;
 
 	/* Create a new element */
 	err = bpf_map_update_elem(map_fd, &obj_fd, &val, BPF_NOEXIST);
-	if (CHECK(err < 0, "bpf_map_update_elem", "err:%d errno:%d\n", err,
-		  errno))
+	if (!ASSERT_OK(err, "bpf_map_update_elem"))
 		return false;
 
 	/* Lookup the newly created element */
 	err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val, 0);
-	if (CHECK(err < 0, "bpf_map_lookup_elem", "err:%d errno:%d", err,
-		  errno))
+	if (!ASSERT_OK(err, "bpf_map_lookup_elem"))
 		return false;
 
 	/* Check the value of the newly created element */
-	if (CHECK(lookup_val.value != val.value, "bpf_map_lookup_elem",
-		  "value got = %x errno:%d", lookup_val.value, val.value))
+	if (!ASSERT_EQ(lookup_val.value, val.value, "bpf_map_lookup_elem"))
 		return false;
 
 	err = bpf_map_delete_elem(map_fd, &obj_fd);
-	if (CHECK(err, "bpf_map_delete_elem()", "err:%d errno:%d\n", err,
-		  errno))
+	if (!ASSERT_OK(err, "bpf_map_delete_elem()"))
 		return false;
 
 	/* The lookup should fail, now that the element has been deleted */
 	err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val, 0);
-	if (CHECK(!err || errno != ENOENT, "bpf_map_lookup_elem",
-		  "err:%d errno:%d\n", err, errno))
+	if (!ASSERT_EQ(err, -ENOENT, "bpf_map_lookup_elem"))
 		return false;
 
 	return true;
@@ -104,35 +97,32 @@ void test_test_local_storage(void)
 	char cmd[256];
 
 	skel = local_storage__open_and_load();
-	if (CHECK(!skel, "skel_load", "lsm skeleton failed\n"))
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
 		goto close_prog;
 
 	err = local_storage__attach(skel);
-	if (CHECK(err, "attach", "lsm attach failed: %d\n", err))
+	if (!ASSERT_OK(err, "attach"))
 		goto close_prog;
 
 	task_fd = sys_pidfd_open(getpid(), 0);
-	if (CHECK(task_fd < 0, "pidfd_open",
-		  "failed to get pidfd err:%d, errno:%d", task_fd, errno))
+	if (!ASSERT_GE(task_fd, 0, "pidfd_open"))
 		goto close_prog;
 
 	if (!check_syscall_operations(bpf_map__fd(skel->maps.task_storage_map),
 				      task_fd))
 		goto close_prog;
 
-	if (CHECK(!mkdtemp(tmp_dir_path), "mkdtemp",
-		  "unable to create tmpdir: %d\n", errno))
+	if (!ASSERT_OK_PTR(mkdtemp(tmp_dir_path), "mkdtemp"))
 		goto close_prog;
 
 	snprintf(tmp_exec_path, sizeof(tmp_exec_path), "%s/copy_of_rm",
 		 tmp_dir_path);
 	snprintf(cmd, sizeof(cmd), "cp /bin/rm %s", tmp_exec_path);
-	if (CHECK_FAIL(system(cmd)))
+	if (!ASSERT_OK(system(cmd), "system(cp)"))
 		goto close_prog_rmdir;
 
 	rm_fd = open(tmp_exec_path, O_RDONLY);
-	if (CHECK(rm_fd < 0, "open", "failed to open %s err:%d, errno:%d",
-		  tmp_exec_path, rm_fd, errno))
+	if (!ASSERT_GE(rm_fd, 0, "open(tmp_exec_path)"))
 		goto close_prog_rmdir;
 
 	if (!check_syscall_operations(bpf_map__fd(skel->maps.inode_storage_map),
@@ -144,8 +134,8 @@ void test_test_local_storage(void)
 	 * unlink its executable. This operation should be denied by the loaded
 	 * LSM program.
 	 */
-	err = run_self_unlink(&skel->bss->monitored_pid, tmp_exec_path);
-	if (CHECK(err != EPERM, "run_self_unlink", "err %d want EPERM\n", err))
+	err = run_self_unlink(skel, tmp_exec_path);
+	if (!ASSERT_EQ(err, EPERM, "run_self_unlink"))
 		goto close_prog_rmdir;
 
 	/* Set the process being monitored to be the current process */
@@ -156,18 +146,16 @@ void test_test_local_storage(void)
 	 */
 	snprintf(cmd, sizeof(cmd), "mv %s/copy_of_rm %s/check_null_ptr",
 		 tmp_dir_path, tmp_dir_path);
-	if (CHECK_FAIL(system(cmd)))
+	if (!ASSERT_OK(system(cmd), "system(mv)"))
 		goto close_prog_rmdir;
 
-	CHECK(skel->data->inode_storage_result != 0, "inode_storage_result",
-	      "inode_local_storage not set\n");
+	ASSERT_EQ(skel->data->inode_storage_result, 0, "inode_storage_result");
 
 	serv_sk = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
-	if (CHECK(serv_sk < 0, "start_server", "failed to start server\n"))
+	if (!ASSERT_GE(serv_sk, 0, "start_server"))
 		goto close_prog_rmdir;
 
-	CHECK(skel->data->sk_storage_result != 0, "sk_storage_result",
-	      "sk_local_storage not set\n");
+	ASSERT_EQ(skel->data->sk_storage_result, 0, "sk_storage_result");
 
 	if (!check_syscall_operations(bpf_map__fd(skel->maps.sk_storage_map),
 				      serv_sk))
diff --git a/tools/testing/selftests/bpf/prog_tests/test_lsm.c b/tools/testing/selftests/bpf/prog_tests/test_lsm.c
index 244c01125126..bdc4fc06bc5a 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_lsm.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_lsm.c
@@ -12,6 +12,7 @@
 #include <stdlib.h>
 
 #include "lsm.skel.h"
+#include "lsm_tailcall.skel.h"
 
 char *CMD_ARGS[] = {"true", NULL};
 
@@ -75,7 +76,8 @@ static int test_lsm(struct lsm *skel)
 	skel->bss->monitored_pid = getpid();
 
 	err = stack_mprotect();
-	if (!ASSERT_EQ(errno, EPERM, "stack_mprotect"))
+	if (!ASSERT_EQ(err, -1, "stack_mprotect") ||
+	    !ASSERT_EQ(errno, EPERM, "stack_mprotect"))
 		return err;
 
 	ASSERT_EQ(skel->bss->mprotect_count, 1, "mprotect_count");
@@ -94,7 +96,7 @@ static int test_lsm(struct lsm *skel)
 	return 0;
 }
 
-void test_test_lsm(void)
+static void test_lsm_basic(void)
 {
 	struct lsm *skel = NULL;
 	int err;
@@ -113,3 +115,46 @@ void test_test_lsm(void)
 close_prog:
 	lsm__destroy(skel);
 }
+
+static void test_lsm_tailcall(void)
+{
+	struct lsm_tailcall *skel = NULL;
+	int map_fd, prog_fd;
+	int err, key;
+
+	skel = lsm_tailcall__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "lsm_tailcall__skel_load"))
+		goto close_prog;
+
+	map_fd = bpf_map__fd(skel->maps.jmp_table);
+	if (CHECK_FAIL(map_fd < 0))
+		goto close_prog;
+
+	prog_fd = bpf_program__fd(skel->progs.lsm_file_permission_prog);
+	if (CHECK_FAIL(prog_fd < 0))
+		goto close_prog;
+
+	key = 0;
+	err = bpf_map_update_elem(map_fd, &key, &prog_fd, BPF_ANY);
+	if (CHECK_FAIL(!err))
+		goto close_prog;
+
+	prog_fd = bpf_program__fd(skel->progs.lsm_kernfs_init_security_prog);
+	if (CHECK_FAIL(prog_fd < 0))
+		goto close_prog;
+
+	err = bpf_map_update_elem(map_fd, &key, &prog_fd, BPF_ANY);
+	if (CHECK_FAIL(err))
+		goto close_prog;
+
+close_prog:
+	lsm_tailcall__destroy(skel);
+}
+
+void test_test_lsm(void)
+{
+	if (test__start_subtest("lsm_basic"))
+		test_lsm_basic();
+	if (test__start_subtest("lsm_tailcall"))
+		test_lsm_tailcall();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_mmap_inner_array.c b/tools/testing/selftests/bpf/prog_tests/test_mmap_inner_array.c
new file mode 100644
index 000000000000..ce745776ed18
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_mmap_inner_array.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <sys/mman.h>
+#include "mmap_inner_array.skel.h"
+
+void test_mmap_inner_array(void)
+{
+	const long page_size = sysconf(_SC_PAGE_SIZE);
+	struct mmap_inner_array *skel;
+	int inner_array_fd, err;
+	void *tmp;
+	__u64 *val;
+
+	skel = mmap_inner_array__open_and_load();
+
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	inner_array_fd = bpf_map__fd(skel->maps.inner_array);
+	tmp = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, inner_array_fd, 0);
+	if (!ASSERT_OK_PTR(tmp, "inner array mmap"))
+		goto out;
+	val = (void *)tmp;
+
+	err = mmap_inner_array__attach(skel);
+	if (!ASSERT_OK(err, "attach"))
+		goto out_unmap;
+
+	skel->bss->pid = getpid();
+	usleep(1);
+
+	/* pid is set, pid_match == true and outer_map_match == false */
+	ASSERT_TRUE(skel->bss->pid_match, "pid match 1");
+	ASSERT_FALSE(skel->bss->outer_map_match, "outer map match 1");
+	ASSERT_FALSE(skel->bss->done, "done 1");
+	ASSERT_EQ(*val, 0, "value match 1");
+
+	err = bpf_map__update_elem(skel->maps.outer_map,
+				   &skel->bss->pid, sizeof(skel->bss->pid),
+				   &inner_array_fd, sizeof(inner_array_fd),
+				   BPF_ANY);
+	if (!ASSERT_OK(err, "update elem"))
+		goto out_unmap;
+	usleep(1);
+
+	/* outer map key is set, outer_map_match == true */
+	ASSERT_TRUE(skel->bss->pid_match, "pid match 2");
+	ASSERT_TRUE(skel->bss->outer_map_match, "outer map match 2");
+	ASSERT_TRUE(skel->bss->done, "done 2");
+	ASSERT_EQ(*val, skel->data->match_value, "value match 2");
+
+out_unmap:
+	munmap(tmp, page_size);
+out:
+	mmap_inner_array__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c b/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c
index ae93411fd582..09ca13bdf6ca 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c
@@ -11,6 +11,7 @@ static int sanity_run(struct bpf_program *prog)
 		.data_in = &pkt_v4,
 		.data_size_in = sizeof(pkt_v4),
 		.repeat = 1,
+		.flags = BPF_F_TEST_SKB_CHECKSUM_COMPLETE,
 	);
 
 	prog_fd = bpf_program__fd(prog);
diff --git a/tools/testing/selftests/bpf/prog_tests/test_strncmp.c b/tools/testing/selftests/bpf/prog_tests/test_strncmp.c
index 7ddd6615b7e7..baceb0de9d49 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_strncmp.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_strncmp.c
@@ -72,7 +72,7 @@ static void test_strncmp_ret(void)
 	got = trigger_strncmp(skel);
 	ASSERT_EQ(got, 0, "strncmp: same str");
 
-	/* Not-null-termainted string  */
+	/* Not-null-terminated string  */
 	memcpy(skel->bss->str, skel->rodata->target, sizeof(skel->bss->str));
 	skel->bss->str[sizeof(skel->bss->str) - 1] = 'A';
 	got = trigger_strncmp(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_id_ops_mapping.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_id_ops_mapping.c
new file mode 100644
index 000000000000..fd8762ba4b67
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_id_ops_mapping.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "struct_ops_id_ops_mapping1.skel.h"
+#include "struct_ops_id_ops_mapping2.skel.h"
+
+static void test_st_ops_id_ops_mapping(void)
+{
+	struct struct_ops_id_ops_mapping1 *skel1 = NULL;
+	struct struct_ops_id_ops_mapping2 *skel2 = NULL;
+	struct bpf_map_info info = {};
+	__u32 len = sizeof(info);
+	int err, pid, prog1_fd, prog2_fd;
+
+	skel1 = struct_ops_id_ops_mapping1__open_and_load();
+	if (!ASSERT_OK_PTR(skel1, "struct_ops_id_ops_mapping1__open"))
+		goto out;
+
+	skel2 = struct_ops_id_ops_mapping2__open_and_load();
+	if (!ASSERT_OK_PTR(skel2, "struct_ops_id_ops_mapping2__open"))
+		goto out;
+
+	err = bpf_map_get_info_by_fd(bpf_map__fd(skel1->maps.st_ops_map),
+				     &info, &len);
+	if (!ASSERT_OK(err, "bpf_map_get_info_by_fd"))
+		goto out;
+
+	skel1->bss->st_ops_id = info.id;
+
+	err = bpf_map_get_info_by_fd(bpf_map__fd(skel2->maps.st_ops_map),
+				     &info, &len);
+	if (!ASSERT_OK(err, "bpf_map_get_info_by_fd"))
+		goto out;
+
+	skel2->bss->st_ops_id = info.id;
+
+	err = struct_ops_id_ops_mapping1__attach(skel1);
+	if (!ASSERT_OK(err, "struct_ops_id_ops_mapping1__attach"))
+		goto out;
+
+	err = struct_ops_id_ops_mapping2__attach(skel2);
+	if (!ASSERT_OK(err, "struct_ops_id_ops_mapping2__attach"))
+		goto out;
+
+	/* run tracing prog that calls .test_1 and checks return */
+	pid = getpid();
+	skel1->bss->test_pid = pid;
+	skel2->bss->test_pid = pid;
+	sys_gettid();
+	skel1->bss->test_pid = 0;
+	skel2->bss->test_pid = 0;
+
+	/* run syscall_prog that calls .test_1 and checks return */
+	prog1_fd = bpf_program__fd(skel1->progs.syscall_prog);
+	err = bpf_prog_test_run_opts(prog1_fd, NULL);
+	ASSERT_OK(err, "bpf_prog_test_run_opts");
+
+	prog2_fd = bpf_program__fd(skel2->progs.syscall_prog);
+	err = bpf_prog_test_run_opts(prog2_fd, NULL);
+	ASSERT_OK(err, "bpf_prog_test_run_opts");
+
+	ASSERT_EQ(skel1->bss->test_err, 0, "skel1->bss->test_err");
+	ASSERT_EQ(skel2->bss->test_err, 0, "skel2->bss->test_err");
+
+out:
+	struct_ops_id_ops_mapping1__destroy(skel1);
+	struct_ops_id_ops_mapping2__destroy(skel2);
+}
+
+void test_struct_ops_id_ops_mapping(void)
+{
+	if (test__start_subtest("st_ops_id_ops_mapping"))
+		test_st_ops_id_ops_mapping();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_kptr_return.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_kptr_return.c
new file mode 100644
index 000000000000..467cc72a3588
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_kptr_return.c
@@ -0,0 +1,16 @@
+#include <test_progs.h>
+
+#include "struct_ops_kptr_return.skel.h"
+#include "struct_ops_kptr_return_fail__wrong_type.skel.h"
+#include "struct_ops_kptr_return_fail__invalid_scalar.skel.h"
+#include "struct_ops_kptr_return_fail__nonzero_offset.skel.h"
+#include "struct_ops_kptr_return_fail__local_kptr.skel.h"
+
+void test_struct_ops_kptr_return(void)
+{
+	RUN_TESTS(struct_ops_kptr_return);
+	RUN_TESTS(struct_ops_kptr_return_fail__wrong_type);
+	RUN_TESTS(struct_ops_kptr_return_fail__invalid_scalar);
+	RUN_TESTS(struct_ops_kptr_return_fail__nonzero_offset);
+	RUN_TESTS(struct_ops_kptr_return_fail__local_kptr);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_maybe_null.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_maybe_null.c
new file mode 100644
index 000000000000..01dc2613c8a5
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_maybe_null.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+
+#include "struct_ops_maybe_null.skel.h"
+#include "struct_ops_maybe_null_fail.skel.h"
+
+/* Test that the verifier accepts a program that access a nullable pointer
+ * with a proper check.
+ */
+static void maybe_null(void)
+{
+	struct struct_ops_maybe_null *skel;
+
+	skel = struct_ops_maybe_null__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_module_open_and_load"))
+		return;
+
+	struct_ops_maybe_null__destroy(skel);
+}
+
+/* Test that the verifier rejects a program that access a nullable pointer
+ * without a check beforehand.
+ */
+static void maybe_null_fail(void)
+{
+	struct struct_ops_maybe_null_fail *skel;
+
+	skel = struct_ops_maybe_null_fail__open_and_load();
+	if (ASSERT_ERR_PTR(skel, "struct_ops_module_fail__open_and_load"))
+		return;
+
+	struct_ops_maybe_null_fail__destroy(skel);
+}
+
+void test_struct_ops_maybe_null(void)
+{
+	/* The verifier verifies the programs at load time, so testing both
+	 * programs in the same compile-unit is complicated. We run them in
+	 * separate objects to simplify the testing.
+	 */
+	if (test__start_subtest("maybe_null"))
+		maybe_null();
+	if (test__start_subtest("maybe_null_fail"))
+		maybe_null_fail();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c
new file mode 100644
index 000000000000..75a0dea511b3
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_module.c
@@ -0,0 +1,317 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <time.h>
+
+#include <sys/epoll.h>
+
+#include "struct_ops_module.skel.h"
+#include "struct_ops_nulled_out_cb.skel.h"
+#include "struct_ops_forgotten_cb.skel.h"
+#include "struct_ops_detach.skel.h"
+#include "unsupported_ops.skel.h"
+
+static void check_map_info(struct bpf_map_info *info)
+{
+	struct bpf_btf_info btf_info;
+	char btf_name[256];
+	u32 btf_info_len = sizeof(btf_info);
+	int err, fd;
+
+	fd = bpf_btf_get_fd_by_id(info->btf_vmlinux_id);
+	if (!ASSERT_GE(fd, 0, "get_value_type_btf_obj_fd"))
+		return;
+
+	memset(&btf_info, 0, sizeof(btf_info));
+	btf_info.name = ptr_to_u64(btf_name);
+	btf_info.name_len = sizeof(btf_name);
+	err = bpf_btf_get_info_by_fd(fd, &btf_info, &btf_info_len);
+	if (!ASSERT_OK(err, "get_value_type_btf_obj_info"))
+		goto cleanup;
+
+	if (!ASSERT_EQ(strcmp(btf_name, "bpf_testmod"), 0, "get_value_type_btf_obj_name"))
+		goto cleanup;
+
+cleanup:
+	close(fd);
+}
+
+static int attach_ops_and_check(struct struct_ops_module *skel,
+				struct bpf_map *map,
+				int expected_test_2_result)
+{
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(map);
+	ASSERT_OK_PTR(link, "attach_test_mod_1");
+	if (!link)
+		return -1;
+
+	/* test_{1,2}() would be called from bpf_dummy_reg() in bpf_testmod.c */
+	ASSERT_EQ(skel->bss->test_1_result, 0xdeadbeef, "test_1_result");
+	ASSERT_EQ(skel->bss->test_2_result, expected_test_2_result, "test_2_result");
+
+	bpf_link__destroy(link);
+	return 0;
+}
+
+static void test_struct_ops_load(void)
+{
+	struct struct_ops_module *skel;
+	struct bpf_map_info info = {};
+	int err;
+	u32 len;
+
+	skel = struct_ops_module__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_module_open"))
+		return;
+
+	skel->struct_ops.testmod_1->data = 13;
+	skel->struct_ops.testmod_1->test_2 = skel->progs.test_3;
+	/* Since test_2() is not being used, it should be disabled from
+	 * auto-loading, or it will fail to load.
+	 */
+	bpf_program__set_autoload(skel->progs.test_2, false);
+	bpf_map__set_autocreate(skel->maps.testmod_zeroed, false);
+
+	err = struct_ops_module__load(skel);
+	if (!ASSERT_OK(err, "struct_ops_module_load"))
+		goto cleanup;
+
+	len = sizeof(info);
+	err = bpf_map_get_info_by_fd(bpf_map__fd(skel->maps.testmod_1), &info,
+				     &len);
+	if (!ASSERT_OK(err, "bpf_map_get_info_by_fd"))
+		goto cleanup;
+
+	check_map_info(&info);
+	/* test_3() will be called from bpf_dummy_reg() in bpf_testmod.c
+	 *
+	 * In bpf_testmod.c it will pass 4 and 13 (the value of data) to
+	 * .test_2.  So, the value of test_2_result should be 20 (4 + 13 +
+	 * 3).
+	 */
+	if (!attach_ops_and_check(skel, skel->maps.testmod_1, 20))
+		goto cleanup;
+	if (!attach_ops_and_check(skel, skel->maps.testmod_2, 12))
+		goto cleanup;
+
+cleanup:
+	struct_ops_module__destroy(skel);
+}
+
+static void test_struct_ops_not_zeroed(void)
+{
+	struct struct_ops_module *skel;
+	int err;
+
+	/* zeroed is 0, and zeroed_op is null */
+	skel = struct_ops_module__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_module_open"))
+		return;
+
+	skel->struct_ops.testmod_zeroed->zeroed = 0;
+	/* zeroed_op prog should be not loaded automatically now */
+	skel->struct_ops.testmod_zeroed->zeroed_op = NULL;
+
+	err = struct_ops_module__load(skel);
+	ASSERT_OK(err, "struct_ops_module_load");
+
+	struct_ops_module__destroy(skel);
+
+	/* zeroed is not 0 */
+	skel = struct_ops_module__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_module_open_not_zeroed"))
+		return;
+
+	/* libbpf should reject the testmod_zeroed since struct
+	 * bpf_testmod_ops in the kernel has no "zeroed" field and the
+	 * value of "zeroed" is non-zero.
+	 */
+	skel->struct_ops.testmod_zeroed->zeroed = 0xdeadbeef;
+	skel->struct_ops.testmod_zeroed->zeroed_op = NULL;
+	err = struct_ops_module__load(skel);
+	ASSERT_ERR(err, "struct_ops_module_load_not_zeroed");
+
+	struct_ops_module__destroy(skel);
+
+	/* zeroed_op is not null */
+	skel = struct_ops_module__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_module_open_not_zeroed_op"))
+		return;
+
+	/* libbpf should reject the testmod_zeroed since the value of its
+	 * "zeroed_op" is not null.
+	 */
+	skel->struct_ops.testmod_zeroed->zeroed_op = skel->progs.test_3;
+	err = struct_ops_module__load(skel);
+	ASSERT_ERR(err, "struct_ops_module_load_not_zeroed_op");
+
+	struct_ops_module__destroy(skel);
+}
+
+/* The signature of an implementation might not match the signature of the
+ * function pointer prototype defined in the BPF program. This mismatch
+ * should be allowed as long as the behavior of the operator program
+ * adheres to the signature in the kernel. Libbpf should not enforce the
+ * signature; rather, let the kernel verifier handle the enforcement.
+ */
+static void test_struct_ops_incompatible(void)
+{
+	struct struct_ops_module *skel;
+	struct bpf_link *link;
+	int err;
+
+	skel = struct_ops_module__open();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_module_open"))
+		return;
+
+	bpf_map__set_autocreate(skel->maps.testmod_zeroed, false);
+
+	err = struct_ops_module__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	link = bpf_map__attach_struct_ops(skel->maps.testmod_incompatible);
+	if (ASSERT_OK_PTR(link, "attach_struct_ops"))
+		bpf_link__destroy(link);
+
+cleanup:
+	struct_ops_module__destroy(skel);
+}
+
+/* validate that it's ok to "turn off" callback that kernel supports */
+static void test_struct_ops_nulled_out_cb(void)
+{
+	struct struct_ops_nulled_out_cb *skel;
+	int err;
+
+	skel = struct_ops_nulled_out_cb__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	/* kernel knows about test_1, but we still null it out */
+	skel->struct_ops.ops->test_1 = NULL;
+
+	err = struct_ops_nulled_out_cb__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	ASSERT_FALSE(bpf_program__autoload(skel->progs.test_1_turn_off), "prog_autoload");
+	ASSERT_LT(bpf_program__fd(skel->progs.test_1_turn_off), 0, "prog_fd");
+
+cleanup:
+	struct_ops_nulled_out_cb__destroy(skel);
+}
+
+/* validate that libbpf generates reasonable error message if struct_ops is
+ * not referenced in any struct_ops map
+ */
+static void test_struct_ops_forgotten_cb(void)
+{
+	struct struct_ops_forgotten_cb *skel;
+	char *log;
+	int err;
+
+	skel = struct_ops_forgotten_cb__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	start_libbpf_log_capture();
+
+	err = struct_ops_forgotten_cb__load(skel);
+	if (!ASSERT_ERR(err, "skel_load"))
+		goto cleanup;
+
+	log = stop_libbpf_log_capture();
+	ASSERT_HAS_SUBSTR(log,
+			  "prog 'test_1_forgotten': SEC(\"struct_ops\") program isn't referenced anywhere, did you forget to use it?",
+			  "libbpf_log");
+	free(log);
+
+	struct_ops_forgotten_cb__destroy(skel);
+
+	/* now let's programmatically use it, we should be fine now */
+	skel = struct_ops_forgotten_cb__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	skel->struct_ops.ops->test_1 = skel->progs.test_1_forgotten; /* not anymore */
+
+	err = struct_ops_forgotten_cb__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+cleanup:
+	struct_ops_forgotten_cb__destroy(skel);
+}
+
+/* Detach a link from a user space program */
+static void test_detach_link(void)
+{
+	struct epoll_event ev, events[2];
+	struct struct_ops_detach *skel;
+	struct bpf_link *link = NULL;
+	int fd, epollfd = -1, nfds;
+	int err;
+
+	skel = struct_ops_detach__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_detach__open_and_load"))
+		return;
+
+	link = bpf_map__attach_struct_ops(skel->maps.testmod_do_detach);
+	if (!ASSERT_OK_PTR(link, "attach_struct_ops"))
+		goto cleanup;
+
+	fd = bpf_link__fd(link);
+	if (!ASSERT_GE(fd, 0, "link_fd"))
+		goto cleanup;
+
+	epollfd = epoll_create1(0);
+	if (!ASSERT_GE(epollfd, 0, "epoll_create1"))
+		goto cleanup;
+
+	ev.events = EPOLLHUP;
+	ev.data.fd = fd;
+	err = epoll_ctl(epollfd, EPOLL_CTL_ADD, fd, &ev);
+	if (!ASSERT_OK(err, "epoll_ctl"))
+		goto cleanup;
+
+	err = bpf_link__detach(link);
+	if (!ASSERT_OK(err, "detach_link"))
+		goto cleanup;
+
+	/* Wait for EPOLLHUP */
+	nfds = epoll_wait(epollfd, events, 2, 500);
+	if (!ASSERT_EQ(nfds, 1, "epoll_wait"))
+		goto cleanup;
+
+	if (!ASSERT_EQ(events[0].data.fd, fd, "epoll_wait_fd"))
+		goto cleanup;
+	if (!ASSERT_TRUE(events[0].events & EPOLLHUP, "events[0].events"))
+		goto cleanup;
+
+cleanup:
+	if (epollfd >= 0)
+		close(epollfd);
+	bpf_link__destroy(link);
+	struct_ops_detach__destroy(skel);
+}
+
+void serial_test_struct_ops_module(void)
+{
+	if (test__start_subtest("struct_ops_load"))
+		test_struct_ops_load();
+	if (test__start_subtest("struct_ops_not_zeroed"))
+		test_struct_ops_not_zeroed();
+	if (test__start_subtest("struct_ops_incompatible"))
+		test_struct_ops_incompatible();
+	if (test__start_subtest("struct_ops_null_out_cb"))
+		test_struct_ops_nulled_out_cb();
+	if (test__start_subtest("struct_ops_forgotten_cb"))
+		test_struct_ops_forgotten_cb();
+	if (test__start_subtest("test_detach_link"))
+		test_detach_link();
+	RUN_TESTS(unsupported_ops);
+}
+
diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_multi_pages.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_multi_pages.c
new file mode 100644
index 000000000000..645d32b5160c
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_multi_pages.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+
+#include "struct_ops_multi_pages.skel.h"
+
+static void do_struct_ops_multi_pages(void)
+{
+	struct struct_ops_multi_pages *skel;
+	struct bpf_link *link;
+
+	/* The size of all trampolines of skel->maps.multi_pages should be
+	 * over 1 page (at least for x86).
+	 */
+	skel = struct_ops_multi_pages__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "struct_ops_multi_pages_open_and_load"))
+		return;
+
+	link = bpf_map__attach_struct_ops(skel->maps.multi_pages);
+	ASSERT_OK_PTR(link, "attach_multi_pages");
+
+	bpf_link__destroy(link);
+	struct_ops_multi_pages__destroy(skel);
+}
+
+void test_struct_ops_multi_pages(void)
+{
+	if (test__start_subtest("multi_pages"))
+		do_struct_ops_multi_pages();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_no_cfi.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_no_cfi.c
new file mode 100644
index 000000000000..106ea447965a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_no_cfi.c
@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <testing_helpers.h>
+
+static void load_bpf_test_no_cfi(void)
+{
+	int fd;
+	int err;
+
+	fd = open("bpf_test_no_cfi.ko", O_RDONLY);
+	if (!ASSERT_GE(fd, 0, "open"))
+		return;
+
+	/* The module will try to register a struct_ops type without
+	 * cfi_stubs and with cfi_stubs.
+	 *
+	 * The one without cfi_stub should fail. The module will be loaded
+	 * successfully only if the result of the registration is as
+	 * expected, or it fails.
+	 */
+	err = finit_module(fd, "", 0);
+	close(fd);
+	if (!ASSERT_OK(err, "finit_module"))
+		return;
+
+	err = delete_module("bpf_test_no_cfi", 0);
+	ASSERT_OK(err, "delete_module");
+}
+
+void test_struct_ops_no_cfi(void)
+{
+	if (test__start_subtest("load_bpf_test_no_cfi"))
+		load_bpf_test_no_cfi();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_struct_ops_refcounted.c b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_refcounted.c
new file mode 100644
index 000000000000..da60c715fc59
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_struct_ops_refcounted.c
@@ -0,0 +1,14 @@
+#include <test_progs.h>
+
+#include "struct_ops_refcounted.skel.h"
+#include "struct_ops_refcounted_fail__ref_leak.skel.h"
+#include "struct_ops_refcounted_fail__global_subprog.skel.h"
+#include "struct_ops_refcounted_fail__tail_call.skel.h"
+
+void test_struct_ops_refcounted(void)
+{
+	RUN_TESTS(struct_ops_refcounted);
+	RUN_TESTS(struct_ops_refcounted_fail__ref_leak);
+	RUN_TESTS(struct_ops_refcounted_fail__global_subprog);
+	RUN_TESTS(struct_ops_refcounted_fail__tail_call);
+}
diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/prog_tests/test_sysctl.c
index bcdbd27f22f0..273dd41ca09e 100644
--- a/tools/testing/selftests/bpf/test_sysctl.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_sysctl.c
@@ -1,22 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2019 Facebook
 
-#include <fcntl.h>
-#include <stdint.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <unistd.h>
-
-#include <linux/filter.h>
-
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-#include <bpf/bpf_endian.h>
-#include "bpf_util.h"
+#include "test_progs.h"
 #include "cgroup_helpers.h"
-#include "testing_helpers.h"
 
 #define CG_PATH			"/foo"
 #define MAX_INSNS		512
@@ -1608,26 +1594,19 @@ static int run_tests(int cgfd)
 	return fails ? -1 : 0;
 }
 
-int main(int argc, char **argv)
+void test_sysctl(void)
 {
-	int cgfd = -1;
-	int err = 0;
+	int cgfd;
 
 	cgfd = cgroup_setup_and_join(CG_PATH);
-	if (cgfd < 0)
-		goto err;
+	if (!ASSERT_OK_FD(cgfd < 0, "create_cgroup"))
+		goto out;
 
-	/* Use libbpf 1.0 API mode */
-	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+	if (!ASSERT_OK(run_tests(cgfd), "run_tests"))
+		goto out;
 
-	if (run_tests(cgfd))
-		goto err;
-
-	goto out;
-err:
-	err = -1;
 out:
 	close(cgfd);
 	cleanup_cgroup_environment();
-	return err;
+	return;
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/test_task_local_data.c b/tools/testing/selftests/bpf/prog_tests/test_task_local_data.c
new file mode 100644
index 000000000000..9fd6306b455c
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_task_local_data.c
@@ -0,0 +1,297 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <pthread.h>
+#include <bpf/btf.h>
+#include <test_progs.h>
+
+#define TLD_FREE_DATA_ON_THREAD_EXIT
+#define TLD_DYN_DATA_SIZE 4096
+#include "task_local_data.h"
+
+struct test_tld_struct {
+	__u64 a;
+	__u64 b;
+	__u64 c;
+	__u64 d;
+};
+
+#include "test_task_local_data.skel.h"
+
+TLD_DEFINE_KEY(value0_key, "value0", sizeof(int));
+
+/*
+ * Reset task local data between subtests by clearing metadata other
+ * than the statically defined value0. This is safe as subtests run
+ * sequentially. Users of task local data library should not touch
+ * library internal.
+ */
+static void reset_tld(void)
+{
+	if (TLD_READ_ONCE(tld_meta_p)) {
+		/* Remove TLDs created by tld_create_key() */
+		tld_meta_p->cnt = 1;
+		tld_meta_p->size = TLD_DYN_DATA_SIZE;
+		memset(&tld_meta_p->metadata[1], 0,
+		       (TLD_MAX_DATA_CNT - 1) * sizeof(struct tld_metadata));
+	}
+}
+
+/* Serialize access to bpf program's global variables */
+static pthread_mutex_t global_mutex;
+
+static tld_key_t *tld_keys;
+
+#define TEST_BASIC_THREAD_NUM 32
+
+void *test_task_local_data_basic_thread(void *arg)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	struct test_task_local_data *skel = (struct test_task_local_data *)arg;
+	int fd, err, tid, *value0, *value1;
+	struct test_tld_struct *value2;
+
+	fd = bpf_map__fd(skel->maps.tld_data_map);
+
+	value0 = tld_get_data(fd, value0_key);
+	if (!ASSERT_OK_PTR(value0, "tld_get_data"))
+		goto out;
+
+	value1 = tld_get_data(fd, tld_keys[1]);
+	if (!ASSERT_OK_PTR(value1, "tld_get_data"))
+		goto out;
+
+	value2 = tld_get_data(fd, tld_keys[2]);
+	if (!ASSERT_OK_PTR(value2, "tld_get_data"))
+		goto out;
+
+	tid = sys_gettid();
+
+	*value0 = tid + 0;
+	*value1 = tid + 1;
+	value2->a = tid + 2;
+	value2->b = tid + 3;
+	value2->c = tid + 4;
+	value2->d = tid + 5;
+
+	pthread_mutex_lock(&global_mutex);
+	/* Run task_main that read task local data and save to global variables */
+	err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.task_main), &opts);
+	ASSERT_OK(err, "run task_main");
+	ASSERT_OK(opts.retval, "task_main retval");
+
+	ASSERT_EQ(skel->bss->test_value0, tid + 0, "tld_get_data value0");
+	ASSERT_EQ(skel->bss->test_value1, tid + 1, "tld_get_data value1");
+	ASSERT_EQ(skel->bss->test_value2.a, tid + 2, "tld_get_data value2.a");
+	ASSERT_EQ(skel->bss->test_value2.b, tid + 3, "tld_get_data value2.b");
+	ASSERT_EQ(skel->bss->test_value2.c, tid + 4, "tld_get_data value2.c");
+	ASSERT_EQ(skel->bss->test_value2.d, tid + 5, "tld_get_data value2.d");
+	pthread_mutex_unlock(&global_mutex);
+
+	/* Make sure valueX are indeed local to threads */
+	ASSERT_EQ(*value0, tid + 0, "value0");
+	ASSERT_EQ(*value1, tid + 1, "value1");
+	ASSERT_EQ(value2->a, tid + 2, "value2.a");
+	ASSERT_EQ(value2->b, tid + 3, "value2.b");
+	ASSERT_EQ(value2->c, tid + 4, "value2.c");
+	ASSERT_EQ(value2->d, tid + 5, "value2.d");
+
+	*value0 = tid + 5;
+	*value1 = tid + 4;
+	value2->a = tid + 3;
+	value2->b = tid + 2;
+	value2->c = tid + 1;
+	value2->d = tid + 0;
+
+	/* Run task_main again */
+	pthread_mutex_lock(&global_mutex);
+	err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.task_main), &opts);
+	ASSERT_OK(err, "run task_main");
+	ASSERT_OK(opts.retval, "task_main retval");
+
+	ASSERT_EQ(skel->bss->test_value0, tid + 5, "tld_get_data value0");
+	ASSERT_EQ(skel->bss->test_value1, tid + 4, "tld_get_data value1");
+	ASSERT_EQ(skel->bss->test_value2.a, tid + 3, "tld_get_data value2.a");
+	ASSERT_EQ(skel->bss->test_value2.b, tid + 2, "tld_get_data value2.b");
+	ASSERT_EQ(skel->bss->test_value2.c, tid + 1, "tld_get_data value2.c");
+	ASSERT_EQ(skel->bss->test_value2.d, tid + 0, "tld_get_data value2.d");
+	pthread_mutex_unlock(&global_mutex);
+
+out:
+	pthread_exit(NULL);
+}
+
+static void test_task_local_data_basic(void)
+{
+	struct test_task_local_data *skel;
+	pthread_t thread[TEST_BASIC_THREAD_NUM];
+	char dummy_key_name[TLD_NAME_LEN];
+	tld_key_t key;
+	int i, err;
+
+	reset_tld();
+
+	ASSERT_OK(pthread_mutex_init(&global_mutex, NULL), "pthread_mutex_init");
+
+	skel = test_task_local_data__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return;
+
+	tld_keys = calloc(TLD_MAX_DATA_CNT, sizeof(tld_key_t));
+	if (!ASSERT_OK_PTR(tld_keys, "calloc tld_keys"))
+		goto out;
+
+	ASSERT_FALSE(tld_key_is_err(value0_key), "TLD_DEFINE_KEY");
+	tld_keys[1] = tld_create_key("value1", sizeof(int));
+	ASSERT_FALSE(tld_key_is_err(tld_keys[1]), "tld_create_key");
+	tld_keys[2] = tld_create_key("value2", sizeof(struct test_tld_struct));
+	ASSERT_FALSE(tld_key_is_err(tld_keys[2]), "tld_create_key");
+
+	/*
+	 * Shouldn't be able to store data exceed a page. Create a TLD just big
+	 * enough to exceed a page. TLDs already created are int value0, int
+	 * value1, and struct test_tld_struct value2.
+	 */
+	key = tld_create_key("value_not_exist",
+			     TLD_PAGE_SIZE - 2 * sizeof(int) - sizeof(struct test_tld_struct) + 1);
+	ASSERT_EQ(tld_key_err_or_zero(key), -E2BIG, "tld_create_key");
+
+	key = tld_create_key("value2", sizeof(struct test_tld_struct));
+	ASSERT_EQ(tld_key_err_or_zero(key), -EEXIST, "tld_create_key");
+
+	/* Shouldn't be able to create the (TLD_MAX_DATA_CNT+1)-th TLD */
+	for (i = 3; i < TLD_MAX_DATA_CNT; i++) {
+		snprintf(dummy_key_name, TLD_NAME_LEN, "dummy_value%d", i);
+		tld_keys[i] = tld_create_key(dummy_key_name, sizeof(int));
+		ASSERT_FALSE(tld_key_is_err(tld_keys[i]), "tld_create_key");
+	}
+	key = tld_create_key("value_not_exist", sizeof(struct test_tld_struct));
+	ASSERT_EQ(tld_key_err_or_zero(key), -ENOSPC, "tld_create_key");
+
+	/* Access TLDs from multiple threads and check if they are thread-specific */
+	for (i = 0; i < TEST_BASIC_THREAD_NUM; i++) {
+		err = pthread_create(&thread[i], NULL, test_task_local_data_basic_thread, skel);
+		if (!ASSERT_OK(err, "pthread_create"))
+			goto out;
+	}
+
+out:
+	for (i = 0; i < TEST_BASIC_THREAD_NUM; i++)
+		pthread_join(thread[i], NULL);
+
+	if (tld_keys) {
+		free(tld_keys);
+		tld_keys = NULL;
+	}
+	tld_free();
+	test_task_local_data__destroy(skel);
+}
+
+#define TEST_RACE_THREAD_NUM (TLD_MAX_DATA_CNT - 3)
+
+void *test_task_local_data_race_thread(void *arg)
+{
+	int err = 0, id = (intptr_t)arg;
+	char key_name[32];
+	tld_key_t key;
+
+	key = tld_create_key("value_not_exist", TLD_PAGE_SIZE + 1);
+	if (tld_key_err_or_zero(key) != -E2BIG) {
+		err = 1;
+		goto out;
+	}
+
+	/* Only one thread will succeed in creating value1 */
+	key = tld_create_key("value1", sizeof(int));
+	if (!tld_key_is_err(key))
+		tld_keys[1] = key;
+
+	/* Only one thread will succeed in creating value2 */
+	key = tld_create_key("value2", sizeof(struct test_tld_struct));
+	if (!tld_key_is_err(key))
+		tld_keys[2] = key;
+
+	snprintf(key_name, 32, "thread_%d", id);
+	tld_keys[id] = tld_create_key(key_name, sizeof(int));
+	if (tld_key_is_err(tld_keys[id]))
+		err = 2;
+out:
+	return (void *)(intptr_t)err;
+}
+
+static void test_task_local_data_race(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	pthread_t thread[TEST_RACE_THREAD_NUM];
+	struct test_task_local_data *skel;
+	int fd, i, j, err, *data;
+	void *ret = NULL;
+
+	skel = test_task_local_data__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return;
+
+	tld_keys = calloc(TLD_MAX_DATA_CNT, sizeof(tld_key_t));
+	if (!ASSERT_OK_PTR(tld_keys, "calloc tld_keys"))
+		goto out;
+
+	fd = bpf_map__fd(skel->maps.tld_data_map);
+
+	ASSERT_FALSE(tld_key_is_err(value0_key), "TLD_DEFINE_KEY");
+	tld_keys[0] = value0_key;
+
+	for (j = 0; j < 100; j++) {
+		reset_tld();
+
+		for (i = 0; i < TEST_RACE_THREAD_NUM; i++) {
+			/*
+			 * Try to make tld_create_key() race with each other. Call
+			 * tld_create_key(), both valid and invalid, from different threads.
+			 */
+			err = pthread_create(&thread[i], NULL, test_task_local_data_race_thread,
+					     (void *)(intptr_t)(i + 3));
+			if (CHECK_FAIL(err))
+				break;
+		}
+
+		/* Wait for all tld_create_key() to return */
+		for (i = 0; i < TEST_RACE_THREAD_NUM; i++) {
+			pthread_join(thread[i], &ret);
+			if (CHECK_FAIL(ret))
+				break;
+		}
+
+		/* Write a unique number to each TLD */
+		for (i = 0; i < TLD_MAX_DATA_CNT; i++) {
+			data = tld_get_data(fd, tld_keys[i]);
+			if (CHECK_FAIL(!data))
+				break;
+			*data = i;
+		}
+
+		/* Read TLDs and check the value to see if any address collides with another */
+		for (i = 0; i < TLD_MAX_DATA_CNT; i++) {
+			data = tld_get_data(fd, tld_keys[i]);
+			if (CHECK_FAIL(*data != i))
+				break;
+		}
+
+		/* Run task_main to make sure no invalid TLDs are added */
+		err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.task_main), &opts);
+		ASSERT_OK(err, "run task_main");
+		ASSERT_OK(opts.retval, "task_main retval");
+	}
+out:
+	if (tld_keys) {
+		free(tld_keys);
+		tld_keys = NULL;
+	}
+	tld_free();
+	test_task_local_data__destroy(skel);
+}
+
+void test_task_local_data(void)
+{
+	if (test__start_subtest("task_local_data_basic"))
+		test_task_local_data_basic();
+	if (test__start_subtest("task_local_data_race"))
+		test_task_local_data_race();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_task_work.c b/tools/testing/selftests/bpf/prog_tests/test_task_work.c
new file mode 100644
index 000000000000..774b31a5f6ca
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_task_work.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <string.h>
+#include <stdio.h>
+#include "task_work.skel.h"
+#include "task_work_fail.skel.h"
+#include <linux/bpf.h>
+#include <linux/perf_event.h>
+#include <sys/syscall.h>
+#include <time.h>
+
+static int perf_event_open(__u32 type, __u64 config, int pid)
+{
+	struct perf_event_attr attr = {
+		.type = type,
+		.config = config,
+		.size = sizeof(struct perf_event_attr),
+		.sample_period = 100000,
+	};
+
+	return syscall(__NR_perf_event_open, &attr, pid, -1, -1, 0);
+}
+
+struct elem {
+	char data[128];
+	struct bpf_task_work tw;
+};
+
+static int verify_map(struct bpf_map *map, const char *expected_data)
+{
+	int err;
+	struct elem value;
+	int processed_values = 0;
+	int k, sz;
+
+	sz = bpf_map__max_entries(map);
+	for (k = 0; k < sz; ++k) {
+		err = bpf_map__lookup_elem(map, &k, sizeof(int), &value, sizeof(struct elem), 0);
+		if (err)
+			continue;
+		if (!ASSERT_EQ(strcmp(expected_data, value.data), 0, "map data")) {
+			fprintf(stderr, "expected '%s', found '%s' in %s map", expected_data,
+				value.data, bpf_map__name(map));
+			return 2;
+		}
+		processed_values++;
+	}
+
+	return processed_values == 0;
+}
+
+static void task_work_run(const char *prog_name, const char *map_name)
+{
+	struct task_work *skel;
+	struct bpf_program *prog;
+	struct bpf_map *map;
+	struct bpf_link *link = NULL;
+	int err, pe_fd = -1, pid, status, pipefd[2];
+	char user_string[] = "hello world";
+
+	if (!ASSERT_NEQ(pipe(pipefd), -1, "pipe"))
+		return;
+
+	pid = fork();
+	if (pid == 0) {
+		__u64 num = 1;
+		int i;
+		char buf;
+
+		close(pipefd[1]);
+		read(pipefd[0], &buf, sizeof(buf));
+		close(pipefd[0]);
+
+		for (i = 0; i < 10000; ++i)
+			num *= time(0) % 7;
+		(void)num;
+		exit(0);
+	}
+	if (!ASSERT_GT(pid, 0, "fork() failed")) {
+		close(pipefd[0]);
+		close(pipefd[1]);
+		return;
+	}
+
+	skel = task_work__open();
+	if (!ASSERT_OK_PTR(skel, "task_work__open"))
+		return;
+
+	bpf_object__for_each_program(prog, skel->obj) {
+		bpf_program__set_autoload(prog, false);
+	}
+
+	prog = bpf_object__find_program_by_name(skel->obj, prog_name);
+	if (!ASSERT_OK_PTR(prog, "prog_name"))
+		goto cleanup;
+	bpf_program__set_autoload(prog, true);
+	skel->bss->user_ptr = (char *)user_string;
+
+	err = task_work__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	pe_fd = perf_event_open(PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES, pid);
+	if (pe_fd == -1 && (errno == ENOENT || errno == EOPNOTSUPP)) {
+		printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n", __func__);
+		test__skip();
+		goto cleanup;
+	}
+	if (!ASSERT_NEQ(pe_fd, -1, "pe_fd")) {
+		fprintf(stderr, "perf_event_open errno: %d, pid: %d\n", errno, pid);
+		goto cleanup;
+	}
+
+	link = bpf_program__attach_perf_event(prog, pe_fd);
+	if (!ASSERT_OK_PTR(link, "attach_perf_event"))
+		goto cleanup;
+
+	/* perf event fd ownership is passed to bpf_link */
+	pe_fd = -1;
+	close(pipefd[0]);
+	write(pipefd[1], user_string, 1);
+	close(pipefd[1]);
+	/* Wait to collect some samples */
+	waitpid(pid, &status, 0);
+	pid = 0;
+	map = bpf_object__find_map_by_name(skel->obj, map_name);
+	if (!ASSERT_OK_PTR(map, "find map_name"))
+		goto cleanup;
+	if (!ASSERT_OK(verify_map(map, user_string), "verify map"))
+		goto cleanup;
+cleanup:
+	if (pe_fd >= 0)
+		close(pe_fd);
+	bpf_link__destroy(link);
+	task_work__destroy(skel);
+	if (pid > 0) {
+		close(pipefd[0]);
+		write(pipefd[1], user_string, 1);
+		close(pipefd[1]);
+		waitpid(pid, &status, 0);
+	}
+}
+
+void test_task_work(void)
+{
+	if (test__start_subtest("test_task_work_hash_map"))
+		task_work_run("oncpu_hash_map", "hmap");
+
+	if (test__start_subtest("test_task_work_array_map"))
+		task_work_run("oncpu_array_map", "arrmap");
+
+	if (test__start_subtest("test_task_work_lru_map"))
+		task_work_run("oncpu_lru_map", "lrumap");
+
+	RUN_TESTS(task_work_fail);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_tc_edt.c b/tools/testing/selftests/bpf/prog_tests/test_tc_edt.c
new file mode 100644
index 000000000000..462512fb191f
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_tc_edt.c
@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+
+/*
+ * BPF-based flow shaping
+ *
+ * The test brings up two veth in two isolated namespaces, attach some flow
+ * shaping program onto it, and ensures that a manual speedtest maximum
+ * value matches the rate set in the BPF shapers.
+ */
+
+#include <asm-generic/socket.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <math.h>
+#include <sys/time.h>
+#include <sys/socket.h>
+#include <bpf/libbpf.h>
+#include <pthread.h>
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "test_tc_edt.skel.h"
+
+#define SERVER_NS "tc-edt-server-ns"
+#define CLIENT_NS "tc-edt-client-ns"
+#define IP4_ADDR_VETH1 "192.168.1.1"
+#define IP4_ADDR_VETH2 "192.168.1.2"
+#define IP4_ADDR_VETH2_HEX 0xC0A80102
+
+#define TIMEOUT_MS		2000
+#define TEST_PORT		9000
+#define TARGET_RATE_MBPS	5.0
+#define TX_BYTES_COUNT		(1 * 1000 * 1000)
+#define RATE_ERROR_PERCENT	2.0
+
+struct connection {
+	int server_listen_fd;
+	int server_conn_fd;
+	int client_conn_fd;
+};
+
+static int setup(struct test_tc_edt *skel)
+{
+	struct nstoken *nstoken_client, *nstoken_server;
+	int ret;
+
+	if (!ASSERT_OK(make_netns(CLIENT_NS), "create client ns"))
+		goto fail;
+	if (!ASSERT_OK(make_netns(SERVER_NS), "create server ns"))
+		goto fail_delete_client_ns;
+
+	nstoken_client = open_netns(CLIENT_NS);
+	if (!ASSERT_OK_PTR(nstoken_client, "open client ns"))
+		goto fail_delete_server_ns;
+	SYS(fail_close_client_ns, "ip link add veth1 type veth peer name %s",
+	    "veth2 netns " SERVER_NS);
+	SYS(fail_close_client_ns, "ip -4 addr add " IP4_ADDR_VETH1 "/24 dev veth1");
+	SYS(fail_close_client_ns, "ip link set veth1 up");
+
+	nstoken_server = open_netns(SERVER_NS);
+	if (!ASSERT_OK_PTR(nstoken_server, "enter server ns"))
+		goto fail_close_client_ns;
+	SYS(fail_close_server_ns, "ip -4 addr add " IP4_ADDR_VETH2 "/24 dev veth2");
+	SYS(fail_close_server_ns, "ip link set veth2 up");
+	SYS(fail_close_server_ns, "tc qdisc add dev veth2 root fq");
+	ret = tc_prog_attach("veth2", -1, bpf_program__fd(skel->progs.tc_prog));
+	if (!ASSERT_OK(ret, "attach bpf prog"))
+		goto fail_close_server_ns;
+	skel->bss->target_rate = TARGET_RATE_MBPS * 1000 * 1000;
+	close_netns(nstoken_server);
+	close_netns(nstoken_client);
+
+	return 0;
+
+fail_close_server_ns:
+	close_netns(nstoken_server);
+fail_close_client_ns:
+	close_netns(nstoken_client);
+fail_delete_server_ns:
+	remove_netns(SERVER_NS);
+fail_delete_client_ns:
+	remove_netns(CLIENT_NS);
+fail:
+	return -1;
+}
+
+static void cleanup(void)
+{
+	remove_netns(CLIENT_NS);
+	remove_netns(SERVER_NS);
+}
+
+static void run_test(void)
+{
+	int server_fd, client_fd, err;
+	double rate_mbps, rate_error;
+	struct nstoken *nstoken;
+	__u64 ts_start, ts_end;
+
+	nstoken = open_netns(SERVER_NS);
+	if (!ASSERT_OK_PTR(nstoken, "open server ns"))
+		return;
+	server_fd = start_server(AF_INET, SOCK_STREAM, IP4_ADDR_VETH2,
+			TEST_PORT, TIMEOUT_MS);
+	if (!ASSERT_OK_FD(server_fd, "start server"))
+		return;
+
+	close_netns(nstoken);
+	nstoken = open_netns(CLIENT_NS);
+	if (!ASSERT_OK_PTR(nstoken, "open client ns"))
+		return;
+	client_fd = connect_to_fd(server_fd, 0);
+	if (!ASSERT_OK_FD(client_fd, "connect client"))
+		return;
+
+	ts_start = get_time_ns();
+	err = send_recv_data(server_fd, client_fd, TX_BYTES_COUNT);
+	ts_end = get_time_ns();
+	close_netns(nstoken);
+	ASSERT_OK(err, "send_recv_data");
+
+	rate_mbps = TX_BYTES_COUNT / ((ts_end - ts_start) / 1000.0);
+	rate_error =
+		fabs((rate_mbps - TARGET_RATE_MBPS) * 100.0 / TARGET_RATE_MBPS);
+
+	ASSERT_LE(rate_error, RATE_ERROR_PERCENT,
+		  "rate error is lower than threshold");
+}
+
+void test_tc_edt(void)
+{
+	struct test_tc_edt *skel;
+
+	skel = test_tc_edt__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel open and load"))
+		return;
+
+	if (!ASSERT_OK(setup(skel), "global setup"))
+		return;
+
+	run_test();
+
+	cleanup();
+	test_tc_edt__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c b/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c
new file mode 100644
index 000000000000..0fe0a8f62486
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c
@@ -0,0 +1,714 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+
+/*
+ * End-to-end eBPF tunnel test suite
+ *   The file tests BPF network tunnels implementation. For each tunnel
+ *   type, the test validates that:
+ *   - basic communication can first be established between the two veths
+ *   - when adding a BPF-based encapsulation on client egress, it now fails
+ *   to communicate with the server
+ *   - when adding a kernel-based decapsulation on server ingress, client
+ *   can now connect
+ *   - when replacing the kernel-based decapsulation with a BPF-based one,
+ *   the client can still connect
+ */
+
+#include <stdio.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <bpf/libbpf.h>
+
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "test_tc_tunnel.skel.h"
+
+#define SERVER_NS	"tc-tunnel-server-ns"
+#define CLIENT_NS	"tc-tunnel-client-ns"
+#define MAC_ADDR_VETH1	"00:11:22:33:44:55"
+#define IP4_ADDR_VETH1	"192.168.1.1"
+#define IP6_ADDR_VETH1	"fd::1"
+#define MAC_ADDR_VETH2	"66:77:88:99:AA:BB"
+#define IP4_ADDR_VETH2	"192.168.1.2"
+#define IP6_ADDR_VETH2	"fd::2"
+
+#define TEST_NAME_MAX_LEN	64
+#define PROG_NAME_MAX_LEN	64
+#define TUNNEL_ARGS_MAX_LEN	128
+#define BUFFER_LEN		2000
+#define DEFAULT_TEST_DATA_SIZE	100
+#define GSO_TEST_DATA_SIZE	BUFFER_LEN
+
+#define TIMEOUT_MS			1000
+#define TEST_PORT			8000
+#define UDP_PORT			5555
+#define MPLS_UDP_PORT			6635
+#define FOU_MPLS_PROTO			137
+#define VXLAN_ID			1
+#define VXLAN_PORT			8472
+#define MPLS_TABLE_ENTRIES_COUNT	65536
+
+static char tx_buffer[BUFFER_LEN], rx_buffer[BUFFER_LEN];
+
+struct subtest_cfg {
+	char *ebpf_tun_type;
+	char *iproute_tun_type;
+	char *mac_tun_type;
+	int ipproto;
+	void (*extra_decap_mod_args_cb)(struct subtest_cfg *cfg, char *dst);
+	bool tunnel_need_veth_mac;
+	bool configure_fou_rx_port;
+	char *tmode;
+	bool expect_kern_decap_failure;
+	bool configure_mpls;
+	bool test_gso;
+	char *tunnel_client_addr;
+	char *tunnel_server_addr;
+	char name[TEST_NAME_MAX_LEN];
+	char *server_addr;
+	int client_egress_prog_fd;
+	int server_ingress_prog_fd;
+	char extra_decap_mod_args[TUNNEL_ARGS_MAX_LEN];
+	int server_fd;
+};
+
+struct connection {
+	int client_fd;
+	int server_fd;
+};
+
+static int build_subtest_name(struct subtest_cfg *cfg, char *dst, size_t size)
+{
+	int ret;
+
+	ret = snprintf(dst, size, "%s_%s", cfg->ebpf_tun_type,
+		       cfg->mac_tun_type);
+
+	return ret < 0 ? ret : 0;
+}
+
+static int set_subtest_progs(struct subtest_cfg *cfg, struct test_tc_tunnel *skel)
+{
+	char prog_name[PROG_NAME_MAX_LEN];
+	struct bpf_program *prog;
+	int ret;
+
+	ret = snprintf(prog_name, PROG_NAME_MAX_LEN, "__encap_");
+	if (ret < 0)
+		return ret;
+	ret = build_subtest_name(cfg, prog_name + ret, PROG_NAME_MAX_LEN - ret);
+	if (ret < 0)
+		return ret;
+	prog = bpf_object__find_program_by_name(skel->obj, prog_name);
+	if (!prog)
+		return -1;
+
+	cfg->client_egress_prog_fd = bpf_program__fd(prog);
+	cfg->server_ingress_prog_fd = bpf_program__fd(skel->progs.decap_f);
+	return 0;
+}
+
+static void set_subtest_addresses(struct subtest_cfg *cfg)
+{
+	if (cfg->ipproto == 6)
+		cfg->server_addr = IP6_ADDR_VETH2;
+	else
+		cfg->server_addr = IP4_ADDR_VETH2;
+
+	/* Some specific tunnel types need specific addressing, it then
+	 * has been already set in the configuration table. Otherwise,
+	 * deduce the relevant addressing from the ipproto
+	 */
+	if (cfg->tunnel_client_addr && cfg->tunnel_server_addr)
+		return;
+
+	if (cfg->ipproto == 6) {
+		cfg->tunnel_client_addr = IP6_ADDR_VETH1;
+		cfg->tunnel_server_addr = IP6_ADDR_VETH2;
+	} else {
+		cfg->tunnel_client_addr = IP4_ADDR_VETH1;
+		cfg->tunnel_server_addr = IP4_ADDR_VETH2;
+	}
+}
+
+static int run_server(struct subtest_cfg *cfg)
+{
+	int family = cfg->ipproto == 6 ? AF_INET6 : AF_INET;
+	struct nstoken *nstoken;
+	struct network_helper_opts opts = {
+		.timeout_ms = TIMEOUT_MS
+	};
+
+	nstoken = open_netns(SERVER_NS);
+	if (!ASSERT_OK_PTR(nstoken, "open server ns"))
+		return -1;
+
+	cfg->server_fd = start_server_str(family, SOCK_STREAM, cfg->server_addr,
+					  TEST_PORT, &opts);
+	close_netns(nstoken);
+	if (!ASSERT_OK_FD(cfg->server_fd, "start server"))
+		return -1;
+
+	return 0;
+}
+
+static int check_server_rx_data(struct subtest_cfg *cfg,
+				struct connection *conn, int len)
+{
+	int err;
+
+	memset(rx_buffer, 0, BUFFER_LEN);
+	err = recv(conn->server_fd, rx_buffer, len, 0);
+	if (!ASSERT_EQ(err, len, "check rx data len"))
+		return 1;
+	if (!ASSERT_MEMEQ(tx_buffer, rx_buffer, len, "check received data"))
+		return 1;
+	return 0;
+}
+
+static struct connection *connect_client_to_server(struct subtest_cfg *cfg)
+{
+	struct network_helper_opts opts = {.timeout_ms = 500};
+	int family = cfg->ipproto == 6 ? AF_INET6 : AF_INET;
+	struct connection *conn = NULL;
+	int client_fd, server_fd;
+
+	conn = malloc(sizeof(struct connection));
+	if (!conn)
+		return conn;
+
+	client_fd = connect_to_addr_str(family, SOCK_STREAM, cfg->server_addr,
+					TEST_PORT, &opts);
+
+	if (client_fd < 0) {
+		free(conn);
+		return NULL;
+	}
+
+	server_fd = accept(cfg->server_fd, NULL, NULL);
+	if (server_fd < 0) {
+		close(client_fd);
+		free(conn);
+		return NULL;
+	}
+
+	conn->server_fd = server_fd;
+	conn->client_fd = client_fd;
+
+	return conn;
+}
+
+static void disconnect_client_from_server(struct subtest_cfg *cfg,
+					  struct connection *conn)
+{
+	close(conn->server_fd);
+	close(conn->client_fd);
+	free(conn);
+}
+
+static int send_and_test_data(struct subtest_cfg *cfg, bool must_succeed)
+{
+	struct connection *conn;
+	int err, res = -1;
+
+	conn = connect_client_to_server(cfg);
+	if (!must_succeed && !ASSERT_ERR_PTR(conn, "connection that must fail"))
+		goto end;
+	else if (!must_succeed)
+		return 0;
+
+	if (!ASSERT_OK_PTR(conn, "connection that must succeed"))
+		return -1;
+
+	err = send(conn->client_fd, tx_buffer, DEFAULT_TEST_DATA_SIZE, 0);
+	if (!ASSERT_EQ(err, DEFAULT_TEST_DATA_SIZE, "send data from client"))
+		goto end;
+	if (check_server_rx_data(cfg, conn, DEFAULT_TEST_DATA_SIZE))
+		goto end;
+
+	if (!cfg->test_gso) {
+		res = 0;
+		goto end;
+	}
+
+	err = send(conn->client_fd, tx_buffer, GSO_TEST_DATA_SIZE, 0);
+	if (!ASSERT_EQ(err, GSO_TEST_DATA_SIZE, "send (large) data from client"))
+		goto end;
+	if (check_server_rx_data(cfg, conn, DEFAULT_TEST_DATA_SIZE))
+		goto end;
+
+	res = 0;
+end:
+	disconnect_client_from_server(cfg, conn);
+	return res;
+}
+
+static void vxlan_decap_mod_args_cb(struct subtest_cfg *cfg, char *dst)
+{
+	snprintf(dst, TUNNEL_ARGS_MAX_LEN, "id %d dstport %d udp6zerocsumrx",
+		 VXLAN_ID, VXLAN_PORT);
+}
+
+static void udp_decap_mod_args_cb(struct subtest_cfg *cfg, char *dst)
+{
+	bool is_mpls = !strcmp(cfg->mac_tun_type, "mpls");
+
+	snprintf(dst, TUNNEL_ARGS_MAX_LEN,
+		 "encap fou encap-sport auto encap-dport %d",
+		 is_mpls ? MPLS_UDP_PORT : UDP_PORT);
+}
+
+static int configure_fou_rx_port(struct subtest_cfg *cfg, bool add)
+{
+	bool is_mpls = strcmp(cfg->mac_tun_type, "mpls") == 0;
+	int fou_proto;
+
+	if (is_mpls)
+		fou_proto = FOU_MPLS_PROTO;
+	else
+		fou_proto = cfg->ipproto == 6 ? 41 : 4;
+
+	SYS(fail, "ip fou %s port %d ipproto %d%s", add ? "add" : "del",
+	    is_mpls ? MPLS_UDP_PORT : UDP_PORT, fou_proto,
+	    cfg->ipproto == 6 ? " -6" : "");
+
+	return 0;
+fail:
+	return 1;
+}
+
+static int add_fou_rx_port(struct subtest_cfg *cfg)
+{
+	return configure_fou_rx_port(cfg, true);
+}
+
+static int del_fou_rx_port(struct subtest_cfg *cfg)
+{
+	return configure_fou_rx_port(cfg, false);
+}
+
+static int update_tunnel_intf_addr(struct subtest_cfg *cfg)
+{
+	SYS(fail, "ip link set dev testtun0 address " MAC_ADDR_VETH2);
+	return 0;
+fail:
+	return -1;
+}
+
+static int configure_kernel_for_mpls(struct subtest_cfg *cfg)
+{
+	SYS(fail, "sysctl -qw net.mpls.platform_labels=%d",
+	    MPLS_TABLE_ENTRIES_COUNT);
+	SYS(fail, "ip -f mpls route add 1000 dev lo");
+	SYS(fail, "ip link set lo up");
+	SYS(fail, "sysctl -qw net.mpls.conf.testtun0.input=1");
+	SYS(fail, "sysctl -qw net.ipv4.conf.lo.rp_filter=0");
+	return 0;
+fail:
+	return -1;
+}
+
+static int configure_encapsulation(struct subtest_cfg *cfg)
+{
+	int ret;
+
+	ret = tc_prog_attach("veth1", -1, cfg->client_egress_prog_fd);
+
+	return ret;
+}
+
+static int configure_kernel_decapsulation(struct subtest_cfg *cfg)
+{
+	struct nstoken *nstoken = open_netns(SERVER_NS);
+	int ret = -1;
+
+	if (!ASSERT_OK_PTR(nstoken, "open server ns"))
+		return ret;
+
+	if (cfg->configure_fou_rx_port &&
+	    !ASSERT_OK(add_fou_rx_port(cfg), "configure FOU RX port"))
+		goto fail;
+	SYS(fail, "ip link add name testtun0 type %s %s remote %s local %s %s",
+	    cfg->iproute_tun_type, cfg->tmode ? cfg->tmode : "",
+	    cfg->tunnel_client_addr, cfg->tunnel_server_addr,
+	    cfg->extra_decap_mod_args);
+	if (cfg->tunnel_need_veth_mac &&
+	    !ASSERT_OK(update_tunnel_intf_addr(cfg), "update testtun0 mac"))
+		goto fail;
+	if (cfg->configure_mpls &&
+	    (!ASSERT_OK(configure_kernel_for_mpls(cfg),
+			"configure MPLS decap")))
+		goto fail;
+	SYS(fail, "sysctl -qw net.ipv4.conf.all.rp_filter=0");
+	SYS(fail, "sysctl -qw net.ipv4.conf.testtun0.rp_filter=0");
+	SYS(fail, "ip link set dev testtun0 up");
+
+	ret = 0;
+fail:
+	close_netns(nstoken);
+	return ret;
+}
+
+static void remove_kernel_decapsulation(struct subtest_cfg *cfg)
+{
+	SYS_NOFAIL("ip link del testtun0");
+	if (cfg->configure_mpls)
+		SYS_NOFAIL("ip -f mpls route del 1000 dev lo");
+	if (cfg->configure_fou_rx_port)
+		del_fou_rx_port(cfg);
+}
+
+static int configure_ebpf_decapsulation(struct subtest_cfg *cfg)
+{
+	struct nstoken *nstoken = open_netns(SERVER_NS);
+	int ret = -1;
+
+	if (!ASSERT_OK_PTR(nstoken, "open server ns"))
+		return ret;
+
+	if (!cfg->expect_kern_decap_failure)
+		SYS(fail, "ip link del testtun0");
+
+	if (!ASSERT_OK(tc_prog_attach("veth2", cfg->server_ingress_prog_fd, -1),
+		       "attach_program"))
+		goto fail;
+
+	ret = 0;
+fail:
+	close_netns(nstoken);
+	return ret;
+}
+
+static void run_test(struct subtest_cfg *cfg)
+{
+	struct nstoken *nstoken;
+
+	if (!ASSERT_OK(run_server(cfg), "run server"))
+		return;
+
+	nstoken = open_netns(CLIENT_NS);
+	if (!ASSERT_OK_PTR(nstoken, "open client ns"))
+		goto fail;
+
+	/* Basic communication must work */
+	if (!ASSERT_OK(send_and_test_data(cfg, true), "connect without any encap"))
+		goto fail;
+
+	/* Attach encapsulation program to client */
+	if (!ASSERT_OK(configure_encapsulation(cfg), "configure encapsulation"))
+		goto fail;
+
+	/* If supported, insert kernel decap module, connection must succeed */
+	if (!cfg->expect_kern_decap_failure) {
+		if (!ASSERT_OK(configure_kernel_decapsulation(cfg),
+					"configure kernel decapsulation"))
+			goto fail;
+		if (!ASSERT_OK(send_and_test_data(cfg, true),
+			       "connect with encap prog and kern decap"))
+			goto fail;
+	}
+
+	/* Replace kernel decapsulation with BPF decapsulation, test must pass */
+	if (!ASSERT_OK(configure_ebpf_decapsulation(cfg), "configure ebpf decapsulation"))
+		goto fail;
+	ASSERT_OK(send_and_test_data(cfg, true), "connect with encap and decap progs");
+
+fail:
+	close_netns(nstoken);
+	close(cfg->server_fd);
+}
+
+static int setup(void)
+{
+	struct nstoken *nstoken_client, *nstoken_server;
+	int fd, err;
+
+	fd = open("/dev/urandom", O_RDONLY);
+	if (!ASSERT_OK_FD(fd, "open urandom"))
+		goto fail;
+	err = read(fd, tx_buffer, BUFFER_LEN);
+	close(fd);
+
+	if (!ASSERT_EQ(err, BUFFER_LEN, "read random bytes"))
+		goto fail;
+
+	/* Configure the testing network */
+	if (!ASSERT_OK(make_netns(CLIENT_NS), "create client ns") ||
+	    !ASSERT_OK(make_netns(SERVER_NS), "create server ns"))
+		goto fail;
+
+	nstoken_client = open_netns(CLIENT_NS);
+	if (!ASSERT_OK_PTR(nstoken_client, "open client ns"))
+		goto fail_delete_ns;
+	SYS(fail_close_ns_client, "ip link add %s type veth peer name %s",
+	    "veth1 mtu 1500 netns " CLIENT_NS " address " MAC_ADDR_VETH1,
+	    "veth2 mtu 1500 netns " SERVER_NS " address " MAC_ADDR_VETH2);
+	SYS(fail_close_ns_client, "ethtool -K veth1 tso off");
+	SYS(fail_close_ns_client, "ip link set veth1 up");
+	nstoken_server = open_netns(SERVER_NS);
+	if (!ASSERT_OK_PTR(nstoken_server, "open server ns"))
+		goto fail_close_ns_client;
+	SYS(fail_close_ns_server, "ip link set veth2 up");
+
+	close_netns(nstoken_server);
+	close_netns(nstoken_client);
+	return 0;
+
+fail_close_ns_server:
+	close_netns(nstoken_server);
+fail_close_ns_client:
+	close_netns(nstoken_client);
+fail_delete_ns:
+	SYS_NOFAIL("ip netns del " CLIENT_NS);
+	SYS_NOFAIL("ip netns del " SERVER_NS);
+fail:
+	return -1;
+}
+
+static int subtest_setup(struct test_tc_tunnel *skel, struct subtest_cfg *cfg)
+{
+	struct nstoken *nstoken_client, *nstoken_server;
+	int ret = -1;
+
+	set_subtest_addresses(cfg);
+	if (!ASSERT_OK(set_subtest_progs(cfg, skel),
+		       "find subtest progs"))
+		goto fail;
+	if (cfg->extra_decap_mod_args_cb)
+		cfg->extra_decap_mod_args_cb(cfg, cfg->extra_decap_mod_args);
+
+	nstoken_client = open_netns(CLIENT_NS);
+	if (!ASSERT_OK_PTR(nstoken_client, "open client ns"))
+		goto fail;
+	SYS(fail_close_client_ns,
+	    "ip -4 addr add " IP4_ADDR_VETH1 "/24 dev veth1");
+	SYS(fail_close_client_ns, "ip -4 route flush table main");
+	SYS(fail_close_client_ns,
+	    "ip -4 route add " IP4_ADDR_VETH2 " mtu 1450 dev veth1");
+	SYS(fail_close_client_ns,
+	    "ip -6 addr add " IP6_ADDR_VETH1 "/64 dev veth1 nodad");
+	SYS(fail_close_client_ns, "ip -6 route flush table main");
+	SYS(fail_close_client_ns,
+	    "ip -6 route add " IP6_ADDR_VETH2 " mtu 1430 dev veth1");
+	nstoken_server = open_netns(SERVER_NS);
+	if (!ASSERT_OK_PTR(nstoken_server, "open server ns"))
+		goto fail_close_client_ns;
+	SYS(fail_close_server_ns,
+	    "ip -4 addr add " IP4_ADDR_VETH2 "/24 dev veth2");
+	SYS(fail_close_server_ns,
+	    "ip -6 addr add " IP6_ADDR_VETH2 "/64 dev veth2 nodad");
+
+	ret = 0;
+
+fail_close_server_ns:
+	close_netns(nstoken_server);
+fail_close_client_ns:
+	close_netns(nstoken_client);
+fail:
+	return ret;
+}
+
+
+static void subtest_cleanup(struct subtest_cfg *cfg)
+{
+	struct nstoken *nstoken;
+
+	nstoken = open_netns(CLIENT_NS);
+	if (ASSERT_OK_PTR(nstoken, "open clien ns")) {
+		SYS_NOFAIL("tc qdisc delete dev veth1 parent ffff:fff1");
+		SYS_NOFAIL("ip a flush veth1");
+		close_netns(nstoken);
+	}
+	nstoken = open_netns(SERVER_NS);
+	if (ASSERT_OK_PTR(nstoken, "open clien ns")) {
+		SYS_NOFAIL("tc qdisc delete dev veth2 parent ffff:fff1");
+		SYS_NOFAIL("ip a flush veth2");
+		if (!cfg->expect_kern_decap_failure)
+			remove_kernel_decapsulation(cfg);
+		close_netns(nstoken);
+	}
+}
+
+static void cleanup(void)
+{
+	remove_netns(CLIENT_NS);
+	remove_netns(SERVER_NS);
+}
+
+static struct subtest_cfg subtests_cfg[] = {
+	{
+		.ebpf_tun_type = "ipip",
+		.mac_tun_type = "none",
+		.iproute_tun_type = "ipip",
+		.ipproto = 4,
+	},
+	{
+		.ebpf_tun_type = "ipip6",
+		.mac_tun_type = "none",
+		.iproute_tun_type = "ip6tnl",
+		.ipproto = 4,
+		.tunnel_client_addr = IP6_ADDR_VETH1,
+		.tunnel_server_addr = IP6_ADDR_VETH2,
+	},
+	{
+		.ebpf_tun_type = "ip6tnl",
+		.iproute_tun_type = "ip6tnl",
+		.mac_tun_type = "none",
+		.ipproto = 6,
+	},
+	{
+		.mac_tun_type = "none",
+		.ebpf_tun_type = "sit",
+		.iproute_tun_type = "sit",
+		.ipproto = 6,
+		.tunnel_client_addr = IP4_ADDR_VETH1,
+		.tunnel_server_addr = IP4_ADDR_VETH2,
+	},
+	{
+		.ebpf_tun_type = "vxlan",
+		.mac_tun_type = "eth",
+		.iproute_tun_type = "vxlan",
+		.ipproto = 4,
+		.extra_decap_mod_args_cb = vxlan_decap_mod_args_cb,
+		.tunnel_need_veth_mac = true
+	},
+	{
+		.ebpf_tun_type = "ip6vxlan",
+		.mac_tun_type = "eth",
+		.iproute_tun_type = "vxlan",
+		.ipproto = 6,
+		.extra_decap_mod_args_cb = vxlan_decap_mod_args_cb,
+		.tunnel_need_veth_mac = true
+	},
+	{
+		.ebpf_tun_type = "gre",
+		.mac_tun_type = "none",
+		.iproute_tun_type = "gre",
+		.ipproto = 4,
+		.test_gso = true
+	},
+	{
+		.ebpf_tun_type = "gre",
+		.mac_tun_type = "eth",
+		.iproute_tun_type = "gretap",
+		.ipproto = 4,
+		.tunnel_need_veth_mac = true,
+		.test_gso = true
+	},
+	{
+		.ebpf_tun_type = "gre",
+		.mac_tun_type = "mpls",
+		.iproute_tun_type = "gre",
+		.ipproto = 4,
+		.configure_mpls = true,
+		.test_gso = true
+	},
+	{
+		.ebpf_tun_type = "ip6gre",
+		.mac_tun_type = "none",
+		.iproute_tun_type = "ip6gre",
+		.ipproto = 6,
+		.test_gso = true,
+	},
+	{
+		.ebpf_tun_type = "ip6gre",
+		.mac_tun_type = "eth",
+		.iproute_tun_type = "ip6gretap",
+		.ipproto = 6,
+		.tunnel_need_veth_mac = true,
+		.test_gso = true
+	},
+	{
+		.ebpf_tun_type = "ip6gre",
+		.mac_tun_type = "mpls",
+		.iproute_tun_type = "ip6gre",
+		.ipproto = 6,
+		.configure_mpls = true,
+		.test_gso = true
+	},
+	{
+		.ebpf_tun_type = "udp",
+		.mac_tun_type = "none",
+		.iproute_tun_type = "ipip",
+		.ipproto = 4,
+		.extra_decap_mod_args_cb = udp_decap_mod_args_cb,
+		.configure_fou_rx_port = true,
+		.test_gso = true
+	},
+	{
+		.ebpf_tun_type = "udp",
+		.mac_tun_type = "eth",
+		.iproute_tun_type = "ipip",
+		.ipproto = 4,
+		.extra_decap_mod_args_cb = udp_decap_mod_args_cb,
+		.configure_fou_rx_port = true,
+		.expect_kern_decap_failure = true,
+		.test_gso = true
+	},
+	{
+		.ebpf_tun_type = "udp",
+		.mac_tun_type = "mpls",
+		.iproute_tun_type = "ipip",
+		.ipproto = 4,
+		.extra_decap_mod_args_cb = udp_decap_mod_args_cb,
+		.configure_fou_rx_port = true,
+		.tmode = "mode any ttl 255",
+		.configure_mpls = true,
+		.test_gso = true
+	},
+	{
+		.ebpf_tun_type = "ip6udp",
+		.mac_tun_type = "none",
+		.iproute_tun_type = "ip6tnl",
+		.ipproto = 6,
+		.extra_decap_mod_args_cb = udp_decap_mod_args_cb,
+		.configure_fou_rx_port = true,
+		.test_gso = true
+	},
+	{
+		.ebpf_tun_type = "ip6udp",
+		.mac_tun_type = "eth",
+		.iproute_tun_type = "ip6tnl",
+		.ipproto = 6,
+		.extra_decap_mod_args_cb = udp_decap_mod_args_cb,
+		.configure_fou_rx_port = true,
+		.expect_kern_decap_failure = true,
+		.test_gso = true
+	},
+	{
+		.ebpf_tun_type = "ip6udp",
+		.mac_tun_type = "mpls",
+		.iproute_tun_type = "ip6tnl",
+		.ipproto = 6,
+		.extra_decap_mod_args_cb = udp_decap_mod_args_cb,
+		.configure_fou_rx_port = true,
+		.tmode = "mode any ttl 255",
+		.expect_kern_decap_failure = true,
+		.test_gso = true
+	},
+};
+
+void test_tc_tunnel(void)
+{
+	struct test_tc_tunnel *skel;
+	struct subtest_cfg *cfg;
+	int i, ret;
+
+	skel = test_tc_tunnel__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel open and load"))
+		return;
+
+	if (!ASSERT_OK(setup(), "global setup"))
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(subtests_cfg); i++) {
+		cfg = &subtests_cfg[i];
+		ret = build_subtest_name(cfg, cfg->name, TEST_NAME_MAX_LEN);
+		if (ret < 0 || !test__start_subtest(cfg->name))
+			continue;
+		if (subtest_setup(skel, cfg) == 0)
+			run_test(cfg);
+		subtest_cleanup(cfg);
+	}
+	cleanup();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c
index 07ad457f3370..eb9309931272 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c
@@ -50,6 +50,7 @@
  */
 
 #include <arpa/inet.h>
+#include <linux/if_link.h>
 #include <linux/if_tun.h>
 #include <linux/limits.h>
 #include <linux/sysctl.h>
@@ -70,6 +71,8 @@
 #define IP4_ADDR2_VETH1 "172.16.1.20"
 #define IP4_ADDR_TUNL_DEV0 "10.1.1.100"
 #define IP4_ADDR_TUNL_DEV1 "10.1.1.200"
+#define IP6_ADDR_TUNL_DEV0 "fc80::100"
+#define IP6_ADDR_TUNL_DEV1 "fc80::200"
 
 #define IP6_ADDR_VETH0 "::11"
 #define IP6_ADDR1_VETH1 "::22"
@@ -89,32 +92,46 @@
 #define IP6VXLAN_TUNL_DEV0 "ip6vxlan00"
 #define IP6VXLAN_TUNL_DEV1 "ip6vxlan11"
 
-#define PING_ARGS "-i 0.01 -c 3 -w 10 -q"
+#define IPIP_TUNL_DEV0 "ipip00"
+#define IPIP_TUNL_DEV1 "ipip11"
 
-#define SYS(fmt, ...)						\
-	({							\
-		char cmd[1024];					\
-		snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__);	\
-		if (!ASSERT_OK(system(cmd), cmd))		\
-			goto fail;				\
-	})
+#define XFRM_AUTH "0x1111111111111111111111111111111111111111"
+#define XFRM_ENC "0x22222222222222222222222222222222"
+#define XFRM_SPI_IN_TO_OUT 0x1
+#define XFRM_SPI_OUT_TO_IN 0x2
 
-#define SYS_NOFAIL(fmt, ...)					\
-	({							\
-		char cmd[1024];					\
-		snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__);	\
-		system(cmd);					\
-	})
+#define GRE_TUNL_DEV0 "gre00"
+#define GRE_TUNL_DEV1 "gre11"
+
+#define IP6GRE_TUNL_DEV0 "ip6gre00"
+#define IP6GRE_TUNL_DEV1 "ip6gre11"
+
+#define ERSPAN_TUNL_DEV0 "erspan00"
+#define ERSPAN_TUNL_DEV1 "erspan11"
+
+#define IP6ERSPAN_TUNL_DEV0 "ip6erspan00"
+#define IP6ERSPAN_TUNL_DEV1 "ip6erspan11"
+
+#define GENEVE_TUNL_DEV0 "geneve00"
+#define GENEVE_TUNL_DEV1 "geneve11"
+
+#define IP6GENEVE_TUNL_DEV0 "ip6geneve00"
+#define IP6GENEVE_TUNL_DEV1 "ip6geneve11"
+
+#define IP6TNL_TUNL_DEV0 "ip6tnl00"
+#define IP6TNL_TUNL_DEV1 "ip6tnl11"
+
+#define PING_ARGS "-i 0.01 -c 3 -w 10 -q"
 
 static int config_device(void)
 {
-	SYS("ip netns add at_ns0");
-	SYS("ip link add veth0 address " MAC_VETH1 " type veth peer name veth1");
-	SYS("ip link set veth0 netns at_ns0");
-	SYS("ip addr add " IP4_ADDR1_VETH1 "/24 dev veth1");
-	SYS("ip link set dev veth1 up mtu 1500");
-	SYS("ip netns exec at_ns0 ip addr add " IP4_ADDR_VETH0 "/24 dev veth0");
-	SYS("ip netns exec at_ns0 ip link set dev veth0 up mtu 1500");
+	SYS(fail, "ip netns add at_ns0");
+	SYS(fail, "ip link add veth0 address " MAC_VETH1 " type veth peer name veth1");
+	SYS(fail, "ip link set veth0 netns at_ns0");
+	SYS(fail, "ip addr add " IP4_ADDR1_VETH1 "/24 dev veth1");
+	SYS(fail, "ip link set dev veth1 up mtu 1500");
+	SYS(fail, "ip netns exec at_ns0 ip addr add " IP4_ADDR_VETH0 "/24 dev veth0");
+	SYS(fail, "ip netns exec at_ns0 ip link set dev veth0 up mtu 1500");
 
 	return 0;
 fail:
@@ -124,31 +141,31 @@ fail:
 static void cleanup(void)
 {
 	SYS_NOFAIL("test -f /var/run/netns/at_ns0 && ip netns delete at_ns0");
-	SYS_NOFAIL("ip link del veth1 2> /dev/null");
-	SYS_NOFAIL("ip link del %s 2> /dev/null", VXLAN_TUNL_DEV1);
-	SYS_NOFAIL("ip link del %s 2> /dev/null", IP6VXLAN_TUNL_DEV1);
+	SYS_NOFAIL("ip link del veth1");
+	SYS_NOFAIL("ip link del %s", VXLAN_TUNL_DEV1);
+	SYS_NOFAIL("ip link del %s", IP6VXLAN_TUNL_DEV1);
 }
 
 static int add_vxlan_tunnel(void)
 {
 	/* at_ns0 namespace */
-	SYS("ip netns exec at_ns0 ip link add dev %s type vxlan external gbp dstport 4789",
+	SYS(fail, "ip netns exec at_ns0 ip link add dev %s type vxlan external gbp dstport 4789",
 	    VXLAN_TUNL_DEV0);
-	SYS("ip netns exec at_ns0 ip link set dev %s address %s up",
+	SYS(fail, "ip netns exec at_ns0 ip link set dev %s address %s up",
 	    VXLAN_TUNL_DEV0, MAC_TUNL_DEV0);
-	SYS("ip netns exec at_ns0 ip addr add dev %s %s/24",
+	SYS(fail, "ip netns exec at_ns0 ip addr add dev %s %s/24",
 	    VXLAN_TUNL_DEV0, IP4_ADDR_TUNL_DEV0);
-	SYS("ip netns exec at_ns0 ip neigh add %s lladdr %s dev %s",
+	SYS(fail, "ip netns exec at_ns0 ip neigh add %s lladdr %s dev %s",
 	    IP4_ADDR_TUNL_DEV1, MAC_TUNL_DEV1, VXLAN_TUNL_DEV0);
-	SYS("ip netns exec at_ns0 ip neigh add %s lladdr %s dev veth0",
+	SYS(fail, "ip netns exec at_ns0 ip neigh add %s lladdr %s dev veth0",
 	    IP4_ADDR2_VETH1, MAC_VETH1);
 
 	/* root namespace */
-	SYS("ip link add dev %s type vxlan external gbp dstport 4789",
+	SYS(fail, "ip link add dev %s type vxlan external gbp dstport 4789",
 	    VXLAN_TUNL_DEV1);
-	SYS("ip link set dev %s address %s up", VXLAN_TUNL_DEV1, MAC_TUNL_DEV1);
-	SYS("ip addr add dev %s %s/24", VXLAN_TUNL_DEV1, IP4_ADDR_TUNL_DEV1);
-	SYS("ip neigh add %s lladdr %s dev %s",
+	SYS(fail, "ip link set dev %s address %s up", VXLAN_TUNL_DEV1, MAC_TUNL_DEV1);
+	SYS(fail, "ip addr add dev %s %s/24", VXLAN_TUNL_DEV1, IP4_ADDR_TUNL_DEV1);
+	SYS(fail, "ip neigh add %s lladdr %s dev %s",
 	    IP4_ADDR_TUNL_DEV0, MAC_TUNL_DEV0, VXLAN_TUNL_DEV1);
 
 	return 0;
@@ -165,26 +182,26 @@ static void delete_vxlan_tunnel(void)
 
 static int add_ip6vxlan_tunnel(void)
 {
-	SYS("ip netns exec at_ns0 ip -6 addr add %s/96 dev veth0",
+	SYS(fail, "ip netns exec at_ns0 ip -6 addr add %s/96 dev veth0",
 	    IP6_ADDR_VETH0);
-	SYS("ip netns exec at_ns0 ip link set dev veth0 up");
-	SYS("ip -6 addr add %s/96 dev veth1", IP6_ADDR1_VETH1);
-	SYS("ip -6 addr add %s/96 dev veth1", IP6_ADDR2_VETH1);
-	SYS("ip link set dev veth1 up");
+	SYS(fail, "ip netns exec at_ns0 ip link set dev veth0 up");
+	SYS(fail, "ip -6 addr add %s/96 dev veth1", IP6_ADDR1_VETH1);
+	SYS(fail, "ip -6 addr add %s/96 dev veth1", IP6_ADDR2_VETH1);
+	SYS(fail, "ip link set dev veth1 up");
 
 	/* at_ns0 namespace */
-	SYS("ip netns exec at_ns0 ip link add dev %s type vxlan external dstport 4789",
+	SYS(fail, "ip netns exec at_ns0 ip link add dev %s type vxlan external dstport 4789",
 	    IP6VXLAN_TUNL_DEV0);
-	SYS("ip netns exec at_ns0 ip addr add dev %s %s/24",
+	SYS(fail, "ip netns exec at_ns0 ip addr add dev %s %s/24",
 	    IP6VXLAN_TUNL_DEV0, IP4_ADDR_TUNL_DEV0);
-	SYS("ip netns exec at_ns0 ip link set dev %s address %s up",
+	SYS(fail, "ip netns exec at_ns0 ip link set dev %s address %s up",
 	    IP6VXLAN_TUNL_DEV0, MAC_TUNL_DEV0);
 
 	/* root namespace */
-	SYS("ip link add dev %s type vxlan external dstport 4789",
+	SYS(fail, "ip link add dev %s type vxlan external dstport 4789",
 	    IP6VXLAN_TUNL_DEV1);
-	SYS("ip addr add dev %s %s/24", IP6VXLAN_TUNL_DEV1, IP4_ADDR_TUNL_DEV1);
-	SYS("ip link set dev %s address %s up",
+	SYS(fail, "ip addr add dev %s %s/24", IP6VXLAN_TUNL_DEV1, IP4_ADDR_TUNL_DEV1);
+	SYS(fail, "ip link set dev %s address %s up",
 	    IP6VXLAN_TUNL_DEV1, MAC_TUNL_DEV1);
 
 	return 0;
@@ -203,45 +220,318 @@ static void delete_ip6vxlan_tunnel(void)
 	SYS_NOFAIL("ip link delete dev %s", IP6VXLAN_TUNL_DEV1);
 }
 
-static int test_ping(int family, const char *addr)
+enum ipip_encap {
+	NONE	= 0,
+	FOU	= 1,
+	GUE	= 2,
+};
+
+static int set_ipip_encap(const char *ipproto, const char *type)
 {
-	SYS("%s %s %s > /dev/null", ping_command(family), PING_ARGS, addr);
+	SYS(fail, "ip -n at_ns0 fou add port 5555 %s", ipproto);
+	SYS(fail, "ip -n at_ns0 link set dev %s type ipip encap %s",
+	    IPIP_TUNL_DEV0, type);
+	SYS(fail, "ip -n at_ns0 link set dev %s type ipip encap-dport 5555",
+	    IPIP_TUNL_DEV0);
+
 	return 0;
 fail:
 	return -1;
 }
 
-static int attach_tc_prog(struct bpf_tc_hook *hook, int igr_fd, int egr_fd)
+static int set_ipv4_addr(const char *dev0, const char *dev1)
 {
-	DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts1, .handle = 1,
-			    .priority = 1, .prog_fd = igr_fd);
-	DECLARE_LIBBPF_OPTS(bpf_tc_opts, opts2, .handle = 1,
-			    .priority = 1, .prog_fd = egr_fd);
-	int ret;
+	SYS(fail, "ip -n at_ns0 link set dev %s up", dev0);
+	SYS(fail, "ip -n at_ns0 addr add dev %s %s/24", dev0, IP4_ADDR_TUNL_DEV0);
+	SYS(fail, "ip link set dev %s up", dev1);
+	SYS(fail, "ip addr add dev %s %s/24", dev1, IP4_ADDR_TUNL_DEV1);
 
-	ret = bpf_tc_hook_create(hook);
-	if (!ASSERT_OK(ret, "create tc hook"))
-		return ret;
+	return 0;
+fail:
+	return 1;
+}
 
-	if (igr_fd >= 0) {
-		hook->attach_point = BPF_TC_INGRESS;
-		ret = bpf_tc_attach(hook, &opts1);
-		if (!ASSERT_OK(ret, "bpf_tc_attach")) {
-			bpf_tc_hook_destroy(hook);
-			return ret;
-		}
+static int add_ipip_tunnel(enum ipip_encap encap)
+{
+	int err;
+	const char *ipproto, *type;
+
+	switch (encap) {
+	case FOU:
+		ipproto = "ipproto 4";
+		type = "fou";
+		break;
+	case GUE:
+		ipproto = "gue";
+		type = ipproto;
+		break;
+	default:
+		ipproto = NULL;
+		type = ipproto;
 	}
 
-	if (egr_fd >= 0) {
-		hook->attach_point = BPF_TC_EGRESS;
-		ret = bpf_tc_attach(hook, &opts2);
-		if (!ASSERT_OK(ret, "bpf_tc_attach")) {
-			bpf_tc_hook_destroy(hook);
-			return ret;
-		}
+	/* at_ns0 namespace */
+	SYS(fail, "ip -n at_ns0 link add dev %s type ipip local %s remote %s",
+	    IPIP_TUNL_DEV0, IP4_ADDR_VETH0, IP4_ADDR1_VETH1);
+
+	if (type && ipproto) {
+		err = set_ipip_encap(ipproto, type);
+		if (!ASSERT_OK(err, "set_ipip_encap"))
+			goto fail;
 	}
 
+	SYS(fail, "ip -n at_ns0 link set dev %s up", IPIP_TUNL_DEV0);
+	SYS(fail, "ip -n at_ns0 addr add dev %s %s/24",
+	    IPIP_TUNL_DEV0, IP4_ADDR_TUNL_DEV0);
+
+	/* root namespace */
+	if (type && ipproto)
+		SYS(fail, "ip fou add port 5555 %s", ipproto);
+	SYS(fail, "ip link add dev %s type ipip external", IPIP_TUNL_DEV1);
+	SYS(fail, "ip link set dev %s up", IPIP_TUNL_DEV1);
+	SYS(fail, "ip addr add dev %s %s/24", IPIP_TUNL_DEV1,
+	    IP4_ADDR_TUNL_DEV1);
+
+	return 0;
+fail:
+	return -1;
+}
+
+static void delete_ipip_tunnel(void)
+{
+	SYS_NOFAIL("ip -n at_ns0 link delete dev %s", IPIP_TUNL_DEV0);
+	SYS_NOFAIL("ip -n at_ns0 fou del port 5555");
+	SYS_NOFAIL("ip link delete dev %s", IPIP_TUNL_DEV1);
+	SYS_NOFAIL("ip fou del port 5555");
+}
+
+static int add_xfrm_tunnel(void)
+{
+	/* at_ns0 namespace
+	 * at_ns0 -> root
+	 */
+	SYS(fail,
+	    "ip netns exec at_ns0 "
+		"ip xfrm state add src %s dst %s proto esp "
+			"spi %d reqid 1 mode tunnel replay-window 42 "
+			"auth-trunc 'hmac(sha1)' %s 96 enc 'cbc(aes)' %s",
+	    IP4_ADDR_VETH0, IP4_ADDR1_VETH1, XFRM_SPI_IN_TO_OUT, XFRM_AUTH, XFRM_ENC);
+	SYS(fail,
+	    "ip netns exec at_ns0 "
+		"ip xfrm policy add src %s/32 dst %s/32 dir out "
+			"tmpl src %s dst %s proto esp reqid 1 "
+			"mode tunnel",
+	    IP4_ADDR_TUNL_DEV0, IP4_ADDR_TUNL_DEV1, IP4_ADDR_VETH0, IP4_ADDR1_VETH1);
+
+	/* root -> at_ns0 */
+	SYS(fail,
+	    "ip netns exec at_ns0 "
+		"ip xfrm state add src %s dst %s proto esp "
+			"spi %d reqid 2 mode tunnel "
+			"auth-trunc 'hmac(sha1)' %s 96 enc 'cbc(aes)' %s",
+	    IP4_ADDR1_VETH1, IP4_ADDR_VETH0, XFRM_SPI_OUT_TO_IN, XFRM_AUTH, XFRM_ENC);
+	SYS(fail,
+	    "ip netns exec at_ns0 "
+		"ip xfrm policy add src %s/32 dst %s/32 dir in "
+			"tmpl src %s dst %s proto esp reqid 2 "
+			"mode tunnel",
+	    IP4_ADDR_TUNL_DEV1, IP4_ADDR_TUNL_DEV0, IP4_ADDR1_VETH1, IP4_ADDR_VETH0);
+
+	/* address & route */
+	SYS(fail, "ip netns exec at_ns0 ip addr add dev veth0 %s/32",
+	    IP4_ADDR_TUNL_DEV0);
+	SYS(fail, "ip netns exec at_ns0 ip route add %s dev veth0 via %s src %s",
+	    IP4_ADDR_TUNL_DEV1, IP4_ADDR1_VETH1, IP4_ADDR_TUNL_DEV0);
+
+	/* root namespace
+	 * at_ns0 -> root
+	 */
+	SYS(fail,
+	    "ip xfrm state add src %s dst %s proto esp "
+		    "spi %d reqid 1 mode tunnel replay-window 42 "
+		    "auth-trunc 'hmac(sha1)' %s 96  enc 'cbc(aes)' %s",
+	    IP4_ADDR_VETH0, IP4_ADDR1_VETH1, XFRM_SPI_IN_TO_OUT, XFRM_AUTH, XFRM_ENC);
+	SYS(fail,
+	    "ip xfrm policy add src %s/32 dst %s/32 dir in "
+		    "tmpl src %s dst %s proto esp reqid 1 "
+		    "mode tunnel",
+	    IP4_ADDR_TUNL_DEV0, IP4_ADDR_TUNL_DEV1, IP4_ADDR_VETH0, IP4_ADDR1_VETH1);
+
+	/* root -> at_ns0 */
+	SYS(fail,
+	    "ip xfrm state add src %s dst %s proto esp "
+		    "spi %d reqid 2 mode tunnel "
+		    "auth-trunc 'hmac(sha1)' %s 96  enc 'cbc(aes)' %s",
+	    IP4_ADDR1_VETH1, IP4_ADDR_VETH0, XFRM_SPI_OUT_TO_IN, XFRM_AUTH, XFRM_ENC);
+	SYS(fail,
+	    "ip xfrm policy add src %s/32 dst %s/32 dir out "
+		    "tmpl src %s dst %s proto esp reqid 2 "
+		    "mode tunnel",
+	    IP4_ADDR_TUNL_DEV1, IP4_ADDR_TUNL_DEV0, IP4_ADDR1_VETH1, IP4_ADDR_VETH0);
+
+	/* address & route */
+	SYS(fail, "ip addr add dev veth1 %s/32", IP4_ADDR_TUNL_DEV1);
+	SYS(fail, "ip route add %s dev veth1 via %s src %s",
+	    IP4_ADDR_TUNL_DEV0, IP4_ADDR_VETH0, IP4_ADDR_TUNL_DEV1);
+
 	return 0;
+fail:
+	return -1;
+}
+
+static void delete_xfrm_tunnel(void)
+{
+	SYS_NOFAIL("ip xfrm policy delete dir out src %s/32 dst %s/32",
+		   IP4_ADDR_TUNL_DEV1, IP4_ADDR_TUNL_DEV0);
+	SYS_NOFAIL("ip xfrm policy delete dir in src %s/32 dst %s/32",
+		   IP4_ADDR_TUNL_DEV0, IP4_ADDR_TUNL_DEV1);
+	SYS_NOFAIL("ip xfrm state delete src %s dst %s proto esp spi %d",
+		   IP4_ADDR_VETH0, IP4_ADDR1_VETH1, XFRM_SPI_IN_TO_OUT);
+	SYS_NOFAIL("ip xfrm state delete src %s dst %s proto esp spi %d",
+		   IP4_ADDR1_VETH1, IP4_ADDR_VETH0, XFRM_SPI_OUT_TO_IN);
+}
+
+static int add_ipv4_tunnel(const char *dev0, const char *dev1,
+			   const char *type, const char *opt)
+{
+	if (!type || !opt || !dev0 || !dev1)
+		return -1;
+
+	SYS(fail, "ip -n at_ns0 link add dev %s type %s %s local %s remote %s",
+	    dev0, type, opt, IP4_ADDR_VETH0, IP4_ADDR1_VETH1);
+
+	SYS(fail, "ip link add dev %s type %s external", dev1, type);
+
+	return set_ipv4_addr(dev0, dev1);
+fail:
+	return -1;
+}
+
+static void delete_tunnel(const char *dev0, const char *dev1)
+{
+	if (!dev0 || !dev1)
+		return;
+
+	SYS_NOFAIL("ip netns exec at_ns0 ip link delete dev %s", dev0);
+	SYS_NOFAIL("ip link delete dev %s", dev1);
+}
+
+static int set_ipv6_addr(const char *dev0, const char *dev1)
+{
+	/* disable IPv6 DAD because it might take too long and fail tests */
+	SYS(fail, "ip -n at_ns0 addr add %s/96 dev veth0 nodad", IP6_ADDR_VETH0);
+	SYS(fail, "ip -n at_ns0 link set dev veth0 up");
+	SYS(fail, "ip addr add %s/96 dev veth1 nodad", IP6_ADDR1_VETH1);
+	SYS(fail, "ip link set dev veth1 up");
+
+	SYS(fail, "ip -n at_ns0 addr add dev %s %s/24", dev0, IP4_ADDR_TUNL_DEV0);
+	SYS(fail, "ip -n at_ns0 addr add dev %s %s/96 nodad", dev0, IP6_ADDR_TUNL_DEV0);
+	SYS(fail, "ip -n at_ns0 link set dev %s up", dev0);
+
+	SYS(fail, "ip addr add dev %s %s/24", dev1, IP4_ADDR_TUNL_DEV1);
+	SYS(fail, "ip addr add dev %s %s/96 nodad", dev1, IP6_ADDR_TUNL_DEV1);
+	SYS(fail, "ip link set dev %s up", dev1);
+	return 0;
+fail:
+	return 1;
+}
+
+static int add_ipv6_tunnel(const char *dev0, const char *dev1,
+			   const char *type, const char *opt)
+{
+	if (!type || !opt || !dev0 || !dev1)
+		return -1;
+
+	SYS(fail, "ip -n at_ns0 link add dev %s type %s %s local %s remote %s",
+	    dev0, type, opt, IP6_ADDR_VETH0, IP6_ADDR1_VETH1);
+
+	SYS(fail, "ip link add dev %s type %s external", dev1, type);
+
+	return set_ipv6_addr(dev0, dev1);
+fail:
+	return -1;
+}
+
+static int add_geneve_tunnel(const char *dev0, const char *dev1,
+			     const char *type, const char *opt)
+{
+	if (!type || !opt || !dev0 || !dev1)
+		return -1;
+
+	SYS(fail, "ip -n at_ns0 link add dev %s type %s id 2 %s remote %s",
+	    dev0, type, opt, IP4_ADDR1_VETH1);
+
+	SYS(fail, "ip link add dev %s type %s %s external", dev1, type, opt);
+
+	return set_ipv4_addr(dev0, dev1);
+fail:
+	return -1;
+}
+
+static int add_ip6geneve_tunnel(const char *dev0, const char *dev1,
+			     const char *type, const char *opt)
+{
+	if (!type || !opt || !dev0 || !dev1)
+		return -1;
+
+	SYS(fail, "ip -n at_ns0 link add dev %s type %s id 22 %s remote %s",
+	    dev0, type, opt, IP6_ADDR1_VETH1);
+
+	SYS(fail, "ip link add dev %s type %s %s external", dev1, type, opt);
+
+	return set_ipv6_addr(dev0, dev1);
+fail:
+	return -1;
+}
+
+static int test_ping(int family, const char *addr)
+{
+	SYS(fail, "%s %s %s > /dev/null", ping_command(family), PING_ARGS, addr);
+	return 0;
+fail:
+	return -1;
+}
+
+static void ping_dev0(void)
+{
+	/* ping from root namespace test */
+	test_ping(AF_INET, IP4_ADDR_TUNL_DEV0);
+}
+
+static void ping_dev1(void)
+{
+	struct nstoken *nstoken;
+
+	/* ping from at_ns0 namespace test */
+	nstoken = open_netns("at_ns0");
+	if (!ASSERT_OK_PTR(nstoken, "setns"))
+		return;
+
+	test_ping(AF_INET, IP4_ADDR_TUNL_DEV1);
+	close_netns(nstoken);
+}
+
+static void ping6_veth0(void)
+{
+	test_ping(AF_INET6, IP6_ADDR_VETH0);
+}
+
+static void ping6_dev0(void)
+{
+	test_ping(AF_INET6, IP6_ADDR_TUNL_DEV0);
+}
+
+static void ping6_dev1(void)
+{
+	struct nstoken *nstoken;
+
+	/* ping from at_ns0 namespace test */
+	nstoken = open_netns("at_ns0");
+	if (!ASSERT_OK_PTR(nstoken, "setns"))
+		return;
+
+	test_ping(AF_INET, IP6_ADDR_TUNL_DEV1);
+	close_netns(nstoken);
 }
 
 static void test_vxlan_tunnel(void)
@@ -251,11 +541,9 @@ static void test_vxlan_tunnel(void)
 	int local_ip_map_fd = -1;
 	int set_src_prog_fd, get_src_prog_fd;
 	int set_dst_prog_fd;
-	int key = 0, ifindex = -1;
+	int key = 0;
 	uint local_ip;
 	int err;
-	DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook,
-			    .attach_point = BPF_TC_INGRESS);
 
 	/* add vxlan tunnel */
 	err = add_vxlan_tunnel();
@@ -266,42 +554,22 @@ static void test_vxlan_tunnel(void)
 	skel = test_tunnel_kern__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
 		goto done;
-	ifindex = if_nametoindex(VXLAN_TUNL_DEV1);
-	if (!ASSERT_NEQ(ifindex, 0, "vxlan11 ifindex"))
-		goto done;
-	tc_hook.ifindex = ifindex;
 	get_src_prog_fd = bpf_program__fd(skel->progs.vxlan_get_tunnel_src);
 	set_src_prog_fd = bpf_program__fd(skel->progs.vxlan_set_tunnel_src);
-	if (!ASSERT_GE(get_src_prog_fd, 0, "bpf_program__fd"))
-		goto done;
-	if (!ASSERT_GE(set_src_prog_fd, 0, "bpf_program__fd"))
-		goto done;
-	if (attach_tc_prog(&tc_hook, get_src_prog_fd, set_src_prog_fd))
+	if (tc_prog_attach(VXLAN_TUNL_DEV1, get_src_prog_fd, set_src_prog_fd))
 		goto done;
 
 	/* load and attach bpf prog to veth dev tc hook point */
-	ifindex = if_nametoindex("veth1");
-	if (!ASSERT_NEQ(ifindex, 0, "veth1 ifindex"))
-		goto done;
-	tc_hook.ifindex = ifindex;
 	set_dst_prog_fd = bpf_program__fd(skel->progs.veth_set_outer_dst);
-	if (!ASSERT_GE(set_dst_prog_fd, 0, "bpf_program__fd"))
-		goto done;
-	if (attach_tc_prog(&tc_hook, set_dst_prog_fd, -1))
+	if (tc_prog_attach("veth1", set_dst_prog_fd, -1))
 		goto done;
 
 	/* load and attach prog set_md to tunnel dev tc hook point at_ns0 */
 	nstoken = open_netns("at_ns0");
 	if (!ASSERT_OK_PTR(nstoken, "setns src"))
 		goto done;
-	ifindex = if_nametoindex(VXLAN_TUNL_DEV0);
-	if (!ASSERT_NEQ(ifindex, 0, "vxlan00 ifindex"))
-		goto done;
-	tc_hook.ifindex = ifindex;
 	set_dst_prog_fd = bpf_program__fd(skel->progs.vxlan_set_tunnel_dst);
-	if (!ASSERT_GE(set_dst_prog_fd, 0, "bpf_program__fd"))
-		goto done;
-	if (attach_tc_prog(&tc_hook, -1, set_dst_prog_fd))
+	if (tc_prog_attach(VXLAN_TUNL_DEV0, -1, set_dst_prog_fd))
 		goto done;
 	close_netns(nstoken);
 
@@ -315,9 +583,7 @@ static void test_vxlan_tunnel(void)
 		goto done;
 
 	/* ping test */
-	err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV0);
-	if (!ASSERT_OK(err, "test_ping"))
-		goto done;
+	ping_dev0();
 
 done:
 	/* delete vxlan tunnel */
@@ -335,11 +601,9 @@ static void test_ip6vxlan_tunnel(void)
 	int local_ip_map_fd = -1;
 	int set_src_prog_fd, get_src_prog_fd;
 	int set_dst_prog_fd;
-	int key = 0, ifindex = -1;
+	int key = 0;
 	uint local_ip;
 	int err;
-	DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook,
-			    .attach_point = BPF_TC_INGRESS);
 
 	/* add vxlan tunnel */
 	err = add_ip6vxlan_tunnel();
@@ -350,31 +614,17 @@ static void test_ip6vxlan_tunnel(void)
 	skel = test_tunnel_kern__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
 		goto done;
-	ifindex = if_nametoindex(IP6VXLAN_TUNL_DEV1);
-	if (!ASSERT_NEQ(ifindex, 0, "ip6vxlan11 ifindex"))
-		goto done;
-	tc_hook.ifindex = ifindex;
 	get_src_prog_fd = bpf_program__fd(skel->progs.ip6vxlan_get_tunnel_src);
 	set_src_prog_fd = bpf_program__fd(skel->progs.ip6vxlan_set_tunnel_src);
-	if (!ASSERT_GE(set_src_prog_fd, 0, "bpf_program__fd"))
-		goto done;
-	if (!ASSERT_GE(get_src_prog_fd, 0, "bpf_program__fd"))
-		goto done;
-	if (attach_tc_prog(&tc_hook, get_src_prog_fd, set_src_prog_fd))
+	if (tc_prog_attach(IP6VXLAN_TUNL_DEV1, get_src_prog_fd, set_src_prog_fd))
 		goto done;
 
 	/* load and attach prog set_md to tunnel dev tc hook point at_ns0 */
 	nstoken = open_netns("at_ns0");
 	if (!ASSERT_OK_PTR(nstoken, "setns src"))
 		goto done;
-	ifindex = if_nametoindex(IP6VXLAN_TUNL_DEV0);
-	if (!ASSERT_NEQ(ifindex, 0, "ip6vxlan00 ifindex"))
-		goto done;
-	tc_hook.ifindex = ifindex;
 	set_dst_prog_fd = bpf_program__fd(skel->progs.ip6vxlan_set_tunnel_dst);
-	if (!ASSERT_GE(set_dst_prog_fd, 0, "bpf_program__fd"))
-		goto done;
-	if (attach_tc_prog(&tc_hook, -1, set_dst_prog_fd))
+	if (tc_prog_attach(IP6VXLAN_TUNL_DEV0, -1, set_dst_prog_fd))
 		goto done;
 	close_netns(nstoken);
 
@@ -388,9 +638,7 @@ static void test_ip6vxlan_tunnel(void)
 		goto done;
 
 	/* ping test */
-	err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV0);
-	if (!ASSERT_OK(err, "test_ping"))
-		goto done;
+	ping_dev0();
 
 done:
 	/* delete ipv6 vxlan tunnel */
@@ -401,22 +649,412 @@ done:
 		test_tunnel_kern__destroy(skel);
 }
 
-#define RUN_TEST(name)							\
+static void test_ipip_tunnel(enum ipip_encap encap)
+{
+	struct test_tunnel_kern *skel = NULL;
+	int set_src_prog_fd, get_src_prog_fd;
+	int err;
+
+	/* add ipip tunnel */
+	err = add_ipip_tunnel(encap);
+	if (!ASSERT_OK(err, "add_ipip_tunnel"))
+		goto done;
+
+	/* load and attach bpf prog to tunnel dev tc hook point */
+	skel = test_tunnel_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+		goto done;
+
+	switch (encap) {
+	case FOU:
+		get_src_prog_fd = bpf_program__fd(
+			skel->progs.ipip_encap_get_tunnel);
+		set_src_prog_fd = bpf_program__fd(
+			skel->progs.ipip_fou_set_tunnel);
+		break;
+	case GUE:
+		get_src_prog_fd = bpf_program__fd(
+			skel->progs.ipip_encap_get_tunnel);
+		set_src_prog_fd = bpf_program__fd(
+			skel->progs.ipip_gue_set_tunnel);
+		break;
+	default:
+		get_src_prog_fd = bpf_program__fd(
+			skel->progs.ipip_get_tunnel);
+		set_src_prog_fd = bpf_program__fd(
+			skel->progs.ipip_set_tunnel);
+	}
+
+	if (tc_prog_attach(IPIP_TUNL_DEV1, get_src_prog_fd, set_src_prog_fd))
+		goto done;
+
+	ping_dev0();
+	ping_dev1();
+
+done:
+	/* delete ipip tunnel */
+	delete_ipip_tunnel();
+	if (skel)
+		test_tunnel_kern__destroy(skel);
+}
+
+static void test_xfrm_tunnel(void)
+{
+	LIBBPF_OPTS(bpf_xdp_attach_opts, opts);
+	struct test_tunnel_kern *skel = NULL;
+	int xdp_prog_fd;
+	int tc_prog_fd;
+	int ifindex;
+	int err;
+
+	err = add_xfrm_tunnel();
+	if (!ASSERT_OK(err, "add_xfrm_tunnel"))
+		return;
+
+	skel = test_tunnel_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+		goto done;
+
+
+	/* attach tc prog to tunnel dev */
+	tc_prog_fd = bpf_program__fd(skel->progs.xfrm_get_state);
+	if (tc_prog_attach("veth1", tc_prog_fd, -1))
+		goto done;
+
+	/* attach xdp prog to tunnel dev */
+	ifindex = if_nametoindex("veth1");
+	if (!ASSERT_NEQ(ifindex, 0, "veth1 ifindex"))
+		goto done;
+	xdp_prog_fd = bpf_program__fd(skel->progs.xfrm_get_state_xdp);
+	if (!ASSERT_GE(xdp_prog_fd, 0, "bpf_program__fd"))
+		goto done;
+	err = bpf_xdp_attach(ifindex, xdp_prog_fd, XDP_FLAGS_REPLACE, &opts);
+	if (!ASSERT_OK(err, "bpf_xdp_attach"))
+		goto done;
+
+	ping_dev1();
+
+	if (!ASSERT_EQ(skel->bss->xfrm_reqid, 1, "req_id"))
+		goto done;
+	if (!ASSERT_EQ(skel->bss->xfrm_spi, XFRM_SPI_IN_TO_OUT, "spi"))
+		goto done;
+	if (!ASSERT_EQ(skel->bss->xfrm_remote_ip, 0xac100164, "remote_ip"))
+		goto done;
+	if (!ASSERT_EQ(skel->bss->xfrm_replay_window, 42, "replay_window"))
+		goto done;
+
+done:
+	delete_xfrm_tunnel();
+	if (skel)
+		test_tunnel_kern__destroy(skel);
+}
+
+enum gre_test {
+	GRE,
+	GRE_NOKEY,
+	GRETAP,
+	GRETAP_NOKEY,
+};
+
+static void test_gre_tunnel(enum gre_test test)
+{
+	struct test_tunnel_kern *skel;
+	int set_fd, get_fd;
+	int err;
+
+	skel = test_tunnel_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+		return;
+
+	switch (test) {
+	case GRE:
+		err = add_ipv4_tunnel(GRE_TUNL_DEV0, GRE_TUNL_DEV1, "gre", "seq");
+		set_fd = bpf_program__fd(skel->progs.gre_set_tunnel_no_key);
+		get_fd = bpf_program__fd(skel->progs.gre_get_tunnel);
+		break;
+	case GRE_NOKEY:
+		err = add_ipv4_tunnel(GRE_TUNL_DEV0, GRE_TUNL_DEV1, "gre", "seq key 2");
+		set_fd = bpf_program__fd(skel->progs.gre_set_tunnel);
+		get_fd = bpf_program__fd(skel->progs.gre_get_tunnel);
+		break;
+	case GRETAP:
+		err = add_ipv4_tunnel(GRE_TUNL_DEV0, GRE_TUNL_DEV1, "gretap", "seq");
+		set_fd = bpf_program__fd(skel->progs.gre_set_tunnel_no_key);
+		get_fd = bpf_program__fd(skel->progs.gre_get_tunnel);
+		break;
+	case GRETAP_NOKEY:
+		err = add_ipv4_tunnel(GRE_TUNL_DEV0, GRE_TUNL_DEV1, "gretap", "seq key 2");
+		set_fd = bpf_program__fd(skel->progs.gre_set_tunnel);
+		get_fd = bpf_program__fd(skel->progs.gre_get_tunnel);
+		break;
+	}
+	if (!ASSERT_OK(err, "add tunnel"))
+		goto done;
+
+	if (tc_prog_attach(GRE_TUNL_DEV1, get_fd, set_fd))
+		goto done;
+
+	ping_dev0();
+	ping_dev1();
+
+done:
+	delete_tunnel(GRE_TUNL_DEV0, GRE_TUNL_DEV1);
+	test_tunnel_kern__destroy(skel);
+}
+
+enum ip6gre_test {
+	IP6GRE,
+	IP6GRETAP
+};
+
+static void test_ip6gre_tunnel(enum ip6gre_test test)
+{
+	struct test_tunnel_kern *skel;
+	int set_fd, get_fd;
+	int err;
+
+	skel = test_tunnel_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+		return;
+
+	switch (test) {
+	case IP6GRE:
+		err = add_ipv6_tunnel(IP6GRE_TUNL_DEV0, IP6GRE_TUNL_DEV1,
+				      "ip6gre", "flowlabel 0xbcdef key 2");
+		break;
+	case IP6GRETAP:
+		err = add_ipv6_tunnel(IP6GRE_TUNL_DEV0, IP6GRE_TUNL_DEV1,
+				      "ip6gretap", "flowlabel 0xbcdef key 2");
+		break;
+	}
+	if (!ASSERT_OK(err, "add tunnel"))
+		goto done;
+
+	set_fd = bpf_program__fd(skel->progs.ip6gretap_set_tunnel);
+	get_fd = bpf_program__fd(skel->progs.ip6gretap_get_tunnel);
+	if (tc_prog_attach(IP6GRE_TUNL_DEV1, get_fd, set_fd))
+		goto done;
+
+	ping6_veth0();
+	ping6_dev1();
+	ping_dev0();
+	ping_dev1();
+done:
+	delete_tunnel(IP6GRE_TUNL_DEV0, IP6GRE_TUNL_DEV1);
+	test_tunnel_kern__destroy(skel);
+}
+
+enum erspan_test {
+	V1,
+	V2
+};
+
+static void test_erspan_tunnel(enum erspan_test test)
+{
+	struct test_tunnel_kern *skel;
+	int set_fd, get_fd;
+	int err;
+
+	skel = test_tunnel_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+		return;
+
+	switch (test) {
+	case V1:
+		err = add_ipv4_tunnel(ERSPAN_TUNL_DEV0, ERSPAN_TUNL_DEV1,
+				      "erspan", "seq key 2 erspan_ver 1 erspan 123");
+		break;
+	case V2:
+		err = add_ipv4_tunnel(ERSPAN_TUNL_DEV0, ERSPAN_TUNL_DEV1,
+				      "erspan",
+				      "seq key 2 erspan_ver 2 erspan_dir egress erspan_hwid 3");
+		break;
+	}
+	if (!ASSERT_OK(err, "add tunnel"))
+		goto done;
+
+	set_fd = bpf_program__fd(skel->progs.erspan_set_tunnel);
+	get_fd = bpf_program__fd(skel->progs.erspan_get_tunnel);
+	if (tc_prog_attach(ERSPAN_TUNL_DEV1, get_fd, set_fd))
+		goto done;
+
+	ping_dev0();
+	ping_dev1();
+done:
+	delete_tunnel(ERSPAN_TUNL_DEV0, ERSPAN_TUNL_DEV1);
+	test_tunnel_kern__destroy(skel);
+}
+
+static void test_ip6erspan_tunnel(enum erspan_test test)
+{
+	struct test_tunnel_kern *skel;
+	int set_fd, get_fd;
+	int err;
+
+	skel = test_tunnel_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+		return;
+
+	switch (test) {
+	case V1:
+		err = add_ipv6_tunnel(IP6ERSPAN_TUNL_DEV0, IP6ERSPAN_TUNL_DEV1,
+				      "ip6erspan", "seq key 2 erspan_ver 1 erspan 123");
+		break;
+	case V2:
+		err = add_ipv6_tunnel(IP6ERSPAN_TUNL_DEV0, IP6ERSPAN_TUNL_DEV1,
+				      "ip6erspan",
+				      "seq key 2 erspan_ver 2 erspan_dir egress erspan_hwid 7");
+		break;
+	}
+	if (!ASSERT_OK(err, "add tunnel"))
+		goto done;
+
+	set_fd = bpf_program__fd(skel->progs.ip4ip6erspan_set_tunnel);
+	get_fd = bpf_program__fd(skel->progs.ip4ip6erspan_get_tunnel);
+	if (tc_prog_attach(IP6ERSPAN_TUNL_DEV1, get_fd, set_fd))
+		goto done;
+
+	ping6_veth0();
+	ping_dev1();
+done:
+	delete_tunnel(IP6ERSPAN_TUNL_DEV0, IP6ERSPAN_TUNL_DEV1);
+	test_tunnel_kern__destroy(skel);
+}
+
+static void test_geneve_tunnel(void)
+{
+	struct test_tunnel_kern *skel;
+	int set_fd, get_fd;
+	int err;
+
+	skel = test_tunnel_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+		return;
+
+	err = add_geneve_tunnel(GENEVE_TUNL_DEV0, GENEVE_TUNL_DEV1,
+				"geneve", "dstport 6081");
+	if (!ASSERT_OK(err, "add tunnel"))
+		goto done;
+
+	set_fd = bpf_program__fd(skel->progs.geneve_set_tunnel);
+	get_fd = bpf_program__fd(skel->progs.geneve_get_tunnel);
+	if (tc_prog_attach(GENEVE_TUNL_DEV1, get_fd, set_fd))
+		goto done;
+
+	ping_dev0();
+	ping_dev1();
+done:
+	delete_tunnel(GENEVE_TUNL_DEV0, GENEVE_TUNL_DEV1);
+	test_tunnel_kern__destroy(skel);
+}
+
+static void test_ip6geneve_tunnel(void)
+{
+	struct test_tunnel_kern *skel;
+	int set_fd, get_fd;
+	int err;
+
+	skel = test_tunnel_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+		return;
+
+	err = add_ip6geneve_tunnel(IP6GENEVE_TUNL_DEV0, IP6GENEVE_TUNL_DEV1,
+				   "geneve", "");
+	if (!ASSERT_OK(err, "add tunnel"))
+		goto done;
+
+	set_fd = bpf_program__fd(skel->progs.ip6geneve_set_tunnel);
+	get_fd = bpf_program__fd(skel->progs.ip6geneve_get_tunnel);
+	if (tc_prog_attach(IP6GENEVE_TUNL_DEV1, get_fd, set_fd))
+		goto done;
+
+	ping_dev0();
+	ping_dev1();
+done:
+	delete_tunnel(IP6GENEVE_TUNL_DEV0, IP6GENEVE_TUNL_DEV1);
+	test_tunnel_kern__destroy(skel);
+}
+
+enum ip6tnl_test {
+	IPIP6,
+	IP6IP6
+};
+
+static void test_ip6tnl_tunnel(enum ip6tnl_test test)
+{
+	struct test_tunnel_kern *skel;
+	int set_fd, get_fd;
+	int err;
+
+	skel = test_tunnel_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+		return;
+
+	err = add_ipv6_tunnel(IP6TNL_TUNL_DEV0, IP6TNL_TUNL_DEV1, "ip6tnl", "");
+	if (!ASSERT_OK(err, "add tunnel"))
+		goto done;
+
+	switch (test) {
+	case IPIP6:
+		set_fd = bpf_program__fd(skel->progs.ipip6_set_tunnel);
+		get_fd = bpf_program__fd(skel->progs.ipip6_get_tunnel);
+		break;
+	case IP6IP6:
+		set_fd = bpf_program__fd(skel->progs.ip6ip6_set_tunnel);
+		get_fd = bpf_program__fd(skel->progs.ip6ip6_get_tunnel);
+		break;
+	}
+	if (tc_prog_attach(IP6TNL_TUNL_DEV1, get_fd, set_fd))
+		goto done;
+
+	ping6_veth0();
+	switch (test) {
+	case IPIP6:
+		ping_dev0();
+		ping_dev1();
+		break;
+	case IP6IP6:
+		ping6_dev0();
+		ping6_dev1();
+		break;
+	}
+
+done:
+	delete_tunnel(IP6TNL_TUNL_DEV0, IP6TNL_TUNL_DEV1);
+	test_tunnel_kern__destroy(skel);
+}
+
+#define RUN_TEST(name, ...)						\
 	({								\
 		if (test__start_subtest(#name)) {			\
-			test_ ## name();				\
+			config_device();				\
+			test_ ## name(__VA_ARGS__);			\
+			cleanup();					\
 		}							\
 	})
 
 static void *test_tunnel_run_tests(void *arg)
 {
-	cleanup();
-	config_device();
-
 	RUN_TEST(vxlan_tunnel);
 	RUN_TEST(ip6vxlan_tunnel);
-
-	cleanup();
+	RUN_TEST(ipip_tunnel, NONE);
+	RUN_TEST(ipip_tunnel, FOU);
+	RUN_TEST(ipip_tunnel, GUE);
+	RUN_TEST(xfrm_tunnel);
+	RUN_TEST(gre_tunnel, GRE);
+	RUN_TEST(gre_tunnel, GRE_NOKEY);
+	RUN_TEST(gre_tunnel, GRETAP);
+	RUN_TEST(gre_tunnel, GRETAP_NOKEY);
+	RUN_TEST(ip6gre_tunnel, IP6GRE);
+	RUN_TEST(ip6gre_tunnel, IP6GRETAP);
+	RUN_TEST(erspan_tunnel, V1);
+	RUN_TEST(erspan_tunnel, V2);
+	RUN_TEST(ip6erspan_tunnel, V1);
+	RUN_TEST(ip6erspan_tunnel, V2);
+	RUN_TEST(geneve_tunnel);
+	RUN_TEST(ip6geneve_tunnel);
+	RUN_TEST(ip6tnl_tunnel, IPIP6);
+	RUN_TEST(ip6tnl_tunnel, IP6IP6);
 
 	return NULL;
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/test_veristat.c b/tools/testing/selftests/bpf/prog_tests/test_veristat.c
new file mode 100644
index 000000000000..b38c16b4247f
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_veristat.c
@@ -0,0 +1,261 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include <string.h>
+#include <stdio.h>
+
+#define __CHECK_STR(str, name)					    \
+	do {							    \
+		if (!ASSERT_HAS_SUBSTR(fix->output, (str), (name))) \
+			goto out;				    \
+	} while (0)
+
+struct fixture {
+	char tmpfile[80];
+	int fd;
+	char *output;
+	size_t sz;
+	char veristat[80];
+};
+
+static struct fixture *init_fixture(void)
+{
+	struct fixture *fix = malloc(sizeof(struct fixture));
+
+	/* for no_alu32 and cpuv4 veristat is in parent folder */
+	if (access("./veristat", F_OK) == 0)
+		strcpy(fix->veristat, "./veristat");
+	else if (access("../veristat", F_OK) == 0)
+		strcpy(fix->veristat, "../veristat");
+	else
+		PRINT_FAIL("Can't find veristat binary");
+
+	snprintf(fix->tmpfile, sizeof(fix->tmpfile), "/tmp/test_veristat.XXXXXX");
+	fix->fd = mkstemp(fix->tmpfile);
+	fix->sz = 1000000;
+	fix->output = malloc(fix->sz);
+	return fix;
+}
+
+static void teardown_fixture(struct fixture *fix)
+{
+	free(fix->output);
+	close(fix->fd);
+	remove(fix->tmpfile);
+	free(fix);
+}
+
+static void test_set_global_vars_succeeds(void)
+{
+	struct fixture *fix = init_fixture();
+
+	SYS(out,
+	    "%s set_global_vars.bpf.o"\
+	    " -G \"var_s64 = 0xf000000000000001\" "\
+	    " -G \"var_u64 = 0xfedcba9876543210\" "\
+	    " -G \"var_s32 = -0x80000000\" "\
+	    " -G \"var_u32 = 0x76543210\" "\
+	    " -G \"var_s16 = -32768\" "\
+	    " -G \"var_u16 = 60652\" "\
+	    " -G \"var_s8 = -128\" "\
+	    " -G \"var_u8 = 255\" "\
+	    " -G \"var_ea = EA2\" "\
+	    " -G \"var_eb  =  EB2\" "\
+	    " -G \"var_ec=EC2\" "\
+	    " -G \"var_b = 1\" "\
+	    " -G \"struct1[2].struct2[1][2].u.var_u8[2]=170\" "\
+	    " -G \"union1.struct3.var_u8_l = 0xaa\" "\
+	    " -G \"union1.struct3.var_u8_h = 0xaa\" "\
+	    " -G \"arr[3]= 171\" "	\
+	    " -G \"arr[EA2] =172\" "	\
+	    " -G \"enum_arr[EC2]=EA3\" " \
+	    " -G \"three_d[31][7][EA2]=173\"" \
+	    " -G \"struct1[2].struct2[1][2].u.mat[5][3]=174\" " \
+	    " -G \"struct11 [ 7 ] [ 5 ] .struct2[0][1].u.mat[3][0] = 175\" " \
+	    " -vl2 > %s", fix->veristat, fix->tmpfile);
+
+	read(fix->fd, fix->output, fix->sz);
+	__CHECK_STR("=0xf000000000000001 ", "var_s64 = 0xf000000000000001");
+	__CHECK_STR("=0xfedcba9876543210 ", "var_u64 = 0xfedcba9876543210");
+	__CHECK_STR("=0x80000000 ", "var_s32 = -0x80000000");
+	__CHECK_STR("=0x76543210 ", "var_u32 = 0x76543210");
+	__CHECK_STR("=0x8000 ", "var_s16 = -32768");
+	__CHECK_STR("=0xecec ", "var_u16 = 60652");
+	__CHECK_STR("=128 ", "var_s8 = -128");
+	__CHECK_STR("=255 ", "var_u8 = 255");
+	__CHECK_STR("=11 ", "var_ea = EA2");
+	__CHECK_STR("=12 ", "var_eb = EB2");
+	__CHECK_STR("=13 ", "var_ec = EC2");
+	__CHECK_STR("=1 ", "var_b = 1");
+	__CHECK_STR("=170 ", "struct1[2].struct2[1][2].u.var_u8[2]=170");
+	__CHECK_STR("=0xaaaa ", "union1.var_u16 = 0xaaaa");
+	__CHECK_STR("=171 ", "arr[3]= 171");
+	__CHECK_STR("=172 ", "arr[EA2] =172");
+	__CHECK_STR("=10 ", "enum_arr[EC2]=EA3");
+	__CHECK_STR("=173 ", "matrix[31][7][11]=173");
+	__CHECK_STR("=174 ", "struct1[2].struct2[1][2].u.mat[5][3]=174");
+	__CHECK_STR("=175 ", "struct11[7][5].struct2[0][1].u.mat[3][0]=175");
+
+out:
+	teardown_fixture(fix);
+}
+
+static void test_set_global_vars_from_file_succeeds(void)
+{
+	struct fixture *fix = init_fixture();
+	char input_file[80];
+	const char *vars = "var_s16 = -32768\nvar_u16 = 60652";
+	int fd;
+
+	snprintf(input_file, sizeof(input_file), "/tmp/veristat_input.XXXXXX");
+	fd = mkstemp(input_file);
+	if (!ASSERT_GE(fd, 0, "valid fd"))
+		goto out;
+
+	write(fd, vars, strlen(vars));
+	syncfs(fd);
+	SYS(out, "%s set_global_vars.bpf.o -G \"@%s\" -vl2 > %s",
+	    fix->veristat, input_file, fix->tmpfile);
+	read(fix->fd, fix->output, fix->sz);
+	__CHECK_STR("=0x8000 ", "var_s16 = -32768");
+	__CHECK_STR("=0xecec ", "var_u16 = 60652");
+
+out:
+	close(fd);
+	remove(input_file);
+	teardown_fixture(fix);
+}
+
+static void test_set_global_vars_out_of_range(void)
+{
+	struct fixture *fix = init_fixture();
+
+	SYS_FAIL(out,
+		 "%s set_global_vars.bpf.o -G \"var_s32 = 2147483648\" -vl2 2> %s",
+		 fix->veristat, fix->tmpfile);
+
+	read(fix->fd, fix->output, fix->sz);
+	__CHECK_STR("is out of range [-2147483648; 2147483647]", "out of range");
+
+out:
+	teardown_fixture(fix);
+}
+
+static void test_unsupported_ptr_array_type(void)
+{
+	struct fixture *fix = init_fixture();
+
+	SYS_FAIL(out,
+		 "%s set_global_vars.bpf.o -G \"ptr_arr[0] = 0\" -vl2 2> %s",
+		 fix->veristat, fix->tmpfile);
+
+	read(fix->fd, fix->output, fix->sz);
+	__CHECK_STR("Can't set ptr_arr[0]. Only ints and enums are supported", "ptr_arr");
+
+out:
+	teardown_fixture(fix);
+}
+
+static void test_array_out_of_bounds(void)
+{
+	struct fixture *fix = init_fixture();
+
+	SYS_FAIL(out,
+		 "%s set_global_vars.bpf.o -G \"arr[99] = 0\" -vl2 2> %s",
+		 fix->veristat, fix->tmpfile);
+
+	read(fix->fd, fix->output, fix->sz);
+	__CHECK_STR("Array index 99 is out of bounds", "arr[99]");
+
+out:
+	teardown_fixture(fix);
+}
+
+static void test_array_index_not_found(void)
+{
+	struct fixture *fix = init_fixture();
+
+	SYS_FAIL(out,
+		 "%s set_global_vars.bpf.o -G \"arr[EG2] = 0\" -vl2 2> %s",
+		 fix->veristat, fix->tmpfile);
+
+	read(fix->fd, fix->output, fix->sz);
+	__CHECK_STR("Can't resolve enum value EG2", "arr[EG2]");
+
+out:
+	teardown_fixture(fix);
+}
+
+static void test_array_index_for_non_array(void)
+{
+	struct fixture *fix = init_fixture();
+
+	SYS_FAIL(out,
+		 "%s set_global_vars.bpf.o -G \"var_b[0] = 1\" -vl2 2> %s",
+		 fix->veristat, fix->tmpfile);
+
+	pread(fix->fd, fix->output, fix->sz, 0);
+	__CHECK_STR("Array index is not expected for var_b", "var_b[0] = 1");
+
+	SYS_FAIL(out,
+		 "%s set_global_vars.bpf.o -G \"union1.struct3[0].var_u8_l=1\" -vl2 2> %s",
+		 fix->veristat, fix->tmpfile);
+
+	pread(fix->fd, fix->output, fix->sz, 0);
+	__CHECK_STR("Array index is not expected for struct3", "union1.struct3[0].var_u8_l=1");
+
+out:
+	teardown_fixture(fix);
+}
+
+static void test_no_array_index_for_array(void)
+{
+	struct fixture *fix = init_fixture();
+
+	SYS_FAIL(out,
+		 "%s set_global_vars.bpf.o -G \"arr = 1\" -vl2 2> %s",
+		 fix->veristat, fix->tmpfile);
+
+	pread(fix->fd, fix->output, fix->sz, 0);
+	__CHECK_STR("Can't set arr. Only ints and enums are supported", "arr = 1");
+
+	SYS_FAIL(out,
+		 "%s set_global_vars.bpf.o -G \"struct1[0].struct2.u.var_u8[2]=1\" -vl2 2> %s",
+		 fix->veristat, fix->tmpfile);
+
+	pread(fix->fd, fix->output, fix->sz, 0);
+	__CHECK_STR("Can't resolve field u for non-composite type", "struct1[0].struct2.u.var_u8[2]=1");
+
+out:
+	teardown_fixture(fix);
+}
+
+void test_veristat(void)
+{
+	if (test__start_subtest("set_global_vars_succeeds"))
+		test_set_global_vars_succeeds();
+
+	if (test__start_subtest("set_global_vars_out_of_range"))
+		test_set_global_vars_out_of_range();
+
+	if (test__start_subtest("set_global_vars_from_file_succeeds"))
+		test_set_global_vars_from_file_succeeds();
+
+	if (test__start_subtest("test_unsupported_ptr_array_type"))
+		test_unsupported_ptr_array_type();
+
+	if (test__start_subtest("test_array_out_of_bounds"))
+		test_array_out_of_bounds();
+
+	if (test__start_subtest("test_array_index_not_found"))
+		test_array_index_not_found();
+
+	if (test__start_subtest("test_array_index_for_non_array"))
+		test_array_index_for_non_array();
+
+	if (test__start_subtest("test_no_array_index_for_array"))
+		test_no_array_index_for_array();
+
+}
+
+#undef __CHECK_STR
diff --git a/tools/testing/selftests/bpf/prog_tests/test_xdp_veth.c b/tools/testing/selftests/bpf/prog_tests/test_xdp_veth.c
new file mode 100644
index 000000000000..3e98a1665936
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_xdp_veth.c
@@ -0,0 +1,599 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Create 3 namespaces with 3 veth peers, and forward packets in-between using
+ * native XDP
+ *
+ * Network topology:
+ *  ----------        ----------       ----------
+ *  |  NS1   |        |  NS2   |       |  NS3   |
+ *  | veth11 |        | veth22 |       | veth33 |
+ *  ----|-----        -----|----       -----|----
+ *      |                  |                |
+ *  ----|------------------|----------------|----
+ *  | veth1              veth2            veth3 |
+ *  |                                           |
+ *  |                     NSO                   |
+ *  ---------------------------------------------
+ *
+ * Test cases:
+ *  - [test_xdp_veth_redirect] : ping veth33 from veth11
+ *
+ *    veth11             veth22              veth33
+ *  (XDP_PASS)          (XDP_TX)           (XDP_PASS)
+ *       |                  |                  |
+ *       |                  |                  |
+ *     veth1             veth2              veth3
+ * (XDP_REDIRECT)     (XDP_REDIRECT)     (XDP_REDIRECT)
+ *      ^ |                ^ |                ^ |
+ *      | |                | |                | |
+ *      | ------------------ ------------------ |
+ *      -----------------------------------------
+ *
+ * - [test_xdp_veth_broadcast_redirect]: broadcast from veth11
+ *     - IPv4 ping : BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS
+ *          -> echo request received by all except veth11
+ *     - IPv4 ping : BPF_F_BROADCAST
+ *          -> echo request received by all veth
+ * - [test_xdp_veth_egress]:
+ *     - all src mac should be the magic mac
+ *
+ *    veth11             veth22              veth33
+ *  (XDP_PASS)         (XDP_PASS)          (XDP_PASS)
+ *       |                  |                  |
+ *       |                  |                  |
+ *     veth1		  veth2              veth3
+ * (XDP_REDIRECT)     (XDP_REDIRECT)     (XDP_REDIRECT)
+ *      |                   ^                  ^
+ *      |                   |                  |
+ *      ----------------------------------------
+ *
+ */
+
+#define _GNU_SOURCE
+#include <net/if.h>
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "xdp_dummy.skel.h"
+#include "xdp_redirect_map.skel.h"
+#include "xdp_redirect_multi_kern.skel.h"
+#include "xdp_tx.skel.h"
+#include <uapi/linux/if_link.h>
+
+#define VETH_PAIRS_COUNT	3
+#define VETH_NAME_MAX_LEN	32
+#define IP_MAX_LEN		16
+#define IP_SRC				"10.1.1.11"
+#define IP_DST				"10.1.1.33"
+#define IP_NEIGH			"10.1.1.253"
+#define PROG_NAME_MAX_LEN	128
+#define NS_NAME_MAX_LEN		32
+
+struct veth_configuration {
+	char local_veth[VETH_NAME_MAX_LEN]; /* Interface in main namespace */
+	char remote_veth[VETH_NAME_MAX_LEN]; /* Peer interface in dedicated namespace*/
+	char namespace[NS_NAME_MAX_LEN]; /* Namespace for the remote veth */
+	int next_veth; /* Local interface to redirect traffic to */
+	char remote_addr[IP_MAX_LEN]; /* IP address of the remote veth */
+};
+
+struct net_configuration {
+	char ns0_name[NS_NAME_MAX_LEN];
+	struct veth_configuration veth_cfg[VETH_PAIRS_COUNT];
+};
+
+static const struct net_configuration default_config = {
+	.ns0_name = "ns0-",
+	{
+		{
+			.local_veth = "veth1-",
+			.remote_veth = "veth11",
+			.next_veth = 1,
+			.remote_addr = IP_SRC,
+			.namespace = "ns-veth11-"
+		},
+		{
+			.local_veth = "veth2-",
+			.remote_veth = "veth22",
+			.next_veth = 2,
+			.remote_addr = "",
+			.namespace = "ns-veth22-"
+		},
+		{
+			.local_veth = "veth3-",
+			.remote_veth = "veth33",
+			.next_veth = 0,
+			.remote_addr = IP_DST,
+			.namespace = "ns-veth33-"
+		}
+	}
+};
+
+struct prog_configuration {
+	char local_name[PROG_NAME_MAX_LEN]; /* BPF prog to attach to local_veth */
+	char remote_name[PROG_NAME_MAX_LEN]; /* BPF prog to attach to remote_veth */
+	u32 local_flags; /* XDP flags to use on local_veth */
+	u32 remote_flags; /* XDP flags to use on remote_veth */
+};
+
+static int attach_programs_to_veth_pair(struct bpf_object **objs, size_t nb_obj,
+					struct net_configuration *net_config,
+					struct prog_configuration *prog, int index)
+{
+	struct bpf_program *local_prog, *remote_prog;
+	struct nstoken *nstoken;
+	int interface, ret, i;
+
+	for (i = 0; i < nb_obj; i++) {
+		local_prog = bpf_object__find_program_by_name(objs[i], prog[index].local_name);
+		if (local_prog)
+			break;
+	}
+	if (!ASSERT_OK_PTR(local_prog, "find local program"))
+		return -1;
+
+	for (i = 0; i < nb_obj; i++) {
+		remote_prog = bpf_object__find_program_by_name(objs[i], prog[index].remote_name);
+		if (remote_prog)
+			break;
+	}
+	if (!ASSERT_OK_PTR(remote_prog, "find remote program"))
+		return -1;
+
+	interface = if_nametoindex(net_config->veth_cfg[index].local_veth);
+	if (!ASSERT_NEQ(interface, 0, "non zero interface index"))
+		return -1;
+
+	ret = bpf_xdp_attach(interface, bpf_program__fd(local_prog),
+			     prog[index].local_flags, NULL);
+	if (!ASSERT_OK(ret, "attach xdp program to local veth"))
+		return -1;
+
+	nstoken = open_netns(net_config->veth_cfg[index].namespace);
+	if (!ASSERT_OK_PTR(nstoken, "switch to remote veth namespace"))
+		return -1;
+
+	interface = if_nametoindex(net_config->veth_cfg[index].remote_veth);
+	if (!ASSERT_NEQ(interface, 0, "non zero interface index")) {
+		close_netns(nstoken);
+		return -1;
+	}
+
+	ret = bpf_xdp_attach(interface, bpf_program__fd(remote_prog),
+			     prog[index].remote_flags, NULL);
+	if (!ASSERT_OK(ret, "attach xdp program to remote veth")) {
+		close_netns(nstoken);
+		return -1;
+	}
+
+	close_netns(nstoken);
+	return 0;
+}
+
+static int create_network(struct net_configuration *net_config)
+{
+	struct nstoken *nstoken = NULL;
+	int i, err;
+
+	memcpy(net_config, &default_config, sizeof(struct net_configuration));
+
+	/* Create unique namespaces */
+	err = append_tid(net_config->ns0_name, NS_NAME_MAX_LEN);
+	if (!ASSERT_OK(err, "append TID to ns0 name"))
+		goto fail;
+	SYS(fail, "ip netns add %s", net_config->ns0_name);
+
+	for (i = 0; i < VETH_PAIRS_COUNT; i++) {
+		err = append_tid(net_config->veth_cfg[i].namespace, NS_NAME_MAX_LEN);
+		if (!ASSERT_OK(err, "append TID to ns name"))
+			goto fail;
+		SYS(fail, "ip netns add %s", net_config->veth_cfg[i].namespace);
+	}
+
+	/* Create interfaces */
+	nstoken = open_netns(net_config->ns0_name);
+	if (!nstoken)
+		goto fail;
+
+	for (i = 0; i < VETH_PAIRS_COUNT; i++) {
+		SYS(fail, "ip link add %s type veth peer name %s netns %s",
+		    net_config->veth_cfg[i].local_veth, net_config->veth_cfg[i].remote_veth,
+		    net_config->veth_cfg[i].namespace);
+		SYS(fail, "ip link set dev %s up", net_config->veth_cfg[i].local_veth);
+		if (net_config->veth_cfg[i].remote_addr[0])
+			SYS(fail, "ip -n %s addr add %s/24 dev %s",
+			    net_config->veth_cfg[i].namespace,
+			    net_config->veth_cfg[i].remote_addr,
+			    net_config->veth_cfg[i].remote_veth);
+		SYS(fail, "ip -n %s link set dev %s up", net_config->veth_cfg[i].namespace,
+		    net_config->veth_cfg[i].remote_veth);
+	}
+
+	close_netns(nstoken);
+	return 0;
+
+fail:
+	close_netns(nstoken);
+	return -1;
+}
+
+static void cleanup_network(struct net_configuration *net_config)
+{
+	int i;
+
+	SYS_NOFAIL("ip netns del %s", net_config->ns0_name);
+	for (i = 0; i < VETH_PAIRS_COUNT; i++)
+		SYS_NOFAIL("ip netns del %s", net_config->veth_cfg[i].namespace);
+}
+
+#define VETH_REDIRECT_SKEL_NB	3
+static void xdp_veth_redirect(u32 flags)
+{
+	struct prog_configuration ping_config[VETH_PAIRS_COUNT] = {
+		{
+			.local_name = "xdp_redirect_map_0",
+			.remote_name = "xdp_dummy_prog",
+			.local_flags = flags,
+			.remote_flags = flags,
+		},
+		{
+			.local_name = "xdp_redirect_map_1",
+			.remote_name = "xdp_tx",
+			.local_flags = flags,
+			.remote_flags = flags,
+		},
+		{
+			.local_name = "xdp_redirect_map_2",
+			.remote_name = "xdp_dummy_prog",
+			.local_flags = flags,
+			.remote_flags = flags,
+		}
+	};
+	struct bpf_object *bpf_objs[VETH_REDIRECT_SKEL_NB];
+	struct xdp_redirect_map *xdp_redirect_map;
+	struct net_configuration net_config;
+	struct nstoken *nstoken = NULL;
+	struct xdp_dummy *xdp_dummy;
+	struct xdp_tx *xdp_tx;
+	int map_fd;
+	int i;
+
+	xdp_dummy = xdp_dummy__open_and_load();
+	if (!ASSERT_OK_PTR(xdp_dummy, "xdp_dummy__open_and_load"))
+		return;
+
+	xdp_tx = xdp_tx__open_and_load();
+	if (!ASSERT_OK_PTR(xdp_tx, "xdp_tx__open_and_load"))
+		goto destroy_xdp_dummy;
+
+	xdp_redirect_map = xdp_redirect_map__open_and_load();
+	if (!ASSERT_OK_PTR(xdp_redirect_map, "xdp_redirect_map__open_and_load"))
+		goto destroy_xdp_tx;
+
+	if (!ASSERT_OK(create_network(&net_config), "create network"))
+		goto destroy_xdp_redirect_map;
+
+	/* Then configure the redirect map and attach programs to interfaces */
+	map_fd = bpf_map__fd(xdp_redirect_map->maps.tx_port);
+	if (!ASSERT_OK_FD(map_fd, "open redirect map"))
+		goto destroy_xdp_redirect_map;
+
+	bpf_objs[0] = xdp_dummy->obj;
+	bpf_objs[1] = xdp_tx->obj;
+	bpf_objs[2] = xdp_redirect_map->obj;
+
+	nstoken = open_netns(net_config.ns0_name);
+	if (!ASSERT_OK_PTR(nstoken, "open NS0"))
+		goto destroy_xdp_redirect_map;
+
+	for (i = 0; i < VETH_PAIRS_COUNT; i++) {
+		int next_veth = net_config.veth_cfg[i].next_veth;
+		int interface_id;
+		int err;
+
+		interface_id = if_nametoindex(net_config.veth_cfg[next_veth].local_veth);
+		if (!ASSERT_NEQ(interface_id, 0, "non zero interface index"))
+			goto destroy_xdp_redirect_map;
+		err = bpf_map_update_elem(map_fd, &i, &interface_id, BPF_ANY);
+		if (!ASSERT_OK(err, "configure interface redirection through map"))
+			goto destroy_xdp_redirect_map;
+		if (attach_programs_to_veth_pair(bpf_objs, VETH_REDIRECT_SKEL_NB,
+						 &net_config, ping_config, i))
+			goto destroy_xdp_redirect_map;
+	}
+
+	/* Test: if all interfaces are properly configured, we must be able to ping
+	 * veth33 from veth11
+	 */
+	ASSERT_OK(SYS_NOFAIL("ip netns exec %s ping -c 1 -W 1 %s > /dev/null",
+			     net_config.veth_cfg[0].namespace, IP_DST), "ping");
+
+destroy_xdp_redirect_map:
+	close_netns(nstoken);
+	xdp_redirect_map__destroy(xdp_redirect_map);
+destroy_xdp_tx:
+	xdp_tx__destroy(xdp_tx);
+destroy_xdp_dummy:
+	xdp_dummy__destroy(xdp_dummy);
+
+	cleanup_network(&net_config);
+}
+
+#define BROADCAST_REDIRECT_SKEL_NB	2
+static void xdp_veth_broadcast_redirect(u32 attach_flags, u64 redirect_flags)
+{
+	struct prog_configuration prog_cfg[VETH_PAIRS_COUNT] = {
+		{
+			.local_name = "xdp_redirect_map_multi_prog",
+			.remote_name = "xdp_count_0",
+			.local_flags = attach_flags,
+			.remote_flags = attach_flags,
+		},
+		{
+			.local_name = "xdp_redirect_map_multi_prog",
+			.remote_name = "xdp_count_1",
+			.local_flags = attach_flags,
+			.remote_flags = attach_flags,
+		},
+		{
+			.local_name = "xdp_redirect_map_multi_prog",
+			.remote_name = "xdp_count_2",
+			.local_flags = attach_flags,
+			.remote_flags = attach_flags,
+		}
+	};
+	struct bpf_object *bpf_objs[BROADCAST_REDIRECT_SKEL_NB];
+	struct xdp_redirect_multi_kern *xdp_redirect_multi_kern;
+	struct xdp_redirect_map *xdp_redirect_map;
+	struct bpf_devmap_val devmap_val = {};
+	struct net_configuration net_config;
+	struct nstoken *nstoken = NULL;
+	u16 protocol = ETH_P_IP;
+	int group_map;
+	int flags_map;
+	int cnt_map;
+	u64 cnt = 0;
+	int i, err;
+
+	xdp_redirect_multi_kern = xdp_redirect_multi_kern__open_and_load();
+	if (!ASSERT_OK_PTR(xdp_redirect_multi_kern, "xdp_redirect_multi_kern__open_and_load"))
+		return;
+
+	xdp_redirect_map = xdp_redirect_map__open_and_load();
+	if (!ASSERT_OK_PTR(xdp_redirect_map, "xdp_redirect_map__open_and_load"))
+		goto destroy_xdp_redirect_multi_kern;
+
+	if (!ASSERT_OK(create_network(&net_config), "create network"))
+		goto destroy_xdp_redirect_map;
+
+	group_map = bpf_map__fd(xdp_redirect_multi_kern->maps.map_all);
+	if (!ASSERT_OK_FD(group_map, "open map_all"))
+		goto destroy_xdp_redirect_map;
+
+	flags_map = bpf_map__fd(xdp_redirect_multi_kern->maps.redirect_flags);
+	if (!ASSERT_OK_FD(group_map, "open map_all"))
+		goto destroy_xdp_redirect_map;
+
+	err = bpf_map_update_elem(flags_map, &protocol, &redirect_flags, BPF_NOEXIST);
+	if (!ASSERT_OK(err, "init IP count"))
+		goto destroy_xdp_redirect_map;
+
+	cnt_map = bpf_map__fd(xdp_redirect_map->maps.rxcnt);
+	if (!ASSERT_OK_FD(cnt_map, "open rxcnt map"))
+		goto destroy_xdp_redirect_map;
+
+	bpf_objs[0] = xdp_redirect_multi_kern->obj;
+	bpf_objs[1] = xdp_redirect_map->obj;
+
+	nstoken = open_netns(net_config.ns0_name);
+	if (!ASSERT_OK_PTR(nstoken, "open NS0"))
+		goto destroy_xdp_redirect_map;
+
+	for (i = 0; i < VETH_PAIRS_COUNT; i++) {
+		int ifindex = if_nametoindex(net_config.veth_cfg[i].local_veth);
+
+		if (attach_programs_to_veth_pair(bpf_objs, BROADCAST_REDIRECT_SKEL_NB,
+						 &net_config, prog_cfg, i))
+			goto destroy_xdp_redirect_map;
+
+		SYS(destroy_xdp_redirect_map,
+		    "ip -n %s neigh add %s lladdr 00:00:00:00:00:01 dev %s",
+		    net_config.veth_cfg[i].namespace, IP_NEIGH, net_config.veth_cfg[i].remote_veth);
+
+		devmap_val.ifindex = ifindex;
+		err = bpf_map_update_elem(group_map, &ifindex, &devmap_val, 0);
+		if (!ASSERT_OK(err, "bpf_map_update_elem"))
+			goto destroy_xdp_redirect_map;
+
+	}
+
+	SYS_NOFAIL("ip netns exec %s ping %s -i 0.1 -c 4 -W1 > /dev/null ",
+		    net_config.veth_cfg[0].namespace, IP_NEIGH);
+
+	for (i = 0; i < VETH_PAIRS_COUNT; i++) {
+		err =  bpf_map_lookup_elem(cnt_map, &i, &cnt);
+		if (!ASSERT_OK(err, "get IP cnt"))
+			goto destroy_xdp_redirect_map;
+
+		if (redirect_flags & BPF_F_EXCLUDE_INGRESS)
+			/* veth11 shouldn't receive the ICMP requests;
+			 * others should
+			 */
+			ASSERT_EQ(cnt, i ? 4 : 0, "compare IP cnt");
+		else
+			/* All remote veth should receive the ICMP requests */
+			ASSERT_EQ(cnt, 4, "compare IP cnt");
+	}
+
+destroy_xdp_redirect_map:
+	close_netns(nstoken);
+	xdp_redirect_map__destroy(xdp_redirect_map);
+destroy_xdp_redirect_multi_kern:
+	xdp_redirect_multi_kern__destroy(xdp_redirect_multi_kern);
+
+	cleanup_network(&net_config);
+}
+
+#define VETH_EGRESS_SKEL_NB	3
+static void xdp_veth_egress(u32 flags)
+{
+	struct prog_configuration prog_cfg[VETH_PAIRS_COUNT] = {
+		{
+			.local_name = "xdp_redirect_map_all_prog",
+			.remote_name = "xdp_dummy_prog",
+			.local_flags = flags,
+			.remote_flags = flags,
+		},
+		{
+			.local_name = "xdp_redirect_map_all_prog",
+			.remote_name = "store_mac_1",
+			.local_flags = flags,
+			.remote_flags = flags,
+		},
+		{
+			.local_name = "xdp_redirect_map_all_prog",
+			.remote_name = "store_mac_2",
+			.local_flags = flags,
+			.remote_flags = flags,
+		}
+	};
+	const char magic_mac[6] = { 0xAA, 0xBB, 0xCC, 0xDD, 0xEE, 0xFF};
+	struct xdp_redirect_multi_kern *xdp_redirect_multi_kern;
+	struct bpf_object *bpf_objs[VETH_EGRESS_SKEL_NB];
+	struct xdp_redirect_map *xdp_redirect_map;
+	struct bpf_devmap_val devmap_val = {};
+	struct net_configuration net_config;
+	int mac_map, egress_map, res_map;
+	struct nstoken *nstoken = NULL;
+	struct xdp_dummy *xdp_dummy;
+	int err;
+	int i;
+
+	xdp_dummy = xdp_dummy__open_and_load();
+	if (!ASSERT_OK_PTR(xdp_dummy, "xdp_dummy__open_and_load"))
+		return;
+
+	xdp_redirect_multi_kern = xdp_redirect_multi_kern__open_and_load();
+	if (!ASSERT_OK_PTR(xdp_redirect_multi_kern, "xdp_redirect_multi_kern__open_and_load"))
+		goto destroy_xdp_dummy;
+
+	xdp_redirect_map = xdp_redirect_map__open_and_load();
+	if (!ASSERT_OK_PTR(xdp_redirect_map, "xdp_redirect_map__open_and_load"))
+		goto destroy_xdp_redirect_multi_kern;
+
+	if (!ASSERT_OK(create_network(&net_config), "create network"))
+		goto destroy_xdp_redirect_map;
+
+	mac_map = bpf_map__fd(xdp_redirect_multi_kern->maps.mac_map);
+	if (!ASSERT_OK_FD(mac_map, "open mac_map"))
+		goto destroy_xdp_redirect_map;
+
+	egress_map = bpf_map__fd(xdp_redirect_multi_kern->maps.map_egress);
+	if (!ASSERT_OK_FD(egress_map, "open map_egress"))
+		goto destroy_xdp_redirect_map;
+
+	devmap_val.bpf_prog.fd = bpf_program__fd(xdp_redirect_multi_kern->progs.xdp_devmap_prog);
+
+	bpf_objs[0] = xdp_dummy->obj;
+	bpf_objs[1] = xdp_redirect_multi_kern->obj;
+	bpf_objs[2] = xdp_redirect_map->obj;
+
+	nstoken = open_netns(net_config.ns0_name);
+	if (!ASSERT_OK_PTR(nstoken, "open NS0"))
+		goto destroy_xdp_redirect_map;
+
+	for (i = 0; i < VETH_PAIRS_COUNT; i++) {
+		int ifindex = if_nametoindex(net_config.veth_cfg[i].local_veth);
+
+		SYS(destroy_xdp_redirect_map,
+		    "ip -n %s neigh add %s lladdr 00:00:00:00:00:01 dev %s",
+		    net_config.veth_cfg[i].namespace, IP_NEIGH, net_config.veth_cfg[i].remote_veth);
+
+		if (attach_programs_to_veth_pair(bpf_objs, VETH_REDIRECT_SKEL_NB,
+						 &net_config, prog_cfg, i))
+			goto destroy_xdp_redirect_map;
+
+		err = bpf_map_update_elem(mac_map, &ifindex, magic_mac, 0);
+		if (!ASSERT_OK(err, "bpf_map_update_elem"))
+			goto destroy_xdp_redirect_map;
+
+		devmap_val.ifindex = ifindex;
+		err = bpf_map_update_elem(egress_map, &ifindex, &devmap_val, 0);
+		if (!ASSERT_OK(err, "bpf_map_update_elem"))
+			goto destroy_xdp_redirect_map;
+	}
+
+	SYS_NOFAIL("ip netns exec %s ping %s -i 0.1 -c 4 -W1 > /dev/null ",
+		    net_config.veth_cfg[0].namespace, IP_NEIGH);
+
+	res_map = bpf_map__fd(xdp_redirect_map->maps.rx_mac);
+	if (!ASSERT_OK_FD(res_map, "open rx_map"))
+		goto destroy_xdp_redirect_map;
+
+	for (i = 0; i < 2; i++) {
+		u32 key = i;
+		u64 res;
+
+		err = bpf_map_lookup_elem(res_map, &key, &res);
+		if (!ASSERT_OK(err, "get MAC res"))
+			goto destroy_xdp_redirect_map;
+
+		ASSERT_STRNEQ((const char *)&res, magic_mac, ETH_ALEN, "compare mac");
+	}
+
+destroy_xdp_redirect_map:
+	close_netns(nstoken);
+	xdp_redirect_map__destroy(xdp_redirect_map);
+destroy_xdp_redirect_multi_kern:
+	xdp_redirect_multi_kern__destroy(xdp_redirect_multi_kern);
+destroy_xdp_dummy:
+	xdp_dummy__destroy(xdp_dummy);
+
+	cleanup_network(&net_config);
+}
+
+void test_xdp_veth_redirect(void)
+{
+	if (test__start_subtest("0"))
+		xdp_veth_redirect(0);
+
+	if (test__start_subtest("DRV_MODE"))
+		xdp_veth_redirect(XDP_FLAGS_DRV_MODE);
+
+	if (test__start_subtest("SKB_MODE"))
+		xdp_veth_redirect(XDP_FLAGS_SKB_MODE);
+}
+
+void test_xdp_veth_broadcast_redirect(void)
+{
+	if (test__start_subtest("0/BROADCAST"))
+		xdp_veth_broadcast_redirect(0, BPF_F_BROADCAST);
+
+	if (test__start_subtest("0/(BROADCAST | EXCLUDE_INGRESS)"))
+		xdp_veth_broadcast_redirect(0, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS);
+
+	if (test__start_subtest("DRV_MODE/BROADCAST"))
+		xdp_veth_broadcast_redirect(XDP_FLAGS_DRV_MODE, BPF_F_BROADCAST);
+
+	if (test__start_subtest("DRV_MODE/(BROADCAST | EXCLUDE_INGRESS)"))
+		xdp_veth_broadcast_redirect(XDP_FLAGS_DRV_MODE,
+					    BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS);
+
+	if (test__start_subtest("SKB_MODE/BROADCAST"))
+		xdp_veth_broadcast_redirect(XDP_FLAGS_SKB_MODE, BPF_F_BROADCAST);
+
+	if (test__start_subtest("SKB_MODE/(BROADCAST | EXCLUDE_INGRESS)"))
+		xdp_veth_broadcast_redirect(XDP_FLAGS_SKB_MODE,
+					    BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS);
+}
+
+void test_xdp_veth_egress(void)
+{
+	if (test__start_subtest("0/egress"))
+		xdp_veth_egress(0);
+
+	if (test__start_subtest("DRV_MODE/egress"))
+		xdp_veth_egress(XDP_FLAGS_DRV_MODE);
+
+	if (test__start_subtest("SKB_MODE/egress"))
+		xdp_veth_egress(XDP_FLAGS_SKB_MODE);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_xsk.c b/tools/testing/selftests/bpf/prog_tests/test_xsk.c
new file mode 100644
index 000000000000..5af28f359cfd
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_xsk.c
@@ -0,0 +1,2596 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <bpf/bpf.h>
+#include <errno.h>
+#include <linux/bitmap.h>
+#include <linux/if_link.h>
+#include <linux/mman.h>
+#include <linux/netdev.h>
+#include <poll.h>
+#include <pthread.h>
+#include <signal.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <unistd.h>
+
+#include "network_helpers.h"
+#include "test_xsk.h"
+#include "xsk_xdp_common.h"
+#include "xsk_xdp_progs.skel.h"
+
+#define DEFAULT_BATCH_SIZE		64
+#define MIN_PKT_SIZE			64
+#define MAX_ETH_JUMBO_SIZE		9000
+#define MAX_INTERFACES			2
+#define MAX_TEARDOWN_ITER		10
+#define MAX_TX_BUDGET_DEFAULT		32
+#define PKT_DUMP_NB_TO_PRINT		16
+/* Just to align the data in the packet */
+#define PKT_HDR_SIZE			(sizeof(struct ethhdr) + 2)
+#define POLL_TMOUT			1000
+#define THREAD_TMOUT			3
+#define UMEM_HEADROOM_TEST_SIZE		128
+#define XSK_DESC__INVALID_OPTION	(0xffff)
+#define XSK_UMEM__INVALID_FRAME_SIZE	(MAX_ETH_JUMBO_SIZE + 1)
+#define XSK_UMEM__LARGE_FRAME_SIZE	(3 * 1024)
+#define XSK_UMEM__MAX_FRAME_SIZE	(4 * 1024)
+
+static const u8 g_mac[ETH_ALEN] = {0x55, 0x44, 0x33, 0x22, 0x11, 0x00};
+
+bool opt_verbose;
+pthread_barrier_t barr;
+pthread_mutex_t pacing_mutex = PTHREAD_MUTEX_INITIALIZER;
+
+int pkts_in_flight;
+
+/* The payload is a word consisting of a packet sequence number in the upper
+ * 16-bits and a intra packet data sequence number in the lower 16 bits. So the 3rd packet's
+ * 5th word of data will contain the number (2<<16) | 4 as they are numbered from 0.
+ */
+static void write_payload(void *dest, u32 pkt_nb, u32 start, u32 size)
+{
+	u32 *ptr = (u32 *)dest, i;
+
+	start /= sizeof(*ptr);
+	size /= sizeof(*ptr);
+	for (i = 0; i < size; i++)
+		ptr[i] = htonl(pkt_nb << 16 | (i + start));
+}
+
+static void gen_eth_hdr(struct xsk_socket_info *xsk, struct ethhdr *eth_hdr)
+{
+	memcpy(eth_hdr->h_dest, xsk->dst_mac, ETH_ALEN);
+	memcpy(eth_hdr->h_source, xsk->src_mac, ETH_ALEN);
+	eth_hdr->h_proto = htons(ETH_P_LOOPBACK);
+}
+
+static bool is_umem_valid(struct ifobject *ifobj)
+{
+	return !!ifobj->umem->umem;
+}
+
+static u32 mode_to_xdp_flags(enum test_mode mode)
+{
+	return (mode == TEST_MODE_SKB) ? XDP_FLAGS_SKB_MODE : XDP_FLAGS_DRV_MODE;
+}
+
+static u64 umem_size(struct xsk_umem_info *umem)
+{
+	return umem->num_frames * umem->frame_size;
+}
+
+int xsk_configure_umem(struct ifobject *ifobj, struct xsk_umem_info *umem, void *buffer,
+			      u64 size)
+{
+	struct xsk_umem_config cfg = {
+		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
+		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
+		.frame_size = umem->frame_size,
+		.frame_headroom = umem->frame_headroom,
+		.flags = XSK_UMEM__DEFAULT_FLAGS
+	};
+	int ret;
+
+	if (umem->fill_size)
+		cfg.fill_size = umem->fill_size;
+
+	if (umem->comp_size)
+		cfg.comp_size = umem->comp_size;
+
+	if (umem->unaligned_mode)
+		cfg.flags |= XDP_UMEM_UNALIGNED_CHUNK_FLAG;
+
+	ret = xsk_umem__create(&umem->umem, buffer, size,
+			       &umem->fq, &umem->cq, &cfg);
+	if (ret)
+		return ret;
+
+	umem->buffer = buffer;
+	if (ifobj->shared_umem && ifobj->rx_on) {
+		umem->base_addr = umem_size(umem);
+		umem->next_buffer = umem_size(umem);
+	}
+
+	return 0;
+}
+
+static u64 umem_alloc_buffer(struct xsk_umem_info *umem)
+{
+	u64 addr;
+
+	addr = umem->next_buffer;
+	umem->next_buffer += umem->frame_size;
+	if (umem->next_buffer >= umem->base_addr + umem_size(umem))
+		umem->next_buffer = umem->base_addr;
+
+	return addr;
+}
+
+static void umem_reset_alloc(struct xsk_umem_info *umem)
+{
+	umem->next_buffer = 0;
+}
+
+static int enable_busy_poll(struct xsk_socket_info *xsk)
+{
+	int sock_opt;
+
+	sock_opt = 1;
+	if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_PREFER_BUSY_POLL,
+		       (void *)&sock_opt, sizeof(sock_opt)) < 0)
+		return -errno;
+
+	sock_opt = 20;
+	if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_BUSY_POLL,
+		       (void *)&sock_opt, sizeof(sock_opt)) < 0)
+		return -errno;
+
+	sock_opt = xsk->batch_size;
+	if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_BUSY_POLL_BUDGET,
+		       (void *)&sock_opt, sizeof(sock_opt)) < 0)
+		return -errno;
+
+	return 0;
+}
+
+int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem,
+				  struct ifobject *ifobject, bool shared)
+{
+	struct xsk_socket_config cfg = {};
+	struct xsk_ring_cons *rxr;
+	struct xsk_ring_prod *txr;
+
+	xsk->umem = umem;
+	cfg.rx_size = xsk->rxqsize;
+	cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
+	cfg.bind_flags = ifobject->bind_flags;
+	if (shared)
+		cfg.bind_flags |= XDP_SHARED_UMEM;
+	if (ifobject->mtu > MAX_ETH_PKT_SIZE)
+		cfg.bind_flags |= XDP_USE_SG;
+	if (umem->comp_size)
+		cfg.tx_size = umem->comp_size;
+	if (umem->fill_size)
+		cfg.rx_size = umem->fill_size;
+
+	txr = ifobject->tx_on ? &xsk->tx : NULL;
+	rxr = ifobject->rx_on ? &xsk->rx : NULL;
+	return xsk_socket__create(&xsk->xsk, ifobject->ifindex, 0, umem->umem, rxr, txr, &cfg);
+}
+
+#define MAX_SKB_FRAGS_PATH "/proc/sys/net/core/max_skb_frags"
+static unsigned int get_max_skb_frags(void)
+{
+	unsigned int max_skb_frags = 0;
+	FILE *file;
+
+	file = fopen(MAX_SKB_FRAGS_PATH, "r");
+	if (!file) {
+		ksft_print_msg("Error opening %s\n", MAX_SKB_FRAGS_PATH);
+		return 0;
+	}
+
+	if (fscanf(file, "%u", &max_skb_frags) != 1)
+		ksft_print_msg("Error reading %s\n", MAX_SKB_FRAGS_PATH);
+
+	fclose(file);
+	return max_skb_frags;
+}
+
+static int set_ring_size(struct ifobject *ifobj)
+{
+	int ret;
+	u32 ctr = 0;
+
+	while (ctr++ < SOCK_RECONF_CTR) {
+		ret = set_hw_ring_size(ifobj->ifname, &ifobj->ring);
+		if (!ret)
+			break;
+
+		/* Retry if it fails */
+		if (ctr >= SOCK_RECONF_CTR || errno != EBUSY)
+			return -errno;
+
+		usleep(USLEEP_MAX);
+	}
+
+	return ret;
+}
+
+int hw_ring_size_reset(struct ifobject *ifobj)
+{
+	ifobj->ring.tx_pending = ifobj->set_ring.default_tx;
+	ifobj->ring.rx_pending = ifobj->set_ring.default_rx;
+	return set_ring_size(ifobj);
+}
+
+static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
+			     struct ifobject *ifobj_rx)
+{
+	u32 i, j;
+
+	for (i = 0; i < MAX_INTERFACES; i++) {
+		struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx;
+
+		ifobj->xsk = &ifobj->xsk_arr[0];
+		ifobj->use_poll = false;
+		ifobj->use_fill_ring = true;
+		ifobj->release_rx = true;
+		ifobj->validation_func = NULL;
+		ifobj->use_metadata = false;
+
+		if (i == 0) {
+			ifobj->rx_on = false;
+			ifobj->tx_on = true;
+		} else {
+			ifobj->rx_on = true;
+			ifobj->tx_on = false;
+		}
+
+		memset(ifobj->umem, 0, sizeof(*ifobj->umem));
+		ifobj->umem->num_frames = DEFAULT_UMEM_BUFFERS;
+		ifobj->umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
+
+		for (j = 0; j < MAX_SOCKETS; j++) {
+			memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j]));
+			ifobj->xsk_arr[j].rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
+			ifobj->xsk_arr[j].batch_size = DEFAULT_BATCH_SIZE;
+			if (i == 0)
+				ifobj->xsk_arr[j].pkt_stream = test->tx_pkt_stream_default;
+			else
+				ifobj->xsk_arr[j].pkt_stream = test->rx_pkt_stream_default;
+
+			memcpy(ifobj->xsk_arr[j].src_mac, g_mac, ETH_ALEN);
+			memcpy(ifobj->xsk_arr[j].dst_mac, g_mac, ETH_ALEN);
+			ifobj->xsk_arr[j].src_mac[5] += ((j * 2) + 0);
+			ifobj->xsk_arr[j].dst_mac[5] += ((j * 2) + 1);
+		}
+	}
+
+	if (ifobj_tx->hw_ring_size_supp)
+		hw_ring_size_reset(ifobj_tx);
+
+	test->ifobj_tx = ifobj_tx;
+	test->ifobj_rx = ifobj_rx;
+	test->current_step = 0;
+	test->total_steps = 1;
+	test->nb_sockets = 1;
+	test->fail = false;
+	test->set_ring = false;
+	test->adjust_tail = false;
+	test->adjust_tail_support = false;
+	test->mtu = MAX_ETH_PKT_SIZE;
+	test->xdp_prog_rx = ifobj_rx->xdp_progs->progs.xsk_def_prog;
+	test->xskmap_rx = ifobj_rx->xdp_progs->maps.xsk;
+	test->xdp_prog_tx = ifobj_tx->xdp_progs->progs.xsk_def_prog;
+	test->xskmap_tx = ifobj_tx->xdp_progs->maps.xsk;
+}
+
+void test_init(struct test_spec *test, struct ifobject *ifobj_tx,
+			   struct ifobject *ifobj_rx, enum test_mode mode,
+			   const struct test_spec *test_to_run)
+{
+	struct pkt_stream *tx_pkt_stream;
+	struct pkt_stream *rx_pkt_stream;
+	u32 i;
+
+	tx_pkt_stream = test->tx_pkt_stream_default;
+	rx_pkt_stream = test->rx_pkt_stream_default;
+	memset(test, 0, sizeof(*test));
+	test->tx_pkt_stream_default = tx_pkt_stream;
+	test->rx_pkt_stream_default = rx_pkt_stream;
+
+	for (i = 0; i < MAX_INTERFACES; i++) {
+		struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx;
+
+		ifobj->bind_flags = XDP_USE_NEED_WAKEUP;
+		if (mode == TEST_MODE_ZC)
+			ifobj->bind_flags |= XDP_ZEROCOPY;
+		else
+			ifobj->bind_flags |= XDP_COPY;
+	}
+
+	memcpy(test->name, test_to_run->name, MAX_TEST_NAME_SIZE);
+	test->test_func = test_to_run->test_func;
+	test->mode = mode;
+	__test_spec_init(test, ifobj_tx, ifobj_rx);
+}
+
+static void test_spec_reset(struct test_spec *test)
+{
+	__test_spec_init(test, test->ifobj_tx, test->ifobj_rx);
+}
+
+static void test_spec_set_xdp_prog(struct test_spec *test, struct bpf_program *xdp_prog_rx,
+				   struct bpf_program *xdp_prog_tx, struct bpf_map *xskmap_rx,
+				   struct bpf_map *xskmap_tx)
+{
+	test->xdp_prog_rx = xdp_prog_rx;
+	test->xdp_prog_tx = xdp_prog_tx;
+	test->xskmap_rx = xskmap_rx;
+	test->xskmap_tx = xskmap_tx;
+}
+
+static int test_spec_set_mtu(struct test_spec *test, int mtu)
+{
+	int err;
+
+	if (test->ifobj_rx->mtu != mtu) {
+		err = xsk_set_mtu(test->ifobj_rx->ifindex, mtu);
+		if (err)
+			return err;
+		test->ifobj_rx->mtu = mtu;
+	}
+	if (test->ifobj_tx->mtu != mtu) {
+		err = xsk_set_mtu(test->ifobj_tx->ifindex, mtu);
+		if (err)
+			return err;
+		test->ifobj_tx->mtu = mtu;
+	}
+
+	return 0;
+}
+
+void pkt_stream_reset(struct pkt_stream *pkt_stream)
+{
+	if (pkt_stream) {
+		pkt_stream->current_pkt_nb = 0;
+		pkt_stream->nb_rx_pkts = 0;
+	}
+}
+
+static struct pkt *pkt_stream_get_next_tx_pkt(struct pkt_stream *pkt_stream)
+{
+	if (pkt_stream->current_pkt_nb >= pkt_stream->nb_pkts)
+		return NULL;
+
+	return &pkt_stream->pkts[pkt_stream->current_pkt_nb++];
+}
+
+static struct pkt *pkt_stream_get_next_rx_pkt(struct pkt_stream *pkt_stream, u32 *pkts_sent)
+{
+	while (pkt_stream->current_pkt_nb < pkt_stream->nb_pkts) {
+		(*pkts_sent)++;
+		if (pkt_stream->pkts[pkt_stream->current_pkt_nb].valid)
+			return &pkt_stream->pkts[pkt_stream->current_pkt_nb++];
+		pkt_stream->current_pkt_nb++;
+	}
+	return NULL;
+}
+
+void pkt_stream_delete(struct pkt_stream *pkt_stream)
+{
+	free(pkt_stream->pkts);
+	free(pkt_stream);
+}
+
+void pkt_stream_restore_default(struct test_spec *test)
+{
+	struct pkt_stream *tx_pkt_stream = test->ifobj_tx->xsk->pkt_stream;
+	struct pkt_stream *rx_pkt_stream = test->ifobj_rx->xsk->pkt_stream;
+
+	if (tx_pkt_stream != test->tx_pkt_stream_default) {
+		pkt_stream_delete(test->ifobj_tx->xsk->pkt_stream);
+		test->ifobj_tx->xsk->pkt_stream = test->tx_pkt_stream_default;
+	}
+
+	if (rx_pkt_stream != test->rx_pkt_stream_default) {
+		pkt_stream_delete(test->ifobj_rx->xsk->pkt_stream);
+		test->ifobj_rx->xsk->pkt_stream = test->rx_pkt_stream_default;
+	}
+}
+
+static struct pkt_stream *__pkt_stream_alloc(u32 nb_pkts)
+{
+	struct pkt_stream *pkt_stream;
+
+	pkt_stream = calloc(1, sizeof(*pkt_stream));
+	if (!pkt_stream)
+		return NULL;
+
+	pkt_stream->pkts = calloc(nb_pkts, sizeof(*pkt_stream->pkts));
+	if (!pkt_stream->pkts) {
+		free(pkt_stream);
+		return NULL;
+	}
+
+	pkt_stream->nb_pkts = nb_pkts;
+	return pkt_stream;
+}
+
+static u32 pkt_nb_frags(u32 frame_size, struct pkt_stream *pkt_stream, struct pkt *pkt)
+{
+	u32 nb_frags = 1, next_frag;
+
+	if (!pkt)
+		return 1;
+
+	if (!pkt_stream->verbatim) {
+		if (!pkt->valid || !pkt->len)
+			return 1;
+		return ceil_u32(pkt->len, frame_size);
+	}
+
+	/* Search for the end of the packet in verbatim mode */
+	if (!pkt_continues(pkt->options))
+		return nb_frags;
+
+	next_frag = pkt_stream->current_pkt_nb;
+	pkt++;
+	while (next_frag++ < pkt_stream->nb_pkts) {
+		nb_frags++;
+		if (!pkt_continues(pkt->options) || !pkt->valid)
+			break;
+		pkt++;
+	}
+	return nb_frags;
+}
+
+static bool set_pkt_valid(int offset, u32 len)
+{
+	return len <= MAX_ETH_JUMBO_SIZE;
+}
+
+static void pkt_set(struct pkt_stream *pkt_stream, struct pkt *pkt, int offset, u32 len)
+{
+	pkt->offset = offset;
+	pkt->len = len;
+	pkt->valid = set_pkt_valid(offset, len);
+}
+
+static void pkt_stream_pkt_set(struct pkt_stream *pkt_stream, struct pkt *pkt, int offset, u32 len)
+{
+	bool prev_pkt_valid = pkt->valid;
+
+	pkt_set(pkt_stream, pkt, offset, len);
+	pkt_stream->nb_valid_entries += pkt->valid - prev_pkt_valid;
+}
+
+static u32 pkt_get_buffer_len(struct xsk_umem_info *umem, u32 len)
+{
+	return ceil_u32(len, umem->frame_size) * umem->frame_size;
+}
+
+static struct pkt_stream *__pkt_stream_generate(u32 nb_pkts, u32 pkt_len, u32 nb_start, u32 nb_off)
+{
+	struct pkt_stream *pkt_stream;
+	u32 i;
+
+	pkt_stream = __pkt_stream_alloc(nb_pkts);
+	if (!pkt_stream)
+		return NULL;
+
+	pkt_stream->nb_pkts = nb_pkts;
+	pkt_stream->max_pkt_len = pkt_len;
+	for (i = 0; i < nb_pkts; i++) {
+		struct pkt *pkt = &pkt_stream->pkts[i];
+
+		pkt_stream_pkt_set(pkt_stream, pkt, 0, pkt_len);
+		pkt->pkt_nb = nb_start + i * nb_off;
+	}
+
+	return pkt_stream;
+}
+
+struct pkt_stream *pkt_stream_generate(u32 nb_pkts, u32 pkt_len)
+{
+	return __pkt_stream_generate(nb_pkts, pkt_len, 0, 1);
+}
+
+static struct pkt_stream *pkt_stream_clone(struct pkt_stream *pkt_stream)
+{
+	return pkt_stream_generate(pkt_stream->nb_pkts, pkt_stream->pkts[0].len);
+}
+
+static int pkt_stream_replace_ifobject(struct ifobject *ifobj, u32 nb_pkts, u32 pkt_len)
+{
+	ifobj->xsk->pkt_stream = pkt_stream_generate(nb_pkts, pkt_len);
+
+	if (!ifobj->xsk->pkt_stream)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len)
+{
+	int ret;
+
+	ret = pkt_stream_replace_ifobject(test->ifobj_tx, nb_pkts, pkt_len);
+	if (ret)
+		return ret;
+
+	return pkt_stream_replace_ifobject(test->ifobj_rx, nb_pkts, pkt_len);
+}
+
+static int __pkt_stream_replace_half(struct ifobject *ifobj, u32 pkt_len,
+				      int offset)
+{
+	struct pkt_stream *pkt_stream;
+	u32 i;
+
+	pkt_stream = pkt_stream_clone(ifobj->xsk->pkt_stream);
+	if (!pkt_stream)
+		return -ENOMEM;
+
+	for (i = 1; i < ifobj->xsk->pkt_stream->nb_pkts; i += 2)
+		pkt_stream_pkt_set(pkt_stream, &pkt_stream->pkts[i], offset, pkt_len);
+
+	ifobj->xsk->pkt_stream = pkt_stream;
+
+	return 0;
+}
+
+static int pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, int offset)
+{
+	int ret = __pkt_stream_replace_half(test->ifobj_tx, pkt_len, offset);
+
+	if (ret)
+		return ret;
+
+	return __pkt_stream_replace_half(test->ifobj_rx, pkt_len, offset);
+}
+
+static int pkt_stream_receive_half(struct test_spec *test)
+{
+	struct pkt_stream *pkt_stream = test->ifobj_tx->xsk->pkt_stream;
+	u32 i;
+
+	if (test->ifobj_rx->xsk->pkt_stream != test->rx_pkt_stream_default)
+		/* Packet stream has already been replaced so we have to release this one.
+		 * The newly created one will be freed by the restore_default() at the
+		 * end of the test
+		 */
+		pkt_stream_delete(test->ifobj_rx->xsk->pkt_stream);
+
+	test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(pkt_stream->nb_pkts,
+							      pkt_stream->pkts[0].len);
+	if (!test->ifobj_rx->xsk->pkt_stream)
+		return -ENOMEM;
+
+	pkt_stream = test->ifobj_rx->xsk->pkt_stream;
+	for (i = 1; i < pkt_stream->nb_pkts; i += 2)
+		pkt_stream->pkts[i].valid = false;
+
+	pkt_stream->nb_valid_entries /= 2;
+
+	return 0;
+}
+
+static int pkt_stream_even_odd_sequence(struct test_spec *test)
+{
+	struct pkt_stream *pkt_stream;
+	u32 i;
+
+	for (i = 0; i < test->nb_sockets; i++) {
+		pkt_stream = test->ifobj_tx->xsk_arr[i].pkt_stream;
+		pkt_stream = __pkt_stream_generate(pkt_stream->nb_pkts / 2,
+						   pkt_stream->pkts[0].len, i, 2);
+		if (!pkt_stream)
+			return -ENOMEM;
+		test->ifobj_tx->xsk_arr[i].pkt_stream = pkt_stream;
+
+		pkt_stream = test->ifobj_rx->xsk_arr[i].pkt_stream;
+		pkt_stream = __pkt_stream_generate(pkt_stream->nb_pkts / 2,
+						   pkt_stream->pkts[0].len, i, 2);
+		if (!pkt_stream)
+			return -ENOMEM;
+		test->ifobj_rx->xsk_arr[i].pkt_stream = pkt_stream;
+	}
+
+	return 0;
+}
+
+static void release_even_odd_sequence(struct test_spec *test)
+{
+	struct pkt_stream *later_free_tx = test->ifobj_tx->xsk->pkt_stream;
+	struct pkt_stream *later_free_rx = test->ifobj_rx->xsk->pkt_stream;
+	int i;
+
+	for (i = 0; i < test->nb_sockets; i++) {
+		/* later_free_{rx/tx} will be freed by restore_default() */
+		if (test->ifobj_tx->xsk_arr[i].pkt_stream != later_free_tx)
+			pkt_stream_delete(test->ifobj_tx->xsk_arr[i].pkt_stream);
+		if (test->ifobj_rx->xsk_arr[i].pkt_stream != later_free_rx)
+			pkt_stream_delete(test->ifobj_rx->xsk_arr[i].pkt_stream);
+	}
+
+}
+
+static u64 pkt_get_addr(struct pkt *pkt, struct xsk_umem_info *umem)
+{
+	if (!pkt->valid)
+		return pkt->offset;
+	return pkt->offset + umem_alloc_buffer(umem);
+}
+
+static void pkt_stream_cancel(struct pkt_stream *pkt_stream)
+{
+	pkt_stream->current_pkt_nb--;
+}
+
+static void pkt_generate(struct xsk_socket_info *xsk, struct xsk_umem_info *umem, u64 addr, u32 len,
+			 u32 pkt_nb, u32 bytes_written)
+{
+	void *data = xsk_umem__get_data(umem->buffer, addr);
+
+	if (len < MIN_PKT_SIZE)
+		return;
+
+	if (!bytes_written) {
+		gen_eth_hdr(xsk, data);
+
+		len -= PKT_HDR_SIZE;
+		data += PKT_HDR_SIZE;
+	} else {
+		bytes_written -= PKT_HDR_SIZE;
+	}
+
+	write_payload(data, pkt_nb, bytes_written, len);
+}
+
+static struct pkt_stream *__pkt_stream_generate_custom(struct ifobject *ifobj, struct pkt *frames,
+						       u32 nb_frames, bool verbatim)
+{
+	u32 i, len = 0, pkt_nb = 0, payload = 0;
+	struct pkt_stream *pkt_stream;
+
+	pkt_stream = __pkt_stream_alloc(nb_frames);
+	if (!pkt_stream)
+		return NULL;
+
+	for (i = 0; i < nb_frames; i++) {
+		struct pkt *pkt = &pkt_stream->pkts[pkt_nb];
+		struct pkt *frame = &frames[i];
+
+		pkt->offset = frame->offset;
+		if (verbatim) {
+			*pkt = *frame;
+			pkt->pkt_nb = payload;
+			if (!frame->valid || !pkt_continues(frame->options))
+				payload++;
+		} else {
+			if (frame->valid)
+				len += frame->len;
+			if (frame->valid && pkt_continues(frame->options))
+				continue;
+
+			pkt->pkt_nb = pkt_nb;
+			pkt->len = len;
+			pkt->valid = frame->valid;
+			pkt->options = 0;
+
+			len = 0;
+		}
+
+		print_verbose("offset: %d len: %u valid: %u options: %u pkt_nb: %u\n",
+			      pkt->offset, pkt->len, pkt->valid, pkt->options, pkt->pkt_nb);
+
+		if (pkt->valid && pkt->len > pkt_stream->max_pkt_len)
+			pkt_stream->max_pkt_len = pkt->len;
+
+		if (pkt->valid)
+			pkt_stream->nb_valid_entries++;
+
+		pkt_nb++;
+	}
+
+	pkt_stream->nb_pkts = pkt_nb;
+	pkt_stream->verbatim = verbatim;
+	return pkt_stream;
+}
+
+static int pkt_stream_generate_custom(struct test_spec *test, struct pkt *pkts, u32 nb_pkts)
+{
+	struct pkt_stream *pkt_stream;
+
+	pkt_stream = __pkt_stream_generate_custom(test->ifobj_tx, pkts, nb_pkts, true);
+	if (!pkt_stream)
+		return -ENOMEM;
+	test->ifobj_tx->xsk->pkt_stream = pkt_stream;
+
+	pkt_stream = __pkt_stream_generate_custom(test->ifobj_rx, pkts, nb_pkts, false);
+	if (!pkt_stream)
+		return -ENOMEM;
+	test->ifobj_rx->xsk->pkt_stream = pkt_stream;
+
+	return 0;
+}
+
+static void pkt_print_data(u32 *data, u32 cnt)
+{
+	u32 i;
+
+	for (i = 0; i < cnt; i++) {
+		u32 seqnum, pkt_nb;
+
+		seqnum = ntohl(*data) & 0xffff;
+		pkt_nb = ntohl(*data) >> 16;
+		ksft_print_msg("%u:%u ", pkt_nb, seqnum);
+		data++;
+	}
+}
+
+static void pkt_dump(void *pkt, u32 len, bool eth_header)
+{
+	struct ethhdr *ethhdr = pkt;
+	u32 i, *data;
+
+	if (eth_header) {
+		/*extract L2 frame */
+		ksft_print_msg("DEBUG>> L2: dst mac: ");
+		for (i = 0; i < ETH_ALEN; i++)
+			ksft_print_msg("%02X", ethhdr->h_dest[i]);
+
+		ksft_print_msg("\nDEBUG>> L2: src mac: ");
+		for (i = 0; i < ETH_ALEN; i++)
+			ksft_print_msg("%02X", ethhdr->h_source[i]);
+
+		data = pkt + PKT_HDR_SIZE;
+	} else {
+		data = pkt;
+	}
+
+	/*extract L5 frame */
+	ksft_print_msg("\nDEBUG>> L5: seqnum: ");
+	pkt_print_data(data, PKT_DUMP_NB_TO_PRINT);
+	ksft_print_msg("....");
+	if (len > PKT_DUMP_NB_TO_PRINT * sizeof(u32)) {
+		ksft_print_msg("\n.... ");
+		pkt_print_data(data + len / sizeof(u32) - PKT_DUMP_NB_TO_PRINT,
+			       PKT_DUMP_NB_TO_PRINT);
+	}
+	ksft_print_msg("\n---------------------------------------\n");
+}
+
+static bool is_offset_correct(struct xsk_umem_info *umem, struct pkt *pkt, u64 addr)
+{
+	u32 headroom = umem->unaligned_mode ? 0 : umem->frame_headroom;
+	u32 offset = addr % umem->frame_size, expected_offset;
+	int pkt_offset = pkt->valid ? pkt->offset : 0;
+
+	if (!umem->unaligned_mode)
+		pkt_offset = 0;
+
+	expected_offset = (pkt_offset + headroom + XDP_PACKET_HEADROOM) % umem->frame_size;
+
+	if (offset == expected_offset)
+		return true;
+
+	ksft_print_msg("[%s] expected [%u], got [%u]\n", __func__, expected_offset, offset);
+	return false;
+}
+
+static bool is_metadata_correct(struct pkt *pkt, void *buffer, u64 addr)
+{
+	void *data = xsk_umem__get_data(buffer, addr);
+	struct xdp_info *meta = data - sizeof(struct xdp_info);
+
+	if (meta->count != pkt->pkt_nb) {
+		ksft_print_msg("[%s] expected meta_count [%d], got meta_count [%llu]\n",
+			       __func__, pkt->pkt_nb,
+			       (unsigned long long)meta->count);
+		return false;
+	}
+
+	return true;
+}
+
+static int is_adjust_tail_supported(struct xsk_xdp_progs *skel_rx, bool *supported)
+{
+	struct bpf_map *data_map;
+	int adjust_value = 0;
+	int key = 0;
+	int ret;
+
+	data_map = bpf_object__find_map_by_name(skel_rx->obj, "xsk_xdp_.bss");
+	if (!data_map || !bpf_map__is_internal(data_map)) {
+		ksft_print_msg("Error: could not find bss section of XDP program\n");
+		return -EINVAL;
+	}
+
+	ret = bpf_map_lookup_elem(bpf_map__fd(data_map), &key, &adjust_value);
+	if (ret) {
+		ksft_print_msg("Error: bpf_map_lookup_elem failed with error %d\n", ret);
+		return ret;
+	}
+
+	/* Set the 'adjust_value' variable to -EOPNOTSUPP in the XDP program if the adjust_tail
+	 * helper is not supported. Skip the adjust_tail test case in this scenario.
+	 */
+	*supported = adjust_value != -EOPNOTSUPP;
+
+	return 0;
+}
+
+static bool is_frag_valid(struct xsk_umem_info *umem, u64 addr, u32 len, u32 expected_pkt_nb,
+			  u32 bytes_processed)
+{
+	u32 seqnum, pkt_nb, *pkt_data, words_to_end, expected_seqnum;
+	void *data = xsk_umem__get_data(umem->buffer, addr);
+
+	addr -= umem->base_addr;
+
+	if (addr >= umem->num_frames * umem->frame_size ||
+	    addr + len > umem->num_frames * umem->frame_size) {
+		ksft_print_msg("Frag invalid addr: %llx len: %u\n",
+			       (unsigned long long)addr, len);
+		return false;
+	}
+	if (!umem->unaligned_mode && addr % umem->frame_size + len > umem->frame_size) {
+		ksft_print_msg("Frag crosses frame boundary addr: %llx len: %u\n",
+			       (unsigned long long)addr, len);
+		return false;
+	}
+
+	pkt_data = data;
+	if (!bytes_processed) {
+		pkt_data += PKT_HDR_SIZE / sizeof(*pkt_data);
+		len -= PKT_HDR_SIZE;
+	} else {
+		bytes_processed -= PKT_HDR_SIZE;
+	}
+
+	expected_seqnum = bytes_processed / sizeof(*pkt_data);
+	seqnum = ntohl(*pkt_data) & 0xffff;
+	pkt_nb = ntohl(*pkt_data) >> 16;
+
+	if (expected_pkt_nb != pkt_nb) {
+		ksft_print_msg("[%s] expected pkt_nb [%u], got pkt_nb [%u]\n",
+			       __func__, expected_pkt_nb, pkt_nb);
+		goto error;
+	}
+	if (expected_seqnum != seqnum) {
+		ksft_print_msg("[%s] expected seqnum at start [%u], got seqnum [%u]\n",
+			       __func__, expected_seqnum, seqnum);
+		goto error;
+	}
+
+	words_to_end = len / sizeof(*pkt_data) - 1;
+	pkt_data += words_to_end;
+	seqnum = ntohl(*pkt_data) & 0xffff;
+	expected_seqnum += words_to_end;
+	if (expected_seqnum != seqnum) {
+		ksft_print_msg("[%s] expected seqnum at end [%u], got seqnum [%u]\n",
+			       __func__, expected_seqnum, seqnum);
+		goto error;
+	}
+
+	return true;
+
+error:
+	pkt_dump(data, len, !bytes_processed);
+	return false;
+}
+
+static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len)
+{
+	if (pkt->len != len) {
+		ksft_print_msg("[%s] expected packet length [%d], got length [%d]\n",
+			       __func__, pkt->len, len);
+		pkt_dump(xsk_umem__get_data(buffer, addr), len, true);
+		return false;
+	}
+
+	return true;
+}
+
+static u32 load_value(u32 *counter)
+{
+	return __atomic_load_n(counter, __ATOMIC_ACQUIRE);
+}
+
+static bool kick_tx_with_check(struct xsk_socket_info *xsk, int *ret)
+{
+	u32 max_budget = MAX_TX_BUDGET_DEFAULT;
+	u32 cons, ready_to_send;
+	int delta;
+
+	cons = load_value(xsk->tx.consumer);
+	ready_to_send = load_value(xsk->tx.producer) - cons;
+	*ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0);
+
+	delta = load_value(xsk->tx.consumer) - cons;
+	/* By default, xsk should consume exact @max_budget descs at one
+	 * send in this case where hitting the max budget limit in while
+	 * loop is triggered in __xsk_generic_xmit(). Please make sure that
+	 * the number of descs to be sent is larger than @max_budget, or
+	 * else the tx.consumer will be updated in xskq_cons_peek_desc()
+	 * in time which hides the issue we try to verify.
+	 */
+	if (ready_to_send > max_budget && delta != max_budget)
+		return false;
+
+	return true;
+}
+
+int kick_tx(struct xsk_socket_info *xsk)
+{
+	int ret;
+
+	if (xsk->check_consumer) {
+		if (!kick_tx_with_check(xsk, &ret))
+			return TEST_FAILURE;
+	} else {
+		ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0);
+	}
+	if (ret >= 0)
+		return TEST_PASS;
+	if (errno == ENOBUFS || errno == EAGAIN || errno == EBUSY || errno == ENETDOWN) {
+		usleep(100);
+		return TEST_PASS;
+	}
+	return TEST_FAILURE;
+}
+
+int kick_rx(struct xsk_socket_info *xsk)
+{
+	int ret;
+
+	ret = recvfrom(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, NULL);
+	if (ret < 0)
+		return TEST_FAILURE;
+
+	return TEST_PASS;
+}
+
+static int complete_pkts(struct xsk_socket_info *xsk, int batch_size)
+{
+	unsigned int rcvd;
+	u32 idx;
+	int ret;
+
+	if (xsk_ring_prod__needs_wakeup(&xsk->tx)) {
+		ret = kick_tx(xsk);
+		if (ret)
+			return TEST_FAILURE;
+	}
+
+	rcvd = xsk_ring_cons__peek(&xsk->umem->cq, batch_size, &idx);
+	if (rcvd) {
+		if (rcvd > xsk->outstanding_tx) {
+			u64 addr = *xsk_ring_cons__comp_addr(&xsk->umem->cq, idx + rcvd - 1);
+
+			ksft_print_msg("[%s] Too many packets completed\n", __func__);
+			ksft_print_msg("Last completion address: %llx\n",
+				       (unsigned long long)addr);
+			return TEST_FAILURE;
+		}
+
+		xsk_ring_cons__release(&xsk->umem->cq, rcvd);
+		xsk->outstanding_tx -= rcvd;
+	}
+
+	return TEST_PASS;
+}
+
+static int __receive_pkts(struct test_spec *test, struct xsk_socket_info *xsk)
+{
+	u32 frags_processed = 0, nb_frags = 0, pkt_len = 0;
+	u32 idx_rx = 0, idx_fq = 0, rcvd, pkts_sent = 0;
+	struct pkt_stream *pkt_stream = xsk->pkt_stream;
+	struct ifobject *ifobj = test->ifobj_rx;
+	struct xsk_umem_info *umem = xsk->umem;
+	struct pollfd fds = { };
+	struct pkt *pkt;
+	u64 first_addr = 0;
+	int ret;
+
+	fds.fd = xsk_socket__fd(xsk->xsk);
+	fds.events = POLLIN;
+
+	ret = kick_rx(xsk);
+	if (ret)
+		return TEST_FAILURE;
+
+	if (ifobj->use_poll) {
+		ret = poll(&fds, 1, POLL_TMOUT);
+		if (ret < 0)
+			return TEST_FAILURE;
+
+		if (!ret) {
+			if (!is_umem_valid(test->ifobj_tx))
+				return TEST_PASS;
+
+			ksft_print_msg("ERROR: [%s] Poll timed out\n", __func__);
+			return TEST_CONTINUE;
+		}
+
+		if (!(fds.revents & POLLIN))
+			return TEST_CONTINUE;
+	}
+
+	rcvd = xsk_ring_cons__peek(&xsk->rx, xsk->batch_size, &idx_rx);
+	if (!rcvd)
+		return TEST_CONTINUE;
+
+	if (ifobj->use_fill_ring) {
+		ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
+		while (ret != rcvd) {
+			if (xsk_ring_prod__needs_wakeup(&umem->fq)) {
+				ret = poll(&fds, 1, POLL_TMOUT);
+				if (ret < 0)
+					return TEST_FAILURE;
+			}
+			ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
+		}
+	}
+
+	while (frags_processed < rcvd) {
+		const struct xdp_desc *desc = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++);
+		u64 addr = desc->addr, orig;
+
+		orig = xsk_umem__extract_addr(addr);
+		addr = xsk_umem__add_offset_to_addr(addr);
+
+		if (!nb_frags) {
+			pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &pkts_sent);
+			if (!pkt) {
+				ksft_print_msg("[%s] received too many packets addr: %lx len %u\n",
+					       __func__, addr, desc->len);
+				return TEST_FAILURE;
+			}
+		}
+
+		print_verbose("Rx: addr: %lx len: %u options: %u pkt_nb: %u valid: %u\n",
+			      addr, desc->len, desc->options, pkt->pkt_nb, pkt->valid);
+
+		if (!is_frag_valid(umem, addr, desc->len, pkt->pkt_nb, pkt_len) ||
+		    !is_offset_correct(umem, pkt, addr) || (ifobj->use_metadata &&
+		    !is_metadata_correct(pkt, umem->buffer, addr)))
+			return TEST_FAILURE;
+
+		if (!nb_frags++)
+			first_addr = addr;
+		frags_processed++;
+		pkt_len += desc->len;
+		if (ifobj->use_fill_ring)
+			*xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) = orig;
+
+		if (pkt_continues(desc->options))
+			continue;
+
+		/* The complete packet has been received */
+		if (!is_pkt_valid(pkt, umem->buffer, first_addr, pkt_len) ||
+		    !is_offset_correct(umem, pkt, addr))
+			return TEST_FAILURE;
+
+		pkt_stream->nb_rx_pkts++;
+		nb_frags = 0;
+		pkt_len = 0;
+	}
+
+	if (nb_frags) {
+		/* In the middle of a packet. Start over from beginning of packet. */
+		idx_rx -= nb_frags;
+		xsk_ring_cons__cancel(&xsk->rx, nb_frags);
+		if (ifobj->use_fill_ring) {
+			idx_fq -= nb_frags;
+			xsk_ring_prod__cancel(&umem->fq, nb_frags);
+		}
+		frags_processed -= nb_frags;
+	}
+
+	if (ifobj->use_fill_ring)
+		xsk_ring_prod__submit(&umem->fq, frags_processed);
+	if (ifobj->release_rx)
+		xsk_ring_cons__release(&xsk->rx, frags_processed);
+
+	pthread_mutex_lock(&pacing_mutex);
+	pkts_in_flight -= pkts_sent;
+	pthread_mutex_unlock(&pacing_mutex);
+	pkts_sent = 0;
+
+	return TEST_CONTINUE;
+}
+
+bool all_packets_received(struct test_spec *test, struct xsk_socket_info *xsk, u32 sock_num,
+			  unsigned long *bitmap)
+{
+	struct pkt_stream *pkt_stream = xsk->pkt_stream;
+
+	if (!pkt_stream) {
+		__set_bit(sock_num, bitmap);
+		return false;
+	}
+
+	if (pkt_stream->nb_rx_pkts == pkt_stream->nb_valid_entries) {
+		__set_bit(sock_num, bitmap);
+		if (bitmap_full(bitmap, test->nb_sockets))
+			return true;
+	}
+
+	return false;
+}
+
+static int receive_pkts(struct test_spec *test)
+{
+	struct timeval tv_end, tv_now, tv_timeout = {THREAD_TMOUT, 0};
+	DECLARE_BITMAP(bitmap, test->nb_sockets);
+	struct xsk_socket_info *xsk;
+	u32 sock_num = 0;
+	int res, ret;
+
+	bitmap_zero(bitmap, test->nb_sockets);
+
+	ret = gettimeofday(&tv_now, NULL);
+	if (ret)
+		return TEST_FAILURE;
+
+	timeradd(&tv_now, &tv_timeout, &tv_end);
+
+	while (1) {
+		xsk = &test->ifobj_rx->xsk_arr[sock_num];
+
+		if ((all_packets_received(test, xsk, sock_num, bitmap)))
+			break;
+
+		res = __receive_pkts(test, xsk);
+		if (!(res == TEST_PASS || res == TEST_CONTINUE))
+			return res;
+
+		ret = gettimeofday(&tv_now, NULL);
+		if (ret)
+			return TEST_FAILURE;
+
+		if (timercmp(&tv_now, &tv_end, >)) {
+			ksft_print_msg("ERROR: [%s] Receive loop timed out\n", __func__);
+			return TEST_FAILURE;
+		}
+		sock_num = (sock_num + 1) % test->nb_sockets;
+	}
+
+	return TEST_PASS;
+}
+
+static int __send_pkts(struct ifobject *ifobject, struct xsk_socket_info *xsk, bool timeout)
+{
+	u32 i, idx = 0, valid_pkts = 0, valid_frags = 0, buffer_len;
+	struct pkt_stream *pkt_stream = xsk->pkt_stream;
+	struct xsk_umem_info *umem = ifobject->umem;
+	bool use_poll = ifobject->use_poll;
+	struct pollfd fds = { };
+	int ret;
+
+	buffer_len = pkt_get_buffer_len(umem, pkt_stream->max_pkt_len);
+	/* pkts_in_flight might be negative if many invalid packets are sent */
+	if (pkts_in_flight >= (int)((umem_size(umem) - xsk->batch_size * buffer_len) /
+	    buffer_len)) {
+		ret = kick_tx(xsk);
+		if (ret)
+			return TEST_FAILURE;
+		return TEST_CONTINUE;
+	}
+
+	fds.fd = xsk_socket__fd(xsk->xsk);
+	fds.events = POLLOUT;
+
+	while (xsk_ring_prod__reserve(&xsk->tx, xsk->batch_size, &idx) < xsk->batch_size) {
+		if (use_poll) {
+			ret = poll(&fds, 1, POLL_TMOUT);
+			if (timeout) {
+				if (ret < 0) {
+					ksft_print_msg("ERROR: [%s] Poll error %d\n",
+						       __func__, errno);
+					return TEST_FAILURE;
+				}
+				if (ret == 0)
+					return TEST_PASS;
+				break;
+			}
+			if (ret <= 0) {
+				ksft_print_msg("ERROR: [%s] Poll error %d\n",
+					       __func__, errno);
+				return TEST_FAILURE;
+			}
+		}
+
+		complete_pkts(xsk, xsk->batch_size);
+	}
+
+	for (i = 0; i < xsk->batch_size; i++) {
+		struct pkt *pkt = pkt_stream_get_next_tx_pkt(pkt_stream);
+		u32 nb_frags_left, nb_frags, bytes_written = 0;
+
+		if (!pkt)
+			break;
+
+		nb_frags = pkt_nb_frags(umem->frame_size, pkt_stream, pkt);
+		if (nb_frags > xsk->batch_size - i) {
+			pkt_stream_cancel(pkt_stream);
+			xsk_ring_prod__cancel(&xsk->tx, xsk->batch_size - i);
+			break;
+		}
+		nb_frags_left = nb_frags;
+
+		while (nb_frags_left--) {
+			struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i);
+
+			tx_desc->addr = pkt_get_addr(pkt, ifobject->umem);
+			if (pkt_stream->verbatim) {
+				tx_desc->len = pkt->len;
+				tx_desc->options = pkt->options;
+			} else if (nb_frags_left) {
+				tx_desc->len = umem->frame_size;
+				tx_desc->options = XDP_PKT_CONTD;
+			} else {
+				tx_desc->len = pkt->len - bytes_written;
+				tx_desc->options = 0;
+			}
+			if (pkt->valid)
+				pkt_generate(xsk, umem, tx_desc->addr, tx_desc->len, pkt->pkt_nb,
+					     bytes_written);
+			bytes_written += tx_desc->len;
+
+			print_verbose("Tx addr: %llx len: %u options: %u pkt_nb: %u\n",
+				      tx_desc->addr, tx_desc->len, tx_desc->options, pkt->pkt_nb);
+
+			if (nb_frags_left) {
+				i++;
+				if (pkt_stream->verbatim)
+					pkt = pkt_stream_get_next_tx_pkt(pkt_stream);
+			}
+		}
+
+		if (pkt && pkt->valid) {
+			valid_pkts++;
+			valid_frags += nb_frags;
+		}
+	}
+
+	pthread_mutex_lock(&pacing_mutex);
+	pkts_in_flight += valid_pkts;
+	pthread_mutex_unlock(&pacing_mutex);
+
+	xsk_ring_prod__submit(&xsk->tx, i);
+	xsk->outstanding_tx += valid_frags;
+
+	if (use_poll) {
+		ret = poll(&fds, 1, POLL_TMOUT);
+		if (ret <= 0) {
+			if (ret == 0 && timeout)
+				return TEST_PASS;
+
+			ksft_print_msg("ERROR: [%s] Poll error %d\n", __func__, ret);
+			return TEST_FAILURE;
+		}
+	}
+
+	if (!timeout) {
+		if (complete_pkts(xsk, i))
+			return TEST_FAILURE;
+
+		usleep(10);
+		return TEST_PASS;
+	}
+
+	return TEST_CONTINUE;
+}
+
+static int wait_for_tx_completion(struct xsk_socket_info *xsk)
+{
+	struct timeval tv_end, tv_now, tv_timeout = {THREAD_TMOUT, 0};
+	int ret;
+
+	ret = gettimeofday(&tv_now, NULL);
+	if (ret)
+		return TEST_FAILURE;
+	timeradd(&tv_now, &tv_timeout, &tv_end);
+
+	while (xsk->outstanding_tx) {
+		ret = gettimeofday(&tv_now, NULL);
+		if (ret)
+			return TEST_FAILURE;
+		if (timercmp(&tv_now, &tv_end, >)) {
+			ksft_print_msg("ERROR: [%s] Transmission loop timed out\n", __func__);
+			return TEST_FAILURE;
+		}
+
+		complete_pkts(xsk, xsk->batch_size);
+	}
+
+	return TEST_PASS;
+}
+
+bool all_packets_sent(struct test_spec *test, unsigned long *bitmap)
+{
+	return bitmap_full(bitmap, test->nb_sockets);
+}
+
+static int send_pkts(struct test_spec *test, struct ifobject *ifobject)
+{
+	bool timeout = !is_umem_valid(test->ifobj_rx);
+	DECLARE_BITMAP(bitmap, test->nb_sockets);
+	u32 i, ret;
+
+	bitmap_zero(bitmap, test->nb_sockets);
+
+	while (!(all_packets_sent(test, bitmap))) {
+		for (i = 0; i < test->nb_sockets; i++) {
+			struct pkt_stream *pkt_stream;
+
+			pkt_stream = ifobject->xsk_arr[i].pkt_stream;
+			if (!pkt_stream || pkt_stream->current_pkt_nb >= pkt_stream->nb_pkts) {
+				__set_bit(i, bitmap);
+				continue;
+			}
+			ret = __send_pkts(ifobject, &ifobject->xsk_arr[i], timeout);
+			if (ret == TEST_CONTINUE && !test->fail)
+				continue;
+
+			if ((ret || test->fail) && !timeout)
+				return TEST_FAILURE;
+
+			if (ret == TEST_PASS && timeout)
+				return ret;
+
+			ret = wait_for_tx_completion(&ifobject->xsk_arr[i]);
+			if (ret)
+				return TEST_FAILURE;
+		}
+	}
+
+	return TEST_PASS;
+}
+
+static int get_xsk_stats(struct xsk_socket *xsk, struct xdp_statistics *stats)
+{
+	int fd = xsk_socket__fd(xsk), err;
+	socklen_t optlen, expected_len;
+
+	optlen = sizeof(*stats);
+	err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, stats, &optlen);
+	if (err) {
+		ksft_print_msg("[%s] getsockopt(XDP_STATISTICS) error %u %s\n",
+			       __func__, -err, strerror(-err));
+		return TEST_FAILURE;
+	}
+
+	expected_len = sizeof(struct xdp_statistics);
+	if (optlen != expected_len) {
+		ksft_print_msg("[%s] getsockopt optlen error. Expected: %u got: %u\n",
+			       __func__, expected_len, optlen);
+		return TEST_FAILURE;
+	}
+
+	return TEST_PASS;
+}
+
+static int validate_rx_dropped(struct ifobject *ifobject)
+{
+	struct xsk_socket *xsk = ifobject->xsk->xsk;
+	struct xdp_statistics stats;
+	int err;
+
+	err = kick_rx(ifobject->xsk);
+	if (err)
+		return TEST_FAILURE;
+
+	err = get_xsk_stats(xsk, &stats);
+	if (err)
+		return TEST_FAILURE;
+
+	/* The receiver calls getsockopt after receiving the last (valid)
+	 * packet which is not the final packet sent in this test (valid and
+	 * invalid packets are sent in alternating fashion with the final
+	 * packet being invalid). Since the last packet may or may not have
+	 * been dropped already, both outcomes must be allowed.
+	 */
+	if (stats.rx_dropped == ifobject->xsk->pkt_stream->nb_pkts / 2 ||
+	    stats.rx_dropped == ifobject->xsk->pkt_stream->nb_pkts / 2 - 1)
+		return TEST_PASS;
+
+	return TEST_FAILURE;
+}
+
+static int validate_rx_full(struct ifobject *ifobject)
+{
+	struct xsk_socket *xsk = ifobject->xsk->xsk;
+	struct xdp_statistics stats;
+	int err;
+
+	usleep(1000);
+	err = kick_rx(ifobject->xsk);
+	if (err)
+		return TEST_FAILURE;
+
+	err = get_xsk_stats(xsk, &stats);
+	if (err)
+		return TEST_FAILURE;
+
+	if (stats.rx_ring_full)
+		return TEST_PASS;
+
+	return TEST_FAILURE;
+}
+
+static int validate_fill_empty(struct ifobject *ifobject)
+{
+	struct xsk_socket *xsk = ifobject->xsk->xsk;
+	struct xdp_statistics stats;
+	int err;
+
+	usleep(1000);
+	err = kick_rx(ifobject->xsk);
+	if (err)
+		return TEST_FAILURE;
+
+	err = get_xsk_stats(xsk, &stats);
+	if (err)
+		return TEST_FAILURE;
+
+	if (stats.rx_fill_ring_empty_descs)
+		return TEST_PASS;
+
+	return TEST_FAILURE;
+}
+
+static int validate_tx_invalid_descs(struct ifobject *ifobject)
+{
+	struct xsk_socket *xsk = ifobject->xsk->xsk;
+	int fd = xsk_socket__fd(xsk);
+	struct xdp_statistics stats;
+	socklen_t optlen;
+	int err;
+
+	optlen = sizeof(stats);
+	err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, &stats, &optlen);
+	if (err) {
+		ksft_print_msg("[%s] getsockopt(XDP_STATISTICS) error %u %s\n",
+			       __func__, -err, strerror(-err));
+		return TEST_FAILURE;
+	}
+
+	if (stats.tx_invalid_descs != ifobject->xsk->pkt_stream->nb_pkts / 2) {
+		ksft_print_msg("[%s] tx_invalid_descs incorrect. Got [%llu] expected [%u]\n",
+			       __func__,
+			       (unsigned long long)stats.tx_invalid_descs,
+			       ifobject->xsk->pkt_stream->nb_pkts);
+		return TEST_FAILURE;
+	}
+
+	return TEST_PASS;
+}
+
+static int xsk_configure(struct test_spec *test, struct ifobject *ifobject,
+			  struct xsk_umem_info *umem, bool tx)
+{
+	int i, ret;
+
+	for (i = 0; i < test->nb_sockets; i++) {
+		bool shared = (ifobject->shared_umem && tx) ? true : !!i;
+		u32 ctr = 0;
+
+		while (ctr++ < SOCK_RECONF_CTR) {
+			ret = xsk_configure_socket(&ifobject->xsk_arr[i], umem,
+						     ifobject, shared);
+			if (!ret)
+				break;
+
+			/* Retry if it fails as xsk_socket__create() is asynchronous */
+			if (ctr >= SOCK_RECONF_CTR)
+				return ret;
+			usleep(USLEEP_MAX);
+		}
+		if (ifobject->busy_poll) {
+			ret = enable_busy_poll(&ifobject->xsk_arr[i]);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int thread_common_ops_tx(struct test_spec *test, struct ifobject *ifobject)
+{
+	int ret = xsk_configure(test, ifobject, test->ifobj_rx->umem, true);
+
+	if (ret)
+		return ret;
+	ifobject->xsk = &ifobject->xsk_arr[0];
+	ifobject->xskmap = test->ifobj_rx->xskmap;
+	memcpy(ifobject->umem, test->ifobj_rx->umem, sizeof(struct xsk_umem_info));
+	ifobject->umem->base_addr = 0;
+
+	return 0;
+}
+
+static int xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream,
+				   bool fill_up)
+{
+	u32 rx_frame_size = umem->frame_size - XDP_PACKET_HEADROOM;
+	u32 idx = 0, filled = 0, buffers_to_fill, nb_pkts;
+	int ret;
+
+	if (umem->num_frames < XSK_RING_PROD__DEFAULT_NUM_DESCS)
+		buffers_to_fill = umem->num_frames;
+	else
+		buffers_to_fill = umem->fill_size;
+
+	ret = xsk_ring_prod__reserve(&umem->fq, buffers_to_fill, &idx);
+	if (ret != buffers_to_fill)
+		return -ENOSPC;
+
+	while (filled < buffers_to_fill) {
+		struct pkt *pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &nb_pkts);
+		u64 addr;
+		u32 i;
+
+		for (i = 0; i < pkt_nb_frags(rx_frame_size, pkt_stream, pkt); i++) {
+			if (!pkt) {
+				if (!fill_up)
+					break;
+				addr = filled * umem->frame_size + umem->base_addr;
+			} else if (pkt->offset >= 0) {
+				addr = pkt->offset % umem->frame_size + umem_alloc_buffer(umem);
+			} else {
+				addr = pkt->offset + umem_alloc_buffer(umem);
+			}
+
+			*xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr;
+			if (++filled >= buffers_to_fill)
+				break;
+		}
+	}
+	xsk_ring_prod__submit(&umem->fq, filled);
+	xsk_ring_prod__cancel(&umem->fq, buffers_to_fill - filled);
+
+	pkt_stream_reset(pkt_stream);
+	umem_reset_alloc(umem);
+
+	return 0;
+}
+
+static int thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
+{
+	LIBBPF_OPTS(bpf_xdp_query_opts, opts);
+	int mmap_flags;
+	u64 umem_sz;
+	void *bufs;
+	int ret;
+	u32 i;
+
+	umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size;
+	mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
+
+	if (ifobject->umem->unaligned_mode)
+		mmap_flags |= MAP_HUGETLB | MAP_HUGE_2MB;
+
+	if (ifobject->shared_umem)
+		umem_sz *= 2;
+
+	bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0);
+	if (bufs == MAP_FAILED)
+		return -errno;
+
+	ret = xsk_configure_umem(ifobject, ifobject->umem, bufs, umem_sz);
+	if (ret)
+		return ret;
+
+	ret = xsk_configure(test, ifobject, ifobject->umem, false);
+	if (ret)
+		return ret;
+
+	ifobject->xsk = &ifobject->xsk_arr[0];
+
+	if (!ifobject->rx_on)
+		return 0;
+
+	ret = xsk_populate_fill_ring(ifobject->umem, ifobject->xsk->pkt_stream,
+				     ifobject->use_fill_ring);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < test->nb_sockets; i++) {
+		ifobject->xsk = &ifobject->xsk_arr[i];
+		ret = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk, i);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+void *worker_testapp_validate_tx(void *arg)
+{
+	struct test_spec *test = (struct test_spec *)arg;
+	struct ifobject *ifobject = test->ifobj_tx;
+	int err;
+
+	if (test->current_step == 1) {
+		if (!ifobject->shared_umem) {
+			if (thread_common_ops(test, ifobject)) {
+				test->fail = true;
+				pthread_exit(NULL);
+			}
+		} else {
+			if (thread_common_ops_tx(test, ifobject)) {
+				test->fail = true;
+				pthread_exit(NULL);
+			}
+		}
+	}
+
+	err = send_pkts(test, ifobject);
+
+	if (!err && ifobject->validation_func)
+		err = ifobject->validation_func(ifobject);
+	if (err)
+		test->fail = true;
+
+	pthread_exit(NULL);
+}
+
+void *worker_testapp_validate_rx(void *arg)
+{
+	struct test_spec *test = (struct test_spec *)arg;
+	struct ifobject *ifobject = test->ifobj_rx;
+	int err;
+
+	if (test->current_step == 1) {
+		err = thread_common_ops(test, ifobject);
+	} else {
+		xsk_clear_xskmap(ifobject->xskmap);
+		err = xsk_update_xskmap(ifobject->xskmap, ifobject->xsk->xsk, 0);
+		if (err)
+			ksft_print_msg("Error: Failed to update xskmap, error %s\n",
+				       strerror(-err));
+	}
+
+	pthread_barrier_wait(&barr);
+
+	/* We leave only now in case of error to avoid getting stuck in the barrier */
+	if (err) {
+		test->fail = true;
+		pthread_exit(NULL);
+	}
+
+	err = receive_pkts(test);
+
+	if (!err && ifobject->validation_func)
+		err = ifobject->validation_func(ifobject);
+
+	if (err) {
+		if (!test->adjust_tail) {
+			test->fail = true;
+		} else {
+			bool supported;
+
+			if (is_adjust_tail_supported(ifobject->xdp_progs, &supported))
+				test->fail = true;
+			else if (!supported)
+				test->adjust_tail_support = false;
+			else
+				test->fail = true;
+		}
+	}
+
+	pthread_exit(NULL);
+}
+
+static void testapp_clean_xsk_umem(struct ifobject *ifobj)
+{
+	u64 umem_sz = ifobj->umem->num_frames * ifobj->umem->frame_size;
+
+	if (ifobj->shared_umem)
+		umem_sz *= 2;
+
+	umem_sz = ceil_u64(umem_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE;
+	xsk_umem__delete(ifobj->umem->umem);
+	munmap(ifobj->umem->buffer, umem_sz);
+}
+
+static void handler(int signum)
+{
+	pthread_exit(NULL);
+}
+
+static bool xdp_prog_changed_rx(struct test_spec *test)
+{
+	struct ifobject *ifobj = test->ifobj_rx;
+
+	return ifobj->xdp_prog != test->xdp_prog_rx || ifobj->mode != test->mode;
+}
+
+static bool xdp_prog_changed_tx(struct test_spec *test)
+{
+	struct ifobject *ifobj = test->ifobj_tx;
+
+	return ifobj->xdp_prog != test->xdp_prog_tx || ifobj->mode != test->mode;
+}
+
+static int xsk_reattach_xdp(struct ifobject *ifobj, struct bpf_program *xdp_prog,
+			     struct bpf_map *xskmap, enum test_mode mode)
+{
+	int err;
+
+	xsk_detach_xdp_program(ifobj->ifindex, mode_to_xdp_flags(ifobj->mode));
+	err = xsk_attach_xdp_program(xdp_prog, ifobj->ifindex, mode_to_xdp_flags(mode));
+	if (err) {
+		ksft_print_msg("Error attaching XDP program\n");
+		return err;
+	}
+
+	if (ifobj->mode != mode && (mode == TEST_MODE_DRV || mode == TEST_MODE_ZC))
+		if (!xsk_is_in_mode(ifobj->ifindex, XDP_FLAGS_DRV_MODE)) {
+			ksft_print_msg("ERROR: XDP prog not in DRV mode\n");
+			return -EINVAL;
+		}
+
+	ifobj->xdp_prog = xdp_prog;
+	ifobj->xskmap = xskmap;
+	ifobj->mode = mode;
+
+	return 0;
+}
+
+static int xsk_attach_xdp_progs(struct test_spec *test, struct ifobject *ifobj_rx,
+				 struct ifobject *ifobj_tx)
+{
+	int err = 0;
+
+	if (xdp_prog_changed_rx(test)) {
+		err = xsk_reattach_xdp(ifobj_rx, test->xdp_prog_rx, test->xskmap_rx, test->mode);
+		if (err)
+			return err;
+	}
+
+	if (!ifobj_tx || ifobj_tx->shared_umem)
+		return 0;
+
+	if (xdp_prog_changed_tx(test))
+		err = xsk_reattach_xdp(ifobj_tx, test->xdp_prog_tx, test->xskmap_tx, test->mode);
+
+	return err;
+}
+
+static void clean_sockets(struct test_spec *test, struct ifobject *ifobj)
+{
+	u32 i;
+
+	if (!ifobj || !test)
+		return;
+
+	for (i = 0; i < test->nb_sockets; i++)
+		xsk_socket__delete(ifobj->xsk_arr[i].xsk);
+}
+
+static void clean_umem(struct test_spec *test, struct ifobject *ifobj1, struct ifobject *ifobj2)
+{
+	if (!ifobj1)
+		return;
+
+	testapp_clean_xsk_umem(ifobj1);
+	if (ifobj2 && !ifobj2->shared_umem)
+		testapp_clean_xsk_umem(ifobj2);
+}
+
+static int __testapp_validate_traffic(struct test_spec *test, struct ifobject *ifobj1,
+				      struct ifobject *ifobj2)
+{
+	pthread_t t0, t1;
+	int err;
+
+	if (test->mtu > MAX_ETH_PKT_SIZE) {
+		if (test->mode == TEST_MODE_ZC && (!ifobj1->multi_buff_zc_supp ||
+						   (ifobj2 && !ifobj2->multi_buff_zc_supp))) {
+			ksft_print_msg("Multi buffer for zero-copy not supported.\n");
+			return TEST_SKIP;
+		}
+		if (test->mode != TEST_MODE_ZC && (!ifobj1->multi_buff_supp ||
+						   (ifobj2 && !ifobj2->multi_buff_supp))) {
+			ksft_print_msg("Multi buffer not supported.\n");
+			return TEST_SKIP;
+		}
+	}
+	err = test_spec_set_mtu(test, test->mtu);
+	if (err) {
+		ksft_print_msg("Error, could not set mtu.\n");
+		return TEST_FAILURE;
+	}
+
+	if (ifobj2) {
+		if (pthread_barrier_init(&barr, NULL, 2))
+			return TEST_FAILURE;
+		pkt_stream_reset(ifobj2->xsk->pkt_stream);
+	}
+
+	test->current_step++;
+	pkt_stream_reset(ifobj1->xsk->pkt_stream);
+	pkts_in_flight = 0;
+
+	signal(SIGUSR1, handler);
+	/*Spawn RX thread */
+	pthread_create(&t0, NULL, ifobj1->func_ptr, test);
+
+	if (ifobj2) {
+		pthread_barrier_wait(&barr);
+		if (pthread_barrier_destroy(&barr)) {
+			pthread_kill(t0, SIGUSR1);
+			clean_sockets(test, ifobj1);
+			clean_umem(test, ifobj1, NULL);
+			return TEST_FAILURE;
+		}
+
+		/*Spawn TX thread */
+		pthread_create(&t1, NULL, ifobj2->func_ptr, test);
+
+		pthread_join(t1, NULL);
+	}
+
+	if (!ifobj2)
+		pthread_kill(t0, SIGUSR1);
+	else
+		pthread_join(t0, NULL);
+
+	if (test->total_steps == test->current_step || test->fail) {
+		clean_sockets(test, ifobj1);
+		clean_sockets(test, ifobj2);
+		clean_umem(test, ifobj1, ifobj2);
+	}
+
+	if (test->fail)
+		return TEST_FAILURE;
+
+	return TEST_PASS;
+}
+
+static int testapp_validate_traffic(struct test_spec *test)
+{
+	struct ifobject *ifobj_rx = test->ifobj_rx;
+	struct ifobject *ifobj_tx = test->ifobj_tx;
+
+	if ((ifobj_rx->umem->unaligned_mode && !ifobj_rx->unaligned_supp) ||
+	    (ifobj_tx->umem->unaligned_mode && !ifobj_tx->unaligned_supp)) {
+		ksft_print_msg("No huge pages present.\n");
+		return TEST_SKIP;
+	}
+
+	if (test->set_ring) {
+		if (ifobj_tx->hw_ring_size_supp) {
+			if (set_ring_size(ifobj_tx)) {
+				ksft_print_msg("Failed to change HW ring size.\n");
+				return TEST_FAILURE;
+			}
+		} else {
+			ksft_print_msg("Changing HW ring size not supported.\n");
+			return TEST_SKIP;
+		}
+	}
+
+	if (xsk_attach_xdp_progs(test, ifobj_rx, ifobj_tx))
+		return TEST_FAILURE;
+	return __testapp_validate_traffic(test, ifobj_rx, ifobj_tx);
+}
+
+static int testapp_validate_traffic_single_thread(struct test_spec *test, struct ifobject *ifobj)
+{
+	return __testapp_validate_traffic(test, ifobj, NULL);
+}
+
+int testapp_teardown(struct test_spec *test)
+{
+	int i;
+
+	for (i = 0; i < MAX_TEARDOWN_ITER; i++) {
+		if (testapp_validate_traffic(test))
+			return TEST_FAILURE;
+		test_spec_reset(test);
+	}
+
+	return TEST_PASS;
+}
+
+static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2)
+{
+	thread_func_t tmp_func_ptr = (*ifobj1)->func_ptr;
+	struct ifobject *tmp_ifobj = (*ifobj1);
+
+	(*ifobj1)->func_ptr = (*ifobj2)->func_ptr;
+	(*ifobj2)->func_ptr = tmp_func_ptr;
+
+	*ifobj1 = *ifobj2;
+	*ifobj2 = tmp_ifobj;
+}
+
+int testapp_bidirectional(struct test_spec *test)
+{
+	int res;
+
+	test->ifobj_tx->rx_on = true;
+	test->ifobj_rx->tx_on = true;
+	test->total_steps = 2;
+	if (testapp_validate_traffic(test))
+		return TEST_FAILURE;
+
+	print_verbose("Switching Tx/Rx direction\n");
+	swap_directions(&test->ifobj_rx, &test->ifobj_tx);
+	res = __testapp_validate_traffic(test, test->ifobj_rx, test->ifobj_tx);
+
+	swap_directions(&test->ifobj_rx, &test->ifobj_tx);
+	return res;
+}
+
+static int swap_xsk_resources(struct test_spec *test)
+{
+	int ret;
+
+	test->ifobj_tx->xsk_arr[0].pkt_stream = NULL;
+	test->ifobj_rx->xsk_arr[0].pkt_stream = NULL;
+	test->ifobj_tx->xsk_arr[1].pkt_stream = test->tx_pkt_stream_default;
+	test->ifobj_rx->xsk_arr[1].pkt_stream = test->rx_pkt_stream_default;
+	test->ifobj_tx->xsk = &test->ifobj_tx->xsk_arr[1];
+	test->ifobj_rx->xsk = &test->ifobj_rx->xsk_arr[1];
+
+	ret = xsk_update_xskmap(test->ifobj_rx->xskmap, test->ifobj_rx->xsk->xsk, 0);
+	if (ret)
+		return TEST_FAILURE;
+
+	return TEST_PASS;
+}
+
+int testapp_xdp_prog_cleanup(struct test_spec *test)
+{
+	test->total_steps = 2;
+	test->nb_sockets = 2;
+	if (testapp_validate_traffic(test))
+		return TEST_FAILURE;
+
+	if (swap_xsk_resources(test)) {
+		clean_sockets(test, test->ifobj_rx);
+		clean_sockets(test, test->ifobj_tx);
+		clean_umem(test, test->ifobj_rx, test->ifobj_tx);
+		return TEST_FAILURE;
+	}
+
+	return testapp_validate_traffic(test);
+}
+
+int testapp_headroom(struct test_spec *test)
+{
+	test->ifobj_rx->umem->frame_headroom = UMEM_HEADROOM_TEST_SIZE;
+	return testapp_validate_traffic(test);
+}
+
+int testapp_stats_rx_dropped(struct test_spec *test)
+{
+	if (test->mode == TEST_MODE_ZC) {
+		ksft_print_msg("Can not run RX_DROPPED test for ZC mode\n");
+		return TEST_SKIP;
+	}
+
+	if (pkt_stream_replace_half(test, MIN_PKT_SIZE * 4, 0))
+		return TEST_FAILURE;
+	test->ifobj_rx->umem->frame_headroom = test->ifobj_rx->umem->frame_size -
+		XDP_PACKET_HEADROOM - MIN_PKT_SIZE * 3;
+	if (pkt_stream_receive_half(test))
+		return TEST_FAILURE;
+	test->ifobj_rx->validation_func = validate_rx_dropped;
+	return testapp_validate_traffic(test);
+}
+
+int testapp_stats_tx_invalid_descs(struct test_spec *test)
+{
+	if (pkt_stream_replace_half(test, XSK_UMEM__INVALID_FRAME_SIZE, 0))
+		return TEST_FAILURE;
+	test->ifobj_tx->validation_func = validate_tx_invalid_descs;
+	return testapp_validate_traffic(test);
+}
+
+int testapp_stats_rx_full(struct test_spec *test)
+{
+	if (pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE))
+		return TEST_FAILURE;
+	test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
+
+	test->ifobj_rx->xsk->rxqsize = DEFAULT_UMEM_BUFFERS;
+	test->ifobj_rx->release_rx = false;
+	test->ifobj_rx->validation_func = validate_rx_full;
+	return testapp_validate_traffic(test);
+}
+
+int testapp_stats_fill_empty(struct test_spec *test)
+{
+	if (pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE))
+		return TEST_FAILURE;
+	test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE);
+
+	test->ifobj_rx->use_fill_ring = false;
+	test->ifobj_rx->validation_func = validate_fill_empty;
+	return testapp_validate_traffic(test);
+}
+
+int testapp_send_receive_unaligned(struct test_spec *test)
+{
+	test->ifobj_tx->umem->unaligned_mode = true;
+	test->ifobj_rx->umem->unaligned_mode = true;
+	/* Let half of the packets straddle a 4K buffer boundary */
+	if (pkt_stream_replace_half(test, MIN_PKT_SIZE, -MIN_PKT_SIZE / 2))
+		return TEST_FAILURE;
+
+	return testapp_validate_traffic(test);
+}
+
+int testapp_send_receive_unaligned_mb(struct test_spec *test)
+{
+	test->mtu = MAX_ETH_JUMBO_SIZE;
+	test->ifobj_tx->umem->unaligned_mode = true;
+	test->ifobj_rx->umem->unaligned_mode = true;
+	if (pkt_stream_replace(test, DEFAULT_PKT_CNT, MAX_ETH_JUMBO_SIZE))
+		return TEST_FAILURE;
+	return testapp_validate_traffic(test);
+}
+
+int testapp_single_pkt(struct test_spec *test)
+{
+	struct pkt pkts[] = {{0, MIN_PKT_SIZE, 0, true}};
+
+	if (pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)))
+		return TEST_FAILURE;
+	return testapp_validate_traffic(test);
+}
+
+int testapp_send_receive_mb(struct test_spec *test)
+{
+	test->mtu = MAX_ETH_JUMBO_SIZE;
+	if (pkt_stream_replace(test, DEFAULT_PKT_CNT, MAX_ETH_JUMBO_SIZE))
+		return TEST_FAILURE;
+
+	return testapp_validate_traffic(test);
+}
+
+int testapp_invalid_desc_mb(struct test_spec *test)
+{
+	struct xsk_umem_info *umem = test->ifobj_tx->umem;
+	u64 umem_size = umem->num_frames * umem->frame_size;
+	struct pkt pkts[] = {
+		/* Valid packet for synch to start with */
+		{0, MIN_PKT_SIZE, 0, true, 0},
+		/* Zero frame len is not legal */
+		{0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
+		{0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
+		{0, 0, 0, false, 0},
+		/* Invalid address in the second frame */
+		{0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
+		{umem_size, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
+		/* Invalid len in the middle */
+		{0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
+		{0, XSK_UMEM__INVALID_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
+		/* Invalid options in the middle */
+		{0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
+		{0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XSK_DESC__INVALID_OPTION},
+		/* Transmit 2 frags, receive 3 */
+		{0, XSK_UMEM__MAX_FRAME_SIZE, 0, true, XDP_PKT_CONTD},
+		{0, XSK_UMEM__MAX_FRAME_SIZE, 0, true, 0},
+		/* Middle frame crosses chunk boundary with small length */
+		{0, XSK_UMEM__LARGE_FRAME_SIZE, 0, false, XDP_PKT_CONTD},
+		{-MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false, 0},
+		/* Valid packet for synch so that something is received */
+		{0, MIN_PKT_SIZE, 0, true, 0}};
+
+	if (umem->unaligned_mode) {
+		/* Crossing a chunk boundary allowed */
+		pkts[12].valid = true;
+		pkts[13].valid = true;
+	}
+
+	test->mtu = MAX_ETH_JUMBO_SIZE;
+	if (pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)))
+		return TEST_FAILURE;
+	return testapp_validate_traffic(test);
+}
+
+int testapp_invalid_desc(struct test_spec *test)
+{
+	struct xsk_umem_info *umem = test->ifobj_tx->umem;
+	u64 umem_size = umem->num_frames * umem->frame_size;
+	struct pkt pkts[] = {
+		/* Zero packet address allowed */
+		{0, MIN_PKT_SIZE, 0, true},
+		/* Allowed packet */
+		{0, MIN_PKT_SIZE, 0, true},
+		/* Straddling the start of umem */
+		{-2, MIN_PKT_SIZE, 0, false},
+		/* Packet too large */
+		{0, XSK_UMEM__INVALID_FRAME_SIZE, 0, false},
+		/* Up to end of umem allowed */
+		{umem_size - MIN_PKT_SIZE - 2 * umem->frame_size, MIN_PKT_SIZE, 0, true},
+		/* After umem ends */
+		{umem_size, MIN_PKT_SIZE, 0, false},
+		/* Straddle the end of umem */
+		{umem_size - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false},
+		/* Straddle a 4K boundary */
+		{0x1000 - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, false},
+		/* Straddle a 2K boundary */
+		{0x800 - MIN_PKT_SIZE / 2, MIN_PKT_SIZE, 0, true},
+		/* Valid packet for synch so that something is received */
+		{0, MIN_PKT_SIZE, 0, true}};
+
+	if (umem->unaligned_mode) {
+		/* Crossing a page boundary allowed */
+		pkts[7].valid = true;
+	}
+	if (umem->frame_size == XSK_UMEM__DEFAULT_FRAME_SIZE / 2) {
+		/* Crossing a 2K frame size boundary not allowed */
+		pkts[8].valid = false;
+	}
+
+	if (test->ifobj_tx->shared_umem) {
+		pkts[4].offset += umem_size;
+		pkts[5].offset += umem_size;
+		pkts[6].offset += umem_size;
+	}
+
+	if (pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)))
+		return TEST_FAILURE;
+	return testapp_validate_traffic(test);
+}
+
+int testapp_xdp_drop(struct test_spec *test)
+{
+	struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs;
+	struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs;
+
+	test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_drop, skel_tx->progs.xsk_xdp_drop,
+			       skel_rx->maps.xsk, skel_tx->maps.xsk);
+
+	if (pkt_stream_receive_half(test))
+		return TEST_FAILURE;
+	return testapp_validate_traffic(test);
+}
+
+int testapp_xdp_metadata_copy(struct test_spec *test)
+{
+	struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs;
+	struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs;
+
+	test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_populate_metadata,
+			       skel_tx->progs.xsk_xdp_populate_metadata,
+			       skel_rx->maps.xsk, skel_tx->maps.xsk);
+	test->ifobj_rx->use_metadata = true;
+
+	skel_rx->bss->count = 0;
+
+	return testapp_validate_traffic(test);
+}
+
+int testapp_xdp_shared_umem(struct test_spec *test)
+{
+	struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs;
+	struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs;
+	int ret;
+
+	test->total_steps = 1;
+	test->nb_sockets = 2;
+
+	test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_shared_umem,
+			       skel_tx->progs.xsk_xdp_shared_umem,
+			       skel_rx->maps.xsk, skel_tx->maps.xsk);
+
+	if (pkt_stream_even_odd_sequence(test))
+		return TEST_FAILURE;
+
+	ret = testapp_validate_traffic(test);
+
+	release_even_odd_sequence(test);
+
+	return ret;
+}
+
+int testapp_poll_txq_tmout(struct test_spec *test)
+{
+	test->ifobj_tx->use_poll = true;
+	/* create invalid frame by set umem frame_size and pkt length equal to 2048 */
+	test->ifobj_tx->umem->frame_size = 2048;
+	if (pkt_stream_replace(test, 2 * DEFAULT_PKT_CNT, 2048))
+		return TEST_FAILURE;
+	return testapp_validate_traffic_single_thread(test, test->ifobj_tx);
+}
+
+int testapp_poll_rxq_tmout(struct test_spec *test)
+{
+	test->ifobj_rx->use_poll = true;
+	return testapp_validate_traffic_single_thread(test, test->ifobj_rx);
+}
+
+int testapp_too_many_frags(struct test_spec *test)
+{
+	struct pkt *pkts;
+	u32 max_frags, i;
+	int ret = TEST_FAILURE;
+
+	if (test->mode == TEST_MODE_ZC) {
+		max_frags = test->ifobj_tx->xdp_zc_max_segs;
+	} else {
+		max_frags = get_max_skb_frags();
+		if (!max_frags) {
+			ksft_print_msg("Can't get MAX_SKB_FRAGS from system, using default (17)\n");
+			max_frags = 17;
+		}
+		max_frags += 1;
+	}
+
+	pkts = calloc(2 * max_frags + 2, sizeof(struct pkt));
+	if (!pkts)
+		return TEST_FAILURE;
+
+	test->mtu = MAX_ETH_JUMBO_SIZE;
+
+	/* Valid packet for synch */
+	pkts[0].len = MIN_PKT_SIZE;
+	pkts[0].valid = true;
+
+	/* One valid packet with the max amount of frags */
+	for (i = 1; i < max_frags + 1; i++) {
+		pkts[i].len = MIN_PKT_SIZE;
+		pkts[i].options = XDP_PKT_CONTD;
+		pkts[i].valid = true;
+	}
+	pkts[max_frags].options = 0;
+
+	/* An invalid packet with the max amount of frags but signals packet
+	 * continues on the last frag
+	 */
+	for (i = max_frags + 1; i < 2 * max_frags + 1; i++) {
+		pkts[i].len = MIN_PKT_SIZE;
+		pkts[i].options = XDP_PKT_CONTD;
+		pkts[i].valid = false;
+	}
+
+	/* Valid packet for synch */
+	pkts[2 * max_frags + 1].len = MIN_PKT_SIZE;
+	pkts[2 * max_frags + 1].valid = true;
+
+	if (pkt_stream_generate_custom(test, pkts, 2 * max_frags + 2)) {
+		free(pkts);
+		return TEST_FAILURE;
+	}
+
+	ret = testapp_validate_traffic(test);
+	free(pkts);
+	return ret;
+}
+
+static int xsk_load_xdp_programs(struct ifobject *ifobj)
+{
+	ifobj->xdp_progs = xsk_xdp_progs__open_and_load();
+	if (libbpf_get_error(ifobj->xdp_progs))
+		return libbpf_get_error(ifobj->xdp_progs);
+
+	return 0;
+}
+
+/* Simple test */
+static bool hugepages_present(void)
+{
+	size_t mmap_sz = 2 * DEFAULT_UMEM_BUFFERS * XSK_UMEM__DEFAULT_FRAME_SIZE;
+	void *bufs;
+
+	bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE,
+		    MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, MAP_HUGE_2MB);
+	if (bufs == MAP_FAILED)
+		return false;
+
+	mmap_sz = ceil_u64(mmap_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE;
+	munmap(bufs, mmap_sz);
+	return true;
+}
+
+int init_iface(struct ifobject *ifobj, thread_func_t func_ptr)
+{
+	LIBBPF_OPTS(bpf_xdp_query_opts, query_opts);
+	int err;
+
+	ifobj->func_ptr = func_ptr;
+
+	err = xsk_load_xdp_programs(ifobj);
+	if (err) {
+		ksft_print_msg("Error loading XDP program\n");
+		return err;
+	}
+
+	if (hugepages_present())
+		ifobj->unaligned_supp = true;
+
+	err = bpf_xdp_query(ifobj->ifindex, XDP_FLAGS_DRV_MODE, &query_opts);
+	if (err) {
+		ksft_print_msg("Error querying XDP capabilities\n");
+		return err;
+	}
+	if (query_opts.feature_flags & NETDEV_XDP_ACT_RX_SG)
+		ifobj->multi_buff_supp = true;
+	if (query_opts.feature_flags & NETDEV_XDP_ACT_XSK_ZEROCOPY) {
+		if (query_opts.xdp_zc_max_segs > 1) {
+			ifobj->multi_buff_zc_supp = true;
+			ifobj->xdp_zc_max_segs = query_opts.xdp_zc_max_segs;
+		} else {
+			ifobj->xdp_zc_max_segs = 0;
+		}
+	}
+
+	return 0;
+}
+
+int testapp_send_receive(struct test_spec *test)
+{
+	return testapp_validate_traffic(test);
+}
+
+int testapp_send_receive_2k_frame(struct test_spec *test)
+{
+	test->ifobj_tx->umem->frame_size = 2048;
+	test->ifobj_rx->umem->frame_size = 2048;
+	if (pkt_stream_replace(test, DEFAULT_PKT_CNT, MIN_PKT_SIZE))
+		return TEST_FAILURE;
+	return testapp_validate_traffic(test);
+}
+
+int testapp_poll_rx(struct test_spec *test)
+{
+	test->ifobj_rx->use_poll = true;
+	return testapp_validate_traffic(test);
+}
+
+int testapp_poll_tx(struct test_spec *test)
+{
+	test->ifobj_tx->use_poll = true;
+	return testapp_validate_traffic(test);
+}
+
+int testapp_aligned_inv_desc(struct test_spec *test)
+{
+	return testapp_invalid_desc(test);
+}
+
+int testapp_aligned_inv_desc_2k_frame(struct test_spec *test)
+{
+	test->ifobj_tx->umem->frame_size = 2048;
+	test->ifobj_rx->umem->frame_size = 2048;
+	return testapp_invalid_desc(test);
+}
+
+int testapp_unaligned_inv_desc(struct test_spec *test)
+{
+	test->ifobj_tx->umem->unaligned_mode = true;
+	test->ifobj_rx->umem->unaligned_mode = true;
+	return testapp_invalid_desc(test);
+}
+
+int testapp_unaligned_inv_desc_4001_frame(struct test_spec *test)
+{
+	u64 page_size, umem_size;
+
+	/* Odd frame size so the UMEM doesn't end near a page boundary. */
+	test->ifobj_tx->umem->frame_size = 4001;
+	test->ifobj_rx->umem->frame_size = 4001;
+	test->ifobj_tx->umem->unaligned_mode = true;
+	test->ifobj_rx->umem->unaligned_mode = true;
+	/* This test exists to test descriptors that staddle the end of
+	 * the UMEM but not a page.
+	 */
+	page_size = sysconf(_SC_PAGESIZE);
+	umem_size = test->ifobj_tx->umem->num_frames * test->ifobj_tx->umem->frame_size;
+	assert(umem_size % page_size > MIN_PKT_SIZE);
+	assert(umem_size % page_size < page_size - MIN_PKT_SIZE);
+
+	return testapp_invalid_desc(test);
+}
+
+int testapp_aligned_inv_desc_mb(struct test_spec *test)
+{
+	return testapp_invalid_desc_mb(test);
+}
+
+int testapp_unaligned_inv_desc_mb(struct test_spec *test)
+{
+	test->ifobj_tx->umem->unaligned_mode = true;
+	test->ifobj_rx->umem->unaligned_mode = true;
+	return testapp_invalid_desc_mb(test);
+}
+
+int testapp_xdp_metadata(struct test_spec *test)
+{
+	return testapp_xdp_metadata_copy(test);
+}
+
+int testapp_xdp_metadata_mb(struct test_spec *test)
+{
+	test->mtu = MAX_ETH_JUMBO_SIZE;
+	return testapp_xdp_metadata_copy(test);
+}
+
+int testapp_hw_sw_min_ring_size(struct test_spec *test)
+{
+	int ret;
+
+	test->set_ring = true;
+	test->total_steps = 2;
+	test->ifobj_tx->ring.tx_pending = DEFAULT_BATCH_SIZE;
+	test->ifobj_tx->ring.rx_pending = DEFAULT_BATCH_SIZE * 2;
+	test->ifobj_tx->xsk->batch_size = 1;
+	test->ifobj_rx->xsk->batch_size = 1;
+	ret = testapp_validate_traffic(test);
+	if (ret)
+		return ret;
+
+	/* Set batch size to hw_ring_size - 1 */
+	test->ifobj_tx->xsk->batch_size = DEFAULT_BATCH_SIZE - 1;
+	test->ifobj_rx->xsk->batch_size = DEFAULT_BATCH_SIZE - 1;
+	return testapp_validate_traffic(test);
+}
+
+int testapp_hw_sw_max_ring_size(struct test_spec *test)
+{
+	u32 max_descs = XSK_RING_PROD__DEFAULT_NUM_DESCS * 4;
+	int ret;
+
+	test->set_ring = true;
+	test->total_steps = 2;
+	test->ifobj_tx->ring.tx_pending = test->ifobj_tx->ring.tx_max_pending;
+	test->ifobj_tx->ring.rx_pending  = test->ifobj_tx->ring.rx_max_pending;
+	test->ifobj_rx->umem->num_frames = max_descs;
+	test->ifobj_rx->umem->fill_size = max_descs;
+	test->ifobj_rx->umem->comp_size = max_descs;
+	test->ifobj_tx->xsk->batch_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
+	test->ifobj_rx->xsk->batch_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
+
+	ret = testapp_validate_traffic(test);
+	if (ret)
+		return ret;
+
+	/* Set batch_size to 8152 for testing, as the ice HW ignores the 3 lowest bits when
+	 * updating the Rx HW tail register.
+	 */
+	test->ifobj_tx->xsk->batch_size = test->ifobj_tx->ring.tx_max_pending - 8;
+	test->ifobj_rx->xsk->batch_size = test->ifobj_tx->ring.tx_max_pending - 8;
+	if (pkt_stream_replace(test, max_descs, MIN_PKT_SIZE)) {
+		clean_sockets(test, test->ifobj_tx);
+		clean_sockets(test, test->ifobj_rx);
+		clean_umem(test, test->ifobj_rx, test->ifobj_tx);
+		return TEST_FAILURE;
+	}
+
+	return testapp_validate_traffic(test);
+}
+
+static int testapp_xdp_adjust_tail(struct test_spec *test, int adjust_value)
+{
+	struct xsk_xdp_progs *skel_rx = test->ifobj_rx->xdp_progs;
+	struct xsk_xdp_progs *skel_tx = test->ifobj_tx->xdp_progs;
+
+	test_spec_set_xdp_prog(test, skel_rx->progs.xsk_xdp_adjust_tail,
+			       skel_tx->progs.xsk_xdp_adjust_tail,
+			       skel_rx->maps.xsk, skel_tx->maps.xsk);
+
+	skel_rx->bss->adjust_value = adjust_value;
+
+	return testapp_validate_traffic(test);
+}
+
+static int testapp_adjust_tail(struct test_spec *test, u32 value, u32 pkt_len)
+{
+	int ret;
+
+	test->adjust_tail_support = true;
+	test->adjust_tail = true;
+	test->total_steps = 1;
+
+	ret = pkt_stream_replace_ifobject(test->ifobj_tx, DEFAULT_BATCH_SIZE, pkt_len);
+	if (ret)
+		return TEST_FAILURE;
+
+	ret = pkt_stream_replace_ifobject(test->ifobj_rx, DEFAULT_BATCH_SIZE, pkt_len + value);
+	if (ret)
+		return TEST_FAILURE;
+
+	ret = testapp_xdp_adjust_tail(test, value);
+	if (ret)
+		return ret;
+
+	if (!test->adjust_tail_support) {
+		ksft_print_msg("%s %sResize pkt with bpf_xdp_adjust_tail() not supported\n",
+				      mode_string(test), busy_poll_string(test));
+		return TEST_SKIP;
+	}
+
+	return 0;
+}
+
+int testapp_adjust_tail_shrink(struct test_spec *test)
+{
+	/* Shrink by 4 bytes for testing purpose */
+	return testapp_adjust_tail(test, -4, MIN_PKT_SIZE * 2);
+}
+
+int testapp_adjust_tail_shrink_mb(struct test_spec *test)
+{
+	test->mtu = MAX_ETH_JUMBO_SIZE;
+	/* Shrink by the frag size */
+	return testapp_adjust_tail(test, -XSK_UMEM__MAX_FRAME_SIZE, XSK_UMEM__LARGE_FRAME_SIZE * 2);
+}
+
+int testapp_adjust_tail_grow(struct test_spec *test)
+{
+	/* Grow by 4 bytes for testing purpose */
+	return testapp_adjust_tail(test, 4, MIN_PKT_SIZE * 2);
+}
+
+int testapp_adjust_tail_grow_mb(struct test_spec *test)
+{
+	test->mtu = MAX_ETH_JUMBO_SIZE;
+	/* Grow by (frag_size - last_frag_Size) - 1 to stay inside the last fragment */
+	return testapp_adjust_tail(test, (XSK_UMEM__MAX_FRAME_SIZE / 2) - 1,
+				   XSK_UMEM__LARGE_FRAME_SIZE * 2);
+}
+
+int testapp_tx_queue_consumer(struct test_spec *test)
+{
+	int nr_packets;
+
+	if (test->mode == TEST_MODE_ZC) {
+		ksft_print_msg("Can not run TX_QUEUE_CONSUMER test for ZC mode\n");
+		return TEST_SKIP;
+	}
+
+	nr_packets = MAX_TX_BUDGET_DEFAULT + 1;
+	if (pkt_stream_replace(test, nr_packets, MIN_PKT_SIZE))
+		return TEST_FAILURE;
+	test->ifobj_tx->xsk->batch_size = nr_packets;
+	test->ifobj_tx->xsk->check_consumer = true;
+
+	return testapp_validate_traffic(test);
+}
+
+struct ifobject *ifobject_create(void)
+{
+	struct ifobject *ifobj;
+
+	ifobj = calloc(1, sizeof(struct ifobject));
+	if (!ifobj)
+		return NULL;
+
+	ifobj->xsk_arr = calloc(MAX_SOCKETS, sizeof(*ifobj->xsk_arr));
+	if (!ifobj->xsk_arr)
+		goto out_xsk_arr;
+
+	ifobj->umem = calloc(1, sizeof(*ifobj->umem));
+	if (!ifobj->umem)
+		goto out_umem;
+
+	return ifobj;
+
+out_umem:
+	free(ifobj->xsk_arr);
+out_xsk_arr:
+	free(ifobj);
+	return NULL;
+}
+
+void ifobject_delete(struct ifobject *ifobj)
+{
+	free(ifobj->umem);
+	free(ifobj->xsk_arr);
+	free(ifobj);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_xsk.h b/tools/testing/selftests/bpf/prog_tests/test_xsk.h
new file mode 100644
index 000000000000..8fc78a057de0
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_xsk.h
@@ -0,0 +1,298 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef TEST_XSK_H_
+#define TEST_XSK_H_
+
+#include <linux/ethtool.h>
+#include <linux/if_xdp.h>
+
+#include "../kselftest.h"
+#include "xsk.h"
+
+#ifndef SO_PREFER_BUSY_POLL
+#define SO_PREFER_BUSY_POLL 69
+#endif
+
+#ifndef SO_BUSY_POLL_BUDGET
+#define SO_BUSY_POLL_BUDGET 70
+#endif
+
+#define TEST_PASS 0
+#define TEST_FAILURE -1
+#define TEST_CONTINUE 1
+#define TEST_SKIP 2
+
+#define DEFAULT_PKT_CNT			(4 * 1024)
+#define DEFAULT_UMEM_BUFFERS		(DEFAULT_PKT_CNT / 4)
+#define HUGEPAGE_SIZE			(2 * 1024 * 1024)
+#define MIN_PKT_SIZE			64
+#define MAX_ETH_PKT_SIZE		1518
+#define MAX_INTERFACE_NAME_CHARS	16
+#define MAX_TEST_NAME_SIZE		48
+#define SOCK_RECONF_CTR			10
+#define USLEEP_MAX			10000
+
+extern bool opt_verbose;
+#define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0)
+
+
+static inline u32 ceil_u32(u32 a, u32 b)
+{
+	return (a + b - 1) / b;
+}
+
+static inline u64 ceil_u64(u64 a, u64 b)
+{
+	return (a + b - 1) / b;
+}
+
+/* Simple test */
+enum test_mode {
+	TEST_MODE_SKB,
+	TEST_MODE_DRV,
+	TEST_MODE_ZC,
+	TEST_MODE_ALL
+};
+
+struct ifobject;
+struct test_spec;
+typedef int (*validation_func_t)(struct ifobject *ifobj);
+typedef void *(*thread_func_t)(void *arg);
+typedef int (*test_func_t)(struct test_spec *test);
+
+struct xsk_socket_info {
+	struct xsk_ring_cons rx;
+	struct xsk_ring_prod tx;
+	struct xsk_umem_info *umem;
+	struct xsk_socket *xsk;
+	struct pkt_stream *pkt_stream;
+	u32 outstanding_tx;
+	u32 rxqsize;
+	u32 batch_size;
+	u8 dst_mac[ETH_ALEN];
+	u8 src_mac[ETH_ALEN];
+	bool check_consumer;
+};
+
+int kick_rx(struct xsk_socket_info *xsk);
+int kick_tx(struct xsk_socket_info *xsk);
+
+struct xsk_umem_info {
+	struct xsk_ring_prod fq;
+	struct xsk_ring_cons cq;
+	struct xsk_umem *umem;
+	u64 next_buffer;
+	u32 num_frames;
+	u32 frame_headroom;
+	void *buffer;
+	u32 frame_size;
+	u32 base_addr;
+	u32 fill_size;
+	u32 comp_size;
+	bool unaligned_mode;
+};
+
+struct set_hw_ring {
+	u32 default_tx;
+	u32 default_rx;
+};
+
+int hw_ring_size_reset(struct ifobject *ifobj);
+
+struct ifobject {
+	char ifname[MAX_INTERFACE_NAME_CHARS];
+	struct xsk_socket_info *xsk;
+	struct xsk_socket_info *xsk_arr;
+	struct xsk_umem_info *umem;
+	thread_func_t func_ptr;
+	validation_func_t validation_func;
+	struct xsk_xdp_progs *xdp_progs;
+	struct bpf_map *xskmap;
+	struct bpf_program *xdp_prog;
+	struct ethtool_ringparam ring;
+	struct set_hw_ring set_ring;
+	enum test_mode mode;
+	int ifindex;
+	int mtu;
+	u32 bind_flags;
+	u32 xdp_zc_max_segs;
+	bool tx_on;
+	bool rx_on;
+	bool use_poll;
+	bool busy_poll;
+	bool use_fill_ring;
+	bool release_rx;
+	bool shared_umem;
+	bool use_metadata;
+	bool unaligned_supp;
+	bool multi_buff_supp;
+	bool multi_buff_zc_supp;
+	bool hw_ring_size_supp;
+};
+struct ifobject *ifobject_create(void);
+void ifobject_delete(struct ifobject *ifobj);
+int init_iface(struct ifobject *ifobj, thread_func_t func_ptr);
+
+int xsk_configure_umem(struct ifobject *ifobj, struct xsk_umem_info *umem, void *buffer, u64 size);
+int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem,
+			 struct ifobject *ifobject, bool shared);
+
+
+struct pkt {
+	int offset;
+	u32 len;
+	u32 pkt_nb;
+	bool valid;
+	u16 options;
+};
+
+struct pkt_stream {
+	u32 nb_pkts;
+	u32 current_pkt_nb;
+	struct pkt *pkts;
+	u32 max_pkt_len;
+	u32 nb_rx_pkts;
+	u32 nb_valid_entries;
+	bool verbatim;
+};
+
+static inline bool pkt_continues(u32 options)
+{
+	return options & XDP_PKT_CONTD;
+}
+
+struct pkt_stream *pkt_stream_generate(u32 nb_pkts, u32 pkt_len);
+void pkt_stream_delete(struct pkt_stream *pkt_stream);
+void pkt_stream_reset(struct pkt_stream *pkt_stream);
+void pkt_stream_restore_default(struct test_spec *test);
+
+struct test_spec {
+	struct ifobject *ifobj_tx;
+	struct ifobject *ifobj_rx;
+	struct pkt_stream *tx_pkt_stream_default;
+	struct pkt_stream *rx_pkt_stream_default;
+	struct bpf_program *xdp_prog_rx;
+	struct bpf_program *xdp_prog_tx;
+	struct bpf_map *xskmap_rx;
+	struct bpf_map *xskmap_tx;
+	test_func_t test_func;
+	int mtu;
+	u16 total_steps;
+	u16 current_step;
+	u16 nb_sockets;
+	bool fail;
+	bool set_ring;
+	bool adjust_tail;
+	bool adjust_tail_support;
+	enum test_mode mode;
+	char name[MAX_TEST_NAME_SIZE];
+};
+
+#define busy_poll_string(test) (test)->ifobj_tx->busy_poll ? "BUSY-POLL " : ""
+static inline char *mode_string(struct test_spec *test)
+{
+	switch (test->mode) {
+	case TEST_MODE_SKB:
+		return "SKB";
+	case TEST_MODE_DRV:
+		return "DRV";
+	case TEST_MODE_ZC:
+		return "ZC";
+	default:
+		return "BOGUS";
+	}
+}
+
+void test_init(struct test_spec *test, struct ifobject *ifobj_tx,
+	       struct ifobject *ifobj_rx, enum test_mode mode,
+	       const struct test_spec *test_to_run);
+
+int testapp_adjust_tail_grow(struct test_spec *test);
+int testapp_adjust_tail_grow_mb(struct test_spec *test);
+int testapp_adjust_tail_shrink(struct test_spec *test);
+int testapp_adjust_tail_shrink_mb(struct test_spec *test);
+int testapp_aligned_inv_desc(struct test_spec *test);
+int testapp_aligned_inv_desc_2k_frame(struct test_spec *test);
+int testapp_aligned_inv_desc_mb(struct test_spec *test);
+int testapp_bidirectional(struct test_spec *test);
+int testapp_headroom(struct test_spec *test);
+int testapp_hw_sw_max_ring_size(struct test_spec *test);
+int testapp_hw_sw_min_ring_size(struct test_spec *test);
+int testapp_poll_rx(struct test_spec *test);
+int testapp_poll_rxq_tmout(struct test_spec *test);
+int testapp_poll_tx(struct test_spec *test);
+int testapp_poll_txq_tmout(struct test_spec *test);
+int testapp_send_receive(struct test_spec *test);
+int testapp_send_receive_2k_frame(struct test_spec *test);
+int testapp_send_receive_mb(struct test_spec *test);
+int testapp_send_receive_unaligned(struct test_spec *test);
+int testapp_send_receive_unaligned_mb(struct test_spec *test);
+int testapp_single_pkt(struct test_spec *test);
+int testapp_stats_fill_empty(struct test_spec *test);
+int testapp_stats_rx_dropped(struct test_spec *test);
+int testapp_stats_tx_invalid_descs(struct test_spec *test);
+int testapp_stats_rx_full(struct test_spec *test);
+int testapp_teardown(struct test_spec *test);
+int testapp_too_many_frags(struct test_spec *test);
+int testapp_tx_queue_consumer(struct test_spec *test);
+int testapp_unaligned_inv_desc(struct test_spec *test);
+int testapp_unaligned_inv_desc_4001_frame(struct test_spec *test);
+int testapp_unaligned_inv_desc_mb(struct test_spec *test);
+int testapp_xdp_drop(struct test_spec *test);
+int testapp_xdp_metadata(struct test_spec *test);
+int testapp_xdp_metadata_mb(struct test_spec *test);
+int testapp_xdp_prog_cleanup(struct test_spec *test);
+int testapp_xdp_shared_umem(struct test_spec *test);
+
+void *worker_testapp_validate_rx(void *arg);
+void *worker_testapp_validate_tx(void *arg);
+
+static const struct test_spec tests[] = {
+	{.name = "SEND_RECEIVE", .test_func = testapp_send_receive},
+	{.name = "SEND_RECEIVE_2K_FRAME", .test_func = testapp_send_receive_2k_frame},
+	{.name = "SEND_RECEIVE_SINGLE_PKT", .test_func = testapp_single_pkt},
+	{.name = "POLL_RX", .test_func = testapp_poll_rx},
+	{.name = "POLL_TX", .test_func = testapp_poll_tx},
+	{.name = "POLL_RXQ_FULL", .test_func = testapp_poll_rxq_tmout},
+	{.name = "POLL_TXQ_FULL", .test_func = testapp_poll_txq_tmout},
+	{.name = "ALIGNED_INV_DESC", .test_func = testapp_aligned_inv_desc},
+	{.name = "ALIGNED_INV_DESC_2K_FRAME_SIZE", .test_func = testapp_aligned_inv_desc_2k_frame},
+	{.name = "UMEM_HEADROOM", .test_func = testapp_headroom},
+	{.name = "BIDIRECTIONAL", .test_func = testapp_bidirectional},
+	{.name = "STAT_RX_DROPPED", .test_func = testapp_stats_rx_dropped},
+	{.name = "STAT_TX_INVALID", .test_func = testapp_stats_tx_invalid_descs},
+	{.name = "STAT_RX_FULL", .test_func = testapp_stats_rx_full},
+	{.name = "STAT_FILL_EMPTY", .test_func = testapp_stats_fill_empty},
+	{.name = "XDP_PROG_CLEANUP", .test_func = testapp_xdp_prog_cleanup},
+	{.name = "XDP_DROP_HALF", .test_func = testapp_xdp_drop},
+	{.name = "XDP_SHARED_UMEM", .test_func = testapp_xdp_shared_umem},
+	{.name = "XDP_METADATA_COPY", .test_func = testapp_xdp_metadata},
+	{.name = "XDP_METADATA_COPY_MULTI_BUFF", .test_func = testapp_xdp_metadata_mb},
+	{.name = "ALIGNED_INV_DESC_MULTI_BUFF", .test_func = testapp_aligned_inv_desc_mb},
+	{.name = "TOO_MANY_FRAGS", .test_func = testapp_too_many_frags},
+	{.name = "XDP_ADJUST_TAIL_SHRINK", .test_func = testapp_adjust_tail_shrink},
+	{.name = "TX_QUEUE_CONSUMER", .test_func = testapp_tx_queue_consumer},
+	};
+
+static const struct test_spec ci_skip_tests[] = {
+	/* Flaky tests */
+	{.name = "XDP_ADJUST_TAIL_SHRINK_MULTI_BUFF", .test_func = testapp_adjust_tail_shrink_mb},
+	{.name = "XDP_ADJUST_TAIL_GROW", .test_func = testapp_adjust_tail_grow},
+	{.name = "XDP_ADJUST_TAIL_GROW_MULTI_BUFF", .test_func = testapp_adjust_tail_grow_mb},
+	{.name = "SEND_RECEIVE_9K_PACKETS", .test_func = testapp_send_receive_mb},
+	/* Tests with huge page dependency */
+	{.name = "SEND_RECEIVE_UNALIGNED", .test_func = testapp_send_receive_unaligned},
+	{.name = "UNALIGNED_INV_DESC", .test_func = testapp_unaligned_inv_desc},
+	{.name = "UNALIGNED_INV_DESC_4001_FRAME_SIZE",
+	 .test_func = testapp_unaligned_inv_desc_4001_frame},
+	{.name = "SEND_RECEIVE_UNALIGNED_9K_PACKETS",
+	 .test_func = testapp_send_receive_unaligned_mb},
+	{.name = "UNALIGNED_INV_DESC_MULTI_BUFF", .test_func = testapp_unaligned_inv_desc_mb},
+	/* Test with HW ring size dependency */
+	{.name = "HW_SW_MIN_RING_SIZE", .test_func = testapp_hw_sw_min_ring_size},
+	{.name = "HW_SW_MAX_RING_SIZE", .test_func = testapp_hw_sw_max_ring_size},
+	/* Too long test */
+	{.name = "TEARDOWN", .test_func = testapp_teardown},
+};
+
+
+#endif				/* TEST_XSK_H_ */
diff --git a/tools/testing/selftests/bpf/prog_tests/time_tai.c b/tools/testing/selftests/bpf/prog_tests/time_tai.c
index a31119823666..f45af1b0ef2c 100644
--- a/tools/testing/selftests/bpf/prog_tests/time_tai.c
+++ b/tools/testing/selftests/bpf/prog_tests/time_tai.c
@@ -56,7 +56,7 @@ void test_time_tai(void)
 	ASSERT_NEQ(ts2, 0, "tai_ts2");
 
 	/* TAI is moving forward only */
-	ASSERT_GT(ts2, ts1, "tai_forward");
+	ASSERT_GE(ts2, ts1, "tai_forward");
 
 	/* Check for future */
 	ret = clock_gettime(CLOCK_TAI, &now_tai);
diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c
index 7eb049214859..34f9ccce2602 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer.c
@@ -2,11 +2,32 @@
 /* Copyright (c) 2021 Facebook */
 #include <test_progs.h>
 #include "timer.skel.h"
+#include "timer_failure.skel.h"
+#include "timer_interrupt.skel.h"
+
+#define NUM_THR 8
+
+static void *spin_lock_thread(void *arg)
+{
+	int i, err, prog_fd = *(int *)arg;
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+
+	for (i = 0; i < 10000; i++) {
+		err = bpf_prog_test_run_opts(prog_fd, &topts);
+		if (!ASSERT_OK(err, "test_run_opts err") ||
+		    !ASSERT_OK(topts.retval, "test_run_opts retval"))
+			break;
+	}
+
+	pthread_exit(arg);
+}
 
 static int timer(struct timer *timer_skel)
 {
-	int err, prog_fd;
+	int i, err, prog_fd;
 	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	pthread_t thread_id[NUM_THR];
+	void *ret;
 
 	err = timer__attach(timer_skel);
 	if (!ASSERT_OK(err, "timer_attach"))
@@ -14,6 +35,7 @@ static int timer(struct timer *timer_skel)
 
 	ASSERT_EQ(timer_skel->data->callback_check, 52, "callback_check1");
 	ASSERT_EQ(timer_skel->data->callback2_check, 52, "callback2_check1");
+	ASSERT_EQ(timer_skel->bss->pinned_callback_check, 0, "pinned_callback_check1");
 
 	prog_fd = bpf_program__fd(timer_skel->progs.test1);
 	err = bpf_prog_test_run_opts(prog_fd, &topts);
@@ -29,12 +51,32 @@ static int timer(struct timer *timer_skel)
 	/* check that timer_cb2() was executed twice */
 	ASSERT_EQ(timer_skel->bss->bss_data, 10, "bss_data");
 
+	/* check that timer_cb3() was executed twice */
+	ASSERT_EQ(timer_skel->bss->abs_data, 12, "abs_data");
+
+	/* check that timer_cb_pinned() was executed twice */
+	ASSERT_EQ(timer_skel->bss->pinned_callback_check, 2, "pinned_callback_check");
+
 	/* check that there were no errors in timer execution */
 	ASSERT_EQ(timer_skel->bss->err, 0, "err");
 
 	/* check that code paths completed */
 	ASSERT_EQ(timer_skel->bss->ok, 1 | 2 | 4, "ok");
 
+	prog_fd = bpf_program__fd(timer_skel->progs.race);
+	for (i = 0; i < NUM_THR; i++) {
+		err = pthread_create(&thread_id[i], NULL,
+				     &spin_lock_thread, &prog_fd);
+		if (!ASSERT_OK(err, "pthread_create"))
+			break;
+	}
+
+	while (i) {
+		err = pthread_join(thread_id[--i], &ret);
+		if (ASSERT_OK(err, "pthread_join"))
+			ASSERT_EQ(ret, (void *)&prog_fd, "pthread_join");
+	}
+
 	return 0;
 }
 
@@ -45,11 +87,49 @@ void serial_test_timer(void)
 	int err;
 
 	timer_skel = timer__open_and_load();
+	if (!timer_skel && errno == EOPNOTSUPP) {
+		test__skip();
+		return;
+	}
 	if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load"))
-		goto cleanup;
+		return;
 
 	err = timer(timer_skel);
 	ASSERT_OK(err, "timer");
-cleanup:
 	timer__destroy(timer_skel);
+
+	RUN_TESTS(timer_failure);
+}
+
+void test_timer_interrupt(void)
+{
+	struct timer_interrupt *skel = NULL;
+	int err, prog_fd;
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+
+	skel = timer_interrupt__open_and_load();
+	if (!skel && errno == EOPNOTSUPP) {
+		test__skip();
+		return;
+	}
+	if (!ASSERT_OK_PTR(skel, "timer_interrupt__open_and_load"))
+		return;
+
+	err = timer_interrupt__attach(skel);
+	if (!ASSERT_OK(err, "timer_interrupt__attach"))
+		goto out;
+
+	prog_fd = bpf_program__fd(skel->progs.test_timer_interrupt);
+	err = bpf_prog_test_run_opts(prog_fd, &opts);
+	if (!ASSERT_OK(err, "bpf_prog_test_run_opts"))
+		goto out;
+
+	usleep(50);
+
+	ASSERT_EQ(skel->bss->in_interrupt, 0, "in_interrupt");
+	if (skel->bss->preempt_count)
+		ASSERT_NEQ(skel->bss->in_interrupt_cb, 0, "in_interrupt_cb");
+
+out:
+	timer_interrupt__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_crash.c b/tools/testing/selftests/bpf/prog_tests/timer_crash.c
index f74b82305da8..b841597c8a3a 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer_crash.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer_crash.c
@@ -12,6 +12,10 @@ static void test_timer_crash_mode(int mode)
 	struct timer_crash *skel;
 
 	skel = timer_crash__open_and_load();
+	if (!skel && errno == EOPNOTSUPP) {
+		test__skip();
+		return;
+	}
 	if (!ASSERT_OK_PTR(skel, "timer_crash__open_and_load"))
 		return;
 	skel->bss->pid = getpid();
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_lockup.c b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c
new file mode 100644
index 000000000000..eb303fa1e09a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c
@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <sched.h>
+#include <test_progs.h>
+#include <pthread.h>
+#include <network_helpers.h>
+#include <sys/sysinfo.h>
+
+#include "timer_lockup.skel.h"
+
+static long cpu;
+static int *timer1_err;
+static int *timer2_err;
+static bool skip;
+
+volatile int k = 0;
+
+static void *timer_lockup_thread(void *arg)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts,
+		.data_in	= &pkt_v4,
+		.data_size_in	= sizeof(pkt_v4),
+		.repeat		= 1000,
+	);
+	int i, prog_fd = *(int *)arg;
+	cpu_set_t cpuset;
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(__sync_fetch_and_add(&cpu, 1), &cpuset);
+	ASSERT_OK(pthread_setaffinity_np(pthread_self(), sizeof(cpuset),
+				         &cpuset),
+		  "cpu affinity");
+
+	for (i = 0; !READ_ONCE(*timer1_err) && !READ_ONCE(*timer2_err); i++) {
+		bpf_prog_test_run_opts(prog_fd, &opts);
+		/* Skip the test if we can't reproduce the race in a reasonable
+		 * amount of time.
+		 */
+		if (i > 50) {
+			WRITE_ONCE(skip, true);
+			break;
+		}
+	}
+
+	return NULL;
+}
+
+void test_timer_lockup(void)
+{
+	int timer1_prog, timer2_prog;
+	struct timer_lockup *skel;
+	pthread_t thrds[2];
+	void *ret;
+
+	if (get_nprocs() < 2) {
+		test__skip();
+		return;
+	}
+
+	skel = timer_lockup__open_and_load();
+	if (!skel && errno == EOPNOTSUPP) {
+		test__skip();
+		return;
+	}
+	if (!ASSERT_OK_PTR(skel, "timer_lockup__open_and_load"))
+		return;
+
+	timer1_prog = bpf_program__fd(skel->progs.timer1_prog);
+	timer2_prog = bpf_program__fd(skel->progs.timer2_prog);
+
+	timer1_err = &skel->bss->timer1_err;
+	timer2_err = &skel->bss->timer2_err;
+
+	if (!ASSERT_OK(pthread_create(&thrds[0], NULL, timer_lockup_thread,
+				      &timer1_prog),
+		       "pthread_create thread1"))
+		goto out;
+	if (!ASSERT_OK(pthread_create(&thrds[1], NULL, timer_lockup_thread,
+				      &timer2_prog),
+		       "pthread_create thread2")) {
+		pthread_exit(&thrds[0]);
+		goto out;
+	}
+
+	pthread_join(thrds[1], &ret);
+	pthread_join(thrds[0], &ret);
+
+	if (skip) {
+		test__skip();
+		goto out;
+	}
+
+	if (*timer1_err != -EDEADLK && *timer1_err != 0)
+		ASSERT_FAIL("timer1_err bad value");
+	if (*timer2_err != -EDEADLK && *timer2_err != 0)
+		ASSERT_FAIL("timer2_err bad value");
+out:
+	timer_lockup__destroy(skel);
+	return;
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_mim.c b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
index 9ff7843909e7..c930c7d7105b 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer_mim.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
@@ -65,6 +65,10 @@ void serial_test_timer_mim(void)
 		goto cleanup;
 
 	timer_skel = timer_mim__open_and_load();
+	if (!timer_skel && errno == EOPNOTSUPP) {
+		test__skip();
+		return;
+	}
 	if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load"))
 		goto cleanup;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/token.c b/tools/testing/selftests/bpf/prog_tests/token.c
new file mode 100644
index 000000000000..b81dde283052
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/token.c
@@ -0,0 +1,1197 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+#define _GNU_SOURCE
+#include <test_progs.h>
+#include <bpf/btf.h>
+#include "cap_helpers.h"
+#include <fcntl.h>
+#include <sched.h>
+#include <signal.h>
+#include <unistd.h>
+#include <linux/filter.h>
+#include <linux/unistd.h>
+#include <linux/mount.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/un.h>
+#include "priv_map.skel.h"
+#include "priv_prog.skel.h"
+#include "dummy_st_ops_success.skel.h"
+#include "token_lsm.skel.h"
+#include "priv_freplace_prog.skel.h"
+
+static inline int sys_mount(const char *dev_name, const char *dir_name,
+			    const char *type, unsigned long flags,
+			    const void *data)
+{
+	return syscall(__NR_mount, dev_name, dir_name, type, flags, data);
+}
+
+static inline int sys_fsopen(const char *fsname, unsigned flags)
+{
+	return syscall(__NR_fsopen, fsname, flags);
+}
+
+static inline int sys_fspick(int dfd, const char *path, unsigned flags)
+{
+	return syscall(__NR_fspick, dfd, path, flags);
+}
+
+static inline int sys_fsconfig(int fs_fd, unsigned cmd, const char *key, const void *val, int aux)
+{
+	return syscall(__NR_fsconfig, fs_fd, cmd, key, val, aux);
+}
+
+static inline int sys_fsmount(int fs_fd, unsigned flags, unsigned ms_flags)
+{
+	return syscall(__NR_fsmount, fs_fd, flags, ms_flags);
+}
+
+static inline int sys_move_mount(int from_dfd, const char *from_path,
+				 int to_dfd, const char *to_path,
+				 unsigned flags)
+{
+	return syscall(__NR_move_mount, from_dfd, from_path, to_dfd, to_path, flags);
+}
+
+static int drop_priv_caps(__u64 *old_caps)
+{
+	return cap_disable_effective((1ULL << CAP_BPF) |
+				     (1ULL << CAP_PERFMON) |
+				     (1ULL << CAP_NET_ADMIN) |
+				     (1ULL << CAP_SYS_ADMIN), old_caps);
+}
+
+static int restore_priv_caps(__u64 old_caps)
+{
+	return cap_enable_effective(old_caps, NULL);
+}
+
+static int set_delegate_mask(int fs_fd, const char *key, __u64 mask, const char *mask_str)
+{
+	char buf[32];
+	int err;
+
+	if (!mask_str) {
+		if (mask == ~0ULL) {
+			mask_str = "any";
+		} else {
+			snprintf(buf, sizeof(buf), "0x%llx", (unsigned long long)mask);
+			mask_str = buf;
+		}
+	}
+
+	err = sys_fsconfig(fs_fd, FSCONFIG_SET_STRING, key,
+			   mask_str, 0);
+	if (err < 0)
+		err = -errno;
+	return err;
+}
+
+#define zclose(fd) do { if (fd >= 0) close(fd); fd = -1; } while (0)
+
+struct bpffs_opts {
+	__u64 cmds;
+	__u64 maps;
+	__u64 progs;
+	__u64 attachs;
+	const char *cmds_str;
+	const char *maps_str;
+	const char *progs_str;
+	const char *attachs_str;
+};
+
+static int create_bpffs_fd(void)
+{
+	int fs_fd;
+
+	/* create VFS context */
+	fs_fd = sys_fsopen("bpf", 0);
+	ASSERT_GE(fs_fd, 0, "fs_fd");
+
+	return fs_fd;
+}
+
+static int materialize_bpffs_fd(int fs_fd, struct bpffs_opts *opts)
+{
+	int err;
+
+	/* set up token delegation mount options */
+	err = set_delegate_mask(fs_fd, "delegate_cmds", opts->cmds, opts->cmds_str);
+	if (!ASSERT_OK(err, "fs_cfg_cmds"))
+		return err;
+	err = set_delegate_mask(fs_fd, "delegate_maps", opts->maps, opts->maps_str);
+	if (!ASSERT_OK(err, "fs_cfg_maps"))
+		return err;
+	err = set_delegate_mask(fs_fd, "delegate_progs", opts->progs, opts->progs_str);
+	if (!ASSERT_OK(err, "fs_cfg_progs"))
+		return err;
+	err = set_delegate_mask(fs_fd, "delegate_attachs", opts->attachs, opts->attachs_str);
+	if (!ASSERT_OK(err, "fs_cfg_attachs"))
+		return err;
+
+	/* instantiate FS object */
+	err = sys_fsconfig(fs_fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0);
+	if (err < 0)
+		return -errno;
+
+	return 0;
+}
+
+/* send FD over Unix domain (AF_UNIX) socket */
+static int sendfd(int sockfd, int fd)
+{
+	struct msghdr msg = {};
+	struct cmsghdr *cmsg;
+	int fds[1] = { fd }, err;
+	char iobuf[1];
+	struct iovec io = {
+		.iov_base = iobuf,
+		.iov_len = sizeof(iobuf),
+	};
+	union {
+		char buf[CMSG_SPACE(sizeof(fds))];
+		struct cmsghdr align;
+	} u;
+
+	msg.msg_iov = &io;
+	msg.msg_iovlen = 1;
+	msg.msg_control = u.buf;
+	msg.msg_controllen = sizeof(u.buf);
+	cmsg = CMSG_FIRSTHDR(&msg);
+	cmsg->cmsg_level = SOL_SOCKET;
+	cmsg->cmsg_type = SCM_RIGHTS;
+	cmsg->cmsg_len = CMSG_LEN(sizeof(fds));
+	memcpy(CMSG_DATA(cmsg), fds, sizeof(fds));
+
+	err = sendmsg(sockfd, &msg, 0);
+	if (err < 0)
+		err = -errno;
+	if (!ASSERT_EQ(err, 1, "sendmsg"))
+		return -EINVAL;
+
+	return 0;
+}
+
+/* receive FD over Unix domain (AF_UNIX) socket */
+static int recvfd(int sockfd, int *fd)
+{
+	struct msghdr msg = {};
+	struct cmsghdr *cmsg;
+	int fds[1], err;
+	char iobuf[1];
+	struct iovec io = {
+		.iov_base = iobuf,
+		.iov_len = sizeof(iobuf),
+	};
+	union {
+		char buf[CMSG_SPACE(sizeof(fds))];
+		struct cmsghdr align;
+	} u;
+
+	msg.msg_iov = &io;
+	msg.msg_iovlen = 1;
+	msg.msg_control = u.buf;
+	msg.msg_controllen = sizeof(u.buf);
+
+	err = recvmsg(sockfd, &msg, 0);
+	if (err < 0)
+		err = -errno;
+	if (!ASSERT_EQ(err, 1, "recvmsg"))
+		return -EINVAL;
+
+	cmsg = CMSG_FIRSTHDR(&msg);
+	if (!ASSERT_OK_PTR(cmsg, "cmsg_null") ||
+	    !ASSERT_EQ(cmsg->cmsg_len, CMSG_LEN(sizeof(fds)), "cmsg_len") ||
+	    !ASSERT_EQ(cmsg->cmsg_level, SOL_SOCKET, "cmsg_level") ||
+	    !ASSERT_EQ(cmsg->cmsg_type, SCM_RIGHTS, "cmsg_type"))
+		return -EINVAL;
+
+	memcpy(fds, CMSG_DATA(cmsg), sizeof(fds));
+	*fd = fds[0];
+
+	return 0;
+}
+
+static ssize_t write_nointr(int fd, const void *buf, size_t count)
+{
+	ssize_t ret;
+
+	do {
+		ret = write(fd, buf, count);
+	} while (ret < 0 && errno == EINTR);
+
+	return ret;
+}
+
+static int write_file(const char *path, const void *buf, size_t count)
+{
+	int fd;
+	ssize_t ret;
+
+	fd = open(path, O_WRONLY | O_CLOEXEC | O_NOCTTY | O_NOFOLLOW);
+	if (fd < 0)
+		return -1;
+
+	ret = write_nointr(fd, buf, count);
+	close(fd);
+	if (ret < 0 || (size_t)ret != count)
+		return -1;
+
+	return 0;
+}
+
+static int create_and_enter_userns(void)
+{
+	uid_t uid;
+	gid_t gid;
+	char map[100];
+
+	uid = getuid();
+	gid = getgid();
+
+	if (unshare(CLONE_NEWUSER))
+		return -1;
+
+	if (write_file("/proc/self/setgroups", "deny", sizeof("deny") - 1) &&
+	    errno != ENOENT)
+		return -1;
+
+	snprintf(map, sizeof(map), "0 %d 1", uid);
+	if (write_file("/proc/self/uid_map", map, strlen(map)))
+		return -1;
+
+
+	snprintf(map, sizeof(map), "0 %d 1", gid);
+	if (write_file("/proc/self/gid_map", map, strlen(map)))
+		return -1;
+
+	if (setgid(0))
+		return -1;
+
+	if (setuid(0))
+		return -1;
+
+	return 0;
+}
+
+typedef int (*child_callback_fn)(int bpffs_fd, struct token_lsm *lsm_skel);
+
+static void child(int sock_fd, struct bpffs_opts *opts, child_callback_fn callback)
+{
+	int mnt_fd = -1, fs_fd = -1, err = 0, bpffs_fd = -1, token_fd = -1;
+	struct token_lsm *lsm_skel = NULL;
+	char one;
+
+	/* load and attach LSM "policy" before we go into unpriv userns */
+	lsm_skel = token_lsm__open_and_load();
+	if (!ASSERT_OK_PTR(lsm_skel, "lsm_skel_load")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+	lsm_skel->bss->my_pid = getpid();
+	err = token_lsm__attach(lsm_skel);
+	if (!ASSERT_OK(err, "lsm_skel_attach"))
+		goto cleanup;
+
+	/* setup userns with root mappings */
+	err = create_and_enter_userns();
+	if (!ASSERT_OK(err, "create_and_enter_userns"))
+		goto cleanup;
+
+	/* setup mountns to allow creating BPF FS (fsopen("bpf")) from unpriv process */
+	err = unshare(CLONE_NEWNS);
+	if (!ASSERT_OK(err, "create_mountns"))
+		goto cleanup;
+
+	err = sys_mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0);
+	if (!ASSERT_OK(err, "remount_root"))
+		goto cleanup;
+
+	fs_fd = create_bpffs_fd();
+	if (!ASSERT_GE(fs_fd, 0, "create_bpffs_fd")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	/* ensure unprivileged child cannot set delegation options */
+	err = set_delegate_mask(fs_fd, "delegate_cmds", 0x1, NULL);
+	ASSERT_EQ(err, -EPERM, "delegate_cmd_eperm");
+	err = set_delegate_mask(fs_fd, "delegate_maps", 0x1, NULL);
+	ASSERT_EQ(err, -EPERM, "delegate_maps_eperm");
+	err = set_delegate_mask(fs_fd, "delegate_progs", 0x1, NULL);
+	ASSERT_EQ(err, -EPERM, "delegate_progs_eperm");
+	err = set_delegate_mask(fs_fd, "delegate_attachs", 0x1, NULL);
+	ASSERT_EQ(err, -EPERM, "delegate_attachs_eperm");
+
+	/* pass BPF FS context object to parent */
+	err = sendfd(sock_fd, fs_fd);
+	if (!ASSERT_OK(err, "send_fs_fd"))
+		goto cleanup;
+
+	/* wait that the parent reads the fd, does the fsconfig() calls
+	 * and send us a signal that it is done
+	 */
+	err = read(sock_fd, &one, sizeof(one));
+	if (!ASSERT_GE(err, 0, "read_one"))
+		goto cleanup;
+
+	/* avoid mucking around with mount namespaces and mounting at
+	 * well-known path, just create O_PATH fd for detached mount
+	 */
+	mnt_fd = sys_fsmount(fs_fd, 0, 0);
+	if (!ASSERT_OK_FD(mnt_fd, "mnt_fd"))
+		goto cleanup;
+
+	/* try to fspick() BPF FS and try to add some delegation options */
+	fs_fd = sys_fspick(mnt_fd, "", FSPICK_EMPTY_PATH);
+	if (!ASSERT_GE(fs_fd, 0, "bpffs_fspick")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	/* ensure unprivileged child cannot reconfigure to set delegation options */
+	err = set_delegate_mask(fs_fd, "delegate_cmds", 0, "any");
+	if (!ASSERT_EQ(err, -EPERM, "delegate_cmd_eperm_reconfig")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+	err = set_delegate_mask(fs_fd, "delegate_maps", 0, "any");
+	if (!ASSERT_EQ(err, -EPERM, "delegate_maps_eperm_reconfig")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+	err = set_delegate_mask(fs_fd, "delegate_progs", 0, "any");
+	if (!ASSERT_EQ(err, -EPERM, "delegate_progs_eperm_reconfig")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+	err = set_delegate_mask(fs_fd, "delegate_attachs", 0, "any");
+	if (!ASSERT_EQ(err, -EPERM, "delegate_attachs_eperm_reconfig")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+	zclose(fs_fd);
+
+	bpffs_fd = openat(mnt_fd, ".", 0, O_RDWR);
+	if (!ASSERT_GE(bpffs_fd, 0, "bpffs_open")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	/* create BPF token FD and pass it to parent for some extra checks */
+	token_fd = bpf_token_create(bpffs_fd, NULL);
+	if (!ASSERT_GT(token_fd, 0, "child_token_create")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+	err = sendfd(sock_fd, token_fd);
+	if (!ASSERT_OK(err, "send_token_fd"))
+		goto cleanup;
+	zclose(token_fd);
+
+	/* do custom test logic with customly set up BPF FS instance */
+	err = callback(bpffs_fd, lsm_skel);
+	if (!ASSERT_OK(err, "test_callback"))
+		goto cleanup;
+
+	err = 0;
+cleanup:
+	zclose(sock_fd);
+	zclose(mnt_fd);
+	zclose(fs_fd);
+	zclose(bpffs_fd);
+	zclose(token_fd);
+
+	lsm_skel->bss->my_pid = 0;
+	token_lsm__destroy(lsm_skel);
+
+	exit(-err);
+}
+
+static int wait_for_pid(pid_t pid)
+{
+	int status, ret;
+
+again:
+	ret = waitpid(pid, &status, 0);
+	if (ret == -1) {
+		if (errno == EINTR)
+			goto again;
+
+		return -1;
+	}
+
+	if (!WIFEXITED(status))
+		return -1;
+
+	return WEXITSTATUS(status);
+}
+
+static void parent(int child_pid, struct bpffs_opts *bpffs_opts, int sock_fd)
+{
+	int fs_fd = -1, token_fd = -1, err;
+	char one = 1;
+
+	err = recvfd(sock_fd, &fs_fd);
+	if (!ASSERT_OK(err, "recv_bpffs_fd"))
+		goto cleanup;
+
+	err = materialize_bpffs_fd(fs_fd, bpffs_opts);
+	if (!ASSERT_GE(err, 0, "materialize_bpffs_fd")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	/* notify the child that we did the fsconfig() calls and it can proceed. */
+	err = write(sock_fd, &one, sizeof(one));
+	if (!ASSERT_EQ(err, sizeof(one), "send_one"))
+		goto cleanup;
+	zclose(fs_fd);
+
+	/* receive BPF token FD back from child for some extra tests */
+	err = recvfd(sock_fd, &token_fd);
+	if (!ASSERT_OK(err, "recv_token_fd"))
+		goto cleanup;
+
+	err = wait_for_pid(child_pid);
+	ASSERT_OK(err, "waitpid_child");
+
+cleanup:
+	zclose(sock_fd);
+	zclose(fs_fd);
+	zclose(token_fd);
+
+	if (child_pid > 0)
+		(void)kill(child_pid, SIGKILL);
+}
+
+static void subtest_userns(struct bpffs_opts *bpffs_opts,
+			   child_callback_fn child_cb)
+{
+	int sock_fds[2] = { -1, -1 };
+	int child_pid = 0, err;
+
+	err = socketpair(AF_UNIX, SOCK_STREAM, 0, sock_fds);
+	if (!ASSERT_OK(err, "socketpair"))
+		goto cleanup;
+
+	child_pid = fork();
+	if (!ASSERT_GE(child_pid, 0, "fork"))
+		goto cleanup;
+
+	if (child_pid == 0) {
+		zclose(sock_fds[0]);
+		return child(sock_fds[1], bpffs_opts, child_cb);
+
+	} else {
+		zclose(sock_fds[1]);
+		return parent(child_pid, bpffs_opts, sock_fds[0]);
+	}
+
+cleanup:
+	zclose(sock_fds[0]);
+	zclose(sock_fds[1]);
+	if (child_pid > 0)
+		(void)kill(child_pid, SIGKILL);
+}
+
+static int userns_map_create(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts);
+	int err, token_fd = -1, map_fd = -1;
+	__u64 old_caps = 0;
+
+	/* create BPF token from BPF FS mount */
+	token_fd = bpf_token_create(mnt_fd, NULL);
+	if (!ASSERT_GT(token_fd, 0, "token_create")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	/* while inside non-init userns, we need both a BPF token *and*
+	 * CAP_BPF inside current userns to create privileged map; let's test
+	 * that neither BPF token alone nor namespaced CAP_BPF is sufficient
+	 */
+	err = drop_priv_caps(&old_caps);
+	if (!ASSERT_OK(err, "drop_caps"))
+		goto cleanup;
+
+	/* no token, no CAP_BPF -> fail */
+	map_opts.map_flags = 0;
+	map_opts.token_fd = 0;
+	map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "wo_token_wo_bpf", 0, 8, 1, &map_opts);
+	if (!ASSERT_LT(map_fd, 0, "stack_map_wo_token_wo_cap_bpf_should_fail")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	/* token without CAP_BPF -> fail */
+	map_opts.map_flags = BPF_F_TOKEN_FD;
+	map_opts.token_fd = token_fd;
+	map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "w_token_wo_bpf", 0, 8, 1, &map_opts);
+	if (!ASSERT_LT(map_fd, 0, "stack_map_w_token_wo_cap_bpf_should_fail")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	/* get back effective local CAP_BPF (and CAP_SYS_ADMIN) */
+	err = restore_priv_caps(old_caps);
+	if (!ASSERT_OK(err, "restore_caps"))
+		goto cleanup;
+
+	/* CAP_BPF without token -> fail */
+	map_opts.map_flags = 0;
+	map_opts.token_fd = 0;
+	map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "wo_token_w_bpf", 0, 8, 1, &map_opts);
+	if (!ASSERT_LT(map_fd, 0, "stack_map_wo_token_w_cap_bpf_should_fail")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	/* finally, namespaced CAP_BPF + token -> success */
+	map_opts.map_flags = BPF_F_TOKEN_FD;
+	map_opts.token_fd = token_fd;
+	map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "w_token_w_bpf", 0, 8, 1, &map_opts);
+	if (!ASSERT_GT(map_fd, 0, "stack_map_w_token_w_cap_bpf")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+cleanup:
+	zclose(token_fd);
+	zclose(map_fd);
+	return err;
+}
+
+static int userns_btf_load(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	LIBBPF_OPTS(bpf_btf_load_opts, btf_opts);
+	int err, token_fd = -1, btf_fd = -1;
+	const void *raw_btf_data;
+	struct btf *btf = NULL;
+	__u32 raw_btf_size;
+	__u64 old_caps = 0;
+
+	/* create BPF token from BPF FS mount */
+	token_fd = bpf_token_create(mnt_fd, NULL);
+	if (!ASSERT_GT(token_fd, 0, "token_create")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	/* while inside non-init userns, we need both a BPF token *and*
+	 * CAP_BPF inside current userns to create privileged map; let's test
+	 * that neither BPF token alone nor namespaced CAP_BPF is sufficient
+	 */
+	err = drop_priv_caps(&old_caps);
+	if (!ASSERT_OK(err, "drop_caps"))
+		goto cleanup;
+
+	/* setup a trivial BTF data to load to the kernel */
+	btf = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf, "empty_btf"))
+		goto cleanup;
+
+	ASSERT_GT(btf__add_int(btf, "int", 4, 0), 0, "int_type");
+
+	raw_btf_data = btf__raw_data(btf, &raw_btf_size);
+	if (!ASSERT_OK_PTR(raw_btf_data, "raw_btf_data"))
+		goto cleanup;
+
+	/* no token + no CAP_BPF -> failure */
+	btf_opts.btf_flags = 0;
+	btf_opts.token_fd = 0;
+	btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts);
+	if (!ASSERT_LT(btf_fd, 0, "no_token_no_cap_should_fail"))
+		goto cleanup;
+
+	/* token + no CAP_BPF -> failure */
+	btf_opts.btf_flags = BPF_F_TOKEN_FD;
+	btf_opts.token_fd = token_fd;
+	btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts);
+	if (!ASSERT_LT(btf_fd, 0, "token_no_cap_should_fail"))
+		goto cleanup;
+
+	/* get back effective local CAP_BPF (and CAP_SYS_ADMIN) */
+	err = restore_priv_caps(old_caps);
+	if (!ASSERT_OK(err, "restore_caps"))
+		goto cleanup;
+
+	/* token + CAP_BPF -> success */
+	btf_opts.btf_flags = BPF_F_TOKEN_FD;
+	btf_opts.token_fd = token_fd;
+	btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts);
+	if (!ASSERT_GT(btf_fd, 0, "token_and_cap_success"))
+		goto cleanup;
+
+	err = 0;
+cleanup:
+	btf__free(btf);
+	zclose(btf_fd);
+	zclose(token_fd);
+	return err;
+}
+
+static int userns_prog_load(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	LIBBPF_OPTS(bpf_prog_load_opts, prog_opts);
+	int err, token_fd = -1, prog_fd = -1;
+	struct bpf_insn insns[] = {
+		/* bpf_jiffies64() requires CAP_BPF */
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_jiffies64),
+		/* bpf_get_current_task() requires CAP_PERFMON */
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_current_task),
+		/* r0 = 0; exit; */
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	size_t insn_cnt = ARRAY_SIZE(insns);
+	__u64 old_caps = 0;
+
+	/* create BPF token from BPF FS mount */
+	token_fd = bpf_token_create(mnt_fd, NULL);
+	if (!ASSERT_GT(token_fd, 0, "token_create")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	/* validate we can successfully load BPF program with token; this
+	 * being XDP program (CAP_NET_ADMIN) using bpf_jiffies64() (CAP_BPF)
+	 * and bpf_get_current_task() (CAP_PERFMON) helpers validates we have
+	 * BPF token wired properly in a bunch of places in the kernel
+	 */
+	prog_opts.prog_flags = BPF_F_TOKEN_FD;
+	prog_opts.token_fd = token_fd;
+	prog_opts.expected_attach_type = BPF_XDP;
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL",
+				insns, insn_cnt, &prog_opts);
+	if (!ASSERT_GT(prog_fd, 0, "prog_fd")) {
+		err = -EPERM;
+		goto cleanup;
+	}
+
+	/* no token + caps -> failure */
+	prog_opts.prog_flags = 0;
+	prog_opts.token_fd = 0;
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL",
+				insns, insn_cnt, &prog_opts);
+	if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) {
+		err = -EPERM;
+		goto cleanup;
+	}
+
+	err = drop_priv_caps(&old_caps);
+	if (!ASSERT_OK(err, "drop_caps"))
+		goto cleanup;
+
+	/* no caps + token -> failure */
+	prog_opts.prog_flags = BPF_F_TOKEN_FD;
+	prog_opts.token_fd = token_fd;
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL",
+				insns, insn_cnt, &prog_opts);
+	if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) {
+		err = -EPERM;
+		goto cleanup;
+	}
+
+	/* no caps + no token -> definitely a failure */
+	prog_opts.prog_flags = 0;
+	prog_opts.token_fd = 0;
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL",
+				insns, insn_cnt, &prog_opts);
+	if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) {
+		err = -EPERM;
+		goto cleanup;
+	}
+
+	err = 0;
+cleanup:
+	zclose(prog_fd);
+	zclose(token_fd);
+	return err;
+}
+
+static int userns_obj_priv_map(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	LIBBPF_OPTS(bpf_object_open_opts, opts);
+	char buf[256];
+	struct priv_map *skel;
+	int err;
+
+	skel = priv_map__open_and_load();
+	if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) {
+		priv_map__destroy(skel);
+		return -EINVAL;
+	}
+
+	/* use bpf_token_path to provide BPF FS path */
+	snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd);
+	opts.bpf_token_path = buf;
+	skel = priv_map__open_opts(&opts);
+	if (!ASSERT_OK_PTR(skel, "obj_token_path_open"))
+		return -EINVAL;
+
+	err = priv_map__load(skel);
+	priv_map__destroy(skel);
+	if (!ASSERT_OK(err, "obj_token_path_load"))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int userns_obj_priv_prog(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	LIBBPF_OPTS(bpf_object_open_opts, opts);
+	char buf[256];
+	struct priv_prog *skel;
+	int err;
+
+	skel = priv_prog__open_and_load();
+	if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) {
+		priv_prog__destroy(skel);
+		return -EINVAL;
+	}
+
+	/* use bpf_token_path to provide BPF FS path */
+	snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd);
+	opts.bpf_token_path = buf;
+	skel = priv_prog__open_opts(&opts);
+	if (!ASSERT_OK_PTR(skel, "obj_token_path_open"))
+		return -EINVAL;
+	err = priv_prog__load(skel);
+	priv_prog__destroy(skel);
+	if (!ASSERT_OK(err, "obj_token_path_load"))
+		return -EINVAL;
+
+	/* provide BPF token, but reject bpf_token_capable() with LSM */
+	lsm_skel->bss->reject_capable = true;
+	lsm_skel->bss->reject_cmd = false;
+	skel = priv_prog__open_opts(&opts);
+	if (!ASSERT_OK_PTR(skel, "obj_token_lsm_reject_cap_open"))
+		return -EINVAL;
+	err = priv_prog__load(skel);
+	priv_prog__destroy(skel);
+	if (!ASSERT_ERR(err, "obj_token_lsm_reject_cap_load"))
+		return -EINVAL;
+
+	/* provide BPF token, but reject bpf_token_cmd() with LSM */
+	lsm_skel->bss->reject_capable = false;
+	lsm_skel->bss->reject_cmd = true;
+	skel = priv_prog__open_opts(&opts);
+	if (!ASSERT_OK_PTR(skel, "obj_token_lsm_reject_cmd_open"))
+		return -EINVAL;
+	err = priv_prog__load(skel);
+	priv_prog__destroy(skel);
+	if (!ASSERT_ERR(err, "obj_token_lsm_reject_cmd_load"))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int userns_obj_priv_freplace_setup(int mnt_fd, struct priv_freplace_prog **fr_skel,
+					  struct priv_prog **skel, int *tgt_fd)
+{
+	LIBBPF_OPTS(bpf_object_open_opts, opts);
+	int err;
+	char buf[256];
+
+	/* use bpf_token_path to provide BPF FS path */
+	snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd);
+	opts.bpf_token_path = buf;
+	*skel = priv_prog__open_opts(&opts);
+	if (!ASSERT_OK_PTR(*skel, "priv_prog__open_opts"))
+		return -EINVAL;
+	err = priv_prog__load(*skel);
+	if (!ASSERT_OK(err, "priv_prog__load"))
+		return -EINVAL;
+
+	*fr_skel = priv_freplace_prog__open_opts(&opts);
+	if (!ASSERT_OK_PTR(*skel, "priv_freplace_prog__open_opts"))
+		return -EINVAL;
+
+	*tgt_fd = bpf_program__fd((*skel)->progs.xdp_prog1);
+	return 0;
+}
+
+/* Verify that freplace works from user namespace, because bpf token is loaded
+ * in bpf_object__prepare
+ */
+static int userns_obj_priv_freplace_prog(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	struct priv_freplace_prog *fr_skel = NULL;
+	struct priv_prog *skel = NULL;
+	int err, tgt_fd;
+
+	err = userns_obj_priv_freplace_setup(mnt_fd, &fr_skel, &skel, &tgt_fd);
+	if (!ASSERT_OK(err, "setup"))
+		goto out;
+
+	err = bpf_object__prepare(fr_skel->obj);
+	if (!ASSERT_OK(err, "freplace__prepare"))
+		goto out;
+
+	err = bpf_program__set_attach_target(fr_skel->progs.new_xdp_prog2, tgt_fd, "xdp_prog1");
+	if (!ASSERT_OK(err, "set_attach_target"))
+		goto out;
+
+	err = priv_freplace_prog__load(fr_skel);
+	ASSERT_OK(err, "priv_freplace_prog__load");
+
+out:
+	priv_freplace_prog__destroy(fr_skel);
+	priv_prog__destroy(skel);
+	return err;
+}
+
+/* Verify that replace fails to set attach target from user namespace without bpf token */
+static int userns_obj_priv_freplace_prog_fail(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	struct priv_freplace_prog *fr_skel = NULL;
+	struct priv_prog *skel = NULL;
+	int err, tgt_fd;
+
+	err = userns_obj_priv_freplace_setup(mnt_fd, &fr_skel, &skel, &tgt_fd);
+	if (!ASSERT_OK(err, "setup"))
+		goto out;
+
+	err = bpf_program__set_attach_target(fr_skel->progs.new_xdp_prog2, tgt_fd, "xdp_prog1");
+	if (ASSERT_ERR(err, "attach fails"))
+		err = 0;
+	else
+		err = -EINVAL;
+
+out:
+	priv_freplace_prog__destroy(fr_skel);
+	priv_prog__destroy(skel);
+	return err;
+}
+
+/* this test is called with BPF FS that doesn't delegate BPF_BTF_LOAD command,
+ * which should cause struct_ops application to fail, as BTF won't be uploaded
+ * into the kernel, even if STRUCT_OPS programs themselves are allowed
+ */
+static int validate_struct_ops_load(int mnt_fd, bool expect_success)
+{
+	LIBBPF_OPTS(bpf_object_open_opts, opts);
+	char buf[256];
+	struct dummy_st_ops_success *skel;
+	int err;
+
+	snprintf(buf, sizeof(buf), "/proc/self/fd/%d", mnt_fd);
+	opts.bpf_token_path = buf;
+	skel = dummy_st_ops_success__open_opts(&opts);
+	if (!ASSERT_OK_PTR(skel, "obj_token_path_open"))
+		return -EINVAL;
+
+	err = dummy_st_ops_success__load(skel);
+	dummy_st_ops_success__destroy(skel);
+	if (expect_success) {
+		if (!ASSERT_OK(err, "obj_token_path_load"))
+			return -EINVAL;
+	} else /* expect failure */ {
+		if (!ASSERT_ERR(err, "obj_token_path_load"))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int userns_obj_priv_btf_fail(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	return validate_struct_ops_load(mnt_fd, false /* should fail */);
+}
+
+static int userns_obj_priv_btf_success(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	return validate_struct_ops_load(mnt_fd, true /* should succeed */);
+}
+
+static const char *token_bpffs_custom_dir()
+{
+	return getenv("BPF_SELFTESTS_BPF_TOKEN_DIR") ?: "/tmp/bpf-token-fs";
+}
+
+#define TOKEN_ENVVAR "LIBBPF_BPF_TOKEN_PATH"
+
+static int userns_obj_priv_implicit_token(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	LIBBPF_OPTS(bpf_object_open_opts, opts);
+	struct dummy_st_ops_success *skel;
+	int err;
+
+	/* before we mount BPF FS with token delegation, struct_ops skeleton
+	 * should fail to load
+	 */
+	skel = dummy_st_ops_success__open_and_load();
+	if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) {
+		dummy_st_ops_success__destroy(skel);
+		return -EINVAL;
+	}
+
+	/* mount custom BPF FS over /sys/fs/bpf so that libbpf can create BPF
+	 * token automatically and implicitly
+	 */
+	err = sys_move_mount(mnt_fd, "", AT_FDCWD, "/sys/fs/bpf", MOVE_MOUNT_F_EMPTY_PATH);
+	if (!ASSERT_OK(err, "move_mount_bpffs"))
+		return -EINVAL;
+
+	/* disable implicit BPF token creation by setting
+	 * LIBBPF_BPF_TOKEN_PATH envvar to empty value, load should fail
+	 */
+	err = setenv(TOKEN_ENVVAR, "", 1 /*overwrite*/);
+	if (!ASSERT_OK(err, "setenv_token_path"))
+		return -EINVAL;
+	skel = dummy_st_ops_success__open_and_load();
+	if (!ASSERT_ERR_PTR(skel, "obj_token_envvar_disabled_load")) {
+		unsetenv(TOKEN_ENVVAR);
+		dummy_st_ops_success__destroy(skel);
+		return -EINVAL;
+	}
+	unsetenv(TOKEN_ENVVAR);
+
+	/* now the same struct_ops skeleton should succeed thanks to libbpf
+	 * creating BPF token from /sys/fs/bpf mount point
+	 */
+	skel = dummy_st_ops_success__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "obj_implicit_token_load"))
+		return -EINVAL;
+
+	dummy_st_ops_success__destroy(skel);
+
+	/* now disable implicit token through empty bpf_token_path, should fail */
+	opts.bpf_token_path = "";
+	skel = dummy_st_ops_success__open_opts(&opts);
+	if (!ASSERT_OK_PTR(skel, "obj_empty_token_path_open"))
+		return -EINVAL;
+
+	err = dummy_st_ops_success__load(skel);
+	dummy_st_ops_success__destroy(skel);
+	if (!ASSERT_ERR(err, "obj_empty_token_path_load"))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int userns_obj_priv_implicit_token_envvar(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	const char *custom_dir = token_bpffs_custom_dir();
+	LIBBPF_OPTS(bpf_object_open_opts, opts);
+	struct dummy_st_ops_success *skel;
+	int err;
+
+	/* before we mount BPF FS with token delegation, struct_ops skeleton
+	 * should fail to load
+	 */
+	skel = dummy_st_ops_success__open_and_load();
+	if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load")) {
+		dummy_st_ops_success__destroy(skel);
+		return -EINVAL;
+	}
+
+	/* mount custom BPF FS over custom location, so libbpf can't create
+	 * BPF token implicitly, unless pointed to it through
+	 * LIBBPF_BPF_TOKEN_PATH envvar
+	 */
+	rmdir(custom_dir);
+	if (!ASSERT_OK(mkdir(custom_dir, 0777), "mkdir_bpffs_custom"))
+		goto err_out;
+	err = sys_move_mount(mnt_fd, "", AT_FDCWD, custom_dir, MOVE_MOUNT_F_EMPTY_PATH);
+	if (!ASSERT_OK(err, "move_mount_bpffs"))
+		goto err_out;
+
+	/* even though we have BPF FS with delegation, it's not at default
+	 * /sys/fs/bpf location, so we still fail to load until envvar is set up
+	 */
+	skel = dummy_st_ops_success__open_and_load();
+	if (!ASSERT_ERR_PTR(skel, "obj_tokenless_load2")) {
+		dummy_st_ops_success__destroy(skel);
+		goto err_out;
+	}
+
+	err = setenv(TOKEN_ENVVAR, custom_dir, 1 /*overwrite*/);
+	if (!ASSERT_OK(err, "setenv_token_path"))
+		goto err_out;
+
+	/* now the same struct_ops skeleton should succeed thanks to libbpf
+	 * creating BPF token from custom mount point
+	 */
+	skel = dummy_st_ops_success__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "obj_implicit_token_load"))
+		goto err_out;
+
+	dummy_st_ops_success__destroy(skel);
+
+	/* now disable implicit token through empty bpf_token_path, envvar
+	 * will be ignored, should fail
+	 */
+	opts.bpf_token_path = "";
+	skel = dummy_st_ops_success__open_opts(&opts);
+	if (!ASSERT_OK_PTR(skel, "obj_empty_token_path_open"))
+		goto err_out;
+
+	err = dummy_st_ops_success__load(skel);
+	dummy_st_ops_success__destroy(skel);
+	if (!ASSERT_ERR(err, "obj_empty_token_path_load"))
+		goto err_out;
+
+	rmdir(custom_dir);
+	unsetenv(TOKEN_ENVVAR);
+	return 0;
+err_out:
+	rmdir(custom_dir);
+	unsetenv(TOKEN_ENVVAR);
+	return -EINVAL;
+}
+
+#define bit(n) (1ULL << (n))
+
+static int userns_bpf_token_info(int mnt_fd, struct token_lsm *lsm_skel)
+{
+	int err, token_fd = -1;
+	struct bpf_token_info info;
+	u32 len = sizeof(struct bpf_token_info);
+
+	/* create BPF token from BPF FS mount */
+	token_fd = bpf_token_create(mnt_fd, NULL);
+	if (!ASSERT_GT(token_fd, 0, "token_create")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	memset(&info, 0, len);
+	err = bpf_obj_get_info_by_fd(token_fd, &info, &len);
+	if (!ASSERT_ERR(err, "bpf_obj_get_token_info"))
+		goto cleanup;
+	if (!ASSERT_EQ(info.allowed_cmds, bit(BPF_MAP_CREATE), "token_info_cmds_map_create")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+	if (!ASSERT_EQ(info.allowed_progs, bit(BPF_PROG_TYPE_XDP), "token_info_progs_xdp")) {
+		err = -EINVAL;
+		goto cleanup;
+	}
+
+	/* The BPF_PROG_TYPE_EXT is not set in token */
+	if (ASSERT_EQ(info.allowed_progs, bit(BPF_PROG_TYPE_EXT), "token_info_progs_ext"))
+		err = -EINVAL;
+
+cleanup:
+	zclose(token_fd);
+	return err;
+}
+
+void test_token(void)
+{
+	if (test__start_subtest("map_token")) {
+		struct bpffs_opts opts = {
+			.cmds_str = "map_create",
+			.maps_str = "stack",
+		};
+
+		subtest_userns(&opts, userns_map_create);
+	}
+	if (test__start_subtest("btf_token")) {
+		struct bpffs_opts opts = {
+			.cmds = 1ULL << BPF_BTF_LOAD,
+		};
+
+		subtest_userns(&opts, userns_btf_load);
+	}
+	if (test__start_subtest("prog_token")) {
+		struct bpffs_opts opts = {
+			.cmds_str = "PROG_LOAD",
+			.progs_str = "XDP",
+			.attachs_str = "xdp",
+		};
+
+		subtest_userns(&opts, userns_prog_load);
+	}
+	if (test__start_subtest("obj_priv_map")) {
+		struct bpffs_opts opts = {
+			.cmds = bit(BPF_MAP_CREATE),
+			.maps = bit(BPF_MAP_TYPE_QUEUE),
+		};
+
+		subtest_userns(&opts, userns_obj_priv_map);
+	}
+	if (test__start_subtest("obj_priv_prog")) {
+		struct bpffs_opts opts = {
+			.cmds = bit(BPF_PROG_LOAD),
+			.progs = bit(BPF_PROG_TYPE_XDP),
+			.attachs = ~0ULL,
+		};
+
+		subtest_userns(&opts, userns_obj_priv_prog);
+	}
+	if (test__start_subtest("obj_priv_freplace_prog")) {
+		struct bpffs_opts opts = {
+			.cmds = bit(BPF_BTF_LOAD) | bit(BPF_PROG_LOAD) | bit(BPF_BTF_GET_FD_BY_ID),
+			.progs = bit(BPF_PROG_TYPE_EXT) | bit(BPF_PROG_TYPE_XDP),
+			.attachs = ~0ULL,
+		};
+		subtest_userns(&opts, userns_obj_priv_freplace_prog);
+	}
+	if (test__start_subtest("obj_priv_freplace_prog_fail")) {
+		struct bpffs_opts opts = {
+			.cmds = bit(BPF_BTF_LOAD) | bit(BPF_PROG_LOAD) | bit(BPF_BTF_GET_FD_BY_ID),
+			.progs = bit(BPF_PROG_TYPE_EXT) | bit(BPF_PROG_TYPE_XDP),
+			.attachs = ~0ULL,
+		};
+		subtest_userns(&opts, userns_obj_priv_freplace_prog_fail);
+	}
+	if (test__start_subtest("obj_priv_btf_fail")) {
+		struct bpffs_opts opts = {
+			/* disallow BTF loading */
+			.cmds = bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD),
+			.maps = bit(BPF_MAP_TYPE_STRUCT_OPS),
+			.progs = bit(BPF_PROG_TYPE_STRUCT_OPS),
+			.attachs = ~0ULL,
+		};
+
+		subtest_userns(&opts, userns_obj_priv_btf_fail);
+	}
+	if (test__start_subtest("obj_priv_btf_success")) {
+		struct bpffs_opts opts = {
+			/* allow BTF loading */
+			.cmds = bit(BPF_BTF_LOAD) | bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD),
+			.maps = bit(BPF_MAP_TYPE_STRUCT_OPS),
+			.progs = bit(BPF_PROG_TYPE_STRUCT_OPS),
+			.attachs = ~0ULL,
+		};
+
+		subtest_userns(&opts, userns_obj_priv_btf_success);
+	}
+	if (test__start_subtest("obj_priv_implicit_token")) {
+		struct bpffs_opts opts = {
+			/* allow BTF loading */
+			.cmds = bit(BPF_BTF_LOAD) | bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD),
+			.maps = bit(BPF_MAP_TYPE_STRUCT_OPS),
+			.progs = bit(BPF_PROG_TYPE_STRUCT_OPS),
+			.attachs = ~0ULL,
+		};
+
+		subtest_userns(&opts, userns_obj_priv_implicit_token);
+	}
+	if (test__start_subtest("obj_priv_implicit_token_envvar")) {
+		struct bpffs_opts opts = {
+			/* allow BTF loading */
+			.cmds = bit(BPF_BTF_LOAD) | bit(BPF_MAP_CREATE) | bit(BPF_PROG_LOAD),
+			.maps = bit(BPF_MAP_TYPE_STRUCT_OPS),
+			.progs = bit(BPF_PROG_TYPE_STRUCT_OPS),
+			.attachs = ~0ULL,
+		};
+
+		subtest_userns(&opts, userns_obj_priv_implicit_token_envvar);
+	}
+	if (test__start_subtest("bpf_token_info")) {
+		struct bpffs_opts opts = {
+			.cmds = bit(BPF_MAP_CREATE),
+			.progs = bit(BPF_PROG_TYPE_XDP),
+			.attachs = ~0ULL,
+		};
+
+		subtest_userns(&opts, userns_bpf_token_info);
+	}
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tp_attach_query.c b/tools/testing/selftests/bpf/prog_tests/tp_attach_query.c
index a479080533db..655d69f0ff0b 100644
--- a/tools/testing/selftests/bpf/prog_tests/tp_attach_query.c
+++ b/tools/testing/selftests/bpf/prog_tests/tp_attach_query.c
@@ -16,8 +16,13 @@ void serial_test_tp_attach_query(void)
 	for (i = 0; i < num_progs; i++)
 		obj[i] = NULL;
 
-	snprintf(buf, sizeof(buf),
-		 "/sys/kernel/debug/tracing/events/sched/sched_switch/id");
+	if (access("/sys/kernel/tracing/trace", F_OK) == 0) {
+		snprintf(buf, sizeof(buf),
+			 "/sys/kernel/tracing/events/sched/sched_switch/id");
+	} else {
+		snprintf(buf, sizeof(buf),
+			 "/sys/kernel/debug/tracing/events/sched/sched_switch/id");
+	}
 	efd = open(buf, O_RDONLY, 0);
 	if (CHECK(efd < 0, "open", "err %d errno %d\n", efd, errno))
 		return;
@@ -45,8 +50,9 @@ void serial_test_tp_attach_query(void)
 		prog_info.xlated_prog_len = 0;
 		prog_info.nr_map_ids = 0;
 		info_len = sizeof(prog_info);
-		err = bpf_obj_get_info_by_fd(prog_fd[i], &prog_info, &info_len);
-		if (CHECK(err, "bpf_obj_get_info_by_fd", "err %d errno %d\n",
+		err = bpf_prog_get_info_by_fd(prog_fd[i], &prog_info,
+					      &info_len);
+		if (CHECK(err, "bpf_prog_get_info_by_fd", "err %d errno %d\n",
 			  err, errno))
 			goto cleanup1;
 		saved_prog_ids[i] = prog_info.id;
diff --git a/tools/testing/selftests/bpf/prog_tests/tp_btf_nullable.c b/tools/testing/selftests/bpf/prog_tests/tp_btf_nullable.c
new file mode 100644
index 000000000000..accc42e01f8a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tp_btf_nullable.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "test_tp_btf_nullable.skel.h"
+
+void test_tp_btf_nullable(void)
+{
+	if (!env.has_testmod) {
+		test__skip();
+		return;
+	}
+
+	RUN_TESTS(test_tp_btf_nullable);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/trace_printk.c b/tools/testing/selftests/bpf/prog_tests/trace_printk.c
index cade7f12315f..e56e88596d64 100644
--- a/tools/testing/selftests/bpf/prog_tests/trace_printk.c
+++ b/tools/testing/selftests/bpf/prog_tests/trace_printk.c
@@ -5,17 +5,19 @@
 
 #include "trace_printk.lskel.h"
 
-#define TRACEBUF	"/sys/kernel/debug/tracing/trace_pipe"
 #define SEARCHMSG	"testing,testing"
 
+static void trace_pipe_cb(const char *str, void *data)
+{
+	if (strstr(str, SEARCHMSG) != NULL)
+		(*(int *)data)++;
+}
+
 void serial_test_trace_printk(void)
 {
 	struct trace_printk_lskel__bss *bss;
-	int err = 0, iter = 0, found = 0;
 	struct trace_printk_lskel *skel;
-	char *buf = NULL;
-	FILE *fp = NULL;
-	size_t buflen;
+	int err = 0, found = 0;
 
 	skel = trace_printk_lskel__open();
 	if (!ASSERT_OK_PTR(skel, "trace_printk__open"))
@@ -34,13 +36,6 @@ void serial_test_trace_printk(void)
 	if (!ASSERT_OK(err, "trace_printk__attach"))
 		goto cleanup;
 
-	fp = fopen(TRACEBUF, "r");
-	if (!ASSERT_OK_PTR(fp, "fopen(TRACEBUF)"))
-		goto cleanup;
-
-	/* We do not want to wait forever if this test fails... */
-	fcntl(fileno(fp), F_SETFL, O_NONBLOCK);
-
 	/* wait for tracepoint to trigger */
 	usleep(1);
 	trace_printk_lskel__detach(skel);
@@ -52,21 +47,12 @@ void serial_test_trace_printk(void)
 		goto cleanup;
 
 	/* verify our search string is in the trace buffer */
-	while (getline(&buf, &buflen, fp) >= 0 || errno == EAGAIN) {
-		if (strstr(buf, SEARCHMSG) != NULL)
-			found++;
-		if (found == bss->trace_printk_ran)
-			break;
-		if (++iter > 1000)
-			break;
-	}
+	ASSERT_OK(read_trace_pipe_iter(trace_pipe_cb, &found, 1000),
+		 "read_trace_pipe_iter");
 
 	if (!ASSERT_EQ(found, bss->trace_printk_ran, "found"))
 		goto cleanup;
 
 cleanup:
 	trace_printk_lskel__destroy(skel);
-	free(buf);
-	if (fp)
-		fclose(fp);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c b/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c
index 7a4e313e8558..2af6a6f2096a 100644
--- a/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c
+++ b/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c
@@ -5,17 +5,19 @@
 
 #include "trace_vprintk.lskel.h"
 
-#define TRACEBUF	"/sys/kernel/debug/tracing/trace_pipe"
 #define SEARCHMSG	"1,2,3,4,5,6,7,8,9,10"
 
+static void trace_pipe_cb(const char *str, void *data)
+{
+	if (strstr(str, SEARCHMSG) != NULL)
+		(*(int *)data)++;
+}
+
 void serial_test_trace_vprintk(void)
 {
 	struct trace_vprintk_lskel__bss *bss;
-	int err = 0, iter = 0, found = 0;
 	struct trace_vprintk_lskel *skel;
-	char *buf = NULL;
-	FILE *fp = NULL;
-	size_t buflen;
+	int err = 0, found = 0;
 
 	skel = trace_vprintk_lskel__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "trace_vprintk__open_and_load"))
@@ -27,13 +29,6 @@ void serial_test_trace_vprintk(void)
 	if (!ASSERT_OK(err, "trace_vprintk__attach"))
 		goto cleanup;
 
-	fp = fopen(TRACEBUF, "r");
-	if (!ASSERT_OK_PTR(fp, "fopen(TRACEBUF)"))
-		goto cleanup;
-
-	/* We do not want to wait forever if this test fails... */
-	fcntl(fileno(fp), F_SETFL, O_NONBLOCK);
-
 	/* wait for tracepoint to trigger */
 	usleep(1);
 	trace_vprintk_lskel__detach(skel);
@@ -45,14 +40,8 @@ void serial_test_trace_vprintk(void)
 		goto cleanup;
 
 	/* verify our search string is in the trace buffer */
-	while (getline(&buf, &buflen, fp) >= 0 || errno == EAGAIN) {
-		if (strstr(buf, SEARCHMSG) != NULL)
-			found++;
-		if (found == bss->trace_vprintk_ran)
-			break;
-		if (++iter > 1000)
-			break;
-	}
+	ASSERT_OK(read_trace_pipe_iter(trace_pipe_cb, &found, 1000),
+		 "read_trace_pipe_iter");
 
 	if (!ASSERT_EQ(found, bss->trace_vprintk_ran, "found"))
 		goto cleanup;
@@ -62,7 +51,4 @@ void serial_test_trace_vprintk(void)
 
 cleanup:
 	trace_vprintk_lskel__destroy(skel);
-	free(buf);
-	if (fp)
-		fclose(fp);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/tracing_failure.c b/tools/testing/selftests/bpf/prog_tests/tracing_failure.c
new file mode 100644
index 000000000000..10e231965589
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tracing_failure.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include "tracing_failure.skel.h"
+
+static void test_bpf_spin_lock(bool is_spin_lock)
+{
+	struct tracing_failure *skel;
+	int err;
+
+	skel = tracing_failure__open();
+	if (!ASSERT_OK_PTR(skel, "tracing_failure__open"))
+		return;
+
+	if (is_spin_lock)
+		bpf_program__set_autoload(skel->progs.test_spin_lock, true);
+	else
+		bpf_program__set_autoload(skel->progs.test_spin_unlock, true);
+
+	err = tracing_failure__load(skel);
+	if (!ASSERT_OK(err, "tracing_failure__load"))
+		goto out;
+
+	err = tracing_failure__attach(skel);
+	ASSERT_ERR(err, "tracing_failure__attach");
+
+out:
+	tracing_failure__destroy(skel);
+}
+
+static void test_tracing_fail_prog(const char *prog_name, const char *exp_msg)
+{
+	struct tracing_failure *skel;
+	struct bpf_program *prog;
+	char log_buf[256];
+	int err;
+
+	skel = tracing_failure__open();
+	if (!ASSERT_OK_PTR(skel, "tracing_failure__open"))
+		return;
+
+	prog = bpf_object__find_program_by_name(skel->obj, prog_name);
+	if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
+		goto out;
+
+	bpf_program__set_autoload(prog, true);
+	bpf_program__set_log_buf(prog, log_buf, sizeof(log_buf));
+
+	err = tracing_failure__load(skel);
+	if (!ASSERT_ERR(err, "tracing_failure__load"))
+		goto out;
+
+	ASSERT_HAS_SUBSTR(log_buf, exp_msg, "log_buf");
+out:
+	tracing_failure__destroy(skel);
+}
+
+static void test_tracing_deny(void)
+{
+	int btf_id;
+
+	/* __rcu_read_lock depends on CONFIG_PREEMPT_RCU */
+	btf_id = libbpf_find_vmlinux_btf_id("__rcu_read_lock", BPF_TRACE_FENTRY);
+	if (btf_id <= 0) {
+		test__skip();
+		return;
+	}
+
+	test_tracing_fail_prog("tracing_deny",
+			       "Attaching tracing programs to function '__rcu_read_lock' is rejected.");
+}
+
+static void test_fexit_noreturns(void)
+{
+	test_tracing_fail_prog("fexit_noreturns",
+			       "Attaching fexit/fmod_ret to __noreturn function 'do_exit' is rejected.");
+}
+
+void test_tracing_failure(void)
+{
+	if (test__start_subtest("bpf_spin_lock"))
+		test_bpf_spin_lock(true);
+	if (test__start_subtest("bpf_spin_unlock"))
+		test_bpf_spin_lock(false);
+	if (test__start_subtest("tracing_deny"))
+		test_tracing_deny();
+	if (test__start_subtest("fexit_noreturns"))
+		test_fexit_noreturns();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tracing_struct.c b/tools/testing/selftests/bpf/prog_tests/tracing_struct.c
index 48dc9472e160..6f8c0bfb0415 100644
--- a/tools/testing/selftests/bpf/prog_tests/tracing_struct.c
+++ b/tools/testing/selftests/bpf/prog_tests/tracing_struct.c
@@ -3,8 +3,9 @@
 
 #include <test_progs.h>
 #include "tracing_struct.skel.h"
+#include "tracing_struct_many_args.skel.h"
 
-static void test_fentry(void)
+static void test_struct_args(void)
 {
 	struct tracing_struct *skel;
 	int err;
@@ -53,12 +54,97 @@ static void test_fentry(void)
 
 	ASSERT_EQ(skel->bss->t5_ret, 1, "t5 ret");
 
-	tracing_struct__detach(skel);
+	ASSERT_EQ(skel->bss->t6, 1, "t6 ret");
+
+destroy_skel:
+	tracing_struct__destroy(skel);
+}
+
+static void test_struct_many_args(void)
+{
+	struct tracing_struct_many_args *skel;
+	int err;
+
+	skel = tracing_struct_many_args__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "tracing_struct_many_args__open_and_load"))
+		return;
+
+	err = tracing_struct_many_args__attach(skel);
+	if (!ASSERT_OK(err, "tracing_struct_many_args__attach"))
+		goto destroy_skel;
+
+	ASSERT_OK(trigger_module_test_read(256), "trigger_read");
+
+	ASSERT_EQ(skel->bss->t7_a, 16, "t7:a");
+	ASSERT_EQ(skel->bss->t7_b, 17, "t7:b");
+	ASSERT_EQ(skel->bss->t7_c, 18, "t7:c");
+	ASSERT_EQ(skel->bss->t7_d, 19, "t7:d");
+	ASSERT_EQ(skel->bss->t7_e, 20, "t7:e");
+	ASSERT_EQ(skel->bss->t7_f_a, 21, "t7:f.a");
+	ASSERT_EQ(skel->bss->t7_f_b, 22, "t7:f.b");
+	ASSERT_EQ(skel->bss->t7_ret, 133, "t7 ret");
+
+	ASSERT_EQ(skel->bss->t8_a, 16, "t8:a");
+	ASSERT_EQ(skel->bss->t8_b, 17, "t8:b");
+	ASSERT_EQ(skel->bss->t8_c, 18, "t8:c");
+	ASSERT_EQ(skel->bss->t8_d, 19, "t8:d");
+	ASSERT_EQ(skel->bss->t8_e, 20, "t8:e");
+	ASSERT_EQ(skel->bss->t8_f_a, 21, "t8:f.a");
+	ASSERT_EQ(skel->bss->t8_f_b, 22, "t8:f.b");
+	ASSERT_EQ(skel->bss->t8_g, 23, "t8:g");
+	ASSERT_EQ(skel->bss->t8_ret, 156, "t8 ret");
+
+	ASSERT_EQ(skel->bss->t9_a, 16, "t9:a");
+	ASSERT_EQ(skel->bss->t9_b, 17, "t9:b");
+	ASSERT_EQ(skel->bss->t9_c, 18, "t9:c");
+	ASSERT_EQ(skel->bss->t9_d, 19, "t9:d");
+	ASSERT_EQ(skel->bss->t9_e, 20, "t9:e");
+	ASSERT_EQ(skel->bss->t9_f, 21, "t9:f");
+	ASSERT_EQ(skel->bss->t9_g, 22, "t9:f");
+	ASSERT_EQ(skel->bss->t9_h_a, 23, "t9:h.a");
+	ASSERT_EQ(skel->bss->t9_h_b, 24, "t9:h.b");
+	ASSERT_EQ(skel->bss->t9_h_c, 25, "t9:h.c");
+	ASSERT_EQ(skel->bss->t9_h_d, 26, "t9:h.d");
+	ASSERT_EQ(skel->bss->t9_i, 27, "t9:i");
+	ASSERT_EQ(skel->bss->t9_ret, 258, "t9 ret");
+
 destroy_skel:
+	tracing_struct_many_args__destroy(skel);
+}
+
+static void test_union_args(void)
+{
+	struct tracing_struct *skel;
+	int err;
+
+	skel = tracing_struct__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "tracing_struct__open_and_load"))
+		return;
+
+	err = tracing_struct__attach(skel);
+	if (!ASSERT_OK(err, "tracing_struct__attach"))
+		goto out;
+
+	ASSERT_OK(trigger_module_test_read(256), "trigger_read");
+
+	ASSERT_EQ(skel->bss->ut1_a_a, 1, "ut1:a.arg.a");
+	ASSERT_EQ(skel->bss->ut1_b, 4, "ut1:b");
+	ASSERT_EQ(skel->bss->ut1_c, 5, "ut1:c");
+
+	ASSERT_EQ(skel->bss->ut2_a, 6, "ut2:a");
+	ASSERT_EQ(skel->bss->ut2_b_a, 2, "ut2:b.arg.a");
+	ASSERT_EQ(skel->bss->ut2_b_b, 3, "ut2:b.arg.b");
+
+out:
 	tracing_struct__destroy(skel);
 }
 
 void test_tracing_struct(void)
 {
-	test_fentry();
+	if (test__start_subtest("struct_args"))
+		test_struct_args();
+	if (test__start_subtest("struct_many_args"))
+		test_struct_many_args();
+	if (test__start_subtest("union_args"))
+		test_union_args();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
index 564b75bc087f..6cd7349d4a2b 100644
--- a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
+++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
@@ -2,8 +2,6 @@
 #define _GNU_SOURCE
 #include <test_progs.h>
 
-#define MAX_TRAMP_PROGS 38
-
 struct inst {
 	struct bpf_object *obj;
 	struct bpf_link   *link;
@@ -37,14 +35,21 @@ void serial_test_trampoline_count(void)
 {
 	char *file = "test_trampoline_count.bpf.o";
 	char *const progs[] = { "fentry_test", "fmod_ret_test", "fexit_test" };
-	struct inst inst[MAX_TRAMP_PROGS + 1] = {};
+	int bpf_max_tramp_links, err, i, prog_fd;
 	struct bpf_program *prog;
 	struct bpf_link *link;
-	int prog_fd, err, i;
+	struct inst *inst;
 	LIBBPF_OPTS(bpf_test_run_opts, opts);
 
+	bpf_max_tramp_links = get_bpf_max_tramp_links();
+	if (!ASSERT_GE(bpf_max_tramp_links, 1, "bpf_max_tramp_links"))
+		return;
+	inst = calloc(bpf_max_tramp_links + 1, sizeof(*inst));
+	if (!ASSERT_OK_PTR(inst, "inst"))
+		return;
+
 	/* attach 'allowed' trampoline programs */
-	for (i = 0; i < MAX_TRAMP_PROGS; i++) {
+	for (i = 0; i < bpf_max_tramp_links; i++) {
 		prog = load_prog(file, progs[i % ARRAY_SIZE(progs)], &inst[i]);
 		if (!prog)
 			goto cleanup;
@@ -74,7 +79,7 @@ void serial_test_trampoline_count(void)
 	if (!ASSERT_EQ(link, NULL, "ptr_is_null"))
 		goto cleanup;
 
-	/* and finaly execute the probe */
+	/* and finally execute the probe */
 	prog_fd = bpf_program__fd(prog);
 	if (!ASSERT_GE(prog_fd, 0, "bpf_program__fd"))
 		goto cleanup;
@@ -83,12 +88,13 @@ void serial_test_trampoline_count(void)
 	if (!ASSERT_OK(err, "bpf_prog_test_run_opts"))
 		goto cleanup;
 
-	ASSERT_EQ(opts.retval & 0xffff, 4, "bpf_modify_return_test.result");
-	ASSERT_EQ(opts.retval >> 16, 1, "bpf_modify_return_test.side_effect");
+	ASSERT_EQ(opts.retval & 0xffff, 33, "bpf_modify_return_test.result");
+	ASSERT_EQ(opts.retval >> 16, 2, "bpf_modify_return_test.side_effect");
 
 cleanup:
 	for (; i >= 0; i--) {
 		bpf_link__destroy(inst[i].link);
 		bpf_object__close(inst[i].obj);
 	}
+	free(inst);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/uninit_stack.c b/tools/testing/selftests/bpf/prog_tests/uninit_stack.c
new file mode 100644
index 000000000000..e64c71948491
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/uninit_stack.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "uninit_stack.skel.h"
+
+void test_uninit_stack(void)
+{
+	RUN_TESTS(uninit_stack);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c b/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c
index 1ed3cc2092db..472f4f9fa95f 100644
--- a/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c
+++ b/tools/testing/selftests/bpf/prog_tests/unpriv_bpf_disabled.c
@@ -7,6 +7,7 @@
 #include "test_unpriv_bpf_disabled.skel.h"
 
 #include "cap_helpers.h"
+#include "bpf_util.h"
 
 /* Using CAP_LAST_CAP is risky here, since it can get pulled in from
  * an old /usr/include/linux/capability.h and be < CAP_BPF; as a result
@@ -146,7 +147,7 @@ static void test_unpriv_bpf_disabled_negative(struct test_unpriv_bpf_disabled *s
 		BPF_MOV64_IMM(BPF_REG_0, 0),
 		BPF_EXIT_INSN(),
 	};
-	const size_t prog_insn_cnt = sizeof(prog_insns) / sizeof(struct bpf_insn);
+	const size_t prog_insn_cnt = ARRAY_SIZE(prog_insns);
 	LIBBPF_OPTS(bpf_prog_load_opts, load_opts);
 	struct bpf_map_info map_info = {};
 	__u32 map_info_len = sizeof(map_info);
@@ -171,7 +172,11 @@ static void test_unpriv_bpf_disabled_negative(struct test_unpriv_bpf_disabled *s
 				prog_insns, prog_insn_cnt, &load_opts),
 		  -EPERM, "prog_load_fails");
 
-	for (i = BPF_MAP_TYPE_HASH; i <= BPF_MAP_TYPE_BLOOM_FILTER; i++)
+	/* some map types require particular correct parameters which could be
+	 * sanity-checked before enforcing -EPERM, so only validate that
+	 * the simple ARRAY and HASH maps are failing with -EPERM
+	 */
+	for (i = BPF_MAP_TYPE_HASH; i <= BPF_MAP_TYPE_ARRAY; i++)
 		ASSERT_EQ(bpf_map_create(i, NULL, sizeof(int), sizeof(int), 1, NULL),
 			  -EPERM, "map_create_fails");
 
@@ -179,7 +184,7 @@ static void test_unpriv_bpf_disabled_negative(struct test_unpriv_bpf_disabled *s
 	ASSERT_EQ(bpf_prog_get_next_id(prog_id, &next), -EPERM, "prog_get_next_id_fails");
 	ASSERT_EQ(bpf_prog_get_next_id(0, &next), -EPERM, "prog_get_next_id_fails");
 
-	if (ASSERT_OK(bpf_obj_get_info_by_fd(map_fds[0], &map_info, &map_info_len),
+	if (ASSERT_OK(bpf_map_get_info_by_fd(map_fds[0], &map_info, &map_info_len),
 		      "obj_get_info_by_fd")) {
 		ASSERT_EQ(bpf_map_get_fd_by_id(map_info.id), -EPERM, "map_get_fd_by_id_fails");
 		ASSERT_EQ(bpf_map_get_next_id(map_info.id, &next), -EPERM,
@@ -187,8 +192,8 @@ static void test_unpriv_bpf_disabled_negative(struct test_unpriv_bpf_disabled *s
 	}
 	ASSERT_EQ(bpf_map_get_next_id(0, &next), -EPERM, "map_get_next_id_fails");
 
-	if (ASSERT_OK(bpf_obj_get_info_by_fd(bpf_link__fd(skel->links.sys_nanosleep_enter),
-					     &link_info, &link_info_len),
+	if (ASSERT_OK(bpf_link_get_info_by_fd(bpf_link__fd(skel->links.sys_nanosleep_enter),
+					      &link_info, &link_info_len),
 		      "obj_get_info_by_fd")) {
 		ASSERT_EQ(bpf_link_get_fd_by_id(link_info.id), -EPERM, "link_get_fd_by_id_fails");
 		ASSERT_EQ(bpf_link_get_next_id(link_info.id, &next), -EPERM,
@@ -269,7 +274,7 @@ void test_unpriv_bpf_disabled(void)
 	}
 
 	prog_fd = bpf_program__fd(skel->progs.sys_nanosleep_enter);
-	ASSERT_OK(bpf_obj_get_info_by_fd(prog_fd, &prog_info, &prog_info_len),
+	ASSERT_OK(bpf_prog_get_info_by_fd(prog_fd, &prog_info, &prog_info_len),
 		  "obj_get_info_by_fd");
 	prog_id = prog_info.id;
 	ASSERT_GT(prog_id, 0, "valid_prog_id");
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe.c b/tools/testing/selftests/bpf/prog_tests/uprobe.c
new file mode 100644
index 000000000000..86404476c1da
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe.c
@@ -0,0 +1,249 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Hengqi Chen */
+
+#include <test_progs.h>
+#include <asm/ptrace.h>
+#include "test_uprobe.skel.h"
+
+static FILE *urand_spawn(int *pid)
+{
+	FILE *f;
+
+	/* urandom_read's stdout is wired into f */
+	f = popen("./urandom_read 1 report-pid", "r");
+	if (!f)
+		return NULL;
+
+	if (fscanf(f, "%d", pid) != 1) {
+		pclose(f);
+		errno = EINVAL;
+		return NULL;
+	}
+
+	return f;
+}
+
+static int urand_trigger(FILE **urand_pipe)
+{
+	int exit_code;
+
+	/* pclose() waits for child process to exit and returns their exit code */
+	exit_code = pclose(*urand_pipe);
+	*urand_pipe = NULL;
+
+	return exit_code;
+}
+
+static void test_uprobe_attach(void)
+{
+	LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
+	struct test_uprobe *skel;
+	FILE *urand_pipe = NULL;
+	int urand_pid = 0, err;
+
+	skel = test_uprobe__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	urand_pipe = urand_spawn(&urand_pid);
+	if (!ASSERT_OK_PTR(urand_pipe, "urand_spawn"))
+		goto cleanup;
+
+	skel->bss->my_pid = urand_pid;
+
+	/* Manual attach uprobe to urandlib_api
+	 * There are two `urandlib_api` symbols in .dynsym section:
+	 *   - urandlib_api@LIBURANDOM_READ_1.0.0
+	 *   - urandlib_api@@LIBURANDOM_READ_2.0.0
+	 * Both are global bind and would cause a conflict if user
+	 * specify the symbol name without a version suffix
+	 */
+	uprobe_opts.func_name = "urandlib_api";
+	skel->links.test4 = bpf_program__attach_uprobe_opts(skel->progs.test4,
+							    urand_pid,
+							    "./liburandom_read.so",
+							    0 /* offset */,
+							    &uprobe_opts);
+	if (!ASSERT_ERR_PTR(skel->links.test4, "urandlib_api_attach_conflict"))
+		goto cleanup;
+
+	uprobe_opts.func_name = "urandlib_api@LIBURANDOM_READ_1.0.0";
+	skel->links.test4 = bpf_program__attach_uprobe_opts(skel->progs.test4,
+							    urand_pid,
+							    "./liburandom_read.so",
+							    0 /* offset */,
+							    &uprobe_opts);
+	if (!ASSERT_OK_PTR(skel->links.test4, "urandlib_api_attach_ok"))
+		goto cleanup;
+
+	/* Auto attach 3 u[ret]probes to urandlib_api_sameoffset */
+	err = test_uprobe__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	/* trigger urandom_read */
+	ASSERT_OK(urand_trigger(&urand_pipe), "urand_exit_code");
+
+	ASSERT_EQ(skel->bss->test1_result, 1, "urandlib_api_sameoffset");
+	ASSERT_EQ(skel->bss->test2_result, 1, "urandlib_api_sameoffset@v1");
+	ASSERT_EQ(skel->bss->test3_result, 3, "urandlib_api_sameoffset@@v2");
+	ASSERT_EQ(skel->bss->test4_result, 1, "urandlib_api");
+
+cleanup:
+	if (urand_pipe)
+		pclose(urand_pipe);
+	test_uprobe__destroy(skel);
+}
+
+#ifdef __x86_64__
+__naked __maybe_unused unsigned long uprobe_regs_change_trigger(void)
+{
+	asm volatile (
+		"ret\n"
+	);
+}
+
+static __naked void uprobe_regs_change(struct pt_regs *before, struct pt_regs *after)
+{
+	asm volatile (
+		"movq %r11,  48(%rdi)\n"
+		"movq %r10,  56(%rdi)\n"
+		"movq  %r9,  64(%rdi)\n"
+		"movq  %r8,  72(%rdi)\n"
+		"movq %rax,  80(%rdi)\n"
+		"movq %rcx,  88(%rdi)\n"
+		"movq %rdx,  96(%rdi)\n"
+		"movq %rsi, 104(%rdi)\n"
+		"movq %rdi, 112(%rdi)\n"
+
+		/* save 2nd argument */
+		"pushq %rsi\n"
+		"call uprobe_regs_change_trigger\n"
+
+		/* save  return value and load 2nd argument pointer to rax */
+		"pushq %rax\n"
+		"movq 8(%rsp), %rax\n"
+
+		"movq %r11,  48(%rax)\n"
+		"movq %r10,  56(%rax)\n"
+		"movq  %r9,  64(%rax)\n"
+		"movq  %r8,  72(%rax)\n"
+		"movq %rcx,  88(%rax)\n"
+		"movq %rdx,  96(%rax)\n"
+		"movq %rsi, 104(%rax)\n"
+		"movq %rdi, 112(%rax)\n"
+
+		/* restore return value and 2nd argument */
+		"pop %rax\n"
+		"pop %rsi\n"
+
+		"movq %rax,  80(%rsi)\n"
+		"ret\n"
+	);
+}
+
+static void regs_common(void)
+{
+	struct pt_regs before = {}, after = {}, expected = {
+		.rax = 0xc0ffe,
+		.rcx = 0xbad,
+		.rdx = 0xdead,
+		.r8  = 0x8,
+		.r9  = 0x9,
+		.r10 = 0x10,
+		.r11 = 0x11,
+		.rdi = 0x12,
+		.rsi = 0x13,
+	};
+	LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
+	struct test_uprobe *skel;
+
+	skel = test_uprobe__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	skel->bss->my_pid = getpid();
+	skel->bss->regs = expected;
+
+	uprobe_opts.func_name = "uprobe_regs_change_trigger";
+	skel->links.test_regs_change = bpf_program__attach_uprobe_opts(skel->progs.test_regs_change,
+							    -1,
+							    "/proc/self/exe",
+							    0 /* offset */,
+							    &uprobe_opts);
+	if (!ASSERT_OK_PTR(skel->links.test_regs_change, "bpf_program__attach_uprobe_opts"))
+		goto cleanup;
+
+	uprobe_regs_change(&before, &after);
+
+	ASSERT_EQ(after.rax, expected.rax, "ax");
+	ASSERT_EQ(after.rcx, expected.rcx, "cx");
+	ASSERT_EQ(after.rdx, expected.rdx, "dx");
+	ASSERT_EQ(after.r8,  expected.r8,  "r8");
+	ASSERT_EQ(after.r9,  expected.r9,  "r9");
+	ASSERT_EQ(after.r10, expected.r10, "r10");
+	ASSERT_EQ(after.r11, expected.r11, "r11");
+	ASSERT_EQ(after.rdi, expected.rdi, "rdi");
+	ASSERT_EQ(after.rsi, expected.rsi, "rsi");
+
+cleanup:
+	test_uprobe__destroy(skel);
+}
+
+static noinline unsigned long uprobe_regs_change_ip_1(void)
+{
+	return 0xc0ffee;
+}
+
+static noinline unsigned long uprobe_regs_change_ip_2(void)
+{
+	return 0xdeadbeef;
+}
+
+static void regs_ip(void)
+{
+	LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
+	struct test_uprobe *skel;
+	unsigned long ret;
+
+	skel = test_uprobe__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	skel->bss->my_pid = getpid();
+	skel->bss->ip = (unsigned long) uprobe_regs_change_ip_2;
+
+	uprobe_opts.func_name = "uprobe_regs_change_ip_1";
+	skel->links.test_regs_change_ip = bpf_program__attach_uprobe_opts(
+						skel->progs.test_regs_change_ip,
+						-1,
+						"/proc/self/exe",
+						0 /* offset */,
+						&uprobe_opts);
+	if (!ASSERT_OK_PTR(skel->links.test_regs_change_ip, "bpf_program__attach_uprobe_opts"))
+		goto cleanup;
+
+	ret = uprobe_regs_change_ip_1();
+	ASSERT_EQ(ret, 0xdeadbeef, "ret");
+
+cleanup:
+	test_uprobe__destroy(skel);
+}
+
+static void test_uprobe_regs_change(void)
+{
+	if (test__start_subtest("regs_change_common"))
+		regs_common();
+	if (test__start_subtest("regs_change_ip"))
+		regs_ip();
+}
+#else
+static void test_uprobe_regs_change(void) { }
+#endif
+
+void test_uprobe(void)
+{
+	if (test__start_subtest("attach"))
+		test_uprobe_attach();
+	test_uprobe_regs_change();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c b/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c
index 35b87c7ba5be..d5b3377aa33c 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c
@@ -5,18 +5,20 @@
 #include "test_uprobe_autoattach.skel.h"
 
 /* uprobe attach point */
-static noinline int autoattach_trigger_func(int arg)
+static noinline int autoattach_trigger_func(int arg1, int arg2, int arg3,
+					    int arg4, int arg5, int arg6,
+					    int arg7, int arg8)
 {
 	asm volatile ("");
-	return arg + 1;
+	return arg1 + arg2 + arg3 + arg4 + arg5 + arg6 + arg7 + arg8 + 1;
 }
 
 void test_uprobe_autoattach(void)
 {
+	const char *devnull_str = "/dev/null";
 	struct test_uprobe_autoattach *skel;
-	int trigger_val = 100, trigger_ret;
-	size_t malloc_sz = 1;
-	char *mem;
+	int trigger_ret;
+	FILE *devnull;
 
 	skel = test_uprobe_autoattach__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
@@ -28,23 +30,45 @@ void test_uprobe_autoattach(void)
 	skel->bss->test_pid = getpid();
 
 	/* trigger & validate uprobe & uretprobe */
-	trigger_ret = autoattach_trigger_func(trigger_val);
+	trigger_ret = autoattach_trigger_func(1, 2, 3, 4, 5, 6, 7, 8);
 
 	skel->bss->test_pid = getpid();
 
 	/* trigger & validate shared library u[ret]probes attached by name */
-	mem = malloc(malloc_sz);
+	devnull = fopen(devnull_str, "r");
 
-	ASSERT_EQ(skel->bss->uprobe_byname_parm1, trigger_val, "check_uprobe_byname_parm1");
+	ASSERT_EQ(skel->bss->uprobe_byname_parm1, 1, "check_uprobe_byname_parm1");
 	ASSERT_EQ(skel->bss->uprobe_byname_ran, 1, "check_uprobe_byname_ran");
 	ASSERT_EQ(skel->bss->uretprobe_byname_rc, trigger_ret, "check_uretprobe_byname_rc");
+	ASSERT_EQ(skel->bss->uretprobe_byname_ret, trigger_ret, "check_uretprobe_byname_ret");
 	ASSERT_EQ(skel->bss->uretprobe_byname_ran, 2, "check_uretprobe_byname_ran");
-	ASSERT_EQ(skel->bss->uprobe_byname2_parm1, malloc_sz, "check_uprobe_byname2_parm1");
+	ASSERT_EQ(skel->bss->uprobe_byname2_parm1, (__u64)(long)devnull_str,
+		  "check_uprobe_byname2_parm1");
 	ASSERT_EQ(skel->bss->uprobe_byname2_ran, 3, "check_uprobe_byname2_ran");
-	ASSERT_EQ(skel->bss->uretprobe_byname2_rc, mem, "check_uretprobe_byname2_rc");
+	ASSERT_EQ(skel->bss->uretprobe_byname2_rc, (__u64)(long)devnull,
+		  "check_uretprobe_byname2_rc");
 	ASSERT_EQ(skel->bss->uretprobe_byname2_ran, 4, "check_uretprobe_byname2_ran");
 
-	free(mem);
+	ASSERT_EQ(skel->bss->a[0], 1, "arg1");
+	ASSERT_EQ(skel->bss->a[1], 2, "arg2");
+	ASSERT_EQ(skel->bss->a[2], 3, "arg3");
+#if FUNC_REG_ARG_CNT > 3
+	ASSERT_EQ(skel->bss->a[3], 4, "arg4");
+#endif
+#if FUNC_REG_ARG_CNT > 4
+	ASSERT_EQ(skel->bss->a[4], 5, "arg5");
+#endif
+#if FUNC_REG_ARG_CNT > 5
+	ASSERT_EQ(skel->bss->a[5], 6, "arg6");
+#endif
+#if FUNC_REG_ARG_CNT > 6
+	ASSERT_EQ(skel->bss->a[6], 7, "arg7");
+#endif
+#if FUNC_REG_ARG_CNT > 7
+	ASSERT_EQ(skel->bss->a[7], 8, "arg8");
+#endif
+
+	fclose(devnull);
 cleanup:
 	test_uprobe_autoattach__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
new file mode 100644
index 000000000000..2ee17ef1dae2
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
@@ -0,0 +1,1376 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <unistd.h>
+#include <pthread.h>
+#include <test_progs.h>
+#include "uprobe_multi.skel.h"
+#include "uprobe_multi_bench.skel.h"
+#include "uprobe_multi_usdt.skel.h"
+#include "uprobe_multi_consumers.skel.h"
+#include "uprobe_multi_pid_filter.skel.h"
+#include "uprobe_multi_session.skel.h"
+#include "uprobe_multi_session_single.skel.h"
+#include "uprobe_multi_session_cookie.skel.h"
+#include "uprobe_multi_session_recursive.skel.h"
+#include "uprobe_multi_verifier.skel.h"
+#include "bpf/libbpf_internal.h"
+#include "testing_helpers.h"
+#include "../sdt.h"
+
+static char test_data[] = "test_data";
+
+noinline void uprobe_multi_func_1(void)
+{
+	asm volatile ("");
+}
+
+noinline void uprobe_multi_func_2(void)
+{
+	asm volatile ("");
+}
+
+noinline void uprobe_multi_func_3(void)
+{
+	asm volatile ("");
+}
+
+noinline void usdt_trigger(void)
+{
+	STAP_PROBE(test, pid_filter_usdt);
+}
+
+noinline void uprobe_session_recursive(int i)
+{
+	if (i)
+		uprobe_session_recursive(i - 1);
+}
+
+struct child {
+	int go[2];
+	int c2p[2]; /* child -> parent channel */
+	int pid;
+	int tid;
+	pthread_t thread;
+	char stack[65536];
+};
+
+static void release_child(struct child *child)
+{
+	int child_status;
+
+	if (!child)
+		return;
+	close(child->go[1]);
+	close(child->go[0]);
+	if (child->thread)
+		pthread_join(child->thread, NULL);
+	close(child->c2p[0]);
+	close(child->c2p[1]);
+	if (child->pid > 0)
+		waitpid(child->pid, &child_status, 0);
+}
+
+static void kick_child(struct child *child)
+{
+	char c = 1;
+
+	if (child) {
+		write(child->go[1], &c, 1);
+		release_child(child);
+	}
+	fflush(NULL);
+}
+
+static int child_func(void *arg)
+{
+	struct child *child = arg;
+	int err, c;
+
+	close(child->go[1]);
+
+	/* wait for parent's kick */
+	err = read(child->go[0], &c, 1);
+	if (err != 1)
+		exit(err);
+
+	uprobe_multi_func_1();
+	uprobe_multi_func_2();
+	uprobe_multi_func_3();
+	usdt_trigger();
+
+	exit(errno);
+}
+
+static int spawn_child_flag(struct child *child, bool clone_vm)
+{
+	/* pipe to notify child to execute the trigger functions */
+	if (pipe(child->go))
+		return -1;
+
+	if (clone_vm) {
+		child->pid = child->tid = clone(child_func, child->stack + sizeof(child->stack)/2,
+						CLONE_VM|SIGCHLD, child);
+	} else {
+		child->pid = child->tid = fork();
+	}
+	if (child->pid < 0) {
+		release_child(child);
+		errno = EINVAL;
+		return -1;
+	}
+
+	/* fork-ed child */
+	if (!clone_vm && child->pid == 0)
+		child_func(child);
+
+	return 0;
+}
+
+static int spawn_child(struct child *child)
+{
+	return spawn_child_flag(child, false);
+}
+
+static void *child_thread(void *ctx)
+{
+	struct child *child = ctx;
+	int c = 0, err;
+
+	child->tid = sys_gettid();
+
+	/* let parent know we are ready */
+	err = write(child->c2p[1], &c, 1);
+	if (err != 1)
+		pthread_exit(&err);
+
+	/* wait for parent's kick */
+	err = read(child->go[0], &c, 1);
+	if (err != 1)
+		pthread_exit(&err);
+
+	uprobe_multi_func_1();
+	uprobe_multi_func_2();
+	uprobe_multi_func_3();
+	usdt_trigger();
+
+	err = 0;
+	pthread_exit(&err);
+}
+
+static int spawn_thread(struct child *child)
+{
+	int c, err;
+
+	/* pipe to notify child to execute the trigger functions */
+	if (pipe(child->go))
+		return -1;
+	/* pipe to notify parent that child thread is ready */
+	if (pipe(child->c2p)) {
+		close(child->go[0]);
+		close(child->go[1]);
+		return -1;
+	}
+
+	child->pid = getpid();
+
+	err = pthread_create(&child->thread, NULL, child_thread, child);
+	if (err) {
+		err = -errno;
+		close(child->go[0]);
+		close(child->go[1]);
+		close(child->c2p[0]);
+		close(child->c2p[1]);
+		errno = -err;
+		return -1;
+	}
+
+	err = read(child->c2p[0], &c, 1);
+	if (!ASSERT_EQ(err, 1, "child_thread_ready"))
+		return -1;
+
+	return 0;
+}
+
+static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child)
+{
+	skel->bss->uprobe_multi_func_1_addr = (__u64) uprobe_multi_func_1;
+	skel->bss->uprobe_multi_func_2_addr = (__u64) uprobe_multi_func_2;
+	skel->bss->uprobe_multi_func_3_addr = (__u64) uprobe_multi_func_3;
+
+	skel->bss->user_ptr = test_data;
+
+	/*
+	 * Disable pid check in bpf program if we are pid filter test,
+	 * because the probe should be executed only by child->pid
+	 * passed at the probe attach.
+	 */
+	skel->bss->pid = child ? 0 : getpid();
+	skel->bss->expect_pid = child ? child->pid : 0;
+
+	/* trigger all probes, if we are testing child *process*, just to make
+	 * sure that PID filtering doesn't let through activations from wrong
+	 * PIDs; when we test child *thread*, we don't want to do this to
+	 * avoid double counting number of triggering events
+	 */
+	if (!child || !child->thread) {
+		uprobe_multi_func_1();
+		uprobe_multi_func_2();
+		uprobe_multi_func_3();
+		usdt_trigger();
+	}
+
+	if (child)
+		kick_child(child);
+
+	/*
+	 * There are 2 entry and 2 exit probe called for each uprobe_multi_func_[123]
+	 * function and each sleepable probe (6) increments uprobe_multi_sleep_result.
+	 */
+	ASSERT_EQ(skel->bss->uprobe_multi_func_1_result, 2, "uprobe_multi_func_1_result");
+	ASSERT_EQ(skel->bss->uprobe_multi_func_2_result, 2, "uprobe_multi_func_2_result");
+	ASSERT_EQ(skel->bss->uprobe_multi_func_3_result, 2, "uprobe_multi_func_3_result");
+
+	ASSERT_EQ(skel->bss->uretprobe_multi_func_1_result, 2, "uretprobe_multi_func_1_result");
+	ASSERT_EQ(skel->bss->uretprobe_multi_func_2_result, 2, "uretprobe_multi_func_2_result");
+	ASSERT_EQ(skel->bss->uretprobe_multi_func_3_result, 2, "uretprobe_multi_func_3_result");
+
+	ASSERT_EQ(skel->bss->uprobe_multi_sleep_result, 6, "uprobe_multi_sleep_result");
+
+	ASSERT_FALSE(skel->bss->bad_pid_seen, "bad_pid_seen");
+
+	if (child) {
+		ASSERT_EQ(skel->bss->child_pid, child->pid, "uprobe_multi_child_pid");
+		ASSERT_EQ(skel->bss->child_tid, child->tid, "uprobe_multi_child_tid");
+	}
+}
+
+static void test_skel_api(void)
+{
+	struct uprobe_multi *skel = NULL;
+	int err;
+
+	skel = uprobe_multi__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi__open_and_load"))
+		goto cleanup;
+
+	err = uprobe_multi__attach(skel);
+	if (!ASSERT_OK(err, "uprobe_multi__attach"))
+		goto cleanup;
+
+	uprobe_multi_test_run(skel, NULL);
+
+cleanup:
+	uprobe_multi__destroy(skel);
+}
+
+static void
+__test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_multi_opts *opts,
+		  struct child *child)
+{
+	pid_t pid = child ? child->pid : -1;
+	struct uprobe_multi *skel = NULL;
+
+	skel = uprobe_multi__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi__open_and_load"))
+		goto cleanup;
+
+	opts->retprobe = false;
+	skel->links.uprobe = bpf_program__attach_uprobe_multi(skel->progs.uprobe, pid,
+							      binary, pattern, opts);
+	if (!ASSERT_OK_PTR(skel->links.uprobe, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	opts->retprobe = true;
+	skel->links.uretprobe = bpf_program__attach_uprobe_multi(skel->progs.uretprobe, pid,
+								 binary, pattern, opts);
+	if (!ASSERT_OK_PTR(skel->links.uretprobe, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	opts->retprobe = false;
+	skel->links.uprobe_sleep = bpf_program__attach_uprobe_multi(skel->progs.uprobe_sleep, pid,
+								    binary, pattern, opts);
+	if (!ASSERT_OK_PTR(skel->links.uprobe_sleep, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	opts->retprobe = true;
+	skel->links.uretprobe_sleep = bpf_program__attach_uprobe_multi(skel->progs.uretprobe_sleep,
+								       pid, binary, pattern, opts);
+	if (!ASSERT_OK_PTR(skel->links.uretprobe_sleep, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	opts->retprobe = false;
+	skel->links.uprobe_extra = bpf_program__attach_uprobe_multi(skel->progs.uprobe_extra, -1,
+								    binary, pattern, opts);
+	if (!ASSERT_OK_PTR(skel->links.uprobe_extra, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	/* Attach (uprobe-backed) USDTs */
+	skel->links.usdt_pid = bpf_program__attach_usdt(skel->progs.usdt_pid, pid, binary,
+							"test", "pid_filter_usdt", NULL);
+	if (!ASSERT_OK_PTR(skel->links.usdt_pid, "attach_usdt_pid"))
+		goto cleanup;
+
+	skel->links.usdt_extra = bpf_program__attach_usdt(skel->progs.usdt_extra, -1, binary,
+							  "test", "pid_filter_usdt", NULL);
+	if (!ASSERT_OK_PTR(skel->links.usdt_extra, "attach_usdt_extra"))
+		goto cleanup;
+
+	uprobe_multi_test_run(skel, child);
+
+	ASSERT_FALSE(skel->bss->bad_pid_seen_usdt, "bad_pid_seen_usdt");
+	if (child) {
+		ASSERT_EQ(skel->bss->child_pid_usdt, child->pid, "usdt_multi_child_pid");
+		ASSERT_EQ(skel->bss->child_tid_usdt, child->tid, "usdt_multi_child_tid");
+	}
+cleanup:
+	uprobe_multi__destroy(skel);
+}
+
+static void
+test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_multi_opts *opts)
+{
+	static struct child child;
+
+	/* no pid filter */
+	__test_attach_api(binary, pattern, opts, NULL);
+
+	/* pid filter */
+	if (!ASSERT_OK(spawn_child(&child), "spawn_child"))
+		return;
+
+	__test_attach_api(binary, pattern, opts, &child);
+
+	/* pid filter (thread) */
+	if (!ASSERT_OK(spawn_thread(&child), "spawn_thread"))
+		return;
+
+	__test_attach_api(binary, pattern, opts, &child);
+}
+
+static void test_attach_api_pattern(void)
+{
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts);
+
+	test_attach_api("/proc/self/exe", "uprobe_multi_func_*", &opts);
+	test_attach_api("/proc/self/exe", "uprobe_multi_func_?", &opts);
+}
+
+static void test_attach_api_syms(void)
+{
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts);
+	const char *syms[3] = {
+		"uprobe_multi_func_1",
+		"uprobe_multi_func_2",
+		"uprobe_multi_func_3",
+	};
+
+	opts.syms = syms;
+	opts.cnt = ARRAY_SIZE(syms);
+	test_attach_api("/proc/self/exe", NULL, &opts);
+}
+
+static void test_attach_api_fails(void)
+{
+	LIBBPF_OPTS(bpf_link_create_opts, opts);
+	const char *path = "/proc/self/exe";
+	struct uprobe_multi *skel = NULL;
+	int prog_fd, link_fd = -1;
+	unsigned long offset = 0;
+
+	skel = uprobe_multi__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi__open_and_load"))
+		goto cleanup;
+
+	prog_fd = bpf_program__fd(skel->progs.uprobe_extra);
+
+	/* abnormal cnt */
+	opts.uprobe_multi.path = path;
+	opts.uprobe_multi.offsets = &offset;
+	opts.uprobe_multi.cnt = INT_MAX;
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -E2BIG, "big cnt"))
+		goto cleanup;
+
+	/* cnt is 0 */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = path,
+		.uprobe_multi.offsets = (unsigned long *) &offset,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EINVAL, "cnt_is_zero"))
+		goto cleanup;
+
+	/* negative offset */
+	offset = -1;
+	opts.uprobe_multi.path = path;
+	opts.uprobe_multi.offsets = (unsigned long *) &offset;
+	opts.uprobe_multi.cnt = 1;
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EINVAL, "offset_is_negative"))
+		goto cleanup;
+
+	/* offsets is NULL */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = path,
+		.uprobe_multi.cnt = 1,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EINVAL, "offsets_is_null"))
+		goto cleanup;
+
+	/* wrong offsets pointer */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = path,
+		.uprobe_multi.offsets = (unsigned long *) 1,
+		.uprobe_multi.cnt = 1,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EFAULT, "offsets_is_wrong"))
+		goto cleanup;
+
+	/* path is NULL */
+	offset = 1;
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.offsets = (unsigned long *) &offset,
+		.uprobe_multi.cnt = 1,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EINVAL, "path_is_null"))
+		goto cleanup;
+
+	/* wrong path pointer  */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = (const char *) 1,
+		.uprobe_multi.offsets = (unsigned long *) &offset,
+		.uprobe_multi.cnt = 1,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EFAULT, "path_is_wrong"))
+		goto cleanup;
+
+	/* wrong path type */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = "/",
+		.uprobe_multi.offsets = (unsigned long *) &offset,
+		.uprobe_multi.cnt = 1,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EBADF, "path_is_wrong_type"))
+		goto cleanup;
+
+	/* wrong cookies pointer */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = path,
+		.uprobe_multi.offsets = (unsigned long *) &offset,
+		.uprobe_multi.cookies = (__u64 *) 1ULL,
+		.uprobe_multi.cnt = 1,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EFAULT, "cookies_is_wrong"))
+		goto cleanup;
+
+	/* wrong ref_ctr_offsets pointer */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = path,
+		.uprobe_multi.offsets = (unsigned long *) &offset,
+		.uprobe_multi.cookies = (__u64 *) &offset,
+		.uprobe_multi.ref_ctr_offsets = (unsigned long *) 1,
+		.uprobe_multi.cnt = 1,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EFAULT, "ref_ctr_offsets_is_wrong"))
+		goto cleanup;
+
+	/* wrong flags */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.flags = 1 << 31,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	if (!ASSERT_EQ(link_fd, -EINVAL, "wrong_flags"))
+		goto cleanup;
+
+	/* wrong pid */
+	LIBBPF_OPTS_RESET(opts,
+		.uprobe_multi.path = path,
+		.uprobe_multi.offsets = (unsigned long *) &offset,
+		.uprobe_multi.cnt = 1,
+		.uprobe_multi.pid = -2,
+	);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		goto cleanup;
+	ASSERT_EQ(link_fd, -EINVAL, "pid_is_wrong");
+
+cleanup:
+	if (link_fd >= 0)
+		close(link_fd);
+	uprobe_multi__destroy(skel);
+}
+
+#ifdef __x86_64__
+noinline void uprobe_multi_error_func(void)
+{
+	/*
+	 * If --fcf-protection=branch is enabled the gcc generates endbr as
+	 * first instruction, so marking the exact address of int3 with the
+	 * symbol to be used in the attach_uprobe_fail_trap test below.
+	 */
+	asm volatile (
+		".globl uprobe_multi_error_func_int3;	\n"
+		"uprobe_multi_error_func_int3:		\n"
+		"int3					\n"
+	);
+}
+
+/*
+ * Attaching uprobe on uprobe_multi_error_func results in error
+ * because it already starts with int3 instruction.
+ */
+static void attach_uprobe_fail_trap(struct uprobe_multi *skel)
+{
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts);
+	const char *syms[4] = {
+		"uprobe_multi_func_1",
+		"uprobe_multi_func_2",
+		"uprobe_multi_func_3",
+		"uprobe_multi_error_func_int3",
+	};
+
+	opts.syms = syms;
+	opts.cnt = ARRAY_SIZE(syms);
+
+	skel->links.uprobe = bpf_program__attach_uprobe_multi(skel->progs.uprobe, -1,
+							      "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_ERR_PTR(skel->links.uprobe, "bpf_program__attach_uprobe_multi")) {
+		bpf_link__destroy(skel->links.uprobe);
+		skel->links.uprobe = NULL;
+	}
+}
+#else
+static void attach_uprobe_fail_trap(struct uprobe_multi *skel) { }
+#endif
+
+short sema_1 __used, sema_2 __used;
+
+static void attach_uprobe_fail_refctr(struct uprobe_multi *skel)
+{
+	unsigned long *tmp_offsets = NULL, *tmp_ref_ctr_offsets = NULL;
+	unsigned long offsets[3], ref_ctr_offsets[3];
+	LIBBPF_OPTS(bpf_link_create_opts, opts);
+	const char *path = "/proc/self/exe";
+	const char *syms[3] = {
+		"uprobe_multi_func_1",
+		"uprobe_multi_func_2",
+	};
+	const char *sema[3] = {
+		"sema_1",
+		"sema_2",
+	};
+	int prog_fd, link_fd, err;
+
+	prog_fd = bpf_program__fd(skel->progs.uprobe_extra);
+
+	err = elf_resolve_syms_offsets("/proc/self/exe", 2, (const char **) &syms,
+				       &tmp_offsets, STT_FUNC);
+	if (!ASSERT_OK(err, "elf_resolve_syms_offsets_func"))
+		return;
+
+	err = elf_resolve_syms_offsets("/proc/self/exe", 2, (const char **) &sema,
+				       &tmp_ref_ctr_offsets, STT_OBJECT);
+	if (!ASSERT_OK(err, "elf_resolve_syms_offsets_sema"))
+		goto cleanup;
+
+	/*
+	 * We attach to 3 uprobes on 2 functions, so 2 uprobes share single function,
+	 * but with different ref_ctr_offset which is not allowed and results in fail.
+	 */
+	offsets[0] = tmp_offsets[0]; /* uprobe_multi_func_1 */
+	offsets[1] = tmp_offsets[1]; /* uprobe_multi_func_2 */
+	offsets[2] = tmp_offsets[1]; /* uprobe_multi_func_2 */
+
+	ref_ctr_offsets[0] = tmp_ref_ctr_offsets[0]; /* sema_1 */
+	ref_ctr_offsets[1] = tmp_ref_ctr_offsets[1]; /* sema_2 */
+	ref_ctr_offsets[2] = tmp_ref_ctr_offsets[0]; /* sema_1, error */
+
+	opts.uprobe_multi.path = path;
+	opts.uprobe_multi.offsets = (const unsigned long *) &offsets;
+	opts.uprobe_multi.ref_ctr_offsets = (const unsigned long *) &ref_ctr_offsets;
+	opts.uprobe_multi.cnt = 3;
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_ERR(link_fd, "link_fd"))
+		close(link_fd);
+
+cleanup:
+	free(tmp_ref_ctr_offsets);
+	free(tmp_offsets);
+}
+
+static void test_attach_uprobe_fails(void)
+{
+	struct uprobe_multi *skel = NULL;
+
+	skel = uprobe_multi__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi__open_and_load"))
+		return;
+
+	/* attach fails due to adding uprobe on trap instruction, x86_64 only */
+	attach_uprobe_fail_trap(skel);
+
+	/* attach fail due to wrong ref_ctr_offs on one of the uprobes */
+	attach_uprobe_fail_refctr(skel);
+
+	uprobe_multi__destroy(skel);
+}
+
+static void __test_link_api(struct child *child)
+{
+	int prog_fd, link1_fd = -1, link2_fd = -1, link3_fd = -1, link4_fd = -1;
+	LIBBPF_OPTS(bpf_link_create_opts, opts);
+	const char *path = "/proc/self/exe";
+	struct uprobe_multi *skel = NULL;
+	unsigned long *offsets = NULL;
+	const char *syms[3] = {
+		"uprobe_multi_func_1",
+		"uprobe_multi_func_2",
+		"uprobe_multi_func_3",
+	};
+	int link_extra_fd = -1;
+	int err;
+
+	err = elf_resolve_syms_offsets(path, 3, syms, (unsigned long **) &offsets, STT_FUNC);
+	if (!ASSERT_OK(err, "elf_resolve_syms_offsets"))
+		return;
+
+	opts.uprobe_multi.path = path;
+	opts.uprobe_multi.offsets = offsets;
+	opts.uprobe_multi.cnt = ARRAY_SIZE(syms);
+	opts.uprobe_multi.pid = child ? child->pid : 0;
+
+	skel = uprobe_multi__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi__open_and_load"))
+		goto cleanup;
+
+	opts.kprobe_multi.flags = 0;
+	prog_fd = bpf_program__fd(skel->progs.uprobe);
+	link1_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_GE(link1_fd, 0, "link1_fd"))
+		goto cleanup;
+
+	opts.kprobe_multi.flags = BPF_F_UPROBE_MULTI_RETURN;
+	prog_fd = bpf_program__fd(skel->progs.uretprobe);
+	link2_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_GE(link2_fd, 0, "link2_fd"))
+		goto cleanup;
+
+	opts.kprobe_multi.flags = 0;
+	prog_fd = bpf_program__fd(skel->progs.uprobe_sleep);
+	link3_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_GE(link3_fd, 0, "link3_fd"))
+		goto cleanup;
+
+	opts.kprobe_multi.flags = BPF_F_UPROBE_MULTI_RETURN;
+	prog_fd = bpf_program__fd(skel->progs.uretprobe_sleep);
+	link4_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_GE(link4_fd, 0, "link4_fd"))
+		goto cleanup;
+
+	opts.kprobe_multi.flags = 0;
+	opts.uprobe_multi.pid = 0;
+	prog_fd = bpf_program__fd(skel->progs.uprobe_extra);
+	link_extra_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
+	if (!ASSERT_GE(link_extra_fd, 0, "link_extra_fd"))
+		goto cleanup;
+
+	uprobe_multi_test_run(skel, child);
+
+cleanup:
+	if (link1_fd >= 0)
+		close(link1_fd);
+	if (link2_fd >= 0)
+		close(link2_fd);
+	if (link3_fd >= 0)
+		close(link3_fd);
+	if (link4_fd >= 0)
+		close(link4_fd);
+	if (link_extra_fd >= 0)
+		close(link_extra_fd);
+
+	uprobe_multi__destroy(skel);
+	free(offsets);
+}
+
+static void test_link_api(void)
+{
+	static struct child child;
+
+	/* no pid filter */
+	__test_link_api(NULL);
+
+	/* pid filter */
+	if (!ASSERT_OK(spawn_child(&child), "spawn_child"))
+		return;
+
+	__test_link_api(&child);
+
+	/* pid filter (thread) */
+	if (!ASSERT_OK(spawn_thread(&child), "spawn_thread"))
+		return;
+
+	__test_link_api(&child);
+}
+
+static struct bpf_program *
+get_program(struct uprobe_multi_consumers *skel, int prog)
+{
+	switch (prog) {
+	case 0:
+		return skel->progs.uprobe_0;
+	case 1:
+		return skel->progs.uprobe_1;
+	case 2:
+		return skel->progs.uprobe_2;
+	case 3:
+		return skel->progs.uprobe_3;
+	default:
+		ASSERT_FAIL("get_program");
+		return NULL;
+	}
+}
+
+static struct bpf_link **
+get_link(struct uprobe_multi_consumers *skel, int link)
+{
+	switch (link) {
+	case 0:
+		return &skel->links.uprobe_0;
+	case 1:
+		return &skel->links.uprobe_1;
+	case 2:
+		return &skel->links.uprobe_2;
+	case 3:
+		return &skel->links.uprobe_3;
+	default:
+		ASSERT_FAIL("get_link");
+		return NULL;
+	}
+}
+
+static int uprobe_attach(struct uprobe_multi_consumers *skel, int idx, unsigned long offset)
+{
+	struct bpf_program *prog = get_program(skel, idx);
+	struct bpf_link **link = get_link(skel, idx);
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts);
+
+	if (!prog || !link)
+		return -1;
+
+	opts.offsets = &offset;
+	opts.cnt = 1;
+
+	/*
+	 * bit/prog: 0 uprobe entry
+	 * bit/prog: 1 uprobe return
+	 * bit/prog: 2 uprobe session without return
+	 * bit/prog: 3 uprobe session with return
+	 */
+	opts.retprobe = idx == 1;
+	opts.session  = idx == 2 || idx == 3;
+
+	*link = bpf_program__attach_uprobe_multi(prog, 0, "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(*link, "bpf_program__attach_uprobe_multi"))
+		return -1;
+	return 0;
+}
+
+static void uprobe_detach(struct uprobe_multi_consumers *skel, int idx)
+{
+	struct bpf_link **link = get_link(skel, idx);
+
+	bpf_link__destroy(*link);
+	*link = NULL;
+}
+
+static bool test_bit(int bit, unsigned long val)
+{
+	return val & (1 << bit);
+}
+
+noinline int
+uprobe_consumer_test(struct uprobe_multi_consumers *skel,
+		     unsigned long before, unsigned long after,
+		     unsigned long offset)
+{
+	int idx;
+
+	/* detach uprobe for each unset programs in 'before' state ... */
+	for (idx = 0; idx < 4; idx++) {
+		if (test_bit(idx, before) && !test_bit(idx, after))
+			uprobe_detach(skel, idx);
+	}
+
+	/* ... and attach all new programs in 'after' state */
+	for (idx = 0; idx < 4; idx++) {
+		if (!test_bit(idx, before) && test_bit(idx, after)) {
+			if (!ASSERT_OK(uprobe_attach(skel, idx, offset), "uprobe_attach_after"))
+				return -1;
+		}
+	}
+	return 0;
+}
+
+/*
+ * We generate 16 consumer_testX functions that will have uprobe installed on
+ * and will be called in separate threads. All function pointer are stored in
+ * "consumers" section and each thread will pick one function based on index.
+ */
+
+extern const void *__start_consumers;
+
+#define __CONSUMER_TEST(func) 							\
+noinline int func(struct uprobe_multi_consumers *skel, unsigned long before,	\
+		  unsigned long after, unsigned long offset)			\
+{										\
+	return uprobe_consumer_test(skel, before, after, offset);		\
+}										\
+void *__ ## func __used __attribute__((section("consumers"))) = (void *) func;
+
+#define CONSUMER_TEST(func) __CONSUMER_TEST(func)
+
+#define C1  CONSUMER_TEST(__PASTE(consumer_test, __COUNTER__))
+#define C4  C1 C1 C1 C1
+#define C16 C4 C4 C4 C4
+
+C16
+
+typedef int (*test_t)(struct uprobe_multi_consumers *, unsigned long,
+		      unsigned long, unsigned long);
+
+static int consumer_test(struct uprobe_multi_consumers *skel,
+			 unsigned long before, unsigned long after,
+			 test_t test, unsigned long offset)
+{
+	int err, idx, ret = -1;
+
+	printf("consumer_test before %lu after %lu\n", before, after);
+
+	/* 'before' is each, we attach uprobe for every set idx */
+	for (idx = 0; idx < 4; idx++) {
+		if (test_bit(idx, before)) {
+			if (!ASSERT_OK(uprobe_attach(skel, idx, offset), "uprobe_attach_before"))
+				goto cleanup;
+		}
+	}
+
+	err = test(skel, before, after, offset);
+	if (!ASSERT_EQ(err, 0, "uprobe_consumer_test"))
+		goto cleanup;
+
+	for (idx = 0; idx < 4; idx++) {
+		bool uret_stays, uret_survives;
+		const char *fmt = "BUG";
+		__u64 val = 0;
+
+		switch (idx) {
+		case 0:
+			/*
+			 * uprobe entry
+			 *   +1 if define in 'before'
+			 */
+			if (test_bit(idx, before))
+				val++;
+			fmt = "prog 0: uprobe";
+			break;
+		case 1:
+			/*
+			 * To trigger uretprobe consumer, the uretprobe under test either stayed from
+			 * before to after (uret_stays + test_bit) or uretprobe instance survived and
+			 * we have uretprobe active in after (uret_survives + test_bit)
+			 */
+			uret_stays = before & after & 0b0110;
+			uret_survives = ((before & 0b0110) && (after & 0b0110) && (before & 0b1001));
+
+			if ((uret_stays || uret_survives) && test_bit(idx, after))
+				val++;
+			fmt = "prog 1: uretprobe";
+			break;
+		case 2:
+			/*
+			 * session with return
+			 *  +1 if defined in 'before'
+			 *  +1 if defined in 'after'
+			 */
+			if (test_bit(idx, before)) {
+				val++;
+				if (test_bit(idx, after))
+					val++;
+			}
+			fmt = "prog 2: session with return";
+			break;
+		case 3:
+			/*
+			 * session without return
+			 *   +1 if defined in 'before'
+			 */
+			if (test_bit(idx, before))
+				val++;
+			fmt = "prog 3: session with NO return";
+			break;
+		}
+
+		if (!ASSERT_EQ(skel->bss->uprobe_result[idx], val, fmt))
+			goto cleanup;
+		skel->bss->uprobe_result[idx] = 0;
+	}
+
+	ret = 0;
+
+cleanup:
+	for (idx = 0; idx < 4; idx++)
+		uprobe_detach(skel, idx);
+	return ret;
+}
+
+#define CONSUMER_MAX 16
+
+/*
+ * Each thread runs 1/16 of the load by running test for single
+ * 'before' number (based on thread index) and full scale of
+ * 'after' numbers.
+ */
+static void *consumer_thread(void *arg)
+{
+	unsigned long idx = (unsigned long) arg;
+	struct uprobe_multi_consumers *skel;
+	unsigned long offset;
+	const void *func;
+	int after;
+
+	skel = uprobe_multi_consumers__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi_consumers__open_and_load"))
+		return NULL;
+
+	func = *((&__start_consumers) + idx);
+
+	offset = get_uprobe_offset(func);
+	if (!ASSERT_GE(offset, 0, "uprobe_offset"))
+		goto out;
+
+	for (after = 0; after < CONSUMER_MAX; after++)
+		if (consumer_test(skel, idx, after, func, offset))
+			goto out;
+
+out:
+	uprobe_multi_consumers__destroy(skel);
+	return NULL;
+}
+
+
+static void test_consumers(void)
+{
+	pthread_t pt[CONSUMER_MAX];
+	unsigned long idx;
+	int err;
+
+	/*
+	 * The idea of this test is to try all possible combinations of
+	 * uprobes consumers attached on single function.
+	 *
+	 *  - 1 uprobe entry consumer
+	 *  - 1 uprobe exit consumer
+	 *  - 1 uprobe session with return
+	 *  - 1 uprobe session without return
+	 *
+	 * The test uses 4 uprobes attached on single function, but that
+	 * translates into single uprobe with 4 consumers in kernel.
+	 *
+	 * The before/after values present the state of attached consumers
+	 * before and after the probed function:
+	 *
+	 *  bit/prog 0 : uprobe entry
+	 *  bit/prog 1 : uprobe return
+	 *
+	 * For example for:
+	 *
+	 *   before = 0b01
+	 *   after  = 0b10
+	 *
+	 * it means that before we call 'uprobe_consumer_test' we attach
+	 * uprobes defined in 'before' value:
+	 *
+	 *   - bit/prog 1: uprobe entry
+	 *
+	 * uprobe_consumer_test is called and inside it we attach and detach
+	 * uprobes based on 'after' value:
+	 *
+	 *   - bit/prog 0: is detached
+	 *   - bit/prog 1: is attached
+	 *
+	 * uprobe_consumer_test returns and we check counters values increased
+	 * by bpf programs on each uprobe to match the expected count based on
+	 * before/after bits.
+	 */
+
+	for (idx = 0; idx < CONSUMER_MAX; idx++) {
+		err = pthread_create(&pt[idx], NULL, consumer_thread, (void *) idx);
+		if (!ASSERT_OK(err, "pthread_create"))
+			break;
+	}
+
+	while (idx)
+		pthread_join(pt[--idx], NULL);
+}
+
+static struct bpf_program *uprobe_multi_program(struct uprobe_multi_pid_filter *skel, int idx)
+{
+	switch (idx) {
+	case 0: return skel->progs.uprobe_multi_0;
+	case 1: return skel->progs.uprobe_multi_1;
+	case 2: return skel->progs.uprobe_multi_2;
+	}
+	return NULL;
+}
+
+#define TASKS 3
+
+static void run_pid_filter(struct uprobe_multi_pid_filter *skel, bool clone_vm, bool retprobe)
+{
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts, .retprobe = retprobe);
+	struct bpf_link *link[TASKS] = {};
+	struct child child[TASKS] = {};
+	int i;
+
+	memset(skel->bss->test, 0, sizeof(skel->bss->test));
+
+	for (i = 0; i < TASKS; i++) {
+		if (!ASSERT_OK(spawn_child_flag(&child[i], clone_vm), "spawn_child"))
+			goto cleanup;
+		skel->bss->pids[i] = child[i].pid;
+	}
+
+	for (i = 0; i < TASKS; i++) {
+		link[i] = bpf_program__attach_uprobe_multi(uprobe_multi_program(skel, i),
+							   child[i].pid, "/proc/self/exe",
+							   "uprobe_multi_func_1", &opts);
+		if (!ASSERT_OK_PTR(link[i], "bpf_program__attach_uprobe_multi"))
+			goto cleanup;
+	}
+
+	for (i = 0; i < TASKS; i++)
+		kick_child(&child[i]);
+
+	for (i = 0; i < TASKS; i++) {
+		ASSERT_EQ(skel->bss->test[i][0], 1, "pid");
+		ASSERT_EQ(skel->bss->test[i][1], 0, "unknown");
+	}
+
+cleanup:
+	for (i = 0; i < TASKS; i++)
+		bpf_link__destroy(link[i]);
+	for (i = 0; i < TASKS; i++)
+		release_child(&child[i]);
+}
+
+static void test_pid_filter_process(bool clone_vm)
+{
+	struct uprobe_multi_pid_filter *skel;
+
+	skel = uprobe_multi_pid_filter__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi_pid_filter__open_and_load"))
+		return;
+
+	run_pid_filter(skel, clone_vm, false);
+	run_pid_filter(skel, clone_vm, true);
+
+	uprobe_multi_pid_filter__destroy(skel);
+}
+
+static void test_session_skel_api(void)
+{
+	struct uprobe_multi_session *skel = NULL;
+	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
+	struct bpf_link *link = NULL;
+	int err;
+
+	skel = uprobe_multi_session__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi_session__open_and_load"))
+		goto cleanup;
+
+	skel->bss->pid = getpid();
+	skel->bss->user_ptr = test_data;
+
+	err = uprobe_multi_session__attach(skel);
+	if (!ASSERT_OK(err, "uprobe_multi_session__attach"))
+		goto cleanup;
+
+	/* trigger all probes */
+	skel->bss->uprobe_multi_func_1_addr = (__u64) uprobe_multi_func_1;
+	skel->bss->uprobe_multi_func_2_addr = (__u64) uprobe_multi_func_2;
+	skel->bss->uprobe_multi_func_3_addr = (__u64) uprobe_multi_func_3;
+
+	uprobe_multi_func_1();
+	uprobe_multi_func_2();
+	uprobe_multi_func_3();
+
+	/*
+	 * We expect 2 for uprobe_multi_func_2 because it runs both entry/return probe,
+	 * uprobe_multi_func_[13] run just the entry probe. All expected numbers are
+	 * doubled, because we run extra test for sleepable session.
+	 */
+	ASSERT_EQ(skel->bss->uprobe_session_result[0], 2, "uprobe_multi_func_1_result");
+	ASSERT_EQ(skel->bss->uprobe_session_result[1], 4, "uprobe_multi_func_2_result");
+	ASSERT_EQ(skel->bss->uprobe_session_result[2], 2, "uprobe_multi_func_3_result");
+
+	/* We expect increase in 3 entry and 1 return session calls -> 4 */
+	ASSERT_EQ(skel->bss->uprobe_multi_sleep_result, 4, "uprobe_multi_sleep_result");
+
+cleanup:
+	bpf_link__destroy(link);
+	uprobe_multi_session__destroy(skel);
+}
+
+static void test_session_single_skel_api(void)
+{
+	struct uprobe_multi_session_single *skel = NULL;
+	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
+	int err;
+
+	skel = uprobe_multi_session_single__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi_session_single__open_and_load"))
+		goto cleanup;
+
+	skel->bss->pid = getpid();
+
+	err = uprobe_multi_session_single__attach(skel);
+	if (!ASSERT_OK(err, "uprobe_multi_session_single__attach"))
+		goto cleanup;
+
+	uprobe_multi_func_1();
+
+	/*
+	 * We expect consumer 0 and 2 to trigger just entry handler (value 1)
+	 * and consumer 1 to hit both (value 2).
+	 */
+	ASSERT_EQ(skel->bss->uprobe_session_result[0], 1, "uprobe_session_result_0");
+	ASSERT_EQ(skel->bss->uprobe_session_result[1], 2, "uprobe_session_result_1");
+	ASSERT_EQ(skel->bss->uprobe_session_result[2], 1, "uprobe_session_result_2");
+
+cleanup:
+	uprobe_multi_session_single__destroy(skel);
+}
+
+static void test_session_cookie_skel_api(void)
+{
+	struct uprobe_multi_session_cookie *skel = NULL;
+	int err;
+
+	skel = uprobe_multi_session_cookie__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi_session_cookie__open_and_load"))
+		goto cleanup;
+
+	skel->bss->pid = getpid();
+
+	err = uprobe_multi_session_cookie__attach(skel);
+	if (!ASSERT_OK(err, "uprobe_multi_session_cookie__attach"))
+		goto cleanup;
+
+	/* trigger all probes */
+	uprobe_multi_func_1();
+	uprobe_multi_func_2();
+	uprobe_multi_func_3();
+
+	ASSERT_EQ(skel->bss->test_uprobe_1_result, 1, "test_uprobe_1_result");
+	ASSERT_EQ(skel->bss->test_uprobe_2_result, 2, "test_uprobe_2_result");
+	ASSERT_EQ(skel->bss->test_uprobe_3_result, 3, "test_uprobe_3_result");
+
+cleanup:
+	uprobe_multi_session_cookie__destroy(skel);
+}
+
+static void test_session_recursive_skel_api(void)
+{
+	struct uprobe_multi_session_recursive *skel = NULL;
+	int i, err;
+
+	skel = uprobe_multi_session_recursive__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi_session_recursive__open_and_load"))
+		goto cleanup;
+
+	skel->bss->pid = getpid();
+
+	err = uprobe_multi_session_recursive__attach(skel);
+	if (!ASSERT_OK(err, "uprobe_multi_session_recursive__attach"))
+		goto cleanup;
+
+	for (i = 0; i < ARRAY_SIZE(skel->bss->test_uprobe_cookie_entry); i++)
+		skel->bss->test_uprobe_cookie_entry[i] = i + 1;
+
+	uprobe_session_recursive(5);
+
+	/*
+	 *                                         entry uprobe:
+	 * uprobe_session_recursive(5) {             *cookie = 1, return 0
+	 *   uprobe_session_recursive(4) {           *cookie = 2, return 1
+	 *     uprobe_session_recursive(3) {         *cookie = 3, return 0
+	 *       uprobe_session_recursive(2) {       *cookie = 4, return 1
+	 *         uprobe_session_recursive(1) {     *cookie = 5, return 0
+	 *           uprobe_session_recursive(0) {   *cookie = 6, return 1
+	 *                                          return uprobe:
+	 *           } i = 0                          not executed
+	 *         } i = 1                            test_uprobe_cookie_return[0] = 5
+	 *       } i = 2                              not executed
+	 *     } i = 3                                test_uprobe_cookie_return[1] = 3
+	 *   } i = 4                                  not executed
+	 * } i = 5                                    test_uprobe_cookie_return[2] = 1
+	 */
+
+	ASSERT_EQ(skel->bss->idx_entry, 6, "idx_entry");
+	ASSERT_EQ(skel->bss->idx_return, 3, "idx_return");
+
+	ASSERT_EQ(skel->bss->test_uprobe_cookie_return[0], 5, "test_uprobe_cookie_return[0]");
+	ASSERT_EQ(skel->bss->test_uprobe_cookie_return[1], 3, "test_uprobe_cookie_return[1]");
+	ASSERT_EQ(skel->bss->test_uprobe_cookie_return[2], 1, "test_uprobe_cookie_return[2]");
+
+cleanup:
+	uprobe_multi_session_recursive__destroy(skel);
+}
+
+static void test_bench_attach_uprobe(void)
+{
+	long attach_start_ns = 0, attach_end_ns = 0;
+	struct uprobe_multi_bench *skel = NULL;
+	long detach_start_ns, detach_end_ns;
+	double attach_delta, detach_delta;
+	int err;
+
+	skel = uprobe_multi_bench__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi_bench__open_and_load"))
+		goto cleanup;
+
+	attach_start_ns = get_time_ns();
+
+	err = uprobe_multi_bench__attach(skel);
+	if (!ASSERT_OK(err, "uprobe_multi_bench__attach"))
+		goto cleanup;
+
+	attach_end_ns = get_time_ns();
+
+	system("./uprobe_multi bench");
+
+	ASSERT_EQ(skel->bss->count, 50000, "uprobes_count");
+
+cleanup:
+	detach_start_ns = get_time_ns();
+	uprobe_multi_bench__destroy(skel);
+	detach_end_ns = get_time_ns();
+
+	attach_delta = (attach_end_ns - attach_start_ns) / 1000000000.0;
+	detach_delta = (detach_end_ns - detach_start_ns) / 1000000000.0;
+
+	printf("%s: attached in %7.3lfs\n", __func__, attach_delta);
+	printf("%s: detached in %7.3lfs\n", __func__, detach_delta);
+}
+
+static void test_bench_attach_usdt(void)
+{
+	long attach_start_ns = 0, attach_end_ns = 0;
+	struct uprobe_multi_usdt *skel = NULL;
+	long detach_start_ns, detach_end_ns;
+	double attach_delta, detach_delta;
+
+	skel = uprobe_multi_usdt__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_multi__open"))
+		goto cleanup;
+
+	attach_start_ns = get_time_ns();
+
+	skel->links.usdt0 = bpf_program__attach_usdt(skel->progs.usdt0, -1, "./uprobe_multi",
+						     "test", "usdt", NULL);
+	if (!ASSERT_OK_PTR(skel->links.usdt0, "bpf_program__attach_usdt"))
+		goto cleanup;
+
+	attach_end_ns = get_time_ns();
+
+	system("./uprobe_multi usdt");
+
+	ASSERT_EQ(skel->bss->count, 50000, "usdt_count");
+
+cleanup:
+	detach_start_ns = get_time_ns();
+	uprobe_multi_usdt__destroy(skel);
+	detach_end_ns = get_time_ns();
+
+	attach_delta = (attach_end_ns - attach_start_ns) / 1000000000.0;
+	detach_delta = (detach_end_ns - detach_start_ns) / 1000000000.0;
+
+	printf("%s: attached in %7.3lfs\n", __func__, attach_delta);
+	printf("%s: detached in %7.3lfs\n", __func__, detach_delta);
+}
+
+void test_uprobe_multi_test(void)
+{
+	if (test__start_subtest("skel_api"))
+		test_skel_api();
+	if (test__start_subtest("attach_api_pattern"))
+		test_attach_api_pattern();
+	if (test__start_subtest("attach_api_syms"))
+		test_attach_api_syms();
+	if (test__start_subtest("link_api"))
+		test_link_api();
+	if (test__start_subtest("bench_uprobe"))
+		test_bench_attach_uprobe();
+	if (test__start_subtest("bench_usdt"))
+		test_bench_attach_usdt();
+	if (test__start_subtest("attach_api_fails"))
+		test_attach_api_fails();
+	if (test__start_subtest("attach_uprobe_fails"))
+		test_attach_uprobe_fails();
+	if (test__start_subtest("consumers"))
+		test_consumers();
+	if (test__start_subtest("filter_fork"))
+		test_pid_filter_process(false);
+	if (test__start_subtest("filter_clone_vm"))
+		test_pid_filter_process(true);
+	if (test__start_subtest("session"))
+		test_session_skel_api();
+	if (test__start_subtest("session_single"))
+		test_session_single_skel_api();
+	if (test__start_subtest("session_cookie"))
+		test_session_cookie_skel_api();
+	if (test__start_subtest("session_cookie_recursive"))
+		test_session_recursive_skel_api();
+	RUN_TESTS(uprobe_multi_verifier);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
new file mode 100644
index 000000000000..955a37751b52
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
@@ -0,0 +1,803 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+
+#ifdef __x86_64__
+
+#include <unistd.h>
+#include <asm/ptrace.h>
+#include <linux/compiler.h>
+#include <linux/stringify.h>
+#include <linux/kernel.h>
+#include <sys/wait.h>
+#include <sys/syscall.h>
+#include <sys/prctl.h>
+#include <asm/prctl.h>
+#include "uprobe_syscall.skel.h"
+#include "uprobe_syscall_executed.skel.h"
+#include "bpf/libbpf_internal.h"
+
+#define USDT_NOP .byte 0x0f, 0x1f, 0x44, 0x00, 0x00
+#include "usdt.h"
+
+#pragma GCC diagnostic ignored "-Wattributes"
+
+__attribute__((aligned(16)))
+__nocf_check __weak __naked unsigned long uprobe_regs_trigger(void)
+{
+	asm volatile (
+		".byte 0x0f, 0x1f, 0x44, 0x00, 0x00\n" /* nop5 */
+		"movq $0xdeadbeef, %rax\n"
+		"ret\n"
+	);
+}
+
+__naked void uprobe_regs(struct pt_regs *before, struct pt_regs *after)
+{
+	asm volatile (
+		"movq %r15,   0(%rdi)\n"
+		"movq %r14,   8(%rdi)\n"
+		"movq %r13,  16(%rdi)\n"
+		"movq %r12,  24(%rdi)\n"
+		"movq %rbp,  32(%rdi)\n"
+		"movq %rbx,  40(%rdi)\n"
+		"movq %r11,  48(%rdi)\n"
+		"movq %r10,  56(%rdi)\n"
+		"movq  %r9,  64(%rdi)\n"
+		"movq  %r8,  72(%rdi)\n"
+		"movq %rax,  80(%rdi)\n"
+		"movq %rcx,  88(%rdi)\n"
+		"movq %rdx,  96(%rdi)\n"
+		"movq %rsi, 104(%rdi)\n"
+		"movq %rdi, 112(%rdi)\n"
+		"movq   $0, 120(%rdi)\n" /* orig_rax */
+		"movq   $0, 128(%rdi)\n" /* rip      */
+		"movq   $0, 136(%rdi)\n" /* cs       */
+		"pushq %rax\n"
+		"pushf\n"
+		"pop %rax\n"
+		"movq %rax, 144(%rdi)\n" /* eflags   */
+		"pop %rax\n"
+		"movq %rsp, 152(%rdi)\n" /* rsp      */
+		"movq   $0, 160(%rdi)\n" /* ss       */
+
+		/* save 2nd argument */
+		"pushq %rsi\n"
+		"call uprobe_regs_trigger\n"
+
+		/* save  return value and load 2nd argument pointer to rax */
+		"pushq %rax\n"
+		"movq 8(%rsp), %rax\n"
+
+		"movq %r15,   0(%rax)\n"
+		"movq %r14,   8(%rax)\n"
+		"movq %r13,  16(%rax)\n"
+		"movq %r12,  24(%rax)\n"
+		"movq %rbp,  32(%rax)\n"
+		"movq %rbx,  40(%rax)\n"
+		"movq %r11,  48(%rax)\n"
+		"movq %r10,  56(%rax)\n"
+		"movq  %r9,  64(%rax)\n"
+		"movq  %r8,  72(%rax)\n"
+		"movq %rcx,  88(%rax)\n"
+		"movq %rdx,  96(%rax)\n"
+		"movq %rsi, 104(%rax)\n"
+		"movq %rdi, 112(%rax)\n"
+		"movq   $0, 120(%rax)\n" /* orig_rax */
+		"movq   $0, 128(%rax)\n" /* rip      */
+		"movq   $0, 136(%rax)\n" /* cs       */
+
+		/* restore return value and 2nd argument */
+		"pop %rax\n"
+		"pop %rsi\n"
+
+		"movq %rax,  80(%rsi)\n"
+
+		"pushf\n"
+		"pop %rax\n"
+
+		"movq %rax, 144(%rsi)\n" /* eflags   */
+		"movq %rsp, 152(%rsi)\n" /* rsp      */
+		"movq   $0, 160(%rsi)\n" /* ss       */
+		"ret\n"
+);
+}
+
+static void test_uprobe_regs_equal(bool retprobe)
+{
+	LIBBPF_OPTS(bpf_uprobe_opts, opts,
+		.retprobe = retprobe,
+	);
+	struct uprobe_syscall *skel = NULL;
+	struct pt_regs before = {}, after = {};
+	unsigned long *pb = (unsigned long *) &before;
+	unsigned long *pa = (unsigned long *) &after;
+	unsigned long *pp;
+	unsigned long offset;
+	unsigned int i, cnt;
+
+	offset = get_uprobe_offset(&uprobe_regs_trigger);
+	if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
+		return;
+
+	skel = uprobe_syscall__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_syscall__open_and_load"))
+		goto cleanup;
+
+	skel->links.probe = bpf_program__attach_uprobe_opts(skel->progs.probe,
+				0, "/proc/self/exe", offset, &opts);
+	if (!ASSERT_OK_PTR(skel->links.probe, "bpf_program__attach_uprobe_opts"))
+		goto cleanup;
+
+	/* make sure uprobe gets optimized */
+	if (!retprobe)
+		uprobe_regs_trigger();
+
+	uprobe_regs(&before, &after);
+
+	pp = (unsigned long *) &skel->bss->regs;
+	cnt = sizeof(before)/sizeof(*pb);
+
+	for (i = 0; i < cnt; i++) {
+		unsigned int offset = i * sizeof(unsigned long);
+
+		/*
+		 * Check register before and after uprobe_regs_trigger call
+		 * that triggers the uretprobe.
+		 */
+		switch (offset) {
+		case offsetof(struct pt_regs, rax):
+			ASSERT_EQ(pa[i], 0xdeadbeef, "return value");
+			break;
+		default:
+			if (!ASSERT_EQ(pb[i], pa[i], "register before-after value check"))
+				fprintf(stdout, "failed register offset %u\n", offset);
+		}
+
+		/*
+		 * Check register seen from bpf program and register after
+		 * uprobe_regs_trigger call (with rax exception, check below).
+		 */
+		switch (offset) {
+		/*
+		 * These values will be different (not set in uretprobe_regs),
+		 * we don't care.
+		 */
+		case offsetof(struct pt_regs, orig_rax):
+		case offsetof(struct pt_regs, rip):
+		case offsetof(struct pt_regs, cs):
+		case offsetof(struct pt_regs, rsp):
+		case offsetof(struct pt_regs, ss):
+			break;
+		/*
+		 * uprobe does not see return value in rax, it needs to see the
+		 * original (before) rax value
+		 */
+		case offsetof(struct pt_regs, rax):
+			if (!retprobe) {
+				ASSERT_EQ(pp[i], pb[i], "uprobe rax prog-before value check");
+				break;
+			}
+		default:
+			if (!ASSERT_EQ(pp[i], pa[i], "register prog-after value check"))
+				fprintf(stdout, "failed register offset %u\n", offset);
+		}
+	}
+
+cleanup:
+	uprobe_syscall__destroy(skel);
+}
+
+#define BPF_TESTMOD_UPROBE_TEST_FILE "/sys/kernel/bpf_testmod_uprobe"
+
+static int write_bpf_testmod_uprobe(unsigned long offset)
+{
+	size_t n, ret;
+	char buf[30];
+	int fd;
+
+	n = sprintf(buf, "%lu", offset);
+
+	fd = open(BPF_TESTMOD_UPROBE_TEST_FILE, O_WRONLY);
+	if (fd < 0)
+		return -errno;
+
+	ret = write(fd, buf, n);
+	close(fd);
+	return ret != n ? (int) ret : 0;
+}
+
+static void test_regs_change(void)
+{
+	struct pt_regs before = {}, after = {};
+	unsigned long *pb = (unsigned long *) &before;
+	unsigned long *pa = (unsigned long *) &after;
+	unsigned long cnt = sizeof(before)/sizeof(*pb);
+	unsigned int i, err, offset;
+
+	offset = get_uprobe_offset(uprobe_regs_trigger);
+
+	err = write_bpf_testmod_uprobe(offset);
+	if (!ASSERT_OK(err, "register_uprobe"))
+		return;
+
+	/* make sure uprobe gets optimized */
+	uprobe_regs_trigger();
+
+	uprobe_regs(&before, &after);
+
+	err = write_bpf_testmod_uprobe(0);
+	if (!ASSERT_OK(err, "unregister_uprobe"))
+		return;
+
+	for (i = 0; i < cnt; i++) {
+		unsigned int offset = i * sizeof(unsigned long);
+
+		switch (offset) {
+		case offsetof(struct pt_regs, rax):
+			ASSERT_EQ(pa[i], 0x12345678deadbeef, "rax");
+			break;
+		case offsetof(struct pt_regs, rcx):
+			ASSERT_EQ(pa[i], 0x87654321feebdaed, "rcx");
+			break;
+		case offsetof(struct pt_regs, r11):
+			ASSERT_EQ(pa[i], (__u64) -1, "r11");
+			break;
+		default:
+			if (!ASSERT_EQ(pa[i], pb[i], "register before-after value check"))
+				fprintf(stdout, "failed register offset %u\n", offset);
+		}
+	}
+}
+
+#ifndef __NR_uretprobe
+#define __NR_uretprobe 335
+#endif
+
+__naked unsigned long uretprobe_syscall_call_1(void)
+{
+	/*
+	 * Pretend we are uretprobe trampoline to trigger the return
+	 * probe invocation in order to verify we get SIGILL.
+	 */
+	asm volatile (
+		"pushq %rax\n"
+		"pushq %rcx\n"
+		"pushq %r11\n"
+		"movq $" __stringify(__NR_uretprobe) ", %rax\n"
+		"syscall\n"
+		"popq %r11\n"
+		"popq %rcx\n"
+		"retq\n"
+	);
+}
+
+__naked unsigned long uretprobe_syscall_call(void)
+{
+	asm volatile (
+		"call uretprobe_syscall_call_1\n"
+		"retq\n"
+	);
+}
+
+static void test_uretprobe_syscall_call(void)
+{
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts,
+		.retprobe = true,
+	);
+	struct uprobe_syscall_executed *skel;
+	int pid, status, err, go[2], c = 0;
+	struct bpf_link *link;
+
+	if (!ASSERT_OK(pipe(go), "pipe"))
+		return;
+
+	skel = uprobe_syscall_executed__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load"))
+		goto cleanup;
+
+	pid = fork();
+	if (!ASSERT_GE(pid, 0, "fork"))
+		goto cleanup;
+
+	/* child */
+	if (pid == 0) {
+		close(go[1]);
+
+		/* wait for parent's kick */
+		err = read(go[0], &c, 1);
+		if (err != 1)
+			exit(-1);
+
+		uretprobe_syscall_call();
+		_exit(0);
+	}
+
+	skel->bss->pid = pid;
+
+	link = bpf_program__attach_uprobe_multi(skel->progs.test_uretprobe_multi,
+						pid, "/proc/self/exe",
+						"uretprobe_syscall_call", &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+	skel->links.test_uretprobe_multi = link;
+
+	/* kick the child */
+	write(go[1], &c, 1);
+	err = waitpid(pid, &status, 0);
+	ASSERT_EQ(err, pid, "waitpid");
+
+	/* verify the child got killed with SIGILL */
+	ASSERT_EQ(WIFSIGNALED(status), 1, "WIFSIGNALED");
+	ASSERT_EQ(WTERMSIG(status), SIGILL, "WTERMSIG");
+
+	/* verify the uretprobe program wasn't called */
+	ASSERT_EQ(skel->bss->executed, 0, "executed");
+
+cleanup:
+	uprobe_syscall_executed__destroy(skel);
+	close(go[1]);
+	close(go[0]);
+}
+
+#define TRAMP "[uprobes-trampoline]"
+
+__attribute__((aligned(16)))
+__nocf_check __weak __naked void uprobe_test(void)
+{
+	asm volatile ("					\n"
+		".byte 0x0f, 0x1f, 0x44, 0x00, 0x00	\n"
+		"ret					\n"
+	);
+}
+
+__attribute__((aligned(16)))
+__nocf_check __weak void usdt_test(void)
+{
+	USDT(optimized_uprobe, usdt);
+}
+
+static int find_uprobes_trampoline(void *tramp_addr)
+{
+	void *start, *end;
+	char line[128];
+	int ret = -1;
+	FILE *maps;
+
+	maps = fopen("/proc/self/maps", "r");
+	if (!maps) {
+		fprintf(stderr, "cannot open maps\n");
+		return -1;
+	}
+
+	while (fgets(line, sizeof(line), maps)) {
+		int m = -1;
+
+		/* We care only about private r-x mappings. */
+		if (sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n", &start, &end, &m) != 2)
+			continue;
+		if (m < 0)
+			continue;
+		if (!strncmp(&line[m], TRAMP, sizeof(TRAMP)-1) && (start == tramp_addr)) {
+			ret = 0;
+			break;
+		}
+	}
+
+	fclose(maps);
+	return ret;
+}
+
+static unsigned char nop5[5] = { 0x0f, 0x1f, 0x44, 0x00, 0x00 };
+
+static void *find_nop5(void *fn)
+{
+	int i;
+
+	for (i = 0; i < 10; i++) {
+		if (!memcmp(nop5, fn + i, 5))
+			return fn + i;
+	}
+	return NULL;
+}
+
+typedef void (__attribute__((nocf_check)) *trigger_t)(void);
+
+static void *check_attach(struct uprobe_syscall_executed *skel, trigger_t trigger,
+			  void *addr, int executed)
+{
+	struct __arch_relative_insn {
+		__u8 op;
+		__s32 raddr;
+	} __packed *call;
+	void *tramp = NULL;
+
+	/* Uprobe gets optimized after first trigger, so let's press twice. */
+	trigger();
+	trigger();
+
+	/* Make sure bpf program got executed.. */
+	ASSERT_EQ(skel->bss->executed, executed, "executed");
+
+	/* .. and check the trampoline is as expected. */
+	call = (struct __arch_relative_insn *) addr;
+	tramp = (void *) (call + 1) + call->raddr;
+	ASSERT_EQ(call->op, 0xe8, "call");
+	ASSERT_OK(find_uprobes_trampoline(tramp), "uprobes_trampoline");
+
+	return tramp;
+}
+
+static void check_detach(void *addr, void *tramp)
+{
+	/* [uprobes_trampoline] stays after detach */
+	ASSERT_OK(find_uprobes_trampoline(tramp), "uprobes_trampoline");
+	ASSERT_OK(memcmp(addr, nop5, 5), "nop5");
+}
+
+static void check(struct uprobe_syscall_executed *skel, struct bpf_link *link,
+		  trigger_t trigger, void *addr, int executed)
+{
+	void *tramp;
+
+	tramp = check_attach(skel, trigger, addr, executed);
+	bpf_link__destroy(link);
+	check_detach(addr, tramp);
+}
+
+static void test_uprobe_legacy(void)
+{
+	struct uprobe_syscall_executed *skel = NULL;
+	LIBBPF_OPTS(bpf_uprobe_opts, opts,
+		.retprobe = true,
+	);
+	struct bpf_link *link;
+	unsigned long offset;
+
+	offset = get_uprobe_offset(&uprobe_test);
+	if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
+		goto cleanup;
+
+	/* uprobe */
+	skel = uprobe_syscall_executed__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load"))
+		return;
+
+	skel->bss->pid = getpid();
+
+	link = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe,
+				0, "/proc/self/exe", offset, NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_opts"))
+		goto cleanup;
+
+	check(skel, link, uprobe_test, uprobe_test, 2);
+
+	/* uretprobe */
+	skel->bss->executed = 0;
+
+	link = bpf_program__attach_uprobe_opts(skel->progs.test_uretprobe,
+				0, "/proc/self/exe", offset, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_opts"))
+		goto cleanup;
+
+	check(skel, link, uprobe_test, uprobe_test, 2);
+
+cleanup:
+	uprobe_syscall_executed__destroy(skel);
+}
+
+static void test_uprobe_multi(void)
+{
+	struct uprobe_syscall_executed *skel = NULL;
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts);
+	struct bpf_link *link;
+	unsigned long offset;
+
+	offset = get_uprobe_offset(&uprobe_test);
+	if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
+		goto cleanup;
+
+	opts.offsets = &offset;
+	opts.cnt = 1;
+
+	skel = uprobe_syscall_executed__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load"))
+		return;
+
+	skel->bss->pid = getpid();
+
+	/* uprobe.multi */
+	link = bpf_program__attach_uprobe_multi(skel->progs.test_uprobe_multi,
+				0, "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	check(skel, link, uprobe_test, uprobe_test, 2);
+
+	/* uretprobe.multi */
+	skel->bss->executed = 0;
+	opts.retprobe = true;
+	link = bpf_program__attach_uprobe_multi(skel->progs.test_uretprobe_multi,
+				0, "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	check(skel, link, uprobe_test, uprobe_test, 2);
+
+cleanup:
+	uprobe_syscall_executed__destroy(skel);
+}
+
+static void test_uprobe_session(void)
+{
+	struct uprobe_syscall_executed *skel = NULL;
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts,
+		.session = true,
+	);
+	struct bpf_link *link;
+	unsigned long offset;
+
+	offset = get_uprobe_offset(&uprobe_test);
+	if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
+		goto cleanup;
+
+	opts.offsets = &offset;
+	opts.cnt = 1;
+
+	skel = uprobe_syscall_executed__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load"))
+		return;
+
+	skel->bss->pid = getpid();
+
+	link = bpf_program__attach_uprobe_multi(skel->progs.test_uprobe_session,
+				0, "/proc/self/exe", NULL, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	check(skel, link, uprobe_test, uprobe_test, 4);
+
+cleanup:
+	uprobe_syscall_executed__destroy(skel);
+}
+
+static void test_uprobe_usdt(void)
+{
+	struct uprobe_syscall_executed *skel;
+	struct bpf_link *link;
+	void *addr;
+
+	errno = 0;
+	addr = find_nop5(usdt_test);
+	if (!ASSERT_OK_PTR(addr, "find_nop5"))
+		return;
+
+	skel = uprobe_syscall_executed__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load"))
+		return;
+
+	skel->bss->pid = getpid();
+
+	link = bpf_program__attach_usdt(skel->progs.test_usdt,
+				-1 /* all PIDs */, "/proc/self/exe",
+				"optimized_uprobe", "usdt", NULL);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_usdt"))
+		goto cleanup;
+
+	check(skel, link, usdt_test, addr, 2);
+
+cleanup:
+	uprobe_syscall_executed__destroy(skel);
+}
+
+/*
+ * Borrowed from tools/testing/selftests/x86/test_shadow_stack.c.
+ *
+ * For use in inline enablement of shadow stack.
+ *
+ * The program can't return from the point where shadow stack gets enabled
+ * because there will be no address on the shadow stack. So it can't use
+ * syscall() for enablement, since it is a function.
+ *
+ * Based on code from nolibc.h. Keep a copy here because this can't pull
+ * in all of nolibc.h.
+ */
+#define ARCH_PRCTL(arg1, arg2)					\
+({								\
+	long _ret;						\
+	register long _num  asm("eax") = __NR_arch_prctl;	\
+	register long _arg1 asm("rdi") = (long)(arg1);		\
+	register long _arg2 asm("rsi") = (long)(arg2);		\
+								\
+	asm volatile (						\
+		"syscall\n"					\
+		: "=a"(_ret)					\
+		: "r"(_arg1), "r"(_arg2),			\
+		  "0"(_num)					\
+		: "rcx", "r11", "memory", "cc"			\
+	);							\
+	_ret;							\
+})
+
+#ifndef ARCH_SHSTK_ENABLE
+#define ARCH_SHSTK_ENABLE	0x5001
+#define ARCH_SHSTK_DISABLE	0x5002
+#define ARCH_SHSTK_SHSTK	(1ULL <<  0)
+#endif
+
+static void test_uretprobe_shadow_stack(void)
+{
+	if (ARCH_PRCTL(ARCH_SHSTK_ENABLE, ARCH_SHSTK_SHSTK)) {
+		test__skip();
+		return;
+	}
+
+	/* Run all the tests with shadow stack in place. */
+
+	test_uprobe_regs_equal(false);
+	test_uprobe_regs_equal(true);
+	test_uretprobe_syscall_call();
+
+	test_uprobe_legacy();
+	test_uprobe_multi();
+	test_uprobe_session();
+	test_uprobe_usdt();
+
+	test_regs_change();
+
+	ARCH_PRCTL(ARCH_SHSTK_DISABLE, ARCH_SHSTK_SHSTK);
+}
+
+static volatile bool race_stop;
+
+static USDT_DEFINE_SEMA(race);
+
+static void *worker_trigger(void *arg)
+{
+	unsigned long rounds = 0;
+
+	while (!race_stop) {
+		uprobe_test();
+		rounds++;
+	}
+
+	printf("tid %ld trigger rounds: %lu\n", sys_gettid(), rounds);
+	return NULL;
+}
+
+static void *worker_attach(void *arg)
+{
+	LIBBPF_OPTS(bpf_uprobe_opts, opts);
+	struct uprobe_syscall_executed *skel;
+	unsigned long rounds = 0, offset;
+	const char *sema[2] = {
+		__stringify(USDT_SEMA(race)),
+		NULL,
+	};
+	unsigned long *ref;
+	int err;
+
+	offset = get_uprobe_offset(&uprobe_test);
+	if (!ASSERT_GE(offset, 0, "get_uprobe_offset"))
+		return NULL;
+
+	err = elf_resolve_syms_offsets("/proc/self/exe", 1, (const char **) &sema, &ref, STT_OBJECT);
+	if (!ASSERT_OK(err, "elf_resolve_syms_offsets_sema"))
+		return NULL;
+
+	opts.ref_ctr_offset = *ref;
+
+	skel = uprobe_syscall_executed__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load"))
+		return NULL;
+
+	skel->bss->pid = getpid();
+
+	while (!race_stop) {
+		skel->links.test_uprobe = bpf_program__attach_uprobe_opts(skel->progs.test_uprobe,
+					0, "/proc/self/exe", offset, &opts);
+		if (!ASSERT_OK_PTR(skel->links.test_uprobe, "bpf_program__attach_uprobe_opts"))
+			break;
+
+		bpf_link__destroy(skel->links.test_uprobe);
+		skel->links.test_uprobe = NULL;
+		rounds++;
+	}
+
+	printf("tid %ld attach rounds: %lu hits: %d\n", sys_gettid(), rounds, skel->bss->executed);
+	uprobe_syscall_executed__destroy(skel);
+	free(ref);
+	return NULL;
+}
+
+static useconds_t race_msec(void)
+{
+	char *env;
+
+	env = getenv("BPF_SELFTESTS_UPROBE_SYSCALL_RACE_MSEC");
+	if (env)
+		return atoi(env);
+
+	/* default duration is 500ms */
+	return 500;
+}
+
+static void test_uprobe_race(void)
+{
+	int err, i, nr_threads;
+	pthread_t *threads;
+
+	nr_threads = libbpf_num_possible_cpus();
+	if (!ASSERT_GT(nr_threads, 0, "libbpf_num_possible_cpus"))
+		return;
+	nr_threads = max(2, nr_threads);
+
+	threads = alloca(sizeof(*threads) * nr_threads);
+	if (!ASSERT_OK_PTR(threads, "malloc"))
+		return;
+
+	for (i = 0; i < nr_threads; i++) {
+		err = pthread_create(&threads[i], NULL, i % 2 ? worker_trigger : worker_attach,
+				     NULL);
+		if (!ASSERT_OK(err, "pthread_create"))
+			goto cleanup;
+	}
+
+	usleep(race_msec() * 1000);
+
+cleanup:
+	race_stop = true;
+	for (nr_threads = i, i = 0; i < nr_threads; i++)
+		pthread_join(threads[i], NULL);
+
+	ASSERT_FALSE(USDT_SEMA_IS_ACTIVE(race), "race_semaphore");
+}
+
+#ifndef __NR_uprobe
+#define __NR_uprobe 336
+#endif
+
+static void test_uprobe_error(void)
+{
+	long err = syscall(__NR_uprobe);
+
+	ASSERT_EQ(err, -1, "error");
+	ASSERT_EQ(errno, ENXIO, "errno");
+}
+
+static void __test_uprobe_syscall(void)
+{
+	if (test__start_subtest("uretprobe_regs_equal"))
+		test_uprobe_regs_equal(true);
+	if (test__start_subtest("uretprobe_syscall_call"))
+		test_uretprobe_syscall_call();
+	if (test__start_subtest("uretprobe_shadow_stack"))
+		test_uretprobe_shadow_stack();
+	if (test__start_subtest("uprobe_legacy"))
+		test_uprobe_legacy();
+	if (test__start_subtest("uprobe_multi"))
+		test_uprobe_multi();
+	if (test__start_subtest("uprobe_session"))
+		test_uprobe_session();
+	if (test__start_subtest("uprobe_usdt"))
+		test_uprobe_usdt();
+	if (test__start_subtest("uprobe_race"))
+		test_uprobe_race();
+	if (test__start_subtest("uprobe_error"))
+		test_uprobe_error();
+	if (test__start_subtest("uprobe_regs_equal"))
+		test_uprobe_regs_equal(false);
+	if (test__start_subtest("regs_change"))
+		test_regs_change();
+}
+#else
+static void __test_uprobe_syscall(void)
+{
+	test__skip();
+}
+#endif
+
+void test_uprobe_syscall(void)
+{
+	__test_uprobe_syscall();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/uretprobe_stack.c b/tools/testing/selftests/bpf/prog_tests/uretprobe_stack.c
new file mode 100644
index 000000000000..6deb8d560ddd
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/uretprobe_stack.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <test_progs.h>
+#include "uretprobe_stack.skel.h"
+#include "../sdt.h"
+
+/* We set up target_1() -> target_2() -> target_3() -> target_4() -> USDT()
+ * call chain, each being traced by our BPF program. On entry or return from
+ * each target_*() we are capturing user stack trace and recording it in
+ * global variable, so that user space part of the test can validate it.
+ *
+ * Note, we put each target function into a custom section to get those
+ * __start_XXX/__stop_XXX symbols, generated by linker for us, which allow us
+ * to know address range of those functions
+ */
+__attribute__((section("uprobe__target_4")))
+__weak int target_4(void)
+{
+	STAP_PROBE1(uretprobe_stack, target, 42);
+	return 42;
+}
+
+extern const void *__start_uprobe__target_4;
+extern const void *__stop_uprobe__target_4;
+
+__attribute__((section("uprobe__target_3")))
+__weak int target_3(void)
+{
+	return target_4();
+}
+
+extern const void *__start_uprobe__target_3;
+extern const void *__stop_uprobe__target_3;
+
+__attribute__((section("uprobe__target_2")))
+__weak int target_2(void)
+{
+	return target_3();
+}
+
+extern const void *__start_uprobe__target_2;
+extern const void *__stop_uprobe__target_2;
+
+__attribute__((section("uprobe__target_1")))
+__weak int target_1(int depth)
+{
+	if (depth < 1)
+		return 1 + target_1(depth + 1);
+	else
+		return target_2();
+}
+
+extern const void *__start_uprobe__target_1;
+extern const void *__stop_uprobe__target_1;
+
+extern const void *__start_uretprobe_stack_sec;
+extern const void *__stop_uretprobe_stack_sec;
+
+struct range {
+	long start;
+	long stop;
+};
+
+static struct range targets[] = {
+	{}, /* we want target_1 to map to target[1], so need 1-based indexing */
+	{ (long)&__start_uprobe__target_1, (long)&__stop_uprobe__target_1 },
+	{ (long)&__start_uprobe__target_2, (long)&__stop_uprobe__target_2 },
+	{ (long)&__start_uprobe__target_3, (long)&__stop_uprobe__target_3 },
+	{ (long)&__start_uprobe__target_4, (long)&__stop_uprobe__target_4 },
+};
+
+static struct range caller = {
+	(long)&__start_uretprobe_stack_sec,
+	(long)&__stop_uretprobe_stack_sec,
+};
+
+static void validate_stack(__u64 *ips, int stack_len, int cnt, ...)
+{
+	int i, j;
+	va_list args;
+
+	if (!ASSERT_GT(stack_len, 0, "stack_len"))
+		return;
+
+	stack_len /= 8;
+
+	/* check if we have enough entries to satisfy test expectations */
+	if (!ASSERT_GE(stack_len, cnt, "stack_len2"))
+		return;
+
+	if (env.verbosity >= VERBOSE_NORMAL) {
+		printf("caller: %#lx - %#lx\n", caller.start, caller.stop);
+		for (i = 1; i < ARRAY_SIZE(targets); i++)
+			printf("target_%d: %#lx - %#lx\n", i, targets[i].start, targets[i].stop);
+		for (i = 0; i < stack_len; i++) {
+			for (j = 1; j < ARRAY_SIZE(targets); j++) {
+				if (ips[i] >= targets[j].start && ips[i] < targets[j].stop)
+					break;
+			}
+			if (j < ARRAY_SIZE(targets)) { /* found target match */
+				printf("ENTRY #%d: %#lx (in target_%d)\n", i, (long)ips[i], j);
+			} else if (ips[i] >= caller.start && ips[i] < caller.stop) {
+				printf("ENTRY #%d: %#lx (in caller)\n", i, (long)ips[i]);
+			} else {
+				printf("ENTRY #%d: %#lx\n", i, (long)ips[i]);
+			}
+		}
+	}
+
+	va_start(args, cnt);
+
+	for (i = cnt - 1; i >= 0; i--) {
+		/* most recent entry is the deepest target function */
+		const struct range *t = va_arg(args, const struct range *);
+
+		ASSERT_GE(ips[i], t->start, "addr_start");
+		ASSERT_LT(ips[i], t->stop, "addr_stop");
+	}
+
+	va_end(args);
+}
+
+/* __weak prevents inlining */
+__attribute__((section("uretprobe_stack_sec")))
+__weak void test_uretprobe_stack(void)
+{
+	LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
+	struct uretprobe_stack *skel;
+	int err;
+
+	skel = uretprobe_stack__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	err = uretprobe_stack__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	/* trigger */
+	ASSERT_EQ(target_1(0), 42 + 1, "trigger_return");
+
+	/*
+	 * Stacks captured on ENTRY uprobes
+	 */
+
+	/* (uprobe 1) target_1 in stack trace*/
+	validate_stack(skel->bss->entry_stack1, skel->bss->entry1_len,
+		       2, &caller, &targets[1]);
+	/* (uprobe 1, recursed) */
+	validate_stack(skel->bss->entry_stack1_recur, skel->bss->entry1_recur_len,
+		       3, &caller, &targets[1], &targets[1]);
+	/* (uprobe 2) caller -> target_1 -> target_1 -> target_2 */
+	validate_stack(skel->bss->entry_stack2, skel->bss->entry2_len,
+		       4, &caller, &targets[1], &targets[1], &targets[2]);
+	/* (uprobe 3) */
+	validate_stack(skel->bss->entry_stack3, skel->bss->entry3_len,
+		       5, &caller, &targets[1], &targets[1], &targets[2], &targets[3]);
+	/* (uprobe 4) caller -> target_1 -> target_1 -> target_2 -> target_3 -> target_4 */
+	validate_stack(skel->bss->entry_stack4, skel->bss->entry4_len,
+		       6, &caller, &targets[1], &targets[1], &targets[2], &targets[3], &targets[4]);
+
+	/* (USDT): full caller -> target_1 -> target_1 -> target_2 (uretprobed)
+	 *              -> target_3 -> target_4 (uretprobes) chain
+	 */
+	validate_stack(skel->bss->usdt_stack, skel->bss->usdt_len,
+		       6, &caller, &targets[1], &targets[1], &targets[2], &targets[3], &targets[4]);
+
+	/*
+	 * Now stacks captured on the way out in EXIT uprobes
+	 */
+
+	/* (uretprobe 4) everything up to target_4, but excluding it */
+	validate_stack(skel->bss->exit_stack4, skel->bss->exit4_len,
+		       5, &caller, &targets[1], &targets[1], &targets[2], &targets[3]);
+	/* we didn't install uretprobes on target_2 and target_3 */
+	/* (uretprobe 1, recur) first target_1 call only */
+	validate_stack(skel->bss->exit_stack1_recur, skel->bss->exit1_recur_len,
+		       2, &caller, &targets[1]);
+	/* (uretprobe 1) just a caller in the stack trace */
+	validate_stack(skel->bss->exit_stack1, skel->bss->exit1_len,
+		       1, &caller);
+
+cleanup:
+	uretprobe_stack__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/usdt.c b/tools/testing/selftests/bpf/prog_tests/usdt.c
index 9ad9da0f215e..f4be5269fa90 100644
--- a/tools/testing/selftests/bpf/prog_tests/usdt.c
+++ b/tools/testing/selftests/bpf/prog_tests/usdt.c
@@ -40,12 +40,79 @@ static void __always_inline trigger_func(int x) {
 	}
 }
 
-static void subtest_basic_usdt(void)
+#if defined(__x86_64__) || defined(__i386__)
+/*
+ * SIB (Scale-Index-Base) addressing format: "size@(base_reg, index_reg, scale)"
+ * - 'size' is the size in bytes of the array element, and its sign indicates
+ *   whether the type is signed (negative) or unsigned (positive).
+ * - 'base_reg' is the register holding the base address, normally rdx or edx
+ * - 'index_reg' is the register holding the index, normally rax or eax
+ * - 'scale' is the scaling factor (typically 1, 2, 4, or 8), which matches the
+ *    size of the element type.
+ *
+ * For example, for an array of 'short' (signed 2-byte elements), the SIB spec would be:
+ * - size: -2 (negative because 'short' is signed)
+ * - scale: 2 (since sizeof(short) == 2)
+ *
+ * The resulting SIB format: "-2@(%%rdx,%%rax,2)" for x86_64, "-2@(%%edx,%%eax,2)" for i386
+ */
+static volatile short array[] = {-1, -2, -3, -4};
+
+#if defined(__x86_64__)
+#define USDT_SIB_ARG_SPEC -2@(%%rdx,%%rax,2)
+#else
+#define USDT_SIB_ARG_SPEC -2@(%%edx,%%eax,2)
+#endif
+
+unsigned short test_usdt_sib_semaphore SEC(".probes");
+
+static void trigger_sib_spec(void)
+{
+	/*
+	 * Force SIB addressing with inline assembly.
+	 *
+	 * You must compile with -std=gnu99 or -std=c99 to use the
+	 * STAP_PROBE_ASM macro.
+	 *
+	 * The STAP_PROBE_ASM macro generates a quoted string that gets
+	 * inserted between the surrounding assembly instructions. In this
+	 * case, USDT_SIB_ARG_SPEC is embedded directly into the instruction
+	 * stream, creating a probe point between the asm statement boundaries.
+	 * It works fine with gcc/clang.
+	 *
+	 * Register constraints:
+	 * - "d"(array): Binds the 'array' variable to %rdx or %edx register
+	 * - "a"(0): Binds the constant 0 to %rax or %eax register
+	 * These ensure that when USDT_SIB_ARG_SPEC references %%rdx(%edx) and
+	 * %%rax(%eax), they contain the expected values for SIB addressing.
+	 *
+	 * The "memory" clobber prevents the compiler from reordering memory
+	 * accesses around the probe point, ensuring that the probe behavior
+	 * is predictable and consistent.
+	 */
+	asm volatile(
+		STAP_PROBE_ASM(test, usdt_sib, USDT_SIB_ARG_SPEC)
+		:
+		: "d"(array), "a"(0)
+		: "memory"
+	);
+}
+#endif
+
+static void subtest_basic_usdt(bool optimized)
 {
 	LIBBPF_OPTS(bpf_usdt_opts, opts);
 	struct test_usdt *skel;
 	struct test_usdt__bss *bss;
-	int err;
+	int err, i, called;
+	const __u64 expected_cookie = 0xcafedeadbeeffeed;
+
+#define TRIGGER(x) ({			\
+	trigger_func(x);		\
+	if (optimized)			\
+		trigger_func(x);	\
+	optimized ? 2 : 1;		\
+	})
 
 	skel = test_usdt__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "skel_open"))
@@ -59,22 +126,32 @@ static void subtest_basic_usdt(void)
 		goto cleanup;
 
 	/* usdt0 won't be auto-attached */
-	opts.usdt_cookie = 0xcafedeadbeeffeed;
+	opts.usdt_cookie = expected_cookie;
 	skel->links.usdt0 = bpf_program__attach_usdt(skel->progs.usdt0,
 						     0 /*self*/, "/proc/self/exe",
 						     "test", "usdt0", &opts);
 	if (!ASSERT_OK_PTR(skel->links.usdt0, "usdt0_link"))
 		goto cleanup;
 
-	trigger_func(1);
+#if defined(__x86_64__) || defined(__i386__)
+	opts.usdt_cookie = expected_cookie;
+	skel->links.usdt_sib = bpf_program__attach_usdt(skel->progs.usdt_sib,
+							 0 /*self*/, "/proc/self/exe",
+							 "test", "usdt_sib", &opts);
+	if (!ASSERT_OK_PTR(skel->links.usdt_sib, "usdt_sib_link"))
+		goto cleanup;
+#endif
+
+	called = TRIGGER(1);
 
-	ASSERT_EQ(bss->usdt0_called, 1, "usdt0_called");
-	ASSERT_EQ(bss->usdt3_called, 1, "usdt3_called");
-	ASSERT_EQ(bss->usdt12_called, 1, "usdt12_called");
+	ASSERT_EQ(bss->usdt0_called, called, "usdt0_called");
+	ASSERT_EQ(bss->usdt3_called, called, "usdt3_called");
+	ASSERT_EQ(bss->usdt12_called, called, "usdt12_called");
 
-	ASSERT_EQ(bss->usdt0_cookie, 0xcafedeadbeeffeed, "usdt0_cookie");
+	ASSERT_EQ(bss->usdt0_cookie, expected_cookie, "usdt0_cookie");
 	ASSERT_EQ(bss->usdt0_arg_cnt, 0, "usdt0_arg_cnt");
 	ASSERT_EQ(bss->usdt0_arg_ret, -ENOENT, "usdt0_arg_ret");
+	ASSERT_EQ(bss->usdt0_arg_size, -ENOENT, "usdt0_arg_size");
 
 	/* auto-attached usdt3 gets default zero cookie value */
 	ASSERT_EQ(bss->usdt3_cookie, 0, "usdt3_cookie");
@@ -86,6 +163,9 @@ static void subtest_basic_usdt(void)
 	ASSERT_EQ(bss->usdt3_args[0], 1, "usdt3_arg1");
 	ASSERT_EQ(bss->usdt3_args[1], 42, "usdt3_arg2");
 	ASSERT_EQ(bss->usdt3_args[2], (uintptr_t)&bla, "usdt3_arg3");
+	ASSERT_EQ(bss->usdt3_arg_sizes[0], 4, "usdt3_arg1_size");
+	ASSERT_EQ(bss->usdt3_arg_sizes[1], 8, "usdt3_arg2_size");
+	ASSERT_EQ(bss->usdt3_arg_sizes[2], 8, "usdt3_arg3_size");
 
 	/* auto-attached usdt12 gets default zero cookie value */
 	ASSERT_EQ(bss->usdt12_cookie, 0, "usdt12_cookie");
@@ -104,17 +184,22 @@ static void subtest_basic_usdt(void)
 	ASSERT_EQ(bss->usdt12_args[10], nums[idx], "usdt12_arg11");
 	ASSERT_EQ(bss->usdt12_args[11], t1.y, "usdt12_arg12");
 
+	int usdt12_expected_arg_sizes[12] = { 4, 4, 8, 8, 4, 8, 8, 8, 4, 2, 2, 1 };
+
+	for (i = 0; i < 12; i++)
+		ASSERT_EQ(bss->usdt12_arg_sizes[i], usdt12_expected_arg_sizes[i], "usdt12_arg_size");
+
 	/* trigger_func() is marked __always_inline, so USDT invocations will be
 	 * inlined in two different places, meaning that each USDT will have
 	 * at least 2 different places to be attached to. This verifies that
 	 * bpf_program__attach_usdt() handles this properly and attaches to
 	 * all possible places of USDT invocation.
 	 */
-	trigger_func(2);
+	called += TRIGGER(2);
 
-	ASSERT_EQ(bss->usdt0_called, 2, "usdt0_called");
-	ASSERT_EQ(bss->usdt3_called, 2, "usdt3_called");
-	ASSERT_EQ(bss->usdt12_called, 2, "usdt12_called");
+	ASSERT_EQ(bss->usdt0_called, called, "usdt0_called");
+	ASSERT_EQ(bss->usdt3_called, called, "usdt3_called");
+	ASSERT_EQ(bss->usdt12_called, called, "usdt12_called");
 
 	/* only check values that depend on trigger_func()'s input value */
 	ASSERT_EQ(bss->usdt3_args[0], 2, "usdt3_arg1");
@@ -133,9 +218,9 @@ static void subtest_basic_usdt(void)
 	if (!ASSERT_OK_PTR(skel->links.usdt3, "usdt3_reattach"))
 		goto cleanup;
 
-	trigger_func(3);
+	called += TRIGGER(3);
 
-	ASSERT_EQ(bss->usdt3_called, 3, "usdt3_called");
+	ASSERT_EQ(bss->usdt3_called, called, "usdt3_called");
 	/* this time usdt3 has custom cookie */
 	ASSERT_EQ(bss->usdt3_cookie, 0xBADC00C51E, "usdt3_cookie");
 	ASSERT_EQ(bss->usdt3_arg_cnt, 3, "usdt3_arg_cnt");
@@ -147,8 +232,19 @@ static void subtest_basic_usdt(void)
 	ASSERT_EQ(bss->usdt3_args[1], 42, "usdt3_arg2");
 	ASSERT_EQ(bss->usdt3_args[2], (uintptr_t)&bla, "usdt3_arg3");
 
+#if defined(__x86_64__) || defined(__i386__)
+	trigger_sib_spec();
+	ASSERT_EQ(bss->usdt_sib_called, 1, "usdt_sib_called");
+	ASSERT_EQ(bss->usdt_sib_cookie, expected_cookie, "usdt_sib_cookie");
+	ASSERT_EQ(bss->usdt_sib_arg_cnt, 1, "usdt_sib_arg_cnt");
+	ASSERT_EQ(bss->usdt_sib_arg, nums[0], "usdt_sib_arg");
+	ASSERT_EQ(bss->usdt_sib_arg_ret, 0, "usdt_sib_arg_ret");
+	ASSERT_EQ(bss->usdt_sib_arg_size, sizeof(nums[0]), "usdt_sib_arg_size");
+#endif
+
 cleanup:
 	test_usdt__destroy(skel);
+#undef TRIGGER
 }
 
 unsigned short test_usdt_100_semaphore SEC(".probes");
@@ -261,8 +357,16 @@ static void subtest_multispec_usdt(void)
 	 */
 	trigger_300_usdts();
 
-	/* we'll reuse usdt_100 BPF program for usdt_300 test */
 	bpf_link__destroy(skel->links.usdt_100);
+
+	bss->usdt_100_called = 0;
+	bss->usdt_100_sum = 0;
+
+	/* If built with arm64/clang, there will be much less number of specs
+	 * for usdt_300 call sites.
+	 */
+#if !defined(__aarch64__) || !defined(__clang__)
+	/* we'll reuse usdt_100 BPF program for usdt_300 test */
 	skel->links.usdt_100 = bpf_program__attach_usdt(skel->progs.usdt_100, -1, "/proc/self/exe",
 							"test", "usdt_300", NULL);
 	err = -errno;
@@ -273,13 +377,11 @@ static void subtest_multispec_usdt(void)
 	/* let's check that there are no "dangling" BPF programs attached due
 	 * to partial success of the above test:usdt_300 attachment
 	 */
-	bss->usdt_100_called = 0;
-	bss->usdt_100_sum = 0;
-
 	f300(777); /* this is 301st instance of usdt_300 */
 
 	ASSERT_EQ(bss->usdt_100_called, 0, "usdt_301_called");
 	ASSERT_EQ(bss->usdt_100_sum, 0, "usdt_301_sum");
+#endif
 
 	/* This time we have USDT with 400 inlined invocations, but arg specs
 	 * should be the same across all sites, so libbpf will only need to
@@ -314,6 +416,7 @@ static FILE *urand_spawn(int *pid)
 
 	if (fscanf(f, "%d", pid) != 1) {
 		pclose(f);
+		errno = EINVAL;
 		return NULL;
 	}
 
@@ -409,7 +512,11 @@ cleanup:
 void test_usdt(void)
 {
 	if (test__start_subtest("basic"))
-		subtest_basic_usdt();
+		subtest_basic_usdt(false);
+#ifdef __x86_64__
+	if (test__start_subtest("basic_optimized"))
+		subtest_basic_usdt(true);
+#endif
 	if (test__start_subtest("multispec"))
 		subtest_multispec_usdt();
 	if (test__start_subtest("urand_auto_attach"))
diff --git a/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c b/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c
index dae68de285b9..9fd3ae987321 100644
--- a/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c
@@ -4,6 +4,7 @@
 #define _GNU_SOURCE
 #include <linux/compiler.h>
 #include <linux/ring_buffer.h>
+#include <linux/build_bug.h>
 #include <pthread.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -19,11 +20,8 @@
 
 #include "../progs/test_user_ringbuf.h"
 
-static size_t log_buf_sz = 1 << 20; /* 1 MB */
-static char obj_log_buf[1048576];
 static const long c_sample_size = sizeof(struct sample) + BPF_RINGBUF_HDR_SZ;
-static const long c_ringbuf_size = 1 << 12; /* 1 small page */
-static const long c_max_entries = c_ringbuf_size / c_sample_size;
+static long c_ringbuf_size, c_max_entries;
 
 static void drain_current_samples(void)
 {
@@ -425,7 +423,9 @@ static void test_user_ringbuf_loop(void)
 	uint32_t remaining_samples = total_samples;
 	int err;
 
-	BUILD_BUG_ON(total_samples <= c_max_entries);
+	if (!ASSERT_LT(c_max_entries, total_samples, "compare_c_max_entries"))
+		return;
+
 	err = load_skel_create_user_ringbuf(&skel, &ringbuf);
 	if (err)
 		return;
@@ -592,7 +592,7 @@ static void *kick_kernel_cb(void *arg)
 	/* Kick the kernel, causing it to drain the ring buffer and then wake
 	 * up the test thread waiting on epoll.
 	 */
-	syscall(__NR_getrlimit);
+	syscall(__NR_prlimit64);
 
 	return NULL;
 }
@@ -644,7 +644,7 @@ static void test_user_ringbuf_blocking_reserve(void)
 	if (!ASSERT_EQ(err, 0, "deferred_kick_thread\n"))
 		goto cleanup;
 
-	/* After spawning another thread that asychronously kicks the kernel to
+	/* After spawning another thread that asynchronously kicks the kernel to
 	 * drain the messages, we're able to block and successfully get a
 	 * sample once we receive an event notification.
 	 */
@@ -663,23 +663,6 @@ cleanup:
 	user_ringbuf_success__destroy(skel);
 }
 
-static struct {
-	const char *prog_name;
-	const char *expected_err_msg;
-} failure_tests[] = {
-	/* failure cases */
-	{"user_ringbuf_callback_bad_access1", "negative offset dynptr_ptr ptr"},
-	{"user_ringbuf_callback_bad_access2", "dereference of modified dynptr_ptr ptr"},
-	{"user_ringbuf_callback_write_forbidden", "invalid mem access 'dynptr_ptr'"},
-	{"user_ringbuf_callback_null_context_write", "invalid mem access 'scalar'"},
-	{"user_ringbuf_callback_null_context_read", "invalid mem access 'scalar'"},
-	{"user_ringbuf_callback_discard_dynptr", "cannot release unowned const bpf_dynptr"},
-	{"user_ringbuf_callback_submit_dynptr", "cannot release unowned const bpf_dynptr"},
-	{"user_ringbuf_callback_invalid_return", "At callback return the register R0 has value"},
-	{"user_ringbuf_callback_reinit_dynptr_mem", "Dynptr has to be an uninitialized dynptr"},
-	{"user_ringbuf_callback_reinit_dynptr_ringbuf", "Dynptr has to be an uninitialized dynptr"},
-};
-
 #define SUCCESS_TEST(_func) { _func, #_func }
 
 static struct {
@@ -700,46 +683,13 @@ static struct {
 	SUCCESS_TEST(test_user_ringbuf_blocking_reserve),
 };
 
-static void verify_fail(const char *prog_name, const char *expected_err_msg)
-{
-	LIBBPF_OPTS(bpf_object_open_opts, opts);
-	struct bpf_program *prog;
-	struct user_ringbuf_fail *skel;
-	int err;
-
-	opts.kernel_log_buf = obj_log_buf;
-	opts.kernel_log_size = log_buf_sz;
-	opts.kernel_log_level = 1;
-
-	skel = user_ringbuf_fail__open_opts(&opts);
-	if (!ASSERT_OK_PTR(skel, "dynptr_fail__open_opts"))
-		goto cleanup;
-
-	prog = bpf_object__find_program_by_name(skel->obj, prog_name);
-	if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
-		goto cleanup;
-
-	bpf_program__set_autoload(prog, true);
-
-	bpf_map__set_max_entries(skel->maps.user_ringbuf, getpagesize());
-
-	err = user_ringbuf_fail__load(skel);
-	if (!ASSERT_ERR(err, "unexpected load success"))
-		goto cleanup;
-
-	if (!ASSERT_OK_PTR(strstr(obj_log_buf, expected_err_msg), "expected_err_msg")) {
-		fprintf(stderr, "Expected err_msg: %s\n", expected_err_msg);
-		fprintf(stderr, "Verifier output: %s\n", obj_log_buf);
-	}
-
-cleanup:
-	user_ringbuf_fail__destroy(skel);
-}
-
 void test_user_ringbuf(void)
 {
 	int i;
 
+	c_ringbuf_size = getpagesize(); /* 1 page */
+	c_max_entries = c_ringbuf_size / c_sample_size;
+
 	for (i = 0; i < ARRAY_SIZE(success_tests); i++) {
 		if (!test__start_subtest(success_tests[i].test_name))
 			continue;
@@ -747,10 +697,5 @@ void test_user_ringbuf(void)
 		success_tests[i].test_callback();
 	}
 
-	for (i = 0; i < ARRAY_SIZE(failure_tests); i++) {
-		if (!test__start_subtest(failure_tests[i].prog_name))
-			continue;
-
-		verify_fail(failure_tests[i].prog_name, failure_tests[i].expected_err_msg);
-	}
+	RUN_TESTS(user_ringbuf_fail);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/verif_stats.c b/tools/testing/selftests/bpf/prog_tests/verif_stats.c
index a47e7c0e1ffd..af4b95f57ac1 100644
--- a/tools/testing/selftests/bpf/prog_tests/verif_stats.c
+++ b/tools/testing/selftests/bpf/prog_tests/verif_stats.c
@@ -16,8 +16,9 @@ void test_verif_stats(void)
 	if (!ASSERT_OK_PTR(skel, "trace_vprintk__open_and_load"))
 		goto cleanup;
 
-	err = bpf_obj_get_info_by_fd(skel->progs.sys_enter.prog_fd, &info, &len);
-	if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd"))
+	err = bpf_prog_get_info_by_fd(skel->progs.sys_enter.prog_fd,
+				      &info, &len);
+	if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd"))
 		goto cleanup;
 
 	if (!ASSERT_GT(info.verified_insns, 0, "verified_insns"))
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
new file mode 100644
index 000000000000..4b4b081b46cc
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -0,0 +1,298 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <test_progs.h>
+
+#include "cap_helpers.h"
+#include "verifier_and.skel.h"
+#include "verifier_arena.skel.h"
+#include "verifier_arena_large.skel.h"
+#include "verifier_array_access.skel.h"
+#include "verifier_async_cb_context.skel.h"
+#include "verifier_basic_stack.skel.h"
+#include "verifier_bitfield_write.skel.h"
+#include "verifier_bounds.skel.h"
+#include "verifier_bounds_deduction.skel.h"
+#include "verifier_bounds_deduction_non_const.skel.h"
+#include "verifier_bounds_mix_sign_unsign.skel.h"
+#include "verifier_bpf_get_stack.skel.h"
+#include "verifier_bpf_trap.skel.h"
+#include "verifier_bswap.skel.h"
+#include "verifier_btf_ctx_access.skel.h"
+#include "verifier_btf_unreliable_prog.skel.h"
+#include "verifier_cfg.skel.h"
+#include "verifier_cgroup_inv_retcode.skel.h"
+#include "verifier_cgroup_skb.skel.h"
+#include "verifier_cgroup_storage.skel.h"
+#include "verifier_const.skel.h"
+#include "verifier_const_or.skel.h"
+#include "verifier_ctx.skel.h"
+#include "verifier_ctx_sk_msg.skel.h"
+#include "verifier_d_path.skel.h"
+#include "verifier_direct_packet_access.skel.h"
+#include "verifier_direct_stack_access_wraparound.skel.h"
+#include "verifier_div0.skel.h"
+#include "verifier_div_overflow.skel.h"
+#include "verifier_global_subprogs.skel.h"
+#include "verifier_global_ptr_args.skel.h"
+#include "verifier_gotol.skel.h"
+#include "verifier_gotox.skel.h"
+#include "verifier_helper_access_var_len.skel.h"
+#include "verifier_helper_packet_access.skel.h"
+#include "verifier_helper_restricted.skel.h"
+#include "verifier_helper_value_access.skel.h"
+#include "verifier_int_ptr.skel.h"
+#include "verifier_iterating_callbacks.skel.h"
+#include "verifier_jeq_infer_not_null.skel.h"
+#include "verifier_jit_convergence.skel.h"
+#include "verifier_ld_ind.skel.h"
+#include "verifier_ldsx.skel.h"
+#include "verifier_leak_ptr.skel.h"
+#include "verifier_linked_scalars.skel.h"
+#include "verifier_live_stack.skel.h"
+#include "verifier_load_acquire.skel.h"
+#include "verifier_loops1.skel.h"
+#include "verifier_lwt.skel.h"
+#include "verifier_map_in_map.skel.h"
+#include "verifier_map_ptr.skel.h"
+#include "verifier_map_ptr_mixing.skel.h"
+#include "verifier_map_ret_val.skel.h"
+#include "verifier_masking.skel.h"
+#include "verifier_may_goto_1.skel.h"
+#include "verifier_may_goto_2.skel.h"
+#include "verifier_meta_access.skel.h"
+#include "verifier_movsx.skel.h"
+#include "verifier_mtu.skel.h"
+#include "verifier_mul.skel.h"
+#include "verifier_netfilter_ctx.skel.h"
+#include "verifier_netfilter_retcode.skel.h"
+#include "verifier_bpf_fastcall.skel.h"
+#include "verifier_or_jmp32_k.skel.h"
+#include "verifier_precision.skel.h"
+#include "verifier_prevent_map_lookup.skel.h"
+#include "verifier_private_stack.skel.h"
+#include "verifier_raw_stack.skel.h"
+#include "verifier_raw_tp_writable.skel.h"
+#include "verifier_reg_equal.skel.h"
+#include "verifier_ref_tracking.skel.h"
+#include "verifier_regalloc.skel.h"
+#include "verifier_ringbuf.skel.h"
+#include "verifier_runtime_jit.skel.h"
+#include "verifier_scalar_ids.skel.h"
+#include "verifier_sdiv.skel.h"
+#include "verifier_search_pruning.skel.h"
+#include "verifier_sock.skel.h"
+#include "verifier_sock_addr.skel.h"
+#include "verifier_sockmap_mutate.skel.h"
+#include "verifier_spill_fill.skel.h"
+#include "verifier_spin_lock.skel.h"
+#include "verifier_stack_ptr.skel.h"
+#include "verifier_store_release.skel.h"
+#include "verifier_subprog_precision.skel.h"
+#include "verifier_subreg.skel.h"
+#include "verifier_tailcall.skel.h"
+#include "verifier_tailcall_jit.skel.h"
+#include "verifier_typedef.skel.h"
+#include "verifier_uninit.skel.h"
+#include "verifier_unpriv.skel.h"
+#include "verifier_unpriv_perf.skel.h"
+#include "verifier_value_adj_spill.skel.h"
+#include "verifier_value.skel.h"
+#include "verifier_value_illegal_alu.skel.h"
+#include "verifier_value_or_null.skel.h"
+#include "verifier_value_ptr_arith.skel.h"
+#include "verifier_var_off.skel.h"
+#include "verifier_vfs_accept.skel.h"
+#include "verifier_vfs_reject.skel.h"
+#include "verifier_xadd.skel.h"
+#include "verifier_xdp.skel.h"
+#include "verifier_xdp_direct_packet_access.skel.h"
+#include "verifier_bits_iter.skel.h"
+#include "verifier_lsm.skel.h"
+#include "irq.skel.h"
+
+#define MAX_ENTRIES 11
+
+struct test_val {
+	unsigned int index;
+	int foo[MAX_ENTRIES];
+};
+
+__maybe_unused
+static void run_tests_aux(const char *skel_name,
+			  skel_elf_bytes_fn elf_bytes_factory,
+			  pre_execution_cb pre_execution_cb)
+{
+	struct test_loader tester = {};
+	__u64 old_caps;
+	int err;
+
+	/* test_verifier tests are executed w/o CAP_SYS_ADMIN, do the same here */
+	err = cap_disable_effective(1ULL << CAP_SYS_ADMIN, &old_caps);
+	if (err) {
+		PRINT_FAIL("failed to drop CAP_SYS_ADMIN: %i, %s\n", err, strerror(-err));
+		return;
+	}
+
+	test_loader__set_pre_execution_cb(&tester, pre_execution_cb);
+	test_loader__run_subtests(&tester, skel_name, elf_bytes_factory);
+	test_loader_fini(&tester);
+
+	err = cap_enable_effective(old_caps, NULL);
+	if (err)
+		PRINT_FAIL("failed to restore CAP_SYS_ADMIN: %i, %s\n", err, strerror(-err));
+}
+
+#define RUN(skel) run_tests_aux(#skel, skel##__elf_bytes, NULL)
+
+void test_verifier_and(void)                  { RUN(verifier_and); }
+void test_verifier_arena(void)                { RUN(verifier_arena); }
+void test_verifier_arena_large(void)          { RUN(verifier_arena_large); }
+void test_verifier_basic_stack(void)          { RUN(verifier_basic_stack); }
+void test_verifier_bitfield_write(void)       { RUN(verifier_bitfield_write); }
+void test_verifier_bounds(void)               { RUN(verifier_bounds); }
+void test_verifier_bounds_deduction(void)     { RUN(verifier_bounds_deduction); }
+void test_verifier_bounds_deduction_non_const(void)     { RUN(verifier_bounds_deduction_non_const); }
+void test_verifier_bounds_mix_sign_unsign(void) { RUN(verifier_bounds_mix_sign_unsign); }
+void test_verifier_bpf_get_stack(void)        { RUN(verifier_bpf_get_stack); }
+void test_verifier_bpf_trap(void)             { RUN(verifier_bpf_trap); }
+void test_verifier_bswap(void)                { RUN(verifier_bswap); }
+void test_verifier_btf_ctx_access(void)       { RUN(verifier_btf_ctx_access); }
+void test_verifier_btf_unreliable_prog(void)  { RUN(verifier_btf_unreliable_prog); }
+void test_verifier_cfg(void)                  { RUN(verifier_cfg); }
+void test_verifier_cgroup_inv_retcode(void)   { RUN(verifier_cgroup_inv_retcode); }
+void test_verifier_cgroup_skb(void)           { RUN(verifier_cgroup_skb); }
+void test_verifier_cgroup_storage(void)       { RUN(verifier_cgroup_storage); }
+void test_verifier_const(void)                { RUN(verifier_const); }
+void test_verifier_const_or(void)             { RUN(verifier_const_or); }
+void test_verifier_ctx(void)                  { RUN(verifier_ctx); }
+void test_verifier_ctx_sk_msg(void)           { RUN(verifier_ctx_sk_msg); }
+void test_verifier_d_path(void)               { RUN(verifier_d_path); }
+void test_verifier_direct_packet_access(void) { RUN(verifier_direct_packet_access); }
+void test_verifier_direct_stack_access_wraparound(void) { RUN(verifier_direct_stack_access_wraparound); }
+void test_verifier_div0(void)                 { RUN(verifier_div0); }
+void test_verifier_div_overflow(void)         { RUN(verifier_div_overflow); }
+void test_verifier_global_subprogs(void)      { RUN(verifier_global_subprogs); }
+void test_verifier_global_ptr_args(void)      { RUN(verifier_global_ptr_args); }
+void test_verifier_gotol(void)                { RUN(verifier_gotol); }
+void test_verifier_gotox(void)                { RUN(verifier_gotox); }
+void test_verifier_helper_access_var_len(void) { RUN(verifier_helper_access_var_len); }
+void test_verifier_helper_packet_access(void) { RUN(verifier_helper_packet_access); }
+void test_verifier_helper_restricted(void)    { RUN(verifier_helper_restricted); }
+void test_verifier_helper_value_access(void)  { RUN(verifier_helper_value_access); }
+void test_verifier_int_ptr(void)              { RUN(verifier_int_ptr); }
+void test_verifier_iterating_callbacks(void)  { RUN(verifier_iterating_callbacks); }
+void test_verifier_jeq_infer_not_null(void)   { RUN(verifier_jeq_infer_not_null); }
+void test_verifier_jit_convergence(void)      { RUN(verifier_jit_convergence); }
+void test_verifier_load_acquire(void)         { RUN(verifier_load_acquire); }
+void test_verifier_ld_ind(void)               { RUN(verifier_ld_ind); }
+void test_verifier_ldsx(void)                  { RUN(verifier_ldsx); }
+void test_verifier_leak_ptr(void)             { RUN(verifier_leak_ptr); }
+void test_verifier_linked_scalars(void)       { RUN(verifier_linked_scalars); }
+void test_verifier_live_stack(void)           { RUN(verifier_live_stack); }
+void test_verifier_loops1(void)               { RUN(verifier_loops1); }
+void test_verifier_lwt(void)                  { RUN(verifier_lwt); }
+void test_verifier_map_in_map(void)           { RUN(verifier_map_in_map); }
+void test_verifier_map_ptr(void)              { RUN(verifier_map_ptr); }
+void test_verifier_map_ptr_mixing(void)       { RUN(verifier_map_ptr_mixing); }
+void test_verifier_map_ret_val(void)          { RUN(verifier_map_ret_val); }
+void test_verifier_masking(void)              { RUN(verifier_masking); }
+void test_verifier_may_goto_1(void)           { RUN(verifier_may_goto_1); }
+void test_verifier_may_goto_2(void)           { RUN(verifier_may_goto_2); }
+void test_verifier_meta_access(void)          { RUN(verifier_meta_access); }
+void test_verifier_movsx(void)                 { RUN(verifier_movsx); }
+void test_verifier_mul(void)                  { RUN(verifier_mul); }
+void test_verifier_netfilter_ctx(void)        { RUN(verifier_netfilter_ctx); }
+void test_verifier_netfilter_retcode(void)    { RUN(verifier_netfilter_retcode); }
+void test_verifier_bpf_fastcall(void)         { RUN(verifier_bpf_fastcall); }
+void test_verifier_or_jmp32_k(void)           { RUN(verifier_or_jmp32_k); }
+void test_verifier_precision(void)            { RUN(verifier_precision); }
+void test_verifier_prevent_map_lookup(void)   { RUN(verifier_prevent_map_lookup); }
+void test_verifier_private_stack(void)        { RUN(verifier_private_stack); }
+void test_verifier_raw_stack(void)            { RUN(verifier_raw_stack); }
+void test_verifier_raw_tp_writable(void)      { RUN(verifier_raw_tp_writable); }
+void test_verifier_reg_equal(void)            { RUN(verifier_reg_equal); }
+void test_verifier_ref_tracking(void)         { RUN(verifier_ref_tracking); }
+void test_verifier_regalloc(void)             { RUN(verifier_regalloc); }
+void test_verifier_ringbuf(void)              { RUN(verifier_ringbuf); }
+void test_verifier_runtime_jit(void)          { RUN(verifier_runtime_jit); }
+void test_verifier_scalar_ids(void)           { RUN(verifier_scalar_ids); }
+void test_verifier_sdiv(void)                 { RUN(verifier_sdiv); }
+void test_verifier_search_pruning(void)       { RUN(verifier_search_pruning); }
+void test_verifier_sock(void)                 { RUN(verifier_sock); }
+void test_verifier_sock_addr(void)            { RUN(verifier_sock_addr); }
+void test_verifier_sockmap_mutate(void)       { RUN(verifier_sockmap_mutate); }
+void test_verifier_spill_fill(void)           { RUN(verifier_spill_fill); }
+void test_verifier_spin_lock(void)            { RUN(verifier_spin_lock); }
+void test_verifier_stack_ptr(void)            { RUN(verifier_stack_ptr); }
+void test_verifier_store_release(void)        { RUN(verifier_store_release); }
+void test_verifier_subprog_precision(void)    { RUN(verifier_subprog_precision); }
+void test_verifier_subreg(void)               { RUN(verifier_subreg); }
+void test_verifier_tailcall(void)             { RUN(verifier_tailcall); }
+void test_verifier_tailcall_jit(void)         { RUN(verifier_tailcall_jit); }
+void test_verifier_typedef(void)              { RUN(verifier_typedef); }
+void test_verifier_uninit(void)               { RUN(verifier_uninit); }
+void test_verifier_unpriv(void)               { RUN(verifier_unpriv); }
+void test_verifier_unpriv_perf(void)          { RUN(verifier_unpriv_perf); }
+void test_verifier_value_adj_spill(void)      { RUN(verifier_value_adj_spill); }
+void test_verifier_value(void)                { RUN(verifier_value); }
+void test_verifier_value_illegal_alu(void)    { RUN(verifier_value_illegal_alu); }
+void test_verifier_value_or_null(void)        { RUN(verifier_value_or_null); }
+void test_verifier_var_off(void)              { RUN(verifier_var_off); }
+void test_verifier_vfs_accept(void)	      { RUN(verifier_vfs_accept); }
+void test_verifier_vfs_reject(void)	      { RUN(verifier_vfs_reject); }
+void test_verifier_xadd(void)                 { RUN(verifier_xadd); }
+void test_verifier_xdp(void)                  { RUN(verifier_xdp); }
+void test_verifier_xdp_direct_packet_access(void) { RUN(verifier_xdp_direct_packet_access); }
+void test_verifier_bits_iter(void) { RUN(verifier_bits_iter); }
+void test_verifier_lsm(void)                  { RUN(verifier_lsm); }
+void test_irq(void)			      { RUN(irq); }
+void test_verifier_mtu(void)		      { RUN(verifier_mtu); }
+
+static int init_test_val_map(struct bpf_object *obj, char *map_name)
+{
+	struct test_val value = {
+		.index = (6 + 1) * sizeof(int),
+		.foo[6] = 0xabcdef12,
+	};
+	struct bpf_map *map;
+	int err, key = 0;
+
+	map = bpf_object__find_map_by_name(obj, map_name);
+	if (!map) {
+		PRINT_FAIL("Can't find map '%s'\n", map_name);
+		return -EINVAL;
+	}
+
+	err = bpf_map_update_elem(bpf_map__fd(map), &key, &value, 0);
+	if (err) {
+		PRINT_FAIL("Error while updating map '%s': %d\n", map_name, err);
+		return err;
+	}
+
+	return 0;
+}
+
+static int init_array_access_maps(struct bpf_object *obj)
+{
+	return init_test_val_map(obj, "map_array_ro");
+}
+
+void test_verifier_array_access(void)
+{
+	run_tests_aux("verifier_array_access",
+		      verifier_array_access__elf_bytes,
+		      init_array_access_maps);
+}
+void test_verifier_async_cb_context(void)    { RUN(verifier_async_cb_context); }
+
+static int init_value_ptr_arith_maps(struct bpf_object *obj)
+{
+	return init_test_val_map(obj, "map_array_48b");
+}
+
+void test_verifier_value_ptr_arith(void)
+{
+	run_tests_aux("verifier_value_ptr_arith",
+		      verifier_value_ptr_arith__elf_bytes,
+		      init_value_ptr_arith_maps);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier_kfunc_prog_types.c b/tools/testing/selftests/bpf/prog_tests/verifier_kfunc_prog_types.c
new file mode 100644
index 000000000000..3918ecc2ee91
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/verifier_kfunc_prog_types.c
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <test_progs.h>
+
+#include "verifier_kfunc_prog_types.skel.h"
+
+void test_verifier_kfunc_prog_types(void)
+{
+	RUN_TESTS(verifier_kfunc_prog_types);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier_log.c b/tools/testing/selftests/bpf/prog_tests/verifier_log.c
new file mode 100644
index 000000000000..8337c6bc5b95
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/verifier_log.c
@@ -0,0 +1,450 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <test_progs.h>
+#include <bpf/btf.h>
+
+#include "test_log_buf.skel.h"
+
+
+static bool check_prog_load(int prog_fd, bool expect_err, const char *tag)
+{
+	if (expect_err) {
+		if (!ASSERT_LT(prog_fd, 0, tag)) {
+			close(prog_fd);
+			return false;
+		}
+	} else /* !expect_err */ {
+		if (!ASSERT_GT(prog_fd, 0, tag))
+			return false;
+	}
+	if (prog_fd >= 0)
+		close(prog_fd);
+	return true;
+}
+
+static struct {
+	/* strategically placed before others to avoid accidental modification by kernel */
+	char filler[1024];
+	char buf[1024];
+	/* strategically placed after buf[] to catch more accidental corruptions */
+	char reference[1024];
+} logs;
+static const struct bpf_insn *insns;
+static size_t insn_cnt;
+
+static int load_prog(struct bpf_prog_load_opts *opts, bool expect_load_error)
+{
+	int prog_fd;
+
+	prog_fd = bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT, "log_prog",
+				"GPL", insns, insn_cnt, opts);
+	check_prog_load(prog_fd, expect_load_error, "prog_load");
+
+	return prog_fd;
+}
+
+static void verif_log_subtest(const char *name, bool expect_load_error, int log_level)
+{
+	LIBBPF_OPTS(bpf_prog_load_opts, opts);
+	char *exp_log, prog_name[16], op_name[32];
+	struct test_log_buf *skel;
+	struct bpf_program *prog;
+	size_t fixed_log_sz;
+	__u32 log_true_sz_fixed, log_true_sz_rolling;
+	int i, mode, err, prog_fd, res;
+
+	skel = test_log_buf__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	bpf_object__for_each_program(prog, skel->obj) {
+		if (strcmp(bpf_program__name(prog), name) == 0)
+			bpf_program__set_autoload(prog, true);
+		else
+			bpf_program__set_autoload(prog, false);
+	}
+
+	err = test_log_buf__load(skel);
+	if (!expect_load_error && !ASSERT_OK(err, "unexpected_load_failure"))
+		goto cleanup;
+	if (expect_load_error && !ASSERT_ERR(err, "unexpected_load_success"))
+		goto cleanup;
+
+	insns = bpf_program__insns(skel->progs.good_prog);
+	insn_cnt = bpf_program__insn_cnt(skel->progs.good_prog);
+
+	opts.log_buf = logs.reference;
+	opts.log_size = sizeof(logs.reference);
+	opts.log_level = log_level | 8 /* BPF_LOG_FIXED */;
+	load_prog(&opts, expect_load_error);
+
+	fixed_log_sz = strlen(logs.reference) + 1;
+	if (!ASSERT_GT(fixed_log_sz, 50, "fixed_log_sz"))
+		goto cleanup;
+	memset(logs.reference + fixed_log_sz, 0, sizeof(logs.reference) - fixed_log_sz);
+
+	/* validate BPF_LOG_FIXED works as verifier log used to work, that is:
+	 * we get -ENOSPC and beginning of the full verifier log. This only
+	 * works for log_level 2 and log_level 1 + failed program. For log
+	 * level 2 we don't reset log at all. For log_level 1 + failed program
+	 * we don't get to verification stats output. With log level 1
+	 * for successful program  final result will be just verifier stats.
+	 * But if provided too short log buf, kernel will NULL-out log->ubuf
+	 * and will stop emitting further log. This means we'll never see
+	 * predictable verifier stats.
+	 * Long story short, we do the following -ENOSPC test only for
+	 * predictable combinations.
+	 */
+	if (log_level >= 2 || expect_load_error) {
+		opts.log_buf = logs.buf;
+		opts.log_level = log_level | 8; /* fixed-length log */
+		opts.log_size = 25;
+
+		prog_fd = bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT, "log_fixed25",
+					"GPL", insns, insn_cnt, &opts);
+		if (!ASSERT_EQ(prog_fd, -ENOSPC, "unexpected_log_fixed_prog_load_result")) {
+			if (prog_fd >= 0)
+				close(prog_fd);
+			goto cleanup;
+		}
+		if (!ASSERT_EQ(strlen(logs.buf), 24, "log_fixed_25"))
+			goto cleanup;
+		if (!ASSERT_STRNEQ(logs.buf, logs.reference, 24, "log_fixed_contents_25"))
+			goto cleanup;
+	}
+
+	/* validate rolling verifier log logic: try all variations of log buf
+	 * length to force various truncation scenarios
+	 */
+	opts.log_buf = logs.buf;
+
+	/* rotating mode, then fixed mode */
+	for (mode = 1; mode >= 0; mode--) {
+		/* prefill logs.buf with 'A's to detect any write beyond allowed length */
+		memset(logs.filler, 'A', sizeof(logs.filler));
+		logs.filler[sizeof(logs.filler) - 1] = '\0';
+		memset(logs.buf, 'A', sizeof(logs.buf));
+		logs.buf[sizeof(logs.buf) - 1] = '\0';
+
+		for (i = 1; i < fixed_log_sz; i++) {
+			opts.log_size = i;
+			opts.log_level = log_level | (mode ? 0 : 8 /* BPF_LOG_FIXED */);
+
+			snprintf(prog_name, sizeof(prog_name),
+				 "log_%s_%d", mode ? "roll" : "fixed", i);
+			prog_fd = bpf_prog_load(BPF_PROG_TYPE_RAW_TRACEPOINT, prog_name,
+						"GPL", insns, insn_cnt, &opts);
+
+			snprintf(op_name, sizeof(op_name),
+				 "log_%s_prog_load_%d", mode ? "roll" : "fixed", i);
+			if (!ASSERT_EQ(prog_fd, -ENOSPC, op_name)) {
+				if (prog_fd >= 0)
+					close(prog_fd);
+				goto cleanup;
+			}
+
+			snprintf(op_name, sizeof(op_name),
+				 "log_%s_strlen_%d", mode ? "roll" : "fixed", i);
+			ASSERT_EQ(strlen(logs.buf), i - 1, op_name);
+
+			if (mode)
+				exp_log = logs.reference + fixed_log_sz - i;
+			else
+				exp_log = logs.reference;
+
+			snprintf(op_name, sizeof(op_name),
+				 "log_%s_contents_%d", mode ? "roll" : "fixed", i);
+			if (!ASSERT_STRNEQ(logs.buf, exp_log, i - 1, op_name)) {
+				printf("CMP:%d\nS1:'%s'\nS2:'%s'\n",
+					strncmp(logs.buf, exp_log, i - 1),
+					logs.buf, exp_log);
+				goto cleanup;
+			}
+
+			/* check that unused portions of logs.buf is not overwritten */
+			snprintf(op_name, sizeof(op_name),
+				 "log_%s_unused_%d", mode ? "roll" : "fixed", i);
+			if (!ASSERT_STREQ(logs.buf + i, logs.filler + i, op_name)) {
+				printf("CMP:%d\nS1:'%s'\nS2:'%s'\n",
+					strcmp(logs.buf + i, logs.filler + i),
+					logs.buf + i, logs.filler + i);
+				goto cleanup;
+			}
+		}
+	}
+
+	/* (FIXED) get actual log size */
+	opts.log_buf = logs.buf;
+	opts.log_level = log_level | 8; /* BPF_LOG_FIXED */
+	opts.log_size = sizeof(logs.buf);
+	opts.log_true_size = 0;
+	res = load_prog(&opts, expect_load_error);
+	ASSERT_NEQ(res, -ENOSPC, "prog_load_res_fixed");
+
+	log_true_sz_fixed = opts.log_true_size;
+	ASSERT_GT(log_true_sz_fixed, 0, "log_true_sz_fixed");
+
+	/* (FIXED, NULL) get actual log size */
+	opts.log_buf = NULL;
+	opts.log_level = log_level | 8; /* BPF_LOG_FIXED */
+	opts.log_size = 0;
+	opts.log_true_size = 0;
+	res = load_prog(&opts, expect_load_error);
+	ASSERT_NEQ(res, -ENOSPC, "prog_load_res_fixed_null");
+	ASSERT_EQ(opts.log_true_size, log_true_sz_fixed, "log_sz_fixed_null_eq");
+
+	/* (ROLLING) get actual log size */
+	opts.log_buf = logs.buf;
+	opts.log_level = log_level;
+	opts.log_size = sizeof(logs.buf);
+	opts.log_true_size = 0;
+	res = load_prog(&opts, expect_load_error);
+	ASSERT_NEQ(res, -ENOSPC, "prog_load_res_rolling");
+
+	log_true_sz_rolling = opts.log_true_size;
+	ASSERT_EQ(log_true_sz_rolling, log_true_sz_fixed, "log_true_sz_eq");
+
+	/* (ROLLING, NULL) get actual log size */
+	opts.log_buf = NULL;
+	opts.log_level = log_level;
+	opts.log_size = 0;
+	opts.log_true_size = 0;
+	res = load_prog(&opts, expect_load_error);
+	ASSERT_NEQ(res, -ENOSPC, "prog_load_res_rolling_null");
+	ASSERT_EQ(opts.log_true_size, log_true_sz_rolling, "log_true_sz_null_eq");
+
+	/* (FIXED) expect -ENOSPC for one byte short log */
+	opts.log_buf = logs.buf;
+	opts.log_level = log_level | 8; /* BPF_LOG_FIXED */
+	opts.log_size = log_true_sz_fixed - 1;
+	opts.log_true_size = 0;
+	res = load_prog(&opts, true /* should fail */);
+	ASSERT_EQ(res, -ENOSPC, "prog_load_res_too_short_fixed");
+
+	/* (FIXED) expect *not* -ENOSPC with exact log_true_size buffer */
+	opts.log_buf = logs.buf;
+	opts.log_level = log_level | 8; /* BPF_LOG_FIXED */
+	opts.log_size = log_true_sz_fixed;
+	opts.log_true_size = 0;
+	res = load_prog(&opts, expect_load_error);
+	ASSERT_NEQ(res, -ENOSPC, "prog_load_res_just_right_fixed");
+
+	/* (ROLLING) expect -ENOSPC for one byte short log */
+	opts.log_buf = logs.buf;
+	opts.log_level = log_level;
+	opts.log_size = log_true_sz_rolling - 1;
+	res = load_prog(&opts, true /* should fail */);
+	ASSERT_EQ(res, -ENOSPC, "prog_load_res_too_short_rolling");
+
+	/* (ROLLING) expect *not* -ENOSPC with exact log_true_size buffer */
+	opts.log_buf = logs.buf;
+	opts.log_level = log_level;
+	opts.log_size = log_true_sz_rolling;
+	opts.log_true_size = 0;
+	res = load_prog(&opts, expect_load_error);
+	ASSERT_NEQ(res, -ENOSPC, "prog_load_res_just_right_rolling");
+
+cleanup:
+	test_log_buf__destroy(skel);
+}
+
+static const void *btf_data;
+static u32 btf_data_sz;
+
+static int load_btf(struct bpf_btf_load_opts *opts, bool expect_err)
+{
+	int fd;
+
+	fd = bpf_btf_load(btf_data, btf_data_sz, opts);
+	if (fd >= 0)
+		close(fd);
+	if (expect_err)
+		ASSERT_LT(fd, 0, "btf_load_failure");
+	else /* !expect_err */
+		ASSERT_GT(fd, 0, "btf_load_success");
+	return fd;
+}
+
+static void verif_btf_log_subtest(bool bad_btf)
+{
+	LIBBPF_OPTS(bpf_btf_load_opts, opts);
+	struct btf *btf;
+	struct btf_type *t;
+	char *exp_log, op_name[32];
+	size_t fixed_log_sz;
+	__u32 log_true_sz_fixed, log_true_sz_rolling;
+	int i, res;
+
+	/* prepare simple BTF contents */
+	btf = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf, "btf_new_empty"))
+		return;
+	res = btf__add_int(btf, "whatever", 4, 0);
+	if (!ASSERT_GT(res, 0, "btf_add_int_id"))
+		goto cleanup;
+	if (bad_btf) {
+		/* btf__add_int() doesn't allow bad value of size, so we'll just
+		 * force-cast btf_type pointer and manually override size to invalid
+		 * 3 if we need to simulate failure
+		 */
+		t = (void *)btf__type_by_id(btf, res);
+		if (!ASSERT_OK_PTR(t, "int_btf_type"))
+			goto cleanup;
+		t->size = 3;
+	}
+
+	btf_data = btf__raw_data(btf, &btf_data_sz);
+	if (!ASSERT_OK_PTR(btf_data, "btf_data"))
+		goto cleanup;
+
+	load_btf(&opts, bad_btf);
+
+	opts.log_buf = logs.reference;
+	opts.log_size = sizeof(logs.reference);
+	opts.log_level = 1 | 8 /* BPF_LOG_FIXED */;
+	load_btf(&opts, bad_btf);
+
+	fixed_log_sz = strlen(logs.reference) + 1;
+	if (!ASSERT_GT(fixed_log_sz, 50, "fixed_log_sz"))
+		goto cleanup;
+	memset(logs.reference + fixed_log_sz, 0, sizeof(logs.reference) - fixed_log_sz);
+
+	/* validate BPF_LOG_FIXED truncation works as verifier log used to work */
+	opts.log_buf = logs.buf;
+	opts.log_level = 1 | 8; /* fixed-length log */
+	opts.log_size = 25;
+	res = load_btf(&opts, true);
+	ASSERT_EQ(res, -ENOSPC, "half_log_fd");
+	ASSERT_EQ(strlen(logs.buf), 24, "log_fixed_25");
+	ASSERT_STRNEQ(logs.buf, logs.reference, 24, op_name);
+
+	/* validate rolling verifier log logic: try all variations of log buf
+	 * length to force various truncation scenarios
+	 */
+	opts.log_buf = logs.buf;
+	opts.log_level = 1; /* rolling log */
+
+	/* prefill logs.buf with 'A's to detect any write beyond allowed length */
+	memset(logs.filler, 'A', sizeof(logs.filler));
+	logs.filler[sizeof(logs.filler) - 1] = '\0';
+	memset(logs.buf, 'A', sizeof(logs.buf));
+	logs.buf[sizeof(logs.buf) - 1] = '\0';
+
+	for (i = 1; i < fixed_log_sz; i++) {
+		opts.log_size = i;
+
+		snprintf(op_name, sizeof(op_name), "log_roll_btf_load_%d", i);
+		res = load_btf(&opts, true);
+		if (!ASSERT_EQ(res, -ENOSPC, op_name))
+			goto cleanup;
+
+		exp_log = logs.reference + fixed_log_sz - i;
+		snprintf(op_name, sizeof(op_name), "log_roll_contents_%d", i);
+		if (!ASSERT_STREQ(logs.buf, exp_log, op_name)) {
+			printf("CMP:%d\nS1:'%s'\nS2:'%s'\n",
+				strcmp(logs.buf, exp_log),
+				logs.buf, exp_log);
+			goto cleanup;
+		}
+
+		/* check that unused portions of logs.buf are not overwritten */
+		snprintf(op_name, sizeof(op_name), "log_roll_unused_tail_%d", i);
+		if (!ASSERT_STREQ(logs.buf + i, logs.filler + i, op_name)) {
+			printf("CMP:%d\nS1:'%s'\nS2:'%s'\n",
+				strcmp(logs.buf + i, logs.filler + i),
+				logs.buf + i, logs.filler + i);
+			goto cleanup;
+		}
+	}
+
+	/* (FIXED) get actual log size */
+	opts.log_buf = logs.buf;
+	opts.log_level = 1 | 8; /* BPF_LOG_FIXED */
+	opts.log_size = sizeof(logs.buf);
+	opts.log_true_size = 0;
+	res = load_btf(&opts, bad_btf);
+	ASSERT_NEQ(res, -ENOSPC, "btf_load_res_fixed");
+
+	log_true_sz_fixed = opts.log_true_size;
+	ASSERT_GT(log_true_sz_fixed, 0, "log_true_sz_fixed");
+
+	/* (FIXED, NULL) get actual log size */
+	opts.log_buf = NULL;
+	opts.log_level = 1 | 8; /* BPF_LOG_FIXED */
+	opts.log_size = 0;
+	opts.log_true_size = 0;
+	res = load_btf(&opts, bad_btf);
+	ASSERT_NEQ(res, -ENOSPC, "btf_load_res_fixed_null");
+	ASSERT_EQ(opts.log_true_size, log_true_sz_fixed, "log_sz_fixed_null_eq");
+
+	/* (ROLLING) get actual log size */
+	opts.log_buf = logs.buf;
+	opts.log_level = 1;
+	opts.log_size = sizeof(logs.buf);
+	opts.log_true_size = 0;
+	res = load_btf(&opts, bad_btf);
+	ASSERT_NEQ(res, -ENOSPC, "btf_load_res_rolling");
+
+	log_true_sz_rolling = opts.log_true_size;
+	ASSERT_EQ(log_true_sz_rolling, log_true_sz_fixed, "log_true_sz_eq");
+
+	/* (ROLLING, NULL) get actual log size */
+	opts.log_buf = NULL;
+	opts.log_level = 1;
+	opts.log_size = 0;
+	opts.log_true_size = 0;
+	res = load_btf(&opts, bad_btf);
+	ASSERT_NEQ(res, -ENOSPC, "btf_load_res_rolling_null");
+	ASSERT_EQ(opts.log_true_size, log_true_sz_rolling, "log_true_sz_null_eq");
+
+	/* (FIXED) expect -ENOSPC for one byte short log */
+	opts.log_buf = logs.buf;
+	opts.log_level = 1 | 8; /* BPF_LOG_FIXED */
+	opts.log_size = log_true_sz_fixed - 1;
+	opts.log_true_size = 0;
+	res = load_btf(&opts, true);
+	ASSERT_EQ(res, -ENOSPC, "btf_load_res_too_short_fixed");
+
+	/* (FIXED) expect *not* -ENOSPC with exact log_true_size buffer */
+	opts.log_buf = logs.buf;
+	opts.log_level = 1 | 8; /* BPF_LOG_FIXED */
+	opts.log_size = log_true_sz_fixed;
+	opts.log_true_size = 0;
+	res = load_btf(&opts, bad_btf);
+	ASSERT_NEQ(res, -ENOSPC, "btf_load_res_just_right_fixed");
+
+	/* (ROLLING) expect -ENOSPC for one byte short log */
+	opts.log_buf = logs.buf;
+	opts.log_level = 1;
+	opts.log_size = log_true_sz_rolling - 1;
+	res = load_btf(&opts, true);
+	ASSERT_EQ(res, -ENOSPC, "btf_load_res_too_short_rolling");
+
+	/* (ROLLING) expect *not* -ENOSPC with exact log_true_size buffer */
+	opts.log_buf = logs.buf;
+	opts.log_level = 1;
+	opts.log_size = log_true_sz_rolling;
+	opts.log_true_size = 0;
+	res = load_btf(&opts, bad_btf);
+	ASSERT_NEQ(res, -ENOSPC, "btf_load_res_just_right_rolling");
+
+cleanup:
+	btf__free(btf);
+}
+
+void test_verifier_log(void)
+{
+	if (test__start_subtest("good_prog-level1"))
+		verif_log_subtest("good_prog", false, 1);
+	if (test__start_subtest("good_prog-level2"))
+		verif_log_subtest("good_prog", false, 2);
+	if (test__start_subtest("bad_prog-level1"))
+		verif_log_subtest("bad_prog", true, 1);
+	if (test__start_subtest("bad_prog-level2"))
+		verif_log_subtest("bad_prog", true, 2);
+	if (test__start_subtest("bad_btf"))
+		verif_btf_log_subtest(true /* bad btf */);
+	if (test__start_subtest("good_btf"))
+		verif_btf_log_subtest(false /* !bad btf */);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c b/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c
index 579d6ee83ce0..4d69d9d55e17 100644
--- a/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c
+++ b/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c
@@ -16,9 +16,12 @@
 #include <sys/wait.h>
 #include <sys/mman.h>
 #include <linux/keyctl.h>
+#include <sys/xattr.h>
+#include <linux/fsverity.h>
 #include <test_progs.h>
 
 #include "test_verify_pkcs7_sig.skel.h"
+#include "test_sig_in_xattr.skel.h"
 
 #define MAX_DATA_SIZE (1024 * 1024)
 #define MAX_SIG_SIZE 1024
@@ -26,6 +29,10 @@
 #define VERIFY_USE_SECONDARY_KEYRING (1UL)
 #define VERIFY_USE_PLATFORM_KEYRING  (2UL)
 
+#ifndef SHA256_DIGEST_SIZE
+#define SHA256_DIGEST_SIZE      32
+#endif
+
 /* In stripped ARM and x86-64 modules, ~ is surprisingly rare. */
 #define MODULE_SIG_STRING "~Module signature appended~\n"
 
@@ -61,6 +68,9 @@ static bool kfunc_not_supported;
 static int libbpf_print_cb(enum libbpf_print_level level, const char *fmt,
 			   va_list args)
 {
+	if (level == LIBBPF_WARN)
+		vprintf(fmt, args);
+
 	if (strcmp(fmt, "libbpf: extern (func ksym) '%s': not found in kernel or module BTFs\n"))
 		return 0;
 
@@ -251,14 +261,14 @@ out:
 	return ret;
 }
 
-void test_verify_pkcs7_sig(void)
+static void test_verify_pkcs7_sig_from_map(void)
 {
 	libbpf_print_fn_t old_print_cb;
 	char tmp_dir_template[] = "/tmp/verify_sigXXXXXX";
 	char *tmp_dir;
 	struct test_verify_pkcs7_sig *skel = NULL;
 	struct bpf_map *map;
-	struct data data;
+	struct data data = {};
 	int ret, zero = 0;
 
 	/* Trigger creation of session keyring. */
@@ -397,3 +407,159 @@ close_prog:
 	skel->bss->monitored_pid = 0;
 	test_verify_pkcs7_sig__destroy(skel);
 }
+
+static int get_signature_size(const char *sig_path)
+{
+	struct stat st;
+
+	if (stat(sig_path, &st) == -1)
+		return -1;
+
+	return st.st_size;
+}
+
+static int add_signature_to_xattr(const char *data_path, const char *sig_path)
+{
+	char sig[MAX_SIG_SIZE] = {0};
+	int fd, size, ret;
+
+	if (sig_path) {
+		fd = open(sig_path, O_RDONLY);
+		if (fd < 0)
+			return -1;
+
+		size = read(fd, sig, MAX_SIG_SIZE);
+		close(fd);
+		if (size <= 0)
+			return -1;
+	} else {
+		/* no sig_path, just write 32 bytes of zeros */
+		size = 32;
+	}
+	ret = setxattr(data_path, "user.sig", sig, size, 0);
+	if (!ASSERT_OK(ret, "setxattr"))
+		return -1;
+
+	return 0;
+}
+
+static int test_open_file(struct test_sig_in_xattr *skel, char *data_path,
+			  pid_t pid, bool should_success, char *name)
+{
+	int ret;
+
+	skel->bss->monitored_pid = pid;
+	ret = open(data_path, O_RDONLY);
+	close(ret);
+	skel->bss->monitored_pid = 0;
+
+	if (should_success) {
+		if (!ASSERT_GE(ret, 0, name))
+			return -1;
+	} else {
+		if (!ASSERT_LT(ret, 0, name))
+			return -1;
+	}
+	return 0;
+}
+
+static void test_pkcs7_sig_fsverity(void)
+{
+	char data_path[PATH_MAX];
+	char sig_path[PATH_MAX];
+	char tmp_dir_template[] = "/tmp/verify_sigXXXXXX";
+	char *tmp_dir;
+	struct test_sig_in_xattr *skel = NULL;
+	pid_t pid;
+	int ret;
+
+	tmp_dir = mkdtemp(tmp_dir_template);
+	if (!ASSERT_OK_PTR(tmp_dir, "mkdtemp"))
+		return;
+
+	snprintf(data_path, PATH_MAX, "%s/data-file", tmp_dir);
+	snprintf(sig_path, PATH_MAX, "%s/sig-file", tmp_dir);
+
+	ret = _run_setup_process(tmp_dir, "setup");
+	if (!ASSERT_OK(ret, "_run_setup_process"))
+		goto out;
+
+	ret = _run_setup_process(tmp_dir, "fsverity-create-sign");
+
+	if (ret) {
+		printf("%s: SKIP: fsverity [sign|enable] doesn't work.\n"
+		       "To run this test, try enable CONFIG_FS_VERITY and enable FSVerity for the filesystem.\n",
+		       __func__);
+		test__skip();
+		goto out;
+	}
+
+	skel = test_sig_in_xattr__open();
+	if (!ASSERT_OK_PTR(skel, "test_sig_in_xattr__open"))
+		goto out;
+	ret = get_signature_size(sig_path);
+	if (!ASSERT_GT(ret, 0, "get_signature_size"))
+		goto out;
+	skel->bss->sig_size = ret;
+	skel->bss->user_keyring_serial = syscall(__NR_request_key, "keyring",
+						 "ebpf_testing_keyring", NULL,
+						 KEY_SPEC_SESSION_KEYRING);
+	memcpy(skel->bss->digest, "FSVerity", 8);
+
+	ret = test_sig_in_xattr__load(skel);
+	if (!ASSERT_OK(ret, "test_sig_in_xattr__load"))
+		goto out;
+
+	ret = test_sig_in_xattr__attach(skel);
+	if (!ASSERT_OK(ret, "test_sig_in_xattr__attach"))
+		goto out;
+
+	pid = getpid();
+
+	/* Case 1: fsverity is not enabled, open should succeed */
+	if (test_open_file(skel, data_path, pid, true, "open_1"))
+		goto out;
+
+	/* Case 2: fsverity is enabled, xattr is missing, open should
+	 * fail
+	 */
+	ret = _run_setup_process(tmp_dir, "fsverity-enable");
+	if (!ASSERT_OK(ret, "fsverity-enable"))
+		goto out;
+	if (test_open_file(skel, data_path, pid, false, "open_2"))
+		goto out;
+
+	/* Case 3: fsverity is enabled, xattr has valid signature, open
+	 * should succeed
+	 */
+	ret = add_signature_to_xattr(data_path, sig_path);
+	if (!ASSERT_OK(ret, "add_signature_to_xattr_1"))
+		goto out;
+
+	if (test_open_file(skel, data_path, pid, true, "open_3"))
+		goto out;
+
+	/* Case 4: fsverity is enabled, xattr has invalid signature, open
+	 * should fail
+	 */
+	ret = add_signature_to_xattr(data_path, NULL);
+	if (!ASSERT_OK(ret, "add_signature_to_xattr_2"))
+		goto out;
+	test_open_file(skel, data_path, pid, false, "open_4");
+
+out:
+	_run_setup_process(tmp_dir, "cleanup");
+	if (!skel)
+		return;
+
+	skel->bss->monitored_pid = 0;
+	test_sig_in_xattr__destroy(skel);
+}
+
+void test_verify_pkcs7_sig(void)
+{
+	if (test__start_subtest("pkcs7_sig_from_map"))
+		test_verify_pkcs7_sig_from_map();
+	if (test__start_subtest("pkcs7_sig_fsverity"))
+		test_pkcs7_sig_fsverity();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/vmlinux.c b/tools/testing/selftests/bpf/prog_tests/vmlinux.c
index 72310cfc6474..6fb2217d940b 100644
--- a/tools/testing/selftests/bpf/prog_tests/vmlinux.c
+++ b/tools/testing/selftests/bpf/prog_tests/vmlinux.c
@@ -16,27 +16,27 @@ static void nsleep()
 
 void test_vmlinux(void)
 {
-	int duration = 0, err;
+	int err;
 	struct test_vmlinux* skel;
 	struct test_vmlinux__bss *bss;
 
 	skel = test_vmlinux__open_and_load();
-	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+	if (!ASSERT_OK_PTR(skel, "test_vmlinux__open_and_load"))
 		return;
 	bss = skel->bss;
 
 	err = test_vmlinux__attach(skel);
-	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+	if (!ASSERT_OK(err, "test_vmlinux__attach"))
 		goto cleanup;
 
 	/* trigger everything */
 	nsleep();
 
-	CHECK(!bss->tp_called, "tp", "not called\n");
-	CHECK(!bss->raw_tp_called, "raw_tp", "not called\n");
-	CHECK(!bss->tp_btf_called, "tp_btf", "not called\n");
-	CHECK(!bss->kprobe_called, "kprobe", "not called\n");
-	CHECK(!bss->fentry_called, "fentry", "not called\n");
+	ASSERT_TRUE(bss->tp_called, "tp");
+	ASSERT_TRUE(bss->raw_tp_called, "raw_tp");
+	ASSERT_TRUE(bss->tp_btf_called, "tp_btf");
+	ASSERT_TRUE(bss->kprobe_called, "kprobe");
+	ASSERT_TRUE(bss->fentry_called, "fentry");
 
 cleanup:
 	test_vmlinux__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/vrf_socket_lookup.c b/tools/testing/selftests/bpf/prog_tests/vrf_socket_lookup.c
new file mode 100644
index 000000000000..2a5e207edad6
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/vrf_socket_lookup.c
@@ -0,0 +1,312 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+
+/*
+ * Topology:
+ * ---------
+ *     NS0 namespace         |   NS1 namespace
+ *			     |
+ *     +--------------+      |   +--------------+
+ *     |    veth01    |----------|    veth10    |
+ *     | 172.16.1.100 |      |   | 172.16.1.200 |
+ *     |     bpf      |      |   +--------------+
+ *     +--------------+      |
+ *      server(UDP/TCP)      |
+ *  +-------------------+    |
+ *  |        vrf1       |    |
+ *  |  +--------------+ |    |   +--------------+
+ *  |  |    veth02    |----------|    veth20    |
+ *  |  | 172.16.2.100 | |    |   | 172.16.2.200 |
+ *  |  |     bpf      | |    |   +--------------+
+ *  |  +--------------+ |    |
+ *  |   server(UDP/TCP) |    |
+ *  +-------------------+    |
+ *
+ * Test flow
+ * -----------
+ *  The tests verifies that socket lookup via TC is VRF aware:
+ *  1) Creates two veth pairs between NS0 and NS1:
+ *     a) veth01 <-> veth10 outside the VRF
+ *     b) veth02 <-> veth20 in the VRF
+ *  2) Attaches to veth01 and veth02 a program that calls:
+ *     a) bpf_skc_lookup_tcp() with TCP and tcp_skc is true
+ *     b) bpf_sk_lookup_tcp() with TCP and tcp_skc is false
+ *     c) bpf_sk_lookup_udp() with UDP
+ *     The program stores the lookup result in bss->lookup_status.
+ *  3) Creates a socket TCP/UDP server in/outside the VRF.
+ *  4) The test expects lookup_status to be:
+ *     a) 0 from device in VRF to server outside VRF
+ *     b) 0 from device outside VRF to server in VRF
+ *     c) 1 from device in VRF to server in VRF
+ *     d) 1 from device outside VRF to server outside VRF
+ */
+
+#include <net/if.h>
+
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "vrf_socket_lookup.skel.h"
+
+#define NS0 "vrf_socket_lookup_0"
+#define NS1 "vrf_socket_lookup_1"
+
+#define IP4_ADDR_VETH01 "172.16.1.100"
+#define IP4_ADDR_VETH10 "172.16.1.200"
+#define IP4_ADDR_VETH02 "172.16.2.100"
+#define IP4_ADDR_VETH20 "172.16.2.200"
+
+#define NON_VRF_PORT 5000
+#define IN_VRF_PORT 5001
+
+#define TIMEOUT_MS 3000
+
+static int make_socket(int sotype, const char *ip, int port,
+		       struct sockaddr_storage *addr)
+{
+	int err, fd;
+
+	err = make_sockaddr(AF_INET, ip, port, addr, NULL);
+	if (!ASSERT_OK(err, "make_address"))
+		return -1;
+
+	fd = socket(AF_INET, sotype, 0);
+	if (!ASSERT_GE(fd, 0, "socket"))
+		return -1;
+
+	if (!ASSERT_OK(settimeo(fd, TIMEOUT_MS), "settimeo"))
+		goto fail;
+
+	return fd;
+fail:
+	close(fd);
+	return -1;
+}
+
+static int make_server(int sotype, const char *ip, int port, const char *ifname)
+{
+	int err, fd = -1;
+
+	fd = start_server(AF_INET, sotype, ip, port, TIMEOUT_MS);
+	if (!ASSERT_GE(fd, 0, "start_server"))
+		return -1;
+
+	if (ifname) {
+		err = setsockopt(fd, SOL_SOCKET, SO_BINDTODEVICE,
+				 ifname, strlen(ifname) + 1);
+		if (!ASSERT_OK(err, "setsockopt(SO_BINDTODEVICE)"))
+			goto fail;
+	}
+
+	return fd;
+fail:
+	close(fd);
+	return -1;
+}
+
+static int attach_progs(char *ifname, int tc_prog_fd, int xdp_prog_fd)
+{
+	LIBBPF_OPTS(bpf_tc_hook, hook, .attach_point = BPF_TC_INGRESS);
+	LIBBPF_OPTS(bpf_tc_opts, opts, .handle = 1, .priority = 1,
+		    .prog_fd = tc_prog_fd);
+	int ret, ifindex;
+
+	ifindex = if_nametoindex(ifname);
+	if (!ASSERT_NEQ(ifindex, 0, "if_nametoindex"))
+		return -1;
+	hook.ifindex = ifindex;
+
+	ret = bpf_tc_hook_create(&hook);
+	if (!ASSERT_OK(ret, "bpf_tc_hook_create"))
+		return ret;
+
+	ret = bpf_tc_attach(&hook, &opts);
+	if (!ASSERT_OK(ret, "bpf_tc_attach")) {
+		bpf_tc_hook_destroy(&hook);
+		return ret;
+	}
+	ret = bpf_xdp_attach(ifindex, xdp_prog_fd, 0, NULL);
+	if (!ASSERT_OK(ret, "bpf_xdp_attach")) {
+		bpf_tc_hook_destroy(&hook);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void cleanup(void)
+{
+	SYS_NOFAIL("test -f /var/run/netns/" NS0 " && ip netns delete "
+		   NS0);
+	SYS_NOFAIL("test -f /var/run/netns/" NS1 " && ip netns delete "
+		   NS1);
+}
+
+static int setup(struct vrf_socket_lookup *skel)
+{
+	int tc_prog_fd, xdp_prog_fd, ret = 0;
+	struct nstoken *nstoken = NULL;
+
+	SYS(fail, "ip netns add " NS0);
+	SYS(fail, "ip netns add " NS1);
+
+	/* NS0 <-> NS1 [veth01 <-> veth10] */
+	SYS(fail, "ip link add veth01 netns " NS0 " type veth peer name veth10"
+	    " netns " NS1);
+	SYS(fail, "ip -net " NS0 " addr add " IP4_ADDR_VETH01 "/24 dev veth01");
+	SYS(fail, "ip -net " NS0 " link set dev veth01 up");
+	SYS(fail, "ip -net " NS1 " addr add " IP4_ADDR_VETH10 "/24 dev veth10");
+	SYS(fail, "ip -net " NS1 " link set dev veth10 up");
+
+	/* NS0 <-> NS1 [veth02 <-> veth20] */
+	SYS(fail, "ip link add veth02 netns " NS0 " type veth peer name veth20"
+	    " netns " NS1);
+	SYS(fail, "ip -net " NS0 " addr add " IP4_ADDR_VETH02 "/24 dev veth02");
+	SYS(fail, "ip -net " NS0 " link set dev veth02 up");
+	SYS(fail, "ip -net " NS1 " addr add " IP4_ADDR_VETH20 "/24 dev veth20");
+	SYS(fail, "ip -net " NS1 " link set dev veth20 up");
+
+	/* veth02 -> vrf1  */
+	SYS(fail, "ip -net " NS0 " link add vrf1 type vrf table 11");
+	SYS(fail, "ip -net " NS0 " route add vrf vrf1 unreachable default"
+	    " metric 4278198272");
+	SYS(fail, "ip -net " NS0 " link set vrf1 alias vrf");
+	SYS(fail, "ip -net " NS0 " link set vrf1 up");
+	SYS(fail, "ip -net " NS0 " link set veth02 master vrf1");
+
+	/* Attach TC and XDP progs to veth devices in NS0 */
+	nstoken = open_netns(NS0);
+	if (!ASSERT_OK_PTR(nstoken, "setns " NS0))
+		goto fail;
+	tc_prog_fd = bpf_program__fd(skel->progs.tc_socket_lookup);
+	if (!ASSERT_GE(tc_prog_fd, 0, "bpf_program__tc_fd"))
+		goto fail;
+	xdp_prog_fd = bpf_program__fd(skel->progs.xdp_socket_lookup);
+	if (!ASSERT_GE(xdp_prog_fd, 0, "bpf_program__xdp_fd"))
+		goto fail;
+
+	if (attach_progs("veth01", tc_prog_fd, xdp_prog_fd))
+		goto fail;
+
+	if (attach_progs("veth02", tc_prog_fd, xdp_prog_fd))
+		goto fail;
+
+	goto close;
+fail:
+	ret = -1;
+close:
+	if (nstoken)
+		close_netns(nstoken);
+	return ret;
+}
+
+static int test_lookup(struct vrf_socket_lookup *skel, int sotype,
+		       const char *ip, int port, bool test_xdp, bool tcp_skc,
+		       int lookup_status_exp)
+{
+	static const char msg[] = "Hello Server";
+	struct sockaddr_storage addr = {};
+	int fd, ret = 0;
+
+	fd = make_socket(sotype, ip, port, &addr);
+	if (fd < 0)
+		return -1;
+
+	skel->bss->test_xdp = test_xdp;
+	skel->bss->tcp_skc = tcp_skc;
+	skel->bss->lookup_status = -1;
+
+	if (sotype == SOCK_STREAM)
+		connect(fd, (void *)&addr, sizeof(struct sockaddr_in));
+	else
+		sendto(fd, msg, sizeof(msg), 0, (void *)&addr,
+		       sizeof(struct sockaddr_in));
+
+	if (!ASSERT_EQ(skel->bss->lookup_status, lookup_status_exp,
+		       "lookup_status"))
+		goto fail;
+
+	goto close;
+
+fail:
+	ret = -1;
+close:
+	close(fd);
+	return ret;
+}
+
+static void _test_vrf_socket_lookup(struct vrf_socket_lookup *skel, int sotype,
+				    bool test_xdp, bool tcp_skc)
+{
+	int in_vrf_server = -1, non_vrf_server = -1;
+	struct nstoken *nstoken = NULL;
+
+	nstoken = open_netns(NS0);
+	if (!ASSERT_OK_PTR(nstoken, "setns " NS0))
+		goto done;
+
+	/* Open sockets in and outside VRF */
+	non_vrf_server = make_server(sotype, "0.0.0.0", NON_VRF_PORT, NULL);
+	if (!ASSERT_GE(non_vrf_server, 0, "make_server__outside_vrf_fd"))
+		goto done;
+
+	in_vrf_server = make_server(sotype, "0.0.0.0", IN_VRF_PORT, "veth02");
+	if (!ASSERT_GE(in_vrf_server, 0, "make_server__in_vrf_fd"))
+		goto done;
+
+	/* Perform test from NS1 */
+	close_netns(nstoken);
+	nstoken = open_netns(NS1);
+	if (!ASSERT_OK_PTR(nstoken, "setns " NS1))
+		goto done;
+
+	if (!ASSERT_OK(test_lookup(skel, sotype, IP4_ADDR_VETH02, NON_VRF_PORT,
+				   test_xdp, tcp_skc, 0), "in_to_out"))
+		goto done;
+	if (!ASSERT_OK(test_lookup(skel, sotype, IP4_ADDR_VETH02, IN_VRF_PORT,
+				   test_xdp, tcp_skc, 1), "in_to_in"))
+		goto done;
+	if (!ASSERT_OK(test_lookup(skel, sotype, IP4_ADDR_VETH01, NON_VRF_PORT,
+				   test_xdp, tcp_skc, 1), "out_to_out"))
+		goto done;
+	if (!ASSERT_OK(test_lookup(skel, sotype, IP4_ADDR_VETH01, IN_VRF_PORT,
+				   test_xdp, tcp_skc, 0), "out_to_in"))
+		goto done;
+
+done:
+	if (non_vrf_server >= 0)
+		close(non_vrf_server);
+	if (in_vrf_server >= 0)
+		close(in_vrf_server);
+	if (nstoken)
+		close_netns(nstoken);
+}
+
+void test_vrf_socket_lookup(void)
+{
+	struct vrf_socket_lookup *skel;
+
+	cleanup();
+
+	skel = vrf_socket_lookup__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "vrf_socket_lookup__open_and_load"))
+		return;
+
+	if (!ASSERT_OK(setup(skel), "setup"))
+		goto done;
+
+	if (test__start_subtest("tc_socket_lookup_tcp"))
+		_test_vrf_socket_lookup(skel, SOCK_STREAM, false, false);
+	if (test__start_subtest("tc_socket_lookup_tcp_skc"))
+		_test_vrf_socket_lookup(skel, SOCK_STREAM, false, false);
+	if (test__start_subtest("tc_socket_lookup_udp"))
+		_test_vrf_socket_lookup(skel, SOCK_STREAM, false, false);
+	if (test__start_subtest("xdp_socket_lookup_tcp"))
+		_test_vrf_socket_lookup(skel, SOCK_STREAM, true, false);
+	if (test__start_subtest("xdp_socket_lookup_tcp_skc"))
+		_test_vrf_socket_lookup(skel, SOCK_STREAM, true, false);
+	if (test__start_subtest("xdp_socket_lookup_udp"))
+		_test_vrf_socket_lookup(skel, SOCK_STREAM, true, false);
+
+done:
+	vrf_socket_lookup__destroy(skel);
+	cleanup();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/wq.c b/tools/testing/selftests/bpf/prog_tests/wq.c
new file mode 100644
index 000000000000..15c67d23128b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/wq.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Benjamin Tissoires */
+#include <test_progs.h>
+#include "wq.skel.h"
+#include "wq_failures.skel.h"
+
+void serial_test_wq(void)
+{
+	struct wq *wq_skel = NULL;
+	int err, prog_fd;
+
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+
+	RUN_TESTS(wq);
+
+	/* re-run the success test to check if the timer was actually executed */
+
+	wq_skel = wq__open_and_load();
+	if (!ASSERT_OK_PTR(wq_skel, "wq_skel_load"))
+		return;
+
+	err = wq__attach(wq_skel);
+	if (!ASSERT_OK(err, "wq_attach"))
+		return;
+
+	prog_fd = bpf_program__fd(wq_skel->progs.test_syscall_array_sleepable);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(topts.retval, 0, "test_run");
+
+	usleep(50); /* 10 usecs should be enough, but give it extra */
+
+	ASSERT_EQ(wq_skel->bss->ok_sleepable, (1 << 1), "ok_sleepable");
+	wq__destroy(wq_skel);
+}
+
+void serial_test_failures_wq(void)
+{
+	RUN_TESTS(wq_failures);
+}
+
+static void test_failure_map_no_btf(void)
+{
+	struct wq *skel = NULL;
+	char log[8192];
+	const struct bpf_insn *insns;
+	size_t insn_cnt;
+	int ret, err, map_fd;
+	LIBBPF_OPTS(bpf_prog_load_opts, opts, .log_size = sizeof(log), .log_buf = log,
+		    .log_level = 2);
+
+	skel = wq__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	err = bpf_object__prepare(skel->obj);
+	if (!ASSERT_OK(err, "skel__prepare"))
+		goto out;
+
+	map_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, "map_no_btf", sizeof(__u32), sizeof(__u64), 100,
+				NULL);
+	if (!ASSERT_GT(map_fd, -1, "map create"))
+		goto out;
+
+	err = bpf_map__reuse_fd(skel->maps.array, map_fd);
+	if (!ASSERT_OK(err, "map reuse fd")) {
+		close(map_fd);
+		goto out;
+	}
+
+	insns = bpf_program__insns(skel->progs.test_map_no_btf);
+	if (!ASSERT_OK_PTR(insns, "insns ptr"))
+		goto out;
+
+	insn_cnt = bpf_program__insn_cnt(skel->progs.test_map_no_btf);
+	if (!ASSERT_GT(insn_cnt, 0u, "insn cnt"))
+		goto out;
+
+	ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts);
+	if (!ASSERT_LT(ret, 0, "prog load failed")) {
+		if (ret > 0)
+			close(ret);
+		goto out;
+	}
+
+	ASSERT_HAS_SUBSTR(log, "map 'map_no_btf' has to have BTF in order to use bpf_wq",
+			  "log complains no map BTF");
+out:
+	wq__destroy(skel);
+}
+
+void test_wq_custom(void)
+{
+	if (test__start_subtest("test_failure_map_no_btf"))
+		test_failure_map_no_btf();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
index 39973ea1ce43..43264347e7d7 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
@@ -37,21 +37,26 @@ static void test_xdp_adjust_tail_shrink(void)
 	bpf_object__close(obj);
 }
 
-static void test_xdp_adjust_tail_grow(void)
+static void test_xdp_adjust_tail_grow(bool is_64k_pagesize)
 {
 	const char *file = "./test_xdp_adjust_tail_grow.bpf.o";
 	struct bpf_object *obj;
-	char buf[4096]; /* avoid segfault: large buf to hold grow results */
+	char buf[8192]; /* avoid segfault: large buf to hold grow results */
 	__u32 expect_sz;
 	int err, prog_fd;
 	LIBBPF_OPTS(bpf_test_run_opts, topts,
 		.data_in = &pkt_v4,
-		.data_size_in = sizeof(pkt_v4),
 		.data_out = buf,
 		.data_size_out = sizeof(buf),
 		.repeat = 1,
 	);
 
+	/* topts.data_size_in as a special signal to bpf prog */
+	if (is_64k_pagesize)
+		topts.data_size_in = sizeof(pkt_v4) - 1;
+	else
+		topts.data_size_in = sizeof(pkt_v4);
+
 	err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
 	if (!ASSERT_OK(err, "test_xdp_adjust_tail_grow"))
 		return;
@@ -76,10 +81,17 @@ static void test_xdp_adjust_tail_grow2(void)
 {
 	const char *file = "./test_xdp_adjust_tail_grow.bpf.o";
 	char buf[4096]; /* avoid segfault: large buf to hold grow results */
-	int tailroom = 320; /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info))*/;
 	struct bpf_object *obj;
 	int err, cnt, i;
 	int max_grow, prog_fd;
+	/* SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) */
+#if defined(__s390x__)
+	int tailroom = 512;
+#elif defined(__powerpc__)
+	int tailroom = 384;
+#else
+	int tailroom = 320;
+#endif
 
 	LIBBPF_OPTS(bpf_test_run_opts, tattr,
 		.repeat		= 1,
@@ -201,7 +213,7 @@ out:
 	bpf_object__close(obj);
 }
 
-static void test_xdp_adjust_frags_tail_grow(void)
+static void test_xdp_adjust_frags_tail_grow_4k(void)
 {
 	const char *file = "./test_xdp_adjust_tail_grow.bpf.o";
 	__u32 exp_size;
@@ -217,7 +229,7 @@ static void test_xdp_adjust_frags_tail_grow(void)
 
 	prog = bpf_object__next_program(obj, NULL);
 	if (bpf_object__load(obj))
-		return;
+		goto out;
 
 	prog_fd = bpf_program__fd(prog);
 
@@ -239,14 +251,20 @@ static void test_xdp_adjust_frags_tail_grow(void)
 	ASSERT_EQ(topts.retval, XDP_TX, "9Kb+10b retval");
 	ASSERT_EQ(topts.data_size_out, exp_size, "9Kb+10b size");
 
-	for (i = 0; i < 9000; i++)
-		ASSERT_EQ(buf[i], 1, "9Kb+10b-old");
+	for (i = 0; i < 9000; i++) {
+		if (buf[i] != 1)
+			ASSERT_EQ(buf[i], 1, "9Kb+10b-old");
+	}
 
-	for (i = 9000; i < 9010; i++)
-		ASSERT_EQ(buf[i], 0, "9Kb+10b-new");
+	for (i = 9000; i < 9010; i++) {
+		if (buf[i] != 0)
+			ASSERT_EQ(buf[i], 0, "9Kb+10b-new");
+	}
 
-	for (i = 9010; i < 16384; i++)
-		ASSERT_EQ(buf[i], 1, "9Kb+10b-untouched");
+	for (i = 9010; i < 16384; i++) {
+		if (buf[i] != 1)
+			ASSERT_EQ(buf[i], 1, "9Kb+10b-untouched");
+	}
 
 	/* Test a too large grow */
 	memset(buf, 1, 16384);
@@ -266,16 +284,93 @@ out:
 	bpf_object__close(obj);
 }
 
+static void test_xdp_adjust_frags_tail_grow_64k(void)
+{
+	const char *file = "./test_xdp_adjust_tail_grow.bpf.o";
+	__u32 exp_size;
+	struct bpf_program *prog;
+	struct bpf_object *obj;
+	int err, i, prog_fd;
+	__u8 *buf;
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+
+	obj = bpf_object__open(file);
+	if (libbpf_get_error(obj))
+		return;
+
+	prog = bpf_object__next_program(obj, NULL);
+	if (bpf_object__load(obj))
+		goto out;
+
+	prog_fd = bpf_program__fd(prog);
+
+	buf = malloc(262144);
+	if (!ASSERT_OK_PTR(buf, "alloc buf 256Kb"))
+		goto out;
+
+	/* Test case add 10 bytes to last frag */
+	memset(buf, 1, 262144);
+	exp_size = 90000 + 10;
+
+	topts.data_in = buf;
+	topts.data_out = buf;
+	topts.data_size_in = 90000;
+	topts.data_size_out = 262144;
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+
+	ASSERT_OK(err, "90Kb+10b");
+	ASSERT_EQ(topts.retval, XDP_TX, "90Kb+10b retval");
+	ASSERT_EQ(topts.data_size_out, exp_size, "90Kb+10b size");
+
+	for (i = 0; i < 90000; i++) {
+		if (buf[i] != 1)
+			ASSERT_EQ(buf[i], 1, "90Kb+10b-old");
+	}
+
+	for (i = 90000; i < 90010; i++) {
+		if (buf[i] != 0)
+			ASSERT_EQ(buf[i], 0, "90Kb+10b-new");
+	}
+
+	for (i = 90010; i < 262144; i++) {
+		if (buf[i] != 1)
+			ASSERT_EQ(buf[i], 1, "90Kb+10b-untouched");
+	}
+
+	/* Test a too large grow */
+	memset(buf, 1, 262144);
+	exp_size = 90001;
+
+	topts.data_in = topts.data_out = buf;
+	topts.data_size_in = 90001;
+	topts.data_size_out = 262144;
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+
+	ASSERT_OK(err, "90Kb+10b");
+	ASSERT_EQ(topts.retval, XDP_DROP, "90Kb+10b retval");
+	ASSERT_EQ(topts.data_size_out, exp_size, "90Kb+10b size");
+
+	free(buf);
+out:
+	bpf_object__close(obj);
+}
+
 void test_xdp_adjust_tail(void)
 {
+	int page_size = getpagesize();
+
 	if (test__start_subtest("xdp_adjust_tail_shrink"))
 		test_xdp_adjust_tail_shrink();
 	if (test__start_subtest("xdp_adjust_tail_grow"))
-		test_xdp_adjust_tail_grow();
+		test_xdp_adjust_tail_grow(page_size == 65536);
 	if (test__start_subtest("xdp_adjust_tail_grow2"))
 		test_xdp_adjust_tail_grow2();
 	if (test__start_subtest("xdp_adjust_frags_tail_shrink"))
 		test_xdp_adjust_frags_tail_shrink();
-	if (test__start_subtest("xdp_adjust_frags_tail_grow"))
-		test_xdp_adjust_frags_tail_grow();
+	if (test__start_subtest("xdp_adjust_frags_tail_grow")) {
+		if (page_size == 65536)
+			test_xdp_adjust_frags_tail_grow_64k();
+		else
+			test_xdp_adjust_frags_tail_grow_4k();
+	}
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
index 062fbc8c8e5e..e6bcb6051402 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
@@ -1,14 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include "test_xdp_attach_fail.skel.h"
 
 #define IFINDEX_LO 1
 #define XDP_FLAGS_REPLACE		(1U << 4)
 
-void serial_test_xdp_attach(void)
+static void test_xdp_attach(const char *file)
 {
 	__u32 duration = 0, id1, id2, id0 = 0, len;
 	struct bpf_object *obj1, *obj2, *obj3;
-	const char *file = "./test_xdp.bpf.o";
 	struct bpf_prog_info info = {};
 	int err, fd1, fd2, fd3;
 	LIBBPF_OPTS(bpf_xdp_attach_opts, opts);
@@ -18,7 +18,7 @@ void serial_test_xdp_attach(void)
 	err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj1, &fd1);
 	if (CHECK_FAIL(err))
 		return;
-	err = bpf_obj_get_info_by_fd(fd1, &info, &len);
+	err = bpf_prog_get_info_by_fd(fd1, &info, &len);
 	if (CHECK_FAIL(err))
 		goto out_1;
 	id1 = info.id;
@@ -28,7 +28,7 @@ void serial_test_xdp_attach(void)
 		goto out_1;
 
 	memset(&info, 0, sizeof(info));
-	err = bpf_obj_get_info_by_fd(fd2, &info, &len);
+	err = bpf_prog_get_info_by_fd(fd2, &info, &len);
 	if (CHECK_FAIL(err))
 		goto out_2;
 	id2 = info.id;
@@ -85,3 +85,75 @@ out_2:
 out_1:
 	bpf_object__close(obj1);
 }
+
+#define ERRMSG_LEN 64
+
+struct xdp_errmsg {
+	char msg[ERRMSG_LEN];
+};
+
+static void on_xdp_errmsg(void *ctx, int cpu, void *data, __u32 size)
+{
+	struct xdp_errmsg *ctx_errmg = ctx, *tp_errmsg = data;
+
+	memcpy(&ctx_errmg->msg, &tp_errmsg->msg, ERRMSG_LEN);
+}
+
+static const char tgt_errmsg[] = "Invalid XDP flags for BPF link attachment";
+
+static void test_xdp_attach_fail(const char *file)
+{
+	struct test_xdp_attach_fail *skel = NULL;
+	struct xdp_errmsg errmsg = {};
+	struct perf_buffer *pb = NULL;
+	struct bpf_object *obj = NULL;
+	int err, fd_xdp;
+
+	LIBBPF_OPTS(bpf_link_create_opts, opts);
+
+	skel = test_xdp_attach_fail__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_xdp_attach_fail__open_and_load"))
+		goto out_close;
+
+	err = test_xdp_attach_fail__attach(skel);
+	if (!ASSERT_EQ(err, 0, "test_xdp_attach_fail__attach"))
+		goto out_close;
+
+	/* set up perf buffer */
+	pb = perf_buffer__new(bpf_map__fd(skel->maps.xdp_errmsg_pb), 1,
+			      on_xdp_errmsg, NULL, &errmsg, NULL);
+	if (!ASSERT_OK_PTR(pb, "perf_buffer__new"))
+		goto out_close;
+
+	err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &fd_xdp);
+	if (!ASSERT_EQ(err, 0, "bpf_prog_test_load"))
+		goto out_close;
+
+	opts.flags = 0xFF; // invalid flags to fail to attach XDP prog
+	err = bpf_link_create(fd_xdp, IFINDEX_LO, BPF_XDP, &opts);
+	if (!ASSERT_EQ(err, -EINVAL, "bpf_link_create"))
+		goto out_close;
+
+	/* read perf buffer */
+	err = perf_buffer__poll(pb, 100);
+	if (!ASSERT_GT(err, -1, "perf_buffer__poll"))
+		goto out_close;
+
+	ASSERT_STRNEQ((const char *) errmsg.msg, tgt_errmsg,
+		      42 /* strlen(tgt_errmsg) */, "check error message");
+
+out_close:
+	perf_buffer__free(pb);
+	bpf_object__close(obj);
+	test_xdp_attach_fail__destroy(skel);
+}
+
+void serial_test_xdp_attach(void)
+{
+	if (test__start_subtest("xdp_attach"))
+		test_xdp_attach("./test_xdp.bpf.o");
+	if (test__start_subtest("xdp_attach_dynptr"))
+		test_xdp_attach("./test_xdp_dynptr.bpf.o");
+	if (test__start_subtest("xdp_attach_failed"))
+		test_xdp_attach_fail("./xdp_dummy.bpf.o");
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
index 5e3a26b15ec6..fb952703653e 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
@@ -17,7 +17,8 @@
 #include "network_helpers.h"
 #include <linux/if_bonding.h>
 #include <linux/limits.h>
-#include <linux/udp.h>
+#include <netinet/udp.h>
+#include <uapi/linux/netdev.h>
 
 #include "xdp_dummy.skel.h"
 #include "xdp_redirect_multi_kern.skel.h"
@@ -141,41 +142,33 @@ static const char * const xmit_policy_names[] = {
 static int bonding_setup(struct skeletons *skeletons, int mode, int xmit_policy,
 			 int bond_both_attach)
 {
-#define SYS(fmt, ...)						\
-	({							\
-		char cmd[1024];					\
-		snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__);	\
-		if (!ASSERT_OK(system(cmd), cmd))		\
-			return -1;				\
-	})
-
-	SYS("ip netns add ns_dst");
-	SYS("ip link add veth1_1 type veth peer name veth2_1 netns ns_dst");
-	SYS("ip link add veth1_2 type veth peer name veth2_2 netns ns_dst");
-
-	SYS("ip link add bond1 type bond mode %s xmit_hash_policy %s",
+	SYS(fail, "ip netns add ns_dst");
+	SYS(fail, "ip link add veth1_1 type veth peer name veth2_1 netns ns_dst");
+	SYS(fail, "ip link add veth1_2 type veth peer name veth2_2 netns ns_dst");
+
+	SYS(fail, "ip link add bond1 type bond mode %s xmit_hash_policy %s",
 	    mode_names[mode], xmit_policy_names[xmit_policy]);
-	SYS("ip link set bond1 up address " BOND1_MAC_STR " addrgenmode none");
-	SYS("ip -netns ns_dst link add bond2 type bond mode %s xmit_hash_policy %s",
+	SYS(fail, "ip link set bond1 up address " BOND1_MAC_STR " addrgenmode none");
+	SYS(fail, "ip -netns ns_dst link add bond2 type bond mode %s xmit_hash_policy %s",
 	    mode_names[mode], xmit_policy_names[xmit_policy]);
-	SYS("ip -netns ns_dst link set bond2 up address " BOND2_MAC_STR " addrgenmode none");
+	SYS(fail, "ip -netns ns_dst link set bond2 up address " BOND2_MAC_STR " addrgenmode none");
 
-	SYS("ip link set veth1_1 master bond1");
+	SYS(fail, "ip link set veth1_1 master bond1");
 	if (bond_both_attach == BOND_BOTH_AND_ATTACH) {
-		SYS("ip link set veth1_2 master bond1");
+		SYS(fail, "ip link set veth1_2 master bond1");
 	} else {
-		SYS("ip link set veth1_2 up addrgenmode none");
+		SYS(fail, "ip link set veth1_2 up addrgenmode none");
 
 		if (xdp_attach(skeletons, skeletons->xdp_dummy->progs.xdp_dummy_prog, "veth1_2"))
 			return -1;
 	}
 
-	SYS("ip -netns ns_dst link set veth2_1 master bond2");
+	SYS(fail, "ip -netns ns_dst link set veth2_1 master bond2");
 
 	if (bond_both_attach == BOND_BOTH_AND_ATTACH)
-		SYS("ip -netns ns_dst link set veth2_2 master bond2");
+		SYS(fail, "ip -netns ns_dst link set veth2_2 master bond2");
 	else
-		SYS("ip -netns ns_dst link set veth2_2 up addrgenmode none");
+		SYS(fail, "ip -netns ns_dst link set veth2_2 up addrgenmode none");
 
 	/* Load a dummy program on sending side as with veth peer needs to have a
 	 * XDP program loaded as well.
@@ -194,8 +187,8 @@ static int bonding_setup(struct skeletons *skeletons, int mode, int xmit_policy,
 	}
 
 	return 0;
-
-#undef SYS
+fail:
+	return -1;
 }
 
 static void bonding_cleanup(struct skeletons *skeletons)
@@ -500,6 +493,123 @@ out:
 	system("ip link del bond_nest2");
 }
 
+static void test_xdp_bonding_features(struct skeletons *skeletons)
+{
+	LIBBPF_OPTS(bpf_xdp_query_opts, query_opts);
+	int bond_idx, veth1_idx, err;
+	struct bpf_link *link = NULL;
+
+	if (!ASSERT_OK(system("ip link add bond type bond"), "add bond"))
+		goto out;
+
+	bond_idx = if_nametoindex("bond");
+	if (!ASSERT_GE(bond_idx, 0, "if_nametoindex bond"))
+		goto out;
+
+	/* query default xdp-feature for bond device */
+	err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts);
+	if (!ASSERT_OK(err, "bond bpf_xdp_query"))
+		goto out;
+
+	if (!ASSERT_EQ(query_opts.feature_flags, 0,
+		       "bond query_opts.feature_flags"))
+		goto out;
+
+	if (!ASSERT_OK(system("ip link add veth0 type veth peer name veth1"),
+		       "add veth{0,1} pair"))
+		goto out;
+
+	if (!ASSERT_OK(system("ip link add veth2 type veth peer name veth3"),
+		       "add veth{2,3} pair"))
+		goto out;
+
+	if (!ASSERT_OK(system("ip link set veth0 master bond"),
+		       "add veth0 to master bond"))
+		goto out;
+
+	/* xdp-feature for bond device should be obtained from the single slave
+	 * device (veth0)
+	 */
+	err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts);
+	if (!ASSERT_OK(err, "bond bpf_xdp_query"))
+		goto out;
+
+	if (!ASSERT_EQ(query_opts.feature_flags,
+		       NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+		       NETDEV_XDP_ACT_RX_SG,
+		       "bond query_opts.feature_flags"))
+		goto out;
+
+	veth1_idx = if_nametoindex("veth1");
+	if (!ASSERT_GE(veth1_idx, 0, "if_nametoindex veth1"))
+		goto out;
+
+	link = bpf_program__attach_xdp(skeletons->xdp_dummy->progs.xdp_dummy_prog,
+				       veth1_idx);
+	if (!ASSERT_OK_PTR(link, "attach program to veth1"))
+		goto out;
+
+	/* xdp-feature for veth0 are changed */
+	err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts);
+	if (!ASSERT_OK(err, "bond bpf_xdp_query"))
+		goto out;
+
+	if (!ASSERT_EQ(query_opts.feature_flags,
+		       NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+		       NETDEV_XDP_ACT_RX_SG | NETDEV_XDP_ACT_NDO_XMIT |
+		       NETDEV_XDP_ACT_NDO_XMIT_SG,
+		       "bond query_opts.feature_flags"))
+		goto out;
+
+	if (!ASSERT_OK(system("ip link set veth2 master bond"),
+		       "add veth2 to master bond"))
+		goto out;
+
+	err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts);
+	if (!ASSERT_OK(err, "bond bpf_xdp_query"))
+		goto out;
+
+	/* xdp-feature for bond device should be set to the most restrict
+	 * value obtained from attached slave devices (veth0 and veth2)
+	 */
+	if (!ASSERT_EQ(query_opts.feature_flags,
+		       NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+		       NETDEV_XDP_ACT_RX_SG,
+		       "bond query_opts.feature_flags"))
+		goto out;
+
+	if (!ASSERT_OK(system("ip link set veth2 nomaster"),
+		       "del veth2 to master bond"))
+		goto out;
+
+	err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts);
+	if (!ASSERT_OK(err, "bond bpf_xdp_query"))
+		goto out;
+
+	if (!ASSERT_EQ(query_opts.feature_flags,
+		       NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+		       NETDEV_XDP_ACT_RX_SG | NETDEV_XDP_ACT_NDO_XMIT |
+		       NETDEV_XDP_ACT_NDO_XMIT_SG,
+		       "bond query_opts.feature_flags"))
+		goto out;
+
+	if (!ASSERT_OK(system("ip link set veth0 nomaster"),
+		       "del veth0 to master bond"))
+		goto out;
+
+	err = bpf_xdp_query(bond_idx, XDP_FLAGS_DRV_MODE, &query_opts);
+	if (!ASSERT_OK(err, "bond bpf_xdp_query"))
+		goto out;
+
+	ASSERT_EQ(query_opts.feature_flags, 0,
+		  "bond query_opts.feature_flags");
+out:
+	bpf_link__destroy(link);
+	system("ip link del veth0");
+	system("ip link del veth2");
+	system("ip link del bond");
+}
+
 static int libbpf_debug_print(enum libbpf_print_level level,
 			      const char *format, va_list args)
 {
@@ -554,6 +664,9 @@ void serial_test_xdp_bonding(void)
 	if (test__start_subtest("xdp_bonding_nested"))
 		test_xdp_bonding_nested(&skeletons);
 
+	if (test__start_subtest("xdp_bonding_features"))
+		test_xdp_bonding_features(&skeletons);
+
 	for (i = 0; i < ARRAY_SIZE(bond_test_cases); i++) {
 		struct bond_test_case *test_case = &bond_test_cases[i];
 
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
index ab4952b9fb1d..ee94c281888a 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
@@ -2,6 +2,23 @@
 #include <test_progs.h>
 #include <network_helpers.h>
 #include "test_xdp_context_test_run.skel.h"
+#include "test_xdp_meta.skel.h"
+
+#define RX_NAME "veth0"
+#define TX_NAME "veth1"
+#define TX_NETNS "xdp_context_tx"
+#define RX_NETNS "xdp_context_rx"
+#define TAP_NAME "tap0"
+#define DUMMY_NAME "dum0"
+#define TAP_NETNS "xdp_context_tuntap"
+
+#define TEST_PAYLOAD_LEN 32
+static const __u8 test_payload[TEST_PAYLOAD_LEN] = {
+	0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08,
+	0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18,
+	0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28,
+	0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38,
+};
 
 void test_xdp_context_error(int prog_fd, struct bpf_test_run_opts opts,
 			    __u32 data_meta, __u32 data, __u32 data_end,
@@ -77,12 +94,10 @@ void test_xdp_context_test_run(void)
 	test_xdp_context_error(prog_fd, opts, 4, sizeof(__u32), sizeof(data),
 			       0, 0, 0);
 
-	/* Meta data must be 32 bytes or smaller */
-	test_xdp_context_error(prog_fd, opts, 0, 36, sizeof(data), 0, 0, 0);
+	/* Meta data must be 255 bytes or smaller */
+	test_xdp_context_error(prog_fd, opts, 0, 256, sizeof(data), 0, 0, 0);
 
-	/* Total size of data must match data_end - data_meta */
-	test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32),
-			       sizeof(data) - 1, 0, 0, 0);
+	/* Total size of data must be data_end - data_meta or larger */
 	test_xdp_context_error(prog_fd, opts, 0, sizeof(__u32),
 			       sizeof(data) + 1, 0, 0, 0);
 
@@ -103,3 +118,395 @@ void test_xdp_context_test_run(void)
 
 	test_xdp_context_test_run__destroy(skel);
 }
+
+static int send_test_packet(int ifindex)
+{
+	int n, sock = -1;
+	__u8 packet[sizeof(struct ethhdr) + TEST_PAYLOAD_LEN];
+
+	/* We use the Ethernet header only to identify the test packet */
+	struct ethhdr eth = {
+		.h_source = { 0x12, 0x34, 0xDE, 0xAD, 0xBE, 0xEF },
+	};
+
+	memcpy(packet, &eth, sizeof(eth));
+	memcpy(packet + sizeof(eth), test_payload, TEST_PAYLOAD_LEN);
+
+	sock = socket(AF_PACKET, SOCK_RAW, IPPROTO_RAW);
+	if (!ASSERT_GE(sock, 0, "socket"))
+		goto err;
+
+	struct sockaddr_ll saddr = {
+		.sll_family = PF_PACKET,
+		.sll_ifindex = ifindex,
+		.sll_halen = ETH_ALEN
+	};
+	n = sendto(sock, packet, sizeof(packet), 0, (struct sockaddr *)&saddr,
+		   sizeof(saddr));
+	if (!ASSERT_EQ(n, sizeof(packet), "sendto"))
+		goto err;
+
+	close(sock);
+	return 0;
+
+err:
+	if (sock >= 0)
+		close(sock);
+	return -1;
+}
+
+static int write_test_packet(int tap_fd)
+{
+	__u8 packet[sizeof(struct ethhdr) + TEST_PAYLOAD_LEN];
+	int n;
+
+	/* The Ethernet header is mostly not relevant. We use it to identify the
+	 * test packet and some BPF helpers we exercise expect to operate on
+	 * Ethernet frames carrying IP packets. Pretend that's the case.
+	 */
+	struct ethhdr eth = {
+		.h_source = { 0x12, 0x34, 0xDE, 0xAD, 0xBE, 0xEF },
+		.h_proto = htons(ETH_P_IP),
+	};
+
+	memcpy(packet, &eth, sizeof(eth));
+	memcpy(packet + sizeof(struct ethhdr), test_payload, TEST_PAYLOAD_LEN);
+
+	n = write(tap_fd, packet, sizeof(packet));
+	if (!ASSERT_EQ(n, sizeof(packet), "write packet"))
+		return -1;
+
+	return 0;
+}
+
+static void dump_err_stream(const struct bpf_program *prog)
+{
+	char buf[512];
+	int ret;
+
+	ret = 0;
+	do {
+		ret = bpf_prog_stream_read(bpf_program__fd(prog),
+					   BPF_STREAM_STDERR, buf, sizeof(buf),
+					   NULL);
+		if (ret > 0)
+			fwrite(buf, sizeof(buf[0]), ret, stderr);
+	} while (ret > 0);
+}
+
+void test_xdp_context_veth(void)
+{
+	LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS);
+	LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+	struct netns_obj *rx_ns = NULL, *tx_ns = NULL;
+	struct bpf_program *tc_prog, *xdp_prog;
+	struct test_xdp_meta *skel = NULL;
+	struct nstoken *nstoken = NULL;
+	int rx_ifindex, tx_ifindex;
+	int ret;
+
+	tx_ns = netns_new(TX_NETNS, false);
+	if (!ASSERT_OK_PTR(tx_ns, "create tx_ns"))
+		return;
+
+	rx_ns = netns_new(RX_NETNS, false);
+	if (!ASSERT_OK_PTR(rx_ns, "create rx_ns"))
+		goto close;
+
+	SYS(close, "ip link add " RX_NAME " netns " RX_NETNS
+	    " type veth peer name " TX_NAME " netns " TX_NETNS);
+
+	nstoken = open_netns(RX_NETNS);
+	if (!ASSERT_OK_PTR(nstoken, "setns rx_ns"))
+		goto close;
+
+	SYS(close, "ip link set dev " RX_NAME " up");
+
+	skel = test_xdp_meta__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open and load skeleton"))
+		goto close;
+
+	rx_ifindex = if_nametoindex(RX_NAME);
+	if (!ASSERT_GE(rx_ifindex, 0, "if_nametoindex rx"))
+		goto close;
+
+	tc_hook.ifindex = rx_ifindex;
+	ret = bpf_tc_hook_create(&tc_hook);
+	if (!ASSERT_OK(ret, "bpf_tc_hook_create"))
+		goto close;
+
+	tc_prog = bpf_object__find_program_by_name(skel->obj, "ing_cls");
+	if (!ASSERT_OK_PTR(tc_prog, "open ing_cls prog"))
+		goto close;
+
+	tc_opts.prog_fd = bpf_program__fd(tc_prog);
+	ret = bpf_tc_attach(&tc_hook, &tc_opts);
+	if (!ASSERT_OK(ret, "bpf_tc_attach"))
+		goto close;
+
+	xdp_prog = bpf_object__find_program_by_name(skel->obj, "ing_xdp");
+	if (!ASSERT_OK_PTR(xdp_prog, "open ing_xdp prog"))
+		goto close;
+
+	ret = bpf_xdp_attach(rx_ifindex,
+			     bpf_program__fd(xdp_prog),
+			     0, NULL);
+	if (!ASSERT_GE(ret, 0, "bpf_xdp_attach"))
+		goto close;
+
+	close_netns(nstoken);
+
+	nstoken = open_netns(TX_NETNS);
+	if (!ASSERT_OK_PTR(nstoken, "setns tx_ns"))
+		goto close;
+
+	SYS(close, "ip link set dev " TX_NAME " up");
+
+	tx_ifindex = if_nametoindex(TX_NAME);
+	if (!ASSERT_GE(tx_ifindex, 0, "if_nametoindex tx"))
+		goto close;
+
+	skel->bss->test_pass = false;
+
+	ret = send_test_packet(tx_ifindex);
+	if (!ASSERT_OK(ret, "send_test_packet"))
+		goto close;
+
+	if (!ASSERT_TRUE(skel->bss->test_pass, "test_pass"))
+		dump_err_stream(tc_prog);
+
+close:
+	close_netns(nstoken);
+	test_xdp_meta__destroy(skel);
+	netns_free(rx_ns);
+	netns_free(tx_ns);
+}
+
+static void test_tuntap(struct bpf_program *xdp_prog,
+			struct bpf_program *tc_prio_1_prog,
+			struct bpf_program *tc_prio_2_prog,
+			bool *test_pass)
+{
+	LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS);
+	LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+	struct netns_obj *ns = NULL;
+	int tap_fd = -1;
+	int tap_ifindex;
+	int ret;
+
+	*test_pass = false;
+
+	ns = netns_new(TAP_NETNS, true);
+	if (!ASSERT_OK_PTR(ns, "create and open ns"))
+		return;
+
+	tap_fd = open_tuntap(TAP_NAME, true);
+	if (!ASSERT_GE(tap_fd, 0, "open_tuntap"))
+		goto close;
+
+	SYS(close, "ip link set dev " TAP_NAME " up");
+
+	tap_ifindex = if_nametoindex(TAP_NAME);
+	if (!ASSERT_GE(tap_ifindex, 0, "if_nametoindex"))
+		goto close;
+
+	tc_hook.ifindex = tap_ifindex;
+	ret = bpf_tc_hook_create(&tc_hook);
+	if (!ASSERT_OK(ret, "bpf_tc_hook_create"))
+		goto close;
+
+	tc_opts.prog_fd = bpf_program__fd(tc_prio_1_prog);
+	ret = bpf_tc_attach(&tc_hook, &tc_opts);
+	if (!ASSERT_OK(ret, "bpf_tc_attach"))
+		goto close;
+
+	if (tc_prio_2_prog) {
+		LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 2,
+			    .prog_fd = bpf_program__fd(tc_prio_2_prog));
+
+		ret = bpf_tc_attach(&tc_hook, &tc_opts);
+		if (!ASSERT_OK(ret, "bpf_tc_attach"))
+			goto close;
+	}
+
+	ret = bpf_xdp_attach(tap_ifindex, bpf_program__fd(xdp_prog),
+			     0, NULL);
+	if (!ASSERT_GE(ret, 0, "bpf_xdp_attach"))
+		goto close;
+
+	ret = write_test_packet(tap_fd);
+	if (!ASSERT_OK(ret, "write_test_packet"))
+		goto close;
+
+	if (!ASSERT_TRUE(*test_pass, "test_pass"))
+		dump_err_stream(tc_prio_2_prog ? : tc_prio_1_prog);
+
+close:
+	if (tap_fd >= 0)
+		close(tap_fd);
+	netns_free(ns);
+}
+
+/* Write a packet to a tap dev and copy it to ingress of a dummy dev */
+static void test_tuntap_mirred(struct bpf_program *xdp_prog,
+			       struct bpf_program *tc_prog,
+			       bool *test_pass)
+{
+	LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS);
+	LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+	struct netns_obj *ns = NULL;
+	int dummy_ifindex;
+	int tap_fd = -1;
+	int tap_ifindex;
+	int ret;
+
+	*test_pass = false;
+
+	ns = netns_new(TAP_NETNS, true);
+	if (!ASSERT_OK_PTR(ns, "netns_new"))
+		return;
+
+	/* Setup dummy interface */
+	SYS(close, "ip link add name " DUMMY_NAME " type dummy");
+	SYS(close, "ip link set dev " DUMMY_NAME " up");
+
+	dummy_ifindex = if_nametoindex(DUMMY_NAME);
+	if (!ASSERT_GE(dummy_ifindex, 0, "if_nametoindex"))
+		goto close;
+
+	tc_hook.ifindex = dummy_ifindex;
+	ret = bpf_tc_hook_create(&tc_hook);
+	if (!ASSERT_OK(ret, "bpf_tc_hook_create"))
+		goto close;
+
+	tc_opts.prog_fd = bpf_program__fd(tc_prog);
+	ret = bpf_tc_attach(&tc_hook, &tc_opts);
+	if (!ASSERT_OK(ret, "bpf_tc_attach"))
+		goto close;
+
+	/* Setup TAP interface */
+	tap_fd = open_tuntap(TAP_NAME, true);
+	if (!ASSERT_GE(tap_fd, 0, "open_tuntap"))
+		goto close;
+
+	SYS(close, "ip link set dev " TAP_NAME " up");
+
+	tap_ifindex = if_nametoindex(TAP_NAME);
+	if (!ASSERT_GE(tap_ifindex, 0, "if_nametoindex"))
+		goto close;
+
+	ret = bpf_xdp_attach(tap_ifindex, bpf_program__fd(xdp_prog), 0, NULL);
+	if (!ASSERT_GE(ret, 0, "bpf_xdp_attach"))
+		goto close;
+
+	/* Copy all packets received from TAP to dummy ingress */
+	SYS(close, "tc qdisc add dev " TAP_NAME " clsact");
+	SYS(close, "tc filter add dev " TAP_NAME " ingress "
+		   "protocol all matchall "
+		   "action mirred ingress mirror dev " DUMMY_NAME);
+
+	/* Receive a packet on TAP */
+	ret = write_test_packet(tap_fd);
+	if (!ASSERT_OK(ret, "write_test_packet"))
+		goto close;
+
+	if (!ASSERT_TRUE(*test_pass, "test_pass"))
+		dump_err_stream(tc_prog);
+
+close:
+	if (tap_fd >= 0)
+		close(tap_fd);
+	netns_free(ns);
+}
+
+void test_xdp_context_tuntap(void)
+{
+	struct test_xdp_meta *skel = NULL;
+
+	skel = test_xdp_meta__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open and load skeleton"))
+		return;
+
+	if (test__start_subtest("data_meta"))
+		test_tuntap(skel->progs.ing_xdp,
+			    skel->progs.ing_cls,
+			    NULL, /* tc prio 2 */
+			    &skel->bss->test_pass);
+	if (test__start_subtest("dynptr_read"))
+		test_tuntap(skel->progs.ing_xdp,
+			    skel->progs.ing_cls_dynptr_read,
+			    NULL, /* tc prio 2 */
+			    &skel->bss->test_pass);
+	if (test__start_subtest("dynptr_slice"))
+		test_tuntap(skel->progs.ing_xdp,
+			    skel->progs.ing_cls_dynptr_slice,
+			    NULL, /* tc prio 2 */
+			    &skel->bss->test_pass);
+	if (test__start_subtest("dynptr_write"))
+		test_tuntap(skel->progs.ing_xdp_zalloc_meta,
+			    skel->progs.ing_cls_dynptr_write,
+			    skel->progs.ing_cls_dynptr_read,
+			    &skel->bss->test_pass);
+	if (test__start_subtest("dynptr_slice_rdwr"))
+		test_tuntap(skel->progs.ing_xdp_zalloc_meta,
+			    skel->progs.ing_cls_dynptr_slice_rdwr,
+			    skel->progs.ing_cls_dynptr_slice,
+			    &skel->bss->test_pass);
+	if (test__start_subtest("dynptr_offset"))
+		test_tuntap(skel->progs.ing_xdp_zalloc_meta,
+			    skel->progs.ing_cls_dynptr_offset_wr,
+			    skel->progs.ing_cls_dynptr_offset_rd,
+			    &skel->bss->test_pass);
+	if (test__start_subtest("dynptr_offset_oob"))
+		test_tuntap(skel->progs.ing_xdp,
+			    skel->progs.ing_cls_dynptr_offset_oob,
+			    skel->progs.ing_cls,
+			    &skel->bss->test_pass);
+	if (test__start_subtest("clone_data_meta_survives_data_write"))
+		test_tuntap_mirred(skel->progs.ing_xdp,
+				   skel->progs.clone_data_meta_survives_data_write,
+				   &skel->bss->test_pass);
+	if (test__start_subtest("clone_data_meta_survives_meta_write"))
+		test_tuntap_mirred(skel->progs.ing_xdp,
+				   skel->progs.clone_data_meta_survives_meta_write,
+				   &skel->bss->test_pass);
+	if (test__start_subtest("clone_meta_dynptr_survives_data_slice_write"))
+		test_tuntap_mirred(skel->progs.ing_xdp,
+				   skel->progs.clone_meta_dynptr_survives_data_slice_write,
+				   &skel->bss->test_pass);
+	if (test__start_subtest("clone_meta_dynptr_survives_meta_slice_write"))
+		test_tuntap_mirred(skel->progs.ing_xdp,
+				   skel->progs.clone_meta_dynptr_survives_meta_slice_write,
+				   &skel->bss->test_pass);
+	if (test__start_subtest("clone_meta_dynptr_rw_before_data_dynptr_write"))
+		test_tuntap_mirred(skel->progs.ing_xdp,
+				   skel->progs.clone_meta_dynptr_rw_before_data_dynptr_write,
+				   &skel->bss->test_pass);
+	if (test__start_subtest("clone_meta_dynptr_rw_before_meta_dynptr_write"))
+		test_tuntap_mirred(skel->progs.ing_xdp,
+				   skel->progs.clone_meta_dynptr_rw_before_meta_dynptr_write,
+				   &skel->bss->test_pass);
+	/* Tests for BPF helpers which touch headroom */
+	if (test__start_subtest("helper_skb_vlan_push_pop"))
+		test_tuntap(skel->progs.ing_xdp,
+			    skel->progs.helper_skb_vlan_push_pop,
+			    NULL, /* tc prio 2 */
+			    &skel->bss->test_pass);
+	if (test__start_subtest("helper_skb_adjust_room"))
+		test_tuntap(skel->progs.ing_xdp,
+			    skel->progs.helper_skb_adjust_room,
+			    NULL, /* tc prio 2 */
+			    &skel->bss->test_pass);
+	if (test__start_subtest("helper_skb_change_head_tail"))
+		test_tuntap(skel->progs.ing_xdp,
+			    skel->progs.helper_skb_change_head_tail,
+			    NULL, /* tc prio 2 */
+			    &skel->bss->test_pass);
+	if (test__start_subtest("helper_skb_change_proto"))
+		test_tuntap(skel->progs.ing_xdp,
+			    skel->progs.helper_skb_change_proto,
+			    NULL, /* tc prio 2 */
+			    &skel->bss->test_pass);
+
+	test_xdp_meta__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
index f775a1613833..df27535995af 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
@@ -2,39 +2,45 @@
 #include <uapi/linux/bpf.h>
 #include <linux/if_link.h>
 #include <test_progs.h>
+#include <network_helpers.h>
 
 #include "test_xdp_with_cpumap_frags_helpers.skel.h"
 #include "test_xdp_with_cpumap_helpers.skel.h"
 
 #define IFINDEX_LO	1
+#define TEST_NS "cpu_attach_ns"
 
 static void test_xdp_with_cpumap_helpers(void)
 {
-	struct test_xdp_with_cpumap_helpers *skel;
+	struct test_xdp_with_cpumap_helpers *skel = NULL;
 	struct bpf_prog_info info = {};
 	__u32 len = sizeof(info);
 	struct bpf_cpumap_val val = {
 		.qsize = 192,
 	};
-	int err, prog_fd, map_fd;
+	int err, prog_fd, prog_redir_fd, map_fd;
+	struct nstoken *nstoken = NULL;
 	__u32 idx = 0;
 
+	SYS(out_close, "ip netns add %s", TEST_NS);
+	nstoken = open_netns(TEST_NS);
+	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+		goto out_close;
+	SYS(out_close, "ip link set dev lo up");
+
 	skel = test_xdp_with_cpumap_helpers__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "test_xdp_with_cpumap_helpers__open_and_load"))
 		return;
 
-	prog_fd = bpf_program__fd(skel->progs.xdp_redir_prog);
-	err = bpf_xdp_attach(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE, NULL);
+	prog_redir_fd = bpf_program__fd(skel->progs.xdp_redir_prog);
+	err = bpf_xdp_attach(IFINDEX_LO, prog_redir_fd, XDP_FLAGS_SKB_MODE, NULL);
 	if (!ASSERT_OK(err, "Generic attach of program with 8-byte CPUMAP"))
 		goto out_close;
 
-	err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL);
-	ASSERT_OK(err, "XDP program detach");
-
 	prog_fd = bpf_program__fd(skel->progs.xdp_dummy_cm);
 	map_fd = bpf_map__fd(skel->maps.cpu_map);
-	err = bpf_obj_get_info_by_fd(prog_fd, &info, &len);
-	if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd"))
+	err = bpf_prog_get_info_by_fd(prog_fd, &info, &len);
+	if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd"))
 		goto out_close;
 
 	val.bpf_prog.fd = prog_fd;
@@ -45,6 +51,26 @@ static void test_xdp_with_cpumap_helpers(void)
 	ASSERT_OK(err, "Read cpumap entry");
 	ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to cpumap entry prog_id");
 
+	/* send a packet to trigger any potential bugs in there */
+	char data[ETH_HLEN] = {};
+	DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
+			    .data_in = &data,
+			    .data_size_in = sizeof(data),
+			    .flags = BPF_F_TEST_XDP_LIVE_FRAMES,
+			    .repeat = 1,
+		);
+	err = bpf_prog_test_run_opts(prog_redir_fd, &opts);
+	ASSERT_OK(err, "XDP test run");
+
+	/* wait for the packets to be flushed, then check that redirect has been
+	 * performed
+	 */
+	kern_sync_rcu();
+	ASSERT_NEQ(skel->bss->redirect_count, 0, "redirected packets");
+
+	err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL);
+	ASSERT_OK(err, "XDP program detach");
+
 	/* can not attach BPF_XDP_CPUMAP program to a device */
 	err = bpf_xdp_attach(IFINDEX_LO, prog_fd, XDP_FLAGS_SKB_MODE, NULL);
 	if (!ASSERT_NEQ(err, 0, "Attach of BPF_XDP_CPUMAP program"))
@@ -65,6 +91,8 @@ static void test_xdp_with_cpumap_helpers(void)
 	ASSERT_NEQ(err, 0, "Add BPF_XDP program with frags to cpumap entry");
 
 out_close:
+	close_netns(nstoken);
+	SYS_NOFAIL("ip netns del %s", TEST_NS);
 	test_xdp_with_cpumap_helpers__destroy(skel);
 }
 
@@ -85,8 +113,8 @@ static void test_xdp_with_cpumap_frags_helpers(void)
 
 	frags_prog_fd = bpf_program__fd(skel->progs.xdp_dummy_cm_frags);
 	map_fd = bpf_map__fd(skel->maps.cpu_map);
-	err = bpf_obj_get_info_by_fd(frags_prog_fd, &info, &len);
-	if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd"))
+	err = bpf_prog_get_info_by_fd(frags_prog_fd, &info, &len);
+	if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd"))
 		goto out_close;
 
 	val.bpf_prog.fd = frags_prog_fd;
@@ -111,7 +139,7 @@ out_close:
 	test_xdp_with_cpumap_frags_helpers__destroy(skel);
 }
 
-void serial_test_xdp_cpumap_attach(void)
+void test_xdp_cpumap_attach(void)
 {
 	if (test__start_subtest("CPUMAP with programs in entries"))
 		test_xdp_with_cpumap_helpers();
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_dev_bound_only.c b/tools/testing/selftests/bpf/prog_tests/xdp_dev_bound_only.c
new file mode 100644
index 000000000000..7dd18c6d06c6
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_dev_bound_only.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <net/if.h>
+#include <test_progs.h>
+#include <network_helpers.h>
+
+#define LOCAL_NETNS "xdp_dev_bound_only_netns"
+
+static int load_dummy_prog(char *name, __u32 ifindex, __u32 flags)
+{
+	struct bpf_insn insns[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN() };
+	LIBBPF_OPTS(bpf_prog_load_opts, opts);
+
+	opts.prog_flags = flags;
+	opts.prog_ifindex = ifindex;
+	return bpf_prog_load(BPF_PROG_TYPE_XDP, name, "GPL", insns, ARRAY_SIZE(insns), &opts);
+}
+
+/* A test case for bpf_offload_netdev->offload handling bug:
+ * - create a veth device (does not support offload);
+ * - create a device bound XDP program with BPF_F_XDP_DEV_BOUND_ONLY flag
+ *   (such programs are not offloaded);
+ * - create a device bound XDP program without flags (such programs are offloaded).
+ * This might lead to 'BUG: kernel NULL pointer dereference'.
+ */
+void test_xdp_dev_bound_only_offdev(void)
+{
+	struct nstoken *tok = NULL;
+	__u32 ifindex;
+	int fd1 = -1;
+	int fd2 = -1;
+
+	SYS(out, "ip netns add " LOCAL_NETNS);
+	tok = open_netns(LOCAL_NETNS);
+	if (!ASSERT_OK_PTR(tok, "open_netns"))
+		goto out;
+	SYS(out, "ip link add eth42 type veth");
+	ifindex = if_nametoindex("eth42");
+	if (!ASSERT_NEQ(ifindex, 0, "if_nametoindex")) {
+		perror("if_nametoindex");
+		goto out;
+	}
+	fd1 = load_dummy_prog("dummy1", ifindex, BPF_F_XDP_DEV_BOUND_ONLY);
+	if (!ASSERT_GE(fd1, 0, "load_dummy_prog #1")) {
+		perror("load_dummy_prog #1");
+		goto out;
+	}
+	/* Program with ifindex is considered offloaded, however veth
+	 * does not support offload => error should be reported.
+	 */
+	fd2 = load_dummy_prog("dummy2", ifindex, 0);
+	ASSERT_EQ(fd2, -EINVAL, "load_dummy_prog #2 (offloaded)");
+
+out:
+	close(fd1);
+	close(fd2);
+	close_netns(tok);
+	/* eth42 was added inside netns, removing the netns will
+	 * also remove eth42 veth pair.
+	 */
+	SYS_NOFAIL("ip netns del " LOCAL_NETNS);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
index ead40016c324..a8ab05216c38 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
@@ -1,42 +1,51 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <arpa/inet.h>
 #include <uapi/linux/bpf.h>
 #include <linux/if_link.h>
+#include <network_helpers.h>
+#include <net/if.h>
 #include <test_progs.h>
 
 #include "test_xdp_devmap_helpers.skel.h"
+#include "test_xdp_devmap_tailcall.skel.h"
 #include "test_xdp_with_devmap_frags_helpers.skel.h"
 #include "test_xdp_with_devmap_helpers.skel.h"
 
 #define IFINDEX_LO 1
+#define TEST_NS "devmap_attach_ns"
 
 static void test_xdp_with_devmap_helpers(void)
 {
-	struct test_xdp_with_devmap_helpers *skel;
+	struct test_xdp_with_devmap_helpers *skel = NULL;
 	struct bpf_prog_info info = {};
 	struct bpf_devmap_val val = {
 		.ifindex = IFINDEX_LO,
 	};
 	__u32 len = sizeof(info);
-	int err, dm_fd, map_fd;
+	int err, dm_fd, dm_fd_redir, map_fd;
+	struct nstoken *nstoken = NULL;
+	char data[ETH_HLEN] = {};
 	__u32 idx = 0;
 
+	SYS(out_close, "ip netns add %s", TEST_NS);
+	nstoken = open_netns(TEST_NS);
+	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+		goto out_close;
+	SYS(out_close, "ip link set dev lo up");
 
 	skel = test_xdp_with_devmap_helpers__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "test_xdp_with_devmap_helpers__open_and_load"))
-		return;
+		goto out_close;
 
-	dm_fd = bpf_program__fd(skel->progs.xdp_redir_prog);
-	err = bpf_xdp_attach(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE, NULL);
+	dm_fd_redir = bpf_program__fd(skel->progs.xdp_redir_prog);
+	err = bpf_xdp_attach(IFINDEX_LO, dm_fd_redir, XDP_FLAGS_SKB_MODE, NULL);
 	if (!ASSERT_OK(err, "Generic attach of program with 8-byte devmap"))
 		goto out_close;
 
-	err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL);
-	ASSERT_OK(err, "XDP program detach");
-
 	dm_fd = bpf_program__fd(skel->progs.xdp_dummy_dm);
 	map_fd = bpf_map__fd(skel->maps.dm_ports);
-	err = bpf_obj_get_info_by_fd(dm_fd, &info, &len);
-	if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd"))
+	err = bpf_prog_get_info_by_fd(dm_fd, &info, &len);
+	if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd"))
 		goto out_close;
 
 	val.bpf_prog.fd = dm_fd;
@@ -47,6 +56,22 @@ static void test_xdp_with_devmap_helpers(void)
 	ASSERT_OK(err, "Read devmap entry");
 	ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to devmap entry prog_id");
 
+	/* send a packet to trigger any potential bugs in there */
+	DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
+			    .data_in = &data,
+			    .data_size_in = sizeof(data),
+			    .flags = BPF_F_TEST_XDP_LIVE_FRAMES,
+			    .repeat = 1,
+		);
+	err = bpf_prog_test_run_opts(dm_fd_redir, &opts);
+	ASSERT_OK(err, "XDP test run");
+
+	/* wait for the packets to be flushed */
+	kern_sync_rcu();
+
+	err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL);
+	ASSERT_OK(err, "XDP program detach");
+
 	/* can not attach BPF_XDP_DEVMAP program to a device */
 	err = bpf_xdp_attach(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE, NULL);
 	if (!ASSERT_NEQ(err, 0, "Attach of BPF_XDP_DEVMAP program"))
@@ -67,6 +92,8 @@ static void test_xdp_with_devmap_helpers(void)
 	ASSERT_NEQ(err, 0, "Add BPF_XDP program with frags to devmap entry");
 
 out_close:
+	close_netns(nstoken);
+	SYS_NOFAIL("ip netns del %s", TEST_NS);
 	test_xdp_with_devmap_helpers__destroy(skel);
 }
 
@@ -81,6 +108,29 @@ static void test_neg_xdp_devmap_helpers(void)
 	}
 }
 
+static void test_xdp_devmap_tailcall(enum bpf_attach_type prog_dev,
+				     enum bpf_attach_type prog_tail,
+				     bool expect_reject)
+{
+	struct test_xdp_devmap_tailcall *skel;
+	int err;
+
+	skel = test_xdp_devmap_tailcall__open();
+	if (!ASSERT_OK_PTR(skel, "test_xdp_devmap_tailcall__open"))
+		return;
+
+	bpf_program__set_expected_attach_type(skel->progs.xdp_devmap, prog_dev);
+	bpf_program__set_expected_attach_type(skel->progs.xdp_entry, prog_tail);
+
+	err = test_xdp_devmap_tailcall__load(skel);
+	if (expect_reject)
+		ASSERT_ERR(err, "test_xdp_devmap_tailcall__load");
+	else
+		ASSERT_OK(err, "test_xdp_devmap_tailcall__load");
+
+	test_xdp_devmap_tailcall__destroy(skel);
+}
+
 static void test_xdp_with_devmap_frags_helpers(void)
 {
 	struct test_xdp_with_devmap_frags_helpers *skel;
@@ -98,8 +148,8 @@ static void test_xdp_with_devmap_frags_helpers(void)
 
 	dm_fd_frags = bpf_program__fd(skel->progs.xdp_dummy_dm_frags);
 	map_fd = bpf_map__fd(skel->maps.dm_ports);
-	err = bpf_obj_get_info_by_fd(dm_fd_frags, &info, &len);
-	if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd"))
+	err = bpf_prog_get_info_by_fd(dm_fd_frags, &info, &len);
+	if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd"))
 		goto out_close;
 
 	val.bpf_prog.fd = dm_fd_frags;
@@ -124,6 +174,86 @@ out_close:
 	test_xdp_with_devmap_frags_helpers__destroy(skel);
 }
 
+static void test_xdp_with_devmap_helpers_veth(void)
+{
+	struct test_xdp_with_devmap_helpers *skel = NULL;
+	struct bpf_prog_info info = {};
+	struct bpf_devmap_val val = {};
+	struct nstoken *nstoken = NULL;
+	__u32 len = sizeof(info);
+	int err, dm_fd, dm_fd_redir, map_fd, ifindex_dst;
+	char data[ETH_HLEN] = {};
+	__u32 idx = 0;
+
+	SYS(out_close, "ip netns add %s", TEST_NS);
+	nstoken = open_netns(TEST_NS);
+	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+		goto out_close;
+
+	SYS(out_close, "ip link add veth_src type veth peer name veth_dst");
+	SYS(out_close, "ip link set dev veth_src up");
+	SYS(out_close, "ip link set dev veth_dst up");
+
+	val.ifindex = if_nametoindex("veth_src");
+	ifindex_dst = if_nametoindex("veth_dst");
+	if (!ASSERT_NEQ(val.ifindex, 0, "val.ifindex") ||
+	    !ASSERT_NEQ(ifindex_dst, 0, "ifindex_dst"))
+		goto out_close;
+
+	skel = test_xdp_with_devmap_helpers__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_xdp_with_devmap_helpers__open_and_load"))
+		goto out_close;
+
+	dm_fd_redir = bpf_program__fd(skel->progs.xdp_redir_prog);
+	err = bpf_xdp_attach(val.ifindex, dm_fd_redir, XDP_FLAGS_DRV_MODE, NULL);
+	if (!ASSERT_OK(err, "Attach of program with 8-byte devmap"))
+		goto out_close;
+
+	dm_fd = bpf_program__fd(skel->progs.xdp_dummy_dm);
+	map_fd = bpf_map__fd(skel->maps.dm_ports);
+	err = bpf_prog_get_info_by_fd(dm_fd, &info, &len);
+	if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd"))
+		goto out_close;
+
+	val.bpf_prog.fd = dm_fd;
+	err = bpf_map_update_elem(map_fd, &idx, &val, 0);
+	ASSERT_OK(err, "Add program to devmap entry");
+
+	err = bpf_map_lookup_elem(map_fd, &idx, &val);
+	ASSERT_OK(err, "Read devmap entry");
+	ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to devmap entry prog_id");
+
+	/* attach dummy to other side to enable reception */
+	dm_fd = bpf_program__fd(skel->progs.xdp_dummy_prog);
+	err = bpf_xdp_attach(ifindex_dst, dm_fd, XDP_FLAGS_DRV_MODE, NULL);
+	if (!ASSERT_OK(err, "Attach of dummy XDP"))
+		goto out_close;
+
+	/* send a packet to trigger any potential bugs in there */
+	DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
+			    .data_in = &data,
+			    .data_size_in = sizeof(data),
+			    .flags = BPF_F_TEST_XDP_LIVE_FRAMES,
+			    .repeat = 1,
+		);
+	err = bpf_prog_test_run_opts(dm_fd_redir, &opts);
+	ASSERT_OK(err, "XDP test run");
+
+	/* wait for the packets to be flushed */
+	kern_sync_rcu();
+
+	err = bpf_xdp_detach(val.ifindex, XDP_FLAGS_DRV_MODE, NULL);
+	ASSERT_OK(err, "XDP program detach");
+
+	err = bpf_xdp_detach(ifindex_dst, XDP_FLAGS_DRV_MODE, NULL);
+	ASSERT_OK(err, "XDP program detach");
+
+out_close:
+	close_netns(nstoken);
+	SYS_NOFAIL("ip netns del %s", TEST_NS);
+	test_xdp_with_devmap_helpers__destroy(skel);
+}
+
 void serial_test_xdp_devmap_attach(void)
 {
 	if (test__start_subtest("DEVMAP with programs in entries"))
@@ -132,6 +262,14 @@ void serial_test_xdp_devmap_attach(void)
 	if (test__start_subtest("DEVMAP with frags programs in entries"))
 		test_xdp_with_devmap_frags_helpers();
 
-	if (test__start_subtest("Verifier check of DEVMAP programs"))
+	if (test__start_subtest("Verifier check of DEVMAP programs")) {
 		test_neg_xdp_devmap_helpers();
+		test_xdp_devmap_tailcall(BPF_XDP_DEVMAP, BPF_XDP_DEVMAP, false);
+		test_xdp_devmap_tailcall(0, 0, true);
+		test_xdp_devmap_tailcall(BPF_XDP_DEVMAP, 0, true);
+		test_xdp_devmap_tailcall(0, BPF_XDP_DEVMAP, true);
+	}
+
+	if (test__start_subtest("DEVMAP with programs in entries on veth"))
+		test_xdp_with_devmap_helpers_veth();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
index a50971c6cf4a..dd34b0cc4b4e 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
@@ -4,19 +4,14 @@
 #include <net/if.h>
 #include <linux/if_ether.h>
 #include <linux/if_packet.h>
+#include <linux/if_link.h>
 #include <linux/ipv6.h>
 #include <linux/in6.h>
-#include <linux/udp.h>
+#include <netinet/udp.h>
 #include <bpf/bpf_endian.h>
+#include <uapi/linux/netdev.h>
 #include "test_xdp_do_redirect.skel.h"
-
-#define SYS(fmt, ...)						\
-	({							\
-		char cmd[1024];					\
-		snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__);	\
-		if (!ASSERT_OK(system(cmd), cmd))		\
-			goto out;				\
-	})
+#include "xdp_dummy.skel.h"
 
 struct udp_packet {
 	struct ethhdr eth;
@@ -63,19 +58,33 @@ static int attach_tc_prog(struct bpf_tc_hook *hook, int fd)
 }
 
 /* The maximum permissible size is: PAGE_SIZE - sizeof(struct xdp_page_head) -
- * sizeof(struct skb_shared_info) - XDP_PACKET_HEADROOM = 3368 bytes
+ * SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) - XDP_PACKET_HEADROOM =
+ * 3408 bytes for 64-byte cacheline and 3216 for 256-byte one.
  */
-#define MAX_PKT_SIZE 3368
+#if defined(__s390x__)
+#define MAX_PKT_SIZE 3216
+#else
+#define MAX_PKT_SIZE 3408
+#endif
+
+#define PAGE_SIZE_4K  4096
+#define PAGE_SIZE_64K 65536
+
 static void test_max_pkt_size(int fd)
 {
-	char data[MAX_PKT_SIZE + 1] = {};
+	char data[PAGE_SIZE_64K + 1] = {};
 	int err;
 	DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
 			    .data_in = &data,
-			    .data_size_in = MAX_PKT_SIZE,
 			    .flags = BPF_F_TEST_XDP_LIVE_FRAMES,
 			    .repeat = 1,
 		);
+
+	if (getpagesize() == PAGE_SIZE_64K)
+		opts.data_size_in = MAX_PKT_SIZE + PAGE_SIZE_64K - PAGE_SIZE_4K;
+	else
+		opts.data_size_in = MAX_PKT_SIZE;
+
 	err = bpf_prog_test_run_opts(fd, &opts);
 	ASSERT_OK(err, "prog_run_max_size");
 
@@ -88,12 +97,12 @@ static void test_max_pkt_size(int fd)
 void test_xdp_do_redirect(void)
 {
 	int err, xdp_prog_fd, tc_prog_fd, ifindex_src, ifindex_dst;
-	char data[sizeof(pkt_udp) + sizeof(__u32)];
+	char data[sizeof(pkt_udp) + sizeof(__u64)];
 	struct test_xdp_do_redirect *skel = NULL;
 	struct nstoken *nstoken = NULL;
 	struct bpf_link *link;
-
-	struct xdp_md ctx_in = { .data = sizeof(__u32),
+	LIBBPF_OPTS(bpf_xdp_query_opts, query_opts);
+	struct xdp_md ctx_in = { .data = sizeof(__u64),
 				 .data_end = sizeof(data) };
 	DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
 			    .data_in = &data,
@@ -107,8 +116,9 @@ void test_xdp_do_redirect(void)
 	DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook,
 			    .attach_point = BPF_TC_INGRESS);
 
-	memcpy(&data[sizeof(__u32)], &pkt_udp, sizeof(pkt_udp));
-	*((__u32 *)data) = 0x42; /* metadata test value */
+	memcpy(&data[sizeof(__u64)], &pkt_udp, sizeof(pkt_udp));
+	((__u32 *)data)[0] = 0x42; /* metadata test value */
+	((__u32 *)data)[1] = 0;
 
 	skel = test_xdp_do_redirect__open();
 	if (!ASSERT_OK_PTR(skel, "skel"))
@@ -120,19 +130,19 @@ void test_xdp_do_redirect(void)
 	 * iface and NUM_PKTS-2 in the TC hook. We match the packets on the UDP
 	 * payload.
 	 */
-	SYS("ip netns add testns");
+	SYS(out, "ip netns add testns");
 	nstoken = open_netns("testns");
 	if (!ASSERT_OK_PTR(nstoken, "setns"))
 		goto out;
 
-	SYS("ip link add veth_src type veth peer name veth_dst");
-	SYS("ip link set dev veth_src address 00:11:22:33:44:55");
-	SYS("ip link set dev veth_dst address 66:77:88:99:aa:bb");
-	SYS("ip link set dev veth_src up");
-	SYS("ip link set dev veth_dst up");
-	SYS("ip addr add dev veth_src fc00::1/64");
-	SYS("ip addr add dev veth_dst fc00::2/64");
-	SYS("ip neigh add fc00::2 dev veth_src lladdr 66:77:88:99:aa:bb");
+	SYS(out, "ip link add veth_src type veth peer name veth_dst");
+	SYS(out, "ip link set dev veth_src address 00:11:22:33:44:55");
+	SYS(out, "ip link set dev veth_dst address 66:77:88:99:aa:bb");
+	SYS(out, "ip link set dev veth_src up");
+	SYS(out, "ip link set dev veth_dst up");
+	SYS(out, "ip addr add dev veth_src fc00::1/64");
+	SYS(out, "ip addr add dev veth_dst fc00::2/64");
+	SYS(out, "ip neigh add fc00::2 dev veth_src lladdr 66:77:88:99:aa:bb");
 
 	/* We enable forwarding in the test namespace because that will cause
 	 * the packets that go through the kernel stack (with XDP_PASS) to be
@@ -145,7 +155,7 @@ void test_xdp_do_redirect(void)
 	 * code didn't have this, so we keep the test behaviour to make sure the
 	 * bug doesn't resurface.
 	 */
-	SYS("sysctl -qw net.ipv6.conf.all.forwarding=1");
+	SYS(out, "sysctl -qw net.ipv6.conf.all.forwarding=1");
 
 	ifindex_src = if_nametoindex("veth_src");
 	ifindex_dst = if_nametoindex("veth_dst");
@@ -153,6 +163,53 @@ void test_xdp_do_redirect(void)
 	    !ASSERT_NEQ(ifindex_dst, 0, "ifindex_dst"))
 		goto out;
 
+	/* Check xdp features supported by veth driver */
+	err = bpf_xdp_query(ifindex_src, XDP_FLAGS_DRV_MODE, &query_opts);
+	if (!ASSERT_OK(err, "veth_src bpf_xdp_query"))
+		goto out;
+
+	if (!ASSERT_EQ(query_opts.feature_flags,
+		       NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+		       NETDEV_XDP_ACT_RX_SG,
+		       "veth_src query_opts.feature_flags"))
+		goto out;
+
+	err = bpf_xdp_query(ifindex_dst, XDP_FLAGS_DRV_MODE, &query_opts);
+	if (!ASSERT_OK(err, "veth_dst bpf_xdp_query"))
+		goto out;
+
+	if (!ASSERT_EQ(query_opts.feature_flags,
+		       NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+		       NETDEV_XDP_ACT_RX_SG,
+		       "veth_dst query_opts.feature_flags"))
+		goto out;
+
+	/* Enable GRO */
+	SYS(out, "ethtool -K veth_src gro on");
+	SYS(out, "ethtool -K veth_dst gro on");
+
+	err = bpf_xdp_query(ifindex_src, XDP_FLAGS_DRV_MODE, &query_opts);
+	if (!ASSERT_OK(err, "veth_src bpf_xdp_query gro on"))
+		goto out;
+
+	if (!ASSERT_EQ(query_opts.feature_flags,
+		       NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+		       NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG |
+		       NETDEV_XDP_ACT_NDO_XMIT_SG,
+		       "veth_src query_opts.feature_flags gro on"))
+		goto out;
+
+	err = bpf_xdp_query(ifindex_dst, XDP_FLAGS_DRV_MODE, &query_opts);
+	if (!ASSERT_OK(err, "veth_dst bpf_xdp_query gro on"))
+		goto out;
+
+	if (!ASSERT_EQ(query_opts.feature_flags,
+		       NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+		       NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG |
+		       NETDEV_XDP_ACT_NDO_XMIT_SG,
+		       "veth_dst query_opts.feature_flags gro on"))
+		goto out;
+
 	memcpy(skel->rodata->expect_dst, &pkt_udp.eth.h_dest, ETH_ALEN);
 	skel->rodata->ifindex_out = ifindex_src; /* redirect back to the same iface */
 	skel->rodata->ifindex_in = ifindex_src;
@@ -196,6 +253,169 @@ out_tc:
 out:
 	if (nstoken)
 		close_netns(nstoken);
-	system("ip netns del testns");
+	SYS_NOFAIL("ip netns del testns");
 	test_xdp_do_redirect__destroy(skel);
 }
+
+#define NS_NB		3
+#define NS0		"NS0"
+#define NS1		"NS1"
+#define NS2		"NS2"
+#define IPV4_NETWORK	"10.1.1"
+#define VETH1_INDEX	111
+#define VETH2_INDEX	222
+
+struct test_data {
+	struct netns_obj *ns[NS_NB];
+	u32 xdp_flags;
+};
+
+static void cleanup(struct test_data *data)
+{
+	int i;
+
+	for (i = 0; i < NS_NB; i++)
+		netns_free(data->ns[i]);
+}
+
+/**
+ * ping_setup -
+ * Create two veth peers and forward packets in-between using XDP
+ *
+ *    ------------           ------------
+ *    |    NS1   |           |    NS2   |
+ *    |   veth0  |           |   veth0  |
+ *    | 10.1.1.1 |           | 10.1.1.2 |
+ *    -----|------           ------|-----
+ *         |                       |
+ *         |                       |
+ *    -----|-----------------------|-------
+ *    |  veth1                   veth2    |
+ *    | (id:111)                (id:222)  |
+ *    |    |                        |     |
+ *    |    ----- xdp forwarding -----     |
+ *    |                                   |
+ *    |               NS0                 |
+ *    -------------------------------------
+ */
+static int ping_setup(struct test_data *data)
+{
+	int i;
+
+	data->ns[0] = netns_new(NS0, false);
+	if (!ASSERT_OK_PTR(data->ns[0], "create ns"))
+		return -1;
+
+	for (i = 1; i < NS_NB; i++) {
+		char ns_name[4] = {};
+
+		snprintf(ns_name, 4, "NS%d", i);
+		data->ns[i] = netns_new(ns_name, false);
+		if (!ASSERT_OK_PTR(data->ns[i], "create ns"))
+			goto fail;
+
+		SYS(fail,
+		    "ip -n %s link add veth%d index %d%d%d type veth peer name veth0 netns %s",
+		    NS0, i, i, i, i, ns_name);
+		SYS(fail, "ip -n %s link set veth%d up", NS0, i);
+
+		SYS(fail, "ip -n %s addr add %s.%d/24 dev veth0", ns_name, IPV4_NETWORK, i);
+		SYS(fail, "ip -n %s link set veth0 up", ns_name);
+	}
+
+	return 0;
+
+fail:
+	cleanup(data);
+	return -1;
+}
+
+static void ping_test(struct test_data *data)
+{
+	struct test_xdp_do_redirect *skel = NULL;
+	struct xdp_dummy *skel_dummy = NULL;
+	struct nstoken *nstoken = NULL;
+	int i, ret;
+
+	skel_dummy = xdp_dummy__open_and_load();
+	if (!ASSERT_OK_PTR(skel_dummy, "open and load xdp_dummy skeleton"))
+		goto close;
+
+	for (i = 1; i < NS_NB; i++) {
+		char ns_name[4] = {};
+
+		snprintf(ns_name, 4, "NS%d", i);
+		nstoken = open_netns(ns_name);
+		if (!ASSERT_OK_PTR(nstoken, "open ns"))
+			goto close;
+
+		ret = bpf_xdp_attach(if_nametoindex("veth0"),
+				     bpf_program__fd(skel_dummy->progs.xdp_dummy_prog),
+				     data->xdp_flags, NULL);
+		if (!ASSERT_GE(ret, 0, "bpf_xdp_attach dummy_prog"))
+			goto close;
+
+		close_netns(nstoken);
+		nstoken = NULL;
+	}
+
+	skel = test_xdp_do_redirect__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open and load skeleton"))
+		goto close;
+
+	nstoken = open_netns(NS0);
+	if (!ASSERT_OK_PTR(nstoken, "open NS0"))
+		goto close;
+
+	ret = bpf_xdp_attach(VETH2_INDEX,
+			     bpf_program__fd(skel->progs.xdp_redirect_to_111),
+			     data->xdp_flags, NULL);
+	if (!ASSERT_GE(ret, 0, "bpf_xdp_attach"))
+		goto close;
+
+	ret = bpf_xdp_attach(VETH1_INDEX,
+			     bpf_program__fd(skel->progs.xdp_redirect_to_222),
+			     data->xdp_flags, NULL);
+	if (!ASSERT_GE(ret, 0, "bpf_xdp_attach"))
+		goto close;
+
+	close_netns(nstoken);
+	nstoken = NULL;
+
+	nstoken = open_netns(NS1);
+	if (!ASSERT_OK_PTR(nstoken, "open NS1"))
+		goto close;
+
+	SYS(close, "ping -c 1 %s.2 > /dev/null", IPV4_NETWORK);
+
+close:
+	close_netns(nstoken);
+	xdp_dummy__destroy(skel_dummy);
+	test_xdp_do_redirect__destroy(skel);
+}
+
+
+static void xdp_redirect_ping(u32 xdp_flags)
+{
+	struct test_data data = {};
+
+	if (ping_setup(&data) < 0)
+		return;
+
+	data.xdp_flags = xdp_flags;
+	ping_test(&data);
+	cleanup(&data);
+}
+
+void test_xdp_index_redirect(void)
+{
+	if (test__start_subtest("noflag"))
+		xdp_redirect_ping(0);
+
+	if (test__start_subtest("drvflag"))
+		xdp_redirect_ping(XDP_FLAGS_DRV_MODE);
+
+	if (test__start_subtest("skbflag"))
+		xdp_redirect_ping(XDP_FLAGS_SKB_MODE);
+}
+
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c b/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c
new file mode 100644
index 000000000000..3f9146d83d79
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <network_helpers.h>
+#include <bpf/btf.h>
+#include <linux/if_link.h>
+#include <netinet/udp.h>
+#include <net/if.h>
+#include <unistd.h>
+
+#include "xdp_flowtable.skel.h"
+
+#define TX_NETNS_NAME	"ns0"
+#define RX_NETNS_NAME	"ns1"
+
+#define TX_NAME		"v0"
+#define FORWARD_NAME	"v1"
+#define RX_NAME		"d0"
+
+#define TX_MAC		"00:00:00:00:00:01"
+#define FORWARD_MAC	"00:00:00:00:00:02"
+#define RX_MAC		"00:00:00:00:00:03"
+#define DST_MAC		"00:00:00:00:00:04"
+
+#define TX_ADDR		"10.0.0.1"
+#define FORWARD_ADDR	"10.0.0.2"
+#define RX_ADDR		"20.0.0.1"
+#define DST_ADDR	"20.0.0.2"
+
+#define PREFIX_LEN	"8"
+#define N_PACKETS	10
+#define UDP_PORT	12345
+#define UDP_PORT_STR	"12345"
+
+static int send_udp_traffic(void)
+{
+	struct sockaddr_storage addr;
+	int i, sock;
+
+	if (make_sockaddr(AF_INET, DST_ADDR, UDP_PORT, &addr, NULL))
+		return -EINVAL;
+
+	sock = socket(AF_INET, SOCK_DGRAM, 0);
+	if (sock < 0)
+		return sock;
+
+	for (i = 0; i < N_PACKETS; i++) {
+		unsigned char buf[] = { 0xaa, 0xbb, 0xcc };
+		int n;
+
+		n = sendto(sock, buf, sizeof(buf), MSG_NOSIGNAL | MSG_CONFIRM,
+			   (struct sockaddr *)&addr, sizeof(addr));
+		if (n != sizeof(buf)) {
+			close(sock);
+			return -EINVAL;
+		}
+
+		usleep(50000); /* 50ms */
+	}
+	close(sock);
+
+	return 0;
+}
+
+void test_xdp_flowtable(void)
+{
+	struct xdp_flowtable *skel = NULL;
+	struct nstoken *tok = NULL;
+	int iifindex, stats_fd;
+	__u32 value, key = 0;
+	struct bpf_link *link;
+
+	if (SYS_NOFAIL("nft -v")) {
+		fprintf(stdout, "Missing required nft tool\n");
+		test__skip();
+		return;
+	}
+
+	SYS(out, "ip netns add " TX_NETNS_NAME);
+	SYS(out, "ip netns add " RX_NETNS_NAME);
+
+	tok = open_netns(RX_NETNS_NAME);
+	if (!ASSERT_OK_PTR(tok, "setns"))
+		goto out;
+
+	SYS(out, "sysctl -qw net.ipv4.conf.all.forwarding=1");
+
+	SYS(out, "ip link add " TX_NAME " type veth peer " FORWARD_NAME);
+	SYS(out, "ip link set " TX_NAME " netns " TX_NETNS_NAME);
+	SYS(out, "ip link set dev " FORWARD_NAME " address " FORWARD_MAC);
+	SYS(out,
+	    "ip addr add " FORWARD_ADDR "/" PREFIX_LEN " dev " FORWARD_NAME);
+	SYS(out, "ip link set dev " FORWARD_NAME " up");
+
+	SYS(out, "ip link add " RX_NAME " type dummy");
+	SYS(out, "ip link set dev " RX_NAME " address " RX_MAC);
+	SYS(out, "ip addr add " RX_ADDR "/" PREFIX_LEN " dev " RX_NAME);
+	SYS(out, "ip link set dev " RX_NAME " up");
+
+	/* configure the flowtable */
+	SYS(out, "nft add table ip filter");
+	SYS(out,
+	    "nft add flowtable ip filter f { hook ingress priority 0\\; "
+	    "devices = { " FORWARD_NAME ", " RX_NAME " }\\; }");
+	SYS(out,
+	    "nft add chain ip filter forward "
+	    "{ type filter hook forward priority 0\\; }");
+	SYS(out,
+	    "nft add rule ip filter forward ip protocol udp th dport "
+	    UDP_PORT_STR " flow add @f");
+
+	/* Avoid ARP calls */
+	SYS(out,
+	    "ip -4 neigh add " DST_ADDR " lladdr " DST_MAC " dev " RX_NAME);
+
+	close_netns(tok);
+	tok = open_netns(TX_NETNS_NAME);
+	if (!ASSERT_OK_PTR(tok, "setns"))
+		goto out;
+
+	SYS(out, "ip addr add " TX_ADDR "/" PREFIX_LEN " dev " TX_NAME);
+	SYS(out, "ip link set dev " TX_NAME " address " TX_MAC);
+	SYS(out, "ip link set dev " TX_NAME " up");
+	SYS(out, "ip route add default via " FORWARD_ADDR);
+
+	close_netns(tok);
+	tok = open_netns(RX_NETNS_NAME);
+	if (!ASSERT_OK_PTR(tok, "setns"))
+		goto out;
+
+	iifindex = if_nametoindex(FORWARD_NAME);
+	if (!ASSERT_NEQ(iifindex, 0, "iifindex"))
+		goto out;
+
+	skel = xdp_flowtable__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel"))
+		goto out;
+
+	link = bpf_program__attach_xdp(skel->progs.xdp_flowtable_do_lookup,
+				       iifindex);
+	if (!ASSERT_OK_PTR(link, "prog_attach"))
+		goto out;
+
+	close_netns(tok);
+	tok = open_netns(TX_NETNS_NAME);
+	if (!ASSERT_OK_PTR(tok, "setns"))
+		goto out;
+
+	if (!ASSERT_OK(send_udp_traffic(), "send udp"))
+		goto out;
+
+	close_netns(tok);
+	tok = open_netns(RX_NETNS_NAME);
+	if (!ASSERT_OK_PTR(tok, "setns"))
+		goto out;
+
+	stats_fd = bpf_map__fd(skel->maps.stats);
+	if (!ASSERT_OK(bpf_map_lookup_elem(stats_fd, &key, &value),
+		       "bpf_map_update_elem stats"))
+		goto out;
+
+	ASSERT_GE(value, N_PACKETS - 2, "bpf_xdp_flow_lookup failed");
+out:
+	xdp_flowtable__destroy(skel);
+	if (tok)
+		close_netns(tok);
+	SYS_NOFAIL("ip netns del " TX_NETNS_NAME);
+	SYS_NOFAIL("ip netns del " RX_NETNS_NAME);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_info.c b/tools/testing/selftests/bpf/prog_tests/xdp_info.c
index cd3aa340e65e..1dbddcab87a8 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_info.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_info.c
@@ -8,6 +8,7 @@ void serial_test_xdp_info(void)
 {
 	__u32 len = sizeof(struct bpf_prog_info), duration = 0, prog_id;
 	const char *file = "./xdp_dummy.bpf.o";
+	LIBBPF_OPTS(bpf_xdp_query_opts, opts);
 	struct bpf_prog_info info = {};
 	struct bpf_object *obj;
 	int err, prog_fd;
@@ -33,7 +34,7 @@ void serial_test_xdp_info(void)
 	if (CHECK_FAIL(err))
 		return;
 
-	err = bpf_obj_get_info_by_fd(prog_fd, &info, &len);
+	err = bpf_prog_get_info_by_fd(prog_fd, &info, &len);
 	if (CHECK(err, "get_prog_info", "errno=%d\n", errno))
 		goto out_close;
 
@@ -61,6 +62,13 @@ void serial_test_xdp_info(void)
 	if (CHECK(prog_id, "prog_id_drv", "unexpected prog_id=%u\n", prog_id))
 		goto out;
 
+	/* Check xdp features supported by lo device */
+	opts.feature_flags = ~0;
+	err = bpf_xdp_query(IFINDEX_LO, XDP_FLAGS_DRV_MODE, &opts);
+	if (!ASSERT_OK(err, "bpf_xdp_query"))
+		goto out;
+
+	ASSERT_EQ(opts.feature_flags, 0, "opts.feature_flags");
 out:
 	bpf_xdp_detach(IFINDEX_LO, 0, NULL);
 out_close:
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_link.c b/tools/testing/selftests/bpf/prog_tests/xdp_link.c
index 3e9d5c5521f0..e7e9f3c22edf 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_link.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_link.c
@@ -29,13 +29,13 @@ void serial_test_xdp_link(void)
 	prog_fd2 = bpf_program__fd(skel2->progs.xdp_handler);
 
 	memset(&prog_info, 0, sizeof(prog_info));
-	err = bpf_obj_get_info_by_fd(prog_fd1, &prog_info, &prog_info_len);
+	err = bpf_prog_get_info_by_fd(prog_fd1, &prog_info, &prog_info_len);
 	if (!ASSERT_OK(err, "fd_info1"))
 		goto cleanup;
 	id1 = prog_info.id;
 
 	memset(&prog_info, 0, sizeof(prog_info));
-	err = bpf_obj_get_info_by_fd(prog_fd2, &prog_info, &prog_info_len);
+	err = bpf_prog_get_info_by_fd(prog_fd2, &prog_info, &prog_info_len);
 	if (!ASSERT_OK(err, "fd_info2"))
 		goto cleanup;
 	id2 = prog_info.id;
@@ -119,7 +119,8 @@ void serial_test_xdp_link(void)
 		goto cleanup;
 
 	memset(&link_info, 0, sizeof(link_info));
-	err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &link_info, &link_info_len);
+	err = bpf_link_get_info_by_fd(bpf_link__fd(link),
+				      &link_info, &link_info_len);
 	if (!ASSERT_OK(err, "link_info"))
 		goto cleanup;
 
@@ -137,7 +138,8 @@ void serial_test_xdp_link(void)
 		goto cleanup;
 
 	memset(&link_info, 0, sizeof(link_info));
-	err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &link_info, &link_info_len);
+	err = bpf_link_get_info_by_fd(bpf_link__fd(link),
+				      &link_info, &link_info_len);
 
 	ASSERT_OK(err, "link_info");
 	ASSERT_EQ(link_info.prog_id, id1, "link_prog_id");
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
new file mode 100644
index 000000000000..19f92affc2da
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c
@@ -0,0 +1,545 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "xdp_metadata.skel.h"
+#include "xdp_metadata2.skel.h"
+#include "xdp_metadata.h"
+#include "xsk.h"
+
+#include <bpf/btf.h>
+#include <linux/errqueue.h>
+#include <linux/if_link.h>
+#include <linux/net_tstamp.h>
+#include <netinet/udp.h>
+#include <sys/mman.h>
+#include <net/if.h>
+#include <poll.h>
+
+#define TX_NAME "veTX"
+#define RX_NAME "veRX"
+
+#define UDP_PAYLOAD_BYTES 4
+
+#define UDP_SOURCE_PORT 1234
+#define AF_XDP_CONSUMER_PORT 8080
+
+#define UMEM_NUM 16
+#define UMEM_FRAME_SIZE XSK_UMEM__DEFAULT_FRAME_SIZE
+#define UMEM_SIZE (UMEM_FRAME_SIZE * UMEM_NUM)
+#define XDP_FLAGS XDP_FLAGS_DRV_MODE
+#define QUEUE_ID 0
+
+#define TX_ADDR "10.0.0.1"
+#define RX_ADDR "10.0.0.2"
+#define PREFIX_LEN "8"
+#define FAMILY AF_INET
+#define TX_NETNS_NAME "xdp_metadata_tx"
+#define RX_NETNS_NAME "xdp_metadata_rx"
+#define TX_MAC "00:00:00:00:00:01"
+#define RX_MAC "00:00:00:00:00:02"
+
+#define VLAN_ID 59
+#define VLAN_PROTO "802.1Q"
+#define VLAN_PID htons(ETH_P_8021Q)
+#define TX_NAME_VLAN TX_NAME "." TO_STR(VLAN_ID)
+
+#define XDP_RSS_TYPE_L4 BIT(3)
+#define VLAN_VID_MASK 0xfff
+
+struct xsk {
+	void *umem_area;
+	struct xsk_umem *umem;
+	struct xsk_ring_prod fill;
+	struct xsk_ring_cons comp;
+	struct xsk_ring_prod tx;
+	struct xsk_ring_cons rx;
+	struct xsk_socket *socket;
+};
+
+static int open_xsk(int ifindex, struct xsk *xsk)
+{
+	int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
+	const struct xsk_socket_config socket_config = {
+		.rx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
+		.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
+		.bind_flags = XDP_COPY,
+	};
+	const struct xsk_umem_config umem_config = {
+		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
+		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
+		.frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE,
+		.flags = XDP_UMEM_UNALIGNED_CHUNK_FLAG | XDP_UMEM_TX_SW_CSUM |
+			 XDP_UMEM_TX_METADATA_LEN,
+		.tx_metadata_len = sizeof(struct xsk_tx_metadata),
+	};
+	__u32 idx;
+	u64 addr;
+	int ret;
+	int i;
+
+	xsk->umem_area = mmap(NULL, UMEM_SIZE, PROT_READ | PROT_WRITE, mmap_flags, -1, 0);
+	if (!ASSERT_NEQ(xsk->umem_area, MAP_FAILED, "mmap"))
+		return -1;
+
+	ret = xsk_umem__create(&xsk->umem,
+			       xsk->umem_area, UMEM_SIZE,
+			       &xsk->fill,
+			       &xsk->comp,
+			       &umem_config);
+	if (!ASSERT_OK(ret, "xsk_umem__create"))
+		return ret;
+
+	ret = xsk_socket__create(&xsk->socket, ifindex, QUEUE_ID,
+				 xsk->umem,
+				 &xsk->rx,
+				 &xsk->tx,
+				 &socket_config);
+	if (!ASSERT_OK(ret, "xsk_socket__create"))
+		return ret;
+
+	/* First half of umem is for TX. This way address matches 1-to-1
+	 * to the completion queue index.
+	 */
+
+	for (i = 0; i < UMEM_NUM / 2; i++) {
+		addr = i * UMEM_FRAME_SIZE;
+		printf("%p: tx_desc[%d] -> %lx\n", xsk, i, addr);
+	}
+
+	/* Second half of umem is for RX. */
+
+	ret = xsk_ring_prod__reserve(&xsk->fill, UMEM_NUM / 2, &idx);
+	if (!ASSERT_EQ(UMEM_NUM / 2, ret, "xsk_ring_prod__reserve"))
+		return ret;
+	if (!ASSERT_EQ(idx, 0, "fill idx != 0"))
+		return -1;
+
+	for (i = 0; i < UMEM_NUM / 2; i++) {
+		addr = (UMEM_NUM / 2 + i) * UMEM_FRAME_SIZE;
+		printf("%p: rx_desc[%d] -> %lx\n", xsk, i, addr);
+		*xsk_ring_prod__fill_addr(&xsk->fill, i) = addr;
+	}
+	xsk_ring_prod__submit(&xsk->fill, ret);
+
+	return 0;
+}
+
+static void close_xsk(struct xsk *xsk)
+{
+	if (xsk->umem)
+		xsk_umem__delete(xsk->umem);
+	if (xsk->socket)
+		xsk_socket__delete(xsk->socket);
+	munmap(xsk->umem_area, UMEM_SIZE);
+}
+
+static int generate_packet(struct xsk *xsk, __u16 dst_port)
+{
+	struct xsk_tx_metadata *meta;
+	struct xdp_desc *tx_desc;
+	struct udphdr *udph;
+	struct ethhdr *eth;
+	struct iphdr *iph;
+	void *data;
+	__u32 idx;
+	int ret;
+
+	ret = xsk_ring_prod__reserve(&xsk->tx, 1, &idx);
+	if (!ASSERT_EQ(ret, 1, "xsk_ring_prod__reserve"))
+		return -1;
+
+	tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx);
+	tx_desc->addr = idx % (UMEM_NUM / 2) * UMEM_FRAME_SIZE + sizeof(struct xsk_tx_metadata);
+	printf("%p: tx_desc[%u]->addr=%llx\n", xsk, idx, tx_desc->addr);
+	data = xsk_umem__get_data(xsk->umem_area, tx_desc->addr);
+
+	meta = data - sizeof(struct xsk_tx_metadata);
+	memset(meta, 0, sizeof(*meta));
+	meta->flags = XDP_TXMD_FLAGS_TIMESTAMP;
+
+	eth = data;
+	iph = (void *)(eth + 1);
+	udph = (void *)(iph + 1);
+
+	memcpy(eth->h_dest, "\x00\x00\x00\x00\x00\x02", ETH_ALEN);
+	memcpy(eth->h_source, "\x00\x00\x00\x00\x00\x01", ETH_ALEN);
+	eth->h_proto = htons(ETH_P_IP);
+
+	iph->version = 0x4;
+	iph->ihl = 0x5;
+	iph->tos = 0x9;
+	iph->tot_len = htons(sizeof(*iph) + sizeof(*udph) + UDP_PAYLOAD_BYTES);
+	iph->id = 0;
+	iph->frag_off = 0;
+	iph->ttl = 0;
+	iph->protocol = IPPROTO_UDP;
+	ASSERT_EQ(inet_pton(FAMILY, TX_ADDR, &iph->saddr), 1, "inet_pton(TX_ADDR)");
+	ASSERT_EQ(inet_pton(FAMILY, RX_ADDR, &iph->daddr), 1, "inet_pton(RX_ADDR)");
+	iph->check = build_ip_csum(iph);
+
+	udph->source = htons(UDP_SOURCE_PORT);
+	udph->dest = htons(dst_port);
+	udph->len = htons(sizeof(*udph) + UDP_PAYLOAD_BYTES);
+	udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
+					 ntohs(udph->len), IPPROTO_UDP, 0);
+
+	memset(udph + 1, 0xAA, UDP_PAYLOAD_BYTES);
+
+	meta->flags |= XDP_TXMD_FLAGS_CHECKSUM;
+	meta->request.csum_start = sizeof(*eth) + sizeof(*iph);
+	meta->request.csum_offset = offsetof(struct udphdr, check);
+
+	tx_desc->len = sizeof(*eth) + sizeof(*iph) + sizeof(*udph) + UDP_PAYLOAD_BYTES;
+	tx_desc->options |= XDP_TX_METADATA;
+	xsk_ring_prod__submit(&xsk->tx, 1);
+
+	ret = sendto(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, 0);
+	if (!ASSERT_GE(ret, 0, "sendto"))
+		return ret;
+
+	return 0;
+}
+
+static int generate_packet_inet(void)
+{
+	char udp_payload[UDP_PAYLOAD_BYTES];
+	struct sockaddr_in rx_addr;
+	int sock_fd, err = 0;
+
+	/* Build a packet */
+	memset(udp_payload, 0xAA, UDP_PAYLOAD_BYTES);
+	rx_addr.sin_addr.s_addr = inet_addr(RX_ADDR);
+	rx_addr.sin_family = AF_INET;
+	rx_addr.sin_port = htons(AF_XDP_CONSUMER_PORT);
+
+	sock_fd = socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP);
+	if (!ASSERT_GE(sock_fd, 0, "socket(AF_INET, SOCK_DGRAM, IPPROTO_UDP)"))
+		return sock_fd;
+
+	err = sendto(sock_fd, udp_payload, UDP_PAYLOAD_BYTES, MSG_DONTWAIT,
+		     (void *)&rx_addr, sizeof(rx_addr));
+	ASSERT_GE(err, 0, "sendto");
+
+	close(sock_fd);
+	return err;
+}
+
+static void complete_tx(struct xsk *xsk)
+{
+	struct xsk_tx_metadata *meta;
+	__u64 addr;
+	void *data;
+	__u32 idx;
+
+	if (ASSERT_EQ(xsk_ring_cons__peek(&xsk->comp, 1, &idx), 1, "xsk_ring_cons__peek")) {
+		addr = *xsk_ring_cons__comp_addr(&xsk->comp, idx);
+
+		printf("%p: complete tx idx=%u addr=%llx\n", xsk, idx, addr);
+
+		data = xsk_umem__get_data(xsk->umem_area, addr);
+		meta = data - sizeof(struct xsk_tx_metadata);
+
+		ASSERT_NEQ(meta->completion.tx_timestamp, 0, "tx_timestamp");
+
+		xsk_ring_cons__release(&xsk->comp, 1);
+	}
+}
+
+static void refill_rx(struct xsk *xsk, __u64 addr)
+{
+	__u32 idx;
+
+	if (ASSERT_EQ(xsk_ring_prod__reserve(&xsk->fill, 1, &idx), 1, "xsk_ring_prod__reserve")) {
+		printf("%p: complete idx=%u addr=%llx\n", xsk, idx, addr);
+		*xsk_ring_prod__fill_addr(&xsk->fill, idx) = addr;
+		xsk_ring_prod__submit(&xsk->fill, 1);
+	}
+}
+
+static int verify_xsk_metadata(struct xsk *xsk, bool sent_from_af_xdp)
+{
+	const struct xdp_desc *rx_desc;
+	struct pollfd fds = {};
+	struct xdp_meta *meta;
+	struct udphdr *udph;
+	struct ethhdr *eth;
+	struct iphdr *iph;
+	__u64 comp_addr;
+	void *data;
+	__u64 addr;
+	__u32 idx = 0;
+	int ret;
+
+	ret = recvfrom(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, NULL);
+	if (!ASSERT_EQ(ret, 0, "recvfrom"))
+		return -1;
+
+	fds.fd = xsk_socket__fd(xsk->socket);
+	fds.events = POLLIN;
+
+	ret = poll(&fds, 1, 1000);
+	if (!ASSERT_GT(ret, 0, "poll"))
+		return -1;
+
+	ret = xsk_ring_cons__peek(&xsk->rx, 1, &idx);
+	if (!ASSERT_EQ(ret, 1, "xsk_ring_cons__peek"))
+		return -2;
+
+	rx_desc = xsk_ring_cons__rx_desc(&xsk->rx, idx);
+	comp_addr = xsk_umem__extract_addr(rx_desc->addr);
+	addr = xsk_umem__add_offset_to_addr(rx_desc->addr);
+	printf("%p: rx_desc[%u]->addr=%llx addr=%llx comp_addr=%llx\n",
+	       xsk, idx, rx_desc->addr, addr, comp_addr);
+	data = xsk_umem__get_data(xsk->umem_area, addr);
+
+	/* Make sure we got the packet offset correctly. */
+
+	eth = data;
+	ASSERT_EQ(eth->h_proto, htons(ETH_P_IP), "eth->h_proto");
+	iph = (void *)(eth + 1);
+	ASSERT_EQ((int)iph->version, 4, "iph->version");
+	udph = (void *)(iph + 1);
+
+	/* custom metadata */
+
+	meta = data - sizeof(struct xdp_meta);
+
+	if (!ASSERT_NEQ(meta->rx_timestamp, 0, "rx_timestamp"))
+		return -1;
+
+	if (!ASSERT_NEQ(meta->rx_hash, 0, "rx_hash"))
+		return -1;
+
+	if (!sent_from_af_xdp) {
+		if (!ASSERT_NEQ(meta->rx_hash_type & XDP_RSS_TYPE_L4, 0, "rx_hash_type"))
+			return -1;
+
+		if (!ASSERT_EQ(meta->rx_vlan_tci & VLAN_VID_MASK, VLAN_ID, "rx_vlan_tci"))
+			return -1;
+
+		if (!ASSERT_EQ(meta->rx_vlan_proto, VLAN_PID, "rx_vlan_proto"))
+			return -1;
+		goto done;
+	}
+
+	ASSERT_EQ(meta->rx_hash_type, 0, "rx_hash_type");
+
+	/* checksum offload */
+	ASSERT_EQ(udph->check, htons(0x721c), "csum");
+
+done:
+	xsk_ring_cons__release(&xsk->rx, 1);
+	refill_rx(xsk, comp_addr);
+
+	return 0;
+}
+
+static void switch_ns_to_rx(struct nstoken **tok)
+{
+	close_netns(*tok);
+	*tok = open_netns(RX_NETNS_NAME);
+}
+
+static void switch_ns_to_tx(struct nstoken **tok)
+{
+	close_netns(*tok);
+	*tok = open_netns(TX_NETNS_NAME);
+}
+
+void test_xdp_metadata(void)
+{
+	struct xdp_metadata2 *bpf_obj2 = NULL;
+	struct xdp_metadata *bpf_obj = NULL;
+	struct bpf_program *new_prog, *prog;
+	struct bpf_devmap_val devmap_e = {};
+	struct bpf_map *prog_arr, *devmap;
+	struct nstoken *tok = NULL;
+	__u32 queue_id = QUEUE_ID;
+	struct xsk tx_xsk = {};
+	struct xsk rx_xsk = {};
+	__u32 val, key = 0;
+	int retries = 10;
+	int rx_ifindex;
+	int tx_ifindex;
+	int sock_fd;
+	int ret;
+
+	/* Setup new networking namespaces, with a veth pair. */
+	SYS(out, "ip netns add " TX_NETNS_NAME);
+	SYS(out, "ip netns add " RX_NETNS_NAME);
+
+	tok = open_netns(TX_NETNS_NAME);
+	if (!ASSERT_OK_PTR(tok, "setns"))
+		goto out;
+	SYS(out, "ip link add numtxqueues 1 numrxqueues 1 " TX_NAME
+	    " type veth peer " RX_NAME " numtxqueues 1 numrxqueues 1");
+	SYS(out, "ip link set " RX_NAME " netns " RX_NETNS_NAME);
+
+	SYS(out, "ip link set dev " TX_NAME " address " TX_MAC);
+	SYS(out, "ip link set dev " TX_NAME " up");
+
+	SYS(out, "ip link add link " TX_NAME " " TX_NAME_VLAN
+		 " type vlan proto " VLAN_PROTO " id " TO_STR(VLAN_ID));
+	SYS(out, "ip link set dev " TX_NAME_VLAN " up");
+	SYS(out, "ip addr add " TX_ADDR "/" PREFIX_LEN " dev " TX_NAME_VLAN);
+
+	/* Avoid ARP calls */
+	SYS(out, "ip -4 neigh add " RX_ADDR " lladdr " RX_MAC " dev " TX_NAME_VLAN);
+
+	switch_ns_to_rx(&tok);
+	if (!ASSERT_OK_PTR(tok, "setns rx"))
+		goto out;
+
+	SYS(out, "ip link set dev " RX_NAME " address " RX_MAC);
+	SYS(out, "ip link set dev " RX_NAME " up");
+	SYS(out, "ip addr add " RX_ADDR "/" PREFIX_LEN " dev " RX_NAME);
+
+	rx_ifindex = if_nametoindex(RX_NAME);
+
+	/* Setup separate AF_XDP for RX interface. */
+
+	ret = open_xsk(rx_ifindex, &rx_xsk);
+	if (!ASSERT_OK(ret, "open_xsk(RX_NAME)"))
+		goto out;
+
+	bpf_obj = xdp_metadata__open();
+	if (!ASSERT_OK_PTR(bpf_obj, "open skeleton"))
+		goto out;
+
+	prog = bpf_object__find_program_by_name(bpf_obj->obj, "rx");
+	bpf_program__set_ifindex(prog, rx_ifindex);
+	bpf_program__set_flags(prog, BPF_F_XDP_DEV_BOUND_ONLY);
+
+	/* Make sure we can load a dev-bound program that performs
+	 * XDP_REDIRECT into a devmap.
+	 */
+	new_prog = bpf_object__find_program_by_name(bpf_obj->obj, "redirect");
+	bpf_program__set_ifindex(new_prog, rx_ifindex);
+	bpf_program__set_flags(new_prog, BPF_F_XDP_DEV_BOUND_ONLY);
+
+	if (!ASSERT_OK(xdp_metadata__load(bpf_obj), "load skeleton"))
+		goto out;
+
+	/* Make sure we can't add dev-bound programs to prog maps. */
+	prog_arr = bpf_object__find_map_by_name(bpf_obj->obj, "prog_arr");
+	if (!ASSERT_OK_PTR(prog_arr, "no prog_arr map"))
+		goto out;
+
+	val = bpf_program__fd(prog);
+	if (!ASSERT_ERR(bpf_map__update_elem(prog_arr, &key, sizeof(key),
+					     &val, sizeof(val), BPF_ANY),
+			"update prog_arr"))
+		goto out;
+
+	/* Make sure we can't add dev-bound programs to devmaps. */
+	devmap = bpf_object__find_map_by_name(bpf_obj->obj, "dev_map");
+	if (!ASSERT_OK_PTR(devmap, "no dev_map found"))
+		goto out;
+
+	devmap_e.bpf_prog.fd = val;
+	if (!ASSERT_ERR(bpf_map__update_elem(devmap, &key, sizeof(key),
+					     &devmap_e, sizeof(devmap_e),
+					     BPF_ANY),
+			"update dev_map"))
+		goto out;
+
+	/* Attach BPF program to RX interface. */
+
+	ret = bpf_xdp_attach(rx_ifindex,
+			     bpf_program__fd(bpf_obj->progs.rx),
+			     XDP_FLAGS, NULL);
+	if (!ASSERT_GE(ret, 0, "bpf_xdp_attach"))
+		goto out;
+
+	sock_fd = xsk_socket__fd(rx_xsk.socket);
+	ret = bpf_map_update_elem(bpf_map__fd(bpf_obj->maps.xsk), &queue_id, &sock_fd, 0);
+	if (!ASSERT_GE(ret, 0, "bpf_map_update_elem"))
+		goto out;
+
+	switch_ns_to_tx(&tok);
+	if (!ASSERT_OK_PTR(tok, "setns tx"))
+		goto out;
+
+	/* Setup separate AF_XDP for TX interface nad send packet to the RX socket. */
+	tx_ifindex = if_nametoindex(TX_NAME);
+	ret = open_xsk(tx_ifindex, &tx_xsk);
+	if (!ASSERT_OK(ret, "open_xsk(TX_NAME)"))
+		goto out;
+
+	if (!ASSERT_GE(generate_packet(&tx_xsk, AF_XDP_CONSUMER_PORT), 0,
+		       "generate AF_XDP_CONSUMER_PORT"))
+		goto out;
+
+	switch_ns_to_rx(&tok);
+	if (!ASSERT_OK_PTR(tok, "setns rx"))
+		goto out;
+
+	/* Verify packet sent from AF_XDP has proper metadata. */
+	if (!ASSERT_GE(verify_xsk_metadata(&rx_xsk, true), 0,
+		       "verify_xsk_metadata"))
+		goto out;
+
+	switch_ns_to_tx(&tok);
+	if (!ASSERT_OK_PTR(tok, "setns tx"))
+		goto out;
+	complete_tx(&tx_xsk);
+
+	/* Now check metadata of packet, generated with network stack */
+	if (!ASSERT_GE(generate_packet_inet(), 0, "generate UDP packet"))
+		goto out;
+
+	switch_ns_to_rx(&tok);
+	if (!ASSERT_OK_PTR(tok, "setns rx"))
+		goto out;
+
+	if (!ASSERT_GE(verify_xsk_metadata(&rx_xsk, false), 0,
+		       "verify_xsk_metadata"))
+		goto out;
+
+	/* Make sure freplace correctly picks up original bound device
+	 * and doesn't crash.
+	 */
+
+	bpf_obj2 = xdp_metadata2__open();
+	if (!ASSERT_OK_PTR(bpf_obj2, "open skeleton"))
+		goto out;
+
+	new_prog = bpf_object__find_program_by_name(bpf_obj2->obj, "freplace_rx");
+	bpf_program__set_attach_target(new_prog, bpf_program__fd(prog), "rx");
+
+	if (!ASSERT_OK(xdp_metadata2__load(bpf_obj2), "load freplace skeleton"))
+		goto out;
+
+	if (!ASSERT_OK(xdp_metadata2__attach(bpf_obj2), "attach freplace"))
+		goto out;
+
+	switch_ns_to_tx(&tok);
+	if (!ASSERT_OK_PTR(tok, "setns tx"))
+		goto out;
+
+	/* Send packet to trigger . */
+	if (!ASSERT_GE(generate_packet(&tx_xsk, AF_XDP_CONSUMER_PORT), 0,
+		       "generate freplace packet"))
+		goto out;
+
+	switch_ns_to_rx(&tok);
+	if (!ASSERT_OK_PTR(tok, "setns rx"))
+		goto out;
+
+	while (!retries--) {
+		if (bpf_obj2->bss->called)
+			break;
+		usleep(10);
+	}
+	ASSERT_GT(bpf_obj2->bss->called, 0, "not called");
+
+out:
+	close_xsk(&rx_xsk);
+	close_xsk(&tx_xsk);
+	xdp_metadata2__destroy(bpf_obj2);
+	xdp_metadata__destroy(bpf_obj);
+	if (tok)
+		close_netns(tok);
+	SYS_NOFAIL("ip netns del " RX_NETNS_NAME);
+	SYS_NOFAIL("ip netns del " TX_NETNS_NAME);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_pull_data.c b/tools/testing/selftests/bpf/prog_tests/xdp_pull_data.c
new file mode 100644
index 000000000000..efa350d04ec5
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_pull_data.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "test_xdp_pull_data.skel.h"
+
+#define PULL_MAX	(1 << 31)
+#define PULL_PLUS_ONE	(1 << 30)
+
+#define XDP_PACKET_HEADROOM 256
+
+/* Find headroom and tailroom occupied by struct xdp_frame and struct
+ * skb_shared_info so that we can calculate the maximum pull lengths for
+ * test cases. They might not be the real size of the structures due to
+ * cache alignment.
+ */
+static int find_xdp_sizes(struct test_xdp_pull_data *skel, int frame_sz)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	struct xdp_md ctx = {};
+	int prog_fd, err;
+	__u8 *buf;
+
+	buf = calloc(frame_sz, sizeof(__u8));
+	if (!ASSERT_OK_PTR(buf, "calloc buf"))
+		return -ENOMEM;
+
+	topts.data_in = buf;
+	topts.data_out = buf;
+	topts.data_size_in = frame_sz;
+	topts.data_size_out = frame_sz;
+	/* Pass a data_end larger than the linear space available to make sure
+	 * bpf_prog_test_run_xdp() will fill the linear data area so that
+	 * xdp_find_sizes can infer the size of struct skb_shared_info
+	 */
+	ctx.data_end = frame_sz;
+	topts.ctx_in = &ctx;
+	topts.ctx_out = &ctx;
+	topts.ctx_size_in = sizeof(ctx);
+	topts.ctx_size_out = sizeof(ctx);
+
+	prog_fd = bpf_program__fd(skel->progs.xdp_find_sizes);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "bpf_prog_test_run_opts");
+
+	free(buf);
+
+	return err;
+}
+
+/* xdp_pull_data_prog will directly read a marker 0xbb stored at buf[1024]
+ * so caller expecting XDP_PASS should always pass pull_len no less than 1024
+ */
+static void run_test(struct test_xdp_pull_data *skel, int retval,
+		     int frame_sz, int buff_len, int meta_len, int data_len,
+		     int pull_len)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, topts);
+	struct xdp_md ctx = {};
+	int prog_fd, err;
+	__u8 *buf;
+
+	buf = calloc(buff_len, sizeof(__u8));
+	if (!ASSERT_OK_PTR(buf, "calloc buf"))
+		return;
+
+	buf[meta_len + 1023] = 0xaa;
+	buf[meta_len + 1024] = 0xbb;
+	buf[meta_len + 1025] = 0xcc;
+
+	topts.data_in = buf;
+	topts.data_out = buf;
+	topts.data_size_in = buff_len;
+	topts.data_size_out = buff_len;
+	ctx.data = meta_len;
+	ctx.data_end = meta_len + data_len;
+	topts.ctx_in = &ctx;
+	topts.ctx_out = &ctx;
+	topts.ctx_size_in = sizeof(ctx);
+	topts.ctx_size_out = sizeof(ctx);
+
+	skel->bss->data_len = data_len;
+	if (pull_len & PULL_MAX) {
+		int headroom = XDP_PACKET_HEADROOM - meta_len - skel->bss->xdpf_sz;
+		int tailroom = frame_sz - XDP_PACKET_HEADROOM -
+			       data_len - skel->bss->sinfo_sz;
+
+		pull_len = pull_len & PULL_PLUS_ONE ? 1 : 0;
+		pull_len += headroom + tailroom + data_len;
+	}
+	skel->bss->pull_len = pull_len;
+
+	prog_fd = bpf_program__fd(skel->progs.xdp_pull_data_prog);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	ASSERT_OK(err, "bpf_prog_test_run_opts");
+	ASSERT_EQ(topts.retval, retval, "xdp_pull_data_prog retval");
+
+	if (retval == XDP_DROP)
+		goto out;
+
+	ASSERT_EQ(ctx.data_end, meta_len + pull_len, "linear data size");
+	ASSERT_EQ(topts.data_size_out, buff_len, "linear + non-linear data size");
+	/* Make sure data around xdp->data_end was not messed up by
+	 * bpf_xdp_pull_data()
+	 */
+	ASSERT_EQ(buf[meta_len + 1023], 0xaa, "data[1023]");
+	ASSERT_EQ(buf[meta_len + 1024], 0xbb, "data[1024]");
+	ASSERT_EQ(buf[meta_len + 1025], 0xcc, "data[1025]");
+out:
+	free(buf);
+}
+
+static void test_xdp_pull_data_basic(void)
+{
+	u32 pg_sz, max_meta_len, max_data_len;
+	struct test_xdp_pull_data *skel;
+
+	skel = test_xdp_pull_data__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_xdp_pull_data__open_and_load"))
+		return;
+
+	pg_sz = sysconf(_SC_PAGE_SIZE);
+
+	if (find_xdp_sizes(skel, pg_sz))
+		goto out;
+
+	max_meta_len = XDP_PACKET_HEADROOM - skel->bss->xdpf_sz;
+	max_data_len = pg_sz - XDP_PACKET_HEADROOM - skel->bss->sinfo_sz;
+
+	/* linear xdp pkt, pull 0 byte */
+	run_test(skel, XDP_PASS, pg_sz, 2048, 0, 2048, 2048);
+
+	/* multi-buf pkt, pull results in linear xdp pkt */
+	run_test(skel, XDP_PASS, pg_sz, 2048, 0, 1024, 2048);
+
+	/* multi-buf pkt, pull 1 byte to linear data area */
+	run_test(skel, XDP_PASS, pg_sz, 9000, 0, 1024, 1025);
+
+	/* multi-buf pkt, pull 0 byte to linear data area */
+	run_test(skel, XDP_PASS, pg_sz, 9000, 0, 1025, 1025);
+
+	/* multi-buf pkt, empty linear data area, pull requires memmove */
+	run_test(skel, XDP_PASS, pg_sz, 9000, 0, 0, PULL_MAX);
+
+	/* multi-buf pkt, no headroom */
+	run_test(skel, XDP_PASS, pg_sz, 9000, max_meta_len, 1024, PULL_MAX);
+
+	/* multi-buf pkt, no tailroom, pull requires memmove */
+	run_test(skel, XDP_PASS, pg_sz, 9000, 0, max_data_len, PULL_MAX);
+
+	/* Test cases with invalid pull length */
+
+	/* linear xdp pkt, pull more than total data len */
+	run_test(skel, XDP_DROP, pg_sz, 2048, 0, 2048, 2049);
+
+	/* multi-buf pkt with no space left in linear data area */
+	run_test(skel, XDP_DROP, pg_sz, 9000, max_meta_len, max_data_len,
+		 PULL_MAX | PULL_PLUS_ONE);
+
+	/* multi-buf pkt, empty linear data area */
+	run_test(skel, XDP_DROP, pg_sz, 9000, 0, 0, PULL_MAX | PULL_PLUS_ONE);
+
+	/* multi-buf pkt, no headroom */
+	run_test(skel, XDP_DROP, pg_sz, 9000, max_meta_len, 1024,
+		 PULL_MAX | PULL_PLUS_ONE);
+
+	/* multi-buf pkt, no tailroom */
+	run_test(skel, XDP_DROP, pg_sz, 9000, 0, max_data_len,
+		 PULL_MAX | PULL_PLUS_ONE);
+
+out:
+	test_xdp_pull_data__destroy(skel);
+}
+
+void test_xdp_pull_data(void)
+{
+	if (test__start_subtest("xdp_pull_data"))
+		test_xdp_pull_data_basic();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_synproxy.c b/tools/testing/selftests/bpf/prog_tests/xdp_synproxy.c
index c72083885b6d..8b50a992d233 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_synproxy.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_synproxy.c
@@ -8,11 +8,6 @@
 
 #define CMD_OUT_BUF_SIZE 1023
 
-#define SYS(cmd) ({ \
-	if (!ASSERT_OK(system(cmd), (cmd))) \
-		goto out; \
-})
-
 #define SYS_OUT(cmd, ...) ({ \
 	char buf[1024]; \
 	snprintf(buf, sizeof(buf), (cmd), ##__VA_ARGS__); \
@@ -69,37 +64,37 @@ static void test_synproxy(bool xdp)
 	char buf[CMD_OUT_BUF_SIZE];
 	size_t size;
 
-	SYS("ip netns add synproxy");
+	SYS(out, "ip netns add synproxy");
 
-	SYS("ip link add tmp0 type veth peer name tmp1");
-	SYS("ip link set tmp1 netns synproxy");
-	SYS("ip link set tmp0 up");
-	SYS("ip addr replace 198.18.0.1/24 dev tmp0");
+	SYS(out, "ip link add tmp0 type veth peer name tmp1");
+	SYS(out, "ip link set tmp1 netns synproxy");
+	SYS(out, "ip link set tmp0 up");
+	SYS(out, "ip addr replace 198.18.0.1/24 dev tmp0");
 
 	/* When checksum offload is enabled, the XDP program sees wrong
 	 * checksums and drops packets.
 	 */
-	SYS("ethtool -K tmp0 tx off");
+	SYS(out, "ethtool -K tmp0 tx off");
 	if (xdp)
 		/* Workaround required for veth. */
-		SYS("ip link set tmp0 xdp object xdp_dummy.bpf.o section xdp 2> /dev/null");
+		SYS(out, "ip link set tmp0 xdp object xdp_dummy.bpf.o section xdp 2> /dev/null");
 
 	ns = open_netns("synproxy");
 	if (!ASSERT_OK_PTR(ns, "setns"))
 		goto out;
 
-	SYS("ip link set lo up");
-	SYS("ip link set tmp1 up");
-	SYS("ip addr replace 198.18.0.2/24 dev tmp1");
-	SYS("sysctl -w net.ipv4.tcp_syncookies=2");
-	SYS("sysctl -w net.ipv4.tcp_timestamps=1");
-	SYS("sysctl -w net.netfilter.nf_conntrack_tcp_loose=0");
-	SYS("iptables-legacy -t raw -I PREROUTING \
+	SYS(out, "ip link set lo up");
+	SYS(out, "ip link set tmp1 up");
+	SYS(out, "ip addr replace 198.18.0.2/24 dev tmp1");
+	SYS(out, "sysctl -w net.ipv4.tcp_syncookies=2");
+	SYS(out, "sysctl -w net.ipv4.tcp_timestamps=1");
+	SYS(out, "sysctl -w net.netfilter.nf_conntrack_tcp_loose=0");
+	SYS(out, "iptables-legacy -t raw -I PREROUTING \
 	    -i tmp1 -p tcp -m tcp --syn --dport 8080 -j CT --notrack");
-	SYS("iptables-legacy -t filter -A INPUT \
+	SYS(out, "iptables-legacy -t filter -A INPUT \
 	    -i tmp1 -p tcp -m tcp --dport 8080 -m state --state INVALID,UNTRACKED \
 	    -j SYNPROXY --sack-perm --timestamp --wscale 7 --mss 1460");
-	SYS("iptables-legacy -t filter -A INPUT \
+	SYS(out, "iptables-legacy -t filter -A INPUT \
 	    -i tmp1 -m state --state INVALID -j DROP");
 
 	ctrl_file = SYS_OUT("./xdp_synproxy --iface tmp1 --ports 8080 \
@@ -170,8 +165,8 @@ out:
 	if (ns)
 		close_netns(ns);
 
-	system("ip link del tmp0");
-	system("ip netns del synproxy");
+	SYS_NOFAIL("ip link del tmp0");
+	SYS_NOFAIL("ip netns del synproxy");
 }
 
 void test_xdp_synproxy(void)
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_vlan.c b/tools/testing/selftests/bpf/prog_tests/xdp_vlan.c
new file mode 100644
index 000000000000..18dd25344de7
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_vlan.c
@@ -0,0 +1,175 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Network topology:
+ *  -----------        -----------
+ *  |  NS1    |        |   NS2   |
+ *  | veth0  -|--------|- veth0  |
+ *  -----------        -----------
+ *
+ */
+
+#define _GNU_SOURCE
+#include <net/if.h>
+#include <uapi/linux/if_link.h>
+
+#include "network_helpers.h"
+#include "test_progs.h"
+#include "test_xdp_vlan.skel.h"
+
+
+#define VETH_NAME	"veth0"
+#define NS_MAX_SIZE	32
+#define NS1_NAME	"ns-xdp-vlan-1-"
+#define NS2_NAME	"ns-xdp-vlan-2-"
+#define NS1_IP_ADDR	"100.64.10.1"
+#define NS2_IP_ADDR	"100.64.10.2"
+#define VLAN_ID		4011
+
+static int setup_network(char *ns1, char *ns2)
+{
+	if (!ASSERT_OK(append_tid(ns1, NS_MAX_SIZE), "create ns1 name"))
+		goto fail;
+	if (!ASSERT_OK(append_tid(ns2, NS_MAX_SIZE), "create ns2 name"))
+		goto fail;
+
+	SYS(fail, "ip netns add %s", ns1);
+	SYS(fail, "ip netns add %s", ns2);
+	SYS(fail, "ip -n %s link add %s type veth peer name %s netns %s",
+	    ns1, VETH_NAME, VETH_NAME, ns2);
+
+	/* NOTICE: XDP require VLAN header inside packet payload
+	 *  - Thus, disable VLAN offloading driver features
+	 */
+	SYS(fail, "ip netns exec %s ethtool -K %s rxvlan off txvlan off", ns1, VETH_NAME);
+	SYS(fail, "ip netns exec %s ethtool -K %s rxvlan off txvlan off", ns2, VETH_NAME);
+
+	/* NS1 configuration */
+	SYS(fail, "ip -n %s addr add %s/24 dev %s", ns1, NS1_IP_ADDR, VETH_NAME);
+	SYS(fail, "ip -n %s link set %s up", ns1, VETH_NAME);
+
+	/* NS2 configuration */
+	SYS(fail, "ip -n %s link add link %s name %s.%d type vlan id %d",
+	    ns2, VETH_NAME, VETH_NAME, VLAN_ID, VLAN_ID);
+	SYS(fail, "ip -n %s addr add %s/24 dev %s.%d", ns2, NS2_IP_ADDR, VETH_NAME, VLAN_ID);
+	SYS(fail, "ip -n %s link set %s up", ns2, VETH_NAME);
+	SYS(fail, "ip -n %s link set %s.%d up", ns2, VETH_NAME, VLAN_ID);
+
+	/* At this point ping should fail because VLAN tags are only used by NS2 */
+	return !SYS_NOFAIL("ip netns exec %s ping -W 1 -c1 %s", ns2, NS1_IP_ADDR);
+
+fail:
+	return -1;
+}
+
+static void cleanup_network(const char *ns1, const char *ns2)
+{
+	SYS_NOFAIL("ip netns del %s", ns1);
+	SYS_NOFAIL("ip netns del %s", ns2);
+}
+
+static void xdp_vlan(struct bpf_program *xdp, struct bpf_program *tc, u32 flags)
+{
+	LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_EGRESS);
+	LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+	char ns1[NS_MAX_SIZE] = NS1_NAME;
+	char ns2[NS_MAX_SIZE] = NS2_NAME;
+	struct nstoken *nstoken = NULL;
+	int interface;
+	int ret;
+
+	if (!ASSERT_OK(setup_network(ns1, ns2), "setup network"))
+		goto cleanup;
+
+	nstoken = open_netns(ns1);
+	if (!ASSERT_OK_PTR(nstoken, "open NS1"))
+		goto cleanup;
+
+	interface = if_nametoindex(VETH_NAME);
+	if (!ASSERT_NEQ(interface, 0, "get interface index"))
+		goto cleanup;
+
+	ret = bpf_xdp_attach(interface, bpf_program__fd(xdp), flags, NULL);
+	if (!ASSERT_OK(ret, "attach xdp_vlan_change"))
+		goto cleanup;
+
+	tc_hook.ifindex = interface;
+	ret = bpf_tc_hook_create(&tc_hook);
+	if (!ASSERT_OK(ret, "bpf_tc_hook_create"))
+		goto detach_xdp;
+
+	/* Now we'll use BPF programs to pop/push the VLAN tags */
+	tc_opts.prog_fd = bpf_program__fd(tc);
+	ret = bpf_tc_attach(&tc_hook, &tc_opts);
+	if (!ASSERT_OK(ret, "bpf_tc_attach"))
+		goto detach_xdp;
+
+	close_netns(nstoken);
+	nstoken = NULL;
+
+	/* Now the namespaces can reach each-other, test with pings */
+	SYS(detach_tc, "ip netns exec %s ping -i 0.2 -W 2 -c 2 %s > /dev/null", ns1, NS2_IP_ADDR);
+	SYS(detach_tc, "ip netns exec %s ping -i 0.2 -W 2 -c 2 %s > /dev/null", ns2, NS1_IP_ADDR);
+
+
+detach_tc:
+	bpf_tc_detach(&tc_hook, &tc_opts);
+detach_xdp:
+	bpf_xdp_detach(interface, flags, NULL);
+cleanup:
+	close_netns(nstoken);
+	cleanup_network(ns1, ns2);
+}
+
+/* First test: Remove VLAN by setting VLAN ID 0, using "xdp_vlan_change"
+ * egress use TC to add back VLAN tag 4011
+ */
+void test_xdp_vlan_change(void)
+{
+	struct test_xdp_vlan *skel;
+
+	skel = test_xdp_vlan__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "xdp_vlan__open_and_load"))
+		return;
+
+	if (test__start_subtest("0"))
+		xdp_vlan(skel->progs.xdp_vlan_change, skel->progs.tc_vlan_push, 0);
+
+	if (test__start_subtest("DRV_MODE"))
+		xdp_vlan(skel->progs.xdp_vlan_change, skel->progs.tc_vlan_push,
+			 XDP_FLAGS_DRV_MODE);
+
+	if (test__start_subtest("SKB_MODE"))
+		xdp_vlan(skel->progs.xdp_vlan_change, skel->progs.tc_vlan_push,
+			 XDP_FLAGS_SKB_MODE);
+
+	test_xdp_vlan__destroy(skel);
+}
+
+/* Second test: XDP prog fully remove vlan header
+ *
+ * Catch kernel bug for generic-XDP, that doesn't allow us to
+ * remove a VLAN header, because skb->protocol still contain VLAN
+ * ETH_P_8021Q indication, and this cause overwriting of our changes.
+ */
+void test_xdp_vlan_remove(void)
+{
+	struct test_xdp_vlan *skel;
+
+	skel = test_xdp_vlan__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "xdp_vlan__open_and_load"))
+		return;
+
+	if (test__start_subtest("0"))
+		xdp_vlan(skel->progs.xdp_vlan_remove_outer2, skel->progs.tc_vlan_push, 0);
+
+	if (test__start_subtest("DRV_MODE"))
+		xdp_vlan(skel->progs.xdp_vlan_remove_outer2, skel->progs.tc_vlan_push,
+			 XDP_FLAGS_DRV_MODE);
+
+	if (test__start_subtest("SKB_MODE"))
+		xdp_vlan(skel->progs.xdp_vlan_remove_outer2, skel->progs.tc_vlan_push,
+			 XDP_FLAGS_SKB_MODE);
+
+	test_xdp_vlan__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdpwall.c b/tools/testing/selftests/bpf/prog_tests/xdpwall.c
index f3927829a55a..4599154c8e9b 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdpwall.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdpwall.c
@@ -9,7 +9,7 @@ void test_xdpwall(void)
 	struct xdpwall *skel;
 
 	skel = xdpwall__open_and_load();
-	ASSERT_OK_PTR(skel, "Does LLMV have https://reviews.llvm.org/D109073?");
+	ASSERT_OK_PTR(skel, "Does LLVM have https://github.com/llvm/llvm-project/commit/ea72b0319d7b0f0c2fcf41d121afa5d031b319d5?");
 
 	xdpwall__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/xfrm_info.c b/tools/testing/selftests/bpf/prog_tests/xfrm_info.c
index 8b03c9bb4862..d37f5394e199 100644
--- a/tools/testing/selftests/bpf/prog_tests/xfrm_info.c
+++ b/tools/testing/selftests/bpf/prog_tests/xfrm_info.c
@@ -69,21 +69,6 @@
     "proto esp aead 'rfc4106(gcm(aes))' " \
     "0xe4d8f4b4da1df18a3510b3781496daa82488b713 128 mode tunnel "
 
-#define SYS(fmt, ...)						\
-	({							\
-		char cmd[1024];					\
-		snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__);	\
-		if (!ASSERT_OK(system(cmd), cmd))		\
-			goto fail;				\
-	})
-
-#define SYS_NOFAIL(fmt, ...)					\
-	({							\
-		char cmd[1024];					\
-		snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__);	\
-		system(cmd);					\
-	})
-
 static int attach_tc_prog(struct bpf_tc_hook *hook, int igr_fd, int egr_fd)
 {
 	LIBBPF_OPTS(bpf_tc_opts, opts1, .handle = 1, .priority = 1,
@@ -126,23 +111,23 @@ static void cleanup(void)
 
 static int config_underlay(void)
 {
-	SYS("ip netns add " NS0);
-	SYS("ip netns add " NS1);
-	SYS("ip netns add " NS2);
+	SYS(fail, "ip netns add " NS0);
+	SYS(fail, "ip netns add " NS1);
+	SYS(fail, "ip netns add " NS2);
 
 	/* NS0 <-> NS1 [veth01 <-> veth10] */
-	SYS("ip link add veth01 netns " NS0 " type veth peer name veth10 netns " NS1);
-	SYS("ip -net " NS0 " addr add " IP4_ADDR_VETH01 "/24 dev veth01");
-	SYS("ip -net " NS0 " link set dev veth01 up");
-	SYS("ip -net " NS1 " addr add " IP4_ADDR_VETH10 "/24 dev veth10");
-	SYS("ip -net " NS1 " link set dev veth10 up");
+	SYS(fail, "ip link add veth01 netns " NS0 " type veth peer name veth10 netns " NS1);
+	SYS(fail, "ip -net " NS0 " addr add " IP4_ADDR_VETH01 "/24 dev veth01");
+	SYS(fail, "ip -net " NS0 " link set dev veth01 up");
+	SYS(fail, "ip -net " NS1 " addr add " IP4_ADDR_VETH10 "/24 dev veth10");
+	SYS(fail, "ip -net " NS1 " link set dev veth10 up");
 
 	/* NS0 <-> NS2 [veth02 <-> veth20] */
-	SYS("ip link add veth02 netns " NS0 " type veth peer name veth20 netns " NS2);
-	SYS("ip -net " NS0 " addr add " IP4_ADDR_VETH02 "/24 dev veth02");
-	SYS("ip -net " NS0 " link set dev veth02 up");
-	SYS("ip -net " NS2 " addr add " IP4_ADDR_VETH20 "/24 dev veth20");
-	SYS("ip -net " NS2 " link set dev veth20 up");
+	SYS(fail, "ip link add veth02 netns " NS0 " type veth peer name veth20 netns " NS2);
+	SYS(fail, "ip -net " NS0 " addr add " IP4_ADDR_VETH02 "/24 dev veth02");
+	SYS(fail, "ip -net " NS0 " link set dev veth02 up");
+	SYS(fail, "ip -net " NS2 " addr add " IP4_ADDR_VETH20 "/24 dev veth20");
+	SYS(fail, "ip -net " NS2 " link set dev veth20 up");
 
 	return 0;
 fail:
@@ -153,20 +138,20 @@ static int setup_xfrm_tunnel_ns(const char *ns, const char *ipv4_local,
 				const char *ipv4_remote, int if_id)
 {
 	/* State: local -> remote */
-	SYS("ip -net %s xfrm state add src %s dst %s spi 1 "
+	SYS(fail, "ip -net %s xfrm state add src %s dst %s spi 1 "
 	    ESP_DUMMY_PARAMS "if_id %d", ns, ipv4_local, ipv4_remote, if_id);
 
 	/* State: local <- remote */
-	SYS("ip -net %s xfrm state add src %s dst %s spi 1 "
+	SYS(fail, "ip -net %s xfrm state add src %s dst %s spi 1 "
 	    ESP_DUMMY_PARAMS "if_id %d", ns, ipv4_remote, ipv4_local, if_id);
 
 	/* Policy: local -> remote */
-	SYS("ip -net %s xfrm policy add dir out src 0.0.0.0/0 dst 0.0.0.0/0 "
+	SYS(fail, "ip -net %s xfrm policy add dir out src 0.0.0.0/0 dst 0.0.0.0/0 "
 	    "if_id %d tmpl src %s dst %s proto esp mode tunnel if_id %d", ns,
 	    if_id, ipv4_local, ipv4_remote, if_id);
 
 	/* Policy: local <- remote */
-	SYS("ip -net %s xfrm policy add dir in src 0.0.0.0/0 dst 0.0.0.0/0 "
+	SYS(fail, "ip -net %s xfrm policy add dir in src 0.0.0.0/0 dst 0.0.0.0/0 "
 	    "if_id %d tmpl src %s dst %s proto esp mode tunnel if_id %d", ns,
 	    if_id, ipv4_remote, ipv4_local, if_id);
 
@@ -274,16 +259,16 @@ static int config_overlay(void)
 	if (!ASSERT_OK(setup_xfrmi_external_dev(NS0), "xfrmi"))
 		goto fail;
 
-	SYS("ip -net " NS0 " addr add 192.168.1.100/24 dev ipsec0");
-	SYS("ip -net " NS0 " link set dev ipsec0 up");
+	SYS(fail, "ip -net " NS0 " addr add 192.168.1.100/24 dev ipsec0");
+	SYS(fail, "ip -net " NS0 " link set dev ipsec0 up");
 
-	SYS("ip -net " NS1 " link add ipsec0 type xfrm if_id %d", IF_ID_1);
-	SYS("ip -net " NS1 " addr add 192.168.1.200/24 dev ipsec0");
-	SYS("ip -net " NS1 " link set dev ipsec0 up");
+	SYS(fail, "ip -net " NS1 " link add ipsec0 type xfrm if_id %d", IF_ID_1);
+	SYS(fail, "ip -net " NS1 " addr add 192.168.1.200/24 dev ipsec0");
+	SYS(fail, "ip -net " NS1 " link set dev ipsec0 up");
 
-	SYS("ip -net " NS2 " link add ipsec0 type xfrm if_id %d", IF_ID_2);
-	SYS("ip -net " NS2 " addr add 192.168.1.200/24 dev ipsec0");
-	SYS("ip -net " NS2 " link set dev ipsec0 up");
+	SYS(fail, "ip -net " NS2 " link add ipsec0 type xfrm if_id %d", IF_ID_2);
+	SYS(fail, "ip -net " NS2 " addr add 192.168.1.200/24 dev ipsec0");
+	SYS(fail, "ip -net " NS2 " link set dev ipsec0 up");
 
 	return 0;
 fail:
@@ -294,7 +279,7 @@ static int test_xfrm_ping(struct xfrm_info *skel, u32 if_id)
 {
 	skel->bss->req_if_id = if_id;
 
-	SYS("ping -i 0.01 -c 3 -w 10 -q 192.168.1.200 > /dev/null");
+	SYS(fail, "ping -i 0.01 -c 3 -w 10 -q 192.168.1.200 > /dev/null");
 
 	if (!ASSERT_EQ(skel->bss->resp_if_id, if_id, "if_id"))
 		goto fail;
diff --git a/tools/testing/selftests/bpf/prog_tests/xsk.c b/tools/testing/selftests/bpf/prog_tests/xsk.c
new file mode 100644
index 000000000000..dd4c35c0e428
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xsk.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <net/if.h>
+#include <stdarg.h>
+
+#include "network_helpers.h"
+#include "test_progs.h"
+#include "test_xsk.h"
+#include "xsk_xdp_progs.skel.h"
+
+#define VETH_RX "veth0"
+#define VETH_TX "veth1"
+#define MTU	1500
+
+int setup_veth(bool busy_poll)
+{
+	SYS(fail,
+	"ip link add %s numtxqueues 4 numrxqueues 4 type veth peer name %s numtxqueues 4 numrxqueues 4",
+	VETH_RX, VETH_TX);
+	SYS(fail, "sysctl -wq net.ipv6.conf.%s.disable_ipv6=1", VETH_RX);
+	SYS(fail, "sysctl -wq net.ipv6.conf.%s.disable_ipv6=1", VETH_TX);
+
+	if (busy_poll) {
+		SYS(fail, "echo 2 > /sys/class/net/%s/napi_defer_hard_irqs", VETH_RX);
+		SYS(fail, "echo 200000 > /sys/class/net/%s/gro_flush_timeout", VETH_RX);
+		SYS(fail, "echo 2 > /sys/class/net/%s/napi_defer_hard_irqs", VETH_TX);
+		SYS(fail, "echo 200000 > /sys/class/net/%s/gro_flush_timeout", VETH_TX);
+	}
+
+	SYS(fail, "ip link set %s mtu %d", VETH_RX, MTU);
+	SYS(fail, "ip link set %s mtu %d", VETH_TX, MTU);
+	SYS(fail, "ip link set %s up", VETH_RX);
+	SYS(fail, "ip link set %s up", VETH_TX);
+
+	return 0;
+
+fail:
+	return -1;
+}
+
+void delete_veth(void)
+{
+	SYS_NOFAIL("ip link del %s", VETH_RX);
+	SYS_NOFAIL("ip link del %s", VETH_TX);
+}
+
+int configure_ifobj(struct ifobject *tx, struct ifobject *rx)
+{
+	rx->ifindex = if_nametoindex(VETH_RX);
+	if (!ASSERT_OK_FD(rx->ifindex, "get RX ifindex"))
+		return -1;
+
+	tx->ifindex = if_nametoindex(VETH_TX);
+	if (!ASSERT_OK_FD(tx->ifindex, "get TX ifindex"))
+		return -1;
+
+	tx->shared_umem = false;
+	rx->shared_umem = false;
+
+
+	return 0;
+}
+
+static void test_xsk(const struct test_spec *test_to_run, enum test_mode mode)
+{
+	struct ifobject *ifobj_tx, *ifobj_rx;
+	struct test_spec test;
+	int ret;
+
+	ifobj_tx = ifobject_create();
+	if (!ASSERT_OK_PTR(ifobj_tx, "create ifobj_tx"))
+		return;
+
+	ifobj_rx = ifobject_create();
+	if (!ASSERT_OK_PTR(ifobj_rx, "create ifobj_rx"))
+		goto delete_tx;
+
+	if (!ASSERT_OK(configure_ifobj(ifobj_tx, ifobj_rx), "conigure ifobj"))
+		goto delete_rx;
+
+	ret = get_hw_ring_size(ifobj_tx->ifname, &ifobj_tx->ring);
+	if (!ret) {
+		ifobj_tx->hw_ring_size_supp = true;
+		ifobj_tx->set_ring.default_tx = ifobj_tx->ring.tx_pending;
+		ifobj_tx->set_ring.default_rx = ifobj_tx->ring.rx_pending;
+	}
+
+	if (!ASSERT_OK(init_iface(ifobj_rx, worker_testapp_validate_rx), "init RX"))
+		goto delete_rx;
+	if (!ASSERT_OK(init_iface(ifobj_tx, worker_testapp_validate_tx), "init TX"))
+		goto delete_rx;
+
+	test_init(&test, ifobj_tx, ifobj_rx, 0, &tests[0]);
+
+	test.tx_pkt_stream_default = pkt_stream_generate(DEFAULT_PKT_CNT, MIN_PKT_SIZE);
+	if (!ASSERT_OK_PTR(test.tx_pkt_stream_default, "TX pkt generation"))
+		goto delete_rx;
+	test.rx_pkt_stream_default = pkt_stream_generate(DEFAULT_PKT_CNT, MIN_PKT_SIZE);
+	if (!ASSERT_OK_PTR(test.rx_pkt_stream_default, "RX pkt generation"))
+		goto delete_rx;
+
+
+	test_init(&test, ifobj_tx, ifobj_rx, mode, test_to_run);
+	ret = test.test_func(&test);
+	if (ret != TEST_SKIP)
+		ASSERT_OK(ret, "Run test");
+	pkt_stream_restore_default(&test);
+
+	if (ifobj_tx->hw_ring_size_supp)
+		hw_ring_size_reset(ifobj_tx);
+
+	pkt_stream_delete(test.tx_pkt_stream_default);
+	pkt_stream_delete(test.rx_pkt_stream_default);
+	xsk_xdp_progs__destroy(ifobj_tx->xdp_progs);
+	xsk_xdp_progs__destroy(ifobj_rx->xdp_progs);
+
+delete_rx:
+	ifobject_delete(ifobj_rx);
+delete_tx:
+	ifobject_delete(ifobj_tx);
+}
+
+void test_ns_xsk_skb(void)
+{
+	int i;
+
+	if (!ASSERT_OK(setup_veth(false), "setup veth"))
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		if (test__start_subtest(tests[i].name))
+			test_xsk(&tests[i], TEST_MODE_SKB);
+	}
+
+	delete_veth();
+}
+
+void test_ns_xsk_drv(void)
+{
+	int i;
+
+	if (!ASSERT_OK(setup_veth(false), "setup veth"))
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		if (test__start_subtest(tests[i].name))
+			test_xsk(&tests[i], TEST_MODE_DRV);
+	}
+
+	delete_veth();
+}
+
diff --git a/tools/testing/selftests/bpf/progs/access_map_in_map.c b/tools/testing/selftests/bpf/progs/access_map_in_map.c
new file mode 100644
index 000000000000..1126871c2ebd
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/access_map_in_map.c
@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <linux/bpf.h>
+#include <time.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+
+struct inner_map_type {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(key_size, 4);
+	__uint(value_size, 4);
+	__uint(max_entries, 1);
+} inner_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 1);
+	__array(values, struct inner_map_type);
+} outer_array_map SEC(".maps") = {
+	.values = {
+		[0] = &inner_map,
+	},
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 1);
+	__array(values, struct inner_map_type);
+} outer_htab_map SEC(".maps") = {
+	.values = {
+		[0] = &inner_map,
+	},
+};
+
+char _license[] SEC("license") = "GPL";
+
+int tgid = 0;
+
+static int acc_map_in_map(void *outer_map)
+{
+	int i, key, value = 0xdeadbeef;
+	void *inner_map;
+
+	if ((bpf_get_current_pid_tgid() >> 32) != tgid)
+		return 0;
+
+	/* Find nonexistent inner map */
+	key = 1;
+	inner_map = bpf_map_lookup_elem(outer_map, &key);
+	if (inner_map)
+		return 0;
+
+	/* Find the old inner map */
+	key = 0;
+	inner_map = bpf_map_lookup_elem(outer_map, &key);
+	if (!inner_map)
+		return 0;
+
+	/* Wait for the old inner map to be replaced */
+	for (i = 0; i < 2048; i++)
+		bpf_map_update_elem(inner_map, &key, &value, 0);
+
+	return 0;
+}
+
+SEC("?kprobe/" SYS_PREFIX "sys_getpgid")
+int access_map_in_array(void *ctx)
+{
+	return acc_map_in_map(&outer_array_map);
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int sleepable_access_map_in_array(void *ctx)
+{
+	return acc_map_in_map(&outer_array_map);
+}
+
+SEC("?kprobe/" SYS_PREFIX "sys_getpgid")
+int access_map_in_htab(void *ctx)
+{
+	return acc_map_in_map(&outer_htab_map);
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int sleepable_access_map_in_htab(void *ctx)
+{
+	return acc_map_in_map(&outer_htab_map);
+}
diff --git a/tools/testing/selftests/bpf/progs/arena_atomics.c b/tools/testing/selftests/bpf/progs/arena_atomics.c
new file mode 100644
index 000000000000..d1841aac94a2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/arena_atomics.c
@@ -0,0 +1,397 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <stdbool.h>
+#include <stdatomic.h>
+#include "bpf_arena_common.h"
+#include "../../../include/linux/filter.h"
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARENA);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__uint(max_entries, 10); /* number of pages */
+#ifdef __TARGET_ARCH_arm64
+	__ulong(map_extra, 0x1ull << 32); /* start of mmap() region */
+#else
+	__ulong(map_extra, 0x1ull << 44); /* start of mmap() region */
+#endif
+} arena SEC(".maps");
+
+#if defined(ENABLE_ATOMICS_TESTS) && defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+bool skip_all_tests __attribute((__section__(".data"))) = false;
+#else
+bool skip_all_tests = true;
+#endif
+
+#if defined(ENABLE_ATOMICS_TESTS) &&		  \
+	defined(__BPF_FEATURE_ADDR_SPACE_CAST) && \
+	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+	 (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64))
+bool skip_lacq_srel_tests __attribute((__section__(".data"))) = false;
+#else
+bool skip_lacq_srel_tests = true;
+#endif
+
+__u32 pid = 0;
+
+__u64 __arena_global add64_value = 1;
+__u64 __arena_global add64_result = 0;
+__u32 __arena_global add32_value = 1;
+__u32 __arena_global add32_result = 0;
+__u64 __arena_global add_stack_value_copy = 0;
+__u64 __arena_global add_stack_result = 0;
+__u64 __arena_global add_noreturn_value = 1;
+
+SEC("raw_tp/sys_enter")
+int add(const void *ctx)
+{
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+#ifdef ENABLE_ATOMICS_TESTS
+	__u64 add_stack_value = 1;
+
+	add64_result = __sync_fetch_and_add(&add64_value, 2);
+	add32_result = __sync_fetch_and_add(&add32_value, 2);
+	add_stack_result = __sync_fetch_and_add(&add_stack_value, 2);
+	add_stack_value_copy = add_stack_value;
+	__sync_fetch_and_add(&add_noreturn_value, 2);
+#endif
+
+	return 0;
+}
+
+__s64 __arena_global sub64_value = 1;
+__s64 __arena_global sub64_result = 0;
+__s32 __arena_global sub32_value = 1;
+__s32 __arena_global sub32_result = 0;
+__s64 __arena_global sub_stack_value_copy = 0;
+__s64 __arena_global sub_stack_result = 0;
+__s64 __arena_global sub_noreturn_value = 1;
+
+SEC("raw_tp/sys_enter")
+int sub(const void *ctx)
+{
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+#ifdef ENABLE_ATOMICS_TESTS
+	__u64 sub_stack_value = 1;
+
+	sub64_result = __sync_fetch_and_sub(&sub64_value, 2);
+	sub32_result = __sync_fetch_and_sub(&sub32_value, 2);
+	sub_stack_result = __sync_fetch_and_sub(&sub_stack_value, 2);
+	sub_stack_value_copy = sub_stack_value;
+	__sync_fetch_and_sub(&sub_noreturn_value, 2);
+#endif
+
+	return 0;
+}
+
+#ifdef __BPF_FEATURE_ATOMIC_MEM_ORDERING
+_Atomic __u64 __arena_global and64_value = (0x110ull << 32);
+_Atomic __u32 __arena_global and32_value = 0x110;
+#else
+__u64 __arena_global and64_value = (0x110ull << 32);
+__u32 __arena_global and32_value = 0x110;
+#endif
+
+SEC("raw_tp/sys_enter")
+int and(const void *ctx)
+{
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+#ifdef ENABLE_ATOMICS_TESTS
+#ifdef __BPF_FEATURE_ATOMIC_MEM_ORDERING
+	__c11_atomic_fetch_and(&and64_value, 0x011ull << 32, memory_order_relaxed);
+	__c11_atomic_fetch_and(&and32_value, 0x011, memory_order_relaxed);
+#else
+	__sync_fetch_and_and(&and64_value, 0x011ull << 32);
+	__sync_fetch_and_and(&and32_value, 0x011);
+#endif
+#endif
+
+	return 0;
+}
+
+#ifdef __BPF_FEATURE_ATOMIC_MEM_ORDERING
+_Atomic __u32 __arena_global or32_value = 0x110;
+_Atomic __u64 __arena_global or64_value = (0x110ull << 32);
+#else
+__u32 __arena_global or32_value = 0x110;
+__u64 __arena_global or64_value = (0x110ull << 32);
+#endif
+
+SEC("raw_tp/sys_enter")
+int or(const void *ctx)
+{
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+#ifdef ENABLE_ATOMICS_TESTS
+#ifdef __BPF_FEATURE_ATOMIC_MEM_ORDERING
+	__c11_atomic_fetch_or(&or64_value, 0x011ull << 32, memory_order_relaxed);
+	__c11_atomic_fetch_or(&or32_value, 0x011, memory_order_relaxed);
+#else
+	__sync_fetch_and_or(&or64_value, 0x011ull << 32);
+	__sync_fetch_and_or(&or32_value, 0x011);
+#endif
+#endif
+
+	return 0;
+}
+
+#ifdef __BPF_FEATURE_ATOMIC_MEM_ORDERING
+_Atomic __u64 __arena_global xor64_value = (0x110ull << 32);
+_Atomic __u32 __arena_global xor32_value = 0x110;
+#else
+__u64 __arena_global xor64_value = (0x110ull << 32);
+__u32 __arena_global xor32_value = 0x110;
+#endif
+
+SEC("raw_tp/sys_enter")
+int xor(const void *ctx)
+{
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+#ifdef ENABLE_ATOMICS_TESTS
+#ifdef __BPF_FEATURE_ATOMIC_MEM_ORDERING
+	__c11_atomic_fetch_xor(&xor64_value, 0x011ull << 32, memory_order_relaxed);
+	__c11_atomic_fetch_xor(&xor32_value, 0x011, memory_order_relaxed);
+#else
+	__sync_fetch_and_xor(&xor64_value, 0x011ull << 32);
+	__sync_fetch_and_xor(&xor32_value, 0x011);
+#endif
+#endif
+
+	return 0;
+}
+
+__u32 __arena_global cmpxchg32_value = 1;
+__u32 __arena_global cmpxchg32_result_fail = 0;
+__u32 __arena_global cmpxchg32_result_succeed = 0;
+__u64 __arena_global cmpxchg64_value = 1;
+__u64 __arena_global cmpxchg64_result_fail = 0;
+__u64 __arena_global cmpxchg64_result_succeed = 0;
+
+SEC("raw_tp/sys_enter")
+int cmpxchg(const void *ctx)
+{
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+#ifdef ENABLE_ATOMICS_TESTS
+	cmpxchg64_result_fail = __sync_val_compare_and_swap(&cmpxchg64_value, 0, 3);
+	cmpxchg64_result_succeed = __sync_val_compare_and_swap(&cmpxchg64_value, 1, 2);
+
+	cmpxchg32_result_fail = __sync_val_compare_and_swap(&cmpxchg32_value, 0, 3);
+	cmpxchg32_result_succeed = __sync_val_compare_and_swap(&cmpxchg32_value, 1, 2);
+#endif
+
+	return 0;
+}
+
+__u64 __arena_global xchg64_value = 1;
+__u64 __arena_global xchg64_result = 0;
+__u32 __arena_global xchg32_value = 1;
+__u32 __arena_global xchg32_result = 0;
+
+SEC("raw_tp/sys_enter")
+int xchg(const void *ctx)
+{
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+#ifdef ENABLE_ATOMICS_TESTS
+	__u64 val64 = 2;
+	__u32 val32 = 2;
+
+	xchg64_result = __sync_lock_test_and_set(&xchg64_value, val64);
+	xchg32_result = __sync_lock_test_and_set(&xchg32_value, val32);
+#endif
+
+	return 0;
+}
+
+__u64 __arena_global uaf_sink;
+volatile __u64 __arena_global uaf_recovery_fails;
+
+SEC("syscall")
+int uaf(const void *ctx)
+{
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+#if defined(ENABLE_ATOMICS_TESTS) && !defined(__TARGET_ARCH_arm64) && \
+    !defined(__TARGET_ARCH_x86)
+	__u32 __arena *page32;
+	__u64 __arena *page64;
+	void __arena *page;
+
+	page = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	bpf_arena_free_pages(&arena, page, 1);
+	uaf_recovery_fails = 24;
+
+	page32 = (__u32 __arena *)page;
+	uaf_sink += __sync_fetch_and_add(page32, 1);
+	uaf_recovery_fails -= 1;
+	__sync_add_and_fetch(page32, 1);
+	uaf_recovery_fails -= 1;
+	uaf_sink += __sync_fetch_and_sub(page32, 1);
+	uaf_recovery_fails -= 1;
+	__sync_sub_and_fetch(page32, 1);
+	uaf_recovery_fails -= 1;
+	uaf_sink += __sync_fetch_and_and(page32, 1);
+	uaf_recovery_fails -= 1;
+	__sync_and_and_fetch(page32, 1);
+	uaf_recovery_fails -= 1;
+	uaf_sink += __sync_fetch_and_or(page32, 1);
+	uaf_recovery_fails -= 1;
+	__sync_or_and_fetch(page32, 1);
+	uaf_recovery_fails -= 1;
+	uaf_sink += __sync_fetch_and_xor(page32, 1);
+	uaf_recovery_fails -= 1;
+	__sync_xor_and_fetch(page32, 1);
+	uaf_recovery_fails -= 1;
+	uaf_sink += __sync_val_compare_and_swap(page32, 0, 1);
+	uaf_recovery_fails -= 1;
+	uaf_sink += __sync_lock_test_and_set(page32, 1);
+	uaf_recovery_fails -= 1;
+
+	page64 = (__u64 __arena *)page;
+	uaf_sink += __sync_fetch_and_add(page64, 1);
+	uaf_recovery_fails -= 1;
+	__sync_add_and_fetch(page64, 1);
+	uaf_recovery_fails -= 1;
+	uaf_sink += __sync_fetch_and_sub(page64, 1);
+	uaf_recovery_fails -= 1;
+	__sync_sub_and_fetch(page64, 1);
+	uaf_recovery_fails -= 1;
+	uaf_sink += __sync_fetch_and_and(page64, 1);
+	uaf_recovery_fails -= 1;
+	__sync_and_and_fetch(page64, 1);
+	uaf_recovery_fails -= 1;
+	uaf_sink += __sync_fetch_and_or(page64, 1);
+	uaf_recovery_fails -= 1;
+	__sync_or_and_fetch(page64, 1);
+	uaf_recovery_fails -= 1;
+	uaf_sink += __sync_fetch_and_xor(page64, 1);
+	uaf_recovery_fails -= 1;
+	__sync_xor_and_fetch(page64, 1);
+	uaf_recovery_fails -= 1;
+	uaf_sink += __sync_val_compare_and_swap(page64, 0, 1);
+	uaf_recovery_fails -= 1;
+	uaf_sink += __sync_lock_test_and_set(page64, 1);
+	uaf_recovery_fails -= 1;
+#endif
+
+	return 0;
+}
+
+#if __clang_major__ >= 18
+__u8 __arena_global load_acquire8_value = 0x12;
+__u16 __arena_global load_acquire16_value = 0x1234;
+__u32 __arena_global load_acquire32_value = 0x12345678;
+__u64 __arena_global load_acquire64_value = 0x1234567890abcdef;
+
+__u8 __arena_global load_acquire8_result = 0;
+__u16 __arena_global load_acquire16_result = 0;
+__u32 __arena_global load_acquire32_result = 0;
+__u64 __arena_global load_acquire64_result = 0;
+#else
+/* clang-17 crashes if the .addr_space.1 ELF section has holes. Work around
+ * this issue by defining the below variables as 64-bit.
+ */
+__u64 __arena_global load_acquire8_value;
+__u64 __arena_global load_acquire16_value;
+__u64 __arena_global load_acquire32_value;
+__u64 __arena_global load_acquire64_value;
+
+__u64 __arena_global load_acquire8_result;
+__u64 __arena_global load_acquire16_result;
+__u64 __arena_global load_acquire32_result;
+__u64 __arena_global load_acquire64_result;
+#endif
+
+SEC("raw_tp/sys_enter")
+int load_acquire(const void *ctx)
+{
+#if defined(ENABLE_ATOMICS_TESTS) &&		  \
+	defined(__BPF_FEATURE_ADDR_SPACE_CAST) && \
+	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+	 (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64))
+
+#define LOAD_ACQUIRE_ARENA(SIZEOP, SIZE, SRC, DST)	\
+	{ asm volatile (				\
+	"r1 = %[" #SRC "] ll;"				\
+	"r1 = addr_space_cast(r1, 0x0, 0x1);"		\
+	".8byte %[load_acquire_insn];"			\
+	"r3 = %[" #DST "] ll;"				\
+	"r3 = addr_space_cast(r3, 0x0, 0x1);"		\
+	"*(" #SIZE " *)(r3 + 0) = r2;"			\
+	:						\
+	: __imm_addr(SRC),				\
+	  __imm_insn(load_acquire_insn,			\
+		     BPF_ATOMIC_OP(BPF_##SIZEOP, BPF_LOAD_ACQ,	\
+				   BPF_REG_2, BPF_REG_1, 0)),	\
+	  __imm_addr(DST)				\
+	: __clobber_all); }				\
+
+	LOAD_ACQUIRE_ARENA(B, u8, load_acquire8_value, load_acquire8_result)
+	LOAD_ACQUIRE_ARENA(H, u16, load_acquire16_value,
+			   load_acquire16_result)
+	LOAD_ACQUIRE_ARENA(W, u32, load_acquire32_value,
+			   load_acquire32_result)
+	LOAD_ACQUIRE_ARENA(DW, u64, load_acquire64_value,
+			   load_acquire64_result)
+#undef LOAD_ACQUIRE_ARENA
+
+#endif
+	return 0;
+}
+
+#if __clang_major__ >= 18
+__u8 __arena_global store_release8_result = 0;
+__u16 __arena_global store_release16_result = 0;
+__u32 __arena_global store_release32_result = 0;
+__u64 __arena_global store_release64_result = 0;
+#else
+/* clang-17 crashes if the .addr_space.1 ELF section has holes. Work around
+ * this issue by defining the below variables as 64-bit.
+ */
+__u64 __arena_global store_release8_result;
+__u64 __arena_global store_release16_result;
+__u64 __arena_global store_release32_result;
+__u64 __arena_global store_release64_result;
+#endif
+
+SEC("raw_tp/sys_enter")
+int store_release(const void *ctx)
+{
+#if defined(ENABLE_ATOMICS_TESTS) &&		  \
+	defined(__BPF_FEATURE_ADDR_SPACE_CAST) && \
+	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+	 (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64))
+
+#define STORE_RELEASE_ARENA(SIZEOP, DST, VAL)	\
+	{ asm volatile (			\
+	"r1 = " VAL ";"				\
+	"r2 = %[" #DST "] ll;"			\
+	"r2 = addr_space_cast(r2, 0x0, 0x1);"	\
+	".8byte %[store_release_insn];"		\
+	:					\
+	: __imm_addr(DST),			\
+	  __imm_insn(store_release_insn,	\
+		     BPF_ATOMIC_OP(BPF_##SIZEOP, BPF_STORE_REL,	\
+				   BPF_REG_2, BPF_REG_1, 0))	\
+	: __clobber_all); }			\
+
+	STORE_RELEASE_ARENA(B, store_release8_result, "0x12")
+	STORE_RELEASE_ARENA(H, store_release16_result, "0x1234")
+	STORE_RELEASE_ARENA(W, store_release32_result, "0x12345678")
+	STORE_RELEASE_ARENA(DW, store_release64_result,
+			    "0x1234567890abcdef ll")
+#undef STORE_RELEASE_ARENA
+
+#endif
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/arena_htab.c b/tools/testing/selftests/bpf/progs/arena_htab.c
new file mode 100644
index 000000000000..81eaa94afeb0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/arena_htab.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#define BPF_NO_KFUNC_PROTOTYPES
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_experimental.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARENA);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__uint(max_entries, 100); /* number of pages */
+} arena SEC(".maps");
+
+#include "bpf_arena_htab.h"
+
+void __arena *htab_for_user;
+bool skip = false;
+
+int zero = 0;
+char __arena arr1[100000];
+char arr2[1000];
+
+SEC("syscall")
+int arena_htab_llvm(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST) || defined(BPF_ARENA_FORCE_ASM)
+	struct htab __arena *htab;
+	char __arena *arr = arr1;
+	__u64 i;
+
+	htab = bpf_alloc(sizeof(*htab));
+	cast_kern(htab);
+	htab_init(htab);
+
+	cast_kern(arr);
+
+	/* first run. No old elems in the table */
+	for (i = zero; i < 100000 && can_loop; i++) {
+		htab_update_elem(htab, i, i);
+		arr[i] = i;
+	}
+
+	/* should replace some elems with new ones */
+	for (i = zero; i < 1000 && can_loop; i++) {
+		htab_update_elem(htab, i, i);
+		/* Access mem to make the verifier use bounded loop logic */
+		arr2[i] = i;
+	}
+	cast_user(htab);
+	htab_for_user = htab;
+#else
+	skip = true;
+#endif
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/arena_htab_asm.c b/tools/testing/selftests/bpf/progs/arena_htab_asm.c
new file mode 100644
index 000000000000..6cd70ea12f0d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/arena_htab_asm.c
@@ -0,0 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#define BPF_ARENA_FORCE_ASM
+#define arena_htab_llvm arena_htab_asm
+#include "arena_htab.c"
diff --git a/tools/testing/selftests/bpf/progs/arena_list.c b/tools/testing/selftests/bpf/progs/arena_list.c
new file mode 100644
index 000000000000..3a2ddcacbea6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/arena_list.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#define BPF_NO_KFUNC_PROTOTYPES
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_experimental.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARENA);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__uint(max_entries, 100); /* number of pages */
+#ifdef __TARGET_ARCH_arm64
+	__ulong(map_extra, 0x1ull << 32); /* start of mmap() region */
+#else
+	__ulong(map_extra, 0x1ull << 44); /* start of mmap() region */
+#endif
+} arena SEC(".maps");
+
+#include "bpf_arena_alloc.h"
+#include "bpf_arena_list.h"
+
+struct elem {
+	struct arena_list_node node;
+	__u64 value;
+};
+
+struct arena_list_head __arena *list_head;
+int list_sum;
+int cnt;
+bool skip = false;
+
+#ifdef __BPF_FEATURE_ADDR_SPACE_CAST
+long __arena arena_sum;
+int __arena test_val = 1;
+struct arena_list_head __arena global_head;
+#else
+long arena_sum SEC(".addr_space.1");
+int test_val SEC(".addr_space.1");
+#endif
+
+int zero;
+
+SEC("syscall")
+int arena_list_add(void *ctx)
+{
+#ifdef __BPF_FEATURE_ADDR_SPACE_CAST
+	__u64 i;
+
+	list_head = &global_head;
+
+	for (i = zero; i < cnt && can_loop; i++) {
+		struct elem __arena *n = bpf_alloc(sizeof(*n));
+
+		test_val++;
+		n->value = i;
+		arena_sum += i;
+		list_add_head(&n->node, list_head);
+	}
+#else
+	skip = true;
+#endif
+	return 0;
+}
+
+SEC("syscall")
+int arena_list_del(void *ctx)
+{
+#ifdef __BPF_FEATURE_ADDR_SPACE_CAST
+	struct elem __arena *n;
+	int sum = 0;
+
+	arena_sum = 0;
+	list_for_each_entry(n, list_head, node) {
+		sum += n->value;
+		arena_sum += n->value;
+		list_del(&n->node);
+		bpf_free(n);
+	}
+	list_sum = sum;
+#else
+	skip = true;
+#endif
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/arena_spin_lock.c b/tools/testing/selftests/bpf/progs/arena_spin_lock.c
new file mode 100644
index 000000000000..086b57a426cf
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/arena_spin_lock.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "bpf_arena_spin_lock.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARENA);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__uint(max_entries, 100); /* number of pages */
+#ifdef __TARGET_ARCH_arm64
+	__ulong(map_extra, 0x1ull << 32); /* start of mmap() region */
+#else
+	__ulong(map_extra, 0x1ull << 44); /* start of mmap() region */
+#endif
+} arena SEC(".maps");
+
+int cs_count;
+
+#if defined(ENABLE_ATOMICS_TESTS) && defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+arena_spinlock_t __arena lock;
+int test_skip = 1;
+#else
+int test_skip = 2;
+#endif
+
+int counter;
+int limit;
+
+SEC("tc")
+int prog(void *ctx)
+{
+	int ret = -2;
+
+#if defined(ENABLE_ATOMICS_TESTS) && defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	unsigned long flags;
+
+	if ((ret = arena_spin_lock_irqsave(&lock, flags))) {
+		if (ret == -EOPNOTSUPP)
+			test_skip = 3;
+		return ret;
+	}
+	if (counter != limit)
+		counter++;
+	bpf_repeat(cs_count);
+	ret = 0;
+	arena_spin_unlock_irqrestore(&lock, flags);
+#endif
+	return ret;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/arena_strsearch.c b/tools/testing/selftests/bpf/progs/arena_strsearch.c
new file mode 100644
index 000000000000..ef6b76658f7f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/arena_strsearch.c
@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include "bpf_experimental.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARENA);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__uint(max_entries, 100); /* number of pages */
+} arena SEC(".maps");
+
+#include "bpf_arena_strsearch.h"
+
+struct glob_test {
+	char const __arena *pat, *str;
+	bool expected;
+};
+
+static bool test(char const __arena *pat, char const __arena *str, bool expected)
+{
+	bool match = glob_match(pat, str);
+	bool success = match == expected;
+
+	/* bpf_printk("glob_match %s %s res %d ok %d", pat, str, match, success); */
+	return success;
+}
+
+/*
+ * The tests are all jammed together in one array to make it simpler
+ * to place that array in the .init.rodata section.  The obvious
+ * "array of structures containing char *" has no way to force the
+ * pointed-to strings to be in a particular section.
+ *
+ * Anyway, a test consists of:
+ * 1. Expected glob_match result: '1' or '0'.
+ * 2. Pattern to match: null-terminated string
+ * 3. String to match against: null-terminated string
+ *
+ * The list of tests is terminated with a final '\0' instead of
+ * a glob_match result character.
+ */
+static const char __arena glob_tests[] =
+	/* Some basic tests */
+	"1" "a\0" "a\0"
+	"0" "a\0" "b\0"
+	"0" "a\0" "aa\0"
+	"0" "a\0" "\0"
+	"1" "\0" "\0"
+	"0" "\0" "a\0"
+	/* Simple character class tests */
+	"1" "[a]\0" "a\0"
+	"0" "[a]\0" "b\0"
+	"0" "[!a]\0" "a\0"
+	"1" "[!a]\0" "b\0"
+	"1" "[ab]\0" "a\0"
+	"1" "[ab]\0" "b\0"
+	"0" "[ab]\0" "c\0"
+	"1" "[!ab]\0" "c\0"
+	"1" "[a-c]\0" "b\0"
+	"0" "[a-c]\0" "d\0"
+	/* Corner cases in character class parsing */
+	"1" "[a-c-e-g]\0" "-\0"
+	"0" "[a-c-e-g]\0" "d\0"
+	"1" "[a-c-e-g]\0" "f\0"
+	"1" "[]a-ceg-ik[]\0" "a\0"
+	"1" "[]a-ceg-ik[]\0" "]\0"
+	"1" "[]a-ceg-ik[]\0" "[\0"
+	"1" "[]a-ceg-ik[]\0" "h\0"
+	"0" "[]a-ceg-ik[]\0" "f\0"
+	"0" "[!]a-ceg-ik[]\0" "h\0"
+	"0" "[!]a-ceg-ik[]\0" "]\0"
+	"1" "[!]a-ceg-ik[]\0" "f\0"
+	/* Simple wild cards */
+	"1" "?\0" "a\0"
+	"0" "?\0" "aa\0"
+	"0" "??\0" "a\0"
+	"1" "?x?\0" "axb\0"
+	"0" "?x?\0" "abx\0"
+	"0" "?x?\0" "xab\0"
+	/* Asterisk wild cards (backtracking) */
+	"0" "*??\0" "a\0"
+	"1" "*??\0" "ab\0"
+	"1" "*??\0" "abc\0"
+	"1" "*??\0" "abcd\0"
+	"0" "??*\0" "a\0"
+	"1" "??*\0" "ab\0"
+	"1" "??*\0" "abc\0"
+	"1" "??*\0" "abcd\0"
+	"0" "?*?\0" "a\0"
+	"1" "?*?\0" "ab\0"
+	"1" "?*?\0" "abc\0"
+	"1" "?*?\0" "abcd\0"
+	"1" "*b\0" "b\0"
+	"1" "*b\0" "ab\0"
+	"0" "*b\0" "ba\0"
+	"1" "*b\0" "bb\0"
+	"1" "*b\0" "abb\0"
+	"1" "*b\0" "bab\0"
+	"1" "*bc\0" "abbc\0"
+	"1" "*bc\0" "bc\0"
+	"1" "*bc\0" "bbc\0"
+	"1" "*bc\0" "bcbc\0"
+	/* Multiple asterisks (complex backtracking) */
+	"1" "*ac*\0" "abacadaeafag\0"
+	"1" "*ac*ae*ag*\0" "abacadaeafag\0"
+	"1" "*a*b*[bc]*[ef]*g*\0" "abacadaeafag\0"
+	"0" "*a*b*[ef]*[cd]*g*\0" "abacadaeafag\0"
+	"1" "*abcd*\0" "abcabcabcabcdefg\0"
+	"1" "*ab*cd*\0" "abcabcabcabcdefg\0"
+	"1" "*abcd*abcdef*\0" "abcabcdabcdeabcdefg\0"
+	"0" "*abcd*\0" "abcabcabcabcefg\0"
+	"0" "*ab*cd*\0" "abcabcabcabcefg\0";
+
+bool skip = false;
+
+SEC("syscall")
+int arena_strsearch(void *ctx)
+{
+	unsigned successes = 0;
+	unsigned n = 0;
+	char const __arena *p = glob_tests;
+
+	/*
+	 * Tests are jammed together in a string.  The first byte is '1'
+	 * or '0' to indicate the expected outcome, or '\0' to indicate the
+	 * end of the tests.  Then come two null-terminated strings: the
+	 * pattern and the string to match it against.
+	 */
+	while (*p) {
+		bool expected = *p++ & 1;
+		char const __arena *pat = p;
+
+		cond_break;
+		p += bpf_arena_strlen(p) + 1;
+		successes += test(pat, p, expected);
+		p += bpf_arena_strlen(p) + 1;
+		n++;
+	}
+
+	n -= successes;
+	/* bpf_printk("glob: %u self-tests passed, %u failed\n", successes, n); */
+
+	return n ? -1 : 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/async_stack_depth.c b/tools/testing/selftests/bpf/progs/async_stack_depth.c
new file mode 100644
index 000000000000..36734683acbd
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/async_stack_depth.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+
+struct hmap_elem {
+	struct bpf_timer timer;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 64);
+	__type(key, int);
+	__type(value, struct hmap_elem);
+} hmap SEC(".maps");
+
+__attribute__((noinline))
+static int timer_cb(void *map, int *key, struct bpf_timer *timer)
+{
+	volatile char buf[256] = {};
+	return buf[69];
+}
+
+__attribute__((noinline))
+static int bad_timer_cb(void *map, int *key, struct bpf_timer *timer)
+{
+	volatile char buf[300] = {};
+	return buf[255] + timer_cb(NULL, NULL, NULL);
+}
+
+SEC("tc")
+__failure __msg("combined stack size of 2 calls is")
+int pseudo_call_check(struct __sk_buff *ctx)
+{
+	struct hmap_elem *elem;
+	volatile char buf[256] = {};
+
+	elem = bpf_map_lookup_elem(&hmap, &(int){0});
+	if (!elem)
+		return 0;
+
+	timer_cb(NULL, NULL, NULL);
+	return bpf_timer_set_callback(&elem->timer, timer_cb) + buf[0];
+}
+
+SEC("tc")
+__failure __msg("combined stack size of 2 calls is")
+int async_call_root_check(struct __sk_buff *ctx)
+{
+	struct hmap_elem *elem;
+	volatile char buf[256] = {};
+
+	elem = bpf_map_lookup_elem(&hmap, &(int){0});
+	if (!elem)
+		return 0;
+
+	return bpf_timer_set_callback(&elem->timer, bad_timer_cb) + buf[0];
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bad_struct_ops.c b/tools/testing/selftests/bpf/progs/bad_struct_ops.c
new file mode 100644
index 000000000000..b3f77b4561c8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bad_struct_ops.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("struct_ops/test_1")
+int BPF_PROG(test_1) { return 0; }
+
+SEC("struct_ops/test_2")
+int BPF_PROG(test_2) { return 0; }
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_1 = {
+	.test_1 = (void *)test_1,
+	.test_2 = (void *)test_2
+};
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops2 testmod_2 = {
+	.test_1 = (void *)test_1
+};
diff --git a/tools/testing/selftests/bpf/progs/bad_struct_ops2.c b/tools/testing/selftests/bpf/progs/bad_struct_ops2.c
new file mode 100644
index 000000000000..64a95f6be86d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bad_struct_ops2.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+/* This is an unused struct_ops program, it lacks corresponding
+ * struct_ops map, which provides attachment information.
+ * W/o additional configuration attempt to load such
+ * BPF object file would fail.
+ */
+SEC("struct_ops/foo")
+void foo(void) {}
diff --git a/tools/testing/selftests/bpf/progs/bench_local_storage_create.c b/tools/testing/selftests/bpf/progs/bench_local_storage_create.c
new file mode 100644
index 000000000000..c8ec0d0368e4
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bench_local_storage_create.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+long create_errs = 0;
+long create_cnts = 0;
+long kmalloc_cnts = 0;
+__u32 bench_pid = 0;
+
+struct storage {
+	__u8 data[64];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct storage);
+} sk_storage_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct storage);
+} task_storage_map SEC(".maps");
+
+SEC("raw_tp/kmalloc")
+int BPF_PROG(kmalloc, unsigned long call_site, const void *ptr,
+	     size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags,
+	     int node)
+{
+	__sync_fetch_and_add(&kmalloc_cnts, 1);
+
+	return 0;
+}
+
+SEC("tp_btf/sched_process_fork")
+int BPF_PROG(sched_process_fork, struct task_struct *parent, struct task_struct *child)
+{
+	struct storage *stg;
+
+	if (parent->tgid != bench_pid)
+		return 0;
+
+	stg = bpf_task_storage_get(&task_storage_map, child, NULL,
+				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (stg)
+		__sync_fetch_and_add(&create_cnts, 1);
+	else
+		__sync_fetch_and_add(&create_errs, 1);
+
+	return 0;
+}
+
+SEC("lsm.s/socket_post_create")
+int BPF_PROG(socket_post_create, struct socket *sock, int family, int type,
+	     int protocol, int kern)
+{
+	struct sock *sk = sock->sk;
+	struct storage *stg;
+	__u32 pid;
+
+	pid = bpf_get_current_pid_tgid() >> 32;
+	if (pid != bench_pid || !sk)
+		return 0;
+
+	stg = bpf_sk_storage_get(&sk_storage_map, sk, NULL,
+				 BPF_LOCAL_STORAGE_GET_F_CREATE);
+
+	if (stg)
+		__sync_fetch_and_add(&create_cnts, 1);
+	else
+		__sync_fetch_and_add(&create_errs, 1);
+
+	return 0;
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bench_sockmap_prog.c b/tools/testing/selftests/bpf/progs/bench_sockmap_prog.c
new file mode 100644
index 000000000000..079bf3794b3a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bench_sockmap_prog.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+long process_byte = 0;
+int  verdict_dir = 0;
+int  dropped = 0;
+int  pkt_size = 0;
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 20);
+	__type(key, int);
+	__type(value, int);
+} sock_map_rx SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 20);
+	__type(key, int);
+	__type(value, int);
+} sock_map_tx SEC(".maps");
+
+SEC("sk_skb/stream_parser")
+int prog_skb_parser(struct __sk_buff *skb)
+{
+	return pkt_size;
+}
+
+SEC("sk_skb/stream_verdict")
+int prog_skb_verdict(struct __sk_buff *skb)
+{
+	int one = 1;
+	int ret =  bpf_sk_redirect_map(skb, &sock_map_rx, one, verdict_dir);
+
+	if (ret == SK_DROP)
+		dropped++;
+	__sync_fetch_and_add(&process_byte, skb->len);
+	return ret;
+}
+
+SEC("sk_skb/stream_verdict")
+int prog_skb_pass(struct __sk_buff *skb)
+{
+	__sync_fetch_and_add(&process_byte, skb->len);
+	return SK_PASS;
+}
+
+SEC("sk_msg")
+int prog_skmsg_verdict(struct sk_msg_md *msg)
+{
+	int one = 1;
+
+	__sync_fetch_and_add(&process_byte, msg->size);
+	return bpf_msg_redirect_map(msg, &sock_map_tx, one, verdict_dir);
+}
+
+SEC("sk_msg")
+int prog_skmsg_pass(struct sk_msg_md *msg)
+{
+	__sync_fetch_and_add(&process_byte, msg->size);
+	return SK_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bind4_prog.c b/tools/testing/selftests/bpf/progs/bind4_prog.c
index a487f60b73ac..b7ddf8ec4ee8 100644
--- a/tools/testing/selftests/bpf/progs/bind4_prog.c
+++ b/tools/testing/selftests/bpf/progs/bind4_prog.c
@@ -12,6 +12,8 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
+#include "bind_prog.h"
+
 #define SERV4_IP		0xc0a801feU /* 192.168.1.254 */
 #define SERV4_PORT		4040
 #define SERV4_REWRITE_IP	0x7f000001U /* 127.0.0.1 */
@@ -118,23 +120,23 @@ int bind_v4_prog(struct bpf_sock_addr *ctx)
 
 	// u8 narrow loads:
 	user_ip4 = 0;
-	user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[0] << 0;
-	user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[1] << 8;
-	user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[2] << 16;
-	user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[3] << 24;
+	user_ip4 |= load_byte(ctx->user_ip4, 0, sizeof(user_ip4));
+	user_ip4 |= load_byte(ctx->user_ip4, 1, sizeof(user_ip4));
+	user_ip4 |= load_byte(ctx->user_ip4, 2, sizeof(user_ip4));
+	user_ip4 |= load_byte(ctx->user_ip4, 3, sizeof(user_ip4));
 	if (ctx->user_ip4 != user_ip4)
 		return 0;
 
 	user_port = 0;
-	user_port |= ((volatile __u8 *)&ctx->user_port)[0] << 0;
-	user_port |= ((volatile __u8 *)&ctx->user_port)[1] << 8;
+	user_port |= load_byte(ctx->user_port, 0, sizeof(user_port));
+	user_port |= load_byte(ctx->user_port, 1, sizeof(user_port));
 	if (ctx->user_port != user_port)
 		return 0;
 
 	// u16 narrow loads:
 	user_ip4 = 0;
-	user_ip4 |= ((volatile __u16 *)&ctx->user_ip4)[0] << 0;
-	user_ip4 |= ((volatile __u16 *)&ctx->user_ip4)[1] << 16;
+	user_ip4 |= load_word(ctx->user_ip4, 0, sizeof(user_ip4));
+	user_ip4 |= load_word(ctx->user_ip4, 1, sizeof(user_ip4));
 	if (ctx->user_ip4 != user_ip4)
 		return 0;
 
@@ -156,4 +158,10 @@ int bind_v4_prog(struct bpf_sock_addr *ctx)
 	return 1;
 }
 
+SEC("cgroup/bind4")
+int bind_v4_deny_prog(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bind6_prog.c b/tools/testing/selftests/bpf/progs/bind6_prog.c
index d62cd9e9cf0e..501c3fc11d35 100644
--- a/tools/testing/selftests/bpf/progs/bind6_prog.c
+++ b/tools/testing/selftests/bpf/progs/bind6_prog.c
@@ -12,6 +12,8 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
+#include "bind_prog.h"
+
 #define SERV6_IP_0		0xfaceb00c /* face:b00c:1234:5678::abcd */
 #define SERV6_IP_1		0x12345678
 #define SERV6_IP_2		0x00000000
@@ -129,25 +131,25 @@ int bind_v6_prog(struct bpf_sock_addr *ctx)
 	// u8 narrow loads:
 	for (i = 0; i < 4; i++) {
 		user_ip6 = 0;
-		user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[0] << 0;
-		user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[1] << 8;
-		user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[2] << 16;
-		user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[3] << 24;
+		user_ip6 |= load_byte(ctx->user_ip6[i], 0, sizeof(user_ip6));
+		user_ip6 |= load_byte(ctx->user_ip6[i], 1, sizeof(user_ip6));
+		user_ip6 |= load_byte(ctx->user_ip6[i], 2, sizeof(user_ip6));
+		user_ip6 |= load_byte(ctx->user_ip6[i], 3, sizeof(user_ip6));
 		if (ctx->user_ip6[i] != user_ip6)
 			return 0;
 	}
 
 	user_port = 0;
-	user_port |= ((volatile __u8 *)&ctx->user_port)[0] << 0;
-	user_port |= ((volatile __u8 *)&ctx->user_port)[1] << 8;
+	user_port |= load_byte(ctx->user_port, 0, sizeof(user_port));
+	user_port |= load_byte(ctx->user_port, 1, sizeof(user_port));
 	if (ctx->user_port != user_port)
 		return 0;
 
 	// u16 narrow loads:
 	for (i = 0; i < 4; i++) {
 		user_ip6 = 0;
-		user_ip6 |= ((volatile __u16 *)&ctx->user_ip6[i])[0] << 0;
-		user_ip6 |= ((volatile __u16 *)&ctx->user_ip6[i])[1] << 16;
+		user_ip6 |= load_word(ctx->user_ip6[i], 0, sizeof(user_ip6));
+		user_ip6 |= load_word(ctx->user_ip6[i], 1, sizeof(user_ip6));
 		if (ctx->user_ip6[i] != user_ip6)
 			return 0;
 	}
@@ -173,4 +175,10 @@ int bind_v6_prog(struct bpf_sock_addr *ctx)
 	return 1;
 }
 
+SEC("cgroup/bind6")
+int bind_v6_deny_prog(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bind_prog.h b/tools/testing/selftests/bpf/progs/bind_prog.h
new file mode 100644
index 000000000000..e830caa940c3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bind_prog.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BIND_PROG_H__
+#define __BIND_PROG_H__
+
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+#define load_byte(src, b, s) \
+	(((volatile __u8 *)&(src))[b] << 8 * b)
+#define load_word(src, w, s) \
+	(((volatile __u16 *)&(src))[w] << 16 * w)
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+#define load_byte(src, b, s) \
+	(((volatile __u8 *)&(src))[(b) + (sizeof(src) - (s))] << 8 * ((s) - (b) - 1))
+#define load_word(src, w, s) \
+	(((volatile __u16 *)&(src))[w] << 16 * (((s) / 2) - (w) - 1))
+#else
+# error "Fix your compiler's __BYTE_ORDER__?!"
+#endif
+
+#endif
diff --git a/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h b/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h
new file mode 100644
index 000000000000..f90531cf3ee5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h
@@ -0,0 +1,542 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#ifndef BPF_ARENA_SPIN_LOCK_H
+#define BPF_ARENA_SPIN_LOCK_H
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_atomic.h"
+
+#define arch_mcs_spin_lock_contended_label(l, label) smp_cond_load_acquire_label(l, VAL, label)
+#define arch_mcs_spin_unlock_contended(l) smp_store_release((l), 1)
+
+#if defined(ENABLE_ATOMICS_TESTS) && defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+
+#define EBUSY 16
+#define EOPNOTSUPP 95
+#define ETIMEDOUT 110
+
+#ifndef __arena
+#define __arena __attribute__((address_space(1)))
+#endif
+
+extern unsigned long CONFIG_NR_CPUS __kconfig;
+
+/*
+ * Typically, we'd just rely on the definition in vmlinux.h for qspinlock, but
+ * PowerPC overrides the definition to define lock->val as u32 instead of
+ * atomic_t, leading to compilation errors.  Import a local definition below so
+ * that we don't depend on the vmlinux.h version.
+ */
+
+struct __qspinlock {
+	union {
+		atomic_t val;
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+		struct {
+			u8 locked;
+			u8 pending;
+		};
+		struct {
+			u16 locked_pending;
+			u16 tail;
+		};
+#else
+		struct {
+			u16 tail;
+			u16 locked_pending;
+		};
+		struct {
+			u8 reserved[2];
+			u8 pending;
+			u8 locked;
+		};
+#endif
+	};
+};
+
+#define arena_spinlock_t struct __qspinlock
+/* FIXME: Using typedef causes CO-RE relocation error */
+/* typedef struct qspinlock arena_spinlock_t; */
+
+struct arena_mcs_spinlock {
+	struct arena_mcs_spinlock __arena *next;
+	int locked;
+	int count;
+};
+
+struct arena_qnode {
+	struct arena_mcs_spinlock mcs;
+};
+
+#define _Q_MAX_NODES		4
+#define _Q_PENDING_LOOPS	1
+
+/*
+ * Bitfields in the atomic value:
+ *
+ *  0- 7: locked byte
+ *     8: pending
+ *  9-15: not used
+ * 16-17: tail index
+ * 18-31: tail cpu (+1)
+ */
+#define _Q_MAX_CPUS		1024
+
+#define	_Q_SET_MASK(type)	(((1U << _Q_ ## type ## _BITS) - 1)\
+				      << _Q_ ## type ## _OFFSET)
+#define _Q_LOCKED_OFFSET	0
+#define _Q_LOCKED_BITS		8
+#define _Q_LOCKED_MASK		_Q_SET_MASK(LOCKED)
+
+#define _Q_PENDING_OFFSET	(_Q_LOCKED_OFFSET + _Q_LOCKED_BITS)
+#define _Q_PENDING_BITS		8
+#define _Q_PENDING_MASK		_Q_SET_MASK(PENDING)
+
+#define _Q_TAIL_IDX_OFFSET	(_Q_PENDING_OFFSET + _Q_PENDING_BITS)
+#define _Q_TAIL_IDX_BITS	2
+#define _Q_TAIL_IDX_MASK	_Q_SET_MASK(TAIL_IDX)
+
+#define _Q_TAIL_CPU_OFFSET	(_Q_TAIL_IDX_OFFSET + _Q_TAIL_IDX_BITS)
+#define _Q_TAIL_CPU_BITS	(32 - _Q_TAIL_CPU_OFFSET)
+#define _Q_TAIL_CPU_MASK	_Q_SET_MASK(TAIL_CPU)
+
+#define _Q_TAIL_OFFSET		_Q_TAIL_IDX_OFFSET
+#define _Q_TAIL_MASK		(_Q_TAIL_IDX_MASK | _Q_TAIL_CPU_MASK)
+
+#define _Q_LOCKED_VAL		(1U << _Q_LOCKED_OFFSET)
+#define _Q_PENDING_VAL		(1U << _Q_PENDING_OFFSET)
+
+struct arena_qnode __arena qnodes[_Q_MAX_CPUS][_Q_MAX_NODES];
+
+static inline u32 encode_tail(int cpu, int idx)
+{
+	u32 tail;
+
+	tail  = (cpu + 1) << _Q_TAIL_CPU_OFFSET;
+	tail |= idx << _Q_TAIL_IDX_OFFSET; /* assume < 4 */
+
+	return tail;
+}
+
+static inline struct arena_mcs_spinlock __arena *decode_tail(u32 tail)
+{
+	u32 cpu = (tail >> _Q_TAIL_CPU_OFFSET) - 1;
+	u32 idx = (tail &  _Q_TAIL_IDX_MASK) >> _Q_TAIL_IDX_OFFSET;
+
+	return &qnodes[cpu][idx].mcs;
+}
+
+static inline
+struct arena_mcs_spinlock __arena *grab_mcs_node(struct arena_mcs_spinlock __arena *base, int idx)
+{
+	return &((struct arena_qnode __arena *)base + idx)->mcs;
+}
+
+#define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK)
+
+/**
+ * xchg_tail - Put in the new queue tail code word & retrieve previous one
+ * @lock : Pointer to queued spinlock structure
+ * @tail : The new queue tail code word
+ * Return: The previous queue tail code word
+ *
+ * xchg(lock, tail)
+ *
+ * p,*,* -> n,*,* ; prev = xchg(lock, node)
+ */
+static __always_inline u32 xchg_tail(arena_spinlock_t __arena *lock, u32 tail)
+{
+	u32 old, new;
+
+	old = atomic_read(&lock->val);
+	do {
+		new = (old & _Q_LOCKED_PENDING_MASK) | tail;
+		/*
+		 * We can use relaxed semantics since the caller ensures that
+		 * the MCS node is properly initialized before updating the
+		 * tail.
+		 */
+		/* These loops are not expected to stall, but we still need to
+		 * prove to the verifier they will terminate eventually.
+		 */
+		cond_break_label(out);
+	} while (!atomic_try_cmpxchg_relaxed(&lock->val, &old, new));
+
+	return old;
+out:
+	bpf_printk("RUNTIME ERROR: %s unexpected cond_break exit!!!", __func__);
+	return old;
+}
+
+/**
+ * clear_pending - clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,* -> *,0,*
+ */
+static __always_inline void clear_pending(arena_spinlock_t __arena *lock)
+{
+	WRITE_ONCE(lock->pending, 0);
+}
+
+/**
+ * clear_pending_set_locked - take ownership and clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,0 -> *,0,1
+ *
+ * Lock stealing is not allowed if this function is used.
+ */
+static __always_inline void clear_pending_set_locked(arena_spinlock_t __arena *lock)
+{
+	WRITE_ONCE(lock->locked_pending, _Q_LOCKED_VAL);
+}
+
+/**
+ * set_locked - Set the lock bit and own the lock
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,*,0 -> *,0,1
+ */
+static __always_inline void set_locked(arena_spinlock_t __arena *lock)
+{
+	WRITE_ONCE(lock->locked, _Q_LOCKED_VAL);
+}
+
+static __always_inline
+u32 arena_fetch_set_pending_acquire(arena_spinlock_t __arena *lock)
+{
+	u32 old, new;
+
+	old = atomic_read(&lock->val);
+	do {
+		new = old | _Q_PENDING_VAL;
+		/*
+		 * These loops are not expected to stall, but we still need to
+		 * prove to the verifier they will terminate eventually.
+		 */
+		cond_break_label(out);
+	} while (!atomic_try_cmpxchg_acquire(&lock->val, &old, new));
+
+	return old;
+out:
+	bpf_printk("RUNTIME ERROR: %s unexpected cond_break exit!!!", __func__);
+	return old;
+}
+
+/**
+ * arena_spin_trylock - try to acquire the queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ * Return: 1 if lock acquired, 0 if failed
+ */
+static __always_inline int arena_spin_trylock(arena_spinlock_t __arena *lock)
+{
+	int val = atomic_read(&lock->val);
+
+	if (unlikely(val))
+		return 0;
+
+	return likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL));
+}
+
+__noinline
+int arena_spin_lock_slowpath(arena_spinlock_t __arena __arg_arena *lock, u32 val)
+{
+	struct arena_mcs_spinlock __arena *prev, *next, *node0, *node;
+	int ret = -ETIMEDOUT;
+	u32 old, tail;
+	int idx;
+
+	/*
+	 * Wait for in-progress pending->locked hand-overs with a bounded
+	 * number of spins so that we guarantee forward progress.
+	 *
+	 * 0,1,0 -> 0,0,1
+	 */
+	if (val == _Q_PENDING_VAL) {
+		int cnt = _Q_PENDING_LOOPS;
+		val = atomic_cond_read_relaxed_label(&lock->val,
+						     (VAL != _Q_PENDING_VAL) || !cnt--,
+						     release_err);
+	}
+
+	/*
+	 * If we observe any contention; queue.
+	 */
+	if (val & ~_Q_LOCKED_MASK)
+		goto queue;
+
+	/*
+	 * trylock || pending
+	 *
+	 * 0,0,* -> 0,1,* -> 0,0,1 pending, trylock
+	 */
+	val = arena_fetch_set_pending_acquire(lock);
+
+	/*
+	 * If we observe contention, there is a concurrent locker.
+	 *
+	 * Undo and queue; our setting of PENDING might have made the
+	 * n,0,0 -> 0,0,0 transition fail and it will now be waiting
+	 * on @next to become !NULL.
+	 */
+	if (unlikely(val & ~_Q_LOCKED_MASK)) {
+
+		/* Undo PENDING if we set it. */
+		if (!(val & _Q_PENDING_MASK))
+			clear_pending(lock);
+
+		goto queue;
+	}
+
+	/*
+	 * We're pending, wait for the owner to go away.
+	 *
+	 * 0,1,1 -> *,1,0
+	 *
+	 * this wait loop must be a load-acquire such that we match the
+	 * store-release that clears the locked bit and create lock
+	 * sequentiality; this is because not all
+	 * clear_pending_set_locked() implementations imply full
+	 * barriers.
+	 */
+	if (val & _Q_LOCKED_MASK)
+		(void)smp_cond_load_acquire_label(&lock->locked, !VAL, release_err);
+
+	/*
+	 * take ownership and clear the pending bit.
+	 *
+	 * 0,1,0 -> 0,0,1
+	 */
+	clear_pending_set_locked(lock);
+	return 0;
+
+	/*
+	 * End of pending bit optimistic spinning and beginning of MCS
+	 * queuing.
+	 */
+queue:
+	node0 = &(qnodes[bpf_get_smp_processor_id()])[0].mcs;
+	idx = node0->count++;
+	tail = encode_tail(bpf_get_smp_processor_id(), idx);
+
+	/*
+	 * 4 nodes are allocated based on the assumption that there will not be
+	 * nested NMIs taking spinlocks. That may not be true in some
+	 * architectures even though the chance of needing more than 4 nodes
+	 * will still be extremely unlikely. When that happens, we simply return
+	 * an error. Original qspinlock has a trylock fallback in this case.
+	 */
+	if (unlikely(idx >= _Q_MAX_NODES)) {
+		ret = -EBUSY;
+		goto release_node_err;
+	}
+
+	node = grab_mcs_node(node0, idx);
+
+	/*
+	 * Ensure that we increment the head node->count before initialising
+	 * the actual node. If the compiler is kind enough to reorder these
+	 * stores, then an IRQ could overwrite our assignments.
+	 */
+	barrier();
+
+	node->locked = 0;
+	node->next = NULL;
+
+	/*
+	 * We touched a (possibly) cold cacheline in the per-cpu queue node;
+	 * attempt the trylock once more in the hope someone let go while we
+	 * weren't watching.
+	 */
+	if (arena_spin_trylock(lock))
+		goto release;
+
+	/*
+	 * Ensure that the initialisation of @node is complete before we
+	 * publish the updated tail via xchg_tail() and potentially link
+	 * @node into the waitqueue via WRITE_ONCE(prev->next, node) below.
+	 */
+	smp_wmb();
+
+	/*
+	 * Publish the updated tail.
+	 * We have already touched the queueing cacheline; don't bother with
+	 * pending stuff.
+	 *
+	 * p,*,* -> n,*,*
+	 */
+	old = xchg_tail(lock, tail);
+	next = NULL;
+
+	/*
+	 * if there was a previous node; link it and wait until reaching the
+	 * head of the waitqueue.
+	 */
+	if (old & _Q_TAIL_MASK) {
+		prev = decode_tail(old);
+
+		/* Link @node into the waitqueue. */
+		WRITE_ONCE(prev->next, node);
+
+		(void)arch_mcs_spin_lock_contended_label(&node->locked, release_node_err);
+
+		/*
+		 * While waiting for the MCS lock, the next pointer may have
+		 * been set by another lock waiter. We cannot prefetch here
+		 * due to lack of equivalent instruction in BPF ISA.
+		 */
+		next = READ_ONCE(node->next);
+	}
+
+	/*
+	 * we're at the head of the waitqueue, wait for the owner & pending to
+	 * go away.
+	 *
+	 * *,x,y -> *,0,0
+	 *
+	 * this wait loop must use a load-acquire such that we match the
+	 * store-release that clears the locked bit and create lock
+	 * sequentiality; this is because the set_locked() function below
+	 * does not imply a full barrier.
+	 */
+	val = atomic_cond_read_acquire_label(&lock->val, !(VAL & _Q_LOCKED_PENDING_MASK),
+					     release_node_err);
+
+	/*
+	 * claim the lock:
+	 *
+	 * n,0,0 -> 0,0,1 : lock, uncontended
+	 * *,*,0 -> *,*,1 : lock, contended
+	 *
+	 * If the queue head is the only one in the queue (lock value == tail)
+	 * and nobody is pending, clear the tail code and grab the lock.
+	 * Otherwise, we only need to grab the lock.
+	 */
+
+	/*
+	 * In the PV case we might already have _Q_LOCKED_VAL set, because
+	 * of lock stealing; therefore we must also allow:
+	 *
+	 * n,0,1 -> 0,0,1
+	 *
+	 * Note: at this point: (val & _Q_PENDING_MASK) == 0, because of the
+	 *       above wait condition, therefore any concurrent setting of
+	 *       PENDING will make the uncontended transition fail.
+	 */
+	if ((val & _Q_TAIL_MASK) == tail) {
+		if (atomic_try_cmpxchg_relaxed(&lock->val, &val, _Q_LOCKED_VAL))
+			goto release; /* No contention */
+	}
+
+	/*
+	 * Either somebody is queued behind us or _Q_PENDING_VAL got set
+	 * which will then detect the remaining tail and queue behind us
+	 * ensuring we'll see a @next.
+	 */
+	set_locked(lock);
+
+	/*
+	 * contended path; wait for next if not observed yet, release.
+	 */
+	if (!next)
+		next = smp_cond_load_relaxed_label(&node->next, (VAL), release_node_err);
+
+	arch_mcs_spin_unlock_contended(&next->locked);
+
+release:;
+	/*
+	 * release the node
+	 *
+	 * Doing a normal dec vs this_cpu_dec is fine. An upper context always
+	 * decrements count it incremented before returning, thus we're fine.
+	 * For contexts interrupting us, they either observe our dec or not.
+	 * Just ensure the compiler doesn't reorder this statement, as a
+	 * this_cpu_dec implicitly implied that.
+	 */
+	barrier();
+	node0->count--;
+	return 0;
+release_node_err:
+	barrier();
+	node0->count--;
+	goto release_err;
+release_err:
+	return ret;
+}
+
+/**
+ * arena_spin_lock - acquire a queued spinlock
+ * @lock: Pointer to queued spinlock structure
+ *
+ * On error, returned value will be negative.
+ * On success, zero is returned.
+ *
+ * The return value _must_ be tested against zero for success,
+ * instead of checking it against negative, for passing the
+ * BPF verifier.
+ *
+ * The user should do:
+ *	if (arena_spin_lock(...) != 0) // failure
+ *		or
+ *	if (arena_spin_lock(...) == 0) // success
+ *		or
+ *	if (arena_spin_lock(...)) // failure
+ *		or
+ *	if (!arena_spin_lock(...)) // success
+ * instead of:
+ *	if (arena_spin_lock(...) < 0) // failure
+ *
+ * The return value can still be inspected later.
+ */
+static __always_inline int arena_spin_lock(arena_spinlock_t __arena *lock)
+{
+	int val = 0;
+
+	if (CONFIG_NR_CPUS > 1024)
+		return -EOPNOTSUPP;
+
+	bpf_preempt_disable();
+	if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL)))
+		return 0;
+
+	val = arena_spin_lock_slowpath(lock, val);
+	/* FIXME: bpf_assert_range(-MAX_ERRNO, 0) once we have it working for all cases. */
+	if (val)
+		bpf_preempt_enable();
+	return val;
+}
+
+/**
+ * arena_spin_unlock - release a queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ */
+static __always_inline void arena_spin_unlock(arena_spinlock_t __arena *lock)
+{
+	/*
+	 * unlock() needs release semantics:
+	 */
+	smp_store_release(&lock->locked, 0);
+	bpf_preempt_enable();
+}
+
+#define arena_spin_lock_irqsave(lock, flags)             \
+	({                                               \
+		int __ret;                               \
+		bpf_local_irq_save(&(flags));            \
+		__ret = arena_spin_lock((lock));         \
+		if (__ret)                               \
+			bpf_local_irq_restore(&(flags)); \
+		(__ret);                                 \
+	})
+
+#define arena_spin_unlock_irqrestore(lock, flags) \
+	({                                        \
+		arena_spin_unlock((lock));        \
+		bpf_local_irq_restore(&(flags));  \
+	})
+
+#endif
+
+#endif /* BPF_ARENA_SPIN_LOCK_H */
diff --git a/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c
new file mode 100644
index 000000000000..9af19dfe4e80
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_cc_cubic.c
@@ -0,0 +1,180 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/* Highlights:
+ * 1. The major difference between this bpf program and tcp_cubic.c
+ *    is that this bpf program relies on `cong_control` rather than
+ *    `cong_avoid` in the struct tcp_congestion_ops.
+ * 2. Logic such as tcp_cwnd_reduction, tcp_cong_avoid, and
+ *    tcp_update_pacing_rate is bypassed when `cong_control` is
+ *    defined, so moving these logic to `cong_control`.
+ * 3. WARNING: This bpf program is NOT the same as tcp_cubic.c.
+ *    The main purpose is to show use cases of the arguments in
+ *    `cong_control`. For simplicity's sake, it reuses tcp cubic's
+ *    kernel functions.
+ */
+
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#define USEC_PER_SEC 1000000UL
+#define TCP_PACING_SS_RATIO (200)
+#define TCP_PACING_CA_RATIO (120)
+#define TCP_REORDERING (12)
+
+extern void cubictcp_init(struct sock *sk) __ksym;
+extern void cubictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) __ksym;
+extern __u32 cubictcp_recalc_ssthresh(struct sock *sk) __ksym;
+extern void cubictcp_state(struct sock *sk, __u8 new_state) __ksym;
+extern __u32 tcp_reno_undo_cwnd(struct sock *sk) __ksym;
+extern void cubictcp_acked(struct sock *sk, const struct ack_sample *sample) __ksym;
+extern void cubictcp_cong_avoid(struct sock *sk, __u32 ack, __u32 acked) __ksym;
+
+static __u64 div64_u64(__u64 dividend, __u64 divisor)
+{
+	return dividend / divisor;
+}
+
+static void tcp_update_pacing_rate(struct sock *sk)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+	__u64 rate;
+
+	/* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */
+	rate = (__u64)tp->mss_cache * ((USEC_PER_SEC / 100) << 3);
+
+	/* current rate is (cwnd * mss) / srtt
+	 * In Slow Start [1], set sk_pacing_rate to 200 % the current rate.
+	 * In Congestion Avoidance phase, set it to 120 % the current rate.
+	 *
+	 * [1] : Normal Slow Start condition is (tp->snd_cwnd < tp->snd_ssthresh)
+	 *	 If snd_cwnd >= (tp->snd_ssthresh / 2), we are approaching
+	 *	 end of slow start and should slow down.
+	 */
+	if (tp->snd_cwnd < tp->snd_ssthresh / 2)
+		rate *= TCP_PACING_SS_RATIO;
+	else
+		rate *= TCP_PACING_CA_RATIO;
+
+	rate *= max(tp->snd_cwnd, tp->packets_out);
+
+	if (tp->srtt_us)
+		rate = div64_u64(rate, (__u64)tp->srtt_us);
+
+	sk->sk_pacing_rate = min(rate, sk->sk_max_pacing_rate);
+}
+
+static void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked,
+			       int newly_lost, int flag)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	int sndcnt = 0;
+	__u32 pkts_in_flight = tp->packets_out - (tp->sacked_out + tp->lost_out) + tp->retrans_out;
+	int delta = tp->snd_ssthresh - pkts_in_flight;
+
+	if (newly_acked_sacked <= 0 || !tp->prior_cwnd)
+		return;
+
+	__u32 prr_delivered = tp->prr_delivered + newly_acked_sacked;
+
+	if (delta < 0) {
+		__u64 dividend =
+			(__u64)tp->snd_ssthresh * prr_delivered + tp->prior_cwnd - 1;
+		sndcnt = (__u32)div64_u64(dividend, (__u64)tp->prior_cwnd) - tp->prr_out;
+	} else {
+		sndcnt = max(prr_delivered - tp->prr_out, newly_acked_sacked);
+		if (flag & FLAG_SND_UNA_ADVANCED && !newly_lost)
+			sndcnt++;
+		sndcnt = min(delta, sndcnt);
+	}
+	/* Force a fast retransmit upon entering fast recovery */
+	sndcnt = max(sndcnt, (tp->prr_out ? 0 : 1));
+	tp->snd_cwnd = pkts_in_flight + sndcnt;
+}
+
+/* Decide whether to run the increase function of congestion control. */
+static bool tcp_may_raise_cwnd(const struct sock *sk, const int flag)
+{
+	if (tcp_sk(sk)->reordering > TCP_REORDERING)
+		return flag & FLAG_FORWARD_PROGRESS;
+
+	return flag & FLAG_DATA_ACKED;
+}
+
+SEC("struct_ops")
+void BPF_PROG(bpf_cubic_init, struct sock *sk)
+{
+	cubictcp_init(sk);
+}
+
+SEC("struct_ops")
+void BPF_PROG(bpf_cubic_cwnd_event, struct sock *sk, enum tcp_ca_event event)
+{
+	cubictcp_cwnd_event(sk, event);
+}
+
+SEC("struct_ops")
+void BPF_PROG(bpf_cubic_cong_control, struct sock *sk, __u32 ack, int flag,
+	      const struct rate_sample *rs)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (((1<<TCP_CA_CWR) | (1<<TCP_CA_Recovery)) &
+			(1 << inet_csk(sk)->icsk_ca_state)) {
+		/* Reduce cwnd if state mandates */
+		tcp_cwnd_reduction(sk, rs->acked_sacked, rs->losses, flag);
+
+		if (!before(tp->snd_una, tp->high_seq)) {
+			/* Reset cwnd to ssthresh in CWR or Recovery (unless it's undone) */
+			if (tp->snd_ssthresh < TCP_INFINITE_SSTHRESH &&
+					inet_csk(sk)->icsk_ca_state == TCP_CA_CWR) {
+				tp->snd_cwnd = tp->snd_ssthresh;
+				tp->snd_cwnd_stamp = tcp_jiffies32;
+			}
+		}
+	} else if (tcp_may_raise_cwnd(sk, flag)) {
+		/* Advance cwnd if state allows */
+		cubictcp_cong_avoid(sk, ack, rs->acked_sacked);
+		tp->snd_cwnd_stamp = tcp_jiffies32;
+	}
+
+	tcp_update_pacing_rate(sk);
+}
+
+SEC("struct_ops")
+__u32 BPF_PROG(bpf_cubic_recalc_ssthresh, struct sock *sk)
+{
+	return cubictcp_recalc_ssthresh(sk);
+}
+
+SEC("struct_ops")
+void BPF_PROG(bpf_cubic_state, struct sock *sk, __u8 new_state)
+{
+	cubictcp_state(sk, new_state);
+}
+
+SEC("struct_ops")
+void BPF_PROG(bpf_cubic_acked, struct sock *sk, const struct ack_sample *sample)
+{
+	cubictcp_acked(sk, sample);
+}
+
+SEC("struct_ops")
+__u32 BPF_PROG(bpf_cubic_undo_cwnd, struct sock *sk)
+{
+	return tcp_reno_undo_cwnd(sk);
+}
+
+SEC(".struct_ops")
+struct tcp_congestion_ops cc_cubic = {
+	.init		= (void *)bpf_cubic_init,
+	.ssthresh	= (void *)bpf_cubic_recalc_ssthresh,
+	.cong_control	= (void *)bpf_cubic_cong_control,
+	.set_state	= (void *)bpf_cubic_state,
+	.undo_cwnd	= (void *)bpf_cubic_undo_cwnd,
+	.cwnd_event	= (void *)bpf_cubic_cwnd_event,
+	.pkts_acked     = (void *)bpf_cubic_acked,
+	.name		= "bpf_cc_cubic",
+};
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bpf_compiler.h b/tools/testing/selftests/bpf/progs/bpf_compiler.h
new file mode 100644
index 000000000000..a7c343dc82e6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_compiler.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BPF_COMPILER_H__
+#define __BPF_COMPILER_H__
+
+#define DO_PRAGMA_(X) _Pragma(#X)
+
+#if __clang__
+#define __pragma_loop_unroll DO_PRAGMA_(clang loop unroll(enable))
+#else
+/* In GCC -funroll-loops, which is enabled with -O2, should have the
+   same impact than the loop-unroll-enable pragma above.  */
+#define __pragma_loop_unroll
+#endif
+
+#if __clang__
+#define __pragma_loop_unroll_count(N) DO_PRAGMA_(clang loop unroll_count(N))
+#else
+#define __pragma_loop_unroll_count(N) DO_PRAGMA_(GCC unroll N)
+#endif
+
+#if __clang__
+#define __pragma_loop_unroll_full DO_PRAGMA_(clang loop unroll(full))
+#else
+#define __pragma_loop_unroll_full DO_PRAGMA_(GCC unroll 65534)
+#endif
+
+#if __clang__
+#define __pragma_loop_no_unroll DO_PRAGMA_(clang loop unroll(disable))
+#else
+#define __pragma_loop_no_unroll DO_PRAGMA_(GCC unroll 1)
+#endif
+
+#endif
diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c
index d9660e7200e2..46fb2b37d3a7 100644
--- a/tools/testing/selftests/bpf/progs/bpf_cubic.c
+++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 
-/* WARNING: This implemenation is not necessarily the same
+/* WARNING: This implementation is not necessarily the same
  * as the tcp_cubic.c.  The purpose is mainly for testing
  * the kernel BPF logic.
  *
@@ -14,15 +14,16 @@
  *    "ca->ack_cnt / delta" operation.
  */
 
-#include <linux/bpf.h>
-#include <linux/stddef.h>
-#include <linux/tcp.h>
-#include "bpf_tcp_helpers.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
 #define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi)
 
+extern __u32 tcp_slow_start(struct tcp_sock *tp, __u32 acked) __ksym;
+extern void tcp_cong_avoid_ai(struct tcp_sock *tp, __u32 w, __u32 acked) __ksym;
+
 #define BICTCP_BETA_SCALE    1024	/* Scale factor beta calculation
 					 * max_cwnd = snd_cwnd * beta
 					 */
@@ -70,7 +71,7 @@ static const __u64 cube_factor = (__u64)(1ull << (10+3*BICTCP_HZ))
 				/ (bic_scale * 10);
 
 /* BIC TCP Parameters */
-struct bictcp {
+struct bpf_bictcp {
 	__u32	cnt;		/* increase cwnd by 1 after ACKs */
 	__u32	last_max_cwnd;	/* last maximum snd_cwnd */
 	__u32	last_cwnd;	/* the last snd_cwnd */
@@ -91,7 +92,7 @@ struct bictcp {
 	__u32	curr_rtt;	/* the minimum rtt of current round */
 };
 
-static inline void bictcp_reset(struct bictcp *ca)
+static void bictcp_reset(struct bpf_bictcp *ca)
 {
 	ca->cnt = 0;
 	ca->last_max_cwnd = 0;
@@ -112,7 +113,7 @@ extern unsigned long CONFIG_HZ __kconfig;
 #define USEC_PER_SEC	1000000UL
 #define USEC_PER_JIFFY	(USEC_PER_SEC / HZ)
 
-static __always_inline __u64 div64_u64(__u64 dividend, __u64 divisor)
+static __u64 div64_u64(__u64 dividend, __u64 divisor)
 {
 	return dividend / divisor;
 }
@@ -120,7 +121,7 @@ static __always_inline __u64 div64_u64(__u64 dividend, __u64 divisor)
 #define div64_ul div64_u64
 
 #define BITS_PER_U64 (sizeof(__u64) * 8)
-static __always_inline int fls64(__u64 x)
+static int fls64(__u64 x)
 {
 	int num = BITS_PER_U64 - 1;
 
@@ -153,15 +154,15 @@ static __always_inline int fls64(__u64 x)
 	return num + 1;
 }
 
-static __always_inline __u32 bictcp_clock_us(const struct sock *sk)
+static __u32 bictcp_clock_us(const struct sock *sk)
 {
 	return tcp_sk(sk)->tcp_mstamp;
 }
 
-static __always_inline void bictcp_hystart_reset(struct sock *sk)
+static void bictcp_hystart_reset(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct bictcp *ca = inet_csk_ca(sk);
+	struct bpf_bictcp *ca = inet_csk_ca(sk);
 
 	ca->round_start = ca->last_ack = bictcp_clock_us(sk);
 	ca->end_seq = tp->snd_nxt;
@@ -169,11 +170,10 @@ static __always_inline void bictcp_hystart_reset(struct sock *sk)
 	ca->sample_cnt = 0;
 }
 
-/* "struct_ops/" prefix is a requirement */
-SEC("struct_ops/bpf_cubic_init")
+SEC("struct_ops")
 void BPF_PROG(bpf_cubic_init, struct sock *sk)
 {
-	struct bictcp *ca = inet_csk_ca(sk);
+	struct bpf_bictcp *ca = inet_csk_ca(sk);
 
 	bictcp_reset(ca);
 
@@ -184,12 +184,11 @@ void BPF_PROG(bpf_cubic_init, struct sock *sk)
 		tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
 }
 
-/* "struct_ops" prefix is a requirement */
-SEC("struct_ops/bpf_cubic_cwnd_event")
+SEC("struct_ops")
 void BPF_PROG(bpf_cubic_cwnd_event, struct sock *sk, enum tcp_ca_event event)
 {
 	if (event == CA_EVENT_TX_START) {
-		struct bictcp *ca = inet_csk_ca(sk);
+		struct bpf_bictcp *ca = inet_csk_ca(sk);
 		__u32 now = tcp_jiffies32;
 		__s32 delta;
 
@@ -230,7 +229,7 @@ static const __u8 v[] = {
  * Newton-Raphson iteration.
  * Avg err ~= 0.195%
  */
-static __always_inline __u32 cubic_root(__u64 a)
+static __u32 cubic_root(__u64 a)
 {
 	__u32 x, b, shift;
 
@@ -263,8 +262,7 @@ static __always_inline __u32 cubic_root(__u64 a)
 /*
  * Compute congestion window to use.
  */
-static __always_inline void bictcp_update(struct bictcp *ca, __u32 cwnd,
-					  __u32 acked)
+static void bictcp_update(struct bpf_bictcp *ca, __u32 cwnd, __u32 acked)
 {
 	__u32 delta, bic_target, max_cnt;
 	__u64 offs, t;
@@ -309,7 +307,7 @@ static __always_inline void bictcp_update(struct bictcp *ca, __u32 cwnd,
 	 * (so time^3 is done by using 64 bit)
 	 * and without the support of division of 64bit numbers
 	 * (so all divisions are done by using 32 bit)
-	 *  also NOTE the unit of those veriables
+	 *  also NOTE the unit of those variables
 	 *	  time  = (t - K) / 2^bictcp_HZ
 	 *	  c = bic_scale >> 10
 	 * rtt  = (srtt >> 3) / HZ
@@ -377,11 +375,11 @@ tcp_friendliness:
 	ca->cnt = max(ca->cnt, 2U);
 }
 
-/* Or simply use the BPF_STRUCT_OPS to avoid the SEC boiler plate. */
-void BPF_STRUCT_OPS(bpf_cubic_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
+SEC("struct_ops")
+void BPF_PROG(bpf_cubic_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct bictcp *ca = inet_csk_ca(sk);
+	struct bpf_bictcp *ca = inet_csk_ca(sk);
 
 	if (!tcp_is_cwnd_limited(sk))
 		return;
@@ -397,10 +395,11 @@ void BPF_STRUCT_OPS(bpf_cubic_cong_avoid, struct sock *sk, __u32 ack, __u32 acke
 	tcp_cong_avoid_ai(tp, ca->cnt, acked);
 }
 
-__u32 BPF_STRUCT_OPS(bpf_cubic_recalc_ssthresh, struct sock *sk)
+SEC("struct_ops")
+__u32 BPF_PROG(bpf_cubic_recalc_ssthresh, struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
-	struct bictcp *ca = inet_csk_ca(sk);
+	struct bpf_bictcp *ca = inet_csk_ca(sk);
 
 	ca->epoch_start = 0;	/* end of epoch */
 
@@ -414,7 +413,8 @@ __u32 BPF_STRUCT_OPS(bpf_cubic_recalc_ssthresh, struct sock *sk)
 	return max((tp->snd_cwnd * beta) / BICTCP_BETA_SCALE, 2U);
 }
 
-void BPF_STRUCT_OPS(bpf_cubic_state, struct sock *sk, __u8 new_state)
+SEC("struct_ops")
+void BPF_PROG(bpf_cubic_state, struct sock *sk, __u8 new_state)
 {
 	if (new_state == TCP_CA_Loss) {
 		bictcp_reset(inet_csk_ca(sk));
@@ -433,7 +433,7 @@ void BPF_STRUCT_OPS(bpf_cubic_state, struct sock *sk, __u8 new_state)
  * We apply another 100% factor because @rate is doubled at this point.
  * We cap the cushion to 1ms.
  */
-static __always_inline __u32 hystart_ack_delay(struct sock *sk)
+static __u32 hystart_ack_delay(struct sock *sk)
 {
 	unsigned long rate;
 
@@ -444,10 +444,10 @@ static __always_inline __u32 hystart_ack_delay(struct sock *sk)
 		   div64_ul((__u64)GSO_MAX_SIZE * 4 * USEC_PER_SEC, rate));
 }
 
-static __always_inline void hystart_update(struct sock *sk, __u32 delay)
+static void hystart_update(struct sock *sk, __u32 delay)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct bictcp *ca = inet_csk_ca(sk);
+	struct bpf_bictcp *ca = inet_csk_ca(sk);
 	__u32 threshold;
 
 	if (hystart_detect & HYSTART_ACK_TRAIN) {
@@ -490,14 +490,17 @@ static __always_inline void hystart_update(struct sock *sk, __u32 delay)
 	}
 }
 
-void BPF_STRUCT_OPS(bpf_cubic_acked, struct sock *sk,
-		    const struct ack_sample *sample)
+int bpf_cubic_acked_called = 0;
+
+SEC("struct_ops")
+void BPF_PROG(bpf_cubic_acked, struct sock *sk, const struct ack_sample *sample)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
-	struct bictcp *ca = inet_csk_ca(sk);
+	struct bpf_bictcp *ca = inet_csk_ca(sk);
 	__u32 delay;
 
-	/* Some calls are for duplicates without timetamps */
+	bpf_cubic_acked_called = 1;
+	/* Some calls are for duplicates without timestamps */
 	if (sample->rtt_us < 0)
 		return;
 
@@ -521,7 +524,8 @@ void BPF_STRUCT_OPS(bpf_cubic_acked, struct sock *sk,
 
 extern __u32 tcp_reno_undo_cwnd(struct sock *sk) __ksym;
 
-__u32 BPF_STRUCT_OPS(bpf_cubic_undo_cwnd, struct sock *sk)
+SEC("struct_ops")
+__u32 BPF_PROG(bpf_cubic_undo_cwnd, struct sock *sk)
 {
 	return tcp_reno_undo_cwnd(sk);
 }
diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp.c b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
index 460682759aed..1cc83140849f 100644
--- a/tools/testing/selftests/bpf/progs/bpf_dctcp.c
+++ b/tools/testing/selftests/bpf/progs/bpf_dctcp.c
@@ -1,24 +1,26 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 Facebook */
 
-/* WARNING: This implemenation is not necessarily the same
+/* WARNING: This implementation is not necessarily the same
  * as the tcp_dctcp.c.  The purpose is mainly for testing
  * the kernel BPF logic.
  */
 
-#include <stddef.h>
-#include <linux/bpf.h>
-#include <linux/types.h>
-#include <linux/stddef.h>
-#include <linux/tcp.h>
-#include <errno.h>
+#include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
-#include "bpf_tcp_helpers.h"
+
+#ifndef EBUSY
+#define EBUSY 16
+#endif
+#define min_not_zero(x, y) ({			\
+	typeof(x) __x = (x);			\
+	typeof(y) __y = (y);			\
+	__x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); })
 
 char _license[] SEC("license") = "GPL";
 
-volatile const char fallback[TCP_CA_NAME_MAX];
+volatile const char fallback_cc[TCP_CA_NAME_MAX];
 const char bpf_dctcp[] = "bpf_dctcp";
 const char tcp_cdg[] = "cdg";
 char cc_res[TCP_CA_NAME_MAX];
@@ -35,7 +37,7 @@ struct {
 
 #define DCTCP_MAX_ALPHA	1024U
 
-struct dctcp {
+struct bpf_dctcp {
 	__u32 old_delivered;
 	__u32 old_delivered_ce;
 	__u32 prior_rcv_nxt;
@@ -48,8 +50,7 @@ struct dctcp {
 static unsigned int dctcp_shift_g = 4; /* g = 1/2^4 */
 static unsigned int dctcp_alpha_on_init = DCTCP_MAX_ALPHA;
 
-static __always_inline void dctcp_reset(const struct tcp_sock *tp,
-					struct dctcp *ca)
+static void dctcp_reset(const struct tcp_sock *tp, struct bpf_dctcp *ca)
 {
 	ca->next_seq = tp->snd_nxt;
 
@@ -57,20 +58,20 @@ static __always_inline void dctcp_reset(const struct tcp_sock *tp,
 	ca->old_delivered_ce = tp->delivered_ce;
 }
 
-SEC("struct_ops/dctcp_init")
-void BPF_PROG(dctcp_init, struct sock *sk)
+SEC("struct_ops")
+void BPF_PROG(bpf_dctcp_init, struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
-	struct dctcp *ca = inet_csk_ca(sk);
+	struct bpf_dctcp *ca = inet_csk_ca(sk);
 	int *stg;
 
-	if (!(tp->ecn_flags & TCP_ECN_OK) && fallback[0]) {
+	if (!(tp->ecn_flags & TCP_ECN_OK) && fallback_cc[0]) {
 		/* Switch to fallback */
 		if (bpf_setsockopt(sk, SOL_TCP, TCP_CONGESTION,
-				   (void *)fallback, sizeof(fallback)) == -EBUSY)
+				   (void *)fallback_cc, sizeof(fallback_cc)) == -EBUSY)
 			ebusy_cnt++;
 
-		/* Switch back to myself and the recurred dctcp_init()
+		/* Switch back to myself and the recurred bpf_dctcp_init()
 		 * will get -EBUSY for all bpf_setsockopt(TCP_CONGESTION),
 		 * except the last "cdg" one.
 		 */
@@ -80,7 +81,7 @@ void BPF_PROG(dctcp_init, struct sock *sk)
 
 		/* Switch back to fallback */
 		if (bpf_setsockopt(sk, SOL_TCP, TCP_CONGESTION,
-				   (void *)fallback, sizeof(fallback)) == -EBUSY)
+				   (void *)fallback_cc, sizeof(fallback_cc)) == -EBUSY)
 			ebusy_cnt++;
 
 		/* Expecting -ENOTSUPP for tcp_cdg_res */
@@ -104,21 +105,21 @@ void BPF_PROG(dctcp_init, struct sock *sk)
 	dctcp_reset(tp, ca);
 }
 
-SEC("struct_ops/dctcp_ssthresh")
-__u32 BPF_PROG(dctcp_ssthresh, struct sock *sk)
+SEC("struct_ops")
+__u32 BPF_PROG(bpf_dctcp_ssthresh, struct sock *sk)
 {
-	struct dctcp *ca = inet_csk_ca(sk);
+	struct bpf_dctcp *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	ca->loss_cwnd = tp->snd_cwnd;
 	return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U);
 }
 
-SEC("struct_ops/dctcp_update_alpha")
-void BPF_PROG(dctcp_update_alpha, struct sock *sk, __u32 flags)
+SEC("struct_ops")
+void BPF_PROG(bpf_dctcp_update_alpha, struct sock *sk, __u32 flags)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
-	struct dctcp *ca = inet_csk_ca(sk);
+	struct bpf_dctcp *ca = inet_csk_ca(sk);
 
 	/* Expired RTT */
 	if (!before(tp->snd_una, ca->next_seq)) {
@@ -144,27 +145,27 @@ void BPF_PROG(dctcp_update_alpha, struct sock *sk, __u32 flags)
 	}
 }
 
-static __always_inline void dctcp_react_to_loss(struct sock *sk)
+static void dctcp_react_to_loss(struct sock *sk)
 {
-	struct dctcp *ca = inet_csk_ca(sk);
+	struct bpf_dctcp *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	ca->loss_cwnd = tp->snd_cwnd;
 	tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U);
 }
 
-SEC("struct_ops/dctcp_state")
-void BPF_PROG(dctcp_state, struct sock *sk, __u8 new_state)
+SEC("struct_ops")
+void BPF_PROG(bpf_dctcp_state, struct sock *sk, __u8 new_state)
 {
 	if (new_state == TCP_CA_Recovery &&
 	    new_state != BPF_CORE_READ_BITFIELD(inet_csk(sk), icsk_ca_state))
 		dctcp_react_to_loss(sk);
-	/* We handle RTO in dctcp_cwnd_event to ensure that we perform only
+	/* We handle RTO in bpf_dctcp_cwnd_event to ensure that we perform only
 	 * one loss-adjustment per RTT.
 	 */
 }
 
-static __always_inline void dctcp_ece_ack_cwr(struct sock *sk, __u32 ce_state)
+static void dctcp_ece_ack_cwr(struct sock *sk, __u32 ce_state)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
@@ -179,9 +180,8 @@ static __always_inline void dctcp_ece_ack_cwr(struct sock *sk, __u32 ce_state)
  * S:	0 <- last pkt was non-CE
  *	1 <- last pkt was CE
  */
-static __always_inline
-void dctcp_ece_ack_update(struct sock *sk, enum tcp_ca_event evt,
-			  __u32 *prior_rcv_nxt, __u32 *ce_state)
+static void dctcp_ece_ack_update(struct sock *sk, enum tcp_ca_event evt,
+				 __u32 *prior_rcv_nxt, __u32 *ce_state)
 {
 	__u32 new_ce_state = (evt == CA_EVENT_ECN_IS_CE) ? 1 : 0;
 
@@ -201,10 +201,10 @@ void dctcp_ece_ack_update(struct sock *sk, enum tcp_ca_event evt,
 	dctcp_ece_ack_cwr(sk, new_ce_state);
 }
 
-SEC("struct_ops/dctcp_cwnd_event")
-void BPF_PROG(dctcp_cwnd_event, struct sock *sk, enum tcp_ca_event ev)
+SEC("struct_ops")
+void BPF_PROG(bpf_dctcp_cwnd_event, struct sock *sk, enum tcp_ca_event ev)
 {
-	struct dctcp *ca = inet_csk_ca(sk);
+	struct bpf_dctcp *ca = inet_csk_ca(sk);
 
 	switch (ev) {
 	case CA_EVENT_ECN_IS_CE:
@@ -220,39 +220,39 @@ void BPF_PROG(dctcp_cwnd_event, struct sock *sk, enum tcp_ca_event ev)
 	}
 }
 
-SEC("struct_ops/dctcp_cwnd_undo")
-__u32 BPF_PROG(dctcp_cwnd_undo, struct sock *sk)
+SEC("struct_ops")
+__u32 BPF_PROG(bpf_dctcp_cwnd_undo, struct sock *sk)
 {
-	const struct dctcp *ca = inet_csk_ca(sk);
+	const struct bpf_dctcp *ca = inet_csk_ca(sk);
 
 	return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
 }
 
 extern void tcp_reno_cong_avoid(struct sock *sk, __u32 ack, __u32 acked) __ksym;
 
-SEC("struct_ops/dctcp_reno_cong_avoid")
-void BPF_PROG(dctcp_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
+SEC("struct_ops")
+void BPF_PROG(bpf_dctcp_cong_avoid, struct sock *sk, __u32 ack, __u32 acked)
 {
 	tcp_reno_cong_avoid(sk, ack, acked);
 }
 
 SEC(".struct_ops")
 struct tcp_congestion_ops dctcp_nouse = {
-	.init		= (void *)dctcp_init,
-	.set_state	= (void *)dctcp_state,
+	.init		= (void *)bpf_dctcp_init,
+	.set_state	= (void *)bpf_dctcp_state,
 	.flags		= TCP_CONG_NEEDS_ECN,
 	.name		= "bpf_dctcp_nouse",
 };
 
 SEC(".struct_ops")
 struct tcp_congestion_ops dctcp = {
-	.init		= (void *)dctcp_init,
-	.in_ack_event   = (void *)dctcp_update_alpha,
-	.cwnd_event	= (void *)dctcp_cwnd_event,
-	.ssthresh	= (void *)dctcp_ssthresh,
-	.cong_avoid	= (void *)dctcp_cong_avoid,
-	.undo_cwnd	= (void *)dctcp_cwnd_undo,
-	.set_state	= (void *)dctcp_state,
+	.init		= (void *)bpf_dctcp_init,
+	.in_ack_event   = (void *)bpf_dctcp_update_alpha,
+	.cwnd_event	= (void *)bpf_dctcp_cwnd_event,
+	.ssthresh	= (void *)bpf_dctcp_ssthresh,
+	.cong_avoid	= (void *)bpf_dctcp_cong_avoid,
+	.undo_cwnd	= (void *)bpf_dctcp_cwnd_undo,
+	.set_state	= (void *)bpf_dctcp_state,
 	.flags		= TCP_CONG_NEEDS_ECN,
 	.name		= "bpf_dctcp",
 };
diff --git a/tools/testing/selftests/bpf/progs/bpf_dctcp_release.c b/tools/testing/selftests/bpf/progs/bpf_dctcp_release.c
index d836f7c372f0..c91763f248b2 100644
--- a/tools/testing/selftests/bpf/progs/bpf_dctcp_release.c
+++ b/tools/testing/selftests/bpf/progs/bpf_dctcp_release.c
@@ -1,19 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2021 Facebook */
 
-#include <stddef.h>
-#include <linux/bpf.h>
-#include <linux/types.h>
-#include <linux/stddef.h>
-#include <linux/tcp.h>
+#include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
-#include "bpf_tcp_helpers.h"
 
 char _license[] SEC("license") = "GPL";
 const char cubic[] = "cubic";
 
-void BPF_STRUCT_OPS(dctcp_nouse_release, struct sock *sk)
+SEC("struct_ops")
+void BPF_PROG(dctcp_nouse_release, struct sock *sk)
 {
 	bpf_setsockopt(sk, SOL_TCP, TCP_CONGESTION,
 		       (void *)cubic, sizeof(cubic));
diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c
index a20c5ed5e454..b04e092fac94 100644
--- a/tools/testing/selftests/bpf/progs/bpf_flow.c
+++ b/tools/testing/selftests/bpf/progs/bpf_flow.c
@@ -337,7 +337,7 @@ PROG(IPV6)(struct __sk_buff *skb)
 	keys->ip_proto = ip6h->nexthdr;
 	keys->flow_label = ip6_flowlabel(ip6h);
 
-	if (keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL)
+	if (keys->flow_label && keys->flags & BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL)
 		return export_flow_keys(keys, BPF_OK);
 
 	return parse_ipv6_proto(skb, ip6h->nexthdr);
diff --git a/tools/testing/selftests/bpf/progs/bpf_gotox.c b/tools/testing/selftests/bpf/progs/bpf_gotox.c
new file mode 100644
index 000000000000..216c71b94c64
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_gotox.c
@@ -0,0 +1,448 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_misc.h"
+
+__u64 in_user;
+__u64 ret_user;
+
+int pid;
+
+/*
+ * Skip all the tests if compiler doesn't support indirect jumps.
+ *
+ * If tests are skipped, then all functions below are compiled as
+ * dummy, such that the skeleton looks the same, and the userspace
+ * program can avoid any checks rather than if data->skip is set.
+ */
+#ifdef __BPF_FEATURE_GOTOX
+__u64 skip SEC(".data") = 0;
+#else
+__u64 skip = 1;
+#endif
+
+struct simple_ctx {
+	__u64 x;
+};
+
+#ifdef __BPF_FEATURE_GOTOX
+__u64 some_var;
+
+/*
+ * This function adds code which will be replaced by a different
+ * number of instructions by the verifier. This adds additional
+ * stress on testing the insn_array maps corresponding to indirect jumps.
+ */
+static __always_inline void adjust_insns(__u64 x)
+{
+	some_var ^= x + bpf_jiffies64();
+}
+
+SEC("syscall")
+int one_switch(struct simple_ctx *ctx)
+{
+	switch (ctx->x) {
+	case 0:
+		adjust_insns(ctx->x + 1);
+		ret_user = 2;
+		break;
+	case 1:
+		adjust_insns(ctx->x + 7);
+		ret_user = 3;
+		break;
+	case 2:
+		adjust_insns(ctx->x + 9);
+		ret_user = 4;
+		break;
+	case 3:
+		adjust_insns(ctx->x + 11);
+		ret_user = 5;
+		break;
+	case 4:
+		adjust_insns(ctx->x + 17);
+		ret_user = 7;
+		break;
+	default:
+		adjust_insns(ctx->x + 177);
+		ret_user = 19;
+		break;
+	}
+
+	return 0;
+}
+
+SEC("syscall")
+int one_switch_non_zero_sec_off(struct simple_ctx *ctx)
+{
+	switch (ctx->x) {
+	case 0:
+		adjust_insns(ctx->x + 1);
+		ret_user = 2;
+		break;
+	case 1:
+		adjust_insns(ctx->x + 7);
+		ret_user = 3;
+		break;
+	case 2:
+		adjust_insns(ctx->x + 9);
+		ret_user = 4;
+		break;
+	case 3:
+		adjust_insns(ctx->x + 11);
+		ret_user = 5;
+		break;
+	case 4:
+		adjust_insns(ctx->x + 17);
+		ret_user = 7;
+		break;
+	default:
+		adjust_insns(ctx->x + 177);
+		ret_user = 19;
+		break;
+	}
+
+	return 0;
+}
+
+SEC("fentry/" SYS_PREFIX "sys_nanosleep")
+int simple_test_other_sec(struct pt_regs *ctx)
+{
+	__u64 x = in_user;
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	switch (x) {
+	case 0:
+		adjust_insns(x + 1);
+		ret_user = 2;
+		break;
+	case 1:
+		adjust_insns(x + 7);
+		ret_user = 3;
+		break;
+	case 2:
+		adjust_insns(x + 9);
+		ret_user = 4;
+		break;
+	case 3:
+		adjust_insns(x + 11);
+		ret_user = 5;
+		break;
+	case 4:
+		adjust_insns(x + 17);
+		ret_user = 7;
+		break;
+	default:
+		adjust_insns(x + 177);
+		ret_user = 19;
+		break;
+	}
+
+	return 0;
+}
+
+SEC("syscall")
+int two_switches(struct simple_ctx *ctx)
+{
+	switch (ctx->x) {
+	case 0:
+		adjust_insns(ctx->x + 1);
+		ret_user = 2;
+		break;
+	case 1:
+		adjust_insns(ctx->x + 7);
+		ret_user = 3;
+		break;
+	case 2:
+		adjust_insns(ctx->x + 9);
+		ret_user = 4;
+		break;
+	case 3:
+		adjust_insns(ctx->x + 11);
+		ret_user = 5;
+		break;
+	case 4:
+		adjust_insns(ctx->x + 17);
+		ret_user = 7;
+		break;
+	default:
+		adjust_insns(ctx->x + 177);
+		ret_user = 19;
+		break;
+	}
+
+	switch (ctx->x + !!ret_user) {
+	case 1:
+		adjust_insns(ctx->x + 7);
+		ret_user = 103;
+		break;
+	case 2:
+		adjust_insns(ctx->x + 9);
+		ret_user = 104;
+		break;
+	case 3:
+		adjust_insns(ctx->x + 11);
+		ret_user = 107;
+		break;
+	case 4:
+		adjust_insns(ctx->x + 11);
+		ret_user = 205;
+		break;
+	case 5:
+		adjust_insns(ctx->x + 11);
+		ret_user = 115;
+		break;
+	default:
+		adjust_insns(ctx->x + 177);
+		ret_user = 1019;
+		break;
+	}
+
+	return 0;
+}
+
+SEC("syscall")
+int big_jump_table(struct simple_ctx *ctx __attribute__((unused)))
+{
+	const void *const jt[256] = {
+		[0 ... 255] = &&default_label,
+		[0] = &&l0,
+		[11] = &&l11,
+		[27] = &&l27,
+		[31] = &&l31,
+	};
+
+	goto *jt[ctx->x & 0xff];
+
+l0:
+	adjust_insns(ctx->x + 1);
+	ret_user = 2;
+	return 0;
+
+l11:
+	adjust_insns(ctx->x + 7);
+	ret_user = 3;
+	return 0;
+
+l27:
+	adjust_insns(ctx->x + 9);
+	ret_user = 4;
+	return 0;
+
+l31:
+	adjust_insns(ctx->x + 11);
+	ret_user = 5;
+	return 0;
+
+default_label:
+	adjust_insns(ctx->x + 177);
+	ret_user = 19;
+	return 0;
+}
+
+SEC("syscall")
+int one_jump_two_maps(struct simple_ctx *ctx __attribute__((unused)))
+{
+	__label__ l1, l2, l3, l4;
+	void *jt1[2] = { &&l1, &&l2 };
+	void *jt2[2] = { &&l3, &&l4 };
+	unsigned int a = ctx->x % 2;
+	unsigned int b = (ctx->x / 2) % 2;
+	volatile int ret = 0;
+
+	if (!(a < 2 && b < 2))
+		return 19;
+
+	if (ctx->x % 2)
+		goto *jt1[a];
+	else
+		goto *jt2[b];
+
+	l1: ret += 1;
+	l2: ret += 3;
+	l3: ret += 5;
+	l4: ret += 7;
+
+	ret_user = ret;
+	return ret;
+}
+
+SEC("syscall")
+int one_map_two_jumps(struct simple_ctx *ctx __attribute__((unused)))
+{
+	__label__ l1, l2, l3;
+	void *jt[3] = { &&l1, &&l2, &&l3 };
+	unsigned int a = (ctx->x >> 2) & 1;
+	unsigned int b = (ctx->x >> 3) & 1;
+	volatile int ret = 0;
+
+	if (ctx->x % 2)
+		goto *jt[a];
+
+	if (ctx->x % 3)
+		goto *jt[a + b];
+
+	l1: ret += 3;
+	l2: ret += 5;
+	l3: ret += 7;
+
+	ret_user = ret;
+	return ret;
+}
+
+/* Just to introduce some non-zero offsets in .text */
+static __noinline int f0(volatile struct simple_ctx *ctx __arg_ctx)
+{
+	if (ctx)
+		return 1;
+	else
+		return 13;
+}
+
+SEC("syscall") int f1(struct simple_ctx *ctx)
+{
+	ret_user = 0;
+	return f0(ctx);
+}
+
+static __noinline int __static_global(__u64 x)
+{
+	switch (x) {
+	case 0:
+		adjust_insns(x + 1);
+		ret_user = 2;
+		break;
+	case 1:
+		adjust_insns(x + 7);
+		ret_user = 3;
+		break;
+	case 2:
+		adjust_insns(x + 9);
+		ret_user = 4;
+		break;
+	case 3:
+		adjust_insns(x + 11);
+		ret_user = 5;
+		break;
+	case 4:
+		adjust_insns(x + 17);
+		ret_user = 7;
+		break;
+	default:
+		adjust_insns(x + 177);
+		ret_user = 19;
+		break;
+	}
+
+	return 0;
+}
+
+SEC("syscall")
+int use_static_global1(struct simple_ctx *ctx)
+{
+	ret_user = 0;
+	return __static_global(ctx->x);
+}
+
+SEC("syscall")
+int use_static_global2(struct simple_ctx *ctx)
+{
+	ret_user = 0;
+	adjust_insns(ctx->x + 1);
+	return __static_global(ctx->x);
+}
+
+SEC("fentry/" SYS_PREFIX "sys_nanosleep")
+int use_static_global_other_sec(void *ctx)
+{
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	return __static_global(in_user);
+}
+
+__noinline int __nonstatic_global(__u64 x)
+{
+	switch (x) {
+	case 0:
+		adjust_insns(x + 1);
+		ret_user = 2;
+		break;
+	case 1:
+		adjust_insns(x + 7);
+		ret_user = 3;
+		break;
+	case 2:
+		adjust_insns(x + 9);
+		ret_user = 4;
+		break;
+	case 3:
+		adjust_insns(x + 11);
+		ret_user = 5;
+		break;
+	case 4:
+		adjust_insns(x + 17);
+		ret_user = 7;
+		break;
+	default:
+		adjust_insns(x + 177);
+		ret_user = 19;
+		break;
+	}
+
+	return 0;
+}
+
+SEC("syscall")
+int use_nonstatic_global1(struct simple_ctx *ctx)
+{
+	ret_user = 0;
+	return __nonstatic_global(ctx->x);
+}
+
+SEC("syscall")
+int use_nonstatic_global2(struct simple_ctx *ctx)
+{
+	ret_user = 0;
+	adjust_insns(ctx->x + 1);
+	return __nonstatic_global(ctx->x);
+}
+
+SEC("fentry/" SYS_PREFIX "sys_nanosleep")
+int use_nonstatic_global_other_sec(void *ctx)
+{
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	return __nonstatic_global(in_user);
+}
+
+#else /* __BPF_FEATURE_GOTOX */
+
+#define SKIP_TEST(TEST_NAME)				\
+	SEC("syscall") int TEST_NAME(void *ctx)		\
+	{						\
+		return 0;				\
+	}
+
+SKIP_TEST(one_switch);
+SKIP_TEST(one_switch_non_zero_sec_off);
+SKIP_TEST(simple_test_other_sec);
+SKIP_TEST(two_switches);
+SKIP_TEST(big_jump_table);
+SKIP_TEST(one_jump_two_maps);
+SKIP_TEST(one_map_two_jumps);
+SKIP_TEST(use_static_global1);
+SKIP_TEST(use_static_global2);
+SKIP_TEST(use_static_global_other_sec);
+SKIP_TEST(use_nonstatic_global1);
+SKIP_TEST(use_nonstatic_global2);
+SKIP_TEST(use_nonstatic_global_other_sec);
+
+#endif /* __BPF_FEATURE_GOTOX */
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bpf_hashmap_lookup.c b/tools/testing/selftests/bpf/progs/bpf_hashmap_lookup.c
new file mode 100644
index 000000000000..1eb74ddca414
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_hashmap_lookup.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+
+#include "vmlinux.h"
+
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+} hash_map_bench SEC(".maps");
+
+/* The number of slots to store times */
+#define NR_SLOTS 32
+#define NR_CPUS 256
+#define CPU_MASK (NR_CPUS-1)
+
+/* Configured by userspace */
+u64 nr_entries;
+u64 nr_loops;
+u32 __attribute__((__aligned__(8))) key[NR_CPUS];
+
+/* Filled by us */
+u64 __attribute__((__aligned__(256))) percpu_times_index[NR_CPUS];
+u64 __attribute__((__aligned__(256))) percpu_times[NR_CPUS][NR_SLOTS];
+
+static inline void patch_key(u32 i)
+{
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	key[0] = i + 1;
+#else
+	key[0] = __builtin_bswap32(i + 1);
+#endif
+	/* the rest of key is random and is configured by userspace */
+}
+
+static int lookup_callback(__u32 index, u32 *unused)
+{
+	patch_key(index);
+	return bpf_map_lookup_elem(&hash_map_bench, key) ? 0 : 1;
+}
+
+static int loop_lookup_callback(__u32 index, u32 *unused)
+{
+	return bpf_loop(nr_entries, lookup_callback, NULL, 0) ? 0 : 1;
+}
+
+SEC("fentry/" SYS_PREFIX "sys_getpgid")
+int benchmark(void *ctx)
+{
+	u32 cpu = bpf_get_smp_processor_id();
+	u32 times_index;
+	u64 start_time;
+
+	times_index = percpu_times_index[cpu & CPU_MASK] % NR_SLOTS;
+	start_time = bpf_ktime_get_ns();
+	bpf_loop(nr_loops, loop_lookup_callback, NULL, 0);
+	percpu_times[cpu & CPU_MASK][times_index] = bpf_ktime_get_ns() - start_time;
+	percpu_times_index[cpu & CPU_MASK] += 1;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter.h b/tools/testing/selftests/bpf/progs/bpf_iter.h
deleted file mode 100644
index c41ee80533ca..000000000000
--- a/tools/testing/selftests/bpf/progs/bpf_iter.h
+++ /dev/null
@@ -1,167 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (c) 2020 Facebook */
-/* "undefine" structs in vmlinux.h, because we "override" them below */
-#define bpf_iter_meta bpf_iter_meta___not_used
-#define bpf_iter__bpf_map bpf_iter__bpf_map___not_used
-#define bpf_iter__ipv6_route bpf_iter__ipv6_route___not_used
-#define bpf_iter__netlink bpf_iter__netlink___not_used
-#define bpf_iter__task bpf_iter__task___not_used
-#define bpf_iter__task_file bpf_iter__task_file___not_used
-#define bpf_iter__task_vma bpf_iter__task_vma___not_used
-#define bpf_iter__tcp bpf_iter__tcp___not_used
-#define tcp6_sock tcp6_sock___not_used
-#define bpf_iter__udp bpf_iter__udp___not_used
-#define udp6_sock udp6_sock___not_used
-#define bpf_iter__unix bpf_iter__unix___not_used
-#define bpf_iter__bpf_map_elem bpf_iter__bpf_map_elem___not_used
-#define bpf_iter__bpf_sk_storage_map bpf_iter__bpf_sk_storage_map___not_used
-#define bpf_iter__sockmap bpf_iter__sockmap___not_used
-#define bpf_iter__bpf_link bpf_iter__bpf_link___not_used
-#define bpf_iter__cgroup bpf_iter__cgroup___not_used
-#define btf_ptr btf_ptr___not_used
-#define BTF_F_COMPACT BTF_F_COMPACT___not_used
-#define BTF_F_NONAME BTF_F_NONAME___not_used
-#define BTF_F_PTR_RAW BTF_F_PTR_RAW___not_used
-#define BTF_F_ZERO BTF_F_ZERO___not_used
-#define bpf_iter__ksym bpf_iter__ksym___not_used
-#include "vmlinux.h"
-#undef bpf_iter_meta
-#undef bpf_iter__bpf_map
-#undef bpf_iter__ipv6_route
-#undef bpf_iter__netlink
-#undef bpf_iter__task
-#undef bpf_iter__task_file
-#undef bpf_iter__task_vma
-#undef bpf_iter__tcp
-#undef tcp6_sock
-#undef bpf_iter__udp
-#undef udp6_sock
-#undef bpf_iter__unix
-#undef bpf_iter__bpf_map_elem
-#undef bpf_iter__bpf_sk_storage_map
-#undef bpf_iter__sockmap
-#undef bpf_iter__bpf_link
-#undef bpf_iter__cgroup
-#undef btf_ptr
-#undef BTF_F_COMPACT
-#undef BTF_F_NONAME
-#undef BTF_F_PTR_RAW
-#undef BTF_F_ZERO
-#undef bpf_iter__ksym
-
-struct bpf_iter_meta {
-	struct seq_file *seq;
-	__u64 session_id;
-	__u64 seq_num;
-} __attribute__((preserve_access_index));
-
-struct bpf_iter__ipv6_route {
-	struct bpf_iter_meta *meta;
-	struct fib6_info *rt;
-} __attribute__((preserve_access_index));
-
-struct bpf_iter__netlink {
-	struct bpf_iter_meta *meta;
-	struct netlink_sock *sk;
-} __attribute__((preserve_access_index));
-
-struct bpf_iter__task {
-	struct bpf_iter_meta *meta;
-	struct task_struct *task;
-} __attribute__((preserve_access_index));
-
-struct bpf_iter__task_file {
-	struct bpf_iter_meta *meta;
-	struct task_struct *task;
-	__u32 fd;
-	struct file *file;
-} __attribute__((preserve_access_index));
-
-struct bpf_iter__task_vma {
-	struct bpf_iter_meta *meta;
-	struct task_struct *task;
-	struct vm_area_struct *vma;
-} __attribute__((preserve_access_index));
-
-struct bpf_iter__bpf_map {
-	struct bpf_iter_meta *meta;
-	struct bpf_map *map;
-} __attribute__((preserve_access_index));
-
-struct bpf_iter__tcp {
-	struct bpf_iter_meta *meta;
-	struct sock_common *sk_common;
-	uid_t uid;
-} __attribute__((preserve_access_index));
-
-struct tcp6_sock {
-	struct tcp_sock	tcp;
-	struct ipv6_pinfo inet6;
-} __attribute__((preserve_access_index));
-
-struct bpf_iter__udp {
-	struct bpf_iter_meta *meta;
-	struct udp_sock *udp_sk;
-	uid_t uid __attribute__((aligned(8)));
-	int bucket __attribute__((aligned(8)));
-} __attribute__((preserve_access_index));
-
-struct udp6_sock {
-	struct udp_sock	udp;
-	struct ipv6_pinfo inet6;
-} __attribute__((preserve_access_index));
-
-struct bpf_iter__unix {
-	struct bpf_iter_meta *meta;
-	struct unix_sock *unix_sk;
-	uid_t uid;
-} __attribute__((preserve_access_index));
-
-struct bpf_iter__bpf_map_elem {
-	struct bpf_iter_meta *meta;
-	struct bpf_map *map;
-	void *key;
-	void *value;
-};
-
-struct bpf_iter__bpf_sk_storage_map {
-	struct bpf_iter_meta *meta;
-	struct bpf_map *map;
-	struct sock *sk;
-	void *value;
-};
-
-struct bpf_iter__sockmap {
-	struct bpf_iter_meta *meta;
-	struct bpf_map *map;
-	void *key;
-	struct sock *sk;
-};
-
-struct bpf_iter__bpf_link {
-	struct bpf_iter_meta *meta;
-	struct bpf_link *link;
-};
-
-struct bpf_iter__cgroup {
-	struct bpf_iter_meta *meta;
-	struct cgroup *cgroup;
-} __attribute__((preserve_access_index));
-
-struct btf_ptr {
-	void *ptr;
-	__u32 type_id;
-	__u32 flags;
-};
-
-enum {
-	BTF_F_COMPACT	=	(1ULL << 0),
-	BTF_F_NONAME	=	(1ULL << 1),
-	BTF_F_PTR_RAW	=	(1ULL << 2),
-	BTF_F_ZERO	=	(1ULL << 3),
-};
-
-struct bpf_iter__ksym {
-	struct bpf_iter_meta *meta;
-	struct kallsym_iter *ksym;
-};
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c
index c5969ca6f26b..19710cc0f250 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_array_map.c
@@ -1,17 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
-struct key_t {
-	int a;
-	int b;
-	int c;
-};
-
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
 	__uint(max_entries, 3);
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c
index d7a69217fb68..f47da665f7e0 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_link.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_link.c
index e1af2f8f75a6..7b69e1887705 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_link.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_link.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2022 Red Hat, Inc. */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
index 6c39e86b666f..c868ffb8080f 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c
index 85fa710fad90..9fdea8cd4c6f 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_array_map.c
@@ -1,17 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
-struct key_t {
-	int a;
-	int b;
-	int c;
-};
-
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
 	__uint(max_entries, 3);
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c
index feaaa2b89c57..aa529f76c7fc 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_percpu_hash_map.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
@@ -20,7 +20,7 @@ struct {
 } hashmap1 SEC(".maps");
 
 /* will set before prog run */
-volatile const __u32 num_cpus = 0;
+volatile const __s32 num_cpus = 0;
 
 /* will collect results during prog run */
 __u32 key_sum_a = 0, key_sum_b = 0, key_sum_c = 0;
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_helpers.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_helpers.c
index 6cecab2b32ba..e88dab196e0f 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_helpers.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_helpers.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Google LLC. */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c
index c7b8e006b171..eb9642923e1c 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_map.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c
index 784a610ce039..73a5cf3ba3d3 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_ipv6_route.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
 
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c b/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c
index 9ba14c37bbcc..3e725b1fce37 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_ksym.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2022, Oracle and/or its affiliates. */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
@@ -33,7 +33,6 @@ int dump_ksym(struct bpf_iter__ksym *ctx)
 	__u32 seq_num = ctx->meta->seq_num;
 	unsigned long value;
 	char type;
-	int ret;
 
 	if (!iter)
 		return 0;
@@ -60,9 +59,7 @@ int dump_ksym(struct bpf_iter__ksym *ctx)
 	} else {
 		BPF_SEQ_PRINTF(seq, "0x%llx %c %s ", value, type, iter->name);
 	}
-	if (!iter->pos_arch_end || iter->pos_arch_end > iter->pos)
-		BPF_SEQ_PRINTF(seq, "CORE ");
-	else if (!iter->pos_mod_end || iter->pos_mod_end > iter->pos)
+	if (!iter->pos_mod_end || iter->pos_mod_end > iter->pos)
 		BPF_SEQ_PRINTF(seq, "MOD ");
 	else if (!iter->pos_ftrace_mod_end || iter->pos_ftrace_mod_end > iter->pos)
 		BPF_SEQ_PRINTF(seq, "FTRACE_MOD ");
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_map_elem.c b/tools/testing/selftests/bpf/progs/bpf_iter_map_elem.c
new file mode 100644
index 000000000000..2f20485e0de3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_map_elem.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u32 value_sum = 0;
+
+SEC("iter/bpf_map_elem")
+int dump_bpf_map_values(struct bpf_iter__bpf_map_elem *ctx)
+{
+	__u32 value = 0;
+
+	if (ctx->value == (void *)0)
+		return 0;
+
+	bpf_probe_read_kernel(&value, sizeof(value), ctx->value);
+	value_sum += value;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c
index a28e51e2dcee..00b2ceae81fb 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_netlink.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
 
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt.c b/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt.c
index b77adfd55d73..a8aa5a71d846 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2021 Facebook */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
@@ -18,23 +18,10 @@
 
 unsigned short reuse_listen_hport = 0;
 unsigned short listen_hport = 0;
-char cubic_cc[TCP_CA_NAME_MAX] = "bpf_cubic";
+const char cubic_cc[] = "bpf_cubic";
 char dctcp_cc[TCP_CA_NAME_MAX] = "bpf_dctcp";
 bool random_retry = false;
 
-static bool tcp_cc_eq(const char *a, const char *b)
-{
-	int i;
-
-	for (i = 0; i < TCP_CA_NAME_MAX; i++) {
-		if (a[i] != b[i])
-			return false;
-		if (!a[i])
-			break;
-	}
-
-	return true;
-}
 
 SEC("iter/tcp")
 int change_tcp_cc(struct bpf_iter__tcp *ctx)
@@ -42,7 +29,6 @@ int change_tcp_cc(struct bpf_iter__tcp *ctx)
 	char cur_cc[TCP_CA_NAME_MAX];
 	struct tcp_sock *tp;
 	struct sock *sk;
-	int ret;
 
 	if (!bpf_tcp_sk(ctx->sk_common))
 		return 0;
@@ -59,7 +45,7 @@ int change_tcp_cc(struct bpf_iter__tcp *ctx)
 			   cur_cc, sizeof(cur_cc)))
 		return 0;
 
-	if (!tcp_cc_eq(cur_cc, cubic_cc))
+	if (bpf_strncmp(cur_cc, TCP_CA_NAME_MAX, cubic_cc))
 		return 0;
 
 	if (random_retry && bpf_get_prandom_u32() % 4 == 1)
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt_unix.c b/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt_unix.c
index eafc877ea460..d92631ec6161 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt_unix.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_setsockopt_unix.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright Amazon.com Inc. or its affiliates. */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
 #include <limits.h>
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_sockmap.c b/tools/testing/selftests/bpf/progs/bpf_iter_sockmap.c
index f3af0e30cead..317fe49760cc 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_sockmap.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_sockmap.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Cloudflare */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task.c b/tools/testing/selftests/bpf/progs/bpf_iter_task.c
deleted file mode 100644
index 96131b9a1caa..000000000000
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task.c
+++ /dev/null
@@ -1,88 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
-#include <bpf/bpf_helpers.h>
-#include <bpf/bpf_tracing.h>
-
-char _license[] SEC("license") = "GPL";
-
-uint32_t tid = 0;
-int num_unknown_tid = 0;
-int num_known_tid = 0;
-
-SEC("iter/task")
-int dump_task(struct bpf_iter__task *ctx)
-{
-	struct seq_file *seq = ctx->meta->seq;
-	struct task_struct *task = ctx->task;
-	static char info[] = "    === END ===";
-
-	if (task == (void *)0) {
-		BPF_SEQ_PRINTF(seq, "%s\n", info);
-		return 0;
-	}
-
-	if (task->pid != tid)
-		num_unknown_tid++;
-	else
-		num_known_tid++;
-
-	if (ctx->meta->seq_num == 0)
-		BPF_SEQ_PRINTF(seq, "    tgid      gid\n");
-
-	BPF_SEQ_PRINTF(seq, "%8d %8d\n", task->tgid, task->pid);
-	return 0;
-}
-
-int num_expected_failure_copy_from_user_task = 0;
-int num_success_copy_from_user_task = 0;
-
-SEC("iter.s/task")
-int dump_task_sleepable(struct bpf_iter__task *ctx)
-{
-	struct seq_file *seq = ctx->meta->seq;
-	struct task_struct *task = ctx->task;
-	static const char info[] = "    === END ===";
-	struct pt_regs *regs;
-	void *ptr;
-	uint32_t user_data = 0;
-	int ret;
-
-	if (task == (void *)0) {
-		BPF_SEQ_PRINTF(seq, "%s\n", info);
-		return 0;
-	}
-
-	/* Read an invalid pointer and ensure we get an error */
-	ptr = NULL;
-	ret = bpf_copy_from_user_task(&user_data, sizeof(uint32_t), ptr, task, 0);
-	if (ret) {
-		++num_expected_failure_copy_from_user_task;
-	} else {
-		BPF_SEQ_PRINTF(seq, "%s\n", info);
-		return 0;
-	}
-
-	/* Try to read the contents of the task's instruction pointer from the
-	 * remote task's address space.
-	 */
-	regs = (struct pt_regs *)bpf_task_pt_regs(task);
-	if (regs == (void *)0) {
-		BPF_SEQ_PRINTF(seq, "%s\n", info);
-		return 0;
-	}
-	ptr = (void *)PT_REGS_IP(regs);
-
-	ret = bpf_copy_from_user_task(&user_data, sizeof(uint32_t), ptr, task, 0);
-	if (ret) {
-		BPF_SEQ_PRINTF(seq, "%s\n", info);
-		return 0;
-	}
-	++num_success_copy_from_user_task;
-
-	if (ctx->meta->seq_num == 0)
-		BPF_SEQ_PRINTF(seq, "    tgid      gid     data\n");
-
-	BPF_SEQ_PRINTF(seq, "%8d %8d %8d\n", task->tgid, task->pid, user_data);
-	return 0;
-}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_btf.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_btf.c
index bca8b889cb10..ef2f7c8d9373 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task_btf.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_btf.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020, Oracle and/or its affiliates. */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_core_read.h>
 
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c
index b0255080662d..959a8d899eaf 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_file.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c
index f2b8167b72a8..f5a309455490 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_stack.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
@@ -35,6 +35,8 @@ int dump_task_stack(struct bpf_iter__task *ctx)
 	return 0;
 }
 
+int num_user_stacks = 0;
+
 SEC("iter/task")
 int get_task_user_stacks(struct bpf_iter__task *ctx)
 {
@@ -51,6 +53,9 @@ int get_task_user_stacks(struct bpf_iter__task *ctx)
 	if (res <= 0)
 		return 0;
 
+	/* Only one task, the current one, should succeed */
+	++num_user_stacks;
+
 	buf_sz += res;
 
 	/* If the verifier doesn't refine bpf_get_task_stack res, and instead
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task_vma.c b/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c
index dd923dc637d5..d64ba7ddaed5 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task_vma.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task_vmas.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
@@ -35,7 +35,7 @@ SEC("iter/task_vma") int proc_maps(struct bpf_iter__task_vma *ctx)
 		return 0;
 
 	file = vma->vm_file;
-	if (task->tgid != pid) {
+	if (task->tgid != (pid_t)pid) {
 		if (one_task)
 			one_task_error = 1;
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c
new file mode 100644
index 000000000000..966ee5a7b066
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c
@@ -0,0 +1,198 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+uint32_t tid = 0;
+int num_unknown_tid = 0;
+int num_known_tid = 0;
+void *user_ptr = 0;
+void *user_ptr_long = 0;
+uint32_t pid = 0;
+
+static char big_str1[5000];
+static char big_str2[5005];
+static char big_str3[4996];
+
+SEC("iter/task")
+int dump_task(struct bpf_iter__task *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct task_struct *task = ctx->task;
+	static char info[] = "    === END ===";
+
+	if (task == (void *)0) {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	if (task->pid != (pid_t)tid)
+		num_unknown_tid++;
+	else
+		num_known_tid++;
+
+	if (ctx->meta->seq_num == 0)
+		BPF_SEQ_PRINTF(seq, "    tgid      gid\n");
+
+	BPF_SEQ_PRINTF(seq, "%8d %8d\n", task->tgid, task->pid);
+	return 0;
+}
+
+int num_expected_failure_copy_from_user_task = 0;
+int num_expected_failure_copy_from_user_task_str = 0;
+int num_success_copy_from_user_task = 0;
+int num_success_copy_from_user_task_str = 0;
+
+SEC("iter.s/task")
+int dump_task_sleepable(struct bpf_iter__task *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct task_struct *task = ctx->task;
+	static const char info[] = "    === END ===";
+	struct pt_regs *regs;
+	char task_str1[10] = "aaaaaaaaaa";
+	char task_str2[10], task_str3[10];
+	char task_str4[20] = "aaaaaaaaaaaaaaaaaaaa";
+	void *ptr;
+	uint32_t user_data = 0;
+	int ret;
+
+	if (task == (void *)0) {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	/* Read an invalid pointer and ensure we get an error */
+	ptr = NULL;
+	ret = bpf_copy_from_user_task(&user_data, sizeof(uint32_t), ptr, task, 0);
+	if (ret) {
+		++num_expected_failure_copy_from_user_task;
+	} else {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	/* Try to read the contents of the task's instruction pointer from the
+	 * remote task's address space.
+	 */
+	regs = (struct pt_regs *)bpf_task_pt_regs(task);
+	if (regs == (void *)0) {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+	ptr = (void *)PT_REGS_IP(regs);
+
+	ret = bpf_copy_from_user_task(&user_data, sizeof(uint32_t), ptr, task, 0);
+	if (ret) {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	++num_success_copy_from_user_task;
+
+	/* Read an invalid pointer and ensure we get an error */
+	ptr = NULL;
+	ret = bpf_copy_from_user_task_str((char *)task_str1, sizeof(task_str1), ptr, task, 0);
+	if (ret >= 0 || task_str1[9] != 'a' || task_str1[0] != '\0') {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	/* Read an invalid pointer and ensure we get error with pad zeros flag */
+	ptr = NULL;
+	ret = bpf_copy_from_user_task_str((char *)task_str1, sizeof(task_str1),
+					  ptr, task, BPF_F_PAD_ZEROS);
+	if (ret >= 0 || task_str1[9] != '\0' || task_str1[0] != '\0') {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	++num_expected_failure_copy_from_user_task_str;
+
+	/* Same length as the string */
+	ret = bpf_copy_from_user_task_str((char *)task_str2, 10, user_ptr, task, 0);
+	/* only need to do the task pid check once */
+	if (bpf_strncmp(task_str2, 10, "test_data\0") != 0 || ret != 10 || task->tgid != pid) {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	/* Shorter length than the string */
+	ret = bpf_copy_from_user_task_str((char *)task_str3, 2, user_ptr, task, 0);
+	if (bpf_strncmp(task_str3, 2, "t\0") != 0 || ret != 2) {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	/* Longer length than the string */
+	ret = bpf_copy_from_user_task_str((char *)task_str4, 20, user_ptr, task, 0);
+	if (bpf_strncmp(task_str4, 10, "test_data\0") != 0 || ret != 10
+	    || task_str4[sizeof(task_str4) - 1] != 'a') {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	/* Longer length than the string with pad zeros flag */
+	ret = bpf_copy_from_user_task_str((char *)task_str4, 20, user_ptr, task, BPF_F_PAD_ZEROS);
+	if (bpf_strncmp(task_str4, 10, "test_data\0") != 0 || ret != 10
+	    || task_str4[sizeof(task_str4) - 1] != '\0') {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	/* Longer length than the string past a page boundary */
+	ret = bpf_copy_from_user_task_str(big_str1, 5000, user_ptr, task, 0);
+	if (bpf_strncmp(big_str1, 10, "test_data\0") != 0 || ret != 10) {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	/* String that crosses a page boundary */
+	ret = bpf_copy_from_user_task_str(big_str1, 5000, user_ptr_long, task, BPF_F_PAD_ZEROS);
+	if (bpf_strncmp(big_str1, 4, "baba") != 0 || ret != 5000
+	    || bpf_strncmp(big_str1 + 4996, 4, "bab\0") != 0) {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	for (int i = 0; i < 4999; ++i) {
+		if (i % 2 == 0) {
+			if (big_str1[i] != 'b') {
+				BPF_SEQ_PRINTF(seq, "%s\n", info);
+				return 0;
+			}
+		} else {
+			if (big_str1[i] != 'a') {
+				BPF_SEQ_PRINTF(seq, "%s\n", info);
+				return 0;
+			}
+		}
+	}
+
+	/* Longer length than the string that crosses a page boundary */
+	ret = bpf_copy_from_user_task_str(big_str2, 5005, user_ptr_long, task, BPF_F_PAD_ZEROS);
+	if (bpf_strncmp(big_str2, 4, "baba") != 0 || ret != 5000
+	    || bpf_strncmp(big_str2 + 4996, 5, "bab\0\0") != 0) {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	/* Shorter length than the string that crosses a page boundary */
+	ret = bpf_copy_from_user_task_str(big_str3, 4996, user_ptr_long, task, 0);
+	if (bpf_strncmp(big_str3, 4, "baba") != 0 || ret != 4996
+	    || bpf_strncmp(big_str3 + 4992, 4, "bab\0") != 0) {
+		BPF_SEQ_PRINTF(seq, "%s\n", info);
+		return 0;
+	}
+
+	++num_success_copy_from_user_task_str;
+
+	if (ctx->meta->seq_num == 0)
+		BPF_SEQ_PRINTF(seq, "    tgid      gid     data\n");
+
+	BPF_SEQ_PRINTF(seq, "%8d %8d %8d\n", task->tgid, task->pid, user_data);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c
index 92267abb462f..b1e509b231cd 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
@@ -99,13 +99,13 @@ static int dump_tcp_sock(struct seq_file *seq, struct tcp_sock *tp,
 	    icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
 	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		timer_active = 1;
-		timer_expires = icsk->icsk_timeout;
+		timer_expires = sp->tcp_retransmit_timer.expires;
 	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
 		timer_active = 4;
-		timer_expires = icsk->icsk_timeout;
-	} else if (timer_pending(&sp->sk_timer)) {
+		timer_expires = sp->tcp_retransmit_timer.expires;
+	} else if (timer_pending(&icsk->icsk_keepalive_timer)) {
 		timer_active = 2;
-		timer_expires = sp->sk_timer.expires;
+		timer_expires = icsk->icsk_keepalive_timer.expires;
 	} else {
 		timer_active = 0;
 		timer_expires = bpf_jiffies64();
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c
index 943f7bba180e..dbc7166aee91 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp6.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
@@ -99,13 +99,13 @@ static int dump_tcp6_sock(struct seq_file *seq, struct tcp6_sock *tp,
 	    icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
 	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		timer_active = 1;
-		timer_expires = icsk->icsk_timeout;
+		timer_expires = sp->tcp_retransmit_timer.expires;
 	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
 		timer_active = 4;
-		timer_expires = icsk->icsk_timeout;
-	} else if (timer_pending(&sp->sk_timer)) {
+		timer_expires = sp->tcp_retransmit_timer.expires;
+	} else if (timer_pending(&icsk->icsk_keepalive_timer)) {
 		timer_active = 2;
-		timer_expires = sp->sk_timer.expires;
+		timer_expires = icsk->icsk_keepalive_timer.expires;
 	} else {
 		timer_active = 0;
 		timer_expires = bpf_jiffies64();
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c
index 2a4647f20c46..6b17e7e86a48 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern3.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c
index 400fdf8d6233..56177508798f 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern4.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
@@ -45,7 +45,7 @@ int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
 	}
 
 	/* fill seq_file buffer */
-	for (i = 0; i < print_len; i++)
+	for (i = 0; i < (int)print_len; i++)
 		bpf_seq_write(seq, &seq_num, sizeof(seq_num));
 
 	return ret;
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern5.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern5.c
index e3a7575e81d2..9d8b7310d2c2 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern5.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern5.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern6.c b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern6.c
index 1c7304f56b1e..b150bd468824 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern6.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern6.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h
index d5e3df66ad9a..6a4c50497c5e 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_test_kern_common.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c
index cf0c485b1ed7..23b2aa2604de 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_udp4.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
@@ -64,7 +64,8 @@ int dump_udp4(struct bpf_iter__udp *ctx)
 		       0, 0L, 0, ctx->uid, 0,
 		       sock_i_ino(&inet->sk),
 		       inet->sk.sk_refcnt.refs.counter, udp_sk,
-		       inet->sk.sk_drops.counter);
+		       udp_sk->drop_counters.drops0.counter +
+		       udp_sk->drop_counters.drops1.counter);
 
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c b/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c
index 5031e21c433f..c48b05aa2a4b 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_udp6.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
@@ -72,7 +72,7 @@ int dump_udp6(struct bpf_iter__udp *ctx)
 		       0, 0L, 0, ctx->uid, 0,
 		       sock_i_ino(&inet->sk),
 		       inet->sk.sk_refcnt.refs.counter, udp_sk,
-		       inet->sk.sk_drops.counter);
-
+		       udp_sk->drop_counters.drops0.counter +
+		       udp_sk->drop_counters.drops1.counter);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_unix.c b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c
index e6aefae38894..fea275df9e22 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_unix.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_unix.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright Amazon.com Inc. or its affiliates. */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_vma_offset.c b/tools/testing/selftests/bpf/progs/bpf_iter_vma_offset.c
index ee7455d2623a..174298e122d3 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_vma_offset.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_vma_offset.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bpf_loop.c b/tools/testing/selftests/bpf/progs/bpf_loop.c
index de1fc82d2710..1d194455b109 100644
--- a/tools/testing/selftests/bpf/progs/bpf_loop.c
+++ b/tools/testing/selftests/bpf/progs/bpf_loop.c
@@ -138,8 +138,6 @@ static int callback_set_0f(int i, void *ctx)
 SEC("fentry/" SYS_PREFIX "sys_nanosleep")
 int prog_non_constant_callback(void *ctx)
 {
-	struct callback_ctx data = {};
-
 	if (bpf_get_current_pid_tgid() >> 32 != pid)
 		return 0;
 
diff --git a/tools/testing/selftests/bpf/progs/bpf_loop_bench.c b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c
index 4ce76eb064c4..d461746fd3c1 100644
--- a/tools/testing/selftests/bpf/progs/bpf_loop_bench.c
+++ b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c
@@ -15,13 +15,16 @@ static int empty_callback(__u32 index, void *data)
 	return 0;
 }
 
+static int outer_loop(__u32 index, void *data)
+{
+	bpf_loop(nr_loops, empty_callback, NULL, 0);
+	__sync_add_and_fetch(&hits, nr_loops);
+	return 0;
+}
+
 SEC("fentry/" SYS_PREFIX "sys_getpgid")
 int benchmark(void *ctx)
 {
-	for (int i = 0; i < 1000; i++) {
-		bpf_loop(nr_loops, empty_callback, NULL, 0);
-
-		__sync_add_and_fetch(&hits, nr_loops);
-	}
+	bpf_loop(1000, outer_loop, NULL, 0);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index 4a01ea9113bf..c9bfbe1bafc1 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
@@ -2,10 +2,195 @@
 #ifndef __BPF_MISC_H__
 #define __BPF_MISC_H__
 
-#define __msg(msg)		__attribute__((btf_decl_tag("comment:test_expect_msg=" msg)))
+#define XSTR(s) STR(s)
+#define STR(s) #s
+
+/* Expand a macro and then stringize the expansion */
+#define QUOTE(str) #str
+#define EXPAND_QUOTE(str) QUOTE(str)
+
+/* This set of attributes controls behavior of the
+ * test_loader.c:test_loader__run_subtests().
+ *
+ * The test_loader sequentially loads each program in a skeleton.
+ * Programs could be loaded in privileged and unprivileged modes.
+ * - __success, __failure, __msg, __regex imply privileged mode;
+ * - __success_unpriv, __failure_unpriv, __msg_unpriv, __regex_unpriv
+ *   imply unprivileged mode.
+ * If combination of privileged and unprivileged attributes is present
+ * both modes are used. If none are present privileged mode is implied.
+ *
+ * See test_loader.c:drop_capabilities() for exact set of capabilities
+ * that differ between privileged and unprivileged modes.
+ *
+ * For test filtering purposes the name of the program loaded in
+ * unprivileged mode is derived from the usual program name by adding
+ * `@unpriv' suffix.
+ *
+ * __msg             Message expected to be found in the verifier log.
+ *                   Multiple __msg attributes could be specified.
+ *                   To match a regular expression use "{{" "}}" brackets,
+ *                   e.g. "foo{{[0-9]+}}"  matches strings like "foo007".
+ *                   Extended POSIX regular expression syntax is allowed
+ *                   inside the brackets.
+ * __not_msg         Message not expected to be found in verifier log.
+ *                   If __msg_not is situated between __msg tags
+ *                   framework matches __msg tags first, and then
+ *                   checks that __msg_not is not present in a portion of
+ *                   a log between bracketing __msg tags.
+ *                   Same regex syntax as for __msg is supported.
+ * __msg_unpriv      Same as __msg but for unprivileged mode.
+ * __not_msg_unpriv  Same as __not_msg but for unprivileged mode.
+ *
+ * __stderr          Message expected to be found in bpf stderr stream. The
+ *                   same regex rules apply like __msg.
+ * __stderr_unpriv   Same as __stderr but for unpriveleged mode.
+ * __stdout          Same as __stderr but for stdout stream.
+ * __stdout_unpriv   Same as __stdout but for unpriveleged mode.
+ *
+ * __xlated          Expect a line in a disassembly log after verifier applies rewrites.
+ *                   Multiple __xlated attributes could be specified.
+ *                   Regular expressions could be specified same way as in __msg.
+ * __xlated_unpriv   Same as __xlated but for unprivileged mode.
+ *
+ * __jited           Match a line in a disassembly of the jited BPF program.
+ *                   Has to be used after __arch_* macro.
+ *                   For example:
+ *
+ *                       __arch_x86_64
+ *                       __jited("   endbr64")
+ *                       __jited("   nopl    (%rax,%rax)")
+ *                       __jited("   xorq    %rax, %rax")
+ *                       ...
+ *                       __naked void some_test(void)
+ *                       {
+ *                           asm volatile (... ::: __clobber_all);
+ *                       }
+ *
+ *                   Regular expressions could be included in patterns same way
+ *                   as in __msg.
+ *
+ *                   By default assume that each pattern has to be matched on the
+ *                   next consecutive line of disassembly, e.g.:
+ *
+ *                       __jited("   endbr64")             # matched on line N
+ *                       __jited("   nopl    (%rax,%rax)") # matched on line N+1
+ *
+ *                   If match occurs on a wrong line an error is reported.
+ *                   To override this behaviour use literal "...", e.g.:
+ *
+ *                       __jited("   endbr64")             # matched on line N
+ *                       __jited("...")                    # not matched
+ *                       __jited("   nopl    (%rax,%rax)") # matched on any line >= N
+ *
+ * __jited_unpriv    Same as __jited but for unprivileged mode.
+ *
+ *
+ * __success         Expect program load success in privileged mode.
+ * __success_unpriv  Expect program load success in unprivileged mode.
+ *
+ * __failure         Expect program load failure in privileged mode.
+ * __failure_unpriv  Expect program load failure in unprivileged mode.
+ *
+ * __retval          Execute the program using BPF_PROG_TEST_RUN command,
+ *                   expect return value to match passed parameter:
+ *                   - a decimal number
+ *                   - a hexadecimal number, when starts from 0x
+ *                   - a macro which expands to one of the above
+ *                   - literal _INT_MIN (expands to INT_MIN)
+ *                   In addition, two special macros are defined below:
+ *                   - POINTER_VALUE
+ *                   - TEST_DATA_LEN
+ * __retval_unpriv   Same, but load program in unprivileged mode.
+ *
+ * __description     Text to be used instead of a program name for display
+ *                   and filtering purposes.
+ *
+ * __log_level       Log level to use for the program, numeric value expected.
+ *
+ * __flag            Adds one flag use for the program, the following values are valid:
+ *                   - BPF_F_STRICT_ALIGNMENT;
+ *                   - BPF_F_TEST_RND_HI32;
+ *                   - BPF_F_TEST_STATE_FREQ;
+ *                   - BPF_F_SLEEPABLE;
+ *                   - BPF_F_XDP_HAS_FRAGS;
+ *                   - A numeric value.
+ *                   Multiple __flag attributes could be specified, the final flags
+ *                   value is derived by applying binary "or" to all specified values.
+ *
+ * __auxiliary         Annotated program is not a separate test, but used as auxiliary
+ *                     for some other test cases and should always be loaded.
+ * __auxiliary_unpriv  Same, but load program in unprivileged mode.
+ *
+ * __arch_*          Specify on which architecture the test case should be tested.
+ *                   Several __arch_* annotations could be specified at once.
+ *                   When test case is not run on current arch it is marked as skipped.
+ * __caps_unpriv     Specify the capabilities that should be set when running the test.
+ *
+ * __linear_size     Specify the size of the linear area of non-linear skbs, or
+ *                   0 for linear skbs.
+ */
+#define __msg(msg)		__attribute__((btf_decl_tag("comment:test_expect_msg=" XSTR(__COUNTER__) "=" msg)))
+#define __not_msg(msg)		__attribute__((btf_decl_tag("comment:test_expect_not_msg=" XSTR(__COUNTER__) "=" msg)))
+#define __xlated(msg)		__attribute__((btf_decl_tag("comment:test_expect_xlated=" XSTR(__COUNTER__) "=" msg)))
+#define __jited(msg)		__attribute__((btf_decl_tag("comment:test_jited=" XSTR(__COUNTER__) "=" msg)))
 #define __failure		__attribute__((btf_decl_tag("comment:test_expect_failure")))
 #define __success		__attribute__((btf_decl_tag("comment:test_expect_success")))
+#define __description(desc)	__attribute__((btf_decl_tag("comment:test_description=" desc)))
+#define __msg_unpriv(msg)	__attribute__((btf_decl_tag("comment:test_expect_msg_unpriv=" XSTR(__COUNTER__) "=" msg)))
+#define __not_msg_unpriv(msg)	__attribute__((btf_decl_tag("comment:test_expect_not_msg_unpriv=" XSTR(__COUNTER__) "=" msg)))
+#define __xlated_unpriv(msg)	__attribute__((btf_decl_tag("comment:test_expect_xlated_unpriv=" XSTR(__COUNTER__) "=" msg)))
+#define __jited_unpriv(msg)	__attribute__((btf_decl_tag("comment:test_jited=" XSTR(__COUNTER__) "=" msg)))
+#define __failure_unpriv	__attribute__((btf_decl_tag("comment:test_expect_failure_unpriv")))
+#define __success_unpriv	__attribute__((btf_decl_tag("comment:test_expect_success_unpriv")))
 #define __log_level(lvl)	__attribute__((btf_decl_tag("comment:test_log_level="#lvl)))
+#define __flag(flag)		__attribute__((btf_decl_tag("comment:test_prog_flags="#flag)))
+#define __retval(val)		__attribute__((btf_decl_tag("comment:test_retval="XSTR(val))))
+#define __retval_unpriv(val)	__attribute__((btf_decl_tag("comment:test_retval_unpriv="XSTR(val))))
+#define __auxiliary		__attribute__((btf_decl_tag("comment:test_auxiliary")))
+#define __auxiliary_unpriv	__attribute__((btf_decl_tag("comment:test_auxiliary_unpriv")))
+#define __btf_path(path)	__attribute__((btf_decl_tag("comment:test_btf_path=" path)))
+#define __arch(arch)		__attribute__((btf_decl_tag("comment:test_arch=" arch)))
+#define __arch_x86_64		__arch("X86_64")
+#define __arch_arm64		__arch("ARM64")
+#define __arch_riscv64		__arch("RISCV64")
+#define __arch_s390x		__arch("s390x")
+#define __caps_unpriv(caps)	__attribute__((btf_decl_tag("comment:test_caps_unpriv=" EXPAND_QUOTE(caps))))
+#define __load_if_JITed()	__attribute__((btf_decl_tag("comment:load_mode=jited")))
+#define __load_if_no_JITed()	__attribute__((btf_decl_tag("comment:load_mode=no_jited")))
+#define __stderr(msg)		__attribute__((btf_decl_tag("comment:test_expect_stderr=" XSTR(__COUNTER__) "=" msg)))
+#define __stderr_unpriv(msg)	__attribute__((btf_decl_tag("comment:test_expect_stderr_unpriv=" XSTR(__COUNTER__) "=" msg)))
+#define __stdout(msg)		__attribute__((btf_decl_tag("comment:test_expect_stdout=" XSTR(__COUNTER__) "=" msg)))
+#define __stdout_unpriv(msg)	__attribute__((btf_decl_tag("comment:test_expect_stdout_unpriv=" XSTR(__COUNTER__) "=" msg)))
+#define __linear_size(sz)	__attribute__((btf_decl_tag("comment:test_linear_size=" XSTR(sz))))
+
+/* Define common capabilities tested using __caps_unpriv */
+#define CAP_NET_ADMIN		12
+#define CAP_SYS_ADMIN		21
+#define CAP_PERFMON		38
+#define CAP_BPF			39
+
+/* Convenience macro for use with 'asm volatile' blocks */
+#define __naked __attribute__((naked))
+#define __clobber_all "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7", "r8", "r9", "memory"
+#define __clobber_common "r0", "r1", "r2", "r3", "r4", "r5", "memory"
+#define __imm(name) [name]"i"(name)
+#define __imm_const(name, expr) [name]"i"(expr)
+#define __imm_addr(name) [name]"i"(&name)
+#define __imm_ptr(name) [name]"r"(&name)
+#define __imm_insn(name, expr) [name]"i"(*(long *)&(expr))
+
+#define sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER))
+#define offsetofend(TYPE, MEMBER) \
+	(offsetof(TYPE, MEMBER) + sizeof_field(TYPE, MEMBER))
+
+/* Magic constants used with __retval() */
+#define POINTER_VALUE	0xbadcafe
+#define TEST_DATA_LEN	64
+
+#ifndef __used
+#define __used __attribute__((used))
+#endif
 
 #if defined(__TARGET_ARCH_x86)
 #define SYSCALL_WRAPPER 1
@@ -16,9 +201,73 @@
 #elif defined(__TARGET_ARCH_arm64)
 #define SYSCALL_WRAPPER 1
 #define SYS_PREFIX "__arm64_"
+#elif defined(__TARGET_ARCH_riscv)
+#define SYSCALL_WRAPPER 1
+#define SYS_PREFIX "__riscv_"
+#elif defined(__TARGET_ARCH_powerpc)
+#define SYSCALL_WRAPPER 1
+#define SYS_PREFIX ""
 #else
 #define SYSCALL_WRAPPER 0
 #define SYS_PREFIX "__se_"
 #endif
 
+/* How many arguments are passed to function in register */
+#if defined(__TARGET_ARCH_x86) || defined(__x86_64__)
+#define FUNC_REG_ARG_CNT 6
+#elif defined(__i386__)
+#define FUNC_REG_ARG_CNT 3
+#elif defined(__TARGET_ARCH_s390) || defined(__s390x__)
+#define FUNC_REG_ARG_CNT 5
+#elif defined(__TARGET_ARCH_arm) || defined(__arm__)
+#define FUNC_REG_ARG_CNT 4
+#elif defined(__TARGET_ARCH_arm64) || defined(__aarch64__)
+#define FUNC_REG_ARG_CNT 8
+#elif defined(__TARGET_ARCH_mips) || defined(__mips__)
+#define FUNC_REG_ARG_CNT 8
+#elif defined(__TARGET_ARCH_powerpc) || defined(__powerpc__) || defined(__powerpc64__)
+#define FUNC_REG_ARG_CNT 8
+#elif defined(__TARGET_ARCH_sparc) || defined(__sparc__)
+#define FUNC_REG_ARG_CNT 6
+#elif defined(__TARGET_ARCH_riscv) || defined(__riscv__)
+#define FUNC_REG_ARG_CNT 8
+#else
+/* default to 5 for others */
+#define FUNC_REG_ARG_CNT 5
+#endif
+
+/* make it look to compiler like value is read and written */
+#define __sink(expr) asm volatile("" : "+g"(expr))
+
+#ifndef ARRAY_SIZE
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#endif
+
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) ||	\
+     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) ||		\
+     defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390) ||	\
+     defined(__TARGET_ARCH_loongarch)) &&				\
+	__clang_major__ >= 18
+#define CAN_USE_GOTOL
+#endif
+
+#if __clang_major__ >= 18
+#define CAN_USE_BPF_ST
+#endif
+
+#if __clang_major__ >= 18 && defined(ENABLE_ATOMICS_TESTS) &&		\
+	(defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) ||	\
+	 (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64)) || \
+	  (defined(__TARGET_ARCH_powerpc))
+#define CAN_USE_LOAD_ACQ_STORE_REL
+#endif
+
+#if defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)
+#define SPEC_V1
+#endif
+
+#if defined(__TARGET_ARCH_x86)
+#define SPEC_V4
+#endif
+
 #endif
diff --git a/tools/testing/selftests/bpf/progs/bpf_qdisc_common.h b/tools/testing/selftests/bpf/progs/bpf_qdisc_common.h
new file mode 100644
index 000000000000..3754f581b328
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_qdisc_common.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _BPF_QDISC_COMMON_H
+#define _BPF_QDISC_COMMON_H
+
+#define NET_XMIT_SUCCESS        0x00
+#define NET_XMIT_DROP           0x01    /* skb dropped                  */
+#define NET_XMIT_CN             0x02    /* congestion notification      */
+
+#define TC_PRIO_CONTROL  7
+#define TC_PRIO_MAX      15
+
+#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8)))
+
+struct bpf_sk_buff_ptr;
+
+static struct qdisc_skb_cb *qdisc_skb_cb(const struct sk_buff *skb)
+{
+	return (struct qdisc_skb_cb *)skb->cb;
+}
+
+static inline unsigned int qdisc_pkt_len(const struct sk_buff *skb)
+{
+	return qdisc_skb_cb(skb)->pkt_len;
+}
+
+#endif
diff --git a/tools/testing/selftests/bpf/progs/bpf_qdisc_fail__incompl_ops.c b/tools/testing/selftests/bpf/progs/bpf_qdisc_fail__incompl_ops.c
new file mode 100644
index 000000000000..f188062ed730
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_qdisc_fail__incompl_ops.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include "bpf_experimental.h"
+#include "bpf_qdisc_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("struct_ops")
+int BPF_PROG(bpf_qdisc_test_enqueue, struct sk_buff *skb, struct Qdisc *sch,
+	     struct bpf_sk_buff_ptr *to_free)
+{
+	bpf_qdisc_skb_drop(skb, to_free);
+	return NET_XMIT_DROP;
+}
+
+SEC("struct_ops")
+struct sk_buff *BPF_PROG(bpf_qdisc_test_dequeue, struct Qdisc *sch)
+{
+	return NULL;
+}
+
+SEC("struct_ops")
+void BPF_PROG(bpf_qdisc_test_reset, struct Qdisc *sch)
+{
+}
+
+SEC("struct_ops")
+void BPF_PROG(bpf_qdisc_test_destroy, struct Qdisc *sch)
+{
+}
+
+SEC(".struct_ops")
+struct Qdisc_ops test = {
+	.enqueue   = (void *)bpf_qdisc_test_enqueue,
+	.dequeue   = (void *)bpf_qdisc_test_dequeue,
+	.reset     = (void *)bpf_qdisc_test_reset,
+	.destroy   = (void *)bpf_qdisc_test_destroy,
+	.id        = "bpf_qdisc_test",
+};
+
diff --git a/tools/testing/selftests/bpf/progs/bpf_qdisc_fifo.c b/tools/testing/selftests/bpf/progs/bpf_qdisc_fifo.c
new file mode 100644
index 000000000000..1de2be3e370b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_qdisc_fifo.c
@@ -0,0 +1,126 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include "bpf_experimental.h"
+#include "bpf_qdisc_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct skb_node {
+	struct sk_buff __kptr * skb;
+	struct bpf_list_node node;
+};
+
+private(A) struct bpf_spin_lock q_fifo_lock;
+private(A) struct bpf_list_head q_fifo __contains(skb_node, node);
+
+bool init_called;
+
+SEC("struct_ops/bpf_fifo_enqueue")
+int BPF_PROG(bpf_fifo_enqueue, struct sk_buff *skb, struct Qdisc *sch,
+	     struct bpf_sk_buff_ptr *to_free)
+{
+	struct skb_node *skbn;
+	u32 pkt_len;
+
+	if (sch->q.qlen == sch->limit)
+		goto drop;
+
+	skbn = bpf_obj_new(typeof(*skbn));
+	if (!skbn)
+		goto drop;
+
+	pkt_len = qdisc_pkt_len(skb);
+
+	sch->q.qlen++;
+	skb = bpf_kptr_xchg(&skbn->skb, skb);
+	if (skb)
+		bpf_qdisc_skb_drop(skb, to_free);
+
+	bpf_spin_lock(&q_fifo_lock);
+	bpf_list_push_back(&q_fifo, &skbn->node);
+	bpf_spin_unlock(&q_fifo_lock);
+
+	sch->qstats.backlog += pkt_len;
+	return NET_XMIT_SUCCESS;
+drop:
+	bpf_qdisc_skb_drop(skb, to_free);
+	return NET_XMIT_DROP;
+}
+
+SEC("struct_ops/bpf_fifo_dequeue")
+struct sk_buff *BPF_PROG(bpf_fifo_dequeue, struct Qdisc *sch)
+{
+	struct bpf_list_node *node;
+	struct sk_buff *skb = NULL;
+	struct skb_node *skbn;
+
+	bpf_spin_lock(&q_fifo_lock);
+	node = bpf_list_pop_front(&q_fifo);
+	bpf_spin_unlock(&q_fifo_lock);
+	if (!node)
+		return NULL;
+
+	skbn = container_of(node, struct skb_node, node);
+	skb = bpf_kptr_xchg(&skbn->skb, skb);
+	bpf_obj_drop(skbn);
+	if (!skb)
+		return NULL;
+
+	sch->qstats.backlog -= qdisc_pkt_len(skb);
+	bpf_qdisc_bstats_update(sch, skb);
+	sch->q.qlen--;
+
+	return skb;
+}
+
+SEC("struct_ops/bpf_fifo_init")
+int BPF_PROG(bpf_fifo_init, struct Qdisc *sch, struct nlattr *opt,
+	     struct netlink_ext_ack *extack)
+{
+	sch->limit = 1000;
+	init_called = true;
+	return 0;
+}
+
+SEC("struct_ops/bpf_fifo_reset")
+void BPF_PROG(bpf_fifo_reset, struct Qdisc *sch)
+{
+	struct bpf_list_node *node;
+	struct skb_node *skbn;
+	int i;
+
+	bpf_for(i, 0, sch->q.qlen) {
+		struct sk_buff *skb = NULL;
+
+		bpf_spin_lock(&q_fifo_lock);
+		node = bpf_list_pop_front(&q_fifo);
+		bpf_spin_unlock(&q_fifo_lock);
+
+		if (!node)
+			break;
+
+		skbn = container_of(node, struct skb_node, node);
+		skb = bpf_kptr_xchg(&skbn->skb, skb);
+		if (skb)
+			bpf_kfree_skb(skb);
+		bpf_obj_drop(skbn);
+	}
+	sch->q.qlen = 0;
+}
+
+SEC("struct_ops")
+void BPF_PROG(bpf_fifo_destroy, struct Qdisc *sch)
+{
+}
+
+SEC(".struct_ops")
+struct Qdisc_ops fifo = {
+	.enqueue   = (void *)bpf_fifo_enqueue,
+	.dequeue   = (void *)bpf_fifo_dequeue,
+	.init      = (void *)bpf_fifo_init,
+	.reset     = (void *)bpf_fifo_reset,
+	.destroy   = (void *)bpf_fifo_destroy,
+	.id        = "bpf_fifo",
+};
+
diff --git a/tools/testing/selftests/bpf/progs/bpf_qdisc_fq.c b/tools/testing/selftests/bpf/progs/bpf_qdisc_fq.c
new file mode 100644
index 000000000000..1a3233a275c7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_qdisc_fq.c
@@ -0,0 +1,756 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* bpf_fq is intended for testing the bpf qdisc infrastructure and not a direct
+ * copy of sch_fq. bpf_fq implements the scheduling algorithm of sch_fq before
+ * 29f834aa326e ("net_sched: sch_fq: add 3 bands and WRR scheduling") was
+ * introduced. It gives each flow a fair chance to transmit packets in a
+ * round-robin fashion. Note that for flow pacing, bpf_fq currently only
+ * respects skb->tstamp but not skb->sk->sk_pacing_rate. In addition, if there
+ * are multiple bpf_fq instances, they will have a shared view of flows and
+ * configuration since some key data structure such as fq_prio_flows,
+ * fq_nonprio_flows, and fq_bpf_data are global.
+ *
+ * To use bpf_fq alone without running selftests, use the following commands.
+ *
+ * 1. Register bpf_fq to the kernel
+ *     bpftool struct_ops register bpf_qdisc_fq.bpf.o /sys/fs/bpf
+ * 2. Add bpf_fq to an interface
+ *     tc qdisc add dev <interface name> root handle <handle> bpf_fq
+ * 3. Delete bpf_fq attached to the interface
+ *     tc qdisc delete dev <interface name> root
+ * 4. Unregister bpf_fq
+ *     bpftool struct_ops unregister name fq
+ *
+ * The qdisc name, bpf_fq, used in tc commands is defined by Qdisc_ops.id.
+ * The struct_ops_map_name, fq, used in the bpftool command is the name of the
+ * Qdisc_ops.
+ *
+ * SEC(".struct_ops")
+ * struct Qdisc_ops fq = {
+ *         ...
+ *         .id        = "bpf_fq",
+ * };
+ */
+
+#include <vmlinux.h>
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_experimental.h"
+#include "bpf_qdisc_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define NSEC_PER_USEC 1000L
+#define NSEC_PER_SEC 1000000000L
+
+#define NUM_QUEUE (1 << 20)
+
+struct fq_bpf_data {
+	u32 quantum;
+	u32 initial_quantum;
+	u32 flow_refill_delay;
+	u32 flow_plimit;
+	u64 horizon;
+	u32 orphan_mask;
+	u32 timer_slack;
+	u64 time_next_delayed_flow;
+	u64 unthrottle_latency_ns;
+	u8 horizon_drop;
+	u32 new_flow_cnt;
+	u32 old_flow_cnt;
+	u64 ktime_cache;
+};
+
+enum {
+	CLS_RET_PRIO	= 0,
+	CLS_RET_NONPRIO = 1,
+	CLS_RET_ERR	= 2,
+};
+
+struct skb_node {
+	u64 tstamp;
+	struct sk_buff __kptr * skb;
+	struct bpf_rb_node node;
+};
+
+struct fq_flow_node {
+	int credit;
+	u32 qlen;
+	u64 age;
+	u64 time_next_packet;
+	struct bpf_list_node list_node;
+	struct bpf_rb_node rb_node;
+	struct bpf_rb_root queue __contains(skb_node, node);
+	struct bpf_spin_lock lock;
+	struct bpf_refcount refcount;
+};
+
+struct dequeue_nonprio_ctx {
+	bool stop_iter;
+	u64 expire;
+	u64 now;
+};
+
+struct remove_flows_ctx {
+	bool gc_only;
+	u32 reset_cnt;
+	u32 reset_max;
+};
+
+struct unset_throttled_flows_ctx {
+	bool unset_all;
+	u64 now;
+};
+
+struct fq_stashed_flow {
+	struct fq_flow_node __kptr * flow;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __u64);
+	__type(value, struct fq_stashed_flow);
+	__uint(max_entries, NUM_QUEUE);
+} fq_nonprio_flows SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __u64);
+	__type(value, struct fq_stashed_flow);
+	__uint(max_entries, 1);
+} fq_prio_flows SEC(".maps");
+
+private(A) struct bpf_spin_lock fq_delayed_lock;
+private(A) struct bpf_rb_root fq_delayed __contains(fq_flow_node, rb_node);
+
+private(B) struct bpf_spin_lock fq_new_flows_lock;
+private(B) struct bpf_list_head fq_new_flows __contains(fq_flow_node, list_node);
+
+private(C) struct bpf_spin_lock fq_old_flows_lock;
+private(C) struct bpf_list_head fq_old_flows __contains(fq_flow_node, list_node);
+
+private(D) struct fq_bpf_data q;
+
+/* Wrapper for bpf_kptr_xchg that expects NULL dst */
+static void bpf_kptr_xchg_back(void *map_val, void *ptr)
+{
+	void *ret;
+
+	ret = bpf_kptr_xchg(map_val, ptr);
+	if (ret)
+		bpf_obj_drop(ret);
+}
+
+static bool skbn_tstamp_less(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	struct skb_node *skbn_a;
+	struct skb_node *skbn_b;
+
+	skbn_a = container_of(a, struct skb_node, node);
+	skbn_b = container_of(b, struct skb_node, node);
+
+	return skbn_a->tstamp < skbn_b->tstamp;
+}
+
+static bool fn_time_next_packet_less(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	struct fq_flow_node *flow_a;
+	struct fq_flow_node *flow_b;
+
+	flow_a = container_of(a, struct fq_flow_node, rb_node);
+	flow_b = container_of(b, struct fq_flow_node, rb_node);
+
+	return flow_a->time_next_packet < flow_b->time_next_packet;
+}
+
+static void
+fq_flows_add_head(struct bpf_list_head *head, struct bpf_spin_lock *lock,
+		  struct fq_flow_node *flow, u32 *flow_cnt)
+{
+	bpf_spin_lock(lock);
+	bpf_list_push_front(head, &flow->list_node);
+	bpf_spin_unlock(lock);
+	*flow_cnt += 1;
+}
+
+static void
+fq_flows_add_tail(struct bpf_list_head *head, struct bpf_spin_lock *lock,
+		  struct fq_flow_node *flow, u32 *flow_cnt)
+{
+	bpf_spin_lock(lock);
+	bpf_list_push_back(head, &flow->list_node);
+	bpf_spin_unlock(lock);
+	*flow_cnt += 1;
+}
+
+static void
+fq_flows_remove_front(struct bpf_list_head *head, struct bpf_spin_lock *lock,
+		      struct bpf_list_node **node, u32 *flow_cnt)
+{
+	bpf_spin_lock(lock);
+	*node = bpf_list_pop_front(head);
+	bpf_spin_unlock(lock);
+	*flow_cnt -= 1;
+}
+
+static bool
+fq_flows_is_empty(struct bpf_list_head *head, struct bpf_spin_lock *lock)
+{
+	struct bpf_list_node *node;
+
+	bpf_spin_lock(lock);
+	node = bpf_list_pop_front(head);
+	if (node) {
+		bpf_list_push_front(head, node);
+		bpf_spin_unlock(lock);
+		return false;
+	}
+	bpf_spin_unlock(lock);
+
+	return true;
+}
+
+/* flow->age is used to denote the state of the flow (not-detached, detached, throttled)
+ * as well as the timestamp when the flow is detached.
+ *
+ * 0: not-detached
+ * 1 - (~0ULL-1): detached
+ * ~0ULL: throttled
+ */
+static void fq_flow_set_detached(struct fq_flow_node *flow)
+{
+	flow->age = bpf_jiffies64();
+}
+
+static bool fq_flow_is_detached(struct fq_flow_node *flow)
+{
+	return flow->age != 0 && flow->age != ~0ULL;
+}
+
+static bool sk_listener(struct sock *sk)
+{
+	return (1 << sk->__sk_common.skc_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV);
+}
+
+static void fq_gc(void);
+
+static int fq_new_flow(void *flow_map, struct fq_stashed_flow **sflow, u64 hash)
+{
+	struct fq_stashed_flow tmp = {};
+	struct fq_flow_node *flow;
+	int ret;
+
+	flow = bpf_obj_new(typeof(*flow));
+	if (!flow)
+		return -ENOMEM;
+
+	flow->credit = q.initial_quantum,
+	flow->qlen = 0,
+	flow->age = 1,
+	flow->time_next_packet = 0,
+
+	ret = bpf_map_update_elem(flow_map, &hash, &tmp, 0);
+	if (ret == -ENOMEM || ret == -E2BIG) {
+		fq_gc();
+		bpf_map_update_elem(&fq_nonprio_flows, &hash, &tmp, 0);
+	}
+
+	*sflow = bpf_map_lookup_elem(flow_map, &hash);
+	if (!*sflow) {
+		bpf_obj_drop(flow);
+		return -ENOMEM;
+	}
+
+	bpf_kptr_xchg_back(&(*sflow)->flow, flow);
+	return 0;
+}
+
+static int
+fq_classify(struct sk_buff *skb, struct fq_stashed_flow **sflow)
+{
+	struct sock *sk = skb->sk;
+	int ret = CLS_RET_NONPRIO;
+	u64 hash = 0;
+
+	if ((skb->priority & TC_PRIO_MAX) == TC_PRIO_CONTROL) {
+		*sflow = bpf_map_lookup_elem(&fq_prio_flows, &hash);
+		ret = CLS_RET_PRIO;
+	} else {
+		if (!sk || sk_listener(sk)) {
+			hash = bpf_skb_get_hash(skb) & q.orphan_mask;
+			/* Avoid collision with an existing flow hash, which
+			 * only uses the lower 32 bits of hash, by setting the
+			 * upper half of hash to 1.
+			 */
+			hash |= (1ULL << 32);
+		} else if (sk->__sk_common.skc_state == TCP_CLOSE) {
+			hash = bpf_skb_get_hash(skb) & q.orphan_mask;
+			hash |= (1ULL << 32);
+		} else {
+			hash = sk->__sk_common.skc_hash;
+		}
+		*sflow = bpf_map_lookup_elem(&fq_nonprio_flows, &hash);
+	}
+
+	if (!*sflow)
+		ret = fq_new_flow(&fq_nonprio_flows, sflow, hash) < 0 ?
+		      CLS_RET_ERR : CLS_RET_NONPRIO;
+
+	return ret;
+}
+
+static bool fq_packet_beyond_horizon(struct sk_buff *skb)
+{
+	return (s64)skb->tstamp > (s64)(q.ktime_cache + q.horizon);
+}
+
+SEC("struct_ops/bpf_fq_enqueue")
+int BPF_PROG(bpf_fq_enqueue, struct sk_buff *skb, struct Qdisc *sch,
+	     struct bpf_sk_buff_ptr *to_free)
+{
+	struct fq_flow_node *flow = NULL, *flow_copy;
+	struct fq_stashed_flow *sflow;
+	u64 time_to_send, jiffies;
+	struct skb_node *skbn;
+	int ret;
+
+	if (sch->q.qlen >= sch->limit)
+		goto drop;
+
+	if (!skb->tstamp) {
+		time_to_send = q.ktime_cache = bpf_ktime_get_ns();
+	} else {
+		if (fq_packet_beyond_horizon(skb)) {
+			q.ktime_cache = bpf_ktime_get_ns();
+			if (fq_packet_beyond_horizon(skb)) {
+				if (q.horizon_drop)
+					goto drop;
+
+				skb->tstamp = q.ktime_cache + q.horizon;
+			}
+		}
+		time_to_send = skb->tstamp;
+	}
+
+	ret = fq_classify(skb, &sflow);
+	if (ret == CLS_RET_ERR)
+		goto drop;
+
+	flow = bpf_kptr_xchg(&sflow->flow, flow);
+	if (!flow)
+		goto drop;
+
+	if (ret == CLS_RET_NONPRIO) {
+		if (flow->qlen >= q.flow_plimit) {
+			bpf_kptr_xchg_back(&sflow->flow, flow);
+			goto drop;
+		}
+
+		if (fq_flow_is_detached(flow)) {
+			flow_copy = bpf_refcount_acquire(flow);
+
+			jiffies = bpf_jiffies64();
+			if ((s64)(jiffies - (flow_copy->age + q.flow_refill_delay)) > 0) {
+				if (flow_copy->credit < q.quantum)
+					flow_copy->credit = q.quantum;
+			}
+			flow_copy->age = 0;
+			fq_flows_add_tail(&fq_new_flows, &fq_new_flows_lock, flow_copy,
+					  &q.new_flow_cnt);
+		}
+	}
+
+	skbn = bpf_obj_new(typeof(*skbn));
+	if (!skbn) {
+		bpf_kptr_xchg_back(&sflow->flow, flow);
+		goto drop;
+	}
+
+	skbn->tstamp = skb->tstamp = time_to_send;
+
+	sch->qstats.backlog += qdisc_pkt_len(skb);
+
+	skb = bpf_kptr_xchg(&skbn->skb, skb);
+	if (skb)
+		bpf_qdisc_skb_drop(skb, to_free);
+
+	bpf_spin_lock(&flow->lock);
+	bpf_rbtree_add(&flow->queue, &skbn->node, skbn_tstamp_less);
+	bpf_spin_unlock(&flow->lock);
+
+	flow->qlen++;
+	bpf_kptr_xchg_back(&sflow->flow, flow);
+
+	sch->q.qlen++;
+	return NET_XMIT_SUCCESS;
+
+drop:
+	bpf_qdisc_skb_drop(skb, to_free);
+	sch->qstats.drops++;
+	return NET_XMIT_DROP;
+}
+
+static int fq_unset_throttled_flows(u32 index, struct unset_throttled_flows_ctx *ctx)
+{
+	struct bpf_rb_node *node = NULL;
+	struct fq_flow_node *flow;
+
+	bpf_spin_lock(&fq_delayed_lock);
+
+	node = bpf_rbtree_first(&fq_delayed);
+	if (!node) {
+		bpf_spin_unlock(&fq_delayed_lock);
+		return 1;
+	}
+
+	flow = container_of(node, struct fq_flow_node, rb_node);
+	if (!ctx->unset_all && flow->time_next_packet > ctx->now) {
+		q.time_next_delayed_flow = flow->time_next_packet;
+		bpf_spin_unlock(&fq_delayed_lock);
+		return 1;
+	}
+
+	node = bpf_rbtree_remove(&fq_delayed, &flow->rb_node);
+
+	bpf_spin_unlock(&fq_delayed_lock);
+
+	if (!node)
+		return 1;
+
+	flow = container_of(node, struct fq_flow_node, rb_node);
+	flow->age = 0;
+	fq_flows_add_tail(&fq_old_flows, &fq_old_flows_lock, flow, &q.old_flow_cnt);
+
+	return 0;
+}
+
+static void fq_flow_set_throttled(struct fq_flow_node *flow)
+{
+	flow->age = ~0ULL;
+
+	if (q.time_next_delayed_flow > flow->time_next_packet)
+		q.time_next_delayed_flow = flow->time_next_packet;
+
+	bpf_spin_lock(&fq_delayed_lock);
+	bpf_rbtree_add(&fq_delayed, &flow->rb_node, fn_time_next_packet_less);
+	bpf_spin_unlock(&fq_delayed_lock);
+}
+
+static void fq_check_throttled(u64 now)
+{
+	struct unset_throttled_flows_ctx ctx = {
+		.unset_all = false,
+		.now = now,
+	};
+	unsigned long sample;
+
+	if (q.time_next_delayed_flow > now)
+		return;
+
+	sample = (unsigned long)(now - q.time_next_delayed_flow);
+	q.unthrottle_latency_ns -= q.unthrottle_latency_ns >> 3;
+	q.unthrottle_latency_ns += sample >> 3;
+
+	q.time_next_delayed_flow = ~0ULL;
+	bpf_loop(NUM_QUEUE, fq_unset_throttled_flows, &ctx, 0);
+}
+
+static struct sk_buff*
+fq_dequeue_nonprio_flows(u32 index, struct dequeue_nonprio_ctx *ctx)
+{
+	u64 time_next_packet, time_to_send;
+	struct bpf_rb_node *rb_node;
+	struct sk_buff *skb = NULL;
+	struct bpf_list_head *head;
+	struct bpf_list_node *node;
+	struct bpf_spin_lock *lock;
+	struct fq_flow_node *flow;
+	struct skb_node *skbn;
+	bool is_empty;
+	u32 *cnt;
+
+	if (q.new_flow_cnt) {
+		head = &fq_new_flows;
+		lock = &fq_new_flows_lock;
+		cnt = &q.new_flow_cnt;
+	} else if (q.old_flow_cnt) {
+		head = &fq_old_flows;
+		lock = &fq_old_flows_lock;
+		cnt = &q.old_flow_cnt;
+	} else {
+		if (q.time_next_delayed_flow != ~0ULL)
+			ctx->expire = q.time_next_delayed_flow;
+		goto break_loop;
+	}
+
+	fq_flows_remove_front(head, lock, &node, cnt);
+	if (!node)
+		goto break_loop;
+
+	flow = container_of(node, struct fq_flow_node, list_node);
+	if (flow->credit <= 0) {
+		flow->credit += q.quantum;
+		fq_flows_add_tail(&fq_old_flows, &fq_old_flows_lock, flow, &q.old_flow_cnt);
+		return NULL;
+	}
+
+	bpf_spin_lock(&flow->lock);
+	rb_node = bpf_rbtree_first(&flow->queue);
+	if (!rb_node) {
+		bpf_spin_unlock(&flow->lock);
+		is_empty = fq_flows_is_empty(&fq_old_flows, &fq_old_flows_lock);
+		if (head == &fq_new_flows && !is_empty) {
+			fq_flows_add_tail(&fq_old_flows, &fq_old_flows_lock, flow, &q.old_flow_cnt);
+		} else {
+			fq_flow_set_detached(flow);
+			bpf_obj_drop(flow);
+		}
+		return NULL;
+	}
+
+	skbn = container_of(rb_node, struct skb_node, node);
+	time_to_send = skbn->tstamp;
+
+	time_next_packet = (time_to_send > flow->time_next_packet) ?
+		time_to_send : flow->time_next_packet;
+	if (ctx->now < time_next_packet) {
+		bpf_spin_unlock(&flow->lock);
+		flow->time_next_packet = time_next_packet;
+		fq_flow_set_throttled(flow);
+		return NULL;
+	}
+
+	rb_node = bpf_rbtree_remove(&flow->queue, rb_node);
+	bpf_spin_unlock(&flow->lock);
+
+	if (!rb_node)
+		goto add_flow_and_break;
+
+	skbn = container_of(rb_node, struct skb_node, node);
+	skb = bpf_kptr_xchg(&skbn->skb, skb);
+	bpf_obj_drop(skbn);
+
+	if (!skb)
+		goto add_flow_and_break;
+
+	flow->credit -= qdisc_skb_cb(skb)->pkt_len;
+	flow->qlen--;
+
+add_flow_and_break:
+	fq_flows_add_head(head, lock, flow, cnt);
+
+break_loop:
+	ctx->stop_iter = true;
+	return skb;
+}
+
+static struct sk_buff *fq_dequeue_prio(void)
+{
+	struct fq_flow_node *flow = NULL;
+	struct fq_stashed_flow *sflow;
+	struct bpf_rb_node *rb_node;
+	struct sk_buff *skb = NULL;
+	struct skb_node *skbn;
+	u64 hash = 0;
+
+	sflow = bpf_map_lookup_elem(&fq_prio_flows, &hash);
+	if (!sflow)
+		return NULL;
+
+	flow = bpf_kptr_xchg(&sflow->flow, flow);
+	if (!flow)
+		return NULL;
+
+	bpf_spin_lock(&flow->lock);
+	rb_node = bpf_rbtree_first(&flow->queue);
+	if (!rb_node) {
+		bpf_spin_unlock(&flow->lock);
+		goto out;
+	}
+
+	skbn = container_of(rb_node, struct skb_node, node);
+	rb_node = bpf_rbtree_remove(&flow->queue, &skbn->node);
+	bpf_spin_unlock(&flow->lock);
+
+	if (!rb_node)
+		goto out;
+
+	skbn = container_of(rb_node, struct skb_node, node);
+	skb = bpf_kptr_xchg(&skbn->skb, skb);
+	bpf_obj_drop(skbn);
+
+out:
+	bpf_kptr_xchg_back(&sflow->flow, flow);
+
+	return skb;
+}
+
+SEC("struct_ops/bpf_fq_dequeue")
+struct sk_buff *BPF_PROG(bpf_fq_dequeue, struct Qdisc *sch)
+{
+	struct dequeue_nonprio_ctx cb_ctx = {};
+	struct sk_buff *skb = NULL;
+	int i;
+
+	if (!sch->q.qlen)
+		goto out;
+
+	skb = fq_dequeue_prio();
+	if (skb)
+		goto dequeue;
+
+	q.ktime_cache = cb_ctx.now = bpf_ktime_get_ns();
+	fq_check_throttled(q.ktime_cache);
+	bpf_for(i, 0, sch->limit) {
+		skb = fq_dequeue_nonprio_flows(i, &cb_ctx);
+		if (cb_ctx.stop_iter)
+			break;
+	};
+
+	if (skb) {
+dequeue:
+		sch->q.qlen--;
+		sch->qstats.backlog -= qdisc_pkt_len(skb);
+		bpf_qdisc_bstats_update(sch, skb);
+		return skb;
+	}
+
+	if (cb_ctx.expire)
+		bpf_qdisc_watchdog_schedule(sch, cb_ctx.expire, q.timer_slack);
+out:
+	return NULL;
+}
+
+static int fq_remove_flows_in_list(u32 index, void *ctx)
+{
+	struct bpf_list_node *node;
+	struct fq_flow_node *flow;
+
+	bpf_spin_lock(&fq_new_flows_lock);
+	node = bpf_list_pop_front(&fq_new_flows);
+	bpf_spin_unlock(&fq_new_flows_lock);
+	if (!node) {
+		bpf_spin_lock(&fq_old_flows_lock);
+		node = bpf_list_pop_front(&fq_old_flows);
+		bpf_spin_unlock(&fq_old_flows_lock);
+		if (!node)
+			return 1;
+	}
+
+	flow = container_of(node, struct fq_flow_node, list_node);
+	bpf_obj_drop(flow);
+
+	return 0;
+}
+
+extern unsigned CONFIG_HZ __kconfig;
+
+/* limit number of collected flows per round */
+#define FQ_GC_MAX 8
+#define FQ_GC_AGE (3*CONFIG_HZ)
+
+static bool fq_gc_candidate(struct fq_flow_node *flow)
+{
+	u64 jiffies = bpf_jiffies64();
+
+	return fq_flow_is_detached(flow) &&
+	       ((s64)(jiffies - (flow->age + FQ_GC_AGE)) > 0);
+}
+
+static int
+fq_remove_flows(struct bpf_map *flow_map, u64 *hash,
+		struct fq_stashed_flow *sflow, struct remove_flows_ctx *ctx)
+{
+	if (sflow->flow &&
+	    (!ctx->gc_only || fq_gc_candidate(sflow->flow))) {
+		bpf_map_delete_elem(flow_map, hash);
+		ctx->reset_cnt++;
+	}
+
+	return ctx->reset_cnt < ctx->reset_max ? 0 : 1;
+}
+
+static void fq_gc(void)
+{
+	struct remove_flows_ctx cb_ctx = {
+		.gc_only = true,
+		.reset_cnt = 0,
+		.reset_max = FQ_GC_MAX,
+	};
+
+	bpf_for_each_map_elem(&fq_nonprio_flows, fq_remove_flows, &cb_ctx, 0);
+}
+
+SEC("struct_ops/bpf_fq_reset")
+void BPF_PROG(bpf_fq_reset, struct Qdisc *sch)
+{
+	struct unset_throttled_flows_ctx utf_ctx = {
+		.unset_all = true,
+	};
+	struct remove_flows_ctx rf_ctx = {
+		.gc_only = false,
+		.reset_cnt = 0,
+		.reset_max = NUM_QUEUE,
+	};
+	struct fq_stashed_flow *sflow;
+	u64 hash = 0;
+
+	sch->q.qlen = 0;
+	sch->qstats.backlog = 0;
+
+	bpf_for_each_map_elem(&fq_nonprio_flows, fq_remove_flows, &rf_ctx, 0);
+
+	rf_ctx.reset_cnt = 0;
+	bpf_for_each_map_elem(&fq_prio_flows, fq_remove_flows, &rf_ctx, 0);
+	fq_new_flow(&fq_prio_flows, &sflow, hash);
+
+	bpf_loop(NUM_QUEUE, fq_remove_flows_in_list, NULL, 0);
+	q.new_flow_cnt = 0;
+	q.old_flow_cnt = 0;
+
+	bpf_loop(NUM_QUEUE, fq_unset_throttled_flows, &utf_ctx, 0);
+}
+
+SEC("struct_ops/bpf_fq_init")
+int BPF_PROG(bpf_fq_init, struct Qdisc *sch, struct nlattr *opt,
+	     struct netlink_ext_ack *extack)
+{
+	struct net_device *dev = sch->dev_queue->dev;
+	u32 psched_mtu = dev->mtu + dev->hard_header_len;
+	struct fq_stashed_flow *sflow;
+	u64 hash = 0;
+
+	if (fq_new_flow(&fq_prio_flows, &sflow, hash) < 0)
+		return -ENOMEM;
+
+	sch->limit = 10000;
+	q.initial_quantum = 10 * psched_mtu;
+	q.quantum = 2 * psched_mtu;
+	q.flow_refill_delay = 40;
+	q.flow_plimit = 100;
+	q.horizon = 10ULL * NSEC_PER_SEC;
+	q.horizon_drop = 1;
+	q.orphan_mask = 1024 - 1;
+	q.timer_slack = 10 * NSEC_PER_USEC;
+	q.time_next_delayed_flow = ~0ULL;
+	q.unthrottle_latency_ns = 0ULL;
+	q.new_flow_cnt = 0;
+	q.old_flow_cnt = 0;
+
+	return 0;
+}
+
+SEC("struct_ops")
+void BPF_PROG(bpf_fq_destroy, struct Qdisc *sch)
+{
+}
+
+SEC(".struct_ops")
+struct Qdisc_ops fq = {
+	.enqueue   = (void *)bpf_fq_enqueue,
+	.dequeue   = (void *)bpf_fq_dequeue,
+	.reset     = (void *)bpf_fq_reset,
+	.init      = (void *)bpf_fq_init,
+	.destroy   = (void *)bpf_fq_destroy,
+	.id        = "bpf_fq",
+};
diff --git a/tools/testing/selftests/bpf/progs/bpf_smc.c b/tools/testing/selftests/bpf/progs/bpf_smc.c
new file mode 100644
index 000000000000..70d8b08f5914
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_smc.c
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_tracing_net.h"
+
+char _license[] SEC("license") = "GPL";
+
+enum {
+	BPF_SMC_LISTEN	= 10,
+};
+
+struct smc_sock___local {
+	struct sock sk;
+	struct smc_sock *listen_smc;
+	bool use_fallback;
+} __attribute__((preserve_access_index));
+
+int smc_cnt = 0;
+int fallback_cnt = 0;
+
+SEC("fentry/smc_release")
+int BPF_PROG(bpf_smc_release, struct socket *sock)
+{
+	/* only count from one side (client) */
+	if (sock->sk->__sk_common.skc_state == BPF_SMC_LISTEN)
+		return 0;
+	smc_cnt++;
+	return 0;
+}
+
+SEC("fentry/smc_switch_to_fallback")
+int BPF_PROG(bpf_smc_switch_to_fallback, struct smc_sock___local *smc)
+{
+	/* only count from one side (client) */
+	if (smc && !smc->listen_smc)
+		fallback_cnt++;
+	return 0;
+}
+
+/* go with default value if no strat was found */
+bool default_ip_strat_value = true;
+
+struct smc_policy_ip_key {
+	__u32	sip;
+	__u32	dip;
+};
+
+struct smc_policy_ip_value {
+	__u8	mode;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(struct smc_policy_ip_key));
+	__uint(value_size, sizeof(struct smc_policy_ip_value));
+	__uint(max_entries, 128);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+} smc_policy_ip SEC(".maps");
+
+static bool smc_check(__u32 src, __u32 dst)
+{
+	struct smc_policy_ip_value *value;
+	struct smc_policy_ip_key key = {
+		.sip = src,
+		.dip = dst,
+	};
+
+	value = bpf_map_lookup_elem(&smc_policy_ip, &key);
+	return value ? value->mode : default_ip_strat_value;
+}
+
+SEC("fmod_ret/update_socket_protocol")
+int BPF_PROG(smc_run, int family, int type, int protocol)
+{
+	struct task_struct *task;
+
+	if (family != AF_INET && family != AF_INET6)
+		return protocol;
+
+	if ((type & 0xf) != SOCK_STREAM)
+		return protocol;
+
+	if (protocol != 0 && protocol != IPPROTO_TCP)
+		return protocol;
+
+	task = bpf_get_current_task_btf();
+	/* Prevent from affecting other tests */
+	if (!task || !task->nsproxy->net_ns->smc.hs_ctrl)
+		return protocol;
+
+	return IPPROTO_SMC;
+}
+
+SEC("struct_ops")
+int BPF_PROG(bpf_smc_set_tcp_option_cond, const struct tcp_sock *tp,
+	     struct inet_request_sock *ireq)
+{
+	return smc_check(ireq->req.__req_common.skc_daddr,
+			 ireq->req.__req_common.skc_rcv_saddr);
+}
+
+SEC("struct_ops")
+int BPF_PROG(bpf_smc_set_tcp_option, struct tcp_sock *tp)
+{
+	return smc_check(tp->inet_conn.icsk_inet.sk.__sk_common.skc_rcv_saddr,
+			 tp->inet_conn.icsk_inet.sk.__sk_common.skc_daddr);
+}
+
+SEC(".struct_ops")
+struct smc_hs_ctrl  linkcheck = {
+	.name		= "linkcheck",
+	.syn_option	= (void *)bpf_smc_set_tcp_option,
+	.synack_option	= (void *)bpf_smc_set_tcp_option_cond,
+};
diff --git a/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c b/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c
index e1e11897e99b..9e7d9674ce2a 100644
--- a/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c
+++ b/tools/testing/selftests/bpf/progs/bpf_syscall_macro.c
@@ -43,9 +43,7 @@ int BPF_KPROBE(handle_sys_prctl)
 
 	/* test for PT_REGS_PARM */
 
-#if !defined(bpf_target_arm64) && !defined(bpf_target_s390)
 	bpf_probe_read_kernel(&tmp, sizeof(tmp), &PT_REGS_PARM1_SYSCALL(real_regs));
-#endif
 	arg1 = tmp;
 	bpf_probe_read_kernel(&arg2, sizeof(arg2), &PT_REGS_PARM2_SYSCALL(real_regs));
 	bpf_probe_read_kernel(&arg3, sizeof(arg3), &PT_REGS_PARM3_SYSCALL(real_regs));
@@ -81,4 +79,30 @@ int BPF_KSYSCALL(prctl_enter, int option, unsigned long arg2,
 	return 0;
 }
 
+__u64 splice_fd_in;
+__u64 splice_off_in;
+__u64 splice_fd_out;
+__u64 splice_off_out;
+__u64 splice_len;
+__u64 splice_flags;
+
+SEC("ksyscall/splice")
+int BPF_KSYSCALL(splice_enter, int fd_in, loff_t *off_in, int fd_out,
+		 loff_t *off_out, size_t len, unsigned int flags)
+{
+	pid_t pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid != filter_pid)
+		return 0;
+
+	splice_fd_in = fd_in;
+	splice_off_in = (__u64)off_in;
+	splice_fd_out = fd_out;
+	splice_off_out = (__u64)off_out;
+	splice_len = len;
+	splice_flags = flags;
+
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c b/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c
index 2ecd833dcd41..8a7a4c1b54e8 100644
--- a/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c
+++ b/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c
@@ -1,14 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <linux/bpf.h>
-#include <linux/types.h>
-#include <bpf/bpf_helpers.h>
+#include "bpf_tracing_net.h"
 #include <bpf/bpf_tracing.h>
-#include "bpf_tcp_helpers.h"
 
 char _license[] SEC("license") = "X";
 
-void BPF_STRUCT_OPS(nogpltcp_init, struct sock *sk)
+SEC("struct_ops")
+void BPF_PROG(nogpltcp_init, struct sock *sk)
 {
 }
 
diff --git a/tools/testing/selftests/bpf/progs/bpf_test_utils.h b/tools/testing/selftests/bpf/progs/bpf_test_utils.h
new file mode 100644
index 000000000000..f4e67b492dd2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_test_utils.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BPF_TEST_UTILS_H__
+#define __BPF_TEST_UTILS_H__
+
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+/* Clobber as many native registers and stack slots as possible. */
+static __always_inline void clobber_regs_stack(void)
+{
+	char tmp_str[] = "123456789";
+	unsigned long tmp;
+
+	bpf_strtoul(tmp_str, sizeof(tmp_str), 0, &tmp);
+	__sink(tmp);
+}
+
+#endif
diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
index b394817126cf..d8dacef37c16 100644
--- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
+++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
@@ -2,6 +2,9 @@
 #ifndef __BPF_TRACING_NET_H__
 #define __BPF_TRACING_NET_H__
 
+#include <vmlinux.h>
+#include <bpf/bpf_core_read.h>
+
 #define AF_INET			2
 #define AF_INET6		10
 
@@ -12,7 +15,11 @@
 #define SO_KEEPALIVE		9
 #define SO_PRIORITY		12
 #define SO_REUSEPORT		15
+#if defined(__TARGET_ARCH_powerpc)
+#define SO_RCVLOWAT		16
+#else
 #define SO_RCVLOWAT		18
+#endif
 #define SO_BINDTODEVICE		25
 #define SO_MARK			36
 #define SO_MAX_PACING_RATE	47
@@ -22,10 +29,12 @@
 
 #define IP_TOS			1
 
+#define SOL_IPV6		41
 #define IPV6_TCLASS		67
 #define IPV6_AUTOFLOWLABEL	70
 
 #define TC_ACT_UNSPEC		(-1)
+#define TC_ACT_OK		0
 #define TC_ACT_SHOT		2
 
 #define SOL_TCP			6
@@ -44,12 +53,42 @@
 #define TCP_SAVED_SYN		28
 #define TCP_CA_NAME_MAX		16
 #define TCP_NAGLE_OFF		1
+#define TCP_RTO_MAX_MS		44
+
+#define TCP_ECN_OK              1
+#define TCP_ECN_QUEUE_CWR       2
+#define TCP_ECN_DEMAND_CWR      4
+#define TCP_ECN_SEEN            8
+
+#define TCP_CONG_NEEDS_ECN     0x2
 
 #define ICSK_TIME_RETRANS	1
 #define ICSK_TIME_PROBE0	3
 #define ICSK_TIME_LOSS_PROBE	5
 #define ICSK_TIME_REO_TIMEOUT	6
 
+#define ETH_ALEN		6
+#define ETH_HLEN		14
+#define ETH_P_IP		0x0800
+#define ETH_P_IPV6		0x86DD
+
+#define NEXTHDR_TCP		6
+
+#define TCPOPT_NOP		1
+#define TCPOPT_EOL		0
+#define TCPOPT_MSS		2
+#define TCPOPT_WINDOW		3
+#define TCPOPT_TIMESTAMP	8
+#define TCPOPT_SACK_PERM	4
+
+#define TCPOLEN_MSS		4
+#define TCPOLEN_WINDOW		3
+#define TCPOLEN_TIMESTAMP	10
+#define TCPOLEN_SACK_PERM	2
+
+#define CHECKSUM_NONE		0
+#define CHECKSUM_PARTIAL	3
+
 #define IFNAMSIZ		16
 
 #define RTF_GATEWAY		0x0002
@@ -57,6 +96,14 @@
 #define TCP_INFINITE_SSTHRESH	0x7fffffff
 #define TCP_PINGPONG_THRESH	3
 
+#define FLAG_DATA_ACKED 0x04 /* This ACK acknowledged new data.		*/
+#define FLAG_SYN_ACKED 0x10 /* This ACK acknowledged SYN.		*/
+#define FLAG_DATA_SACKED 0x20 /* New SACK.				*/
+#define FLAG_SND_UNA_ADVANCED \
+	0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */
+#define FLAG_ACKED (FLAG_DATA_ACKED | FLAG_SYN_ACKED)
+#define FLAG_FORWARD_PROGRESS (FLAG_ACKED | FLAG_DATA_SACKED)
+
 #define fib_nh_dev		nh_common.nhc_dev
 #define fib_nh_gw_family	nh_common.nhc_gw_family
 #define fib_nh_gw6		nh_common.nhc_gw.ipv6
@@ -65,6 +112,8 @@
 #define inet_rcv_saddr		sk.__sk_common.skc_rcv_saddr
 #define inet_dport		sk.__sk_common.skc_dport
 
+#define udp_portaddr_hash	inet.sk.__sk_common.skc_u16hashes[1]
+
 #define ir_loc_addr		req.__req_common.skc_rcv_saddr
 #define ir_num			req.__req_common.skc_num
 #define ir_rmt_addr		req.__req_common.skc_daddr
@@ -78,10 +127,13 @@
 #define sk_rmem_alloc		sk_backlog.rmem_alloc
 #define sk_refcnt		__sk_common.skc_refcnt
 #define sk_state		__sk_common.skc_state
+#define sk_net			__sk_common.skc_net
+#define sk_rcv_saddr		__sk_common.skc_rcv_saddr
 #define sk_v6_daddr		__sk_common.skc_v6_daddr
 #define sk_v6_rcv_saddr		__sk_common.skc_v6_rcv_saddr
 #define sk_flags		__sk_common.skc_flags
 #define sk_reuse		__sk_common.skc_reuse
+#define sk_cookie		__sk_common.skc_cookie
 
 #define s6_addr32		in6_u.u6_addr32
 
@@ -92,4 +144,51 @@
 #define tw_v6_daddr		__tw_common.skc_v6_daddr
 #define tw_v6_rcv_saddr		__tw_common.skc_v6_rcv_saddr
 
+#define tcp_jiffies32 ((__u32)bpf_jiffies64())
+
+#ifndef min
+#define min(a, b) ((a) < (b) ? (a) : (b))
+#endif
+#ifndef max
+#define max(a, b) ((a) > (b) ? (a) : (b))
+#endif
+
+static inline bool before(__u32 seq1, __u32 seq2)
+{
+	return (__s32)(seq1 - seq2) < 0;
+}
+
+#define after(seq2, seq1) before(seq1, seq2)
+
+static inline struct inet_connection_sock *inet_csk(const struct sock *sk)
+{
+	return (struct inet_connection_sock *)sk;
+}
+
+static inline void *inet_csk_ca(const struct sock *sk)
+{
+	return (void *)inet_csk(sk)->icsk_ca_priv;
+}
+
+static inline struct tcp_sock *tcp_sk(const struct sock *sk)
+{
+	return (struct tcp_sock *)sk;
+}
+
+static inline bool tcp_in_slow_start(const struct tcp_sock *tp)
+{
+	return tp->snd_cwnd < tp->snd_ssthresh;
+}
+
+static inline bool tcp_is_cwnd_limited(const struct sock *sk)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+
+	/* If in slow start, ensure cwnd grows to twice what was ACKed. */
+	if (tcp_in_slow_start(tp))
+		return tp->snd_cwnd < 2 * tp->max_packets_out;
+
+	return !!BPF_CORE_READ_BITFIELD(tp, is_cwnd_limited);
+}
+
 #endif
diff --git a/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_signed_arr_elem_sz.c b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_signed_arr_elem_sz.c
new file mode 100644
index 000000000000..21a560427b10
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/btf__core_reloc_arrays___err_bad_signed_arr_elem_sz.c
@@ -0,0 +1,3 @@
+#include "core_reloc_types.h"
+
+void f(struct core_reloc_arrays___err_bad_signed_arr_elem_sz x) {}
diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c
index e5560a656030..e01690618e1e 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c
@@ -53,7 +53,7 @@ struct bitfields_only_mixed_types {
  */
 /* ------ END-EXPECTED-OUTPUT ------ */
 struct bitfield_mixed_with_others {
-	long: 4; /* char is enough as a backing field */
+	char: 4; /* char is enough as a backing field */
 	int a: 4;
 	/* 8-bit implicit padding */
 	short b; /* combined with previous bitfield */
diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c
index ba97165bdb28..a657651eba52 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c
@@ -14,9 +14,9 @@ typedef int *ptr_arr_t[6];
 
 typedef int *ptr_multiarr_t[7][8][9][10];
 
-typedef int * (*fn_ptr_arr_t[11])();
+typedef int * (*fn_ptr_arr_t[11])(void);
 
-typedef int * (*fn_ptr_multiarr_t[12][13])();
+typedef int * (*fn_ptr_multiarr_t[12][13])(void);
 
 struct root_struct {
 	arr_t _1;
diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c
index e304b6204bd9..7998f27df7dd 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c
@@ -58,7 +58,81 @@ union jump_code_union {
 	} __attribute__((packed));
 };
 
-/*------ END-EXPECTED-OUTPUT ------ */
+/* ----- START-EXPECTED-OUTPUT ----- */
+/*
+ *struct nested_packed_but_aligned_struct {
+ *	int x1;
+ *	int x2;
+ *};
+ *
+ *struct outer_implicitly_packed_struct {
+ *	char y1;
+ *	struct nested_packed_but_aligned_struct y2;
+ *} __attribute__((packed));
+ *
+ */
+/* ------ END-EXPECTED-OUTPUT ------ */
+
+struct nested_packed_but_aligned_struct {
+	int x1;
+	int x2;
+} __attribute__((packed));
+
+struct outer_implicitly_packed_struct {
+	char y1;
+	struct nested_packed_but_aligned_struct y2;
+};
+/* ----- START-EXPECTED-OUTPUT ----- */
+/*
+ *struct usb_ss_ep_comp_descriptor {
+ *	char: 8;
+ *	char bDescriptorType;
+ *	char bMaxBurst;
+ *	short wBytesPerInterval;
+ *};
+ *
+ *struct usb_host_endpoint {
+ *	long: 64;
+ *	char: 8;
+ *	struct usb_ss_ep_comp_descriptor ss_ep_comp;
+ *	long: 0;
+ *} __attribute__((packed));
+ *
+ */
+/* ------ END-EXPECTED-OUTPUT ------ */
+
+struct usb_ss_ep_comp_descriptor {
+	char: 8;
+	char bDescriptorType;
+	char bMaxBurst;
+	int: 0;
+	short wBytesPerInterval;
+} __attribute__((packed));
+
+struct usb_host_endpoint {
+	long: 64;
+	char: 8;
+	struct usb_ss_ep_comp_descriptor ss_ep_comp;
+	long: 0;
+};
+
+/* ----- START-EXPECTED-OUTPUT ----- */
+struct nested_packed_struct {
+	int a;
+	char b;
+} __attribute__((packed));
+
+struct outer_nonpacked_struct {
+	short a;
+	struct nested_packed_struct b;
+};
+
+struct outer_packed_struct {
+	short a;
+	struct nested_packed_struct b;
+} __attribute__((packed));
+
+/* ------ END-EXPECTED-OUTPUT ------ */
 
 int f(struct {
 	struct packed_trailing_space _1;
@@ -69,6 +143,10 @@ int f(struct {
 	union union_is_never_packed _6;
 	union union_does_not_need_packing _7;
 	union jump_code_union _8;
+	struct outer_implicitly_packed_struct _9;
+	struct usb_host_endpoint _10;
+	struct outer_nonpacked_struct _11;
+	struct outer_packed_struct _12;
 } *_)
 {
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c
index 7cb522d22a66..79276fbe454a 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c
@@ -19,7 +19,7 @@ struct padded_implicitly {
 /*
  *struct padded_explicitly {
  *	int a;
- *	int: 32;
+ *	long: 0;
  *	int b;
  *};
  *
@@ -28,41 +28,28 @@ struct padded_implicitly {
 
 struct padded_explicitly {
 	int a;
-	int: 1; /* algo will explicitly pad with full 32 bits here */
+	int: 1; /* algo will emit aligning `long: 0;` here */
 	int b;
 };
 
 /* ----- START-EXPECTED-OUTPUT ----- */
-/*
- *struct padded_a_lot {
- *	int a;
- *	long: 32;
- *	long: 64;
- *	long: 64;
- *	int b;
- *};
- *
- */
-/* ------ END-EXPECTED-OUTPUT ------ */
-
 struct padded_a_lot {
 	int a;
-	/* 32 bit of implicit padding here, which algo will make explicit */
 	long: 64;
 	long: 64;
 	int b;
 };
 
+/* ------ END-EXPECTED-OUTPUT ------ */
+
 /* ----- START-EXPECTED-OUTPUT ----- */
 /*
  *struct padded_cache_line {
  *	int a;
- *	long: 32;
  *	long: 64;
  *	long: 64;
  *	long: 64;
  *	int b;
- *	long: 32;
  *	long: 64;
  *	long: 64;
  *	long: 64;
@@ -85,7 +72,7 @@ struct padded_cache_line {
  *struct zone {
  *	int a;
  *	short b;
- *	short: 16;
+ *	long: 0;
  *	struct zone_padding __pad__;
  *};
  *
@@ -108,6 +95,131 @@ struct padding_wo_named_members {
 	long: 64;
 };
 
+struct padding_weird_1 {
+	int a;
+	long: 64;
+	short: 16;
+	short b;
+};
+
+/* ------ END-EXPECTED-OUTPUT ------ */
+
+/* ----- START-EXPECTED-OUTPUT ----- */
+/*
+ *struct padding_weird_2 {
+ *	long: 56;
+ *	char a;
+ *	long: 56;
+ *	char b;
+ *	char: 8;
+ *};
+ *
+ */
+/* ------ END-EXPECTED-OUTPUT ------ */
+struct padding_weird_2 {
+	int: 32;	/* these paddings will be collapsed into `long: 56;` */
+	short: 16;
+	char: 8;
+	char a;
+	int: 32;	/* these paddings will be collapsed into `long: 56;` */
+	short: 16;
+	char: 8;
+	char b;
+	char: 8;
+};
+
+/* ----- START-EXPECTED-OUTPUT ----- */
+struct exact_1byte {
+	char x;
+};
+
+struct padded_1byte {
+	char: 8;
+};
+
+struct exact_2bytes {
+	short x;
+};
+
+struct padded_2bytes {
+	short: 16;
+};
+
+struct exact_4bytes {
+	int x;
+};
+
+struct padded_4bytes {
+	int: 32;
+};
+
+struct exact_8bytes {
+	long x;
+};
+
+struct padded_8bytes {
+	long: 64;
+};
+
+struct ff_periodic_effect {
+	int: 32;
+	short magnitude;
+	long: 0;
+	short phase;
+	long: 0;
+	int: 32;
+	int custom_len;
+	short *custom_data;
+};
+
+struct ib_wc {
+	long: 64;
+	long: 64;
+	int: 32;
+	int byte_len;
+	void *qp;
+	union {} ex;
+	long: 64;
+	int slid;
+	int wc_flags;
+	long: 64;
+	char smac[6];
+	long: 0;
+	char network_hdr_type;
+};
+
+struct acpi_object_method {
+	long: 64;
+	char: 8;
+	char type;
+	short reference_count;
+	char flags;
+	short: 0;
+	char: 8;
+	char sync_level;
+	long: 64;
+	void *node;
+	void *aml_start;
+	union {} dispatch;
+	long: 64;
+	int aml_length;
+};
+
+struct nested_unpacked {
+	int x;
+};
+
+struct nested_packed {
+	struct nested_unpacked a;
+	char c;
+} __attribute__((packed));
+
+struct outer_mixed_but_unpacked {
+	struct nested_packed b1;
+	short a1;
+	struct nested_packed b2;
+};
+
 /* ------ END-EXPECTED-OUTPUT ------ */
 
 int f(struct {
@@ -117,6 +229,20 @@ int f(struct {
 	struct padded_cache_line _4;
 	struct zone _5;
 	struct padding_wo_named_members _6;
+	struct padding_weird_1 _7;
+	struct padding_weird_2 _8;
+	struct exact_1byte _100;
+	struct padded_1byte _101;
+	struct exact_2bytes _102;
+	struct padded_2bytes _103;
+	struct exact_4bytes _104;
+	struct padded_4bytes _105;
+	struct exact_8bytes _106;
+	struct padded_8bytes _107;
+	struct ff_periodic_effect _200;
+	struct ib_wc _201;
+	struct acpi_object_method _202;
+	struct outer_mixed_but_unpacked _203;
 } *_)
 {
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
index 4ee4748133fe..29d01fff32bd 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
@@ -25,6 +25,39 @@ typedef enum {
 	H = 2,
 } e3_t;
 
+/* ----- START-EXPECTED-OUTPUT ----- */
+/*
+ *enum e_byte {
+ *	EBYTE_1 = 0,
+ *	EBYTE_2 = 1,
+ *} __attribute__((mode(byte)));
+ *
+ */
+/* ----- END-EXPECTED-OUTPUT ----- */
+enum e_byte {
+	EBYTE_1,
+	EBYTE_2,
+} __attribute__((mode(byte)));
+
+/* ----- START-EXPECTED-OUTPUT ----- */
+/*
+ *enum e_word {
+ *	EWORD_1 = 0LL,
+ *	EWORD_2 = 1LL,
+ *} __attribute__((mode(word)));
+ *
+ */
+/* ----- END-EXPECTED-OUTPUT ----- */
+enum e_word {
+	EWORD_1,
+	EWORD_2,
+} __attribute__((mode(word))); /* force to use 8-byte backing for this enum */
+
+/* ----- START-EXPECTED-OUTPUT ----- */
+enum e_big {
+	EBIG_1 = 1000000000000ULL,
+};
+
 typedef int int_t;
 
 typedef volatile const int * volatile const crazy_ptr_t;
@@ -51,7 +84,7 @@ typedef void (*printf_fn_t)(const char *, ...);
  *	typedef int (*fn_t)(int);
  *	typedef char * const * (*fn_ptr2_t)(s_t, fn_t);
  *
- * - `fn_complext_t`: pointer to a function returning struct and accepting
+ * - `fn_complex_t`: pointer to a function returning struct and accepting
  *   union and struct. All structs and enum are anonymous and defined inline.
  *
  * - `signal_t: pointer to a function accepting a pointer to a function as an
@@ -67,7 +100,7 @@ typedef void (*printf_fn_t)(const char *, ...);
  *   `int -> char *` function and returns pointer to a char. Equivalent:
  *   typedef char * (*fn_input_t)(int);
  *   typedef char * (*fn_output_outer_t)(fn_input_t);
- *   typedef const fn_output_outer_t (* fn_output_inner_t)();
+ *   typedef const fn_output_outer_t (* fn_output_inner_t)(void);
  *   typedef const fn_output_inner_t fn_ptr_arr2_t[5];
  */
 /* ----- START-EXPECTED-OUTPUT ----- */
@@ -94,7 +127,7 @@ typedef void (* (*signal_t)(int, void (*)(int)))(int);
 
 typedef char * (*fn_ptr_arr1_t[10])(int **);
 
-typedef char * (* (* const fn_ptr_arr2_t[5])())(char * (*)(int));
+typedef char * (* (* const fn_ptr_arr2_t[5])(void))(char * (*)(int));
 
 struct struct_w_typedefs {
 	int_t a;
@@ -224,6 +257,9 @@ struct root_struct {
 	enum e2 _2;
 	e2_t _2_1;
 	e3_t _2_2;
+	enum e_byte _100;
+	enum e_word _101;
+	enum e_big _102;
 	struct struct_w_typedefs _3;
 	anon_struct_t _7;
 	struct struct_fwd *_8;
diff --git a/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c b/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c
index 38f78d9345de..d93f68024cc6 100644
--- a/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c
+++ b/tools/testing/selftests/bpf/progs/btf_type_tag_percpu.c
@@ -30,36 +30,42 @@ int BPF_PROG(test_percpu2, struct bpf_testmod_btf_type_tag_2 *arg)
 
 /* trace_cgroup_mkdir(struct cgroup *cgrp, const char *path)
  *
- * struct cgroup_rstat_cpu {
+ * struct css_rstat_cpu {
  *   ...
- *   struct cgroup *updated_children;
+ *   struct cgroup_subsys_state *updated_children;
  *   ...
  * };
  *
- * struct cgroup {
+ * struct cgroup_subsys_state {
+ *   ...
+ *   struct css_rstat_cpu __percpu *rstat_cpu;
  *   ...
- *   struct cgroup_rstat_cpu __percpu *rstat_cpu;
+ * };
+ *
+ * struct cgroup {
+ *   struct cgroup_subsys_state self;
  *   ...
  * };
  */
 SEC("tp_btf/cgroup_mkdir")
 int BPF_PROG(test_percpu_load, struct cgroup *cgrp, const char *path)
 {
-	g = (__u64)cgrp->rstat_cpu->updated_children;
+	g = (__u64)cgrp->self.rstat_cpu->updated_children;
 	return 0;
 }
 
 SEC("tp_btf/cgroup_mkdir")
 int BPF_PROG(test_percpu_helper, struct cgroup *cgrp, const char *path)
 {
-	struct cgroup_rstat_cpu *rstat;
+	struct css_rstat_cpu *rstat;
 	__u32 cpu;
 
 	cpu = bpf_get_smp_processor_id();
-	rstat = (struct cgroup_rstat_cpu *)bpf_per_cpu_ptr(cgrp->rstat_cpu, cpu);
+	rstat = (struct css_rstat_cpu *)bpf_per_cpu_ptr(
+			cgrp->self.rstat_cpu, cpu);
 	if (rstat) {
 		/* READ_ONCE */
-		*(volatile int *)rstat;
+		*(volatile long *)rstat;
 	}
 
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/cb_refs.c b/tools/testing/selftests/bpf/progs/cb_refs.c
index 7653df1bc787..5d6fc7f01ebb 100644
--- a/tools/testing/selftests/bpf/progs/cb_refs.c
+++ b/tools/testing/selftests/bpf/progs/cb_refs.c
@@ -2,9 +2,10 @@
 #include <vmlinux.h>
 #include <bpf/bpf_tracing.h>
 #include <bpf/bpf_helpers.h>
+#include "../test_kmods/bpf_testmod_kfunc.h"
 
 struct map_value {
-	struct prog_test_ref_kfunc __kptr_ref *ptr;
+	struct prog_test_ref_kfunc __kptr *ptr;
 };
 
 struct {
@@ -14,9 +15,6 @@ struct {
 	__uint(max_entries, 16);
 } array_map SEC(".maps");
 
-extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym;
-extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym;
-
 static __noinline int cb1(void *map, void *key, void *value, void *ctx)
 {
 	void *p = *(void **)ctx;
@@ -35,6 +33,7 @@ int underflow_prog(void *ctx)
 	if (!p)
 		return 0;
 	bpf_for_each_map_elem(&array_map, cb1, &p, 0);
+	bpf_kfunc_call_test_release(p);
 	return 0;
 }
 
@@ -52,7 +51,6 @@ int leak_prog(void *ctx)
 {
 	struct prog_test_ref_kfunc *p;
 	struct map_value *v;
-	unsigned long sl;
 
 	v = bpf_map_lookup_elem(&array_map, &(int){0});
 	if (!v)
diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi.h b/tools/testing/selftests/bpf/progs/cg_storage_multi.h
index a0778fe7857a..41d59f0ee606 100644
--- a/tools/testing/selftests/bpf/progs/cg_storage_multi.h
+++ b/tools/testing/selftests/bpf/progs/cg_storage_multi.h
@@ -3,8 +3,6 @@
 #ifndef __PROGS_CG_STORAGE_MULTI_H
 #define __PROGS_CG_STORAGE_MULTI_H
 
-#include <asm/types.h>
-
 struct cgroup_value {
 	__u32 egress_pkts;
 	__u32 ingress_pkts;
diff --git a/tools/testing/selftests/bpf/progs/cgroup_ancestor.c b/tools/testing/selftests/bpf/progs/cgroup_ancestor.c
new file mode 100644
index 000000000000..8c2deb4fc493
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cgroup_ancestor.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_tracing_net.h"
+#define NUM_CGROUP_LEVELS	4
+
+__u64 cgroup_ids[NUM_CGROUP_LEVELS];
+__u16 dport;
+
+static __always_inline void log_nth_level(struct __sk_buff *skb, __u32 level)
+{
+	/* [1] &level passed to external function that may change it, it's
+	 *     incompatible with loop unroll.
+	 */
+	cgroup_ids[level] = bpf_skb_ancestor_cgroup_id(skb, level);
+}
+
+SEC("tc")
+int log_cgroup_id(struct __sk_buff *skb)
+{
+	struct sock *sk = (void *)skb->sk;
+
+	if (!sk)
+		return TC_ACT_OK;
+
+	sk = bpf_core_cast(sk, struct sock);
+	if (sk->sk_protocol == IPPROTO_UDP && sk->sk_dport == dport) {
+		log_nth_level(skb, 0);
+		log_nth_level(skb, 1);
+		log_nth_level(skb, 2);
+		log_nth_level(skb, 3);
+	}
+
+	return TC_ACT_OK;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c
index b2a409e6382a..932b8ecd4ae3 100644
--- a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c
+++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_getsockopt.c
@@ -12,6 +12,7 @@ __u32 invocations = 0;
 __u32 assertion_error = 0;
 __u32 retval_value = 0;
 __u32 ctx_retval_value = 0;
+__u32 page_size = 0;
 
 SEC("cgroup/getsockopt")
 int get_retval(struct bpf_sockopt *ctx)
@@ -20,6 +21,10 @@ int get_retval(struct bpf_sockopt *ctx)
 	ctx_retval_value = ctx->retval;
 	__sync_fetch_and_add(&invocations, 1);
 
+	/* optval larger than PAGE_SIZE use kernel's buffer. */
+	if (ctx->optlen > page_size)
+		ctx->optlen = 0;
+
 	return 1;
 }
 
@@ -31,6 +36,10 @@ int set_eisconn(struct bpf_sockopt *ctx)
 	if (bpf_set_retval(-EISCONN))
 		assertion_error = 1;
 
+	/* optval larger than PAGE_SIZE use kernel's buffer. */
+	if (ctx->optlen > page_size)
+		ctx->optlen = 0;
+
 	return 1;
 }
 
@@ -41,5 +50,9 @@ int clear_retval(struct bpf_sockopt *ctx)
 
 	ctx->retval = 0;
 
+	/* optval larger than PAGE_SIZE use kernel's buffer. */
+	if (ctx->optlen > page_size)
+		ctx->optlen = 0;
+
 	return 1;
 }
diff --git a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c
index d6e5903e06ba..45a0e9f492a9 100644
--- a/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c
+++ b/tools/testing/selftests/bpf/progs/cgroup_getset_retval_setsockopt.c
@@ -11,6 +11,7 @@
 __u32 invocations = 0;
 __u32 assertion_error = 0;
 __u32 retval_value = 0;
+__s32 page_size = 0;
 
 SEC("cgroup/setsockopt")
 int get_retval(struct bpf_sockopt *ctx)
@@ -18,6 +19,10 @@ int get_retval(struct bpf_sockopt *ctx)
 	retval_value = bpf_get_retval();
 	__sync_fetch_and_add(&invocations, 1);
 
+	/* optval larger than PAGE_SIZE use kernel's buffer. */
+	if (ctx->optlen > page_size)
+		ctx->optlen = 0;
+
 	return 1;
 }
 
@@ -29,6 +34,10 @@ int set_eunatch(struct bpf_sockopt *ctx)
 	if (bpf_set_retval(-EUNATCH))
 		assertion_error = 1;
 
+	/* optval larger than PAGE_SIZE use kernel's buffer. */
+	if (ctx->optlen > page_size)
+		ctx->optlen = 0;
+
 	return 0;
 }
 
@@ -40,6 +49,10 @@ int set_eisconn(struct bpf_sockopt *ctx)
 	if (bpf_set_retval(-EISCONN))
 		assertion_error = 1;
 
+	/* optval larger than PAGE_SIZE use kernel's buffer. */
+	if (ctx->optlen > page_size)
+		ctx->optlen = 0;
+
 	return 0;
 }
 
@@ -48,5 +61,9 @@ int legacy_eperm(struct bpf_sockopt *ctx)
 {
 	__sync_fetch_and_add(&invocations, 1);
 
+	/* optval larger than PAGE_SIZE use kernel's buffer. */
+	if (ctx->optlen > page_size)
+		ctx->optlen = 0;
+
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c b/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c
index c74362854948..ff189a736ad8 100644
--- a/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c
+++ b/tools/testing/selftests/bpf/progs/cgroup_hierarchical_stats.c
@@ -37,8 +37,9 @@ struct {
 	__type(value, struct attach_counter);
 } attach_counters SEC(".maps");
 
-extern void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) __ksym;
-extern void cgroup_rstat_flush(struct cgroup *cgrp) __ksym;
+extern void css_rstat_updated(
+		struct cgroup_subsys_state *css, int cpu) __ksym;
+extern void css_rstat_flush(struct cgroup_subsys_state *css) __ksym;
 
 static uint64_t cgroup_id(struct cgroup *cgrp)
 {
@@ -75,7 +76,7 @@ int BPF_PROG(counter, struct cgroup *dst_cgrp, struct task_struct *leader,
 	else if (create_percpu_attach_counter(cg_id, 1))
 		return 0;
 
-	cgroup_rstat_updated(dst_cgrp, bpf_get_smp_processor_id());
+	css_rstat_updated(&dst_cgrp->self, bpf_get_smp_processor_id());
 	return 0;
 }
 
@@ -141,7 +142,7 @@ int BPF_PROG(dumper, struct bpf_iter_meta *meta, struct cgroup *cgrp)
 		return 1;
 
 	/* Flush the stats to make sure we get the most updated numbers */
-	cgroup_rstat_flush(cgrp);
+	css_rstat_flush(&cgrp->self);
 
 	total_counter = bpf_map_lookup_elem(&attach_counters, &cg_id);
 	if (!total_counter) {
diff --git a/tools/testing/selftests/bpf/progs/cgroup_iter.c b/tools/testing/selftests/bpf/progs/cgroup_iter.c
index de03997322a7..f30841997a8d 100644
--- a/tools/testing/selftests/bpf/progs/cgroup_iter.c
+++ b/tools/testing/selftests/bpf/progs/cgroup_iter.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2022 Google */
-
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
diff --git a/tools/testing/selftests/bpf/progs/cgroup_mprog.c b/tools/testing/selftests/bpf/progs/cgroup_mprog.c
new file mode 100644
index 000000000000..6a0ea02c4de2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cgroup_mprog.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+SEC("cgroup/getsockopt")
+int getsockopt_1(struct bpf_sockopt *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/getsockopt")
+int getsockopt_2(struct bpf_sockopt *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/getsockopt")
+int getsockopt_3(struct bpf_sockopt *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/getsockopt")
+int getsockopt_4(struct bpf_sockopt *ctx)
+{
+	return 1;
+}
diff --git a/tools/testing/selftests/bpf/progs/cgroup_preorder.c b/tools/testing/selftests/bpf/progs/cgroup_preorder.c
new file mode 100644
index 000000000000..4ef6202baa0a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cgroup_preorder.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+unsigned int idx;
+__u8 result[4];
+
+SEC("cgroup/getsockopt")
+int child(struct bpf_sockopt *ctx)
+{
+	if (idx < 4)
+		result[idx++] = 1;
+	return 1;
+}
+
+SEC("cgroup/getsockopt")
+int child_2(struct bpf_sockopt *ctx)
+{
+	if (idx < 4)
+		result[idx++] = 2;
+	return 1;
+}
+
+SEC("cgroup/getsockopt")
+int parent(struct bpf_sockopt *ctx)
+{
+	if (idx < 4)
+		result[idx++] = 3;
+	return 1;
+}
+
+SEC("cgroup/getsockopt")
+int parent_2(struct bpf_sockopt *ctx)
+{
+	if (idx < 4)
+		result[idx++] = 4;
+	return 1;
+}
diff --git a/tools/testing/selftests/bpf/progs/cgroup_read_xattr.c b/tools/testing/selftests/bpf/progs/cgroup_read_xattr.c
new file mode 100644
index 000000000000..88e13e17ec9e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cgroup_read_xattr.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_experimental.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+char value[16];
+
+static __always_inline void read_xattr(struct cgroup *cgroup)
+{
+	struct bpf_dynptr value_ptr;
+
+	bpf_dynptr_from_mem(value, sizeof(value), 0, &value_ptr);
+	bpf_cgroup_read_xattr(cgroup, "user.bpf_test",
+			      &value_ptr);
+}
+
+SEC("lsm.s/socket_connect")
+__success
+int BPF_PROG(trusted_cgroup_ptr_sleepable)
+{
+	u64 cgrp_id = bpf_get_current_cgroup_id();
+	struct cgroup *cgrp;
+
+	cgrp = bpf_cgroup_from_id(cgrp_id);
+	if (!cgrp)
+		return 0;
+
+	read_xattr(cgrp);
+	bpf_cgroup_release(cgrp);
+	return 0;
+}
+
+SEC("lsm/socket_connect")
+__success
+int BPF_PROG(trusted_cgroup_ptr_non_sleepable)
+{
+	u64 cgrp_id = bpf_get_current_cgroup_id();
+	struct cgroup *cgrp;
+
+	cgrp = bpf_cgroup_from_id(cgrp_id);
+	if (!cgrp)
+		return 0;
+
+	read_xattr(cgrp);
+	bpf_cgroup_release(cgrp);
+	return 0;
+}
+
+SEC("lsm/socket_connect")
+__success
+int BPF_PROG(use_css_iter_non_sleepable)
+{
+	u64 cgrp_id = bpf_get_current_cgroup_id();
+	struct cgroup_subsys_state *css;
+	struct cgroup *cgrp;
+
+	cgrp = bpf_cgroup_from_id(cgrp_id);
+	if (!cgrp)
+		return 0;
+
+	bpf_for_each(css, css, &cgrp->self, BPF_CGROUP_ITER_ANCESTORS_UP)
+		read_xattr(css->cgroup);
+
+	bpf_cgroup_release(cgrp);
+	return 0;
+}
+
+SEC("lsm.s/socket_connect")
+__failure __msg("kernel func bpf_iter_css_new requires RCU critical section protection")
+int BPF_PROG(use_css_iter_sleepable_missing_rcu_lock)
+{
+	u64 cgrp_id = bpf_get_current_cgroup_id();
+	struct cgroup_subsys_state *css;
+	struct cgroup *cgrp;
+
+	cgrp = bpf_cgroup_from_id(cgrp_id);
+	if (!cgrp)
+		return 0;
+
+	bpf_for_each(css, css, &cgrp->self, BPF_CGROUP_ITER_ANCESTORS_UP)
+		read_xattr(css->cgroup);
+
+	bpf_cgroup_release(cgrp);
+	return 0;
+}
+
+SEC("lsm.s/socket_connect")
+__success
+int BPF_PROG(use_css_iter_sleepable_with_rcu_lock)
+{
+	u64 cgrp_id = bpf_get_current_cgroup_id();
+	struct cgroup_subsys_state *css;
+	struct cgroup *cgrp;
+
+	bpf_rcu_read_lock();
+	cgrp = bpf_cgroup_from_id(cgrp_id);
+	if (!cgrp)
+		goto out;
+
+	bpf_for_each(css, css, &cgrp->self, BPF_CGROUP_ITER_ANCESTORS_UP)
+		read_xattr(css->cgroup);
+
+	bpf_cgroup_release(cgrp);
+out:
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("lsm/socket_connect")
+__success
+int BPF_PROG(use_bpf_cgroup_ancestor)
+{
+	u64 cgrp_id = bpf_get_current_cgroup_id();
+	struct cgroup *cgrp, *ancestor;
+
+	cgrp = bpf_cgroup_from_id(cgrp_id);
+	if (!cgrp)
+		return 0;
+
+	ancestor = bpf_cgroup_ancestor(cgrp, 1);
+	if (!ancestor)
+		goto out;
+
+	read_xattr(cgrp);
+	bpf_cgroup_release(ancestor);
+out:
+	bpf_cgroup_release(cgrp);
+	return 0;
+}
+
+SEC("cgroup/sendmsg4")
+__success
+int BPF_PROG(cgroup_skb)
+{
+	u64 cgrp_id = bpf_get_current_cgroup_id();
+	struct cgroup *cgrp, *ancestor;
+
+	cgrp = bpf_cgroup_from_id(cgrp_id);
+	if (!cgrp)
+		return 0;
+
+	ancestor = bpf_cgroup_ancestor(cgrp, 1);
+	if (!ancestor)
+		goto out;
+
+	read_xattr(cgrp);
+	bpf_cgroup_release(ancestor);
+out:
+	bpf_cgroup_release(cgrp);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/cgroup_skb_direct_packet_access.c b/tools/testing/selftests/bpf/progs/cgroup_skb_direct_packet_access.c
new file mode 100644
index 000000000000..e32b07d802bb
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cgroup_skb_direct_packet_access.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+__u32 data_end;
+
+SEC("cgroup_skb/ingress")
+int direct_packet_access(struct __sk_buff *skb)
+{
+	data_end = skb->data_end;
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c
index 88638315c582..ac86a8a61605 100644
--- a/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c
+++ b/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c
@@ -66,7 +66,6 @@ static inline int is_allowed_peer_cg(struct __sk_buff *skb,
 SEC("cgroup_skb/ingress")
 int ingress_lookup(struct __sk_buff *skb)
 {
-	__u32 serv_port_key = 0;
 	struct ipv6hdr ip6h;
 	struct tcphdr tcph;
 
diff --git a/tools/testing/selftests/bpf/progs/cgroup_storage.c b/tools/testing/selftests/bpf/progs/cgroup_storage.c
new file mode 100644
index 000000000000..db1e4d2d3281
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cgroup_storage.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_CGROUP_STORAGE);
+	__type(key, struct bpf_cgroup_storage_key);
+	__type(value, __u64);
+} cgroup_storage SEC(".maps");
+
+SEC("cgroup_skb/egress")
+int bpf_prog(struct __sk_buff *skb)
+{
+	__u64 *counter;
+
+	counter = bpf_get_local_storage(&cgroup_storage, 0);
+	__sync_fetch_and_add(counter, 1);
+
+	/* Drop one out of every two packets */
+	return (*counter & 1);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/cgroup_tcp_skb.c b/tools/testing/selftests/bpf/progs/cgroup_tcp_skb.c
new file mode 100644
index 000000000000..1e2e73f3b749
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cgroup_tcp_skb.c
@@ -0,0 +1,382 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+#include <linux/bpf.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+
+#include <sys/types.h>
+#include <sys/socket.h>
+
+#include "cgroup_tcp_skb.h"
+
+char _license[] SEC("license") = "GPL";
+
+__u16 g_sock_port = 0;
+__u32 g_sock_state = 0;
+int g_unexpected = 0;
+__u32 g_packet_count = 0;
+
+int needed_tcp_pkt(struct __sk_buff *skb, struct tcphdr *tcph)
+{
+	struct ipv6hdr ip6h;
+
+	if (skb->protocol != bpf_htons(ETH_P_IPV6))
+		return 0;
+	if (bpf_skb_load_bytes(skb, 0, &ip6h, sizeof(ip6h)))
+		return 0;
+
+	if (ip6h.nexthdr != IPPROTO_TCP)
+		return 0;
+
+	if (bpf_skb_load_bytes(skb, sizeof(ip6h), tcph, sizeof(*tcph)))
+		return 0;
+
+	if (tcph->source != bpf_htons(g_sock_port) &&
+	    tcph->dest != bpf_htons(g_sock_port))
+		return 0;
+
+	return 1;
+}
+
+/* Run accept() on a socket in the cgroup to receive a new connection. */
+static int egress_accept(struct tcphdr *tcph)
+{
+	if (g_sock_state ==  SYN_RECV_SENDING_SYN_ACK) {
+		if (tcph->fin || !tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = SYN_RECV;
+		return 1;
+	}
+
+	return 0;
+}
+
+static int ingress_accept(struct tcphdr *tcph)
+{
+	switch (g_sock_state) {
+	case INIT:
+		if (!tcph->syn || tcph->fin || tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = SYN_RECV_SENDING_SYN_ACK;
+		break;
+	case SYN_RECV:
+		if (tcph->fin || tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = ESTABLISHED;
+		break;
+	default:
+		return 0;
+	}
+
+	return 1;
+}
+
+/* Run connect() on a socket in the cgroup to start a new connection. */
+static int egress_connect(struct tcphdr *tcph)
+{
+	if (g_sock_state == INIT) {
+		if (!tcph->syn || tcph->fin || tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = SYN_SENT;
+		return 1;
+	}
+
+	return 0;
+}
+
+static int ingress_connect(struct tcphdr *tcph)
+{
+	if (g_sock_state == SYN_SENT) {
+		if (tcph->fin || !tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = ESTABLISHED;
+		return 1;
+	}
+
+	return 0;
+}
+
+/* The connection is closed by the peer outside the cgroup. */
+static int egress_close_remote(struct tcphdr *tcph)
+{
+	switch (g_sock_state) {
+	case ESTABLISHED:
+		break;
+	case CLOSE_WAIT_SENDING_ACK:
+		if (tcph->fin || tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = CLOSE_WAIT;
+		break;
+	case CLOSE_WAIT:
+		if (!tcph->fin)
+			g_unexpected++;
+		else
+			g_sock_state = LAST_ACK;
+		break;
+	default:
+		return 0;
+	}
+
+	return 1;
+}
+
+static int ingress_close_remote(struct tcphdr *tcph)
+{
+	switch (g_sock_state) {
+	case ESTABLISHED:
+		if (tcph->fin)
+			g_sock_state = CLOSE_WAIT_SENDING_ACK;
+		break;
+	case LAST_ACK:
+		if (tcph->fin || tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = CLOSED;
+		break;
+	default:
+		return 0;
+	}
+
+	return 1;
+}
+
+/* The connection is closed by the endpoint inside the cgroup. */
+static int egress_close_local(struct tcphdr *tcph)
+{
+	switch (g_sock_state) {
+	case ESTABLISHED:
+		if (tcph->fin)
+			g_sock_state = FIN_WAIT1;
+		break;
+	case TIME_WAIT_SENDING_ACK:
+		if (tcph->fin || tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = TIME_WAIT;
+		break;
+	default:
+		return 0;
+	}
+
+	return 1;
+}
+
+static int ingress_close_local(struct tcphdr *tcph)
+{
+	switch (g_sock_state) {
+	case ESTABLISHED:
+		break;
+	case FIN_WAIT1:
+		if (tcph->fin || tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = FIN_WAIT2;
+		break;
+	case FIN_WAIT2:
+		if (!tcph->fin || tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = TIME_WAIT_SENDING_ACK;
+		break;
+	default:
+		return 0;
+	}
+
+	return 1;
+}
+
+/* Check the types of outgoing packets of a server socket to make sure they
+ * are consistent with the state of the server socket.
+ *
+ * The connection is closed by the client side.
+ */
+SEC("cgroup_skb/egress")
+int server_egress(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Egress of the server socket. */
+	if (egress_accept(&tcph) || egress_close_remote(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
+
+/* Check the types of incoming packets of a server socket to make sure they
+ * are consistent with the state of the server socket.
+ *
+ * The connection is closed by the client side.
+ */
+SEC("cgroup_skb/ingress")
+int server_ingress(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Ingress of the server socket. */
+	if (ingress_accept(&tcph) || ingress_close_remote(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
+
+/* Check the types of outgoing packets of a server socket to make sure they
+ * are consistent with the state of the server socket.
+ *
+ * The connection is closed by the server side.
+ */
+SEC("cgroup_skb/egress")
+int server_egress_srv(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Egress of the server socket. */
+	if (egress_accept(&tcph) || egress_close_local(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
+
+/* Check the types of incoming packets of a server socket to make sure they
+ * are consistent with the state of the server socket.
+ *
+ * The connection is closed by the server side.
+ */
+SEC("cgroup_skb/ingress")
+int server_ingress_srv(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Ingress of the server socket. */
+	if (ingress_accept(&tcph) || ingress_close_local(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
+
+/* Check the types of outgoing packets of a client socket to make sure they
+ * are consistent with the state of the client socket.
+ *
+ * The connection is closed by the server side.
+ */
+SEC("cgroup_skb/egress")
+int client_egress_srv(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Egress of the server socket. */
+	if (egress_connect(&tcph) || egress_close_remote(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
+
+/* Check the types of incoming packets of a client socket to make sure they
+ * are consistent with the state of the client socket.
+ *
+ * The connection is closed by the server side.
+ */
+SEC("cgroup_skb/ingress")
+int client_ingress_srv(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Ingress of the server socket. */
+	if (ingress_connect(&tcph) || ingress_close_remote(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
+
+/* Check the types of outgoing packets of a client socket to make sure they
+ * are consistent with the state of the client socket.
+ *
+ * The connection is closed by the client side.
+ */
+SEC("cgroup_skb/egress")
+int client_egress(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Egress of the server socket. */
+	if (egress_connect(&tcph) || egress_close_local(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
+
+/* Check the types of incoming packets of a client socket to make sure they
+ * are consistent with the state of the client socket.
+ *
+ * The connection is closed by the client side.
+ */
+SEC("cgroup_skb/ingress")
+int client_ingress(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Ingress of the server socket. */
+	if (ingress_connect(&tcph) || ingress_close_local(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
diff --git a/tools/testing/selftests/bpf/progs/cgrp_kfunc_common.h b/tools/testing/selftests/bpf/progs/cgrp_kfunc_common.h
index 7d30855bfe78..73ba32e9a693 100644
--- a/tools/testing/selftests/bpf/progs/cgrp_kfunc_common.h
+++ b/tools/testing/selftests/bpf/progs/cgrp_kfunc_common.h
@@ -10,10 +10,10 @@
 #include <bpf/bpf_tracing.h>
 
 struct __cgrps_kfunc_map_value {
-	struct cgroup __kptr_ref * cgrp;
+	struct cgroup __kptr * cgrp;
 };
 
-struct hash_map {
+struct {
 	__uint(type, BPF_MAP_TYPE_HASH);
 	__type(key, int);
 	__type(value, struct __cgrps_kfunc_map_value);
@@ -21,9 +21,11 @@ struct hash_map {
 } __cgrps_kfunc_map SEC(".maps");
 
 struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym;
-struct cgroup *bpf_cgroup_kptr_get(struct cgroup **pp) __ksym;
 void bpf_cgroup_release(struct cgroup *p) __ksym;
 struct cgroup *bpf_cgroup_ancestor(struct cgroup *cgrp, int level) __ksym;
+struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym;
+void bpf_rcu_read_lock(void) __ksym;
+void bpf_rcu_read_unlock(void) __ksym;
 
 static inline struct __cgrps_kfunc_map_value *cgrps_kfunc_map_value_lookup(struct cgroup *cgrp)
 {
@@ -60,6 +62,11 @@ static inline int cgrps_kfunc_map_insert(struct cgroup *cgrp)
 	}
 
 	acquired = bpf_cgroup_acquire(cgrp);
+	if (!acquired) {
+		bpf_map_delete_elem(&__cgrps_kfunc_map, &id);
+		return -ENOENT;
+	}
+
 	old = bpf_kptr_xchg(&v->cgrp, acquired);
 	if (old) {
 		bpf_cgroup_release(old);
diff --git a/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c b/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c
index a1369b5ebcf8..9fe9c4a4e8f6 100644
--- a/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c
+++ b/tools/testing/selftests/bpf/progs/cgrp_kfunc_failure.c
@@ -5,6 +5,7 @@
 #include <bpf/bpf_tracing.h>
 #include <bpf/bpf_helpers.h>
 
+#include "bpf_misc.h"
 #include "cgrp_kfunc_common.h"
 
 char _license[] SEC("license") = "GPL";
@@ -28,6 +29,7 @@ static struct __cgrps_kfunc_map_value *insert_lookup_cgrp(struct cgroup *cgrp)
 }
 
 SEC("tp_btf/cgroup_mkdir")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
 int BPF_PROG(cgrp_kfunc_acquire_untrusted, struct cgroup *cgrp, const char *path)
 {
 	struct cgroup *acquired;
@@ -39,63 +41,86 @@ int BPF_PROG(cgrp_kfunc_acquire_untrusted, struct cgroup *cgrp, const char *path
 
 	/* Can't invoke bpf_cgroup_acquire() on an untrusted pointer. */
 	acquired = bpf_cgroup_acquire(v->cgrp);
+	if (acquired)
+		bpf_cgroup_release(acquired);
+
+	return 0;
+}
+
+SEC("tp_btf/cgroup_mkdir")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
+int BPF_PROG(cgrp_kfunc_acquire_no_null_check, struct cgroup *cgrp, const char *path)
+{
+	struct cgroup *acquired;
+
+	acquired = bpf_cgroup_acquire(cgrp);
+	/*
+	 * Can't invoke bpf_cgroup_release() without checking the return value
+	 * of bpf_cgroup_acquire().
+	 */
 	bpf_cgroup_release(acquired);
 
 	return 0;
 }
 
 SEC("tp_btf/cgroup_mkdir")
+__failure __msg("arg#0 pointer type STRUCT cgroup must point")
 int BPF_PROG(cgrp_kfunc_acquire_fp, struct cgroup *cgrp, const char *path)
 {
 	struct cgroup *acquired, *stack_cgrp = (struct cgroup *)&path;
 
 	/* Can't invoke bpf_cgroup_acquire() on a random frame pointer. */
 	acquired = bpf_cgroup_acquire((struct cgroup *)&stack_cgrp);
-	bpf_cgroup_release(acquired);
+	if (acquired)
+		bpf_cgroup_release(acquired);
 
 	return 0;
 }
 
 SEC("kretprobe/cgroup_destroy_locked")
+__failure __msg("calling kernel function bpf_cgroup_acquire is not allowed")
 int BPF_PROG(cgrp_kfunc_acquire_unsafe_kretprobe, struct cgroup *cgrp)
 {
 	struct cgroup *acquired;
 
 	/* Can't acquire an untrusted struct cgroup * pointer. */
 	acquired = bpf_cgroup_acquire(cgrp);
-	bpf_cgroup_release(acquired);
+	if (acquired)
+		bpf_cgroup_release(acquired);
 
 	return 0;
 }
 
 SEC("tp_btf/cgroup_mkdir")
+__failure __msg("cgrp_kfunc_acquire_trusted_walked")
 int BPF_PROG(cgrp_kfunc_acquire_trusted_walked, struct cgroup *cgrp, const char *path)
 {
 	struct cgroup *acquired;
 
 	/* Can't invoke bpf_cgroup_acquire() on a pointer obtained from walking a trusted cgroup. */
 	acquired = bpf_cgroup_acquire(cgrp->old_dom_cgrp);
-	bpf_cgroup_release(acquired);
+	if (acquired)
+		bpf_cgroup_release(acquired);
 
 	return 0;
 }
 
-
 SEC("tp_btf/cgroup_mkdir")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
 int BPF_PROG(cgrp_kfunc_acquire_null, struct cgroup *cgrp, const char *path)
 {
 	struct cgroup *acquired;
 
 	/* Can't invoke bpf_cgroup_acquire() on a NULL pointer. */
 	acquired = bpf_cgroup_acquire(NULL);
-	if (!acquired)
-		return 0;
-	bpf_cgroup_release(acquired);
+	if (acquired)
+		bpf_cgroup_release(acquired);
 
 	return 0;
 }
 
 SEC("tp_btf/cgroup_mkdir")
+__failure __msg("Unreleased reference")
 int BPF_PROG(cgrp_kfunc_acquire_unreleased, struct cgroup *cgrp, const char *path)
 {
 	struct cgroup *acquired;
@@ -103,59 +128,13 @@ int BPF_PROG(cgrp_kfunc_acquire_unreleased, struct cgroup *cgrp, const char *pat
 	acquired = bpf_cgroup_acquire(cgrp);
 
 	/* Acquired cgroup is never released. */
+	__sink(acquired);
 
 	return 0;
 }
 
 SEC("tp_btf/cgroup_mkdir")
-int BPF_PROG(cgrp_kfunc_get_non_kptr_param, struct cgroup *cgrp, const char *path)
-{
-	struct cgroup *kptr;
-
-	/* Cannot use bpf_cgroup_kptr_get() on a non-kptr, even on a valid cgroup. */
-	kptr = bpf_cgroup_kptr_get(&cgrp);
-	if (!kptr)
-		return 0;
-
-	bpf_cgroup_release(kptr);
-
-	return 0;
-}
-
-SEC("tp_btf/cgroup_mkdir")
-int BPF_PROG(cgrp_kfunc_get_non_kptr_acquired, struct cgroup *cgrp, const char *path)
-{
-	struct cgroup *kptr, *acquired;
-
-	acquired = bpf_cgroup_acquire(cgrp);
-
-	/* Cannot use bpf_cgroup_kptr_get() on a non-map-value, even if the kptr was acquired. */
-	kptr = bpf_cgroup_kptr_get(&acquired);
-	bpf_cgroup_release(acquired);
-	if (!kptr)
-		return 0;
-
-	bpf_cgroup_release(kptr);
-
-	return 0;
-}
-
-SEC("tp_btf/cgroup_mkdir")
-int BPF_PROG(cgrp_kfunc_get_null, struct cgroup *cgrp, const char *path)
-{
-	struct cgroup *kptr;
-
-	/* Cannot use bpf_cgroup_kptr_get() on a NULL pointer. */
-	kptr = bpf_cgroup_kptr_get(NULL);
-	if (!kptr)
-		return 0;
-
-	bpf_cgroup_release(kptr);
-
-	return 0;
-}
-
-SEC("tp_btf/cgroup_mkdir")
+__failure __msg("Unreleased reference")
 int BPF_PROG(cgrp_kfunc_xchg_unreleased, struct cgroup *cgrp, const char *path)
 {
 	struct cgroup *kptr;
@@ -175,7 +154,8 @@ int BPF_PROG(cgrp_kfunc_xchg_unreleased, struct cgroup *cgrp, const char *path)
 }
 
 SEC("tp_btf/cgroup_mkdir")
-int BPF_PROG(cgrp_kfunc_get_unreleased, struct cgroup *cgrp, const char *path)
+__failure __msg("must be referenced or trusted")
+int BPF_PROG(cgrp_kfunc_rcu_get_release, struct cgroup *cgrp, const char *path)
 {
 	struct cgroup *kptr;
 	struct __cgrps_kfunc_map_value *v;
@@ -184,16 +164,18 @@ int BPF_PROG(cgrp_kfunc_get_unreleased, struct cgroup *cgrp, const char *path)
 	if (!v)
 		return 0;
 
-	kptr = bpf_cgroup_kptr_get(&v->cgrp);
-	if (!kptr)
-		return 0;
-
-	/* Kptr acquired above is never released. */
+	bpf_rcu_read_lock();
+	kptr = v->cgrp;
+	if (kptr)
+		/* Can't release a cgroup kptr stored in a map. */
+		bpf_cgroup_release(kptr);
+	bpf_rcu_read_unlock();
 
 	return 0;
 }
 
 SEC("tp_btf/cgroup_mkdir")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
 int BPF_PROG(cgrp_kfunc_release_untrusted, struct cgroup *cgrp, const char *path)
 {
 	struct __cgrps_kfunc_map_value *v;
@@ -209,6 +191,7 @@ int BPF_PROG(cgrp_kfunc_release_untrusted, struct cgroup *cgrp, const char *path
 }
 
 SEC("tp_btf/cgroup_mkdir")
+__failure __msg("arg#0 pointer type STRUCT cgroup must point")
 int BPF_PROG(cgrp_kfunc_release_fp, struct cgroup *cgrp, const char *path)
 {
 	struct cgroup *acquired = (struct cgroup *)&path;
@@ -220,6 +203,7 @@ int BPF_PROG(cgrp_kfunc_release_fp, struct cgroup *cgrp, const char *path)
 }
 
 SEC("tp_btf/cgroup_mkdir")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
 int BPF_PROG(cgrp_kfunc_release_null, struct cgroup *cgrp, const char *path)
 {
 	struct __cgrps_kfunc_map_value local, *v;
@@ -241,6 +225,8 @@ int BPF_PROG(cgrp_kfunc_release_null, struct cgroup *cgrp, const char *path)
 		return -ENOENT;
 
 	acquired = bpf_cgroup_acquire(cgrp);
+	if (!acquired)
+		return -ENOENT;
 
 	old = bpf_kptr_xchg(&v->cgrp, acquired);
 
@@ -251,6 +237,7 @@ int BPF_PROG(cgrp_kfunc_release_null, struct cgroup *cgrp, const char *path)
 }
 
 SEC("tp_btf/cgroup_mkdir")
+__failure __msg("release kernel function bpf_cgroup_release expects")
 int BPF_PROG(cgrp_kfunc_release_unacquired, struct cgroup *cgrp, const char *path)
 {
 	/* Cannot release trusted cgroup pointer which was not acquired. */
diff --git a/tools/testing/selftests/bpf/progs/cgrp_kfunc_success.c b/tools/testing/selftests/bpf/progs/cgrp_kfunc_success.c
index 0c23ea32df9f..02d8f160ca0e 100644
--- a/tools/testing/selftests/bpf/progs/cgrp_kfunc_success.c
+++ b/tools/testing/selftests/bpf/progs/cgrp_kfunc_success.c
@@ -38,7 +38,10 @@ int BPF_PROG(test_cgrp_acquire_release_argument, struct cgroup *cgrp, const char
 		return 0;
 
 	acquired = bpf_cgroup_acquire(cgrp);
-	bpf_cgroup_release(acquired);
+	if (!acquired)
+		err = 1;
+	else
+		bpf_cgroup_release(acquired);
 
 	return 0;
 }
@@ -61,7 +64,7 @@ int BPF_PROG(test_cgrp_acquire_leave_in_map, struct cgroup *cgrp, const char *pa
 SEC("tp_btf/cgroup_mkdir")
 int BPF_PROG(test_cgrp_xchg_release, struct cgroup *cgrp, const char *path)
 {
-	struct cgroup *kptr;
+	struct cgroup *kptr, *cg;
 	struct __cgrps_kfunc_map_value *v;
 	long status;
 
@@ -80,6 +83,16 @@ int BPF_PROG(test_cgrp_xchg_release, struct cgroup *cgrp, const char *path)
 		return 0;
 	}
 
+	kptr = v->cgrp;
+	if (!kptr) {
+		err = 4;
+		return 0;
+	}
+
+	cg = bpf_cgroup_ancestor(kptr, 1);
+	if (cg)	/* verifier only check */
+		bpf_cgroup_release(cg);
+
 	kptr = bpf_kptr_xchg(&v->cgrp, NULL);
 	if (!kptr) {
 		err = 3;
@@ -113,13 +126,11 @@ int BPF_PROG(test_cgrp_get_release, struct cgroup *cgrp, const char *path)
 		return 0;
 	}
 
-	kptr = bpf_cgroup_kptr_get(&v->cgrp);
-	if (!kptr) {
+	bpf_rcu_read_lock();
+	kptr = v->cgrp;
+	if (!kptr)
 		err = 3;
-		return 0;
-	}
-
-	bpf_cgroup_release(kptr);
+	bpf_rcu_read_unlock();
 
 	return 0;
 }
@@ -168,3 +179,57 @@ int BPF_PROG(test_cgrp_get_ancestors, struct cgroup *cgrp, const char *path)
 
 	return 0;
 }
+
+SEC("tp_btf/cgroup_mkdir")
+int BPF_PROG(test_cgrp_from_id, struct cgroup *cgrp, const char *path)
+{
+	struct cgroup *parent, *res;
+	u64 parent_cgid;
+
+	if (!is_test_kfunc_task())
+		return 0;
+
+	/* @cgrp's ID is not visible yet, let's test with the parent */
+	parent = bpf_cgroup_ancestor(cgrp, cgrp->level - 1);
+	if (!parent) {
+		err = 1;
+		return 0;
+	}
+
+	parent_cgid = parent->kn->id;
+	bpf_cgroup_release(parent);
+
+	res = bpf_cgroup_from_id(parent_cgid);
+	if (!res) {
+		err = 2;
+		return 0;
+	}
+
+	bpf_cgroup_release(res);
+
+	if (res != parent) {
+		err = 3;
+		return 0;
+	}
+
+	res = bpf_cgroup_from_id((u64)-1);
+	if (res) {
+		bpf_cgroup_release(res);
+		err = 4;
+		return 0;
+	}
+
+	return 0;
+}
+
+SEC("syscall")
+int test_cgrp_from_id_ns(void *ctx)
+{
+	struct cgroup *cg;
+
+	cg = bpf_cgroup_from_id(1);
+	if (!cg)
+		return 42;
+	bpf_cgroup_release(cg);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_attach_cgroup.c b/tools/testing/selftests/bpf/progs/cgrp_ls_attach_cgroup.c
index 6652d18465b2..8aeba1b75c83 100644
--- a/tools/testing/selftests/bpf/progs/cgrp_ls_attach_cgroup.c
+++ b/tools/testing/selftests/bpf/progs/cgrp_ls_attach_cgroup.c
@@ -84,7 +84,6 @@ int BPF_PROG(update_cookie_tracing, struct socket *sock,
 	     struct sockaddr *uaddr, int addr_len, int flags)
 {
 	struct socket_cookie *p;
-	struct tcp_sock *tcp_sk;
 
 	if (uaddr->sa_family != AF_INET6)
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c b/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c
index a043d8fefdac..3500e4b69ebe 100644
--- a/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c
+++ b/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c
@@ -21,50 +21,74 @@ struct {
 	__type(value, long);
 } map_b SEC(".maps");
 
-SEC("fentry/bpf_local_storage_lookup")
-int BPF_PROG(on_lookup)
-{
-	struct task_struct *task = bpf_get_current_task_btf();
+int target_hid = 0;
+bool is_cgroup1 = 0;
 
-	bpf_cgrp_storage_delete(&map_a, task->cgroups->dfl_cgrp);
-	bpf_cgrp_storage_delete(&map_b, task->cgroups->dfl_cgrp);
-	return 0;
-}
+struct cgroup *bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id) __ksym;
+void bpf_cgroup_release(struct cgroup *cgrp) __ksym;
 
-SEC("fentry/bpf_local_storage_update")
-int BPF_PROG(on_update)
+static void __on_update(struct cgroup *cgrp)
 {
-	struct task_struct *task = bpf_get_current_task_btf();
 	long *ptr;
 
-	ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0,
-				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (ptr)
 		*ptr += 1;
 
-	ptr = bpf_cgrp_storage_get(&map_b, task->cgroups->dfl_cgrp, 0,
-				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	ptr = bpf_cgrp_storage_get(&map_b, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (ptr)
 		*ptr += 1;
+}
+
+SEC("fentry/bpf_local_storage_update")
+int BPF_PROG(on_update)
+{
+	struct task_struct *task = bpf_get_current_task_btf();
+	struct cgroup *cgrp;
 
+	if (is_cgroup1) {
+		cgrp = bpf_task_get_cgroup1(task, target_hid);
+		if (!cgrp)
+			return 0;
+
+		__on_update(cgrp);
+		bpf_cgroup_release(cgrp);
+		return 0;
+	}
+
+	__on_update(task->cgroups->dfl_cgrp);
 	return 0;
 }
 
-SEC("tp_btf/sys_enter")
-int BPF_PROG(on_enter, struct pt_regs *regs, long id)
+static void __on_enter(struct pt_regs *regs, long id, struct cgroup *cgrp)
 {
-	struct task_struct *task;
 	long *ptr;
 
-	task = bpf_get_current_task_btf();
-	ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0,
-				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (ptr)
 		*ptr = 200;
 
-	ptr = bpf_cgrp_storage_get(&map_b, task->cgroups->dfl_cgrp, 0,
-				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	ptr = bpf_cgrp_storage_get(&map_b, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (ptr)
 		*ptr = 100;
+}
+
+SEC("tp_btf/sys_enter")
+int BPF_PROG(on_enter, struct pt_regs *regs, long id)
+{
+	struct task_struct *task = bpf_get_current_task_btf();
+	struct cgroup *cgrp;
+
+	if (is_cgroup1) {
+		cgrp = bpf_task_get_cgroup1(task, target_hid);
+		if (!cgrp)
+			return 0;
+
+		__on_enter(regs, id, cgrp);
+		bpf_cgroup_release(cgrp);
+		return 0;
+	}
+
+	__on_enter(regs, id, task->cgroups->dfl_cgrp);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c b/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c
index 2d11ed528b6f..a2de95f85648 100644
--- a/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c
+++ b/tools/testing/selftests/bpf/progs/cgrp_ls_sleepable.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
-
-#include "bpf_iter.h"
+#include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include "bpf_misc.h"
@@ -15,16 +14,19 @@ struct {
 	__type(value, long);
 } map_a SEC(".maps");
 
-__u32 target_pid;
+__s32 target_pid;
 __u64 cgroup_id;
+int target_hid;
+bool is_cgroup1;
 
+struct cgroup *bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id) __ksym;
+void bpf_cgroup_release(struct cgroup *cgrp) __ksym;
 void bpf_rcu_read_lock(void) __ksym;
 void bpf_rcu_read_unlock(void) __ksym;
 
 SEC("?iter.s/cgroup")
 int cgroup_iter(struct bpf_iter__cgroup *ctx)
 {
-	struct seq_file *seq = ctx->meta->seq;
 	struct cgroup *cgrp = ctx->cgroup;
 	long *ptr;
 
@@ -38,23 +40,50 @@ int cgroup_iter(struct bpf_iter__cgroup *ctx)
 	return 0;
 }
 
+static void __no_rcu_lock(struct cgroup *cgrp)
+{
+	long *ptr;
+
+	/* Note that trace rcu is held in sleepable prog, so we can use
+	 * bpf_cgrp_storage_get() in sleepable prog.
+	 */
+	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0,
+				   BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (ptr)
+		cgroup_id = cgrp->kn->id;
+}
+
 SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
-int no_rcu_lock(void *ctx)
+int cgrp1_no_rcu_lock(void *ctx)
 {
 	struct task_struct *task;
 	struct cgroup *cgrp;
-	long *ptr;
 
 	task = bpf_get_current_task_btf();
 	if (task->pid != target_pid)
 		return 0;
 
-	/* ptr_to_btf_id semantics. should work. */
-	cgrp = task->cgroups->dfl_cgrp;
-	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0,
-				   BPF_LOCAL_STORAGE_GET_F_CREATE);
-	if (ptr)
-		cgroup_id = cgrp->kn->id;
+	/* bpf_task_get_cgroup1 can work in sleepable prog */
+	cgrp = bpf_task_get_cgroup1(task, target_hid);
+	if (!cgrp)
+		return 0;
+
+	__no_rcu_lock(cgrp);
+	bpf_cgroup_release(cgrp);
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int no_rcu_lock(void *ctx)
+{
+	struct task_struct *task;
+
+	task = bpf_get_current_task_btf();
+	if (task->pid != target_pid)
+		return 0;
+
+	/* task->cgroups is untrusted in sleepable prog outside of RCU CS */
+	__no_rcu_lock(task->cgroups->dfl_cgrp);
 	return 0;
 }
 
@@ -69,9 +98,25 @@ int yes_rcu_lock(void *ctx)
 	if (task->pid != target_pid)
 		return 0;
 
+	if (is_cgroup1) {
+		bpf_rcu_read_lock();
+		cgrp = bpf_task_get_cgroup1(task, target_hid);
+		if (!cgrp) {
+			bpf_rcu_read_unlock();
+			return 0;
+		}
+
+		ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE);
+		if (ptr)
+			cgroup_id = cgrp->kn->id;
+		bpf_cgroup_release(cgrp);
+		bpf_rcu_read_unlock();
+		return 0;
+	}
+
 	bpf_rcu_read_lock();
 	cgrp = task->cgroups->dfl_cgrp;
-	/* cgrp is untrusted and cannot pass to bpf_cgrp_storage_get() helper. */
+	/* cgrp is trusted under RCU CS */
 	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (ptr)
 		cgroup_id = cgrp->kn->id;
diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c b/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c
index 9ebb8e2fe541..1c348f000f38 100644
--- a/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c
+++ b/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c
@@ -27,62 +27,100 @@ pid_t target_pid = 0;
 int mismatch_cnt = 0;
 int enter_cnt = 0;
 int exit_cnt = 0;
+int target_hid = 0;
+bool is_cgroup1 = 0;
 
-SEC("tp_btf/sys_enter")
-int BPF_PROG(on_enter, struct pt_regs *regs, long id)
+struct cgroup *bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id) __ksym;
+void bpf_cgroup_release(struct cgroup *cgrp) __ksym;
+
+static void __on_enter(struct pt_regs *regs, long id, struct cgroup *cgrp)
 {
-	struct task_struct *task;
 	long *ptr;
 	int err;
 
-	task = bpf_get_current_task_btf();
-	if (task->pid != target_pid)
-		return 0;
-
 	/* populate value 0 */
-	ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0,
+	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0,
 				   BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!ptr)
-		return 0;
+		return;
 
 	/* delete value 0 */
-	err = bpf_cgrp_storage_delete(&map_a, task->cgroups->dfl_cgrp);
+	err = bpf_cgrp_storage_delete(&map_a, cgrp);
 	if (err)
-		return 0;
+		return;
 
 	/* value is not available */
-	ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0, 0);
+	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0, 0);
 	if (ptr)
-		return 0;
+		return;
 
 	/* re-populate the value */
-	ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0,
+	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0,
 				   BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!ptr)
-		return 0;
+		return;
 	__sync_fetch_and_add(&enter_cnt, 1);
 	*ptr = MAGIC_VALUE + enter_cnt;
-
-	return 0;
 }
 
-SEC("tp_btf/sys_exit")
-int BPF_PROG(on_exit, struct pt_regs *regs, long id)
+SEC("tp_btf/sys_enter")
+int BPF_PROG(on_enter, struct pt_regs *regs, long id)
 {
 	struct task_struct *task;
-	long *ptr;
+	struct cgroup *cgrp;
 
 	task = bpf_get_current_task_btf();
 	if (task->pid != target_pid)
 		return 0;
 
-	ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0,
+	if (is_cgroup1) {
+		cgrp = bpf_task_get_cgroup1(task, target_hid);
+		if (!cgrp)
+			return 0;
+
+		__on_enter(regs, id, cgrp);
+		bpf_cgroup_release(cgrp);
+		return 0;
+	}
+
+	__on_enter(regs, id, task->cgroups->dfl_cgrp);
+	return 0;
+}
+
+static void __on_exit(struct pt_regs *regs, long id, struct cgroup *cgrp)
+{
+	long *ptr;
+
+	ptr = bpf_cgrp_storage_get(&map_a, cgrp, 0,
 				   BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!ptr)
-		return 0;
+		return;
 
 	__sync_fetch_and_add(&exit_cnt, 1);
 	if (*ptr != MAGIC_VALUE + exit_cnt)
 		__sync_fetch_and_add(&mismatch_cnt, 1);
+}
+
+SEC("tp_btf/sys_exit")
+int BPF_PROG(on_exit, struct pt_regs *regs, long id)
+{
+	struct task_struct *task;
+	struct cgroup *cgrp;
+
+	task = bpf_get_current_task_btf();
+	if (task->pid != target_pid)
+		return 0;
+
+	if (is_cgroup1) {
+		cgrp = bpf_task_get_cgroup1(task, target_hid);
+		if (!cgrp)
+			return 0;
+
+		__on_exit(regs, id, cgrp);
+		bpf_cgroup_release(cgrp);
+		return 0;
+	}
+
+	__on_exit(regs, id, task->cgroups->dfl_cgrp);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/compute_live_registers.c b/tools/testing/selftests/bpf/progs/compute_live_registers.c
new file mode 100644
index 000000000000..6884ab99a421
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/compute_live_registers.c
@@ -0,0 +1,440 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
+#include "bpf_arena_common.h"
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} test_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARENA);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__uint(max_entries, 1);
+} arena SEC(".maps");
+
+SEC("socket")
+__log_level(2)
+__msg(" 0: .......... (b7) r0 = 42")
+__msg(" 1: 0......... (bf) r1 = r0")
+__msg(" 2: .1........ (bf) r2 = r1")
+__msg(" 3: ..2....... (bf) r3 = r2")
+__msg(" 4: ...3...... (bf) r4 = r3")
+__msg(" 5: ....4..... (bf) r5 = r4")
+__msg(" 6: .....5.... (bf) r6 = r5")
+__msg(" 7: ......6... (bf) r7 = r6")
+__msg(" 8: .......7.. (bf) r8 = r7")
+__msg(" 9: ........8. (bf) r9 = r8")
+__msg("10: .........9 (bf) r0 = r9")
+__msg("11: 0......... (95) exit")
+__naked void assign_chain(void)
+{
+	asm volatile (
+		"r0 = 42;"
+		"r1 = r0;"
+		"r2 = r1;"
+		"r3 = r2;"
+		"r4 = r3;"
+		"r5 = r4;"
+		"r6 = r5;"
+		"r7 = r6;"
+		"r8 = r7;"
+		"r9 = r8;"
+		"r0 = r9;"
+		"exit;"
+		::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("0: .......... (b7) r1 = 7")
+__msg("1: .1........ (07) r1 += 7")
+__msg("2: .......... (b7) r2 = 7")
+__msg("3: ..2....... (b7) r3 = 42")
+__msg("4: ..23...... (0f) r2 += r3")
+__msg("5: .......... (b7) r0 = 0")
+__msg("6: 0......... (95) exit")
+__naked void arithmetics(void)
+{
+	asm volatile (
+		"r1 = 7;"
+		"r1 += 7;"
+		"r2 = 7;"
+		"r3 = 42;"
+		"r2 += r3;"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+
+#ifdef CAN_USE_BPF_ST
+SEC("socket")
+__log_level(2)
+__msg("  1: .1........ (07) r1 += -8")
+__msg("  2: .1........ (7a) *(u64 *)(r1 +0) = 7")
+__msg("  3: .1........ (b7) r2 = 42")
+__msg("  4: .12....... (7b) *(u64 *)(r1 +0) = r2")
+__msg("  5: .12....... (7b) *(u64 *)(r1 +0) = r2")
+__msg("  6: .......... (b7) r0 = 0")
+__naked void store(void)
+{
+	asm volatile (
+		"r1 = r10;"
+		"r1 += -8;"
+		"*(u64 *)(r1 +0) = 7;"
+		"r2 = 42;"
+		"*(u64 *)(r1 +0) = r2;"
+		"*(u64 *)(r1 +0) = r2;"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+#endif
+
+SEC("socket")
+__log_level(2)
+__msg("1: ....4..... (07) r4 += -8")
+__msg("2: ....4..... (79) r5 = *(u64 *)(r4 +0)")
+__msg("3: ....45.... (07) r4 += -8")
+__naked void load(void)
+{
+	asm volatile (
+		"r4 = r10;"
+		"r4 += -8;"
+		"r5 = *(u64 *)(r4 +0);"
+		"r4 += -8;"
+		"r0 = r5;"
+		"exit;"
+		::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("0: .1........ (61) r2 = *(u32 *)(r1 +0)")
+__msg("1: ..2....... (d4) r2 = le64 r2")
+__msg("2: ..2....... (bf) r0 = r2")
+__naked void endian(void)
+{
+	asm volatile (
+		"r2 = *(u32 *)(r1 +0);"
+		"r2 = le64 r2;"
+		"r0 = r2;"
+		"exit;"
+		::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg(" 8: 0......... (b7) r1 = 1")
+__msg(" 9: 01........ (db) r1 = atomic64_fetch_add((u64 *)(r0 +0), r1)")
+__msg("10: 01........ (c3) lock *(u32 *)(r0 +0) += r1")
+__msg("11: 01........ (db) r1 = atomic64_xchg((u64 *)(r0 +0), r1)")
+__msg("12: 01........ (bf) r2 = r0")
+__msg("13: .12....... (bf) r0 = r1")
+__msg("14: 012....... (db) r0 = atomic64_cmpxchg((u64 *)(r2 +0), r0, r1)")
+__naked void atomic(void)
+{
+	asm volatile (
+		"r2 = r10;"
+		"r2 += -8;"
+		"r1 = 0;"
+		"*(u64 *)(r2 +0) = r1;"
+		"r1 = %[test_map] ll;"
+		"call %[bpf_map_lookup_elem];"
+		"if r0 == 0 goto 1f;"
+		"r1 = 1;"
+		"r1 = atomic_fetch_add((u64 *)(r0 +0), r1);"
+		".8byte %[add_nofetch];" /* same as "lock *(u32 *)(r0 +0) += r1;" */
+		"r1 = xchg_64(r0 + 0, r1);"
+		"r2 = r0;"
+		"r0 = r1;"
+		"r0 = cmpxchg_64(r2 + 0, r0, r1);"
+		"1: exit;"
+		:
+		: __imm(bpf_map_lookup_elem),
+		  __imm_addr(test_map),
+		  __imm_insn(add_nofetch, BPF_ATOMIC_OP(BPF_W, BPF_ADD, BPF_REG_0, BPF_REG_1, 0))
+		: __clobber_all);
+}
+
+#ifdef CAN_USE_LOAD_ACQ_STORE_REL
+
+SEC("socket")
+__log_level(2)
+__msg("2: .12....... (db) store_release((u64 *)(r2 -8), r1)")
+__msg("3: .......... (bf) r3 = r10")
+__msg("4: ...3...... (db) r4 = load_acquire((u64 *)(r3 -8))")
+__naked void atomic_load_acq_store_rel(void)
+{
+	asm volatile (
+		"r1 = 42;"
+		"r2 = r10;"
+		".8byte %[store_release_insn];" /* store_release((u64 *)(r2 - 8), r1); */
+		"r3 = r10;"
+		".8byte %[load_acquire_insn];" /* r4 = load_acquire((u64 *)(r3 + 0)); */
+		"r0 = r4;"
+		"exit;"
+		:
+		: __imm_insn(store_release_insn,
+			     BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_2, BPF_REG_1, -8)),
+		  __imm_insn(load_acquire_insn,
+			     BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_4, BPF_REG_3, -8))
+		: __clobber_all);
+}
+
+#endif /* CAN_USE_LOAD_ACQ_STORE_REL */
+
+SEC("socket")
+__log_level(2)
+__msg("4: .12....7.. (85) call bpf_trace_printk#6")
+__msg("5: 0......7.. (0f) r0 += r7")
+__naked void regular_call(void)
+{
+	asm volatile (
+		"r7 = 1;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 1;"
+		"call %[bpf_trace_printk];"
+		"r0 += r7;"
+		"exit;"
+		:
+		: __imm(bpf_trace_printk)
+		: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("2: 012....... (25) if r1 > 0x7 goto pc+1")
+__msg("3: ..2....... (bf) r0 = r2")
+__naked void if1(void)
+{
+	asm volatile (
+		"r0 = 1;"
+		"r2 = 2;"
+		"if r1 > 0x7 goto +1;"
+		"r0 = r2;"
+		"exit;"
+		::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("3: 0123...... (2d) if r1 > r3 goto pc+1")
+__msg("4: ..2....... (bf) r0 = r2")
+__naked void if2(void)
+{
+	asm volatile (
+		"r0 = 1;"
+		"r2 = 2;"
+		"r3 = 7;"
+		"if r1 > r3 goto +1;"
+		"r0 = r2;"
+		"exit;"
+		::: __clobber_all);
+}
+
+/* Verifier misses that r2 is alive if jset is not handled properly */
+SEC("socket")
+__log_level(2)
+__msg("2: 012....... (45) if r1 & 0x7 goto pc+1")
+__naked void if3_jset_bug(void)
+{
+	asm volatile (
+		"r0 = 1;"
+		"r2 = 2;"
+		"if r1 & 0x7 goto +1;"
+		"exit;"
+		"r0 = r2;"
+		"exit;"
+		::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("0: .......... (b7) r1 = 0")
+__msg("1: .1........ (b7) r2 = 7")
+__msg("2: .12....... (25) if r1 > 0x7 goto pc+4")
+__msg("3: .12....... (07) r1 += 1")
+__msg("4: .12....... (27) r2 *= 2")
+__msg("5: .12....... (05) goto pc+0")
+__msg("6: .12....... (05) goto pc-5")
+__msg("7: .......... (b7) r0 = 0")
+__msg("8: 0......... (95) exit")
+__naked void loop(void)
+{
+	asm volatile (
+		"r1 = 0;"
+		"r2 = 7;"
+		"if r1 > 0x7 goto +4;"
+		"r1 += 1;"
+		"r2 *= 2;"
+		"goto +0;"
+		"goto -5;"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_trace_printk)
+		: __clobber_all);
+}
+
+#ifdef CAN_USE_GOTOL
+SEC("socket")
+__log_level(2)
+__msg("2: .123...... (25) if r1 > 0x7 goto pc+2")
+__msg("3: ..2....... (bf) r0 = r2")
+__msg("4: 0......... (06) gotol pc+1")
+__msg("5: ...3...... (bf) r0 = r3")
+__msg("6: 0......... (95) exit")
+__naked void gotol(void)
+{
+	asm volatile (
+		"r2 = 42;"
+		"r3 = 24;"
+		"if r1 > 0x7 goto +2;"
+		"r0 = r2;"
+		"gotol +1;"
+		"r0 = r3;"
+		"exit;"
+		:
+		: __imm(bpf_trace_printk)
+		: __clobber_all);
+}
+#endif
+
+SEC("socket")
+__log_level(2)
+__msg("0: .......... (b7) r1 = 1")
+__msg("1: .1........ (e5) may_goto pc+1")
+__msg("2: .......... (05) goto pc-3")
+__msg("3: .1........ (bf) r0 = r1")
+__msg("4: 0......... (95) exit")
+__naked void may_goto(void)
+{
+	asm volatile (
+	"1: r1 = 1;"
+	".8byte %[may_goto];"
+	"goto 1b;"
+	"r0 = r1;"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id),
+	  __imm_insn(may_goto, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, +1 /* offset */, 0))
+	: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("1: 0......... (18) r2 = 0x7")
+__msg("3: 0.2....... (0f) r0 += r2")
+__naked void ldimm64(void)
+{
+	asm volatile (
+		"r0 = 0;"
+		"r2 = 0x7 ll;"
+		"r0 += r2;"
+		"exit;"
+		:
+		:: __clobber_all);
+}
+
+/* No rules specific for LD_ABS/LD_IND, default behaviour kicks in */
+SEC("socket")
+__log_level(2)
+__msg("2: 0123456789 (30) r0 = *(u8 *)skb[42]")
+__msg("3: 012.456789 (0f) r7 += r0")
+__msg("4: 012.456789 (b7) r3 = 42")
+__msg("5: 0123456789 (50) r0 = *(u8 *)skb[r3 + 0]")
+__msg("6: 0......7.. (0f) r7 += r0")
+__naked void ldabs(void)
+{
+	asm volatile (
+		"r6 = r1;"
+		"r7 = 0;"
+		"r0 = *(u8 *)skb[42];"
+		"r7 += r0;"
+		"r3 = 42;"
+		".8byte %[ld_ind];" /* same as "r0 = *(u8 *)skb[r3];" */
+		"r7 += r0;"
+		"r0 = r7;"
+		"exit;"
+		:
+		: __imm_insn(ld_ind, BPF_LD_IND(BPF_B, BPF_REG_3, 0))
+		: __clobber_all);
+}
+
+
+#ifdef __BPF_FEATURE_ADDR_SPACE_CAST
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__log_level(2)
+__msg(" 6: .12345.... (85) call bpf_arena_alloc_pages")
+__msg(" 7: 0......... (bf) r1 = addr_space_cast(r0, 0, 1)")
+__msg(" 8: .1........ (b7) r2 = 42")
+__naked void addr_space_cast(void)
+{
+	asm volatile (
+		"r1 = %[arena] ll;"
+		"r2 = 0;"
+		"r3 = 1;"
+		"r4 = 0;"
+		"r5 = 0;"
+		"call %[bpf_arena_alloc_pages];"
+		"r1 = addr_space_cast(r0, 0, 1);"
+		"r2 = 42;"
+		"*(u64 *)(r1 +0) = r2;"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_arena_alloc_pages),
+		  __imm_addr(arena)
+		: __clobber_all);
+}
+#endif
+
+static __used __naked int aux1(void)
+{
+	asm volatile (
+		"r0 = r1;"
+		"r0 += r2;"
+		"exit;"
+		::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("0: ....45.... (b7) r1 = 1")
+__msg("1: .1..45.... (b7) r2 = 2")
+__msg("2: .12.45.... (b7) r3 = 3")
+/* Conservative liveness for subprog parameters. */
+__msg("3: .12345.... (85) call pc+2")
+__msg("4: .......... (b7) r0 = 0")
+__msg("5: 0......... (95) exit")
+__msg("6: .12....... (bf) r0 = r1")
+__msg("7: 0.2....... (0f) r0 += r2")
+/* Conservative liveness for subprog return value. */
+__msg("8: 0......... (95) exit")
+__naked void subprog1(void)
+{
+	asm volatile (
+		"r1 = 1;"
+		"r2 = 2;"
+		"r3 = 3;"
+		"call aux1;"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+
+/* to retain debug info for BTF generation */
+void kfunc_root(void)
+{
+	bpf_arena_alloc_pages(0, 0, 0, 0, 0);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/connect4_dropper.c b/tools/testing/selftests/bpf/progs/connect4_dropper.c
index d3f4c5e4fb69..a3819a5d09c8 100644
--- a/tools/testing/selftests/bpf/progs/connect4_dropper.c
+++ b/tools/testing/selftests/bpf/progs/connect4_dropper.c
@@ -13,12 +13,14 @@
 #define VERDICT_REJECT	0
 #define VERDICT_PROCEED	1
 
+int port;
+
 SEC("cgroup/connect4")
 int connect_v4_dropper(struct bpf_sock_addr *ctx)
 {
 	if (ctx->type != SOCK_STREAM)
 		return VERDICT_PROCEED;
-	if (ctx->user_port == bpf_htons(60120))
+	if (ctx->user_port == bpf_htons(port))
 		return VERDICT_REJECT;
 	return VERDICT_PROCEED;
 }
diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c
index ec25371de789..9d158cfad981 100644
--- a/tools/testing/selftests/bpf/progs/connect4_prog.c
+++ b/tools/testing/selftests/bpf/progs/connect4_prog.c
@@ -14,8 +14,6 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
-#include "bpf_tcp_helpers.h"
-
 #define SRC_REWRITE_IP4		0x7f000004U
 #define DST_REWRITE_IP4		0x7f000001U
 #define DST_REWRITE_PORT4	4444
@@ -32,7 +30,14 @@
 #define IFNAMSIZ 16
 #endif
 
-__attribute__ ((noinline))
+#ifndef SOL_TCP
+#define SOL_TCP 6
+#endif
+
+const char reno[] = "reno";
+const char cubic[] = "cubic";
+
+__attribute__ ((noinline)) __weak
 int do_bind(struct bpf_sock_addr *ctx)
 {
 	struct sockaddr_in sa = {};
@@ -48,35 +53,27 @@ int do_bind(struct bpf_sock_addr *ctx)
 }
 
 static __inline int verify_cc(struct bpf_sock_addr *ctx,
-			      char expected[TCP_CA_NAME_MAX])
+			      const char expected[])
 {
 	char buf[TCP_CA_NAME_MAX];
-	int i;
 
 	if (bpf_getsockopt(ctx, SOL_TCP, TCP_CONGESTION, &buf, sizeof(buf)))
 		return 1;
 
-	for (i = 0; i < TCP_CA_NAME_MAX; i++) {
-		if (buf[i] != expected[i])
-			return 1;
-		if (buf[i] == 0)
-			break;
-	}
+	if (bpf_strncmp(buf, TCP_CA_NAME_MAX, expected))
+		return 1;
 
 	return 0;
 }
 
 static __inline int set_cc(struct bpf_sock_addr *ctx)
 {
-	char reno[TCP_CA_NAME_MAX] = "reno";
-	char cubic[TCP_CA_NAME_MAX] = "cubic";
-
-	if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &reno, sizeof(reno)))
+	if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, (void *)reno, sizeof(reno)))
 		return 1;
 	if (verify_cc(ctx, reno))
 		return 1;
 
-	if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, &cubic, sizeof(cubic)))
+	if (bpf_setsockopt(ctx, SOL_TCP, TCP_CONGESTION, (void *)cubic, sizeof(cubic)))
 		return 1;
 	if (verify_cc(ctx, cubic))
 		return 1;
@@ -197,4 +194,10 @@ int connect_v4_prog(struct bpf_sock_addr *ctx)
 	return do_bind(ctx) ? 1 : 0;
 }
 
+SEC("cgroup/connect4")
+int connect_v4_deny_prog(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/connect6_prog.c b/tools/testing/selftests/bpf/progs/connect6_prog.c
index 40266d2c737c..e98573b00ddb 100644
--- a/tools/testing/selftests/bpf/progs/connect6_prog.c
+++ b/tools/testing/selftests/bpf/progs/connect6_prog.c
@@ -90,4 +90,10 @@ int connect_v6_prog(struct bpf_sock_addr *ctx)
 	return 1;
 }
 
+SEC("cgroup/connect6")
+int connect_v6_deny_prog(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/connect_unix_prog.c b/tools/testing/selftests/bpf/progs/connect_unix_prog.c
new file mode 100644
index 000000000000..ba60adadb335
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/connect_unix_prog.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+
+#include <string.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_kfuncs.h"
+
+__u8 SERVUN_REWRITE_ADDRESS[] = "\0bpf_cgroup_unix_test_rewrite";
+
+SEC("cgroup/connect_unix")
+int connect_unix_prog(struct bpf_sock_addr *ctx)
+{
+	struct bpf_sock_addr_kern *sa_kern = bpf_cast_to_kern_ctx(ctx);
+	struct sockaddr_un *sa_kern_unaddr;
+	__u32 unaddrlen = offsetof(struct sockaddr_un, sun_path) +
+			  sizeof(SERVUN_REWRITE_ADDRESS) - 1;
+	int ret;
+
+	/* Rewrite destination. */
+	ret = bpf_sock_addr_set_sun_path(sa_kern, SERVUN_REWRITE_ADDRESS,
+					 sizeof(SERVUN_REWRITE_ADDRESS) - 1);
+	if (ret)
+		return 0;
+
+	if (sa_kern->uaddrlen != unaddrlen)
+		return 0;
+
+	sa_kern_unaddr = bpf_core_cast(sa_kern->uaddr, struct sockaddr_un);
+	if (memcmp(sa_kern_unaddr->sun_path, SERVUN_REWRITE_ADDRESS,
+			sizeof(SERVUN_REWRITE_ADDRESS) - 1) != 0)
+		return 0;
+
+	return 1;
+}
+
+SEC("cgroup/connect_unix")
+int connect_unix_deny_prog(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/core_kern.c b/tools/testing/selftests/bpf/progs/core_kern.c
index 2715fe27d4cf..004f2acef2eb 100644
--- a/tools/testing/selftests/bpf/progs/core_kern.c
+++ b/tools/testing/selftests/bpf/progs/core_kern.c
@@ -77,7 +77,7 @@ int balancer_ingress(struct __sk_buff *ctx)
 	void *data_end = (void *)(long)ctx->data_end;
 	void *data = (void *)(long)ctx->data;
 	void *ptr;
-	int ret = 0, nh_off, i = 0;
+	int nh_off, i = 0;
 
 	nh_off = 14;
 
diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h
index fd8e1b4c6762..5760ae015e09 100644
--- a/tools/testing/selftests/bpf/progs/core_reloc_types.h
+++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h
@@ -347,6 +347,7 @@ struct core_reloc_nesting___err_too_deep {
  */
 struct core_reloc_arrays_output {
 	int a2;
+	int a3;
 	char b123;
 	int c1c;
 	int d00d;
@@ -455,6 +456,15 @@ struct core_reloc_arrays___err_bad_zero_sz_arr {
 	struct core_reloc_arrays_substruct d[1][2];
 };
 
+struct core_reloc_arrays___err_bad_signed_arr_elem_sz {
+	/* int -> short (signed!): not supported case */
+	short a[5];
+	char b[2][3][4];
+	struct core_reloc_arrays_substruct c[3];
+	struct core_reloc_arrays_substruct d[1][2];
+	struct core_reloc_arrays_substruct f[][2];
+};
+
 /*
  * PRIMITIVES
  */
diff --git a/tools/testing/selftests/bpf/progs/cpumask_common.h b/tools/testing/selftests/bpf/progs/cpumask_common.h
new file mode 100644
index 000000000000..86085b79f5ca
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cpumask_common.h
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#ifndef _CPUMASK_COMMON_H
+#define _CPUMASK_COMMON_H
+
+#include "errno.h"
+#include <stdbool.h>
+
+/* Should use BTF_FIELDS_MAX, but it is not always available in vmlinux.h,
+ * so use the hard-coded number as a workaround.
+ */
+#define CPUMASK_KPTR_FIELDS_MAX 11
+
+int err;
+
+#define private(name) SEC(".bss." #name) __attribute__((aligned(8)))
+private(MASK) static struct bpf_cpumask __kptr * global_mask;
+
+struct __cpumask_map_value {
+	struct bpf_cpumask __kptr * cpumask;
+};
+
+struct array_map {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct __cpumask_map_value);
+	__uint(max_entries, 1);
+} __cpumask_map SEC(".maps");
+
+struct bpf_cpumask *bpf_cpumask_create(void) __ksym __weak;
+void bpf_cpumask_release(struct bpf_cpumask *cpumask) __ksym __weak;
+struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask) __ksym __weak;
+u32 bpf_cpumask_first(const struct cpumask *cpumask) __ksym __weak;
+u32 bpf_cpumask_first_zero(const struct cpumask *cpumask) __ksym __weak;
+u32 bpf_cpumask_first_and(const struct cpumask *src1,
+			  const struct cpumask *src2) __ksym __weak;
+void bpf_cpumask_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym __weak;
+void bpf_cpumask_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym __weak;
+bool bpf_cpumask_test_cpu(u32 cpu, const struct cpumask *cpumask) __ksym __weak;
+bool bpf_cpumask_test_and_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym __weak;
+bool bpf_cpumask_test_and_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) __ksym __weak;
+void bpf_cpumask_setall(struct bpf_cpumask *cpumask) __ksym __weak;
+void bpf_cpumask_clear(struct bpf_cpumask *cpumask) __ksym __weak;
+bool bpf_cpumask_and(struct bpf_cpumask *cpumask,
+		     const struct cpumask *src1,
+		     const struct cpumask *src2) __ksym __weak;
+void bpf_cpumask_or(struct bpf_cpumask *cpumask,
+		    const struct cpumask *src1,
+		    const struct cpumask *src2) __ksym __weak;
+void bpf_cpumask_xor(struct bpf_cpumask *cpumask,
+		     const struct cpumask *src1,
+		     const struct cpumask *src2) __ksym __weak;
+bool bpf_cpumask_equal(const struct cpumask *src1, const struct cpumask *src2) __ksym __weak;
+bool bpf_cpumask_intersects(const struct cpumask *src1, const struct cpumask *src2) __ksym __weak;
+bool bpf_cpumask_subset(const struct cpumask *src1, const struct cpumask *src2) __ksym __weak;
+bool bpf_cpumask_empty(const struct cpumask *cpumask) __ksym __weak;
+bool bpf_cpumask_full(const struct cpumask *cpumask) __ksym __weak;
+void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) __ksym __weak;
+u32 bpf_cpumask_any_distribute(const struct cpumask *src) __ksym __weak;
+u32 bpf_cpumask_any_and_distribute(const struct cpumask *src1,
+				   const struct cpumask *src2) __ksym __weak;
+u32 bpf_cpumask_weight(const struct cpumask *cpumask) __ksym __weak;
+int bpf_cpumask_populate(struct cpumask *cpumask, void *src, size_t src__sz) __ksym __weak;
+
+void bpf_rcu_read_lock(void) __ksym __weak;
+void bpf_rcu_read_unlock(void) __ksym __weak;
+
+static inline const struct cpumask *cast(struct bpf_cpumask *cpumask)
+{
+	return (const struct cpumask *)cpumask;
+}
+
+static inline struct bpf_cpumask *create_cpumask(void)
+{
+	struct bpf_cpumask *cpumask;
+
+	cpumask = bpf_cpumask_create();
+	if (!cpumask) {
+		err = 1;
+		return NULL;
+	}
+
+	if (!bpf_cpumask_empty(cast(cpumask))) {
+		err = 2;
+		bpf_cpumask_release(cpumask);
+		return NULL;
+	}
+
+	return cpumask;
+}
+
+static inline struct __cpumask_map_value *cpumask_map_value_lookup(void)
+{
+	u32 key = 0;
+
+	return bpf_map_lookup_elem(&__cpumask_map, &key);
+}
+
+static inline int cpumask_map_insert(struct bpf_cpumask *mask)
+{
+	struct __cpumask_map_value local, *v;
+	long status;
+	struct bpf_cpumask *old;
+	u32 key = 0;
+
+	local.cpumask = NULL;
+	status = bpf_map_update_elem(&__cpumask_map, &key, &local, 0);
+	if (status) {
+		bpf_cpumask_release(mask);
+		return status;
+	}
+
+	v = bpf_map_lookup_elem(&__cpumask_map, &key);
+	if (!v) {
+		bpf_cpumask_release(mask);
+		return -ENOENT;
+	}
+
+	old = bpf_kptr_xchg(&v->cpumask, mask);
+	if (old) {
+		bpf_cpumask_release(old);
+		return -EEXIST;
+	}
+
+	return 0;
+}
+
+#endif /* _CPUMASK_COMMON_H */
diff --git a/tools/testing/selftests/bpf/progs/cpumask_failure.c b/tools/testing/selftests/bpf/progs/cpumask_failure.c
new file mode 100644
index 000000000000..8a2fd596c8a3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cpumask_failure.c
@@ -0,0 +1,262 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#include "cpumask_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct kptr_nested_array_2 {
+	struct bpf_cpumask __kptr * mask;
+};
+
+struct kptr_nested_array_1 {
+	/* Make btf_parse_fields() in map_create() return -E2BIG */
+	struct kptr_nested_array_2 d_2[CPUMASK_KPTR_FIELDS_MAX + 1];
+};
+
+struct kptr_nested_array {
+	struct kptr_nested_array_1 d_1;
+};
+
+private(MASK_NESTED) static struct kptr_nested_array global_mask_nested_arr;
+
+/* Prototype for all of the program trace events below:
+ *
+ * TRACE_EVENT(task_newtask,
+ *         TP_PROTO(struct task_struct *p, u64 clone_flags)
+ */
+
+SEC("tp_btf/task_newtask")
+__failure __msg("Unreleased reference")
+int BPF_PROG(test_alloc_no_release, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+
+	cpumask = create_cpumask();
+	__sink(cpumask);
+
+	/* cpumask is never released. */
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("NULL pointer passed to trusted arg0")
+int BPF_PROG(test_alloc_double_release, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+
+	cpumask = create_cpumask();
+
+	/* cpumask is released twice. */
+	bpf_cpumask_release(cpumask);
+	bpf_cpumask_release(cpumask);
+
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("must be referenced")
+int BPF_PROG(test_acquire_wrong_cpumask, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+
+	/* Can't acquire a non-struct bpf_cpumask. */
+	cpumask = bpf_cpumask_acquire((struct bpf_cpumask *)task->cpus_ptr);
+	__sink(cpumask);
+
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("bpf_cpumask_set_cpu args#1 expected pointer to STRUCT bpf_cpumask")
+int BPF_PROG(test_mutate_cpumask, struct task_struct *task, u64 clone_flags)
+{
+	/* Can't set the CPU of a non-struct bpf_cpumask. */
+	bpf_cpumask_set_cpu(0, (struct bpf_cpumask *)task->cpus_ptr);
+
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("Unreleased reference")
+int BPF_PROG(test_insert_remove_no_release, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+	struct __cpumask_map_value *v;
+
+	cpumask = create_cpumask();
+	if (!cpumask)
+		return 0;
+
+	if (cpumask_map_insert(cpumask))
+		return 0;
+
+	v = cpumask_map_value_lookup();
+	if (!v)
+		return 0;
+
+	cpumask = bpf_kptr_xchg(&v->cpumask, NULL);
+
+	/* cpumask is never released. */
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("NULL pointer passed to trusted arg0")
+int BPF_PROG(test_cpumask_null, struct task_struct *task, u64 clone_flags)
+{
+  /* NULL passed to KF_TRUSTED_ARGS kfunc. */
+	bpf_cpumask_empty(NULL);
+
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("R2 must be a rcu pointer")
+int BPF_PROG(test_global_mask_out_of_rcu, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *local, *prev;
+
+	local = create_cpumask();
+	if (!local)
+		return 0;
+
+	prev = bpf_kptr_xchg(&global_mask, local);
+	if (prev) {
+		bpf_cpumask_release(prev);
+		err = 3;
+		return 0;
+	}
+
+	bpf_rcu_read_lock();
+	local = global_mask;
+	if (!local) {
+		err = 4;
+		bpf_rcu_read_unlock();
+		return 0;
+	}
+
+	bpf_rcu_read_unlock();
+
+	/* RCU region is exited before calling KF_RCU kfunc. */
+
+	bpf_cpumask_test_cpu(0, (const struct cpumask *)local);
+
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("NULL pointer passed to trusted arg1")
+int BPF_PROG(test_global_mask_no_null_check, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *local, *prev;
+
+	local = create_cpumask();
+	if (!local)
+		return 0;
+
+	prev = bpf_kptr_xchg(&global_mask, local);
+	if (prev) {
+		bpf_cpumask_release(prev);
+		err = 3;
+		return 0;
+	}
+
+	bpf_rcu_read_lock();
+	local = global_mask;
+
+	/* No NULL check is performed on global cpumask kptr. */
+	bpf_cpumask_test_cpu(0, (const struct cpumask *)local);
+
+	bpf_rcu_read_unlock();
+
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("Possibly NULL pointer passed to helper arg2")
+int BPF_PROG(test_global_mask_rcu_no_null_check, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *prev, *curr;
+
+	curr = bpf_cpumask_create();
+	if (!curr)
+		return 0;
+
+	prev = bpf_kptr_xchg(&global_mask, curr);
+	if (prev)
+		bpf_cpumask_release(prev);
+
+	bpf_rcu_read_lock();
+	curr = global_mask;
+	/* PTR_TO_BTF_ID | PTR_MAYBE_NULL | MEM_RCU passed to bpf_kptr_xchg() */
+	prev = bpf_kptr_xchg(&global_mask, curr);
+	bpf_rcu_read_unlock();
+	if (prev)
+		bpf_cpumask_release(prev);
+
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("has no valid kptr")
+int BPF_PROG(test_invalid_nested_array, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *local, *prev;
+
+	local = create_cpumask();
+	if (!local)
+		return 0;
+
+	prev = bpf_kptr_xchg(&global_mask_nested_arr.d_1.d_2[CPUMASK_KPTR_FIELDS_MAX].mask, local);
+	if (prev) {
+		bpf_cpumask_release(prev);
+		err = 3;
+		return 0;
+	}
+
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("type=scalar expected=fp")
+int BPF_PROG(test_populate_invalid_destination, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *invalid = (struct bpf_cpumask *)0x123456;
+	u64 bits;
+	int ret;
+
+	ret = bpf_cpumask_populate((struct cpumask *)invalid, &bits, sizeof(bits));
+	if (!ret)
+		err = 2;
+
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("leads to invalid memory access")
+int BPF_PROG(test_populate_invalid_source, struct task_struct *task, u64 clone_flags)
+{
+	void *garbage = (void *)0x123456;
+	struct bpf_cpumask *local;
+	int ret;
+
+	local = create_cpumask();
+	if (!local) {
+		err = 1;
+		return 0;
+	}
+
+	ret = bpf_cpumask_populate((struct cpumask *)local, garbage, 8);
+	if (!ret)
+		err = 2;
+
+	bpf_cpumask_release(local);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/cpumask_success.c b/tools/testing/selftests/bpf/progs/cpumask_success.c
new file mode 100644
index 000000000000..0e04c31b91c0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cpumask_success.c
@@ -0,0 +1,890 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+#include "cpumask_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+int pid, nr_cpus;
+
+struct kptr_nested {
+	struct bpf_cpumask __kptr * mask;
+};
+
+struct kptr_nested_pair {
+	struct bpf_cpumask __kptr * mask_1;
+	struct bpf_cpumask __kptr * mask_2;
+};
+
+struct kptr_nested_mid {
+	int dummy;
+	struct kptr_nested m;
+};
+
+struct kptr_nested_deep {
+	struct kptr_nested_mid ptrs[2];
+	struct kptr_nested_pair ptr_pairs[3];
+};
+
+struct kptr_nested_deep_array_1_2 {
+	int dummy;
+	struct bpf_cpumask __kptr * mask[CPUMASK_KPTR_FIELDS_MAX];
+};
+
+struct kptr_nested_deep_array_1_1 {
+	int dummy;
+	struct kptr_nested_deep_array_1_2 d_2;
+};
+
+struct kptr_nested_deep_array_1 {
+	long dummy;
+	struct kptr_nested_deep_array_1_1 d_1;
+};
+
+struct kptr_nested_deep_array_2_2 {
+	long dummy[2];
+	struct bpf_cpumask __kptr * mask;
+};
+
+struct kptr_nested_deep_array_2_1 {
+	int dummy;
+	struct kptr_nested_deep_array_2_2 d_2[CPUMASK_KPTR_FIELDS_MAX];
+};
+
+struct kptr_nested_deep_array_2 {
+	long dummy;
+	struct kptr_nested_deep_array_2_1 d_1;
+};
+
+struct kptr_nested_deep_array_3_2 {
+	long dummy[2];
+	struct bpf_cpumask __kptr * mask;
+};
+
+struct kptr_nested_deep_array_3_1 {
+	int dummy;
+	struct kptr_nested_deep_array_3_2 d_2;
+};
+
+struct kptr_nested_deep_array_3 {
+	long dummy;
+	struct kptr_nested_deep_array_3_1 d_1[CPUMASK_KPTR_FIELDS_MAX];
+};
+
+private(MASK) static struct bpf_cpumask __kptr * global_mask_array[2];
+private(MASK) static struct bpf_cpumask __kptr * global_mask_array_l2[2][1];
+private(MASK) static struct bpf_cpumask __kptr * global_mask_array_one[1];
+private(MASK) static struct kptr_nested global_mask_nested[2];
+private(MASK_DEEP) static struct kptr_nested_deep global_mask_nested_deep;
+private(MASK_1) static struct kptr_nested_deep_array_1 global_mask_nested_deep_array_1;
+private(MASK_2) static struct kptr_nested_deep_array_2 global_mask_nested_deep_array_2;
+private(MASK_3) static struct kptr_nested_deep_array_3 global_mask_nested_deep_array_3;
+
+static bool is_test_task(void)
+{
+	int cur_pid = bpf_get_current_pid_tgid() >> 32;
+
+	return pid == cur_pid;
+}
+
+static bool create_cpumask_set(struct bpf_cpumask **out1,
+			       struct bpf_cpumask **out2,
+			       struct bpf_cpumask **out3,
+			       struct bpf_cpumask **out4)
+{
+	struct bpf_cpumask *mask1, *mask2, *mask3, *mask4;
+
+	mask1 = create_cpumask();
+	if (!mask1)
+		return false;
+
+	mask2 = create_cpumask();
+	if (!mask2) {
+		bpf_cpumask_release(mask1);
+		err = 3;
+		return false;
+	}
+
+	mask3 = create_cpumask();
+	if (!mask3) {
+		bpf_cpumask_release(mask1);
+		bpf_cpumask_release(mask2);
+		err = 4;
+		return false;
+	}
+
+	mask4 = create_cpumask();
+	if (!mask4) {
+		bpf_cpumask_release(mask1);
+		bpf_cpumask_release(mask2);
+		bpf_cpumask_release(mask3);
+		err = 5;
+		return false;
+	}
+
+	*out1 = mask1;
+	*out2 = mask2;
+	*out3 = mask3;
+	*out4 = mask4;
+
+	return true;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_alloc_free_cpumask, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+
+	if (!is_test_task())
+		return 0;
+
+	cpumask = create_cpumask();
+	if (!cpumask)
+		return 0;
+
+	bpf_cpumask_release(cpumask);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_set_clear_cpu, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+
+	if (!is_test_task())
+		return 0;
+
+	cpumask = create_cpumask();
+	if (!cpumask)
+		return 0;
+
+	bpf_cpumask_set_cpu(0, cpumask);
+	if (!bpf_cpumask_test_cpu(0, cast(cpumask))) {
+		err = 3;
+		goto release_exit;
+	}
+
+	bpf_cpumask_clear_cpu(0, cpumask);
+	if (bpf_cpumask_test_cpu(0, cast(cpumask))) {
+		err = 4;
+		goto release_exit;
+	}
+
+release_exit:
+	bpf_cpumask_release(cpumask);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_setall_clear_cpu, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+
+	if (!is_test_task())
+		return 0;
+
+	cpumask = create_cpumask();
+	if (!cpumask)
+		return 0;
+
+	bpf_cpumask_setall(cpumask);
+	if (!bpf_cpumask_full(cast(cpumask))) {
+		err = 3;
+		goto release_exit;
+	}
+
+	bpf_cpumask_clear(cpumask);
+	if (!bpf_cpumask_empty(cast(cpumask))) {
+		err = 4;
+		goto release_exit;
+	}
+
+release_exit:
+	bpf_cpumask_release(cpumask);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_first_firstzero_cpu, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+
+	if (!is_test_task())
+		return 0;
+
+	cpumask = create_cpumask();
+	if (!cpumask)
+		return 0;
+
+	if (bpf_cpumask_first(cast(cpumask)) < nr_cpus) {
+		err = 3;
+		goto release_exit;
+	}
+
+	if (bpf_cpumask_first_zero(cast(cpumask)) != 0) {
+		bpf_printk("first zero: %d", bpf_cpumask_first_zero(cast(cpumask)));
+		err = 4;
+		goto release_exit;
+	}
+
+	bpf_cpumask_set_cpu(0, cpumask);
+	if (bpf_cpumask_first(cast(cpumask)) != 0) {
+		err = 5;
+		goto release_exit;
+	}
+
+	if (bpf_cpumask_first_zero(cast(cpumask)) != 1) {
+		err = 6;
+		goto release_exit;
+	}
+
+release_exit:
+	bpf_cpumask_release(cpumask);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_firstand_nocpu, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *mask1, *mask2;
+	u32 first;
+
+	if (!is_test_task())
+		return 0;
+
+	mask1 = create_cpumask();
+	if (!mask1)
+		return 0;
+
+	mask2 = create_cpumask();
+	if (!mask2)
+		goto release_exit;
+
+	bpf_cpumask_set_cpu(0, mask1);
+	bpf_cpumask_set_cpu(1, mask2);
+
+	first = bpf_cpumask_first_and(cast(mask1), cast(mask2));
+	if (first <= 1)
+		err = 3;
+
+release_exit:
+	if (mask1)
+		bpf_cpumask_release(mask1);
+	if (mask2)
+		bpf_cpumask_release(mask2);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_test_and_set_clear, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+
+	if (!is_test_task())
+		return 0;
+
+	cpumask = create_cpumask();
+	if (!cpumask)
+		return 0;
+
+	if (bpf_cpumask_test_and_set_cpu(0, cpumask)) {
+		err = 3;
+		goto release_exit;
+	}
+
+	if (!bpf_cpumask_test_and_set_cpu(0, cpumask)) {
+		err = 4;
+		goto release_exit;
+	}
+
+	if (!bpf_cpumask_test_and_clear_cpu(0, cpumask)) {
+		err = 5;
+		goto release_exit;
+	}
+
+release_exit:
+	bpf_cpumask_release(cpumask);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_and_or_xor, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *mask1, *mask2, *dst1, *dst2;
+
+	if (!is_test_task())
+		return 0;
+
+	if (!create_cpumask_set(&mask1, &mask2, &dst1, &dst2))
+		return 0;
+
+	bpf_cpumask_set_cpu(0, mask1);
+	bpf_cpumask_set_cpu(1, mask2);
+
+	if (bpf_cpumask_and(dst1, cast(mask1), cast(mask2))) {
+		err = 6;
+		goto release_exit;
+	}
+	if (!bpf_cpumask_empty(cast(dst1))) {
+		err = 7;
+		goto release_exit;
+	}
+
+	bpf_cpumask_or(dst1, cast(mask1), cast(mask2));
+	if (!bpf_cpumask_test_cpu(0, cast(dst1))) {
+		err = 8;
+		goto release_exit;
+	}
+	if (!bpf_cpumask_test_cpu(1, cast(dst1))) {
+		err = 9;
+		goto release_exit;
+	}
+
+	bpf_cpumask_xor(dst2, cast(mask1), cast(mask2));
+	if (!bpf_cpumask_equal(cast(dst1), cast(dst2))) {
+		err = 10;
+		goto release_exit;
+	}
+
+release_exit:
+	bpf_cpumask_release(mask1);
+	bpf_cpumask_release(mask2);
+	bpf_cpumask_release(dst1);
+	bpf_cpumask_release(dst2);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_intersects_subset, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *mask1, *mask2, *dst1, *dst2;
+
+	if (!is_test_task())
+		return 0;
+
+	if (!create_cpumask_set(&mask1, &mask2, &dst1, &dst2))
+		return 0;
+
+	bpf_cpumask_set_cpu(0, mask1);
+	bpf_cpumask_set_cpu(1, mask2);
+	if (bpf_cpumask_intersects(cast(mask1), cast(mask2))) {
+		err = 6;
+		goto release_exit;
+	}
+
+	bpf_cpumask_or(dst1, cast(mask1), cast(mask2));
+	if (!bpf_cpumask_subset(cast(mask1), cast(dst1))) {
+		err = 7;
+		goto release_exit;
+	}
+
+	if (!bpf_cpumask_subset(cast(mask2), cast(dst1))) {
+		err = 8;
+		goto release_exit;
+	}
+
+	if (bpf_cpumask_subset(cast(dst1), cast(mask1))) {
+		err = 9;
+		goto release_exit;
+	}
+
+release_exit:
+	bpf_cpumask_release(mask1);
+	bpf_cpumask_release(mask2);
+	bpf_cpumask_release(dst1);
+	bpf_cpumask_release(dst2);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_copy_any_anyand, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *mask1, *mask2, *dst1, *dst2;
+	int cpu;
+
+	if (!is_test_task())
+		return 0;
+
+	if (!create_cpumask_set(&mask1, &mask2, &dst1, &dst2))
+		return 0;
+
+	bpf_cpumask_set_cpu(0, mask1);
+	bpf_cpumask_set_cpu(1, mask2);
+	bpf_cpumask_or(dst1, cast(mask1), cast(mask2));
+
+	cpu = bpf_cpumask_any_distribute(cast(mask1));
+	if (cpu != 0) {
+		err = 6;
+		goto release_exit;
+	}
+
+	cpu = bpf_cpumask_any_distribute(cast(dst2));
+	if (cpu < nr_cpus) {
+		err = 7;
+		goto release_exit;
+	}
+
+	bpf_cpumask_copy(dst2, cast(dst1));
+	if (!bpf_cpumask_equal(cast(dst1), cast(dst2))) {
+		err = 8;
+		goto release_exit;
+	}
+
+	cpu = bpf_cpumask_any_distribute(cast(dst2));
+	if (cpu > 1) {
+		err = 9;
+		goto release_exit;
+	}
+
+	cpu = bpf_cpumask_any_and_distribute(cast(mask1), cast(mask2));
+	if (cpu < nr_cpus) {
+		err = 10;
+		goto release_exit;
+	}
+
+release_exit:
+	bpf_cpumask_release(mask1);
+	bpf_cpumask_release(mask2);
+	bpf_cpumask_release(dst1);
+	bpf_cpumask_release(dst2);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_insert_leave, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+
+	cpumask = create_cpumask();
+	if (!cpumask)
+		return 0;
+
+	if (cpumask_map_insert(cpumask))
+		err = 3;
+
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_insert_remove_release, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *cpumask;
+	struct __cpumask_map_value *v;
+
+	cpumask = create_cpumask();
+	if (!cpumask)
+		return 0;
+
+	if (cpumask_map_insert(cpumask)) {
+		err = 3;
+		return 0;
+	}
+
+	v = cpumask_map_value_lookup();
+	if (!v) {
+		err = 4;
+		return 0;
+	}
+
+	cpumask = bpf_kptr_xchg(&v->cpumask, NULL);
+	if (cpumask)
+		bpf_cpumask_release(cpumask);
+	else
+		err = 5;
+
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_global_mask_rcu, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *local, *prev;
+
+	if (!is_test_task())
+		return 0;
+
+	local = create_cpumask();
+	if (!local)
+		return 0;
+
+	prev = bpf_kptr_xchg(&global_mask, local);
+	if (prev) {
+		bpf_cpumask_release(prev);
+		err = 3;
+		return 0;
+	}
+
+	bpf_rcu_read_lock();
+	local = global_mask;
+	if (!local) {
+		err = 4;
+		bpf_rcu_read_unlock();
+		return 0;
+	}
+
+	bpf_cpumask_test_cpu(0, (const struct cpumask *)local);
+	bpf_rcu_read_unlock();
+
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_global_mask_array_one_rcu, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *local, *prev;
+
+	if (!is_test_task())
+		return 0;
+
+	/* Kptr arrays with one element are special cased, being treated
+	 * just like a single pointer.
+	 */
+
+	local = create_cpumask();
+	if (!local)
+		return 0;
+
+	prev = bpf_kptr_xchg(&global_mask_array_one[0], local);
+	if (prev) {
+		bpf_cpumask_release(prev);
+		err = 3;
+		return 0;
+	}
+
+	bpf_rcu_read_lock();
+	local = global_mask_array_one[0];
+	if (!local) {
+		err = 4;
+		bpf_rcu_read_unlock();
+		return 0;
+	}
+
+	bpf_rcu_read_unlock();
+
+	return 0;
+}
+
+static int _global_mask_array_rcu(struct bpf_cpumask **mask0,
+				  struct bpf_cpumask **mask1)
+{
+	struct bpf_cpumask *local;
+
+	if (!is_test_task())
+		return 0;
+
+	/* Check if two kptrs in the array work and independently */
+
+	local = create_cpumask();
+	if (!local)
+		return 0;
+
+	bpf_rcu_read_lock();
+
+	local = bpf_kptr_xchg(mask0, local);
+	if (local) {
+		err = 1;
+		goto err_exit;
+	}
+
+	/* [<mask 0>, *] */
+	if (!*mask0) {
+		err = 2;
+		goto err_exit;
+	}
+
+	if (!mask1)
+		goto err_exit;
+
+	/* [*, NULL] */
+	if (*mask1) {
+		err = 3;
+		goto err_exit;
+	}
+
+	local = create_cpumask();
+	if (!local) {
+		err = 9;
+		goto err_exit;
+	}
+
+	local = bpf_kptr_xchg(mask1, local);
+	if (local) {
+		err = 10;
+		goto err_exit;
+	}
+
+	/* [<mask 0>, <mask 1>] */
+	if (!*mask0 || !*mask1 || *mask0 == *mask1) {
+		err = 11;
+		goto err_exit;
+	}
+
+err_exit:
+	if (local)
+		bpf_cpumask_release(local);
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_global_mask_array_rcu, struct task_struct *task, u64 clone_flags)
+{
+	return _global_mask_array_rcu(&global_mask_array[0], &global_mask_array[1]);
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_global_mask_array_l2_rcu, struct task_struct *task, u64 clone_flags)
+{
+	return _global_mask_array_rcu(&global_mask_array_l2[0][0], &global_mask_array_l2[1][0]);
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_global_mask_nested_rcu, struct task_struct *task, u64 clone_flags)
+{
+	return _global_mask_array_rcu(&global_mask_nested[0].mask, &global_mask_nested[1].mask);
+}
+
+/* Ensure that the field->offset has been correctly advanced from one
+ * nested struct or array sub-tree to another. In the case of
+ * kptr_nested_deep, it comprises two sub-trees: ktpr_1 and kptr_2.  By
+ * calling bpf_kptr_xchg() on every single kptr in both nested sub-trees,
+ * the verifier should reject the program if the field->offset of any kptr
+ * is incorrect.
+ *
+ * For instance, if we have 10 kptrs in a nested struct and a program that
+ * accesses each kptr individually with bpf_kptr_xchg(), the compiler
+ * should emit instructions to access 10 different offsets if it works
+ * correctly. If the field->offset values of any pair of them are
+ * incorrectly the same, the number of unique offsets in btf_record for
+ * this nested struct should be less than 10. The verifier should fail to
+ * discover some of the offsets emitted by the compiler.
+ *
+ * Even if the field->offset values of kptrs are not duplicated, the
+ * verifier should fail to find a btf_field for the instruction accessing a
+ * kptr if the corresponding field->offset is pointing to a random
+ * incorrect offset.
+ */
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_global_mask_nested_deep_rcu, struct task_struct *task, u64 clone_flags)
+{
+	int r, i;
+
+	r = _global_mask_array_rcu(&global_mask_nested_deep.ptrs[0].m.mask,
+				   &global_mask_nested_deep.ptrs[1].m.mask);
+	if (r)
+		return r;
+
+	for (i = 0; i < 3; i++) {
+		r = _global_mask_array_rcu(&global_mask_nested_deep.ptr_pairs[i].mask_1,
+					   &global_mask_nested_deep.ptr_pairs[i].mask_2);
+		if (r)
+			return r;
+	}
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_global_mask_nested_deep_array_rcu, struct task_struct *task, u64 clone_flags)
+{
+	int i;
+
+	for (i = 0; i < CPUMASK_KPTR_FIELDS_MAX; i++)
+		_global_mask_array_rcu(&global_mask_nested_deep_array_1.d_1.d_2.mask[i], NULL);
+
+	for (i = 0; i < CPUMASK_KPTR_FIELDS_MAX; i++)
+		_global_mask_array_rcu(&global_mask_nested_deep_array_2.d_1.d_2[i].mask, NULL);
+
+	for (i = 0; i < CPUMASK_KPTR_FIELDS_MAX; i++)
+		_global_mask_array_rcu(&global_mask_nested_deep_array_3.d_1[i].d_2.mask, NULL);
+
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_cpumask_weight, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *local;
+
+	if (!is_test_task())
+		return 0;
+
+	local = create_cpumask();
+	if (!local)
+		return 0;
+
+	if (bpf_cpumask_weight(cast(local)) != 0) {
+		err = 3;
+		goto out;
+	}
+
+	bpf_cpumask_set_cpu(0, local);
+	if (bpf_cpumask_weight(cast(local)) != 1) {
+		err = 4;
+		goto out;
+	}
+
+	/*
+	 * Make sure that adding additional CPUs changes the weight. Test to
+	 * see whether the CPU was set to account for running on UP machines.
+	 */
+	bpf_cpumask_set_cpu(1, local);
+	if (bpf_cpumask_test_cpu(1, cast(local)) && bpf_cpumask_weight(cast(local)) != 2) {
+		err = 5;
+		goto out;
+	}
+
+	bpf_cpumask_clear(local);
+	if (bpf_cpumask_weight(cast(local)) != 0) {
+		err = 6;
+		goto out;
+	}
+out:
+	bpf_cpumask_release(local);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_refcount_null_tracking, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *mask1, *mask2;
+
+	mask1 = bpf_cpumask_create();
+	mask2 = bpf_cpumask_create();
+
+	if (!mask1 || !mask2)
+		goto free_masks_return;
+
+	bpf_cpumask_test_cpu(0, (const struct cpumask *)mask1);
+	bpf_cpumask_test_cpu(0, (const struct cpumask *)mask2);
+
+free_masks_return:
+	if (mask1)
+		bpf_cpumask_release(mask1);
+	if (mask2)
+		bpf_cpumask_release(mask2);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_populate_reject_small_mask, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *local;
+	u8 toofewbits;
+	int ret;
+
+	if (!is_test_task())
+		return 0;
+
+	local = create_cpumask();
+	if (!local)
+		return 0;
+
+	/* The kfunc should prevent this operation */
+	ret = bpf_cpumask_populate((struct cpumask *)local, &toofewbits, sizeof(toofewbits));
+	if (ret != -EACCES)
+		err = 2;
+
+	bpf_cpumask_release(local);
+
+	return 0;
+}
+
+/* Mask is guaranteed to be large enough for bpf_cpumask_t. */
+#define CPUMASK_TEST_MASKLEN (sizeof(cpumask_t))
+
+/* Add an extra word for the test_populate_reject_unaligned test. */
+u64 bits[CPUMASK_TEST_MASKLEN / 8 + 1];
+extern bool CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS __kconfig __weak;
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_populate_reject_unaligned, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *mask;
+	char *src;
+	int ret;
+
+	if (!is_test_task())
+		return 0;
+
+	/* Skip if unaligned accesses are fine for this arch.  */
+	if (CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
+		return 0;
+
+	mask = bpf_cpumask_create();
+	if (!mask) {
+		err = 1;
+		return 0;
+	}
+
+	/* Misalign the source array by a byte. */
+	src = &((char *)bits)[1];
+
+	ret = bpf_cpumask_populate((struct cpumask *)mask, src, CPUMASK_TEST_MASKLEN);
+	if (ret != -EINVAL)
+		err = 2;
+
+	bpf_cpumask_release(mask);
+
+	return 0;
+}
+
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_populate, struct task_struct *task, u64 clone_flags)
+{
+	struct bpf_cpumask *mask;
+	bool bit;
+	int ret;
+	int i;
+
+	if (!is_test_task())
+		return 0;
+
+	/* Set only odd bits. */
+	__builtin_memset(bits, 0xaa, CPUMASK_TEST_MASKLEN);
+
+	mask = bpf_cpumask_create();
+	if (!mask) {
+		err = 1;
+		return 0;
+	}
+
+	/* Pass the entire bits array, the kfunc will only copy the valid bits. */
+	ret = bpf_cpumask_populate((struct cpumask *)mask, bits, CPUMASK_TEST_MASKLEN);
+	if (ret) {
+		err = 2;
+		goto out;
+	}
+
+	/*
+	 * Test is there to appease the verifier. We cannot directly
+	 * access NR_CPUS, the upper bound for nr_cpus, so we infer
+	 * it from the size of cpumask_t.
+	 */
+	if (nr_cpus < 0 || nr_cpus >= CPUMASK_TEST_MASKLEN * 8) {
+		err = 3;
+		goto out;
+	}
+
+	bpf_for(i, 0, nr_cpus) {
+		/* Odd-numbered bits should be set, even ones unset. */
+		bit = bpf_cpumask_test_cpu(i, (const struct cpumask *)mask);
+		if (bit == (i % 2 != 0))
+			continue;
+
+		err = 4;
+		break;
+	}
+
+out:
+	bpf_cpumask_release(mask);
+
+	return 0;
+}
+
+#undef CPUMASK_TEST_MASKLEN
diff --git a/tools/testing/selftests/bpf/progs/crypto_basic.c b/tools/testing/selftests/bpf/progs/crypto_basic.c
new file mode 100644
index 000000000000..8cf7168b42d5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/crypto_basic.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_kfuncs.h"
+#include "crypto_common.h"
+
+int status;
+SEC("syscall")
+int crypto_release(void *ctx)
+{
+	struct bpf_crypto_params params = {
+		.type = "skcipher",
+		.algo = "ecb(aes)",
+		.key_len = 16,
+	};
+
+	struct bpf_crypto_ctx *cctx;
+	int err = 0;
+
+	status = 0;
+
+	cctx = bpf_crypto_ctx_create(&params, sizeof(params), &err);
+
+	if (!cctx) {
+		status = err;
+		return 0;
+	}
+
+	bpf_crypto_ctx_release(cctx);
+
+	return 0;
+}
+
+SEC("syscall")
+__failure __msg("Unreleased reference")
+int crypto_acquire(void *ctx)
+{
+	struct bpf_crypto_params params = {
+		.type = "skcipher",
+		.algo = "ecb(aes)",
+		.key_len = 16,
+	};
+	struct bpf_crypto_ctx *cctx;
+	int err = 0;
+
+	status = 0;
+
+	cctx = bpf_crypto_ctx_create(&params, sizeof(params), &err);
+
+	if (!cctx) {
+		status = err;
+		return 0;
+	}
+
+	cctx = bpf_crypto_ctx_acquire(cctx);
+	if (!cctx)
+		return -EINVAL;
+
+	bpf_crypto_ctx_release(cctx);
+
+	return 0;
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/crypto_bench.c b/tools/testing/selftests/bpf/progs/crypto_bench.c
new file mode 100644
index 000000000000..4ac956b26240
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/crypto_bench.c
@@ -0,0 +1,107 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_kfuncs.h"
+#include "crypto_common.h"
+
+const volatile unsigned int len = 16;
+char cipher[128] = {};
+u32 key_len, authsize;
+char dst[256] = {};
+u8 key[256] = {};
+long hits = 0;
+int status;
+
+SEC("syscall")
+int crypto_setup(void *args)
+{
+	struct bpf_crypto_ctx *cctx;
+	struct bpf_crypto_params params = {
+		.type = "skcipher",
+		.key_len = key_len,
+		.authsize = authsize,
+	};
+	int err = 0;
+
+	status = 0;
+
+	if (!cipher[0] || !key_len || key_len > 256) {
+		status = -EINVAL;
+		return 0;
+	}
+
+	__builtin_memcpy(&params.algo, cipher, sizeof(cipher));
+	__builtin_memcpy(&params.key, key, sizeof(key));
+	cctx = bpf_crypto_ctx_create(&params, sizeof(params), &err);
+
+	if (!cctx) {
+		status = err;
+		return 0;
+	}
+
+	err = crypto_ctx_insert(cctx);
+	if (err && err != -EEXIST)
+		status = err;
+
+	return 0;
+}
+
+SEC("tc")
+int crypto_encrypt(struct __sk_buff *skb)
+{
+	struct __crypto_ctx_value *v;
+	struct bpf_crypto_ctx *ctx;
+	struct bpf_dynptr psrc, pdst;
+
+	v = crypto_ctx_value_lookup();
+	if (!v) {
+		status = -ENOENT;
+		return 0;
+	}
+
+	ctx = v->ctx;
+	if (!ctx) {
+		status = -ENOENT;
+		return 0;
+	}
+
+	bpf_dynptr_from_skb(skb, 0, &psrc);
+	bpf_dynptr_from_mem(dst, len, 0, &pdst);
+
+	status = bpf_crypto_encrypt(ctx, &psrc, &pdst, NULL);
+	__sync_add_and_fetch(&hits, 1);
+
+	return 0;
+}
+
+SEC("tc")
+int crypto_decrypt(struct __sk_buff *skb)
+{
+	struct bpf_dynptr psrc, pdst;
+	struct __crypto_ctx_value *v;
+	struct bpf_crypto_ctx *ctx;
+
+	v = crypto_ctx_value_lookup();
+	if (!v)
+		return -ENOENT;
+
+	ctx = v->ctx;
+	if (!ctx)
+		return -ENOENT;
+
+	bpf_dynptr_from_skb(skb, 0, &psrc);
+	bpf_dynptr_from_mem(dst, len, 0, &pdst);
+
+	status = bpf_crypto_decrypt(ctx, &psrc, &pdst, NULL);
+	__sync_add_and_fetch(&hits, 1);
+
+	return 0;
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/crypto_common.h b/tools/testing/selftests/bpf/progs/crypto_common.h
new file mode 100644
index 000000000000..57dd7a68a8c3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/crypto_common.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#ifndef _CRYPTO_COMMON_H
+#define _CRYPTO_COMMON_H
+
+#include "errno.h"
+#include <stdbool.h>
+
+struct bpf_crypto_ctx *bpf_crypto_ctx_create(const struct bpf_crypto_params *params,
+					     u32 params__sz, int *err) __ksym;
+struct bpf_crypto_ctx *bpf_crypto_ctx_acquire(struct bpf_crypto_ctx *ctx) __ksym;
+void bpf_crypto_ctx_release(struct bpf_crypto_ctx *ctx) __ksym;
+int bpf_crypto_encrypt(struct bpf_crypto_ctx *ctx, const struct bpf_dynptr *src,
+		       const struct bpf_dynptr *dst, const struct bpf_dynptr *iv) __ksym;
+int bpf_crypto_decrypt(struct bpf_crypto_ctx *ctx, const struct bpf_dynptr *src,
+		       const struct bpf_dynptr *dst, const struct bpf_dynptr *iv) __ksym;
+
+struct __crypto_ctx_value {
+	struct bpf_crypto_ctx __kptr * ctx;
+};
+
+struct array_map {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct __crypto_ctx_value);
+	__uint(max_entries, 1);
+} __crypto_ctx_map SEC(".maps");
+
+static inline struct __crypto_ctx_value *crypto_ctx_value_lookup(void)
+{
+	u32 key = 0;
+
+	return bpf_map_lookup_elem(&__crypto_ctx_map, &key);
+}
+
+static inline int crypto_ctx_insert(struct bpf_crypto_ctx *ctx)
+{
+	struct __crypto_ctx_value local, *v;
+	struct bpf_crypto_ctx *old;
+	u32 key = 0;
+	int err;
+
+	local.ctx = NULL;
+	err = bpf_map_update_elem(&__crypto_ctx_map, &key, &local, 0);
+	if (err) {
+		bpf_crypto_ctx_release(ctx);
+		return err;
+	}
+
+	v = bpf_map_lookup_elem(&__crypto_ctx_map, &key);
+	if (!v) {
+		bpf_crypto_ctx_release(ctx);
+		return -ENOENT;
+	}
+
+	old = bpf_kptr_xchg(&v->ctx, ctx);
+	if (old) {
+		bpf_crypto_ctx_release(old);
+		return -EEXIST;
+	}
+
+	return 0;
+}
+
+#endif /* _CRYPTO_COMMON_H */
diff --git a/tools/testing/selftests/bpf/progs/crypto_sanity.c b/tools/testing/selftests/bpf/progs/crypto_sanity.c
new file mode 100644
index 000000000000..dfd8a258f14a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/crypto_sanity.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_kfuncs.h"
+#include "crypto_common.h"
+
+unsigned char key[256] = {};
+u16 udp_test_port = 7777;
+u32 authsize, key_len;
+char algo[128] = {};
+char dst[16] = {}, dst_bad[8] = {};
+int status;
+
+static int skb_dynptr_validate(struct __sk_buff *skb, struct bpf_dynptr *psrc)
+{
+	struct ipv6hdr ip6h;
+	struct udphdr udph;
+	u32 offset;
+
+	if (skb->protocol != __bpf_constant_htons(ETH_P_IPV6))
+		return -1;
+
+	if (bpf_skb_load_bytes(skb, ETH_HLEN, &ip6h, sizeof(ip6h)))
+		return -1;
+
+	if (ip6h.nexthdr != IPPROTO_UDP)
+		return -1;
+
+	if (bpf_skb_load_bytes(skb, ETH_HLEN + sizeof(ip6h), &udph, sizeof(udph)))
+		return -1;
+
+	if (udph.dest != __bpf_htons(udp_test_port))
+		return -1;
+
+	offset = ETH_HLEN + sizeof(ip6h) + sizeof(udph);
+	if (skb->len < offset + 16)
+		return -1;
+
+	/* let's make sure that 16 bytes of payload are in the linear part of skb */
+	bpf_skb_pull_data(skb, offset + 16);
+	bpf_dynptr_from_skb(skb, 0, psrc);
+	bpf_dynptr_adjust(psrc, offset, offset + 16);
+
+	return 0;
+}
+
+SEC("syscall")
+int skb_crypto_setup(void *ctx)
+{
+	struct bpf_crypto_params params = {
+		.type = "skcipher",
+		.key_len = key_len,
+		.authsize = authsize,
+	};
+	struct bpf_crypto_ctx *cctx;
+	int err;
+
+	status = 0;
+	if (key_len > 256) {
+		status = -EINVAL;
+		return 0;
+	}
+
+	__builtin_memcpy(&params.algo, algo, sizeof(algo));
+	__builtin_memcpy(&params.key, key, sizeof(key));
+
+	cctx = bpf_crypto_ctx_create(&params, sizeof(params), &err);
+	if (!cctx) {
+		status = err;
+		return 0;
+	}
+
+	err = crypto_ctx_insert(cctx);
+	if (err && err != -EEXIST)
+		status = err;
+	return 0;
+}
+
+SEC("tc")
+int decrypt_sanity(struct __sk_buff *skb)
+{
+	struct __crypto_ctx_value *v;
+	struct bpf_crypto_ctx *ctx;
+	struct bpf_dynptr psrc, pdst;
+	int err;
+
+	status = 0;
+	err = skb_dynptr_validate(skb, &psrc);
+	if (err < 0) {
+		status = err;
+		return TC_ACT_SHOT;
+	}
+
+	v = crypto_ctx_value_lookup();
+	if (!v) {
+		status = -ENOENT;
+		return TC_ACT_SHOT;
+	}
+
+	ctx = v->ctx;
+	if (!ctx) {
+		status = -ENOENT;
+		return TC_ACT_SHOT;
+	}
+
+	/* Check also bad case where the dst buffer is smaller than the
+	 * skb's linear section.
+	 */
+	bpf_dynptr_from_mem(dst_bad, sizeof(dst_bad), 0, &pdst);
+	status = bpf_crypto_decrypt(ctx, &psrc, &pdst, NULL);
+	if (!status)
+		status = -EIO;
+	if (status != -EINVAL)
+		goto err;
+
+	/* dst is a global variable to make testing part easier to check.
+	 * In real production code, a percpu map should be used to store
+	 * the result.
+	 */
+	bpf_dynptr_from_mem(dst, sizeof(dst), 0, &pdst);
+	status = bpf_crypto_decrypt(ctx, &psrc, &pdst, NULL);
+err:
+	return TC_ACT_SHOT;
+}
+
+SEC("tc")
+int encrypt_sanity(struct __sk_buff *skb)
+{
+	struct __crypto_ctx_value *v;
+	struct bpf_crypto_ctx *ctx;
+	struct bpf_dynptr psrc, pdst;
+	int err;
+
+	status = 0;
+	err = skb_dynptr_validate(skb, &psrc);
+	if (err < 0) {
+		status = err;
+		return TC_ACT_SHOT;
+	}
+
+	v = crypto_ctx_value_lookup();
+	if (!v) {
+		status = -ENOENT;
+		return TC_ACT_SHOT;
+	}
+
+	ctx = v->ctx;
+	if (!ctx) {
+		status = -ENOENT;
+		return TC_ACT_SHOT;
+	}
+
+	/* Check also bad case where the dst buffer is smaller than the
+	 * skb's linear section.
+	 */
+	bpf_dynptr_from_mem(dst_bad, sizeof(dst_bad), 0, &pdst);
+	status = bpf_crypto_encrypt(ctx, &psrc, &pdst, NULL);
+	if (!status)
+		status = -EIO;
+	if (status != -EINVAL)
+		goto err;
+
+	/* dst is a global variable to make testing part easier to check.
+	 * In real production code, a percpu map should be used to store
+	 * the result.
+	 */
+	bpf_dynptr_from_mem(dst, sizeof(dst), 0, &pdst);
+	status = bpf_crypto_encrypt(ctx, &psrc, &pdst, NULL);
+err:
+	return TC_ACT_SHOT;
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/csum_diff_test.c b/tools/testing/selftests/bpf/progs/csum_diff_test.c
new file mode 100644
index 000000000000..9438f1773a58
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/csum_diff_test.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates */
+#include <linux/types.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#define BUFF_SZ 512
+
+/* Will be updated by benchmark before program loading */
+char to_buff[BUFF_SZ];
+const volatile unsigned int to_buff_len = 0;
+char from_buff[BUFF_SZ];
+const volatile unsigned int from_buff_len = 0;
+unsigned short seed = 0;
+
+short result;
+
+char _license[] SEC("license") = "GPL";
+
+SEC("tc")
+int compute_checksum(void *ctx)
+{
+	int to_len_half = to_buff_len / 2;
+	int from_len_half = from_buff_len / 2;
+	short result2;
+
+	/* Calculate checksum in one go */
+	result2 = bpf_csum_diff((void *)from_buff, from_buff_len,
+				(void *)to_buff, to_buff_len, seed);
+
+	/* Calculate checksum by concatenating bpf_csum_diff()*/
+	result = bpf_csum_diff((void *)from_buff, from_buff_len - from_len_half,
+			       (void *)to_buff, to_buff_len - to_len_half, seed);
+
+	result = bpf_csum_diff((void *)from_buff + (from_buff_len - from_len_half), from_len_half,
+			       (void *)to_buff + (to_buff_len - to_len_half), to_len_half, result);
+
+	result = (result == result2) ? result : 0;
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/decap_sanity.c b/tools/testing/selftests/bpf/progs/decap_sanity.c
new file mode 100644
index 000000000000..bd3c657c58a7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/decap_sanity.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define UDP_TEST_PORT 7777
+
+void *bpf_cast_to_kern_ctx(void *) __ksym;
+bool init_csum_partial = false;
+bool final_csum_none = false;
+bool broken_csum_start = false;
+
+static unsigned int skb_headlen(const struct sk_buff *skb)
+{
+	return skb->len - skb->data_len;
+}
+
+static unsigned int skb_headroom(const struct sk_buff *skb)
+{
+	return skb->data - skb->head;
+}
+
+static int skb_checksum_start_offset(const struct sk_buff *skb)
+{
+	return skb->csum_start - skb_headroom(skb);
+}
+
+SEC("tc")
+int decap_sanity(struct __sk_buff *skb)
+{
+	struct sk_buff *kskb;
+	struct ipv6hdr ip6h;
+	struct udphdr udph;
+	int err;
+
+	if (skb->protocol != __bpf_constant_htons(ETH_P_IPV6))
+		return TC_ACT_SHOT;
+
+	if (bpf_skb_load_bytes(skb, ETH_HLEN, &ip6h, sizeof(ip6h)))
+		return TC_ACT_SHOT;
+
+	if (ip6h.nexthdr != IPPROTO_UDP)
+		return TC_ACT_SHOT;
+
+	if (bpf_skb_load_bytes(skb, ETH_HLEN + sizeof(ip6h), &udph, sizeof(udph)))
+		return TC_ACT_SHOT;
+
+	if (udph.dest != __bpf_constant_htons(UDP_TEST_PORT))
+		return TC_ACT_SHOT;
+
+	kskb = bpf_cast_to_kern_ctx(skb);
+	init_csum_partial = (kskb->ip_summed == CHECKSUM_PARTIAL);
+	err = bpf_skb_adjust_room(skb, -(s32)(ETH_HLEN + sizeof(ip6h) + sizeof(udph)),
+				  1, BPF_F_ADJ_ROOM_FIXED_GSO);
+	if (err)
+		return TC_ACT_SHOT;
+	final_csum_none = (kskb->ip_summed == CHECKSUM_NONE);
+	if (kskb->ip_summed == CHECKSUM_PARTIAL &&
+	    (unsigned int)skb_checksum_start_offset(kskb) >= skb_headlen(kskb))
+		broken_csum_start = true;
+
+	return TC_ACT_SHOT;
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/dev_cgroup.c b/tools/testing/selftests/bpf/progs/dev_cgroup.c
index 79b54a4fa244..c1dfbd2b56fc 100644
--- a/tools/testing/selftests/bpf/progs/dev_cgroup.c
+++ b/tools/testing/selftests/bpf/progs/dev_cgroup.c
@@ -41,14 +41,14 @@ int bpf_prog1(struct bpf_cgroup_dev_ctx *ctx)
 	bpf_trace_printk(fmt, sizeof(fmt), ctx->major, ctx->minor);
 #endif
 
-	/* Allow access to /dev/zero and /dev/random.
+	/* Allow access to /dev/null and /dev/urandom.
 	 * Forbid everything else.
 	 */
 	if (ctx->major != 1 || type != BPF_DEVCG_DEV_CHAR)
 		return 0;
 
 	switch (ctx->minor) {
-	case 5: /* 1:5 /dev/zero */
+	case 3: /* 1:3 /dev/null */
 	case 9: /* 1:9 /dev/urandom */
 		return 1;
 	}
diff --git a/tools/testing/selftests/bpf/progs/dmabuf_iter.c b/tools/testing/selftests/bpf/progs/dmabuf_iter.c
new file mode 100644
index 000000000000..13cdb11fdeb2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/dmabuf_iter.c
@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Google LLC */
+#include <vmlinux.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_helpers.h>
+
+/* From uapi/linux/dma-buf.h */
+#define DMA_BUF_NAME_LEN 32
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, DMA_BUF_NAME_LEN);
+	__type(value, bool);
+	__uint(max_entries, 5);
+} testbuf_hash SEC(".maps");
+
+/*
+ * Fields output by this iterator are delimited by newlines. Convert any
+ * newlines in user-provided printed strings to spaces.
+ */
+static void sanitize_string(char *src, size_t size)
+{
+	for (char *c = src; (size_t)(c - src) < size && *c; ++c)
+		if (*c == '\n')
+			*c = ' ';
+}
+
+SEC("iter/dmabuf")
+int dmabuf_collector(struct bpf_iter__dmabuf *ctx)
+{
+	const struct dma_buf *dmabuf = ctx->dmabuf;
+	struct seq_file *seq = ctx->meta->seq;
+	unsigned long inode = 0;
+	size_t size;
+	const char *pname, *exporter;
+	char name[DMA_BUF_NAME_LEN] = {'\0'};
+
+	if (!dmabuf)
+		return 0;
+
+	if (BPF_CORE_READ_INTO(&inode, dmabuf, file, f_inode, i_ino) ||
+	    bpf_core_read(&size, sizeof(size), &dmabuf->size) ||
+	    bpf_core_read(&pname, sizeof(pname), &dmabuf->name) ||
+	    bpf_core_read(&exporter, sizeof(exporter), &dmabuf->exp_name))
+		return 1;
+
+	/* Buffers are not required to be named */
+	if (pname) {
+		if (bpf_probe_read_kernel(name, sizeof(name), pname))
+			return 1;
+
+		/* Name strings can be provided by userspace */
+		sanitize_string(name, sizeof(name));
+	}
+
+	BPF_SEQ_PRINTF(seq, "%lu\n%llu\n%s\n%s\n", inode, size, name, exporter);
+	return 0;
+}
+
+SEC("syscall")
+int iter_dmabuf_for_each(const void *ctx)
+{
+	struct dma_buf *d;
+
+	bpf_for_each(dmabuf, d) {
+		char name[DMA_BUF_NAME_LEN];
+		const char *pname;
+		bool *found;
+		long len;
+		int i;
+
+		if (bpf_core_read(&pname, sizeof(pname), &d->name))
+			return 1;
+
+		/* Buffers are not required to be named */
+		if (!pname)
+			continue;
+
+		len = bpf_probe_read_kernel_str(name, sizeof(name), pname);
+		if (len < 0)
+			return 1;
+
+		/*
+		 * The entire name buffer is used as a map key.
+		 * Zeroize any uninitialized trailing bytes after the NUL.
+		 */
+		bpf_for(i, len, DMA_BUF_NAME_LEN)
+			name[i] = 0;
+
+		found = bpf_map_lookup_elem(&testbuf_hash, name);
+		if (found) {
+			bool t = true;
+
+			bpf_map_update_elem(&testbuf_hash, name, &t, BPF_EXIST);
+		}
+	}
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/dummy_st_ops_fail.c b/tools/testing/selftests/bpf/progs/dummy_st_ops_fail.c
new file mode 100644
index 000000000000..0bf969a0b5ed
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/dummy_st_ops_fail.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("struct_ops.s/test_2")
+__failure __msg("attach to unsupported member test_2 of struct bpf_dummy_ops")
+int BPF_PROG(test_unsupported_field_sleepable,
+	     struct bpf_dummy_ops_state *state, int a1, unsigned short a2,
+	     char a3, unsigned long a4)
+{
+	/* Tries to mark an unsleepable field in struct bpf_dummy_ops as sleepable. */
+	return 0;
+}
+
+SEC(".struct_ops")
+struct bpf_dummy_ops dummy_1 = {
+	.test_1 = NULL,
+	.test_2 = (void *)test_unsupported_field_sleepable,
+	.test_sleepable = (void *)NULL,
+};
diff --git a/tools/testing/selftests/bpf/progs/dummy_st_ops.c b/tools/testing/selftests/bpf/progs/dummy_st_ops_success.c
index ead87edb75e2..ec0c595d47af 100644
--- a/tools/testing/selftests/bpf/progs/dummy_st_ops.c
+++ b/tools/testing/selftests/bpf/progs/dummy_st_ops_success.c
@@ -1,19 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (C) 2021. Huawei Technologies Co., Ltd */
-#include <linux/bpf.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
-struct bpf_dummy_ops_state {
-	int val;
-} __attribute__((preserve_access_index));
-
-struct bpf_dummy_ops {
-	int (*test_1)(struct bpf_dummy_ops_state *state);
-	int (*test_2)(struct bpf_dummy_ops_state *state, int a1, unsigned short a2,
-		      char a3, unsigned long a4);
-};
-
 char _license[] SEC("license") = "GPL";
 
 SEC("struct_ops/test_1")
@@ -21,8 +11,17 @@ int BPF_PROG(test_1, struct bpf_dummy_ops_state *state)
 {
 	int ret;
 
-	if (!state)
-		return 0xf2f3f4f5;
+	/* Check that 'state' nullable status is detected correctly.
+	 * If 'state' argument would be assumed non-null by verifier
+	 * the code below would be deleted as dead (which it shouldn't).
+	 * Hide it from the compiler behind 'asm' block to avoid
+	 * unnecessary optimizations.
+	 */
+	asm volatile (
+		"if %[state] != 0 goto +2;"
+		"r0 = 0xf2f3f4f5;"
+		"exit;"
+	::[state]"p"(state));
 
 	ret = state->val;
 	state->val = 0x5a;
@@ -35,7 +34,7 @@ SEC("struct_ops/test_2")
 int BPF_PROG(test_2, struct bpf_dummy_ops_state *state, int a1, unsigned short a2,
 	     char a3, unsigned long a4)
 {
-	test_2_args[0] = (unsigned long)state;
+	test_2_args[0] = state->val;
 	test_2_args[1] = a1;
 	test_2_args[2] = a2;
 	test_2_args[3] = a3;
@@ -43,8 +42,15 @@ int BPF_PROG(test_2, struct bpf_dummy_ops_state *state, int a1, unsigned short a
 	return 0;
 }
 
+SEC("struct_ops.s/test_sleepable")
+int BPF_PROG(test_sleepable, struct bpf_dummy_ops_state *state)
+{
+	return 0;
+}
+
 SEC(".struct_ops")
 struct bpf_dummy_ops dummy_1 = {
 	.test_1 = (void *)test_1,
 	.test_2 = (void *)test_2,
+	.test_sleepable = (void *)test_sleepable,
 };
diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c
index 78debc1b3820..dda6a8dada82 100644
--- a/tools/testing/selftests/bpf/progs/dynptr_fail.c
+++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c
@@ -3,9 +3,13 @@
 
 #include <errno.h>
 #include <string.h>
+#include <stdbool.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <linux/if_ether.h>
 #include "bpf_misc.h"
+#include "bpf_kfuncs.h"
 
 char _license[] SEC("license") = "GPL";
 
@@ -35,6 +39,13 @@ struct {
 	__type(value, __u32);
 } array_map3 SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} array_map4 SEC(".maps");
+
 struct sample {
 	int pid;
 	long value;
@@ -67,10 +78,10 @@ static int get_map_val_dynptr(struct bpf_dynptr *ptr)
  * bpf_ringbuf_submit/discard_dynptr call
  */
 SEC("?raw_tp")
-__failure __msg("Unreleased reference id=1")
+__failure __msg("Unreleased reference id=2")
 int ringbuf_missing_release1(void *ctx)
 {
-	struct bpf_dynptr ptr;
+	struct bpf_dynptr ptr = {};
 
 	bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr);
 
@@ -80,7 +91,7 @@ int ringbuf_missing_release1(void *ctx)
 }
 
 SEC("?raw_tp")
-__failure __msg("Unreleased reference id=2")
+__failure __msg("Unreleased reference id=4")
 int ringbuf_missing_release2(void *ctx)
 {
 	struct bpf_dynptr ptr1, ptr2;
@@ -138,7 +149,7 @@ int ringbuf_release_uninit_dynptr(void *ctx)
 
 /* A dynptr can't be used after it has been invalidated */
 SEC("?raw_tp")
-__failure __msg("Expected an initialized dynptr as arg #3")
+__failure __msg("Expected an initialized dynptr as arg #2")
 int use_after_invalid(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -181,7 +192,7 @@ done:
 
 /* Can't add a dynptr to a map */
 SEC("?raw_tp")
-__failure __msg("invalid indirect read from stack")
+__failure __msg("invalid read from stack")
 int add_dynptr_to_map1(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -199,7 +210,7 @@ int add_dynptr_to_map1(void *ctx)
 
 /* Can't add a struct with an embedded dynptr to a map */
 SEC("?raw_tp")
-__failure __msg("invalid indirect read from stack")
+__failure __msg("invalid read from stack")
 int add_dynptr_to_map2(void *ctx)
 {
 	struct test_info x;
@@ -237,11 +248,52 @@ done:
 	return 0;
 }
 
+/* A data slice can't be accessed out of bounds */
+SEC("?tc")
+__failure __msg("value is outside of the allowed memory range")
+int data_slice_out_of_bounds_skb(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+	char buffer[sizeof(*hdr)] = {};
+
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	hdr = bpf_dynptr_slice_rdwr(&ptr, 0, buffer, sizeof(buffer));
+	if (!hdr)
+		return SK_DROP;
+
+	/* this should fail */
+	*(__u8*)(hdr + 1) = 1;
+
+	return SK_PASS;
+}
+
+/* A metadata slice can't be accessed out of bounds */
+SEC("?tc")
+__failure __msg("value is outside of the allowed memory range")
+int data_slice_out_of_bounds_skb_meta(struct __sk_buff *skb)
+{
+	struct bpf_dynptr meta;
+	__u8 *md;
+
+	bpf_dynptr_from_skb_meta(skb, 0, &meta);
+
+	md = bpf_dynptr_slice_rdwr(&meta, 0, NULL, sizeof(*md));
+	if (!md)
+		return SK_DROP;
+
+	/* this should fail */
+	*(md + 1) = 42;
+
+	return SK_PASS;
+}
+
 SEC("?raw_tp")
 __failure __msg("value is outside of the allowed memory range")
 int data_slice_out_of_bounds_map_value(void *ctx)
 {
-	__u32 key = 0, map_val;
+	__u32 map_val;
 	struct bpf_dynptr ptr;
 	void *data;
 
@@ -358,7 +410,6 @@ int data_slice_missing_null_check2(void *ctx)
 		/* this should fail */
 		*data2 = 3;
 
-done:
 	bpf_ringbuf_discard_dynptr(&ptr, 0);
 	return 0;
 }
@@ -367,7 +418,7 @@ done:
  * dynptr argument
  */
 SEC("?raw_tp")
-__failure __msg("invalid indirect read from stack")
+__failure __msg("invalid read from stack")
 int invalid_helper1(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -382,7 +433,7 @@ int invalid_helper1(void *ctx)
 
 /* A dynptr can't be passed into a helper function at a non-zero offset */
 SEC("?raw_tp")
-__failure __msg("Expected an initialized dynptr as arg #3")
+__failure __msg("cannot pass in dynptr at an offset=-8")
 int invalid_helper2(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -392,13 +443,12 @@ int invalid_helper2(void *ctx)
 
 	/* this should fail */
 	bpf_dynptr_read(read_data, sizeof(read_data), (void *)&ptr + 8, 0, 0);
-
 	return 0;
 }
 
 /* A bpf_dynptr is invalidated if it's been written into */
 SEC("?raw_tp")
-__failure __msg("Expected an initialized dynptr as arg #1")
+__failure __msg("Expected an initialized dynptr as arg #0")
 int invalid_write1(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -411,6 +461,7 @@ int invalid_write1(void *ctx)
 
 	/* this should fail */
 	data = bpf_dynptr_data(&ptr, 0, 1);
+	__sink(data);
 
 	return 0;
 }
@@ -420,7 +471,7 @@ int invalid_write1(void *ctx)
  * offset
  */
 SEC("?raw_tp")
-__failure __msg("Expected an initialized dynptr as arg #3")
+__failure __msg("cannot overwrite referenced dynptr")
 int invalid_write2(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -444,7 +495,7 @@ int invalid_write2(void *ctx)
  * non-const offset
  */
 SEC("?raw_tp")
-__failure __msg("Expected an initialized dynptr as arg #1")
+__failure __msg("cannot overwrite referenced dynptr")
 int invalid_write3(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -476,7 +527,7 @@ static int invalid_write4_callback(__u32 index, void *data)
  * be invalidated as a dynptr
  */
 SEC("?raw_tp")
-__failure __msg("arg 1 is an unacquired reference")
+__failure __msg("cannot overwrite referenced dynptr")
 int invalid_write4(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -584,7 +635,7 @@ int invalid_read4(void *ctx)
 
 /* Initializing a dynptr on an offset should fail */
 SEC("?raw_tp")
-__failure __msg("invalid write to stack")
+__failure __msg("cannot pass in dynptr at an offset=0")
 int invalid_offset(void *ctx)
 {
 	struct bpf_dynptr ptr;
@@ -623,7 +674,7 @@ static int release_twice_callback_fn(__u32 index, void *data)
 }
 
 /* Test that releasing a dynptr twice, where one of the releases happens
- * within a calback function, fails
+ * within a callback function, fails
  */
 SEC("?raw_tp")
 __failure __msg("arg 1 is an unacquired reference")
@@ -653,3 +704,1292 @@ int dynptr_from_mem_invalid_api(void *ctx)
 
 	return 0;
 }
+
+SEC("?tc")
+__failure __msg("cannot overwrite referenced dynptr") __log_level(2)
+int dynptr_pruning_overwrite(struct __sk_buff *ctx)
+{
+	asm volatile (
+		"r9 = 0xeB9F;				\
+		 r6 = %[ringbuf] ll;			\
+		 r1 = r6;				\
+		 r2 = 8;				\
+		 r3 = 0;				\
+		 r4 = r10;				\
+		 r4 += -16;				\
+		 call %[bpf_ringbuf_reserve_dynptr];	\
+		 if r0 == 0 goto pjmp1;			\
+		 goto pjmp2;				\
+	pjmp1:						\
+		 *(u64 *)(r10 - 16) = r9;		\
+	pjmp2:						\
+		 r1 = r10;				\
+		 r1 += -16;				\
+		 r2 = 0;				\
+		 call %[bpf_ringbuf_discard_dynptr];	"
+		:
+		: __imm(bpf_ringbuf_reserve_dynptr),
+		  __imm(bpf_ringbuf_discard_dynptr),
+		  __imm_addr(ringbuf)
+		: __clobber_all
+	);
+	return 0;
+}
+
+SEC("?tc")
+__success __msg("12: safe") __log_level(2)
+int dynptr_pruning_stacksafe(struct __sk_buff *ctx)
+{
+	asm volatile (
+		"r9 = 0xeB9F;				\
+		 r6 = %[ringbuf] ll;			\
+		 r1 = r6;				\
+		 r2 = 8;				\
+		 r3 = 0;				\
+		 r4 = r10;				\
+		 r4 += -16;				\
+		 call %[bpf_ringbuf_reserve_dynptr];	\
+		 if r0 == 0 goto stjmp1;		\
+		 goto stjmp2;				\
+	stjmp1:						\
+		 r9 = r9;				\
+	stjmp2:						\
+		 r1 = r10;				\
+		 r1 += -16;				\
+		 r2 = 0;				\
+		 call %[bpf_ringbuf_discard_dynptr];	"
+		:
+		: __imm(bpf_ringbuf_reserve_dynptr),
+		  __imm(bpf_ringbuf_discard_dynptr),
+		  __imm_addr(ringbuf)
+		: __clobber_all
+	);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("cannot overwrite referenced dynptr") __log_level(2)
+int dynptr_pruning_type_confusion(struct __sk_buff *ctx)
+{
+	asm volatile (
+		"r6 = %[array_map4] ll;			\
+		 r7 = %[ringbuf] ll;			\
+		 r1 = r6;				\
+		 r2 = r10;				\
+		 r2 += -8;				\
+		 r9 = 0;				\
+		 *(u64 *)(r2 + 0) = r9;			\
+		 r3 = r10;				\
+		 r3 += -24;				\
+		 r9 = 0xeB9FeB9F;			\
+		 *(u64 *)(r10 - 16) = r9;		\
+		 *(u64 *)(r10 - 24) = r9;		\
+		 r9 = 0;				\
+		 r4 = 0;				\
+		 r8 = r2;				\
+		 call %[bpf_map_update_elem];		\
+		 r1 = r6;				\
+		 r2 = r8;				\
+		 call %[bpf_map_lookup_elem];		\
+		 if r0 != 0 goto tjmp1;			\
+		 exit;					\
+	tjmp1:						\
+		 r8 = r0;				\
+		 r1 = r7;				\
+		 r2 = 8;				\
+		 r3 = 0;				\
+		 r4 = r10;				\
+		 r4 += -16;				\
+		 r0 = *(u64 *)(r0 + 0);			\
+		 call %[bpf_ringbuf_reserve_dynptr];	\
+		 if r0 == 0 goto tjmp2;			\
+		 r8 = r8;				\
+		 r8 = r8;				\
+		 r8 = r8;				\
+		 r8 = r8;				\
+		 r8 = r8;				\
+		 r8 = r8;				\
+		 r8 = r8;				\
+		 goto tjmp3;				\
+	tjmp2:						\
+		 *(u64 *)(r10 - 8) = r9;		\
+		 *(u64 *)(r10 - 16) = r9;		\
+		 r1 = r8;				\
+		 r1 += 8;				\
+		 r2 = 0;				\
+		 r3 = 0;				\
+		 r4 = r10;				\
+		 r4 += -16;				\
+		 call %[bpf_dynptr_from_mem];		\
+	tjmp3:						\
+		 r1 = r10;				\
+		 r1 += -16;				\
+		 r2 = 0;				\
+		 call %[bpf_ringbuf_discard_dynptr];	"
+		:
+		: __imm(bpf_map_update_elem),
+		  __imm(bpf_map_lookup_elem),
+		  __imm(bpf_ringbuf_reserve_dynptr),
+		  __imm(bpf_dynptr_from_mem),
+		  __imm(bpf_ringbuf_discard_dynptr),
+		  __imm_addr(array_map4),
+		  __imm_addr(ringbuf)
+		: __clobber_all
+	);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("dynptr has to be at a constant offset") __log_level(2)
+int dynptr_var_off_overwrite(struct __sk_buff *ctx)
+{
+	asm volatile (
+		"r9 = 16;				\
+		 *(u32 *)(r10 - 4) = r9;		\
+		 r8 = *(u32 *)(r10 - 4);		\
+		 if r8 >= 0 goto vjmp1;			\
+		 r0 = 1;				\
+		 exit;					\
+	vjmp1:						\
+		 if r8 <= 16 goto vjmp2;		\
+		 r0 = 1;				\
+		 exit;					\
+	vjmp2:						\
+		 r8 &= 16;				\
+		 r1 = %[ringbuf] ll;			\
+		 r2 = 8;				\
+		 r3 = 0;				\
+		 r4 = r10;				\
+		 r4 += -32;				\
+		 r4 += r8;				\
+		 call %[bpf_ringbuf_reserve_dynptr];	\
+		 r9 = 0xeB9F;				\
+		 *(u64 *)(r10 - 16) = r9;		\
+		 r1 = r10;				\
+		 r1 += -32;				\
+		 r1 += r8;				\
+		 r2 = 0;				\
+		 call %[bpf_ringbuf_discard_dynptr];	"
+		:
+		: __imm(bpf_ringbuf_reserve_dynptr),
+		  __imm(bpf_ringbuf_discard_dynptr),
+		  __imm_addr(ringbuf)
+		: __clobber_all
+	);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("cannot overwrite referenced dynptr") __log_level(2)
+int dynptr_partial_slot_invalidate(struct __sk_buff *ctx)
+{
+	asm volatile (
+		"r6 = %[ringbuf] ll;			\
+		 r7 = %[array_map4] ll;			\
+		 r1 = r7;				\
+		 r2 = r10;				\
+		 r2 += -8;				\
+		 r9 = 0;				\
+		 *(u64 *)(r2 + 0) = r9;			\
+		 r3 = r2;				\
+		 r4 = 0;				\
+		 r8 = r2;				\
+		 call %[bpf_map_update_elem];		\
+		 r1 = r7;				\
+		 r2 = r8;				\
+		 call %[bpf_map_lookup_elem];		\
+		 if r0 != 0 goto sjmp1;			\
+		 exit;					\
+	sjmp1:						\
+		 r7 = r0;				\
+		 r1 = r6;				\
+		 r2 = 8;				\
+		 r3 = 0;				\
+		 r4 = r10;				\
+		 r4 += -24;				\
+		 call %[bpf_ringbuf_reserve_dynptr];	\
+		 *(u64 *)(r10 - 16) = r9;		\
+		 r1 = r7;				\
+		 r2 = 8;				\
+		 r3 = 0;				\
+		 r4 = r10;				\
+		 r4 += -16;				\
+		 call %[bpf_dynptr_from_mem];		\
+		 r1 = r10;				\
+		 r1 += -512;				\
+		 r2 = 488;				\
+		 r3 = r10;				\
+		 r3 += -24;				\
+		 r4 = 0;				\
+		 r5 = 0;				\
+		 call %[bpf_dynptr_read];		\
+		 r8 = 1;				\
+		 if r0 != 0 goto sjmp2;			\
+		 r8 = 0;				\
+	sjmp2:						\
+		 r1 = r10;				\
+		 r1 += -24;				\
+		 r2 = 0;				\
+		 call %[bpf_ringbuf_discard_dynptr];	"
+		:
+		: __imm(bpf_map_update_elem),
+		  __imm(bpf_map_lookup_elem),
+		  __imm(bpf_ringbuf_reserve_dynptr),
+		  __imm(bpf_ringbuf_discard_dynptr),
+		  __imm(bpf_dynptr_from_mem),
+		  __imm(bpf_dynptr_read),
+		  __imm_addr(ringbuf),
+		  __imm_addr(array_map4)
+		: __clobber_all
+	);
+	return 0;
+}
+
+/* Test that it is allowed to overwrite unreferenced dynptr. */
+SEC("?raw_tp")
+__success
+int dynptr_overwrite_unref(void *ctx)
+{
+	struct bpf_dynptr ptr;
+
+	if (get_map_val_dynptr(&ptr))
+		return 0;
+	if (get_map_val_dynptr(&ptr))
+		return 0;
+	if (get_map_val_dynptr(&ptr))
+		return 0;
+
+	return 0;
+}
+
+/* Test that slices are invalidated on reinitializing a dynptr. */
+SEC("?raw_tp")
+__failure __msg("invalid mem access 'scalar'")
+int dynptr_invalidate_slice_reinit(void *ctx)
+{
+	struct bpf_dynptr ptr;
+	__u8 *p;
+
+	if (get_map_val_dynptr(&ptr))
+		return 0;
+	p = bpf_dynptr_data(&ptr, 0, 1);
+	if (!p)
+		return 0;
+	if (get_map_val_dynptr(&ptr))
+		return 0;
+	/* this should fail */
+	return *p;
+}
+
+/* Invalidation of dynptr slices on destruction of dynptr should not miss
+ * mem_or_null pointers.
+ */
+SEC("?raw_tp")
+__failure __msg("R{{[0-9]+}} type=scalar expected=percpu_ptr_")
+int dynptr_invalidate_slice_or_null(void *ctx)
+{
+	struct bpf_dynptr ptr;
+	__u8 *p;
+
+	if (get_map_val_dynptr(&ptr))
+		return 0;
+
+	p = bpf_dynptr_data(&ptr, 0, 1);
+	*(__u8 *)&ptr = 0;
+	/* this should fail */
+	bpf_this_cpu_ptr(p);
+	return 0;
+}
+
+/* Destruction of dynptr should also any slices obtained from it */
+SEC("?raw_tp")
+__failure __msg("R{{[0-9]+}} invalid mem access 'scalar'")
+int dynptr_invalidate_slice_failure(void *ctx)
+{
+	struct bpf_dynptr ptr1;
+	struct bpf_dynptr ptr2;
+	__u8 *p1, *p2;
+
+	if (get_map_val_dynptr(&ptr1))
+		return 0;
+	if (get_map_val_dynptr(&ptr2))
+		return 0;
+
+	p1 = bpf_dynptr_data(&ptr1, 0, 1);
+	if (!p1)
+		return 0;
+	p2 = bpf_dynptr_data(&ptr2, 0, 1);
+	if (!p2)
+		return 0;
+
+	*(__u8 *)&ptr1 = 0;
+	/* this should fail */
+	return *p1;
+}
+
+/* Invalidation of slices should be scoped and should not prevent dereferencing
+ * slices of another dynptr after destroying unrelated dynptr
+ */
+SEC("?raw_tp")
+__success
+int dynptr_invalidate_slice_success(void *ctx)
+{
+	struct bpf_dynptr ptr1;
+	struct bpf_dynptr ptr2;
+	__u8 *p1, *p2;
+
+	if (get_map_val_dynptr(&ptr1))
+		return 1;
+	if (get_map_val_dynptr(&ptr2))
+		return 1;
+
+	p1 = bpf_dynptr_data(&ptr1, 0, 1);
+	if (!p1)
+		return 1;
+	p2 = bpf_dynptr_data(&ptr2, 0, 1);
+	if (!p2)
+		return 1;
+
+	*(__u8 *)&ptr1 = 0;
+	return *p2;
+}
+
+/* Overwriting referenced dynptr should be rejected */
+SEC("?raw_tp")
+__failure __msg("cannot overwrite referenced dynptr")
+int dynptr_overwrite_ref(void *ctx)
+{
+	struct bpf_dynptr ptr;
+
+	bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &ptr);
+	/* this should fail */
+	if (get_map_val_dynptr(&ptr))
+		bpf_ringbuf_discard_dynptr(&ptr, 0);
+	return 0;
+}
+
+/* Reject writes to dynptr slot from bpf_dynptr_read */
+SEC("?raw_tp")
+__failure __msg("potential write to dynptr at off=-16")
+int dynptr_read_into_slot(void *ctx)
+{
+	union {
+		struct {
+			char _pad[48];
+			struct bpf_dynptr ptr;
+		};
+		char buf[64];
+	} data;
+
+	bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &data.ptr);
+	/* this should fail */
+	bpf_dynptr_read(data.buf, sizeof(data.buf), &data.ptr, 0, 0);
+
+	return 0;
+}
+
+/* bpf_dynptr_slice()s are read-only and cannot be written to */
+SEC("?tc")
+__failure __msg("R{{[0-9]+}} cannot write into rdonly_mem")
+int skb_invalid_slice_write(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+	char buffer[sizeof(*hdr)] = {};
+
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	hdr = bpf_dynptr_slice(&ptr, 0, buffer, sizeof(buffer));
+	if (!hdr)
+		return SK_DROP;
+
+	/* this should fail */
+	hdr->h_proto = 1;
+
+	return SK_PASS;
+}
+
+/* bpf_dynptr_slice()s are read-only and cannot be written to */
+SEC("?tc")
+__failure __msg("R{{[0-9]+}} cannot write into rdonly_mem")
+int skb_meta_invalid_slice_write(struct __sk_buff *skb)
+{
+	struct bpf_dynptr meta;
+	__u8 *md;
+
+	bpf_dynptr_from_skb_meta(skb, 0, &meta);
+
+	md = bpf_dynptr_slice(&meta, 0, NULL, sizeof(*md));
+	if (!md)
+		return SK_DROP;
+
+	/* this should fail */
+	*md = 42;
+
+	return SK_PASS;
+}
+
+/* The read-only data slice is invalidated whenever a helper changes packet data */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int skb_invalid_data_slice1(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+	char buffer[sizeof(*hdr)] = {};
+
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	hdr = bpf_dynptr_slice(&ptr, 0, buffer, sizeof(buffer));
+	if (!hdr)
+		return SK_DROP;
+
+	val = hdr->h_proto;
+
+	if (bpf_skb_pull_data(skb, skb->len))
+		return SK_DROP;
+
+	/* this should fail */
+	val = hdr->h_proto;
+
+	return SK_PASS;
+}
+
+/* The read-write data slice is invalidated whenever a helper changes packet data */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int skb_invalid_data_slice2(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+	char buffer[sizeof(*hdr)] = {};
+
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	hdr = bpf_dynptr_slice_rdwr(&ptr, 0, buffer, sizeof(buffer));
+	if (!hdr)
+		return SK_DROP;
+
+	hdr->h_proto = 123;
+
+	if (bpf_skb_pull_data(skb, skb->len))
+		return SK_DROP;
+
+	/* this should fail */
+	hdr->h_proto = 1;
+
+	return SK_PASS;
+}
+
+/* The read-only data slice is invalidated whenever bpf_dynptr_write() is called */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int skb_invalid_data_slice3(struct __sk_buff *skb)
+{
+	char write_data[64] = "hello there, world!!";
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+	char buffer[sizeof(*hdr)] = {};
+
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	hdr = bpf_dynptr_slice(&ptr, 0, buffer, sizeof(buffer));
+	if (!hdr)
+		return SK_DROP;
+
+	val = hdr->h_proto;
+
+	bpf_dynptr_write(&ptr, 0, write_data, sizeof(write_data), 0);
+
+	/* this should fail */
+	val = hdr->h_proto;
+
+	return SK_PASS;
+}
+
+/* The read-write data slice is invalidated whenever bpf_dynptr_write() is called */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int skb_invalid_data_slice4(struct __sk_buff *skb)
+{
+	char write_data[64] = "hello there, world!!";
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+	char buffer[sizeof(*hdr)] = {};
+
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+	hdr = bpf_dynptr_slice_rdwr(&ptr, 0, buffer, sizeof(buffer));
+	if (!hdr)
+		return SK_DROP;
+
+	hdr->h_proto = 123;
+
+	bpf_dynptr_write(&ptr, 0, write_data, sizeof(write_data), 0);
+
+	/* this should fail */
+	hdr->h_proto = 1;
+
+	return SK_PASS;
+}
+
+/* Read-only skb data slice is invalidated on write to skb metadata */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int ro_skb_slice_invalid_after_metadata_write(struct __sk_buff *skb)
+{
+	struct bpf_dynptr data, meta;
+	__u8 *d;
+
+	bpf_dynptr_from_skb(skb, 0, &data);
+	bpf_dynptr_from_skb_meta(skb, 0, &meta);
+
+	d = bpf_dynptr_slice(&data, 0, NULL, sizeof(*d));
+	if (!d)
+		return SK_DROP;
+
+	bpf_dynptr_write(&meta, 0, "x", 1, 0);
+
+	/* this should fail */
+	val = *d;
+
+	return SK_PASS;
+}
+
+/* Read-write skb data slice is invalidated on write to skb metadata */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int rw_skb_slice_invalid_after_metadata_write(struct __sk_buff *skb)
+{
+	struct bpf_dynptr data, meta;
+	__u8 *d;
+
+	bpf_dynptr_from_skb(skb, 0, &data);
+	bpf_dynptr_from_skb_meta(skb, 0, &meta);
+
+	d = bpf_dynptr_slice_rdwr(&data, 0, NULL, sizeof(*d));
+	if (!d)
+		return SK_DROP;
+
+	bpf_dynptr_write(&meta, 0, "x", 1, 0);
+
+	/* this should fail */
+	*d = 42;
+
+	return SK_PASS;
+}
+
+/* Read-only skb metadata slice is invalidated on write to skb data */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int ro_skb_meta_slice_invalid_after_payload_write(struct __sk_buff *skb)
+{
+	struct bpf_dynptr data, meta;
+	__u8 *md;
+
+	bpf_dynptr_from_skb(skb, 0, &data);
+	bpf_dynptr_from_skb_meta(skb, 0, &meta);
+
+	md = bpf_dynptr_slice(&meta, 0, NULL, sizeof(*md));
+	if (!md)
+		return SK_DROP;
+
+	bpf_dynptr_write(&data, 0, "x", 1, 0);
+
+	/* this should fail */
+	val = *md;
+
+	return SK_PASS;
+}
+
+/* Read-write skb metadata slice is invalidated on write to skb data slice */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int rw_skb_meta_slice_invalid_after_payload_write(struct __sk_buff *skb)
+{
+	struct bpf_dynptr data, meta;
+	__u8 *md;
+
+	bpf_dynptr_from_skb(skb, 0, &data);
+	bpf_dynptr_from_skb_meta(skb, 0, &meta);
+
+	md = bpf_dynptr_slice_rdwr(&meta, 0, NULL, sizeof(*md));
+	if (!md)
+		return SK_DROP;
+
+	bpf_dynptr_write(&data, 0, "x", 1, 0);
+
+	/* this should fail */
+	*md = 42;
+
+	return SK_PASS;
+}
+
+/* Read-only skb metadata slice is invalidated whenever a helper changes packet data */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int ro_skb_meta_slice_invalid_after_payload_helper(struct __sk_buff *skb)
+{
+	struct bpf_dynptr meta;
+	__u8 *md;
+
+	bpf_dynptr_from_skb_meta(skb, 0, &meta);
+
+	md = bpf_dynptr_slice(&meta, 0, NULL, sizeof(*md));
+	if (!md)
+		return SK_DROP;
+
+	if (bpf_skb_pull_data(skb, skb->len))
+		return SK_DROP;
+
+	/* this should fail */
+	val = *md;
+
+	return SK_PASS;
+}
+
+/* Read-write skb metadata slice is invalidated whenever a helper changes packet data */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int rw_skb_meta_slice_invalid_after_payload_helper(struct __sk_buff *skb)
+{
+	struct bpf_dynptr meta;
+	__u8 *md;
+
+	bpf_dynptr_from_skb_meta(skb, 0, &meta);
+
+	md = bpf_dynptr_slice_rdwr(&meta, 0, NULL, sizeof(*md));
+	if (!md)
+		return SK_DROP;
+
+	if (bpf_skb_pull_data(skb, skb->len))
+		return SK_DROP;
+
+	/* this should fail */
+	*md = 42;
+
+	return SK_PASS;
+}
+
+/* Read-only skb metadata slice is invalidated on write to skb metadata */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int ro_skb_meta_slice_invalid_after_metadata_write(struct __sk_buff *skb)
+{
+	struct bpf_dynptr meta;
+	__u8 *md;
+
+	bpf_dynptr_from_skb_meta(skb, 0, &meta);
+
+	md = bpf_dynptr_slice(&meta, 0, NULL, sizeof(*md));
+	if (!md)
+		return SK_DROP;
+
+	bpf_dynptr_write(&meta, 0, "x", 1, 0);
+
+	/* this should fail */
+	val = *md;
+
+	return SK_PASS;
+}
+
+/* Read-write skb metadata slice is invalidated on write to skb metadata */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int rw_skb_meta_slice_invalid_after_metadata_write(struct __sk_buff *skb)
+{
+	struct bpf_dynptr meta;
+	__u8 *md;
+
+	bpf_dynptr_from_skb_meta(skb, 0, &meta);
+
+	md = bpf_dynptr_slice_rdwr(&meta, 0, NULL, sizeof(*md));
+	if (!md)
+		return SK_DROP;
+
+	bpf_dynptr_write(&meta, 0, "x", 1, 0);
+
+	/* this should fail */
+	*md = 42;
+
+	return SK_PASS;
+}
+
+/* The read-only data slice is invalidated whenever a helper changes packet data */
+SEC("?xdp")
+__failure __msg("invalid mem access 'scalar'")
+int xdp_invalid_data_slice1(struct xdp_md *xdp)
+{
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+	char buffer[sizeof(*hdr)] = {};
+
+	bpf_dynptr_from_xdp(xdp, 0, &ptr);
+	hdr = bpf_dynptr_slice(&ptr, 0, buffer, sizeof(buffer));
+	if (!hdr)
+		return SK_DROP;
+
+	val = hdr->h_proto;
+
+	if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(*hdr)))
+		return XDP_DROP;
+
+	/* this should fail */
+	val = hdr->h_proto;
+
+	return XDP_PASS;
+}
+
+/* The read-write data slice is invalidated whenever a helper changes packet data */
+SEC("?xdp")
+__failure __msg("invalid mem access 'scalar'")
+int xdp_invalid_data_slice2(struct xdp_md *xdp)
+{
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+	char buffer[sizeof(*hdr)] = {};
+
+	bpf_dynptr_from_xdp(xdp, 0, &ptr);
+	hdr = bpf_dynptr_slice_rdwr(&ptr, 0, buffer, sizeof(buffer));
+	if (!hdr)
+		return SK_DROP;
+
+	hdr->h_proto = 9;
+
+	if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(*hdr)))
+		return XDP_DROP;
+
+	/* this should fail */
+	hdr->h_proto = 1;
+
+	return XDP_PASS;
+}
+
+/* Only supported prog type can create skb-type dynptrs */
+SEC("?raw_tp")
+__failure __msg("calling kernel function bpf_dynptr_from_skb is not allowed")
+int skb_invalid_ctx(void *ctx)
+{
+	struct bpf_dynptr ptr;
+
+	/* this should fail */
+	bpf_dynptr_from_skb(ctx, 0, &ptr);
+
+	return 0;
+}
+
+/* Only supported prog type can create skb_meta-type dynptrs */
+SEC("?raw_tp")
+__failure __msg("calling kernel function bpf_dynptr_from_skb_meta is not allowed")
+int skb_meta_invalid_ctx(void *ctx)
+{
+	struct bpf_dynptr meta;
+
+	/* this should fail */
+	bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+
+	return 0;
+}
+
+SEC("fentry/skb_tx_error")
+__failure __msg("must be referenced or trusted")
+int BPF_PROG(skb_invalid_ctx_fentry, void *skb)
+{
+	struct bpf_dynptr ptr;
+
+	/* this should fail */
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	return 0;
+}
+
+SEC("fexit/skb_tx_error")
+__failure __msg("must be referenced or trusted")
+int BPF_PROG(skb_invalid_ctx_fexit, void *skb)
+{
+	struct bpf_dynptr ptr;
+
+	/* this should fail */
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	return 0;
+}
+
+/* Reject writes to dynptr slot for uninit arg */
+SEC("?raw_tp")
+__failure __msg("potential write to dynptr at off=-16")
+int uninit_write_into_slot(void *ctx)
+{
+	struct {
+		char buf[64];
+		struct bpf_dynptr ptr;
+	} data;
+
+	bpf_ringbuf_reserve_dynptr(&ringbuf, 80, 0, &data.ptr);
+	/* this should fail */
+	bpf_get_current_comm(data.buf, 80);
+
+	return 0;
+}
+
+/* Only supported prog type can create xdp-type dynptrs */
+SEC("?raw_tp")
+__failure __msg("calling kernel function bpf_dynptr_from_xdp is not allowed")
+int xdp_invalid_ctx(void *ctx)
+{
+	struct bpf_dynptr ptr;
+
+	/* this should fail */
+	bpf_dynptr_from_xdp(ctx, 0, &ptr);
+
+	return 0;
+}
+
+__u32 hdr_size = sizeof(struct ethhdr);
+/* Can't pass in variable-sized len to bpf_dynptr_slice */
+SEC("?tc")
+__failure __msg("unbounded memory access")
+int dynptr_slice_var_len1(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+	char buffer[sizeof(*hdr)] = {};
+
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	/* this should fail */
+	hdr = bpf_dynptr_slice(&ptr, 0, buffer, hdr_size);
+	if (!hdr)
+		return SK_DROP;
+
+	return SK_PASS;
+}
+
+/* Can't pass in variable-sized len to bpf_dynptr_slice */
+SEC("?tc")
+__failure __msg("must be a known constant")
+int dynptr_slice_var_len2(struct __sk_buff *skb)
+{
+	char buffer[sizeof(struct ethhdr)] = {};
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	if (hdr_size <= sizeof(buffer)) {
+		/* this should fail */
+		hdr = bpf_dynptr_slice_rdwr(&ptr, 0, buffer, hdr_size);
+		if (!hdr)
+			return SK_DROP;
+		hdr->h_proto = 12;
+	}
+
+	return SK_PASS;
+}
+
+static int callback(__u32 index, void *data)
+{
+        *(__u32 *)data = 123;
+
+        return 0;
+}
+
+/* If the dynptr is written into in a callback function, its data
+ * slices should be invalidated as well.
+ */
+SEC("?raw_tp")
+__failure __msg("invalid mem access 'scalar'")
+int invalid_data_slices(void *ctx)
+{
+	struct bpf_dynptr ptr;
+	__u32 *slice;
+
+	if (get_map_val_dynptr(&ptr))
+		return 0;
+
+	slice = bpf_dynptr_data(&ptr, 0, sizeof(__u32));
+	if (!slice)
+		return 0;
+
+	bpf_loop(10, callback, &ptr, 0);
+
+	/* this should fail */
+	*slice = 1;
+
+	return 0;
+}
+
+/* Program types that don't allow writes to packet data should fail if
+ * bpf_dynptr_slice_rdwr is called
+ */
+SEC("cgroup_skb/ingress")
+__failure __msg("the prog does not allow writes to packet data")
+int invalid_slice_rdwr_rdonly(struct __sk_buff *skb)
+{
+	char buffer[sizeof(struct ethhdr)] = {};
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	/* this should fail since cgroup_skb doesn't allow
+	 * changing packet data
+	 */
+	hdr = bpf_dynptr_slice_rdwr(&ptr, 0, buffer, sizeof(buffer));
+	__sink(hdr);
+
+	return 0;
+}
+
+/* bpf_dynptr_adjust can only be called on initialized dynptrs */
+SEC("?raw_tp")
+__failure __msg("Expected an initialized dynptr as arg #0")
+int dynptr_adjust_invalid(void *ctx)
+{
+	struct bpf_dynptr ptr = {};
+
+	/* this should fail */
+	bpf_dynptr_adjust(&ptr, 1, 2);
+
+	return 0;
+}
+
+/* bpf_dynptr_is_null can only be called on initialized dynptrs */
+SEC("?raw_tp")
+__failure __msg("Expected an initialized dynptr as arg #0")
+int dynptr_is_null_invalid(void *ctx)
+{
+	struct bpf_dynptr ptr = {};
+
+	/* this should fail */
+	bpf_dynptr_is_null(&ptr);
+
+	return 0;
+}
+
+/* bpf_dynptr_is_rdonly can only be called on initialized dynptrs */
+SEC("?raw_tp")
+__failure __msg("Expected an initialized dynptr as arg #0")
+int dynptr_is_rdonly_invalid(void *ctx)
+{
+	struct bpf_dynptr ptr = {};
+
+	/* this should fail */
+	bpf_dynptr_is_rdonly(&ptr);
+
+	return 0;
+}
+
+/* bpf_dynptr_size can only be called on initialized dynptrs */
+SEC("?raw_tp")
+__failure __msg("Expected an initialized dynptr as arg #0")
+int dynptr_size_invalid(void *ctx)
+{
+	struct bpf_dynptr ptr = {};
+
+	/* this should fail */
+	bpf_dynptr_size(&ptr);
+
+	return 0;
+}
+
+/* Only initialized dynptrs can be cloned */
+SEC("?raw_tp")
+__failure __msg("Expected an initialized dynptr as arg #0")
+int clone_invalid1(void *ctx)
+{
+	struct bpf_dynptr ptr1 = {};
+	struct bpf_dynptr ptr2;
+
+	/* this should fail */
+	bpf_dynptr_clone(&ptr1, &ptr2);
+
+	return 0;
+}
+
+/* Can't overwrite an existing dynptr when cloning */
+SEC("?xdp")
+__failure __msg("cannot overwrite referenced dynptr")
+int clone_invalid2(struct xdp_md *xdp)
+{
+	struct bpf_dynptr ptr1;
+	struct bpf_dynptr clone;
+
+	bpf_dynptr_from_xdp(xdp, 0, &ptr1);
+
+	bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &clone);
+
+	/* this should fail */
+	bpf_dynptr_clone(&ptr1, &clone);
+
+	bpf_ringbuf_submit_dynptr(&clone, 0);
+
+	return 0;
+}
+
+/* Invalidating a dynptr should invalidate its clones */
+SEC("?raw_tp")
+__failure __msg("Expected an initialized dynptr as arg #2")
+int clone_invalidate1(void *ctx)
+{
+	struct bpf_dynptr clone;
+	struct bpf_dynptr ptr;
+	char read_data[64];
+
+	bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr);
+
+	bpf_dynptr_clone(&ptr, &clone);
+
+	bpf_ringbuf_submit_dynptr(&ptr, 0);
+
+	/* this should fail */
+	bpf_dynptr_read(read_data, sizeof(read_data), &clone, 0, 0);
+
+	return 0;
+}
+
+/* Invalidating a dynptr should invalidate its parent */
+SEC("?raw_tp")
+__failure __msg("Expected an initialized dynptr as arg #2")
+int clone_invalidate2(void *ctx)
+{
+	struct bpf_dynptr ptr;
+	struct bpf_dynptr clone;
+	char read_data[64];
+
+	bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr);
+
+	bpf_dynptr_clone(&ptr, &clone);
+
+	bpf_ringbuf_submit_dynptr(&clone, 0);
+
+	/* this should fail */
+	bpf_dynptr_read(read_data, sizeof(read_data), &ptr, 0, 0);
+
+	return 0;
+}
+
+/* Invalidating a dynptr should invalidate its siblings */
+SEC("?raw_tp")
+__failure __msg("Expected an initialized dynptr as arg #2")
+int clone_invalidate3(void *ctx)
+{
+	struct bpf_dynptr ptr;
+	struct bpf_dynptr clone1;
+	struct bpf_dynptr clone2;
+	char read_data[64];
+
+	bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr);
+
+	bpf_dynptr_clone(&ptr, &clone1);
+
+	bpf_dynptr_clone(&ptr, &clone2);
+
+	bpf_ringbuf_submit_dynptr(&clone2, 0);
+
+	/* this should fail */
+	bpf_dynptr_read(read_data, sizeof(read_data), &clone1, 0, 0);
+
+	return 0;
+}
+
+/* Invalidating a dynptr should invalidate any data slices
+ * of its clones
+ */
+SEC("?raw_tp")
+__failure __msg("invalid mem access 'scalar'")
+int clone_invalidate4(void *ctx)
+{
+	struct bpf_dynptr ptr;
+	struct bpf_dynptr clone;
+	int *data;
+
+	bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr);
+
+	bpf_dynptr_clone(&ptr, &clone);
+	data = bpf_dynptr_data(&clone, 0, sizeof(val));
+	if (!data)
+		return 0;
+
+	bpf_ringbuf_submit_dynptr(&ptr, 0);
+
+	/* this should fail */
+	*data = 123;
+
+	return 0;
+}
+
+/* Invalidating a dynptr should invalidate any data slices
+ * of its parent
+ */
+SEC("?raw_tp")
+__failure __msg("invalid mem access 'scalar'")
+int clone_invalidate5(void *ctx)
+{
+	struct bpf_dynptr ptr;
+	struct bpf_dynptr clone;
+	int *data;
+
+	bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr);
+	data = bpf_dynptr_data(&ptr, 0, sizeof(val));
+	if (!data)
+		return 0;
+
+	bpf_dynptr_clone(&ptr, &clone);
+
+	bpf_ringbuf_submit_dynptr(&clone, 0);
+
+	/* this should fail */
+	*data = 123;
+
+	return 0;
+}
+
+/* Invalidating a dynptr should invalidate any data slices
+ * of its sibling
+ */
+SEC("?raw_tp")
+__failure __msg("invalid mem access 'scalar'")
+int clone_invalidate6(void *ctx)
+{
+	struct bpf_dynptr ptr;
+	struct bpf_dynptr clone1;
+	struct bpf_dynptr clone2;
+	int *data;
+
+	bpf_ringbuf_reserve_dynptr(&ringbuf, val, 0, &ptr);
+
+	bpf_dynptr_clone(&ptr, &clone1);
+
+	bpf_dynptr_clone(&ptr, &clone2);
+
+	data = bpf_dynptr_data(&clone1, 0, sizeof(val));
+	if (!data)
+		return 0;
+
+	bpf_ringbuf_submit_dynptr(&clone2, 0);
+
+	/* this should fail */
+	*data = 123;
+
+	return 0;
+}
+
+/* A skb clone's data slices should be invalid anytime packet data changes */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int clone_skb_packet_data(struct __sk_buff *skb)
+{
+	char buffer[sizeof(__u32)] = {};
+	struct bpf_dynptr clone;
+	struct bpf_dynptr ptr;
+	__u32 *data;
+
+	bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	bpf_dynptr_clone(&ptr, &clone);
+	data = bpf_dynptr_slice_rdwr(&clone, 0, buffer, sizeof(buffer));
+	if (!data)
+		return XDP_DROP;
+
+	if (bpf_skb_pull_data(skb, skb->len))
+		return SK_DROP;
+
+	/* this should fail */
+	*data = 123;
+
+	return 0;
+}
+
+/* A skb clone's metadata slice becomes invalid anytime packet data changes */
+SEC("?tc")
+__failure __msg("invalid mem access 'scalar'")
+int clone_skb_packet_meta(struct __sk_buff *skb)
+{
+	struct bpf_dynptr clone, meta;
+	__u8 *md;
+
+	bpf_dynptr_from_skb_meta(skb, 0, &meta);
+	bpf_dynptr_clone(&meta, &clone);
+	md = bpf_dynptr_slice_rdwr(&clone, 0, NULL, sizeof(*md));
+	if (!md)
+		return SK_DROP;
+
+	if (bpf_skb_pull_data(skb, skb->len))
+		return SK_DROP;
+
+	/* this should fail */
+	*md = 42;
+
+	return 0;
+}
+
+/* A xdp clone's data slices should be invalid anytime packet data changes */
+SEC("?xdp")
+__failure __msg("invalid mem access 'scalar'")
+int clone_xdp_packet_data(struct xdp_md *xdp)
+{
+	char buffer[sizeof(__u32)] = {};
+	struct bpf_dynptr clone;
+	struct bpf_dynptr ptr;
+	struct ethhdr *hdr;
+	__u32 *data;
+
+	bpf_dynptr_from_xdp(xdp, 0, &ptr);
+
+	bpf_dynptr_clone(&ptr, &clone);
+	data = bpf_dynptr_slice_rdwr(&clone, 0, buffer, sizeof(buffer));
+	if (!data)
+		return XDP_DROP;
+
+	if (bpf_xdp_adjust_head(xdp, 0 - (int)sizeof(*hdr)))
+		return XDP_DROP;
+
+	/* this should fail */
+	*data = 123;
+
+	return 0;
+}
+
+/* Buffers that are provided must be sufficiently long */
+SEC("?cgroup_skb/egress")
+__failure __msg("memory, len pair leads to invalid memory access")
+int test_dynptr_skb_small_buff(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	char buffer[8] = {};
+	__u64 *data;
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr)) {
+		err = 1;
+		return 1;
+	}
+
+	/* This may return NULL. SKB may require a buffer */
+	data = bpf_dynptr_slice(&ptr, 0, buffer, 9);
+
+	return !!data;
+}
+
+__noinline long global_call_bpf_dynptr(const struct bpf_dynptr *dynptr)
+{
+	long ret = 0;
+	/* Avoid leaving this global function empty to avoid having the compiler
+	 * optimize away the call to this global function.
+	 */
+	__sink(ret);
+	return ret;
+}
+
+SEC("?raw_tp")
+__failure __msg("arg#0 expected pointer to stack or const struct bpf_dynptr")
+int test_dynptr_reg_type(void *ctx)
+{
+	struct task_struct *current = NULL;
+	/* R1 should be holding a PTR_TO_BTF_ID, so this shouldn't be a
+	 * reg->type that can be passed to a function accepting a
+	 * ARG_PTR_TO_DYNPTR | MEM_RDONLY. process_dynptr_func() should catch
+	 * this.
+	 */
+	global_call_bpf_dynptr((const struct bpf_dynptr *)current);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/dynptr_success.c b/tools/testing/selftests/bpf/progs/dynptr_success.c
index 35db7c6c1fc7..e0d672d93adf 100644
--- a/tools/testing/selftests/bpf/progs/dynptr_success.c
+++ b/tools/testing/selftests/bpf/progs/dynptr_success.c
@@ -1,17 +1,21 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2022 Facebook */
 
+#include <vmlinux.h>
 #include <string.h>
-#include <linux/bpf.h>
+#include <stdbool.h>
 #include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
 #include "bpf_misc.h"
 #include "errno.h"
 
+#define PAGE_SIZE_64K 65536
+
 char _license[] SEC("license") = "GPL";
 
 int pid, err, val;
 
-struct sample {
+struct ringbuf_sample {
 	int pid;
 	int seq;
 	long value;
@@ -30,11 +34,11 @@ struct {
 	__type(value, __u32);
 } array_map SEC(".maps");
 
-SEC("tp/syscalls/sys_enter_nanosleep")
+SEC("?tp/syscalls/sys_enter_nanosleep")
 int test_read_write(void *ctx)
 {
 	char write_data[64] = "hello there, world!!";
-	char read_data[64] = {}, buf[64] = {};
+	char read_data[64] = {};
 	struct bpf_dynptr ptr;
 	int i;
 
@@ -61,8 +65,8 @@ int test_read_write(void *ctx)
 	return 0;
 }
 
-SEC("tp/syscalls/sys_enter_nanosleep")
-int test_data_slice(void *ctx)
+SEC("?tp/syscalls/sys_enter_nanosleep")
+int test_dynptr_data(void *ctx)
 {
 	__u32 key = 0, val = 235, *map_val;
 	struct bpf_dynptr ptr;
@@ -118,7 +122,7 @@ int test_data_slice(void *ctx)
 
 static int ringbuf_callback(__u32 index, void *data)
 {
-	struct sample *sample;
+	struct ringbuf_sample *sample;
 
 	struct bpf_dynptr *ptr = (struct bpf_dynptr *)data;
 
@@ -131,11 +135,11 @@ static int ringbuf_callback(__u32 index, void *data)
 	return 0;
 }
 
-SEC("tp/syscalls/sys_enter_nanosleep")
+SEC("?tp/syscalls/sys_enter_nanosleep")
 int test_ringbuf(void *ctx)
 {
 	struct bpf_dynptr ptr;
-	struct sample *sample;
+	struct ringbuf_sample *sample;
 
 	if (bpf_get_current_pid_tgid() >> 32 != pid)
 		return 0;
@@ -163,3 +167,971 @@ done:
 	bpf_ringbuf_discard_dynptr(&ptr, 0);
 	return 0;
 }
+
+SEC("?cgroup_skb/egress")
+int test_skb_readonly(struct __sk_buff *skb)
+{
+	__u8 write_data[2] = {1, 2};
+	struct bpf_dynptr ptr;
+	int ret;
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr)) {
+		err = 1;
+		return 1;
+	}
+
+	/* since cgroup skbs are read only, writes should fail */
+	ret = bpf_dynptr_write(&ptr, 0, write_data, sizeof(write_data), 0);
+	if (ret != -EINVAL) {
+		err = 2;
+		return 1;
+	}
+
+	return 1;
+}
+
+SEC("?cgroup_skb/egress")
+int test_dynptr_skb_data(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	__u64 *data;
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr)) {
+		err = 1;
+		return 1;
+	}
+
+	/* This should return NULL. Must use bpf_dynptr_slice API */
+	data = bpf_dynptr_data(&ptr, 0, 1);
+	if (data) {
+		err = 2;
+		return 1;
+	}
+
+	return 1;
+}
+
+SEC("?tc")
+int test_dynptr_skb_meta_data(struct __sk_buff *skb)
+{
+	struct bpf_dynptr meta;
+	__u8 *md;
+	int ret;
+
+	err = 1;
+	ret = bpf_dynptr_from_skb_meta(skb, 0, &meta);
+	if (ret)
+		return 1;
+
+	/* This should return NULL. Must use bpf_dynptr_slice API */
+	err = 2;
+	md = bpf_dynptr_data(&meta, 0, sizeof(*md));
+	if (md)
+		return 1;
+
+	err = 0;
+	return 1;
+}
+
+/* Check that skb metadata dynptr ops don't accept any flags. */
+SEC("?tc")
+int test_dynptr_skb_meta_flags(struct __sk_buff *skb)
+{
+	const __u64 INVALID_FLAGS = ~0ULL;
+	struct bpf_dynptr meta;
+	__u8 buf;
+	int ret;
+
+	err = 1;
+	ret = bpf_dynptr_from_skb_meta(skb, INVALID_FLAGS, &meta);
+	if (ret != -EINVAL)
+		return 1;
+
+	err = 2;
+	ret = bpf_dynptr_from_skb_meta(skb, 0, &meta);
+	if (ret)
+		return 1;
+
+	err = 3;
+	ret = bpf_dynptr_read(&buf, 0, &meta, 0, INVALID_FLAGS);
+	if (ret != -EINVAL)
+		return 1;
+
+	err = 4;
+	ret = bpf_dynptr_write(&meta, 0, &buf, 0, INVALID_FLAGS);
+	if (ret != -EINVAL)
+		return 1;
+
+	err = 0;
+	return 1;
+}
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int test_adjust(void *ctx)
+{
+	struct bpf_dynptr ptr;
+	__u32 bytes = 64;
+	__u32 off = 10;
+	__u32 trim = 15;
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	err = bpf_ringbuf_reserve_dynptr(&ringbuf, bytes, 0, &ptr);
+	if (err) {
+		err = 1;
+		goto done;
+	}
+
+	if (bpf_dynptr_size(&ptr) != bytes) {
+		err = 2;
+		goto done;
+	}
+
+	/* Advance the dynptr by off */
+	err = bpf_dynptr_adjust(&ptr, off, bpf_dynptr_size(&ptr));
+	if (err) {
+		err = 3;
+		goto done;
+	}
+
+	if (bpf_dynptr_size(&ptr) != bytes - off) {
+		err = 4;
+		goto done;
+	}
+
+	/* Trim the dynptr */
+	err = bpf_dynptr_adjust(&ptr, off, 15);
+	if (err) {
+		err = 5;
+		goto done;
+	}
+
+	/* Check that the size was adjusted correctly */
+	if (bpf_dynptr_size(&ptr) != trim - off) {
+		err = 6;
+		goto done;
+	}
+
+done:
+	bpf_ringbuf_discard_dynptr(&ptr, 0);
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int test_adjust_err(void *ctx)
+{
+	char write_data[45] = "hello there, world!!";
+	struct bpf_dynptr ptr;
+	__u32 size = 64;
+	__u32 off = 20;
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 0, &ptr)) {
+		err = 1;
+		goto done;
+	}
+
+	/* Check that start can't be greater than end */
+	if (bpf_dynptr_adjust(&ptr, 5, 1) != -EINVAL) {
+		err = 2;
+		goto done;
+	}
+
+	/* Check that start can't be greater than size */
+	if (bpf_dynptr_adjust(&ptr, size + 1, size + 1) != -ERANGE) {
+		err = 3;
+		goto done;
+	}
+
+	/* Check that end can't be greater than size */
+	if (bpf_dynptr_adjust(&ptr, 0, size + 1) != -ERANGE) {
+		err = 4;
+		goto done;
+	}
+
+	if (bpf_dynptr_adjust(&ptr, off, size)) {
+		err = 5;
+		goto done;
+	}
+
+	/* Check that you can't write more bytes than available into the dynptr
+	 * after you've adjusted it
+	 */
+	if (bpf_dynptr_write(&ptr, 0, &write_data, sizeof(write_data), 0) != -E2BIG) {
+		err = 6;
+		goto done;
+	}
+
+	/* Check that even after adjusting, submitting/discarding
+	 * a ringbuf dynptr works
+	 */
+	bpf_ringbuf_submit_dynptr(&ptr, 0);
+	return 0;
+
+done:
+	bpf_ringbuf_discard_dynptr(&ptr, 0);
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int test_zero_size_dynptr(void *ctx)
+{
+	char write_data = 'x', read_data;
+	struct bpf_dynptr ptr;
+	__u32 size = 64;
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 0, &ptr)) {
+		err = 1;
+		goto done;
+	}
+
+	/* After this, the dynptr has a size of 0 */
+	if (bpf_dynptr_adjust(&ptr, size, size)) {
+		err = 2;
+		goto done;
+	}
+
+	/* Test that reading + writing non-zero bytes is not ok */
+	if (bpf_dynptr_read(&read_data, sizeof(read_data), &ptr, 0, 0) != -E2BIG) {
+		err = 3;
+		goto done;
+	}
+
+	if (bpf_dynptr_write(&ptr, 0, &write_data, sizeof(write_data), 0) != -E2BIG) {
+		err = 4;
+		goto done;
+	}
+
+	/* Test that reading + writing 0 bytes from a 0-size dynptr is ok */
+	if (bpf_dynptr_read(&read_data, 0, &ptr, 0, 0)) {
+		err = 5;
+		goto done;
+	}
+
+	if (bpf_dynptr_write(&ptr, 0, &write_data, 0, 0)) {
+		err = 6;
+		goto done;
+	}
+
+	err = 0;
+
+done:
+	bpf_ringbuf_discard_dynptr(&ptr, 0);
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_nanosleep")
+int test_dynptr_is_null(void *ctx)
+{
+	struct bpf_dynptr ptr1;
+	struct bpf_dynptr ptr2;
+	__u64 size = 4;
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	/* Pass in invalid flags, get back an invalid dynptr */
+	if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 123, &ptr1) != -EINVAL) {
+		err = 1;
+		goto exit_early;
+	}
+
+	/* Test that the invalid dynptr is null */
+	if (!bpf_dynptr_is_null(&ptr1)) {
+		err = 2;
+		goto exit_early;
+	}
+
+	/* Get a valid dynptr */
+	if (bpf_ringbuf_reserve_dynptr(&ringbuf, size, 0, &ptr2)) {
+		err = 3;
+		goto exit;
+	}
+
+	/* Test that the valid dynptr is not null */
+	if (bpf_dynptr_is_null(&ptr2)) {
+		err = 4;
+		goto exit;
+	}
+
+exit:
+	bpf_ringbuf_discard_dynptr(&ptr2, 0);
+exit_early:
+	bpf_ringbuf_discard_dynptr(&ptr1, 0);
+	return 0;
+}
+
+SEC("cgroup_skb/egress")
+int test_dynptr_is_rdonly(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr1;
+	struct bpf_dynptr ptr2;
+	struct bpf_dynptr ptr3;
+
+	/* Pass in invalid flags, get back an invalid dynptr */
+	if (bpf_dynptr_from_skb(skb, 123, &ptr1) != -EINVAL) {
+		err = 1;
+		return 0;
+	}
+
+	/* Test that an invalid dynptr is_rdonly returns false */
+	if (bpf_dynptr_is_rdonly(&ptr1)) {
+		err = 2;
+		return 0;
+	}
+
+	/* Get a read-only dynptr */
+	if (bpf_dynptr_from_skb(skb, 0, &ptr2)) {
+		err = 3;
+		return 0;
+	}
+
+	/* Test that the dynptr is read-only */
+	if (!bpf_dynptr_is_rdonly(&ptr2)) {
+		err = 4;
+		return 0;
+	}
+
+	/* Get a read-writeable dynptr */
+	if (bpf_ringbuf_reserve_dynptr(&ringbuf, 64, 0, &ptr3)) {
+		err = 5;
+		goto done;
+	}
+
+	/* Test that the dynptr is read-only */
+	if (bpf_dynptr_is_rdonly(&ptr3)) {
+		err = 6;
+		goto done;
+	}
+
+done:
+	bpf_ringbuf_discard_dynptr(&ptr3, 0);
+	return 0;
+}
+
+SEC("cgroup_skb/egress")
+int test_dynptr_clone(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr1;
+	struct bpf_dynptr ptr2;
+	__u32 off = 2, size;
+
+	/* Get a dynptr */
+	if (bpf_dynptr_from_skb(skb, 0, &ptr1)) {
+		err = 1;
+		return 0;
+	}
+
+	if (bpf_dynptr_adjust(&ptr1, off, bpf_dynptr_size(&ptr1))) {
+		err = 2;
+		return 0;
+	}
+
+	/* Clone the dynptr */
+	if (bpf_dynptr_clone(&ptr1, &ptr2)) {
+		err = 3;
+		return 0;
+	}
+
+	size = bpf_dynptr_size(&ptr1);
+
+	/* Check that the clone has the same size and rd-only */
+	if (bpf_dynptr_size(&ptr2) != size) {
+		err = 4;
+		return 0;
+	}
+
+	if (bpf_dynptr_is_rdonly(&ptr2) != bpf_dynptr_is_rdonly(&ptr1)) {
+		err = 5;
+		return 0;
+	}
+
+	/* Advance and trim the original dynptr */
+	bpf_dynptr_adjust(&ptr1, 5, 5);
+
+	/* Check that only original dynptr was affected, and the clone wasn't */
+	if (bpf_dynptr_size(&ptr2) != size) {
+		err = 6;
+		return 0;
+	}
+
+	return 0;
+}
+
+SEC("?cgroup_skb/egress")
+int test_dynptr_skb_no_buff(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	__u64 *data;
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr)) {
+		err = 1;
+		return 1;
+	}
+
+	/* This may return NULL. SKB may require a buffer */
+	data = bpf_dynptr_slice(&ptr, 0, NULL, 1);
+
+	return !!data;
+}
+
+SEC("?cgroup_skb/egress")
+int test_dynptr_skb_strcmp(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	char *data;
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr)) {
+		err = 1;
+		return 1;
+	}
+
+	/* This may return NULL. SKB may require a buffer */
+	data = bpf_dynptr_slice(&ptr, 0, NULL, 10);
+	if (data) {
+		bpf_strncmp(data, 10, "foo");
+		return 1;
+	}
+
+	return 1;
+}
+
+SEC("tp_btf/kfree_skb")
+int BPF_PROG(test_dynptr_skb_tp_btf, void *skb, void *location)
+{
+	__u8 write_data[2] = {1, 2};
+	struct bpf_dynptr ptr;
+	int ret;
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr)) {
+		err = 1;
+		return 1;
+	}
+
+	/* since tp_btf skbs are read only, writes should fail */
+	ret = bpf_dynptr_write(&ptr, 0, write_data, sizeof(write_data), 0);
+	if (ret != -EINVAL) {
+		err = 2;
+		return 1;
+	}
+
+	return 1;
+}
+
+static inline int bpf_memcmp(const char *a, const char *b, u32 size)
+{
+	int i;
+
+	bpf_for(i, 0, size) {
+		if (a[i] != b[i])
+			return a[i] < b[i] ? -1 : 1;
+	}
+	return 0;
+}
+
+SEC("?tp/syscalls/sys_enter_nanosleep")
+int test_dynptr_copy(void *ctx)
+{
+	char data[] = "hello there, world!!";
+	char buf[32] = {'\0'};
+	__u32 sz = sizeof(data);
+	struct bpf_dynptr src, dst;
+
+	bpf_ringbuf_reserve_dynptr(&ringbuf, sz, 0, &src);
+	bpf_ringbuf_reserve_dynptr(&ringbuf, sz, 0, &dst);
+
+	/* Test basic case of copying contiguous memory backed dynptrs */
+	err = bpf_dynptr_write(&src, 0, data, sz, 0);
+	err = err ?: bpf_dynptr_copy(&dst, 0, &src, 0, sz);
+	err = err ?: bpf_dynptr_read(buf, sz, &dst, 0, 0);
+	err = err ?: bpf_memcmp(data, buf, sz);
+
+	/* Test that offsets are handled correctly */
+	err = err ?: bpf_dynptr_copy(&dst, 3, &src, 5, sz - 5);
+	err = err ?: bpf_dynptr_read(buf, sz - 5, &dst, 3, 0);
+	err = err ?: bpf_memcmp(data + 5, buf, sz - 5);
+
+	bpf_ringbuf_discard_dynptr(&src, 0);
+	bpf_ringbuf_discard_dynptr(&dst, 0);
+	return 0;
+}
+
+SEC("xdp")
+int test_dynptr_copy_xdp(struct xdp_md *xdp)
+{
+	struct bpf_dynptr ptr_buf, ptr_xdp;
+	char data[] = "qwertyuiopasdfghjkl";
+	char buf[32] = {'\0'};
+	__u32 len = sizeof(data), xdp_data_size;
+	int i, chunks = 200;
+
+	/* ptr_xdp is backed by non-contiguous memory */
+	bpf_dynptr_from_xdp(xdp, 0, &ptr_xdp);
+	xdp_data_size = bpf_dynptr_size(&ptr_xdp);
+	bpf_ringbuf_reserve_dynptr(&ringbuf, len * chunks, 0, &ptr_buf);
+
+	/* Destination dynptr is backed by non-contiguous memory */
+	bpf_for(i, 0, chunks) {
+		err = bpf_dynptr_write(&ptr_buf, i * len, data, len, 0);
+		if (err)
+			goto out;
+	}
+
+	err = bpf_dynptr_copy(&ptr_xdp, 0, &ptr_buf, 0, len * chunks);
+	if (err)
+		goto out;
+
+	bpf_for(i, 0, chunks) {
+		__builtin_memset(buf, 0, sizeof(buf));
+		err = bpf_dynptr_read(&buf, len, &ptr_xdp, i * len, 0);
+		if (err)
+			goto out;
+		if (bpf_memcmp(data, buf, len) != 0)
+			goto out;
+	}
+
+	/* Source dynptr is backed by non-contiguous memory */
+	__builtin_memset(buf, 0, sizeof(buf));
+	bpf_for(i, 0, chunks) {
+		err = bpf_dynptr_write(&ptr_buf, i * len, buf, len, 0);
+		if (err)
+			goto out;
+	}
+
+	err = bpf_dynptr_copy(&ptr_buf, 0, &ptr_xdp, 0, len * chunks);
+	if (err)
+		goto out;
+
+	bpf_for(i, 0, chunks) {
+		__builtin_memset(buf, 0, sizeof(buf));
+		err = bpf_dynptr_read(&buf, len, &ptr_buf, i * len, 0);
+		if (err)
+			goto out;
+		if (bpf_memcmp(data, buf, len) != 0)
+			goto out;
+	}
+
+	/* Both source and destination dynptrs are backed by non-contiguous memory */
+	err = bpf_dynptr_copy(&ptr_xdp, 2, &ptr_xdp, len, len * (chunks - 1));
+	if (err)
+		goto out;
+
+	bpf_for(i, 0, chunks - 1) {
+		__builtin_memset(buf, 0, sizeof(buf));
+		err = bpf_dynptr_read(&buf, len, &ptr_xdp, 2 + i * len, 0);
+		if (err)
+			goto out;
+		if (bpf_memcmp(data, buf, len) != 0)
+			goto out;
+	}
+
+	if (bpf_dynptr_copy(&ptr_xdp, xdp_data_size - 3000, &ptr_xdp, 0, len * chunks) != -E2BIG)
+		err = 1;
+
+out:
+	bpf_ringbuf_discard_dynptr(&ptr_buf, 0);
+	return XDP_DROP;
+}
+
+char memset_zero_data[] = "data to be zeroed";
+
+SEC("?tp/syscalls/sys_enter_nanosleep")
+int test_dynptr_memset_zero(void *ctx)
+{
+	__u32 data_sz = sizeof(memset_zero_data);
+	char zeroes[32] = {'\0'};
+	struct bpf_dynptr ptr;
+
+	err = bpf_dynptr_from_mem(memset_zero_data, data_sz, 0, &ptr);
+	err = err ?: bpf_dynptr_memset(&ptr, 0, data_sz, 0);
+	err = err ?: bpf_memcmp(zeroes, memset_zero_data, data_sz);
+
+	return 0;
+}
+
+#define DYNPTR_MEMSET_VAL 42
+
+char memset_notzero_data[] = "data to be overwritten";
+
+SEC("?tp/syscalls/sys_enter_nanosleep")
+int test_dynptr_memset_notzero(void *ctx)
+{
+	u32 data_sz = sizeof(memset_notzero_data);
+	struct bpf_dynptr ptr;
+	char expected[32];
+
+	__builtin_memset(expected, DYNPTR_MEMSET_VAL, data_sz);
+
+	err = bpf_dynptr_from_mem(memset_notzero_data, data_sz, 0, &ptr);
+	err = err ?: bpf_dynptr_memset(&ptr, 0, data_sz, DYNPTR_MEMSET_VAL);
+	err = err ?: bpf_memcmp(expected, memset_notzero_data, data_sz);
+
+	return 0;
+}
+
+char memset_zero_offset_data[] = "data to be zeroed partially";
+
+SEC("?tp/syscalls/sys_enter_nanosleep")
+int test_dynptr_memset_zero_offset(void *ctx)
+{
+	char expected[] = "data to \0\0\0\0eroed partially";
+	__u32 data_sz = sizeof(memset_zero_offset_data);
+	struct bpf_dynptr ptr;
+
+	err = bpf_dynptr_from_mem(memset_zero_offset_data, data_sz, 0, &ptr);
+	err = err ?: bpf_dynptr_memset(&ptr, 8, 4, 0);
+	err = err ?: bpf_memcmp(expected, memset_zero_offset_data, data_sz);
+
+	return 0;
+}
+
+char memset_zero_adjusted_data[] = "data to be zeroed partially";
+
+SEC("?tp/syscalls/sys_enter_nanosleep")
+int test_dynptr_memset_zero_adjusted(void *ctx)
+{
+	char expected[] = "data\0\0\0\0be zeroed partially";
+	__u32 data_sz = sizeof(memset_zero_adjusted_data);
+	struct bpf_dynptr ptr;
+
+	err = bpf_dynptr_from_mem(memset_zero_adjusted_data, data_sz, 0, &ptr);
+	err = err ?: bpf_dynptr_adjust(&ptr, 4, 8);
+	err = err ?: bpf_dynptr_memset(&ptr, 0, bpf_dynptr_size(&ptr), 0);
+	err = err ?: bpf_memcmp(expected, memset_zero_adjusted_data, data_sz);
+
+	return 0;
+}
+
+char memset_overflow_data[] = "memset overflow data";
+
+SEC("?tp/syscalls/sys_enter_nanosleep")
+int test_dynptr_memset_overflow(void *ctx)
+{
+	__u32 data_sz = sizeof(memset_overflow_data);
+	struct bpf_dynptr ptr;
+	int ret;
+
+	err = bpf_dynptr_from_mem(memset_overflow_data, data_sz, 0, &ptr);
+	ret = bpf_dynptr_memset(&ptr, 0, data_sz + 1, 0);
+	if (ret != -E2BIG)
+		err = 1;
+
+	return 0;
+}
+
+SEC("?tp/syscalls/sys_enter_nanosleep")
+int test_dynptr_memset_overflow_offset(void *ctx)
+{
+	__u32 data_sz = sizeof(memset_overflow_data);
+	struct bpf_dynptr ptr;
+	int ret;
+
+	err = bpf_dynptr_from_mem(memset_overflow_data, data_sz, 0, &ptr);
+	ret = bpf_dynptr_memset(&ptr, 1, data_sz, 0);
+	if (ret != -E2BIG)
+		err = 1;
+
+	return 0;
+}
+
+SEC("?cgroup_skb/egress")
+int test_dynptr_memset_readonly(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	int ret;
+
+	err = bpf_dynptr_from_skb(skb, 0, &ptr);
+
+	/* cgroup skbs are read only, memset should fail */
+	ret = bpf_dynptr_memset(&ptr, 0, bpf_dynptr_size(&ptr), 0);
+	if (ret != -EINVAL)
+		err = 1;
+
+	return 0;
+}
+
+#define min_t(type, x, y) ({		\
+	type __x = (x);			\
+	type __y = (y);			\
+	__x < __y ? __x : __y; })
+
+SEC("xdp")
+int test_dynptr_memset_xdp_chunks(struct xdp_md *xdp)
+{
+	u32 data_sz, chunk_sz, offset = 0;
+	const int max_chunks = 200;
+	struct bpf_dynptr ptr_xdp;
+	char expected_buf[32];
+	char buf[32];
+	int i;
+
+	__builtin_memset(expected_buf, DYNPTR_MEMSET_VAL, sizeof(expected_buf));
+
+	/* ptr_xdp is backed by non-contiguous memory */
+	bpf_dynptr_from_xdp(xdp, 0, &ptr_xdp);
+	data_sz = bpf_dynptr_size(&ptr_xdp);
+
+	err = bpf_dynptr_memset(&ptr_xdp, 0, data_sz, DYNPTR_MEMSET_VAL);
+	if (err) {
+		/* bpf_dynptr_memset() eventually called bpf_xdp_pointer()
+		 * where if data_sz is greater than 0xffff, -EFAULT will be
+		 * returned. For 64K page size, data_sz is greater than
+		 * 64K, so error is expected and let us zero out error and
+		 * return success.
+		 */
+		if (data_sz >= PAGE_SIZE_64K)
+			err = 0;
+		goto out;
+	}
+
+	bpf_for(i, 0, max_chunks) {
+		offset = i * sizeof(buf);
+		if (offset >= data_sz)
+			goto out;
+		chunk_sz = min_t(u32, sizeof(buf), data_sz - offset);
+		err = bpf_dynptr_read(&buf, chunk_sz, &ptr_xdp, offset, 0);
+		if (err)
+			goto out;
+		err = bpf_memcmp(buf, expected_buf, sizeof(buf));
+		if (err)
+			goto out;
+	}
+out:
+	return XDP_DROP;
+}
+
+void *user_ptr;
+/* Contains the copy of the data pointed by user_ptr.
+ * Size 384 to make it not fit into a single kernel chunk when copying
+ * but less than the maximum bpf stack size (512).
+ */
+char expected_str[384];
+__u32 test_len[7] = {0/* placeholder */, 0, 1, 2, 255, 256, 257};
+
+typedef int (*bpf_read_dynptr_fn_t)(struct bpf_dynptr *dptr, u64 off,
+				    u64 size, const void *unsafe_ptr);
+
+/* Returns the offset just before the end of the maximum sized xdp fragment.
+ * Any write larger than 32 bytes will be split between 2 fragments.
+ */
+__u32 xdp_near_frag_end_offset(void)
+{
+	const __u32 headroom = 256;
+	const __u32 max_frag_size =  __PAGE_SIZE - headroom - sizeof(struct skb_shared_info);
+
+	/* 32 bytes before the approximate end of the fragment */
+	return max_frag_size - 32;
+}
+
+/* Use __always_inline on test_dynptr_probe[_str][_xdp]() and callbacks
+ * of type bpf_read_dynptr_fn_t to prevent compiler from generating
+ * indirect calls that make program fail to load with "unknown opcode" error.
+ */
+static __always_inline void test_dynptr_probe(void *ptr, bpf_read_dynptr_fn_t bpf_read_dynptr_fn)
+{
+	char buf[sizeof(expected_str)];
+	struct bpf_dynptr ptr_buf;
+	int i;
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return;
+
+	err = bpf_ringbuf_reserve_dynptr(&ringbuf, sizeof(buf), 0, &ptr_buf);
+
+	bpf_for(i, 0, ARRAY_SIZE(test_len)) {
+		__u32 len = test_len[i];
+
+		err = err ?: bpf_read_dynptr_fn(&ptr_buf, 0, test_len[i], ptr);
+		if (len > sizeof(buf))
+			break;
+		err = err ?: bpf_dynptr_read(&buf, len, &ptr_buf, 0, 0);
+
+		if (err || bpf_memcmp(expected_str, buf, len))
+			err = 1;
+
+		/* Reset buffer and dynptr */
+		__builtin_memset(buf, 0, sizeof(buf));
+		err = err ?: bpf_dynptr_write(&ptr_buf, 0, buf, len, 0);
+	}
+	bpf_ringbuf_discard_dynptr(&ptr_buf, 0);
+}
+
+static __always_inline void test_dynptr_probe_str(void *ptr,
+						  bpf_read_dynptr_fn_t bpf_read_dynptr_fn)
+{
+	char buf[sizeof(expected_str)];
+	struct bpf_dynptr ptr_buf;
+	__u32 cnt, i;
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return;
+
+	bpf_ringbuf_reserve_dynptr(&ringbuf, sizeof(buf), 0, &ptr_buf);
+
+	bpf_for(i, 0, ARRAY_SIZE(test_len)) {
+		__u32 len = test_len[i];
+
+		cnt = bpf_read_dynptr_fn(&ptr_buf, 0, len, ptr);
+		if (cnt != len)
+			err = 1;
+
+		if (len > sizeof(buf))
+			continue;
+		err = err ?: bpf_dynptr_read(&buf, len, &ptr_buf, 0, 0);
+		if (!len)
+			continue;
+		if (err || bpf_memcmp(expected_str, buf, len - 1) || buf[len - 1] != '\0')
+			err = 1;
+	}
+	bpf_ringbuf_discard_dynptr(&ptr_buf, 0);
+}
+
+static __always_inline void test_dynptr_probe_xdp(struct xdp_md *xdp, void *ptr,
+						  bpf_read_dynptr_fn_t bpf_read_dynptr_fn)
+{
+	struct bpf_dynptr ptr_xdp;
+	char buf[sizeof(expected_str)];
+	__u32 off, i;
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return;
+
+	off = xdp_near_frag_end_offset();
+	err = bpf_dynptr_from_xdp(xdp, 0, &ptr_xdp);
+
+	bpf_for(i, 0, ARRAY_SIZE(test_len)) {
+		__u32 len = test_len[i];
+
+		err = err ?: bpf_read_dynptr_fn(&ptr_xdp, off, len, ptr);
+		if (len > sizeof(buf))
+			continue;
+		err = err ?: bpf_dynptr_read(&buf, len, &ptr_xdp, off, 0);
+		if (err || bpf_memcmp(expected_str, buf, len))
+			err = 1;
+		/* Reset buffer and dynptr */
+		__builtin_memset(buf, 0, sizeof(buf));
+		err = err ?: bpf_dynptr_write(&ptr_xdp, off, buf, len, 0);
+	}
+}
+
+static __always_inline void test_dynptr_probe_str_xdp(struct xdp_md *xdp, void *ptr,
+						      bpf_read_dynptr_fn_t bpf_read_dynptr_fn)
+{
+	struct bpf_dynptr ptr_xdp;
+	char buf[sizeof(expected_str)];
+	__u32 cnt, off, i;
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return;
+
+	off = xdp_near_frag_end_offset();
+	err = bpf_dynptr_from_xdp(xdp, 0, &ptr_xdp);
+	if (err)
+		return;
+
+	bpf_for(i, 0, ARRAY_SIZE(test_len)) {
+		__u32 len = test_len[i];
+
+		cnt = bpf_read_dynptr_fn(&ptr_xdp, off, len, ptr);
+		if (cnt != len)
+			err = 1;
+
+		if (len > sizeof(buf))
+			continue;
+		err = err ?: bpf_dynptr_read(&buf, len, &ptr_xdp, off, 0);
+
+		if (!len)
+			continue;
+		if (err || bpf_memcmp(expected_str, buf, len - 1) || buf[len - 1] != '\0')
+			err = 1;
+
+		__builtin_memset(buf, 0, sizeof(buf));
+		err = err ?: bpf_dynptr_write(&ptr_xdp, off, buf, len, 0);
+	}
+}
+
+SEC("xdp")
+int test_probe_read_user_dynptr(struct xdp_md *xdp)
+{
+	test_dynptr_probe(user_ptr, bpf_probe_read_user_dynptr);
+	if (!err)
+		test_dynptr_probe_xdp(xdp, user_ptr, bpf_probe_read_user_dynptr);
+	return XDP_PASS;
+}
+
+SEC("xdp")
+int test_probe_read_kernel_dynptr(struct xdp_md *xdp)
+{
+	test_dynptr_probe(expected_str, bpf_probe_read_kernel_dynptr);
+	if (!err)
+		test_dynptr_probe_xdp(xdp, expected_str, bpf_probe_read_kernel_dynptr);
+	return XDP_PASS;
+}
+
+SEC("xdp")
+int test_probe_read_user_str_dynptr(struct xdp_md *xdp)
+{
+	test_dynptr_probe_str(user_ptr, bpf_probe_read_user_str_dynptr);
+	if (!err)
+		test_dynptr_probe_str_xdp(xdp, user_ptr, bpf_probe_read_user_str_dynptr);
+	return XDP_PASS;
+}
+
+SEC("xdp")
+int test_probe_read_kernel_str_dynptr(struct xdp_md *xdp)
+{
+	test_dynptr_probe_str(expected_str, bpf_probe_read_kernel_str_dynptr);
+	if (!err)
+		test_dynptr_probe_str_xdp(xdp, expected_str, bpf_probe_read_kernel_str_dynptr);
+	return XDP_PASS;
+}
+
+SEC("fentry.s/" SYS_PREFIX "sys_nanosleep")
+int test_copy_from_user_dynptr(void *ctx)
+{
+	test_dynptr_probe(user_ptr, bpf_copy_from_user_dynptr);
+	return 0;
+}
+
+SEC("fentry.s/" SYS_PREFIX "sys_nanosleep")
+int test_copy_from_user_str_dynptr(void *ctx)
+{
+	test_dynptr_probe_str(user_ptr, bpf_copy_from_user_str_dynptr);
+	return 0;
+}
+
+static int bpf_copy_data_from_user_task(struct bpf_dynptr *dptr, u64 off,
+					u64 size, const void *unsafe_ptr)
+{
+	struct task_struct *task = bpf_get_current_task_btf();
+
+	return bpf_copy_from_user_task_dynptr(dptr, off, size, unsafe_ptr, task);
+}
+
+static int bpf_copy_data_from_user_task_str(struct bpf_dynptr *dptr, u64 off,
+					    u64 size, const void *unsafe_ptr)
+{
+	struct task_struct *task = bpf_get_current_task_btf();
+
+	return bpf_copy_from_user_task_str_dynptr(dptr, off, size, unsafe_ptr, task);
+}
+
+SEC("fentry.s/" SYS_PREFIX "sys_nanosleep")
+int test_copy_from_user_task_dynptr(void *ctx)
+{
+	test_dynptr_probe(user_ptr, bpf_copy_data_from_user_task);
+	return 0;
+}
+
+SEC("fentry.s/" SYS_PREFIX "sys_nanosleep")
+int test_copy_from_user_task_str_dynptr(void *ctx)
+{
+	test_dynptr_probe_str(user_ptr, bpf_copy_data_from_user_task_str);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/epilogue_exit.c b/tools/testing/selftests/bpf/progs/epilogue_exit.c
new file mode 100644
index 000000000000..35fec7c75bef
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/epilogue_exit.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+__success
+/* save __u64 *ctx to stack */
+__xlated("0: *(u64 *)(r10 -8) = r1")
+/* main prog */
+__xlated("1: r1 = *(u64 *)(r1 +0)")
+__xlated("2: r2 = *(u64 *)(r1 +0)")
+__xlated("3: r3 = 0")
+__xlated("4: r4 = 1")
+__xlated("5: if r2 == 0x0 goto pc+10")
+__xlated("6: r0 = 0")
+__xlated("7: *(u64 *)(r1 +0) = r3")
+/* epilogue */
+__xlated("8: r1 = *(u64 *)(r10 -8)")
+__xlated("9: r1 = *(u64 *)(r1 +0)")
+__xlated("10: r6 = *(u64 *)(r1 +0)")
+__xlated("11: r6 += 10000")
+__xlated("12: *(u64 *)(r1 +0) = r6")
+__xlated("13: r0 = r6")
+__xlated("14: r0 *= 2")
+__xlated("15: exit")
+/* 2nd part of the main prog after the first exit */
+__xlated("16: *(u64 *)(r1 +0) = r4")
+__xlated("17: r0 = 1")
+/* Clear the r1 to ensure it does not have
+ * off-by-1 error and ensure it jumps back to the
+ * beginning of epilogue which initializes
+ * the r1 with the ctx ptr.
+ */
+__xlated("18: r1 = 0")
+__xlated("19: gotol pc-12")
+SEC("struct_ops/test_epilogue_exit")
+__naked int test_epilogue_exit(void)
+{
+	asm volatile (
+	"r1 = *(u64 *)(r1 +0);"
+	"r2 = *(u64 *)(r1 +0);"
+	"r3 = 0;"
+	"r4 = 1;"
+	"if r2 == 0 goto +3;"
+	"r0 = 0;"
+	"*(u64 *)(r1 + 0) = r3;"
+	"exit;"
+	"*(u64 *)(r1 + 0) = r4;"
+	"r0 = 1;"
+	"r1 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_st_ops epilogue_exit = {
+	.test_epilogue = (void *)test_epilogue_exit,
+};
+
+SEC("syscall")
+__retval(20000)
+int syscall_epilogue_exit0(void *ctx)
+{
+	struct st_ops_args args = { .a = 1 };
+
+	return bpf_kfunc_st_ops_test_epilogue(&args);
+}
+
+SEC("syscall")
+__retval(20002)
+int syscall_epilogue_exit1(void *ctx)
+{
+	struct st_ops_args args = {};
+
+	return bpf_kfunc_st_ops_test_epilogue(&args);
+}
diff --git a/tools/testing/selftests/bpf/progs/epilogue_tailcall.c b/tools/testing/selftests/bpf/progs/epilogue_tailcall.c
new file mode 100644
index 000000000000..153514691ba4
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/epilogue_tailcall.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+static __noinline __used int subprog(struct st_ops_args *args)
+{
+	args->a += 1;
+	return args->a;
+}
+
+SEC("struct_ops/test_epilogue_subprog")
+int BPF_PROG(test_epilogue_subprog, struct st_ops_args *args)
+{
+	subprog(args);
+	return args->a;
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+	__array(values, void (void));
+} epilogue_map SEC(".maps") = {
+	.values = {
+		[0] = (void *)&test_epilogue_subprog,
+	}
+};
+
+SEC("struct_ops/test_epilogue_tailcall")
+int test_epilogue_tailcall(unsigned long long *ctx)
+{
+	bpf_tail_call(ctx, &epilogue_map, 0);
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_st_ops epilogue_tailcall = {
+	.test_epilogue = (void *)test_epilogue_tailcall,
+};
+
+SEC(".struct_ops.link")
+struct bpf_testmod_st_ops epilogue_subprog = {
+	.test_epilogue = (void *)test_epilogue_subprog,
+};
+
+SEC("syscall")
+int syscall_epilogue_tailcall(struct st_ops_args *args)
+{
+	return bpf_kfunc_st_ops_test_epilogue(args);
+}
diff --git a/tools/testing/selftests/bpf/progs/err.h b/tools/testing/selftests/bpf/progs/err.h
new file mode 100644
index 000000000000..38529779a236
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/err.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ERR_H__
+#define __ERR_H__
+
+#define MAX_ERRNO 4095
+#define IS_ERR_VALUE(x) (unsigned long)(void *)(x) >= (unsigned long)-MAX_ERRNO
+
+#define __STR(x) #x
+
+#define set_if_not_errno_or_zero(x, y)			\
+({							\
+	asm volatile ("if %0 s< -4095 goto +1\n"	\
+		      "if %0 s<= 0 goto +1\n"		\
+		      "%0 = " __STR(y) "\n"		\
+		      : "+r"(x));			\
+})
+
+static inline int IS_ERR_OR_NULL(const void *ptr)
+{
+	return !ptr || IS_ERR_VALUE((unsigned long)ptr);
+}
+
+static inline long PTR_ERR(const void *ptr)
+{
+	return (long) ptr;
+}
+
+#endif /* __ERR_H__ */
diff --git a/tools/testing/selftests/bpf/progs/exceptions.c b/tools/testing/selftests/bpf/progs/exceptions.c
new file mode 100644
index 000000000000..f09cd14d8e04
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/exceptions.c
@@ -0,0 +1,368 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_endian.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+#ifndef ETH_P_IP
+#define ETH_P_IP 0x0800
+#endif
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 4);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+static __noinline int static_func(u64 i)
+{
+	bpf_throw(32);
+	return i;
+}
+
+__noinline int global2static_simple(u64 i)
+{
+	static_func(i + 2);
+	return i - 1;
+}
+
+__noinline int global2static(u64 i)
+{
+	if (i == ETH_P_IP)
+		bpf_throw(16);
+	return static_func(i);
+}
+
+static __noinline int static2global(u64 i)
+{
+	return global2static(i) + i;
+}
+
+SEC("tc")
+int exception_throw_always_1(struct __sk_buff *ctx)
+{
+	bpf_throw(64);
+	return 0;
+}
+
+/* In this case, the global func will never be seen executing after call to
+ * static subprog, hence verifier will DCE the remaining instructions. Ensure we
+ * are resilient to that.
+ */
+SEC("tc")
+int exception_throw_always_2(struct __sk_buff *ctx)
+{
+	return global2static_simple(ctx->protocol);
+}
+
+SEC("tc")
+int exception_throw_unwind_1(struct __sk_buff *ctx)
+{
+	return static2global(bpf_ntohs(ctx->protocol));
+}
+
+SEC("tc")
+int exception_throw_unwind_2(struct __sk_buff *ctx)
+{
+	return static2global(bpf_ntohs(ctx->protocol) - 1);
+}
+
+SEC("tc")
+int exception_throw_default(struct __sk_buff *ctx)
+{
+	bpf_throw(0);
+	return 1;
+}
+
+SEC("tc")
+int exception_throw_default_value(struct __sk_buff *ctx)
+{
+	bpf_throw(5);
+	return 1;
+}
+
+SEC("tc")
+int exception_tail_call_target(struct __sk_buff *ctx)
+{
+	bpf_throw(16);
+	return 0;
+}
+
+static __noinline
+int exception_tail_call_subprog(struct __sk_buff *ctx)
+{
+	volatile int ret = 10;
+
+	bpf_tail_call_static(ctx, &jmp_table, 0);
+	return ret;
+}
+
+SEC("tc")
+int exception_tail_call(struct __sk_buff *ctx) {
+	volatile int ret = 0;
+
+	ret = exception_tail_call_subprog(ctx);
+	return ret + 8;
+}
+
+__noinline int exception_ext_global(struct __sk_buff *ctx)
+{
+	volatile int ret = 0;
+
+	return ret;
+}
+
+static __noinline int exception_ext_static(struct __sk_buff *ctx)
+{
+	return exception_ext_global(ctx);
+}
+
+SEC("tc")
+int exception_ext(struct __sk_buff *ctx)
+{
+	return exception_ext_static(ctx);
+}
+
+__noinline int exception_cb_mod_global(u64 cookie)
+{
+	volatile int ret = 0;
+
+	return ret;
+}
+
+/* Example of how the exception callback supplied during verification can still
+ * introduce extensions by calling to dummy global functions, and alter runtime
+ * behavior.
+ *
+ * Right now we don't allow freplace attachment to exception callback itself,
+ * but if the need arises this restriction is technically feasible to relax in
+ * the future.
+ */
+__noinline int exception_cb_mod(u64 cookie)
+{
+	return exception_cb_mod_global(cookie) + cookie + 10;
+}
+
+SEC("tc")
+__exception_cb(exception_cb_mod)
+int exception_ext_mod_cb_runtime(struct __sk_buff *ctx)
+{
+	bpf_throw(25);
+	return 0;
+}
+
+__noinline static int subprog(struct __sk_buff *ctx)
+{
+	return bpf_ktime_get_ns();
+}
+
+__noinline static int throwing_subprog(struct __sk_buff *ctx)
+{
+	if (ctx->tstamp)
+		bpf_throw(0);
+	return bpf_ktime_get_ns();
+}
+
+__noinline int global_subprog(struct __sk_buff *ctx)
+{
+	return bpf_ktime_get_ns();
+}
+
+__noinline int throwing_global_subprog(struct __sk_buff *ctx)
+{
+	if (ctx->tstamp)
+		bpf_throw(0);
+	return bpf_ktime_get_ns();
+}
+
+SEC("tc")
+int exception_throw_subprog(struct __sk_buff *ctx)
+{
+	switch (ctx->protocol) {
+	case 1:
+		return subprog(ctx);
+	case 2:
+		return global_subprog(ctx);
+	case 3:
+		return throwing_subprog(ctx);
+	case 4:
+		return throwing_global_subprog(ctx);
+	default:
+		break;
+	}
+	bpf_throw(1);
+	return 0;
+}
+
+__noinline int assert_nz_gfunc(u64 c)
+{
+	volatile u64 cookie = c;
+
+	bpf_assert(cookie != 0);
+	return 0;
+}
+
+__noinline int assert_zero_gfunc(u64 c)
+{
+	volatile u64 cookie = c;
+
+	bpf_assert(bpf_cmp_unlikely(cookie, ==, 0));
+	return 0;
+}
+
+__noinline int assert_neg_gfunc(s64 c)
+{
+	volatile s64 cookie = c;
+
+	bpf_assert(bpf_cmp_unlikely(cookie, <, 0));
+	return 0;
+}
+
+__noinline int assert_pos_gfunc(s64 c)
+{
+	volatile s64 cookie = c;
+
+	bpf_assert(bpf_cmp_unlikely(cookie, >, 0));
+	return 0;
+}
+
+__noinline int assert_negeq_gfunc(s64 c)
+{
+	volatile s64 cookie = c;
+
+	bpf_assert(bpf_cmp_unlikely(cookie, <=, -1));
+	return 0;
+}
+
+__noinline int assert_poseq_gfunc(s64 c)
+{
+	volatile s64 cookie = c;
+
+	bpf_assert(bpf_cmp_unlikely(cookie, >=, 1));
+	return 0;
+}
+
+__noinline int assert_nz_gfunc_with(u64 c)
+{
+	volatile u64 cookie = c;
+
+	bpf_assert_with(cookie != 0, cookie + 100);
+	return 0;
+}
+
+__noinline int assert_zero_gfunc_with(u64 c)
+{
+	volatile u64 cookie = c;
+
+	bpf_assert_with(bpf_cmp_unlikely(cookie, ==, 0), cookie + 100);
+	return 0;
+}
+
+__noinline int assert_neg_gfunc_with(s64 c)
+{
+	volatile s64 cookie = c;
+
+	bpf_assert_with(bpf_cmp_unlikely(cookie, <, 0), cookie + 100);
+	return 0;
+}
+
+__noinline int assert_pos_gfunc_with(s64 c)
+{
+	volatile s64 cookie = c;
+
+	bpf_assert_with(bpf_cmp_unlikely(cookie, >, 0), cookie + 100);
+	return 0;
+}
+
+__noinline int assert_negeq_gfunc_with(s64 c)
+{
+	volatile s64 cookie = c;
+
+	bpf_assert_with(bpf_cmp_unlikely(cookie, <=, -1), cookie + 100);
+	return 0;
+}
+
+__noinline int assert_poseq_gfunc_with(s64 c)
+{
+	volatile s64 cookie = c;
+
+	bpf_assert_with(bpf_cmp_unlikely(cookie, >=, 1), cookie + 100);
+	return 0;
+}
+
+#define check_assert(name, cookie, tag)				\
+SEC("tc")							\
+int exception##tag##name(struct __sk_buff *ctx)			\
+{								\
+	return name(cookie) + 1;				\
+}
+
+check_assert(assert_nz_gfunc, 5, _);
+check_assert(assert_zero_gfunc, 0, _);
+check_assert(assert_neg_gfunc, -100, _);
+check_assert(assert_pos_gfunc, 100, _);
+check_assert(assert_negeq_gfunc, -1, _);
+check_assert(assert_poseq_gfunc, 1, _);
+
+check_assert(assert_nz_gfunc_with, 5, _);
+check_assert(assert_zero_gfunc_with, 0, _);
+check_assert(assert_neg_gfunc_with, -100, _);
+check_assert(assert_pos_gfunc_with, 100, _);
+check_assert(assert_negeq_gfunc_with, -1, _);
+check_assert(assert_poseq_gfunc_with, 1, _);
+
+check_assert(assert_nz_gfunc, 0, _bad_);
+check_assert(assert_zero_gfunc, 5, _bad_);
+check_assert(assert_neg_gfunc, 100, _bad_);
+check_assert(assert_pos_gfunc, -100, _bad_);
+check_assert(assert_negeq_gfunc, 1, _bad_);
+check_assert(assert_poseq_gfunc, -1, _bad_);
+
+check_assert(assert_nz_gfunc_with, 0, _bad_);
+check_assert(assert_zero_gfunc_with, 5, _bad_);
+check_assert(assert_neg_gfunc_with, 100, _bad_);
+check_assert(assert_pos_gfunc_with, -100, _bad_);
+check_assert(assert_negeq_gfunc_with, 1, _bad_);
+check_assert(assert_poseq_gfunc_with, -1, _bad_);
+
+SEC("tc")
+int exception_assert_range(struct __sk_buff *ctx)
+{
+	u64 time = bpf_ktime_get_ns();
+
+	bpf_assert_range(time, 0, ~0ULL);
+	return 1;
+}
+
+SEC("tc")
+int exception_assert_range_with(struct __sk_buff *ctx)
+{
+	u64 time = bpf_ktime_get_ns();
+
+	bpf_assert_range_with(time, 0, ~0ULL, 10);
+	return 1;
+}
+
+SEC("tc")
+int exception_bad_assert_range(struct __sk_buff *ctx)
+{
+	u64 time = bpf_ktime_get_ns();
+
+	bpf_assert_range(time, -100, 100);
+	return 1;
+}
+
+SEC("tc")
+int exception_bad_assert_range_with(struct __sk_buff *ctx)
+{
+	u64 time = bpf_ktime_get_ns();
+
+	bpf_assert_range_with(time, -1000, 1000, 10);
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/exceptions_assert.c b/tools/testing/selftests/bpf/progs/exceptions_assert.c
new file mode 100644
index 000000000000..a01c2736890f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/exceptions_assert.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <limits.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_endian.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+#define check_assert(type, op, name, value)				\
+	SEC("?tc")							\
+	__log_level(2) __failure					\
+	int check_assert_##name(void *ctx)				\
+	{								\
+		type num = bpf_ktime_get_ns();				\
+		bpf_assert(bpf_cmp_unlikely(num, op, value));		\
+		return *(u64 *)num;					\
+	}
+
+__msg(": R0=0xffffffff80000000")
+check_assert(s64, ==, eq_int_min, INT_MIN);
+__msg(": R0=0x7fffffff")
+check_assert(s64, ==, eq_int_max, INT_MAX);
+__msg(": R0=0")
+check_assert(s64, ==, eq_zero, 0);
+__msg(": R0=0x8000000000000000 R1=0x8000000000000000")
+check_assert(s64, ==, eq_llong_min, LLONG_MIN);
+__msg(": R0=0x7fffffffffffffff R1=0x7fffffffffffffff")
+check_assert(s64, ==, eq_llong_max, LLONG_MAX);
+
+__msg(": R0=scalar(id=1,smax=0x7ffffffe)")
+check_assert(s64, <, lt_pos, INT_MAX);
+__msg(": R0=scalar(id=1,smax=-1,umin=0x8000000000000000,var_off=(0x8000000000000000; 0x7fffffffffffffff))")
+check_assert(s64, <, lt_zero, 0);
+__msg(": R0=scalar(id=1,smax=0xffffffff7fffffff")
+check_assert(s64, <, lt_neg, INT_MIN);
+
+__msg(": R0=scalar(id=1,smax=0x7fffffff)")
+check_assert(s64, <=, le_pos, INT_MAX);
+__msg(": R0=scalar(id=1,smax=0)")
+check_assert(s64, <=, le_zero, 0);
+__msg(": R0=scalar(id=1,smax=0xffffffff80000000")
+check_assert(s64, <=, le_neg, INT_MIN);
+
+__msg(": R0=scalar(id=1,smin=umin=0x80000000,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+check_assert(s64, >, gt_pos, INT_MAX);
+__msg(": R0=scalar(id=1,smin=umin=1,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+check_assert(s64, >, gt_zero, 0);
+__msg(": R0=scalar(id=1,smin=0xffffffff80000001")
+check_assert(s64, >, gt_neg, INT_MIN);
+
+__msg(": R0=scalar(id=1,smin=umin=0x7fffffff,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+check_assert(s64, >=, ge_pos, INT_MAX);
+__msg(": R0=scalar(id=1,smin=0,umax=0x7fffffffffffffff,var_off=(0x0; 0x7fffffffffffffff))")
+check_assert(s64, >=, ge_zero, 0);
+__msg(": R0=scalar(id=1,smin=0xffffffff80000000")
+check_assert(s64, >=, ge_neg, INT_MIN);
+
+SEC("?tc")
+__log_level(2) __failure
+__msg(": R0=0 R1=ctx() R2=scalar(smin=0xffffffff80000002,smax=smax32=0x7ffffffd,smin32=0x80000002) R10=fp0")
+int check_assert_range_s64(struct __sk_buff *ctx)
+{
+	struct bpf_sock *sk = ctx->sk;
+	s64 num;
+
+	_Static_assert(_Generic((sk->rx_queue_mapping), s32: 1, default: 0), "type match");
+	if (!sk)
+		return 0;
+	num = sk->rx_queue_mapping;
+	bpf_assert_range(num, INT_MIN + 2, INT_MAX - 2);
+	return *((u8 *)ctx + num);
+}
+
+SEC("?tc")
+__log_level(2) __failure
+__msg(": R1=ctx() R2=scalar(smin=umin=smin32=umin32=4096,smax=umax=smax32=umax32=8192,var_off=(0x0; 0x3fff))")
+int check_assert_range_u64(struct __sk_buff *ctx)
+{
+	u64 num = ctx->len;
+
+	bpf_assert_range(num, 4096, 8192);
+	return *((u8 *)ctx + num);
+}
+
+SEC("?tc")
+__log_level(2) __failure
+__msg(": R0=0 R1=ctx() R2=4096 R10=fp0")
+int check_assert_single_range_s64(struct __sk_buff *ctx)
+{
+	struct bpf_sock *sk = ctx->sk;
+	s64 num;
+
+	_Static_assert(_Generic((sk->rx_queue_mapping), s32: 1, default: 0), "type match");
+	if (!sk)
+		return 0;
+	num = sk->rx_queue_mapping;
+
+	bpf_assert_range(num, 4096, 4096);
+	return *((u8 *)ctx + num);
+}
+
+SEC("?tc")
+__log_level(2) __failure
+__msg(": R1=ctx() R2=4096 R10=fp0")
+int check_assert_single_range_u64(struct __sk_buff *ctx)
+{
+	u64 num = ctx->len;
+
+	bpf_assert_range(num, 4096, 4096);
+	return *((u8 *)ctx + num);
+}
+
+SEC("?tc")
+__log_level(2) __failure
+__msg(": R1=pkt(off=64,r=64) R2=pkt_end() R6=pkt(r=64) R10=fp0")
+int check_assert_generic(struct __sk_buff *ctx)
+{
+	u8 *data_end = (void *)(long)ctx->data_end;
+	u8 *data = (void *)(long)ctx->data;
+
+	bpf_assert(data + 64 <= data_end);
+	return data[128];
+}
+
+SEC("?fentry/bpf_check")
+__failure __msg("At program exit the register R1 has smin=64 smax=64")
+int check_assert_with_return(void *ctx)
+{
+	bpf_assert_with(!ctx, 64);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/exceptions_ext.c b/tools/testing/selftests/bpf/progs/exceptions_ext.c
new file mode 100644
index 000000000000..743c05185d9b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/exceptions_ext.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_experimental.h"
+
+SEC("?fentry")
+int pfentry(void *ctx)
+{
+	return 0;
+}
+
+SEC("?fentry")
+int throwing_fentry(void *ctx)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+__noinline int exception_cb(u64 cookie)
+{
+	return cookie + 64;
+}
+
+SEC("?freplace")
+int extension(struct __sk_buff *ctx)
+{
+	return 0;
+}
+
+SEC("?freplace")
+__exception_cb(exception_cb)
+int throwing_exception_cb_extension(u64 cookie)
+{
+	bpf_throw(32);
+	return 0;
+}
+
+SEC("?freplace")
+__exception_cb(exception_cb)
+int throwing_extension(struct __sk_buff *ctx)
+{
+	bpf_throw(64);
+	return 0;
+}
+
+SEC("?fexit")
+int pfexit(void *ctx)
+{
+	return 0;
+}
+
+SEC("?fexit")
+int throwing_fexit(void *ctx)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+SEC("?fmod_ret")
+int pfmod_ret(void *ctx)
+{
+	return 0;
+}
+
+SEC("?fmod_ret")
+int throwing_fmod_ret(void *ctx)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/exceptions_fail.c b/tools/testing/selftests/bpf/progs/exceptions_fail.c
new file mode 100644
index 000000000000..8a0fdff89927
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/exceptions_fail.c
@@ -0,0 +1,349 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+extern void bpf_rcu_read_lock(void) __ksym;
+
+#define private(name) SEC(".bss." #name) __hidden __attribute__((aligned(8)))
+
+struct foo {
+	struct bpf_rb_node node;
+};
+
+struct hmap_elem {
+	struct bpf_timer timer;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 64);
+	__type(key, int);
+	__type(value, struct hmap_elem);
+} hmap SEC(".maps");
+
+private(A) struct bpf_spin_lock lock;
+private(A) struct bpf_rb_root rbtree __contains(foo, node);
+
+__noinline void *exception_cb_bad_ret_type(u64 cookie)
+{
+	return NULL;
+}
+
+__noinline int exception_cb_bad_arg_0(void)
+{
+	return 0;
+}
+
+__noinline int exception_cb_bad_arg_2(int a, int b)
+{
+	return 0;
+}
+
+__noinline int exception_cb_ok_arg_small(int a)
+{
+	return 0;
+}
+
+SEC("?tc")
+__exception_cb(exception_cb_bad_ret_type)
+__failure __msg("Global function exception_cb_bad_ret_type() doesn't return scalar.")
+int reject_exception_cb_type_1(struct __sk_buff *ctx)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+SEC("?tc")
+__exception_cb(exception_cb_bad_arg_0)
+__failure __msg("exception cb only supports single integer argument")
+int reject_exception_cb_type_2(struct __sk_buff *ctx)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+SEC("?tc")
+__exception_cb(exception_cb_bad_arg_2)
+__failure __msg("exception cb only supports single integer argument")
+int reject_exception_cb_type_3(struct __sk_buff *ctx)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+SEC("?tc")
+__exception_cb(exception_cb_ok_arg_small)
+__success
+int reject_exception_cb_type_4(struct __sk_buff *ctx)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+__noinline
+static int timer_cb(void *map, int *key, struct bpf_timer *timer)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("cannot be called from callback subprog")
+int reject_async_callback_throw(struct __sk_buff *ctx)
+{
+	struct hmap_elem *elem;
+
+	elem = bpf_map_lookup_elem(&hmap, &(int){0});
+	if (!elem)
+		return 0;
+	return bpf_timer_set_callback(&elem->timer, timer_cb);
+}
+
+__noinline static int subprog_lock(struct __sk_buff *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_spin_lock(&lock);
+	if (ctx->len)
+		bpf_throw(0);
+	return ret;
+}
+
+SEC("?tc")
+__failure __msg("function calls are not allowed while holding a lock")
+int reject_with_lock(void *ctx)
+{
+	bpf_spin_lock(&lock);
+	bpf_throw(0);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("function calls are not allowed while holding a lock")
+int reject_subprog_with_lock(void *ctx)
+{
+	return subprog_lock(ctx);
+}
+
+SEC("?tc")
+__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_rcu_read_lock-ed region")
+int reject_with_rcu_read_lock(void *ctx)
+{
+	bpf_rcu_read_lock();
+	bpf_throw(0);
+	return 0;
+}
+
+__noinline static int throwing_subprog(struct __sk_buff *ctx)
+{
+	if (ctx->len)
+		bpf_throw(0);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_rcu_read_lock-ed region")
+int reject_subprog_with_rcu_read_lock(void *ctx)
+{
+	bpf_rcu_read_lock();
+	return throwing_subprog(ctx);
+}
+
+static bool rbless(struct bpf_rb_node *n1, const struct bpf_rb_node *n2)
+{
+	bpf_throw(0);
+	return true;
+}
+
+SEC("?tc")
+__failure __msg("function calls are not allowed while holding a lock")
+int reject_with_rbtree_add_throw(void *ctx)
+{
+	struct foo *f;
+
+	f = bpf_obj_new(typeof(*f));
+	if (!f)
+		return 0;
+	bpf_spin_lock(&lock);
+	bpf_rbtree_add(&rbtree, &f->node, rbless);
+	bpf_spin_unlock(&lock);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("Unreleased reference")
+int reject_with_reference(void *ctx)
+{
+	struct foo *f;
+
+	f = bpf_obj_new(typeof(*f));
+	if (!f)
+		return 0;
+	bpf_throw(0);
+	return 0;
+}
+
+__noinline static int subprog_ref(struct __sk_buff *ctx)
+{
+	struct foo *f;
+
+	f = bpf_obj_new(typeof(*f));
+	if (!f)
+		return 0;
+	bpf_throw(0);
+	return 0;
+}
+
+__noinline static int subprog_cb_ref(u32 i, void *ctx)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("Unreleased reference")
+int reject_with_cb_reference(void *ctx)
+{
+	struct foo *f;
+
+	f = bpf_obj_new(typeof(*f));
+	if (!f)
+		return 0;
+	bpf_loop(5, subprog_cb_ref, NULL, 0);
+	bpf_obj_drop(f);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("cannot be called from callback")
+int reject_with_cb(void *ctx)
+{
+	bpf_loop(5, subprog_cb_ref, NULL, 0);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("Unreleased reference")
+int reject_with_subprog_reference(void *ctx)
+{
+	return subprog_ref(ctx) + 1;
+}
+
+__noinline int throwing_exception_cb(u64 c)
+{
+	bpf_throw(0);
+	return c;
+}
+
+__noinline int exception_cb1(u64 c)
+{
+	return c;
+}
+
+__noinline int exception_cb2(u64 c)
+{
+	return c;
+}
+
+static __noinline int static_func(struct __sk_buff *ctx)
+{
+	return exception_cb1(ctx->tstamp);
+}
+
+__noinline int global_func(struct __sk_buff *ctx)
+{
+	return exception_cb1(ctx->tstamp);
+}
+
+SEC("?tc")
+__exception_cb(throwing_exception_cb)
+__failure __msg("cannot be called from callback subprog")
+int reject_throwing_exception_cb(struct __sk_buff *ctx)
+{
+	return 0;
+}
+
+SEC("?tc")
+__exception_cb(exception_cb1)
+__failure __msg("cannot call exception cb directly")
+int reject_exception_cb_call_global_func(struct __sk_buff *ctx)
+{
+	return global_func(ctx);
+}
+
+SEC("?tc")
+__exception_cb(exception_cb1)
+__failure __msg("cannot call exception cb directly")
+int reject_exception_cb_call_static_func(struct __sk_buff *ctx)
+{
+	return static_func(ctx);
+}
+
+SEC("?tc")
+__exception_cb(exception_cb1)
+__exception_cb(exception_cb2)
+__failure __msg("multiple exception callback tags for main subprog")
+int reject_multiple_exception_cb(struct __sk_buff *ctx)
+{
+	bpf_throw(0);
+	return 16;
+}
+
+__noinline int exception_cb_bad_ret(u64 c)
+{
+	return c;
+}
+
+SEC("?fentry/bpf_check")
+__exception_cb(exception_cb_bad_ret)
+__failure __msg("At program exit the register R0 has unknown scalar value should")
+int reject_set_exception_cb_bad_ret1(void *ctx)
+{
+	return 0;
+}
+
+SEC("?fentry/bpf_check")
+__failure __msg("At program exit the register R1 has smin=64 smax=64 should")
+int reject_set_exception_cb_bad_ret2(void *ctx)
+{
+	bpf_throw(64);
+	return 0;
+}
+
+__noinline static int loop_cb1(u32 index, int *ctx)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+__noinline static int loop_cb2(u32 index, int *ctx)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("cannot be called from callback")
+int reject_exception_throw_cb(struct __sk_buff *ctx)
+{
+	bpf_loop(5, loop_cb1, NULL, 0);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("cannot be called from callback")
+int reject_exception_throw_cb_diff(struct __sk_buff *ctx)
+{
+	if (ctx->protocol)
+		bpf_loop(5, loop_cb1, NULL, 0);
+	else
+		bpf_loop(5, loop_cb2, NULL, 0);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/fd_htab_lookup.c b/tools/testing/selftests/bpf/progs/fd_htab_lookup.c
new file mode 100644
index 000000000000..a4a9e1db626f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fd_htab_lookup.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2025. Huawei Technologies Co., Ltd */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct inner_map_type {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(key_size, 4);
+	__uint(value_size, 4);
+	__uint(max_entries, 1);
+} inner_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+	__uint(max_entries, 64);
+	__type(key, int);
+	__type(value, int);
+	__array(values, struct inner_map_type);
+} outer_map SEC(".maps") = {
+	.values = {
+		[0] = &inner_map,
+	},
+};
diff --git a/tools/testing/selftests/bpf/progs/fentry_many_args.c b/tools/testing/selftests/bpf/progs/fentry_many_args.c
new file mode 100644
index 000000000000..b61bb92fee2c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fentry_many_args.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Tencent */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u64 test1_result = 0;
+SEC("fentry/bpf_testmod_fentry_test7")
+int BPF_PROG(test1, __u64 a, void *b, short c, int d, void *e, char f,
+	     int g)
+{
+	test1_result = a == 16 && b == (void *)17 && c == 18 && d == 19 &&
+		e == (void *)20 && f == 21 && g == 22;
+	return 0;
+}
+
+__u64 test2_result = 0;
+SEC("fentry/bpf_testmod_fentry_test11")
+int BPF_PROG(test2, __u64 a, void *b, short c, int d, void *e, char f,
+	     int g, unsigned int h, long i, __u64 j, unsigned long k)
+{
+	test2_result = a == 16 && b == (void *)17 && c == 18 && d == 19 &&
+		e == (void *)20 && f == 21 && g == 22 && h == 23 &&
+		i == 24 && j == 25 && k == 26;
+	return 0;
+}
+
+__u64 test3_result = 0;
+SEC("fentry/bpf_testmod_fentry_test11")
+int BPF_PROG(test3, __u64 a, __u64 b, __u64 c, __u64 d, __u64 e, __u64 f,
+	     __u64 g, __u64 h, __u64 i, __u64 j, __u64 k)
+{
+	test3_result = a == 16 && b == 17 && c == 18 && d == 19 &&
+		e == 20 && f == 21 && g == 22 && h == 23 &&
+		i == 24 && j == 25 && k == 26;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/fentry_recursive.c b/tools/testing/selftests/bpf/progs/fentry_recursive.c
new file mode 100644
index 000000000000..2c9fb5ac42b2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fentry_recursive.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Red Hat, Inc. */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+/* Dummy fentry bpf prog for testing fentry attachment chains */
+SEC("fentry/XXX")
+int BPF_PROG(recursive_attach, int a)
+{
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/fentry_recursive_target.c b/tools/testing/selftests/bpf/progs/fentry_recursive_target.c
new file mode 100644
index 000000000000..267c876d0aba
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fentry_recursive_target.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Red Hat, Inc. */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+/* Dummy fentry bpf prog for testing fentry attachment chains. It's going to be
+ * a start of the chain.
+ */
+SEC("fentry/bpf_testmod_fentry_test1")
+int BPF_PROG(test1, int a)
+{
+	return 0;
+}
+
+/* Dummy bpf prog for testing attach_btf presence when attaching an fentry
+ * program.
+ */
+SEC("raw_tp/sys_enter")
+int BPF_PROG(fentry_target, struct pt_regs *regs, long id)
+{
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c
index 4547b059d487..983b7c233382 100644
--- a/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/progs/fexit_bpf2bpf.c
@@ -120,8 +120,6 @@ int new_get_skb_ifindex(int val, struct __sk_buff *skb, int var)
 	void *data = (void *)(long)skb->data;
 	struct ipv6hdr ip6, *ip6p;
 	int ifindex = skb->ifindex;
-	__u32 eth_proto;
-	__u32 nh_off;
 
 	/* check that BPF extension can read packet via direct packet access */
 	if (data + 14 + sizeof(ip6) > data_end)
diff --git a/tools/testing/selftests/bpf/progs/fexit_many_args.c b/tools/testing/selftests/bpf/progs/fexit_many_args.c
new file mode 100644
index 000000000000..53b335c2dafb
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fexit_many_args.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Tencent */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u64 test1_result = 0;
+SEC("fexit/bpf_testmod_fentry_test7")
+int BPF_PROG(test1, __u64 a, void *b, short c, int d, void *e, char f,
+	     int g, int ret)
+{
+	test1_result = a == 16 && b == (void *)17 && c == 18 && d == 19 &&
+		e == (void *)20 && f == 21 && g == 22 && ret == 133;
+	return 0;
+}
+
+__u64 test2_result = 0;
+SEC("fexit/bpf_testmod_fentry_test11")
+int BPF_PROG(test2, __u64 a, void *b, short c, int d, void *e, char f,
+	     int g, unsigned int h, long i, __u64 j, unsigned long k,
+	     int ret)
+{
+	test2_result = a == 16 && b == (void *)17 && c == 18 && d == 19 &&
+		e == (void *)20 && f == 21 && g == 22 && h == 23 &&
+		i == 24 && j == 25 && k == 26 && ret == 231;
+	return 0;
+}
+
+__u64 test3_result = 0;
+SEC("fexit/bpf_testmod_fentry_test11")
+int BPF_PROG(test3, __u64 a, __u64 b, __u64 c, __u64 d, __u64 e, __u64 f,
+	     __u64 g, __u64 h, __u64 i, __u64 j, __u64 k, __u64 ret)
+{
+	test3_result = a == 16 && b == 17 && c == 18 && d == 19 &&
+		e == 20 && f == 21 && g == 22 && h == 23 &&
+		i == 24 && j == 25 && k == 26 && ret == 231;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/fib_lookup.c b/tools/testing/selftests/bpf/progs/fib_lookup.c
new file mode 100644
index 000000000000..7b5dd2214ff4
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fib_lookup.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <linux/types.h>
+#include <linux/bpf.h>
+#include <linux/pkt_cls.h>
+#include <bpf/bpf_helpers.h>
+
+struct bpf_fib_lookup fib_params = {};
+int fib_lookup_ret = 0;
+int lookup_flags = 0;
+
+SEC("tc")
+int fib_lookup(struct __sk_buff *skb)
+{
+	fib_lookup_ret = bpf_fib_lookup(skb, &fib_params, sizeof(fib_params),
+					lookup_flags);
+
+	return TC_ACT_SHOT;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/file_reader.c b/tools/testing/selftests/bpf/progs/file_reader.c
new file mode 100644
index 000000000000..4d756b623557
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/file_reader.c
@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <string.h>
+#include <stdbool.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "errno.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} arrmap SEC(".maps");
+
+struct elem {
+	struct file *file;
+	struct bpf_task_work tw;
+};
+
+char user_buf[256000];
+char tmp_buf[256000];
+
+int pid = 0;
+int err, run_success = 0;
+
+static int validate_file_read(struct file *file);
+static int task_work_callback(struct bpf_map *map, void *key, void *value);
+
+SEC("lsm/file_open")
+int on_open_expect_fault(void *c)
+{
+	struct bpf_dynptr dynptr;
+	struct file *file;
+	int local_err = 1;
+	__u32 user_buf_sz = sizeof(user_buf);
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	file = bpf_get_task_exe_file(bpf_get_current_task_btf());
+	if (!file)
+		return 0;
+
+	if (bpf_dynptr_from_file(file, 0, &dynptr))
+		goto out;
+
+	local_err = bpf_dynptr_read(tmp_buf, user_buf_sz, &dynptr, user_buf_sz, 0);
+	if (local_err == -EFAULT) { /* Expect page fault */
+		local_err = 0;
+		run_success = 1;
+	}
+out:
+	bpf_dynptr_file_discard(&dynptr);
+	if (local_err)
+		err = local_err;
+	bpf_put_file(file);
+	return 0;
+}
+
+SEC("lsm/file_open")
+int on_open_validate_file_read(void *c)
+{
+	struct task_struct *task = bpf_get_current_task_btf();
+	struct elem *work;
+	int key = 0;
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	work = bpf_map_lookup_elem(&arrmap, &key);
+	if (!work) {
+		err = 1;
+		return 0;
+	}
+	bpf_task_work_schedule_signal_impl(task, &work->tw, &arrmap, task_work_callback, NULL);
+	return 0;
+}
+
+/* Called in a sleepable context, read 256K bytes, cross check with user space read data */
+static int task_work_callback(struct bpf_map *map, void *key, void *value)
+{
+	struct task_struct *task = bpf_get_current_task_btf();
+	struct file *file = bpf_get_task_exe_file(task);
+
+	if (!file)
+		return 0;
+
+	err = validate_file_read(file);
+	if (!err)
+		run_success = 1;
+	bpf_put_file(file);
+	return 0;
+}
+
+static int verify_dynptr_read(struct bpf_dynptr *ptr, u32 off, char *user_buf, u32 len)
+{
+	int i;
+
+	if (bpf_dynptr_read(tmp_buf, len, ptr, off, 0))
+		return 1;
+
+	/* Verify file contents read from BPF is the same as the one read from userspace */
+	bpf_for(i, 0, len)
+	{
+		if (tmp_buf[i] != user_buf[i])
+			return 1;
+	}
+	return 0;
+}
+
+static int validate_file_read(struct file *file)
+{
+	struct bpf_dynptr dynptr;
+	int loc_err = 1, off;
+	__u32 user_buf_sz = sizeof(user_buf);
+
+	if (bpf_dynptr_from_file(file, 0, &dynptr))
+		goto cleanup;
+
+	loc_err = verify_dynptr_read(&dynptr, 0, user_buf, user_buf_sz);
+	off = 1;
+	loc_err = loc_err ?: verify_dynptr_read(&dynptr, off, user_buf + off, user_buf_sz - off);
+	off = user_buf_sz - 1;
+	loc_err = loc_err ?: verify_dynptr_read(&dynptr, off, user_buf + off, user_buf_sz - off);
+	/* Read file with random offset and length */
+	off = 4097;
+	loc_err = loc_err ?: verify_dynptr_read(&dynptr, off, user_buf + off, 100);
+
+	/* Adjust dynptr, verify read */
+	loc_err = loc_err ?: bpf_dynptr_adjust(&dynptr, off, off + 1);
+	loc_err = loc_err ?: verify_dynptr_read(&dynptr, 0, user_buf + off, 1);
+	/* Can't read more than 1 byte */
+	loc_err = loc_err ?: verify_dynptr_read(&dynptr, 0, user_buf + off, 2) == 0;
+	/* Can't read with far offset */
+	loc_err = loc_err ?: verify_dynptr_read(&dynptr, 1, user_buf + off, 1) == 0;
+
+cleanup:
+	bpf_dynptr_file_discard(&dynptr);
+	return loc_err;
+}
diff --git a/tools/testing/selftests/bpf/progs/file_reader_fail.c b/tools/testing/selftests/bpf/progs/file_reader_fail.c
new file mode 100644
index 000000000000..32fe28ed2439
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/file_reader_fail.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <string.h>
+#include <stdbool.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+int err;
+void *user_ptr;
+
+SEC("lsm/file_open")
+__failure
+__msg("Unreleased reference id=")
+int on_nanosleep_unreleased_ref(void *ctx)
+{
+	struct task_struct *task = bpf_get_current_task_btf();
+	struct file *file = bpf_get_task_exe_file(task);
+	struct bpf_dynptr dynptr;
+
+	if (!file)
+		return 0;
+
+	err = bpf_dynptr_from_file(file, 0, &dynptr);
+	return err ? 1 : 0;
+}
+
+SEC("xdp")
+__failure
+__msg("Expected a dynptr of type file as arg #0")
+int xdp_wrong_dynptr_type(struct xdp_md *xdp)
+{
+	struct bpf_dynptr dynptr;
+
+	bpf_dynptr_from_xdp(xdp, 0, &dynptr);
+	bpf_dynptr_file_discard(&dynptr);
+	return 0;
+}
+
+SEC("xdp")
+__failure
+__msg("Expected an initialized dynptr as arg #0")
+int xdp_no_dynptr_type(struct xdp_md *xdp)
+{
+	struct bpf_dynptr dynptr;
+
+	bpf_dynptr_file_discard(&dynptr);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/find_vma.c b/tools/testing/selftests/bpf/progs/find_vma.c
index 38034fb82530..02b82774469c 100644
--- a/tools/testing/selftests/bpf/progs/find_vma.c
+++ b/tools/testing/selftests/bpf/progs/find_vma.c
@@ -25,7 +25,7 @@ static long check_vma(struct task_struct *task, struct vm_area_struct *vma,
 {
 	if (vma->vm_file)
 		bpf_probe_read_kernel_str(d_iname, DNAME_INLINE_LEN - 1,
-					  vma->vm_file->f_path.dentry->d_iname);
+					  vma->vm_file->f_path.dentry->d_shortname.string);
 
 	/* check for VM_EXEC */
 	if (vma->vm_flags & VM_EXEC)
diff --git a/tools/testing/selftests/bpf/progs/find_vma_fail1.c b/tools/testing/selftests/bpf/progs/find_vma_fail1.c
index b3b326b8e2d1..7ba9a428f228 100644
--- a/tools/testing/selftests/bpf/progs/find_vma_fail1.c
+++ b/tools/testing/selftests/bpf/progs/find_vma_fail1.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2021 Facebook */
 #include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
+#define vm_flags vm_start
 
 char _license[] SEC("license") = "GPL";
 
@@ -13,7 +14,7 @@ static long write_vma(struct task_struct *task, struct vm_area_struct *vma,
 		      struct callback_ctx *data)
 {
 	/* writing to vma, which is illegal */
-	vma->vm_flags |= 0x55;
+	vma->vm_start = 0xffffffffff600000;
 
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/for_each_hash_modify.c b/tools/testing/selftests/bpf/progs/for_each_hash_modify.c
new file mode 100644
index 000000000000..82307166f789
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/for_each_hash_modify.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Intel Corporation */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 128);
+	__type(key, __u64);
+	__type(value, __u64);
+} hashmap SEC(".maps");
+
+static int cb(struct bpf_map *map, __u64 *key, __u64 *val, void *arg)
+{
+	bpf_map_delete_elem(map, key);
+	bpf_map_update_elem(map, key, val, 0);
+	return 0;
+}
+
+SEC("tc")
+int test_pkt_access(struct __sk_buff *skb)
+{
+	(void)skb;
+
+	bpf_for_each_map_elem(&hashmap, cb, NULL, 0);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/for_each_multi_maps.c b/tools/testing/selftests/bpf/progs/for_each_multi_maps.c
new file mode 100644
index 000000000000..ff0bed7d4459
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/for_each_multi_maps.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 3);
+	__type(key, __u32);
+	__type(value, __u64);
+} arraymap SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 5);
+	__type(key, __u32);
+	__type(value, __u64);
+} hashmap SEC(".maps");
+
+struct callback_ctx {
+	int output;
+};
+
+u32 data_output = 0;
+int use_array = 0;
+
+static __u64
+check_map_elem(struct bpf_map *map, __u32 *key, __u64 *val,
+	       struct callback_ctx *data)
+{
+	data->output += *val;
+	return 0;
+}
+
+SEC("tc")
+int test_pkt_access(struct __sk_buff *skb)
+{
+	struct callback_ctx data;
+
+	data.output = 0;
+	if (use_array)
+		bpf_for_each_map_elem(&arraymap, check_map_elem, &data, 0);
+	else
+		bpf_for_each_map_elem(&hashmap, check_map_elem, &data, 0);
+	data_output = data.output;
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/free_timer.c b/tools/testing/selftests/bpf/progs/free_timer.c
new file mode 100644
index 000000000000..4501ae8fc414
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/free_timer.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2025. Huawei Technologies Co., Ltd */
+#include <linux/bpf.h>
+#include <time.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+#define MAX_ENTRIES 8
+
+struct map_value {
+	struct bpf_timer timer;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, MAX_ENTRIES);
+} map SEC(".maps");
+
+static int timer_cb(void *map, void *key, struct map_value *value)
+{
+	volatile int sum = 0;
+	int i;
+
+	bpf_for(i, 0, 1024 * 1024) sum += i;
+
+	return 0;
+}
+
+static int start_cb(int key)
+{
+	struct map_value *value;
+
+	value = bpf_map_lookup_elem(&map, (void *)&key);
+	if (!value)
+		return 0;
+
+	bpf_timer_init(&value->timer, &map, CLOCK_MONOTONIC);
+	bpf_timer_set_callback(&value->timer, timer_cb);
+	/* Hope 100us will be enough to wake-up and run the overwrite thread */
+	bpf_timer_start(&value->timer, 100000, BPF_F_TIMER_CPU_PIN);
+
+	return 0;
+}
+
+static int overwrite_cb(int key)
+{
+	struct map_value zero = {};
+
+	/* Free the timer which may run on other CPU */
+	bpf_map_update_elem(&map, (void *)&key, &zero, BPF_ANY);
+
+	return 0;
+}
+
+SEC("syscall")
+int BPF_PROG(start_timer)
+{
+	bpf_loop(MAX_ENTRIES, start_cb, NULL, 0);
+	return 0;
+}
+
+SEC("syscall")
+int BPF_PROG(overwrite_timer)
+{
+	bpf_loop(MAX_ENTRIES, overwrite_cb, NULL, 0);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/freplace_attach_probe.c b/tools/testing/selftests/bpf/progs/freplace_attach_probe.c
index bb2a77c5b62b..370a0e1922e0 100644
--- a/tools/testing/selftests/bpf/progs/freplace_attach_probe.c
+++ b/tools/testing/selftests/bpf/progs/freplace_attach_probe.c
@@ -23,7 +23,7 @@ struct {
 SEC("freplace/handle_kprobe")
 int new_handle_kprobe(struct pt_regs *ctx)
 {
-	struct hmap_elem zero = {}, *val;
+	struct hmap_elem *val;
 	int key = 0;
 
 	val = bpf_map_lookup_elem(&hash_map, &key);
diff --git a/tools/testing/selftests/bpf/progs/freplace_connect_v4_prog.c b/tools/testing/selftests/bpf/progs/freplace_connect_v4_prog.c
index 544e5ac90461..d09bbd8ae8a8 100644
--- a/tools/testing/selftests/bpf/progs/freplace_connect_v4_prog.c
+++ b/tools/testing/selftests/bpf/progs/freplace_connect_v4_prog.c
@@ -12,7 +12,7 @@
 SEC("freplace/connect_v4_prog")
 int new_connect_v4_prog(struct bpf_sock_addr *ctx)
 {
-	// return value thats in invalid range
+	// return value that's in invalid range
 	return 255;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/freplace_dead_global_func.c b/tools/testing/selftests/bpf/progs/freplace_dead_global_func.c
new file mode 100644
index 000000000000..e6a75f86cac6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/freplace_dead_global_func.c
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+SEC("freplace")
+int freplace_prog(void)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/freplace_unreliable_prog.c b/tools/testing/selftests/bpf/progs/freplace_unreliable_prog.c
new file mode 100644
index 000000000000..624078abf3de
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/freplace_unreliable_prog.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+SEC("freplace/btf_unreliable_kprobe")
+/* context type is what BPF verifier expects for kprobe context, but target
+ * program has `stuct whatever *ctx` argument, so freplace operation will be
+ * rejected with the following message:
+ *
+ * arg0 replace_btf_unreliable_kprobe(struct pt_regs *) doesn't match btf_unreliable_kprobe(struct whatever *)
+ */
+int replace_btf_unreliable_kprobe(bpf_user_pt_regs_t *ctx)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/get_branch_snapshot.c b/tools/testing/selftests/bpf/progs/get_branch_snapshot.c
index a1b139888048..511ac634eef0 100644
--- a/tools/testing/selftests/bpf/progs/get_branch_snapshot.c
+++ b/tools/testing/selftests/bpf/progs/get_branch_snapshot.c
@@ -15,7 +15,7 @@ long total_entries = 0;
 #define ENTRY_CNT 32
 struct perf_branch_entry entries[ENTRY_CNT] = {};
 
-static inline bool in_range(__u64 val)
+static inline bool gbs_in_range(__u64 val)
 {
 	return (val >= address_low) && (val < address_high);
 }
@@ -31,7 +31,7 @@ int BPF_PROG(test1, int n, int ret)
 	for (i = 0; i < ENTRY_CNT; i++) {
 		if (i >= total_entries)
 			break;
-		if (in_range(entries[i].from) && in_range(entries[i].to))
+		if (gbs_in_range(entries[i].from) && gbs_in_range(entries[i].to))
 			test1_hits++;
 		else if (!test1_hits)
 			wasted_entries++;
diff --git a/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
index 68587b1de34e..30fd504856c7 100644
--- a/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
+++ b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
@@ -4,34 +4,16 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__uint(max_entries, 1);
-	__type(key, __u32);
-	__type(value, __u64);
-} cg_ids SEC(".maps");
-
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__uint(max_entries, 1);
-	__type(key, __u32);
-	__type(value, __u32);
-} pidmap SEC(".maps");
+__u64 cg_id;
+__u64 expected_pid;
 
 SEC("tracepoint/syscalls/sys_enter_nanosleep")
 int trace(void *ctx)
 {
 	__u32 pid = bpf_get_current_pid_tgid();
-	__u32 key = 0, *expected_pid;
-	__u64 *val;
-
-	expected_pid = bpf_map_lookup_elem(&pidmap, &key);
-	if (!expected_pid || *expected_pid != pid)
-		return 0;
 
-	val = bpf_map_lookup_elem(&cg_ids, &key);
-	if (val)
-		*val = bpf_get_current_cgroup_id();
+	if (expected_pid == pid)
+		cg_id = bpf_get_current_cgroup_id();
 
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/get_func_ip_test.c b/tools/testing/selftests/bpf/progs/get_func_ip_test.c
index 8559e698b40d..2011cacdeb18 100644
--- a/tools/testing/selftests/bpf/progs/get_func_ip_test.c
+++ b/tools/testing/selftests/bpf/progs/get_func_ip_test.c
@@ -1,18 +1,16 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/bpf.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
-#include <stdbool.h>
 
 char _license[] SEC("license") = "GPL";
 
-extern const void bpf_fentry_test1 __ksym;
+extern int bpf_fentry_test1(int a) __ksym;
+extern int bpf_modify_return_test(int a, int *b) __ksym;
+
 extern const void bpf_fentry_test2 __ksym;
 extern const void bpf_fentry_test3 __ksym;
 extern const void bpf_fentry_test4 __ksym;
-extern const void bpf_modify_return_test __ksym;
-extern const void bpf_fentry_test6 __ksym;
-extern const void bpf_fentry_test7 __ksym;
 
 extern bool CONFIG_X86_KERNEL_IBT __kconfig __weak;
 
@@ -83,3 +81,25 @@ int test6(struct pt_regs *ctx)
 	test6_result = (const void *) addr == 0;
 	return 0;
 }
+
+unsigned long uprobe_trigger;
+
+__u64 test7_result = 0;
+SEC("uprobe//proc/self/exe:uprobe_trigger")
+int BPF_UPROBE(test7)
+{
+	__u64 addr = bpf_get_func_ip(ctx);
+
+	test7_result = (const void *) addr == (const void *) uprobe_trigger;
+	return 0;
+}
+
+__u64 test8_result = 0;
+SEC("uretprobe//proc/self/exe:uprobe_trigger")
+int BPF_URETPROBE(test8, int ret)
+{
+	__u64 addr = bpf_get_func_ip(ctx);
+
+	test8_result = (const void *) addr == (const void *) uprobe_trigger;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/get_func_ip_uprobe_test.c b/tools/testing/selftests/bpf/progs/get_func_ip_uprobe_test.c
new file mode 100644
index 000000000000..052f8a4345a8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/get_func_ip_uprobe_test.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+unsigned long uprobe_trigger_body;
+
+__u64 test1_result = 0;
+SEC("uprobe//proc/self/exe:uprobe_trigger_body+1")
+int BPF_UPROBE(test1)
+{
+	__u64 addr = bpf_get_func_ip(ctx);
+
+	test1_result = (const void *) addr == (const void *) uprobe_trigger_body + 1;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/getpeername4_prog.c b/tools/testing/selftests/bpf/progs/getpeername4_prog.c
new file mode 100644
index 000000000000..4c97208cd25d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/getpeername4_prog.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Google LLC */
+
+#include "vmlinux.h"
+
+#include <string.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_kfuncs.h"
+
+#define REWRITE_ADDRESS_IP4   0xc0a801fe // 192.168.1.254
+#define REWRITE_ADDRESS_PORT4 4040
+
+SEC("cgroup/getpeername4")
+int getpeername_v4_prog(struct bpf_sock_addr *ctx)
+{
+	ctx->user_ip4 = bpf_htonl(REWRITE_ADDRESS_IP4);
+	ctx->user_port = bpf_htons(REWRITE_ADDRESS_PORT4);
+
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/getpeername6_prog.c b/tools/testing/selftests/bpf/progs/getpeername6_prog.c
new file mode 100644
index 000000000000..070e4d7f636c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/getpeername6_prog.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Google LLC */
+
+#include "vmlinux.h"
+
+#include <string.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_kfuncs.h"
+
+#define REWRITE_ADDRESS_IP6_0 0xfaceb00c
+#define REWRITE_ADDRESS_IP6_1 0x12345678
+#define REWRITE_ADDRESS_IP6_2 0x00000000
+#define REWRITE_ADDRESS_IP6_3 0x0000abcd
+
+#define REWRITE_ADDRESS_PORT6 6060
+
+SEC("cgroup/getpeername6")
+int getpeername_v6_prog(struct bpf_sock_addr *ctx)
+{
+	ctx->user_ip6[0] = bpf_htonl(REWRITE_ADDRESS_IP6_0);
+	ctx->user_ip6[1] = bpf_htonl(REWRITE_ADDRESS_IP6_1);
+	ctx->user_ip6[2] = bpf_htonl(REWRITE_ADDRESS_IP6_2);
+	ctx->user_ip6[3] = bpf_htonl(REWRITE_ADDRESS_IP6_3);
+	ctx->user_port = bpf_htons(REWRITE_ADDRESS_PORT6);
+
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/getpeername_unix_prog.c b/tools/testing/selftests/bpf/progs/getpeername_unix_prog.c
new file mode 100644
index 000000000000..5a76754f846b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/getpeername_unix_prog.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+
+#include <string.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_kfuncs.h"
+
+__u8 SERVUN_REWRITE_ADDRESS[] = "\0bpf_cgroup_unix_test_rewrite";
+
+SEC("cgroup/getpeername_unix")
+int getpeername_unix_prog(struct bpf_sock_addr *ctx)
+{
+	struct bpf_sock_addr_kern *sa_kern = bpf_cast_to_kern_ctx(ctx);
+	struct sockaddr_un *sa_kern_unaddr;
+	__u32 unaddrlen = offsetof(struct sockaddr_un, sun_path) +
+			  sizeof(SERVUN_REWRITE_ADDRESS) - 1;
+	int ret;
+
+	ret = bpf_sock_addr_set_sun_path(sa_kern, SERVUN_REWRITE_ADDRESS,
+					 sizeof(SERVUN_REWRITE_ADDRESS) - 1);
+	if (ret)
+		return 1;
+
+	if (sa_kern->uaddrlen != unaddrlen)
+		return 1;
+
+	sa_kern_unaddr = bpf_core_cast(sa_kern->uaddr, struct sockaddr_un);
+	if (memcmp(sa_kern_unaddr->sun_path, SERVUN_REWRITE_ADDRESS,
+			sizeof(SERVUN_REWRITE_ADDRESS) - 1) != 0)
+		return 1;
+
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/getsockname4_prog.c b/tools/testing/selftests/bpf/progs/getsockname4_prog.c
new file mode 100644
index 000000000000..e298487c6347
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/getsockname4_prog.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Google LLC */
+
+#include "vmlinux.h"
+
+#include <string.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_kfuncs.h"
+
+#define REWRITE_ADDRESS_IP4   0xc0a801fe // 192.168.1.254
+#define REWRITE_ADDRESS_PORT4 4040
+
+SEC("cgroup/getsockname4")
+int getsockname_v4_prog(struct bpf_sock_addr *ctx)
+{
+	ctx->user_ip4 = bpf_htonl(REWRITE_ADDRESS_IP4);
+	ctx->user_port = bpf_htons(REWRITE_ADDRESS_PORT4);
+
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/getsockname6_prog.c b/tools/testing/selftests/bpf/progs/getsockname6_prog.c
new file mode 100644
index 000000000000..811d10cd5525
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/getsockname6_prog.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Google LLC */
+
+#include "vmlinux.h"
+
+#include <string.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_kfuncs.h"
+
+#define REWRITE_ADDRESS_IP6_0 0xfaceb00c
+#define REWRITE_ADDRESS_IP6_1 0x12345678
+#define REWRITE_ADDRESS_IP6_2 0x00000000
+#define REWRITE_ADDRESS_IP6_3 0x0000abcd
+
+#define REWRITE_ADDRESS_PORT6 6060
+
+SEC("cgroup/getsockname6")
+int getsockname_v6_prog(struct bpf_sock_addr *ctx)
+{
+	ctx->user_ip6[0] = bpf_htonl(REWRITE_ADDRESS_IP6_0);
+	ctx->user_ip6[1] = bpf_htonl(REWRITE_ADDRESS_IP6_1);
+	ctx->user_ip6[2] = bpf_htonl(REWRITE_ADDRESS_IP6_2);
+	ctx->user_ip6[3] = bpf_htonl(REWRITE_ADDRESS_IP6_3);
+	ctx->user_port = bpf_htons(REWRITE_ADDRESS_PORT6);
+
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/getsockname_unix_prog.c b/tools/testing/selftests/bpf/progs/getsockname_unix_prog.c
new file mode 100644
index 000000000000..7867113c696f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/getsockname_unix_prog.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+
+#include <string.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_kfuncs.h"
+
+__u8 SERVUN_REWRITE_ADDRESS[] = "\0bpf_cgroup_unix_test_rewrite";
+
+SEC("cgroup/getsockname_unix")
+int getsockname_unix_prog(struct bpf_sock_addr *ctx)
+{
+	struct bpf_sock_addr_kern *sa_kern = bpf_cast_to_kern_ctx(ctx);
+	struct sockaddr_un *sa_kern_unaddr;
+	__u32 unaddrlen = offsetof(struct sockaddr_un, sun_path) +
+			  sizeof(SERVUN_REWRITE_ADDRESS) - 1;
+	int ret;
+
+	ret = bpf_sock_addr_set_sun_path(sa_kern, SERVUN_REWRITE_ADDRESS,
+					 sizeof(SERVUN_REWRITE_ADDRESS) - 1);
+	if (ret)
+		return 1;
+
+	if (sa_kern->uaddrlen != unaddrlen)
+		return 1;
+
+	sa_kern_unaddr = bpf_core_cast(sa_kern->uaddr, struct sockaddr_un);
+	if (memcmp(sa_kern_unaddr->sun_path, SERVUN_REWRITE_ADDRESS,
+			sizeof(SERVUN_REWRITE_ADDRESS) - 1) != 0)
+		return 1;
+
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/htab_mem_bench.c b/tools/testing/selftests/bpf/progs/htab_mem_bench.c
new file mode 100644
index 000000000000..b1b721b14d67
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/htab_mem_bench.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <stdbool.h>
+#include <errno.h>
+#include <linux/types.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#define OP_BATCH 64
+
+struct update_ctx {
+	unsigned int from;
+	unsigned int step;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, 4);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+} htab SEC(".maps");
+
+char _license[] SEC("license") = "GPL";
+
+unsigned char zeroed_value[4096];
+unsigned int nr_thread = 0;
+long op_cnt = 0;
+
+static int write_htab(unsigned int i, struct update_ctx *ctx, unsigned int flags)
+{
+	bpf_map_update_elem(&htab, &ctx->from, zeroed_value, flags);
+	ctx->from += ctx->step;
+
+	return 0;
+}
+
+static int overwrite_htab(unsigned int i, struct update_ctx *ctx)
+{
+	return write_htab(i, ctx, 0);
+}
+
+static int newwrite_htab(unsigned int i, struct update_ctx *ctx)
+{
+	return write_htab(i, ctx, BPF_NOEXIST);
+}
+
+static int del_htab(unsigned int i, struct update_ctx *ctx)
+{
+	bpf_map_delete_elem(&htab, &ctx->from);
+	ctx->from += ctx->step;
+
+	return 0;
+}
+
+SEC("?tp/syscalls/sys_enter_getpgid")
+int overwrite(void *ctx)
+{
+	struct update_ctx update;
+
+	update.from = bpf_get_smp_processor_id();
+	update.step = nr_thread;
+	bpf_loop(OP_BATCH, overwrite_htab, &update, 0);
+	__sync_fetch_and_add(&op_cnt, 1);
+	return 0;
+}
+
+SEC("?tp/syscalls/sys_enter_getpgid")
+int batch_add_batch_del(void *ctx)
+{
+	struct update_ctx update;
+
+	update.from = bpf_get_smp_processor_id();
+	update.step = nr_thread;
+	bpf_loop(OP_BATCH, overwrite_htab, &update, 0);
+
+	update.from = bpf_get_smp_processor_id();
+	bpf_loop(OP_BATCH, del_htab, &update, 0);
+
+	__sync_fetch_and_add(&op_cnt, 2);
+	return 0;
+}
+
+SEC("?tp/syscalls/sys_enter_getpgid")
+int add_only(void *ctx)
+{
+	struct update_ctx update;
+
+	update.from = bpf_get_smp_processor_id() / 2;
+	update.step = nr_thread / 2;
+	bpf_loop(OP_BATCH, newwrite_htab, &update, 0);
+	__sync_fetch_and_add(&op_cnt, 1);
+	return 0;
+}
+
+SEC("?tp/syscalls/sys_enter_getppid")
+int del_only(void *ctx)
+{
+	struct update_ctx update;
+
+	update.from = bpf_get_smp_processor_id() / 2;
+	update.step = nr_thread / 2;
+	bpf_loop(OP_BATCH, del_htab, &update, 0);
+	__sync_fetch_and_add(&op_cnt, 1);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/htab_reuse.c b/tools/testing/selftests/bpf/progs/htab_reuse.c
new file mode 100644
index 000000000000..7f7368cb3095
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/htab_reuse.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct htab_val {
+	struct bpf_spin_lock lock;
+	unsigned int data;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 64);
+	__type(key, unsigned int);
+	__type(value, struct htab_val);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+} htab SEC(".maps");
diff --git a/tools/testing/selftests/bpf/progs/htab_update.c b/tools/testing/selftests/bpf/progs/htab_update.c
index 7481bb30b29b..195d3b2fba00 100644
--- a/tools/testing/selftests/bpf/progs/htab_update.c
+++ b/tools/testing/selftests/bpf/progs/htab_update.c
@@ -6,24 +6,31 @@
 
 char _license[] SEC("license") = "GPL";
 
+/* Map value type: has BTF-managed field (bpf_timer) */
+struct val {
+	struct bpf_timer t;
+	__u64 payload;
+};
+
 struct {
 	__uint(type, BPF_MAP_TYPE_HASH);
 	__uint(max_entries, 1);
-	__uint(key_size, sizeof(__u32));
-	__uint(value_size, sizeof(__u32));
+	__type(key, __u32);
+	__type(value, struct val);
 } htab SEC(".maps");
 
 int pid = 0;
 int update_err = 0;
 
-SEC("?fentry/lookup_elem_raw")
-int lookup_elem_raw(void *ctx)
+SEC("?fentry/bpf_obj_free_fields")
+int bpf_obj_free_fields(void *ctx)
 {
-	__u32 key = 0, value = 1;
+	__u32 key = 0;
+	struct val value = { .payload = 1 };
 
 	if ((bpf_get_current_pid_tgid() >> 32) != pid)
 		return 0;
 
-	update_err = bpf_map_update_elem(&htab, &key, &value, 0);
+	update_err = bpf_map_update_elem(&htab, &key, &value, BPF_ANY);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/inner_array_lookup.c b/tools/testing/selftests/bpf/progs/inner_array_lookup.c
new file mode 100644
index 000000000000..c2c8f2fa451d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/inner_array_lookup.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct inner_map {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 5);
+	__type(key, int);
+	__type(value, int);
+} inner_map1 SEC(".maps");
+
+struct outer_map {
+	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+	__uint(max_entries, 3);
+	__type(key, int);
+	__array(values, struct inner_map);
+} outer_map1 SEC(".maps") = {
+	.values = {
+		[2] = &inner_map1,
+	},
+};
+
+SEC("raw_tp/sys_enter")
+int handle__sys_enter(void *ctx)
+{
+	int outer_key = 2, inner_key = 3;
+	int *val;
+	void *map;
+
+	map = bpf_map_lookup_elem(&outer_map1, &outer_key);
+	if (!map)
+		return 1;
+
+	val = bpf_map_lookup_elem(map, &inner_key);
+	if (!val)
+		return 1;
+
+	if (*val == 1)
+		*val = 2;
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/ip_check_defrag.c b/tools/testing/selftests/bpf/progs/ip_check_defrag.c
new file mode 100644
index 000000000000..0e87ad1ebcfa
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/ip_check_defrag.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include "bpf_tracing_net.h"
+
+#define NF_DROP			0
+#define NF_ACCEPT		1
+#define ETH_P_IP		0x0800
+#define ETH_P_IPV6		0x86DD
+#define IP_MF			0x2000
+#define IP_OFFSET		0x1FFF
+#define NEXTHDR_FRAGMENT	44
+
+volatile int shootdowns = 0;
+
+static bool is_frag_v4(struct iphdr *iph)
+{
+	int offset;
+	int flags;
+
+	offset = bpf_ntohs(iph->frag_off);
+	flags = offset & ~IP_OFFSET;
+	offset &= IP_OFFSET;
+	offset <<= 3;
+
+	return (flags & IP_MF) || offset;
+}
+
+static bool is_frag_v6(struct ipv6hdr *ip6h)
+{
+	/* Simplifying assumption that there are no extension headers
+	 * between fixed header and fragmentation header. This assumption
+	 * is only valid in this test case. It saves us the hassle of
+	 * searching all potential extension headers.
+	 */
+	return ip6h->nexthdr == NEXTHDR_FRAGMENT;
+}
+
+static int handle_v4(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	u8 iph_buf[20] = {};
+	struct iphdr *iph;
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr))
+		return NF_DROP;
+
+	iph = bpf_dynptr_slice(&ptr, 0, iph_buf, sizeof(iph_buf));
+	if (!iph)
+		return NF_DROP;
+
+	/* Shootdown any frags */
+	if (is_frag_v4(iph)) {
+		shootdowns++;
+		return NF_DROP;
+	}
+
+	return NF_ACCEPT;
+}
+
+static int handle_v6(struct __sk_buff *skb)
+{
+	struct bpf_dynptr ptr;
+	struct ipv6hdr *ip6h;
+	u8 ip6h_buf[40] = {};
+
+	if (bpf_dynptr_from_skb(skb, 0, &ptr))
+		return NF_DROP;
+
+	ip6h = bpf_dynptr_slice(&ptr, 0, ip6h_buf, sizeof(ip6h_buf));
+	if (!ip6h)
+		return NF_DROP;
+
+	/* Shootdown any frags */
+	if (is_frag_v6(ip6h)) {
+		shootdowns++;
+		return NF_DROP;
+	}
+
+	return NF_ACCEPT;
+}
+
+SEC("netfilter")
+int defrag(struct bpf_nf_ctx *ctx)
+{
+	struct __sk_buff *skb = (struct __sk_buff *)ctx->skb;
+
+	switch (bpf_ntohs(ctx->skb->protocol)) {
+	case ETH_P_IP:
+		return handle_v4(skb);
+	case ETH_P_IPV6:
+		return handle_v6(skb);
+	default:
+		return NF_ACCEPT;
+	}
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/irq.c b/tools/testing/selftests/bpf/progs/irq.c
new file mode 100644
index 000000000000..74d912b22de9
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/irq.c
@@ -0,0 +1,566 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+unsigned long global_flags;
+
+extern void bpf_local_irq_save(unsigned long *) __weak __ksym;
+extern void bpf_local_irq_restore(unsigned long *) __weak __ksym;
+extern int bpf_copy_from_user_str(void *dst, u32 dst__sz, const void *unsafe_ptr__ign, u64 flags) __weak __ksym;
+
+struct bpf_res_spin_lock lockA __hidden SEC(".data.A");
+struct bpf_res_spin_lock lockB __hidden SEC(".data.B");
+
+SEC("?tc")
+__failure __msg("arg#0 doesn't point to an irq flag on stack")
+int irq_save_bad_arg(struct __sk_buff *ctx)
+{
+	bpf_local_irq_save(&global_flags);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("arg#0 doesn't point to an irq flag on stack")
+int irq_restore_bad_arg(struct __sk_buff *ctx)
+{
+	bpf_local_irq_restore(&global_flags);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_local_irq_save-ed region")
+int irq_restore_missing_2(struct __sk_buff *ctx)
+{
+	unsigned long flags1;
+	unsigned long flags2;
+
+	bpf_local_irq_save(&flags1);
+	bpf_local_irq_save(&flags2);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_local_irq_save-ed region")
+int irq_restore_missing_3(struct __sk_buff *ctx)
+{
+	unsigned long flags1;
+	unsigned long flags2;
+	unsigned long flags3;
+
+	bpf_local_irq_save(&flags1);
+	bpf_local_irq_save(&flags2);
+	bpf_local_irq_save(&flags3);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_local_irq_save-ed region")
+int irq_restore_missing_3_minus_2(struct __sk_buff *ctx)
+{
+	unsigned long flags1;
+	unsigned long flags2;
+	unsigned long flags3;
+
+	bpf_local_irq_save(&flags1);
+	bpf_local_irq_save(&flags2);
+	bpf_local_irq_save(&flags3);
+	bpf_local_irq_restore(&flags3);
+	bpf_local_irq_restore(&flags2);
+	return 0;
+}
+
+static __noinline void local_irq_save(unsigned long *flags)
+{
+	bpf_local_irq_save(flags);
+}
+
+static __noinline void local_irq_restore(unsigned long *flags)
+{
+	bpf_local_irq_restore(flags);
+}
+
+SEC("?tc")
+__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_local_irq_save-ed region")
+int irq_restore_missing_1_subprog(struct __sk_buff *ctx)
+{
+	unsigned long flags;
+
+	local_irq_save(&flags);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_local_irq_save-ed region")
+int irq_restore_missing_2_subprog(struct __sk_buff *ctx)
+{
+	unsigned long flags1;
+	unsigned long flags2;
+
+	local_irq_save(&flags1);
+	local_irq_save(&flags2);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_local_irq_save-ed region")
+int irq_restore_missing_3_subprog(struct __sk_buff *ctx)
+{
+	unsigned long flags1;
+	unsigned long flags2;
+	unsigned long flags3;
+
+	local_irq_save(&flags1);
+	local_irq_save(&flags2);
+	local_irq_save(&flags3);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_local_irq_save-ed region")
+int irq_restore_missing_3_minus_2_subprog(struct __sk_buff *ctx)
+{
+	unsigned long flags1;
+	unsigned long flags2;
+	unsigned long flags3;
+
+	local_irq_save(&flags1);
+	local_irq_save(&flags2);
+	local_irq_save(&flags3);
+	local_irq_restore(&flags3);
+	local_irq_restore(&flags2);
+	return 0;
+}
+
+SEC("?tc")
+__success
+int irq_balance(struct __sk_buff *ctx)
+{
+	unsigned long flags;
+
+	local_irq_save(&flags);
+	local_irq_restore(&flags);
+	return 0;
+}
+
+SEC("?tc")
+__success
+int irq_balance_n(struct __sk_buff *ctx)
+{
+	unsigned long flags1;
+	unsigned long flags2;
+	unsigned long flags3;
+
+	local_irq_save(&flags1);
+	local_irq_save(&flags2);
+	local_irq_save(&flags3);
+	local_irq_restore(&flags3);
+	local_irq_restore(&flags2);
+	local_irq_restore(&flags1);
+	return 0;
+}
+
+static __noinline void local_irq_balance(void)
+{
+	unsigned long flags;
+
+	local_irq_save(&flags);
+	local_irq_restore(&flags);
+}
+
+static __noinline void local_irq_balance_n(void)
+{
+	unsigned long flags1;
+	unsigned long flags2;
+	unsigned long flags3;
+
+	local_irq_save(&flags1);
+	local_irq_save(&flags2);
+	local_irq_save(&flags3);
+	local_irq_restore(&flags3);
+	local_irq_restore(&flags2);
+	local_irq_restore(&flags1);
+}
+
+SEC("?tc")
+__success
+int irq_balance_subprog(struct __sk_buff *ctx)
+{
+	local_irq_balance();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("sleepable helper bpf_copy_from_user#")
+int irq_sleepable_helper(void *ctx)
+{
+	unsigned long flags;
+	u32 data;
+
+	local_irq_save(&flags);
+	bpf_copy_from_user(&data, sizeof(data), NULL);
+	local_irq_restore(&flags);
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("kernel func bpf_copy_from_user_str is sleepable within IRQ-disabled region")
+int irq_sleepable_kfunc(void *ctx)
+{
+	unsigned long flags;
+	u32 data;
+
+	local_irq_save(&flags);
+	bpf_copy_from_user_str(&data, sizeof(data), NULL, 0);
+	local_irq_restore(&flags);
+	return 0;
+}
+
+int __noinline global_local_irq_balance(void)
+{
+	local_irq_balance_n();
+	return 0;
+}
+
+SEC("?tc")
+__success
+int irq_global_subprog(struct __sk_buff *ctx)
+{
+	unsigned long flags;
+
+	bpf_local_irq_save(&flags);
+	global_local_irq_balance();
+	bpf_local_irq_restore(&flags);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("cannot restore irq state out of order")
+int irq_restore_ooo(struct __sk_buff *ctx)
+{
+	unsigned long flags1;
+	unsigned long flags2;
+
+	bpf_local_irq_save(&flags1);
+	bpf_local_irq_save(&flags2);
+	bpf_local_irq_restore(&flags1);
+	bpf_local_irq_restore(&flags2);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("cannot restore irq state out of order")
+int irq_restore_ooo_3(struct __sk_buff *ctx)
+{
+	unsigned long flags1;
+	unsigned long flags2;
+	unsigned long flags3;
+
+	bpf_local_irq_save(&flags1);
+	bpf_local_irq_save(&flags2);
+	bpf_local_irq_restore(&flags2);
+	bpf_local_irq_save(&flags3);
+	bpf_local_irq_restore(&flags1);
+	bpf_local_irq_restore(&flags3);
+	return 0;
+}
+
+static __noinline void local_irq_save_3(unsigned long *flags1, unsigned long *flags2,
+					unsigned long *flags3)
+{
+	local_irq_save(flags1);
+	local_irq_save(flags2);
+	local_irq_save(flags3);
+}
+
+SEC("?tc")
+__success
+int irq_restore_3_subprog(struct __sk_buff *ctx)
+{
+	unsigned long flags1;
+	unsigned long flags2;
+	unsigned long flags3;
+
+	local_irq_save_3(&flags1, &flags2, &flags3);
+	bpf_local_irq_restore(&flags3);
+	bpf_local_irq_restore(&flags2);
+	bpf_local_irq_restore(&flags1);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("cannot restore irq state out of order")
+int irq_restore_4_subprog(struct __sk_buff *ctx)
+{
+	unsigned long flags1;
+	unsigned long flags2;
+	unsigned long flags3;
+	unsigned long flags4;
+
+	local_irq_save_3(&flags1, &flags2, &flags3);
+	bpf_local_irq_restore(&flags3);
+	bpf_local_irq_save(&flags4);
+	bpf_local_irq_restore(&flags4);
+	bpf_local_irq_restore(&flags1);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("cannot restore irq state out of order")
+int irq_restore_ooo_3_subprog(struct __sk_buff *ctx)
+{
+	unsigned long flags1;
+	unsigned long flags2;
+	unsigned long flags3;
+
+	local_irq_save_3(&flags1, &flags2, &flags3);
+	bpf_local_irq_restore(&flags3);
+	bpf_local_irq_restore(&flags2);
+	bpf_local_irq_save(&flags3);
+	bpf_local_irq_restore(&flags1);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("expected an initialized")
+int irq_restore_invalid(struct __sk_buff *ctx)
+{
+	unsigned long flags1;
+	unsigned long flags = 0xfaceb00c;
+
+	bpf_local_irq_save(&flags1);
+	bpf_local_irq_restore(&flags);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("expected uninitialized")
+int irq_save_invalid(struct __sk_buff *ctx)
+{
+	unsigned long flags1;
+
+	bpf_local_irq_save(&flags1);
+	bpf_local_irq_save(&flags1);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("expected an initialized")
+int irq_restore_iter(struct __sk_buff *ctx)
+{
+	struct bpf_iter_num it;
+
+	bpf_iter_num_new(&it, 0, 42);
+	bpf_local_irq_restore((unsigned long *)&it);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("Unreleased reference id=1")
+int irq_save_iter(struct __sk_buff *ctx)
+{
+	struct bpf_iter_num it;
+
+	/* Ensure same sized slot has st->ref_obj_id set, so we reject based on
+	 * slot_type != STACK_IRQ_FLAG...
+	 */
+	_Static_assert(sizeof(it) == sizeof(unsigned long), "broken iterator size");
+
+	bpf_iter_num_new(&it, 0, 42);
+	bpf_local_irq_save((unsigned long *)&it);
+	bpf_local_irq_restore((unsigned long *)&it);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("expected an initialized")
+int irq_flag_overwrite(struct __sk_buff *ctx)
+{
+	unsigned long flags;
+
+	bpf_local_irq_save(&flags);
+	flags = 0xdeadbeef;
+	bpf_local_irq_restore(&flags);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("expected an initialized")
+int irq_flag_overwrite_partial(struct __sk_buff *ctx)
+{
+	unsigned long flags;
+
+	bpf_local_irq_save(&flags);
+	*(((char *)&flags) + 1) = 0xff;
+	bpf_local_irq_restore(&flags);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("cannot restore irq state out of order")
+int irq_ooo_refs_array(struct __sk_buff *ctx)
+{
+	unsigned long flags[4];
+	struct { int i; } *p;
+
+	/* refs=1 */
+	bpf_local_irq_save(&flags[0]);
+
+	/* refs=1,2 */
+	p = bpf_obj_new(typeof(*p));
+	if (!p) {
+		bpf_local_irq_restore(&flags[0]);
+		return 0;
+	}
+
+	/* refs=1,2,3 */
+	bpf_local_irq_save(&flags[1]);
+
+	/* refs=1,2,3,4 */
+	bpf_local_irq_save(&flags[2]);
+
+	/* Now when we remove ref=2, the verifier must not break the ordering in
+	 * the refs array between 1,3,4. With an older implementation, the
+	 * verifier would swap the last element with the removed element, but to
+	 * maintain the stack property we need to use memmove.
+	 */
+	bpf_obj_drop(p);
+
+	/* Save and restore to reset active_irq_id to 3, as the ordering is now
+	 * refs=1,4,3. When restoring the linear scan will find prev_id in order
+	 * as 3 instead of 4.
+	 */
+	bpf_local_irq_save(&flags[3]);
+	bpf_local_irq_restore(&flags[3]);
+
+	/* With the incorrect implementation, we can release flags[1], flags[2],
+	 * and flags[0], i.e. in the wrong order.
+	 */
+	bpf_local_irq_restore(&flags[1]);
+	bpf_local_irq_restore(&flags[2]);
+	bpf_local_irq_restore(&flags[0]);
+	return 0;
+}
+
+int __noinline
+global_subprog(int i)
+{
+	if (i)
+		bpf_printk("%p", &i);
+	return i;
+}
+
+int __noinline
+global_sleepable_helper_subprog(int i)
+{
+	if (i)
+		bpf_copy_from_user(&i, sizeof(i), NULL);
+	return i;
+}
+
+int __noinline
+global_sleepable_kfunc_subprog(int i)
+{
+	if (i)
+		bpf_copy_from_user_str(&i, sizeof(i), NULL, 0);
+	global_subprog(i);
+	return i;
+}
+
+int __noinline
+global_subprog_calling_sleepable_global(int i)
+{
+	if (!i)
+		global_sleepable_kfunc_subprog(i);
+	return i;
+}
+
+SEC("?syscall")
+__success
+int irq_non_sleepable_global_subprog(void *ctx)
+{
+	unsigned long flags;
+
+	bpf_local_irq_save(&flags);
+	global_subprog(0);
+	bpf_local_irq_restore(&flags);
+	return 0;
+}
+
+SEC("?syscall")
+__failure __msg("global functions that may sleep are not allowed in non-sleepable context")
+int irq_sleepable_helper_global_subprog(void *ctx)
+{
+	unsigned long flags;
+
+	bpf_local_irq_save(&flags);
+	global_sleepable_helper_subprog(0);
+	bpf_local_irq_restore(&flags);
+	return 0;
+}
+
+SEC("?syscall")
+__failure __msg("global functions that may sleep are not allowed in non-sleepable context")
+int irq_sleepable_global_subprog_indirect(void *ctx)
+{
+	unsigned long flags;
+
+	bpf_local_irq_save(&flags);
+	global_subprog_calling_sleepable_global(0);
+	bpf_local_irq_restore(&flags);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("cannot restore irq state out of order")
+int irq_ooo_lock_cond_inv(struct __sk_buff *ctx)
+{
+	unsigned long flags1, flags2;
+
+	if (bpf_res_spin_lock_irqsave(&lockA, &flags1))
+		return 0;
+	if (bpf_res_spin_lock_irqsave(&lockB, &flags2)) {
+		bpf_res_spin_unlock_irqrestore(&lockA, &flags1);
+		return 0;
+	}
+
+	bpf_res_spin_unlock_irqrestore(&lockB, &flags1);
+	bpf_res_spin_unlock_irqrestore(&lockA, &flags2);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("function calls are not allowed")
+int irq_wrong_kfunc_class_1(struct __sk_buff *ctx)
+{
+	unsigned long flags1;
+
+	if (bpf_res_spin_lock_irqsave(&lockA, &flags1))
+		return 0;
+	/* For now, bpf_local_irq_restore is not allowed in critical section,
+	 * but this test ensures error will be caught with kfunc_class when it's
+	 * opened up. Tested by temporarily permitting this kfunc in critical
+	 * section.
+	 */
+	bpf_local_irq_restore(&flags1);
+	bpf_res_spin_unlock_irqrestore(&lockA, &flags1);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("function calls are not allowed")
+int irq_wrong_kfunc_class_2(struct __sk_buff *ctx)
+{
+	unsigned long flags1, flags2;
+
+	bpf_local_irq_save(&flags1);
+	if (bpf_res_spin_lock_irqsave(&lockA, &flags2))
+		return 0;
+	bpf_local_irq_restore(&flags2);
+	bpf_res_spin_unlock_irqrestore(&lockA, &flags1);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c
new file mode 100644
index 000000000000..7dd92a303bf6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/iters.c
@@ -0,0 +1,1929 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "bpf_compiler.h"
+
+static volatile int zero = 0;
+
+int my_pid;
+int arr[256];
+int small_arr[16] SEC(".data.small_arr");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 10);
+	__type(key, int);
+	__type(value, int);
+} amap SEC(".maps");
+
+#ifdef REAL_TEST
+#define MY_PID_GUARD() if (my_pid != (bpf_get_current_pid_tgid() >> 32)) return 0
+#else
+#define MY_PID_GUARD() ({ })
+#endif
+
+SEC("?raw_tp")
+__failure __msg("math between map_value pointer and register with unbounded min value is not allowed")
+int iter_err_unsafe_c_loop(const void *ctx)
+{
+	struct bpf_iter_num it;
+	int *v, i = zero; /* obscure initial value of i */
+
+	MY_PID_GUARD();
+
+	bpf_iter_num_new(&it, 0, 1000);
+	while ((v = bpf_iter_num_next(&it))) {
+		i++;
+	}
+	bpf_iter_num_destroy(&it);
+
+	small_arr[i] = 123; /* invalid */
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("unbounded memory access")
+int iter_err_unsafe_asm_loop(const void *ctx)
+{
+	struct bpf_iter_num it;
+
+	MY_PID_GUARD();
+
+	asm volatile (
+		"r6 = %[zero];" /* iteration counter */
+		"r1 = %[it];" /* iterator state */
+		"r2 = 0;"
+		"r3 = 1000;"
+		"r4 = 1;"
+		"call %[bpf_iter_num_new];"
+	"loop:"
+		"r1 = %[it];"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto out;"
+		"r6 += 1;"
+		"goto loop;"
+	"out:"
+		"r1 = %[it];"
+		"call %[bpf_iter_num_destroy];"
+		"r1 = %[small_arr];"
+		"r2 = r6;"
+		"r2 <<= 2;"
+		"r1 += r2;"
+		"*(u32 *)(r1 + 0) = r6;" /* invalid */
+		:
+		: [it]"r"(&it),
+		  [small_arr]"r"(small_arr),
+		  [zero]"r"(zero),
+		  __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy)
+		: __clobber_common, "r6"
+	);
+
+	return 0;
+}
+
+SEC("raw_tp")
+__success
+int iter_while_loop(const void *ctx)
+{
+	struct bpf_iter_num it;
+	int *v;
+
+	MY_PID_GUARD();
+
+	bpf_iter_num_new(&it, 0, 3);
+	while ((v = bpf_iter_num_next(&it))) {
+		bpf_printk("ITER_BASIC: E1 VAL: v=%d", *v);
+	}
+	bpf_iter_num_destroy(&it);
+
+	return 0;
+}
+
+SEC("raw_tp")
+__success
+int iter_while_loop_auto_cleanup(const void *ctx)
+{
+	__attribute__((cleanup(bpf_iter_num_destroy))) struct bpf_iter_num it;
+	int *v;
+
+	MY_PID_GUARD();
+
+	bpf_iter_num_new(&it, 0, 3);
+	while ((v = bpf_iter_num_next(&it))) {
+		bpf_printk("ITER_BASIC: E1 VAL: v=%d", *v);
+	}
+	/* (!) no explicit bpf_iter_num_destroy() */
+
+	return 0;
+}
+
+SEC("raw_tp")
+__success
+int iter_for_loop(const void *ctx)
+{
+	struct bpf_iter_num it;
+	int *v;
+
+	MY_PID_GUARD();
+
+	bpf_iter_num_new(&it, 5, 10);
+	for (v = bpf_iter_num_next(&it); v; v = bpf_iter_num_next(&it)) {
+		bpf_printk("ITER_BASIC: E2 VAL: v=%d", *v);
+	}
+	bpf_iter_num_destroy(&it);
+
+	return 0;
+}
+
+SEC("raw_tp")
+__success
+int iter_bpf_for_each_macro(const void *ctx)
+{
+	int *v;
+
+	MY_PID_GUARD();
+
+	bpf_for_each(num, v, 5, 10) {
+		bpf_printk("ITER_BASIC: E2 VAL: v=%d", *v);
+	}
+
+	return 0;
+}
+
+SEC("raw_tp")
+__success
+int iter_bpf_for_macro(const void *ctx)
+{
+	int i;
+
+	MY_PID_GUARD();
+
+	bpf_for(i, 5, 10) {
+		bpf_printk("ITER_BASIC: E2 VAL: v=%d", i);
+	}
+
+	return 0;
+}
+
+SEC("raw_tp")
+__success
+int iter_pragma_unroll_loop(const void *ctx)
+{
+	struct bpf_iter_num it;
+	int *v, i;
+
+	MY_PID_GUARD();
+
+	bpf_iter_num_new(&it, 0, 2);
+	__pragma_loop_no_unroll
+	for (i = 0; i < 3; i++) {
+		v = bpf_iter_num_next(&it);
+		bpf_printk("ITER_BASIC: E3 VAL: i=%d v=%d", i, v ? *v : -1);
+	}
+	bpf_iter_num_destroy(&it);
+
+	return 0;
+}
+
+SEC("raw_tp")
+__success
+int iter_manual_unroll_loop(const void *ctx)
+{
+	struct bpf_iter_num it;
+	int *v;
+
+	MY_PID_GUARD();
+
+	bpf_iter_num_new(&it, 100, 200);
+	v = bpf_iter_num_next(&it);
+	bpf_printk("ITER_BASIC: E4 VAL: v=%d", v ? *v : -1);
+	v = bpf_iter_num_next(&it);
+	bpf_printk("ITER_BASIC: E4 VAL: v=%d", v ? *v : -1);
+	v = bpf_iter_num_next(&it);
+	bpf_printk("ITER_BASIC: E4 VAL: v=%d", v ? *v : -1);
+	v = bpf_iter_num_next(&it);
+	bpf_printk("ITER_BASIC: E4 VAL: v=%d\n", v ? *v : -1);
+	bpf_iter_num_destroy(&it);
+
+	return 0;
+}
+
+SEC("raw_tp")
+__success
+int iter_multiple_sequential_loops(const void *ctx)
+{
+	struct bpf_iter_num it;
+	int *v, i;
+
+	MY_PID_GUARD();
+
+	bpf_iter_num_new(&it, 0, 3);
+	while ((v = bpf_iter_num_next(&it))) {
+		bpf_printk("ITER_BASIC: E1 VAL: v=%d", *v);
+	}
+	bpf_iter_num_destroy(&it);
+
+	bpf_iter_num_new(&it, 5, 10);
+	for (v = bpf_iter_num_next(&it); v; v = bpf_iter_num_next(&it)) {
+		bpf_printk("ITER_BASIC: E2 VAL: v=%d", *v);
+	}
+	bpf_iter_num_destroy(&it);
+
+	bpf_iter_num_new(&it, 0, 2);
+	__pragma_loop_no_unroll
+	for (i = 0; i < 3; i++) {
+		v = bpf_iter_num_next(&it);
+		bpf_printk("ITER_BASIC: E3 VAL: i=%d v=%d", i, v ? *v : -1);
+	}
+	bpf_iter_num_destroy(&it);
+
+	bpf_iter_num_new(&it, 100, 200);
+	v = bpf_iter_num_next(&it);
+	bpf_printk("ITER_BASIC: E4 VAL: v=%d", v ? *v : -1);
+	v = bpf_iter_num_next(&it);
+	bpf_printk("ITER_BASIC: E4 VAL: v=%d", v ? *v : -1);
+	v = bpf_iter_num_next(&it);
+	bpf_printk("ITER_BASIC: E4 VAL: v=%d", v ? *v : -1);
+	v = bpf_iter_num_next(&it);
+	bpf_printk("ITER_BASIC: E4 VAL: v=%d\n", v ? *v : -1);
+	bpf_iter_num_destroy(&it);
+
+	return 0;
+}
+
+SEC("raw_tp")
+__success
+int iter_limit_cond_break_loop(const void *ctx)
+{
+	struct bpf_iter_num it;
+	int *v, i = 0, sum = 0;
+
+	MY_PID_GUARD();
+
+	bpf_iter_num_new(&it, 0, 10);
+	while ((v = bpf_iter_num_next(&it))) {
+		bpf_printk("ITER_SIMPLE: i=%d v=%d", i, *v);
+		sum += *v;
+
+		i++;
+		if (i > 3)
+			break;
+	}
+	bpf_iter_num_destroy(&it);
+
+	bpf_printk("ITER_SIMPLE: sum=%d\n", sum);
+
+	return 0;
+}
+
+SEC("raw_tp")
+__success
+int iter_obfuscate_counter(const void *ctx)
+{
+	struct bpf_iter_num it;
+	int *v, sum = 0;
+	/* Make i's initial value unknowable for verifier to prevent it from
+	 * pruning if/else branch inside the loop body and marking i as precise.
+	 */
+	int i = zero;
+
+	MY_PID_GUARD();
+
+	bpf_iter_num_new(&it, 0, 10);
+	while ((v = bpf_iter_num_next(&it))) {
+		int x;
+
+		i += 1;
+
+		/* If we initialized i as `int i = 0;` above, verifier would
+		 * track that i becomes 1 on first iteration after increment
+		 * above, and here verifier would eagerly prune else branch
+		 * and mark i as precise, ruining open-coded iterator logic
+		 * completely, as each next iteration would have a different
+		 * *precise* value of i, and thus there would be no
+		 * convergence of state. This would result in reaching maximum
+		 * instruction limit, no matter what the limit is.
+		 */
+		if (i == 1)
+			x = 123;
+		else
+			x = i * 3 + 1;
+
+		bpf_printk("ITER_OBFUSCATE_COUNTER: i=%d v=%d x=%d", i, *v, x);
+
+		sum += x;
+	}
+	bpf_iter_num_destroy(&it);
+
+	bpf_printk("ITER_OBFUSCATE_COUNTER: sum=%d\n", sum);
+
+	return 0;
+}
+
+SEC("raw_tp")
+__success
+int iter_search_loop(const void *ctx)
+{
+	struct bpf_iter_num it;
+	int *v, *elem = NULL;
+	bool found = false;
+
+	MY_PID_GUARD();
+
+	bpf_iter_num_new(&it, 0, 10);
+
+	while ((v = bpf_iter_num_next(&it))) {
+		bpf_printk("ITER_SEARCH_LOOP: v=%d", *v);
+
+		if (*v == 2) {
+			found = true;
+			elem = v;
+			barrier_var(elem);
+		}
+	}
+
+	/* should fail to verify if bpf_iter_num_destroy() is here */
+
+	if (found)
+		/* here found element will be wrong, we should have copied
+		 * value to a variable, but here we want to make sure we can
+		 * access memory after the loop anyways
+		 */
+		bpf_printk("ITER_SEARCH_LOOP: FOUND IT = %d!\n", *elem);
+	else
+		bpf_printk("ITER_SEARCH_LOOP: NOT FOUND IT!\n");
+
+	bpf_iter_num_destroy(&it);
+
+	return 0;
+}
+
+SEC("raw_tp")
+__success
+int iter_array_fill(const void *ctx)
+{
+	int sum, i;
+
+	MY_PID_GUARD();
+
+	bpf_for(i, 0, ARRAY_SIZE(arr)) {
+		arr[i] = i * 2;
+	}
+
+	sum = 0;
+	bpf_for(i, 0, ARRAY_SIZE(arr)) {
+		sum += arr[i];
+	}
+
+	bpf_printk("ITER_ARRAY_FILL: sum=%d (should be %d)\n", sum, 255 * 256);
+
+	return 0;
+}
+
+static int arr2d[4][5];
+static int arr2d_row_sums[4];
+static int arr2d_col_sums[5];
+
+SEC("raw_tp")
+__success
+int iter_nested_iters(const void *ctx)
+{
+	int sum, row, col;
+
+	MY_PID_GUARD();
+
+	bpf_for(row, 0, ARRAY_SIZE(arr2d)) {
+		bpf_for( col, 0, ARRAY_SIZE(arr2d[0])) {
+			arr2d[row][col] = row * col;
+		}
+	}
+
+	/* zero-initialize sums */
+	sum = 0;
+	bpf_for(row, 0, ARRAY_SIZE(arr2d)) {
+		arr2d_row_sums[row] = 0;
+	}
+	bpf_for(col, 0, ARRAY_SIZE(arr2d[0])) {
+		arr2d_col_sums[col] = 0;
+	}
+
+	/* calculate sums */
+	bpf_for(row, 0, ARRAY_SIZE(arr2d)) {
+		bpf_for(col, 0, ARRAY_SIZE(arr2d[0])) {
+			sum += arr2d[row][col];
+			arr2d_row_sums[row] += arr2d[row][col];
+			arr2d_col_sums[col] += arr2d[row][col];
+		}
+	}
+
+	bpf_printk("ITER_NESTED_ITERS: total sum=%d", sum);
+	bpf_for(row, 0, ARRAY_SIZE(arr2d)) {
+		bpf_printk("ITER_NESTED_ITERS: row #%d sum=%d", row, arr2d_row_sums[row]);
+	}
+	bpf_for(col, 0, ARRAY_SIZE(arr2d[0])) {
+		bpf_printk("ITER_NESTED_ITERS: col #%d sum=%d%s",
+			   col, arr2d_col_sums[col],
+			   col == ARRAY_SIZE(arr2d[0]) - 1 ? "\n" : "");
+	}
+
+	return 0;
+}
+
+SEC("raw_tp")
+__success
+int iter_nested_deeply_iters(const void *ctx)
+{
+	int sum = 0;
+
+	MY_PID_GUARD();
+
+	bpf_repeat(10) {
+		bpf_repeat(10) {
+			bpf_repeat(10) {
+				bpf_repeat(10) {
+					bpf_repeat(10) {
+						sum += 1;
+					}
+				}
+			}
+		}
+		/* validate that we can break from inside bpf_repeat() */
+		break;
+	}
+
+	return sum;
+}
+
+static __noinline void fill_inner_dimension(int row)
+{
+	int col;
+
+	bpf_for(col, 0, ARRAY_SIZE(arr2d[0])) {
+		arr2d[row][col] = row * col;
+	}
+}
+
+static __noinline int sum_inner_dimension(int row)
+{
+	int sum = 0, col;
+
+	bpf_for(col, 0, ARRAY_SIZE(arr2d[0])) {
+		sum += arr2d[row][col];
+		arr2d_row_sums[row] += arr2d[row][col];
+		arr2d_col_sums[col] += arr2d[row][col];
+	}
+
+	return sum;
+}
+
+SEC("raw_tp")
+__success
+int iter_subprog_iters(const void *ctx)
+{
+	int sum, row, col;
+
+	MY_PID_GUARD();
+
+	bpf_for(row, 0, ARRAY_SIZE(arr2d)) {
+		fill_inner_dimension(row);
+	}
+
+	/* zero-initialize sums */
+	sum = 0;
+	bpf_for(row, 0, ARRAY_SIZE(arr2d)) {
+		arr2d_row_sums[row] = 0;
+	}
+	bpf_for(col, 0, ARRAY_SIZE(arr2d[0])) {
+		arr2d_col_sums[col] = 0;
+	}
+
+	/* calculate sums */
+	bpf_for(row, 0, ARRAY_SIZE(arr2d)) {
+		sum += sum_inner_dimension(row);
+	}
+
+	bpf_printk("ITER_SUBPROG_ITERS: total sum=%d", sum);
+	bpf_for(row, 0, ARRAY_SIZE(arr2d)) {
+		bpf_printk("ITER_SUBPROG_ITERS: row #%d sum=%d",
+			   row, arr2d_row_sums[row]);
+	}
+	bpf_for(col, 0, ARRAY_SIZE(arr2d[0])) {
+		bpf_printk("ITER_SUBPROG_ITERS: col #%d sum=%d%s",
+			   col, arr2d_col_sums[col],
+			   col == ARRAY_SIZE(arr2d[0]) - 1 ? "\n" : "");
+	}
+
+	return 0;
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 1000);
+} hash_map SEC(".maps");
+
+SEC("?raw_tp")
+__failure __msg("invalid mem access 'scalar'")
+int iter_err_too_permissive1(const void *ctx)
+{
+	int *map_val = NULL;
+	int key = 0;
+
+	MY_PID_GUARD();
+
+	map_val = bpf_map_lookup_elem(&hash_map, &key);
+	if (!map_val)
+		return 0;
+
+	bpf_repeat(1000000) {
+		map_val = NULL;
+	}
+
+	*map_val = 123;
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("invalid mem access 'map_value_or_null'")
+int iter_err_too_permissive2(const void *ctx)
+{
+	int *map_val = NULL;
+	int key = 0;
+
+	MY_PID_GUARD();
+
+	map_val = bpf_map_lookup_elem(&hash_map, &key);
+	if (!map_val)
+		return 0;
+
+	bpf_repeat(1000000) {
+		map_val = bpf_map_lookup_elem(&hash_map, &key);
+	}
+
+	*map_val = 123;
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("invalid mem access 'map_value_or_null'")
+int iter_err_too_permissive3(const void *ctx)
+{
+	int *map_val = NULL;
+	int key = 0;
+	bool found = false;
+
+	MY_PID_GUARD();
+
+	bpf_repeat(1000000) {
+		map_val = bpf_map_lookup_elem(&hash_map, &key);
+		found = true;
+	}
+
+	if (found)
+		*map_val = 123;
+
+	return 0;
+}
+
+SEC("raw_tp")
+__success
+int iter_tricky_but_fine(const void *ctx)
+{
+	int *map_val = NULL;
+	int key = 0;
+	bool found = false;
+
+	MY_PID_GUARD();
+
+	bpf_repeat(1000000) {
+		map_val = bpf_map_lookup_elem(&hash_map, &key);
+		if (map_val) {
+			found = true;
+			break;
+		}
+	}
+
+	if (found)
+		*map_val = 123;
+
+	return 0;
+}
+
+#define __bpf_memzero(p, sz) bpf_probe_read_kernel((p), (sz), 0)
+
+SEC("raw_tp")
+__success
+int iter_stack_array_loop(const void *ctx)
+{
+	long arr1[16], arr2[16], sum = 0;
+	int i;
+
+	MY_PID_GUARD();
+
+	/* zero-init arr1 and arr2 in such a way that verifier doesn't know
+	 * it's all zeros; if we don't do that, we'll make BPF verifier track
+	 * all combination of zero/non-zero stack slots for arr1/arr2, which
+	 * will lead to O(2^(ARRAY_SIZE(arr1)+ARRAY_SIZE(arr2))) different
+	 * states
+	 */
+	__bpf_memzero(arr1, sizeof(arr1));
+	__bpf_memzero(arr2, sizeof(arr1));
+
+	/* validate that we can break and continue when using bpf_for() */
+	bpf_for(i, 0, ARRAY_SIZE(arr1)) {
+		if (i & 1) {
+			arr1[i] = i;
+			continue;
+		} else {
+			arr2[i] = i;
+			break;
+		}
+	}
+
+	bpf_for(i, 0, ARRAY_SIZE(arr1)) {
+		sum += arr1[i] + arr2[i];
+	}
+
+	return sum;
+}
+
+static __noinline void fill(struct bpf_iter_num *it, int *arr, __u32 n, int mul)
+{
+	int *t, i;
+
+	while ((t = bpf_iter_num_next(it))) {
+		i = *t;
+		if (i >= n)
+			break;
+		arr[i] =  i * mul;
+	}
+}
+
+static __noinline int sum(struct bpf_iter_num *it, int *arr, __u32 n)
+{
+	int *t, i, sum = 0;
+
+	while ((t = bpf_iter_num_next(it))) {
+		i = *t;
+		if ((__u32)i >= n)
+			break;
+		sum += arr[i];
+	}
+
+	return sum;
+}
+
+SEC("raw_tp")
+__success
+int iter_pass_iter_ptr_to_subprog(const void *ctx)
+{
+	int arr1[16], arr2[32];
+	struct bpf_iter_num it;
+	int n, sum1, sum2;
+
+	MY_PID_GUARD();
+
+	/* fill arr1 */
+	n = ARRAY_SIZE(arr1);
+	bpf_iter_num_new(&it, 0, n);
+	fill(&it, arr1, n, 2);
+	bpf_iter_num_destroy(&it);
+
+	/* fill arr2 */
+	n = ARRAY_SIZE(arr2);
+	bpf_iter_num_new(&it, 0, n);
+	fill(&it, arr2, n, 10);
+	bpf_iter_num_destroy(&it);
+
+	/* sum arr1 */
+	n = ARRAY_SIZE(arr1);
+	bpf_iter_num_new(&it, 0, n);
+	sum1 = sum(&it, arr1, n);
+	bpf_iter_num_destroy(&it);
+
+	/* sum arr2 */
+	n = ARRAY_SIZE(arr2);
+	bpf_iter_num_new(&it, 0, n);
+	sum2 = sum(&it, arr2, n);
+	bpf_iter_num_destroy(&it);
+
+	bpf_printk("sum1=%d, sum2=%d", sum1, sum2);
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure
+__msg("R1 type=scalar expected=fp")
+__naked int delayed_read_mark(void)
+{
+	/* This is equivalent to C program below.
+	 * The call to bpf_iter_num_next() is reachable with r7 values &fp[-16] and 0xdead.
+	 * State with r7=&fp[-16] is visited first and follows r6 != 42 ... continue branch.
+	 * At this point iterator next() call is reached with r7 that has no read mark.
+	 * Loop body with r7=0xdead would only be visited if verifier would decide to continue
+	 * with second loop iteration. Absence of read mark on r7 might affect state
+	 * equivalent logic used for iterator convergence tracking.
+	 *
+	 * r7 = &fp[-16]
+	 * fp[-16] = 0
+	 * r6 = bpf_get_prandom_u32()
+	 * bpf_iter_num_new(&fp[-8], 0, 10)
+	 * while (bpf_iter_num_next(&fp[-8])) {
+	 *   r6++
+	 *   if (r6 != 42) {
+	 *     r7 = 0xdead
+	 *     continue;
+	 *   }
+	 *   bpf_probe_read_user(r7, 8, 0xdeadbeef); // this is not safe
+	 * }
+	 * bpf_iter_num_destroy(&fp[-8])
+	 * return 0
+	 */
+	asm volatile (
+		"r7 = r10;"
+		"r7 += -16;"
+		"r0 = 0;"
+		"*(u64 *)(r7 + 0) = r0;"
+		"call %[bpf_get_prandom_u32];"
+		"r6 = r0;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+	"1:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto 2f;"
+		"r6 += 1;"
+		"if r6 != 42 goto 3f;"
+		"r7 = 0xdead;"
+		"goto 1b;"
+	"3:"
+		"r1 = r7;"
+		"r2 = 8;"
+		"r3 = 0xdeadbeef;"
+		"call %[bpf_probe_read_user];"
+		"goto 1b;"
+	"2:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32),
+		  __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy),
+		  __imm(bpf_probe_read_user)
+		: __clobber_all
+	);
+}
+
+SEC("?raw_tp")
+__failure
+__msg("math between fp pointer and register with unbounded")
+__naked int delayed_precision_mark(void)
+{
+	/* This is equivalent to C program below.
+	 * The test is similar to delayed_iter_mark but verifies that incomplete
+	 * precision don't fool verifier.
+	 * The call to bpf_iter_num_next() is reachable with r7 values -16 and -32.
+	 * State with r7=-16 is visited first and follows r6 != 42 ... continue branch.
+	 * At this point iterator next() call is reached with r7 that has no read
+	 * and precision marks.
+	 * Loop body with r7=-32 would only be visited if verifier would decide to continue
+	 * with second loop iteration. Absence of precision mark on r7 might affect state
+	 * equivalent logic used for iterator convergence tracking.
+	 *
+	 * r8 = 0
+	 * fp[-16] = 0
+	 * r7 = -16
+	 * r6 = bpf_get_prandom_u32()
+	 * bpf_iter_num_new(&fp[-8], 0, 10)
+	 * while (bpf_iter_num_next(&fp[-8])) {
+	 *   if (r6 != 42) {
+	 *     r7 = -32
+	 *     r6 = bpf_get_prandom_u32()
+	 *     continue;
+	 *   }
+	 *   r0 = r10
+	 *   r0 += r7
+	 *   r8 = *(u64 *)(r0 + 0)           // this is not safe
+	 *   r6 = bpf_get_prandom_u32()
+	 * }
+	 * bpf_iter_num_destroy(&fp[-8])
+	 * return r8
+	 */
+	asm volatile (
+		"r8 = 0;"
+		"*(u64 *)(r10 - 16) = r8;"
+		"r7 = -16;"
+		"call %[bpf_get_prandom_u32];"
+		"r6 = r0;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+	"1:"
+		"r1 = r10;"
+		"r1 += -8;\n"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto 2f;"
+		"if r6 != 42 goto 3f;"
+		"r7 = -33;"
+		"call %[bpf_get_prandom_u32];"
+		"r6 = r0;"
+		"goto 1b;\n"
+	"3:"
+		"r0 = r10;"
+		"r0 += r7;"
+		"r8 = *(u64 *)(r0 + 0);"
+		"call %[bpf_get_prandom_u32];"
+		"r6 = r0;"
+		"goto 1b;\n"
+	"2:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = r8;"
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32),
+		  __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy),
+		  __imm(bpf_probe_read_user)
+		: __clobber_all
+	);
+}
+
+SEC("?raw_tp")
+__failure
+__msg("math between fp pointer and register with unbounded")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked int loop_state_deps1(void)
+{
+	/* This is equivalent to C program below.
+	 *
+	 * The case turns out to be tricky in a sense that:
+	 * - states with c=-25 are explored only on a second iteration
+	 *   of the outer loop;
+	 * - states with read+precise mark on c are explored only on
+	 *   second iteration of the inner loop and in a state which
+	 *   is pushed to states stack first.
+	 *
+	 * Depending on the details of iterator convergence logic
+	 * verifier might stop states traversal too early and miss
+	 * unsafe c=-25 memory access.
+	 *
+	 *   j = iter_new();		 // fp[-16]
+	 *   a = 0;			 // r6
+	 *   b = 0;			 // r7
+	 *   c = -24;			 // r8
+	 *   while (iter_next(j)) {
+	 *     i = iter_new();		 // fp[-8]
+	 *     a = 0;			 // r6
+	 *     b = 0;			 // r7
+	 *     while (iter_next(i)) {
+	 *	 if (a == 1) {
+	 *	   a = 0;
+	 *	   b = 1;
+	 *	 } else if (a == 0) {
+	 *	   a = 1;
+	 *	   if (random() == 42)
+	 *	     continue;
+	 *	   if (b == 1) {
+	 *	     *(r10 + c) = 7;  // this is not safe
+	 *	     iter_destroy(i);
+	 *	     iter_destroy(j);
+	 *	     return;
+	 *	   }
+	 *	 }
+	 *     }
+	 *     iter_destroy(i);
+	 *     a = 0;
+	 *     b = 0;
+	 *     c = -25;
+	 *   }
+	 *   iter_destroy(j);
+	 *   return;
+	 */
+	asm volatile (
+		"r1 = r10;"
+		"r1 += -16;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+		"r6 = 0;"
+		"r7 = 0;"
+		"r8 = -24;"
+	"j_loop_%=:"
+		"r1 = r10;"
+		"r1 += -16;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto j_loop_end_%=;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+		"r6 = 0;"
+		"r7 = 0;"
+	"i_loop_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto i_loop_end_%=;"
+	"check_one_r6_%=:"
+		"if r6 != 1 goto check_zero_r6_%=;"
+		"r6 = 0;"
+		"r7 = 1;"
+		"goto i_loop_%=;"
+	"check_zero_r6_%=:"
+		"if r6 != 0 goto i_loop_%=;"
+		"r6 = 1;"
+		"call %[bpf_get_prandom_u32];"
+		"if r0 != 42 goto check_one_r7_%=;"
+		"goto i_loop_%=;"
+	"check_one_r7_%=:"
+		"if r7 != 1 goto i_loop_%=;"
+		"r0 = r10;"
+		"r0 += r8;"
+		"r1 = 7;"
+		"*(u64 *)(r0 + 0) = r1;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r1 = r10;"
+		"r1 += -16;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+	"i_loop_end_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r6 = 0;"
+		"r7 = 0;"
+		"r8 = -25;"
+		"goto j_loop_%=;"
+	"j_loop_end_%=:"
+		"r1 = r10;"
+		"r1 += -16;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32),
+		  __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy)
+		: __clobber_all
+	);
+}
+
+SEC("?raw_tp")
+__failure
+__msg("math between fp pointer and register with unbounded")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked int loop_state_deps2(void)
+{
+	/* This is equivalent to C program below.
+	 *
+	 * The case turns out to be tricky in a sense that:
+	 * - states with read+precise mark on c are explored only on a second
+	 *   iteration of the first inner loop and in a state which is pushed to
+	 *   states stack first.
+	 * - states with c=-25 are explored only on a second iteration of the
+	 *   second inner loop and in a state which is pushed to states stack
+	 *   first.
+	 *
+	 * Depending on the details of iterator convergence logic
+	 * verifier might stop states traversal too early and miss
+	 * unsafe c=-25 memory access.
+	 *
+	 *   j = iter_new();             // fp[-16]
+	 *   a = 0;                      // r6
+	 *   b = 0;                      // r7
+	 *   c = -24;                    // r8
+	 *   while (iter_next(j)) {
+	 *     i = iter_new();           // fp[-8]
+	 *     a = 0;                    // r6
+	 *     b = 0;                    // r7
+	 *     while (iter_next(i)) {
+	 *       if (a == 1) {
+	 *         a = 0;
+	 *         b = 1;
+	 *       } else if (a == 0) {
+	 *         a = 1;
+	 *         if (random() == 42)
+	 *           continue;
+	 *         if (b == 1) {
+	 *           *(r10 + c) = 7;     // this is not safe
+	 *           iter_destroy(i);
+	 *           iter_destroy(j);
+	 *           return;
+	 *         }
+	 *       }
+	 *     }
+	 *     iter_destroy(i);
+	 *     i = iter_new();           // fp[-8]
+	 *     a = 0;                    // r6
+	 *     b = 0;                    // r7
+	 *     while (iter_next(i)) {
+	 *       if (a == 1) {
+	 *         a = 0;
+	 *         b = 1;
+	 *       } else if (a == 0) {
+	 *         a = 1;
+	 *         if (random() == 42)
+	 *           continue;
+	 *         if (b == 1) {
+	 *           a = 0;
+	 *           c = -25;
+	 *         }
+	 *       }
+	 *     }
+	 *     iter_destroy(i);
+	 *   }
+	 *   iter_destroy(j);
+	 *   return;
+	 */
+	asm volatile (
+		"r1 = r10;"
+		"r1 += -16;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+		"r6 = 0;"
+		"r7 = 0;"
+		"r8 = -24;"
+	"j_loop_%=:"
+		"r1 = r10;"
+		"r1 += -16;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto j_loop_end_%=;"
+
+		/* first inner loop */
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+		"r6 = 0;"
+		"r7 = 0;"
+	"i_loop_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto i_loop_end_%=;"
+	"check_one_r6_%=:"
+		"if r6 != 1 goto check_zero_r6_%=;"
+		"r6 = 0;"
+		"r7 = 1;"
+		"goto i_loop_%=;"
+	"check_zero_r6_%=:"
+		"if r6 != 0 goto i_loop_%=;"
+		"r6 = 1;"
+		"call %[bpf_get_prandom_u32];"
+		"if r0 != 42 goto check_one_r7_%=;"
+		"goto i_loop_%=;"
+	"check_one_r7_%=:"
+		"if r7 != 1 goto i_loop_%=;"
+		"r0 = r10;"
+		"r0 += r8;"
+		"r1 = 7;"
+		"*(u64 *)(r0 + 0) = r1;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r1 = r10;"
+		"r1 += -16;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+	"i_loop_end_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+
+		/* second inner loop */
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+		"r6 = 0;"
+		"r7 = 0;"
+	"i2_loop_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto i2_loop_end_%=;"
+	"check2_one_r6_%=:"
+		"if r6 != 1 goto check2_zero_r6_%=;"
+		"r6 = 0;"
+		"r7 = 1;"
+		"goto i2_loop_%=;"
+	"check2_zero_r6_%=:"
+		"if r6 != 0 goto i2_loop_%=;"
+		"r6 = 1;"
+		"call %[bpf_get_prandom_u32];"
+		"if r0 != 42 goto check2_one_r7_%=;"
+		"goto i2_loop_%=;"
+	"check2_one_r7_%=:"
+		"if r7 != 1 goto i2_loop_%=;"
+		"r6 = 0;"
+		"r8 = -25;"
+		"goto i2_loop_%=;"
+	"i2_loop_end_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+
+		"r6 = 0;"
+		"r7 = 0;"
+		"goto j_loop_%=;"
+	"j_loop_end_%=:"
+		"r1 = r10;"
+		"r1 += -16;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32),
+		  __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy)
+		: __clobber_all
+	);
+}
+
+SEC("?raw_tp")
+__failure
+__msg("math between fp pointer and register with unbounded")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked int loop_state_deps3(void)
+{
+	/* This is equivalent to a C program below.
+	 *
+	 *   if (random() != 24) {       // assume false branch is placed first
+	 *     i = iter_new();           // fp[-8]
+	 *     while (iter_next(i));
+	 *     iter_destroy(i);
+	 *     return;
+	 *   }
+	 *
+	 *   for (i = 10; i > 0; i--);   // increase dfs_depth for child states
+	 *
+	 *   i = iter_new();             // fp[-8]
+	 *   b = -24;                    // r8
+	 *   for (;;) {                  // checkpoint (L)
+	 *     if (iter_next(i))         // checkpoint (N)
+	 *       break;
+	 *     if (random() == 77) {     // assume false branch is placed first
+	 *       *(u64 *)(r10 + b) = 7;  // this is not safe when b == -25
+	 *       iter_destroy(i);
+	 *       return;
+	 *     }
+	 *     if (random() == 42) {     // assume false branch is placed first
+	 *       b = -25;
+	 *     }
+	 *   }
+	 *   iter_destroy(i);
+	 *
+	 * In case of a buggy verifier first loop might poison
+	 * env->cur_state->loop_entry with a state having 0 branches
+	 * and small dfs_depth. This would trigger NOT_EXACT states
+	 * comparison for some states within second loop.
+	 * Specifically, checkpoint (L) might be problematic if:
+	 * - branch with '*(u64 *)(r10 + b) = 7' is not explored yet;
+	 * - checkpoint (L) is first reached in state {b=-24};
+	 * - traversal is pruned at checkpoint (N) setting checkpoint's (L)
+	 *   branch count to 0, thus making it eligible for use in pruning;
+	 * - checkpoint (L) is next reached in state {b=-25},
+	 *   this would cause NOT_EXACT comparison with a state {b=-24}
+	 *   while 'b' is not marked precise yet.
+	 */
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+		"if r0 == 24 goto 2f;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 5;"
+		"call %[bpf_iter_num_new];"
+	"1:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_next];"
+		"if r0 != 0 goto 1b;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+	"2:"
+		/* loop to increase dfs_depth */
+		"r0 = 10;"
+	"3:"
+		"r0 -= 1;"
+		"if r0 != 0 goto 3b;"
+		/* end of loop */
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+		"r8 = -24;"
+	"main_loop_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto main_loop_end_%=;"
+		/* first if */
+		"call %[bpf_get_prandom_u32];"
+		"if r0 == 77 goto unsafe_write_%=;"
+		/* second if */
+		"call %[bpf_get_prandom_u32];"
+		"if r0 == 42 goto poison_r8_%=;"
+		/* iterate */
+		"goto main_loop_%=;"
+	"main_loop_end_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+
+	"unsafe_write_%=:"
+		"r0 = r10;"
+		"r0 += r8;"
+		"r1 = 7;"
+		"*(u64 *)(r0 + 0) = r1;"
+		"goto main_loop_end_%=;"
+
+	"poison_r8_%=:"
+		"r8 = -25;"
+		"goto main_loop_%=;"
+		:
+		: __imm(bpf_get_prandom_u32),
+		  __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy)
+		: __clobber_all
+	);
+}
+
+SEC("?raw_tp")
+__success
+__naked int triple_continue(void)
+{
+	/* This is equivalent to C program below.
+	 * High branching factor of the loop body turned out to be
+	 * problematic for one of the iterator convergence tracking
+	 * algorithms explored.
+	 *
+	 * r6 = bpf_get_prandom_u32()
+	 * bpf_iter_num_new(&fp[-8], 0, 10)
+	 * while (bpf_iter_num_next(&fp[-8])) {
+	 *   if (bpf_get_prandom_u32() != 42)
+	 *     continue;
+	 *   if (bpf_get_prandom_u32() != 42)
+	 *     continue;
+	 *   if (bpf_get_prandom_u32() != 42)
+	 *     continue;
+	 *   r0 += 0;
+	 * }
+	 * bpf_iter_num_destroy(&fp[-8])
+	 * return 0
+	 */
+	asm volatile (
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+	"loop_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto loop_end_%=;"
+		"call %[bpf_get_prandom_u32];"
+		"if r0 != 42 goto loop_%=;"
+		"call %[bpf_get_prandom_u32];"
+		"if r0 != 42 goto loop_%=;"
+		"call %[bpf_get_prandom_u32];"
+		"if r0 != 42 goto loop_%=;"
+		"r0 += 0;"
+		"goto loop_%=;"
+	"loop_end_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32),
+		  __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy)
+		: __clobber_all
+	);
+}
+
+SEC("?raw_tp")
+__success
+__naked int widen_spill(void)
+{
+	/* This is equivalent to C program below.
+	 * The counter is stored in fp[-16], if this counter is not widened
+	 * verifier states representing loop iterations would never converge.
+	 *
+	 * fp[-16] = 0
+	 * bpf_iter_num_new(&fp[-8], 0, 10)
+	 * while (bpf_iter_num_next(&fp[-8])) {
+	 *   r0 = fp[-16];
+	 *   r0 += 1;
+	 *   fp[-16] = r0;
+	 * }
+	 * bpf_iter_num_destroy(&fp[-8])
+	 * return 0
+	 */
+	asm volatile (
+		"r0 = 0;"
+		"*(u64 *)(r10 - 16) = r0;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+	"loop_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto loop_end_%=;"
+		"r0 = *(u64 *)(r10 - 16);"
+		"r0 += 1;"
+		"*(u64 *)(r10 - 16) = r0;"
+		"goto loop_%=;"
+	"loop_end_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy)
+		: __clobber_all
+	);
+}
+
+SEC("raw_tp")
+__success
+__naked int checkpoint_states_deletion(void)
+{
+	/* This is equivalent to C program below.
+	 *
+	 *   int *a, *b, *c, *d, *e, *f;
+	 *   int i, sum = 0;
+	 *   bpf_for(i, 0, 10) {
+	 *     a = bpf_map_lookup_elem(&amap, &i);
+	 *     b = bpf_map_lookup_elem(&amap, &i);
+	 *     c = bpf_map_lookup_elem(&amap, &i);
+	 *     d = bpf_map_lookup_elem(&amap, &i);
+	 *     e = bpf_map_lookup_elem(&amap, &i);
+	 *     f = bpf_map_lookup_elem(&amap, &i);
+	 *     if (a) sum += 1;
+	 *     if (b) sum += 1;
+	 *     if (c) sum += 1;
+	 *     if (d) sum += 1;
+	 *     if (e) sum += 1;
+	 *     if (f) sum += 1;
+	 *   }
+	 *   return 0;
+	 *
+	 * The body of the loop spawns multiple simulation paths
+	 * with different combination of NULL/non-NULL information for a/b/c/d/e/f.
+	 * Each combination is unique from states_equal() point of view.
+	 * Explored states checkpoint is created after each iterator next call.
+	 * Iterator convergence logic expects that eventually current state
+	 * would get equal to one of the explored states and thus loop
+	 * exploration would be finished (at-least for a specific path).
+	 * Verifier evicts explored states with high miss to hit ratio
+	 * to to avoid comparing current state with too many explored
+	 * states per instruction.
+	 * This test is designed to "stress test" eviction policy defined using formula:
+	 *
+	 *    sl->miss_cnt > sl->hit_cnt * N + N // if true sl->state is evicted
+	 *
+	 * Currently N is set to 64, which allows for 6 variables in this test.
+	 */
+	asm volatile (
+		"r6 = 0;"                  /* a */
+		"r7 = 0;"                  /* b */
+		"r8 = 0;"                  /* c */
+		"*(u64 *)(r10 - 24) = r6;" /* d */
+		"*(u64 *)(r10 - 32) = r6;" /* e */
+		"*(u64 *)(r10 - 40) = r6;" /* f */
+		"r9 = 0;"                  /* sum */
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+	"loop_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto loop_end_%=;"
+
+		"*(u64 *)(r10 - 16) = r0;"
+
+		"r1 = %[amap] ll;"
+		"r2 = r10;"
+		"r2 += -16;"
+		"call %[bpf_map_lookup_elem];"
+		"r6 = r0;"
+
+		"r1 = %[amap] ll;"
+		"r2 = r10;"
+		"r2 += -16;"
+		"call %[bpf_map_lookup_elem];"
+		"r7 = r0;"
+
+		"r1 = %[amap] ll;"
+		"r2 = r10;"
+		"r2 += -16;"
+		"call %[bpf_map_lookup_elem];"
+		"r8 = r0;"
+
+		"r1 = %[amap] ll;"
+		"r2 = r10;"
+		"r2 += -16;"
+		"call %[bpf_map_lookup_elem];"
+		"*(u64 *)(r10 - 24) = r0;"
+
+		"r1 = %[amap] ll;"
+		"r2 = r10;"
+		"r2 += -16;"
+		"call %[bpf_map_lookup_elem];"
+		"*(u64 *)(r10 - 32) = r0;"
+
+		"r1 = %[amap] ll;"
+		"r2 = r10;"
+		"r2 += -16;"
+		"call %[bpf_map_lookup_elem];"
+		"*(u64 *)(r10 - 40) = r0;"
+
+		"if r6 == 0 goto +1;"
+		"r9 += 1;"
+		"if r7 == 0 goto +1;"
+		"r9 += 1;"
+		"if r8 == 0 goto +1;"
+		"r9 += 1;"
+		"r0 = *(u64 *)(r10 - 24);"
+		"if r0 == 0 goto +1;"
+		"r9 += 1;"
+		"r0 = *(u64 *)(r10 - 32);"
+		"if r0 == 0 goto +1;"
+		"r9 += 1;"
+		"r0 = *(u64 *)(r10 - 40);"
+		"if r0 == 0 goto +1;"
+		"r9 += 1;"
+
+		"goto loop_%=;"
+	"loop_end_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_map_lookup_elem),
+		  __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy),
+		  __imm_addr(amap)
+		: __clobber_all
+	);
+}
+
+struct {
+	int data[32];
+	int n;
+} loop_data;
+
+SEC("raw_tp")
+__success
+int iter_arr_with_actual_elem_count(const void *ctx)
+{
+	int i, n = loop_data.n, sum = 0;
+
+	if (n > ARRAY_SIZE(loop_data.data))
+		return 0;
+
+	bpf_for(i, 0, n) {
+		/* no rechecking of i against ARRAY_SIZE(loop_data.n) */
+		sum += loop_data.data[i];
+	}
+
+	return sum;
+}
+
+__u32 upper, select_n, result;
+__u64 global;
+
+static __noinline bool nest_2(char *str)
+{
+	/* some insns (including branch insns) to ensure stacksafe() is triggered
+	 * in nest_2(). This way, stacksafe() can compare frame associated with nest_1().
+	 */
+	if (str[0] == 't')
+		return true;
+	if (str[1] == 'e')
+		return true;
+	if (str[2] == 's')
+		return true;
+	if (str[3] == 't')
+		return true;
+	return false;
+}
+
+static __noinline bool nest_1(int n)
+{
+	/* case 0: allocate stack, case 1: no allocate stack */
+	switch (n) {
+	case 0: {
+		char comm[16];
+
+		if (bpf_get_current_comm(comm, 16))
+			return false;
+		return nest_2(comm);
+	}
+	case 1:
+		return nest_2((char *)&global);
+	default:
+		return false;
+	}
+}
+
+SEC("raw_tp")
+__success
+int iter_subprog_check_stacksafe(const void *ctx)
+{
+	long i;
+
+	bpf_for(i, 0, upper) {
+		if (!nest_1(select_n)) {
+			result = 1;
+			return 0;
+		}
+	}
+
+	result = 2;
+	return 0;
+}
+
+struct bpf_iter_num global_it;
+
+SEC("raw_tp")
+__failure __msg("arg#0 expected pointer to an iterator on stack")
+int iter_new_bad_arg(const void *ctx)
+{
+	bpf_iter_num_new(&global_it, 0, 1);
+	return 0;
+}
+
+SEC("raw_tp")
+__failure __msg("arg#0 expected pointer to an iterator on stack")
+int iter_next_bad_arg(const void *ctx)
+{
+	bpf_iter_num_next(&global_it);
+	return 0;
+}
+
+SEC("raw_tp")
+__failure __msg("arg#0 expected pointer to an iterator on stack")
+int iter_destroy_bad_arg(const void *ctx)
+{
+	bpf_iter_num_destroy(&global_it);
+	return 0;
+}
+
+SEC("raw_tp")
+__success
+int clean_live_states(const void *ctx)
+{
+	char buf[1];
+	int i, j, k, l, m, n, o;
+
+	bpf_for(i, 0, 10)
+	bpf_for(j, 0, 10)
+	bpf_for(k, 0, 10)
+	bpf_for(l, 0, 10)
+	bpf_for(m, 0, 10)
+	bpf_for(n, 0, 10)
+	bpf_for(o, 0, 10) {
+		if (unlikely(bpf_get_prandom_u32()))
+			buf[0] = 42;
+		bpf_printk("%s", buf);
+	}
+	return 0;
+}
+
+SEC("?raw_tp")
+__flag(BPF_F_TEST_STATE_FREQ)
+__failure __msg("misaligned stack access off 0+-31+0 size 8")
+__naked int absent_mark_in_the_middle_state(void)
+{
+	/* This is equivalent to C program below.
+	 *
+	 * r8 = bpf_get_prandom_u32();
+	 * r6 = -32;
+	 * bpf_iter_num_new(&fp[-8], 0, 10);
+	 * if (unlikely(bpf_get_prandom_u32()))
+	 *   r6 = -31;
+	 * while (bpf_iter_num_next(&fp[-8])) {
+	 *   if (unlikely(bpf_get_prandom_u32()))
+	 *     *(fp + r6) = 7;
+	 * }
+	 * bpf_iter_num_destroy(&fp[-8])
+	 * return 0
+	 */
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+		"r8 = r0;"
+		"r7 = 0;"
+		"r6 = -32;"
+		"r0 = 0;"
+		"*(u64 *)(r10 - 16) = r0;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+		"call %[bpf_get_prandom_u32];"
+		"if r0 == r8 goto change_r6_%=;"
+	"loop_%=:"
+		"call noop;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto loop_end_%=;"
+		"call %[bpf_get_prandom_u32];"
+		"if r0 == r8 goto use_r6_%=;"
+		"goto loop_%=;"
+	"loop_end_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+	"use_r6_%=:"
+		"r0 = r10;"
+		"r0 += r6;"
+		"r1 = 7;"
+		"*(u64 *)(r0 + 0) = r1;"
+		"goto loop_%=;"
+	"change_r6_%=:"
+		"r6 = -31;"
+		"goto loop_%=;"
+		:
+		: __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy),
+		  __imm(bpf_get_prandom_u32)
+		: __clobber_all
+	);
+}
+
+__used __naked
+static int noop(void)
+{
+	asm volatile (
+		"r0 = 0;"
+		"exit;"
+	);
+}
+
+SEC("?raw_tp")
+__flag(BPF_F_TEST_STATE_FREQ)
+__failure __msg("misaligned stack access off 0+-31+0 size 8")
+__naked int absent_mark_in_the_middle_state2(void)
+{
+	/* This is equivalent to C program below.
+	 *
+	 *     r8 = bpf_get_prandom_u32();
+	 *     r6 = -32;
+	 *     bpf_iter_num_new(&fp[-8], 0, 10);
+	 *     if (unlikely(bpf_get_prandom_u32())) {
+	 *       r6 = -31;
+	 * jump_into_loop:
+	 *       goto +0;
+	 *       goto loop;
+	 *     }
+	 *     if (unlikely(bpf_get_prandom_u32()))
+	 *       goto jump_into_loop;
+	 * loop:
+	 *     while (bpf_iter_num_next(&fp[-8])) {
+	 *       if (unlikely(bpf_get_prandom_u32()))
+	 *         *(fp + r6) = 7;
+	 *     }
+	 *     bpf_iter_num_destroy(&fp[-8])
+	 *     return 0
+	 */
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+		"r8 = r0;"
+		"r7 = 0;"
+		"r6 = -32;"
+		"r0 = 0;"
+		"*(u64 *)(r10 - 16) = r0;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+		"call %[bpf_get_prandom_u32];"
+		"if r0 == r8 goto change_r6_%=;"
+		"call %[bpf_get_prandom_u32];"
+		"if r0 == r8 goto jump_into_loop_%=;"
+	"loop_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto loop_end_%=;"
+		"call %[bpf_get_prandom_u32];"
+		"if r0 == r8 goto use_r6_%=;"
+		"goto loop_%=;"
+	"loop_end_%=:"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+	"use_r6_%=:"
+		"r0 = r10;"
+		"r0 += r6;"
+		"r1 = 7;"
+		"*(u64 *)(r0 + 0) = r1;"
+		"goto loop_%=;"
+	"change_r6_%=:"
+		"r6 = -31;"
+	"jump_into_loop_%=: "
+		"goto +0;"
+		"goto loop_%=;"
+		:
+		: __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_next),
+		  __imm(bpf_iter_num_destroy),
+		  __imm(bpf_get_prandom_u32)
+		: __clobber_all
+	);
+}
+
+SEC("?raw_tp")
+__flag(BPF_F_TEST_STATE_FREQ)
+__failure __msg("misaligned stack access off 0+-31+0 size 8")
+__naked int absent_mark_in_the_middle_state3(void)
+{
+	/*
+	 * bpf_iter_num_new(&fp[-8], 0, 10)
+	 * loop1(-32, &fp[-8])
+	 * loop1_wrapper(&fp[-8])
+	 * bpf_iter_num_destroy(&fp[-8])
+	 */
+	asm volatile (
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+		/* call #1 */
+		"r1 = -32;"
+		"r2 = r10;"
+		"r2 += -8;"
+		"call loop1;"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		/* call #2 */
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+		"r1 = r10;"
+		"r1 += -8;"
+		"call loop1_wrapper;"
+		/* return */
+		"r1 = r10;"
+		"r1 += -8;"
+		"call %[bpf_iter_num_destroy];"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm(bpf_iter_num_new),
+		  __imm(bpf_iter_num_destroy),
+		  __imm(bpf_get_prandom_u32)
+		: __clobber_all
+	);
+}
+
+__used __naked
+static int loop1(void)
+{
+	/*
+	 *  int loop1(num, iter) {
+	 *     r6 = num;
+	 *     r7 = iter;
+	 *     while (bpf_iter_num_next(r7)) {
+	 *       if (unlikely(bpf_get_prandom_u32()))
+	 *         *(fp + r6) = 7;
+	 *     }
+	 *     return 0
+	 *  }
+	 */
+	asm volatile (
+		"r6 = r1;"
+		"r7 = r2;"
+		"call %[bpf_get_prandom_u32];"
+		"r8 = r0;"
+	"loop_%=:"
+		"r1 = r7;"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto loop_end_%=;"
+		"call %[bpf_get_prandom_u32];"
+		"if r0 == r8 goto use_r6_%=;"
+		"goto loop_%=;"
+	"loop_end_%=:"
+		"r0 = 0;"
+		"exit;"
+	"use_r6_%=:"
+		"r0 = r10;"
+		"r0 += r6;"
+		"r1 = 7;"
+		"*(u64 *)(r0 + 0) = r1;"
+		"goto loop_%=;"
+		:
+		: __imm(bpf_iter_num_next),
+		  __imm(bpf_get_prandom_u32)
+		: __clobber_all
+	);
+}
+
+__used __naked
+static int loop1_wrapper(void)
+{
+	/*
+	 *  int loop1_wrapper(iter) {
+	 *    r6 = -32;
+	 *    r7 = iter;
+	 *    if (unlikely(bpf_get_prandom_u32()))
+	 *      r6 = -31;
+	 *    loop1(r6, r7);
+	 *    return 0;
+	 *  }
+	 */
+	asm volatile (
+		"r6 = -32;"
+		"r7 = r1;"
+		"call %[bpf_get_prandom_u32];"
+		"r8 = r0;"
+		"call %[bpf_get_prandom_u32];"
+		"if r0 == r8 goto change_r6_%=;"
+	"loop_%=:"
+		"r1 = r6;"
+		"r2 = r7;"
+		"call loop1;"
+		"r0 = 0;"
+		"exit;"
+	"change_r6_%=:"
+		"r6 = -31;"
+		"goto loop_%=;"
+		:
+		: __imm(bpf_iter_num_next),
+		  __imm(bpf_get_prandom_u32)
+		: __clobber_all
+	);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/iters_css.c b/tools/testing/selftests/bpf/progs/iters_css.c
new file mode 100644
index 000000000000..ec1f6c2f590b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/iters_css.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Chuyi Zhou <zhouchuyi@bytedance.com> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+char _license[] SEC("license") = "GPL";
+
+pid_t target_pid;
+u64 root_cg_id, leaf_cg_id;
+u64 first_cg_id, last_cg_id;
+
+int pre_order_cnt, post_order_cnt, tree_high;
+
+struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym;
+void bpf_cgroup_release(struct cgroup *p) __ksym;
+void bpf_rcu_read_lock(void) __ksym;
+void bpf_rcu_read_unlock(void) __ksym;
+
+SEC("fentry.s/" SYS_PREFIX "sys_getpgid")
+int iter_css_for_each(const void *ctx)
+{
+	struct task_struct *cur_task = bpf_get_current_task_btf();
+	struct cgroup_subsys_state *root_css, *leaf_css, *pos;
+	struct cgroup *root_cgrp, *leaf_cgrp, *cur_cgrp;
+
+	if (cur_task->pid != target_pid)
+		return 0;
+
+	root_cgrp = bpf_cgroup_from_id(root_cg_id);
+
+	if (!root_cgrp)
+		return 0;
+
+	leaf_cgrp = bpf_cgroup_from_id(leaf_cg_id);
+
+	if (!leaf_cgrp) {
+		bpf_cgroup_release(root_cgrp);
+		return 0;
+	}
+	root_css = &root_cgrp->self;
+	leaf_css = &leaf_cgrp->self;
+	pre_order_cnt = post_order_cnt = tree_high = 0;
+	first_cg_id = last_cg_id = 0;
+
+	bpf_rcu_read_lock();
+	bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) {
+		cur_cgrp = pos->cgroup;
+		post_order_cnt++;
+		last_cg_id = cur_cgrp->kn->id;
+	}
+
+	bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_PRE) {
+		cur_cgrp = pos->cgroup;
+		pre_order_cnt++;
+		if (!first_cg_id)
+			first_cg_id = cur_cgrp->kn->id;
+	}
+
+	bpf_for_each(css, pos, leaf_css, BPF_CGROUP_ITER_ANCESTORS_UP)
+		tree_high++;
+
+	bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_ANCESTORS_UP)
+		tree_high--;
+	bpf_rcu_read_unlock();
+	bpf_cgroup_release(root_cgrp);
+	bpf_cgroup_release(leaf_cgrp);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/iters_css_task.c b/tools/testing/selftests/bpf/progs/iters_css_task.c
new file mode 100644
index 000000000000..9ac758649cb8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/iters_css_task.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Chuyi Zhou <zhouchuyi@bytedance.com> */
+
+#include "vmlinux.h"
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym;
+struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym;
+void bpf_cgroup_release(struct cgroup *p) __ksym;
+
+pid_t target_pid;
+int css_task_cnt;
+u64 cg_id;
+
+SEC("lsm/file_mprotect")
+int BPF_PROG(iter_css_task_for_each, struct vm_area_struct *vma,
+	    unsigned long reqprot, unsigned long prot, int ret)
+{
+	struct task_struct *cur_task = bpf_get_current_task_btf();
+	struct cgroup_subsys_state *css;
+	struct task_struct *task;
+	struct cgroup *cgrp;
+
+	if (cur_task->pid != target_pid)
+		return ret;
+
+	cgrp = bpf_cgroup_from_id(cg_id);
+
+	if (!cgrp)
+		return -EPERM;
+
+	css = &cgrp->self;
+	css_task_cnt = 0;
+
+	bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS)
+		if (task->pid == target_pid)
+			css_task_cnt++;
+
+	bpf_cgroup_release(cgrp);
+
+	return -EPERM;
+}
+
+static inline u64 cgroup_id(struct cgroup *cgrp)
+{
+	return cgrp->kn->id;
+}
+
+SEC("?iter/cgroup")
+int cgroup_id_printer(struct bpf_iter__cgroup *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct cgroup *cgrp = ctx->cgroup;
+	struct cgroup_subsys_state *css;
+	struct task_struct *task;
+
+	/* epilogue */
+	if (cgrp == NULL) {
+		BPF_SEQ_PRINTF(seq, "epilogue\n");
+		return 0;
+	}
+
+	/* prologue */
+	if (ctx->meta->seq_num == 0)
+		BPF_SEQ_PRINTF(seq, "prologue\n");
+
+	BPF_SEQ_PRINTF(seq, "%8llu\n", cgroup_id(cgrp));
+
+	css = &cgrp->self;
+	css_task_cnt = 0;
+	bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) {
+		if (task->pid == target_pid)
+			css_task_cnt++;
+	}
+
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int BPF_PROG(iter_css_task_for_each_sleep)
+{
+	u64 cgrp_id = bpf_get_current_cgroup_id();
+	struct cgroup *cgrp = bpf_cgroup_from_id(cgrp_id);
+	struct cgroup_subsys_state *css;
+	struct task_struct *task;
+
+	if (cgrp == NULL)
+		return 0;
+	css = &cgrp->self;
+
+	bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) {
+
+	}
+	bpf_cgroup_release(cgrp);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/iters_looping.c b/tools/testing/selftests/bpf/progs/iters_looping.c
new file mode 100644
index 000000000000..d00fd570255a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/iters_looping.c
@@ -0,0 +1,216 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <errno.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define ITER_HELPERS						\
+	  __imm(bpf_iter_num_new),				\
+	  __imm(bpf_iter_num_next),				\
+	  __imm(bpf_iter_num_destroy)
+
+SEC("?raw_tp")
+__success
+int force_clang_to_emit_btf_for_externs(void *ctx)
+{
+	/* we need this as a workaround to enforce compiler emitting BTF
+	 * information for bpf_iter_num_{new,next,destroy}() kfuncs,
+	 * as, apparently, it doesn't emit it for symbols only referenced from
+	 * assembly (or cleanup attribute, for that matter, as well)
+	 */
+	bpf_repeat(0);
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__success
+int consume_first_item_only(void *ctx)
+{
+	struct bpf_iter_num iter;
+
+	asm volatile (
+		/* create iterator */
+		"r1 = %[iter];"
+		"r2 = 0;"
+		"r3 = 1000;"
+		"call %[bpf_iter_num_new];"
+
+		/* consume first item */
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_next];"
+
+		"if r0 == 0 goto +1;"
+		"r0 = *(u32 *)(r0 + 0);"
+
+		/* destroy iterator */
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_destroy];"
+		:
+		: __imm_ptr(iter), ITER_HELPERS
+		: __clobber_common
+	);
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("R0 invalid mem access 'scalar'")
+int missing_null_check_fail(void *ctx)
+{
+	struct bpf_iter_num iter;
+
+	asm volatile (
+		/* create iterator */
+		"r1 = %[iter];"
+		"r2 = 0;"
+		"r3 = 1000;"
+		"call %[bpf_iter_num_new];"
+
+		/* consume first element */
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_next];"
+
+		/* FAIL: deref with no NULL check */
+		"r1 = *(u32 *)(r0 + 0);"
+
+		/* destroy iterator */
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_destroy];"
+		:
+		: __imm_ptr(iter), ITER_HELPERS
+		: __clobber_common
+	);
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure
+__msg("invalid access to memory, mem_size=4 off=0 size=8")
+__msg("R0 min value is outside of the allowed memory range")
+int wrong_sized_read_fail(void *ctx)
+{
+	struct bpf_iter_num iter;
+
+	asm volatile (
+		/* create iterator */
+		"r1 = %[iter];"
+		"r2 = 0;"
+		"r3 = 1000;"
+		"call %[bpf_iter_num_new];"
+
+		/* consume first element */
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_next];"
+
+		"if r0 == 0 goto +1;"
+		/* FAIL: deref more than available 4 bytes */
+		"r0 = *(u64 *)(r0 + 0);"
+
+		/* destroy iterator */
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_destroy];"
+		:
+		: __imm_ptr(iter), ITER_HELPERS
+		: __clobber_common
+	);
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__flag(BPF_F_TEST_STATE_FREQ)
+int simplest_loop(void *ctx)
+{
+	struct bpf_iter_num iter;
+
+	asm volatile (
+		"r6 = 0;" /* init sum */
+
+		/* create iterator */
+		"r1 = %[iter];"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+
+	"1:"
+		/* consume next item */
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_next];"
+
+		"if r0 == 0 goto 2f;"
+		"r0 = *(u32 *)(r0 + 0);"
+		"r6 += r0;" /* accumulate sum */
+		"goto 1b;"
+
+	"2:"
+		/* destroy iterator */
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_destroy];"
+		:
+		: __imm_ptr(iter), ITER_HELPERS
+		: __clobber_common, "r6"
+	);
+
+	return 0;
+}
+
+__used
+static void iterator_with_diff_stack_depth(int x)
+{
+	struct bpf_iter_num iter;
+
+	asm volatile (
+		"if r1 == 42 goto 0f;"
+		"*(u64 *)(r10 - 128) = 0;"
+	"0:"
+		/* create iterator */
+		"r1 = %[iter];"
+		"r2 = 0;"
+		"r3 = 10;"
+		"call %[bpf_iter_num_new];"
+	"1:"
+		/* consume next item */
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_next];"
+		"if r0 == 0 goto 2f;"
+		"goto 1b;"
+	"2:"
+		/* destroy iterator */
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_destroy];"
+		:
+		: __imm_ptr(iter), ITER_HELPERS
+		: __clobber_common, "r6"
+	);
+}
+
+SEC("socket")
+__success
+__naked int widening_stack_size_bug(void *ctx)
+{
+	/*
+	 * Depending on iterator_with_diff_stack_depth() parameter value,
+	 * subprogram stack depth is either 8 or 128 bytes. Arrange values so
+	 * that it is 128 on a first call and 8 on a second. This triggered a
+	 * bug in verifier's widen_imprecise_scalars() logic.
+	 */
+	asm volatile (
+		"r6 = 0;"
+		"r1 = 0;"
+	"1:"
+		"call iterator_with_diff_stack_depth;"
+		"r1 = 42;"
+		"r6 += 1;"
+		"if r6 < 2 goto 1b;"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
diff --git a/tools/testing/selftests/bpf/progs/iters_num.c b/tools/testing/selftests/bpf/progs/iters_num.c
new file mode 100644
index 000000000000..7a77a8daee0d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/iters_num.c
@@ -0,0 +1,242 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <limits.h>
+#include <linux/errno.h>
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+const volatile __s64 exp_empty_zero = 0 + 1;
+__s64 res_empty_zero;
+
+SEC("raw_tp/sys_enter")
+int num_empty_zero(const void *ctx)
+{
+	__s64 sum = 0, i;
+
+	bpf_for(i, 0, 0) sum += i;
+	res_empty_zero = 1 + sum;
+
+	return 0;
+}
+
+const volatile __s64 exp_empty_int_min = 0 + 2;
+__s64 res_empty_int_min;
+
+SEC("raw_tp/sys_enter")
+int num_empty_int_min(const void *ctx)
+{
+	__s64 sum = 0, i;
+
+	bpf_for(i, INT_MIN, INT_MIN) sum += i;
+	res_empty_int_min = 2 + sum;
+
+	return 0;
+}
+
+const volatile __s64 exp_empty_int_max = 0 + 3;
+__s64 res_empty_int_max;
+
+SEC("raw_tp/sys_enter")
+int num_empty_int_max(const void *ctx)
+{
+	__s64 sum = 0, i;
+
+	bpf_for(i, INT_MAX, INT_MAX) sum += i;
+	res_empty_int_max = 3 + sum;
+
+	return 0;
+}
+
+const volatile __s64 exp_empty_minus_one = 0 + 4;
+__s64 res_empty_minus_one;
+
+SEC("raw_tp/sys_enter")
+int num_empty_minus_one(const void *ctx)
+{
+	__s64 sum = 0, i;
+
+	bpf_for(i, -1, -1) sum += i;
+	res_empty_minus_one = 4 + sum;
+
+	return 0;
+}
+
+const volatile __s64 exp_simple_sum = 9 * 10 / 2;
+__s64 res_simple_sum;
+
+SEC("raw_tp/sys_enter")
+int num_simple_sum(const void *ctx)
+{
+	__s64 sum = 0, i;
+
+	bpf_for(i, 0, 10) sum += i;
+	res_simple_sum = sum;
+
+	return 0;
+}
+
+const volatile __s64 exp_neg_sum = -11 * 10 / 2;
+__s64 res_neg_sum;
+
+SEC("raw_tp/sys_enter")
+int num_neg_sum(const void *ctx)
+{
+	__s64 sum = 0, i;
+
+	bpf_for(i, -10, 0) sum += i;
+	res_neg_sum = sum;
+
+	return 0;
+}
+
+const volatile __s64 exp_very_neg_sum = INT_MIN + (__s64)(INT_MIN + 1);
+__s64 res_very_neg_sum;
+
+SEC("raw_tp/sys_enter")
+int num_very_neg_sum(const void *ctx)
+{
+	__s64 sum = 0, i;
+
+	bpf_for(i, INT_MIN, INT_MIN + 2) sum += i;
+	res_very_neg_sum = sum;
+
+	return 0;
+}
+
+const volatile __s64 exp_very_big_sum = (__s64)(INT_MAX - 1) + (__s64)(INT_MAX - 2);
+__s64 res_very_big_sum;
+
+SEC("raw_tp/sys_enter")
+int num_very_big_sum(const void *ctx)
+{
+	__s64 sum = 0, i;
+
+	bpf_for(i, INT_MAX - 2, INT_MAX) sum += i;
+	res_very_big_sum = sum;
+
+	return 0;
+}
+
+const volatile __s64 exp_neg_pos_sum = -3;
+__s64 res_neg_pos_sum;
+
+SEC("raw_tp/sys_enter")
+int num_neg_pos_sum(const void *ctx)
+{
+	__s64 sum = 0, i;
+
+	bpf_for(i, -3, 3) sum += i;
+	res_neg_pos_sum = sum;
+
+	return 0;
+}
+
+const volatile __s64 exp_invalid_range = -EINVAL;
+__s64 res_invalid_range;
+
+SEC("raw_tp/sys_enter")
+int num_invalid_range(const void *ctx)
+{
+	struct bpf_iter_num it;
+
+	res_invalid_range = bpf_iter_num_new(&it, 1, 0);
+	bpf_iter_num_destroy(&it);
+
+	return 0;
+}
+
+const volatile __s64 exp_max_range = 0 + 10;
+__s64 res_max_range;
+
+SEC("raw_tp/sys_enter")
+int num_max_range(const void *ctx)
+{
+	struct bpf_iter_num it;
+
+	res_max_range = 10 + bpf_iter_num_new(&it, 0, BPF_MAX_LOOPS);
+	bpf_iter_num_destroy(&it);
+
+	return 0;
+}
+
+const volatile __s64 exp_e2big_range = -E2BIG;
+__s64 res_e2big_range;
+
+SEC("raw_tp/sys_enter")
+int num_e2big_range(const void *ctx)
+{
+	struct bpf_iter_num it;
+
+	res_e2big_range = bpf_iter_num_new(&it, -1, BPF_MAX_LOOPS);
+	bpf_iter_num_destroy(&it);
+
+	return 0;
+}
+
+const volatile __s64 exp_succ_elem_cnt = 10;
+__s64 res_succ_elem_cnt;
+
+SEC("raw_tp/sys_enter")
+int num_succ_elem_cnt(const void *ctx)
+{
+	struct bpf_iter_num it;
+	int cnt = 0, *v;
+
+	bpf_iter_num_new(&it, 0, 10);
+	while ((v = bpf_iter_num_next(&it))) {
+		cnt++;
+	}
+	bpf_iter_num_destroy(&it);
+
+	res_succ_elem_cnt = cnt;
+
+	return 0;
+}
+
+const volatile __s64 exp_overfetched_elem_cnt = 5;
+__s64 res_overfetched_elem_cnt;
+
+SEC("raw_tp/sys_enter")
+int num_overfetched_elem_cnt(const void *ctx)
+{
+	struct bpf_iter_num it;
+	int cnt = 0, *v, i;
+
+	bpf_iter_num_new(&it, 0, 5);
+	for (i = 0; i < 10; i++) {
+		v = bpf_iter_num_next(&it);
+		if (v)
+			cnt++;
+	}
+	bpf_iter_num_destroy(&it);
+
+	res_overfetched_elem_cnt = cnt;
+
+	return 0;
+}
+
+const volatile __s64 exp_fail_elem_cnt = 20 + 0;
+__s64 res_fail_elem_cnt;
+
+SEC("raw_tp/sys_enter")
+int num_fail_elem_cnt(const void *ctx)
+{
+	struct bpf_iter_num it;
+	int cnt = 0, *v, i;
+
+	bpf_iter_num_new(&it, 100, 10);
+	for (i = 0; i < 10; i++) {
+		v = bpf_iter_num_next(&it);
+		if (v)
+			cnt++;
+	}
+	bpf_iter_num_destroy(&it);
+
+	res_fail_elem_cnt = 20 + cnt;
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/iters_state_safety.c b/tools/testing/selftests/bpf/progs/iters_state_safety.c
new file mode 100644
index 000000000000..d273b46dfc7c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/iters_state_safety.c
@@ -0,0 +1,426 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Facebook */
+
+#include <errno.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define ITER_HELPERS						\
+	  __imm(bpf_iter_num_new),				\
+	  __imm(bpf_iter_num_next),				\
+	  __imm(bpf_iter_num_destroy)
+
+SEC("?raw_tp")
+__success
+int force_clang_to_emit_btf_for_externs(void *ctx)
+{
+	/* we need this as a workaround to enforce compiler emitting BTF
+	 * information for bpf_iter_num_{new,next,destroy}() kfuncs,
+	 * as, apparently, it doesn't emit it for symbols only referenced from
+	 * assembly (or cleanup attribute, for that matter, as well)
+	 */
+	bpf_repeat(0);
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("fp-8=iter_num(ref_id=1,state=active,depth=0)")
+int create_and_destroy(void *ctx)
+{
+	struct bpf_iter_num iter;
+
+	asm volatile (
+		/* create iterator */
+		"r1 = %[iter];"
+		"r2 = 0;"
+		"r3 = 1000;"
+		"call %[bpf_iter_num_new];"
+		/* destroy iterator */
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_destroy];"
+		:
+		: __imm_ptr(iter), ITER_HELPERS
+		: __clobber_common
+	);
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("Unreleased reference id=1")
+int create_and_forget_to_destroy_fail(void *ctx)
+{
+	struct bpf_iter_num iter;
+
+	asm volatile (
+		/* create iterator */
+		"r1 = %[iter];"
+		"r2 = 0;"
+		"r3 = 1000;"
+		"call %[bpf_iter_num_new];"
+		:
+		: __imm_ptr(iter), ITER_HELPERS
+		: __clobber_common
+	);
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("expected an initialized iter_num as arg #0")
+int destroy_without_creating_fail(void *ctx)
+{
+	/* init with zeros to stop verifier complaining about uninit stack */
+	struct bpf_iter_num iter;
+
+	asm volatile (
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_destroy];"
+		:
+		: __imm_ptr(iter), ITER_HELPERS
+		: __clobber_common
+	);
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("expected an initialized iter_num as arg #0")
+int compromise_iter_w_direct_write_fail(void *ctx)
+{
+	struct bpf_iter_num iter;
+
+	asm volatile (
+		/* create iterator */
+		"r1 = %[iter];"
+		"r2 = 0;"
+		"r3 = 1000;"
+		"call %[bpf_iter_num_new];"
+
+		/* directly write over first half of iter state */
+		"*(u64 *)(%[iter] + 0) = r0;"
+
+		/* (attempt to) destroy iterator */
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_destroy];"
+		:
+		: __imm_ptr(iter), ITER_HELPERS
+		: __clobber_common
+	);
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("Unreleased reference id=1")
+int compromise_iter_w_direct_write_and_skip_destroy_fail(void *ctx)
+{
+	struct bpf_iter_num iter;
+
+	asm volatile (
+		/* create iterator */
+		"r1 = %[iter];"
+		"r2 = 0;"
+		"r3 = 1000;"
+		"call %[bpf_iter_num_new];"
+
+		/* directly write over first half of iter state */
+		"*(u64 *)(%[iter] + 0) = r0;"
+
+		/* don't destroy iter, leaking ref, which should fail */
+		:
+		: __imm_ptr(iter), ITER_HELPERS
+		: __clobber_common
+	);
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("expected an initialized iter_num as arg #0")
+int compromise_iter_w_helper_write_fail(void *ctx)
+{
+	struct bpf_iter_num iter;
+
+	asm volatile (
+		/* create iterator */
+		"r1 = %[iter];"
+		"r2 = 0;"
+		"r3 = 1000;"
+		"call %[bpf_iter_num_new];"
+
+		/* overwrite 8th byte with bpf_probe_read_kernel() */
+		"r1 = %[iter];"
+		"r1 += 7;"
+		"r2 = 1;"
+		"r3 = 0;" /* NULL */
+		"call %[bpf_probe_read_kernel];"
+
+		/* (attempt to) destroy iterator */
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_destroy];"
+		:
+		: __imm_ptr(iter), ITER_HELPERS, __imm(bpf_probe_read_kernel)
+		: __clobber_common
+	);
+
+	return 0;
+}
+
+static __noinline void subprog_with_iter(void)
+{
+	struct bpf_iter_num iter;
+
+	bpf_iter_num_new(&iter, 0, 1);
+
+	return;
+}
+
+SEC("?raw_tp")
+__failure
+/* ensure there was a call to subprog, which might happen without __noinline */
+__msg("returning from callee:")
+__msg("Unreleased reference id=1")
+int leak_iter_from_subprog_fail(void *ctx)
+{
+	subprog_with_iter();
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("fp-8=iter_num(ref_id=1,state=active,depth=0)")
+int valid_stack_reuse(void *ctx)
+{
+	struct bpf_iter_num iter;
+
+	asm volatile (
+		/* create iterator */
+		"r1 = %[iter];"
+		"r2 = 0;"
+		"r3 = 1000;"
+		"call %[bpf_iter_num_new];"
+		/* destroy iterator */
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_destroy];"
+
+		/* now reuse same stack slots */
+
+		/* create iterator */
+		"r1 = %[iter];"
+		"r2 = 0;"
+		"r3 = 1000;"
+		"call %[bpf_iter_num_new];"
+		/* destroy iterator */
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_destroy];"
+		:
+		: __imm_ptr(iter), ITER_HELPERS
+		: __clobber_common
+	);
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("expected uninitialized iter_num as arg #0")
+int double_create_fail(void *ctx)
+{
+	struct bpf_iter_num iter;
+
+	asm volatile (
+		/* create iterator */
+		"r1 = %[iter];"
+		"r2 = 0;"
+		"r3 = 1000;"
+		"call %[bpf_iter_num_new];"
+		/* (attempt to) create iterator again */
+		"r1 = %[iter];"
+		"r2 = 0;"
+		"r3 = 1000;"
+		"call %[bpf_iter_num_new];"
+		/* destroy iterator */
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_destroy];"
+		:
+		: __imm_ptr(iter), ITER_HELPERS
+		: __clobber_common
+	);
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("expected an initialized iter_num as arg #0")
+int double_destroy_fail(void *ctx)
+{
+	struct bpf_iter_num iter;
+
+	asm volatile (
+		/* create iterator */
+		"r1 = %[iter];"
+		"r2 = 0;"
+		"r3 = 1000;"
+		"call %[bpf_iter_num_new];"
+		/* destroy iterator */
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_destroy];"
+		/* (attempt to) destroy iterator again */
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_destroy];"
+		:
+		: __imm_ptr(iter), ITER_HELPERS
+		: __clobber_common
+	);
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("expected an initialized iter_num as arg #0")
+int next_without_new_fail(void *ctx)
+{
+	struct bpf_iter_num iter;
+
+	asm volatile (
+		/* don't create iterator and try to iterate*/
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_next];"
+		/* destroy iterator */
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_destroy];"
+		:
+		: __imm_ptr(iter), ITER_HELPERS
+		: __clobber_common
+	);
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("expected an initialized iter_num as arg #0")
+int next_after_destroy_fail(void *ctx)
+{
+	struct bpf_iter_num iter;
+
+	asm volatile (
+		/* create iterator */
+		"r1 = %[iter];"
+		"r2 = 0;"
+		"r3 = 1000;"
+		"call %[bpf_iter_num_new];"
+		/* destroy iterator */
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_destroy];"
+		/* don't create iterator and try to iterate*/
+		"r1 = %[iter];"
+		"call %[bpf_iter_num_next];"
+		:
+		: __imm_ptr(iter), ITER_HELPERS
+		: __clobber_common
+	);
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("invalid read from stack")
+int __naked read_from_iter_slot_fail(void)
+{
+	asm volatile (
+		/* r6 points to struct bpf_iter_num on the stack */
+		"r6 = r10;"
+		"r6 += -24;"
+
+		/* create iterator */
+		"r1 = r6;"
+		"r2 = 0;"
+		"r3 = 1000;"
+		"call %[bpf_iter_num_new];"
+
+		/* attempt to leak bpf_iter_num state */
+		"r7 = *(u64 *)(r6 + 0);"
+		"r8 = *(u64 *)(r6 + 8);"
+
+		/* destroy iterator */
+		"r1 = r6;"
+		"call %[bpf_iter_num_destroy];"
+
+		/* leak bpf_iter_num state */
+		"r0 = r7;"
+		"if r7 > r8 goto +1;"
+		"r0 = r8;"
+		"exit;"
+		:
+		: ITER_HELPERS
+		: __clobber_common, "r6", "r7", "r8"
+	);
+}
+
+int zero;
+
+SEC("?raw_tp")
+__failure
+__flag(BPF_F_TEST_STATE_FREQ)
+__msg("Unreleased reference")
+int stacksafe_should_not_conflate_stack_spill_and_iter(void *ctx)
+{
+	struct bpf_iter_num iter;
+
+	asm volatile (
+		/* Create a fork in logic, with general setup as follows:
+		 *   - fallthrough (first) path is valid;
+		 *   - branch (second) path is invalid.
+		 * Then depending on what we do in fallthrough vs branch path,
+		 * we try to detect bugs in func_states_equal(), regsafe(),
+		 * refsafe(), stack_safe(), and similar by tricking verifier
+		 * into believing that branch state is a valid subset of
+		 * a fallthrough state. Verifier should reject overall
+		 * validation, unless there is a bug somewhere in verifier
+		 * logic.
+		 */
+		"call %[bpf_get_prandom_u32];"
+		"r6 = r0;"
+		"call %[bpf_get_prandom_u32];"
+		"r7 = r0;"
+
+		"if r6 > r7 goto bad;" /* fork */
+
+		/* spill r6 into stack slot of bpf_iter_num var */
+		"*(u64 *)(%[iter] + 0) = r6;"
+
+		"goto skip_bad;"
+
+	"bad:"
+		/* create iterator in the same stack slot */
+		"r1 = %[iter];"
+		"r2 = 0;"
+		"r3 = 1000;"
+		"call %[bpf_iter_num_new];"
+
+		/* but then forget about it and overwrite it back to r6 spill */
+		"*(u64 *)(%[iter] + 0) = r6;"
+
+	"skip_bad:"
+		"goto +0;" /* force checkpoint */
+
+		/* corrupt stack slots, if they are really dynptr */
+		"*(u64 *)(%[iter] + 0) = r6;"
+		:
+		: __imm_ptr(iter),
+		  __imm_addr(zero),
+		  __imm(bpf_get_prandom_u32),
+		  __imm(bpf_dynptr_from_mem),
+		  ITER_HELPERS
+		: __clobber_common, "r6", "r7"
+	);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/iters_task.c b/tools/testing/selftests/bpf/progs/iters_task.c
new file mode 100644
index 000000000000..e4d53e40ff20
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/iters_task.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Chuyi Zhou <zhouchuyi@bytedance.com> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+char _license[] SEC("license") = "GPL";
+
+pid_t target_pid;
+int procs_cnt, threads_cnt, proc_threads_cnt, invalid_cnt;
+
+void bpf_rcu_read_lock(void) __ksym;
+void bpf_rcu_read_unlock(void) __ksym;
+
+SEC("fentry.s/" SYS_PREFIX "sys_getpgid")
+int iter_task_for_each_sleep(void *ctx)
+{
+	struct task_struct *cur_task = bpf_get_current_task_btf();
+	struct task_struct *pos;
+
+	if (cur_task->pid != target_pid)
+		return 0;
+	procs_cnt = threads_cnt = proc_threads_cnt = 0;
+
+	bpf_rcu_read_lock();
+	bpf_for_each(task, pos, NULL, ~0U) {
+		/* Below instructions shouldn't be executed for invalid flags */
+		invalid_cnt++;
+	}
+
+	bpf_for_each(task, pos, NULL, BPF_TASK_ITER_PROC_THREADS) {
+		/* Below instructions shouldn't be executed for invalid task__nullable */
+		invalid_cnt++;
+	}
+
+	bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS)
+		if (pos->pid == target_pid)
+			procs_cnt++;
+
+	bpf_for_each(task, pos, cur_task, BPF_TASK_ITER_PROC_THREADS)
+		proc_threads_cnt++;
+
+	bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_THREADS)
+		if (pos->tgid == target_pid)
+			threads_cnt++;
+	bpf_rcu_read_unlock();
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/iters_task_failure.c b/tools/testing/selftests/bpf/progs/iters_task_failure.c
new file mode 100644
index 000000000000..fe3663dedbe1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/iters_task_failure.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Chuyi Zhou <zhouchuyi@bytedance.com> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym;
+void bpf_cgroup_release(struct cgroup *p) __ksym;
+void bpf_rcu_read_lock(void) __ksym;
+void bpf_rcu_read_unlock(void) __ksym;
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("kernel func bpf_iter_task_new requires RCU critical section protection")
+int BPF_PROG(iter_tasks_without_lock)
+{
+	struct task_struct *pos;
+
+	bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS) {
+
+	}
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("kernel func bpf_iter_css_new requires RCU critical section protection")
+int BPF_PROG(iter_css_without_lock)
+{
+	u64 cg_id = bpf_get_current_cgroup_id();
+	struct cgroup *cgrp = bpf_cgroup_from_id(cg_id);
+	struct cgroup_subsys_state *root_css, *pos;
+
+	if (!cgrp)
+		return 0;
+	root_css = &cgrp->self;
+
+	bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) {
+
+	}
+	bpf_cgroup_release(cgrp);
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("expected an RCU CS when using bpf_iter_task_next")
+int BPF_PROG(iter_tasks_lock_and_unlock)
+{
+	struct task_struct *pos;
+
+	bpf_rcu_read_lock();
+	bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS) {
+		bpf_rcu_read_unlock();
+
+		bpf_rcu_read_lock();
+	}
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("expected an RCU CS when using bpf_iter_css_next")
+int BPF_PROG(iter_css_lock_and_unlock)
+{
+	u64 cg_id = bpf_get_current_cgroup_id();
+	struct cgroup *cgrp = bpf_cgroup_from_id(cg_id);
+	struct cgroup_subsys_state *root_css, *pos;
+
+	if (!cgrp)
+		return 0;
+	root_css = &cgrp->self;
+
+	bpf_rcu_read_lock();
+	bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) {
+		bpf_rcu_read_unlock();
+
+		bpf_rcu_read_lock();
+	}
+	bpf_rcu_read_unlock();
+	bpf_cgroup_release(cgrp);
+	return 0;
+}
+
+SEC("?fentry/" SYS_PREFIX "sys_getpgid")
+__failure __msg("css_task_iter is only allowed in bpf_lsm, bpf_iter and sleepable progs")
+int BPF_PROG(iter_css_task_for_each)
+{
+	u64 cg_id = bpf_get_current_cgroup_id();
+	struct cgroup *cgrp = bpf_cgroup_from_id(cg_id);
+	struct cgroup_subsys_state *css;
+	struct task_struct *task;
+
+	if (cgrp == NULL)
+		return 0;
+	css = &cgrp->self;
+
+	bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) {
+
+	}
+	bpf_cgroup_release(cgrp);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/iters_task_vma.c b/tools/testing/selftests/bpf/progs/iters_task_vma.c
new file mode 100644
index 000000000000..dc0c3691dcc2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/iters_task_vma.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include "bpf_experimental.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+pid_t target_pid = 0;
+unsigned int vmas_seen = 0;
+
+struct {
+	__u64 vm_start;
+	__u64 vm_end;
+} vm_ranges[1000];
+
+SEC("raw_tp/sys_enter")
+int iter_task_vma_for_each(const void *ctx)
+{
+	struct task_struct *task = bpf_get_current_task_btf();
+	struct vm_area_struct *vma;
+	unsigned int seen = 0;
+
+	if (task->pid != target_pid)
+		return 0;
+
+	if (vmas_seen)
+		return 0;
+
+	bpf_for_each(task_vma, vma, task, 0) {
+		if (bpf_cmp_unlikely(seen, >=, 1000))
+			break;
+
+		vm_ranges[seen].vm_start = vma->vm_start;
+		vm_ranges[seen].vm_end = vma->vm_end;
+		seen++;
+	}
+
+	vmas_seen = seen;
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/iters_testmod.c b/tools/testing/selftests/bpf/progs/iters_testmod.c
new file mode 100644
index 000000000000..5379e9960ffd
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/iters_testmod.c
@@ -0,0 +1,171 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include "bpf_experimental.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("raw_tp/sys_enter")
+__success
+int iter_next_trusted(const void *ctx)
+{
+	struct task_struct *cur_task = bpf_get_current_task_btf();
+	struct bpf_iter_task_vma vma_it;
+	struct vm_area_struct *vma_ptr;
+
+	bpf_iter_task_vma_new(&vma_it, cur_task, 0);
+
+	vma_ptr = bpf_iter_task_vma_next(&vma_it);
+	if (vma_ptr == NULL)
+		goto out;
+
+	bpf_kfunc_trusted_vma_test(vma_ptr);
+out:
+	bpf_iter_task_vma_destroy(&vma_it);
+	return 0;
+}
+
+SEC("raw_tp/sys_enter")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
+int iter_next_trusted_or_null(const void *ctx)
+{
+	struct task_struct *cur_task = bpf_get_current_task_btf();
+	struct bpf_iter_task_vma vma_it;
+	struct vm_area_struct *vma_ptr;
+
+	bpf_iter_task_vma_new(&vma_it, cur_task, 0);
+
+	vma_ptr = bpf_iter_task_vma_next(&vma_it);
+
+	bpf_kfunc_trusted_vma_test(vma_ptr);
+
+	bpf_iter_task_vma_destroy(&vma_it);
+	return 0;
+}
+
+SEC("raw_tp/sys_enter")
+__success
+int iter_next_rcu(const void *ctx)
+{
+	struct task_struct *cur_task = bpf_get_current_task_btf();
+	struct bpf_iter_task task_it;
+	struct task_struct *task_ptr;
+
+	bpf_iter_task_new(&task_it, cur_task, 0);
+
+	task_ptr = bpf_iter_task_next(&task_it);
+	if (task_ptr == NULL)
+		goto out;
+
+	bpf_kfunc_rcu_task_test(task_ptr);
+out:
+	bpf_iter_task_destroy(&task_it);
+	return 0;
+}
+
+SEC("raw_tp/sys_enter")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
+int iter_next_rcu_or_null(const void *ctx)
+{
+	struct task_struct *cur_task = bpf_get_current_task_btf();
+	struct bpf_iter_task task_it;
+	struct task_struct *task_ptr;
+
+	bpf_iter_task_new(&task_it, cur_task, 0);
+
+	task_ptr = bpf_iter_task_next(&task_it);
+
+	bpf_kfunc_rcu_task_test(task_ptr);
+
+	bpf_iter_task_destroy(&task_it);
+	return 0;
+}
+
+SEC("raw_tp/sys_enter")
+__failure __msg("R1 must be referenced or trusted")
+int iter_next_rcu_not_trusted(const void *ctx)
+{
+	struct task_struct *cur_task = bpf_get_current_task_btf();
+	struct bpf_iter_task task_it;
+	struct task_struct *task_ptr;
+
+	bpf_iter_task_new(&task_it, cur_task, 0);
+
+	task_ptr = bpf_iter_task_next(&task_it);
+	if (task_ptr == NULL)
+		goto out;
+
+	bpf_kfunc_trusted_task_test(task_ptr);
+out:
+	bpf_iter_task_destroy(&task_it);
+	return 0;
+}
+
+SEC("raw_tp/sys_enter")
+__failure __msg("R1 cannot write into rdonly_mem")
+/* Message should not be 'R1 cannot write into rdonly_trusted_mem' */
+int iter_next_ptr_mem_not_trusted(const void *ctx)
+{
+	struct bpf_iter_num num_it;
+	int *num_ptr;
+
+	bpf_iter_num_new(&num_it, 0, 10);
+
+	num_ptr = bpf_iter_num_next(&num_it);
+	if (num_ptr == NULL)
+		goto out;
+
+	bpf_kfunc_trusted_num_test(num_ptr);
+out:
+	bpf_iter_num_destroy(&num_it);
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("kernel func bpf_kfunc_ret_rcu_test requires RCU critical section protection")
+int iter_ret_rcu_test_protected(const void *ctx)
+{
+	struct task_struct *p;
+
+	p = bpf_kfunc_ret_rcu_test();
+	return p->pid;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("R1 type=rcu_ptr_or_null_ expected=")
+int iter_ret_rcu_test_type(const void *ctx)
+{
+	struct task_struct *p;
+
+	bpf_rcu_read_lock();
+	p = bpf_kfunc_ret_rcu_test();
+	bpf_this_cpu_ptr(p);
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("kernel func bpf_kfunc_ret_rcu_test_nostruct requires RCU critical section protection")
+int iter_ret_rcu_test_protected_nostruct(const void *ctx)
+{
+	void *p;
+
+	p = bpf_kfunc_ret_rcu_test_nostruct(4);
+	return *(int *)p;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("R1 type=rdonly_rcu_mem_or_null expected=")
+int iter_ret_rcu_test_type_nostruct(const void *ctx)
+{
+	void *p;
+
+	bpf_rcu_read_lock();
+	p = bpf_kfunc_ret_rcu_test_nostruct(4);
+	bpf_this_cpu_ptr(p);
+	bpf_rcu_read_unlock();
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/iters_testmod_seq.c b/tools/testing/selftests/bpf/progs/iters_testmod_seq.c
new file mode 100644
index 000000000000..83791348bed5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/iters_testmod_seq.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct bpf_iter_testmod_seq {
+	u64 :64;
+	u64 :64;
+};
+
+extern int bpf_iter_testmod_seq_new(struct bpf_iter_testmod_seq *it, s64 value, int cnt) __ksym;
+extern s64 *bpf_iter_testmod_seq_next(struct bpf_iter_testmod_seq *it) __ksym;
+extern s64 bpf_iter_testmod_seq_value(int blah, struct bpf_iter_testmod_seq *it) __ksym;
+extern void bpf_iter_testmod_seq_destroy(struct bpf_iter_testmod_seq *it) __ksym;
+
+const volatile __s64 exp_empty = 0 + 1;
+__s64 res_empty;
+
+SEC("raw_tp/sys_enter")
+__success __log_level(2)
+__msg("fp-16=iter_testmod_seq(ref_id=1,state=active,depth=0)")
+__msg("fp-16=iter_testmod_seq(ref_id=1,state=drained,depth=0)")
+__msg("call bpf_iter_testmod_seq_destroy")
+int testmod_seq_empty(const void *ctx)
+{
+	__s64 sum = 0, *i;
+
+	bpf_for_each(testmod_seq, i, 1000, 0) sum += *i;
+	res_empty = 1 + sum;
+
+	return 0;
+}
+
+const volatile __s64 exp_full = 1000000;
+__s64 res_full;
+
+SEC("raw_tp/sys_enter")
+__success __log_level(2)
+__msg("fp-16=iter_testmod_seq(ref_id=1,state=active,depth=0)")
+__msg("fp-16=iter_testmod_seq(ref_id=1,state=drained,depth=0)")
+__msg("call bpf_iter_testmod_seq_destroy")
+int testmod_seq_full(const void *ctx)
+{
+	__s64 sum = 0, *i;
+
+	bpf_for_each(testmod_seq, i, 1000, 1000) sum += *i;
+	res_full = sum;
+
+	return 0;
+}
+
+const volatile __s64 exp_truncated = 10 * 1000000;
+__s64 res_truncated;
+
+static volatile int zero = 0;
+
+SEC("raw_tp/sys_enter")
+__success __log_level(2)
+__msg("fp-16=iter_testmod_seq(ref_id=1,state=active,depth=0)")
+__msg("fp-16=iter_testmod_seq(ref_id=1,state=drained,depth=0)")
+__msg("call bpf_iter_testmod_seq_destroy")
+int testmod_seq_truncated(const void *ctx)
+{
+	__s64 sum = 0, *i;
+	int cnt = zero;
+
+	bpf_for_each(testmod_seq, i, 10, 2000000) {
+		sum += *i;
+		cnt++;
+		if (cnt >= 1000000)
+			break;
+	}
+	res_truncated = sum;
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure
+__msg("expected an initialized iter_testmod_seq as arg #1")
+int testmod_seq_getter_before_bad(const void *ctx)
+{
+	struct bpf_iter_testmod_seq it;
+
+	return bpf_iter_testmod_seq_value(0, &it);
+}
+
+SEC("?raw_tp")
+__failure
+__msg("expected an initialized iter_testmod_seq as arg #1")
+int testmod_seq_getter_after_bad(const void *ctx)
+{
+	struct bpf_iter_testmod_seq it;
+	s64 sum = 0, *v;
+
+	bpf_iter_testmod_seq_new(&it, 100, 100);
+
+	while ((v = bpf_iter_testmod_seq_next(&it))) {
+		sum += *v;
+	}
+
+	bpf_iter_testmod_seq_destroy(&it);
+
+	return sum + bpf_iter_testmod_seq_value(0, &it);
+}
+
+SEC("?socket")
+__success __retval(1000000)
+int testmod_seq_getter_good(const void *ctx)
+{
+	struct bpf_iter_testmod_seq it;
+	s64 sum = 0, *v;
+
+	bpf_iter_testmod_seq_new(&it, 100, 100);
+
+	while ((v = bpf_iter_testmod_seq_next(&it))) {
+		sum += *v;
+	}
+
+	sum *= bpf_iter_testmod_seq_value(0, &it);
+
+	bpf_iter_testmod_seq_destroy(&it);
+
+	return sum;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c b/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c
new file mode 100644
index 000000000000..4d619bea9c75
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#ifndef __clang__
+#pragma GCC diagnostic ignored "-Warray-bounds"
+#endif
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, u64);
+	__type(value, u64);
+} m_hash SEC(".maps");
+
+SEC("?raw_tp")
+__failure __msg("R8 invalid mem access 'map_value_or_null")
+int jeq_infer_not_null_ptr_to_btfid(void *ctx)
+{
+	struct bpf_map *map = (struct bpf_map *)&m_hash;
+	struct bpf_map *inner_map = map->inner_map_meta;
+	u64 key = 0, ret = 0, *val;
+
+	val = bpf_map_lookup_elem(map, &key);
+	/* Do not mark ptr as non-null if one of them is
+	 * PTR_TO_BTF_ID (R9), reject because of invalid
+	 * access to map value (R8).
+	 *
+	 * Here, we need to inline those insns to access
+	 * R8 directly, since compiler may use other reg
+	 * once it figures out val==inner_map.
+	 */
+	asm volatile("r8 = %[val];\n"
+		     "r9 = %[inner_map];\n"
+		     "if r8 != r9 goto +1;\n"
+		     "%[ret] = *(u64 *)(r8 +0);\n"
+		     : [ret] "+r"(ret)
+		     : [inner_map] "r"(inner_map), [val] "r"(val)
+		     : "r8", "r9");
+
+	return ret;
+}
diff --git a/tools/testing/selftests/bpf/progs/jit_probe_mem.c b/tools/testing/selftests/bpf/progs/jit_probe_mem.c
new file mode 100644
index 000000000000..82190d79de37
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/jit_probe_mem.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+static struct prog_test_ref_kfunc __kptr *v;
+long total_sum = -1;
+
+SEC("tc")
+int test_jit_probe_mem(struct __sk_buff *ctx)
+{
+	struct prog_test_ref_kfunc *p;
+	unsigned long zero = 0, sum;
+
+	p = bpf_kfunc_call_test_acquire(&zero);
+	if (!p)
+		return 1;
+
+	p = bpf_kptr_xchg(&v, p);
+	if (p)
+		goto release_out;
+
+	/* Direct map value access of kptr, should be PTR_UNTRUSTED */
+	p = v;
+	if (!p)
+		return 1;
+
+	asm volatile (
+		"r9 = %[p];"
+		"%[sum] = 0;"
+
+		/* r8 = p->a */
+		"r8 = *(u32 *)(r9 + 0);"
+		"%[sum] += r8;"
+
+		/* r8 = p->b */
+		"r8 = *(u32 *)(r9 + 4);"
+		"%[sum] += r8;"
+
+		"r9 += 8;"
+		/* r9 = p->a */
+		"r9 = *(u32 *)(r9 - 8);"
+		"%[sum] += r9;"
+
+		: [sum] "=r"(sum)
+		: [p] "r"(p)
+		: "r8", "r9"
+	);
+
+	total_sum = sum;
+	return 0;
+release_out:
+	bpf_kfunc_call_test_release(p);
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c b/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c
index 767472bc5a97..b9670e9a6e3d 100644
--- a/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c
+++ b/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c
@@ -1,8 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
-
-extern void bpf_kfunc_call_test_destructive(void) __ksym;
+#include "../test_kmods/bpf_testmod_kfunc.h"
 
 SEC("tc")
 int kfunc_destructive_test(void)
diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_fail.c b/tools/testing/selftests/bpf/progs/kfunc_call_fail.c
index b98313d391c6..a1963497f0bf 100644
--- a/tools/testing/selftests/bpf/progs/kfunc_call_fail.c
+++ b/tools/testing/selftests/bpf/progs/kfunc_call_fail.c
@@ -2,14 +2,7 @@
 /* Copyright (c) 2021 Facebook */
 #include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
-
-extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym;
-extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym;
-extern void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym;
-extern int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size) __ksym;
-extern int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym;
-extern int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym;
-extern void bpf_kfunc_call_int_mem_release(int *p) __ksym;
+#include "../test_kmods/bpf_testmod_kfunc.h"
 
 struct syscall_test_args {
 	__u8 data[16];
@@ -157,4 +150,11 @@ int kfunc_call_test_mem_acquire_fail(struct __sk_buff *skb)
 	return ret;
 }
 
+SEC("?tc")
+int kfunc_call_test_pointer_arg_type_mismatch(struct __sk_buff *skb)
+{
+	bpf_kfunc_call_test_pass_ctx((void *)10);
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_race.c b/tools/testing/selftests/bpf/progs/kfunc_call_race.c
index 4e8fed75a4e0..48f64827cd93 100644
--- a/tools/testing/selftests/bpf/progs/kfunc_call_race.c
+++ b/tools/testing/selftests/bpf/progs/kfunc_call_race.c
@@ -1,8 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
-
-extern void bpf_testmod_test_mod_kfunc(int i) __ksym;
+#include "../test_kmods/bpf_testmod_kfunc.h"
 
 SEC("tc")
 int kfunc_call_fail(struct __sk_buff *ctx)
diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c
index f636e50be259..8b86113a0126 100644
--- a/tools/testing/selftests/bpf/progs/kfunc_call_test.c
+++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c
@@ -2,20 +2,24 @@
 /* Copyright (c) 2021 Facebook */
 #include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
+#include "../test_kmods/bpf_testmod_kfunc.h"
 
-extern int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym;
-extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b,
-				  __u32 c, __u64 d) __ksym;
+SEC("tc")
+int kfunc_call_test4(struct __sk_buff *skb)
+{
+	struct bpf_sock *sk = skb->sk;
+	long tmp;
 
-extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym;
-extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym;
-extern void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) __ksym;
-extern void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) __ksym;
-extern void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) __ksym;
-extern void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym;
-extern void bpf_kfunc_call_test_mem_len_fail2(__u64 *mem, int len) __ksym;
-extern int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size) __ksym;
-extern int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym;
+	if (!sk)
+		return -1;
+
+	sk = bpf_sk_fullsock(sk);
+	if (!sk)
+		return -1;
+
+	tmp = bpf_kfunc_call_test4(-3, -30, -200, -1000);
+	return (tmp >> 32) + tmp;
+}
 
 SEC("tc")
 int kfunc_call_test2(struct __sk_buff *skb)
@@ -163,4 +167,51 @@ int kfunc_call_test_get_mem(struct __sk_buff *skb)
 	return ret;
 }
 
+SEC("tc")
+int kfunc_call_test_static_unused_arg(struct __sk_buff *skb)
+{
+
+	u32 expected = 5, actual;
+
+	actual = bpf_kfunc_call_test_static_unused_arg(expected, 0xdeadbeef);
+	return actual != expected ? -1 : 0;
+}
+
+struct ctx_val {
+	struct bpf_testmod_ctx __kptr *ctx;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct ctx_val);
+} ctx_map SEC(".maps");
+
+SEC("tc")
+int kfunc_call_ctx(struct __sk_buff *skb)
+{
+	struct bpf_testmod_ctx *ctx;
+	int err = 0;
+
+	ctx = bpf_testmod_ctx_create(&err);
+	if (!ctx && !err)
+		err = -1;
+	if (ctx) {
+		int key = 0;
+		struct ctx_val *ctx_val = bpf_map_lookup_elem(&ctx_map, &key);
+
+		/* Transfer ctx to map to be freed via implicit dtor call
+		 * on cleanup.
+		 */
+		if (ctx_val)
+			ctx = bpf_kptr_xchg(&ctx_val->ctx, ctx);
+		if (ctx) {
+			bpf_testmod_ctx_release(ctx);
+			err = -1;
+		}
+	}
+	return err;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c
index c1fdecabeabf..8e150e85b50d 100644
--- a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c
+++ b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c
@@ -1,13 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2021 Facebook */
-#include <linux/bpf.h>
-#include <bpf/bpf_helpers.h>
-#include "bpf_tcp_helpers.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
 
 extern const int bpf_prog_active __ksym;
-extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b,
-				  __u32 c, __u64 d) __ksym;
-extern struct sock *bpf_kfunc_call_test3(struct sock *sk) __ksym;
 int active_res = -1;
 int sk_state_res = -1;
 
@@ -28,7 +23,7 @@ int __noinline f1(struct __sk_buff *skb)
 	if (active)
 		active_res = *active;
 
-	sk_state_res = bpf_kfunc_call_test3((struct sock *)sk)->sk_state;
+	sk_state_res = bpf_kfunc_call_test3((struct sock *)sk)->__sk_common.skc_state;
 
 	return (__u32)bpf_kfunc_call_test1((struct sock *)sk, 1, 2, 3, 4);
 }
diff --git a/tools/testing/selftests/bpf/progs/kfunc_module_order.c b/tools/testing/selftests/bpf/progs/kfunc_module_order.c
new file mode 100644
index 000000000000..76003d04c95f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/kfunc_module_order.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+extern int bpf_test_modorder_retx(void) __ksym;
+extern int bpf_test_modorder_rety(void) __ksym;
+
+SEC("classifier")
+int call_kfunc_xy(struct __sk_buff *skb)
+{
+	int ret1, ret2;
+
+	ret1 = bpf_test_modorder_retx();
+	ret2 = bpf_test_modorder_rety();
+
+	return ret1 == 'x' && ret2 == 'y' ? 0 : -1;
+}
+
+SEC("classifier")
+int call_kfunc_yx(struct __sk_buff *skb)
+{
+	int ret1, ret2;
+
+	ret1 = bpf_test_modorder_rety();
+	ret2 = bpf_test_modorder_retx();
+
+	return ret1 == 'y' && ret2 == 'x' ? 0 : -1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/kmem_cache_iter.c b/tools/testing/selftests/bpf/progs/kmem_cache_iter.c
new file mode 100644
index 000000000000..b9c8f9457492
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/kmem_cache_iter.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Google */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_experimental.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define SLAB_NAME_MAX  32
+
+struct kmem_cache_result {
+	char name[SLAB_NAME_MAX];
+	long obj_size;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(void *));
+	__uint(value_size, SLAB_NAME_MAX);
+	__uint(max_entries, 1);
+} slab_hash SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(struct kmem_cache_result));
+	__uint(max_entries, 1024);
+} slab_result SEC(".maps");
+
+extern struct kmem_cache *bpf_get_kmem_cache(u64 addr) __ksym;
+
+/* Result, will be checked by userspace */
+int task_struct_found;
+int kmem_cache_seen;
+int open_coded_seen;
+
+SEC("iter/kmem_cache")
+int slab_info_collector(struct bpf_iter__kmem_cache *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct kmem_cache *s = ctx->s;
+	struct kmem_cache_result *r;
+	int idx;
+
+	if (s) {
+		/* To make sure if the slab_iter implements the seq interface
+		 * properly and it's also useful for debugging.
+		 */
+		BPF_SEQ_PRINTF(seq, "%s: %u\n", s->name, s->size);
+
+		idx = kmem_cache_seen;
+		r = bpf_map_lookup_elem(&slab_result, &idx);
+		if (r == NULL)
+			return 0;
+
+		kmem_cache_seen++;
+
+		/* Save name and size to match /proc/slabinfo */
+		bpf_probe_read_kernel_str(r->name, sizeof(r->name), s->name);
+		r->obj_size = s->size;
+
+		if (!bpf_strncmp(r->name, 11, "task_struct"))
+			bpf_map_update_elem(&slab_hash, &s, r->name, BPF_NOEXIST);
+	}
+
+	return 0;
+}
+
+SEC("raw_tp/bpf_test_finish")
+int BPF_PROG(check_task_struct)
+{
+	u64 curr = bpf_get_current_task();
+	struct kmem_cache *s;
+	char *name;
+
+	s = bpf_get_kmem_cache(curr);
+	if (s == NULL) {
+		task_struct_found = -1;
+		return 0;
+	}
+	name = bpf_map_lookup_elem(&slab_hash, &s);
+	if (name && !bpf_strncmp(name, 11, "task_struct"))
+		task_struct_found = 1;
+	else
+		task_struct_found = -2;
+	return 0;
+}
+
+SEC("syscall")
+int open_coded_iter(const void *ctx)
+{
+	struct kmem_cache *s;
+
+	bpf_for_each(kmem_cache, s) {
+		struct kmem_cache_result *r;
+
+		r = bpf_map_lookup_elem(&slab_result, &open_coded_seen);
+		if (!r)
+			break;
+
+		if (r->obj_size != s->size)
+			break;
+
+		open_coded_seen++;
+	}
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/kprobe_multi_override.c b/tools/testing/selftests/bpf/progs/kprobe_multi_override.c
new file mode 100644
index 000000000000..28f8487c9059
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/kprobe_multi_override.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+SEC("kprobe.multi")
+int test_override(struct pt_regs *ctx)
+{
+	bpf_override_return(ctx, 123);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/kprobe_multi_session.c b/tools/testing/selftests/bpf/progs/kprobe_multi_session.c
new file mode 100644
index 000000000000..bd8b7fb7061e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/kprobe_multi_session.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <stdbool.h>
+#include "bpf_kfuncs.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+extern const void bpf_fentry_test1 __ksym;
+extern const void bpf_fentry_test2 __ksym;
+extern const void bpf_fentry_test3 __ksym;
+extern const void bpf_fentry_test4 __ksym;
+extern const void bpf_fentry_test5 __ksym;
+extern const void bpf_fentry_test6 __ksym;
+extern const void bpf_fentry_test7 __ksym;
+extern const void bpf_fentry_test8 __ksym;
+
+int pid = 0;
+
+__u64 kprobe_session_result[8];
+
+static int session_check(void *ctx)
+{
+	unsigned int i;
+	__u64 addr;
+	const void *kfuncs[] = {
+		&bpf_fentry_test1,
+		&bpf_fentry_test2,
+		&bpf_fentry_test3,
+		&bpf_fentry_test4,
+		&bpf_fentry_test5,
+		&bpf_fentry_test6,
+		&bpf_fentry_test7,
+		&bpf_fentry_test8,
+	};
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 1;
+
+	addr = bpf_get_func_ip(ctx);
+
+	for (i = 0; i < ARRAY_SIZE(kfuncs); i++) {
+		if (kfuncs[i] == (void *) addr) {
+			kprobe_session_result[i]++;
+			break;
+		}
+	}
+
+	/*
+	 * Force probes for function bpf_fentry_test[5-8] not to
+	 * install and execute the return probe
+	 */
+	if (((const void *) addr == &bpf_fentry_test5) ||
+	    ((const void *) addr == &bpf_fentry_test6) ||
+	    ((const void *) addr == &bpf_fentry_test7) ||
+	    ((const void *) addr == &bpf_fentry_test8))
+		return 1;
+
+	return 0;
+}
+
+/*
+ * No tests in here, just to trigger 'bpf_fentry_test*'
+ * through tracing test_run
+ */
+SEC("fentry/bpf_modify_return_test")
+int BPF_PROG(trigger)
+{
+	return 0;
+}
+
+SEC("kprobe.session/bpf_fentry_test*")
+int test_kprobe(struct pt_regs *ctx)
+{
+	return session_check(ctx);
+}
diff --git a/tools/testing/selftests/bpf/progs/kprobe_multi_session_cookie.c b/tools/testing/selftests/bpf/progs/kprobe_multi_session_cookie.c
new file mode 100644
index 000000000000..0835b5edf685
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/kprobe_multi_session_cookie.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <stdbool.h>
+#include "bpf_kfuncs.h"
+
+char _license[] SEC("license") = "GPL";
+
+int pid = 0;
+
+__u64 test_kprobe_1_result = 0;
+__u64 test_kprobe_2_result = 0;
+__u64 test_kprobe_3_result = 0;
+
+/*
+ * No tests in here, just to trigger 'bpf_fentry_test*'
+ * through tracing test_run
+ */
+SEC("fentry/bpf_modify_return_test")
+int BPF_PROG(trigger)
+{
+	return 0;
+}
+
+static int check_cookie(__u64 val, __u64 *result)
+{
+	__u64 *cookie;
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 1;
+
+	cookie = bpf_session_cookie();
+
+	if (bpf_session_is_return())
+		*result = *cookie == val ? val : 0;
+	else
+		*cookie = val;
+	return 0;
+}
+
+SEC("kprobe.session/bpf_fentry_test1")
+int test_kprobe_1(struct pt_regs *ctx)
+{
+	return check_cookie(1, &test_kprobe_1_result);
+}
+
+SEC("kprobe.session/bpf_fentry_test1")
+int test_kprobe_2(struct pt_regs *ctx)
+{
+	return check_cookie(2, &test_kprobe_2_result);
+}
+
+SEC("kprobe.session/bpf_fentry_test1")
+int test_kprobe_3(struct pt_regs *ctx)
+{
+	return check_cookie(3, &test_kprobe_3_result);
+}
diff --git a/tools/testing/selftests/bpf/progs/kprobe_multi_verifier.c b/tools/testing/selftests/bpf/progs/kprobe_multi_verifier.c
new file mode 100644
index 000000000000..288577e81deb
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/kprobe_multi_verifier.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/usdt.bpf.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+
+SEC("kprobe.session")
+__success
+int kprobe_session_return_0(struct pt_regs *ctx)
+{
+	return 0;
+}
+
+SEC("kprobe.session")
+__success
+int kprobe_session_return_1(struct pt_regs *ctx)
+{
+	return 1;
+}
+
+SEC("kprobe.session")
+__failure
+__msg("At program exit the register R0 has smin=2 smax=2 should have been in [0, 1]")
+int kprobe_session_return_2(struct pt_regs *ctx)
+{
+	return 2;
+}
diff --git a/tools/testing/selftests/bpf/progs/kprobe_write_ctx.c b/tools/testing/selftests/bpf/progs/kprobe_write_ctx.c
new file mode 100644
index 000000000000..f77aef0474d3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/kprobe_write_ctx.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+#if defined(__TARGET_ARCH_x86)
+SEC("kprobe")
+int kprobe_write_ctx(struct pt_regs *ctx)
+{
+	ctx->ax = 0;
+	return 0;
+}
+
+SEC("kprobe.multi")
+int kprobe_multi_write_ctx(struct pt_regs *ctx)
+{
+	ctx->ax = 0;
+	return 0;
+}
+#endif
diff --git a/tools/testing/selftests/bpf/progs/kptr_xchg_inline.c b/tools/testing/selftests/bpf/progs/kptr_xchg_inline.c
new file mode 100644
index 000000000000..2414ac20b6d5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/kptr_xchg_inline.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <linux/types.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_experimental.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct bin_data {
+	char blob[32];
+};
+
+#define private(name) SEC(".bss." #name) __hidden __attribute__((aligned(8)))
+private(kptr) struct bin_data __kptr * ptr;
+
+SEC("tc")
+__naked int kptr_xchg_inline(void)
+{
+	asm volatile (
+		"r1 = %[ptr] ll;"
+		"r2 = 0;"
+		"call %[bpf_kptr_xchg];"
+		"if r0 == 0 goto 1f;"
+		"r1 = r0;"
+		"r2 = 0;"
+		"call %[bpf_obj_drop_impl];"
+	"1:"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm_addr(ptr),
+		  __imm(bpf_kptr_xchg),
+		  __imm(bpf_obj_drop_impl)
+		: __clobber_all
+	);
+}
+
+/* BTF FUNC records are not generated for kfuncs referenced
+ * from inline assembly. These records are necessary for
+ * libbpf to link the program. The function below is a hack
+ * to ensure that BTF FUNC records are generated.
+ */
+void __btf_root(void)
+{
+	bpf_obj_drop(NULL);
+}
diff --git a/tools/testing/selftests/bpf/progs/linked_funcs1.c b/tools/testing/selftests/bpf/progs/linked_funcs1.c
index b05571bc67d5..049a1f78de3f 100644
--- a/tools/testing/selftests/bpf/progs/linked_funcs1.c
+++ b/tools/testing/selftests/bpf/progs/linked_funcs1.c
@@ -5,9 +5,10 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include <bpf/bpf_core_read.h>
+#include "bpf_misc.h"
 
 /* weak and shared between two files */
-const volatile int my_tid __weak;
+const volatile __u32 my_tid __weak;
 long syscall_id __weak;
 
 int output_val1;
@@ -51,6 +52,7 @@ __weak int set_output_weak(int x)
 	 * cause problems for BPF static linker
 	 */
 	whatever = bpf_core_type_size(struct task_struct);
+	__sink(whatever);
 
 	output_weak1 = x;
 	return x;
@@ -61,6 +63,8 @@ extern int set_output_val2(int x);
 /* here we'll force set_output_ctx2() to be __hidden in the final obj file */
 __hidden extern void set_output_ctx2(__u64 *ctx);
 
+void *bpf_cast_to_kern_ctx(void *obj) __ksym;
+
 SEC("?raw_tp/sys_enter")
 int BPF_PROG(handler1, struct pt_regs *regs, long id)
 {
@@ -71,6 +75,7 @@ int BPF_PROG(handler1, struct pt_regs *regs, long id)
 
 	/* make sure we have CO-RE relocations in main program */
 	whatever = bpf_core_type_size(struct task_struct);
+	__sink(whatever);
 
 	set_output_val2(1000);
 	set_output_ctx2(ctx); /* ctx definition is hidden in BPF_PROG macro */
@@ -83,4 +88,10 @@ int BPF_PROG(handler1, struct pt_regs *regs, long id)
 	return 0;
 }
 
+/* Generate BTF FUNC record and test linking with duplicate extern functions */
+void kfunc_gen1(void)
+{
+	bpf_cast_to_kern_ctx(0);
+}
+
 char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/linked_funcs2.c b/tools/testing/selftests/bpf/progs/linked_funcs2.c
index ee7e3848ee4f..96850759fd8d 100644
--- a/tools/testing/selftests/bpf/progs/linked_funcs2.c
+++ b/tools/testing/selftests/bpf/progs/linked_funcs2.c
@@ -5,6 +5,7 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include <bpf/bpf_core_read.h>
+#include "bpf_misc.h"
 
 /* weak and shared between both files */
 const volatile int my_tid __weak;
@@ -51,6 +52,7 @@ __weak int set_output_weak(int x)
 	 * cause problems for BPF static linker
 	 */
 	whatever = 2 * bpf_core_type_size(struct task_struct);
+	__sink(whatever);
 
 	output_weak2 = x;
 	return 2 * x;
@@ -61,16 +63,19 @@ extern int set_output_val1(int x);
 /* here we'll force set_output_ctx1() to be __hidden in the final obj file */
 __hidden extern void set_output_ctx1(__u64 *ctx);
 
+void *bpf_cast_to_kern_ctx(void *obj) __ksym;
+
 SEC("?raw_tp/sys_enter")
 int BPF_PROG(handler2, struct pt_regs *regs, long id)
 {
 	static volatile int whatever;
 
-	if (my_tid != (u32)bpf_get_current_pid_tgid() || id != syscall_id)
+	if (my_tid != (s32)bpf_get_current_pid_tgid() || id != syscall_id)
 		return 0;
 
 	/* make sure we have CO-RE relocations in main program */
 	whatever = bpf_core_type_size(struct task_struct);
+	__sink(whatever);
 
 	set_output_val1(2000);
 	set_output_ctx1(ctx); /* ctx definition is hidden in BPF_PROG macro */
@@ -83,4 +88,10 @@ int BPF_PROG(handler2, struct pt_regs *regs, long id)
 	return 0;
 }
 
+/* Generate BTF FUNC record and test linking with duplicate extern functions */
+void kfunc_gen2(void)
+{
+	bpf_cast_to_kern_ctx(0);
+}
+
 char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/linked_list.c b/tools/testing/selftests/bpf/progs/linked_list.c
index 4ad88da5cda2..421f40835acd 100644
--- a/tools/testing/selftests/bpf/progs/linked_list.c
+++ b/tools/testing/selftests/bpf/progs/linked_list.c
@@ -4,13 +4,26 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_core_read.h>
 #include "bpf_experimental.h"
-
-#ifndef ARRAY_SIZE
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-#endif
+#include "bpf_misc.h"
 
 #include "linked_list.h"
 
+struct head_nested_inner {
+	struct bpf_spin_lock lock;
+	struct bpf_list_head head __contains(foo, node2);
+};
+
+struct head_nested {
+	int dummy;
+	struct head_nested_inner inner;
+};
+
+private(C) struct bpf_spin_lock glock_c;
+private(C) struct bpf_list_head ghead_array[2] __contains(foo, node2);
+private(C) struct bpf_list_head ghead_array_one[1] __contains(foo, node2);
+
+private(D) struct head_nested ghead_nested;
+
 static __always_inline
 int list_push_pop(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool leave_in_map)
 {
@@ -25,7 +38,7 @@ int list_push_pop(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool l
 	n = bpf_list_pop_front(head);
 	bpf_spin_unlock(lock);
 	if (n) {
-		bpf_obj_drop(container_of(n, struct foo, node));
+		bpf_obj_drop(container_of(n, struct foo, node2));
 		bpf_obj_drop(f);
 		return 3;
 	}
@@ -34,7 +47,7 @@ int list_push_pop(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool l
 	n = bpf_list_pop_back(head);
 	bpf_spin_unlock(lock);
 	if (n) {
-		bpf_obj_drop(container_of(n, struct foo, node));
+		bpf_obj_drop(container_of(n, struct foo, node2));
 		bpf_obj_drop(f);
 		return 4;
 	}
@@ -42,7 +55,7 @@ int list_push_pop(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool l
 
 	bpf_spin_lock(lock);
 	f->data = 42;
-	bpf_list_push_front(head, &f->node);
+	bpf_list_push_front(head, &f->node2);
 	bpf_spin_unlock(lock);
 	if (leave_in_map)
 		return 0;
@@ -51,7 +64,7 @@ int list_push_pop(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool l
 	bpf_spin_unlock(lock);
 	if (!n)
 		return 5;
-	f = container_of(n, struct foo, node);
+	f = container_of(n, struct foo, node2);
 	if (f->data != 42) {
 		bpf_obj_drop(f);
 		return 6;
@@ -59,14 +72,14 @@ int list_push_pop(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool l
 
 	bpf_spin_lock(lock);
 	f->data = 13;
-	bpf_list_push_front(head, &f->node);
+	bpf_list_push_front(head, &f->node2);
 	bpf_spin_unlock(lock);
 	bpf_spin_lock(lock);
 	n = bpf_list_pop_front(head);
 	bpf_spin_unlock(lock);
 	if (!n)
 		return 7;
-	f = container_of(n, struct foo, node);
+	f = container_of(n, struct foo, node2);
 	if (f->data != 13) {
 		bpf_obj_drop(f);
 		return 8;
@@ -77,7 +90,7 @@ int list_push_pop(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool l
 	n = bpf_list_pop_front(head);
 	bpf_spin_unlock(lock);
 	if (n) {
-		bpf_obj_drop(container_of(n, struct foo, node));
+		bpf_obj_drop(container_of(n, struct foo, node2));
 		return 9;
 	}
 
@@ -85,7 +98,7 @@ int list_push_pop(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool l
 	n = bpf_list_pop_back(head);
 	bpf_spin_unlock(lock);
 	if (n) {
-		bpf_obj_drop(container_of(n, struct foo, node));
+		bpf_obj_drop(container_of(n, struct foo, node2));
 		return 10;
 	}
 	return 0;
@@ -96,7 +109,7 @@ static __always_inline
 int list_push_pop_multiple(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool leave_in_map)
 {
 	struct bpf_list_node *n;
-	struct foo *f[8], *pf;
+	struct foo *f[200], *pf;
 	int i;
 
 	/* Loop following this check adds nodes 2-at-a-time in order to
@@ -119,8 +132,8 @@ int list_push_pop_multiple(struct bpf_spin_lock *lock, struct bpf_list_head *hea
 		f[i + 1]->data = i + 1;
 
 		bpf_spin_lock(lock);
-		bpf_list_push_front(head, &f[i]->node);
-		bpf_list_push_front(head, &f[i + 1]->node);
+		bpf_list_push_front(head, &f[i]->node2);
+		bpf_list_push_front(head, &f[i + 1]->node2);
 		bpf_spin_unlock(lock);
 	}
 
@@ -130,13 +143,13 @@ int list_push_pop_multiple(struct bpf_spin_lock *lock, struct bpf_list_head *hea
 		bpf_spin_unlock(lock);
 		if (!n)
 			return 3;
-		pf = container_of(n, struct foo, node);
+		pf = container_of(n, struct foo, node2);
 		if (pf->data != (ARRAY_SIZE(f) - i - 1)) {
 			bpf_obj_drop(pf);
 			return 4;
 		}
 		bpf_spin_lock(lock);
-		bpf_list_push_back(head, &pf->node);
+		bpf_list_push_back(head, &pf->node2);
 		bpf_spin_unlock(lock);
 	}
 
@@ -149,7 +162,7 @@ int list_push_pop_multiple(struct bpf_spin_lock *lock, struct bpf_list_head *hea
 		bpf_spin_unlock(lock);
 		if (!n)
 			return 5;
-		pf = container_of(n, struct foo, node);
+		pf = container_of(n, struct foo, node2);
 		if (pf->data != i) {
 			bpf_obj_drop(pf);
 			return 6;
@@ -160,7 +173,7 @@ int list_push_pop_multiple(struct bpf_spin_lock *lock, struct bpf_list_head *hea
 	n = bpf_list_pop_back(head);
 	bpf_spin_unlock(lock);
 	if (n) {
-		bpf_obj_drop(container_of(n, struct foo, node));
+		bpf_obj_drop(container_of(n, struct foo, node2));
 		return 7;
 	}
 
@@ -168,7 +181,7 @@ int list_push_pop_multiple(struct bpf_spin_lock *lock, struct bpf_list_head *hea
 	n = bpf_list_pop_front(head);
 	bpf_spin_unlock(lock);
 	if (n) {
-		bpf_obj_drop(container_of(n, struct foo, node));
+		bpf_obj_drop(container_of(n, struct foo, node2));
 		return 8;
 	}
 	return 0;
@@ -199,7 +212,7 @@ int list_in_list(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool le
 
 	bpf_spin_lock(lock);
 	f->data = 42;
-	bpf_list_push_front(head, &f->node);
+	bpf_list_push_front(head, &f->node2);
 	bpf_spin_unlock(lock);
 
 	if (leave_in_map)
@@ -210,7 +223,7 @@ int list_in_list(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool le
 	bpf_spin_unlock(lock);
 	if (!n)
 		return 4;
-	f = container_of(n, struct foo, node);
+	f = container_of(n, struct foo, node2);
 	if (f->data != 42) {
 		bpf_obj_drop(f);
 		return 5;
@@ -260,7 +273,7 @@ int test_list_push_pop_multiple(struct bpf_spin_lock *lock, struct bpf_list_head
 {
 	int ret;
 
-	ret = list_push_pop_multiple(lock ,head, false);
+	ret = list_push_pop_multiple(lock, head, false);
 	if (ret)
 		return ret;
 	return list_push_pop_multiple(lock, head, true);
@@ -310,10 +323,35 @@ int global_list_push_pop(void *ctx)
 }
 
 SEC("tc")
+int global_list_push_pop_nested(void *ctx)
+{
+	return test_list_push_pop(&ghead_nested.inner.lock, &ghead_nested.inner.head);
+}
+
+SEC("tc")
+int global_list_array_push_pop(void *ctx)
+{
+	int r;
+
+	r = test_list_push_pop(&glock_c, &ghead_array[0]);
+	if (r)
+		return r;
+
+	r = test_list_push_pop(&glock_c, &ghead_array[1]);
+	if (r)
+		return r;
+
+	/* Arrays with only one element is a special case, being treated
+	 * just like a bpf_list_head variable by the verifier, not an
+	 * array.
+	 */
+	return test_list_push_pop(&glock_c, &ghead_array_one[0]);
+}
+
+SEC("tc")
 int map_list_push_pop_multiple(void *ctx)
 {
 	struct map_value *v;
-	int ret;
 
 	v = bpf_map_lookup_elem(&array_map, &(int){0});
 	if (!v)
@@ -326,7 +364,6 @@ int inner_map_list_push_pop_multiple(void *ctx)
 {
 	struct map_value *v;
 	void *map;
-	int ret;
 
 	map = bpf_map_lookup_elem(&map_of_maps, &(int){0});
 	if (!map)
@@ -352,7 +389,6 @@ SEC("tc")
 int map_list_in_list(void *ctx)
 {
 	struct map_value *v;
-	int ret;
 
 	v = bpf_map_lookup_elem(&array_map, &(int){0});
 	if (!v)
@@ -365,7 +401,6 @@ int inner_map_list_in_list(void *ctx)
 {
 	struct map_value *v;
 	void *map;
-	int ret;
 
 	map = bpf_map_lookup_elem(&map_of_maps, &(int){0});
 	if (!map)
diff --git a/tools/testing/selftests/bpf/progs/linked_list.h b/tools/testing/selftests/bpf/progs/linked_list.h
index 3fb2412552fc..c0f3609a7ffa 100644
--- a/tools/testing/selftests/bpf/progs/linked_list.h
+++ b/tools/testing/selftests/bpf/progs/linked_list.h
@@ -22,7 +22,7 @@ struct foo {
 struct map_value {
 	struct bpf_spin_lock lock;
 	int data;
-	struct bpf_list_head head __contains(foo, node);
+	struct bpf_list_head head __contains(foo, node2);
 };
 
 struct array_map {
@@ -50,7 +50,7 @@ struct {
 #define private(name) SEC(".bss." #name) __hidden __attribute__((aligned(8)))
 
 private(A) struct bpf_spin_lock glock;
-private(A) struct bpf_list_head ghead __contains(foo, node);
+private(A) struct bpf_list_head ghead __contains(foo, node2);
 private(B) struct bpf_spin_lock glock2;
 
 #endif
diff --git a/tools/testing/selftests/bpf/progs/linked_list_fail.c b/tools/testing/selftests/bpf/progs/linked_list_fail.c
index 1d9017240e19..ddd26d1a083f 100644
--- a/tools/testing/selftests/bpf/progs/linked_list_fail.c
+++ b/tools/testing/selftests/bpf/progs/linked_list_fail.c
@@ -54,28 +54,43 @@
 		return 0;                                   \
 	}
 
-CHECK(kptr, push_front, &f->head);
-CHECK(kptr, push_back, &f->head);
 CHECK(kptr, pop_front, &f->head);
 CHECK(kptr, pop_back, &f->head);
 
-CHECK(global, push_front, &ghead);
-CHECK(global, push_back, &ghead);
 CHECK(global, pop_front, &ghead);
 CHECK(global, pop_back, &ghead);
 
-CHECK(map, push_front, &v->head);
-CHECK(map, push_back, &v->head);
 CHECK(map, pop_front, &v->head);
 CHECK(map, pop_back, &v->head);
 
-CHECK(inner_map, push_front, &iv->head);
-CHECK(inner_map, push_back, &iv->head);
 CHECK(inner_map, pop_front, &iv->head);
 CHECK(inner_map, pop_back, &iv->head);
 
 #undef CHECK
 
+#define CHECK(test, op, hexpr, nexpr)					\
+	SEC("?tc")							\
+	int test##_missing_lock_##op(void *ctx)				\
+	{								\
+		INIT;							\
+		bpf_list_##op(hexpr, nexpr);				\
+		return 0;						\
+	}
+
+CHECK(kptr, push_front, &f->head, &b->node);
+CHECK(kptr, push_back, &f->head, &b->node);
+
+CHECK(global, push_front, &ghead, &f->node2);
+CHECK(global, push_back, &ghead, &f->node2);
+
+CHECK(map, push_front, &v->head, &f->node2);
+CHECK(map, push_back, &v->head, &f->node2);
+
+CHECK(inner_map, push_front, &iv->head, &f->node2);
+CHECK(inner_map, push_back, &iv->head, &f->node2);
+
+#undef CHECK
+
 #define CHECK(test, op, lexpr, hexpr)                       \
 	SEC("?tc")                                          \
 	int test##_incorrect_lock_##op(void *ctx)           \
@@ -108,13 +123,48 @@ CHECK(inner_map, pop_back, &iv->head);
 	CHECK(inner_map_global, op, &iv->lock, &ghead);        \
 	CHECK(inner_map_map, op, &iv->lock, &v->head);
 
-CHECK_OP(push_front);
-CHECK_OP(push_back);
 CHECK_OP(pop_front);
 CHECK_OP(pop_back);
 
 #undef CHECK
 #undef CHECK_OP
+
+#define CHECK(test, op, lexpr, hexpr, nexpr)				\
+	SEC("?tc")							\
+	int test##_incorrect_lock_##op(void *ctx)			\
+	{								\
+		INIT;							\
+		bpf_spin_lock(lexpr);					\
+		bpf_list_##op(hexpr, nexpr);				\
+		return 0;						\
+	}
+
+#define CHECK_OP(op)							\
+	CHECK(kptr_kptr, op, &f1->lock, &f2->head, &b->node);		\
+	CHECK(kptr_global, op, &f1->lock, &ghead, &f->node2);		\
+	CHECK(kptr_map, op, &f1->lock, &v->head, &f->node2);		\
+	CHECK(kptr_inner_map, op, &f1->lock, &iv->head, &f->node2);	\
+									\
+	CHECK(global_global, op, &glock2, &ghead, &f->node2);		\
+	CHECK(global_kptr, op, &glock, &f1->head, &b->node);		\
+	CHECK(global_map, op, &glock, &v->head, &f->node2);		\
+	CHECK(global_inner_map, op, &glock, &iv->head, &f->node2);	\
+									\
+	CHECK(map_map, op, &v->lock, &v2->head, &f->node2);		\
+	CHECK(map_kptr, op, &v->lock, &f2->head, &b->node);		\
+	CHECK(map_global, op, &v->lock, &ghead, &f->node2);		\
+	CHECK(map_inner_map, op, &v->lock, &iv->head, &f->node2);	\
+									\
+	CHECK(inner_map_inner_map, op, &iv->lock, &iv2->head, &f->node2);\
+	CHECK(inner_map_kptr, op, &iv->lock, &f2->head, &b->node);	\
+	CHECK(inner_map_global, op, &iv->lock, &ghead, &f->node2);	\
+	CHECK(inner_map_map, op, &iv->lock, &v->head, &f->node2);
+
+CHECK_OP(push_front);
+CHECK_OP(push_back);
+
+#undef CHECK
+#undef CHECK_OP
 #undef INIT
 
 SEC("?kprobe/xyz")
@@ -176,8 +226,7 @@ int obj_new_no_composite(void *ctx)
 SEC("?tc")
 int obj_new_no_struct(void *ctx)
 {
-
-	bpf_obj_new(union { int data; unsigned udata; });
+	(void)bpf_obj_new(union { int data; unsigned udata; });
 	return 0;
 }
 
@@ -202,7 +251,7 @@ int new_null_ret(void *ctx)
 SEC("?tc")
 int obj_new_acq(void *ctx)
 {
-	bpf_obj_new(struct foo);
+	(void)bpf_obj_new(struct foo);
 	return 0;
 }
 
@@ -288,7 +337,7 @@ int direct_read_node(void *ctx)
 	f = bpf_obj_new(typeof(*f));
 	if (!f)
 		return 0;
-	return *(int *)&f->node;
+	return *(int *)&f->node2;
 }
 
 SEC("?tc")
@@ -299,12 +348,12 @@ int direct_write_node(void *ctx)
 	f = bpf_obj_new(typeof(*f));
 	if (!f)
 		return 0;
-	*(int *)&f->node = 0;
+	*(int *)&f->node2 = 0;
 	return 0;
 }
 
 static __always_inline
-int write_after_op(void (*push_op)(void *head, void *node))
+int use_after_unlock(bool push_front)
 {
 	struct foo *f;
 
@@ -312,36 +361,11 @@ int write_after_op(void (*push_op)(void *head, void *node))
 	if (!f)
 		return 0;
 	bpf_spin_lock(&glock);
-	push_op(&ghead, &f->node);
 	f->data = 42;
-	bpf_spin_unlock(&glock);
-
-	return 0;
-}
-
-SEC("?tc")
-int write_after_push_front(void *ctx)
-{
-	return write_after_op((void *)bpf_list_push_front);
-}
-
-SEC("?tc")
-int write_after_push_back(void *ctx)
-{
-	return write_after_op((void *)bpf_list_push_back);
-}
-
-static __always_inline
-int use_after_unlock(void (*op)(void *head, void *node))
-{
-	struct foo *f;
-
-	f = bpf_obj_new(typeof(*f));
-	if (!f)
-		return 0;
-	bpf_spin_lock(&glock);
-	f->data = 42;
-	op(&ghead, &f->node);
+	if (push_front)
+		bpf_list_push_front(&ghead, &f->node2);
+	else
+		bpf_list_push_back(&ghead, &f->node2);
 	bpf_spin_unlock(&glock);
 
 	return f->data;
@@ -350,17 +374,17 @@ int use_after_unlock(void (*op)(void *head, void *node))
 SEC("?tc")
 int use_after_unlock_push_front(void *ctx)
 {
-	return use_after_unlock((void *)bpf_list_push_front);
+	return use_after_unlock(true);
 }
 
 SEC("?tc")
 int use_after_unlock_push_back(void *ctx)
 {
-	return use_after_unlock((void *)bpf_list_push_back);
+	return use_after_unlock(false);
 }
 
 static __always_inline
-int list_double_add(void (*op)(void *head, void *node))
+int list_double_add(bool push_front)
 {
 	struct foo *f;
 
@@ -368,8 +392,13 @@ int list_double_add(void (*op)(void *head, void *node))
 	if (!f)
 		return 0;
 	bpf_spin_lock(&glock);
-	op(&ghead, &f->node);
-	op(&ghead, &f->node);
+	if (push_front) {
+		bpf_list_push_front(&ghead, &f->node2);
+		bpf_list_push_front(&ghead, &f->node2);
+	} else {
+		bpf_list_push_back(&ghead, &f->node2);
+		bpf_list_push_back(&ghead, &f->node2);
+	}
 	bpf_spin_unlock(&glock);
 
 	return 0;
@@ -378,13 +407,13 @@ int list_double_add(void (*op)(void *head, void *node))
 SEC("?tc")
 int double_push_front(void *ctx)
 {
-	return list_double_add((void *)bpf_list_push_front);
+	return list_double_add(true);
 }
 
 SEC("?tc")
 int double_push_back(void *ctx)
 {
-	return list_double_add((void *)bpf_list_push_back);
+	return list_double_add(false);
 }
 
 SEC("?tc")
@@ -426,7 +455,7 @@ int incorrect_node_var_off(struct __sk_buff *ctx)
 	if (!f)
 		return 0;
 	bpf_spin_lock(&glock);
-	bpf_list_push_front(&ghead, (void *)&f->node + ctx->protocol);
+	bpf_list_push_front(&ghead, (void *)&f->node2 + ctx->protocol);
 	bpf_spin_unlock(&glock);
 
 	return 0;
@@ -441,7 +470,7 @@ int incorrect_node_off1(void *ctx)
 	if (!f)
 		return 0;
 	bpf_spin_lock(&glock);
-	bpf_list_push_front(&ghead, (void *)&f->node + 1);
+	bpf_list_push_front(&ghead, (void *)&f->node2 + 1);
 	bpf_spin_unlock(&glock);
 
 	return 0;
@@ -456,7 +485,7 @@ int incorrect_node_off2(void *ctx)
 	if (!f)
 		return 0;
 	bpf_spin_lock(&glock);
-	bpf_list_push_front(&ghead, &f->node2);
+	bpf_list_push_front(&ghead, &f->node);
 	bpf_spin_unlock(&glock);
 
 	return 0;
@@ -486,7 +515,7 @@ int incorrect_head_var_off1(struct __sk_buff *ctx)
 	if (!f)
 		return 0;
 	bpf_spin_lock(&glock);
-	bpf_list_push_front((void *)&ghead + ctx->protocol, &f->node);
+	bpf_list_push_front((void *)&ghead + ctx->protocol, &f->node2);
 	bpf_spin_unlock(&glock);
 
 	return 0;
@@ -501,7 +530,7 @@ int incorrect_head_var_off2(struct __sk_buff *ctx)
 	if (!f)
 		return 0;
 	bpf_spin_lock(&glock);
-	bpf_list_push_front((void *)&f->head + ctx->protocol, &f->node);
+	bpf_list_push_front((void *)&f->head + ctx->protocol, &f->node2);
 	bpf_spin_unlock(&glock);
 
 	return 0;
@@ -533,14 +562,13 @@ SEC("?tc")
 int incorrect_head_off2(void *ctx)
 {
 	struct foo *f;
-	struct bar *b;
 
 	f = bpf_obj_new(typeof(*f));
 	if (!f)
 		return 0;
 
 	bpf_spin_lock(&glock);
-	bpf_list_push_front((void *)&ghead + 1, &f->node);
+	bpf_list_push_front((void *)&ghead + 1, &f->node2);
 	bpf_spin_unlock(&glock);
 
 	return 0;
@@ -562,7 +590,9 @@ int pop_ptr_off(void *(*op)(void *head))
 	n = op(&p->head);
 	bpf_spin_unlock(&p->lock);
 
-	bpf_this_cpu_ptr(n);
+	if (!n)
+		return 0;
+	bpf_spin_lock((void *)n);
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/linked_list_peek.c b/tools/testing/selftests/bpf/progs/linked_list_peek.c
new file mode 100644
index 000000000000..264e81bfb287
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/linked_list_peek.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+struct node_data {
+	struct bpf_list_node l;
+	int key;
+};
+
+#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8)))
+private(A) struct bpf_spin_lock glock;
+private(A) struct bpf_list_head ghead __contains(node_data, l);
+
+#define list_entry(ptr, type, member) container_of(ptr, type, member)
+#define NR_NODES 16
+
+int zero = 0;
+
+SEC("syscall")
+__retval(0)
+long list_peek(void *ctx)
+{
+	struct bpf_list_node *l_n;
+	struct node_data *n;
+	int i, err = 0;
+
+	bpf_spin_lock(&glock);
+	l_n = bpf_list_front(&ghead);
+	bpf_spin_unlock(&glock);
+	if (l_n)
+		return __LINE__;
+
+	bpf_spin_lock(&glock);
+	l_n = bpf_list_back(&ghead);
+	bpf_spin_unlock(&glock);
+	if (l_n)
+		return __LINE__;
+
+	for (i = zero; i < NR_NODES && can_loop; i++) {
+		n = bpf_obj_new(typeof(*n));
+		if (!n)
+			return __LINE__;
+		n->key = i;
+		bpf_spin_lock(&glock);
+		bpf_list_push_back(&ghead, &n->l);
+		bpf_spin_unlock(&glock);
+	}
+
+	bpf_spin_lock(&glock);
+
+	l_n = bpf_list_front(&ghead);
+	if (!l_n) {
+		err = __LINE__;
+		goto done;
+	}
+
+	n = list_entry(l_n, struct node_data, l);
+	if (n->key != 0) {
+		err = __LINE__;
+		goto done;
+	}
+
+	l_n = bpf_list_back(&ghead);
+	if (!l_n) {
+		err = __LINE__;
+		goto done;
+	}
+
+	n = list_entry(l_n, struct node_data, l);
+	if (n->key != NR_NODES - 1) {
+		err = __LINE__;
+		goto done;
+	}
+
+done:
+	bpf_spin_unlock(&glock);
+	return err;
+}
+
+#define TEST_FB(op, dolock)					\
+SEC("syscall")							\
+__failure __msg(MSG)						\
+long test_##op##_spinlock_##dolock(void *ctx)			\
+{								\
+	struct bpf_list_node *l_n;				\
+	__u64 jiffies = 0;					\
+								\
+	if (dolock)						\
+		bpf_spin_lock(&glock);				\
+	l_n = bpf_list_##op(&ghead);				\
+	if (l_n)						\
+		jiffies = bpf_jiffies64();			\
+	if (dolock)						\
+		bpf_spin_unlock(&glock);			\
+								\
+	return !!jiffies;					\
+}
+
+#define MSG "call bpf_list_{{(front|back).+}}; R0{{(_w)?}}=ptr_or_null_node_data(id={{[0-9]+}},non_own_ref"
+TEST_FB(front, true)
+TEST_FB(back, true)
+#undef MSG
+
+#define MSG "bpf_spin_lock at off=0 must be held for bpf_list_head"
+TEST_FB(front, false)
+TEST_FB(back, false)
+#undef MSG
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/livepatch_trampoline.c b/tools/testing/selftests/bpf/progs/livepatch_trampoline.c
new file mode 100644
index 000000000000..15579d5bcd91
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/livepatch_trampoline.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+int fentry_hit;
+int fexit_hit;
+int my_pid;
+
+SEC("fentry/cmdline_proc_show")
+int BPF_PROG(fentry_cmdline)
+{
+	if (my_pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	fentry_hit = 1;
+	return 0;
+}
+
+SEC("fexit/cmdline_proc_show")
+int BPF_PROG(fexit_cmdline)
+{
+	if (my_pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	fexit_hit = 1;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/local_kptr_stash.c b/tools/testing/selftests/bpf/progs/local_kptr_stash.c
new file mode 100644
index 000000000000..d736506a4c80
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/local_kptr_stash.c
@@ -0,0 +1,285 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "../bpf_experimental.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+struct plain_local;
+
+struct node_data {
+	long key;
+	long data;
+	struct plain_local __kptr * stashed_in_local_kptr;
+	struct bpf_rb_node node;
+};
+
+struct refcounted_node {
+	long data;
+	struct bpf_rb_node rb_node;
+	struct bpf_refcount refcount;
+};
+
+struct stash {
+	struct bpf_spin_lock l;
+	struct refcounted_node __kptr *stashed;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct stash);
+	__uint(max_entries, 10);
+} refcounted_node_stash SEC(".maps");
+
+struct plain_local {
+	long key;
+	long data;
+};
+
+struct local_with_root {
+	long key;
+	struct bpf_spin_lock l;
+	struct bpf_rb_root r __contains(node_data, node);
+};
+
+struct map_value {
+	struct prog_test_ref_kfunc *not_kptr;
+	struct prog_test_ref_kfunc __kptr *val;
+	struct node_data __kptr *node;
+	struct plain_local __kptr *plain;
+	struct local_with_root __kptr *local_root;
+};
+
+/* This is necessary so that LLVM generates BTF for node_data struct
+ * If it's not included, a fwd reference for node_data will be generated but
+ * no struct. Example BTF of "node" field in map_value when not included:
+ *
+ * [10] PTR '(anon)' type_id=35
+ * [34] FWD 'node_data' fwd_kind=struct
+ * [35] TYPE_TAG 'kptr_ref' type_id=34
+ *
+ * (with no node_data struct defined)
+ * Had to do the same w/ bpf_kfunc_call_test_release below
+ */
+struct node_data *just_here_because_btf_bug;
+struct refcounted_node *just_here_because_btf_bug2;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 2);
+} some_nodes SEC(".maps");
+
+static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	struct node_data *node_a;
+	struct node_data *node_b;
+
+	node_a = container_of(a, struct node_data, node);
+	node_b = container_of(b, struct node_data, node);
+
+	return node_a->key < node_b->key;
+}
+
+static int create_and_stash(int idx, int val)
+{
+	struct plain_local *inner_local_kptr;
+	struct map_value *mapval;
+	struct node_data *res;
+
+	mapval = bpf_map_lookup_elem(&some_nodes, &idx);
+	if (!mapval)
+		return 1;
+
+	inner_local_kptr = bpf_obj_new(typeof(*inner_local_kptr));
+	if (!inner_local_kptr)
+		return 2;
+
+	res = bpf_obj_new(typeof(*res));
+	if (!res) {
+		bpf_obj_drop(inner_local_kptr);
+		return 3;
+	}
+	res->key = val;
+
+	inner_local_kptr = bpf_kptr_xchg(&res->stashed_in_local_kptr, inner_local_kptr);
+	if (inner_local_kptr) {
+		/* Should never happen, we just obj_new'd res */
+		bpf_obj_drop(inner_local_kptr);
+		bpf_obj_drop(res);
+		return 4;
+	}
+
+	res = bpf_kptr_xchg(&mapval->node, res);
+	if (res)
+		bpf_obj_drop(res);
+	return 0;
+}
+
+SEC("tc")
+long stash_rb_nodes(void *ctx)
+{
+	return create_and_stash(0, 41) ?: create_and_stash(1, 42);
+}
+
+SEC("tc")
+long stash_plain(void *ctx)
+{
+	struct map_value *mapval;
+	struct plain_local *res;
+	int idx = 0;
+
+	mapval = bpf_map_lookup_elem(&some_nodes, &idx);
+	if (!mapval)
+		return 1;
+
+	res = bpf_obj_new(typeof(*res));
+	if (!res)
+		return 1;
+	res->key = 41;
+
+	res = bpf_kptr_xchg(&mapval->plain, res);
+	if (res)
+		bpf_obj_drop(res);
+	return 0;
+}
+
+SEC("tc")
+long stash_local_with_root(void *ctx)
+{
+	struct local_with_root *res;
+	struct map_value *mapval;
+	struct node_data *n;
+	int idx = 0;
+
+	mapval = bpf_map_lookup_elem(&some_nodes, &idx);
+	if (!mapval)
+		return 1;
+
+	res = bpf_obj_new(typeof(*res));
+	if (!res)
+		return 2;
+	res->key = 41;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n) {
+		bpf_obj_drop(res);
+		return 3;
+	}
+
+	bpf_spin_lock(&res->l);
+	bpf_rbtree_add(&res->r, &n->node, less);
+	bpf_spin_unlock(&res->l);
+
+	res = bpf_kptr_xchg(&mapval->local_root, res);
+	if (res) {
+		bpf_obj_drop(res);
+		return 4;
+	}
+	return 0;
+}
+
+SEC("tc")
+long unstash_rb_node(void *ctx)
+{
+	struct plain_local *inner_local_kptr = NULL;
+	struct map_value *mapval;
+	struct node_data *res;
+	long retval;
+	int key = 1;
+
+	mapval = bpf_map_lookup_elem(&some_nodes, &key);
+	if (!mapval)
+		return 1;
+
+	res = bpf_kptr_xchg(&mapval->node, NULL);
+	if (res) {
+		inner_local_kptr = bpf_kptr_xchg(&res->stashed_in_local_kptr, inner_local_kptr);
+		if (!inner_local_kptr) {
+			bpf_obj_drop(res);
+			return 1;
+		}
+		bpf_obj_drop(inner_local_kptr);
+
+		retval = res->key;
+		bpf_obj_drop(res);
+		return retval;
+	}
+	return 1;
+}
+
+SEC("tc")
+long stash_test_ref_kfunc(void *ctx)
+{
+	struct prog_test_ref_kfunc *res;
+	struct map_value *mapval;
+	int key = 0;
+
+	mapval = bpf_map_lookup_elem(&some_nodes, &key);
+	if (!mapval)
+		return 1;
+
+	res = bpf_kptr_xchg(&mapval->val, NULL);
+	if (res)
+		bpf_kfunc_call_test_release(res);
+	return 0;
+}
+
+SEC("tc")
+long refcount_acquire_without_unstash(void *ctx)
+{
+	struct refcounted_node *p;
+	struct stash *s;
+	int ret = 0;
+
+	s = bpf_map_lookup_elem(&refcounted_node_stash, &ret);
+	if (!s)
+		return 1;
+
+	if (!s->stashed)
+		/* refcount_acquire failure is expected when no refcounted_node
+		 * has been stashed before this program executes
+		 */
+		return 2;
+
+	p = bpf_refcount_acquire(s->stashed);
+	if (!p)
+		return 3;
+
+	ret = s->stashed ? s->stashed->data : -1;
+	bpf_obj_drop(p);
+	return ret;
+}
+
+/* Helper for refcount_acquire_without_unstash test */
+SEC("tc")
+long stash_refcounted_node(void *ctx)
+{
+	struct refcounted_node *p;
+	struct stash *s;
+	int key = 0;
+
+	s = bpf_map_lookup_elem(&refcounted_node_stash, &key);
+	if (!s)
+		return 1;
+
+	p = bpf_obj_new(typeof(*p));
+	if (!p)
+		return 2;
+	p->data = 42;
+
+	p = bpf_kptr_xchg(&s->stashed, p);
+	if (p) {
+		bpf_obj_drop(p);
+		return 3;
+	}
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/local_kptr_stash_fail.c b/tools/testing/selftests/bpf/progs/local_kptr_stash_fail.c
new file mode 100644
index 000000000000..fcf7a7567da2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/local_kptr_stash_fail.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include "../bpf_experimental.h"
+#include "bpf_misc.h"
+
+struct node_data {
+	long key;
+	long data;
+	struct bpf_rb_node node;
+};
+
+struct map_value {
+	struct node_data __kptr *node;
+};
+
+struct node_data2 {
+	long key[4];
+};
+
+/* This is necessary so that LLVM generates BTF for node_data struct
+ * If it's not included, a fwd reference for node_data will be generated but
+ * no struct. Example BTF of "node" field in map_value when not included:
+ *
+ * [10] PTR '(anon)' type_id=35
+ * [34] FWD 'node_data' fwd_kind=struct
+ * [35] TYPE_TAG 'kptr_ref' type_id=34
+ */
+struct node_data *just_here_because_btf_bug;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 2);
+} some_nodes SEC(".maps");
+
+SEC("tc")
+__failure __msg("invalid kptr access, R2 type=ptr_node_data2 expected=ptr_node_data")
+long stash_rb_nodes(void *ctx)
+{
+	struct map_value *mapval;
+	struct node_data2 *res;
+	int idx = 0;
+
+	mapval = bpf_map_lookup_elem(&some_nodes, &idx);
+	if (!mapval)
+		return 1;
+
+	res = bpf_obj_new(typeof(*res));
+	if (!res)
+		return 1;
+	res->key[0] = 40;
+
+	res = bpf_kptr_xchg(&mapval->node, res);
+	if (res)
+		bpf_obj_drop(res);
+	return 0;
+}
+
+SEC("tc")
+__failure __msg("R1 must have zero offset when passed to release func")
+long drop_rb_node_off(void *ctx)
+{
+	struct map_value *mapval;
+	struct node_data *res;
+	int idx = 0;
+
+	mapval = bpf_map_lookup_elem(&some_nodes, &idx);
+	if (!mapval)
+		return 1;
+
+	res = bpf_obj_new(typeof(*res));
+	if (!res)
+		return 1;
+	/* Try releasing with graph node offset */
+	bpf_obj_drop(&res->node);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/local_storage.c b/tools/testing/selftests/bpf/progs/local_storage.c
index 19423ed862e3..637e75df2e14 100644
--- a/tools/testing/selftests/bpf/progs/local_storage.c
+++ b/tools/testing/selftests/bpf/progs/local_storage.c
@@ -13,9 +13,10 @@ char _license[] SEC("license") = "GPL";
 
 #define DUMMY_STORAGE_VALUE 0xdeadbeef
 
-int monitored_pid = 0;
+__u32 monitored_pid = 0;
 int inode_storage_result = -1;
 int sk_storage_result = -1;
+int task_storage_result = -1;
 
 struct local_storage {
 	struct inode *exec_inode;
@@ -50,26 +51,57 @@ struct {
 	__type(value, struct local_storage);
 } task_storage_map SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct local_storage);
+} task_storage_map2 SEC(".maps");
+
 SEC("lsm/inode_unlink")
 int BPF_PROG(unlink_hook, struct inode *dir, struct dentry *victim)
 {
 	__u32 pid = bpf_get_current_pid_tgid() >> 32;
+	struct bpf_local_storage *local_storage;
 	struct local_storage *storage;
+	struct task_struct *task;
 	bool is_self_unlink;
 
 	if (pid != monitored_pid)
 		return 0;
 
-	storage = bpf_task_storage_get(&task_storage_map,
-				       bpf_get_current_task_btf(), 0, 0);
-	if (storage) {
-		/* Don't let an executable delete itself */
-		is_self_unlink = storage->exec_inode == victim->d_inode;
-		if (is_self_unlink)
-			return -EPERM;
-	}
+	task = bpf_get_current_task_btf();
+	if (!task)
+		return 0;
 
-	return 0;
+	task_storage_result = -1;
+
+	storage = bpf_task_storage_get(&task_storage_map, task, 0, 0);
+	if (!storage)
+		return 0;
+
+	/* Don't let an executable delete itself */
+	is_self_unlink = storage->exec_inode == victim->d_inode;
+
+	storage = bpf_task_storage_get(&task_storage_map2, task, 0,
+				       BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (!storage || storage->value)
+		return 0;
+
+	if (bpf_task_storage_delete(&task_storage_map, task))
+		return 0;
+
+	/* Ensure that the task_storage_map is disconnected from the storage.
+	 * The storage memory should not be freed back to the
+	 * bpf_mem_alloc.
+	 */
+	local_storage = task->bpf_storage;
+	if (!local_storage || local_storage->smap)
+		return 0;
+
+	task_storage_result = 0;
+
+	return is_self_unlink ? -EPERM : 0;
 }
 
 SEC("lsm.s/inode_rename")
@@ -77,7 +109,6 @@ int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry,
 	     struct inode *new_dir, struct dentry *new_dentry,
 	     unsigned int flags)
 {
-	__u32 pid = bpf_get_current_pid_tgid() >> 32;
 	struct local_storage *storage;
 	int err;
 
@@ -109,35 +140,43 @@ int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address,
 {
 	__u32 pid = bpf_get_current_pid_tgid() >> 32;
 	struct local_storage *storage;
-	int err;
+	struct sock *sk = sock->sk;
 
-	if (pid != monitored_pid)
+	if (pid != monitored_pid || !sk)
 		return 0;
 
-	storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0,
-				     BPF_LOCAL_STORAGE_GET_F_CREATE);
+	storage = bpf_sk_storage_get(&sk_storage_map, sk, 0, 0);
 	if (!storage)
 		return 0;
 
+	sk_storage_result = -1;
 	if (storage->value != DUMMY_STORAGE_VALUE)
-		sk_storage_result = -1;
+		return 0;
 
 	/* This tests that we can associate multiple elements
 	 * with the local storage.
 	 */
-	storage = bpf_sk_storage_get(&sk_storage_map2, sock->sk, 0,
+	storage = bpf_sk_storage_get(&sk_storage_map2, sk, 0,
 				     BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!storage)
 		return 0;
 
-	err = bpf_sk_storage_delete(&sk_storage_map, sock->sk);
-	if (err)
+	if (bpf_sk_storage_delete(&sk_storage_map2, sk))
 		return 0;
 
-	err = bpf_sk_storage_delete(&sk_storage_map2, sock->sk);
-	if (!err)
-		sk_storage_result = err;
+	storage = bpf_sk_storage_get(&sk_storage_map2, sk, 0,
+				     BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (!storage)
+		return 0;
 
+	if (bpf_sk_storage_delete(&sk_storage_map, sk))
+		return 0;
+
+	/* Ensure that the sk_storage_map is disconnected from the storage. */
+	if (!sk->sk_bpf_storage || sk->sk_bpf_storage->smap)
+		return 0;
+
+	sk_storage_result = 0;
 	return 0;
 }
 
@@ -147,11 +186,12 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family, int type,
 {
 	__u32 pid = bpf_get_current_pid_tgid() >> 32;
 	struct local_storage *storage;
+	struct sock *sk = sock->sk;
 
-	if (pid != monitored_pid)
+	if (pid != monitored_pid || !sk)
 		return 0;
 
-	storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0,
+	storage = bpf_sk_storage_get(&sk_storage_map, sk, 0,
 				     BPF_LOCAL_STORAGE_GET_F_CREATE);
 	if (!storage)
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/loop1.c b/tools/testing/selftests/bpf/progs/loop1.c
index 50e66772c046..b0fa26fb4760 100644
--- a/tools/testing/selftests/bpf/progs/loop1.c
+++ b/tools/testing/selftests/bpf/progs/loop1.c
@@ -1,11 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2019 Facebook
-#include <linux/sched.h>
-#include <linux/ptrace.h>
-#include <stdint.h>
-#include <stddef.h>
-#include <stdbool.h>
-#include <linux/bpf.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
diff --git a/tools/testing/selftests/bpf/progs/loop2.c b/tools/testing/selftests/bpf/progs/loop2.c
index 947bb7e988c2..0227409d4b0e 100644
--- a/tools/testing/selftests/bpf/progs/loop2.c
+++ b/tools/testing/selftests/bpf/progs/loop2.c
@@ -1,11 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2019 Facebook
-#include <linux/sched.h>
-#include <linux/ptrace.h>
-#include <stdint.h>
-#include <stddef.h>
-#include <stdbool.h>
-#include <linux/bpf.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
diff --git a/tools/testing/selftests/bpf/progs/loop3.c b/tools/testing/selftests/bpf/progs/loop3.c
index 717dab14322b..5d1c9a775e6b 100644
--- a/tools/testing/selftests/bpf/progs/loop3.c
+++ b/tools/testing/selftests/bpf/progs/loop3.c
@@ -1,11 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2019 Facebook
-#include <linux/sched.h>
-#include <linux/ptrace.h>
-#include <stdint.h>
-#include <stddef.h>
-#include <stdbool.h>
-#include <linux/bpf.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
diff --git a/tools/testing/selftests/bpf/progs/loop4.c b/tools/testing/selftests/bpf/progs/loop4.c
index b35337926d66..0de0357f57cc 100644
--- a/tools/testing/selftests/bpf/progs/loop4.c
+++ b/tools/testing/selftests/bpf/progs/loop4.c
@@ -3,6 +3,8 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
+#include "bpf_compiler.h"
+
 char _license[] SEC("license") = "GPL";
 
 SEC("socket")
@@ -10,7 +12,7 @@ int combinations(volatile struct __sk_buff* skb)
 {
 	int ret = 0, i;
 
-#pragma nounroll
+	__pragma_loop_no_unroll
 	for (i = 0; i < 20; i++)
 		if (skb->len)
 			ret |= 1 << i;
diff --git a/tools/testing/selftests/bpf/progs/loop6.c b/tools/testing/selftests/bpf/progs/loop6.c
index 38de0331e6b4..dd36aff4fba3 100644
--- a/tools/testing/selftests/bpf/progs/loop6.c
+++ b/tools/testing/selftests/bpf/progs/loop6.c
@@ -1,10 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <linux/ptrace.h>
-#include <stddef.h>
-#include <linux/bpf.h>
+#include <vmlinux.h>
+#include <bpf/bpf_core_read.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
 
 char _license[] SEC("license") = "GPL";
 
@@ -25,12 +25,6 @@ char _license[] SEC("license") = "GPL";
 #define SG_CHAIN	0x01UL
 #define SG_END		0x02UL
 
-struct scatterlist {
-	unsigned long   page_link;
-	unsigned int    offset;
-	unsigned int    length;
-};
-
 #define sg_is_chain(sg)		((sg)->page_link & SG_CHAIN)
 #define sg_is_last(sg)		((sg)->page_link & SG_END)
 #define sg_chain_ptr(sg)	\
@@ -61,7 +55,7 @@ static inline struct scatterlist *get_sgp(struct scatterlist **sgs, int i)
 	return sgp;
 }
 
-int config = 0;
+int run_once = 0;
 int result = 0;
 
 SEC("kprobe/virtqueue_add_sgs")
@@ -72,28 +66,30 @@ int BPF_KPROBE(trace_virtqueue_add_sgs, void *unused, struct scatterlist **sgs,
 	__u64 length1 = 0, length2 = 0;
 	unsigned int i, n, len;
 
-	if (config != 0)
+	if (run_once != 0)
 		return 0;
 
 	for (i = 0; (i < VIRTIO_MAX_SGS) && (i < out_sgs); i++) {
+		__sink(out_sgs);
 		for (n = 0, sgp = get_sgp(sgs, i); sgp && (n < SG_MAX);
 		     sgp = __sg_next(sgp)) {
-			bpf_probe_read_kernel(&len, sizeof(len), &sgp->length);
+			len = BPF_CORE_READ(sgp, length);
 			length1 += len;
 			n++;
 		}
 	}
 
 	for (i = 0; (i < VIRTIO_MAX_SGS) && (i < in_sgs); i++) {
+		__sink(in_sgs);
 		for (n = 0, sgp = get_sgp(sgs, i); sgp && (n < SG_MAX);
 		     sgp = __sg_next(sgp)) {
-			bpf_probe_read_kernel(&len, sizeof(len), &sgp->length);
+			len = BPF_CORE_READ(sgp, length);
 			length2 += len;
 			n++;
 		}
 	}
 
-	config = 1;
+	run_once = 1;
 	result = length2 - length1;
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/lpm_trie.h b/tools/testing/selftests/bpf/progs/lpm_trie.h
new file mode 100644
index 000000000000..76aa5821807f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/lpm_trie.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __PROGS_LPM_TRIE_H
+#define __PROGS_LPM_TRIE_H
+
+struct trie_key {
+	__u32 prefixlen;
+	__u32 data;
+};
+
+/* Benchmark operations */
+enum {
+	LPM_OP_NOOP = 0,
+	LPM_OP_BASELINE,
+	LPM_OP_LOOKUP,
+	LPM_OP_INSERT,
+	LPM_OP_UPDATE,
+	LPM_OP_DELETE,
+	LPM_OP_FREE
+};
+
+/*
+ * Return values from run_bench.
+ *
+ * Negative values are also allowed and represent kernel error codes.
+ */
+#define LPM_BENCH_SUCCESS	0
+#define LPM_BENCH_REINIT_MAP 	1	/* Reset trie to initial state for current op */
+
+#endif
diff --git a/tools/testing/selftests/bpf/progs/lpm_trie_bench.c b/tools/testing/selftests/bpf/progs/lpm_trie_bench.c
new file mode 100644
index 000000000000..a0e6ebd5507a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/lpm_trie_bench.c
@@ -0,0 +1,230 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Cloudflare */
+
+#include <vmlinux.h>
+#include <errno.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_misc.h"
+#include "bpf_atomic.h"
+#include "progs/lpm_trie.h"
+
+#define BPF_OBJ_NAME_LEN 16U
+#define MAX_ENTRIES 100000000
+#define NR_LOOPS 10000
+
+char _license[] SEC("license") = "GPL";
+
+/* Filled by userspace. See fill_map() in bench_lpm_trie_map.c */
+struct {
+	__uint(type, BPF_MAP_TYPE_LPM_TRIE);
+	__type(key, struct trie_key);
+	__type(value, __u32);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__uint(max_entries, MAX_ENTRIES);
+} trie_map SEC(".maps");
+
+long hits;
+long duration_ns;
+
+/* Configured from userspace */
+__u32 nr_entries;
+__u32 prefixlen;
+bool random;
+__u8 op;
+
+static __u64 latency_free_start;
+
+SEC("fentry/bpf_map_free_deferred")
+int BPF_PROG(trie_free_entry, struct work_struct *work)
+{
+	struct bpf_map *map = container_of(work, struct bpf_map, work);
+	char name[BPF_OBJ_NAME_LEN];
+	u32 map_type;
+
+	map_type = BPF_CORE_READ(map, map_type);
+	if (map_type != BPF_MAP_TYPE_LPM_TRIE)
+		return 0;
+
+	/*
+	 * Ideally we'd have access to the map ID but that's already
+	 * freed before we enter trie_free().
+	 */
+	BPF_CORE_READ_STR_INTO(&name, map, name);
+	if (bpf_strncmp(name, BPF_OBJ_NAME_LEN, "trie_free_map"))
+		return 0;
+
+	latency_free_start = bpf_ktime_get_ns();
+
+	return 0;
+}
+
+SEC("fexit/bpf_map_free_deferred")
+int BPF_PROG(trie_free_exit, struct work_struct *work)
+{
+	__u64 val;
+
+	if (!latency_free_start)
+		return 0;
+
+	val = bpf_ktime_get_ns() - latency_free_start;
+	latency_free_start = 0;
+
+	__sync_add_and_fetch(&duration_ns, val);
+	__sync_add_and_fetch(&hits, 1);
+
+	return 0;
+}
+
+static __u32 cur_key;
+
+static __always_inline void generate_key(struct trie_key *key)
+{
+	key->prefixlen = prefixlen;
+
+	if (random)
+		key->data = bpf_get_prandom_u32() % nr_entries;
+	else
+		key->data = cur_key++ % nr_entries;
+}
+
+static int noop(__u32 index, __u32 *unused)
+{
+	return 0;
+}
+
+static int baseline(__u32 index, __u32 *unused)
+{
+	struct trie_key key;
+	__u32 blackbox = 0;
+
+	generate_key(&key);
+	/* Avoid compiler optimizing out the modulo */
+	barrier_var(blackbox);
+	blackbox = READ_ONCE(key.data);
+
+	return 0;
+}
+
+static int lookup(__u32 index, int *retval)
+{
+	struct trie_key key;
+
+	generate_key(&key);
+	if (!bpf_map_lookup_elem(&trie_map, &key)) {
+		*retval = -ENOENT;
+		return 1;
+	}
+
+	return 0;
+}
+
+static int insert(__u32 index, int *retval)
+{
+	struct trie_key key;
+	u32 val = 1;
+	int err;
+
+	generate_key(&key);
+	err = bpf_map_update_elem(&trie_map, &key, &val, BPF_NOEXIST);
+	if (err) {
+		*retval = err;
+		return 1;
+	}
+
+	/* Is this the last entry? */
+	if (key.data == nr_entries - 1) {
+		/* For atomicity concerns, see the comment in delete() */
+		*retval = LPM_BENCH_REINIT_MAP;
+		return 1;
+	}
+
+	return 0;
+}
+
+static int update(__u32 index, int *retval)
+{
+	struct trie_key key;
+	u32 val = 1;
+	int err;
+
+	generate_key(&key);
+	err = bpf_map_update_elem(&trie_map, &key, &val, BPF_EXIST);
+	if (err) {
+		*retval = err;
+		return 1;
+	}
+
+	return 0;
+}
+
+static int delete(__u32 index, int *retval)
+{
+	struct trie_key key;
+	int err;
+
+	generate_key(&key);
+	err = bpf_map_delete_elem(&trie_map, &key);
+	if (err) {
+		*retval = err;
+		return 1;
+	}
+
+	/* Do we need to refill the map? */
+	if (key.data == nr_entries - 1) {
+		/*
+		 * Atomicity isn't required because DELETE only supports
+		 * one producer running concurrently. What we need is a
+		 * way to track how many entries have been deleted from
+		 * the trie between consecutive invocations of the BPF
+		 * prog because a single bpf_loop() call might not
+		 * delete all entries, e.g. when NR_LOOPS < nr_entries.
+		 */
+		*retval = LPM_BENCH_REINIT_MAP;
+		return 1;
+	}
+
+	return 0;
+}
+
+SEC("xdp")
+int BPF_PROG(run_bench)
+{
+	int err = LPM_BENCH_SUCCESS;
+	u64 start, delta;
+	int loops;
+
+	start = bpf_ktime_get_ns();
+
+	switch (op) {
+	case LPM_OP_NOOP:
+		loops = bpf_loop(NR_LOOPS, noop, NULL, 0);
+		break;
+	case LPM_OP_BASELINE:
+		loops = bpf_loop(NR_LOOPS, baseline, NULL, 0);
+		break;
+	case LPM_OP_LOOKUP:
+		loops = bpf_loop(NR_LOOPS, lookup, &err, 0);
+		break;
+	case LPM_OP_INSERT:
+		loops = bpf_loop(NR_LOOPS, insert, &err, 0);
+		break;
+	case LPM_OP_UPDATE:
+		loops = bpf_loop(NR_LOOPS, update, &err, 0);
+		break;
+	case LPM_OP_DELETE:
+		loops = bpf_loop(NR_LOOPS, delete, &err, 0);
+		break;
+	default:
+		bpf_printk("invalid benchmark operation\n");
+		return -1;
+	}
+
+	delta = bpf_ktime_get_ns() - start;
+
+	__sync_add_and_fetch(&duration_ns, delta);
+	__sync_add_and_fetch(&hits, loops);
+
+	return err;
+}
diff --git a/tools/testing/selftests/bpf/progs/lpm_trie_map.c b/tools/testing/selftests/bpf/progs/lpm_trie_map.c
new file mode 100644
index 000000000000..6e60d686b664
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/lpm_trie_map.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#define MAX_ENTRIES 100000000
+
+struct trie_key {
+	__u32 prefixlen;
+	__u32 data;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_LPM_TRIE);
+	__type(key, struct trie_key);
+	__type(value, __u32);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__uint(max_entries, MAX_ENTRIES);
+} trie_free_map SEC(".maps");
diff --git a/tools/testing/selftests/bpf/progs/lru_bug.c b/tools/testing/selftests/bpf/progs/lru_bug.c
index 687081a724b3..ad73029cb1e3 100644
--- a/tools/testing/selftests/bpf/progs/lru_bug.c
+++ b/tools/testing/selftests/bpf/progs/lru_bug.c
@@ -4,7 +4,7 @@
 #include <bpf/bpf_helpers.h>
 
 struct map_value {
-	struct task_struct __kptr *ptr;
+	struct task_struct __kptr_untrusted *ptr;
 };
 
 struct {
diff --git a/tools/testing/selftests/bpf/progs/lsm.c b/tools/testing/selftests/bpf/progs/lsm.c
index d8d8af623bc2..7de173daf27b 100644
--- a/tools/testing/selftests/bpf/progs/lsm.c
+++ b/tools/testing/selftests/bpf/progs/lsm.c
@@ -4,11 +4,12 @@
  * Copyright 2020 Google LLC.
  */
 
-#include "bpf_misc.h"
 #include "vmlinux.h"
+#include <errno.h>
+#include <bpf/bpf_core_read.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
-#include  <errno.h>
+#include "bpf_misc.h"
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
@@ -88,14 +89,16 @@ SEC("lsm/file_mprotect")
 int BPF_PROG(test_int_hook, struct vm_area_struct *vma,
 	     unsigned long reqprot, unsigned long prot, int ret)
 {
-	if (ret != 0)
+	struct mm_struct *mm = vma->vm_mm;
+
+	if (ret != 0 || !mm)
 		return ret;
 
-	__u32 pid = bpf_get_current_pid_tgid() >> 32;
+	__s32 pid = bpf_get_current_pid_tgid() >> 32;
 	int is_stack = 0;
 
-	is_stack = (vma->vm_start <= vma->vm_mm->start_stack &&
-		    vma->vm_end >= vma->vm_mm->start_stack);
+	is_stack = (vma->vm_start <= mm->start_stack &&
+		    vma->vm_end >= mm->start_stack);
 
 	if (is_stack && monitored_pid == pid) {
 		mprotect_count++;
@@ -164,8 +167,8 @@ int copy_test = 0;
 SEC("fentry.s/" SYS_PREFIX "sys_setdomainname")
 int BPF_PROG(test_sys_setdomainname, struct pt_regs *regs)
 {
-	void *ptr = (void *)PT_REGS_PARM1(regs);
-	int len = PT_REGS_PARM2(regs);
+	void *ptr = (void *)PT_REGS_PARM1_SYSCALL(regs);
+	int len = PT_REGS_PARM2_SYSCALL(regs);
 	int buf = 0;
 	long ret;
 
diff --git a/tools/testing/selftests/bpf/progs/lsm_cgroup.c b/tools/testing/selftests/bpf/progs/lsm_cgroup.c
index 02c11d16b692..d7598538aa2d 100644
--- a/tools/testing/selftests/bpf/progs/lsm_cgroup.c
+++ b/tools/testing/selftests/bpf/progs/lsm_cgroup.c
@@ -103,11 +103,15 @@ static __always_inline int real_bind(struct socket *sock,
 				     int addrlen)
 {
 	struct sockaddr_ll sa = {};
+	struct sock *sk = sock->sk;
 
-	if (sock->sk->__sk_common.skc_family != AF_PACKET)
+	if (!sk)
+		return 1;
+
+	if (sk->__sk_common.skc_family != AF_PACKET)
 		return 1;
 
-	if (sock->sk->sk_kern_sock)
+	if (sk->sk_kern_sock)
 		return 1;
 
 	bpf_probe_read_kernel(&sa, sizeof(sa), address);
diff --git a/tools/testing/selftests/bpf/progs/lsm_tailcall.c b/tools/testing/selftests/bpf/progs/lsm_tailcall.c
new file mode 100644
index 000000000000..6e7e58051e64
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/lsm_tailcall.c
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Huawei Technologies Co., Ltd */
+
+#include "vmlinux.h"
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+SEC("lsm/file_permission")
+int lsm_file_permission_prog(void *ctx)
+{
+	return 0;
+}
+
+SEC("lsm/kernfs_init_security")
+int lsm_kernfs_init_security_prog(void *ctx)
+{
+	return 0;
+}
+
+SEC("lsm/kernfs_init_security")
+int lsm_kernfs_init_security_entry(void *ctx)
+{
+	bpf_tail_call_static(ctx, &jmp_table, 0);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/map_excl.c b/tools/testing/selftests/bpf/progs/map_excl.c
new file mode 100644
index 000000000000..d461684728e4
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/map_excl.c
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2025 Google LLC. */
+#include <linux/bpf.h>
+#include <time.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, __u32);
+	__type(value, __u32);
+	__uint(max_entries, 1);
+} excl_map SEC(".maps");
+
+char _license[] SEC("license") = "GPL";
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int should_have_access(void *ctx)
+{
+	int key = 0, value = 0xdeadbeef;
+
+	bpf_map_update_elem(&excl_map, &key, &value, 0);
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int should_not_have_access(void *ctx)
+{
+	int key = 0, value = 0xdeadbeef;
+
+	bpf_map_update_elem(&excl_map, &key, &value, 0);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/map_in_map_btf.c b/tools/testing/selftests/bpf/progs/map_in_map_btf.c
new file mode 100644
index 000000000000..7a1336d7b16a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/map_in_map_btf.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+struct node_data {
+	__u64 data;
+	struct bpf_list_node node;
+};
+
+struct map_value {
+	struct bpf_list_head head __contains(node_data, node);
+	struct bpf_spin_lock lock;
+};
+
+struct inner_array_type {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 1);
+} inner_array SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__uint(key_size, 4);
+	__uint(value_size, 4);
+	__uint(max_entries, 1);
+	__array(values, struct inner_array_type);
+} outer_array SEC(".maps") = {
+	.values = {
+		[0] = &inner_array,
+	},
+};
+
+char _license[] SEC("license") = "GPL";
+
+int pid = 0;
+bool done = false;
+
+SEC("fentry/" SYS_PREFIX "sys_nanosleep")
+int add_to_list_in_inner_array(void *ctx)
+{
+	struct map_value *value;
+	struct node_data *new;
+	struct bpf_map *map;
+	int zero = 0;
+
+	if (done || (u32)bpf_get_current_pid_tgid() != pid)
+		return 0;
+
+	map = bpf_map_lookup_elem(&outer_array, &zero);
+	if (!map)
+		return 0;
+
+	value = bpf_map_lookup_elem(map, &zero);
+	if (!value)
+		return 0;
+
+	new = bpf_obj_new(typeof(*new));
+	if (!new)
+		return 0;
+
+	bpf_spin_lock(&value->lock);
+	bpf_list_push_back(&value->head, &new->node);
+	bpf_spin_unlock(&value->lock);
+	done = true;
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/map_kptr.c b/tools/testing/selftests/bpf/progs/map_kptr.c
index eb8217803493..edaba481db9d 100644
--- a/tools/testing/selftests/bpf/progs/map_kptr.c
+++ b/tools/testing/selftests/bpf/progs/map_kptr.c
@@ -2,10 +2,11 @@
 #include <vmlinux.h>
 #include <bpf/bpf_tracing.h>
 #include <bpf/bpf_helpers.h>
+#include "../test_kmods/bpf_testmod_kfunc.h"
 
 struct map_value {
-	struct prog_test_ref_kfunc __kptr *unref_ptr;
-	struct prog_test_ref_kfunc __kptr_ref *ref_ptr;
+	struct prog_test_ref_kfunc __kptr_untrusted *unref_ptr;
+	struct prog_test_ref_kfunc __kptr *ref_ptr;
 };
 
 struct array_map {
@@ -15,6 +16,13 @@ struct array_map {
 	__uint(max_entries, 1);
 } array_map SEC(".maps");
 
+struct pcpu_array_map {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 1);
+} pcpu_array_map SEC(".maps");
+
 struct hash_map {
 	__uint(type, BPF_MAP_TYPE_HASH);
 	__type(key, int);
@@ -22,6 +30,13 @@ struct hash_map {
 	__uint(max_entries, 1);
 } hash_map SEC(".maps");
 
+struct pcpu_hash_map {
+	__uint(type, BPF_MAP_TYPE_PERCPU_HASH);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 1);
+} pcpu_hash_map SEC(".maps");
+
 struct hash_malloc_map {
 	__uint(type, BPF_MAP_TYPE_HASH);
 	__type(key, int);
@@ -30,6 +45,14 @@ struct hash_malloc_map {
 	__uint(map_flags, BPF_F_NO_PREALLOC);
 } hash_malloc_map SEC(".maps");
 
+struct pcpu_hash_malloc_map {
+	__uint(type, BPF_MAP_TYPE_PERCPU_HASH);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 1);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+} pcpu_hash_malloc_map SEC(".maps");
+
 struct lru_hash_map {
 	__uint(type, BPF_MAP_TYPE_LRU_HASH);
 	__type(key, int);
@@ -37,6 +60,41 @@ struct lru_hash_map {
 	__uint(max_entries, 1);
 } lru_hash_map SEC(".maps");
 
+struct lru_pcpu_hash_map {
+	__uint(type, BPF_MAP_TYPE_LRU_PERCPU_HASH);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 1);
+} lru_pcpu_hash_map SEC(".maps");
+
+struct cgrp_ls_map {
+	__uint(type, BPF_MAP_TYPE_CGRP_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct map_value);
+} cgrp_ls_map SEC(".maps");
+
+struct task_ls_map {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct map_value);
+} task_ls_map SEC(".maps");
+
+struct inode_ls_map {
+	__uint(type, BPF_MAP_TYPE_INODE_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct map_value);
+} inode_ls_map SEC(".maps");
+
+struct sk_ls_map {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct map_value);
+} sk_ls_map SEC(".maps");
+
 #define DEFINE_MAP_OF_MAP(map_type, inner_map_type, name)       \
 	struct {                                                \
 		__uint(type, map_type);                         \
@@ -52,15 +110,16 @@ DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_map, array_of_array_maps);
 DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_ARRAY_OF_MAPS, hash_map, array_of_hash_maps);
 DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_ARRAY_OF_MAPS, hash_malloc_map, array_of_hash_malloc_maps);
 DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_ARRAY_OF_MAPS, lru_hash_map, array_of_lru_hash_maps);
+DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_ARRAY_OF_MAPS, pcpu_array_map, array_of_pcpu_array_maps);
+DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_ARRAY_OF_MAPS, pcpu_hash_map, array_of_pcpu_hash_maps);
 DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, array_map, hash_of_array_maps);
 DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, hash_map, hash_of_hash_maps);
 DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, hash_malloc_map, hash_of_hash_malloc_maps);
 DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, lru_hash_map, hash_of_lru_hash_maps);
+DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, pcpu_array_map, hash_of_pcpu_array_maps);
+DEFINE_MAP_OF_MAP(BPF_MAP_TYPE_HASH_OF_MAPS, pcpu_hash_map, hash_of_pcpu_hash_maps);
 
-extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym;
-extern struct prog_test_ref_kfunc *
-bpf_kfunc_call_test_kptr_get(struct prog_test_ref_kfunc **p, int a, int b) __ksym;
-extern void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym;
+#define WRITE_ONCE(x, val) ((*(volatile typeof(x) *) &(x)) = (val))
 
 static void test_kptr_unref(struct map_value *v)
 {
@@ -68,15 +127,15 @@ static void test_kptr_unref(struct map_value *v)
 
 	p = v->unref_ptr;
 	/* store untrusted_ptr_or_null_ */
-	v->unref_ptr = p;
+	WRITE_ONCE(v->unref_ptr, p);
 	if (!p)
 		return;
 	if (p->a + p->b > 100)
 		return;
 	/* store untrusted_ptr_ */
-	v->unref_ptr = p;
+	WRITE_ONCE(v->unref_ptr, p);
 	/* store NULL */
-	v->unref_ptr = NULL;
+	WRITE_ONCE(v->unref_ptr, NULL);
 }
 
 static void test_kptr_ref(struct map_value *v)
@@ -85,21 +144,32 @@ static void test_kptr_ref(struct map_value *v)
 
 	p = v->ref_ptr;
 	/* store ptr_or_null_ */
-	v->unref_ptr = p;
+	WRITE_ONCE(v->unref_ptr, p);
 	if (!p)
 		return;
+	/*
+	 * p is rcu_ptr_prog_test_ref_kfunc,
+	 * because bpf prog is non-sleepable and runs in RCU CS.
+	 * p can be passed to kfunc that requires KF_RCU.
+	 */
+	bpf_kfunc_call_test_ref(p);
 	if (p->a + p->b > 100)
 		return;
 	/* store NULL */
 	p = bpf_kptr_xchg(&v->ref_ptr, NULL);
 	if (!p)
 		return;
+	/*
+	 * p is trusted_ptr_prog_test_ref_kfunc.
+	 * p can be passed to kfunc that requires KF_RCU.
+	 */
+	bpf_kfunc_call_test_ref(p);
 	if (p->a + p->b > 100) {
 		bpf_kfunc_call_test_release(p);
 		return;
 	}
 	/* store ptr_ */
-	v->unref_ptr = p;
+	WRITE_ONCE(v->unref_ptr, p);
 	bpf_kfunc_call_test_release(p);
 
 	p = bpf_kfunc_call_test_acquire(&(unsigned long){0});
@@ -116,25 +186,10 @@ static void test_kptr_ref(struct map_value *v)
 	bpf_kfunc_call_test_release(p);
 }
 
-static void test_kptr_get(struct map_value *v)
-{
-	struct prog_test_ref_kfunc *p;
-
-	p = bpf_kfunc_call_test_kptr_get(&v->ref_ptr, 0, 0);
-	if (!p)
-		return;
-	if (p->a + p->b > 100) {
-		bpf_kfunc_call_test_release(p);
-		return;
-	}
-	bpf_kfunc_call_test_release(p);
-}
-
 static void test_kptr(struct map_value *v)
 {
 	test_kptr_unref(v);
 	test_kptr_ref(v);
-	test_kptr_get(v);
 }
 
 SEC("tc")
@@ -153,11 +208,65 @@ int test_map_kptr(struct __sk_buff *ctx)
 	TEST(hash_map);
 	TEST(hash_malloc_map);
 	TEST(lru_hash_map);
+	TEST(pcpu_array_map);
+	TEST(pcpu_hash_map);
 
 #undef TEST
 	return 0;
 }
 
+SEC("tp_btf/cgroup_mkdir")
+int BPF_PROG(test_cgrp_map_kptr, struct cgroup *cgrp, const char *path)
+{
+	struct map_value *v;
+
+	v = bpf_cgrp_storage_get(&cgrp_ls_map, cgrp, NULL, BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (v)
+		test_kptr(v);
+	return 0;
+}
+
+SEC("lsm/inode_unlink")
+int BPF_PROG(test_task_map_kptr, struct inode *inode, struct dentry *victim)
+{
+	struct task_struct *task;
+	struct map_value *v;
+
+	task = bpf_get_current_task_btf();
+	if (!task)
+		return 0;
+	v = bpf_task_storage_get(&task_ls_map, task, NULL, BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (v)
+		test_kptr(v);
+	return 0;
+}
+
+SEC("lsm/inode_unlink")
+int BPF_PROG(test_inode_map_kptr, struct inode *inode, struct dentry *victim)
+{
+	struct map_value *v;
+
+	v = bpf_inode_storage_get(&inode_ls_map, inode, NULL, BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (v)
+		test_kptr(v);
+	return 0;
+}
+
+SEC("tc")
+int test_sk_map_kptr(struct __sk_buff *ctx)
+{
+	struct map_value *v;
+	struct bpf_sock *sk;
+
+	sk = ctx->sk;
+	if (!sk)
+		return 0;
+	v = bpf_sk_storage_get(&sk_ls_map, sk, NULL, BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (v)
+		test_kptr(v);
+	return 0;
+}
+
 SEC("tc")
 int test_map_in_map_kptr(struct __sk_buff *ctx)
 {
@@ -178,115 +287,254 @@ int test_map_in_map_kptr(struct __sk_buff *ctx)
 	TEST(array_of_hash_maps);
 	TEST(array_of_hash_malloc_maps);
 	TEST(array_of_lru_hash_maps);
+	TEST(array_of_pcpu_array_maps);
+	TEST(array_of_pcpu_hash_maps);
 	TEST(hash_of_array_maps);
 	TEST(hash_of_hash_maps);
 	TEST(hash_of_hash_malloc_maps);
 	TEST(hash_of_lru_hash_maps);
+	TEST(hash_of_pcpu_array_maps);
+	TEST(hash_of_pcpu_hash_maps);
 
 #undef TEST
 	return 0;
 }
 
-SEC("tc")
-int test_map_kptr_ref(struct __sk_buff *ctx)
+int ref = 1;
+
+static __always_inline
+int test_map_kptr_ref_pre(struct map_value *v)
 {
 	struct prog_test_ref_kfunc *p, *p_st;
 	unsigned long arg = 0;
-	struct map_value *v;
-	int key = 0, ret;
+	int ret;
 
 	p = bpf_kfunc_call_test_acquire(&arg);
 	if (!p)
 		return 1;
+	ref++;
 
 	p_st = p->next;
-	if (p_st->cnt.refs.counter != 2) {
+	if (p_st->cnt.refs.counter != ref) {
 		ret = 2;
 		goto end;
 	}
 
-	v = bpf_map_lookup_elem(&array_map, &key);
-	if (!v) {
-		ret = 3;
-		goto end;
-	}
-
 	p = bpf_kptr_xchg(&v->ref_ptr, p);
 	if (p) {
-		ret = 4;
-		goto end;
-	}
-	if (p_st->cnt.refs.counter != 2)
-		return 5;
-
-	p = bpf_kfunc_call_test_kptr_get(&v->ref_ptr, 0, 0);
-	if (!p)
-		return 6;
-	if (p_st->cnt.refs.counter != 3) {
-		ret = 7;
+		ret = 3;
 		goto end;
 	}
-	bpf_kfunc_call_test_release(p);
-	if (p_st->cnt.refs.counter != 2)
-		return 8;
+	if (p_st->cnt.refs.counter != ref)
+		return 4;
 
 	p = bpf_kptr_xchg(&v->ref_ptr, NULL);
 	if (!p)
-		return 9;
+		return 5;
 	bpf_kfunc_call_test_release(p);
-	if (p_st->cnt.refs.counter != 1)
-		return 10;
+	ref--;
+	if (p_st->cnt.refs.counter != ref)
+		return 6;
 
 	p = bpf_kfunc_call_test_acquire(&arg);
 	if (!p)
-		return 11;
+		return 7;
+	ref++;
 	p = bpf_kptr_xchg(&v->ref_ptr, p);
 	if (p) {
-		ret = 12;
+		ret = 8;
 		goto end;
 	}
-	if (p_st->cnt.refs.counter != 2)
-		return 13;
+	if (p_st->cnt.refs.counter != ref)
+		return 9;
 	/* Leave in map */
 
 	return 0;
 end:
+	ref--;
 	bpf_kfunc_call_test_release(p);
 	return ret;
 }
 
-SEC("tc")
-int test_map_kptr_ref2(struct __sk_buff *ctx)
+static __always_inline
+int test_map_kptr_ref_post(struct map_value *v)
 {
 	struct prog_test_ref_kfunc *p, *p_st;
-	struct map_value *v;
-	int key = 0;
-
-	v = bpf_map_lookup_elem(&array_map, &key);
-	if (!v)
-		return 1;
 
 	p_st = v->ref_ptr;
-	if (!p_st || p_st->cnt.refs.counter != 2)
-		return 2;
+	if (!p_st || p_st->cnt.refs.counter != ref)
+		return 1;
 
 	p = bpf_kptr_xchg(&v->ref_ptr, NULL);
 	if (!p)
-		return 3;
-	if (p_st->cnt.refs.counter != 2) {
+		return 2;
+	if (p_st->cnt.refs.counter != ref) {
 		bpf_kfunc_call_test_release(p);
-		return 4;
+		return 3;
 	}
 
 	p = bpf_kptr_xchg(&v->ref_ptr, p);
 	if (p) {
 		bpf_kfunc_call_test_release(p);
-		return 5;
+		return 4;
 	}
-	if (p_st->cnt.refs.counter != 2)
-		return 6;
+	if (p_st->cnt.refs.counter != ref)
+		return 5;
+
+	return 0;
+}
+
+#define TEST(map)                            \
+	v = bpf_map_lookup_elem(&map, &key); \
+	if (!v)                              \
+		return -1;                   \
+	ret = test_map_kptr_ref_pre(v);      \
+	if (ret)                             \
+		return ret;
+
+#define TEST_PCPU(map)                                 \
+	v = bpf_map_lookup_percpu_elem(&map, &key, 0); \
+	if (!v)                                        \
+		return -1;                             \
+	ret = test_map_kptr_ref_pre(v);                \
+	if (ret)                                       \
+		return ret;
+
+SEC("tc")
+int test_map_kptr_ref1(struct __sk_buff *ctx)
+{
+	struct map_value *v, val = {};
+	int key = 0, ret;
+
+	bpf_map_update_elem(&hash_map, &key, &val, 0);
+	bpf_map_update_elem(&hash_malloc_map, &key, &val, 0);
+	bpf_map_update_elem(&lru_hash_map, &key, &val, 0);
+
+	bpf_map_update_elem(&pcpu_hash_map, &key, &val, 0);
+	bpf_map_update_elem(&pcpu_hash_malloc_map, &key, &val, 0);
+	bpf_map_update_elem(&lru_pcpu_hash_map, &key, &val, 0);
+
+	TEST(array_map);
+	TEST(hash_map);
+	TEST(hash_malloc_map);
+	TEST(lru_hash_map);
+
+	TEST_PCPU(pcpu_array_map);
+	TEST_PCPU(pcpu_hash_map);
+	TEST_PCPU(pcpu_hash_malloc_map);
+	TEST_PCPU(lru_pcpu_hash_map);
+
+	return 0;
+}
+
+#undef TEST
+#undef TEST_PCPU
+
+#define TEST(map)                            \
+	v = bpf_map_lookup_elem(&map, &key); \
+	if (!v)                              \
+		return -1;                   \
+	ret = test_map_kptr_ref_post(v);     \
+	if (ret)                             \
+		return ret;
+
+#define TEST_PCPU(map)                                 \
+	v = bpf_map_lookup_percpu_elem(&map, &key, 0); \
+	if (!v)                                        \
+		return -1;                             \
+	ret = test_map_kptr_ref_post(v);               \
+	if (ret)                                       \
+		return ret;
+
+SEC("tc")
+int test_map_kptr_ref2(struct __sk_buff *ctx)
+{
+	struct map_value *v;
+	int key = 0, ret;
+
+	TEST(array_map);
+	TEST(hash_map);
+	TEST(hash_malloc_map);
+	TEST(lru_hash_map);
+
+	TEST_PCPU(pcpu_array_map);
+	TEST_PCPU(pcpu_hash_map);
+	TEST_PCPU(pcpu_hash_malloc_map);
+	TEST_PCPU(lru_pcpu_hash_map);
 
 	return 0;
 }
 
+#undef TEST
+#undef TEST_PCPU
+
+SEC("tc")
+int test_map_kptr_ref3(struct __sk_buff *ctx)
+{
+	struct prog_test_ref_kfunc *p;
+	unsigned long sp = 0;
+
+	p = bpf_kfunc_call_test_acquire(&sp);
+	if (!p)
+		return 1;
+	ref++;
+	if (p->cnt.refs.counter != ref) {
+		bpf_kfunc_call_test_release(p);
+		return 2;
+	}
+	bpf_kfunc_call_test_release(p);
+	ref--;
+	return 0;
+}
+
+SEC("syscall")
+int test_ls_map_kptr_ref1(void *ctx)
+{
+	struct task_struct *current;
+	struct map_value *v;
+
+	current = bpf_get_current_task_btf();
+	if (!current)
+		return 100;
+	v = bpf_task_storage_get(&task_ls_map, current, NULL, 0);
+	if (v)
+		return 150;
+	v = bpf_task_storage_get(&task_ls_map, current, NULL, BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (!v)
+		return 200;
+	return test_map_kptr_ref_pre(v);
+}
+
+SEC("syscall")
+int test_ls_map_kptr_ref2(void *ctx)
+{
+	struct task_struct *current;
+	struct map_value *v;
+
+	current = bpf_get_current_task_btf();
+	if (!current)
+		return 100;
+	v = bpf_task_storage_get(&task_ls_map, current, NULL, 0);
+	if (!v)
+		return 200;
+	return test_map_kptr_ref_post(v);
+}
+
+SEC("syscall")
+int test_ls_map_kptr_ref_del(void *ctx)
+{
+	struct task_struct *current;
+	struct map_value *v;
+
+	current = bpf_get_current_task_btf();
+	if (!current)
+		return 100;
+	v = bpf_task_storage_get(&task_ls_map, current, NULL, 0);
+	if (!v)
+		return 200;
+	if (!v->ref_ptr)
+		return 300;
+	return bpf_task_storage_delete(&task_ls_map, current);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/map_kptr_fail.c b/tools/testing/selftests/bpf/progs/map_kptr_fail.c
index 760e41e1a632..4c0ff01f1a96 100644
--- a/tools/testing/selftests/bpf/progs/map_kptr_fail.c
+++ b/tools/testing/selftests/bpf/progs/map_kptr_fail.c
@@ -4,12 +4,13 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_core_read.h>
 #include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
 
 struct map_value {
 	char buf[8];
-	struct prog_test_ref_kfunc __kptr *unref_ptr;
-	struct prog_test_ref_kfunc __kptr_ref *ref_ptr;
-	struct prog_test_member __kptr_ref *ref_memb_ptr;
+	struct prog_test_ref_kfunc __kptr_untrusted *unref_ptr;
+	struct prog_test_ref_kfunc __kptr *ref_ptr;
+	struct prog_test_member __kptr *ref_memb_ptr;
 };
 
 struct array_map {
@@ -19,10 +20,6 @@ struct array_map {
 	__uint(max_entries, 1);
 } array_map SEC(".maps");
 
-extern struct prog_test_ref_kfunc *bpf_kfunc_call_test_acquire(unsigned long *sp) __ksym;
-extern struct prog_test_ref_kfunc *
-bpf_kfunc_call_test_kptr_get(struct prog_test_ref_kfunc **p, int a, int b) __ksym;
-
 SEC("?tc")
 __failure __msg("kptr access size must be BPF_DW")
 int size_not_bpf_dw(struct __sk_buff *ctx)
@@ -220,68 +217,7 @@ int reject_kptr_xchg_on_unref(struct __sk_buff *ctx)
 }
 
 SEC("?tc")
-__failure __msg("arg#0 expected pointer to map value")
-int reject_kptr_get_no_map_val(struct __sk_buff *ctx)
-{
-	bpf_kfunc_call_test_kptr_get((void *)&ctx, 0, 0);
-	return 0;
-}
-
-SEC("?tc")
-__failure __msg("arg#0 expected pointer to map value")
-int reject_kptr_get_no_null_map_val(struct __sk_buff *ctx)
-{
-	bpf_kfunc_call_test_kptr_get(bpf_map_lookup_elem(&array_map, &(int){0}), 0, 0);
-	return 0;
-}
-
-SEC("?tc")
-__failure __msg("arg#0 no referenced kptr at map value offset=0")
-int reject_kptr_get_no_kptr(struct __sk_buff *ctx)
-{
-	struct map_value *v;
-	int key = 0;
-
-	v = bpf_map_lookup_elem(&array_map, &key);
-	if (!v)
-		return 0;
-
-	bpf_kfunc_call_test_kptr_get((void *)v, 0, 0);
-	return 0;
-}
-
-SEC("?tc")
-__failure __msg("arg#0 no referenced kptr at map value offset=8")
-int reject_kptr_get_on_unref(struct __sk_buff *ctx)
-{
-	struct map_value *v;
-	int key = 0;
-
-	v = bpf_map_lookup_elem(&array_map, &key);
-	if (!v)
-		return 0;
-
-	bpf_kfunc_call_test_kptr_get(&v->unref_ptr, 0, 0);
-	return 0;
-}
-
-SEC("?tc")
-__failure __msg("kernel function bpf_kfunc_call_test_kptr_get args#0")
-int reject_kptr_get_bad_type_match(struct __sk_buff *ctx)
-{
-	struct map_value *v;
-	int key = 0;
-
-	v = bpf_map_lookup_elem(&array_map, &key);
-	if (!v)
-		return 0;
-
-	bpf_kfunc_call_test_kptr_get((void *)&v->ref_memb_ptr, 0, 0);
-	return 0;
-}
-
-SEC("?tc")
-__failure __msg("R1 type=untrusted_ptr_or_null_ expected=percpu_ptr_")
+__failure __msg("R1 type=rcu_ptr_or_null_ expected=percpu_ptr_")
 int mark_ref_as_untrusted_or_null(struct __sk_buff *ctx)
 {
 	struct map_value *v;
@@ -316,7 +252,7 @@ int reject_untrusted_store_to_ref(struct __sk_buff *ctx)
 }
 
 SEC("?tc")
-__failure __msg("R2 type=untrusted_ptr_ expected=ptr_")
+__failure __msg("R2 must be referenced")
 int reject_untrusted_xchg(struct __sk_buff *ctx)
 {
 	struct prog_test_ref_kfunc *p;
@@ -409,7 +345,7 @@ int reject_indirect_global_func_access(struct __sk_buff *ctx)
 }
 
 SEC("?tc")
-__failure __msg("Unreleased reference id=5 alloc_insn=")
+__failure __msg("Unreleased reference id=4 alloc_insn=")
 int kptr_xchg_ref_state(struct __sk_buff *ctx)
 {
 	struct prog_test_ref_kfunc *p;
@@ -428,9 +364,10 @@ int kptr_xchg_ref_state(struct __sk_buff *ctx)
 }
 
 SEC("?tc")
-__failure __msg("Unreleased reference id=3 alloc_insn=")
-int kptr_get_ref_state(struct __sk_buff *ctx)
+__failure __msg("Possibly NULL pointer passed to helper arg2")
+int kptr_xchg_possibly_null(struct __sk_buff *ctx)
 {
+	struct prog_test_ref_kfunc *p;
 	struct map_value *v;
 	int key = 0;
 
@@ -438,7 +375,13 @@ int kptr_get_ref_state(struct __sk_buff *ctx)
 	if (!v)
 		return 0;
 
-	bpf_kfunc_call_test_kptr_get(&v->ref_ptr, 0, 0);
+	p = bpf_kfunc_call_test_acquire(&(unsigned long){0});
+
+	/* PTR_TO_BTF_ID | PTR_MAYBE_NULL passed to bpf_kptr_xchg() */
+	p = bpf_kptr_xchg(&v->ref_ptr, p);
+	if (p)
+		bpf_kfunc_call_test_release(p);
+
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/map_percpu_stats.c b/tools/testing/selftests/bpf/progs/map_percpu_stats.c
new file mode 100644
index 000000000000..63245785eb69
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/map_percpu_stats.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+__u32 target_id;
+
+__s64 bpf_map_sum_elem_count(const struct bpf_map *map) __ksym;
+
+SEC("iter/bpf_map")
+int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct bpf_map *map = ctx->map;
+
+	if (map && map->id == target_id)
+		BPF_SEQ_PRINTF(seq, "%lld", bpf_map_sum_elem_count(map));
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
index db388f593d0a..efaf622c28dd 100644
--- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c
+++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
@@ -103,6 +103,8 @@ struct {
 	__type(value, __u32);
 } m_hash SEC(".maps");
 
+__s64 bpf_map_sum_elem_count(struct bpf_map *map) __ksym;
+
 static inline int check_hash(void)
 {
 	struct bpf_htab *hash = (struct bpf_htab *)&m_hash;
@@ -115,6 +117,8 @@ static inline int check_hash(void)
 	VERIFY(hash->elem_size == 64);
 
 	VERIFY(hash->count.counter == 0);
+	VERIFY(bpf_map_sum_elem_count(map) == 0);
+
 	for (i = 0; i < HALF_ENTRIES; ++i) {
 		const __u32 key = i;
 		const __u32 val = 1;
@@ -123,6 +127,7 @@ static inline int check_hash(void)
 			return 0;
 	}
 	VERIFY(hash->count.counter == HALF_ENTRIES);
+	VERIFY(bpf_map_sum_elem_count(map) == HALF_ENTRIES);
 
 	return 1;
 }
@@ -311,7 +316,7 @@ struct lpm_trie {
 } __attribute__((preserve_access_index));
 
 struct lpm_key {
-	struct bpf_lpm_trie_key trie_key;
+	struct bpf_lpm_trie_key_hdr trie_key;
 	__u32 data;
 };
 
diff --git a/tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c b/tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c
new file mode 100644
index 000000000000..3b984b6ae7c0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c
@@ -0,0 +1,229 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+SEC("tp_btf/sys_enter")
+__success
+__log_level(2)
+__msg("r8 = *(u64 *)(r7 +0)          ; R7=ptr_nameidata(off={{[0-9]+}}) R8=rdonly_untrusted_mem(sz=0)")
+__msg("r9 = *(u8 *)(r8 +0)           ; R8=rdonly_untrusted_mem(sz=0) R9=scalar")
+int btf_id_to_ptr_mem(void *ctx)
+{
+	struct task_struct *task;
+	struct nameidata *idata;
+	u64 ret, off;
+
+	task = bpf_get_current_task_btf();
+	idata = task->nameidata;
+	off = bpf_core_field_offset(struct nameidata, pathname);
+	/*
+	 * asm block to have reliable match target for __msg, equivalent of:
+	 *   ret = task->nameidata->pathname[0];
+	 */
+	asm volatile (
+	"r7 = %[idata];"
+	"r7 += %[off];"
+	"r8 = *(u64 *)(r7 + 0);"
+	"r9 = *(u8 *)(r8 + 0);"
+	"%[ret] = r9;"
+	: [ret]"=r"(ret)
+	: [idata]"r"(idata),
+	  [off]"r"(off)
+	: "r7", "r8", "r9");
+	return ret;
+}
+
+SEC("socket")
+__success
+__retval(0)
+int ldx_is_ok_bad_addr(void *ctx)
+{
+	char *p;
+
+	if (!bpf_core_enum_value_exists(enum bpf_features, BPF_FEAT_RDONLY_CAST_TO_VOID))
+		return 42;
+
+	p = bpf_rdonly_cast(0, 0);
+	return p[0x7fff];
+}
+
+SEC("socket")
+__success
+__retval(1)
+int ldx_is_ok_good_addr(void *ctx)
+{
+	int v, *p;
+
+	v = 1;
+	p = bpf_rdonly_cast(&v, 0);
+	return *p;
+}
+
+SEC("socket")
+__success
+int offset_not_tracked(void *ctx)
+{
+	int *p, i, s;
+
+	p = bpf_rdonly_cast(0, 0);
+	s = 0;
+	bpf_for(i, 0, 1000 * 1000 * 1000) {
+		p++;
+		s += *p;
+	}
+	return s;
+}
+
+SEC("socket")
+__failure
+__msg("cannot write into rdonly_untrusted_mem")
+int stx_not_ok(void *ctx)
+{
+	int v, *p;
+
+	v = 1;
+	p = bpf_rdonly_cast(&v, 0);
+	*p = 1;
+	return 0;
+}
+
+SEC("socket")
+__failure
+__msg("cannot write into rdonly_untrusted_mem")
+int atomic_not_ok(void *ctx)
+{
+	int v, *p;
+
+	v = 1;
+	p = bpf_rdonly_cast(&v, 0);
+	__sync_fetch_and_add(p, 1);
+	return 0;
+}
+
+SEC("socket")
+__failure
+__msg("cannot write into rdonly_untrusted_mem")
+int atomic_rmw_not_ok(void *ctx)
+{
+	long v, *p;
+
+	v = 1;
+	p = bpf_rdonly_cast(&v, 0);
+	return __sync_val_compare_and_swap(p, 0, 42);
+}
+
+SEC("socket")
+__failure
+__msg("invalid access to memory, mem_size=0 off=0 size=4")
+__msg("R1 min value is outside of the allowed memory range")
+int kfunc_param_not_ok(void *ctx)
+{
+	int *p;
+
+	p = bpf_rdonly_cast(0, 0);
+	bpf_kfunc_trusted_num_test(p);
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure
+__msg("R1 type=rdonly_untrusted_mem expected=")
+int helper_param_not_ok(void *ctx)
+{
+	char *p;
+
+	p = bpf_rdonly_cast(0, 0);
+	/*
+	 * Any helper with ARG_CONST_SIZE_OR_ZERO constraint will do,
+	 * the most permissive constraint
+	 */
+	bpf_copy_from_user(p, 0, (void *)42);
+	return 0;
+}
+
+static __noinline u64 *get_some_addr(void)
+{
+	if (bpf_get_prandom_u32())
+		return bpf_rdonly_cast(0, bpf_core_type_id_kernel(struct sock));
+	else
+		return bpf_rdonly_cast(0, 0);
+}
+
+SEC("socket")
+__success
+__retval(0)
+int mixed_mem_type(void *ctx)
+{
+	u64 *p;
+
+	/* Try to avoid compiler hoisting load to if branches by using __noinline func. */
+	p = get_some_addr();
+	return *p;
+}
+
+__attribute__((__aligned__(8)))
+u8 global[] = {
+	0x11, 0x22, 0x33, 0x44,
+	0x55, 0x66, 0x77, 0x88,
+	0x99
+};
+
+__always_inline
+static u64 combine(void *p)
+{
+	u64 acc;
+
+	acc = 0;
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	acc |= (*(u64 *)p >> 56) << 24;
+	acc |= (*(u32 *)p >> 24) << 16;
+	acc |= (*(u16 *)p >> 8)  << 8;
+	acc |= *(u8 *)p;
+#else
+	acc |= (*(u64 *)p & 0xff) << 24;
+	acc |= (*(u32 *)p & 0xff) << 16;
+	acc |= (*(u16 *)p & 0xff) << 8;
+	acc |= *(u8 *)p;
+#endif
+	return acc;
+}
+
+SEC("socket")
+__retval(0x88442211)
+int diff_size_access(void *ctx)
+{
+	return combine(bpf_rdonly_cast(&global, 0));
+}
+
+SEC("socket")
+__retval(0x99553322)
+int misaligned_access(void *ctx)
+{
+	return combine(bpf_rdonly_cast(&global, 0) + 1);
+}
+
+__weak int return_one(void)
+{
+	return 1;
+}
+
+SEC("socket")
+__success
+__retval(1)
+int null_check(void *ctx)
+{
+	int *p;
+
+	p = bpf_rdonly_cast(0, 0);
+	if (p == 0)
+		/* make this a function call to avoid compiler
+		 * moving r0 assignment before check.
+		 */
+		return return_one();
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/missed_kprobe.c b/tools/testing/selftests/bpf/progs/missed_kprobe.c
new file mode 100644
index 000000000000..51a4fe64c917
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/missed_kprobe.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+/*
+ * No tests in here, just to trigger 'bpf_fentry_test*'
+ * through tracing test_run
+ */
+SEC("fentry/bpf_modify_return_test")
+int BPF_PROG(trigger)
+{
+	return 0;
+}
+
+SEC("kprobe/bpf_fentry_test1")
+int test1(struct pt_regs *ctx)
+{
+	bpf_kfunc_common_test();
+	return 0;
+}
+
+SEC("kprobe/bpf_kfunc_common_test")
+int test2(struct pt_regs *ctx)
+{
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/missed_kprobe_recursion.c b/tools/testing/selftests/bpf/progs/missed_kprobe_recursion.c
new file mode 100644
index 000000000000..29c18d869ec1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/missed_kprobe_recursion.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+/*
+ * No tests in here, just to trigger 'bpf_fentry_test*'
+ * through tracing test_run
+ */
+SEC("fentry/bpf_modify_return_test")
+int BPF_PROG(trigger)
+{
+	return 0;
+}
+
+SEC("kprobe.multi/bpf_fentry_test1")
+int test1(struct pt_regs *ctx)
+{
+	bpf_kfunc_common_test();
+	return 0;
+}
+
+SEC("kprobe/bpf_kfunc_common_test")
+int test2(struct pt_regs *ctx)
+{
+	return 0;
+}
+
+SEC("kprobe/bpf_kfunc_common_test")
+int test3(struct pt_regs *ctx)
+{
+	return 0;
+}
+
+SEC("kprobe/bpf_kfunc_common_test")
+int test4(struct pt_regs *ctx)
+{
+	return 0;
+}
+
+SEC("kprobe.multi/bpf_kfunc_common_test")
+int test5(struct pt_regs *ctx)
+{
+	return 0;
+}
+
+SEC("kprobe.session/bpf_kfunc_common_test")
+int test6(struct pt_regs *ctx)
+{
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/missed_tp_recursion.c b/tools/testing/selftests/bpf/progs/missed_tp_recursion.c
new file mode 100644
index 000000000000..762385f827c5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/missed_tp_recursion.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+/*
+ * No tests in here, just to trigger 'bpf_fentry_test*'
+ * through tracing test_run
+ */
+SEC("fentry/bpf_modify_return_test")
+int BPF_PROG(trigger)
+{
+	return 0;
+}
+
+SEC("kprobe/bpf_fentry_test1")
+int test1(struct pt_regs *ctx)
+{
+	bpf_printk("test");
+	return 0;
+}
+
+SEC("tp/bpf_trace/bpf_trace_printk")
+int test2(struct pt_regs *ctx)
+{
+	return 0;
+}
+
+SEC("tp/bpf_trace/bpf_trace_printk")
+int test3(struct pt_regs *ctx)
+{
+	return 0;
+}
+
+SEC("tp/bpf_trace/bpf_trace_printk")
+int test4(struct pt_regs *ctx)
+{
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/mmap_inner_array.c b/tools/testing/selftests/bpf/progs/mmap_inner_array.c
new file mode 100644
index 000000000000..90aacbc2938a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mmap_inner_array.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct inner_array_type {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__type(key, __u32);
+	__type(value, __u64);
+	__uint(max_entries, 1);
+} inner_array SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+	__uint(key_size, 4);
+	__uint(value_size, 4);
+	__uint(max_entries, 1);
+	__array(values, struct inner_array_type);
+} outer_map SEC(".maps");
+
+int pid = 0;
+__u64 match_value = 0x13572468;
+bool done = false;
+bool pid_match = false;
+bool outer_map_match = false;
+
+SEC("fentry/" SYS_PREFIX "sys_nanosleep")
+int add_to_list_in_inner_array(void *ctx)
+{
+	__u32 curr_pid, zero = 0;
+	struct bpf_map *map;
+	__u64 *value;
+
+	curr_pid = (u32)bpf_get_current_pid_tgid();
+	if (done || curr_pid != pid)
+		return 0;
+
+	pid_match = true;
+	map = bpf_map_lookup_elem(&outer_map, &curr_pid);
+	if (!map)
+		return 0;
+
+	outer_map_match = true;
+	value = bpf_map_lookup_elem(map, &zero);
+	if (!value)
+		return 0;
+
+	*value = match_value;
+	done = true;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/modify_return.c b/tools/testing/selftests/bpf/progs/modify_return.c
index 8b7466a15c6b..3376d4849f58 100644
--- a/tools/testing/selftests/bpf/progs/modify_return.c
+++ b/tools/testing/selftests/bpf/progs/modify_return.c
@@ -47,3 +47,43 @@ int BPF_PROG(fexit_test, int a, __u64 b, int ret)
 
 	return 0;
 }
+
+static int sequence2;
+
+__u64 fentry_result2 = 0;
+SEC("fentry/bpf_modify_return_test2")
+int BPF_PROG(fentry_test2, int a, int *b, short c, int d, void *e, char f,
+	     int g)
+{
+	sequence2++;
+	fentry_result2 = (sequence2 == 1);
+	return 0;
+}
+
+__u64 fmod_ret_result2 = 0;
+SEC("fmod_ret/bpf_modify_return_test2")
+int BPF_PROG(fmod_ret_test2, int a, int *b, short c, int d, void *e, char f,
+	     int g, int ret)
+{
+	sequence2++;
+	/* This is the first fmod_ret program, the ret passed should be 0 */
+	fmod_ret_result2 = (sequence2 == 2 && ret == 0);
+	return input_retval;
+}
+
+__u64 fexit_result2 = 0;
+SEC("fexit/bpf_modify_return_test2")
+int BPF_PROG(fexit_test2, int a, int *b, short c, int d, void *e, char f,
+	     int g, int ret)
+{
+	sequence2++;
+	/* If the input_reval is non-zero a successful modification should have
+	 * occurred.
+	 */
+	if (input_retval)
+		fexit_result2 = (sequence2 == 3 && ret == input_retval);
+	else
+		fexit_result2 = (sequence2 == 3 && ret == 29);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf.h b/tools/testing/selftests/bpf/progs/mptcp_bpf.h
new file mode 100644
index 000000000000..3b188ccdcc40
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+#ifndef __MPTCP_BPF_H__
+#define __MPTCP_BPF_H__
+
+#include "bpf_experimental.h"
+
+/* list helpers from include/linux/list.h */
+static inline int list_is_head(const struct list_head *list,
+			       const struct list_head *head)
+{
+	return list == head;
+}
+
+#define list_entry(ptr, type, member)					\
+	container_of(ptr, type, member)
+
+#define list_first_entry(ptr, type, member)				\
+	list_entry((ptr)->next, type, member)
+
+#define list_next_entry(pos, member)					\
+	list_entry((pos)->member.next, typeof(*(pos)), member)
+
+#define list_entry_is_head(pos, head, member)				\
+	list_is_head(&pos->member, (head))
+
+/* small difference: 'can_loop' has been added in the conditions */
+#define list_for_each_entry(pos, head, member)				\
+	for (pos = list_first_entry(head, typeof(*pos), member);	\
+	     !list_entry_is_head(pos, head, member) && can_loop;	\
+	     pos = list_next_entry(pos, member))
+
+/* mptcp helpers from protocol.h */
+#define mptcp_for_each_subflow(__msk, __subflow)			\
+	list_for_each_entry(__subflow, &((__msk)->conn_list), node)
+
+static __always_inline struct sock *
+mptcp_subflow_tcp_sock(const struct mptcp_subflow_context *subflow)
+{
+	return subflow->tcp_sock;
+}
+
+#endif
diff --git a/tools/testing/selftests/bpf/progs/mptcp_sock.c b/tools/testing/selftests/bpf/progs/mptcp_sock.c
index 91a0d7eff2ac..f3acb90588c7 100644
--- a/tools/testing/selftests/bpf/progs/mptcp_sock.c
+++ b/tools/testing/selftests/bpf/progs/mptcp_sock.c
@@ -2,9 +2,9 @@
 /* Copyright (c) 2020, Tessares SA. */
 /* Copyright (c) 2022, SUSE. */
 
-#include <linux/bpf.h>
+#include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
-#include "bpf_tcp_helpers.h"
+#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 __u32 token = 0;
diff --git a/tools/testing/selftests/bpf/progs/mptcp_sockmap.c b/tools/testing/selftests/bpf/progs/mptcp_sockmap.c
new file mode 100644
index 000000000000..d4eef0cbadb9
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mptcp_sockmap.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "bpf_tracing_net.h"
+
+char _license[] SEC("license") = "GPL";
+
+int sk_index;
+int redirect_idx;
+int trace_port;
+int helper_ret;
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+	__uint(max_entries, 100);
+} sock_map SEC(".maps");
+
+SEC("sockops")
+int mptcp_sockmap_inject(struct bpf_sock_ops *skops)
+{
+	struct bpf_sock *sk;
+
+	/* only accept specified connection */
+	if (skops->local_port != trace_port ||
+	    skops->op != BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB)
+		return 1;
+
+	sk = skops->sk;
+	if (!sk)
+		return 1;
+
+	/* update sk handler */
+	helper_ret = bpf_sock_map_update(skops, &sock_map, &sk_index, BPF_NOEXIST);
+
+	return 1;
+}
+
+SEC("sk_skb/stream_verdict")
+int mptcp_sockmap_redirect(struct __sk_buff *skb)
+{
+	/* redirect skb to the sk under sock_map[redirect_idx] */
+	return bpf_sk_redirect_map(skb, &sock_map, redirect_idx, 0);
+}
diff --git a/tools/testing/selftests/bpf/progs/mptcp_subflow.c b/tools/testing/selftests/bpf/progs/mptcp_subflow.c
new file mode 100644
index 000000000000..41389e579578
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mptcp_subflow.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020, Tessares SA. */
+/* Copyright (c) 2024, Kylin Software */
+
+/* vmlinux.h, bpf_helpers.h and other 'define' */
+#include "bpf_tracing_net.h"
+#include "mptcp_bpf.h"
+
+char _license[] SEC("license") = "GPL";
+
+char cc[TCP_CA_NAME_MAX] = "reno";
+int pid;
+
+/* Associate a subflow counter to each token */
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+	__uint(max_entries, 100);
+} mptcp_sf SEC(".maps");
+
+SEC("sockops")
+int mptcp_subflow(struct bpf_sock_ops *skops)
+{
+	__u32 init = 1, key, mark, *cnt;
+	struct mptcp_sock *msk;
+	struct bpf_sock *sk;
+	int err;
+
+	if (skops->op != BPF_SOCK_OPS_TCP_CONNECT_CB)
+		return 1;
+
+	sk = skops->sk;
+	if (!sk)
+		return 1;
+
+	msk = bpf_skc_to_mptcp_sock(sk);
+	if (!msk)
+		return 1;
+
+	key = msk->token;
+	cnt = bpf_map_lookup_elem(&mptcp_sf, &key);
+	if (cnt) {
+		/* A new subflow is added to an existing MPTCP connection */
+		__sync_fetch_and_add(cnt, 1);
+		mark = *cnt;
+	} else {
+		/* A new MPTCP connection is just initiated and this is its primary subflow */
+		bpf_map_update_elem(&mptcp_sf, &key, &init, BPF_ANY);
+		mark = init;
+	}
+
+	/* Set the mark of the subflow's socket based on appearance order */
+	err = bpf_setsockopt(skops, SOL_SOCKET, SO_MARK, &mark, sizeof(mark));
+	if (err < 0)
+		return 1;
+	if (mark == 2)
+		err = bpf_setsockopt(skops, SOL_TCP, TCP_CONGESTION, cc, TCP_CA_NAME_MAX);
+
+	return 1;
+}
+
+static int _check_getsockopt_subflow_mark(struct mptcp_sock *msk, struct bpf_sockopt *ctx)
+{
+	struct mptcp_subflow_context *subflow;
+	int i = 0;
+
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk;
+
+		ssk = mptcp_subflow_tcp_sock(bpf_core_cast(subflow,
+							   struct mptcp_subflow_context));
+
+		if (ssk->sk_mark != ++i) {
+			ctx->retval = -2;
+			break;
+		}
+	}
+
+	return 1;
+}
+
+static int _check_getsockopt_subflow_cc(struct mptcp_sock *msk, struct bpf_sockopt *ctx)
+{
+	struct mptcp_subflow_context *subflow;
+
+	mptcp_for_each_subflow(msk, subflow) {
+		struct inet_connection_sock *icsk;
+		struct sock *ssk;
+
+		ssk = mptcp_subflow_tcp_sock(bpf_core_cast(subflow,
+							   struct mptcp_subflow_context));
+		icsk = bpf_core_cast(ssk, struct inet_connection_sock);
+
+		if (ssk->sk_mark == 2 &&
+		    __builtin_memcmp(icsk->icsk_ca_ops->name, cc, TCP_CA_NAME_MAX)) {
+			ctx->retval = -2;
+			break;
+		}
+	}
+
+	return 1;
+}
+
+SEC("cgroup/getsockopt")
+int _getsockopt_subflow(struct bpf_sockopt *ctx)
+{
+	struct bpf_sock *sk = ctx->sk;
+	struct mptcp_sock *msk;
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 1;
+
+	if (!sk || sk->protocol != IPPROTO_MPTCP ||
+	    (!(ctx->level == SOL_SOCKET && ctx->optname == SO_MARK) &&
+	     !(ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION)))
+		return 1;
+
+	msk = bpf_core_cast(sk, struct mptcp_sock);
+	if (msk->pm.extra_subflows != 1) {
+		ctx->retval = -1;
+		return 1;
+	}
+
+	if (ctx->optname == SO_MARK)
+		return _check_getsockopt_subflow_mark(msk, ctx);
+	return _check_getsockopt_subflow_cc(msk, ctx);
+}
diff --git a/tools/testing/selftests/bpf/progs/mptcpify.c b/tools/testing/selftests/bpf/progs/mptcpify.c
new file mode 100644
index 000000000000..cbdc730c3a47
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mptcpify.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023, SUSE. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+#include "bpf_tracing_net.h"
+
+char _license[] SEC("license") = "GPL";
+int pid;
+
+SEC("fmod_ret/update_socket_protocol")
+int BPF_PROG(mptcpify, int family, int type, int protocol)
+{
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return protocol;
+
+	if ((family == AF_INET || family == AF_INET6) &&
+	    type == SOCK_STREAM &&
+	    (!protocol || protocol == IPPROTO_TCP)) {
+		return IPPROTO_MPTCP;
+	}
+
+	return protocol;
+}
diff --git a/tools/testing/selftests/bpf/progs/nested_acquire.c b/tools/testing/selftests/bpf/progs/nested_acquire.c
new file mode 100644
index 000000000000..49ad7b9adf56
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/nested_acquire.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("tp_btf/tcp_probe")
+__success
+int BPF_PROG(test_nested_acquire_nonzero, struct sock *sk, struct sk_buff *skb)
+{
+	struct sk_buff *ptr;
+
+	ptr = bpf_kfunc_nested_acquire_nonzero_offset_test(&sk->sk_write_queue);
+
+	bpf_kfunc_nested_release_test(ptr);
+	return 0;
+}
+
+SEC("tp_btf/tcp_probe")
+__success
+int BPF_PROG(test_nested_acquire_zero, struct sock *sk, struct sk_buff *skb)
+{
+	struct sk_buff *ptr;
+
+	ptr = bpf_kfunc_nested_acquire_zero_offset_test(&sk->__sk_common);
+
+	bpf_kfunc_nested_release_test(ptr);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/nested_trust_common.h b/tools/testing/selftests/bpf/progs/nested_trust_common.h
new file mode 100644
index 000000000000..1784b496be2e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/nested_trust_common.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#ifndef _NESTED_TRUST_COMMON_H
+#define _NESTED_TRUST_COMMON_H
+
+#include <stdbool.h>
+
+bool bpf_cpumask_test_cpu(unsigned int cpu, const struct cpumask *cpumask) __ksym;
+__u32 bpf_cpumask_first_zero(const struct cpumask *cpumask) __ksym;
+
+#endif /* _NESTED_TRUST_COMMON_H */
diff --git a/tools/testing/selftests/bpf/progs/nested_trust_failure.c b/tools/testing/selftests/bpf/progs/nested_trust_failure.c
new file mode 100644
index 000000000000..3568ec450100
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/nested_trust_failure.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#include "nested_trust_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, u64);
+} sk_storage_map SEC(".maps");
+
+/* Prototype for all of the program trace events below:
+ *
+ * TRACE_EVENT(task_newtask,
+ *         TP_PROTO(struct task_struct *p, u64 clone_flags)
+ */
+
+SEC("tp_btf/task_newtask")
+__failure __msg("R2 must be")
+int BPF_PROG(test_invalid_nested_user_cpus, struct task_struct *task, u64 clone_flags)
+{
+	bpf_cpumask_test_cpu(0, task->user_cpus_ptr);
+	return 0;
+}
+
+/* Although R2 is of type sk_buff but sock_common is expected, we will hit untrusted ptr first. */
+SEC("tp_btf/tcp_probe")
+__failure __msg("R2 type=untrusted_ptr_ expected=ptr_, trusted_ptr_, rcu_ptr_")
+int BPF_PROG(test_invalid_skb_field, struct sock *sk, struct sk_buff *skb)
+{
+	bpf_sk_storage_get(&sk_storage_map, skb->next, 0, 0);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/nested_trust_success.c b/tools/testing/selftests/bpf/progs/nested_trust_success.c
new file mode 100644
index 000000000000..2b66953ca82e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/nested_trust_success.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#include "nested_trust_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, u64);
+} sk_storage_map SEC(".maps");
+
+SEC("tp_btf/task_newtask")
+__success
+int BPF_PROG(test_read_cpumask, struct task_struct *task, u64 clone_flags)
+{
+	bpf_cpumask_test_cpu(0, task->cpus_ptr);
+	return 0;
+}
+
+SEC("tp_btf/tcp_probe")
+__success
+int BPF_PROG(test_skb_field, struct sock *sk, struct sk_buff *skb)
+{
+	bpf_sk_storage_get(&sk_storage_map, skb->sk, 0, 0);
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__success
+int BPF_PROG(test_nested_offset, struct task_struct *task, u64 clone_flags)
+{
+	bpf_cpumask_first_zero(&task->cpus_mask);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/net_timestamping.c b/tools/testing/selftests/bpf/progs/net_timestamping.c
new file mode 100644
index 000000000000..b4c2f0f2be11
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/net_timestamping.c
@@ -0,0 +1,248 @@
+#include "vmlinux.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_kfuncs.h"
+#include <errno.h>
+
+__u32 monitored_pid = 0;
+
+int nr_active;
+int nr_snd;
+int nr_passive;
+int nr_sched;
+int nr_txsw;
+int nr_ack;
+
+struct sk_stg {
+	__u64 sendmsg_ns;	/* record ts when sendmsg is called */
+};
+
+struct sk_tskey {
+	u64 cookie;
+	u32 tskey;
+};
+
+struct delay_info {
+	u64 sendmsg_ns;		/* record ts when sendmsg is called */
+	u32 sched_delay;	/* SCHED_CB - sendmsg_ns */
+	u32 snd_sw_delay;	/* SND_SW_CB - SCHED_CB */
+	u32 ack_delay;		/* ACK_CB - SND_SW_CB */
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct sk_stg);
+} sk_stg_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, struct sk_tskey);
+	__type(value, struct delay_info);
+	__uint(max_entries, 1024);
+} time_map SEC(".maps");
+
+static u64 delay_tolerance_nsec = 10000000000; /* 10 second as an example */
+
+extern int bpf_sock_ops_enable_tx_tstamp(struct bpf_sock_ops_kern *skops, u64 flags) __ksym;
+
+static int bpf_test_sockopt(void *ctx, const struct sock *sk, int expected)
+{
+	int tmp, new = SK_BPF_CB_TX_TIMESTAMPING;
+	int opt = SK_BPF_CB_FLAGS;
+	int level = SOL_SOCKET;
+
+	if (bpf_setsockopt(ctx, level, opt, &new, sizeof(new)) != expected)
+		return 1;
+
+	if (bpf_getsockopt(ctx, level, opt, &tmp, sizeof(tmp)) != expected ||
+	    (!expected && tmp != new))
+		return 1;
+
+	return 0;
+}
+
+static bool bpf_test_access_sockopt(void *ctx, const struct sock *sk)
+{
+	if (bpf_test_sockopt(ctx, sk, -EOPNOTSUPP))
+		return true;
+	return false;
+}
+
+static bool bpf_test_access_load_hdr_opt(struct bpf_sock_ops *skops)
+{
+	u8 opt[3] = {0};
+	int load_flags = 0;
+	int ret;
+
+	ret = bpf_load_hdr_opt(skops, opt, sizeof(opt), load_flags);
+	if (ret != -EOPNOTSUPP)
+		return true;
+
+	return false;
+}
+
+static bool bpf_test_access_cb_flags_set(struct bpf_sock_ops *skops)
+{
+	int ret;
+
+	ret = bpf_sock_ops_cb_flags_set(skops, 0);
+	if (ret != -EOPNOTSUPP)
+		return true;
+
+	return false;
+}
+
+/* In the timestamping callbacks, we're not allowed to call the following
+ * BPF CALLs for the safety concern. Return false if expected.
+ */
+static bool bpf_test_access_bpf_calls(struct bpf_sock_ops *skops,
+				      const struct sock *sk)
+{
+	if (bpf_test_access_sockopt(skops, sk))
+		return true;
+
+	if (bpf_test_access_load_hdr_opt(skops))
+		return true;
+
+	if (bpf_test_access_cb_flags_set(skops))
+		return true;
+
+	return false;
+}
+
+static bool bpf_test_delay(struct bpf_sock_ops *skops, const struct sock *sk)
+{
+	struct bpf_sock_ops_kern *skops_kern;
+	u64 timestamp = bpf_ktime_get_ns();
+	struct skb_shared_info *shinfo;
+	struct delay_info dinfo = {0};
+	struct sk_tskey key = {0};
+	struct delay_info *val;
+	struct sk_buff *skb;
+	struct sk_stg *stg;
+	u64 prior_ts, delay;
+
+	if (bpf_test_access_bpf_calls(skops, sk))
+		return false;
+
+	skops_kern = bpf_cast_to_kern_ctx(skops);
+	skb = skops_kern->skb;
+	shinfo = bpf_core_cast(skb->head + skb->end, struct skb_shared_info);
+
+	key.cookie = bpf_get_socket_cookie(skops);
+	if (!key.cookie)
+		return false;
+
+	if (skops->op == BPF_SOCK_OPS_TSTAMP_SENDMSG_CB) {
+		stg = bpf_sk_storage_get(&sk_stg_map, (void *)sk, 0, 0);
+		if (!stg)
+			return false;
+		dinfo.sendmsg_ns = stg->sendmsg_ns;
+		bpf_sock_ops_enable_tx_tstamp(skops_kern, 0);
+		key.tskey = shinfo->tskey;
+		if (!key.tskey)
+			return false;
+		bpf_map_update_elem(&time_map, &key, &dinfo, BPF_ANY);
+		return true;
+	}
+
+	key.tskey = shinfo->tskey;
+	if (!key.tskey)
+		return false;
+
+	val = bpf_map_lookup_elem(&time_map, &key);
+	if (!val)
+		return false;
+
+	switch (skops->op) {
+	case BPF_SOCK_OPS_TSTAMP_SCHED_CB:
+		val->sched_delay = timestamp - val->sendmsg_ns;
+		delay = val->sched_delay;
+		break;
+	case BPF_SOCK_OPS_TSTAMP_SND_SW_CB:
+		prior_ts = val->sched_delay + val->sendmsg_ns;
+		val->snd_sw_delay = timestamp - prior_ts;
+		delay = val->snd_sw_delay;
+		break;
+	case BPF_SOCK_OPS_TSTAMP_ACK_CB:
+		prior_ts = val->snd_sw_delay + val->sched_delay + val->sendmsg_ns;
+		val->ack_delay = timestamp - prior_ts;
+		delay = val->ack_delay;
+		break;
+	}
+
+	if (delay >= delay_tolerance_nsec)
+		return false;
+
+	/* Since it's the last one, remove from the map after latency check */
+	if (skops->op == BPF_SOCK_OPS_TSTAMP_ACK_CB)
+		bpf_map_delete_elem(&time_map, &key);
+
+	return true;
+}
+
+SEC("fentry/tcp_sendmsg_locked")
+int BPF_PROG(trace_tcp_sendmsg_locked, struct sock *sk, struct msghdr *msg,
+	     size_t size)
+{
+	__u32 pid = bpf_get_current_pid_tgid() >> 32;
+	u64 timestamp = bpf_ktime_get_ns();
+	u32 flag = sk->sk_bpf_cb_flags;
+	struct sk_stg *stg;
+
+	if (pid != monitored_pid || !flag)
+		return 0;
+
+	stg = bpf_sk_storage_get(&sk_stg_map, sk, 0,
+				 BPF_SK_STORAGE_GET_F_CREATE);
+	if (!stg)
+		return 0;
+
+	stg->sendmsg_ns = timestamp;
+	nr_snd += 1;
+	return 0;
+}
+
+SEC("sockops")
+int skops_sockopt(struct bpf_sock_ops *skops)
+{
+	struct bpf_sock *bpf_sk = skops->sk;
+	const struct sock *sk;
+
+	if (!bpf_sk)
+		return 1;
+
+	sk = (struct sock *)bpf_skc_to_tcp_sock(bpf_sk);
+	if (!sk)
+		return 1;
+
+	switch (skops->op) {
+	case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+		nr_active += !bpf_test_sockopt(skops, sk, 0);
+		break;
+	case BPF_SOCK_OPS_TSTAMP_SENDMSG_CB:
+		if (bpf_test_delay(skops, sk))
+			nr_snd += 1;
+		break;
+	case BPF_SOCK_OPS_TSTAMP_SCHED_CB:
+		if (bpf_test_delay(skops, sk))
+			nr_sched += 1;
+		break;
+	case BPF_SOCK_OPS_TSTAMP_SND_SW_CB:
+		if (bpf_test_delay(skops, sk))
+			nr_txsw += 1;
+		break;
+	case BPF_SOCK_OPS_TSTAMP_ACK_CB:
+		if (bpf_test_delay(skops, sk))
+			nr_ack += 1;
+		break;
+	}
+
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/netcnt_prog.c b/tools/testing/selftests/bpf/progs/netcnt_prog.c
index f718b2c212dc..f9ef8aee56f1 100644
--- a/tools/testing/selftests/bpf/progs/netcnt_prog.c
+++ b/tools/testing/selftests/bpf/progs/netcnt_prog.c
@@ -26,7 +26,6 @@ SEC("cgroup/skb")
 int bpf_nextcnt(struct __sk_buff *skb)
 {
 	union percpu_net_cnt *percpu_cnt;
-	char fmt[] = "%d %llu %llu\n";
 	union net_cnt *cnt;
 	__u64 ts, dt;
 	int ret;
diff --git a/tools/testing/selftests/bpf/progs/netif_receive_skb.c b/tools/testing/selftests/bpf/progs/netif_receive_skb.c
index 1d8918dfbd3f..9e067dcbf607 100644
--- a/tools/testing/selftests/bpf/progs/netif_receive_skb.c
+++ b/tools/testing/selftests/bpf/progs/netif_receive_skb.c
@@ -5,6 +5,7 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include <bpf/bpf_core_read.h>
+#include "bpf_misc.h"
 
 #include <errno.h>
 
@@ -23,10 +24,6 @@ bool skip = false;
 #define BADPTR			0
 #endif
 
-#ifndef ARRAY_SIZE
-#define ARRAY_SIZE(x)	(sizeof(x) / sizeof((x)[0]))
-#endif
-
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
 	__uint(max_entries, 1);
@@ -53,7 +50,6 @@ static int __strncmp(const void *m1, const void *m2, size_t len)
 	do {								\
 		static const char _expectedval[EXPECTED_STRSIZE] =	\
 							_expected;	\
-		static const char _ptrtype[64] = #_type;		\
 		__u64 _hflags = _flags | BTF_F_COMPACT;			\
 		static _type _ptrdata = __VA_ARGS__;			\
 		static struct btf_ptr _ptr = { };			\
diff --git a/tools/testing/selftests/bpf/progs/netns_cookie_prog.c b/tools/testing/selftests/bpf/progs/netns_cookie_prog.c
index aeff3a4f9287..94040714af18 100644
--- a/tools/testing/selftests/bpf/progs/netns_cookie_prog.c
+++ b/tools/testing/selftests/bpf/progs/netns_cookie_prog.c
@@ -27,6 +27,9 @@ struct {
 	__type(value, __u64);
 } sock_map SEC(".maps");
 
+int tcx_init_netns_cookie, tcx_netns_cookie;
+int cgroup_skb_init_netns_cookie, cgroup_skb_netns_cookie;
+
 SEC("sockops")
 int get_netns_cookie_sockops(struct bpf_sock_ops *ctx)
 {
@@ -81,4 +84,20 @@ int get_netns_cookie_sk_msg(struct sk_msg_md *msg)
 	return 1;
 }
 
+SEC("tcx/ingress")
+int get_netns_cookie_tcx(struct __sk_buff *skb)
+{
+	tcx_init_netns_cookie = bpf_get_netns_cookie(NULL);
+	tcx_netns_cookie = bpf_get_netns_cookie(skb);
+	return TCX_PASS;
+}
+
+SEC("cgroup_skb/ingress")
+int get_netns_cookie_cgroup_skb(struct __sk_buff *skb)
+{
+	cgroup_skb_init_netns_cookie = bpf_get_netns_cookie(NULL);
+	cgroup_skb_netns_cookie = bpf_get_netns_cookie(skb);
+	return SK_PASS;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/normal_map_btf.c b/tools/testing/selftests/bpf/progs/normal_map_btf.c
new file mode 100644
index 000000000000..a45c9299552c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/normal_map_btf.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+struct node_data {
+	__u64 data;
+	struct bpf_list_node node;
+};
+
+struct map_value {
+	struct bpf_list_head head __contains(node_data, node);
+	struct bpf_spin_lock lock;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 1);
+} array SEC(".maps");
+
+char _license[] SEC("license") = "GPL";
+
+int pid = 0;
+bool done = false;
+
+SEC("fentry/" SYS_PREFIX "sys_nanosleep")
+int add_to_list_in_array(void *ctx)
+{
+	struct map_value *value;
+	struct node_data *new;
+	int zero = 0;
+
+	if (done || (int)bpf_get_current_pid_tgid() != pid)
+		return 0;
+
+	value = bpf_map_lookup_elem(&array, &zero);
+	if (!value)
+		return 0;
+
+	new = bpf_obj_new(typeof(*new));
+	if (!new)
+		return 0;
+
+	bpf_spin_lock(&value->lock);
+	bpf_list_push_back(&value->head, &new->node);
+	bpf_spin_unlock(&value->lock);
+	done = true;
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/percpu_alloc_array.c b/tools/testing/selftests/bpf/progs/percpu_alloc_array.c
new file mode 100644
index 000000000000..37c2d2608ec0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/percpu_alloc_array.c
@@ -0,0 +1,190 @@
+#include "bpf_experimental.h"
+
+struct val_t {
+	long b, c, d;
+};
+
+struct elem {
+	long sum;
+	struct val_t __percpu_kptr *pc;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} array SEC(".maps");
+
+void bpf_rcu_read_lock(void) __ksym;
+void bpf_rcu_read_unlock(void) __ksym;
+
+const volatile int nr_cpus;
+
+/* Initialize the percpu object */
+SEC("?fentry/bpf_fentry_test1")
+int BPF_PROG(test_array_map_1)
+{
+	struct val_t __percpu_kptr *p;
+	struct elem *e;
+	int index = 0;
+
+	e = bpf_map_lookup_elem(&array, &index);
+	if (!e)
+		return 0;
+
+	p = bpf_percpu_obj_new(struct val_t);
+	if (!p)
+		return 0;
+
+	p = bpf_kptr_xchg(&e->pc, p);
+	if (p)
+		bpf_percpu_obj_drop(p);
+
+	return 0;
+}
+
+/* Update percpu data */
+SEC("?fentry/bpf_fentry_test2")
+int BPF_PROG(test_array_map_2)
+{
+	struct val_t __percpu_kptr *p;
+	struct val_t *v;
+	struct elem *e;
+	int index = 0;
+
+	e = bpf_map_lookup_elem(&array, &index);
+	if (!e)
+		return 0;
+
+	p = e->pc;
+	if (!p)
+		return 0;
+
+	v = bpf_per_cpu_ptr(p, 0);
+	if (!v)
+		return 0;
+	v->c = 1;
+	v->d = 2;
+
+	return 0;
+}
+
+int cpu0_field_d, sum_field_c;
+int my_pid;
+
+/* Summarize percpu data */
+SEC("?fentry/bpf_fentry_test3")
+int BPF_PROG(test_array_map_3)
+{
+	struct val_t __percpu_kptr *p;
+	int i, index = 0;
+	struct val_t *v;
+	struct elem *e;
+
+	if ((bpf_get_current_pid_tgid() >> 32) != my_pid)
+		return 0;
+
+	e = bpf_map_lookup_elem(&array, &index);
+	if (!e)
+		return 0;
+
+	p = e->pc;
+	if (!p)
+		return 0;
+
+	bpf_for(i, 0, nr_cpus) {
+		v = bpf_per_cpu_ptr(p, i);
+		if (v) {
+			if (i == 0)
+				cpu0_field_d = v->d;
+			sum_field_c += v->c;
+		}
+	}
+
+	return 0;
+}
+
+/* Explicitly free allocated percpu data */
+SEC("?fentry/bpf_fentry_test4")
+int BPF_PROG(test_array_map_4)
+{
+	struct val_t __percpu_kptr *p;
+	struct elem *e;
+	int index = 0;
+
+	e = bpf_map_lookup_elem(&array, &index);
+	if (!e)
+		return 0;
+
+	/* delete */
+	p = bpf_kptr_xchg(&e->pc, NULL);
+	if (p) {
+		bpf_percpu_obj_drop(p);
+	}
+
+	return 0;
+}
+
+SEC("?fentry.s/bpf_fentry_test1")
+int BPF_PROG(test_array_map_10)
+{
+	struct val_t __percpu_kptr *p, *p1;
+	int i, index = 0;
+	struct val_t *v;
+	struct elem *e;
+
+	if ((bpf_get_current_pid_tgid() >> 32) != my_pid)
+		return 0;
+
+	e = bpf_map_lookup_elem(&array, &index);
+	if (!e)
+		return 0;
+
+	bpf_rcu_read_lock();
+	p = e->pc;
+	if (!p) {
+		p = bpf_percpu_obj_new(struct val_t);
+		if (!p)
+			goto out;
+
+		p1 = bpf_kptr_xchg(&e->pc, p);
+		if (p1) {
+			/* race condition */
+			bpf_percpu_obj_drop(p1);
+		}
+	}
+
+	v = bpf_this_cpu_ptr(p);
+	v->c = 3;
+	v = bpf_this_cpu_ptr(p);
+	v->c = 0;
+
+	v = bpf_per_cpu_ptr(p, 0);
+	if (!v)
+		goto out;
+	v->c = 1;
+	v->d = 2;
+
+	/* delete */
+	p1 = bpf_kptr_xchg(&e->pc, NULL);
+	if (!p1)
+		goto out;
+
+	bpf_for(i, 0, nr_cpus) {
+		v = bpf_per_cpu_ptr(p, i);
+		if (v) {
+			if (i == 0)
+				cpu0_field_d = v->d;
+			sum_field_c += v->c;
+		}
+	}
+
+	/* finally release p */
+	bpf_percpu_obj_drop(p1);
+out:
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/percpu_alloc_cgrp_local_storage.c b/tools/testing/selftests/bpf/progs/percpu_alloc_cgrp_local_storage.c
new file mode 100644
index 000000000000..a2acf9aa6c24
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/percpu_alloc_cgrp_local_storage.c
@@ -0,0 +1,109 @@
+#include "bpf_experimental.h"
+
+struct val_t {
+	long b, c, d;
+};
+
+struct elem {
+	long sum;
+	struct val_t __percpu_kptr *pc;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_CGRP_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct elem);
+} cgrp SEC(".maps");
+
+const volatile int nr_cpus;
+
+/* Initialize the percpu object */
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(test_cgrp_local_storage_1)
+{
+	struct task_struct *task;
+	struct val_t __percpu_kptr *p;
+	struct elem *e;
+
+	task = bpf_get_current_task_btf();
+	e = bpf_cgrp_storage_get(&cgrp, task->cgroups->dfl_cgrp, 0,
+				 BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (!e)
+		return 0;
+
+	p = bpf_percpu_obj_new(struct val_t);
+	if (!p)
+		return 0;
+
+	p = bpf_kptr_xchg(&e->pc, p);
+	if (p)
+		bpf_percpu_obj_drop(p);
+
+	return 0;
+}
+
+/* Percpu data collection */
+SEC("fentry/bpf_fentry_test2")
+int BPF_PROG(test_cgrp_local_storage_2)
+{
+	struct task_struct *task;
+	struct val_t __percpu_kptr *p;
+	struct val_t *v;
+	struct elem *e;
+
+	task = bpf_get_current_task_btf();
+	e = bpf_cgrp_storage_get(&cgrp, task->cgroups->dfl_cgrp, 0, 0);
+	if (!e)
+		return 0;
+
+	p = e->pc;
+	if (!p)
+		return 0;
+
+	v = bpf_per_cpu_ptr(p, 0);
+	if (!v)
+		return 0;
+	v->c = 1;
+	v->d = 2;
+	return 0;
+}
+
+int cpu0_field_d, sum_field_c;
+int my_pid;
+
+/* Summarize percpu data collection */
+SEC("fentry/bpf_fentry_test3")
+int BPF_PROG(test_cgrp_local_storage_3)
+{
+	struct task_struct *task;
+	struct val_t __percpu_kptr *p;
+	struct val_t *v;
+	struct elem *e;
+	int i;
+
+	if ((bpf_get_current_pid_tgid() >> 32) != my_pid)
+		return 0;
+
+	task = bpf_get_current_task_btf();
+	e = bpf_cgrp_storage_get(&cgrp, task->cgroups->dfl_cgrp, 0, 0);
+	if (!e)
+		return 0;
+
+	p = e->pc;
+	if (!p)
+		return 0;
+
+	bpf_for(i, 0, nr_cpus) {
+		v = bpf_per_cpu_ptr(p, i);
+		if (v) {
+			if (i == 0)
+				cpu0_field_d = v->d;
+			sum_field_c += v->c;
+		}
+	}
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c b/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c
new file mode 100644
index 000000000000..f2b8eb2ff76f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/percpu_alloc_fail.c
@@ -0,0 +1,182 @@
+#include "bpf_experimental.h"
+#include "bpf_misc.h"
+
+struct val_t {
+	long b, c, d;
+};
+
+struct val2_t {
+	long b;
+};
+
+struct val_with_ptr_t {
+	char *p;
+};
+
+struct val_with_rb_root_t {
+	struct bpf_spin_lock lock;
+};
+
+struct val_600b_t {
+	char b[600];
+};
+
+struct elem {
+	long sum;
+	struct val_t __percpu_kptr *pc;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} array SEC(".maps");
+
+long ret;
+
+SEC("?fentry/bpf_fentry_test1")
+__failure __msg("store to referenced kptr disallowed")
+int BPF_PROG(test_array_map_1)
+{
+	struct val_t __percpu_kptr *p;
+	struct elem *e;
+	int index = 0;
+
+	e = bpf_map_lookup_elem(&array, &index);
+	if (!e)
+		return 0;
+
+	p = bpf_percpu_obj_new(struct val_t);
+	if (!p)
+		return 0;
+
+	p = bpf_kptr_xchg(&e->pc, p);
+	if (p)
+		bpf_percpu_obj_drop(p);
+
+	e->pc = (struct val_t __percpu_kptr *)ret;
+	return 0;
+}
+
+SEC("?fentry/bpf_fentry_test1")
+__failure __msg("invalid kptr access, R2 type=percpu_ptr_val2_t expected=ptr_val_t")
+int BPF_PROG(test_array_map_2)
+{
+	struct val2_t __percpu_kptr *p2;
+	struct val_t __percpu_kptr *p;
+	struct elem *e;
+	int index = 0;
+
+	e = bpf_map_lookup_elem(&array, &index);
+	if (!e)
+		return 0;
+
+	p2 = bpf_percpu_obj_new(struct val2_t);
+	if (!p2)
+		return 0;
+
+	p = bpf_kptr_xchg(&e->pc, p2);
+	if (p)
+		bpf_percpu_obj_drop(p);
+
+	return 0;
+}
+
+SEC("?fentry.s/bpf_fentry_test1")
+__failure __msg("R1 type=scalar expected=percpu_ptr_, percpu_rcu_ptr_, percpu_trusted_ptr_")
+int BPF_PROG(test_array_map_3)
+{
+	struct val_t __percpu_kptr *p, *p1;
+	struct val_t *v;
+	struct elem *e;
+	int index = 0;
+
+	e = bpf_map_lookup_elem(&array, &index);
+	if (!e)
+		return 0;
+
+	p = bpf_percpu_obj_new(struct val_t);
+	if (!p)
+		return 0;
+
+	p1 = bpf_kptr_xchg(&e->pc, p);
+	if (p1)
+		bpf_percpu_obj_drop(p1);
+
+	v = bpf_this_cpu_ptr(p);
+	ret = v->b;
+	return 0;
+}
+
+SEC("?fentry.s/bpf_fentry_test1")
+__failure __msg("arg#0 expected for bpf_percpu_obj_drop_impl()")
+int BPF_PROG(test_array_map_4)
+{
+	struct val_t __percpu_kptr *p;
+
+	p = bpf_percpu_obj_new(struct val_t);
+	if (!p)
+		return 0;
+
+	bpf_obj_drop(p);
+	return 0;
+}
+
+SEC("?fentry.s/bpf_fentry_test1")
+__failure __msg("arg#0 expected for bpf_obj_drop_impl()")
+int BPF_PROG(test_array_map_5)
+{
+	struct val_t *p;
+
+	p = bpf_obj_new(struct val_t);
+	if (!p)
+		return 0;
+
+	bpf_percpu_obj_drop(p);
+	return 0;
+}
+
+SEC("?fentry.s/bpf_fentry_test1")
+__failure __msg("bpf_percpu_obj_new type ID argument must be of a struct of scalars")
+int BPF_PROG(test_array_map_6)
+{
+	struct val_with_ptr_t __percpu_kptr *p;
+
+	p = bpf_percpu_obj_new(struct val_with_ptr_t);
+	if (!p)
+		return 0;
+
+	bpf_percpu_obj_drop(p);
+	return 0;
+}
+
+SEC("?fentry.s/bpf_fentry_test1")
+__failure __msg("bpf_percpu_obj_new type ID argument must not contain special fields")
+int BPF_PROG(test_array_map_7)
+{
+	struct val_with_rb_root_t __percpu_kptr *p;
+
+	p = bpf_percpu_obj_new(struct val_with_rb_root_t);
+	if (!p)
+		return 0;
+
+	bpf_percpu_obj_drop(p);
+	return 0;
+}
+
+SEC("?fentry.s/bpf_fentry_test1")
+__failure __msg("bpf_percpu_obj_new type size (600) is greater than 512")
+int BPF_PROG(test_array_map_8)
+{
+	struct val_600b_t __percpu_kptr *p;
+
+	p = bpf_percpu_obj_new(struct val_600b_t);
+	if (!p)
+		return 0;
+
+	bpf_percpu_obj_drop(p);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/perfbuf_bench.c b/tools/testing/selftests/bpf/progs/perfbuf_bench.c
index 45204fe0c570..29c1639fc78a 100644
--- a/tools/testing/selftests/bpf/progs/perfbuf_bench.c
+++ b/tools/testing/selftests/bpf/progs/perfbuf_bench.c
@@ -22,7 +22,6 @@ long dropped __attribute__((aligned(128))) = 0;
 SEC("fentry/" SYS_PREFIX "sys_getpgid")
 int bench_perfbuf(void *ctx)
 {
-	__u64 *sample;
 	int i;
 
 	for (i = 0; i < batch_cnt; i++) {
diff --git a/tools/testing/selftests/bpf/progs/preempt_lock.c b/tools/testing/selftests/bpf/progs/preempt_lock.c
new file mode 100644
index 000000000000..7d04254e61f1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/preempt_lock.c
@@ -0,0 +1,212 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+extern int bpf_copy_from_user_str(void *dst, u32 dst__sz, const void *unsafe_ptr__ign, u64 flags) __weak __ksym;
+
+SEC("?tc")
+__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_preempt_disable-ed region")
+int preempt_lock_missing_1(struct __sk_buff *ctx)
+{
+	bpf_preempt_disable();
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_preempt_disable-ed region")
+int preempt_lock_missing_2(struct __sk_buff *ctx)
+{
+	bpf_preempt_disable();
+	bpf_preempt_disable();
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_preempt_disable-ed region")
+int preempt_lock_missing_3(struct __sk_buff *ctx)
+{
+	bpf_preempt_disable();
+	bpf_preempt_disable();
+	bpf_preempt_disable();
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_preempt_disable-ed region")
+int preempt_lock_missing_3_minus_2(struct __sk_buff *ctx)
+{
+	bpf_preempt_disable();
+	bpf_preempt_disable();
+	bpf_preempt_disable();
+	bpf_preempt_enable();
+	bpf_preempt_enable();
+	return 0;
+}
+
+static __noinline void preempt_disable(void)
+{
+	bpf_preempt_disable();
+}
+
+static __noinline void preempt_enable(void)
+{
+	bpf_preempt_enable();
+}
+
+SEC("?tc")
+__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_preempt_disable-ed region")
+int preempt_lock_missing_1_subprog(struct __sk_buff *ctx)
+{
+	preempt_disable();
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_preempt_disable-ed region")
+int preempt_lock_missing_2_subprog(struct __sk_buff *ctx)
+{
+	preempt_disable();
+	preempt_disable();
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_preempt_disable-ed region")
+int preempt_lock_missing_2_minus_1_subprog(struct __sk_buff *ctx)
+{
+	preempt_disable();
+	preempt_disable();
+	preempt_enable();
+	return 0;
+}
+
+static __noinline void preempt_balance_subprog(void)
+{
+	preempt_disable();
+	preempt_enable();
+}
+
+SEC("?tc")
+__success int preempt_balance(struct __sk_buff *ctx)
+{
+	bpf_guard_preempt();
+	return 0;
+}
+
+SEC("?tc")
+__success int preempt_balance_subprog_test(struct __sk_buff *ctx)
+{
+	preempt_balance_subprog();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("sleepable helper bpf_copy_from_user#")
+int preempt_sleepable_helper(void *ctx)
+{
+	u32 data;
+
+	bpf_preempt_disable();
+	bpf_copy_from_user(&data, sizeof(data), NULL);
+	bpf_preempt_enable();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure __msg("kernel func bpf_copy_from_user_str is sleepable within non-preemptible region")
+int preempt_sleepable_kfunc(void *ctx)
+{
+	u32 data;
+
+	bpf_preempt_disable();
+	bpf_copy_from_user_str(&data, sizeof(data), NULL, 0);
+	bpf_preempt_enable();
+	return 0;
+}
+
+int __noinline preempt_global_subprog(void)
+{
+	preempt_balance_subprog();
+	return 0;
+}
+
+SEC("?tc")
+__success
+int preempt_global_subprog_test(struct __sk_buff *ctx)
+{
+	preempt_disable();
+	preempt_global_subprog();
+	preempt_enable();
+	return 0;
+}
+
+int __noinline
+global_subprog(int i)
+{
+	if (i)
+		bpf_printk("%p", &i);
+	return i;
+}
+
+int __noinline
+global_sleepable_helper_subprog(int i)
+{
+	if (i)
+		bpf_copy_from_user(&i, sizeof(i), NULL);
+	return i;
+}
+
+int __noinline
+global_sleepable_kfunc_subprog(int i)
+{
+	if (i)
+		bpf_copy_from_user_str(&i, sizeof(i), NULL, 0);
+	global_subprog(i);
+	return i;
+}
+
+int __noinline
+global_subprog_calling_sleepable_global(int i)
+{
+	if (!i)
+		global_sleepable_kfunc_subprog(i);
+	return i;
+}
+
+SEC("?syscall")
+__failure __msg("global functions that may sleep are not allowed in non-sleepable context")
+int preempt_global_sleepable_helper_subprog(struct __sk_buff *ctx)
+{
+	preempt_disable();
+	if (ctx->mark)
+		global_sleepable_helper_subprog(ctx->mark);
+	preempt_enable();
+	return 0;
+}
+
+SEC("?syscall")
+__failure __msg("global functions that may sleep are not allowed in non-sleepable context")
+int preempt_global_sleepable_kfunc_subprog(struct __sk_buff *ctx)
+{
+	preempt_disable();
+	if (ctx->mark)
+		global_sleepable_kfunc_subprog(ctx->mark);
+	preempt_enable();
+	return 0;
+}
+
+SEC("?syscall")
+__failure __msg("global functions that may sleep are not allowed in non-sleepable context")
+int preempt_global_sleepable_subprog_indirect(struct __sk_buff *ctx)
+{
+	preempt_disable();
+	if (ctx->mark)
+		global_subprog_calling_sleepable_global(ctx->mark);
+	preempt_enable();
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/preempted_bpf_ma_op.c b/tools/testing/selftests/bpf/progs/preempted_bpf_ma_op.c
new file mode 100644
index 000000000000..55907ef961bf
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/preempted_bpf_ma_op.c
@@ -0,0 +1,106 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_experimental.h"
+
+struct bin_data {
+	char data[256];
+	struct bpf_spin_lock lock;
+};
+
+struct map_value {
+	struct bin_data __kptr * data;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 2048);
+} array SEC(".maps");
+
+char _license[] SEC("license") = "GPL";
+
+bool nomem_err = false;
+
+static int del_array(unsigned int i, int *from)
+{
+	struct map_value *value;
+	struct bin_data *old;
+
+	value = bpf_map_lookup_elem(&array, from);
+	if (!value)
+		return 1;
+
+	old = bpf_kptr_xchg(&value->data, NULL);
+	if (old)
+		bpf_obj_drop(old);
+
+	(*from)++;
+	return 0;
+}
+
+static int add_array(unsigned int i, int *from)
+{
+	struct bin_data *old, *new;
+	struct map_value *value;
+
+	value = bpf_map_lookup_elem(&array, from);
+	if (!value)
+		return 1;
+
+	new = bpf_obj_new(typeof(*new));
+	if (!new) {
+		nomem_err = true;
+		return 1;
+	}
+
+	old = bpf_kptr_xchg(&value->data, new);
+	if (old)
+		bpf_obj_drop(old);
+
+	(*from)++;
+	return 0;
+}
+
+static void del_then_add_array(int from)
+{
+	int i;
+
+	i = from;
+	bpf_loop(512, del_array, &i, 0);
+
+	i = from;
+	bpf_loop(512, add_array, &i, 0);
+}
+
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG2(test0, int, a)
+{
+	del_then_add_array(0);
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test2")
+int BPF_PROG2(test1, int, a, u64, b)
+{
+	del_then_add_array(512);
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test3")
+int BPF_PROG2(test2, char, a, int, b, u64, c)
+{
+	del_then_add_array(1024);
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test4")
+int BPF_PROG2(test3, void *, a, char, b, int, c, u64, d)
+{
+	del_then_add_array(1536);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/prepare.c b/tools/testing/selftests/bpf/progs/prepare.c
new file mode 100644
index 000000000000..cfc1f48e0d28
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/prepare.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+int err;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_RINGBUF);
+	__uint(max_entries, 4096);
+} ringbuf SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u32);
+} array_map SEC(".maps");
+
+SEC("cgroup_skb/egress")
+int program(struct __sk_buff *skb)
+{
+	err = 0;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/priv_freplace_prog.c b/tools/testing/selftests/bpf/progs/priv_freplace_prog.c
new file mode 100644
index 000000000000..ccf1b04010ba
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/priv_freplace_prog.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+SEC("freplace/xdp_prog1")
+int new_xdp_prog2(struct xdp_md *xd)
+{
+	return XDP_DROP;
+}
diff --git a/tools/testing/selftests/bpf/progs/priv_map.c b/tools/testing/selftests/bpf/progs/priv_map.c
new file mode 100644
index 000000000000..9085be50f03b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/priv_map.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_QUEUE);
+	__uint(max_entries, 1);
+	__type(value, __u32);
+} priv_map SEC(".maps");
diff --git a/tools/testing/selftests/bpf/progs/priv_prog.c b/tools/testing/selftests/bpf/progs/priv_prog.c
new file mode 100644
index 000000000000..725e29595079
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/priv_prog.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+SEC("xdp")
+int xdp_prog1(struct xdp_md *xdp)
+{
+	return XDP_DROP;
+}
diff --git a/tools/testing/selftests/bpf/progs/pro_epilogue.c b/tools/testing/selftests/bpf/progs/pro_epilogue.c
new file mode 100644
index 000000000000..d97d6e07ef5c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/pro_epilogue.c
@@ -0,0 +1,154 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+void __kfunc_btf_root(void)
+{
+	bpf_kfunc_st_ops_inc10(NULL);
+}
+
+static __noinline __used int subprog(struct st_ops_args *args)
+{
+	args->a += 1;
+	return args->a;
+}
+
+__success
+/* prologue */
+__xlated("0: r6 = *(u64 *)(r1 +0)")
+__xlated("1: r7 = *(u64 *)(r6 +0)")
+__xlated("2: r7 += 1000")
+__xlated("3: *(u64 *)(r6 +0) = r7")
+/* main prog */
+__xlated("4: r1 = *(u64 *)(r1 +0)")
+__xlated("5: r6 = r1")
+__xlated("6: call kernel-function")
+__xlated("7: r1 = r6")
+__xlated("8: call pc+1")
+__xlated("9: exit")
+SEC("struct_ops/test_prologue")
+__naked int test_prologue(void)
+{
+	asm volatile (
+	"r1 = *(u64 *)(r1 +0);"
+	"r6 = r1;"
+	"call %[bpf_kfunc_st_ops_inc10];"
+	"r1 = r6;"
+	"call subprog;"
+	"exit;"
+	:
+	: __imm(bpf_kfunc_st_ops_inc10)
+	: __clobber_all);
+}
+
+__success
+/* save __u64 *ctx to stack */
+__xlated("0: *(u64 *)(r10 -8) = r1")
+/* main prog */
+__xlated("1: r1 = *(u64 *)(r1 +0)")
+__xlated("2: r6 = r1")
+__xlated("3: call kernel-function")
+__xlated("4: r1 = r6")
+__xlated("5: call pc+")
+/* epilogue */
+__xlated("6: r1 = *(u64 *)(r10 -8)")
+__xlated("7: r1 = *(u64 *)(r1 +0)")
+__xlated("8: r6 = *(u64 *)(r1 +0)")
+__xlated("9: r6 += 10000")
+__xlated("10: *(u64 *)(r1 +0) = r6")
+__xlated("11: r0 = r6")
+__xlated("12: r0 *= 2")
+__xlated("13: exit")
+SEC("struct_ops/test_epilogue")
+__naked int test_epilogue(void)
+{
+	asm volatile (
+	"r1 = *(u64 *)(r1 +0);"
+	"r6 = r1;"
+	"call %[bpf_kfunc_st_ops_inc10];"
+	"r1 = r6;"
+	"call subprog;"
+	"exit;"
+	:
+	: __imm(bpf_kfunc_st_ops_inc10)
+	: __clobber_all);
+}
+
+__success
+/* prologue */
+__xlated("0: r6 = *(u64 *)(r1 +0)")
+__xlated("1: r7 = *(u64 *)(r6 +0)")
+__xlated("2: r7 += 1000")
+__xlated("3: *(u64 *)(r6 +0) = r7")
+/* save __u64 *ctx to stack */
+__xlated("4: *(u64 *)(r10 -8) = r1")
+/* main prog */
+__xlated("5: r1 = *(u64 *)(r1 +0)")
+__xlated("6: r6 = r1")
+__xlated("7: call kernel-function")
+__xlated("8: r1 = r6")
+__xlated("9: call pc+")
+/* epilogue */
+__xlated("10: r1 = *(u64 *)(r10 -8)")
+__xlated("11: r1 = *(u64 *)(r1 +0)")
+__xlated("12: r6 = *(u64 *)(r1 +0)")
+__xlated("13: r6 += 10000")
+__xlated("14: *(u64 *)(r1 +0) = r6")
+__xlated("15: r0 = r6")
+__xlated("16: r0 *= 2")
+__xlated("17: exit")
+SEC("struct_ops/test_pro_epilogue")
+__naked int test_pro_epilogue(void)
+{
+	asm volatile (
+	"r1 = *(u64 *)(r1 +0);"
+	"r6 = r1;"
+	"call %[bpf_kfunc_st_ops_inc10];"
+	"r1 = r6;"
+	"call subprog;"
+	"exit;"
+	:
+	: __imm(bpf_kfunc_st_ops_inc10)
+	: __clobber_all);
+}
+
+SEC("syscall")
+__retval(1011) /* PROLOGUE_A [1000] + KFUNC_INC10 + SUBPROG_A [1] */
+int syscall_prologue(void *ctx)
+{
+	struct st_ops_args args = {};
+
+	return bpf_kfunc_st_ops_test_prologue(&args);
+}
+
+SEC("syscall")
+__retval(20022) /* (KFUNC_INC10 + SUBPROG_A [1] + EPILOGUE_A [10000]) * 2 */
+int syscall_epilogue(void *ctx)
+{
+	struct st_ops_args args = {};
+
+	return bpf_kfunc_st_ops_test_epilogue(&args);
+}
+
+SEC("syscall")
+__retval(22022) /* (PROLOGUE_A [1000] + KFUNC_INC10 + SUBPROG_A [1] + EPILOGUE_A [10000]) * 2 */
+int syscall_pro_epilogue(void *ctx)
+{
+	struct st_ops_args args = {};
+
+	return bpf_kfunc_st_ops_test_pro_epilogue(&args);
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_st_ops pro_epilogue = {
+	.test_prologue = (void *)test_prologue,
+	.test_epilogue = (void *)test_epilogue,
+	.test_pro_epilogue = (void *)test_pro_epilogue,
+};
diff --git a/tools/testing/selftests/bpf/progs/pro_epilogue_goto_start.c b/tools/testing/selftests/bpf/progs/pro_epilogue_goto_start.c
new file mode 100644
index 000000000000..6048d79be48b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/pro_epilogue_goto_start.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+__success
+/* prologue */
+__xlated("0: r6 = *(u64 *)(r1 +0)")
+__xlated("1: r7 = *(u64 *)(r6 +0)")
+__xlated("2: r7 += 1000")
+__xlated("3: *(u64 *)(r6 +0) = r7")
+/* main prog */
+__xlated("4: if r1 == 0x0 goto pc+5")
+__xlated("5: if r1 == 0x1 goto pc+2")
+__xlated("6: r1 = 1")
+__xlated("7: goto pc-3")
+__xlated("8: r1 = 0")
+__xlated("9: goto pc-6")
+__xlated("10: r0 = 0")
+__xlated("11: exit")
+SEC("struct_ops/test_prologue_goto_start")
+__naked int test_prologue_goto_start(void)
+{
+	asm volatile (
+	"if r1 == 0 goto +5;"
+	"if r1 == 1 goto +2;"
+	"r1 = 1;"
+	"goto -3;"
+	"r1 = 0;"
+	"goto -6;"
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+__success
+/* save __u64 *ctx to stack */
+__xlated("0: *(u64 *)(r10 -8) = r1")
+/* main prog */
+__xlated("1: if r1 == 0x0 goto pc+5")
+__xlated("2: if r1 == 0x1 goto pc+2")
+__xlated("3: r1 = 1")
+__xlated("4: goto pc-3")
+__xlated("5: r1 = 0")
+__xlated("6: goto pc-6")
+__xlated("7: r0 = 0")
+/* epilogue */
+__xlated("8: r1 = *(u64 *)(r10 -8)")
+__xlated("9: r1 = *(u64 *)(r1 +0)")
+__xlated("10: r6 = *(u64 *)(r1 +0)")
+__xlated("11: r6 += 10000")
+__xlated("12: *(u64 *)(r1 +0) = r6")
+__xlated("13: r0 = r6")
+__xlated("14: r0 *= 2")
+__xlated("15: exit")
+SEC("struct_ops/test_epilogue_goto_start")
+__naked int test_epilogue_goto_start(void)
+{
+	asm volatile (
+	"if r1 == 0 goto +5;"
+	"if r1 == 1 goto +2;"
+	"r1 = 1;"
+	"goto -3;"
+	"r1 = 0;"
+	"goto -6;"
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+__success
+/* prologue */
+__xlated("0: r6 = *(u64 *)(r1 +0)")
+__xlated("1: r7 = *(u64 *)(r6 +0)")
+__xlated("2: r7 += 1000")
+__xlated("3: *(u64 *)(r6 +0) = r7")
+/* save __u64 *ctx to stack */
+__xlated("4: *(u64 *)(r10 -8) = r1")
+/* main prog */
+__xlated("5: if r1 == 0x0 goto pc+5")
+__xlated("6: if r1 == 0x1 goto pc+2")
+__xlated("7: r1 = 1")
+__xlated("8: goto pc-3")
+__xlated("9: r1 = 0")
+__xlated("10: goto pc-6")
+__xlated("11: r0 = 0")
+/* epilogue */
+__xlated("12: r1 = *(u64 *)(r10 -8)")
+__xlated("13: r1 = *(u64 *)(r1 +0)")
+__xlated("14: r6 = *(u64 *)(r1 +0)")
+__xlated("15: r6 += 10000")
+__xlated("16: *(u64 *)(r1 +0) = r6")
+__xlated("17: r0 = r6")
+__xlated("18: r0 *= 2")
+__xlated("19: exit")
+SEC("struct_ops/test_pro_epilogue_goto_start")
+__naked int test_pro_epilogue_goto_start(void)
+{
+	asm volatile (
+	"if r1 == 0 goto +5;"
+	"if r1 == 1 goto +2;"
+	"r1 = 1;"
+	"goto -3;"
+	"r1 = 0;"
+	"goto -6;"
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_st_ops epilogue_goto_start = {
+	.test_prologue = (void *)test_prologue_goto_start,
+	.test_epilogue = (void *)test_epilogue_goto_start,
+	.test_pro_epilogue = (void *)test_pro_epilogue_goto_start,
+};
+
+SEC("syscall")
+__retval(0)
+int syscall_prologue_goto_start(void *ctx)
+{
+	struct st_ops_args args = {};
+
+	return bpf_kfunc_st_ops_test_prologue(&args);
+}
+
+SEC("syscall")
+__retval(20000) /* (EPILOGUE_A [10000]) * 2 */
+int syscall_epilogue_goto_start(void *ctx)
+{
+	struct st_ops_args args = {};
+
+	return bpf_kfunc_st_ops_test_epilogue(&args);
+}
+
+SEC("syscall")
+__retval(22000) /* (PROLOGUE_A [1000] + EPILOGUE_A [10000]) * 2 */
+int syscall_pro_epilogue_goto_start(void *ctx)
+{
+	struct st_ops_args args = {};
+
+	return bpf_kfunc_st_ops_test_pro_epilogue(&args);
+}
diff --git a/tools/testing/selftests/bpf/progs/pro_epilogue_with_kfunc.c b/tools/testing/selftests/bpf/progs/pro_epilogue_with_kfunc.c
new file mode 100644
index 000000000000..a5a8f08ac8fb
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/pro_epilogue_with_kfunc.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+void __kfunc_btf_root(void)
+{
+	bpf_kfunc_st_ops_inc10(NULL);
+}
+
+static __noinline __used int subprog(struct st_ops_args *args)
+{
+	args->a += 1;
+	return args->a;
+}
+
+__success
+/* prologue */
+__xlated("0: r8 = r1")
+__xlated("1: r1 = 0")
+__xlated("2: call kernel-function")
+__xlated("3: if r0 != 0x0 goto pc+5")
+__xlated("4: r6 = *(u64 *)(r8 +0)")
+__xlated("5: r7 = *(u64 *)(r6 +0)")
+__xlated("6: r7 += 1000")
+__xlated("7: *(u64 *)(r6 +0) = r7")
+__xlated("8: goto pc+2")
+__xlated("9: r1 = r0")
+__xlated("10: call kernel-function")
+__xlated("11: r1 = r8")
+/* save __u64 *ctx to stack */
+__xlated("12: *(u64 *)(r10 -8) = r1")
+/* main prog */
+__xlated("13: r1 = *(u64 *)(r1 +0)")
+__xlated("14: r6 = r1")
+__xlated("15: call kernel-function")
+__xlated("16: r1 = r6")
+__xlated("17: call pc+")
+/* epilogue */
+__xlated("18: r1 = 0")
+__xlated("19: r6 = 0")
+__xlated("20: call kernel-function")
+__xlated("21: if r0 != 0x0 goto pc+6")
+__xlated("22: r1 = *(u64 *)(r10 -8)")
+__xlated("23: r1 = *(u64 *)(r1 +0)")
+__xlated("24: r6 = *(u64 *)(r1 +0)")
+__xlated("25: r6 += 10000")
+__xlated("26: *(u64 *)(r1 +0) = r6")
+__xlated("27: goto pc+2")
+__xlated("28: r1 = r0")
+__xlated("29: call kernel-function")
+__xlated("30: r0 = r6")
+__xlated("31: r0 *= 2")
+__xlated("32: exit")
+SEC("struct_ops/test_pro_epilogue")
+__naked int test_kfunc_pro_epilogue(void)
+{
+	asm volatile (
+	"r1 = *(u64 *)(r1 +0);"
+	"r6 = r1;"
+	"call %[bpf_kfunc_st_ops_inc10];"
+	"r1 = r6;"
+	"call subprog;"
+	"exit;"
+	:
+	: __imm(bpf_kfunc_st_ops_inc10)
+	: __clobber_all);
+}
+
+SEC("syscall")
+__retval(22022) /* (PROLOGUE_A [1000] + KFUNC_INC10 + SUBPROG_A [1] + EPILOGUE_A [10000]) * 2 */
+int syscall_pro_epilogue(void *ctx)
+{
+	struct st_ops_args args = {};
+
+	return bpf_kfunc_st_ops_test_pro_epilogue(&args);
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_st_ops pro_epilogue_with_kfunc = {
+	.test_pro_epilogue = (void *)test_kfunc_pro_epilogue,
+};
diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h
index 92331053dba3..813143b4985d 100644
--- a/tools/testing/selftests/bpf/progs/profiler.inc.h
+++ b/tools/testing/selftests/bpf/progs/profiler.inc.h
@@ -6,6 +6,10 @@
 #include <bpf/bpf_tracing.h>
 
 #include "profiler.h"
+#include "err.h"
+#include "bpf_experimental.h"
+#include "bpf_compiler.h"
+#include "bpf_misc.h"
 
 #ifndef NULL
 #define NULL 0
@@ -16,7 +20,6 @@
 #define O_DIRECTORY 00200000
 #define __O_TMPFILE 020000000
 #define O_TMPFILE (__O_TMPFILE | O_DIRECTORY)
-#define MAX_ERRNO 4095
 #define S_IFMT 00170000
 #define S_IFSOCK 0140000
 #define S_IFLNK 0120000
@@ -34,7 +37,6 @@
 #define S_ISBLK(m) (((m)&S_IFMT) == S_IFBLK)
 #define S_ISFIFO(m) (((m)&S_IFMT) == S_IFIFO)
 #define S_ISSOCK(m) (((m)&S_IFMT) == S_IFSOCK)
-#define IS_ERR_VALUE(x) (unsigned long)(void*)(x) >= (unsigned long)-MAX_ERRNO
 
 #define KILL_DATA_ARRAY_SIZE 8
 
@@ -132,10 +134,6 @@ struct {
 	__uint(max_entries, 16);
 } disallowed_exec_inodes SEC(".maps");
 
-#ifndef ARRAY_SIZE
-#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(arr[0]))
-#endif
-
 static INLINE bool IS_ERR(const void* ptr)
 {
 	return IS_ERR_VALUE((unsigned long)ptr);
@@ -156,10 +154,10 @@ probe_read_lim(void* dst, void* src, unsigned long len, unsigned long max)
 {
 	len = len < max ? len : max;
 	if (len > 1) {
-		if (bpf_probe_read(dst, len, src))
+		if (bpf_probe_read_kernel(dst, len, src))
 			return 0;
 	} else if (len == 1) {
-		if (bpf_probe_read(dst, 1, src))
+		if (bpf_probe_read_kernel(dst, 1, src))
 			return 0;
 	}
 	return len;
@@ -169,7 +167,7 @@ static INLINE int get_var_spid_index(struct var_kill_data_arr_t* arr_struct,
 				     int spid)
 {
 #ifdef UNROLL
-#pragma unroll
+	__pragma_loop_unroll
 #endif
 	for (int i = 0; i < ARRAY_SIZE(arr_struct->array); i++)
 		if (arr_struct->array[i].meta.pid == spid)
@@ -185,7 +183,7 @@ static INLINE void populate_ancestors(struct task_struct* task,
 
 	ancestors_data->num_ancestors = 0;
 #ifdef UNROLL
-#pragma unroll
+	__pragma_loop_unroll
 #endif
 	for (num_ancestors = 0; num_ancestors < MAX_ANCESTORS; num_ancestors++) {
 		parent = BPF_CORE_READ(parent, real_parent);
@@ -212,20 +210,20 @@ static INLINE void* read_full_cgroup_path(struct kernfs_node* cgroup_node,
 	size_t filepart_length;
 
 #ifdef UNROLL
-#pragma unroll
+	__pragma_loop_unroll
 #endif
 	for (int i = 0; i < MAX_CGROUPS_PATH_DEPTH; i++) {
 		filepart_length =
-			bpf_probe_read_str(payload, MAX_PATH, BPF_CORE_READ(cgroup_node, name));
+			bpf_probe_read_kernel_str(payload, MAX_PATH,
+						  BPF_CORE_READ(cgroup_node, name));
 		if (!cgroup_node)
 			return payload;
 		if (cgroup_node == cgroup_root_node)
 			*root_pos = payload - payload_start;
-		if (filepart_length <= MAX_PATH) {
-			barrier_var(filepart_length);
+		if (bpf_cmp_likely(filepart_length, <=, MAX_PATH)) {
 			payload += filepart_length;
 		}
-		cgroup_node = BPF_CORE_READ(cgroup_node, parent);
+		cgroup_node = BPF_CORE_READ(cgroup_node, __parent);
 	}
 	return payload;
 }
@@ -261,7 +259,7 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data,
 		int cgrp_id = bpf_core_enum_value(enum cgroup_subsys_id___local,
 						  pids_cgrp_id___local);
 #ifdef UNROLL
-#pragma unroll
+		__pragma_loop_unroll
 #endif
 		for (int i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
 			struct cgroup_subsys_state* subsys =
@@ -303,19 +301,17 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data,
 	cgroup_data->cgroup_full_length = 0;
 
 	size_t cgroup_root_length =
-		bpf_probe_read_str(payload, MAX_PATH, BPF_CORE_READ(root_kernfs, name));
-	barrier_var(cgroup_root_length);
-	if (cgroup_root_length <= MAX_PATH) {
-		barrier_var(cgroup_root_length);
+		bpf_probe_read_kernel_str(payload, MAX_PATH,
+					  BPF_CORE_READ(root_kernfs, name));
+	if (bpf_cmp_likely(cgroup_root_length, <=, MAX_PATH)) {
 		cgroup_data->cgroup_root_length = cgroup_root_length;
 		payload += cgroup_root_length;
 	}
 
 	size_t cgroup_proc_length =
-		bpf_probe_read_str(payload, MAX_PATH, BPF_CORE_READ(proc_kernfs, name));
-	barrier_var(cgroup_proc_length);
-	if (cgroup_proc_length <= MAX_PATH) {
-		barrier_var(cgroup_proc_length);
+		bpf_probe_read_kernel_str(payload, MAX_PATH,
+					  BPF_CORE_READ(proc_kernfs, name));
+	if (bpf_cmp_likely(cgroup_proc_length, <=, MAX_PATH)) {
 		cgroup_data->cgroup_proc_length = cgroup_proc_length;
 		payload += cgroup_proc_length;
 	}
@@ -345,9 +341,7 @@ static INLINE void* populate_var_metadata(struct var_metadata_t* metadata,
 	metadata->comm_length = 0;
 
 	size_t comm_length = bpf_core_read_str(payload, TASK_COMM_LEN, &task->comm);
-	barrier_var(comm_length);
-	if (comm_length <= TASK_COMM_LEN) {
-		barrier_var(comm_length);
+	if (bpf_cmp_likely(comm_length, <=, TASK_COMM_LEN)) {
 		metadata->comm_length = comm_length;
 		payload += comm_length;
 	}
@@ -395,7 +389,8 @@ static INLINE int trace_var_sys_kill(void* ctx, int tpid, int sig)
 		arr_struct = bpf_map_lookup_elem(&data_heap, &zero);
 		if (arr_struct == NULL)
 			return 0;
-		bpf_probe_read(&arr_struct->array[0], sizeof(arr_struct->array[0]), kill_data);
+		bpf_probe_read_kernel(&arr_struct->array[0],
+				      sizeof(arr_struct->array[0]), kill_data);
 	} else {
 		int index = get_var_spid_index(arr_struct, spid);
 
@@ -405,12 +400,13 @@ static INLINE int trace_var_sys_kill(void* ctx, int tpid, int sig)
 			if (kill_data == NULL)
 				return 0;
 #ifdef UNROLL
-#pragma unroll
+			__pragma_loop_unroll
 #endif
 			for (int i = 0; i < ARRAY_SIZE(arr_struct->array); i++)
 				if (arr_struct->array[i].meta.pid == 0) {
-					bpf_probe_read(&arr_struct->array[i],
-						       sizeof(arr_struct->array[i]), kill_data);
+					bpf_probe_read_kernel(&arr_struct->array[i],
+							      sizeof(arr_struct->array[i]),
+							      kill_data);
 					bpf_map_update_elem(&var_tpid_to_data, &tpid,
 							    arr_struct, 0);
 
@@ -427,17 +423,17 @@ static INLINE int trace_var_sys_kill(void* ctx, int tpid, int sig)
 		if (delta_sec < STALE_INFO) {
 			kill_data->kill_count++;
 			kill_data->last_kill_time = bpf_ktime_get_ns();
-			bpf_probe_read(&arr_struct->array[index],
-				       sizeof(arr_struct->array[index]),
-				       kill_data);
+			bpf_probe_read_kernel(&arr_struct->array[index],
+					      sizeof(arr_struct->array[index]),
+					      kill_data);
 		} else {
 			struct var_kill_data_t* kill_data =
 				get_var_kill_data(ctx, spid, tpid, sig);
 			if (kill_data == NULL)
 				return 0;
-			bpf_probe_read(&arr_struct->array[index],
-				       sizeof(arr_struct->array[index]),
-				       kill_data);
+			bpf_probe_read_kernel(&arr_struct->array[index],
+					      sizeof(arr_struct->array[index]),
+					      kill_data);
 		}
 	}
 	bpf_map_update_elem(&var_tpid_to_data, &tpid, arr_struct, 0);
@@ -484,15 +480,15 @@ read_absolute_file_path_from_dentry(struct dentry* filp_dentry, void* payload)
 	struct dentry* parent_dentry;
 
 #ifdef UNROLL
-#pragma unroll
+	__pragma_loop_unroll
 #endif
 	for (int i = 0; i < MAX_PATH_DEPTH; i++) {
-		filepart_length = bpf_probe_read_str(payload, MAX_PATH,
-						     BPF_CORE_READ(filp_dentry, d_name.name));
-		barrier_var(filepart_length);
-		if (filepart_length > MAX_PATH)
+		filepart_length =
+			bpf_probe_read_kernel_str(payload, MAX_PATH,
+						  BPF_CORE_READ(filp_dentry, d_name.name));
+		bpf_nop_mov(filepart_length);
+		if (bpf_cmp_unlikely(filepart_length, >, MAX_PATH))
 			break;
-		barrier_var(filepart_length);
 		payload += filepart_length;
 		length += filepart_length;
 
@@ -510,7 +506,7 @@ is_ancestor_in_allowed_inodes(struct dentry* filp_dentry)
 {
 	struct dentry* parent_dentry;
 #ifdef UNROLL
-#pragma unroll
+	__pragma_loop_unroll
 #endif
 	for (int i = 0; i < MAX_PATH_DEPTH; i++) {
 		u64 dir_ino = BPF_CORE_READ(filp_dentry, d_inode, i_ino);
@@ -572,19 +568,18 @@ ssize_t BPF_KPROBE(kprobe__proc_sys_write,
 	sysctl_data->sysctl_val_length = 0;
 	sysctl_data->sysctl_path_length = 0;
 
-	size_t sysctl_val_length = bpf_probe_read_str(payload, CTL_MAXNAME, buf);
-	barrier_var(sysctl_val_length);
-	if (sysctl_val_length <= CTL_MAXNAME) {
-		barrier_var(sysctl_val_length);
+	size_t sysctl_val_length = bpf_probe_read_kernel_str(payload,
+							     CTL_MAXNAME, buf);
+	if (bpf_cmp_likely(sysctl_val_length, <=, CTL_MAXNAME)) {
 		sysctl_data->sysctl_val_length = sysctl_val_length;
 		payload += sysctl_val_length;
 	}
 
-	size_t sysctl_path_length = bpf_probe_read_str(payload, MAX_PATH,
-						       BPF_CORE_READ(filp, f_path.dentry, d_name.name));
-	barrier_var(sysctl_path_length);
-	if (sysctl_path_length <= MAX_PATH) {
-		barrier_var(sysctl_path_length);
+	size_t sysctl_path_length =
+		bpf_probe_read_kernel_str(payload, MAX_PATH,
+					  BPF_CORE_READ(filp, f_path.dentry,
+							d_name.name));
+	if (bpf_cmp_likely(sysctl_path_length, <=, MAX_PATH)) {
 		sysctl_data->sysctl_path_length = sysctl_path_length;
 		payload += sysctl_path_length;
 	}
@@ -601,7 +596,7 @@ out:
 }
 
 SEC("tracepoint/syscalls/sys_enter_kill")
-int tracepoint__syscalls__sys_enter_kill(struct trace_event_raw_sys_enter* ctx)
+int tracepoint__syscalls__sys_enter_kill(struct syscall_trace_enter* ctx)
 {
 	struct bpf_func_stats_ctx stats_ctx;
 
@@ -632,13 +627,14 @@ int raw_tracepoint__sched_process_exit(void* ctx)
 	struct kernfs_node* proc_kernfs = BPF_CORE_READ(task, cgroups, dfl_cgrp, kn);
 
 #ifdef UNROLL
-#pragma unroll
+	__pragma_loop_unroll
 #endif
 	for (int i = 0; i < ARRAY_SIZE(arr_struct->array); i++) {
 		struct var_kill_data_t* past_kill_data = &arr_struct->array[i];
 
-		if (past_kill_data != NULL && past_kill_data->kill_target_pid == tpid) {
-			bpf_probe_read(kill_data, sizeof(*past_kill_data), past_kill_data);
+		if (past_kill_data != NULL && past_kill_data->kill_target_pid == (pid_t)tpid) {
+			bpf_probe_read_kernel(kill_data, sizeof(*past_kill_data),
+					      past_kill_data);
 			void* payload = kill_data->payload;
 			size_t offset = kill_data->payload_length;
 			if (offset >= MAX_METADATA_PAYLOAD_LEN + MAX_CGROUP_PAYLOAD_LEN)
@@ -649,18 +645,16 @@ int raw_tracepoint__sched_process_exit(void* ctx)
 			kill_data->kill_target_cgroup_proc_length = 0;
 
 			size_t comm_length = bpf_core_read_str(payload, TASK_COMM_LEN, &task->comm);
-			barrier_var(comm_length);
-			if (comm_length <= TASK_COMM_LEN) {
-				barrier_var(comm_length);
+			if (bpf_cmp_likely(comm_length, <=, TASK_COMM_LEN)) {
 				kill_data->kill_target_name_length = comm_length;
 				payload += comm_length;
 			}
 
-			size_t cgroup_proc_length = bpf_probe_read_str(payload, KILL_TARGET_LEN,
-								       BPF_CORE_READ(proc_kernfs, name));
-			barrier_var(cgroup_proc_length);
-			if (cgroup_proc_length <= KILL_TARGET_LEN) {
-				barrier_var(cgroup_proc_length);
+			size_t cgroup_proc_length =
+				bpf_probe_read_kernel_str(payload,
+							  KILL_TARGET_LEN,
+							  BPF_CORE_READ(proc_kernfs, name));
+			if (bpf_cmp_likely(cgroup_proc_length, <=, KILL_TARGET_LEN)) {
 				kill_data->kill_target_cgroup_proc_length = cgroup_proc_length;
 				payload += cgroup_proc_length;
 			}
@@ -718,10 +712,9 @@ int raw_tracepoint__sched_process_exec(struct bpf_raw_tracepoint_args* ctx)
 	proc_exec_data->parent_start_time = BPF_CORE_READ(parent_task, start_time);
 
 	const char* filename = BPF_CORE_READ(bprm, filename);
-	size_t bin_path_length = bpf_probe_read_str(payload, MAX_FILENAME_LEN, filename);
-	barrier_var(bin_path_length);
-	if (bin_path_length <= MAX_FILENAME_LEN) {
-		barrier_var(bin_path_length);
+	size_t bin_path_length =
+		bpf_probe_read_kernel_str(payload, MAX_FILENAME_LEN, filename);
+	if (bpf_cmp_likely(bin_path_length, <=, MAX_FILENAME_LEN)) {
 		proc_exec_data->bin_path_length = bin_path_length;
 		payload += bin_path_length;
 	}
@@ -731,8 +724,7 @@ int raw_tracepoint__sched_process_exec(struct bpf_raw_tracepoint_args* ctx)
 	unsigned int cmdline_length = probe_read_lim(payload, arg_start,
 						     arg_end - arg_start, MAX_ARGS_LEN);
 
-	if (cmdline_length <= MAX_ARGS_LEN) {
-		barrier_var(cmdline_length);
+	if (bpf_cmp_likely(cmdline_length, <=, MAX_ARGS_LEN)) {
 		proc_exec_data->cmdline_length = cmdline_length;
 		payload += cmdline_length;
 	}
@@ -809,9 +801,7 @@ int kprobe_ret__do_filp_open(struct pt_regs* ctx)
 	payload = populate_cgroup_info(&filemod_data->cgroup_data, task, payload);
 
 	size_t len = read_absolute_file_path_from_dentry(filp_dentry, payload);
-	barrier_var(len);
-	if (len <= MAX_FILEPATH_LENGTH) {
-		barrier_var(len);
+	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
 		payload += len;
 		filemod_data->dst_filepath_length = len;
 	}
@@ -826,7 +816,7 @@ out:
 
 SEC("kprobe/vfs_link")
 int BPF_KPROBE(kprobe__vfs_link,
-	       struct dentry* old_dentry, struct user_namespace *mnt_userns,
+	       struct dentry* old_dentry, struct mnt_idmap *idmap,
 	       struct inode* dir, struct dentry* new_dentry,
 	       struct inode** delegated_inode)
 {
@@ -864,17 +854,13 @@ int BPF_KPROBE(kprobe__vfs_link,
 	payload = populate_cgroup_info(&filemod_data->cgroup_data, task, payload);
 
 	size_t len = read_absolute_file_path_from_dentry(old_dentry, payload);
-	barrier_var(len);
-	if (len <= MAX_FILEPATH_LENGTH) {
-		barrier_var(len);
+	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
 		payload += len;
 		filemod_data->src_filepath_length = len;
 	}
 
 	len = read_absolute_file_path_from_dentry(new_dentry, payload);
-	barrier_var(len);
-	if (len <= MAX_FILEPATH_LENGTH) {
-		barrier_var(len);
+	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
 		payload += len;
 		filemod_data->dst_filepath_length = len;
 	}
@@ -922,17 +908,14 @@ int BPF_KPROBE(kprobe__vfs_symlink, struct inode* dir, struct dentry* dentry,
 					      filemod_data->payload);
 	payload = populate_cgroup_info(&filemod_data->cgroup_data, task, payload);
 
-	size_t len = bpf_probe_read_str(payload, MAX_FILEPATH_LENGTH, oldname);
-	barrier_var(len);
-	if (len <= MAX_FILEPATH_LENGTH) {
-		barrier_var(len);
+	size_t len = bpf_probe_read_kernel_str(payload, MAX_FILEPATH_LENGTH,
+					       oldname);
+	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
 		payload += len;
 		filemod_data->src_filepath_length = len;
 	}
 	len = read_absolute_file_path_from_dentry(dentry, payload);
-	barrier_var(len);
-	if (len <= MAX_FILEPATH_LENGTH) {
-		barrier_var(len);
+	if (bpf_cmp_likely(len, <=, MAX_FILEPATH_LENGTH)) {
 		payload += len;
 		filemod_data->dst_filepath_length = len;
 	}
diff --git a/tools/testing/selftests/bpf/progs/pyperf.h b/tools/testing/selftests/bpf/progs/pyperf.h
index 6c7b1fb268d6..86484f07e1d1 100644
--- a/tools/testing/selftests/bpf/progs/pyperf.h
+++ b/tools/testing/selftests/bpf/progs/pyperf.h
@@ -7,6 +7,8 @@
 #include <stdbool.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "bpf_compiler.h"
 
 #define FUNCTION_NAME_LEN 64
 #define FILE_NAME_LEN 128
@@ -294,17 +296,22 @@ int __on_event(struct bpf_raw_tracepoint_args *ctx)
 	if (ctx.done)
 		return 0;
 #else
-#ifdef NO_UNROLL
-#pragma clang loop unroll(disable)
+#if defined(USE_ITER)
+/* no for loop, no unrolling */
+#elif defined(NO_UNROLL)
+	__pragma_loop_no_unroll
+#elif defined(UNROLL_COUNT)
+	__pragma_loop_unroll_count(UNROLL_COUNT)
 #else
-#ifdef UNROLL_COUNT
-#pragma clang loop unroll_count(UNROLL_COUNT)
-#else
-#pragma clang loop unroll(full)
-#endif
+	__pragma_loop_unroll_full
 #endif /* NO_UNROLL */
 		/* Unwind python stack */
+#ifdef USE_ITER
+		int i;
+		bpf_for(i, 0, STACK_MAX_LEN) {
+#else /* !USE_ITER */
 		for (int i = 0; i < STACK_MAX_LEN; ++i) {
+#endif
 			if (frame_ptr && get_frame_data(frame_ptr, pidData, &frame, &sym)) {
 				int32_t new_symbol_id = *symbol_counter * 64 + cur_cpu;
 				int32_t *symbol_id = bpf_map_lookup_elem(&symbolmap, &sym);
@@ -339,7 +346,7 @@ int __on_event(struct bpf_raw_tracepoint_args *ctx)
 SEC("raw_tracepoint/kfree_skb")
 int on_event(struct bpf_raw_tracepoint_args* ctx)
 {
-	int i, ret = 0;
+	int ret = 0;
 	ret |= __on_event(ctx);
 	ret |= __on_event(ctx);
 	ret |= __on_event(ctx);
diff --git a/tools/testing/selftests/bpf/progs/pyperf180.c b/tools/testing/selftests/bpf/progs/pyperf180.c
index c39f559d3100..42c4a8b62e36 100644
--- a/tools/testing/selftests/bpf/progs/pyperf180.c
+++ b/tools/testing/selftests/bpf/progs/pyperf180.c
@@ -1,4 +1,26 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2019 Facebook
 #define STACK_MAX_LEN 180
+
+/* llvm upstream commit at clang18
+ *   https://github.com/llvm/llvm-project/commit/1a2e77cf9e11dbf56b5720c607313a566eebb16e
+ * changed inlining behavior and caused compilation failure as some branch
+ * target distance exceeded 16bit representation which is the maximum for
+ * cpu v1/v2/v3. Macro __BPF_CPU_VERSION__ is later implemented in clang18
+ * to specify which cpu version is used for compilation. So a smaller
+ * unroll_count can be set if __BPF_CPU_VERSION__ is less than 4, which
+ * reduced some branch target distances and resolved the compilation failure.
+ *
+ * To capture the case where a developer/ci uses clang18 but the corresponding
+ * repo checkpoint does not have __BPF_CPU_VERSION__, a smaller unroll_count
+ * will be set as well to prevent potential compilation failures.
+ */
+#ifdef __BPF_CPU_VERSION__
+#if __BPF_CPU_VERSION__ < 4
+#define UNROLL_COUNT 90
+#endif
+#elif __clang_major__ == 18
+#define UNROLL_COUNT 90
+#endif
+
 #include "pyperf.h"
diff --git a/tools/testing/selftests/bpf/progs/pyperf600_iter.c b/tools/testing/selftests/bpf/progs/pyperf600_iter.c
new file mode 100644
index 000000000000..d62e1b200c30
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/pyperf600_iter.c
@@ -0,0 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2023 Meta Platforms, Inc. and affiliates.
+#define STACK_MAX_LEN 600
+#define SUBPROGS
+#define NO_UNROLL
+#define USE_ITER
+#include "pyperf.h"
diff --git a/tools/testing/selftests/bpf/progs/pyperf600_nounroll.c b/tools/testing/selftests/bpf/progs/pyperf600_nounroll.c
index 6beff7502f4d..520b58c4f8db 100644
--- a/tools/testing/selftests/bpf/progs/pyperf600_nounroll.c
+++ b/tools/testing/selftests/bpf/progs/pyperf600_nounroll.c
@@ -2,7 +2,4 @@
 // Copyright (c) 2019 Facebook
 #define STACK_MAX_LEN 600
 #define NO_UNROLL
-/* clang will not unroll at all.
- * Total program size is around 2k insns
- */
 #include "pyperf.h"
diff --git a/tools/testing/selftests/bpf/progs/raw_tp_null.c b/tools/testing/selftests/bpf/progs/raw_tp_null.c
new file mode 100644
index 000000000000..efa416f53968
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/raw_tp_null.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+int tid;
+int i;
+
+SEC("tp_btf/bpf_testmod_test_raw_tp_null_tp")
+int BPF_PROG(test_raw_tp_null, struct sk_buff *skb)
+{
+	struct task_struct *task = bpf_get_current_task_btf();
+
+	if (task->pid != tid)
+		return 0;
+
+	/* If dead code elimination kicks in, the increment +=2 will be
+	 * removed. For raw_tp programs attaching to tracepoints in kernel
+	 * modules, we mark input arguments as PTR_MAYBE_NULL, so branch
+	 * prediction should never kick in.
+	 */
+	asm volatile ("%[i] += 1; if %[ctx] != 0 goto +1; %[i] += 2;"
+			: [i]"+r"(i)
+			: [ctx]"r"(skb)
+			: "memory");
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c b/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c
new file mode 100644
index 000000000000..0d58114a4955
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/raw_tp_null_fail.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+/* Ensure module parameter has PTR_MAYBE_NULL */
+SEC("tp_btf/bpf_testmod_test_raw_tp_null_tp")
+__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'")
+int test_raw_tp_null_bpf_testmod_test_raw_tp_null_arg_1(void *ctx) {
+    asm volatile("r1 = *(u64 *)(r1 +0); r1 = *(u64 *)(r1 +0);" ::: __clobber_all);
+    return 0;
+}
+
+/* Check NULL marking */
+SEC("tp_btf/sched_pi_setprio")
+__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'")
+int test_raw_tp_null_sched_pi_setprio_arg_2(void *ctx) {
+    asm volatile("r1 = *(u64 *)(r1 +8); r1 = *(u64 *)(r1 +0);" ::: __clobber_all);
+    return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/rbtree.c b/tools/testing/selftests/bpf/progs/rbtree.c
new file mode 100644
index 000000000000..49fe93d7e059
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/rbtree.c
@@ -0,0 +1,323 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_experimental.h"
+
+struct node_data {
+	long key;
+	long data;
+	struct bpf_rb_node node;
+};
+
+struct root_nested_inner {
+	struct bpf_spin_lock glock;
+	struct bpf_rb_root root __contains(node_data, node);
+};
+
+struct root_nested {
+	struct root_nested_inner inner;
+};
+
+long less_callback_ran = -1;
+long removed_key = -1;
+long first_data[2] = {-1, -1};
+
+#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8)))
+private(A) struct bpf_spin_lock glock;
+private(A) struct bpf_rb_root groot __contains(node_data, node);
+private(A) struct bpf_rb_root groot_array[2] __contains(node_data, node);
+private(A) struct bpf_rb_root groot_array_one[1] __contains(node_data, node);
+private(B) struct root_nested groot_nested;
+
+static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	struct node_data *node_a;
+	struct node_data *node_b;
+
+	node_a = container_of(a, struct node_data, node);
+	node_b = container_of(b, struct node_data, node);
+	less_callback_ran = 1;
+
+	return node_a->key < node_b->key;
+}
+
+static long __add_three(struct bpf_rb_root *root, struct bpf_spin_lock *lock)
+{
+	struct node_data *n, *m;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 1;
+	n->key = 5;
+
+	m = bpf_obj_new(typeof(*m));
+	if (!m) {
+		bpf_obj_drop(n);
+		return 2;
+	}
+	m->key = 1;
+
+	bpf_spin_lock(lock);
+	bpf_rbtree_add(root, &n->node, less);
+	bpf_rbtree_add(root, &m->node, less);
+	bpf_spin_unlock(lock);
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 3;
+	n->key = 3;
+
+	bpf_spin_lock(lock);
+	bpf_rbtree_add(root, &n->node, less);
+	bpf_spin_unlock(lock);
+	return 0;
+}
+
+SEC("tc")
+long rbtree_add_nodes(void *ctx)
+{
+	return __add_three(&groot, &glock);
+}
+
+SEC("tc")
+long rbtree_add_nodes_nested(void *ctx)
+{
+	return __add_three(&groot_nested.inner.root, &groot_nested.inner.glock);
+}
+
+SEC("tc")
+long rbtree_add_and_remove(void *ctx)
+{
+	struct bpf_rb_node *res = NULL;
+	struct node_data *n, *m = NULL;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		goto err_out;
+	n->key = 5;
+
+	m = bpf_obj_new(typeof(*m));
+	if (!m)
+		goto err_out;
+	m->key = 3;
+
+	bpf_spin_lock(&glock);
+	bpf_rbtree_add(&groot, &n->node, less);
+	bpf_rbtree_add(&groot, &m->node, less);
+	res = bpf_rbtree_remove(&groot, &n->node);
+	bpf_spin_unlock(&glock);
+
+	if (!res)
+		return 1;
+
+	n = container_of(res, struct node_data, node);
+	removed_key = n->key;
+	bpf_obj_drop(n);
+
+	return 0;
+err_out:
+	if (n)
+		bpf_obj_drop(n);
+	if (m)
+		bpf_obj_drop(m);
+	return 1;
+}
+
+SEC("tc")
+long rbtree_add_and_remove_array(void *ctx)
+{
+	struct bpf_rb_node *res1 = NULL, *res2 = NULL, *res3 = NULL;
+	struct node_data *nodes[3][2] = {{NULL, NULL}, {NULL, NULL}, {NULL, NULL}};
+	struct node_data *n;
+	long k1 = -1, k2 = -1, k3 = -1;
+	int i, j;
+
+	for (i = 0; i < 3; i++) {
+		for (j = 0; j < 2; j++) {
+			nodes[i][j] = bpf_obj_new(typeof(*nodes[i][j]));
+			if (!nodes[i][j])
+				goto err_out;
+			nodes[i][j]->key = i * 2 + j;
+		}
+	}
+
+	bpf_spin_lock(&glock);
+	for (i = 0; i < 2; i++)
+		for (j = 0; j < 2; j++)
+			bpf_rbtree_add(&groot_array[i], &nodes[i][j]->node, less);
+	for (j = 0; j < 2; j++)
+		bpf_rbtree_add(&groot_array_one[0], &nodes[2][j]->node, less);
+	res1 = bpf_rbtree_remove(&groot_array[0], &nodes[0][0]->node);
+	res2 = bpf_rbtree_remove(&groot_array[1], &nodes[1][0]->node);
+	res3 = bpf_rbtree_remove(&groot_array_one[0], &nodes[2][0]->node);
+	bpf_spin_unlock(&glock);
+
+	if (res1) {
+		n = container_of(res1, struct node_data, node);
+		k1 = n->key;
+		bpf_obj_drop(n);
+	}
+	if (res2) {
+		n = container_of(res2, struct node_data, node);
+		k2 = n->key;
+		bpf_obj_drop(n);
+	}
+	if (res3) {
+		n = container_of(res3, struct node_data, node);
+		k3 = n->key;
+		bpf_obj_drop(n);
+	}
+	if (k1 != 0 || k2 != 2 || k3 != 4)
+		return 2;
+
+	return 0;
+
+err_out:
+	for (i = 0; i < 3; i++) {
+		for (j = 0; j < 2; j++) {
+			if (nodes[i][j])
+				bpf_obj_drop(nodes[i][j]);
+		}
+	}
+	return 1;
+}
+
+SEC("tc")
+long rbtree_first_and_remove(void *ctx)
+{
+	struct bpf_rb_node *res = NULL;
+	struct node_data *n, *m, *o;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 1;
+	n->key = 3;
+	n->data = 4;
+
+	m = bpf_obj_new(typeof(*m));
+	if (!m)
+		goto err_out;
+	m->key = 5;
+	m->data = 6;
+
+	o = bpf_obj_new(typeof(*o));
+	if (!o)
+		goto err_out;
+	o->key = 1;
+	o->data = 2;
+
+	bpf_spin_lock(&glock);
+	bpf_rbtree_add(&groot, &n->node, less);
+	bpf_rbtree_add(&groot, &m->node, less);
+	bpf_rbtree_add(&groot, &o->node, less);
+
+	res = bpf_rbtree_first(&groot);
+	if (!res) {
+		bpf_spin_unlock(&glock);
+		return 2;
+	}
+
+	o = container_of(res, struct node_data, node);
+	first_data[0] = o->data;
+
+	res = bpf_rbtree_remove(&groot, &o->node);
+	bpf_spin_unlock(&glock);
+
+	if (!res)
+		return 5;
+
+	o = container_of(res, struct node_data, node);
+	removed_key = o->key;
+	bpf_obj_drop(o);
+
+	bpf_spin_lock(&glock);
+	res = bpf_rbtree_first(&groot);
+	if (!res) {
+		bpf_spin_unlock(&glock);
+		return 3;
+	}
+
+	o = container_of(res, struct node_data, node);
+	first_data[1] = o->data;
+	bpf_spin_unlock(&glock);
+
+	return 0;
+err_out:
+	if (n)
+		bpf_obj_drop(n);
+	if (m)
+		bpf_obj_drop(m);
+	return 1;
+}
+
+SEC("tc")
+long rbtree_api_release_aliasing(void *ctx)
+{
+	struct node_data *n, *m, *o;
+	struct bpf_rb_node *res, *res2;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 1;
+	n->key = 41;
+	n->data = 42;
+
+	bpf_spin_lock(&glock);
+	bpf_rbtree_add(&groot, &n->node, less);
+	bpf_spin_unlock(&glock);
+
+	bpf_spin_lock(&glock);
+
+	/* m and o point to the same node,
+	 * but verifier doesn't know this
+	 */
+	res = bpf_rbtree_first(&groot);
+	if (!res)
+		goto err_out;
+	o = container_of(res, struct node_data, node);
+
+	res = bpf_rbtree_first(&groot);
+	if (!res)
+		goto err_out;
+	m = container_of(res, struct node_data, node);
+
+	res = bpf_rbtree_remove(&groot, &m->node);
+	/* Retval of previous remove returns an owning reference to m,
+	 * which is the same node non-owning ref o is pointing at.
+	 * We can safely try to remove o as the second rbtree_remove will
+	 * return NULL since the node isn't in a tree.
+	 *
+	 * Previously we relied on the verifier type system + rbtree_remove
+	 * invalidating non-owning refs to ensure that rbtree_remove couldn't
+	 * fail, but now rbtree_remove does runtime checking so we no longer
+	 * invalidate non-owning refs after remove.
+	 */
+	res2 = bpf_rbtree_remove(&groot, &o->node);
+
+	bpf_spin_unlock(&glock);
+
+	if (res) {
+		o = container_of(res, struct node_data, node);
+		first_data[0] = o->data;
+		bpf_obj_drop(o);
+	}
+	if (res2) {
+		/* The second remove fails, so res2 is null and this doesn't
+		 * execute
+		 */
+		m = container_of(res2, struct node_data, node);
+		first_data[1] = m->data;
+		bpf_obj_drop(m);
+	}
+	return 0;
+
+err_out:
+	bpf_spin_unlock(&glock);
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/rbtree_btf_fail__add_wrong_type.c b/tools/testing/selftests/bpf/progs/rbtree_btf_fail__add_wrong_type.c
new file mode 100644
index 000000000000..60079b202c07
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/rbtree_btf_fail__add_wrong_type.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_experimental.h"
+
+struct node_data {
+	int key;
+	int data;
+	struct bpf_rb_node node;
+};
+
+struct node_data2 {
+	int key;
+	struct bpf_rb_node node;
+	int data;
+};
+
+static bool less2(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	struct node_data2 *node_a;
+	struct node_data2 *node_b;
+
+	node_a = container_of(a, struct node_data2, node);
+	node_b = container_of(b, struct node_data2, node);
+
+	return node_a->key < node_b->key;
+}
+
+#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8)))
+private(A) struct bpf_spin_lock glock;
+private(A) struct bpf_rb_root groot __contains(node_data, node);
+
+SEC("tc")
+long rbtree_api_add__add_wrong_type(void *ctx)
+{
+	struct node_data2 *n;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 1;
+
+	bpf_spin_lock(&glock);
+	bpf_rbtree_add(&groot, &n->node, less2);
+	bpf_spin_unlock(&glock);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/rbtree_btf_fail__wrong_node_type.c b/tools/testing/selftests/bpf/progs/rbtree_btf_fail__wrong_node_type.c
new file mode 100644
index 000000000000..7651843f5a80
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/rbtree_btf_fail__wrong_node_type.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_experimental.h"
+
+/* BTF load should fail as bpf_rb_root __contains this type and points to
+ * 'node', but 'node' is not a bpf_rb_node
+ */
+struct node_data {
+	int key;
+	int data;
+	struct bpf_list_node node;
+};
+
+#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8)))
+private(A) struct bpf_spin_lock glock;
+private(A) struct bpf_rb_root groot __contains(node_data, node);
+
+SEC("tc")
+long rbtree_api_add__wrong_node_type(void *ctx)
+{
+	struct node_data *n;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 1;
+
+	bpf_spin_lock(&glock);
+	bpf_rbtree_first(&groot);
+	bpf_spin_unlock(&glock);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/rbtree_fail.c b/tools/testing/selftests/bpf/progs/rbtree_fail.c
new file mode 100644
index 000000000000..4acb6af2dfe3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/rbtree_fail.c
@@ -0,0 +1,304 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_experimental.h"
+#include "bpf_misc.h"
+
+struct node_data {
+	long key;
+	long data;
+	struct bpf_rb_node node;
+};
+
+#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8)))
+private(A) struct bpf_spin_lock glock;
+private(A) struct bpf_rb_root groot __contains(node_data, node);
+private(A) struct bpf_rb_root groot2 __contains(node_data, node);
+
+static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	struct node_data *node_a;
+	struct node_data *node_b;
+
+	node_a = container_of(a, struct node_data, node);
+	node_b = container_of(b, struct node_data, node);
+
+	return node_a->key < node_b->key;
+}
+
+SEC("?tc")
+__failure __msg("bpf_spin_lock at off=16 must be held for bpf_rb_root")
+long rbtree_api_nolock_add(void *ctx)
+{
+	struct node_data *n;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 1;
+
+	bpf_rbtree_add(&groot, &n->node, less);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("bpf_spin_lock at off=16 must be held for bpf_rb_root")
+long rbtree_api_nolock_remove(void *ctx)
+{
+	struct node_data *n;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 1;
+
+	bpf_spin_lock(&glock);
+	bpf_rbtree_add(&groot, &n->node, less);
+	bpf_spin_unlock(&glock);
+
+	bpf_rbtree_remove(&groot, &n->node);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("bpf_spin_lock at off=16 must be held for bpf_rb_root")
+long rbtree_api_nolock_first(void *ctx)
+{
+	bpf_rbtree_first(&groot);
+	return 0;
+}
+
+SEC("?tc")
+__retval(0)
+long rbtree_api_remove_unadded_node(void *ctx)
+{
+	struct node_data *n, *m;
+	struct bpf_rb_node *res_n, *res_m;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 1;
+
+	m = bpf_obj_new(typeof(*m));
+	if (!m) {
+		bpf_obj_drop(n);
+		return 1;
+	}
+
+	bpf_spin_lock(&glock);
+	bpf_rbtree_add(&groot, &n->node, less);
+
+	res_n = bpf_rbtree_remove(&groot, &n->node);
+
+	res_m = bpf_rbtree_remove(&groot, &m->node);
+	bpf_spin_unlock(&glock);
+
+	bpf_obj_drop(m);
+	if (res_n)
+		bpf_obj_drop(container_of(res_n, struct node_data, node));
+	if (res_m) {
+		bpf_obj_drop(container_of(res_m, struct node_data, node));
+		/* m was not added to the rbtree */
+		return 2;
+	}
+
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("Unreleased reference id=3 alloc_insn={{[0-9]+}}")
+long rbtree_api_remove_no_drop(void *ctx)
+{
+	struct bpf_rb_node *res;
+	struct node_data *n;
+
+	bpf_spin_lock(&glock);
+	res = bpf_rbtree_first(&groot);
+	if (!res)
+		goto unlock_err;
+
+	res = bpf_rbtree_remove(&groot, res);
+
+	if (res) {
+		n = container_of(res, struct node_data, node);
+		__sink(n);
+	}
+	bpf_spin_unlock(&glock);
+
+	/* if (res) { bpf_obj_drop(n); } is missing here */
+	return 0;
+
+unlock_err:
+	bpf_spin_unlock(&glock);
+	return 1;
+}
+
+SEC("?tc")
+__failure __msg("arg#1 expected pointer to allocated object")
+long rbtree_api_add_to_multiple_trees(void *ctx)
+{
+	struct node_data *n;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 1;
+
+	bpf_spin_lock(&glock);
+	bpf_rbtree_add(&groot, &n->node, less);
+
+	/* This add should fail since n already in groot's tree */
+	bpf_rbtree_add(&groot2, &n->node, less);
+	bpf_spin_unlock(&glock);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("dereference of modified ptr_or_null_ ptr R2 off=16 disallowed")
+long rbtree_api_use_unchecked_remove_retval(void *ctx)
+{
+	struct bpf_rb_node *res;
+
+	bpf_spin_lock(&glock);
+
+	res = bpf_rbtree_first(&groot);
+	if (!res)
+		goto err_out;
+	res = bpf_rbtree_remove(&groot, res);
+
+	bpf_spin_unlock(&glock);
+
+	bpf_spin_lock(&glock);
+	/* Must check res for NULL before using in rbtree_add below */
+	bpf_rbtree_add(&groot, res, less);
+	bpf_spin_unlock(&glock);
+	return 0;
+
+err_out:
+	bpf_spin_unlock(&glock);
+	return 1;
+}
+
+SEC("?tc")
+__failure __msg("bpf_rbtree_remove can only take non-owning or refcounted bpf_rb_node pointer")
+long rbtree_api_add_release_unlock_escape(void *ctx)
+{
+	struct node_data *n;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 1;
+
+	bpf_spin_lock(&glock);
+	bpf_rbtree_add(&groot, &n->node, less);
+	bpf_spin_unlock(&glock);
+
+	bpf_spin_lock(&glock);
+	/* After add() in previous critical section, n should be
+	 * release_on_unlock and released after previous spin_unlock,
+	 * so should not be possible to use it here
+	 */
+	bpf_rbtree_remove(&groot, &n->node);
+	bpf_spin_unlock(&glock);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("bpf_rbtree_remove can only take non-owning or refcounted bpf_rb_node pointer")
+long rbtree_api_first_release_unlock_escape(void *ctx)
+{
+	struct bpf_rb_node *res;
+	struct node_data *n;
+
+	bpf_spin_lock(&glock);
+	res = bpf_rbtree_first(&groot);
+	if (!res) {
+		bpf_spin_unlock(&glock);
+		return 1;
+	}
+	n = container_of(res, struct node_data, node);
+	bpf_spin_unlock(&glock);
+
+	bpf_spin_lock(&glock);
+	/* After first() in previous critical section, n should be
+	 * release_on_unlock and released after previous spin_unlock,
+	 * so should not be possible to use it here
+	 */
+	bpf_rbtree_remove(&groot, &n->node);
+	bpf_spin_unlock(&glock);
+	return 0;
+}
+
+static bool less__bad_fn_call_add(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	struct node_data *node_a;
+	struct node_data *node_b;
+
+	node_a = container_of(a, struct node_data, node);
+	node_b = container_of(b, struct node_data, node);
+	bpf_rbtree_add(&groot, &node_a->node, less);
+
+	return node_a->key < node_b->key;
+}
+
+static bool less__bad_fn_call_remove(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	struct node_data *node_a;
+	struct node_data *node_b;
+
+	node_a = container_of(a, struct node_data, node);
+	node_b = container_of(b, struct node_data, node);
+	bpf_rbtree_remove(&groot, &node_a->node);
+
+	return node_a->key < node_b->key;
+}
+
+static bool less__bad_fn_call_first_unlock_after(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	struct node_data *node_a;
+	struct node_data *node_b;
+
+	node_a = container_of(a, struct node_data, node);
+	node_b = container_of(b, struct node_data, node);
+	bpf_rbtree_first(&groot);
+	bpf_spin_unlock(&glock);
+
+	return node_a->key < node_b->key;
+}
+
+static __always_inline
+long add_with_cb(bool (cb)(struct bpf_rb_node *a, const struct bpf_rb_node *b))
+{
+	struct node_data *n;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 1;
+
+	bpf_spin_lock(&glock);
+	bpf_rbtree_add(&groot, &n->node, cb);
+	bpf_spin_unlock(&glock);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("arg#1 expected pointer to allocated object")
+long rbtree_api_add_bad_cb_bad_fn_call_add(void *ctx)
+{
+	return add_with_cb(less__bad_fn_call_add);
+}
+
+SEC("?tc")
+__failure __msg("rbtree_remove not allowed in rbtree cb")
+long rbtree_api_add_bad_cb_bad_fn_call_remove(void *ctx)
+{
+	return add_with_cb(less__bad_fn_call_remove);
+}
+
+SEC("?tc")
+__failure __msg("can't spin_{lock,unlock} in rbtree cb")
+long rbtree_api_add_bad_cb_bad_fn_call_first_unlock_after(void *ctx)
+{
+	return add_with_cb(less__bad_fn_call_first_unlock_after);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/rbtree_search.c b/tools/testing/selftests/bpf/progs/rbtree_search.c
new file mode 100644
index 000000000000..b05565d1db0d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/rbtree_search.c
@@ -0,0 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+struct node_data {
+	struct bpf_refcount ref;
+	struct bpf_rb_node r0;
+	struct bpf_rb_node r1;
+	int key0;
+	int key1;
+};
+
+#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8)))
+private(A) struct bpf_spin_lock glock0;
+private(A) struct bpf_rb_root groot0 __contains(node_data, r0);
+
+private(B) struct bpf_spin_lock glock1;
+private(B) struct bpf_rb_root groot1 __contains(node_data, r1);
+
+#define rb_entry(ptr, type, member) container_of(ptr, type, member)
+#define NR_NODES 16
+
+int zero = 0;
+
+static bool less0(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	struct node_data *node_a;
+	struct node_data *node_b;
+
+	node_a = rb_entry(a, struct node_data, r0);
+	node_b = rb_entry(b, struct node_data, r0);
+
+	return node_a->key0 < node_b->key0;
+}
+
+static bool less1(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	struct node_data *node_a;
+	struct node_data *node_b;
+
+	node_a = rb_entry(a, struct node_data, r1);
+	node_b = rb_entry(b, struct node_data, r1);
+
+	return node_a->key1 < node_b->key1;
+}
+
+SEC("syscall")
+__retval(0)
+long rbtree_search(void *ctx)
+{
+	struct bpf_rb_node *rb_n, *rb_m, *gc_ns[NR_NODES];
+	long lookup_key = NR_NODES / 2;
+	struct node_data *n, *m;
+	int i, nr_gc = 0;
+
+	for (i = zero; i < NR_NODES && can_loop; i++) {
+		n = bpf_obj_new(typeof(*n));
+		if (!n)
+			return __LINE__;
+
+		m = bpf_refcount_acquire(n);
+
+		n->key0 = i;
+		m->key1 = i;
+
+		bpf_spin_lock(&glock0);
+		bpf_rbtree_add(&groot0, &n->r0, less0);
+		bpf_spin_unlock(&glock0);
+
+		bpf_spin_lock(&glock1);
+		bpf_rbtree_add(&groot1, &m->r1, less1);
+		bpf_spin_unlock(&glock1);
+	}
+
+	n = NULL;
+	bpf_spin_lock(&glock0);
+	rb_n = bpf_rbtree_root(&groot0);
+	while (can_loop) {
+		if (!rb_n) {
+			bpf_spin_unlock(&glock0);
+			return __LINE__;
+		}
+
+		n = rb_entry(rb_n, struct node_data, r0);
+		if (lookup_key == n->key0)
+			break;
+		if (nr_gc < NR_NODES)
+			gc_ns[nr_gc++] = rb_n;
+		if (lookup_key < n->key0)
+			rb_n = bpf_rbtree_left(&groot0, rb_n);
+		else
+			rb_n = bpf_rbtree_right(&groot0, rb_n);
+	}
+
+	if (!n || lookup_key != n->key0) {
+		bpf_spin_unlock(&glock0);
+		return __LINE__;
+	}
+
+	for (i = 0; i < nr_gc; i++) {
+		rb_n = gc_ns[i];
+		gc_ns[i] = bpf_rbtree_remove(&groot0, rb_n);
+	}
+
+	m = bpf_refcount_acquire(n);
+	bpf_spin_unlock(&glock0);
+
+	for (i = 0; i < nr_gc; i++) {
+		rb_n = gc_ns[i];
+		if (rb_n) {
+			n = rb_entry(rb_n, struct node_data, r0);
+			bpf_obj_drop(n);
+		}
+	}
+
+	if (!m)
+		return __LINE__;
+
+	bpf_spin_lock(&glock1);
+	rb_m = bpf_rbtree_remove(&groot1, &m->r1);
+	bpf_spin_unlock(&glock1);
+	bpf_obj_drop(m);
+	if (!rb_m)
+		return __LINE__;
+	bpf_obj_drop(rb_entry(rb_m, struct node_data, r1));
+
+	return 0;
+}
+
+#define TEST_ROOT(dolock)				\
+SEC("syscall")						\
+__failure __msg(MSG)					\
+long test_root_spinlock_##dolock(void *ctx)		\
+{							\
+	struct bpf_rb_node *rb_n;			\
+	__u64 jiffies = 0;				\
+							\
+	if (dolock)					\
+		bpf_spin_lock(&glock0);			\
+	rb_n = bpf_rbtree_root(&groot0);		\
+	if (rb_n)					\
+		jiffies = bpf_jiffies64();		\
+	if (dolock)					\
+		bpf_spin_unlock(&glock0);		\
+							\
+	return !!jiffies;				\
+}
+
+#define TEST_LR(op, dolock)				\
+SEC("syscall")						\
+__failure __msg(MSG)					\
+long test_##op##_spinlock_##dolock(void *ctx)		\
+{							\
+	struct bpf_rb_node *rb_n;			\
+	struct node_data *n;				\
+	__u64 jiffies = 0;				\
+							\
+	bpf_spin_lock(&glock0);				\
+	rb_n = bpf_rbtree_root(&groot0);		\
+	if (!rb_n) {					\
+		bpf_spin_unlock(&glock0);		\
+		return 1;				\
+	}						\
+	n = rb_entry(rb_n, struct node_data, r0);	\
+	n = bpf_refcount_acquire(n);			\
+	bpf_spin_unlock(&glock0);			\
+	if (!n)						\
+		return 1;				\
+							\
+	if (dolock)					\
+		bpf_spin_lock(&glock0);			\
+	rb_n = bpf_rbtree_##op(&groot0, &n->r0);	\
+	if (rb_n)					\
+		jiffies = bpf_jiffies64();		\
+	if (dolock)					\
+		bpf_spin_unlock(&glock0);		\
+							\
+	return !!jiffies;				\
+}
+
+/*
+ * Use a separate MSG macro instead of passing to TEST_XXX(..., MSG)
+ * to ensure the message itself is not in the bpf prog lineinfo
+ * which the verifier includes in its log.
+ * Otherwise, the test_loader will incorrectly match the prog lineinfo
+ * instead of the log generated by the verifier.
+ */
+#define MSG "call bpf_rbtree_root{{.+}}; R0{{(_w)?}}=rcu_ptr_or_null_node_data(id={{[0-9]+}},non_own_ref"
+TEST_ROOT(true)
+#undef MSG
+#define MSG "call bpf_rbtree_{{(left|right).+}}; R0{{(_w)?}}=rcu_ptr_or_null_node_data(id={{[0-9]+}},non_own_ref"
+TEST_LR(left,  true)
+TEST_LR(right, true)
+#undef MSG
+
+#define MSG "bpf_spin_lock at off=0 must be held for bpf_rb_root"
+TEST_ROOT(false)
+TEST_LR(left, false)
+TEST_LR(right, false)
+#undef MSG
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/rcu_read_lock.c b/tools/testing/selftests/bpf/progs/rcu_read_lock.c
index 5cecbdbbb16e..d70c28824bbe 100644
--- a/tools/testing/selftests/bpf/progs/rcu_read_lock.c
+++ b/tools/testing/selftests/bpf/progs/rcu_read_lock.c
@@ -16,14 +16,15 @@ struct {
 	__type(value, long);
 } map_a SEC(".maps");
 
-__u32 user_data, key_serial, target_pid;
+__u32 user_data, target_pid;
+__s32 key_serial;
 __u64 flags, task_storage_val, cgroup_id;
 
-struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym;
+struct bpf_key *bpf_lookup_user_key(__s32 serial, __u64 flags) __ksym;
 void bpf_key_put(struct bpf_key *key) __ksym;
 void bpf_rcu_read_lock(void) __ksym;
 void bpf_rcu_read_unlock(void) __ksym;
-struct task_struct *bpf_task_acquire_not_zero(struct task_struct *p) __ksym;
+struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym;
 void bpf_task_release(struct task_struct *p) __ksym;
 
 SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
@@ -81,7 +82,7 @@ int no_lock(void *ctx)
 {
 	struct task_struct *task, *real_parent;
 
-	/* no bpf_rcu_read_lock(), old code still works */
+	/* old style ptr_to_btf_id is not allowed in sleepable */
 	task = bpf_get_current_task_btf();
 	real_parent = task->real_parent;
 	(void)bpf_task_storage_get(&map_a, real_parent, 0, 0);
@@ -159,13 +160,8 @@ int task_acquire(void *ctx)
 		goto out;
 
 	/* acquire a reference which can be used outside rcu read lock region */
-	gparent = bpf_task_acquire_not_zero(gparent);
+	gparent = bpf_task_acquire(gparent);
 	if (!gparent)
-		/* Until we resolve the issues with using task->rcu_users, we
-		 * expect bpf_task_acquire_not_zero() to return a NULL task.
-		 * See the comment at the definition of
-		 * bpf_task_acquire_not_zero() for more details.
-		 */
 		goto out;
 
 	(void)bpf_task_storage_get(&map_a, gparent, 0, 0);
@@ -179,8 +175,6 @@ SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
 int miss_lock(void *ctx)
 {
 	struct task_struct *task;
-	struct css_set *cgroups;
-	struct cgroup *dfl_cgrp;
 
 	/* missing bpf_rcu_read_lock() */
 	task = bpf_get_current_task_btf();
@@ -195,8 +189,6 @@ SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
 int miss_unlock(void *ctx)
 {
 	struct task_struct *task;
-	struct css_set *cgroups;
-	struct cgroup *dfl_cgrp;
 
 	/* missing bpf_rcu_read_unlock() */
 	task = bpf_get_current_task_btf();
@@ -251,7 +243,8 @@ out:
 }
 
 SEC("?lsm.s/bpf")
-int BPF_PROG(inproper_sleepable_kfunc, int cmd, union bpf_attr *attr, unsigned int size)
+int BPF_PROG(inproper_sleepable_kfunc, int cmd, union bpf_attr *attr, unsigned int size,
+	     bool kernel)
 {
 	struct bpf_key *bkey;
 
@@ -285,14 +278,54 @@ out:
 	return 0;
 }
 
+SEC("?fentry.s/" SYS_PREFIX "sys_nanosleep")
+int nested_rcu_region_unbalanced_1(void *ctx)
+{
+	struct task_struct *task, *real_parent;
+
+	/* nested rcu read lock regions */
+	task = bpf_get_current_task_btf();
+	bpf_rcu_read_lock();
+	bpf_rcu_read_lock();
+	real_parent = task->real_parent;
+	if (!real_parent)
+		goto out;
+	(void)bpf_task_storage_get(&map_a, real_parent, 0, 0);
+out:
+	bpf_rcu_read_unlock();
+	bpf_rcu_read_unlock();
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_nanosleep")
+int nested_rcu_region_unbalanced_2(void *ctx)
+{
+	struct task_struct *task, *real_parent;
+
+	/* nested rcu read lock regions */
+	task = bpf_get_current_task_btf();
+	bpf_rcu_read_lock();
+	bpf_rcu_read_lock();
+	bpf_rcu_read_lock();
+	real_parent = task->real_parent;
+	if (!real_parent)
+		goto out;
+	(void)bpf_task_storage_get(&map_a, real_parent, 0, 0);
+out:
+	bpf_rcu_read_unlock();
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
 SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
-int task_untrusted_non_rcuptr(void *ctx)
+int task_trusted_non_rcuptr(void *ctx)
 {
 	struct task_struct *task, *group_leader;
 
 	task = bpf_get_current_task_btf();
 	bpf_rcu_read_lock();
-	/* the pointer group_leader marked as untrusted */
+	/* the pointer group_leader is explicitly marked as trusted */
 	group_leader = task->real_parent->group_leader;
 	(void)bpf_task_storage_get(&map_a, group_leader, 0, 0);
 	bpf_rcu_read_unlock();
@@ -328,3 +361,181 @@ int cross_rcu_region(void *ctx)
 	bpf_rcu_read_unlock();
 	return 0;
 }
+
+__noinline
+static int static_subprog(void *ctx)
+{
+	volatile int ret = 0;
+
+	if (bpf_get_prandom_u32())
+		return ret + 42;
+	return ret + bpf_get_prandom_u32();
+}
+
+__noinline
+int global_subprog(u64 a)
+{
+	volatile int ret = a;
+
+	return ret + static_subprog(NULL);
+}
+
+__noinline
+static int static_subprog_lock(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_lock();
+	if (bpf_get_prandom_u32())
+		return ret + 42;
+	return ret + bpf_get_prandom_u32();
+}
+
+__noinline
+int global_subprog_lock(u64 a)
+{
+	volatile int ret = a;
+
+	return ret + static_subprog_lock(NULL);
+}
+
+__noinline
+static int static_subprog_unlock(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_unlock();
+	if (bpf_get_prandom_u32())
+		return ret + 42;
+	return ret + bpf_get_prandom_u32();
+}
+
+__noinline
+int global_subprog_unlock(u64 a)
+{
+	volatile int ret = a;
+
+	return ret + static_subprog_unlock(NULL);
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_subprog(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_lock();
+	if (bpf_get_prandom_u32())
+		ret += static_subprog(ctx);
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_global_subprog(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_lock();
+	if (bpf_get_prandom_u32())
+		ret += global_subprog(ret);
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_subprog_lock(void *ctx)
+{
+	volatile int ret = 0;
+
+	ret += static_subprog_lock(ctx);
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_global_subprog_lock(void *ctx)
+{
+	volatile int ret = 0;
+
+	ret += global_subprog_lock(ret);
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_subprog_unlock(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_lock();
+	ret += static_subprog_unlock(ctx);
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_global_subprog_unlock(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_lock();
+	ret += global_subprog_unlock(ret);
+	return 0;
+}
+
+int __noinline
+global_sleepable_helper_subprog(int i)
+{
+	if (i)
+		bpf_copy_from_user(&i, sizeof(i), NULL);
+	return i;
+}
+
+int __noinline
+global_sleepable_kfunc_subprog(int i)
+{
+	if (i)
+		bpf_copy_from_user_str(&i, sizeof(i), NULL, 0);
+	global_subprog(i);
+	return i;
+}
+
+int __noinline
+global_subprog_calling_sleepable_global(int i)
+{
+	if (!i)
+		global_sleepable_kfunc_subprog(i);
+	return i;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_sleepable_helper_global_subprog(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_lock();
+	ret += global_sleepable_helper_subprog(ret);
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_sleepable_kfunc_global_subprog(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_lock();
+	ret += global_sleepable_kfunc_subprog(ret);
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int rcu_read_lock_sleepable_global_subprog_indirect(void *ctx)
+{
+	volatile int ret = 0;
+
+	bpf_rcu_read_lock();
+	ret += global_subprog_calling_sleepable_global(ret);
+	bpf_rcu_read_unlock();
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/rcu_tasks_trace_gp.c b/tools/testing/selftests/bpf/progs/rcu_tasks_trace_gp.c
new file mode 100644
index 000000000000..df4873558634
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/rcu_tasks_trace_gp.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+struct task_ls_map {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, int);
+} task_ls_map SEC(".maps");
+
+long gp_seq;
+
+SEC("syscall")
+int do_call_rcu_tasks_trace(void *ctx)
+{
+    struct task_struct *current;
+    int *v;
+
+    current = bpf_get_current_task_btf();
+    v = bpf_task_storage_get(&task_ls_map, current, NULL, BPF_LOCAL_STORAGE_GET_F_CREATE);
+    if (!v)
+        return 1;
+    /* Invoke call_rcu_tasks_trace */
+    return bpf_task_storage_delete(&task_ls_map, current);
+}
+
+SEC("kprobe/rcu_tasks_trace_postgp")
+int rcu_tasks_trace_postgp(void *ctx)
+{
+    __sync_add_and_fetch(&gp_seq, 1);
+    return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c b/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c
index a47bb0120719..69da05bb6c63 100644
--- a/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c
+++ b/tools/testing/selftests/bpf/progs/read_bpf_task_storage_busy.c
@@ -4,7 +4,7 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
-extern bool CONFIG_PREEMPT __kconfig __weak;
+extern bool CONFIG_PREEMPTION __kconfig __weak;
 extern const int bpf_task_storage_busy __ksym;
 
 char _license[] SEC("license") = "GPL";
@@ -23,9 +23,8 @@ SEC("raw_tp/sys_enter")
 int BPF_PROG(read_bpf_task_storage_busy)
 {
 	int *value;
-	int key;
 
-	if (!CONFIG_PREEMPT)
+	if (!CONFIG_PREEMPTION)
 		return 0;
 
 	if (bpf_get_current_pid_tgid() >> 32 != pid)
diff --git a/tools/testing/selftests/bpf/progs/read_cgroupfs_xattr.c b/tools/testing/selftests/bpf/progs/read_cgroupfs_xattr.c
new file mode 100644
index 000000000000..405adbe5e8b0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/read_cgroupfs_xattr.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_experimental.h"
+
+char _license[] SEC("license") = "GPL";
+
+pid_t target_pid = 0;
+
+char xattr_value[64];
+static const char expected_value_a[] = "bpf_selftest_value_a";
+static const char expected_value_b[] = "bpf_selftest_value_b";
+bool found_value_a;
+bool found_value_b;
+
+SEC("lsm.s/file_open")
+int BPF_PROG(test_file_open)
+{
+	u64 cgrp_id = bpf_get_current_cgroup_id();
+	struct cgroup_subsys_state *css, *tmp;
+	struct bpf_dynptr value_ptr;
+	struct cgroup *cgrp;
+
+	if ((bpf_get_current_pid_tgid() >> 32) != target_pid)
+		return 0;
+
+	bpf_rcu_read_lock();
+	cgrp = bpf_cgroup_from_id(cgrp_id);
+	if (!cgrp) {
+		bpf_rcu_read_unlock();
+		return 0;
+	}
+
+	css = &cgrp->self;
+	bpf_dynptr_from_mem(xattr_value, sizeof(xattr_value), 0, &value_ptr);
+	bpf_for_each(css, tmp, css, BPF_CGROUP_ITER_ANCESTORS_UP) {
+		int ret;
+
+		ret = bpf_cgroup_read_xattr(tmp->cgroup, "user.bpf_test",
+					    &value_ptr);
+		if (ret < 0)
+			continue;
+
+		if (ret == sizeof(expected_value_a) &&
+		    !bpf_strncmp(xattr_value, sizeof(expected_value_a), expected_value_a))
+			found_value_a = true;
+		if (ret == sizeof(expected_value_b) &&
+		    !bpf_strncmp(xattr_value, sizeof(expected_value_b), expected_value_b))
+			found_value_b = true;
+	}
+
+	bpf_rcu_read_unlock();
+	bpf_cgroup_release(cgrp);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/read_vsyscall.c b/tools/testing/selftests/bpf/progs/read_vsyscall.c
new file mode 100644
index 000000000000..395591374d4f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/read_vsyscall.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2024. Huawei Technologies Co., Ltd */
+#include "vmlinux.h"
+#include <linux/types.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+
+int target_pid = 0;
+void *user_ptr = 0;
+int read_ret[10];
+
+char _license[] SEC("license") = "GPL";
+
+/*
+ * These are the kfuncs, the others are helpers
+ */
+int bpf_copy_from_user_str(void *dst, u32, const void *, u64) __weak __ksym;
+int bpf_copy_from_user_task_str(void *dst, u32, const void *,
+				struct task_struct *, u64) __weak __ksym;
+
+SEC("fentry/" SYS_PREFIX "sys_nanosleep")
+int do_probe_read(void *ctx)
+{
+	char buf[8];
+
+	if ((bpf_get_current_pid_tgid() >> 32) != target_pid)
+		return 0;
+
+	read_ret[0] = bpf_probe_read_kernel(buf, sizeof(buf), user_ptr);
+	read_ret[1] = bpf_probe_read_kernel_str(buf, sizeof(buf), user_ptr);
+	read_ret[2] = bpf_probe_read(buf, sizeof(buf), user_ptr);
+	read_ret[3] = bpf_probe_read_str(buf, sizeof(buf), user_ptr);
+	read_ret[4] = bpf_probe_read_user(buf, sizeof(buf), user_ptr);
+	read_ret[5] = bpf_probe_read_user_str(buf, sizeof(buf), user_ptr);
+
+	return 0;
+}
+
+SEC("fentry.s/" SYS_PREFIX "sys_nanosleep")
+int do_copy_from_user(void *ctx)
+{
+	char buf[8];
+
+	if ((bpf_get_current_pid_tgid() >> 32) != target_pid)
+		return 0;
+
+	read_ret[6] = bpf_copy_from_user(buf, sizeof(buf), user_ptr);
+	read_ret[7] = bpf_copy_from_user_task(buf, sizeof(buf), user_ptr,
+					      bpf_get_current_task_btf(), 0);
+	read_ret[8] = bpf_copy_from_user_str((char *)buf, sizeof(buf), user_ptr, 0);
+	read_ret[9] = bpf_copy_from_user_task_str((char *)buf,
+						  sizeof(buf),
+						  user_ptr,
+						  bpf_get_current_task_btf(),
+						  0);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/recvmsg4_prog.c b/tools/testing/selftests/bpf/progs/recvmsg4_prog.c
index 3d1ae8b3402f..59748c95471a 100644
--- a/tools/testing/selftests/bpf/progs/recvmsg4_prog.c
+++ b/tools/testing/selftests/bpf/progs/recvmsg4_prog.c
@@ -17,8 +17,6 @@ SEC("cgroup/recvmsg4")
 int recvmsg4_prog(struct bpf_sock_addr *ctx)
 {
 	struct bpf_sock *sk;
-	__u32 user_ip4;
-	__u16 user_port;
 
 	sk = ctx->sk;
 	if (!sk)
diff --git a/tools/testing/selftests/bpf/progs/recvmsg6_prog.c b/tools/testing/selftests/bpf/progs/recvmsg6_prog.c
index 27dfb21b21b4..d9a4016596d5 100644
--- a/tools/testing/selftests/bpf/progs/recvmsg6_prog.c
+++ b/tools/testing/selftests/bpf/progs/recvmsg6_prog.c
@@ -20,8 +20,6 @@ SEC("cgroup/recvmsg6")
 int recvmsg6_prog(struct bpf_sock_addr *ctx)
 {
 	struct bpf_sock *sk;
-	__u32 user_ip4;
-	__u16 user_port;
 
 	sk = ctx->sk;
 	if (!sk)
diff --git a/tools/testing/selftests/bpf/progs/recvmsg_unix_prog.c b/tools/testing/selftests/bpf/progs/recvmsg_unix_prog.c
new file mode 100644
index 000000000000..1c7ab44bccfa
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/recvmsg_unix_prog.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+
+#include <string.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_kfuncs.h"
+
+__u8 SERVUN_ADDRESS[] = "\0bpf_cgroup_unix_test";
+
+SEC("cgroup/recvmsg_unix")
+int recvmsg_unix_prog(struct bpf_sock_addr *ctx)
+{
+	struct bpf_sock_addr_kern *sa_kern = bpf_cast_to_kern_ctx(ctx);
+	struct sockaddr_un *sa_kern_unaddr;
+	__u32 unaddrlen = offsetof(struct sockaddr_un, sun_path) +
+			  sizeof(SERVUN_ADDRESS) - 1;
+	int ret;
+
+	ret = bpf_sock_addr_set_sun_path(sa_kern, SERVUN_ADDRESS,
+					 sizeof(SERVUN_ADDRESS) - 1);
+	if (ret)
+		return 1;
+
+	if (sa_kern->uaddrlen != unaddrlen)
+		return 1;
+
+	sa_kern_unaddr = bpf_core_cast(sa_kern->uaddr, struct sockaddr_un);
+	if (memcmp(sa_kern_unaddr->sun_path, SERVUN_ADDRESS,
+			sizeof(SERVUN_ADDRESS) - 1) != 0)
+		return 1;
+
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr.c b/tools/testing/selftests/bpf/progs/refcounted_kptr.c
new file mode 100644
index 000000000000..1aca85d86aeb
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/refcounted_kptr.c
@@ -0,0 +1,631 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+extern void bpf_rcu_read_lock(void) __ksym;
+extern void bpf_rcu_read_unlock(void) __ksym;
+
+struct node_data {
+	long key;
+	long list_data;
+	struct bpf_rb_node r;
+	struct bpf_list_node l;
+	struct bpf_refcount ref;
+};
+
+struct map_value {
+	struct node_data __kptr *node;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 2);
+} stashed_nodes SEC(".maps");
+
+struct node_acquire {
+	long key;
+	long data;
+	struct bpf_rb_node node;
+	struct bpf_refcount refcount;
+};
+
+#define private(name) SEC(".bss." #name) __hidden __attribute__((aligned(8)))
+private(A) struct bpf_spin_lock lock;
+private(A) struct bpf_rb_root root __contains(node_data, r);
+private(A) struct bpf_list_head head __contains(node_data, l);
+
+private(B) struct bpf_spin_lock alock;
+private(B) struct bpf_rb_root aroot __contains(node_acquire, node);
+
+private(C) struct bpf_spin_lock block;
+private(C) struct bpf_rb_root broot __contains(node_data, r);
+
+static bool less(struct bpf_rb_node *node_a, const struct bpf_rb_node *node_b)
+{
+	struct node_data *a;
+	struct node_data *b;
+
+	a = container_of(node_a, struct node_data, r);
+	b = container_of(node_b, struct node_data, r);
+
+	return a->key < b->key;
+}
+
+static bool less_a(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	struct node_acquire *node_a;
+	struct node_acquire *node_b;
+
+	node_a = container_of(a, struct node_acquire, node);
+	node_b = container_of(b, struct node_acquire, node);
+
+	return node_a->key < node_b->key;
+}
+
+static long __insert_in_tree_and_list(struct bpf_list_head *head,
+				      struct bpf_rb_root *root,
+				      struct bpf_spin_lock *lock)
+{
+	struct node_data *n, *m;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return -1;
+
+	m = bpf_refcount_acquire(n);
+	m->key = 123;
+	m->list_data = 456;
+
+	bpf_spin_lock(lock);
+	if (bpf_rbtree_add(root, &n->r, less)) {
+		/* Failure to insert - unexpected */
+		bpf_spin_unlock(lock);
+		bpf_obj_drop(m);
+		return -2;
+	}
+	bpf_spin_unlock(lock);
+
+	bpf_spin_lock(lock);
+	if (bpf_list_push_front(head, &m->l)) {
+		/* Failure to insert - unexpected */
+		bpf_spin_unlock(lock);
+		return -3;
+	}
+	bpf_spin_unlock(lock);
+	return 0;
+}
+
+static long __stash_map_insert_tree(int idx, int val, struct bpf_rb_root *root,
+				    struct bpf_spin_lock *lock)
+{
+	struct map_value *mapval;
+	struct node_data *n, *m;
+
+	mapval = bpf_map_lookup_elem(&stashed_nodes, &idx);
+	if (!mapval)
+		return -1;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return -2;
+
+	n->key = val;
+	m = bpf_refcount_acquire(n);
+
+	n = bpf_kptr_xchg(&mapval->node, n);
+	if (n) {
+		bpf_obj_drop(n);
+		bpf_obj_drop(m);
+		return -3;
+	}
+
+	bpf_spin_lock(lock);
+	if (bpf_rbtree_add(root, &m->r, less)) {
+		/* Failure to insert - unexpected */
+		bpf_spin_unlock(lock);
+		return -4;
+	}
+	bpf_spin_unlock(lock);
+	return 0;
+}
+
+static long __read_from_tree(struct bpf_rb_root *root,
+			     struct bpf_spin_lock *lock,
+			     bool remove_from_tree)
+{
+	struct bpf_rb_node *rb;
+	struct node_data *n;
+	long res = -99;
+
+	bpf_spin_lock(lock);
+
+	rb = bpf_rbtree_first(root);
+	if (!rb) {
+		bpf_spin_unlock(lock);
+		return -1;
+	}
+
+	n = container_of(rb, struct node_data, r);
+	res = n->key;
+
+	if (!remove_from_tree) {
+		bpf_spin_unlock(lock);
+		return res;
+	}
+
+	rb = bpf_rbtree_remove(root, rb);
+	bpf_spin_unlock(lock);
+	if (!rb)
+		return -2;
+	n = container_of(rb, struct node_data, r);
+	bpf_obj_drop(n);
+	return res;
+}
+
+static long __read_from_list(struct bpf_list_head *head,
+			     struct bpf_spin_lock *lock,
+			     bool remove_from_list)
+{
+	struct bpf_list_node *l;
+	struct node_data *n;
+	long res = -99;
+
+	bpf_spin_lock(lock);
+
+	l = bpf_list_pop_front(head);
+	if (!l) {
+		bpf_spin_unlock(lock);
+		return -1;
+	}
+
+	n = container_of(l, struct node_data, l);
+	res = n->list_data;
+
+	if (!remove_from_list) {
+		if (bpf_list_push_back(head, &n->l)) {
+			bpf_spin_unlock(lock);
+			return -2;
+		}
+	}
+
+	bpf_spin_unlock(lock);
+
+	if (remove_from_list)
+		bpf_obj_drop(n);
+	return res;
+}
+
+static long __read_from_unstash(int idx)
+{
+	struct node_data *n = NULL;
+	struct map_value *mapval;
+	long val = -99;
+
+	mapval = bpf_map_lookup_elem(&stashed_nodes, &idx);
+	if (!mapval)
+		return -1;
+
+	n = bpf_kptr_xchg(&mapval->node, n);
+	if (!n)
+		return -2;
+
+	val = n->key;
+	bpf_obj_drop(n);
+	return val;
+}
+
+#define INSERT_READ_BOTH(rem_tree, rem_list, desc)			\
+SEC("tc")								\
+__description(desc)							\
+__success __retval(579)							\
+long insert_and_remove_tree_##rem_tree##_list_##rem_list(void *ctx)	\
+{									\
+	long err, tree_data, list_data;					\
+									\
+	err = __insert_in_tree_and_list(&head, &root, &lock);		\
+	if (err)							\
+		return err;						\
+									\
+	err = __read_from_tree(&root, &lock, rem_tree);			\
+	if (err < 0)							\
+		return err;						\
+	else								\
+		tree_data = err;					\
+									\
+	err = __read_from_list(&head, &lock, rem_list);			\
+	if (err < 0)							\
+		return err;						\
+	else								\
+		list_data = err;					\
+									\
+	return tree_data + list_data;					\
+}
+
+/* After successful insert of struct node_data into both collections:
+ *   - it should have refcount = 2
+ *   - removing / not removing the node_data from a collection after
+ *     reading should have no effect on ability to read / remove from
+ *     the other collection
+ */
+INSERT_READ_BOTH(true, true, "insert_read_both: remove from tree + list");
+INSERT_READ_BOTH(false, false, "insert_read_both: remove from neither");
+INSERT_READ_BOTH(true, false, "insert_read_both: remove from tree");
+INSERT_READ_BOTH(false, true, "insert_read_both: remove from list");
+
+#undef INSERT_READ_BOTH
+#define INSERT_READ_BOTH(rem_tree, rem_list, desc)			\
+SEC("tc")								\
+__description(desc)							\
+__success __retval(579)							\
+long insert_and_remove_lf_tree_##rem_tree##_list_##rem_list(void *ctx)	\
+{									\
+	long err, tree_data, list_data;					\
+									\
+	err = __insert_in_tree_and_list(&head, &root, &lock);		\
+	if (err)							\
+		return err;						\
+									\
+	err = __read_from_list(&head, &lock, rem_list);			\
+	if (err < 0)							\
+		return err;						\
+	else								\
+		list_data = err;					\
+									\
+	err = __read_from_tree(&root, &lock, rem_tree);			\
+	if (err < 0)							\
+		return err;						\
+	else								\
+		tree_data = err;					\
+									\
+	return tree_data + list_data;					\
+}
+
+/* Similar to insert_read_both, but list data is read and possibly removed
+ * first
+ *
+ * Results should be no different than reading and possibly removing rbtree
+ * node first
+ */
+INSERT_READ_BOTH(true, true, "insert_read_both_list_first: remove from tree + list");
+INSERT_READ_BOTH(false, false, "insert_read_both_list_first: remove from neither");
+INSERT_READ_BOTH(true, false, "insert_read_both_list_first: remove from tree");
+INSERT_READ_BOTH(false, true, "insert_read_both_list_first: remove from list");
+
+#define INSERT_DOUBLE_READ_AND_DEL(read_fn, read_root, desc)		\
+SEC("tc")								\
+__description(desc)							\
+__success __retval(-1)							\
+long insert_double_##read_fn##_and_del_##read_root(void *ctx)		\
+{									\
+	long err, list_data;						\
+									\
+	err = __insert_in_tree_and_list(&head, &root, &lock);		\
+	if (err)							\
+		return err;						\
+									\
+	err = read_fn(&read_root, &lock, true);				\
+	if (err < 0)							\
+		return err;						\
+	else								\
+		list_data = err;					\
+									\
+	err = read_fn(&read_root, &lock, true);				\
+	if (err < 0)							\
+		return err;						\
+									\
+	return err + list_data;						\
+}
+
+/* Insert into both tree and list, then try reading-and-removing from either twice
+ *
+ * The second read-and-remove should fail on read step since the node has
+ * already been removed
+ */
+INSERT_DOUBLE_READ_AND_DEL(__read_from_tree, root, "insert_double_del: 2x read-and-del from tree");
+INSERT_DOUBLE_READ_AND_DEL(__read_from_list, head, "insert_double_del: 2x read-and-del from list");
+
+#define INSERT_STASH_READ(rem_tree, desc)				\
+SEC("tc")								\
+__description(desc)							\
+__success __retval(84)							\
+long insert_rbtree_and_stash__del_tree_##rem_tree(void *ctx)		\
+{									\
+	long err, tree_data, map_data;					\
+									\
+	err = __stash_map_insert_tree(0, 42, &root, &lock);		\
+	if (err)							\
+		return err;						\
+									\
+	err = __read_from_tree(&root, &lock, rem_tree);			\
+	if (err < 0)							\
+		return err;						\
+	else								\
+		tree_data = err;					\
+									\
+	err = __read_from_unstash(0);					\
+	if (err < 0)							\
+		return err;						\
+	else								\
+		map_data = err;						\
+									\
+	return tree_data + map_data;					\
+}
+
+/* Stash a refcounted node in map_val, insert same node into tree, then try
+ * reading data from tree then unstashed map_val, possibly removing from tree
+ *
+ * Removing from tree should have no effect on map_val kptr validity
+ */
+INSERT_STASH_READ(true, "insert_stash_read: remove from tree");
+INSERT_STASH_READ(false, "insert_stash_read: don't remove from tree");
+
+SEC("tc")
+__success
+long rbtree_refcounted_node_ref_escapes(void *ctx)
+{
+	struct node_acquire *n, *m;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 1;
+
+	bpf_spin_lock(&alock);
+	bpf_rbtree_add(&aroot, &n->node, less_a);
+	m = bpf_refcount_acquire(n);
+	bpf_spin_unlock(&alock);
+	if (!m)
+		return 2;
+
+	m->key = 2;
+	bpf_obj_drop(m);
+	return 0;
+}
+
+SEC("tc")
+__success
+long rbtree_refcounted_node_ref_escapes_owning_input(void *ctx)
+{
+	struct node_acquire *n, *m;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 1;
+
+	m = bpf_refcount_acquire(n);
+	m->key = 2;
+
+	bpf_spin_lock(&alock);
+	bpf_rbtree_add(&aroot, &n->node, less_a);
+	bpf_spin_unlock(&alock);
+
+	bpf_obj_drop(m);
+
+	return 0;
+}
+
+static long __stash_map_empty_xchg(struct node_data *n, int idx)
+{
+	struct map_value *mapval = bpf_map_lookup_elem(&stashed_nodes, &idx);
+
+	if (!mapval) {
+		bpf_obj_drop(n);
+		return 1;
+	}
+	n = bpf_kptr_xchg(&mapval->node, n);
+	if (n) {
+		bpf_obj_drop(n);
+		return 2;
+	}
+	return 0;
+}
+
+SEC("tc")
+long rbtree_wrong_owner_remove_fail_a1(void *ctx)
+{
+	struct node_data *n, *m;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 1;
+	m = bpf_refcount_acquire(n);
+
+	if (__stash_map_empty_xchg(n, 0)) {
+		bpf_obj_drop(m);
+		return 2;
+	}
+
+	if (__stash_map_empty_xchg(m, 1))
+		return 3;
+
+	return 0;
+}
+
+SEC("tc")
+long rbtree_wrong_owner_remove_fail_b(void *ctx)
+{
+	struct map_value *mapval;
+	struct node_data *n;
+	int idx = 0;
+
+	mapval = bpf_map_lookup_elem(&stashed_nodes, &idx);
+	if (!mapval)
+		return 1;
+
+	n = bpf_kptr_xchg(&mapval->node, NULL);
+	if (!n)
+		return 2;
+
+	bpf_spin_lock(&block);
+
+	bpf_rbtree_add(&broot, &n->r, less);
+
+	bpf_spin_unlock(&block);
+	return 0;
+}
+
+SEC("tc")
+long rbtree_wrong_owner_remove_fail_a2(void *ctx)
+{
+	struct map_value *mapval;
+	struct bpf_rb_node *res;
+	struct node_data *m;
+	int idx = 1;
+
+	mapval = bpf_map_lookup_elem(&stashed_nodes, &idx);
+	if (!mapval)
+		return 1;
+
+	m = bpf_kptr_xchg(&mapval->node, NULL);
+	if (!m)
+		return 2;
+	bpf_spin_lock(&lock);
+
+	/* make m non-owning ref */
+	bpf_list_push_back(&head, &m->l);
+	res = bpf_rbtree_remove(&root, &m->r);
+
+	bpf_spin_unlock(&lock);
+	if (res) {
+		bpf_obj_drop(container_of(res, struct node_data, r));
+		return 3;
+	}
+	return 0;
+}
+
+SEC("?fentry.s/bpf_testmod_test_read")
+__success
+int BPF_PROG(rbtree_sleepable_rcu,
+	     struct file *file, struct kobject *kobj,
+	     struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len)
+{
+	struct bpf_rb_node *rb;
+	struct node_data *n, *m = NULL;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 0;
+
+	bpf_rcu_read_lock();
+	bpf_spin_lock(&lock);
+	bpf_rbtree_add(&root, &n->r, less);
+	rb = bpf_rbtree_first(&root);
+	if (!rb)
+		goto err_out;
+
+	rb = bpf_rbtree_remove(&root, rb);
+	if (!rb)
+		goto err_out;
+
+	m = container_of(rb, struct node_data, r);
+
+err_out:
+	bpf_spin_unlock(&lock);
+	bpf_rcu_read_unlock();
+	if (m)
+		bpf_obj_drop(m);
+	return 0;
+}
+
+SEC("?fentry.s/bpf_testmod_test_read")
+__success
+int BPF_PROG(rbtree_sleepable_rcu_no_explicit_rcu_lock,
+	     struct file *file, struct kobject *kobj,
+	     struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len)
+{
+	struct bpf_rb_node *rb;
+	struct node_data *n, *m = NULL;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 0;
+
+	/* No explicit bpf_rcu_read_lock */
+	bpf_spin_lock(&lock);
+	bpf_rbtree_add(&root, &n->r, less);
+	rb = bpf_rbtree_first(&root);
+	if (!rb)
+		goto err_out;
+
+	rb = bpf_rbtree_remove(&root, rb);
+	if (!rb)
+		goto err_out;
+
+	m = container_of(rb, struct node_data, r);
+
+err_out:
+	bpf_spin_unlock(&lock);
+	/* No explicit bpf_rcu_read_unlock */
+	if (m)
+		bpf_obj_drop(m);
+	return 0;
+}
+
+private(kptr_ref) u64 ref;
+
+static int probe_read_refcount(void)
+{
+	u32 refcount;
+
+	bpf_probe_read_kernel(&refcount, sizeof(refcount), (void *) ref);
+	return refcount;
+}
+
+static int __insert_in_list(struct bpf_list_head *head, struct bpf_spin_lock *lock,
+			    struct node_data __kptr **node)
+{
+	struct node_data *node_new, *node_ref, *node_old;
+
+	node_new = bpf_obj_new(typeof(*node_new));
+	if (!node_new)
+		return -1;
+
+	node_ref = bpf_refcount_acquire(node_new);
+	node_old = bpf_kptr_xchg(node, node_new);
+	if (node_old) {
+		bpf_obj_drop(node_old);
+		bpf_obj_drop(node_ref);
+		return -2;
+	}
+
+	bpf_spin_lock(lock);
+	bpf_list_push_front(head, &node_ref->l);
+	ref = (u64)(void *) &node_ref->ref;
+	bpf_spin_unlock(lock);
+	return probe_read_refcount();
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_HASH);
+	__type(key, int);
+	__type(value, struct map_value);
+	__uint(max_entries, 1);
+} percpu_hash SEC(".maps");
+
+SEC("tc")
+int percpu_hash_refcount_leak(void *ctx)
+{
+	struct map_value *v;
+	int key = 0;
+
+	v = bpf_map_lookup_elem(&percpu_hash, &key);
+	if (!v)
+		return 0;
+
+	return __insert_in_list(&head, &lock, &v->node);
+}
+
+SEC("tc")
+int check_percpu_hash_refcount(void *ctx)
+{
+	return probe_read_refcount();
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c
new file mode 100644
index 000000000000..836c8ab7b908
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/refcounted_kptr_fail.c
@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_experimental.h"
+#include "bpf_misc.h"
+
+struct node_acquire {
+	long key;
+	long data;
+	struct bpf_rb_node node;
+	struct bpf_refcount refcount;
+};
+
+extern void bpf_rcu_read_lock(void) __ksym;
+extern void bpf_rcu_read_unlock(void) __ksym;
+
+#define private(name) SEC(".data." #name) __hidden __attribute__((aligned(8)))
+private(A) struct bpf_spin_lock glock;
+private(A) struct bpf_rb_root groot __contains(node_acquire, node);
+
+static bool less(struct bpf_rb_node *a, const struct bpf_rb_node *b)
+{
+	struct node_acquire *node_a;
+	struct node_acquire *node_b;
+
+	node_a = container_of(a, struct node_acquire, node);
+	node_b = container_of(b, struct node_acquire, node);
+
+	return node_a->key < node_b->key;
+}
+
+SEC("?tc")
+__failure __msg("Unreleased reference id=4 alloc_insn={{[0-9]+}}")
+long rbtree_refcounted_node_ref_escapes(void *ctx)
+{
+	struct node_acquire *n, *m;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 1;
+
+	bpf_spin_lock(&glock);
+	bpf_rbtree_add(&groot, &n->node, less);
+	/* m becomes an owning ref but is never drop'd or added to a tree */
+	m = bpf_refcount_acquire(n);
+	bpf_spin_unlock(&glock);
+	if (!m)
+		return 2;
+
+	m->key = 2;
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
+long refcount_acquire_maybe_null(void *ctx)
+{
+	struct node_acquire *n, *m;
+
+	n = bpf_obj_new(typeof(*n));
+	/* Intentionally not testing !n
+	 * it's MAYBE_NULL for refcount_acquire
+	 */
+	m = bpf_refcount_acquire(n);
+	if (m)
+		bpf_obj_drop(m);
+	if (n)
+		bpf_obj_drop(n);
+
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("Unreleased reference id=3 alloc_insn={{[0-9]+}}")
+long rbtree_refcounted_node_ref_escapes_owning_input(void *ctx)
+{
+	struct node_acquire *n, *m;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 1;
+
+	/* m becomes an owning ref but is never drop'd or added to a tree */
+	m = bpf_refcount_acquire(n);
+	m->key = 2;
+
+	bpf_spin_lock(&glock);
+	bpf_rbtree_add(&groot, &n->node, less);
+	bpf_spin_unlock(&glock);
+
+	return 0;
+}
+
+SEC("?fentry.s/bpf_testmod_test_read")
+__failure __msg("function calls are not allowed while holding a lock")
+int BPF_PROG(rbtree_fail_sleepable_lock_across_rcu,
+	     struct file *file, struct kobject *kobj,
+	     struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len)
+{
+	struct node_acquire *n;
+
+	n = bpf_obj_new(typeof(*n));
+	if (!n)
+		return 0;
+
+	/* spin_{lock,unlock} are in different RCU CS */
+	bpf_rcu_read_lock();
+	bpf_spin_lock(&glock);
+	bpf_rbtree_add(&groot, &n->node, less);
+	bpf_rcu_read_unlock();
+
+	bpf_rcu_read_lock();
+	bpf_spin_unlock(&glock);
+	bpf_rcu_read_unlock();
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/res_spin_lock.c b/tools/testing/selftests/bpf/progs/res_spin_lock.c
new file mode 100644
index 000000000000..22c4fb8b9266
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/res_spin_lock.c
@@ -0,0 +1,147 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024-2025 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#define EDEADLK 35
+#define ETIMEDOUT 110
+
+struct arr_elem {
+	struct bpf_res_spin_lock lock;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 64);
+	__type(key, int);
+	__type(value, struct arr_elem);
+} arrmap SEC(".maps");
+
+struct bpf_res_spin_lock lockA __hidden SEC(".data.A");
+struct bpf_res_spin_lock lockB __hidden SEC(".data.B");
+
+SEC("tc")
+int res_spin_lock_test(struct __sk_buff *ctx)
+{
+	struct arr_elem *elem1, *elem2;
+	int r;
+
+	elem1 = bpf_map_lookup_elem(&arrmap, &(int){0});
+	if (!elem1)
+		return -1;
+	elem2 = bpf_map_lookup_elem(&arrmap, &(int){0});
+	if (!elem2)
+		return -1;
+
+	r = bpf_res_spin_lock(&elem1->lock);
+	if (r)
+		return r;
+	r = bpf_res_spin_lock(&elem2->lock);
+	if (!r) {
+		bpf_res_spin_unlock(&elem2->lock);
+		bpf_res_spin_unlock(&elem1->lock);
+		return -1;
+	}
+	bpf_res_spin_unlock(&elem1->lock);
+	return r != -EDEADLK;
+}
+
+SEC("tc")
+int res_spin_lock_test_AB(struct __sk_buff *ctx)
+{
+	int r;
+
+	r = bpf_res_spin_lock(&lockA);
+	if (r)
+		return !r;
+	/* Only unlock if we took the lock. */
+	if (!bpf_res_spin_lock(&lockB))
+		bpf_res_spin_unlock(&lockB);
+	bpf_res_spin_unlock(&lockA);
+	return 0;
+}
+
+int err;
+
+SEC("tc")
+int res_spin_lock_test_BA(struct __sk_buff *ctx)
+{
+	int r;
+
+	r = bpf_res_spin_lock(&lockB);
+	if (r)
+		return !r;
+	if (!bpf_res_spin_lock(&lockA))
+		bpf_res_spin_unlock(&lockA);
+	else
+		err = -EDEADLK;
+	bpf_res_spin_unlock(&lockB);
+	return err ?: 0;
+}
+
+SEC("tc")
+int res_spin_lock_test_held_lock_max(struct __sk_buff *ctx)
+{
+	struct bpf_res_spin_lock *locks[48] = {};
+	struct arr_elem *e;
+	u64 time_beg, time;
+	int ret = 0, i;
+
+	_Static_assert(ARRAY_SIZE(((struct rqspinlock_held){}).locks) == 31,
+		       "RES_NR_HELD assumed to be 31");
+
+	for (i = 0; i < 34; i++) {
+		int key = i;
+
+		/* We cannot pass in i as it will get spilled/filled by the compiler and
+		 * loses bounds in verifier state.
+		 */
+		e = bpf_map_lookup_elem(&arrmap, &key);
+		if (!e)
+			return 1;
+		locks[i] = &e->lock;
+	}
+
+	for (; i < 48; i++) {
+		int key = i - 2;
+
+		/* We cannot pass in i as it will get spilled/filled by the compiler and
+		 * loses bounds in verifier state.
+		 */
+		e = bpf_map_lookup_elem(&arrmap, &key);
+		if (!e)
+			return 1;
+		locks[i] = &e->lock;
+	}
+
+	time_beg = bpf_ktime_get_ns();
+	for (i = 0; i < 34; i++) {
+		if (bpf_res_spin_lock(locks[i]))
+			goto end;
+	}
+
+	/* Trigger AA, after exhausting entries in the held lock table. This
+	 * time, only the timeout can save us, as AA detection won't succeed.
+	 */
+	ret = bpf_res_spin_lock(locks[34]);
+	if (!ret) {
+		bpf_res_spin_unlock(locks[34]);
+		ret = 1;
+		goto end;
+	}
+
+	ret = ret != -ETIMEDOUT ? 2 : 0;
+
+end:
+	for (i = i - 1; i >= 0; i--)
+		bpf_res_spin_unlock(locks[i]);
+	time = bpf_ktime_get_ns() - time_beg;
+	/* Time spent should be easily above our limit (1/4 s), since AA
+	 * detection won't be expedited due to lack of held lock entry.
+	 */
+	return ret ?: (time > 1000000000 / 4 ? 0 : 1);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/res_spin_lock_fail.c b/tools/testing/selftests/bpf/progs/res_spin_lock_fail.c
new file mode 100644
index 000000000000..330682a88c16
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/res_spin_lock_fail.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024-2025 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+struct arr_elem {
+	struct bpf_res_spin_lock lock;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct arr_elem);
+} arrmap SEC(".maps");
+
+long value;
+
+struct bpf_spin_lock lock __hidden SEC(".data.A");
+struct bpf_res_spin_lock res_lock __hidden SEC(".data.B");
+
+SEC("?tc")
+__failure __msg("point to map value or allocated object")
+int res_spin_lock_arg(struct __sk_buff *ctx)
+{
+	struct arr_elem *elem;
+
+	elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+	if (!elem)
+		return 0;
+	bpf_res_spin_lock((struct bpf_res_spin_lock *)bpf_core_cast(&elem->lock, struct __sk_buff));
+	bpf_res_spin_lock(&elem->lock);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("AA deadlock detected")
+int res_spin_lock_AA(struct __sk_buff *ctx)
+{
+	struct arr_elem *elem;
+
+	elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+	if (!elem)
+		return 0;
+	bpf_res_spin_lock(&elem->lock);
+	bpf_res_spin_lock(&elem->lock);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("AA deadlock detected")
+int res_spin_lock_cond_AA(struct __sk_buff *ctx)
+{
+	struct arr_elem *elem;
+
+	elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+	if (!elem)
+		return 0;
+	if (bpf_res_spin_lock(&elem->lock))
+		return 0;
+	bpf_res_spin_lock(&elem->lock);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("unlock of different lock")
+int res_spin_lock_mismatch_1(struct __sk_buff *ctx)
+{
+	struct arr_elem *elem;
+
+	elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+	if (!elem)
+		return 0;
+	if (bpf_res_spin_lock(&elem->lock))
+		return 0;
+	bpf_res_spin_unlock(&res_lock);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("unlock of different lock")
+int res_spin_lock_mismatch_2(struct __sk_buff *ctx)
+{
+	struct arr_elem *elem;
+
+	elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+	if (!elem)
+		return 0;
+	if (bpf_res_spin_lock(&res_lock))
+		return 0;
+	bpf_res_spin_unlock(&elem->lock);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("unlock of different lock")
+int res_spin_lock_irq_mismatch_1(struct __sk_buff *ctx)
+{
+	struct arr_elem *elem;
+	unsigned long f1;
+
+	elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+	if (!elem)
+		return 0;
+	bpf_local_irq_save(&f1);
+	if (bpf_res_spin_lock(&res_lock))
+		return 0;
+	bpf_res_spin_unlock_irqrestore(&res_lock, &f1);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("unlock of different lock")
+int res_spin_lock_irq_mismatch_2(struct __sk_buff *ctx)
+{
+	struct arr_elem *elem;
+	unsigned long f1;
+
+	elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+	if (!elem)
+		return 0;
+	if (bpf_res_spin_lock_irqsave(&res_lock, &f1))
+		return 0;
+	bpf_res_spin_unlock(&res_lock);
+	return 0;
+}
+
+SEC("?tc")
+__success
+int res_spin_lock_ooo(struct __sk_buff *ctx)
+{
+	struct arr_elem *elem;
+
+	elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+	if (!elem)
+		return 0;
+	if (bpf_res_spin_lock(&res_lock))
+		return 0;
+	if (bpf_res_spin_lock(&elem->lock)) {
+		bpf_res_spin_unlock(&res_lock);
+		return 0;
+	}
+	bpf_res_spin_unlock(&elem->lock);
+	bpf_res_spin_unlock(&res_lock);
+	return 0;
+}
+
+SEC("?tc")
+__success
+int res_spin_lock_ooo_irq(struct __sk_buff *ctx)
+{
+	struct arr_elem *elem;
+	unsigned long f1, f2;
+
+	elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+	if (!elem)
+		return 0;
+	if (bpf_res_spin_lock_irqsave(&res_lock, &f1))
+		return 0;
+	if (bpf_res_spin_lock_irqsave(&elem->lock, &f2)) {
+		bpf_res_spin_unlock_irqrestore(&res_lock, &f1);
+		/* We won't have a unreleased IRQ flag error here. */
+		return 0;
+	}
+	bpf_res_spin_unlock_irqrestore(&elem->lock, &f2);
+	bpf_res_spin_unlock_irqrestore(&res_lock, &f1);
+	return 0;
+}
+
+struct bpf_res_spin_lock lock1 __hidden SEC(".data.OO1");
+struct bpf_res_spin_lock lock2 __hidden SEC(".data.OO2");
+
+SEC("?tc")
+__failure __msg("bpf_res_spin_unlock cannot be out of order")
+int res_spin_lock_ooo_unlock(struct __sk_buff *ctx)
+{
+	if (bpf_res_spin_lock(&lock1))
+		return 0;
+	if (bpf_res_spin_lock(&lock2)) {
+		bpf_res_spin_unlock(&lock1);
+		return 0;
+	}
+	bpf_res_spin_unlock(&lock1);
+	bpf_res_spin_unlock(&lock2);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("off 1 doesn't point to 'struct bpf_res_spin_lock' that is at 0")
+int res_spin_lock_bad_off(struct __sk_buff *ctx)
+{
+	struct arr_elem *elem;
+
+	elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+	if (!elem)
+		return 0;
+	bpf_res_spin_lock((void *)&elem->lock + 1);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("R1 doesn't have constant offset. bpf_res_spin_lock has to be at the constant offset")
+int res_spin_lock_var_off(struct __sk_buff *ctx)
+{
+	struct arr_elem *elem;
+	u64 val = value;
+
+	elem = bpf_map_lookup_elem(&arrmap, &(int){0});
+	if (!elem) {
+		// FIXME: Only inline assembly use in assert macro doesn't emit
+		//	  BTF definition.
+		bpf_throw(0);
+		return 0;
+	}
+	bpf_assert_range(val, 0, 40);
+	bpf_res_spin_lock((void *)&value + val);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("map 'res_spin.bss' has no valid bpf_res_spin_lock")
+int res_spin_lock_no_lock_map(struct __sk_buff *ctx)
+{
+	bpf_res_spin_lock((void *)&value + 1);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("local 'kptr' has no valid bpf_res_spin_lock")
+int res_spin_lock_no_lock_kptr(struct __sk_buff *ctx)
+{
+	struct { int i; } *p = bpf_obj_new(typeof(*p));
+
+	if (!p)
+		return 0;
+	bpf_res_spin_lock((void *)p);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/ringbuf_bench.c b/tools/testing/selftests/bpf/progs/ringbuf_bench.c
index 6a468496f539..d96c7d1e8fc2 100644
--- a/tools/testing/selftests/bpf/progs/ringbuf_bench.c
+++ b/tools/testing/selftests/bpf/progs/ringbuf_bench.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2020 Facebook
 
+#include <stdbool.h>
 #include <linux/bpf.h>
 #include <stdint.h>
 #include <bpf/bpf_helpers.h>
@@ -14,9 +15,11 @@ struct {
 
 const volatile int batch_cnt = 0;
 const volatile long use_output = 0;
+const volatile bool bench_producer = false;
 
 long sample_val = 42;
 long dropped __attribute__((aligned(128))) = 0;
+long hits __attribute__((aligned(128))) = 0;
 
 const volatile long wakeup_data_size = 0;
 
@@ -24,6 +27,9 @@ static __always_inline long get_flags()
 {
 	long sz;
 
+	if (bench_producer)
+		return BPF_RB_NO_WAKEUP;
+
 	if (!wakeup_data_size)
 		return 0;
 
@@ -47,6 +53,8 @@ int bench_ringbuf(void *ctx)
 				*sample = sample_val;
 				flags = get_flags();
 				bpf_ringbuf_submit(sample, flags);
+				if (bench_producer)
+					__sync_add_and_fetch(&hits, 1);
 			}
 		}
 	} else {
@@ -55,6 +63,9 @@ int bench_ringbuf(void *ctx)
 			if (bpf_ringbuf_output(&ringbuf, &sample_val,
 					       sizeof(sample_val), flags))
 				__sync_add_and_fetch(&dropped, 1);
+			else if (bench_producer)
+				__sync_add_and_fetch(&hits, 1);
+
 		}
 	}
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/security_bpf_map.c b/tools/testing/selftests/bpf/progs/security_bpf_map.c
new file mode 100644
index 000000000000..7216b3450e96
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/security_bpf_map.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+#define EPERM 1 /* Operation not permitted */
+
+/* From include/linux/mm.h. */
+#define FMODE_WRITE	0x2
+
+struct map;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, __u32);
+	__type(value, __u32);
+	__uint(max_entries, 1);
+} prot_status_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __u32);
+	__type(value, __u32);
+	__uint(max_entries, 3);
+} prot_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __u32);
+	__type(value, __u32);
+	__uint(max_entries, 3);
+} not_prot_map SEC(".maps");
+
+SEC("fmod_ret/security_bpf_map")
+int BPF_PROG(fmod_bpf_map, struct bpf_map *map, int fmode)
+{
+	__u32 key = 0;
+	__u32 *status_ptr = bpf_map_lookup_elem(&prot_status_map, &key);
+
+	if (!status_ptr || !*status_ptr)
+		return 0;
+
+	if (map == &prot_map) {
+		/* Allow read-only access */
+		if (fmode & FMODE_WRITE)
+			return -EPERM;
+	}
+
+	return 0;
+}
+
+/*
+ * This program keeps references to maps. This is needed to prevent
+ * optimizing them out.
+ */
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(fentry_dummy1, int a)
+{
+	__u32 key = 0;
+	__u32 val1 = a;
+	__u32 val2 = a + 1;
+
+	bpf_map_update_elem(&prot_map, &key, &val1, BPF_ANY);
+	bpf_map_update_elem(&not_prot_map, &key, &val2, BPF_ANY);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/sendmsg4_prog.c b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c
index ea75a44cb7fc..edc159598a0e 100644
--- a/tools/testing/selftests/bpf/progs/sendmsg4_prog.c
+++ b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c
@@ -21,8 +21,6 @@
 SEC("cgroup/sendmsg4")
 int sendmsg_v4_prog(struct bpf_sock_addr *ctx)
 {
-	int prio;
-
 	if (ctx->type != SOCK_DGRAM)
 		return 0;
 
@@ -51,4 +49,10 @@ int sendmsg_v4_prog(struct bpf_sock_addr *ctx)
 	return 1;
 }
 
+SEC("cgroup/sendmsg4")
+int sendmsg_v4_deny_prog(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c
index bf9b46b806f6..36a7f960799f 100644
--- a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c
+++ b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c
@@ -20,6 +20,11 @@
 #define DST_REWRITE_IP6_2	0
 #define DST_REWRITE_IP6_3	1
 
+#define DST_REWRITE_IP6_V4_MAPPED_0	0
+#define DST_REWRITE_IP6_V4_MAPPED_1	0
+#define DST_REWRITE_IP6_V4_MAPPED_2	0x0000FFFF
+#define DST_REWRITE_IP6_V4_MAPPED_3	0xc0a80004 // 192.168.0.4
+
 #define DST_REWRITE_PORT6	6666
 
 SEC("cgroup/sendmsg6")
@@ -59,4 +64,56 @@ int sendmsg_v6_prog(struct bpf_sock_addr *ctx)
 	return 1;
 }
 
+SEC("cgroup/sendmsg6")
+int sendmsg_v6_v4mapped_prog(struct bpf_sock_addr *ctx)
+{
+	/* Rewrite source. */
+	ctx->msg_src_ip6[0] = bpf_htonl(SRC_REWRITE_IP6_0);
+	ctx->msg_src_ip6[1] = bpf_htonl(SRC_REWRITE_IP6_1);
+	ctx->msg_src_ip6[2] = bpf_htonl(SRC_REWRITE_IP6_2);
+	ctx->msg_src_ip6[3] = bpf_htonl(SRC_REWRITE_IP6_3);
+
+	/* Rewrite destination. */
+	ctx->user_ip6[0] = bpf_htonl(DST_REWRITE_IP6_V4_MAPPED_0);
+	ctx->user_ip6[1] = bpf_htonl(DST_REWRITE_IP6_V4_MAPPED_1);
+	ctx->user_ip6[2] = bpf_htonl(DST_REWRITE_IP6_V4_MAPPED_2);
+	ctx->user_ip6[3] = bpf_htonl(DST_REWRITE_IP6_V4_MAPPED_3);
+
+	ctx->user_port = bpf_htons(DST_REWRITE_PORT6);
+
+	return 1;
+}
+
+SEC("cgroup/sendmsg6")
+int sendmsg_v6_wildcard_prog(struct bpf_sock_addr *ctx)
+{
+	/* Rewrite source. */
+	ctx->msg_src_ip6[0] = bpf_htonl(SRC_REWRITE_IP6_0);
+	ctx->msg_src_ip6[1] = bpf_htonl(SRC_REWRITE_IP6_1);
+	ctx->msg_src_ip6[2] = bpf_htonl(SRC_REWRITE_IP6_2);
+	ctx->msg_src_ip6[3] = bpf_htonl(SRC_REWRITE_IP6_3);
+
+	/* Rewrite destination. */
+	ctx->user_ip6[0] = bpf_htonl(0);
+	ctx->user_ip6[1] = bpf_htonl(0);
+	ctx->user_ip6[2] = bpf_htonl(0);
+	ctx->user_ip6[3] = bpf_htonl(0);
+
+	ctx->user_port = bpf_htons(DST_REWRITE_PORT6);
+
+	return 1;
+}
+
+SEC("cgroup/sendmsg6")
+int sendmsg_v6_preserve_dst_prog(struct bpf_sock_addr *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/sendmsg6")
+int sendmsg_v6_deny_prog(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/sendmsg_unix_prog.c b/tools/testing/selftests/bpf/progs/sendmsg_unix_prog.c
new file mode 100644
index 000000000000..332d0eb1116f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/sendmsg_unix_prog.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+
+#include <string.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_kfuncs.h"
+
+__u8 SERVUN_REWRITE_ADDRESS[] = "\0bpf_cgroup_unix_test_rewrite";
+
+SEC("cgroup/sendmsg_unix")
+int sendmsg_unix_prog(struct bpf_sock_addr *ctx)
+{
+	struct bpf_sock_addr_kern *sa_kern = bpf_cast_to_kern_ctx(ctx);
+	struct sockaddr_un *sa_kern_unaddr;
+	__u32 unaddrlen = offsetof(struct sockaddr_un, sun_path) +
+			  sizeof(SERVUN_REWRITE_ADDRESS) - 1;
+	int ret;
+
+	/* Rewrite destination. */
+	ret = bpf_sock_addr_set_sun_path(sa_kern, SERVUN_REWRITE_ADDRESS,
+					 sizeof(SERVUN_REWRITE_ADDRESS) - 1);
+	if (ret)
+		return 0;
+
+	if (sa_kern->uaddrlen != unaddrlen)
+		return 0;
+
+	sa_kern_unaddr = bpf_core_cast(sa_kern->uaddr, struct sockaddr_un);
+	if (memcmp(sa_kern_unaddr->sun_path, SERVUN_REWRITE_ADDRESS,
+			sizeof(SERVUN_REWRITE_ADDRESS) - 1) != 0)
+		return 0;
+
+	return 1;
+}
+
+SEC("cgroup/sendmsg_unix")
+int sendmsg_unix_deny_prog(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/set_global_vars.c b/tools/testing/selftests/bpf/progs/set_global_vars.c
new file mode 100644
index 000000000000..ebaef28b2cb3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/set_global_vars.c
@@ -0,0 +1,106 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include "bpf_experimental.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include <stdbool.h>
+
+char _license[] SEC("license") = "GPL";
+
+typedef __s32 s32;
+typedef s32 i32;
+typedef __u8 u8;
+
+enum Enum { EA1 = 0, EA2 = 11, EA3 = 10 };
+enum Enumu64 {EB1 = 0llu, EB2 = 12llu };
+enum Enums64 { EC1 = 0ll, EC2 = 13ll };
+
+const volatile __s64 var_s64 = -1;
+const volatile __u64 var_u64 = 0;
+const volatile i32 var_s32 = -1;
+const volatile __u32 var_u32 = 0;
+const volatile __s16 var_s16 = -1;
+const volatile __u16 var_u16 = 0;
+const volatile __s8 var_s8 = -1;
+const volatile u8 var_u8 = 0;
+const volatile enum Enum var_ea = EA1;
+const volatile enum Enumu64 var_eb = EB1;
+const volatile enum Enums64 var_ec = EC1;
+const volatile bool var_b = false;
+const volatile i32 arr[32];
+const volatile enum Enum enum_arr[32];
+const volatile i32 three_d[47][19][17];
+const volatile i32 *ptr_arr[32];
+
+struct Struct {
+	int:16;
+	__u16 filler;
+	struct {
+		const __u16 filler2;
+	};
+	struct Struct2 {
+		__u16 filler;
+		volatile struct {
+			const int:1;
+			union {
+				const volatile u8 var_u8[3];
+				const volatile __s16 filler3;
+				const int:1;
+				s32 mat[7][5];
+			} u;
+		};
+	} struct2[2][4];
+};
+
+const volatile __u32 stru = 0; /* same prefix as below */
+const volatile struct Struct struct1[3];
+const volatile struct Struct struct11[11][7];
+
+struct Struct3 {
+	struct {
+		u8 var_u8_l;
+	};
+	struct {
+		struct {
+			u8 var_u8_h;
+		};
+	};
+};
+
+typedef struct Struct3 Struct3_t;
+
+union Union {
+	__u16 var_u16;
+	Struct3_t struct3;
+};
+
+const volatile union Union union1 = {.var_u16 = -1};
+
+SEC("socket")
+int test_set_globals(void *ctx)
+{
+	volatile __s8 a;
+
+	a = var_s64;
+	a = var_u64;
+	a = var_s32;
+	a = var_u32;
+	a = var_s16;
+	a = var_u16;
+	a = var_s8;
+	a = var_u8;
+	a = var_ea;
+	a = var_eb;
+	a = var_ec;
+	a = var_b;
+	a = struct1[2].struct2[1][2].u.var_u8[2];
+	a = union1.var_u16;
+	a = arr[3];
+	a = arr[EA2];
+	a = enum_arr[EC2];
+	a = three_d[31][7][EA2];
+	a = struct1[2].struct2[1][2].u.mat[5][3];
+	a = struct11[7][5].struct2[0][1].u.mat[3][0];
+
+	return a;
+}
diff --git a/tools/testing/selftests/bpf/progs/setget_sockopt.c b/tools/testing/selftests/bpf/progs/setget_sockopt.c
index 9523333b8905..d330b1511979 100644
--- a/tools/testing/selftests/bpf/progs/setget_sockopt.c
+++ b/tools/testing/selftests/bpf/progs/setget_sockopt.c
@@ -6,10 +6,7 @@
 #include <bpf/bpf_core_read.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
-
-#ifndef ARRAY_SIZE
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-#endif
+#include "bpf_misc.h"
 
 extern unsigned long CONFIG_HZ __kconfig;
 
@@ -22,6 +19,7 @@ int nr_active;
 int nr_connect;
 int nr_binddev;
 int nr_socket_post_create;
+int nr_fin_wait1;
 
 struct sockopt_test {
 	int opt;
@@ -61,6 +59,11 @@ static const struct sockopt_test sol_tcp_tests[] = {
 	{ .opt = TCP_THIN_LINEAR_TIMEOUTS, .flip = 1, },
 	{ .opt = TCP_USER_TIMEOUT, .new = 123400, .expected = 123400, },
 	{ .opt = TCP_NOTSENT_LOWAT, .new = 1314, .expected = 1314, },
+	{ .opt = TCP_BPF_SOCK_OPS_CB_FLAGS, .new = BPF_SOCK_OPS_ALL_CB_FLAGS,
+	  .expected = BPF_SOCK_OPS_ALL_CB_FLAGS, },
+	{ .opt = TCP_BPF_DELACK_MAX, .new = 30000, .expected = 30000, },
+	{ .opt = TCP_BPF_RTO_MIN, .new = 30000, .expected = 30000, },
+	{ .opt = TCP_RTO_MAX_MS, .new = 2000, .expected = 2000, },
 	{ .opt = 0, },
 };
 
@@ -80,6 +83,14 @@ struct loop_ctx {
 	struct sock *sk;
 };
 
+static bool sk_is_tcp(struct sock *sk)
+{
+	return (sk->__sk_common.skc_family == AF_INET ||
+		sk->__sk_common.skc_family == AF_INET6) &&
+		sk->sk_type == SOCK_STREAM &&
+		sk->sk_protocol == IPPROTO_TCP;
+}
+
 static int bpf_test_sockopt_flip(void *ctx, struct sock *sk,
 				 const struct sockopt_test *t,
 				 int level)
@@ -88,6 +99,9 @@ static int bpf_test_sockopt_flip(void *ctx, struct sock *sk,
 
 	opt = t->opt;
 
+	if (opt == SO_TXREHASH && !sk_is_tcp(sk))
+		return 0;
+
 	if (bpf_getsockopt(ctx, level, opt, &old, sizeof(old)))
 		return 1;
 	/* kernel initialized txrehash to 255 */
@@ -355,11 +369,30 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family,
 	return 1;
 }
 
+SEC("cgroup/getsockopt")
+int _getsockopt(struct bpf_sockopt *ctx)
+{
+	struct bpf_sock *sk = ctx->sk;
+	int *optval = ctx->optval;
+	struct tcp_sock *tp;
+
+	if (!sk || ctx->level != SOL_TCP || ctx->optname != TCP_BPF_SOCK_OPS_CB_FLAGS)
+		return 1;
+
+	tp = bpf_core_cast(sk, struct tcp_sock);
+	if (ctx->optval + sizeof(int) <= ctx->optval_end) {
+		*optval = tp->bpf_sock_ops_cb_flags;
+		ctx->retval = 0;
+	}
+	return 1;
+}
+
 SEC("sockops")
 int skops_sockopt(struct bpf_sock_ops *skops)
 {
 	struct bpf_sock *bpf_sk = skops->sk;
 	struct sock *sk;
+	int flags;
 
 	if (!bpf_sk)
 		return 1;
@@ -386,6 +419,12 @@ int skops_sockopt(struct bpf_sock_ops *skops)
 		nr_passive += !(bpf_test_sockopt(skops, sk) ||
 				test_tcp_maxseg(skops, sk) ||
 				test_tcp_saved_syn(skops, sk));
+		flags = skops->bpf_sock_ops_cb_flags | BPF_SOCK_OPS_STATE_CB_FLAG;
+		bpf_setsockopt(skops, SOL_TCP, TCP_BPF_SOCK_OPS_CB_FLAGS, &flags, sizeof(flags));
+		break;
+	case BPF_SOCK_OPS_STATE_CB:
+		if (skops->args[1] == BPF_TCP_CLOSE_WAIT)
+			nr_fin_wait1 += !bpf_test_sockopt(skops, sk);
 		break;
 	}
 
diff --git a/tools/testing/selftests/bpf/progs/sk_bypass_prot_mem.c b/tools/testing/selftests/bpf/progs/sk_bypass_prot_mem.c
new file mode 100644
index 000000000000..09a00d11ffcc
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/sk_bypass_prot_mem.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright 2025 Google LLC */
+
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <errno.h>
+
+extern int tcp_memory_per_cpu_fw_alloc __ksym;
+extern int udp_memory_per_cpu_fw_alloc __ksym;
+
+int nr_cpus;
+bool tcp_activated, udp_activated;
+long tcp_memory_allocated, udp_memory_allocated;
+
+struct sk_prot {
+	long *memory_allocated;
+	int *memory_per_cpu_fw_alloc;
+};
+
+static int drain_memory_per_cpu_fw_alloc(__u32 i, struct sk_prot *sk_prot_ctx)
+{
+	int *memory_per_cpu_fw_alloc;
+
+	memory_per_cpu_fw_alloc = bpf_per_cpu_ptr(sk_prot_ctx->memory_per_cpu_fw_alloc, i);
+	if (memory_per_cpu_fw_alloc)
+		*sk_prot_ctx->memory_allocated += *memory_per_cpu_fw_alloc;
+
+	return 0;
+}
+
+static long get_memory_allocated(struct sock *_sk, int *memory_per_cpu_fw_alloc)
+{
+	struct sock *sk = bpf_core_cast(_sk, struct sock);
+	struct sk_prot sk_prot_ctx;
+	long memory_allocated;
+
+	/* net_aligned_data.{tcp,udp}_memory_allocated was not available. */
+	memory_allocated = sk->__sk_common.skc_prot->memory_allocated->counter;
+
+	sk_prot_ctx.memory_allocated = &memory_allocated;
+	sk_prot_ctx.memory_per_cpu_fw_alloc = memory_per_cpu_fw_alloc;
+
+	bpf_loop(nr_cpus, drain_memory_per_cpu_fw_alloc, &sk_prot_ctx, 0);
+
+	return memory_allocated;
+}
+
+static void fentry_init_sock(struct sock *sk, bool *activated,
+			     long *memory_allocated, int *memory_per_cpu_fw_alloc)
+{
+	if (!*activated)
+		return;
+
+	*memory_allocated = get_memory_allocated(sk, memory_per_cpu_fw_alloc);
+	*activated = false;
+}
+
+SEC("fentry/tcp_init_sock")
+int BPF_PROG(fentry_tcp_init_sock, struct sock *sk)
+{
+	fentry_init_sock(sk, &tcp_activated,
+			 &tcp_memory_allocated, &tcp_memory_per_cpu_fw_alloc);
+	return 0;
+}
+
+SEC("fentry/udp_init_sock")
+int BPF_PROG(fentry_udp_init_sock, struct sock *sk)
+{
+	fentry_init_sock(sk, &udp_activated,
+			 &udp_memory_allocated, &udp_memory_per_cpu_fw_alloc);
+	return 0;
+}
+
+SEC("cgroup/sock_create")
+int sock_create(struct bpf_sock *ctx)
+{
+	int err, val = 1;
+
+	err = bpf_setsockopt(ctx, SOL_SOCKET, SK_BPF_BYPASS_PROT_MEM,
+			     &val, sizeof(val));
+	if (err)
+		goto err;
+
+	val = 0;
+
+	err = bpf_getsockopt(ctx, SOL_SOCKET, SK_BPF_BYPASS_PROT_MEM,
+			     &val, sizeof(val));
+	if (err)
+		goto err;
+
+	if (val != 1) {
+		err = -EINVAL;
+		goto err;
+	}
+
+	return 1;
+
+err:
+	bpf_set_retval(err);
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c b/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c
new file mode 100644
index 000000000000..46d6eb2a3b17
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/sk_storage_omem_uncharge.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Facebook */
+#include "vmlinux.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+void *local_storage_ptr = NULL;
+void *sk_ptr = NULL;
+int cookie_found = 0;
+__u64 cookie = 0;
+__u32 omem = 0;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, int);
+} sk_storage SEC(".maps");
+
+SEC("fexit/bpf_local_storage_destroy")
+int BPF_PROG(bpf_local_storage_destroy, struct bpf_local_storage *local_storage)
+{
+	struct sock *sk;
+
+	if (local_storage_ptr != local_storage)
+		return 0;
+
+	sk = bpf_core_cast(sk_ptr, struct sock);
+	if (sk->sk_cookie.counter != cookie)
+		return 0;
+
+	cookie_found++;
+	omem = sk->sk_omem_alloc.counter;
+	local_storage_ptr = NULL;
+
+	return 0;
+}
+
+SEC("fentry/inet6_sock_destruct")
+int BPF_PROG(inet6_sock_destruct, struct sock *sk)
+{
+	int *value;
+
+	if (!cookie || sk->sk_cookie.counter != cookie)
+		return 0;
+
+	value = bpf_sk_storage_get(&sk_storage, sk, 0, 0);
+	if (value && *value == 0xdeadbeef) {
+		cookie_found++;
+		sk_ptr = sk;
+		local_storage_ptr = sk->sk_bpf_storage;
+	}
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/skb_pkt_end.c b/tools/testing/selftests/bpf/progs/skb_pkt_end.c
index 992b7861003a..3bb4451524a1 100644
--- a/tools/testing/selftests/bpf/progs/skb_pkt_end.c
+++ b/tools/testing/selftests/bpf/progs/skb_pkt_end.c
@@ -1,5 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
+#ifndef BPF_NO_PRESERVE_ACCESS_INDEX
 #define BPF_NO_PRESERVE_ACCESS_INDEX
+#endif
 #include <vmlinux.h>
 #include <bpf/bpf_core_read.h>
 #include <bpf/bpf_helpers.h>
@@ -31,6 +33,8 @@ int main_prog(struct __sk_buff *skb)
 	struct iphdr *ip = NULL;
 	struct tcphdr *tcp;
 	__u8 proto = 0;
+	int urg_ptr;
+	u32 offset;
 
 	if (!(ip = get_iphdr(skb)))
 		goto out;
@@ -46,7 +50,14 @@ int main_prog(struct __sk_buff *skb)
 	if (!tcp)
 		goto out;
 
-	return tcp->urg_ptr;
+	urg_ptr = tcp->urg_ptr;
+
+	/* Checksum validation part */
+	proto++;
+	offset = sizeof(struct ethhdr) + offsetof(struct iphdr, protocol);
+	bpf_skb_store_bytes(skb, offset, &proto, sizeof(proto), BPF_F_RECOMPUTE_CSUM);
+
+	return urg_ptr;
 out:
 	return -1;
 }
diff --git a/tools/testing/selftests/bpf/progs/sock_addr_kern.c b/tools/testing/selftests/bpf/progs/sock_addr_kern.c
new file mode 100644
index 000000000000..84ad515eafd6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/sock_addr_kern.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Google LLC */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+SEC("syscall")
+int init_sock(struct init_sock_args *args)
+{
+	bpf_kfunc_init_sock(args);
+
+	return 0;
+}
+
+SEC("syscall")
+int close_sock(void *ctx)
+{
+	bpf_kfunc_close_sock();
+
+	return 0;
+}
+
+SEC("syscall")
+int kernel_connect(struct addr_args *args)
+{
+	return bpf_kfunc_call_kernel_connect(args);
+}
+
+SEC("syscall")
+int kernel_bind(struct addr_args *args)
+{
+	return bpf_kfunc_call_kernel_bind(args);
+}
+
+SEC("syscall")
+int kernel_listen(struct addr_args *args)
+{
+	return bpf_kfunc_call_kernel_listen();
+}
+
+SEC("syscall")
+int kernel_sendmsg(struct sendmsg_args *args)
+{
+	return bpf_kfunc_call_kernel_sendmsg(args);
+}
+
+SEC("syscall")
+int sock_sendmsg(struct sendmsg_args *args)
+{
+	return bpf_kfunc_call_sock_sendmsg(args);
+}
+
+SEC("syscall")
+int kernel_getsockname(struct addr_args *args)
+{
+	return bpf_kfunc_call_kernel_getsockname(args);
+}
+
+SEC("syscall")
+int kernel_getpeername(struct addr_args *args)
+{
+	return bpf_kfunc_call_kernel_getpeername(args);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/sock_destroy_prog.c b/tools/testing/selftests/bpf/progs/sock_destroy_prog.c
new file mode 100644
index 000000000000..9e0bf7a54cec
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/sock_destroy_prog.c
@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#include "bpf_tracing_net.h"
+
+__be16 serv_port = 0;
+
+int bpf_sock_destroy(struct sock_common *sk) __ksym;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} tcp_conn_sockets SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} udp_conn_sockets SEC(".maps");
+
+SEC("cgroup/connect6")
+int sock_connect(struct bpf_sock_addr *ctx)
+{
+	__u64 sock_cookie = 0;
+	int key = 0;
+	__u32 keyc = 0;
+
+	if (ctx->family != AF_INET6 || ctx->user_family != AF_INET6)
+		return 1;
+
+	sock_cookie = bpf_get_socket_cookie(ctx);
+	if (ctx->protocol == IPPROTO_TCP)
+		bpf_map_update_elem(&tcp_conn_sockets, &key, &sock_cookie, 0);
+	else if (ctx->protocol == IPPROTO_UDP)
+		bpf_map_update_elem(&udp_conn_sockets, &keyc, &sock_cookie, 0);
+	else
+		return 1;
+
+	return 1;
+}
+
+SEC("iter/tcp")
+int iter_tcp6_client(struct bpf_iter__tcp *ctx)
+{
+	struct sock_common *sk_common = ctx->sk_common;
+	__u64 sock_cookie = 0;
+	__u64 *val;
+	int key = 0;
+
+	if (!sk_common)
+		return 0;
+
+	if (sk_common->skc_family != AF_INET6)
+		return 0;
+
+	sock_cookie  = bpf_get_socket_cookie(sk_common);
+	val = bpf_map_lookup_elem(&tcp_conn_sockets, &key);
+	if (!val)
+		return 0;
+	/* Destroy connected client sockets. */
+	if (sock_cookie == *val)
+		bpf_sock_destroy(sk_common);
+
+	return 0;
+}
+
+SEC("iter/tcp")
+int iter_tcp6_server(struct bpf_iter__tcp *ctx)
+{
+	struct sock_common *sk_common = ctx->sk_common;
+	const struct inet_connection_sock *icsk;
+	const struct inet_sock *inet;
+	struct tcp6_sock *tcp_sk;
+	__be16 srcp;
+
+	if (!sk_common)
+		return 0;
+
+	if (sk_common->skc_family != AF_INET6)
+		return 0;
+
+	tcp_sk = bpf_skc_to_tcp6_sock(sk_common);
+	if (!tcp_sk)
+		return 0;
+
+	icsk = &tcp_sk->tcp.inet_conn;
+	inet = &icsk->icsk_inet;
+	srcp = inet->inet_sport;
+
+	/* Destroy server sockets. */
+	if (srcp == serv_port)
+		bpf_sock_destroy(sk_common);
+
+	return 0;
+}
+
+
+SEC("iter/udp")
+int iter_udp6_client(struct bpf_iter__udp *ctx)
+{
+	struct udp_sock *udp_sk = ctx->udp_sk;
+	struct sock *sk = (struct sock *) udp_sk;
+	__u64 sock_cookie = 0, *val;
+	int key = 0;
+
+	if (!sk)
+		return 0;
+
+	sock_cookie  = bpf_get_socket_cookie(sk);
+	val = bpf_map_lookup_elem(&udp_conn_sockets, &key);
+	if (!val)
+		return 0;
+	/* Destroy connected client sockets. */
+	if (sock_cookie == *val)
+		bpf_sock_destroy((struct sock_common *)sk);
+
+	return 0;
+}
+
+SEC("iter/udp")
+int iter_udp6_server(struct bpf_iter__udp *ctx)
+{
+	struct udp_sock *udp_sk = ctx->udp_sk;
+	struct sock *sk = (struct sock *) udp_sk;
+	struct inet_sock *inet;
+	__be16 srcp;
+
+	if (!sk)
+		return 0;
+
+	inet = &udp_sk->inet;
+	srcp = inet->inet_sport;
+	if (srcp == serv_port)
+		bpf_sock_destroy((struct sock_common *)sk);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/sock_destroy_prog_fail.c b/tools/testing/selftests/bpf/progs/sock_destroy_prog_fail.c
new file mode 100644
index 000000000000..dd6850b58e25
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/sock_destroy_prog_fail.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+int bpf_sock_destroy(struct sock_common *sk) __ksym;
+
+SEC("tp_btf/tcp_destroy_sock")
+__failure __msg("calling kernel function bpf_sock_destroy is not allowed")
+int BPF_PROG(trace_tcp_destroy_sock, struct sock *sk)
+{
+	/* should not load */
+	bpf_sock_destroy((struct sock_common *)sk);
+
+	return 0;
+}
+
diff --git a/tools/testing/selftests/bpf/progs/sock_iter_batch.c b/tools/testing/selftests/bpf/progs/sock_iter_batch.c
new file mode 100644
index 000000000000..77966ded5467
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/sock_iter_batch.c
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2024 Meta
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_endian.h>
+#include "bpf_tracing_net.h"
+#include "bpf_kfuncs.h"
+
+#define ATTR __always_inline
+#include "test_jhash.h"
+
+static bool ipv6_addr_loopback(const struct in6_addr *a)
+{
+	return (a->s6_addr32[0] | a->s6_addr32[1] |
+		a->s6_addr32[2] | (a->s6_addr32[3] ^ bpf_htonl(1))) == 0;
+}
+
+static bool ipv4_addr_loopback(__be32 a)
+{
+	return a == bpf_ntohl(0x7f000001);
+}
+
+volatile const unsigned int sf;
+volatile const unsigned int ss;
+volatile const __u16 ports[2];
+unsigned int bucket[2];
+
+SEC("iter/tcp")
+int iter_tcp_soreuse(struct bpf_iter__tcp *ctx)
+{
+	struct sock *sk = (struct sock *)ctx->sk_common;
+	struct inet_hashinfo *hinfo;
+	unsigned int hash;
+	__u64 sock_cookie;
+	struct net *net;
+	int idx;
+
+	if (!sk)
+		return 0;
+
+	sock_cookie = bpf_get_socket_cookie(sk);
+	sk = bpf_core_cast(sk, struct sock);
+	if (sk->sk_family != sf ||
+	    (ss && sk->sk_state != ss) ||
+	    (sk->sk_family == AF_INET6 ?
+	    !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr) :
+	    !ipv4_addr_loopback(sk->sk_rcv_saddr)))
+		return 0;
+
+	if (sk->sk_num == ports[0])
+		idx = 0;
+	else if (sk->sk_num == ports[1])
+		idx = 1;
+	else if (!ports[0] && !ports[1])
+		idx = 0;
+	else
+		return 0;
+
+	/* bucket selection as in inet_lhash2_bucket_sk() */
+	net = sk->sk_net.net;
+	hash = jhash2(sk->sk_v6_rcv_saddr.s6_addr32, 4, net->hash_mix);
+	hash ^= sk->sk_num;
+	hinfo = net->ipv4.tcp_death_row.hashinfo;
+	bucket[idx] = hash & hinfo->lhash2_mask;
+	bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx));
+	bpf_seq_write(ctx->meta->seq, &sock_cookie, sizeof(sock_cookie));
+
+	return 0;
+}
+
+volatile const __u64 destroy_cookie;
+
+SEC("iter/tcp")
+int iter_tcp_destroy(struct bpf_iter__tcp *ctx)
+{
+	struct sock_common *sk_common = (struct sock_common *)ctx->sk_common;
+	__u64 sock_cookie;
+
+	if (!sk_common)
+		return 0;
+
+	sock_cookie = bpf_get_socket_cookie(sk_common);
+	if (sock_cookie != destroy_cookie)
+		return 0;
+
+	bpf_sock_destroy(sk_common);
+	bpf_seq_write(ctx->meta->seq, &sock_cookie, sizeof(sock_cookie));
+
+	return 0;
+}
+
+#define udp_sk(ptr) container_of(ptr, struct udp_sock, inet.sk)
+
+SEC("iter/udp")
+int iter_udp_soreuse(struct bpf_iter__udp *ctx)
+{
+	struct sock *sk = (struct sock *)ctx->udp_sk;
+	struct udp_table *udptable;
+	__u64 sock_cookie;
+	int idx;
+
+	if (!sk)
+		return 0;
+
+	sock_cookie = bpf_get_socket_cookie(sk);
+	sk = bpf_core_cast(sk, struct sock);
+	if (sk->sk_family != sf ||
+	    (sk->sk_family == AF_INET6 ?
+	    !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr) :
+	    !ipv4_addr_loopback(sk->sk_rcv_saddr)))
+		return 0;
+
+	if (sk->sk_num == ports[0])
+		idx = 0;
+	else if (sk->sk_num == ports[1])
+		idx = 1;
+	else if (!ports[0] && !ports[1])
+		idx = 0;
+	else
+		return 0;
+
+	/* bucket selection as in udp_hashslot2() */
+	udptable = sk->sk_net.net->ipv4.udp_table;
+	bucket[idx] = udp_sk(sk)->udp_portaddr_hash & udptable->mask;
+	bpf_seq_write(ctx->meta->seq, &idx, sizeof(idx));
+	bpf_seq_write(ctx->meta->seq, &sock_cookie, sizeof(sock_cookie));
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
index e2468a6d01a5..0660f29dca95 100644
--- a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
+++ b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
@@ -1,6 +1,7 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
+#include "bpf_misc.h"
 
 struct {
 	__uint(type, BPF_MAP_TYPE_SOCKMAP);
@@ -40,6 +41,9 @@ int bpf_prog2(struct __sk_buff *skb)
 	__u8 *d = data;
 	__u8 sk, map;
 
+	__sink(lport);
+	__sink(rport);
+
 	if (data + 8 > data_end)
 		return SK_DROP;
 
diff --git a/tools/testing/selftests/bpf/progs/sockopt_inherit.c b/tools/testing/selftests/bpf/progs/sockopt_inherit.c
index 9fb241b97291..a3434b840928 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_inherit.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_inherit.c
@@ -9,6 +9,8 @@ char _license[] SEC("license") = "GPL";
 #define CUSTOM_INHERIT2			1
 #define CUSTOM_LISTENER			2
 
+__s32 page_size = 0;
+
 struct sockopt_inherit {
 	__u8 val;
 };
@@ -55,7 +57,7 @@ int _getsockopt(struct bpf_sockopt *ctx)
 	__u8 *optval = ctx->optval;
 
 	if (ctx->level != SOL_CUSTOM)
-		return 1; /* only interested in SOL_CUSTOM */
+		goto out; /* only interested in SOL_CUSTOM */
 
 	if (optval + 1 > optval_end)
 		return 0; /* EPERM, bounds check */
@@ -70,6 +72,12 @@ int _getsockopt(struct bpf_sockopt *ctx)
 	ctx->optlen = 1;
 
 	return 1;
+
+out:
+	/* optval larger than PAGE_SIZE use kernel's buffer. */
+	if (ctx->optlen > page_size)
+		ctx->optlen = 0;
+	return 1;
 }
 
 SEC("cgroup/setsockopt")
@@ -80,7 +88,7 @@ int _setsockopt(struct bpf_sockopt *ctx)
 	__u8 *optval = ctx->optval;
 
 	if (ctx->level != SOL_CUSTOM)
-		return 1; /* only interested in SOL_CUSTOM */
+		goto out; /* only interested in SOL_CUSTOM */
 
 	if (optval + 1 > optval_end)
 		return 0; /* EPERM, bounds check */
@@ -93,4 +101,10 @@ int _setsockopt(struct bpf_sockopt *ctx)
 	ctx->optlen = -1;
 
 	return 1;
+
+out:
+	/* optval larger than PAGE_SIZE use kernel's buffer. */
+	if (ctx->optlen > page_size)
+		ctx->optlen = 0;
+	return 1;
 }
diff --git a/tools/testing/selftests/bpf/progs/sockopt_multi.c b/tools/testing/selftests/bpf/progs/sockopt_multi.c
index 177a59069dae..db67278e12d4 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_multi.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_multi.c
@@ -5,6 +5,8 @@
 
 char _license[] SEC("license") = "GPL";
 
+__s32 page_size = 0;
+
 SEC("cgroup/getsockopt")
 int _getsockopt_child(struct bpf_sockopt *ctx)
 {
@@ -12,7 +14,7 @@ int _getsockopt_child(struct bpf_sockopt *ctx)
 	__u8 *optval = ctx->optval;
 
 	if (ctx->level != SOL_IP || ctx->optname != IP_TOS)
-		return 1;
+		goto out;
 
 	if (optval + 1 > optval_end)
 		return 0; /* EPERM, bounds check */
@@ -26,6 +28,12 @@ int _getsockopt_child(struct bpf_sockopt *ctx)
 	ctx->optlen = 1;
 
 	return 1;
+
+out:
+	/* optval larger than PAGE_SIZE use kernel's buffer. */
+	if (ctx->optlen > page_size)
+		ctx->optlen = 0;
+	return 1;
 }
 
 SEC("cgroup/getsockopt")
@@ -35,7 +43,7 @@ int _getsockopt_parent(struct bpf_sockopt *ctx)
 	__u8 *optval = ctx->optval;
 
 	if (ctx->level != SOL_IP || ctx->optname != IP_TOS)
-		return 1;
+		goto out;
 
 	if (optval + 1 > optval_end)
 		return 0; /* EPERM, bounds check */
@@ -49,6 +57,12 @@ int _getsockopt_parent(struct bpf_sockopt *ctx)
 	ctx->optlen = 1;
 
 	return 1;
+
+out:
+	/* optval larger than PAGE_SIZE use kernel's buffer. */
+	if (ctx->optlen > page_size)
+		ctx->optlen = 0;
+	return 1;
 }
 
 SEC("cgroup/setsockopt")
@@ -58,7 +72,7 @@ int _setsockopt(struct bpf_sockopt *ctx)
 	__u8 *optval = ctx->optval;
 
 	if (ctx->level != SOL_IP || ctx->optname != IP_TOS)
-		return 1;
+		goto out;
 
 	if (optval + 1 > optval_end)
 		return 0; /* EPERM, bounds check */
@@ -67,4 +81,10 @@ int _setsockopt(struct bpf_sockopt *ctx)
 	ctx->optlen = 1;
 
 	return 1;
+
+out:
+	/* optval larger than PAGE_SIZE use kernel's buffer. */
+	if (ctx->optlen > page_size)
+		ctx->optlen = 0;
+	return 1;
 }
diff --git a/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c
index 1bce83b6e3a7..5c3614333b01 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_qos_to_cc.c
@@ -1,25 +1,23 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2021 Facebook */
-#include <string.h>
-#include <linux/tcp.h>
-#include <netinet/in.h>
-#include <linux/bpf.h>
-#include <bpf/bpf_helpers.h>
-#include "bpf_tcp_helpers.h"
+#include "bpf_tracing_net.h"
 
 char _license[] SEC("license") = "GPL";
 
+__s32 page_size = 0;
+
+const char cc_reno[TCP_CA_NAME_MAX] = "reno";
+const char cc_cubic[TCP_CA_NAME_MAX] = "cubic";
+
 SEC("cgroup/setsockopt")
 int sockopt_qos_to_cc(struct bpf_sockopt *ctx)
 {
 	void *optval_end = ctx->optval_end;
 	int *optval = ctx->optval;
 	char buf[TCP_CA_NAME_MAX];
-	char cc_reno[TCP_CA_NAME_MAX] = "reno";
-	char cc_cubic[TCP_CA_NAME_MAX] = "cubic";
 
 	if (ctx->level != SOL_IPV6 || ctx->optname != IPV6_TCLASS)
-		return 1;
+		goto out;
 
 	if (optval + 1 > optval_end)
 		return 0; /* EPERM, bounds check */
@@ -27,13 +25,19 @@ int sockopt_qos_to_cc(struct bpf_sockopt *ctx)
 	if (bpf_getsockopt(ctx->sk, SOL_TCP, TCP_CONGESTION, &buf, sizeof(buf)))
 		return 0;
 
-	if (!tcp_cc_eq(buf, cc_cubic))
+	if (bpf_strncmp(buf, sizeof(buf), cc_cubic))
 		return 0;
 
 	if (*optval == 0x2d) {
-		if (bpf_setsockopt(ctx->sk, SOL_TCP, TCP_CONGESTION, &cc_reno,
+		if (bpf_setsockopt(ctx->sk, SOL_TCP, TCP_CONGESTION, (void *)&cc_reno,
 				sizeof(cc_reno)))
 			return 0;
 	}
 	return 1;
+
+out:
+	/* optval larger than PAGE_SIZE use kernel's buffer. */
+	if (ctx->optlen > page_size)
+		ctx->optlen = 0;
+	return 1;
 }
diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c
index c8d810010a94..cb990a7d3d45 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_sk.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c
@@ -32,6 +32,12 @@ int _getsockopt(struct bpf_sockopt *ctx)
 	__u8 *optval_end = ctx->optval_end;
 	__u8 *optval = ctx->optval;
 	struct sockopt_sk *storage;
+	struct bpf_sock *sk;
+
+	/* Bypass AF_NETLINK. */
+	sk = ctx->sk;
+	if (sk && sk->family == AF_NETLINK)
+		goto out;
 
 	/* Make sure bpf_get_netns_cookie is callable.
 	 */
@@ -46,8 +52,7 @@ int _getsockopt(struct bpf_sockopt *ctx)
 		 * let next BPF program in the cgroup chain or kernel
 		 * handle it.
 		 */
-		ctx->optlen = 0; /* bypass optval>PAGE_SIZE */
-		return 1;
+		goto out;
 	}
 
 	if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) {
@@ -55,7 +60,7 @@ int _getsockopt(struct bpf_sockopt *ctx)
 		 * let next BPF program in the cgroup chain or kernel
 		 * handle it.
 		 */
-		return 1;
+		goto out;
 	}
 
 	if (ctx->level == SOL_TCP && ctx->optname == TCP_CONGESTION) {
@@ -63,7 +68,7 @@ int _getsockopt(struct bpf_sockopt *ctx)
 		 * let next BPF program in the cgroup chain or kernel
 		 * handle it.
 		 */
-		return 1;
+		goto out;
 	}
 
 	if (ctx->level == SOL_TCP && ctx->optname == TCP_ZEROCOPY_RECEIVE) {
@@ -79,7 +84,7 @@ int _getsockopt(struct bpf_sockopt *ctx)
 		if (((struct tcp_zerocopy_receive *)optval)->address != 0)
 			return 0; /* unexpected data */
 
-		return 1;
+		goto out;
 	}
 
 	if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) {
@@ -123,6 +128,12 @@ int _getsockopt(struct bpf_sockopt *ctx)
 	ctx->optlen = 1;
 
 	return 1;
+
+out:
+	/* optval larger than PAGE_SIZE use kernel's buffer. */
+	if (ctx->optlen > page_size)
+		ctx->optlen = 0;
+	return 1;
 }
 
 SEC("cgroup/setsockopt")
@@ -131,6 +142,12 @@ int _setsockopt(struct bpf_sockopt *ctx)
 	__u8 *optval_end = ctx->optval_end;
 	__u8 *optval = ctx->optval;
 	struct sockopt_sk *storage;
+	struct bpf_sock *sk;
+
+	/* Bypass AF_NETLINK. */
+	sk = ctx->sk;
+	if (sk && sk->family == AF_NETLINK)
+		goto out;
 
 	/* Make sure bpf_get_netns_cookie is callable.
 	 */
@@ -212,4 +229,10 @@ int _setsockopt(struct bpf_sockopt *ctx)
 			   */
 
 	return 1;
+
+out:
+	/* optval larger than PAGE_SIZE use kernel's buffer. */
+	if (ctx->optlen > page_size)
+		ctx->optlen = 0;
+	return 1;
 }
diff --git a/tools/testing/selftests/bpf/progs/stacktrace_ips.c b/tools/testing/selftests/bpf/progs/stacktrace_ips.c
new file mode 100644
index 000000000000..a96c8150d7f5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/stacktrace_ips.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#ifndef PERF_MAX_STACK_DEPTH
+#define PERF_MAX_STACK_DEPTH         127
+#endif
+
+typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH];
+
+struct {
+	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
+	__uint(max_entries, 16384);
+	__type(key, __u32);
+	__type(value, stack_trace_t);
+} stackmap SEC(".maps");
+
+extern bool CONFIG_UNWINDER_ORC __kconfig __weak;
+
+/*
+ * This function is here to have CONFIG_UNWINDER_ORC
+ * used and added to object BTF.
+ */
+int unused(void)
+{
+	return CONFIG_UNWINDER_ORC ? 0 : 1;
+}
+
+__u32 stack_key;
+
+SEC("kprobe.multi")
+int kprobe_multi_test(struct pt_regs *ctx)
+{
+	stack_key = bpf_get_stackid(ctx, &stackmap, 0);
+	return 0;
+}
+
+SEC("raw_tp/bpf_testmod_test_read")
+int rawtp_test(void *ctx)
+{
+	/* Skip ebpf program entry in the stack. */
+	stack_key = bpf_get_stackid(ctx, &stackmap, 0);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/stacktrace_map.c
index 728dbd39eff0..0c77df05be7f 100644
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
+++ b/tools/testing/selftests/bpf/progs/stacktrace_map.c
@@ -38,7 +38,7 @@ struct {
 	__type(value, stack_trace_t);
 } stack_amap SEC(".maps");
 
-/* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
+/* taken from /sys/kernel/tracing/events/sched/sched_switch/format */
 struct sched_switch_args {
 	unsigned long long pad;
 	char prev_comm[TASK_COMM_LEN];
@@ -50,6 +50,7 @@ struct sched_switch_args {
 	int next_prio;
 };
 
+__u32 stack_id;
 SEC("tracepoint/sched/sched_switch")
 int oncpu(struct sched_switch_args *ctx)
 {
@@ -64,6 +65,7 @@ int oncpu(struct sched_switch_args *ctx)
 	/* The size of stackmap and stackid_hmap should be the same */
 	key = bpf_get_stackid(ctx, &stackmap, 0);
 	if ((int)key >= 0) {
+		stack_id = key;
 		bpf_map_update_elem(&stackid_hmap, &key, &val, 0);
 		stack_p = bpf_map_lookup_elem(&stack_amap, &key);
 		if (stack_p)
diff --git a/tools/testing/selftests/bpf/progs/stream.c b/tools/testing/selftests/bpf/progs/stream.c
new file mode 100644
index 000000000000..4a5bd852f10c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/stream.c
@@ -0,0 +1,237 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+#include "bpf_arena_common.h"
+
+struct arr_elem {
+	struct bpf_res_spin_lock lock;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct arr_elem);
+} arrmap SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARENA);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__uint(max_entries, 1); /* number of pages */
+} arena SEC(".maps");
+
+struct elem {
+	struct bpf_timer timer;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} array SEC(".maps");
+
+#define ENOSPC 28
+#define _STR "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
+
+int size;
+u64 fault_addr;
+void *arena_ptr;
+
+SEC("syscall")
+__success __retval(0)
+int stream_exhaust(void *ctx)
+{
+	/* Use global variable for loop convergence. */
+	size = 0;
+	bpf_repeat(BPF_MAX_LOOPS) {
+		if (bpf_stream_printk(BPF_STDOUT, _STR) == -ENOSPC && size == 99954)
+			return 0;
+		size += sizeof(_STR) - 1;
+	}
+	return 1;
+}
+
+SEC("syscall")
+__arch_x86_64
+__arch_arm64
+__arch_s390x
+__success __retval(0)
+__stderr("ERROR: Timeout detected for may_goto instruction")
+__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}")
+__stderr("Call trace:\n"
+"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n"
+"|[ \t]+[^\n]+\n)*}}")
+int stream_cond_break(void *ctx)
+{
+	while (can_loop)
+		;
+	return 0;
+}
+
+SEC("syscall")
+__success __retval(0)
+__stderr("ERROR: AA or ABBA deadlock detected for bpf_res_spin_lock")
+__stderr("{{Attempted lock   = (0x[0-9a-fA-F]+)\n"
+"Total held locks = 1\n"
+"Held lock\\[ 0\\] = \\1}}")
+__stderr("...")
+__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}")
+__stderr("Call trace:\n"
+"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n"
+"|[ \t]+[^\n]+\n)*}}")
+int stream_deadlock(void *ctx)
+{
+	struct bpf_res_spin_lock *lock, *nlock;
+
+	lock = bpf_map_lookup_elem(&arrmap, &(int){0});
+	if (!lock)
+		return 1;
+	nlock = bpf_map_lookup_elem(&arrmap, &(int){0});
+	if (!nlock)
+		return 1;
+	if (bpf_res_spin_lock(lock))
+		return 1;
+	if (bpf_res_spin_lock(nlock)) {
+		bpf_res_spin_unlock(lock);
+		return 0;
+	}
+	bpf_res_spin_unlock(nlock);
+	bpf_res_spin_unlock(lock);
+	return 1;
+}
+
+SEC("syscall")
+__success __retval(0)
+int stream_syscall(void *ctx)
+{
+	bpf_stream_printk(BPF_STDOUT, "foo");
+	return 0;
+}
+
+SEC("syscall")
+__arch_x86_64
+__arch_arm64
+__success __retval(0)
+__stderr("ERROR: Arena WRITE access at unmapped address 0x{{.*}}")
+__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}")
+__stderr("Call trace:\n"
+"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n"
+"|[ \t]+[^\n]+\n)*}}")
+int stream_arena_write_fault(void *ctx)
+{
+	struct bpf_arena *ptr = (void *)&arena;
+	u64 user_vm_start;
+
+	/* Prevent GCC bounds warning: casting &arena to struct bpf_arena *
+	 * triggers bounds checking since the map definition is smaller than struct
+	 * bpf_arena. barrier_var() makes the pointer opaque to GCC, preventing the
+	 * bounds analysis
+	 */
+	barrier_var(ptr);
+	user_vm_start = ptr->user_vm_start;
+	fault_addr = user_vm_start + 0x7fff;
+	bpf_addr_space_cast(user_vm_start, 0, 1);
+	asm volatile (
+		"r1 = %0;"
+		"r2 = 1;"
+		"*(u32 *)(r1 + 0x7fff) = r2;"
+		:
+		: "r" (user_vm_start)
+		: "r1", "r2"
+	);
+	return 0;
+}
+
+SEC("syscall")
+__arch_x86_64
+__arch_arm64
+__success __retval(0)
+__stderr("ERROR: Arena READ access at unmapped address 0x{{.*}}")
+__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}")
+__stderr("Call trace:\n"
+"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n"
+"|[ \t]+[^\n]+\n)*}}")
+int stream_arena_read_fault(void *ctx)
+{
+	struct bpf_arena *ptr = (void *)&arena;
+	u64 user_vm_start;
+
+	/* Prevent GCC bounds warning: casting &arena to struct bpf_arena *
+	 * triggers bounds checking since the map definition is smaller than struct
+	 * bpf_arena. barrier_var() makes the pointer opaque to GCC, preventing the
+	 * bounds analysis
+	 */
+	barrier_var(ptr);
+	user_vm_start = ptr->user_vm_start;
+	fault_addr = user_vm_start + 0x7fff;
+	bpf_addr_space_cast(user_vm_start, 0, 1);
+	asm volatile (
+		"r1 = %0;"
+		"r1 = *(u32 *)(r1 + 0x7fff);"
+		:
+		: "r" (user_vm_start)
+		: "r1"
+	);
+	return 0;
+}
+
+static __noinline void subprog(void)
+{
+	int __arena *addr = (int __arena *)0xdeadbeef;
+
+	arena_ptr = &arena;
+	*addr = 1;
+}
+
+SEC("syscall")
+__arch_x86_64
+__arch_arm64
+__success __retval(0)
+__stderr("ERROR: Arena WRITE access at unmapped address 0x{{.*}}")
+__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}")
+__stderr("Call trace:\n"
+"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n"
+"|[ \t]+[^\n]+\n)*}}")
+int stream_arena_subprog_fault(void *ctx)
+{
+	subprog();
+	return 0;
+}
+
+static __noinline int timer_cb(void *map, int *key, struct bpf_timer *timer)
+{
+	int __arena *addr = (int __arena *)0xdeadbeef;
+
+	arena_ptr = &arena;
+	*addr = 1;
+	return 0;
+}
+
+SEC("syscall")
+__arch_x86_64
+__arch_arm64
+__success __retval(0)
+__stderr("ERROR: Arena WRITE access at unmapped address 0x{{.*}}")
+__stderr("CPU: {{[0-9]+}} UID: 0 PID: {{[0-9]+}} Comm: {{.*}}")
+__stderr("Call trace:\n"
+"{{([a-zA-Z_][a-zA-Z0-9_]*\\+0x[0-9a-fA-F]+/0x[0-9a-fA-F]+\n"
+"|[ \t]+[^\n]+\n)*}}")
+int stream_arena_callback_fault(void *ctx)
+{
+	struct bpf_timer *arr_timer;
+
+	arr_timer = bpf_map_lookup_elem(&array, &(int){0});
+	if (!arr_timer)
+		return 0;
+	bpf_timer_init(arr_timer, &array, 1);
+	bpf_timer_set_callback(arr_timer, timer_cb);
+	bpf_timer_start(arr_timer, 0, 0);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/stream_fail.c b/tools/testing/selftests/bpf/progs/stream_fail.c
new file mode 100644
index 000000000000..3662515f0107
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/stream_fail.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_misc.h"
+
+SEC("syscall")
+__failure __msg("Possibly NULL pointer passed")
+int stream_vprintk_null_arg(void *ctx)
+{
+	bpf_stream_vprintk_impl(BPF_STDOUT, "", NULL, 0, NULL);
+	return 0;
+}
+
+SEC("syscall")
+__failure __msg("R3 type=scalar expected=")
+int stream_vprintk_scalar_arg(void *ctx)
+{
+	bpf_stream_vprintk_impl(BPF_STDOUT, "", (void *)46, 0, NULL);
+	return 0;
+}
+
+SEC("syscall")
+__failure __msg("arg#1 doesn't point to a const string")
+int stream_vprintk_string_arg(void *ctx)
+{
+	bpf_stream_vprintk_impl(BPF_STDOUT, ctx, NULL, 0, NULL);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c b/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c
new file mode 100644
index 000000000000..826e6b6aff7e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2025 Red Hat, Inc.*/
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <linux/limits.h>
+#include "bpf_misc.h"
+#include "errno.h"
+
+char *user_ptr = (char *)1;
+char *invalid_kern_ptr = (char *)-1;
+
+/*
+ * When passing userspace pointers, the error code differs based on arch:
+ *   -ERANGE on arches with non-overlapping address spaces
+ *   -EFAULT on other arches
+ */
+#if defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_loongarch) || \
+    defined(__TARGET_ARCH_powerpc) || defined(__TARGET_ARCH_x86)
+#define USER_PTR_ERR -ERANGE
+#else
+#define USER_PTR_ERR -EFAULT
+#endif
+
+/*
+ * On s390, __get_kernel_nofault (used in string kfuncs) returns 0 for NULL and
+ * user_ptr (instead of causing an exception) so the below two groups of tests
+ * are not applicable.
+ */
+#ifndef __TARGET_ARCH_s390
+
+/* Passing NULL to string kfuncs (treated as a userspace ptr) */
+SEC("syscall") __retval(USER_PTR_ERR) int test_strcmp_null1(void *ctx) { return bpf_strcmp(NULL, "hello"); }
+SEC("syscall")  __retval(USER_PTR_ERR)int test_strcmp_null2(void *ctx) { return bpf_strcmp("hello", NULL); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strcasecmp_null1(void *ctx) { return bpf_strcasecmp(NULL, "HELLO"); }
+SEC("syscall")  __retval(USER_PTR_ERR)int test_strcasecmp_null2(void *ctx) { return bpf_strcasecmp("HELLO", NULL); }
+SEC("syscall")  __retval(USER_PTR_ERR)int test_strchr_null(void *ctx) { return bpf_strchr(NULL, 'a'); }
+SEC("syscall")  __retval(USER_PTR_ERR)int test_strchrnul_null(void *ctx) { return bpf_strchrnul(NULL, 'a'); }
+SEC("syscall")  __retval(USER_PTR_ERR)int test_strnchr_null(void *ctx) { return bpf_strnchr(NULL, 1, 'a'); }
+SEC("syscall")  __retval(USER_PTR_ERR)int test_strrchr_null(void *ctx) { return bpf_strrchr(NULL, 'a'); }
+SEC("syscall")  __retval(USER_PTR_ERR)int test_strlen_null(void *ctx) { return bpf_strlen(NULL); }
+SEC("syscall")  __retval(USER_PTR_ERR)int test_strnlen_null(void *ctx) { return bpf_strnlen(NULL, 1); }
+SEC("syscall")  __retval(USER_PTR_ERR)int test_strspn_null1(void *ctx) { return bpf_strspn(NULL, "hello"); }
+SEC("syscall")  __retval(USER_PTR_ERR)int test_strspn_null2(void *ctx) { return bpf_strspn("hello", NULL); }
+SEC("syscall")  __retval(USER_PTR_ERR)int test_strcspn_null1(void *ctx) { return bpf_strcspn(NULL, "hello"); }
+SEC("syscall")  __retval(USER_PTR_ERR)int test_strcspn_null2(void *ctx) { return bpf_strcspn("hello", NULL); }
+SEC("syscall")  __retval(USER_PTR_ERR)int test_strstr_null1(void *ctx) { return bpf_strstr(NULL, "hello"); }
+SEC("syscall")  __retval(USER_PTR_ERR)int test_strstr_null2(void *ctx) { return bpf_strstr("hello", NULL); }
+SEC("syscall")  __retval(USER_PTR_ERR)int test_strcasestr_null1(void *ctx) { return bpf_strcasestr(NULL, "hello"); }
+SEC("syscall")  __retval(USER_PTR_ERR)int test_strcasestr_null2(void *ctx) { return bpf_strcasestr("hello", NULL); }
+SEC("syscall")  __retval(USER_PTR_ERR)int test_strnstr_null1(void *ctx) { return bpf_strnstr(NULL, "hello", 1); }
+SEC("syscall")  __retval(USER_PTR_ERR)int test_strnstr_null2(void *ctx) { return bpf_strnstr("hello", NULL, 1); }
+SEC("syscall")  __retval(USER_PTR_ERR)int test_strncasestr_null1(void *ctx) { return bpf_strncasestr(NULL, "hello", 1); }
+SEC("syscall")  __retval(USER_PTR_ERR)int test_strncasestr_null2(void *ctx) { return bpf_strncasestr("hello", NULL, 1); }
+
+/* Passing userspace ptr to string kfuncs */
+SEC("syscall") __retval(USER_PTR_ERR) int test_strcmp_user_ptr1(void *ctx) { return bpf_strcmp(user_ptr, "hello"); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strcmp_user_ptr2(void *ctx) { return bpf_strcmp("hello", user_ptr); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strcasecmp_user_ptr1(void *ctx) { return bpf_strcasecmp(user_ptr, "HELLO"); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strcasecmp_user_ptr2(void *ctx) { return bpf_strcasecmp("HELLO", user_ptr); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strchr_user_ptr(void *ctx) { return bpf_strchr(user_ptr, 'a'); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strchrnul_user_ptr(void *ctx) { return bpf_strchrnul(user_ptr, 'a'); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strnchr_user_ptr(void *ctx) { return bpf_strnchr(user_ptr, 1, 'a'); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strrchr_user_ptr(void *ctx) { return bpf_strrchr(user_ptr, 'a'); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strlen_user_ptr(void *ctx) { return bpf_strlen(user_ptr); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strnlen_user_ptr(void *ctx) { return bpf_strnlen(user_ptr, 1); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strspn_user_ptr1(void *ctx) { return bpf_strspn(user_ptr, "hello"); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strspn_user_ptr2(void *ctx) { return bpf_strspn("hello", user_ptr); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strcspn_user_ptr1(void *ctx) { return bpf_strcspn(user_ptr, "hello"); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strcspn_user_ptr2(void *ctx) { return bpf_strcspn("hello", user_ptr); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strstr_user_ptr1(void *ctx) { return bpf_strstr(user_ptr, "hello"); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strstr_user_ptr2(void *ctx) { return bpf_strstr("hello", user_ptr); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strcasestr_user_ptr1(void *ctx) { return bpf_strcasestr(user_ptr, "hello"); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strcasestr_user_ptr2(void *ctx) { return bpf_strcasestr("hello", user_ptr); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strnstr_user_ptr1(void *ctx) { return bpf_strnstr(user_ptr, "hello", 1); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strnstr_user_ptr2(void *ctx) { return bpf_strnstr("hello", user_ptr, 1); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strncasestr_user_ptr1(void *ctx) { return bpf_strncasestr(user_ptr, "hello", 1); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strncasestr_user_ptr2(void *ctx) { return bpf_strncasestr("hello", user_ptr, 1); }
+
+#endif /* __TARGET_ARCH_s390 */
+
+/* Passing invalid kernel ptr to string kfuncs should always return -EFAULT */
+SEC("syscall") __retval(-EFAULT) int test_strcmp_pagefault1(void *ctx) { return bpf_strcmp(invalid_kern_ptr, "hello"); }
+SEC("syscall") __retval(-EFAULT) int test_strcmp_pagefault2(void *ctx) { return bpf_strcmp("hello", invalid_kern_ptr); }
+SEC("syscall") __retval(-EFAULT) int test_strcasecmp_pagefault1(void *ctx) { return bpf_strcasecmp(invalid_kern_ptr, "HELLO"); }
+SEC("syscall") __retval(-EFAULT) int test_strcasecmp_pagefault2(void *ctx) { return bpf_strcasecmp("HELLO", invalid_kern_ptr); }
+SEC("syscall") __retval(-EFAULT) int test_strchr_pagefault(void *ctx) { return bpf_strchr(invalid_kern_ptr, 'a'); }
+SEC("syscall") __retval(-EFAULT) int test_strchrnul_pagefault(void *ctx) { return bpf_strchrnul(invalid_kern_ptr, 'a'); }
+SEC("syscall") __retval(-EFAULT) int test_strnchr_pagefault(void *ctx) { return bpf_strnchr(invalid_kern_ptr, 1, 'a'); }
+SEC("syscall") __retval(-EFAULT) int test_strrchr_pagefault(void *ctx) { return bpf_strrchr(invalid_kern_ptr, 'a'); }
+SEC("syscall") __retval(-EFAULT) int test_strlen_pagefault(void *ctx) { return bpf_strlen(invalid_kern_ptr); }
+SEC("syscall") __retval(-EFAULT) int test_strnlen_pagefault(void *ctx) { return bpf_strnlen(invalid_kern_ptr, 1); }
+SEC("syscall") __retval(-EFAULT) int test_strspn_pagefault1(void *ctx) { return bpf_strspn(invalid_kern_ptr, "hello"); }
+SEC("syscall") __retval(-EFAULT) int test_strspn_pagefault2(void *ctx) { return bpf_strspn("hello", invalid_kern_ptr); }
+SEC("syscall") __retval(-EFAULT) int test_strcspn_pagefault1(void *ctx) { return bpf_strcspn(invalid_kern_ptr, "hello"); }
+SEC("syscall") __retval(-EFAULT) int test_strcspn_pagefault2(void *ctx) { return bpf_strcspn("hello", invalid_kern_ptr); }
+SEC("syscall") __retval(-EFAULT) int test_strstr_pagefault1(void *ctx) { return bpf_strstr(invalid_kern_ptr, "hello"); }
+SEC("syscall") __retval(-EFAULT) int test_strstr_pagefault2(void *ctx) { return bpf_strstr("hello", invalid_kern_ptr); }
+SEC("syscall") __retval(-EFAULT) int test_strcasestr_pagefault1(void *ctx) { return bpf_strcasestr(invalid_kern_ptr, "hello"); }
+SEC("syscall") __retval(-EFAULT) int test_strcasestr_pagefault2(void *ctx) { return bpf_strcasestr("hello", invalid_kern_ptr); }
+SEC("syscall") __retval(-EFAULT) int test_strnstr_pagefault1(void *ctx) { return bpf_strnstr(invalid_kern_ptr, "hello", 1); }
+SEC("syscall") __retval(-EFAULT) int test_strnstr_pagefault2(void *ctx) { return bpf_strnstr("hello", invalid_kern_ptr, 1); }
+SEC("syscall") __retval(-EFAULT) int test_strncasestr_pagefault1(void *ctx) { return bpf_strncasestr(invalid_kern_ptr, "hello", 1); }
+SEC("syscall") __retval(-EFAULT) int test_strncasestr_pagefault2(void *ctx) { return bpf_strncasestr("hello", invalid_kern_ptr, 1); }
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c b/tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c
new file mode 100644
index 000000000000..05e1da1f250f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2025 Red Hat, Inc.*/
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <linux/limits.h>
+
+char long_str[XATTR_SIZE_MAX + 1];
+
+SEC("syscall") int test_strcmp_too_long(void *ctx) { return bpf_strcmp(long_str, long_str); }
+SEC("syscall") int test_strcasecmp_too_long(void *ctx) { return bpf_strcasecmp(long_str, long_str); }
+SEC("syscall") int test_strchr_too_long(void *ctx) { return bpf_strchr(long_str, 'b'); }
+SEC("syscall") int test_strchrnul_too_long(void *ctx) { return bpf_strchrnul(long_str, 'b'); }
+SEC("syscall") int test_strnchr_too_long(void *ctx) { return bpf_strnchr(long_str, sizeof(long_str), 'b'); }
+SEC("syscall") int test_strrchr_too_long(void *ctx) { return bpf_strrchr(long_str, 'b'); }
+SEC("syscall") int test_strlen_too_long(void *ctx) { return bpf_strlen(long_str); }
+SEC("syscall") int test_strnlen_too_long(void *ctx) { return bpf_strnlen(long_str, sizeof(long_str)); }
+SEC("syscall") int test_strspn_str_too_long(void *ctx) { return bpf_strspn(long_str, "a"); }
+SEC("syscall") int test_strspn_accept_too_long(void *ctx) { return bpf_strspn("b", long_str); }
+SEC("syscall") int test_strcspn_str_too_long(void *ctx) { return bpf_strcspn(long_str, "b"); }
+SEC("syscall") int test_strcspn_reject_too_long(void *ctx) { return bpf_strcspn("b", long_str); }
+SEC("syscall") int test_strstr_too_long(void *ctx) { return bpf_strstr(long_str, "hello"); }
+SEC("syscall") int test_strcasestr_too_long(void *ctx) { return bpf_strcasestr(long_str, "hello"); }
+SEC("syscall") int test_strnstr_too_long(void *ctx) { return bpf_strnstr(long_str, "hello", sizeof(long_str)); }
+SEC("syscall") int test_strncasestr_too_long(void *ctx) { return bpf_strncasestr(long_str, "hello", sizeof(long_str)); }
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c
new file mode 100644
index 000000000000..a8513964516b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2025 Red Hat, Inc.*/
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "errno.h"
+
+char str[] = "hello world";
+
+#define __test(retval) SEC("syscall") __success __retval(retval)
+
+/* Functional tests */
+__test(0) int test_strcmp_eq(void *ctx) { return bpf_strcmp(str, "hello world"); }
+__test(1) int test_strcmp_neq(void *ctx) { return bpf_strcmp(str, "hello"); }
+__test(0) int test_strcasecmp_eq1(void *ctx) { return bpf_strcasecmp(str, "hello world"); }
+__test(0) int test_strcasecmp_eq2(void *ctx) { return bpf_strcasecmp(str, "HELLO WORLD"); }
+__test(0) int test_strcasecmp_eq3(void *ctx) { return bpf_strcasecmp(str, "HELLO world"); }
+__test(1) int test_strcasecmp_neq1(void *ctx) { return bpf_strcasecmp(str, "hello"); }
+__test(1) int test_strcasecmp_neq2(void *ctx) { return bpf_strcasecmp(str, "HELLO"); }
+__test(1) int test_strchr_found(void *ctx) { return bpf_strchr(str, 'e'); }
+__test(11) int test_strchr_null(void *ctx) { return bpf_strchr(str, '\0'); }
+__test(-ENOENT) int test_strchr_notfound(void *ctx) { return bpf_strchr(str, 'x'); }
+__test(1) int test_strchrnul_found(void *ctx) { return bpf_strchrnul(str, 'e'); }
+__test(11) int test_strchrnul_notfound(void *ctx) { return bpf_strchrnul(str, 'x'); }
+__test(1) int test_strnchr_found(void *ctx) { return bpf_strnchr(str, 5, 'e'); }
+__test(11) int test_strnchr_null(void *ctx) { return bpf_strnchr(str, 12, '\0'); }
+__test(-ENOENT) int test_strnchr_notfound(void *ctx) { return bpf_strnchr(str, 5, 'w'); }
+__test(9) int test_strrchr_found(void *ctx) { return bpf_strrchr(str, 'l'); }
+__test(11) int test_strrchr_null(void *ctx) { return bpf_strrchr(str, '\0'); }
+__test(-ENOENT) int test_strrchr_notfound(void *ctx) { return bpf_strrchr(str, 'x'); }
+__test(11) int test_strlen(void *ctx) { return bpf_strlen(str); }
+__test(11) int test_strnlen(void *ctx) { return bpf_strnlen(str, 12); }
+__test(5) int test_strspn(void *ctx) { return bpf_strspn(str, "ehlo"); }
+__test(2) int test_strcspn(void *ctx) { return bpf_strcspn(str, "lo"); }
+__test(6) int test_strstr_found(void *ctx) { return bpf_strstr(str, "world"); }
+__test(6) int test_strcasestr_found(void *ctx) { return bpf_strcasestr(str, "woRLD"); }
+__test(-ENOENT) int test_strstr_notfound(void *ctx) { return bpf_strstr(str, "hi"); }
+__test(-ENOENT) int test_strcasestr_notfound(void *ctx) { return bpf_strcasestr(str, "hi"); }
+__test(0) int test_strstr_empty(void *ctx) { return bpf_strstr(str, ""); }
+__test(0) int test_strcasestr_empty(void *ctx) { return bpf_strcasestr(str, ""); }
+__test(0) int test_strnstr_found1(void *ctx) { return bpf_strnstr("", "", 0); }
+__test(0) int test_strnstr_found2(void *ctx) { return bpf_strnstr(str, "hello", 5); }
+__test(0) int test_strnstr_found3(void *ctx) { return bpf_strnstr(str, "hello", 6); }
+__test(-ENOENT) int test_strnstr_notfound1(void *ctx) { return bpf_strnstr(str, "hi", 10); }
+__test(-ENOENT) int test_strnstr_notfound2(void *ctx) { return bpf_strnstr(str, "hello", 4); }
+__test(-ENOENT) int test_strnstr_notfound3(void *ctx) { return bpf_strnstr("", "a", 0); }
+__test(0) int test_strnstr_empty(void *ctx) { return bpf_strnstr(str, "", 1); }
+__test(0) int test_strncasestr_found1(void *ctx) { return bpf_strncasestr("", "", 0); }
+__test(0) int test_strncasestr_found2(void *ctx) { return bpf_strncasestr(str, "heLLO", 5); }
+__test(0) int test_strncasestr_found3(void *ctx) { return bpf_strncasestr(str, "heLLO", 6); }
+__test(-ENOENT) int test_strncasestr_notfound1(void *ctx) { return bpf_strncasestr(str, "hi", 10); }
+__test(-ENOENT) int test_strncasestr_notfound2(void *ctx) { return bpf_strncasestr(str, "hello", 4); }
+__test(-ENOENT) int test_strncasestr_notfound3(void *ctx) { return bpf_strncasestr("", "a", 0); }
+__test(0) int test_strncasestr_empty(void *ctx) { return bpf_strncasestr(str, "", 1); }
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/strncmp_bench.c b/tools/testing/selftests/bpf/progs/strncmp_bench.c
index 18373a7df76e..f47bf88f8d2a 100644
--- a/tools/testing/selftests/bpf/progs/strncmp_bench.c
+++ b/tools/testing/selftests/bpf/progs/strncmp_bench.c
@@ -35,7 +35,10 @@ static __always_inline int local_strncmp(const char *s1, unsigned int sz,
 SEC("tp/syscalls/sys_enter_getpgid")
 int strncmp_no_helper(void *ctx)
 {
-	if (local_strncmp(str, cmp_str_len + 1, target) < 0)
+	const char *target_str = target;
+
+	barrier_var(target_str);
+	if (local_strncmp(str, cmp_str_len + 1, target_str) < 0)
 		__sync_add_and_fetch(&hits, 1);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h
index 753718595c26..6e1918deaf26 100644
--- a/tools/testing/selftests/bpf/progs/strobemeta.h
+++ b/tools/testing/selftests/bpf/progs/strobemeta.h
@@ -10,6 +10,8 @@
 #include <linux/types.h>
 #include <bpf/bpf_helpers.h>
 
+#include "bpf_compiler.h"
+
 typedef uint32_t pid_t;
 struct task_struct {};
 
@@ -24,9 +26,11 @@ struct task_struct {};
 #define STACK_TABLE_EPOCH_SHIFT 20
 #define STROBE_MAX_STR_LEN 1
 #define STROBE_MAX_CFGS 32
+#define READ_MAP_VAR_PAYLOAD_CAP					\
+	((1 + STROBE_MAX_MAP_ENTRIES * 2) * STROBE_MAX_STR_LEN)
 #define STROBE_MAX_PAYLOAD						\
 	(STROBE_MAX_STRS * STROBE_MAX_STR_LEN +				\
-	STROBE_MAX_MAPS * (1 + STROBE_MAX_MAP_ENTRIES * 2) * STROBE_MAX_STR_LEN)
+	 STROBE_MAX_MAPS * READ_MAP_VAR_PAYLOAD_CAP)
 
 struct strobe_value_header {
 	/*
@@ -135,7 +139,7 @@ struct strobe_value_loc {
 	 * tpidr_el0 for aarch64).
 	 * TLS_IMM_EXEC: absolute address of GOT entry containing offset
 	 * from thread pointer;
-	 * TLS_GENERAL_DYN: absolute addres of double GOT entry
+	 * TLS_GENERAL_DYN: absolute address of double GOT entry
 	 * containing tls_index_t struct;
 	 */
 	int64_t offset;
@@ -326,9 +330,9 @@ static void *calc_location(struct strobe_value_loc *loc, void *tls_base)
 	}
 	bpf_probe_read_user(&tls_ptr, sizeof(void *), dtv);
 	/* if pointer has (void *)-1 value, then TLS wasn't initialized yet */
-	return tls_ptr && tls_ptr != (void *)-1
-		? tls_ptr + tls_index.offset
-		: NULL;
+	if (!tls_ptr || tls_ptr == (void *)-1)
+		return NULL;
+	return tls_ptr + tls_index.offset;
 }
 
 #ifdef SUBPROGS
@@ -355,7 +359,7 @@ static __always_inline uint64_t read_str_var(struct strobemeta_cfg *cfg,
 					     size_t idx, void *tls_base,
 					     struct strobe_value_generic *value,
 					     struct strobemeta_payload *data,
-					     void *payload)
+					     size_t off)
 {
 	void *location;
 	uint64_t len;
@@ -366,10 +370,10 @@ static __always_inline uint64_t read_str_var(struct strobemeta_cfg *cfg,
 		return 0;
 
 	bpf_probe_read_user(value, sizeof(struct strobe_value_generic), location);
-	len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN, value->ptr);
+	len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN, value->ptr);
 	/*
 	 * if bpf_probe_read_user_str returns error (<0), due to casting to
-	 * unsinged int, it will become big number, so next check is
+	 * unsigned int, it will become big number, so next check is
 	 * sufficient to check for errors AND prove to BPF verifier, that
 	 * bpf_probe_read_user_str won't return anything bigger than
 	 * STROBE_MAX_STR_LEN
@@ -378,31 +382,30 @@ static __always_inline uint64_t read_str_var(struct strobemeta_cfg *cfg,
 		return 0;
 
 	data->str_lens[idx] = len;
-	return len;
+	return off + len;
 }
 
-static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
-					  size_t idx, void *tls_base,
-					  struct strobe_value_generic *value,
-					  struct strobemeta_payload *data,
-					  void *payload)
+static __always_inline uint64_t read_map_var(struct strobemeta_cfg *cfg,
+					     size_t idx, void *tls_base,
+					     struct strobe_value_generic *value,
+					     struct strobemeta_payload *data,
+					     size_t off)
 {
 	struct strobe_map_descr* descr = &data->map_descrs[idx];
 	struct strobe_map_raw map;
 	void *location;
 	uint64_t len;
-	int i;
 
 	descr->tag_len = 0; /* presume no tag is set */
 	descr->cnt = -1; /* presume no value is set */
 
 	location = calc_location(&cfg->map_locs[idx], tls_base);
 	if (!location)
-		return payload;
+		return off;
 
 	bpf_probe_read_user(value, sizeof(struct strobe_value_generic), location);
 	if (bpf_probe_read_user(&map, sizeof(struct strobe_map_raw), value->ptr))
-		return payload;
+		return off;
 
 	descr->id = map.id;
 	descr->cnt = map.cnt;
@@ -411,38 +414,38 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
 		data->req_meta_valid = 1;
 	}
 
-	len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN, map.tag);
+	len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN, map.tag);
 	if (len <= STROBE_MAX_STR_LEN) {
 		descr->tag_len = len;
-		payload += len;
+		off += len;
 	}
 
 #ifdef NO_UNROLL
-#pragma clang loop unroll(disable)
+	__pragma_loop_no_unroll
 #else
-#pragma unroll
+	__pragma_loop_unroll
 #endif
 	for (int i = 0; i < STROBE_MAX_MAP_ENTRIES; ++i) {
 		if (i >= map.cnt)
 			break;
 
 		descr->key_lens[i] = 0;
-		len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN,
+		len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN,
 					      map.entries[i].key);
 		if (len <= STROBE_MAX_STR_LEN) {
 			descr->key_lens[i] = len;
-			payload += len;
+			off += len;
 		}
 		descr->val_lens[i] = 0;
-		len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN,
+		len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN,
 					      map.entries[i].val);
 		if (len <= STROBE_MAX_STR_LEN) {
 			descr->val_lens[i] = len;
-			payload += len;
+			off += len;
 		}
 	}
 
-	return payload;
+	return off;
 }
 
 #ifdef USE_BPF_LOOP
@@ -456,14 +459,20 @@ struct read_var_ctx {
 	struct strobemeta_payload *data;
 	void *tls_base;
 	struct strobemeta_cfg *cfg;
-	void *payload;
+	size_t payload_off;
 	/* value gets mutated */
 	struct strobe_value_generic *value;
 	enum read_type type;
 };
 
-static int read_var_callback(__u32 index, struct read_var_ctx *ctx)
+static int read_var_callback(__u64 index, struct read_var_ctx *ctx)
 {
+	/* lose precision info for ctx->payload_off, verifier won't track
+	 * double xor, barrier_var() is needed to force clang keep both xors.
+	 */
+	ctx->payload_off ^= index;
+	barrier_var(ctx->payload_off);
+	ctx->payload_off ^= index;
 	switch (ctx->type) {
 	case READ_INT_VAR:
 		if (index >= STROBE_MAX_INTS)
@@ -473,14 +482,18 @@ static int read_var_callback(__u32 index, struct read_var_ctx *ctx)
 	case READ_MAP_VAR:
 		if (index >= STROBE_MAX_MAPS)
 			return 1;
-		ctx->payload = read_map_var(ctx->cfg, index, ctx->tls_base,
-					    ctx->value, ctx->data, ctx->payload);
+		if (ctx->payload_off > sizeof(ctx->data->payload) - READ_MAP_VAR_PAYLOAD_CAP)
+			return 1;
+		ctx->payload_off = read_map_var(ctx->cfg, index, ctx->tls_base,
+						ctx->value, ctx->data, ctx->payload_off);
 		break;
 	case READ_STR_VAR:
 		if (index >= STROBE_MAX_STRS)
 			return 1;
-		ctx->payload += read_str_var(ctx->cfg, index, ctx->tls_base,
-					     ctx->value, ctx->data, ctx->payload);
+		if (ctx->payload_off > sizeof(ctx->data->payload) - STROBE_MAX_STR_LEN)
+			return 1;
+		ctx->payload_off = read_str_var(ctx->cfg, index, ctx->tls_base,
+						ctx->value, ctx->data, ctx->payload_off);
 		break;
 	}
 	return 0;
@@ -502,7 +515,8 @@ static void *read_strobe_meta(struct task_struct *task,
 	pid_t pid = bpf_get_current_pid_tgid() >> 32;
 	struct strobe_value_generic value = {0};
 	struct strobemeta_cfg *cfg;
-	void *tls_base, *payload;
+	size_t payload_off;
+	void *tls_base;
 
 	cfg = bpf_map_lookup_elem(&strobemeta_cfgs, &pid);
 	if (!cfg)
@@ -510,7 +524,7 @@ static void *read_strobe_meta(struct task_struct *task,
 
 	data->int_vals_set_mask = 0;
 	data->req_meta_valid = 0;
-	payload = data->payload;
+	payload_off = 0;
 	/*
 	 * we don't have struct task_struct definition, it should be:
 	 * tls_base = (void *)task->thread.fsbase;
@@ -523,7 +537,7 @@ static void *read_strobe_meta(struct task_struct *task,
 		.tls_base = tls_base,
 		.value = &value,
 		.data = data,
-		.payload = payload,
+		.payload_off = 0,
 	};
 	int err;
 
@@ -541,30 +555,35 @@ static void *read_strobe_meta(struct task_struct *task,
 	err = bpf_loop(STROBE_MAX_MAPS, read_var_callback, &ctx, 0);
 	if (err != STROBE_MAX_MAPS)
 		return NULL;
+
+	payload_off = ctx.payload_off;
+	/* this should not really happen, here only to satisfy verifier */
+	if (payload_off > sizeof(data->payload))
+		payload_off = sizeof(data->payload);
 #else
 #ifdef NO_UNROLL
-#pragma clang loop unroll(disable)
+	__pragma_loop_no_unroll
 #else
-#pragma unroll
+	__pragma_loop_unroll
 #endif /* NO_UNROLL */
 	for (int i = 0; i < STROBE_MAX_INTS; ++i) {
 		read_int_var(cfg, i, tls_base, &value, data);
 	}
 #ifdef NO_UNROLL
-#pragma clang loop unroll(disable)
+	__pragma_loop_no_unroll
 #else
-#pragma unroll
+	__pragma_loop_unroll
 #endif /* NO_UNROLL */
 	for (int i = 0; i < STROBE_MAX_STRS; ++i) {
-		payload += read_str_var(cfg, i, tls_base, &value, data, payload);
+		payload_off = read_str_var(cfg, i, tls_base, &value, data, payload_off);
 	}
 #ifdef NO_UNROLL
-#pragma clang loop unroll(disable)
+	__pragma_loop_no_unroll
 #else
-#pragma unroll
+	__pragma_loop_unroll
 #endif /* NO_UNROLL */
 	for (int i = 0; i < STROBE_MAX_MAPS; ++i) {
-		payload = read_map_var(cfg, i, tls_base, &value, data, payload);
+		payload_off = read_map_var(cfg, i, tls_base, &value, data, payload_off);
 	}
 #endif /* USE_BPF_LOOP */
 
@@ -572,7 +591,7 @@ static void *read_strobe_meta(struct task_struct *task,
 	 * return pointer right after end of payload, so it's possible to
 	 * calculate exact amount of useful data that needs to be sent
 	 */
-	return payload;
+	return &data->payload[payload_off];
 }
 
 SEC("raw_tracepoint/kfree_skb")
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_autocreate.c b/tools/testing/selftests/bpf/progs/struct_ops_autocreate.c
new file mode 100644
index 000000000000..ba10c3896213
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_autocreate.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+int test_1_result = 0;
+
+SEC("struct_ops/test_1")
+int BPF_PROG(test_1)
+{
+	test_1_result = 42;
+	return 0;
+}
+
+SEC("struct_ops/test_1")
+int BPF_PROG(test_2)
+{
+	return 0;
+}
+
+struct bpf_testmod_ops___v1 {
+	int (*test_1)(void);
+};
+
+struct bpf_testmod_ops___v2 {
+	int (*test_1)(void);
+	int (*does_not_exist)(void);
+};
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops___v1 testmod_1 = {
+	.test_1 = (void *)test_1
+};
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops___v2 testmod_2 = {
+	.test_1 = (void *)test_1,
+	.does_not_exist = (void *)test_2
+};
+
+SEC("?.struct_ops")
+struct bpf_testmod_ops___v1 optional_map = {
+	.test_1 = (void *)test_1,
+};
+
+SEC("?.struct_ops.link")
+struct bpf_testmod_ops___v1 optional_map2 = {
+	.test_1 = (void *)test_1,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_autocreate2.c b/tools/testing/selftests/bpf/progs/struct_ops_autocreate2.c
new file mode 100644
index 000000000000..6049d9c902d3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_autocreate2.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+int test_1_result = 0;
+
+SEC("?struct_ops/test_1")
+int BPF_PROG(foo)
+{
+	test_1_result = 42;
+	return 0;
+}
+
+SEC("?struct_ops/test_1")
+int BPF_PROG(bar)
+{
+	test_1_result = 24;
+	return 0;
+}
+
+struct bpf_testmod_ops {
+	int (*test_1)(void);
+};
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_1 = {
+	.test_1 = (void *)bar
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_detach.c b/tools/testing/selftests/bpf/progs/struct_ops_detach.c
new file mode 100644
index 000000000000..284a5b008e0c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_detach.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "../test_kmods/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+/*
+ * This subprogram validates that libbpf handles the situation in which BPF
+ * object has subprograms in .text section, but has no entry BPF programs.
+ * At some point that was causing issues due to legacy logic of treating such
+ * subprogram as entry program (with unknown program type, which would fail).
+ */
+int dangling_subprog(void)
+{
+	/* do nothing, just be here */
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_do_detach;
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_forgotten_cb.c b/tools/testing/selftests/bpf/progs/struct_ops_forgotten_cb.c
new file mode 100644
index 000000000000..d8cc99f5c2e2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_forgotten_cb.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("struct_ops/test_1")
+int BPF_PROG(test_1_forgotten)
+{
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops ops = {
+	/* we forgot to reference test_1_forgotten above, oops */
+};
+
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping1.c b/tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping1.c
new file mode 100644
index 000000000000..ad8bb546c9bf
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping1.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define bpf_kfunc_multi_st_ops_test_1(args) bpf_kfunc_multi_st_ops_test_1(args, st_ops_id)
+int st_ops_id;
+
+int test_pid;
+int test_err;
+
+#define MAP1_MAGIC 1234
+
+SEC("struct_ops")
+int BPF_PROG(test_1, struct st_ops_args *args)
+{
+	return MAP1_MAGIC;
+}
+
+SEC("tp_btf/sys_enter")
+int BPF_PROG(sys_enter, struct pt_regs *regs, long id)
+{
+	struct st_ops_args args = {};
+	struct task_struct *task;
+	int ret;
+
+	task = bpf_get_current_task_btf();
+	if (!test_pid || task->pid != test_pid)
+		return 0;
+
+	ret = bpf_kfunc_multi_st_ops_test_1(&args);
+	if (ret != MAP1_MAGIC)
+		test_err++;
+
+	return 0;
+}
+
+SEC("syscall")
+int syscall_prog(void *ctx)
+{
+	struct st_ops_args args = {};
+	int ret;
+
+	ret = bpf_kfunc_multi_st_ops_test_1(&args);
+	if (ret != MAP1_MAGIC)
+		test_err++;
+
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_multi_st_ops st_ops_map = {
+	.test_1 = (void *)test_1,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping2.c b/tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping2.c
new file mode 100644
index 000000000000..cea1a2f4b62f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_id_ops_mapping2.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define bpf_kfunc_multi_st_ops_test_1(args) bpf_kfunc_multi_st_ops_test_1(args, st_ops_id)
+int st_ops_id;
+
+int test_pid;
+int test_err;
+
+#define MAP2_MAGIC 4567
+
+SEC("struct_ops")
+int BPF_PROG(test_1, struct st_ops_args *args)
+{
+	return MAP2_MAGIC;
+}
+
+SEC("tp_btf/sys_enter")
+int BPF_PROG(sys_enter, struct pt_regs *regs, long id)
+{
+	struct st_ops_args args = {};
+	struct task_struct *task;
+	int ret;
+
+	task = bpf_get_current_task_btf();
+	if (!test_pid || task->pid != test_pid)
+		return 0;
+
+	ret = bpf_kfunc_multi_st_ops_test_1(&args);
+	if (ret != MAP2_MAGIC)
+		test_err++;
+
+	return 0;
+}
+
+SEC("syscall")
+int syscall_prog(void *ctx)
+{
+	struct st_ops_args args = {};
+	int ret;
+
+	ret = bpf_kfunc_multi_st_ops_test_1(&args);
+	if (ret != MAP2_MAGIC)
+		test_err++;
+
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_multi_st_ops st_ops_map = {
+	.test_1 = (void *)test_1,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c
new file mode 100644
index 000000000000..2b98b7710816
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return.c
@@ -0,0 +1,30 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+void bpf_task_release(struct task_struct *p) __ksym;
+
+/* This test struct_ops BPF programs returning referenced kptr. The verifier should
+ * allow a referenced kptr or a NULL pointer to be returned. A referenced kptr to task
+ * here is acquired automatically as the task argument is tagged with "__ref".
+ */
+SEC("struct_ops/test_return_ref_kptr")
+struct task_struct *BPF_PROG(kptr_return, int dummy,
+			     struct task_struct *task, struct cgroup *cgrp)
+{
+	if (dummy % 2) {
+		bpf_task_release(task);
+		return NULL;
+	}
+	return task;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_kptr_return = {
+	.test_return_ref_kptr = (void *)kptr_return,
+};
+
+
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__invalid_scalar.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__invalid_scalar.c
new file mode 100644
index 000000000000..caeea158ef69
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__invalid_scalar.c
@@ -0,0 +1,26 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym;
+void bpf_task_release(struct task_struct *p) __ksym;
+
+/* This test struct_ops BPF programs returning referenced kptr. The verifier should
+ * reject programs returning a non-zero scalar value.
+ */
+SEC("struct_ops/test_return_ref_kptr")
+__failure __msg("At program exit the register R0 has smin=1 smax=1 should have been in [0, 0]")
+struct task_struct *BPF_PROG(kptr_return_fail__invalid_scalar, int dummy,
+			     struct task_struct *task, struct cgroup *cgrp)
+{
+	bpf_task_release(task);
+	return (struct task_struct *)1;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_kptr_return = {
+	.test_return_ref_kptr = (void *)kptr_return_fail__invalid_scalar,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__local_kptr.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__local_kptr.c
new file mode 100644
index 000000000000..b8b4f05c3d7f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__local_kptr.c
@@ -0,0 +1,34 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_experimental.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym;
+void bpf_task_release(struct task_struct *p) __ksym;
+
+/* This test struct_ops BPF programs returning referenced kptr. The verifier should
+ * reject programs returning a local kptr.
+ */
+SEC("struct_ops/test_return_ref_kptr")
+__failure __msg("At program exit the register R0 is not a known value (ptr_or_null_)")
+struct task_struct *BPF_PROG(kptr_return_fail__local_kptr, int dummy,
+			     struct task_struct *task, struct cgroup *cgrp)
+{
+	struct task_struct *t;
+
+	bpf_task_release(task);
+
+	t = bpf_obj_new(typeof(*task));
+	if (!t)
+		return NULL;
+
+	return t;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_kptr_return = {
+	.test_return_ref_kptr = (void *)kptr_return_fail__local_kptr,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__nonzero_offset.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__nonzero_offset.c
new file mode 100644
index 000000000000..7ddeb28c2329
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__nonzero_offset.c
@@ -0,0 +1,25 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym;
+void bpf_task_release(struct task_struct *p) __ksym;
+
+/* This test struct_ops BPF programs returning referenced kptr. The verifier should
+ * reject programs returning a modified referenced kptr.
+ */
+SEC("struct_ops/test_return_ref_kptr")
+__failure __msg("dereference of modified trusted_ptr_ ptr R0 off={{[0-9]+}} disallowed")
+struct task_struct *BPF_PROG(kptr_return_fail__nonzero_offset, int dummy,
+			     struct task_struct *task, struct cgroup *cgrp)
+{
+	return (struct task_struct *)&task->jobctl;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_kptr_return = {
+	.test_return_ref_kptr = (void *)kptr_return_fail__nonzero_offset,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__wrong_type.c b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__wrong_type.c
new file mode 100644
index 000000000000..6a2dd5367802
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_kptr_return_fail__wrong_type.c
@@ -0,0 +1,30 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym;
+void bpf_task_release(struct task_struct *p) __ksym;
+
+/* This test struct_ops BPF programs returning referenced kptr. The verifier should
+ * reject programs returning a referenced kptr of the wrong type.
+ */
+SEC("struct_ops/test_return_ref_kptr")
+__failure __msg("At program exit the register R0 is not a known value (ptr_or_null_)")
+struct task_struct *BPF_PROG(kptr_return_fail__wrong_type, int dummy,
+			     struct task_struct *task, struct cgroup *cgrp)
+{
+	struct task_struct *ret;
+
+	ret = (struct task_struct *)bpf_cgroup_acquire(cgrp);
+	bpf_task_release(task);
+
+	return ret;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_kptr_return = {
+	.test_return_ref_kptr = (void *)kptr_return_fail__wrong_type,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_maybe_null.c b/tools/testing/selftests/bpf/progs/struct_ops_maybe_null.c
new file mode 100644
index 000000000000..ccab3935aa42
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_maybe_null.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+pid_t tgid = 0;
+
+/* This is a test BPF program that uses struct_ops to access an argument
+ * that may be NULL. This is a test for the verifier to ensure that it can
+ * rip PTR_MAYBE_NULL correctly.
+ */
+SEC("struct_ops/test_maybe_null")
+int BPF_PROG(test_maybe_null, int dummy,
+	     struct task_struct *task)
+{
+	if (task)
+		tgid = task->tgid;
+
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_1 = {
+	.test_maybe_null = (void *)test_maybe_null,
+};
+
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_maybe_null_fail.c b/tools/testing/selftests/bpf/progs/struct_ops_maybe_null_fail.c
new file mode 100644
index 000000000000..8b5515f4f724
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_maybe_null_fail.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+pid_t tgid = 0;
+
+SEC("struct_ops/test_maybe_null_struct_ptr")
+int BPF_PROG(test_maybe_null_struct_ptr, int dummy,
+	     struct task_struct *task)
+{
+	tgid = task->tgid;
+
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_struct_ptr = {
+	.test_maybe_null = (void *)test_maybe_null_struct_ptr,
+};
+
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_module.c b/tools/testing/selftests/bpf/progs/struct_ops_module.c
new file mode 100644
index 000000000000..71c420c3a5a6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_module.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+int test_1_result = 0;
+int test_2_result = 0;
+
+SEC("struct_ops/test_1")
+int BPF_PROG(test_1)
+{
+	test_1_result = 0xdeadbeef;
+	return 0;
+}
+
+SEC("struct_ops/test_2")
+void BPF_PROG(test_2, int a, int b)
+{
+	test_2_result = a + b;
+}
+
+SEC("?struct_ops/test_3")
+int BPF_PROG(test_3, int a, int b)
+{
+	test_2_result = a + b + 3;
+	return a + b + 3;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_1 = {
+	.test_1 = (void *)test_1,
+	.test_2 = (void *)test_2,
+	.data = 0x1,
+};
+
+SEC("struct_ops/test_2")
+void BPF_PROG(test_2_v2, int a, int b)
+{
+	test_2_result = a * b;
+}
+
+struct bpf_testmod_ops___v2 {
+	int (*test_1)(void);
+	void (*test_2)(int a, int b);
+	int (*test_maybe_null)(int dummy, struct task_struct *task);
+};
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops___v2 testmod_2 = {
+	.test_1 = (void *)test_1,
+	.test_2 = (void *)test_2_v2,
+};
+
+struct bpf_testmod_ops___zeroed {
+	int (*test_1)(void);
+	void (*test_2)(int a, int b);
+	int (*test_maybe_null)(int dummy, struct task_struct *task);
+	void (*zeroed_op)(int a, int b);
+	int zeroed;
+};
+
+SEC("struct_ops/test_3")
+int BPF_PROG(zeroed_op)
+{
+	return 1;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops___zeroed testmod_zeroed = {
+	.test_1 = (void *)test_1,
+	.test_2 = (void *)test_2_v2,
+	.zeroed_op = (void *)zeroed_op,
+};
+
+struct bpf_testmod_ops___incompatible {
+	int (*test_1)(void);
+	void (*test_2)(int *a);
+	int data;
+};
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops___incompatible testmod_incompatible = {
+	.test_1 = (void *)test_1,
+	.test_2 = (void *)test_2,
+	.data = 3,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_multi_pages.c b/tools/testing/selftests/bpf/progs/struct_ops_multi_pages.c
new file mode 100644
index 000000000000..5b23ea817f1f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_multi_pages.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define TRAMP(x) \
+	SEC("struct_ops/tramp_" #x)		\
+	int BPF_PROG(tramp_ ## x, int a)	\
+	{					\
+		return a;			\
+	}
+
+TRAMP(1)
+TRAMP(2)
+TRAMP(3)
+TRAMP(4)
+TRAMP(5)
+TRAMP(6)
+TRAMP(7)
+TRAMP(8)
+TRAMP(9)
+TRAMP(10)
+TRAMP(11)
+TRAMP(12)
+TRAMP(13)
+TRAMP(14)
+TRAMP(15)
+TRAMP(16)
+TRAMP(17)
+TRAMP(18)
+TRAMP(19)
+TRAMP(20)
+TRAMP(21)
+TRAMP(22)
+TRAMP(23)
+TRAMP(24)
+TRAMP(25)
+TRAMP(26)
+TRAMP(27)
+TRAMP(28)
+TRAMP(29)
+TRAMP(30)
+TRAMP(31)
+TRAMP(32)
+TRAMP(33)
+TRAMP(34)
+TRAMP(35)
+TRAMP(36)
+TRAMP(37)
+TRAMP(38)
+TRAMP(39)
+TRAMP(40)
+
+#define F_TRAMP(x) .tramp_ ## x = (void *)tramp_ ## x
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops multi_pages = {
+	F_TRAMP(1),
+	F_TRAMP(2),
+	F_TRAMP(3),
+	F_TRAMP(4),
+	F_TRAMP(5),
+	F_TRAMP(6),
+	F_TRAMP(7),
+	F_TRAMP(8),
+	F_TRAMP(9),
+	F_TRAMP(10),
+	F_TRAMP(11),
+	F_TRAMP(12),
+	F_TRAMP(13),
+	F_TRAMP(14),
+	F_TRAMP(15),
+	F_TRAMP(16),
+	F_TRAMP(17),
+	F_TRAMP(18),
+	F_TRAMP(19),
+	F_TRAMP(20),
+	F_TRAMP(21),
+	F_TRAMP(22),
+	F_TRAMP(23),
+	F_TRAMP(24),
+	F_TRAMP(25),
+	F_TRAMP(26),
+	F_TRAMP(27),
+	F_TRAMP(28),
+	F_TRAMP(29),
+	F_TRAMP(30),
+	F_TRAMP(31),
+	F_TRAMP(32),
+	F_TRAMP(33),
+	F_TRAMP(34),
+	F_TRAMP(35),
+	F_TRAMP(36),
+	F_TRAMP(37),
+	F_TRAMP(38),
+	F_TRAMP(39),
+	F_TRAMP(40),
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_nulled_out_cb.c b/tools/testing/selftests/bpf/progs/struct_ops_nulled_out_cb.c
new file mode 100644
index 000000000000..5d0937fa07be
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_nulled_out_cb.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+int rand;
+int arr[1];
+
+SEC("struct_ops/test_1")
+int BPF_PROG(test_1_turn_off)
+{
+	return arr[rand]; /* potentially way out of range access */
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops ops = {
+	.test_1 = (void *)test_1_turn_off,
+};
+
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c b/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c
new file mode 100644
index 000000000000..dbe646013811
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+#if defined(__TARGET_ARCH_x86) || defined(__TARGET_ARCH_arm64)
+bool skip __attribute((__section__(".data"))) = false;
+#else
+bool skip = true;
+#endif
+
+void bpf_testmod_ops3_call_test_2(void) __ksym;
+
+int val_i, val_j;
+
+__noinline static int subprog2(int *a, int *b)
+{
+	return val_i + a[10] + b[20];
+}
+
+__noinline static int subprog1(int *a)
+{
+	/* stack size 200 bytes */
+	int b[50] = {};
+
+	b[20] = 2;
+	return subprog2(a, b);
+}
+
+
+SEC("struct_ops")
+int BPF_PROG(test_1)
+{
+	/* stack size 400 bytes */
+	int a[100] = {};
+
+	a[10] = 1;
+	val_i = subprog1(a);
+	bpf_testmod_ops3_call_test_2();
+	return 0;
+}
+
+SEC("struct_ops")
+int BPF_PROG(test_2)
+{
+	/* stack size 200 bytes */
+	int a[50] = {};
+
+	a[10] = 3;
+	val_j = subprog1(a);
+	return 0;
+}
+
+SEC(".struct_ops")
+struct bpf_testmod_ops3 testmod_1 = {
+	.test_1 = (void *)test_1,
+	.test_2 = (void *)test_2,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c
new file mode 100644
index 000000000000..3d89ad7cbe2a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+#if defined(__TARGET_ARCH_x86) || defined(__TARGET_ARCH_arm64)
+bool skip __attribute((__section__(".data"))) = false;
+#else
+bool skip = true;
+#endif
+
+void bpf_testmod_ops3_call_test_2(void) __ksym;
+
+int val_i, val_j;
+
+__noinline static int subprog2(int *a, int *b)
+{
+	return val_i + a[10] + b[20];
+}
+
+__noinline static int subprog1(int *a)
+{
+	/* stack size 200 bytes */
+	int b[50] = {};
+
+	b[20] = 2;
+	return subprog2(a, b);
+}
+
+
+SEC("struct_ops")
+int BPF_PROG(test_1)
+{
+	/* stack size 100 bytes */
+	int a[25] = {};
+
+	a[10] = 1;
+	val_i = subprog1(a);
+	bpf_testmod_ops3_call_test_2();
+	return 0;
+}
+
+SEC("struct_ops")
+int BPF_PROG(test_2)
+{
+	/* stack size 400 bytes */
+	int a[100] = {};
+
+	a[10] = 3;
+	val_j = subprog1(a);
+	return 0;
+}
+
+SEC(".struct_ops")
+struct bpf_testmod_ops3 testmod_1 = {
+	.test_1 = (void *)test_1,
+	.test_2 = (void *)test_2,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c
new file mode 100644
index 000000000000..b1f6d7e5a8e5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+#if defined(__TARGET_ARCH_x86) || defined(__TARGET_ARCH_arm64)
+bool skip __attribute((__section__(".data"))) = false;
+#else
+bool skip = true;
+#endif
+
+void bpf_testmod_ops3_call_test_1(void) __ksym;
+
+int val_i, val_j;
+
+__noinline static int subprog2(int *a, int *b)
+{
+	return val_i + a[1] + b[20];
+}
+
+__noinline static int subprog1(int *a)
+{
+	/* stack size 400 bytes */
+	int b[100] = {};
+
+	b[20] = 2;
+	return subprog2(a, b);
+}
+
+
+SEC("struct_ops")
+int BPF_PROG(test_1)
+{
+	/* stack size 20 bytes */
+	int a[5] = {};
+
+	a[1] = 1;
+	val_j += subprog1(a);
+	bpf_testmod_ops3_call_test_1();
+	return 0;
+}
+
+SEC(".struct_ops")
+struct bpf_testmod_ops3 testmod_1 = {
+	.test_1 = (void *)test_1,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_refcounted.c b/tools/testing/selftests/bpf/progs/struct_ops_refcounted.c
new file mode 100644
index 000000000000..9c0a65466356
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_refcounted.c
@@ -0,0 +1,31 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+__attribute__((nomerge)) extern void bpf_task_release(struct task_struct *p) __ksym;
+
+/* This is a test BPF program that uses struct_ops to access a referenced
+ * kptr argument. This is a test for the verifier to ensure that it
+ * 1) recognizes the task as a referenced object (i.e., ref_obj_id > 0), and
+ * 2) the same reference can be acquired from multiple paths as long as it
+ *    has not been released.
+ */
+SEC("struct_ops/test_refcounted")
+int BPF_PROG(refcounted, int dummy, struct task_struct *task)
+{
+	if (dummy == 1)
+		bpf_task_release(task);
+	else
+		bpf_task_release(task);
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_refcounted = {
+	.test_refcounted = (void *)refcounted,
+};
+
+
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__global_subprog.c b/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__global_subprog.c
new file mode 100644
index 000000000000..ae074aa62852
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__global_subprog.c
@@ -0,0 +1,39 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+extern void bpf_task_release(struct task_struct *p) __ksym;
+
+__noinline int subprog_release(__u64 *ctx __arg_ctx)
+{
+	struct task_struct *task = (struct task_struct *)ctx[1];
+	int dummy = (int)ctx[0];
+
+	bpf_task_release(task);
+
+	return dummy + 1;
+}
+
+/* Test that the verifier rejects a program that contains a global
+ * subprogram with referenced kptr arguments
+ */
+SEC("struct_ops/test_refcounted")
+__failure __log_level(2)
+__msg("Validating subprog_release() func#1...")
+__msg("invalid bpf_context access off=8. Reference may already be released")
+int refcounted_fail__global_subprog(unsigned long long *ctx)
+{
+	struct task_struct *task = (struct task_struct *)ctx[1];
+
+	bpf_task_release(task);
+
+	return subprog_release(ctx);
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_ref_acquire = {
+	.test_refcounted = (void *)refcounted_fail__global_subprog,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__ref_leak.c b/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__ref_leak.c
new file mode 100644
index 000000000000..e945b1a04294
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__ref_leak.c
@@ -0,0 +1,22 @@
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+/* Test that the verifier rejects a program that acquires a referenced
+ * kptr through context without releasing the reference
+ */
+SEC("struct_ops/test_refcounted")
+__failure __msg("Unreleased reference id=1 alloc_insn=0")
+int BPF_PROG(refcounted_fail__ref_leak, int dummy,
+	     struct task_struct *task)
+{
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_ref_acquire = {
+	.test_refcounted = (void *)refcounted_fail__ref_leak,
+};
diff --git a/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__tail_call.c b/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__tail_call.c
new file mode 100644
index 000000000000..3b125025a1f2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/struct_ops_refcounted_fail__tail_call.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} prog_array SEC(".maps");
+
+/* Test that the verifier rejects a program with referenced kptr arguments
+ * that tail call
+ */
+SEC("struct_ops/test_refcounted")
+__failure __msg("program with __ref argument cannot tail call")
+int refcounted_fail__tail_call(unsigned long long *ctx)
+{
+	struct task_struct *task = (struct task_struct *)ctx[1];
+
+	bpf_task_release(task);
+	bpf_tail_call(ctx, &prog_array, 0);
+
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod_ref_acquire = {
+	.test_refcounted = (void *)refcounted_fail__tail_call,
+};
+
diff --git a/tools/testing/selftests/bpf/progs/summarization.c b/tools/testing/selftests/bpf/progs/summarization.c
new file mode 100644
index 000000000000..f89effe82c9e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/summarization.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+__noinline
+long changes_pkt_data(struct __sk_buff *sk)
+{
+	return bpf_skb_pull_data(sk, 0);
+}
+
+__noinline __weak
+long does_not_change_pkt_data(struct __sk_buff *sk)
+{
+	return 0;
+}
+
+SEC("?tc")
+int main_changes_with_subprogs(struct __sk_buff *sk)
+{
+	changes_pkt_data(sk);
+	does_not_change_pkt_data(sk);
+	return 0;
+}
+
+SEC("?tc")
+int main_changes(struct __sk_buff *sk)
+{
+	bpf_skb_pull_data(sk, 0);
+	return 0;
+}
+
+SEC("?tc")
+int main_does_not_change(struct __sk_buff *sk)
+{
+	return 0;
+}
+
+__noinline
+long might_sleep(struct pt_regs *ctx __arg_ctx)
+{
+	int i;
+
+	bpf_copy_from_user(&i, sizeof(i), NULL);
+	return i;
+}
+
+__noinline __weak
+long does_not_sleep(struct pt_regs *ctx __arg_ctx)
+{
+	return 0;
+}
+
+SEC("?uprobe.s")
+int main_might_sleep_with_subprogs(struct pt_regs *ctx)
+{
+	might_sleep(ctx);
+	does_not_sleep(ctx);
+	return 0;
+}
+
+SEC("?uprobe.s")
+int main_might_sleep(struct pt_regs *ctx)
+{
+	int i;
+
+	bpf_copy_from_user(&i, sizeof(i), NULL);
+	return i;
+}
+
+SEC("?uprobe.s")
+int main_does_not_sleep(struct pt_regs *ctx)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/summarization_freplace.c b/tools/testing/selftests/bpf/progs/summarization_freplace.c
new file mode 100644
index 000000000000..935f00e0e9ea
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/summarization_freplace.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+
+SEC("?freplace")
+long changes_pkt_data(struct __sk_buff *sk)
+{
+	return bpf_skb_pull_data(sk, 0);
+}
+
+SEC("?freplace")
+long does_not_change_pkt_data(struct __sk_buff *sk)
+{
+	return 0;
+}
+
+SEC("?freplace")
+long might_sleep(struct pt_regs *ctx)
+{
+	int i;
+
+	bpf_copy_from_user(&i, sizeof(i), NULL);
+	return i;
+}
+
+SEC("?freplace")
+long does_not_sleep(struct pt_regs *ctx)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/syscall.c b/tools/testing/selftests/bpf/progs/syscall.c
index e550f728962d..b698cc62a371 100644
--- a/tools/testing/selftests/bpf/progs/syscall.c
+++ b/tools/testing/selftests/bpf/progs/syscall.c
@@ -6,9 +6,16 @@
 #include <bpf/bpf_tracing.h>
 #include <../../../tools/include/linux/filter.h>
 #include <linux/btf.h>
+#include <string.h>
+#include <errno.h>
+#include "bpf_misc.h"
 
 char _license[] SEC("license") = "GPL";
 
+struct bpf_map {
+	int id;
+}  __attribute__((preserve_access_index));
+
 struct args {
 	__u64 log_buf;
 	__u32 log_size;
@@ -27,6 +34,37 @@ struct args {
 	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \
 	BTF_INT_ENC(encoding, bits_offset, bits)
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, union bpf_attr);
+	__uint(max_entries, 1);
+} bpf_attr_array SEC(".maps");
+
+struct inner_map_type {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(key_size, 4);
+	__uint(value_size, 4);
+	__uint(max_entries, 1);
+} inner_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 1);
+	__array(values, struct inner_map_type);
+} outer_array_map SEC(".maps") = {
+	.values = {
+		[0] = &inner_map,
+	},
+};
+
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+	return (__u64) (unsigned long) ptr;
+}
+
 static int btf_load(void)
 {
 	struct btf_blob {
@@ -38,9 +76,9 @@ static int btf_load(void)
 			.magic = BTF_MAGIC,
 			.version = BTF_VERSION,
 			.hdr_len = sizeof(struct btf_header),
-			.type_len = sizeof(__u32) * 8,
-			.str_off = sizeof(__u32) * 8,
-			.str_len = sizeof(__u32),
+			.type_len = sizeof(raw_btf.types),
+			.str_off = offsetof(struct btf_blob, str) - offsetof(struct btf_blob, types),
+			.str_len = sizeof(raw_btf.str),
 		},
 		.types = {
 			/* long */
@@ -58,7 +96,7 @@ static int btf_load(void)
 }
 
 SEC("syscall")
-int bpf_prog(struct args *ctx)
+int load_prog(struct args *ctx)
 {
 	static char license[] = "GPL";
 	static struct bpf_insn insns[] = {
@@ -82,7 +120,7 @@ int bpf_prog(struct args *ctx)
 	static __u64 value = 34;
 	static union bpf_attr prog_load_attr = {
 		.prog_type = BPF_PROG_TYPE_XDP,
-		.insn_cnt = sizeof(insns) / sizeof(insns[0]),
+		.insn_cnt = ARRAY_SIZE(insns),
 	};
 	int ret;
 
@@ -94,8 +132,8 @@ int bpf_prog(struct args *ctx)
 	map_create_attr.max_entries = ctx->max_entries;
 	map_create_attr.btf_fd = ret;
 
-	prog_load_attr.license = (long) license;
-	prog_load_attr.insns = (long) insns;
+	prog_load_attr.license = ptr_to_u64(license);
+	prog_load_attr.insns = ptr_to_u64(insns);
 	prog_load_attr.log_buf = ctx->log_buf;
 	prog_load_attr.log_size = ctx->log_size;
 	prog_load_attr.log_level = 1;
@@ -107,8 +145,8 @@ int bpf_prog(struct args *ctx)
 	insns[3].imm = ret;
 
 	map_update_attr.map_fd = ret;
-	map_update_attr.key = (long) &key;
-	map_update_attr.value = (long) &value;
+	map_update_attr.key = ptr_to_u64(&key);
+	map_update_attr.value = ptr_to_u64(&value);
 	ret = bpf_sys_bpf(BPF_MAP_UPDATE_ELEM, &map_update_attr, sizeof(map_update_attr));
 	if (ret < 0)
 		return ret;
@@ -119,3 +157,52 @@ int bpf_prog(struct args *ctx)
 	ctx->prog_fd = ret;
 	return 1;
 }
+
+SEC("syscall")
+int update_outer_map(void *ctx)
+{
+	int zero = 0, ret = 0, outer_fd = -1, inner_fd = -1, err;
+	const int attr_sz = sizeof(union bpf_attr);
+	union bpf_attr *attr;
+
+	attr = bpf_map_lookup_elem((struct bpf_map *)&bpf_attr_array, &zero);
+	if (!attr)
+		goto out;
+
+	memset(attr, 0, attr_sz);
+	attr->map_id = ((struct bpf_map *)&outer_array_map)->id;
+	outer_fd = bpf_sys_bpf(BPF_MAP_GET_FD_BY_ID, attr, attr_sz);
+	if (outer_fd < 0)
+		goto out;
+
+	memset(attr, 0, attr_sz);
+	attr->map_type = BPF_MAP_TYPE_ARRAY;
+	attr->key_size = 4;
+	attr->value_size = 4;
+	attr->max_entries = 1;
+	inner_fd = bpf_sys_bpf(BPF_MAP_CREATE, attr, attr_sz);
+	if (inner_fd < 0)
+		goto out;
+
+	memset(attr, 0, attr_sz);
+	attr->map_fd = outer_fd;
+	attr->key = ptr_to_u64(&zero);
+	attr->value = ptr_to_u64(&inner_fd);
+	err = bpf_sys_bpf(BPF_MAP_UPDATE_ELEM, attr, attr_sz);
+	if (err)
+		goto out;
+
+	memset(attr, 0, attr_sz);
+	attr->map_fd = outer_fd;
+	attr->key = ptr_to_u64(&zero);
+	err = bpf_sys_bpf(BPF_MAP_DELETE_ELEM, attr, attr_sz);
+	if (err)
+		goto out;
+	ret = 1;
+out:
+	if (inner_fd >= 0)
+		bpf_sys_close(inner_fd);
+	if (outer_fd >= 0)
+		bpf_sys_close(outer_fd);
+	return ret;
+}
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c
index 7fab39a3bb12..99c8d1d8a187 100644
--- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c
@@ -2,6 +2,7 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 #include "bpf_legacy.h"
+#include "bpf_misc.h"
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
@@ -20,6 +21,8 @@ int subprog_tail2(struct __sk_buff *skb)
 	else
 		bpf_tail_call_static(skb, &jmp_table, 1);
 
+	__sink(arr[sizeof(arr) - 1]);
+
 	return skb->len;
 }
 
@@ -30,6 +33,8 @@ int subprog_tail(struct __sk_buff *skb)
 
 	bpf_tail_call_static(skb, &jmp_table, 0);
 
+	__sink(arr[sizeof(arr) - 1]);
+
 	return skb->len * 2;
 }
 
@@ -38,6 +43,8 @@ int classifier_0(struct __sk_buff *skb)
 {
 	volatile char arr[128] = {};
 
+	__sink(arr[sizeof(arr) - 1]);
+
 	return subprog_tail2(skb);
 }
 
@@ -46,6 +53,8 @@ int classifier_1(struct __sk_buff *skb)
 {
 	volatile char arr[128] = {};
 
+	__sink(arr[sizeof(arr) - 1]);
+
 	return skb->len * 3;
 }
 
@@ -54,6 +63,8 @@ int entry(struct __sk_buff *skb)
 {
 	volatile char arr[128] = {};
 
+	__sink(arr[sizeof(arr) - 1]);
+
 	return subprog_tail(skb);
 }
 
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf6.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf6.c
index 41ce83da78e8..4a9f63bea66c 100644
--- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf6.c
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf6.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
 
 #define __unused __attribute__((unused))
 
@@ -36,6 +37,8 @@ int entry(struct __sk_buff *skb)
 	/* Have data on stack which size is not a multiple of 8 */
 	volatile char arr[1] = {};
 
+	__sink(arr[0]);
+
 	return subprog_tail(skb);
 }
 
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_fentry.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_fentry.c
new file mode 100644
index 000000000000..8436c6729167
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_fentry.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Leon Hwang */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+int count = 0;
+
+SEC("fentry/subprog_tail")
+int BPF_PROG(fentry, struct sk_buff *skb)
+{
+	count++;
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_fexit.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_fexit.c
new file mode 100644
index 000000000000..fe16412c6e6e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_fexit.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Leon Hwang */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+int count = 0;
+
+SEC("fexit/subprog_tail")
+int BPF_PROG(fexit, struct sk_buff *skb)
+{
+	count++;
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy1.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy1.c
new file mode 100644
index 000000000000..d556b19413d7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy1.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_legacy.h"
+#include "bpf_test_utils.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+int count = 0;
+
+static __noinline
+int subprog_tail(struct __sk_buff *skb)
+{
+	bpf_tail_call_static(skb, &jmp_table, 0);
+	return 0;
+}
+
+SEC("tc")
+int entry(struct __sk_buff *skb)
+{
+	int ret = 1;
+
+	clobber_regs_stack();
+
+	count++;
+	subprog_tail(skb);
+	subprog_tail(skb);
+
+	return ret;
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy2.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy2.c
new file mode 100644
index 000000000000..ae94c9c70ab7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy2.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "bpf_test_utils.h"
+
+int classifier_0(struct __sk_buff *skb);
+int classifier_1(struct __sk_buff *skb);
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 2);
+	__uint(key_size, sizeof(__u32));
+	__array(values, void (void));
+} jmp_table SEC(".maps") = {
+	.values = {
+		[0] = (void *) &classifier_0,
+		[1] = (void *) &classifier_1,
+	},
+};
+
+int count0 = 0;
+int count1 = 0;
+
+static __noinline
+int subprog_tail0(struct __sk_buff *skb)
+{
+	bpf_tail_call_static(skb, &jmp_table, 0);
+	return 0;
+}
+
+__auxiliary
+SEC("tc")
+int classifier_0(struct __sk_buff *skb)
+{
+	count0++;
+	subprog_tail0(skb);
+	return 0;
+}
+
+static __noinline
+int subprog_tail1(struct __sk_buff *skb)
+{
+	bpf_tail_call_static(skb, &jmp_table, 1);
+	return 0;
+}
+
+__auxiliary
+SEC("tc")
+int classifier_1(struct __sk_buff *skb)
+{
+	count1++;
+	subprog_tail1(skb);
+	return 0;
+}
+
+__success
+__retval(33)
+SEC("tc")
+int tailcall_bpf2bpf_hierarchy_2(struct __sk_buff *skb)
+{
+	int ret = 0;
+
+	clobber_regs_stack();
+
+	subprog_tail0(skb);
+	subprog_tail1(skb);
+
+	__sink(ret);
+	return (count1 << 16) | count0;
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy3.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy3.c
new file mode 100644
index 000000000000..56b6b0099840
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy3.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "bpf_test_utils.h"
+
+int classifier_0(struct __sk_buff *skb);
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__array(values, void (void));
+} jmp_table0 SEC(".maps") = {
+	.values = {
+		[0] = (void *) &classifier_0,
+	},
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__array(values, void (void));
+} jmp_table1 SEC(".maps") = {
+	.values = {
+		[0] = (void *) &classifier_0,
+	},
+};
+
+int count = 0;
+
+static __noinline
+int subprog_tail(struct __sk_buff *skb, void *jmp_table)
+{
+	bpf_tail_call_static(skb, jmp_table, 0);
+	return 0;
+}
+
+__auxiliary
+SEC("tc")
+int classifier_0(struct __sk_buff *skb)
+{
+	count++;
+	subprog_tail(skb, &jmp_table0);
+	subprog_tail(skb, &jmp_table1);
+	return count;
+}
+
+__success
+__retval(33)
+SEC("tc")
+int tailcall_bpf2bpf_hierarchy_3(struct __sk_buff *skb)
+{
+	int ret = 0;
+
+	clobber_regs_stack();
+
+	bpf_tail_call_static(skb, &jmp_table0, 0);
+
+	__sink(ret);
+	return ret;
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy_fentry.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy_fentry.c
new file mode 100644
index 000000000000..5261395713cd
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf_hierarchy_fentry.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Leon Hwang */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_test_utils.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+int count = 0;
+
+static __noinline
+int subprog_tail(void *ctx)
+{
+	bpf_tail_call_static(ctx, &jmp_table, 0);
+	return 0;
+}
+
+SEC("fentry/dummy")
+int BPF_PROG(fentry, struct sk_buff *skb)
+{
+	clobber_regs_stack();
+
+	count++;
+	subprog_tail(ctx);
+	subprog_tail(ctx);
+
+	return 0;
+}
+
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/tailcall_fail.c b/tools/testing/selftests/bpf/progs/tailcall_fail.c
new file mode 100644
index 000000000000..bc77921d2bb0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_fail.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+extern void bpf_rcu_read_lock(void) __ksym;
+extern void bpf_rcu_read_unlock(void) __ksym;
+
+#define private(name) SEC(".bss." #name) __hidden __attribute__((aligned(8)))
+
+private(A) struct bpf_spin_lock lock;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 3);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+SEC("?tc")
+__failure __msg("function calls are not allowed while holding a lock")
+int reject_tail_call_spin_lock(struct __sk_buff *ctx)
+{
+	bpf_spin_lock(&lock);
+	bpf_tail_call_static(ctx, &jmp_table, 0);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("tail_call cannot be used inside bpf_rcu_read_lock-ed region")
+int reject_tail_call_rcu_lock(struct __sk_buff *ctx)
+{
+	bpf_rcu_read_lock();
+	bpf_tail_call_static(ctx, &jmp_table, 0);
+	bpf_rcu_read_unlock();
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("tail_call cannot be used inside bpf_preempt_disable-ed region")
+int reject_tail_call_preempt_lock(struct __sk_buff *ctx)
+{
+	bpf_guard_preempt();
+	bpf_tail_call_static(ctx, &jmp_table, 0);
+	return 0;
+}
+
+SEC("?tc")
+__failure __msg("tail_call would lead to reference leak")
+int reject_tail_call_ref(struct __sk_buff *ctx)
+{
+	struct foo { int i; } *p;
+
+	p = bpf_obj_new(typeof(*p));
+	bpf_tail_call_static(ctx, &jmp_table, 0);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/tailcall_freplace.c b/tools/testing/selftests/bpf/progs/tailcall_freplace.c
new file mode 100644
index 000000000000..6713b809df44
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_freplace.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+int count = 0;
+
+SEC("freplace")
+int entry_freplace(struct __sk_buff *skb)
+{
+	count++;
+	bpf_tail_call_static(skb, &jmp_table, 0);
+	return count;
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/tailcall_poke.c b/tools/testing/selftests/bpf/progs/tailcall_poke.c
new file mode 100644
index 000000000000..c78b94b75e83
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall_poke.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+SEC("?fentry/bpf_fentry_test1")
+int BPF_PROG(test, int a)
+{
+	bpf_tail_call_static(ctx, &jmp_table, 0);
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(call1, int a)
+{
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(call2, int a)
+{
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_common.h b/tools/testing/selftests/bpf/progs/task_kfunc_common.h
index c0ffd171743e..e9c4fea7a4bb 100644
--- a/tools/testing/selftests/bpf/progs/task_kfunc_common.h
+++ b/tools/testing/selftests/bpf/progs/task_kfunc_common.h
@@ -10,10 +10,10 @@
 #include <bpf/bpf_tracing.h>
 
 struct __tasks_kfunc_map_value {
-	struct task_struct __kptr_ref * task;
+	struct task_struct __kptr * task;
 };
 
-struct hash_map {
+struct {
 	__uint(type, BPF_MAP_TYPE_HASH);
 	__type(key, int);
 	__type(value, struct __tasks_kfunc_map_value);
@@ -21,9 +21,11 @@ struct hash_map {
 } __tasks_kfunc_map SEC(".maps");
 
 struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym;
-struct task_struct *bpf_task_kptr_get(struct task_struct **pp) __ksym;
 void bpf_task_release(struct task_struct *p) __ksym;
 struct task_struct *bpf_task_from_pid(s32 pid) __ksym;
+struct task_struct *bpf_task_from_vpid(s32 vpid) __ksym;
+void bpf_rcu_read_lock(void) __ksym;
+void bpf_rcu_read_unlock(void) __ksym;
 
 static inline struct __tasks_kfunc_map_value *tasks_kfunc_map_value_lookup(struct task_struct *p)
 {
@@ -60,6 +62,9 @@ static inline int tasks_kfunc_map_insert(struct task_struct *p)
 	}
 
 	acquired = bpf_task_acquire(p);
+	if (!acquired)
+		return -ENOENT;
+
 	old = bpf_kptr_xchg(&v->task, acquired);
 	if (old) {
 		bpf_task_release(old);
diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_failure.c b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c
index 1b47b94dbca0..4c07ea193f72 100644
--- a/tools/testing/selftests/bpf/progs/task_kfunc_failure.c
+++ b/tools/testing/selftests/bpf/progs/task_kfunc_failure.c
@@ -5,6 +5,7 @@
 #include <bpf/bpf_tracing.h>
 #include <bpf/bpf_helpers.h>
 
+#include "bpf_misc.h"
 #include "task_kfunc_common.h"
 
 char _license[] SEC("license") = "GPL";
@@ -27,6 +28,7 @@ static struct __tasks_kfunc_map_value *insert_lookup_task(struct task_struct *ta
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
 int BPF_PROG(task_kfunc_acquire_untrusted, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *acquired;
@@ -38,49 +40,67 @@ int BPF_PROG(task_kfunc_acquire_untrusted, struct task_struct *task, u64 clone_f
 
 	/* Can't invoke bpf_task_acquire() on an untrusted pointer. */
 	acquired = bpf_task_acquire(v->task);
+	if (!acquired)
+		return 0;
+
 	bpf_task_release(acquired);
 
 	return 0;
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("arg#0 pointer type STRUCT task_struct must point")
 int BPF_PROG(task_kfunc_acquire_fp, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *acquired, *stack_task = (struct task_struct *)&clone_flags;
 
 	/* Can't invoke bpf_task_acquire() on a random frame pointer. */
 	acquired = bpf_task_acquire((struct task_struct *)&stack_task);
+	if (!acquired)
+		return 0;
+
 	bpf_task_release(acquired);
 
 	return 0;
 }
 
 SEC("kretprobe/free_task")
+__failure __msg("calling kernel function bpf_task_acquire is not allowed")
 int BPF_PROG(task_kfunc_acquire_unsafe_kretprobe, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *acquired;
 
+	/* Can't call bpf_task_acquire() or bpf_task_release() in an untrusted prog. */
 	acquired = bpf_task_acquire(task);
-	/* Can't release a bpf_task_acquire()'d task without a NULL check. */
+	if (!acquired)
+		return 0;
 	bpf_task_release(acquired);
 
 	return 0;
 }
 
-SEC("tp_btf/task_newtask")
-int BPF_PROG(task_kfunc_acquire_trusted_walked, struct task_struct *task, u64 clone_flags)
+SEC("kretprobe/free_task")
+__failure __msg("calling kernel function bpf_task_acquire is not allowed")
+int BPF_PROG(task_kfunc_acquire_unsafe_kretprobe_rcu, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *acquired;
 
-	/* Can't invoke bpf_task_acquire() on a trusted pointer obtained from walking a struct. */
-	acquired = bpf_task_acquire(task->group_leader);
-	bpf_task_release(acquired);
+	bpf_rcu_read_lock();
+	if (!task) {
+		bpf_rcu_read_unlock();
+		return 0;
+	}
+	/* Can't call bpf_task_acquire() or bpf_task_release() in an untrusted prog. */
+	acquired = bpf_task_acquire(task);
+	if (acquired)
+		bpf_task_release(acquired);
+	bpf_rcu_read_unlock();
 
 	return 0;
 }
 
-
 SEC("tp_btf/task_newtask")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
 int BPF_PROG(task_kfunc_acquire_null, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *acquired;
@@ -95,6 +115,7 @@ int BPF_PROG(task_kfunc_acquire_null, struct task_struct *task, u64 clone_flags)
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("Unreleased reference")
 int BPF_PROG(task_kfunc_acquire_unreleased, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *acquired;
@@ -102,59 +123,13 @@ int BPF_PROG(task_kfunc_acquire_unreleased, struct task_struct *task, u64 clone_
 	acquired = bpf_task_acquire(task);
 
 	/* Acquired task is never released. */
+	__sink(acquired);
 
 	return 0;
 }
 
 SEC("tp_btf/task_newtask")
-int BPF_PROG(task_kfunc_get_non_kptr_param, struct task_struct *task, u64 clone_flags)
-{
-	struct task_struct *kptr;
-
-	/* Cannot use bpf_task_kptr_get() on a non-kptr, even on a valid task. */
-	kptr = bpf_task_kptr_get(&task);
-	if (!kptr)
-		return 0;
-
-	bpf_task_release(kptr);
-
-	return 0;
-}
-
-SEC("tp_btf/task_newtask")
-int BPF_PROG(task_kfunc_get_non_kptr_acquired, struct task_struct *task, u64 clone_flags)
-{
-	struct task_struct *kptr, *acquired;
-
-	acquired = bpf_task_acquire(task);
-
-	/* Cannot use bpf_task_kptr_get() on a non-kptr, even if it was acquired. */
-	kptr = bpf_task_kptr_get(&acquired);
-	bpf_task_release(acquired);
-	if (!kptr)
-		return 0;
-
-	bpf_task_release(kptr);
-
-	return 0;
-}
-
-SEC("tp_btf/task_newtask")
-int BPF_PROG(task_kfunc_get_null, struct task_struct *task, u64 clone_flags)
-{
-	struct task_struct *kptr;
-
-	/* Cannot use bpf_task_kptr_get() on a NULL pointer. */
-	kptr = bpf_task_kptr_get(NULL);
-	if (!kptr)
-		return 0;
-
-	bpf_task_release(kptr);
-
-	return 0;
-}
-
-SEC("tp_btf/task_newtask")
+__failure __msg("Unreleased reference")
 int BPF_PROG(task_kfunc_xchg_unreleased, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *kptr;
@@ -174,25 +149,20 @@ int BPF_PROG(task_kfunc_xchg_unreleased, struct task_struct *task, u64 clone_fla
 }
 
 SEC("tp_btf/task_newtask")
-int BPF_PROG(task_kfunc_get_unreleased, struct task_struct *task, u64 clone_flags)
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
+int BPF_PROG(task_kfunc_acquire_release_no_null_check, struct task_struct *task, u64 clone_flags)
 {
-	struct task_struct *kptr;
-	struct __tasks_kfunc_map_value *v;
-
-	v = insert_lookup_task(task);
-	if (!v)
-		return 0;
-
-	kptr = bpf_task_kptr_get(&v->task);
-	if (!kptr)
-		return 0;
+	struct task_struct *acquired;
 
-	/* Kptr acquired above is never released. */
+	acquired = bpf_task_acquire(task);
+	/* Can't invoke bpf_task_release() on an acquired task without a NULL check. */
+	bpf_task_release(acquired);
 
 	return 0;
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
 int BPF_PROG(task_kfunc_release_untrusted, struct task_struct *task, u64 clone_flags)
 {
 	struct __tasks_kfunc_map_value *v;
@@ -208,6 +178,7 @@ int BPF_PROG(task_kfunc_release_untrusted, struct task_struct *task, u64 clone_f
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("arg#0 pointer type STRUCT task_struct must point")
 int BPF_PROG(task_kfunc_release_fp, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *acquired = (struct task_struct *)&clone_flags;
@@ -219,6 +190,7 @@ int BPF_PROG(task_kfunc_release_fp, struct task_struct *task, u64 clone_flags)
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
 int BPF_PROG(task_kfunc_release_null, struct task_struct *task, u64 clone_flags)
 {
 	struct __tasks_kfunc_map_value local, *v;
@@ -240,17 +212,19 @@ int BPF_PROG(task_kfunc_release_null, struct task_struct *task, u64 clone_flags)
 		return -ENOENT;
 
 	acquired = bpf_task_acquire(task);
+	if (!acquired)
+		return -EEXIST;
 
 	old = bpf_kptr_xchg(&v->task, acquired);
 
 	/* old cannot be passed to bpf_task_release() without a NULL check. */
 	bpf_task_release(old);
-	bpf_task_release(old);
 
 	return 0;
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("release kernel function bpf_task_release expects")
 int BPF_PROG(task_kfunc_release_unacquired, struct task_struct *task, u64 clone_flags)
 {
 	/* Cannot release trusted task pointer which was not acquired. */
@@ -260,6 +234,7 @@ int BPF_PROG(task_kfunc_release_unacquired, struct task_struct *task, u64 clone_
 }
 
 SEC("tp_btf/task_newtask")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
 int BPF_PROG(task_kfunc_from_pid_no_null_check, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *acquired;
@@ -272,13 +247,94 @@ int BPF_PROG(task_kfunc_from_pid_no_null_check, struct task_struct *task, u64 cl
 	return 0;
 }
 
+SEC("tp_btf/task_newtask")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
+int BPF_PROG(task_kfunc_from_vpid_no_null_check, struct task_struct *task, u64 clone_flags)
+{
+	struct task_struct *acquired;
+
+	acquired = bpf_task_from_vpid(task->pid);
+
+	/* Releasing bpf_task_from_vpid() lookup without a NULL check. */
+	bpf_task_release(acquired);
+
+	return 0;
+}
+
 SEC("lsm/task_free")
+__failure __msg("R1 must be a rcu pointer")
 int BPF_PROG(task_kfunc_from_lsm_task_free, struct task_struct *task)
 {
 	struct task_struct *acquired;
 
 	/* the argument of lsm task_free hook is untrusted. */
 	acquired = bpf_task_acquire(task);
+	if (!acquired)
+		return 0;
+
 	bpf_task_release(acquired);
 	return 0;
 }
+
+SEC("tp_btf/task_newtask")
+__failure __msg("access beyond the end of member comm")
+int BPF_PROG(task_access_comm1, struct task_struct *task, u64 clone_flags)
+{
+	bpf_strncmp(task->comm, 17, "foo");
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("access beyond the end of member comm")
+int BPF_PROG(task_access_comm2, struct task_struct *task, u64 clone_flags)
+{
+	bpf_strncmp(task->comm + 1, 16, "foo");
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("write into memory")
+int BPF_PROG(task_access_comm3, struct task_struct *task, u64 clone_flags)
+{
+	bpf_probe_read_kernel(task->comm, 16, task->comm);
+	return 0;
+}
+
+SEC("fentry/__set_task_comm")
+__failure __msg("R1 type=ptr_ expected")
+int BPF_PROG(task_access_comm4, struct task_struct *task, const char *buf, bool exec)
+{
+	/*
+	 * task->comm is a legacy ptr_to_btf_id. The verifier cannot guarantee
+	 * its safety. Hence it cannot be accessed with normal load insns.
+	 */
+	bpf_strncmp(task->comm, 16, "foo");
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+__failure __msg("R1 must be referenced or trusted")
+int BPF_PROG(task_kfunc_release_in_map, struct task_struct *task, u64 clone_flags)
+{
+	struct task_struct *local;
+	struct __tasks_kfunc_map_value *v;
+
+	if (tasks_kfunc_map_insert(task))
+		return 0;
+
+	v = tasks_kfunc_map_value_lookup(task);
+	if (!v)
+		return 0;
+
+	bpf_rcu_read_lock();
+	local = v->task;
+	if (!local) {
+		bpf_rcu_read_unlock();
+		return 0;
+	}
+	/* Can't release a kptr that's still stored in a map. */
+	bpf_task_release(local);
+	bpf_rcu_read_unlock();
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/task_kfunc_success.c b/tools/testing/selftests/bpf/progs/task_kfunc_success.c
index 9f359cfd29e7..5fb4fc19d26a 100644
--- a/tools/testing/selftests/bpf/progs/task_kfunc_success.c
+++ b/tools/testing/selftests/bpf/progs/task_kfunc_success.c
@@ -5,6 +5,7 @@
 #include <bpf/bpf_tracing.h>
 #include <bpf/bpf_helpers.h>
 
+#include "../bpf_experimental.h"
 #include "task_kfunc_common.h"
 
 char _license[] SEC("license") = "GPL";
@@ -17,6 +18,17 @@ int err, pid;
  *         TP_PROTO(struct task_struct *p, u64 clone_flags)
  */
 
+struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym __weak;
+
+struct task_struct *bpf_task_acquire___one(struct task_struct *task) __ksym __weak;
+/* The two-param bpf_task_acquire doesn't exist */
+struct task_struct *bpf_task_acquire___two(struct task_struct *p, void *ctx) __ksym __weak;
+/* Incorrect type for first param */
+struct task_struct *bpf_task_acquire___three(void *ctx) __ksym __weak;
+
+void invalid_kfunc(void) __ksym __weak;
+void bpf_testmod_test_mod_kfunc(int i) __ksym __weak;
+
 static bool is_test_kfunc_task(void)
 {
 	int cur_pid = bpf_get_current_pid_tgid() >> 32;
@@ -26,10 +38,71 @@ static bool is_test_kfunc_task(void)
 
 static int test_acquire_release(struct task_struct *task)
 {
-	struct task_struct *acquired;
+	struct task_struct *acquired = NULL;
+
+	if (!bpf_ksym_exists(bpf_task_acquire)) {
+		err = 3;
+		return 0;
+	}
+	if (!bpf_ksym_exists(bpf_testmod_test_mod_kfunc)) {
+		err = 4;
+		return 0;
+	}
+	if (bpf_ksym_exists(invalid_kfunc)) {
+		/* the verifier's dead code elimination should remove this */
+		err = 5;
+		asm volatile ("goto -1"); /* for (;;); */
+	}
 
 	acquired = bpf_task_acquire(task);
-	bpf_task_release(acquired);
+	if (acquired)
+		bpf_task_release(acquired);
+	else
+		err = 6;
+
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_task_kfunc_flavor_relo, struct task_struct *task, u64 clone_flags)
+{
+	struct task_struct *acquired = NULL;
+	int fake_ctx = 42;
+
+	if (bpf_ksym_exists(bpf_task_acquire___one)) {
+		acquired = bpf_task_acquire___one(task);
+	} else if (bpf_ksym_exists(bpf_task_acquire___two)) {
+		/* Here, bpf_object__resolve_ksym_func_btf_id's find_ksym_btf_id
+		 * call will find vmlinux's bpf_task_acquire, but subsequent
+		 * bpf_core_types_are_compat will fail
+		 */
+		acquired = bpf_task_acquire___two(task, &fake_ctx);
+		err = 3;
+		return 0;
+	} else if (bpf_ksym_exists(bpf_task_acquire___three)) {
+		/* bpf_core_types_are_compat will fail similarly to above case */
+		acquired = bpf_task_acquire___three(&fake_ctx);
+		err = 4;
+		return 0;
+	}
+
+	if (acquired)
+		bpf_task_release(acquired);
+	else
+		err = 5;
+	return 0;
+}
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(test_task_kfunc_flavor_relo_not_found, struct task_struct *task, u64 clone_flags)
+{
+	/* Neither symbol should successfully resolve.
+	 * Success or failure of one ___flavor should not affect others
+	 */
+	if (bpf_ksym_exists(bpf_task_acquire___two))
+		err = 1;
+	else if (bpf_ksym_exists(bpf_task_acquire___three))
+		err = 2;
 
 	return 0;
 }
@@ -70,8 +143,9 @@ int BPF_PROG(test_task_acquire_leave_in_map, struct task_struct *task, u64 clone
 SEC("tp_btf/task_newtask")
 int BPF_PROG(test_task_xchg_release, struct task_struct *task, u64 clone_flags)
 {
-	struct task_struct *kptr;
-	struct __tasks_kfunc_map_value *v;
+	struct task_struct *kptr, *acquired;
+	struct __tasks_kfunc_map_value *v, *local;
+	int refcnt, refcnt_after_drop;
 	long status;
 
 	if (!is_test_kfunc_task())
@@ -95,13 +169,63 @@ int BPF_PROG(test_task_xchg_release, struct task_struct *task, u64 clone_flags)
 		return 0;
 	}
 
+	local = bpf_obj_new(typeof(*local));
+	if (!local) {
+		err = 4;
+		bpf_task_release(kptr);
+		return 0;
+	}
+
+	kptr = bpf_kptr_xchg(&local->task, kptr);
+	if (kptr) {
+		err = 5;
+		bpf_obj_drop(local);
+		bpf_task_release(kptr);
+		return 0;
+	}
+
+	kptr = bpf_kptr_xchg(&local->task, NULL);
+	if (!kptr) {
+		err = 6;
+		bpf_obj_drop(local);
+		return 0;
+	}
+
+	/* Stash a copy into local kptr and check if it is released recursively */
+	acquired = bpf_task_acquire(kptr);
+	if (!acquired) {
+		err = 7;
+		bpf_obj_drop(local);
+		bpf_task_release(kptr);
+		return 0;
+	}
+	bpf_probe_read_kernel(&refcnt, sizeof(refcnt), &acquired->rcu_users);
+
+	acquired = bpf_kptr_xchg(&local->task, acquired);
+	if (acquired) {
+		err = 8;
+		bpf_obj_drop(local);
+		bpf_task_release(kptr);
+		bpf_task_release(acquired);
+		return 0;
+	}
+
+	bpf_obj_drop(local);
+
+	bpf_probe_read_kernel(&refcnt_after_drop, sizeof(refcnt_after_drop), &kptr->rcu_users);
+	if (refcnt != refcnt_after_drop + 1) {
+		err = 9;
+		bpf_task_release(kptr);
+		return 0;
+	}
+
 	bpf_task_release(kptr);
 
 	return 0;
 }
 
 SEC("tp_btf/task_newtask")
-int BPF_PROG(test_task_get_release, struct task_struct *task, u64 clone_flags)
+int BPF_PROG(test_task_map_acquire_release, struct task_struct *task, u64 clone_flags)
 {
 	struct task_struct *kptr;
 	struct __tasks_kfunc_map_value *v;
@@ -122,18 +246,18 @@ int BPF_PROG(test_task_get_release, struct task_struct *task, u64 clone_flags)
 		return 0;
 	}
 
-	kptr = bpf_task_kptr_get(&v->task);
-	if (kptr) {
-		/* Until we resolve the issues with using task->rcu_users, we
-		 * expect bpf_task_kptr_get() to return a NULL task. See the
-		 * comment at the definition of bpf_task_acquire_not_zero() for
-		 * more details.
-		 */
-		bpf_task_release(kptr);
+	bpf_rcu_read_lock();
+	kptr = v->task;
+	if (!kptr) {
 		err = 3;
-		return 0;
+	} else {
+		kptr = bpf_task_acquire(kptr);
+		if (!kptr)
+			err = 4;
+		else
+			bpf_task_release(kptr);
 	}
-
+	bpf_rcu_read_unlock();
 
 	return 0;
 }
@@ -148,7 +272,10 @@ int BPF_PROG(test_task_current_acquire_release, struct task_struct *task, u64 cl
 
 	current = bpf_get_current_task_btf();
 	acquired = bpf_task_acquire(current);
-	bpf_task_release(acquired);
+	if (acquired)
+		bpf_task_release(acquired);
+	else
+		err = 1;
 
 	return 0;
 }
@@ -171,8 +298,6 @@ static void lookup_compare_pid(const struct task_struct *p)
 SEC("tp_btf/task_newtask")
 int BPF_PROG(test_task_from_pid_arg, struct task_struct *task, u64 clone_flags)
 {
-	struct task_struct *acquired;
-
 	if (!is_test_kfunc_task())
 		return 0;
 
@@ -183,8 +308,6 @@ int BPF_PROG(test_task_from_pid_arg, struct task_struct *task, u64 clone_flags)
 SEC("tp_btf/task_newtask")
 int BPF_PROG(test_task_from_pid_current, struct task_struct *task, u64 clone_flags)
 {
-	struct task_struct *current, *acquired;
-
 	if (!is_test_kfunc_task())
 		return 0;
 
@@ -208,11 +331,13 @@ static int is_pid_lookup_valid(s32 pid)
 SEC("tp_btf/task_newtask")
 int BPF_PROG(test_task_from_pid_invalid, struct task_struct *task, u64 clone_flags)
 {
-	struct task_struct *acquired;
-
 	if (!is_test_kfunc_task())
 		return 0;
 
+	bpf_strncmp(task->comm, 12, "foo");
+	bpf_strncmp(task->comm, 16, "foo");
+	bpf_strncmp(&task->comm[8], 4, "foo");
+
 	if (is_pid_lookup_valid(-1)) {
 		err = 1;
 		return 0;
@@ -225,3 +350,70 @@ int BPF_PROG(test_task_from_pid_invalid, struct task_struct *task, u64 clone_fla
 
 	return 0;
 }
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(task_kfunc_acquire_trusted_walked, struct task_struct *task, u64 clone_flags)
+{
+	struct task_struct *acquired;
+
+	/* task->group_leader is listed as a trusted, non-NULL field of task struct. */
+	acquired = bpf_task_acquire(task->group_leader);
+	if (acquired)
+		bpf_task_release(acquired);
+	else
+		err = 1;
+
+
+	return 0;
+}
+
+SEC("syscall")
+int test_task_from_vpid_current(const void *ctx)
+{
+	struct task_struct *current, *v_task;
+
+	v_task = bpf_task_from_vpid(1);
+	if (!v_task) {
+		err = 1;
+		return 0;
+	}
+
+	current = bpf_get_current_task_btf();
+
+	/* The current process should be the init process (pid 1) in the new pid namespace. */
+	if (current != v_task)
+		err = 2;
+
+	bpf_task_release(v_task);
+	return 0;
+}
+
+SEC("syscall")
+int test_task_from_vpid_invalid(const void *ctx)
+{
+	struct task_struct *v_task;
+
+	v_task = bpf_task_from_vpid(-1);
+	if (v_task) {
+		err = 1;
+		goto err;
+	}
+
+	/* There should be only one process (current process) in the new pid namespace. */
+	v_task = bpf_task_from_vpid(2);
+	if (v_task) {
+		err = 2;
+		goto err;
+	}
+
+	v_task = bpf_task_from_vpid(9999);
+	if (v_task) {
+		err = 3;
+		goto err;
+	}
+
+	return 0;
+err:
+	bpf_task_release(v_task);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/task_local_data.bpf.h b/tools/testing/selftests/bpf/progs/task_local_data.bpf.h
new file mode 100644
index 000000000000..432fff2af844
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/task_local_data.bpf.h
@@ -0,0 +1,237 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TASK_LOCAL_DATA_BPF_H
+#define __TASK_LOCAL_DATA_BPF_H
+
+/*
+ * Task local data is a library that facilitates sharing per-task data
+ * between user space and bpf programs.
+ *
+ *
+ * USAGE
+ *
+ * A TLD, an entry of data in task local data, first needs to be created by the
+ * user space. This is done by calling user space API, TLD_DEFINE_KEY() or
+ * tld_create_key(), with the name of the TLD and the size.
+ *
+ * TLD_DEFINE_KEY(prio, "priority", sizeof(int));
+ *
+ * or
+ *
+ * void func_call(...) {
+ *     tld_key_t prio, in_cs;
+ *
+ *     prio = tld_create_key("priority", sizeof(int));
+ *     in_cs = tld_create_key("in_critical_section", sizeof(bool));
+ *     ...
+ *
+ * A key associated with the TLD, which has an opaque type tld_key_t, will be
+ * initialized or returned. It can be used to get a pointer to the TLD in the
+ * user space by calling tld_get_data().
+ *
+ * In a bpf program, tld_object_init() first needs to be called to initialized a
+ * tld_object on the stack. Then, TLDs can be accessed by calling tld_get_data().
+ * The API will try to fetch the key by the name and use it to locate the data.
+ * A pointer to the TLD will be returned. It also caches the key in a task local
+ * storage map, tld_key_map, whose value type, struct tld_keys, must be defined
+ * by the developer.
+ *
+ * struct tld_keys {
+ *     tld_key_t prio;
+ *     tld_key_t in_cs;
+ * };
+ *
+ * SEC("struct_ops")
+ * void prog(struct task_struct task, ...)
+ * {
+ *     struct tld_object tld_obj;
+ *     int err, *p;
+ *
+ *     err = tld_object_init(task, &tld_obj);
+ *     if (err)
+ *         return;
+ *
+ *     p = tld_get_data(&tld_obj, prio, "priority", sizeof(int));
+ *     if (p)
+ *         // do something depending on *p
+ */
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+
+#define TLD_ROUND_MASK(x, y) ((__typeof__(x))((y) - 1))
+#define TLD_ROUND_UP(x, y) ((((x) - 1) | TLD_ROUND_MASK(x, y)) + 1)
+
+#define TLD_MAX_DATA_CNT (__PAGE_SIZE / sizeof(struct tld_metadata) - 1)
+
+#ifndef TLD_NAME_LEN
+#define TLD_NAME_LEN 62
+#endif
+
+#ifndef TLD_KEY_MAP_CREATE_RETRY
+#define TLD_KEY_MAP_CREATE_RETRY 10
+#endif
+
+typedef struct {
+	__s16 off;
+} tld_key_t;
+
+struct tld_metadata {
+	char name[TLD_NAME_LEN];
+	__u16 size;
+};
+
+struct tld_meta_u {
+	__u8 cnt;
+	__u16 size;
+	struct tld_metadata metadata[TLD_MAX_DATA_CNT];
+};
+
+struct tld_data_u {
+	__u64 start; /* offset of tld_data_u->data in a page */
+	char data[__PAGE_SIZE - sizeof(__u64)];
+};
+
+struct tld_map_value {
+	struct tld_data_u __uptr *data;
+	struct tld_meta_u __uptr *meta;
+};
+
+typedef struct tld_uptr_dummy {
+	struct tld_data_u data[0];
+	struct tld_meta_u meta[0];
+} *tld_uptr_dummy_t;
+
+struct tld_object {
+	struct tld_map_value *data_map;
+	struct tld_keys *key_map;
+	/*
+	 * Force the compiler to generate the actual definition of tld_meta_u
+	 * and tld_data_u in BTF. Without it, tld_meta_u and u_tld_data will
+	 * be BTF_KIND_FWD.
+	 */
+	tld_uptr_dummy_t dummy[0];
+};
+
+/*
+ * Map value of tld_key_map for caching keys. Must be defined by the developer.
+ * Members should be tld_key_t and passed to the 3rd argument of tld_fetch_key().
+ */
+struct tld_keys;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct tld_map_value);
+} tld_data_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct tld_keys);
+} tld_key_map SEC(".maps");
+
+/**
+ * tld_object_init() - Initialize a tld_object.
+ *
+ * @task: The task_struct of the target task
+ * @tld_obj: A pointer to a tld_object to be initialized
+ *
+ * Return 0 on success; -ENODATA if the user space did not initialize task local data
+ * for the current task through tld_get_data(); -ENOMEM if the creation of tld_key_map
+ * fails
+ */
+__attribute__((unused))
+static int tld_object_init(struct task_struct *task, struct tld_object *tld_obj)
+{
+	int i;
+
+	tld_obj->data_map = bpf_task_storage_get(&tld_data_map, task, 0, 0);
+	if (!tld_obj->data_map)
+		return -ENODATA;
+
+	bpf_for(i, 0, TLD_KEY_MAP_CREATE_RETRY) {
+		tld_obj->key_map = bpf_task_storage_get(&tld_key_map, task, 0,
+							BPF_LOCAL_STORAGE_GET_F_CREATE);
+		if (likely(tld_obj->key_map))
+			break;
+	}
+	if (!tld_obj->key_map)
+		return -ENOMEM;
+
+	return 0;
+}
+
+/*
+ * Return the offset of TLD if @name is found. Otherwise, return the current TLD count
+ * using the nonpositive range so that the next tld_get_data() can skip fetching key if
+ * no new TLD is added or start comparing name from the first newly added TLD.
+ */
+__attribute__((unused))
+static int __tld_fetch_key(struct tld_object *tld_obj, const char *name, int i_start)
+{
+	struct tld_metadata *metadata;
+	int i, cnt, start, off = 0;
+
+	if (!tld_obj->data_map || !tld_obj->data_map->data || !tld_obj->data_map->meta)
+		return 0;
+
+	start = tld_obj->data_map->data->start;
+	cnt = tld_obj->data_map->meta->cnt;
+	metadata = tld_obj->data_map->meta->metadata;
+
+	bpf_for(i, 0, cnt) {
+		if (i >= TLD_MAX_DATA_CNT)
+			break;
+
+		if (i >= i_start && !bpf_strncmp(metadata[i].name, TLD_NAME_LEN, name))
+			return start + off;
+
+		off += TLD_ROUND_UP(metadata[i].size, 8);
+	}
+
+	return -cnt;
+}
+
+/**
+ * tld_get_data() - Retrieve a pointer to the TLD associated with the name.
+ *
+ * @tld_obj: A pointer to a valid tld_object initialized by tld_object_init()
+ * @key: The cached key of the TLD in tld_key_map
+ * @name: The name of the key associated with a TLD
+ * @size: The size of the TLD. Must be a known constant value
+ *
+ * Return a pointer to the TLD associated with @name; NULL if not found or @size is too
+ * big. @key is used to cache the key if the TLD is found to speed up subsequent calls.
+ * It should be defined as an member of tld_keys of tld_key_t type by the developer.
+ */
+#define tld_get_data(tld_obj, key, name, size)						\
+	({										\
+		void *data = NULL, *_data = (tld_obj)->data_map->data;			\
+		long off = (tld_obj)->key_map->key.off;					\
+		int cnt;								\
+											\
+		if (likely(_data)) {							\
+			if (likely(off > 0)) {						\
+				barrier_var(off);					\
+				if (likely(off < __PAGE_SIZE - size))			\
+					data = _data + off;				\
+			} else {							\
+				cnt = -(off);						\
+				if (likely((tld_obj)->data_map->meta) &&		\
+				    cnt < (tld_obj)->data_map->meta->cnt) {		\
+					off = __tld_fetch_key(tld_obj, name, cnt);	\
+					(tld_obj)->key_map->key.off = off;		\
+											\
+					if (likely(off < __PAGE_SIZE - size)) {		\
+						barrier_var(off);			\
+						if (off > 0)				\
+							data = _data + off;		\
+					}						\
+				}							\
+			}								\
+		}									\
+		data;									\
+	})
+
+#endif
diff --git a/tools/testing/selftests/bpf/progs/task_ls_recursion.c b/tools/testing/selftests/bpf/progs/task_ls_recursion.c
index 4542dc683b44..f1853c38aada 100644
--- a/tools/testing/selftests/bpf/progs/task_ls_recursion.c
+++ b/tools/testing/selftests/bpf/progs/task_ls_recursion.c
@@ -27,23 +27,6 @@ struct {
 	__type(value, long);
 } map_b SEC(".maps");
 
-SEC("fentry/bpf_local_storage_lookup")
-int BPF_PROG(on_lookup)
-{
-	struct task_struct *task = bpf_get_current_task_btf();
-
-	if (!test_pid || task->pid != test_pid)
-		return 0;
-
-	/* The bpf_task_storage_delete will call
-	 * bpf_local_storage_lookup.  The prog->active will
-	 * stop the recursion.
-	 */
-	bpf_task_storage_delete(&map_a, task);
-	bpf_task_storage_delete(&map_b, task);
-	return 0;
-}
-
 SEC("fentry/bpf_local_storage_update")
 int BPF_PROG(on_update)
 {
diff --git a/tools/testing/selftests/bpf/progs/task_ls_uptr.c b/tools/testing/selftests/bpf/progs/task_ls_uptr.c
new file mode 100644
index 000000000000..ddbe11b46eef
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/task_ls_uptr.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "uptr_test_common.h"
+
+struct task_struct *bpf_task_from_pid(s32 pid) __ksym;
+void bpf_task_release(struct task_struct *p) __ksym;
+void bpf_cgroup_release(struct cgroup *cgrp) __ksym;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct value_type);
+} datamap SEC(".maps");
+
+pid_t target_pid = 0;
+pid_t parent_pid = 0;
+
+SEC("tp_btf/sys_enter")
+int on_enter(__u64 *ctx)
+{
+	struct task_struct *task, *data_task;
+	struct value_type *ptr;
+	struct user_data *udata;
+	struct cgroup *cgrp;
+
+	task = bpf_get_current_task_btf();
+	if (task->pid != target_pid)
+		return 0;
+
+	data_task = bpf_task_from_pid(parent_pid);
+	if (!data_task)
+		return 0;
+
+	ptr = bpf_task_storage_get(&datamap, data_task, 0, 0);
+	bpf_task_release(data_task);
+	if (!ptr)
+		return 0;
+
+	cgrp = bpf_kptr_xchg(&ptr->cgrp, NULL);
+	if (cgrp) {
+		int lvl = cgrp->level;
+
+		bpf_cgroup_release(cgrp);
+		return lvl;
+	}
+
+	udata = ptr->udata;
+	if (!udata || udata->result)
+		return 0;
+	udata->result = MAGIC_VALUE + udata->a + udata->b;
+
+	udata = ptr->nested.udata;
+	if (udata && !udata->nested_result)
+		udata->nested_result = udata->result;
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c b/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c
index ea2dbb80f7b3..986829aaf73a 100644
--- a/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c
+++ b/tools/testing/selftests/bpf/progs/task_storage_nodeadlock.c
@@ -10,7 +10,7 @@ char _license[] SEC("license") = "GPL";
 #define EBUSY 16
 #endif
 
-extern bool CONFIG_PREEMPT __kconfig __weak;
+extern bool CONFIG_PREEMPTION __kconfig __weak;
 int nr_get_errs = 0;
 int nr_del_errs = 0;
 
@@ -29,7 +29,7 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family, int type,
 	int ret, zero = 0;
 	int *value;
 
-	if (!CONFIG_PREEMPT)
+	if (!CONFIG_PREEMPTION)
 		return 0;
 
 	task = bpf_get_current_task_btf();
diff --git a/tools/testing/selftests/bpf/progs/task_work.c b/tools/testing/selftests/bpf/progs/task_work.c
new file mode 100644
index 000000000000..663a80990f8f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/task_work.c
@@ -0,0 +1,107 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <string.h>
+#include <stdbool.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "errno.h"
+
+char _license[] SEC("license") = "GPL";
+
+const void *user_ptr = NULL;
+
+struct elem {
+	char data[128];
+	struct bpf_task_work tw;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} hmap SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} arrmap SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_LRU_HASH);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} lrumap SEC(".maps");
+
+static int process_work(struct bpf_map *map, void *key, void *value)
+{
+	struct elem *work = value;
+
+	bpf_copy_from_user_str(work->data, sizeof(work->data), (const void *)user_ptr, 0);
+	return 0;
+}
+
+int key = 0;
+
+SEC("perf_event")
+int oncpu_hash_map(struct pt_regs *args)
+{
+	struct elem empty_work = { .data = { 0 } };
+	struct elem *work;
+	struct task_struct *task;
+	int err;
+
+	task = bpf_get_current_task_btf();
+	err = bpf_map_update_elem(&hmap, &key, &empty_work, BPF_NOEXIST);
+	if (err)
+		return 0;
+	work = bpf_map_lookup_elem(&hmap, &key);
+	if (!work)
+		return 0;
+
+	bpf_task_work_schedule_resume_impl(task, &work->tw, &hmap, process_work, NULL);
+	return 0;
+}
+
+SEC("perf_event")
+int oncpu_array_map(struct pt_regs *args)
+{
+	struct elem *work;
+	struct task_struct *task;
+
+	task = bpf_get_current_task_btf();
+	work = bpf_map_lookup_elem(&arrmap, &key);
+	if (!work)
+		return 0;
+	bpf_task_work_schedule_signal_impl(task, &work->tw, &arrmap, process_work, NULL);
+	return 0;
+}
+
+SEC("perf_event")
+int oncpu_lru_map(struct pt_regs *args)
+{
+	struct elem empty_work = { .data = { 0 } };
+	struct elem *work;
+	struct task_struct *task;
+	int err;
+
+	task = bpf_get_current_task_btf();
+	work = bpf_map_lookup_elem(&lrumap, &key);
+	if (work)
+		return 0;
+	err = bpf_map_update_elem(&lrumap, &key, &empty_work, BPF_NOEXIST);
+	if (err)
+		return 0;
+	work = bpf_map_lookup_elem(&lrumap, &key);
+	if (!work || work->data[0])
+		return 0;
+	bpf_task_work_schedule_resume_impl(task, &work->tw, &lrumap, process_work, NULL);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/task_work_fail.c b/tools/testing/selftests/bpf/progs/task_work_fail.c
new file mode 100644
index 000000000000..1270953fd092
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/task_work_fail.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <string.h>
+#include <stdbool.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+const void *user_ptr = NULL;
+
+struct elem {
+	char data[128];
+	struct bpf_task_work tw;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} hmap SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} arrmap SEC(".maps");
+
+static int process_work(struct bpf_map *map, void *key, void *value)
+{
+	struct elem *work = value;
+
+	bpf_copy_from_user_str(work->data, sizeof(work->data), (const void *)user_ptr, 0);
+	return 0;
+}
+
+int key = 0;
+
+SEC("perf_event")
+__failure __msg("doesn't match map pointer in R3")
+int mismatch_map(struct pt_regs *args)
+{
+	struct elem *work;
+	struct task_struct *task;
+
+	task = bpf_get_current_task_btf();
+	work = bpf_map_lookup_elem(&arrmap, &key);
+	if (!work)
+		return 0;
+	bpf_task_work_schedule_resume_impl(task, &work->tw, &hmap, process_work, NULL);
+	return 0;
+}
+
+SEC("perf_event")
+__failure __msg("arg#1 doesn't point to a map value")
+int no_map_task_work(struct pt_regs *args)
+{
+	struct task_struct *task;
+	struct bpf_task_work tw;
+
+	task = bpf_get_current_task_btf();
+	bpf_task_work_schedule_resume_impl(task, &tw, &hmap, process_work, NULL);
+	return 0;
+}
+
+SEC("perf_event")
+__failure __msg("Possibly NULL pointer passed to trusted arg1")
+int task_work_null(struct pt_regs *args)
+{
+	struct task_struct *task;
+
+	task = bpf_get_current_task_btf();
+	bpf_task_work_schedule_resume_impl(task, NULL, &hmap, process_work, NULL);
+	return 0;
+}
+
+SEC("perf_event")
+__failure __msg("Possibly NULL pointer passed to trusted arg2")
+int map_null(struct pt_regs *args)
+{
+	struct elem *work;
+	struct task_struct *task;
+
+	task = bpf_get_current_task_btf();
+	work = bpf_map_lookup_elem(&arrmap, &key);
+	if (!work)
+		return 0;
+	bpf_task_work_schedule_resume_impl(task, &work->tw, NULL, process_work, NULL);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/task_work_stress.c b/tools/testing/selftests/bpf/progs/task_work_stress.c
new file mode 100644
index 000000000000..55e555f7f41b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/task_work_stress.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <string.h>
+#include <stdbool.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+
+#define ENTRIES 128
+
+char _license[] SEC("license") = "GPL";
+
+__u64 callback_scheduled = 0;
+__u64 callback_success = 0;
+__u64 schedule_error = 0;
+__u64 delete_success = 0;
+
+struct elem {
+	__u32 count;
+	struct bpf_task_work tw;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__uint(max_entries, ENTRIES);
+	__type(key, int);
+	__type(value, struct elem);
+} hmap SEC(".maps");
+
+static int process_work(struct bpf_map *map, void *key, void *value)
+{
+	__sync_fetch_and_add(&callback_success, 1);
+	return 0;
+}
+
+SEC("syscall")
+int schedule_task_work(void *ctx)
+{
+	struct elem empty_work = {.count = 0};
+	struct elem *work;
+	int key = 0, err;
+
+	key = bpf_ktime_get_ns() % ENTRIES;
+	work = bpf_map_lookup_elem(&hmap, &key);
+	if (!work) {
+		bpf_map_update_elem(&hmap, &key, &empty_work, BPF_NOEXIST);
+		work = bpf_map_lookup_elem(&hmap, &key);
+		if (!work)
+			return 0;
+	}
+	err = bpf_task_work_schedule_signal_impl(bpf_get_current_task_btf(), &work->tw, &hmap,
+						 process_work, NULL);
+	if (err)
+		__sync_fetch_and_add(&schedule_error, 1);
+	else
+		__sync_fetch_and_add(&callback_scheduled, 1);
+	return 0;
+}
+
+SEC("syscall")
+int delete_task_work(void *ctx)
+{
+	int key = 0, err;
+
+	key = bpf_get_prandom_u32() % ENTRIES;
+	err = bpf_map_delete_elem(&hmap, &key);
+	if (!err)
+		__sync_fetch_and_add(&delete_success, 1);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c b/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c
new file mode 100644
index 000000000000..fe6249d99b31
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tc_bpf2bpf.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+__noinline
+int subprog_tc(struct __sk_buff *skb)
+{
+	int ret = 1;
+
+	__sink(skb);
+	__sink(ret);
+	/* let verifier know that 'subprog_tc' can change pointers to skb->data */
+	bpf_skb_change_proto(skb, 0, 0);
+	return ret;
+}
+
+SEC("tc")
+int entry_tc(struct __sk_buff *skb)
+{
+	return subprog_tc(skb);
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/tc_dummy.c b/tools/testing/selftests/bpf/progs/tc_dummy.c
new file mode 100644
index 000000000000..69a3d0dc8787
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tc_dummy.c
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_legacy.h"
+
+SEC("tc")
+int entry(struct __sk_buff *skb)
+{
+	return 1;
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/tcp_ca_incompl_cong_ops.c b/tools/testing/selftests/bpf/progs/tcp_ca_incompl_cong_ops.c
index 7bb872fb22dd..0016c90e9c13 100644
--- a/tools/testing/selftests/bpf/progs/tcp_ca_incompl_cong_ops.c
+++ b/tools/testing/selftests/bpf/progs/tcp_ca_incompl_cong_ops.c
@@ -1,24 +1,18 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include "vmlinux.h"
-
+#include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 
-static inline struct tcp_sock *tcp_sk(const struct sock *sk)
-{
-	return (struct tcp_sock *)sk;
-}
-
-SEC("struct_ops/incompl_cong_ops_ssthresh")
+SEC("struct_ops")
 __u32 BPF_PROG(incompl_cong_ops_ssthresh, struct sock *sk)
 {
 	return tcp_sk(sk)->snd_ssthresh;
 }
 
-SEC("struct_ops/incompl_cong_ops_undo_cwnd")
+SEC("struct_ops")
 __u32 BPF_PROG(incompl_cong_ops_undo_cwnd, struct sock *sk)
 {
 	return tcp_sk(sk)->snd_cwnd;
diff --git a/tools/testing/selftests/bpf/progs/tcp_ca_kfunc.c b/tools/testing/selftests/bpf/progs/tcp_ca_kfunc.c
new file mode 100644
index 000000000000..f95862f570b7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tcp_ca_kfunc.c
@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+
+extern void bbr_init(struct sock *sk) __ksym;
+extern void bbr_main(struct sock *sk, u32 ack, int flag, const struct rate_sample *rs) __ksym;
+extern u32 bbr_sndbuf_expand(struct sock *sk) __ksym;
+extern u32 bbr_undo_cwnd(struct sock *sk) __ksym;
+extern void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event) __ksym;
+extern u32 bbr_ssthresh(struct sock *sk) __ksym;
+extern u32 bbr_min_tso_segs(struct sock *sk) __ksym;
+extern void bbr_set_state(struct sock *sk, u8 new_state) __ksym;
+
+extern void dctcp_init(struct sock *sk) __ksym;
+extern void dctcp_update_alpha(struct sock *sk, u32 flags) __ksym;
+extern void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) __ksym;
+extern u32 dctcp_ssthresh(struct sock *sk) __ksym;
+extern u32 dctcp_cwnd_undo(struct sock *sk) __ksym;
+extern void dctcp_state(struct sock *sk, u8 new_state) __ksym;
+
+extern void cubictcp_init(struct sock *sk) __ksym;
+extern u32 cubictcp_recalc_ssthresh(struct sock *sk) __ksym;
+extern void cubictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) __ksym;
+extern void cubictcp_state(struct sock *sk, u8 new_state) __ksym;
+extern void cubictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) __ksym;
+extern void cubictcp_acked(struct sock *sk, const struct ack_sample *sample) __ksym;
+
+SEC("struct_ops")
+void BPF_PROG(init, struct sock *sk)
+{
+	bbr_init(sk);
+	dctcp_init(sk);
+	cubictcp_init(sk);
+}
+
+SEC("struct_ops")
+void BPF_PROG(in_ack_event, struct sock *sk, u32 flags)
+{
+	dctcp_update_alpha(sk, flags);
+}
+
+SEC("struct_ops")
+void BPF_PROG(cong_control, struct sock *sk, u32 ack, int flag, const struct rate_sample *rs)
+{
+	bbr_main(sk, ack, flag, rs);
+}
+
+SEC("struct_ops")
+void BPF_PROG(cong_avoid, struct sock *sk, u32 ack, u32 acked)
+{
+	cubictcp_cong_avoid(sk, ack, acked);
+}
+
+SEC("struct_ops")
+u32 BPF_PROG(sndbuf_expand, struct sock *sk)
+{
+	return bbr_sndbuf_expand(sk);
+}
+
+SEC("struct_ops")
+u32 BPF_PROG(undo_cwnd, struct sock *sk)
+{
+	bbr_undo_cwnd(sk);
+	return dctcp_cwnd_undo(sk);
+}
+
+SEC("struct_ops")
+void BPF_PROG(cwnd_event, struct sock *sk, enum tcp_ca_event event)
+{
+	bbr_cwnd_event(sk, event);
+	dctcp_cwnd_event(sk, event);
+	cubictcp_cwnd_event(sk, event);
+}
+
+SEC("struct_ops")
+u32 BPF_PROG(ssthresh, struct sock *sk)
+{
+	bbr_ssthresh(sk);
+	dctcp_ssthresh(sk);
+	return cubictcp_recalc_ssthresh(sk);
+}
+
+SEC("struct_ops")
+u32 BPF_PROG(min_tso_segs, struct sock *sk)
+{
+	return bbr_min_tso_segs(sk);
+}
+
+SEC("struct_ops")
+void BPF_PROG(set_state, struct sock *sk, u8 new_state)
+{
+	bbr_set_state(sk, new_state);
+	dctcp_state(sk, new_state);
+	cubictcp_state(sk, new_state);
+}
+
+SEC("struct_ops")
+void BPF_PROG(pkts_acked, struct sock *sk, const struct ack_sample *sample)
+{
+	cubictcp_acked(sk, sample);
+}
+
+SEC(".struct_ops")
+struct tcp_congestion_ops tcp_ca_kfunc = {
+	.init		= (void *)init,
+	.in_ack_event	= (void *)in_ack_event,
+	.cong_control	= (void *)cong_control,
+	.cong_avoid	= (void *)cong_avoid,
+	.sndbuf_expand	= (void *)sndbuf_expand,
+	.undo_cwnd	= (void *)undo_cwnd,
+	.cwnd_event	= (void *)cwnd_event,
+	.ssthresh	= (void *)ssthresh,
+	.min_tso_segs	= (void *)min_tso_segs,
+	.set_state	= (void *)set_state,
+	.pkts_acked     = (void *)pkts_acked,
+	.name		= "tcp_ca_kfunc",
+};
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/tcp_ca_unsupp_cong_op.c b/tools/testing/selftests/bpf/progs/tcp_ca_unsupp_cong_op.c
index c06f4a41c21a..54f916a931c6 100644
--- a/tools/testing/selftests/bpf/progs/tcp_ca_unsupp_cong_op.c
+++ b/tools/testing/selftests/bpf/progs/tcp_ca_unsupp_cong_op.c
@@ -7,7 +7,7 @@
 
 char _license[] SEC("license") = "GPL";
 
-SEC("struct_ops/unsupp_cong_op_get_info")
+SEC("struct_ops")
 size_t BPF_PROG(unsupp_cong_op_get_info, struct sock *sk, u32 ext, int *attr,
 		union tcp_cc_info *info)
 {
diff --git a/tools/testing/selftests/bpf/progs/tcp_ca_update.c b/tools/testing/selftests/bpf/progs/tcp_ca_update.c
new file mode 100644
index 000000000000..e4bd82bc0d01
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tcp_ca_update.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+int ca1_cnt = 0;
+int ca2_cnt = 0;
+
+SEC("struct_ops")
+void BPF_PROG(ca_update_1_init, struct sock *sk)
+{
+	ca1_cnt++;
+}
+
+SEC("struct_ops")
+void BPF_PROG(ca_update_2_init, struct sock *sk)
+{
+	ca2_cnt++;
+}
+
+SEC("struct_ops")
+void BPF_PROG(ca_update_cong_control, struct sock *sk,
+	      const struct rate_sample *rs)
+{
+}
+
+SEC("struct_ops")
+__u32 BPF_PROG(ca_update_ssthresh, struct sock *sk)
+{
+	return tcp_sk(sk)->snd_ssthresh;
+}
+
+SEC("struct_ops")
+__u32 BPF_PROG(ca_update_undo_cwnd, struct sock *sk)
+{
+	return tcp_sk(sk)->snd_cwnd;
+}
+
+SEC(".struct_ops.link")
+struct tcp_congestion_ops ca_update_1 = {
+	.init = (void *)ca_update_1_init,
+	.cong_control = (void *)ca_update_cong_control,
+	.ssthresh = (void *)ca_update_ssthresh,
+	.undo_cwnd = (void *)ca_update_undo_cwnd,
+	.name = "tcp_ca_update",
+};
+
+SEC(".struct_ops.link")
+struct tcp_congestion_ops ca_update_2 = {
+	.init = (void *)ca_update_2_init,
+	.cong_control = (void *)ca_update_cong_control,
+	.ssthresh = (void *)ca_update_ssthresh,
+	.undo_cwnd = (void *)ca_update_undo_cwnd,
+	.name = "tcp_ca_update",
+};
+
+SEC(".struct_ops.link")
+struct tcp_congestion_ops ca_wrong = {
+	.cong_control = (void *)ca_update_cong_control,
+	.ssthresh = (void *)ca_update_ssthresh,
+	.undo_cwnd = (void *)ca_update_undo_cwnd,
+	.name = "tcp_ca_wrong",
+};
+
+SEC(".struct_ops")
+struct tcp_congestion_ops ca_no_link = {
+	.cong_control = (void *)ca_update_cong_control,
+	.ssthresh = (void *)ca_update_ssthresh,
+	.undo_cwnd = (void *)ca_update_undo_cwnd,
+	.name = "tcp_ca_no_link",
+};
diff --git a/tools/testing/selftests/bpf/progs/tcp_ca_write_sk_pacing.c b/tools/testing/selftests/bpf/progs/tcp_ca_write_sk_pacing.c
index 43447704cf0e..022291f21dfb 100644
--- a/tools/testing/selftests/bpf/progs/tcp_ca_write_sk_pacing.c
+++ b/tools/testing/selftests/bpf/progs/tcp_ca_write_sk_pacing.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include "vmlinux.h"
-
+#include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
@@ -9,14 +8,17 @@ char _license[] SEC("license") = "GPL";
 
 #define USEC_PER_SEC 1000000UL
 
-#define min(a, b) ((a) < (b) ? (a) : (b))
+static unsigned int tcp_left_out(const struct tcp_sock *tp)
+{
+	return tp->sacked_out + tp->lost_out;
+}
 
-static inline struct tcp_sock *tcp_sk(const struct sock *sk)
+static unsigned int tcp_packets_in_flight(const struct tcp_sock *tp)
 {
-	return (struct tcp_sock *)sk;
+	return tp->packets_out - tcp_left_out(tp) + tp->retrans_out;
 }
 
-SEC("struct_ops/write_sk_pacing_init")
+SEC("struct_ops")
 void BPF_PROG(write_sk_pacing_init, struct sock *sk)
 {
 #ifdef ENABLE_ATOMICS_TESTS
@@ -27,24 +29,25 @@ void BPF_PROG(write_sk_pacing_init, struct sock *sk)
 #endif
 }
 
-SEC("struct_ops/write_sk_pacing_cong_control")
+SEC("struct_ops")
 void BPF_PROG(write_sk_pacing_cong_control, struct sock *sk,
 	      const struct rate_sample *rs)
 {
-	const struct tcp_sock *tp = tcp_sk(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
 	unsigned long rate =
 		((tp->snd_cwnd * tp->mss_cache * USEC_PER_SEC) << 3) /
 		(tp->srtt_us ?: 1U << 3);
 	sk->sk_pacing_rate = min(rate, sk->sk_max_pacing_rate);
+	tp->app_limited = (tp->delivered + tcp_packets_in_flight(tp)) ?: 1;
 }
 
-SEC("struct_ops/write_sk_pacing_ssthresh")
+SEC("struct_ops")
 __u32 BPF_PROG(write_sk_pacing_ssthresh, struct sock *sk)
 {
 	return tcp_sk(sk)->snd_ssthresh;
 }
 
-SEC("struct_ops/write_sk_pacing_undo_cwnd")
+SEC("struct_ops")
 __u32 BPF_PROG(write_sk_pacing_undo_cwnd, struct sock *sk)
 {
 	return tcp_sk(sk)->snd_cwnd;
diff --git a/tools/testing/selftests/bpf/progs/tcp_rtt.c b/tools/testing/selftests/bpf/progs/tcp_rtt.c
index 0988d79f1587..42c729f85524 100644
--- a/tools/testing/selftests/bpf/progs/tcp_rtt.c
+++ b/tools/testing/selftests/bpf/progs/tcp_rtt.c
@@ -10,6 +10,9 @@ struct tcp_rtt_storage {
 	__u32 delivered;
 	__u32 delivered_ce;
 	__u32 icsk_retransmits;
+
+	__u32 mrtt_us;	/* args[0] */
+	__u32 srtt;	/* args[1] */
 };
 
 struct {
@@ -55,5 +58,8 @@ int _sockops(struct bpf_sock_ops *ctx)
 	storage->delivered_ce = tcp_sk->delivered_ce;
 	storage->icsk_retransmits = tcp_sk->icsk_retransmits;
 
+	storage->mrtt_us = ctx->args[0];
+	storage->srtt = ctx->args[1];
+
 	return 1;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_access_variable_array.c b/tools/testing/selftests/bpf/progs/test_access_variable_array.c
new file mode 100644
index 000000000000..326b7d1f496a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_access_variable_array.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Bytedance */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+unsigned long span = 0;
+
+SEC("fentry/sched_balance_rq")
+int BPF_PROG(fentry_fentry, int this_cpu, struct rq *this_rq,
+		struct sched_domain *sd)
+{
+	span = sd->span[0];
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_assign_reuse.c b/tools/testing/selftests/bpf/progs/test_assign_reuse.c
new file mode 100644
index 000000000000..4f2e2321ea06
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_assign_reuse.c
@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+#include <linux/pkt_cls.h>
+
+char LICENSE[] SEC("license") = "GPL";
+
+__u64 sk_cookie_seen;
+__u64 reuseport_executed;
+union {
+	struct tcphdr tcp;
+	struct udphdr udp;
+} headers;
+
+const volatile __u16 dest_port;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} sk_map SEC(".maps");
+
+SEC("sk_reuseport")
+int reuse_accept(struct sk_reuseport_md *ctx)
+{
+	reuseport_executed++;
+
+	if (ctx->ip_protocol == IPPROTO_TCP) {
+		if (ctx->data + sizeof(headers.tcp) > ctx->data_end)
+			return SK_DROP;
+
+		if (__builtin_memcmp(&headers.tcp, ctx->data, sizeof(headers.tcp)) != 0)
+			return SK_DROP;
+	} else if (ctx->ip_protocol == IPPROTO_UDP) {
+		if (ctx->data + sizeof(headers.udp) > ctx->data_end)
+			return SK_DROP;
+
+		if (__builtin_memcmp(&headers.udp, ctx->data, sizeof(headers.udp)) != 0)
+			return SK_DROP;
+	} else {
+		return SK_DROP;
+	}
+
+	sk_cookie_seen = bpf_get_socket_cookie(ctx->sk);
+	return SK_PASS;
+}
+
+SEC("sk_reuseport")
+int reuse_drop(struct sk_reuseport_md *ctx)
+{
+	reuseport_executed++;
+	sk_cookie_seen = 0;
+	return SK_DROP;
+}
+
+static int
+assign_sk(struct __sk_buff *skb)
+{
+	int zero = 0, ret = 0;
+	struct bpf_sock *sk;
+
+	sk = bpf_map_lookup_elem(&sk_map, &zero);
+	if (!sk)
+		return TC_ACT_SHOT;
+	ret = bpf_sk_assign(skb, sk, 0);
+	bpf_sk_release(sk);
+	return ret ? TC_ACT_SHOT : TC_ACT_OK;
+}
+
+static bool
+maybe_assign_tcp(struct __sk_buff *skb, struct tcphdr *th)
+{
+	if (th + 1 > (void *)(long)(skb->data_end))
+		return TC_ACT_SHOT;
+
+	if (!th->syn || th->ack || th->dest != bpf_htons(dest_port))
+		return TC_ACT_OK;
+
+	__builtin_memcpy(&headers.tcp, th, sizeof(headers.tcp));
+	return assign_sk(skb);
+}
+
+static bool
+maybe_assign_udp(struct __sk_buff *skb, struct udphdr *uh)
+{
+	if (uh + 1 > (void *)(long)(skb->data_end))
+		return TC_ACT_SHOT;
+
+	if (uh->dest != bpf_htons(dest_port))
+		return TC_ACT_OK;
+
+	__builtin_memcpy(&headers.udp, uh, sizeof(headers.udp));
+	return assign_sk(skb);
+}
+
+SEC("tc")
+int tc_main(struct __sk_buff *skb)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	void *data = (void *)(long)skb->data;
+	struct ethhdr *eth;
+
+	eth = (struct ethhdr *)(data);
+	if (eth + 1 > data_end)
+		return TC_ACT_SHOT;
+
+	if (eth->h_proto == bpf_htons(ETH_P_IP)) {
+		struct iphdr *iph = (struct iphdr *)(data + sizeof(*eth));
+
+		if (iph + 1 > data_end)
+			return TC_ACT_SHOT;
+
+		if (iph->protocol == IPPROTO_TCP)
+			return maybe_assign_tcp(skb, (struct tcphdr *)(iph + 1));
+		else if (iph->protocol == IPPROTO_UDP)
+			return maybe_assign_udp(skb, (struct udphdr *)(iph + 1));
+		else
+			return TC_ACT_SHOT;
+	} else {
+		struct ipv6hdr *ip6h = (struct ipv6hdr *)(data + sizeof(*eth));
+
+		if (ip6h + 1 > data_end)
+			return TC_ACT_SHOT;
+
+		if (ip6h->nexthdr == IPPROTO_TCP)
+			return maybe_assign_tcp(skb, (struct tcphdr *)(ip6h + 1));
+		else if (ip6h->nexthdr == IPPROTO_UDP)
+			return maybe_assign_udp(skb, (struct udphdr *)(ip6h + 1));
+		else
+			return TC_ACT_SHOT;
+	}
+}
diff --git a/tools/testing/selftests/bpf/progs/test_attach_kprobe_sleepable.c b/tools/testing/selftests/bpf/progs/test_attach_kprobe_sleepable.c
new file mode 100644
index 000000000000..f548b7446218
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_attach_kprobe_sleepable.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2017 Facebook
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_misc.h"
+
+int kprobe_res = 0;
+
+/**
+ * This program will be manually made sleepable on the userspace side
+ * and should thus be unattachable.
+ */
+SEC("kprobe/" SYS_PREFIX "sys_nanosleep")
+int handle_kprobe_sleepable(struct pt_regs *ctx)
+{
+	kprobe_res = 1;
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_attach_probe.c b/tools/testing/selftests/bpf/progs/test_attach_probe.c
index a1e45fec8938..fb79e6cab932 100644
--- a/tools/testing/selftests/bpf/progs/test_attach_probe.c
+++ b/tools/testing/selftests/bpf/progs/test_attach_probe.c
@@ -5,30 +5,25 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include <bpf/bpf_core_read.h>
+#include <errno.h>
 #include "bpf_misc.h"
 
-int kprobe_res = 0;
+u32 dynamic_sz = 1;
 int kprobe2_res = 0;
-int kretprobe_res = 0;
 int kretprobe2_res = 0;
-int uprobe_res = 0;
-int uretprobe_res = 0;
 int uprobe_byname_res = 0;
 int uretprobe_byname_res = 0;
 int uprobe_byname2_res = 0;
 int uretprobe_byname2_res = 0;
 int uprobe_byname3_sleepable_res = 0;
+int uprobe_byname3_str_sleepable_res = 0;
 int uprobe_byname3_res = 0;
 int uretprobe_byname3_sleepable_res = 0;
+int uretprobe_byname3_str_sleepable_res = 0;
 int uretprobe_byname3_res = 0;
 void *user_ptr = 0;
 
-SEC("kprobe")
-int handle_kprobe(struct pt_regs *ctx)
-{
-	kprobe_res = 1;
-	return 0;
-}
+int bpf_copy_from_user_str(void *dst, u32, const void *, u64) __weak __ksym;
 
 SEC("ksyscall/nanosleep")
 int BPF_KSYSCALL(handle_kprobe_auto, struct __kernel_timespec *req, struct __kernel_timespec *rem)
@@ -37,24 +32,6 @@ int BPF_KSYSCALL(handle_kprobe_auto, struct __kernel_timespec *req, struct __ker
 	return 0;
 }
 
-/**
- * This program will be manually made sleepable on the userspace side
- * and should thus be unattachable.
- */
-SEC("kprobe/" SYS_PREFIX "sys_nanosleep")
-int handle_kprobe_sleepable(struct pt_regs *ctx)
-{
-	kprobe_res = 2;
-	return 0;
-}
-
-SEC("kretprobe")
-int handle_kretprobe(struct pt_regs *ctx)
-{
-	kretprobe_res = 2;
-	return 0;
-}
-
 SEC("kretsyscall/nanosleep")
 int BPF_KRETPROBE(handle_kretprobe_auto, int ret)
 {
@@ -63,16 +40,14 @@ int BPF_KRETPROBE(handle_kretprobe_auto, int ret)
 }
 
 SEC("uprobe")
-int handle_uprobe(struct pt_regs *ctx)
+int handle_uprobe_ref_ctr(struct pt_regs *ctx)
 {
-	uprobe_res = 3;
 	return 0;
 }
 
 SEC("uretprobe")
-int handle_uretprobe(struct pt_regs *ctx)
+int handle_uretprobe_ref_ctr(struct pt_regs *ctx)
 {
-	uretprobe_res = 4;
 	return 0;
 }
 
@@ -92,18 +67,19 @@ int handle_uretprobe_byname(struct pt_regs *ctx)
 }
 
 SEC("uprobe")
-int handle_uprobe_byname2(struct pt_regs *ctx)
+int BPF_UPROBE(handle_uprobe_byname2, const char *pathname, const char *mode)
 {
-	unsigned int size = PT_REGS_PARM1(ctx);
+	char mode_buf[2] = {};
 
-	/* verify malloc size */
-	if (size == 1)
+	/* verify fopen mode */
+	bpf_probe_read_user(mode_buf, sizeof(mode_buf), mode);
+	if (mode_buf[0] == 'r' && mode_buf[1] == 0)
 		uprobe_byname2_res = 7;
 	return 0;
 }
 
 SEC("uretprobe")
-int handle_uretprobe_byname2(struct pt_regs *ctx)
+int BPF_URETPROBE(handle_uretprobe_byname2, void *ret)
 {
 	uretprobe_byname2_res = 8;
 	return 0;
@@ -117,11 +93,61 @@ static __always_inline bool verify_sleepable_user_copy(void)
 	return bpf_strncmp(data, sizeof(data), "test_data") == 0;
 }
 
+static __always_inline bool verify_sleepable_user_copy_str(void)
+{
+	int ret;
+	char data_long[20];
+	char data_long_pad[20];
+	char data_long_err[20];
+	char data_short[4];
+	char data_short_pad[4];
+
+	ret = bpf_copy_from_user_str(data_short, sizeof(data_short), user_ptr, 0);
+
+	if (bpf_strncmp(data_short, 4, "tes\0") != 0 || ret != 4)
+		return false;
+
+	ret = bpf_copy_from_user_str(data_short_pad, sizeof(data_short_pad), user_ptr, BPF_F_PAD_ZEROS);
+
+	if (bpf_strncmp(data_short, 4, "tes\0") != 0 || ret != 4)
+		return false;
+
+	/* Make sure this passes the verifier */
+	ret = bpf_copy_from_user_str(data_long, dynamic_sz & sizeof(data_long), user_ptr, 0);
+
+	if (ret != 0)
+		return false;
+
+	ret = bpf_copy_from_user_str(data_long, sizeof(data_long), user_ptr, 0);
+
+	if (bpf_strncmp(data_long, 10, "test_data\0") != 0 || ret != 10)
+		return false;
+
+	ret = bpf_copy_from_user_str(data_long_pad, sizeof(data_long_pad), user_ptr, BPF_F_PAD_ZEROS);
+
+	if (bpf_strncmp(data_long_pad, 10, "test_data\0") != 0 || ret != 10 || data_long_pad[19] != '\0')
+		return false;
+
+	ret = bpf_copy_from_user_str(data_long_err, sizeof(data_long_err), (void *)data_long, BPF_F_PAD_ZEROS);
+
+	if (ret > 0 || data_long_err[19] != '\0')
+		return false;
+
+	ret = bpf_copy_from_user_str(data_long, sizeof(data_long), user_ptr, 2);
+
+	if (ret != -EINVAL)
+		return false;
+
+	return true;
+}
+
 SEC("uprobe.s//proc/self/exe:trigger_func3")
 int handle_uprobe_byname3_sleepable(struct pt_regs *ctx)
 {
 	if (verify_sleepable_user_copy())
 		uprobe_byname3_sleepable_res = 9;
+	if (verify_sleepable_user_copy_str())
+		uprobe_byname3_str_sleepable_res = 10;
 	return 0;
 }
 
@@ -132,7 +158,7 @@ int handle_uprobe_byname3_sleepable(struct pt_regs *ctx)
 SEC("uprobe//proc/self/exe:trigger_func3")
 int handle_uprobe_byname3(struct pt_regs *ctx)
 {
-	uprobe_byname3_res = 10;
+	uprobe_byname3_res = 11;
 	return 0;
 }
 
@@ -140,14 +166,16 @@ SEC("uretprobe.s//proc/self/exe:trigger_func3")
 int handle_uretprobe_byname3_sleepable(struct pt_regs *ctx)
 {
 	if (verify_sleepable_user_copy())
-		uretprobe_byname3_sleepable_res = 11;
+		uretprobe_byname3_sleepable_res = 12;
+	if (verify_sleepable_user_copy_str())
+		uretprobe_byname3_str_sleepable_res = 13;
 	return 0;
 }
 
 SEC("uretprobe//proc/self/exe:trigger_func3")
 int handle_uretprobe_byname3(struct pt_regs *ctx)
 {
-	uretprobe_byname3_res = 12;
+	uretprobe_byname3_res = 14;
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_attach_probe_manual.c b/tools/testing/selftests/bpf/progs/test_attach_probe_manual.c
new file mode 100644
index 000000000000..7f08bce94596
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_attach_probe_manual.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2017 Facebook
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_misc.h"
+
+int kprobe_res = 0;
+int kretprobe_res = 0;
+int uprobe_res = 0;
+int uretprobe_res = 0;
+int uprobe_byname_res = 0;
+void *user_ptr = 0;
+
+SEC("kprobe")
+int handle_kprobe(struct pt_regs *ctx)
+{
+	kprobe_res = 1;
+	return 0;
+}
+
+SEC("kretprobe")
+int handle_kretprobe(struct pt_regs *ctx)
+{
+	kretprobe_res = 2;
+	return 0;
+}
+
+SEC("uprobe")
+int handle_uprobe(struct pt_regs *ctx)
+{
+	uprobe_res = 3;
+	return 0;
+}
+
+SEC("uretprobe")
+int handle_uretprobe(struct pt_regs *ctx)
+{
+	uretprobe_res = 4;
+	return 0;
+}
+
+SEC("uprobe")
+int handle_uprobe_byname(struct pt_regs *ctx)
+{
+	uprobe_byname_res = 5;
+	return 0;
+}
+
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_bpf_cookie.c b/tools/testing/selftests/bpf/progs/test_bpf_cookie.c
index 5a3a80f751c4..c83142b55f47 100644
--- a/tools/testing/selftests/bpf/progs/test_bpf_cookie.c
+++ b/tools/testing/selftests/bpf/progs/test_bpf_cookie.c
@@ -15,6 +15,8 @@ __u64 uprobe_res;
 __u64 uretprobe_res;
 __u64 tp_res;
 __u64 pe_res;
+__u64 raw_tp_res;
+__u64 tp_btf_res;
 __u64 fentry_res;
 __u64 fexit_res;
 __u64 fmod_ret_res;
@@ -87,6 +89,20 @@ int handle_pe(struct pt_regs *ctx)
 	return 0;
 }
 
+SEC("raw_tp/sys_enter")
+int handle_raw_tp(void *ctx)
+{
+	update(ctx, &raw_tp_res);
+	return 0;
+}
+
+SEC("tp_btf/sys_enter")
+int handle_tp_btf(void *ctx)
+{
+	update(ctx, &tp_btf_res);
+	return 0;
+}
+
 SEC("fentry/bpf_fentry_test1")
 int BPF_PROG(fentry_test1, int a)
 {
diff --git a/tools/testing/selftests/bpf/progs/test_bpf_ma.c b/tools/testing/selftests/bpf/progs/test_bpf_ma.c
new file mode 100644
index 000000000000..4a4e0b8d9b72
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_bpf_ma.c
@@ -0,0 +1,285 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_experimental.h"
+#include "bpf_misc.h"
+
+struct generic_map_value {
+	void *data;
+};
+
+char _license[] SEC("license") = "GPL";
+
+const unsigned int data_sizes[] = {16, 32, 64, 96, 128, 192, 256, 512, 1024, 2048, 4096};
+const volatile unsigned int data_btf_ids[ARRAY_SIZE(data_sizes)] = {};
+
+const unsigned int percpu_data_sizes[] = {8, 16, 32, 64, 96, 128, 192, 256, 512};
+const volatile unsigned int percpu_data_btf_ids[ARRAY_SIZE(data_sizes)] = {};
+
+int err = 0;
+u32 pid = 0;
+
+#define DEFINE_ARRAY_WITH_KPTR(_size) \
+	struct bin_data_##_size { \
+		char data[_size - sizeof(void *)]; \
+	}; \
+	/* See Commit 5d8d6634ccc, force btf generation for type bin_data_##_size */	\
+	struct bin_data_##_size *__bin_data_##_size; \
+	struct map_value_##_size { \
+		struct bin_data_##_size __kptr * data; \
+	}; \
+	struct { \
+		__uint(type, BPF_MAP_TYPE_ARRAY); \
+		__type(key, int); \
+		__type(value, struct map_value_##_size); \
+		__uint(max_entries, 128); \
+	} array_##_size SEC(".maps")
+
+#define DEFINE_ARRAY_WITH_PERCPU_KPTR(_size) \
+	struct percpu_bin_data_##_size { \
+		char data[_size]; \
+	}; \
+	struct percpu_bin_data_##_size *__percpu_bin_data_##_size; \
+	struct map_value_percpu_##_size { \
+		struct percpu_bin_data_##_size __percpu_kptr * data; \
+	}; \
+	struct { \
+		__uint(type, BPF_MAP_TYPE_ARRAY); \
+		__type(key, int); \
+		__type(value, struct map_value_percpu_##_size); \
+		__uint(max_entries, 128); \
+	} array_percpu_##_size SEC(".maps")
+
+static __always_inline void batch_alloc(struct bpf_map *map, unsigned int batch, unsigned int idx)
+{
+	struct generic_map_value *value;
+	unsigned int i, key;
+	void *old, *new;
+
+	for (i = 0; i < batch; i++) {
+		key = i;
+		value = bpf_map_lookup_elem(map, &key);
+		if (!value) {
+			err = 1;
+			return;
+		}
+		new = bpf_obj_new_impl(data_btf_ids[idx], NULL);
+		if (!new) {
+			err = 2;
+			return;
+		}
+		old = bpf_kptr_xchg(&value->data, new);
+		if (old) {
+			bpf_obj_drop(old);
+			err = 3;
+			return;
+		}
+	}
+}
+
+static __always_inline void batch_free(struct bpf_map *map, unsigned int batch, unsigned int idx)
+{
+	struct generic_map_value *value;
+	unsigned int i, key;
+	void *old;
+
+	for (i = 0; i < batch; i++) {
+		key = i;
+		value = bpf_map_lookup_elem(map, &key);
+		if (!value) {
+			err = 4;
+			return;
+		}
+		old = bpf_kptr_xchg(&value->data, NULL);
+		if (!old) {
+			err = 5;
+			return;
+		}
+		bpf_obj_drop(old);
+	}
+}
+
+static __always_inline void batch_percpu_alloc(struct bpf_map *map, unsigned int batch,
+					       unsigned int idx)
+{
+	struct generic_map_value *value;
+	unsigned int i, key;
+	void *old, *new;
+
+	for (i = 0; i < batch; i++) {
+		key = i;
+		value = bpf_map_lookup_elem(map, &key);
+		if (!value) {
+			err = 1;
+			return;
+		}
+		/* per-cpu allocator may not be able to refill in time */
+		new = bpf_percpu_obj_new_impl(percpu_data_btf_ids[idx], NULL);
+		if (!new)
+			continue;
+
+		old = bpf_kptr_xchg(&value->data, new);
+		if (old) {
+			bpf_percpu_obj_drop(old);
+			err = 2;
+			return;
+		}
+	}
+}
+
+static __always_inline void batch_percpu_free(struct bpf_map *map, unsigned int batch,
+					      unsigned int idx)
+{
+	struct generic_map_value *value;
+	unsigned int i, key;
+	void *old;
+
+	for (i = 0; i < batch; i++) {
+		key = i;
+		value = bpf_map_lookup_elem(map, &key);
+		if (!value) {
+			err = 3;
+			return;
+		}
+		old = bpf_kptr_xchg(&value->data, NULL);
+		if (!old)
+			continue;
+		bpf_percpu_obj_drop(old);
+	}
+}
+
+#define CALL_BATCH_ALLOC(size, batch, idx) \
+	batch_alloc((struct bpf_map *)(&array_##size), batch, idx)
+
+#define CALL_BATCH_ALLOC_FREE(size, batch, idx) \
+	do { \
+		batch_alloc((struct bpf_map *)(&array_##size), batch, idx); \
+		batch_free((struct bpf_map *)(&array_##size), batch, idx); \
+	} while (0)
+
+#define CALL_BATCH_PERCPU_ALLOC(size, batch, idx) \
+	batch_percpu_alloc((struct bpf_map *)(&array_percpu_##size), batch, idx)
+
+#define CALL_BATCH_PERCPU_ALLOC_FREE(size, batch, idx) \
+	do { \
+		batch_percpu_alloc((struct bpf_map *)(&array_percpu_##size), batch, idx); \
+		batch_percpu_free((struct bpf_map *)(&array_percpu_##size), batch, idx); \
+	} while (0)
+
+/* kptr doesn't support bin_data_8 which is a zero-sized array */
+DEFINE_ARRAY_WITH_KPTR(16);
+DEFINE_ARRAY_WITH_KPTR(32);
+DEFINE_ARRAY_WITH_KPTR(64);
+DEFINE_ARRAY_WITH_KPTR(96);
+DEFINE_ARRAY_WITH_KPTR(128);
+DEFINE_ARRAY_WITH_KPTR(192);
+DEFINE_ARRAY_WITH_KPTR(256);
+DEFINE_ARRAY_WITH_KPTR(512);
+DEFINE_ARRAY_WITH_KPTR(1024);
+DEFINE_ARRAY_WITH_KPTR(2048);
+DEFINE_ARRAY_WITH_KPTR(4096);
+
+DEFINE_ARRAY_WITH_PERCPU_KPTR(8);
+DEFINE_ARRAY_WITH_PERCPU_KPTR(16);
+DEFINE_ARRAY_WITH_PERCPU_KPTR(32);
+DEFINE_ARRAY_WITH_PERCPU_KPTR(64);
+DEFINE_ARRAY_WITH_PERCPU_KPTR(96);
+DEFINE_ARRAY_WITH_PERCPU_KPTR(128);
+DEFINE_ARRAY_WITH_PERCPU_KPTR(192);
+DEFINE_ARRAY_WITH_PERCPU_KPTR(256);
+DEFINE_ARRAY_WITH_PERCPU_KPTR(512);
+
+SEC("?fentry/" SYS_PREFIX "sys_nanosleep")
+int test_batch_alloc_free(void *ctx)
+{
+	if ((u32)bpf_get_current_pid_tgid() != pid)
+		return 0;
+
+	/* Alloc 128 16-bytes objects in batch to trigger refilling,
+	 * then free 128 16-bytes objects in batch to trigger freeing.
+	 */
+	CALL_BATCH_ALLOC_FREE(16, 128, 0);
+	CALL_BATCH_ALLOC_FREE(32, 128, 1);
+	CALL_BATCH_ALLOC_FREE(64, 128, 2);
+	CALL_BATCH_ALLOC_FREE(96, 128, 3);
+	CALL_BATCH_ALLOC_FREE(128, 128, 4);
+	CALL_BATCH_ALLOC_FREE(192, 128, 5);
+	CALL_BATCH_ALLOC_FREE(256, 128, 6);
+	CALL_BATCH_ALLOC_FREE(512, 64, 7);
+	CALL_BATCH_ALLOC_FREE(1024, 32, 8);
+	CALL_BATCH_ALLOC_FREE(2048, 16, 9);
+	CALL_BATCH_ALLOC_FREE(4096, 8, 10);
+
+	return 0;
+}
+
+SEC("?fentry/" SYS_PREFIX "sys_nanosleep")
+int test_free_through_map_free(void *ctx)
+{
+	if ((u32)bpf_get_current_pid_tgid() != pid)
+		return 0;
+
+	/* Alloc 128 16-bytes objects in batch to trigger refilling,
+	 * then free these objects through map free.
+	 */
+	CALL_BATCH_ALLOC(16, 128, 0);
+	CALL_BATCH_ALLOC(32, 128, 1);
+	CALL_BATCH_ALLOC(64, 128, 2);
+	CALL_BATCH_ALLOC(96, 128, 3);
+	CALL_BATCH_ALLOC(128, 128, 4);
+	CALL_BATCH_ALLOC(192, 128, 5);
+	CALL_BATCH_ALLOC(256, 128, 6);
+	CALL_BATCH_ALLOC(512, 64, 7);
+	CALL_BATCH_ALLOC(1024, 32, 8);
+	CALL_BATCH_ALLOC(2048, 16, 9);
+	CALL_BATCH_ALLOC(4096, 8, 10);
+
+	return 0;
+}
+
+SEC("?fentry/" SYS_PREFIX "sys_nanosleep")
+int test_batch_percpu_alloc_free(void *ctx)
+{
+	if ((u32)bpf_get_current_pid_tgid() != pid)
+		return 0;
+
+	/* Alloc 128 8-bytes per-cpu objects in batch to trigger refilling,
+	 * then free 128 8-bytes per-cpu objects in batch to trigger freeing.
+	 */
+	CALL_BATCH_PERCPU_ALLOC_FREE(8, 128, 0);
+	CALL_BATCH_PERCPU_ALLOC_FREE(16, 128, 1);
+	CALL_BATCH_PERCPU_ALLOC_FREE(32, 128, 2);
+	CALL_BATCH_PERCPU_ALLOC_FREE(64, 128, 3);
+	CALL_BATCH_PERCPU_ALLOC_FREE(96, 128, 4);
+	CALL_BATCH_PERCPU_ALLOC_FREE(128, 128, 5);
+	CALL_BATCH_PERCPU_ALLOC_FREE(192, 128, 6);
+	CALL_BATCH_PERCPU_ALLOC_FREE(256, 128, 7);
+	CALL_BATCH_PERCPU_ALLOC_FREE(512, 64, 8);
+
+	return 0;
+}
+
+SEC("?fentry/" SYS_PREFIX "sys_nanosleep")
+int test_percpu_free_through_map_free(void *ctx)
+{
+	if ((u32)bpf_get_current_pid_tgid() != pid)
+		return 0;
+
+	/* Alloc 128 8-bytes per-cpu objects in batch to trigger refilling,
+	 * then free these object through map free.
+	 */
+	CALL_BATCH_PERCPU_ALLOC(8, 128, 0);
+	CALL_BATCH_PERCPU_ALLOC(16, 128, 1);
+	CALL_BATCH_PERCPU_ALLOC(32, 128, 2);
+	CALL_BATCH_PERCPU_ALLOC(64, 128, 3);
+	CALL_BATCH_PERCPU_ALLOC(96, 128, 4);
+	CALL_BATCH_PERCPU_ALLOC(128, 128, 5);
+	CALL_BATCH_PERCPU_ALLOC(192, 128, 6);
+	CALL_BATCH_PERCPU_ALLOC(256, 128, 7);
+	CALL_BATCH_PERCPU_ALLOC(512, 64, 8);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf.c b/tools/testing/selftests/bpf/progs/test_bpf_nf.c
index 227e85e85dda..f7b330ddd007 100644
--- a/tools/testing/selftests/bpf/progs/test_bpf_nf.c
+++ b/tools/testing/selftests/bpf/progs/test_bpf_nf.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#define BPF_NO_KFUNC_PROTOTYPES
 #include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
@@ -9,10 +10,14 @@
 #define EINVAL 22
 #define ENOENT 2
 
+#define NF_CT_ZONE_DIR_ORIG (1 << IP_CT_DIR_ORIGINAL)
+#define NF_CT_ZONE_DIR_REPL (1 << IP_CT_DIR_REPLY)
+
 extern unsigned long CONFIG_HZ __kconfig;
 
 int test_einval_bpf_tuple = 0;
 int test_einval_reserved = 0;
+int test_einval_reserved_new = 0;
 int test_einval_netns_id = 0;
 int test_einval_len_opts = 0;
 int test_eproto_l4proto = 0;
@@ -22,6 +27,11 @@ int test_eafnosupport = 0;
 int test_alloc_entry = -EINVAL;
 int test_insert_entry = -EAFNOSUPPORT;
 int test_succ_lookup = -ENOENT;
+int test_ct_zone_id_alloc_entry = -EINVAL;
+int test_ct_zone_id_insert_entry = -EAFNOSUPPORT;
+int test_ct_zone_id_succ_lookup = -ENOENT;
+int test_ct_zone_dir_enoent_lookup = 0;
+int test_ct_zone_id_enoent_lookup = 0;
 u32 test_delta_timeout = 0;
 u32 test_status = 0;
 u32 test_insert_lookup_mark = 0;
@@ -34,12 +44,28 @@ __be16 dport = 0;
 int test_exist_lookup = -ENOENT;
 u32 test_exist_lookup_mark = 0;
 
+enum nf_nat_manip_type___local {
+	NF_NAT_MANIP_SRC___local,
+	NF_NAT_MANIP_DST___local
+};
+
 struct nf_conn;
 
 struct bpf_ct_opts___local {
 	s32 netns_id;
 	s32 error;
 	u8 l4proto;
+	u8 dir;
+	u8 reserved[2];
+};
+
+struct bpf_ct_opts___new {
+	s32 netns_id;
+	s32 error;
+	u8 l4proto;
+	u8 dir;
+	u16 ct_zone_id;
+	u8 ct_zone_dir;
 	u8 reserved[3];
 } __attribute__((preserve_access_index));
 
@@ -58,7 +84,7 @@ int bpf_ct_change_timeout(struct nf_conn *, u32) __ksym;
 int bpf_ct_set_status(struct nf_conn *, u32) __ksym;
 int bpf_ct_change_status(struct nf_conn *, u32) __ksym;
 int bpf_ct_set_nat_info(struct nf_conn *, union nf_inet_addr *,
-			int port, enum nf_nat_manip_type) __ksym;
+			int port, enum nf_nat_manip_type___local) __ksym;
 
 static __always_inline void
 nf_ct_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32,
@@ -70,7 +96,6 @@ nf_ct_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32,
 	struct bpf_ct_opts___local opts_def = { .l4proto = IPPROTO_TCP, .netns_id = -1 };
 	struct bpf_sock_tuple bpf_tuple;
 	struct nf_conn *ct;
-	int err;
 
 	__builtin_memset(&bpf_tuple, 0, sizeof(bpf_tuple.ipv4));
 
@@ -157,10 +182,10 @@ nf_ct_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32,
 
 		/* snat */
 		saddr.ip = bpf_get_prandom_u32();
-		bpf_ct_set_nat_info(ct, &saddr, sport, NF_NAT_MANIP_SRC);
+		bpf_ct_set_nat_info(ct, &saddr, sport, NF_NAT_MANIP_SRC___local);
 		/* dnat */
 		daddr.ip = bpf_get_prandom_u32();
-		bpf_ct_set_nat_info(ct, &daddr, dport, NF_NAT_MANIP_DST);
+		bpf_ct_set_nat_info(ct, &daddr, dport, NF_NAT_MANIP_DST___local);
 
 		ct_ins = bpf_ct_insert_entry(ct);
 		if (ct_ins) {
@@ -216,10 +241,97 @@ nf_ct_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32,
 	}
 }
 
+static __always_inline void
+nf_ct_opts_new_test(struct nf_conn *(*lookup_fn)(void *, struct bpf_sock_tuple *, u32,
+						 struct bpf_ct_opts___new *, u32),
+		    struct nf_conn *(*alloc_fn)(void *, struct bpf_sock_tuple *, u32,
+						struct bpf_ct_opts___new *, u32),
+		    void *ctx)
+{
+	struct bpf_ct_opts___new opts_def = { .l4proto = IPPROTO_TCP, .netns_id = -1 };
+	struct bpf_sock_tuple bpf_tuple;
+	struct nf_conn *ct;
+
+	__builtin_memset(&bpf_tuple, 0, sizeof(bpf_tuple.ipv4));
+
+	opts_def.reserved[0] = 1;
+	ct = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def,
+		       sizeof(opts_def));
+	opts_def.reserved[0] = 0;
+	if (ct)
+		bpf_ct_release(ct);
+	else
+		test_einval_reserved_new = opts_def.error;
+
+	bpf_tuple.ipv4.saddr = bpf_get_prandom_u32(); /* src IP */
+	bpf_tuple.ipv4.daddr = bpf_get_prandom_u32(); /* dst IP */
+	bpf_tuple.ipv4.sport = bpf_get_prandom_u32(); /* src port */
+	bpf_tuple.ipv4.dport = bpf_get_prandom_u32(); /* dst port */
+
+	/* use non-default ct zone */
+	opts_def.ct_zone_id = 10;
+	opts_def.ct_zone_dir = NF_CT_ZONE_DIR_ORIG;
+	ct = alloc_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4), &opts_def,
+		      sizeof(opts_def));
+	if (ct) {
+		__u16 sport = bpf_get_prandom_u32();
+		__u16 dport = bpf_get_prandom_u32();
+		union nf_inet_addr saddr = {};
+		union nf_inet_addr daddr = {};
+		struct nf_conn *ct_ins;
+
+		bpf_ct_set_timeout(ct, 10000);
+
+		/* snat */
+		saddr.ip = bpf_get_prandom_u32();
+		bpf_ct_set_nat_info(ct, &saddr, sport, NF_NAT_MANIP_SRC___local);
+		/* dnat */
+		daddr.ip = bpf_get_prandom_u32();
+		bpf_ct_set_nat_info(ct, &daddr, dport, NF_NAT_MANIP_DST___local);
+
+		ct_ins = bpf_ct_insert_entry(ct);
+		if (ct_ins) {
+			struct nf_conn *ct_lk;
+
+			/* entry should exist in same ct zone we inserted it */
+			ct_lk = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4),
+					  &opts_def, sizeof(opts_def));
+			if (ct_lk) {
+				bpf_ct_release(ct_lk);
+				test_ct_zone_id_succ_lookup = 0;
+			}
+
+			/* entry should not exist with wrong direction */
+			opts_def.ct_zone_dir = NF_CT_ZONE_DIR_REPL;
+			ct_lk = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4),
+					  &opts_def, sizeof(opts_def));
+			opts_def.ct_zone_dir = NF_CT_ZONE_DIR_ORIG;
+			if (ct_lk)
+				bpf_ct_release(ct_lk);
+			else
+				test_ct_zone_dir_enoent_lookup = opts_def.error;
+
+			/* entry should not exist in default ct zone */
+			opts_def.ct_zone_id = 0;
+			ct_lk = lookup_fn(ctx, &bpf_tuple, sizeof(bpf_tuple.ipv4),
+					  &opts_def, sizeof(opts_def));
+			if (ct_lk)
+				bpf_ct_release(ct_lk);
+			else
+				test_ct_zone_id_enoent_lookup = opts_def.error;
+
+			bpf_ct_release(ct_ins);
+			test_ct_zone_id_insert_entry = 0;
+		}
+		test_ct_zone_id_alloc_entry = 0;
+	}
+}
+
 SEC("xdp")
 int nf_xdp_ct_test(struct xdp_md *ctx)
 {
 	nf_ct_test((void *)bpf_xdp_ct_lookup, (void *)bpf_xdp_ct_alloc, ctx);
+	nf_ct_opts_new_test((void *)bpf_xdp_ct_lookup, (void *)bpf_xdp_ct_alloc, ctx);
 	return 0;
 }
 
@@ -227,6 +339,7 @@ SEC("tc")
 int nf_skb_ct_test(struct __sk_buff *ctx)
 {
 	nf_ct_test((void *)bpf_skb_ct_lookup, (void *)bpf_skb_ct_alloc, ctx);
+	nf_ct_opts_new_test((void *)bpf_skb_ct_lookup, (void *)bpf_skb_ct_alloc, ctx);
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_bpf_nf_fail.c b/tools/testing/selftests/bpf/progs/test_bpf_nf_fail.c
index 0e4759ab38ff..a586f087ffeb 100644
--- a/tools/testing/selftests/bpf/progs/test_bpf_nf_fail.c
+++ b/tools/testing/selftests/bpf/progs/test_bpf_nf_fail.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#define BPF_NO_KFUNC_PROTOTYPES
 #include <vmlinux.h>
 #include <bpf/bpf_tracing.h>
 #include <bpf/bpf_helpers.h>
diff --git a/tools/testing/selftests/bpf/progs/test_btf_ext.c b/tools/testing/selftests/bpf/progs/test_btf_ext.c
new file mode 100644
index 000000000000..cdf20331db04
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_btf_ext.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2025 Meta Platforms Inc. */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+__noinline static void f0(void)
+{
+	__u64 a = 1;
+
+	__sink(a);
+}
+
+SEC("xdp")
+__u64 global_func(struct xdp_md *xdp)
+{
+	f0();
+	return XDP_DROP;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c
index e2bea4da194b..1cd1a1b72cb5 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c
@@ -1,31 +1,27 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
 
-#include <string.h>
-#include <errno.h>
-#include <netinet/in.h>
-#include <linux/stddef.h>
-#include <linux/bpf.h>
-#include <linux/ipv6.h>
-#include <linux/tcp.h>
-#include <linux/if_ether.h>
-#include <linux/pkt_cls.h>
-
+#include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
-#include "bpf_tcp_helpers.h"
+
+#ifndef ENOENT
+#define ENOENT 2
+#endif
 
 struct sockaddr_in6 srv_sa6 = {};
+struct sockaddr_in srv_sa4 = {};
 __u16 listen_tp_sport = 0;
 __u16 req_sk_sport = 0;
 __u32 recv_cookie = 0;
 __u32 gen_cookie = 0;
+__u32 mss = 0;
 __u32 linum = 0;
 
 #define LOG() ({ if (!linum) linum = __LINE__; })
 
-static void test_syncookie_helper(struct ipv6hdr *ip6h, struct tcphdr *th,
-				  struct tcp_sock *tp,
+static void test_syncookie_helper(void *iphdr, int iphdr_size,
+				  struct tcphdr *th, struct tcp_sock *tp,
 				  struct __sk_buff *skb)
 {
 	if (th->syn) {
@@ -44,17 +40,18 @@ static void test_syncookie_helper(struct ipv6hdr *ip6h, struct tcphdr *th,
 			return;
 		}
 
-		mss_cookie = bpf_tcp_gen_syncookie(tp, ip6h, sizeof(*ip6h),
+		mss_cookie = bpf_tcp_gen_syncookie(tp, iphdr, iphdr_size,
 						   th, 40);
 		if (mss_cookie < 0) {
 			if (mss_cookie != -ENOENT)
 				LOG();
 		} else {
 			gen_cookie = (__u32)mss_cookie;
+			mss = mss_cookie >> 32;
 		}
 	} else if (gen_cookie) {
 		/* It was in cookie mode */
-		int ret = bpf_tcp_check_syncookie(tp, ip6h, sizeof(*ip6h),
+		int ret = bpf_tcp_check_syncookie(tp, iphdr, iphdr_size,
 						  th, sizeof(*th));
 
 		if (ret < 0) {
@@ -66,26 +63,58 @@ static void test_syncookie_helper(struct ipv6hdr *ip6h, struct tcphdr *th,
 	}
 }
 
-static int handle_ip6_tcp(struct ipv6hdr *ip6h, struct __sk_buff *skb)
+static int handle_ip_tcp(struct ethhdr *eth, struct __sk_buff *skb)
 {
-	struct bpf_sock_tuple *tuple;
+	struct bpf_sock_tuple *tuple = NULL;
+	unsigned int tuple_len = 0;
 	struct bpf_sock *bpf_skc;
-	unsigned int tuple_len;
+	void *data_end, *iphdr;
+	struct ipv6hdr *ip6h;
+	struct iphdr *ip4h;
 	struct tcphdr *th;
-	void *data_end;
+	int iphdr_size;
 
 	data_end = (void *)(long)(skb->data_end);
 
-	th = (struct tcphdr *)(ip6h + 1);
-	if (th + 1 > data_end)
-		return TC_ACT_OK;
-
-	/* Is it the testing traffic? */
-	if (th->dest != srv_sa6.sin6_port)
+	switch (eth->h_proto) {
+	case bpf_htons(ETH_P_IP):
+		ip4h = (struct iphdr *)(eth + 1);
+		if (ip4h + 1 > data_end)
+			return TC_ACT_OK;
+		if (ip4h->protocol != IPPROTO_TCP)
+			return TC_ACT_OK;
+		th = (struct tcphdr *)(ip4h + 1);
+		if (th + 1 > data_end)
+			return TC_ACT_OK;
+		/* Is it the testing traffic? */
+		if (th->dest != srv_sa4.sin_port)
+			return TC_ACT_OK;
+		tuple_len = sizeof(tuple->ipv4);
+		tuple = (struct bpf_sock_tuple *)&ip4h->saddr;
+		iphdr = ip4h;
+		iphdr_size = sizeof(*ip4h);
+		break;
+	case bpf_htons(ETH_P_IPV6):
+		ip6h = (struct ipv6hdr *)(eth + 1);
+		if (ip6h + 1 > data_end)
+			return TC_ACT_OK;
+		if (ip6h->nexthdr != IPPROTO_TCP)
+			return TC_ACT_OK;
+		th = (struct tcphdr *)(ip6h + 1);
+		if (th + 1 > data_end)
+			return TC_ACT_OK;
+		/* Is it the testing traffic? */
+		if (th->dest != srv_sa6.sin6_port)
+			return TC_ACT_OK;
+		tuple_len = sizeof(tuple->ipv6);
+		tuple = (struct bpf_sock_tuple *)&ip6h->saddr;
+		iphdr = ip6h;
+		iphdr_size = sizeof(*ip6h);
+		break;
+	default:
 		return TC_ACT_OK;
+	}
 
-	tuple_len = sizeof(tuple->ipv6);
-	tuple = (struct bpf_sock_tuple *)&ip6h->saddr;
 	if ((void *)tuple + tuple_len > data_end) {
 		LOG();
 		return TC_ACT_OK;
@@ -132,7 +161,7 @@ static int handle_ip6_tcp(struct ipv6hdr *ip6h, struct __sk_buff *skb)
 
 		listen_tp_sport = tp->inet_conn.icsk_inet.sk.__sk_common.skc_num;
 
-		test_syncookie_helper(ip6h, th, tp, skb);
+		test_syncookie_helper(iphdr, iphdr_size, th, tp, skb);
 		bpf_sk_release(tp);
 		return TC_ACT_OK;
 	}
@@ -148,7 +177,6 @@ release:
 SEC("tc")
 int cls_ingress(struct __sk_buff *skb)
 {
-	struct ipv6hdr *ip6h;
 	struct ethhdr *eth;
 	void *data_end;
 
@@ -158,17 +186,11 @@ int cls_ingress(struct __sk_buff *skb)
 	if (eth + 1 > data_end)
 		return TC_ACT_OK;
 
-	if (eth->h_proto != bpf_htons(ETH_P_IPV6))
-		return TC_ACT_OK;
-
-	ip6h = (struct ipv6hdr *)(eth + 1);
-	if (ip6h + 1 > data_end)
+	if (eth->h_proto != bpf_htons(ETH_P_IP) &&
+	    eth->h_proto != bpf_htons(ETH_P_IPV6))
 		return TC_ACT_OK;
 
-	if (ip6h->nexthdr == IPPROTO_TCP)
-		return handle_ip6_tcp(ip6h, skb);
-
-	return TC_ACT_OK;
+	return handle_ip_tcp(eth, skb);
 }
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_build_id.c b/tools/testing/selftests/bpf/progs/test_build_id.c
new file mode 100644
index 000000000000..32ce59f9aa27
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_build_id.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+struct bpf_stack_build_id stack_sleepable[128];
+int res_sleepable;
+
+struct bpf_stack_build_id stack_nofault[128];
+int res_nofault;
+
+SEC("uprobe.multi/./uprobe_multi:uprobe")
+int uprobe_nofault(struct pt_regs *ctx)
+{
+	res_nofault = bpf_get_stack(ctx, stack_nofault, sizeof(stack_nofault),
+				    BPF_F_USER_STACK | BPF_F_USER_BUILD_ID);
+
+	return 0;
+}
+
+SEC("uprobe.multi.s/./uprobe_multi:uprobe")
+int uprobe_sleepable(struct pt_regs *ctx)
+{
+	res_sleepable = bpf_get_stack(ctx, stack_sleepable, sizeof(stack_sleepable),
+				      BPF_F_USER_STACK | BPF_F_USER_BUILD_ID);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c b/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c
new file mode 100644
index 000000000000..4fee0fdc7607
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_cgroup1_hierarchy.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+
+__u32 target_ancestor_level;
+__u64 target_ancestor_cgid;
+int target_pid, target_hid;
+
+struct cgroup *bpf_task_get_cgroup1(struct task_struct *task, int hierarchy_id) __ksym;
+struct cgroup *bpf_cgroup_ancestor(struct cgroup *cgrp, int level) __ksym;
+void bpf_cgroup_release(struct cgroup *cgrp) __ksym;
+
+static int bpf_link_create_verify(int cmd)
+{
+	struct cgroup *cgrp, *ancestor;
+	struct task_struct *task;
+	int ret = 0;
+
+	if (cmd != BPF_LINK_CREATE)
+		return 0;
+
+	task = bpf_get_current_task_btf();
+
+	/* Then it can run in parallel with others */
+	if (task->pid != target_pid)
+		return 0;
+
+	cgrp = bpf_task_get_cgroup1(task, target_hid);
+	if (!cgrp)
+		return 0;
+
+	/* Refuse it if its cgid or its ancestor's cgid is the target cgid */
+	if (cgrp->kn->id == target_ancestor_cgid)
+		ret = -1;
+
+	ancestor = bpf_cgroup_ancestor(cgrp, target_ancestor_level);
+	if (!ancestor)
+		goto out;
+
+	if (ancestor->kn->id == target_ancestor_cgid)
+		ret = -1;
+	bpf_cgroup_release(ancestor);
+
+out:
+	bpf_cgroup_release(cgrp);
+	return ret;
+}
+
+SEC("lsm/bpf")
+int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
+{
+	return bpf_link_create_verify(cmd);
+}
+
+SEC("lsm.s/bpf")
+int BPF_PROG(lsm_s_run, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
+{
+	return bpf_link_create_verify(cmd);
+}
+
+SEC("fentry")
+int BPF_PROG(fentry_run)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_check_mtu.c b/tools/testing/selftests/bpf/progs/test_check_mtu.c
index 2ec1de11a3ae..7b6b2b342c1d 100644
--- a/tools/testing/selftests/bpf/progs/test_check_mtu.c
+++ b/tools/testing/selftests/bpf/progs/test_check_mtu.c
@@ -7,6 +7,7 @@
 
 #include <stddef.h>
 #include <stdint.h>
+#include <errno.h>
 
 char _license[] SEC("license") = "GPL";
 
@@ -288,3 +289,14 @@ int tc_input_len_exceed(struct __sk_buff *ctx)
 	global_bpf_mtu_xdp = mtu_len;
 	return retval;
 }
+
+SEC("tc")
+int tc_chk_segs_flag(struct __sk_buff *ctx)
+{
+	__u32 mtu_len = 0;
+	int err;
+
+	err = bpf_check_mtu(ctx, GLOBAL_USER_IFINDEX, &mtu_len, 0, BPF_MTU_CHK_SEGS);
+
+	return err == -EINVAL ? BPF_OK : BPF_DROP;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c
index 2833ad722cb7..26a53e54b8fa 100644
--- a/tools/testing/selftests/bpf/progs/test_cls_redirect.c
+++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c
@@ -15,12 +15,16 @@
 #include <linux/ipv6.h>
 #include <linux/pkt_cls.h>
 #include <linux/tcp.h>
-#include <linux/udp.h>
+#include <netinet/udp.h>
 
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
+#include "bpf_compiler.h"
 #include "test_cls_redirect.h"
+#include "bpf_misc.h"
+
+#pragma GCC diagnostic ignored "-Waddress-of-packed-member"
 
 #ifdef SUBPROGS
 #define INLINING __noinline
@@ -28,9 +32,6 @@
 #define INLINING __always_inline
 #endif
 
-#define offsetofend(TYPE, MEMBER) \
-	(offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER)))
-
 #define IP_OFFSET_MASK (0x1FFF)
 #define IP_MF (0x2000)
 
@@ -126,7 +127,7 @@ typedef uint8_t *net_ptr __attribute__((align_value(8)));
 typedef struct buf {
 	struct __sk_buff *skb;
 	net_ptr head;
-	/* NB: tail musn't have alignment other than 1, otherwise
+	/* NB: tail mustn't have alignment other than 1, otherwise
 	* LLVM will go and eliminate code, e.g. when checking packet lengths.
 	*/
 	uint8_t *const tail;
@@ -267,7 +268,7 @@ static INLINING void pkt_ipv4_checksum(struct iphdr *iph)
 	uint32_t acc = 0;
 	uint16_t *ipw = (uint16_t *)iph;
 
-#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (size_t i = 0; i < sizeof(struct iphdr) / 2; i++) {
 		acc += ipw[i];
 	}
@@ -294,7 +295,7 @@ bool pkt_skip_ipv6_extension_headers(buf_t *pkt,
 	};
 	*is_fragment = false;
 
-#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (int i = 0; i < 6; i++) {
 		switch (exthdr.next) {
 		case IPPROTO_FRAGMENT:
@@ -600,7 +601,7 @@ static INLINING ret_t get_next_hop(buf_t *pkt, encap_headers_t *encap,
 		return TC_ACT_SHOT;
 	}
 
-	/* Skip the remainig next hops (may be zero). */
+	/* Skip the remaining next hops (may be zero). */
 	return skip_next_hops(pkt, encap->unigue.hop_count -
 					   encap->unigue.next_hop - 1);
 }
@@ -610,8 +611,8 @@ static INLINING ret_t get_next_hop(buf_t *pkt, encap_headers_t *encap,
  *
  *    fill_tuple(&t, foo, sizeof(struct iphdr), 123, 321)
  *
- * clang will substitue a costant for sizeof, which allows the verifier
- * to track it's value. Based on this, it can figure out the constant
+ * clang will substitute a constant for sizeof, which allows the verifier
+ * to track its value. Based on this, it can figure out the constant
  * return value, and calling code works while still being "generic" to
  * IPv4 and IPv6.
  */
diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.h b/tools/testing/selftests/bpf/progs/test_cls_redirect.h
index 76eab0aacba0..eb55cb8a3dbd 100644
--- a/tools/testing/selftests/bpf/progs/test_cls_redirect.h
+++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.h
@@ -10,7 +10,16 @@
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
-#include <linux/udp.h>
+#include <netinet/udp.h>
+
+/* offsetof() is used in static asserts, and the libbpf-redefined CO-RE
+ * friendly version breaks compilation for older clang versions <= 15
+ * when invoked in a static assert.  Restore original here.
+ */
+#ifdef offsetof
+#undef offsetof
+#define offsetof(type, member) __builtin_offsetof(type, member)
+#endif
 
 struct gre_base_hdr {
 	uint16_t flags;
diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c b/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c
new file mode 100644
index 000000000000..dfd4a2710391
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c
@@ -0,0 +1,981 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+// Copyright (c) 2019, 2020 Cloudflare
+
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdint.h>
+#include <string.h>
+
+#include <linux/bpf.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/pkt_cls.h>
+#include <linux/tcp.h>
+#include <netinet/udp.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#include "test_cls_redirect.h"
+#include "bpf_kfuncs.h"
+
+#pragma GCC diagnostic ignored "-Waddress-of-packed-member"
+
+#define offsetofend(TYPE, MEMBER) \
+	(offsetof(TYPE, MEMBER) + sizeof((((TYPE *)0)->MEMBER)))
+
+#define IP_OFFSET_MASK (0x1FFF)
+#define IP_MF (0x2000)
+
+char _license[] SEC("license") = "Dual BSD/GPL";
+
+/**
+ * Destination port and IP used for UDP encapsulation.
+ */
+volatile const __be16 ENCAPSULATION_PORT;
+volatile const __be32 ENCAPSULATION_IP;
+
+typedef struct {
+	uint64_t processed_packets_total;
+	uint64_t l3_protocol_packets_total_ipv4;
+	uint64_t l3_protocol_packets_total_ipv6;
+	uint64_t l4_protocol_packets_total_tcp;
+	uint64_t l4_protocol_packets_total_udp;
+	uint64_t accepted_packets_total_syn;
+	uint64_t accepted_packets_total_syn_cookies;
+	uint64_t accepted_packets_total_last_hop;
+	uint64_t accepted_packets_total_icmp_echo_request;
+	uint64_t accepted_packets_total_established;
+	uint64_t forwarded_packets_total_gue;
+	uint64_t forwarded_packets_total_gre;
+
+	uint64_t errors_total_unknown_l3_proto;
+	uint64_t errors_total_unknown_l4_proto;
+	uint64_t errors_total_malformed_ip;
+	uint64_t errors_total_fragmented_ip;
+	uint64_t errors_total_malformed_icmp;
+	uint64_t errors_total_unwanted_icmp;
+	uint64_t errors_total_malformed_icmp_pkt_too_big;
+	uint64_t errors_total_malformed_tcp;
+	uint64_t errors_total_malformed_udp;
+	uint64_t errors_total_icmp_echo_replies;
+	uint64_t errors_total_malformed_encapsulation;
+	uint64_t errors_total_encap_adjust_failed;
+	uint64_t errors_total_encap_buffer_too_small;
+	uint64_t errors_total_redirect_loop;
+	uint64_t errors_total_encap_mtu_violate;
+} metrics_t;
+
+typedef enum {
+	INVALID = 0,
+	UNKNOWN,
+	ECHO_REQUEST,
+	SYN,
+	SYN_COOKIE,
+	ESTABLISHED,
+} verdict_t;
+
+typedef struct {
+	uint16_t src, dst;
+} flow_ports_t;
+
+_Static_assert(
+	sizeof(flow_ports_t) !=
+		offsetofend(struct bpf_sock_tuple, ipv4.dport) -
+			offsetof(struct bpf_sock_tuple, ipv4.sport) - 1,
+	"flow_ports_t must match sport and dport in struct bpf_sock_tuple");
+_Static_assert(
+	sizeof(flow_ports_t) !=
+		offsetofend(struct bpf_sock_tuple, ipv6.dport) -
+			offsetof(struct bpf_sock_tuple, ipv6.sport) - 1,
+	"flow_ports_t must match sport and dport in struct bpf_sock_tuple");
+
+struct iphdr_info {
+	void *hdr;
+	__u64 len;
+};
+
+typedef int ret_t;
+
+/* This is a bit of a hack. We need a return value which allows us to
+ * indicate that the regular flow of the program should continue,
+ * while allowing functions to use XDP_PASS and XDP_DROP, etc.
+ */
+static const ret_t CONTINUE_PROCESSING = -1;
+
+/* Convenience macro to call functions which return ret_t.
+ */
+#define MAYBE_RETURN(x)                           \
+	do {                                      \
+		ret_t __ret = x;                  \
+		if (__ret != CONTINUE_PROCESSING) \
+			return __ret;             \
+	} while (0)
+
+static bool ipv4_is_fragment(const struct iphdr *ip)
+{
+	uint16_t frag_off = ip->frag_off & bpf_htons(IP_OFFSET_MASK);
+	return (ip->frag_off & bpf_htons(IP_MF)) != 0 || frag_off > 0;
+}
+
+static int pkt_parse_ipv4(struct bpf_dynptr *dynptr, __u64 *offset, struct iphdr *iphdr)
+{
+	if (bpf_dynptr_read(iphdr, sizeof(*iphdr), dynptr, *offset, 0))
+		return -1;
+
+	*offset += sizeof(*iphdr);
+
+	if (iphdr->ihl < 5)
+		return -1;
+
+	/* skip ipv4 options */
+	*offset += (iphdr->ihl - 5) * 4;
+
+	return 0;
+}
+
+/* Parse the L4 ports from a packet, assuming a layout like TCP or UDP. */
+static bool pkt_parse_icmp_l4_ports(struct bpf_dynptr *dynptr, __u64 *offset, flow_ports_t *ports)
+{
+	if (bpf_dynptr_read(ports, sizeof(*ports), dynptr, *offset, 0))
+		return false;
+
+	*offset += sizeof(*ports);
+
+	/* Ports in the L4 headers are reversed, since we are parsing an ICMP
+	 * payload which is going towards the eyeball.
+	 */
+	uint16_t dst = ports->src;
+	ports->src = ports->dst;
+	ports->dst = dst;
+	return true;
+}
+
+static uint16_t pkt_checksum_fold(uint32_t csum)
+{
+	/* The highest reasonable value for an IPv4 header
+	 * checksum requires two folds, so we just do that always.
+	 */
+	csum = (csum & 0xffff) + (csum >> 16);
+	csum = (csum & 0xffff) + (csum >> 16);
+	return (uint16_t)~csum;
+}
+
+static void pkt_ipv4_checksum(struct iphdr *iph)
+{
+	iph->check = 0;
+
+	/* An IP header without options is 20 bytes. Two of those
+	 * are the checksum, which we always set to zero. Hence,
+	 * the maximum accumulated value is 18 / 2 * 0xffff = 0x8fff7,
+	 * which fits in 32 bit.
+	 */
+	_Static_assert(sizeof(struct iphdr) == 20, "iphdr must be 20 bytes");
+	uint32_t acc = 0;
+	uint16_t *ipw = (uint16_t *)iph;
+
+	for (size_t i = 0; i < sizeof(struct iphdr) / 2; i++)
+		acc += ipw[i];
+
+	iph->check = pkt_checksum_fold(acc);
+}
+
+static bool pkt_skip_ipv6_extension_headers(struct bpf_dynptr *dynptr, __u64 *offset,
+					    const struct ipv6hdr *ipv6, uint8_t *upper_proto,
+					    bool *is_fragment)
+{
+	/* We understand five extension headers.
+	 * https://tools.ietf.org/html/rfc8200#section-4.1 states that all
+	 * headers should occur once, except Destination Options, which may
+	 * occur twice. Hence we give up after 6 headers.
+	 */
+	struct {
+		uint8_t next;
+		uint8_t len;
+	} exthdr = {
+		.next = ipv6->nexthdr,
+	};
+	*is_fragment = false;
+
+	for (int i = 0; i < 6; i++) {
+		switch (exthdr.next) {
+		case IPPROTO_FRAGMENT:
+			*is_fragment = true;
+			/* NB: We don't check that hdrlen == 0 as per spec. */
+			/* fallthrough; */
+
+		case IPPROTO_HOPOPTS:
+		case IPPROTO_ROUTING:
+		case IPPROTO_DSTOPTS:
+		case IPPROTO_MH:
+			if (bpf_dynptr_read(&exthdr, sizeof(exthdr), dynptr, *offset, 0))
+				return false;
+
+			/* hdrlen is in 8-octet units, and excludes the first 8 octets. */
+			*offset += (exthdr.len + 1) * 8;
+
+			/* Decode next header */
+			break;
+
+		default:
+			/* The next header is not one of the known extension
+			 * headers, treat it as the upper layer header.
+			 *
+			 * This handles IPPROTO_NONE.
+			 *
+			 * Encapsulating Security Payload (50) and Authentication
+			 * Header (51) also end up here (and will trigger an
+			 * unknown proto error later). They have a custom header
+			 * format and seem too esoteric to care about.
+			 */
+			*upper_proto = exthdr.next;
+			return true;
+		}
+	}
+
+	/* We never found an upper layer header. */
+	return false;
+}
+
+static int pkt_parse_ipv6(struct bpf_dynptr *dynptr, __u64 *offset, struct ipv6hdr *ipv6,
+			  uint8_t *proto, bool *is_fragment)
+{
+	if (bpf_dynptr_read(ipv6, sizeof(*ipv6), dynptr, *offset, 0))
+		return -1;
+
+	*offset += sizeof(*ipv6);
+
+	if (!pkt_skip_ipv6_extension_headers(dynptr, offset, ipv6, proto, is_fragment))
+		return -1;
+
+	return 0;
+}
+
+/* Global metrics, per CPU
+ */
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, unsigned int);
+	__type(value, metrics_t);
+} metrics_map SEC(".maps");
+
+static metrics_t *get_global_metrics(void)
+{
+	uint64_t key = 0;
+	return bpf_map_lookup_elem(&metrics_map, &key);
+}
+
+static ret_t accept_locally(struct __sk_buff *skb, encap_headers_t *encap)
+{
+	const int payload_off =
+		sizeof(*encap) +
+		sizeof(struct in_addr) * encap->unigue.hop_count;
+	int32_t encap_overhead = payload_off - sizeof(struct ethhdr);
+
+	/* Changing the ethertype if the encapsulated packet is ipv6 */
+	if (encap->gue.proto_ctype == IPPROTO_IPV6)
+		encap->eth.h_proto = bpf_htons(ETH_P_IPV6);
+
+	if (bpf_skb_adjust_room(skb, -encap_overhead, BPF_ADJ_ROOM_MAC,
+				BPF_F_ADJ_ROOM_FIXED_GSO |
+				BPF_F_ADJ_ROOM_NO_CSUM_RESET) ||
+	    bpf_csum_level(skb, BPF_CSUM_LEVEL_DEC))
+		return TC_ACT_SHOT;
+
+	return bpf_redirect(skb->ifindex, BPF_F_INGRESS);
+}
+
+static ret_t forward_with_gre(struct __sk_buff *skb, struct bpf_dynptr *dynptr,
+			      encap_headers_t *encap, struct in_addr *next_hop,
+			      metrics_t *metrics)
+{
+	const int payload_off =
+		sizeof(*encap) +
+		sizeof(struct in_addr) * encap->unigue.hop_count;
+	int32_t encap_overhead =
+		payload_off - sizeof(struct ethhdr) - sizeof(struct iphdr);
+	int32_t delta = sizeof(struct gre_base_hdr) - encap_overhead;
+	__u8 encap_buffer[sizeof(encap_gre_t)] = {};
+	uint16_t proto = ETH_P_IP;
+	uint32_t mtu_len = 0;
+	encap_gre_t *encap_gre;
+
+	metrics->forwarded_packets_total_gre++;
+
+	/* Loop protection: the inner packet's TTL is decremented as a safeguard
+	 * against any forwarding loop. As the only interesting field is the TTL
+	 * hop limit for IPv6, it is easier to use bpf_skb_load_bytes/bpf_skb_store_bytes
+	 * as they handle the split packets if needed (no need for the data to be
+	 * in the linear section).
+	 */
+	if (encap->gue.proto_ctype == IPPROTO_IPV6) {
+		proto = ETH_P_IPV6;
+		uint8_t ttl;
+		int rc;
+
+		rc = bpf_skb_load_bytes(
+			skb, payload_off + offsetof(struct ipv6hdr, hop_limit),
+			&ttl, 1);
+		if (rc != 0) {
+			metrics->errors_total_malformed_encapsulation++;
+			return TC_ACT_SHOT;
+		}
+
+		if (ttl == 0) {
+			metrics->errors_total_redirect_loop++;
+			return TC_ACT_SHOT;
+		}
+
+		ttl--;
+		rc = bpf_skb_store_bytes(
+			skb, payload_off + offsetof(struct ipv6hdr, hop_limit),
+			&ttl, 1, 0);
+		if (rc != 0) {
+			metrics->errors_total_malformed_encapsulation++;
+			return TC_ACT_SHOT;
+		}
+	} else {
+		uint8_t ttl;
+		int rc;
+
+		rc = bpf_skb_load_bytes(
+			skb, payload_off + offsetof(struct iphdr, ttl), &ttl,
+			1);
+		if (rc != 0) {
+			metrics->errors_total_malformed_encapsulation++;
+			return TC_ACT_SHOT;
+		}
+
+		if (ttl == 0) {
+			metrics->errors_total_redirect_loop++;
+			return TC_ACT_SHOT;
+		}
+
+		/* IPv4 also has a checksum to patch. While the TTL is only one byte,
+		 * this function only works for 2 and 4 bytes arguments (the result is
+		 * the same).
+		 */
+		rc = bpf_l3_csum_replace(
+			skb, payload_off + offsetof(struct iphdr, check), ttl,
+			ttl - 1, 2);
+		if (rc != 0) {
+			metrics->errors_total_malformed_encapsulation++;
+			return TC_ACT_SHOT;
+		}
+
+		ttl--;
+		rc = bpf_skb_store_bytes(
+			skb, payload_off + offsetof(struct iphdr, ttl), &ttl, 1,
+			0);
+		if (rc != 0) {
+			metrics->errors_total_malformed_encapsulation++;
+			return TC_ACT_SHOT;
+		}
+	}
+
+	if (bpf_check_mtu(skb, skb->ifindex, &mtu_len, delta, 0)) {
+		metrics->errors_total_encap_mtu_violate++;
+		return TC_ACT_SHOT;
+	}
+
+	if (bpf_skb_adjust_room(skb, delta, BPF_ADJ_ROOM_NET,
+				BPF_F_ADJ_ROOM_FIXED_GSO |
+				BPF_F_ADJ_ROOM_NO_CSUM_RESET) ||
+	    bpf_csum_level(skb, BPF_CSUM_LEVEL_INC)) {
+		metrics->errors_total_encap_adjust_failed++;
+		return TC_ACT_SHOT;
+	}
+
+	if (bpf_skb_pull_data(skb, sizeof(encap_gre_t))) {
+		metrics->errors_total_encap_buffer_too_small++;
+		return TC_ACT_SHOT;
+	}
+
+	encap_gre = bpf_dynptr_slice_rdwr(dynptr, 0, encap_buffer, sizeof(encap_buffer));
+	if (!encap_gre) {
+		metrics->errors_total_encap_buffer_too_small++;
+		return TC_ACT_SHOT;
+	}
+
+	encap_gre->ip.protocol = IPPROTO_GRE;
+	encap_gre->ip.daddr = next_hop->s_addr;
+	encap_gre->ip.saddr = ENCAPSULATION_IP;
+	encap_gre->ip.tot_len =
+		bpf_htons(bpf_ntohs(encap_gre->ip.tot_len) + delta);
+	encap_gre->gre.flags = 0;
+	encap_gre->gre.protocol = bpf_htons(proto);
+	pkt_ipv4_checksum((void *)&encap_gre->ip);
+
+	if (encap_gre == encap_buffer)
+		bpf_dynptr_write(dynptr, 0, encap_buffer, sizeof(encap_buffer), 0);
+
+	return bpf_redirect(skb->ifindex, 0);
+}
+
+static ret_t forward_to_next_hop(struct __sk_buff *skb, struct bpf_dynptr *dynptr,
+				 encap_headers_t *encap, struct in_addr *next_hop,
+				 metrics_t *metrics)
+{
+	/* swap L2 addresses */
+	/* This assumes that packets are received from a router.
+	 * So just swapping the MAC addresses here will make the packet go back to
+	 * the router, which will send it to the appropriate machine.
+	 */
+	unsigned char temp[ETH_ALEN];
+	memcpy(temp, encap->eth.h_dest, sizeof(temp));
+	memcpy(encap->eth.h_dest, encap->eth.h_source,
+	       sizeof(encap->eth.h_dest));
+	memcpy(encap->eth.h_source, temp, sizeof(encap->eth.h_source));
+
+	if (encap->unigue.next_hop == encap->unigue.hop_count - 1 &&
+	    encap->unigue.last_hop_gre) {
+		return forward_with_gre(skb, dynptr, encap, next_hop, metrics);
+	}
+
+	metrics->forwarded_packets_total_gue++;
+	uint32_t old_saddr = encap->ip.saddr;
+	encap->ip.saddr = encap->ip.daddr;
+	encap->ip.daddr = next_hop->s_addr;
+	if (encap->unigue.next_hop < encap->unigue.hop_count) {
+		encap->unigue.next_hop++;
+	}
+
+	/* Remove ip->saddr, add next_hop->s_addr */
+	const uint64_t off = offsetof(typeof(*encap), ip.check);
+	int ret = bpf_l3_csum_replace(skb, off, old_saddr, next_hop->s_addr, 4);
+	if (ret < 0) {
+		return TC_ACT_SHOT;
+	}
+
+	return bpf_redirect(skb->ifindex, 0);
+}
+
+static ret_t skip_next_hops(__u64 *offset, int n)
+{
+	switch (n) {
+	case 1:
+		*offset += sizeof(struct in_addr);
+	case 0:
+		return CONTINUE_PROCESSING;
+
+	default:
+		return TC_ACT_SHOT;
+	}
+}
+
+/* Get the next hop from the GLB header.
+ *
+ * Sets next_hop->s_addr to 0 if there are no more hops left.
+ * pkt is positioned just after the variable length GLB header
+ * iff the call is successful.
+ */
+static ret_t get_next_hop(struct bpf_dynptr *dynptr, __u64 *offset, encap_headers_t *encap,
+			  struct in_addr *next_hop)
+{
+	if (encap->unigue.next_hop > encap->unigue.hop_count)
+		return TC_ACT_SHOT;
+
+	/* Skip "used" next hops. */
+	MAYBE_RETURN(skip_next_hops(offset, encap->unigue.next_hop));
+
+	if (encap->unigue.next_hop == encap->unigue.hop_count) {
+		/* No more next hops, we are at the end of the GLB header. */
+		next_hop->s_addr = 0;
+		return CONTINUE_PROCESSING;
+	}
+
+	if (bpf_dynptr_read(next_hop, sizeof(*next_hop), dynptr, *offset, 0))
+		return TC_ACT_SHOT;
+
+	*offset += sizeof(*next_hop);
+
+	/* Skip the remaining next hops (may be zero). */
+	return skip_next_hops(offset, encap->unigue.hop_count - encap->unigue.next_hop - 1);
+}
+
+/* Fill a bpf_sock_tuple to be used with the socket lookup functions.
+ * This is a kludge that let's us work around verifier limitations:
+ *
+ *    fill_tuple(&t, foo, sizeof(struct iphdr), 123, 321)
+ *
+ * clang will substitute a constant for sizeof, which allows the verifier
+ * to track it's value. Based on this, it can figure out the constant
+ * return value, and calling code works while still being "generic" to
+ * IPv4 and IPv6.
+ */
+static uint64_t fill_tuple(struct bpf_sock_tuple *tuple, void *iph,
+				    uint64_t iphlen, uint16_t sport, uint16_t dport)
+{
+	switch (iphlen) {
+	case sizeof(struct iphdr): {
+		struct iphdr *ipv4 = (struct iphdr *)iph;
+		tuple->ipv4.daddr = ipv4->daddr;
+		tuple->ipv4.saddr = ipv4->saddr;
+		tuple->ipv4.sport = sport;
+		tuple->ipv4.dport = dport;
+		return sizeof(tuple->ipv4);
+	}
+
+	case sizeof(struct ipv6hdr): {
+		struct ipv6hdr *ipv6 = (struct ipv6hdr *)iph;
+		memcpy(&tuple->ipv6.daddr, &ipv6->daddr,
+		       sizeof(tuple->ipv6.daddr));
+		memcpy(&tuple->ipv6.saddr, &ipv6->saddr,
+		       sizeof(tuple->ipv6.saddr));
+		tuple->ipv6.sport = sport;
+		tuple->ipv6.dport = dport;
+		return sizeof(tuple->ipv6);
+	}
+
+	default:
+		return 0;
+	}
+}
+
+static verdict_t classify_tcp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple,
+			      uint64_t tuplen, void *iph, struct tcphdr *tcp)
+{
+	struct bpf_sock *sk =
+		bpf_skc_lookup_tcp(skb, tuple, tuplen, BPF_F_CURRENT_NETNS, 0);
+
+	if (sk == NULL)
+		return UNKNOWN;
+
+	if (sk->state != BPF_TCP_LISTEN) {
+		bpf_sk_release(sk);
+		return ESTABLISHED;
+	}
+
+	if (iph != NULL && tcp != NULL) {
+		/* Kludge: we've run out of arguments, but need the length of the ip header. */
+		uint64_t iphlen = sizeof(struct iphdr);
+
+		if (tuplen == sizeof(tuple->ipv6))
+			iphlen = sizeof(struct ipv6hdr);
+
+		if (bpf_tcp_check_syncookie(sk, iph, iphlen, tcp,
+					    sizeof(*tcp)) == 0) {
+			bpf_sk_release(sk);
+			return SYN_COOKIE;
+		}
+	}
+
+	bpf_sk_release(sk);
+	return UNKNOWN;
+}
+
+static verdict_t classify_udp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, uint64_t tuplen)
+{
+	struct bpf_sock *sk =
+		bpf_sk_lookup_udp(skb, tuple, tuplen, BPF_F_CURRENT_NETNS, 0);
+
+	if (sk == NULL)
+		return UNKNOWN;
+
+	if (sk->state == BPF_TCP_ESTABLISHED) {
+		bpf_sk_release(sk);
+		return ESTABLISHED;
+	}
+
+	bpf_sk_release(sk);
+	return UNKNOWN;
+}
+
+static verdict_t classify_icmp(struct __sk_buff *skb, uint8_t proto, struct bpf_sock_tuple *tuple,
+			       uint64_t tuplen, metrics_t *metrics)
+{
+	switch (proto) {
+	case IPPROTO_TCP:
+		return classify_tcp(skb, tuple, tuplen, NULL, NULL);
+
+	case IPPROTO_UDP:
+		return classify_udp(skb, tuple, tuplen);
+
+	default:
+		metrics->errors_total_malformed_icmp++;
+		return INVALID;
+	}
+}
+
+static verdict_t process_icmpv4(struct __sk_buff *skb, struct bpf_dynptr *dynptr, __u64 *offset,
+				metrics_t *metrics)
+{
+	struct icmphdr icmp;
+	struct iphdr ipv4;
+
+	if (bpf_dynptr_read(&icmp, sizeof(icmp), dynptr, *offset, 0)) {
+		metrics->errors_total_malformed_icmp++;
+		return INVALID;
+	}
+
+	*offset += sizeof(icmp);
+
+	/* We should never receive encapsulated echo replies. */
+	if (icmp.type == ICMP_ECHOREPLY) {
+		metrics->errors_total_icmp_echo_replies++;
+		return INVALID;
+	}
+
+	if (icmp.type == ICMP_ECHO)
+		return ECHO_REQUEST;
+
+	if (icmp.type != ICMP_DEST_UNREACH || icmp.code != ICMP_FRAG_NEEDED) {
+		metrics->errors_total_unwanted_icmp++;
+		return INVALID;
+	}
+
+	if (pkt_parse_ipv4(dynptr, offset, &ipv4)) {
+		metrics->errors_total_malformed_icmp_pkt_too_big++;
+		return INVALID;
+	}
+
+	/* The source address in the outer IP header is from the entity that
+	 * originated the ICMP message. Use the original IP header to restore
+	 * the correct flow tuple.
+	 */
+	struct bpf_sock_tuple tuple;
+	tuple.ipv4.saddr = ipv4.daddr;
+	tuple.ipv4.daddr = ipv4.saddr;
+
+	if (!pkt_parse_icmp_l4_ports(dynptr, offset, (flow_ports_t *)&tuple.ipv4.sport)) {
+		metrics->errors_total_malformed_icmp_pkt_too_big++;
+		return INVALID;
+	}
+
+	return classify_icmp(skb, ipv4.protocol, &tuple,
+			     sizeof(tuple.ipv4), metrics);
+}
+
+static verdict_t process_icmpv6(struct bpf_dynptr *dynptr, __u64 *offset, struct __sk_buff *skb,
+				metrics_t *metrics)
+{
+	struct bpf_sock_tuple tuple;
+	struct ipv6hdr ipv6;
+	struct icmp6hdr icmp6;
+	bool is_fragment;
+	uint8_t l4_proto;
+
+	if (bpf_dynptr_read(&icmp6, sizeof(icmp6), dynptr, *offset, 0)) {
+		metrics->errors_total_malformed_icmp++;
+		return INVALID;
+	}
+
+	/* We should never receive encapsulated echo replies. */
+	if (icmp6.icmp6_type == ICMPV6_ECHO_REPLY) {
+		metrics->errors_total_icmp_echo_replies++;
+		return INVALID;
+	}
+
+	if (icmp6.icmp6_type == ICMPV6_ECHO_REQUEST) {
+		return ECHO_REQUEST;
+	}
+
+	if (icmp6.icmp6_type != ICMPV6_PKT_TOOBIG) {
+		metrics->errors_total_unwanted_icmp++;
+		return INVALID;
+	}
+
+	if (pkt_parse_ipv6(dynptr, offset, &ipv6, &l4_proto, &is_fragment)) {
+		metrics->errors_total_malformed_icmp_pkt_too_big++;
+		return INVALID;
+	}
+
+	if (is_fragment) {
+		metrics->errors_total_fragmented_ip++;
+		return INVALID;
+	}
+
+	/* Swap source and dest addresses. */
+	memcpy(&tuple.ipv6.saddr, &ipv6.daddr, sizeof(tuple.ipv6.saddr));
+	memcpy(&tuple.ipv6.daddr, &ipv6.saddr, sizeof(tuple.ipv6.daddr));
+
+	if (!pkt_parse_icmp_l4_ports(dynptr, offset, (flow_ports_t *)&tuple.ipv6.sport)) {
+		metrics->errors_total_malformed_icmp_pkt_too_big++;
+		return INVALID;
+	}
+
+	return classify_icmp(skb, l4_proto, &tuple, sizeof(tuple.ipv6),
+			     metrics);
+}
+
+static verdict_t process_tcp(struct bpf_dynptr *dynptr, __u64 *offset, struct __sk_buff *skb,
+			     struct iphdr_info *info, metrics_t *metrics)
+{
+	struct bpf_sock_tuple tuple;
+	struct tcphdr tcp;
+	uint64_t tuplen;
+
+	metrics->l4_protocol_packets_total_tcp++;
+
+	if (bpf_dynptr_read(&tcp, sizeof(tcp), dynptr, *offset, 0)) {
+		metrics->errors_total_malformed_tcp++;
+		return INVALID;
+	}
+
+	*offset += sizeof(tcp);
+
+	if (tcp.syn)
+		return SYN;
+
+	tuplen = fill_tuple(&tuple, info->hdr, info->len, tcp.source, tcp.dest);
+	return classify_tcp(skb, &tuple, tuplen, info->hdr, &tcp);
+}
+
+static verdict_t process_udp(struct bpf_dynptr *dynptr, __u64 *offset, struct __sk_buff *skb,
+			     struct iphdr_info *info, metrics_t *metrics)
+{
+	struct bpf_sock_tuple tuple;
+	struct udphdr udph;
+	uint64_t tuplen;
+
+	metrics->l4_protocol_packets_total_udp++;
+
+	if (bpf_dynptr_read(&udph, sizeof(udph), dynptr, *offset, 0)) {
+		metrics->errors_total_malformed_udp++;
+		return INVALID;
+	}
+	*offset += sizeof(udph);
+
+	tuplen = fill_tuple(&tuple, info->hdr, info->len, udph.source, udph.dest);
+	return classify_udp(skb, &tuple, tuplen);
+}
+
+static verdict_t process_ipv4(struct __sk_buff *skb, struct bpf_dynptr *dynptr,
+			      __u64 *offset, metrics_t *metrics)
+{
+	struct iphdr ipv4;
+	struct iphdr_info info = {
+		.hdr = &ipv4,
+		.len = sizeof(ipv4),
+	};
+
+	metrics->l3_protocol_packets_total_ipv4++;
+
+	if (pkt_parse_ipv4(dynptr, offset, &ipv4)) {
+		metrics->errors_total_malformed_ip++;
+		return INVALID;
+	}
+
+	if (ipv4.version != 4) {
+		metrics->errors_total_malformed_ip++;
+		return INVALID;
+	}
+
+	if (ipv4_is_fragment(&ipv4)) {
+		metrics->errors_total_fragmented_ip++;
+		return INVALID;
+	}
+
+	switch (ipv4.protocol) {
+	case IPPROTO_ICMP:
+		return process_icmpv4(skb, dynptr, offset, metrics);
+
+	case IPPROTO_TCP:
+		return process_tcp(dynptr, offset, skb, &info, metrics);
+
+	case IPPROTO_UDP:
+		return process_udp(dynptr, offset, skb, &info, metrics);
+
+	default:
+		metrics->errors_total_unknown_l4_proto++;
+		return INVALID;
+	}
+}
+
+static verdict_t process_ipv6(struct __sk_buff *skb, struct bpf_dynptr *dynptr,
+			      __u64 *offset, metrics_t *metrics)
+{
+	struct ipv6hdr ipv6;
+	struct iphdr_info info = {
+		.hdr = &ipv6,
+		.len = sizeof(ipv6),
+	};
+	uint8_t l4_proto;
+	bool is_fragment;
+
+	metrics->l3_protocol_packets_total_ipv6++;
+
+	if (pkt_parse_ipv6(dynptr, offset, &ipv6, &l4_proto, &is_fragment)) {
+		metrics->errors_total_malformed_ip++;
+		return INVALID;
+	}
+
+	if (ipv6.version != 6) {
+		metrics->errors_total_malformed_ip++;
+		return INVALID;
+	}
+
+	if (is_fragment) {
+		metrics->errors_total_fragmented_ip++;
+		return INVALID;
+	}
+
+	switch (l4_proto) {
+	case IPPROTO_ICMPV6:
+		return process_icmpv6(dynptr, offset, skb, metrics);
+
+	case IPPROTO_TCP:
+		return process_tcp(dynptr, offset, skb, &info, metrics);
+
+	case IPPROTO_UDP:
+		return process_udp(dynptr, offset, skb, &info, metrics);
+
+	default:
+		metrics->errors_total_unknown_l4_proto++;
+		return INVALID;
+	}
+}
+
+SEC("tc")
+int cls_redirect(struct __sk_buff *skb)
+{
+	__u8 encap_buffer[sizeof(encap_headers_t)] = {};
+	struct bpf_dynptr dynptr;
+	struct in_addr next_hop;
+	/* Tracks offset of the dynptr. This will be unnecessary once
+	 * bpf_dynptr_advance() is available.
+	 */
+	__u64 off = 0;
+	ret_t ret;
+
+	bpf_dynptr_from_skb(skb, 0, &dynptr);
+
+	metrics_t *metrics = get_global_metrics();
+	if (metrics == NULL)
+		return TC_ACT_SHOT;
+
+	metrics->processed_packets_total++;
+
+	/* Pass bogus packets as long as we're not sure they're
+	 * destined for us.
+	 */
+	if (skb->protocol != bpf_htons(ETH_P_IP))
+		return TC_ACT_OK;
+
+	encap_headers_t *encap;
+
+	/* Make sure that all encapsulation headers are available in
+	 * the linear portion of the skb. This makes it easy to manipulate them.
+	 */
+	if (bpf_skb_pull_data(skb, sizeof(*encap)))
+		return TC_ACT_OK;
+
+	encap = bpf_dynptr_slice_rdwr(&dynptr, 0, encap_buffer, sizeof(encap_buffer));
+	if (!encap)
+		return TC_ACT_OK;
+
+	off += sizeof(*encap);
+
+	if (encap->ip.ihl != 5)
+		/* We never have any options. */
+		return TC_ACT_OK;
+
+	if (encap->ip.daddr != ENCAPSULATION_IP ||
+	    encap->ip.protocol != IPPROTO_UDP)
+		return TC_ACT_OK;
+
+	/* TODO Check UDP length? */
+	if (encap->udp.dest != ENCAPSULATION_PORT)
+		return TC_ACT_OK;
+
+	/* We now know that the packet is destined to us, we can
+	 * drop bogus ones.
+	 */
+	if (ipv4_is_fragment((void *)&encap->ip)) {
+		metrics->errors_total_fragmented_ip++;
+		return TC_ACT_SHOT;
+	}
+
+	if (encap->gue.variant != 0) {
+		metrics->errors_total_malformed_encapsulation++;
+		return TC_ACT_SHOT;
+	}
+
+	if (encap->gue.control != 0) {
+		metrics->errors_total_malformed_encapsulation++;
+		return TC_ACT_SHOT;
+	}
+
+	if (encap->gue.flags != 0) {
+		metrics->errors_total_malformed_encapsulation++;
+		return TC_ACT_SHOT;
+	}
+
+	if (encap->gue.hlen !=
+	    sizeof(encap->unigue) / 4 + encap->unigue.hop_count) {
+		metrics->errors_total_malformed_encapsulation++;
+		return TC_ACT_SHOT;
+	}
+
+	if (encap->unigue.version != 0) {
+		metrics->errors_total_malformed_encapsulation++;
+		return TC_ACT_SHOT;
+	}
+
+	if (encap->unigue.reserved != 0)
+		return TC_ACT_SHOT;
+
+	MAYBE_RETURN(get_next_hop(&dynptr, &off, encap, &next_hop));
+
+	if (next_hop.s_addr == 0) {
+		metrics->accepted_packets_total_last_hop++;
+		return accept_locally(skb, encap);
+	}
+
+	verdict_t verdict;
+	switch (encap->gue.proto_ctype) {
+	case IPPROTO_IPIP:
+		verdict = process_ipv4(skb, &dynptr, &off, metrics);
+		break;
+
+	case IPPROTO_IPV6:
+		verdict = process_ipv6(skb, &dynptr, &off, metrics);
+		break;
+
+	default:
+		metrics->errors_total_unknown_l3_proto++;
+		return TC_ACT_SHOT;
+	}
+
+	switch (verdict) {
+	case INVALID:
+		/* metrics have already been bumped */
+		return TC_ACT_SHOT;
+
+	case UNKNOWN:
+		return forward_to_next_hop(skb, &dynptr, encap, &next_hop, metrics);
+
+	case ECHO_REQUEST:
+		metrics->accepted_packets_total_icmp_echo_request++;
+		break;
+
+	case SYN:
+		if (encap->unigue.forward_syn) {
+			return forward_to_next_hop(skb, &dynptr, encap, &next_hop,
+						   metrics);
+		}
+
+		metrics->accepted_packets_total_syn++;
+		break;
+
+	case SYN_COOKIE:
+		metrics->accepted_packets_total_syn_cookies++;
+		break;
+
+	case ESTABLISHED:
+		metrics->accepted_packets_total_established++;
+		break;
+	}
+
+	ret = accept_locally(skb, encap);
+
+	if (encap == encap_buffer)
+		bpf_dynptr_write(&dynptr, 0, encap_buffer, sizeof(encap_buffer), 0);
+
+	return ret;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_core_read_macros.c b/tools/testing/selftests/bpf/progs/test_core_read_macros.c
index fd54caa17319..873d85a4739b 100644
--- a/tools/testing/selftests/bpf/progs/test_core_read_macros.c
+++ b/tools/testing/selftests/bpf/progs/test_core_read_macros.c
@@ -36,7 +36,7 @@ int handler(void *ctx)
 		return 0;
 
 	/* next pointers for kernel address space have to be initialized from
-	 * BPF side, user-space mmaped addresses are stil user-space addresses
+	 * BPF side, user-space mmaped addresses are still user-space addresses
 	 */
 	k_probe_in.next = &k_probe_in;
 	__builtin_preserve_access_index(({k_core_in.next = &k_core_in;}));
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c
index 51b3f79df523..448403634eea 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_arrays.c
@@ -15,6 +15,7 @@ struct {
 
 struct core_reloc_arrays_output {
 	int a2;
+	int a3;
 	char b123;
 	int c1c;
 	int d00d;
@@ -41,6 +42,7 @@ int test_core_arrays(void *ctx)
 {
 	struct core_reloc_arrays *in = (void *)&data.in;
 	struct core_reloc_arrays_output *out = (void *)&data.out;
+	int *a;
 
 	if (CORE_READ(&out->a2, &in->a[2]))
 		return 1;
@@ -53,6 +55,9 @@ int test_core_arrays(void *ctx)
 	if (CORE_READ(&out->f01c, &in->f[0][1].c))
 		return 1;
 
+	a = __builtin_preserve_access_index(({ in->a; }));
+	out->a3 = a[0] + a[1] + a[2] + a[3];
+
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c
index ab1e647aeb31..b86fdda2a6ea 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_bitfields_probed.c
@@ -42,7 +42,6 @@ int test_core_bitfields(void *ctx)
 {
 	struct core_reloc_bitfields *in = (void *)&data.in;
 	struct core_reloc_bitfields_output *out = (void *)&data.out;
-	uint64_t res;
 
 	out->ub1 = BPF_CORE_READ_BITFIELD_PROBED(in, ub1);
 	out->ub2 = BPF_CORE_READ_BITFIELD_PROBED(in, ub2);
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c
index a17dd83eae67..ee4a601dcb06 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_kernel.c
@@ -53,7 +53,7 @@ int test_core_kernel(void *ctx)
 	struct task_struct *task = (void *)bpf_get_current_task();
 	struct core_reloc_kernel_output *out = (void *)&data.out;
 	uint64_t pid_tgid = bpf_get_current_pid_tgid();
-	uint32_t real_tgid = (uint32_t)pid_tgid;
+	int32_t real_tgid = (int32_t)pid_tgid;
 	int pid, tgid;
 
 	if (data.my_pid_tgid != pid_tgid)
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_module.c b/tools/testing/selftests/bpf/progs/test_core_reloc_module.c
index f59f175c7baf..bcb31ff92dcc 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_module.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_module.c
@@ -43,8 +43,8 @@ int BPF_PROG(test_core_module_probed,
 #if __has_builtin(__builtin_preserve_enum_value)
 	struct core_reloc_module_output *out = (void *)&data.out;
 	__u64 pid_tgid = bpf_get_current_pid_tgid();
-	__u32 real_tgid = (__u32)(pid_tgid >> 32);
-	__u32 real_pid = (__u32)pid_tgid;
+	__s32 real_tgid = (__s32)(pid_tgid >> 32);
+	__s32 real_pid = (__s32)pid_tgid;
 
 	if (data.my_pid_tgid != pid_tgid)
 		return 0;
@@ -77,8 +77,8 @@ int BPF_PROG(test_core_module_direct,
 #if __has_builtin(__builtin_preserve_enum_value)
 	struct core_reloc_module_output *out = (void *)&data.out;
 	__u64 pid_tgid = bpf_get_current_pid_tgid();
-	__u32 real_tgid = (__u32)(pid_tgid >> 32);
-	__u32 real_pid = (__u32)pid_tgid;
+	__s32 real_tgid = (__s32)(pid_tgid >> 32);
+	__s32 real_pid = (__s32)pid_tgid;
 
 	if (data.my_pid_tgid != pid_tgid)
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_type_id.c b/tools/testing/selftests/bpf/progs/test_core_reloc_type_id.c
index 22aba3f6e344..6fc8b9d66e34 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_type_id.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_type_id.c
@@ -80,7 +80,7 @@ int test_core_type_id(void *ctx)
 	 * to detect whether this test has to be executed, however strange
 	 * that might look like.
 	 *
-	 *   [0] https://reviews.llvm.org/D85174
+	 *   [0] https://github.com/llvm/llvm-project/commit/00602ee7ef0bf6c68d690a2bd729c12b95c95c99
 	 */
 #if __has_builtin(__builtin_preserve_type_info)
 	struct core_reloc_type_id_output *out = (void *)&data.out;
diff --git a/tools/testing/selftests/bpf/progs/test_deny_namespace.c b/tools/testing/selftests/bpf/progs/test_deny_namespace.c
index 09ad5a4ebd1f..e96b901a733c 100644
--- a/tools/testing/selftests/bpf/progs/test_deny_namespace.c
+++ b/tools/testing/selftests/bpf/progs/test_deny_namespace.c
@@ -5,12 +5,10 @@
 #include <errno.h>
 #include <linux/capability.h>
 
-struct kernel_cap_struct {
-	__u32 cap[_LINUX_CAPABILITY_U32S_3];
-} __attribute__((preserve_access_index));
+typedef struct { unsigned long long val; } kernel_cap_t;
 
 struct cred {
-	struct kernel_cap_struct cap_effective;
+	kernel_cap_t cap_effective;
 } __attribute__((preserve_access_index));
 
 char _license[] SEC("license") = "GPL";
@@ -18,15 +16,14 @@ char _license[] SEC("license") = "GPL";
 SEC("lsm.s/userns_create")
 int BPF_PROG(test_userns_create, const struct cred *cred, int ret)
 {
-	struct kernel_cap_struct caps = cred->cap_effective;
-	int cap_index = CAP_TO_INDEX(CAP_SYS_ADMIN);
-	__u32 cap_mask = CAP_TO_MASK(CAP_SYS_ADMIN);
+	kernel_cap_t caps = cred->cap_effective;
+	__u64 cap_mask = 1ULL << CAP_SYS_ADMIN;
 
 	if (ret)
 		return 0;
 
 	ret = -EPERM;
-	if (caps.cap[cap_index] & cap_mask)
+	if (caps.val & cap_mask)
 		return 0;
 
 	return -EPERM;
diff --git a/tools/testing/selftests/bpf/progs/test_fill_link_info.c b/tools/testing/selftests/bpf/progs/test_fill_link_info.c
new file mode 100644
index 000000000000..fac33a14f200
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_fill_link_info.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+#include <stdbool.h>
+
+extern bool CONFIG_X86_KERNEL_IBT __kconfig __weak;
+extern bool CONFIG_PPC_FTRACE_OUT_OF_LINE __kconfig __weak;
+extern bool CONFIG_KPROBES_ON_FTRACE __kconfig __weak;
+extern bool CONFIG_PPC64 __kconfig __weak;
+
+/* This function is here to have CONFIG_X86_KERNEL_IBT,
+ * CONFIG_PPC_FTRACE_OUT_OF_LINE, CONFIG_KPROBES_ON_FTRACE,
+ * CONFIG_PPC6 used and added to object BTF.
+ */
+int unused(void)
+{
+	return CONFIG_X86_KERNEL_IBT ||
+			CONFIG_PPC_FTRACE_OUT_OF_LINE ||
+			CONFIG_KPROBES_ON_FTRACE ||
+			CONFIG_PPC64 ? 0 : 1;
+}
+
+SEC("kprobe")
+int BPF_PROG(kprobe_run)
+{
+	return 0;
+}
+
+SEC("uprobe")
+int BPF_PROG(uprobe_run)
+{
+	return 0;
+}
+
+SEC("tracepoint")
+int BPF_PROG(tp_run)
+{
+	return 0;
+}
+
+SEC("perf_event")
+int event_run(void *ctx)
+{
+	return 0;
+}
+
+SEC("kprobe.multi")
+int BPF_PROG(kmulti_run)
+{
+	return 0;
+}
+
+SEC("uprobe.multi")
+int BPF_PROG(umulti_run)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_fsverity.c b/tools/testing/selftests/bpf/progs/test_fsverity.c
new file mode 100644
index 000000000000..9e0f73e8189c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_fsverity.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_kfuncs.h"
+
+char _license[] SEC("license") = "GPL";
+
+#ifndef SHA256_DIGEST_SIZE
+#define SHA256_DIGEST_SIZE      32
+#endif
+
+#define SIZEOF_STRUCT_FSVERITY_DIGEST 4  /* sizeof(struct fsverity_digest) */
+
+char expected_digest[SIZEOF_STRUCT_FSVERITY_DIGEST + SHA256_DIGEST_SIZE];
+char digest[SIZEOF_STRUCT_FSVERITY_DIGEST + SHA256_DIGEST_SIZE];
+__u32 monitored_pid;
+__u32 got_fsverity;
+__u32 digest_matches;
+
+SEC("lsm.s/file_open")
+int BPF_PROG(test_file_open, struct file *f)
+{
+	struct bpf_dynptr digest_ptr;
+	__u32 pid;
+	int ret;
+	int i;
+
+	pid = bpf_get_current_pid_tgid() >> 32;
+	if (pid != monitored_pid)
+		return 0;
+
+	bpf_dynptr_from_mem(digest, sizeof(digest), 0, &digest_ptr);
+	ret = bpf_get_fsverity_digest(f, &digest_ptr);
+	if (ret < 0)
+		return 0;
+	got_fsverity = 1;
+
+	for (i = 0; i < (int)sizeof(digest); i++) {
+		if (digest[i] != expected_digest[i])
+			return 0;
+	}
+
+	digest_matches = 1;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_get_xattr.c b/tools/testing/selftests/bpf/progs/test_get_xattr.c
new file mode 100644
index 000000000000..54305f4c9f2d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_get_xattr.c
@@ -0,0 +1,84 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_kfuncs.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+__u32 monitored_pid;
+__u32 found_xattr_from_file;
+__u32 found_xattr_from_dentry;
+
+static const char expected_value[] = "hello";
+char value1[32];
+char value2[32];
+
+/* Matches caller of test_get_xattr() in prog_tests/fs_kfuncs.c */
+static const char xattr_names[][64] = {
+	/* The following work. */
+	"user.kfuncs",
+	"security.bpf.xxx",
+
+	/* The following do not work. */
+	"security.bpf",
+	"security.selinux"
+};
+
+SEC("lsm.s/file_open")
+int BPF_PROG(test_file_open, struct file *f)
+{
+	struct bpf_dynptr value_ptr;
+	__u32 pid;
+	int ret, i;
+
+	pid = bpf_get_current_pid_tgid() >> 32;
+	if (pid != monitored_pid)
+		return 0;
+
+	bpf_dynptr_from_mem(value1, sizeof(value1), 0, &value_ptr);
+
+	for (i = 0; i < ARRAY_SIZE(xattr_names); i++) {
+		ret = bpf_get_file_xattr(f, xattr_names[i], &value_ptr);
+		if (ret == sizeof(expected_value))
+			break;
+	}
+	if (ret != sizeof(expected_value))
+		return 0;
+	if (bpf_strncmp(value1, ret, expected_value))
+		return 0;
+	found_xattr_from_file = 1;
+	return 0;
+}
+
+SEC("lsm.s/inode_getxattr")
+int BPF_PROG(test_inode_getxattr, struct dentry *dentry, char *name)
+{
+	struct bpf_dynptr value_ptr;
+	__u32 pid;
+	int ret, i;
+
+	pid = bpf_get_current_pid_tgid() >> 32;
+	if (pid != monitored_pid)
+		return 0;
+
+	bpf_dynptr_from_mem(value2, sizeof(value2), 0, &value_ptr);
+
+	for (i = 0; i < ARRAY_SIZE(xattr_names); i++) {
+		ret = bpf_get_dentry_xattr(dentry, xattr_names[i], &value_ptr);
+		if (ret == sizeof(expected_value))
+			break;
+	}
+	if (ret != sizeof(expected_value))
+		return 0;
+	if (bpf_strncmp(value2, ret, expected_value))
+		return 0;
+	found_xattr_from_dentry = 1;
+
+	/* return non-zero to fail getxattr from user space */
+	return -EINVAL;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_func1.c b/tools/testing/selftests/bpf/progs/test_global_func1.c
index 7b42dad187b8..fc69ff18880d 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func1.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func1.c
@@ -3,14 +3,15 @@
 #include <stddef.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
 
-#ifndef MAX_STACK
-#define MAX_STACK (512 - 3 * 32 + 8)
-#endif
+#define MAX_STACK 260
 
 static __attribute__ ((noinline))
 int f0(int var, struct __sk_buff *skb)
 {
+	asm volatile ("");
+
 	return skb->len;
 }
 
@@ -19,6 +20,8 @@ int f1(struct __sk_buff *skb)
 {
 	volatile char buf[MAX_STACK] = {};
 
+	__sink(buf[MAX_STACK - 1]);
+
 	return f0(0, skb) + skb->len;
 }
 
@@ -27,6 +30,10 @@ int f3(int, struct __sk_buff *skb, int);
 __attribute__ ((noinline))
 int f2(int val, struct __sk_buff *skb)
 {
+	volatile char buf[MAX_STACK] = {};
+
+	__sink(buf[MAX_STACK - 1]);
+
 	return f1(skb) + f3(val, skb, 1);
 }
 
@@ -35,11 +42,14 @@ int f3(int val, struct __sk_buff *skb, int var)
 {
 	volatile char buf[MAX_STACK] = {};
 
+	__sink(buf[MAX_STACK - 1]);
+
 	return skb->ifindex * val * var;
 }
 
 SEC("tc")
-int test_cls(struct __sk_buff *skb)
+__failure __msg("combined stack size of 3 calls is")
+int global_func1(struct __sk_buff *skb)
 {
 	return f0(1, skb) + f1(skb) + f2(2, skb) + f3(3, skb, 4);
 }
diff --git a/tools/testing/selftests/bpf/progs/test_global_func10.c b/tools/testing/selftests/bpf/progs/test_global_func10.c
index 97b7031d0e22..09d027bd3ea8 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func10.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func10.c
@@ -2,14 +2,19 @@
 #include <stddef.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#if !defined(__clang__)
+#pragma GCC diagnostic ignored "-Wmaybe-uninitialized"
+#endif
 
 struct Small {
-	int x;
+	long x;
 };
 
 struct Big {
-	int x;
-	int y;
+	long x;
+	long y;
 };
 
 __noinline int foo(const struct Big *big)
@@ -21,7 +26,8 @@ __noinline int foo(const struct Big *big)
 }
 
 SEC("cgroup_skb/ingress")
-int test_cls(struct __sk_buff *skb)
+__failure __msg("invalid read from stack")
+int global_func10(struct __sk_buff *skb)
 {
 	const struct Small small = {.x = skb->len };
 
diff --git a/tools/testing/selftests/bpf/progs/test_global_func11.c b/tools/testing/selftests/bpf/progs/test_global_func11.c
index ef5277d982d9..283e036dc401 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func11.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func11.c
@@ -2,6 +2,7 @@
 #include <stddef.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
 
 struct S {
 	int x;
@@ -13,7 +14,8 @@ __noinline int foo(const struct S *s)
 }
 
 SEC("cgroup_skb/ingress")
-int test_cls(struct __sk_buff *skb)
+__failure __msg("Caller passes invalid args into func#1")
+int global_func11(struct __sk_buff *skb)
 {
 	return foo((const void *)skb);
 }
diff --git a/tools/testing/selftests/bpf/progs/test_global_func12.c b/tools/testing/selftests/bpf/progs/test_global_func12.c
index 62343527cc59..6e03d42519a6 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func12.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func12.c
@@ -2,6 +2,7 @@
 #include <stddef.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
 
 struct S {
 	int x;
@@ -13,9 +14,12 @@ __noinline int foo(const struct S *s)
 }
 
 SEC("cgroup_skb/ingress")
-int test_cls(struct __sk_buff *skb)
+__failure __msg("invalid mem access 'mem_or_null'")
+int global_func12(struct __sk_buff *skb)
 {
 	const struct S s = {.x = skb->len };
 
-	return foo(&s);
+	foo(&s);
+
+	return 1;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_global_func13.c b/tools/testing/selftests/bpf/progs/test_global_func13.c
index ff8897c1ac22..02ea80da75b5 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func13.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func13.c
@@ -2,6 +2,7 @@
 #include <stddef.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
 
 struct S {
 	int x;
@@ -16,7 +17,8 @@ __noinline int foo(const struct S *s)
 }
 
 SEC("cgroup_skb/ingress")
-int test_cls(struct __sk_buff *skb)
+__failure __msg("Caller passes invalid args into func#1")
+int global_func13(struct __sk_buff *skb)
 {
 	const struct S *s = (const struct S *)(0xbedabeda);
 
diff --git a/tools/testing/selftests/bpf/progs/test_global_func14.c b/tools/testing/selftests/bpf/progs/test_global_func14.c
index 698c77199ebf..33b7d5efd7b2 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func14.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func14.c
@@ -2,6 +2,7 @@
 #include <stddef.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
 
 struct S;
 
@@ -14,7 +15,8 @@ __noinline int foo(const struct S *s)
 }
 
 SEC("cgroup_skb/ingress")
-int test_cls(struct __sk_buff *skb)
+__failure __msg("reference type('FWD S') size cannot be determined")
+int global_func14(struct __sk_buff *skb)
 {
 
 	return foo(NULL);
diff --git a/tools/testing/selftests/bpf/progs/test_global_func15.c b/tools/testing/selftests/bpf/progs/test_global_func15.c
index c19c435988d5..201cc000b3f4 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func15.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func15.c
@@ -2,6 +2,7 @@
 #include <stddef.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
 
 __noinline int foo(unsigned int *v)
 {
@@ -12,7 +13,8 @@ __noinline int foo(unsigned int *v)
 }
 
 SEC("cgroup_skb/ingress")
-int test_cls(struct __sk_buff *skb)
+__failure __msg("At program exit the register R0 has ")
+int global_func15(struct __sk_buff *skb)
 {
 	unsigned int v = 1;
 
@@ -20,3 +22,35 @@ int test_cls(struct __sk_buff *skb)
 
 	return v;
 }
+
+SEC("cgroup_skb/ingress")
+__log_level(2) __flag(BPF_F_TEST_STATE_FREQ)
+__failure
+/* check that fallthrough code path marks r0 as precise */
+__msg("mark_precise: frame0: regs=r0 stack= before 2: (b7) r0 = 1")
+/* check that branch code path marks r0 as precise */
+__msg("mark_precise: frame0: regs=r0 stack= before 0: (85) call bpf_get_prandom_u32#7")
+__msg("At program exit the register R0 has ")
+__naked int global_func15_tricky_pruning(void)
+{
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+		"if r0 s> 1000 goto 1f;"
+		"r0 = 1;"
+	"1:"
+		"goto +0;" /* checkpoint */
+		/* cgroup_skb/ingress program is expected to return [0, 1]
+		 * values, so branch above makes sure that in a fallthrough
+		 * case we have a valid 1 stored in R0 register, but in
+		 * a branch case we assign some random value to R0.  So if
+		 * there is something wrong with precision tracking for R0 at
+		 * program exit, we might erroneously prune branch case,
+		 * because R0 in fallthrough case is imprecise (and thus any
+		 * value is valid from POV of verifier is_state_equal() logic)
+		 */
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32)
+		: __clobber_common
+	);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_func16.c b/tools/testing/selftests/bpf/progs/test_global_func16.c
index 0312d1e8d8c0..e3e64bc472cd 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func16.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func16.c
@@ -2,6 +2,7 @@
 #include <stddef.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
 
 __noinline int foo(int (*arr)[10])
 {
@@ -12,7 +13,8 @@ __noinline int foo(int (*arr)[10])
 }
 
 SEC("cgroup_skb/ingress")
-int test_cls(struct __sk_buff *skb)
+__success
+int global_func16(struct __sk_buff *skb)
 {
 	int array[10];
 
diff --git a/tools/testing/selftests/bpf/progs/test_global_func17.c b/tools/testing/selftests/bpf/progs/test_global_func17.c
index 2b8b9b8ba018..5de44b09e8ec 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func17.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func17.c
@@ -1,16 +1,19 @@
 // SPDX-License-Identifier: GPL-2.0-only
 #include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
 
 __noinline int foo(int *p)
 {
+	barrier_var(p);
 	return p ? (*p = 42) : 0;
 }
 
 const volatile int i;
 
 SEC("tc")
-int test_cls(struct __sk_buff *skb)
+__failure __msg("Caller passes invalid args into func#1")
+int global_func17(struct __sk_buff *skb)
 {
 	return foo((int *)&i);
 }
diff --git a/tools/testing/selftests/bpf/progs/test_global_func2.c b/tools/testing/selftests/bpf/progs/test_global_func2.c
index 2c18d82923a2..2beab9c3b68a 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func2.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func2.c
@@ -1,4 +1,49 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2020 Facebook */
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
 #define MAX_STACK (512 - 3 * 32)
-#include "test_global_func1.c"
+
+static __attribute__ ((noinline))
+int f0(int var, struct __sk_buff *skb)
+{
+	return skb->len;
+}
+
+__attribute__ ((noinline))
+int f1(struct __sk_buff *skb)
+{
+	volatile char buf[MAX_STACK] = {};
+
+	__sink(buf[MAX_STACK - 1]);
+
+	return f0(0, skb) + skb->len;
+}
+
+int f3(int, struct __sk_buff *skb, int);
+
+__attribute__ ((noinline))
+int f2(int val, struct __sk_buff *skb)
+{
+	return f1(skb) + f3(val, skb, 1);
+}
+
+__attribute__ ((noinline))
+int f3(int val, struct __sk_buff *skb, int var)
+{
+	volatile char buf[MAX_STACK] = {};
+
+	__sink(buf[MAX_STACK - 1]);
+
+	return skb->ifindex * val * var;
+}
+
+SEC("tc")
+__success
+int global_func2(struct __sk_buff *skb)
+{
+	return f0(1, skb) + f1(skb) + f2(2, skb) + f3(3, skb, 4);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_func3.c b/tools/testing/selftests/bpf/progs/test_global_func3.c
index 01bf8275dfd6..142b682d3c2f 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func3.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func3.c
@@ -3,6 +3,7 @@
 #include <stddef.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
 
 __attribute__ ((noinline))
 int f1(struct __sk_buff *skb)
@@ -46,20 +47,15 @@ int f7(struct __sk_buff *skb)
 	return f6(skb);
 }
 
-#ifndef NO_FN8
 __attribute__ ((noinline))
 int f8(struct __sk_buff *skb)
 {
 	return f7(skb);
 }
-#endif
 
 SEC("tc")
-int test_cls(struct __sk_buff *skb)
+__failure __msg("the call stack of 8 frames")
+int global_func3(struct __sk_buff *skb)
 {
-#ifndef NO_FN8
 	return f8(skb);
-#else
-	return f7(skb);
-#endif
 }
diff --git a/tools/testing/selftests/bpf/progs/test_global_func4.c b/tools/testing/selftests/bpf/progs/test_global_func4.c
index 610f75edf276..1733d87ad3f3 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func4.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func4.c
@@ -1,4 +1,55 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2020 Facebook */
-#define NO_FN8
-#include "test_global_func3.c"
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+__attribute__ ((noinline))
+int f1(struct __sk_buff *skb)
+{
+	return skb->len;
+}
+
+__attribute__ ((noinline))
+int f2(int val, struct __sk_buff *skb)
+{
+	return f1(skb) + val;
+}
+
+__attribute__ ((noinline))
+int f3(int val, struct __sk_buff *skb, int var)
+{
+	return f2(var, skb) + val;
+}
+
+__attribute__ ((noinline))
+int f4(struct __sk_buff *skb)
+{
+	return f3(1, skb, 2);
+}
+
+__attribute__ ((noinline))
+int f5(struct __sk_buff *skb)
+{
+	return f4(skb);
+}
+
+__attribute__ ((noinline))
+int f6(struct __sk_buff *skb)
+{
+	return f5(skb);
+}
+
+__attribute__ ((noinline))
+int f7(struct __sk_buff *skb)
+{
+	return f6(skb);
+}
+
+SEC("tc")
+__success
+int global_func4(struct __sk_buff *skb)
+{
+	return f7(skb);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_func5.c b/tools/testing/selftests/bpf/progs/test_global_func5.c
index 9248d03e0d06..257c0569ff98 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func5.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func5.c
@@ -3,6 +3,7 @@
 #include <stddef.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
 
 __attribute__ ((noinline))
 int f1(struct __sk_buff *skb)
@@ -25,7 +26,8 @@ int f3(int val, struct __sk_buff *skb)
 }
 
 SEC("tc")
-int test_cls(struct __sk_buff *skb)
+__failure __msg("expects pointer to ctx")
+int global_func5(struct __sk_buff *skb)
 {
 	return f1(skb) + f2(2, skb) + f3(3, skb);
 }
diff --git a/tools/testing/selftests/bpf/progs/test_global_func6.c b/tools/testing/selftests/bpf/progs/test_global_func6.c
index af8c78bdfb25..46c38c8f2cf0 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func6.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func6.c
@@ -3,6 +3,7 @@
 #include <stddef.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
 
 __attribute__ ((noinline))
 int f1(struct __sk_buff *skb)
@@ -25,7 +26,8 @@ int f3(int val, struct __sk_buff *skb)
 }
 
 SEC("tc")
-int test_cls(struct __sk_buff *skb)
+__failure __msg("modified ctx ptr R2")
+int global_func6(struct __sk_buff *skb)
 {
 	return f1(skb) + f2(2, skb) + f3(3, skb);
 }
diff --git a/tools/testing/selftests/bpf/progs/test_global_func7.c b/tools/testing/selftests/bpf/progs/test_global_func7.c
index 6cb8e2f5254c..f182febfde3c 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func7.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func7.c
@@ -3,6 +3,7 @@
 #include <stddef.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
 
 __attribute__ ((noinline))
 void foo(struct __sk_buff *skb)
@@ -11,7 +12,8 @@ void foo(struct __sk_buff *skb)
 }
 
 SEC("tc")
-int test_cls(struct __sk_buff *skb)
+__failure __msg("foo() doesn't return scalar")
+int global_func7(struct __sk_buff *skb)
 {
 	foo(skb);
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_global_func8.c b/tools/testing/selftests/bpf/progs/test_global_func8.c
index d55a6544b1ab..9b9c57fa2dd3 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func8.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func8.c
@@ -3,6 +3,7 @@
 #include <stddef.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
 
 __noinline int foo(struct __sk_buff *skb)
 {
@@ -10,7 +11,8 @@ __noinline int foo(struct __sk_buff *skb)
 }
 
 SEC("cgroup_skb/ingress")
-int test_cls(struct __sk_buff *skb)
+__success
+int global_func8(struct __sk_buff *skb)
 {
 	if (!foo(skb))
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_global_func9.c b/tools/testing/selftests/bpf/progs/test_global_func9.c
index bd233ddede98..1f2cb0159b8d 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func9.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func9.c
@@ -2,6 +2,7 @@
 #include <stddef.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
 
 struct S {
 	int x;
@@ -74,7 +75,8 @@ __noinline int quuz(int **p)
 }
 
 SEC("cgroup_skb/ingress")
-int test_cls(struct __sk_buff *skb)
+__success
+int global_func9(struct __sk_buff *skb)
 {
 	int result = 0;
 
diff --git a/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c b/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c
new file mode 100644
index 000000000000..143c8a4852bf
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_global_func_ctx_args.c
@@ -0,0 +1,172 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+static long stack[256];
+
+/*
+ * KPROBE contexts
+ */
+
+__weak int kprobe_typedef_ctx_subprog(bpf_user_pt_regs_t *ctx)
+{
+	return bpf_get_stack(ctx, &stack, sizeof(stack), 0);
+}
+
+SEC("?kprobe")
+__success
+int kprobe_typedef_ctx(void *ctx)
+{
+	return kprobe_typedef_ctx_subprog(ctx);
+}
+
+/* s390x defines:
+ *
+ * typedef user_pt_regs bpf_user_pt_regs_t;
+ * typedef struct { ... } user_pt_regs;
+ *
+ * And so "canonical" underlying struct type is anonymous.
+ * So on s390x only valid ways to have PTR_TO_CTX argument in global subprogs
+ * are:
+ *   - bpf_user_pt_regs_t *ctx (typedef);
+ *   - struct bpf_user_pt_regs_t *ctx (backwards compatible struct hack);
+ *   - void *ctx __arg_ctx (arg:ctx tag)
+ *
+ * Other architectures also allow using underlying struct types (e.g.,
+ * `struct pt_regs *ctx` for x86-64)
+ */
+#ifndef bpf_target_s390
+
+#define pt_regs_struct_t typeof(*(__PT_REGS_CAST((struct pt_regs *)NULL)))
+
+__weak int kprobe_struct_ctx_subprog(pt_regs_struct_t *ctx)
+{
+	return bpf_get_stack((void *)ctx, &stack, sizeof(stack), 0);
+}
+
+SEC("?kprobe")
+__success
+int kprobe_resolved_ctx(void *ctx)
+{
+	return kprobe_struct_ctx_subprog(ctx);
+}
+
+#endif
+
+/* this is current hack to make this work on old kernels */
+struct bpf_user_pt_regs_t {};
+
+__weak int kprobe_workaround_ctx_subprog(struct bpf_user_pt_regs_t *ctx)
+{
+	return bpf_get_stack(ctx, &stack, sizeof(stack), 0);
+}
+
+SEC("?kprobe")
+__success
+int kprobe_workaround_ctx(void *ctx)
+{
+	return kprobe_workaround_ctx_subprog(ctx);
+}
+
+/*
+ * RAW_TRACEPOINT contexts
+ */
+
+__weak int raw_tp_ctx_subprog(struct bpf_raw_tracepoint_args *ctx)
+{
+	return bpf_get_stack(ctx, &stack, sizeof(stack), 0);
+}
+
+SEC("?raw_tp")
+__success
+int raw_tp_ctx(void *ctx)
+{
+	return raw_tp_ctx_subprog(ctx);
+}
+
+/*
+ * RAW_TRACEPOINT_WRITABLE contexts
+ */
+
+__weak int raw_tp_writable_ctx_subprog(struct bpf_raw_tracepoint_args *ctx)
+{
+	return bpf_get_stack(ctx, &stack, sizeof(stack), 0);
+}
+
+SEC("?raw_tp")
+__success
+int raw_tp_writable_ctx(void *ctx)
+{
+	return raw_tp_writable_ctx_subprog(ctx);
+}
+
+/*
+ * PERF_EVENT contexts
+ */
+
+__weak int perf_event_ctx_subprog(struct bpf_perf_event_data *ctx)
+{
+	return bpf_get_stack(ctx, &stack, sizeof(stack), 0);
+}
+
+SEC("?perf_event")
+__success
+int perf_event_ctx(void *ctx)
+{
+	return perf_event_ctx_subprog(ctx);
+}
+
+/* this global subprog can be now called from many types of entry progs, each
+ * with different context type
+ */
+__weak int subprog_ctx_tag(void *ctx __arg_ctx)
+{
+	return bpf_get_stack(ctx, stack, sizeof(stack), 0);
+}
+
+struct my_struct { int x; };
+
+__weak int subprog_multi_ctx_tags(void *ctx1 __arg_ctx,
+				  struct my_struct *mem,
+				  void *ctx2 __arg_ctx)
+{
+	if (!mem)
+		return 0;
+
+	return bpf_get_stack(ctx1, stack, sizeof(stack), 0) +
+	       mem->x +
+	       bpf_get_stack(ctx2, stack, sizeof(stack), 0);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+int arg_tag_ctx_raw_tp(void *ctx)
+{
+	struct my_struct x = { .x = 123 };
+
+	return subprog_ctx_tag(ctx) + subprog_multi_ctx_tags(ctx, &x, ctx);
+}
+
+SEC("?perf_event")
+__success __log_level(2)
+int arg_tag_ctx_perf(void *ctx)
+{
+	struct my_struct x = { .x = 123 };
+
+	return subprog_ctx_tag(ctx) + subprog_multi_ctx_tags(ctx, &x, ctx);
+}
+
+SEC("?kprobe")
+__success __log_level(2)
+int arg_tag_ctx_kprobe(void *ctx)
+{
+	struct my_struct x = { .x = 123 };
+
+	return subprog_ctx_tag(ctx) + subprog_multi_ctx_tags(ctx, &x, ctx);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_map_resize.c b/tools/testing/selftests/bpf/progs/test_global_map_resize.c
new file mode 100644
index 000000000000..ee65bad0436d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_global_map_resize.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+/* rodata section */
+const volatile pid_t pid;
+const volatile size_t bss_array_len;
+const volatile size_t data_array_len;
+
+/* bss section */
+int sum = 0;
+int array[1];
+
+/* custom data section */
+int my_array[1] SEC(".data.custom");
+
+/* custom data section which should NOT be resizable,
+ * since it contains a single var which is not an array
+ */
+int my_int SEC(".data.non_array");
+
+/* custom data section which should NOT be resizable,
+ * since its last var is not an array
+ */
+int my_array_first[1] SEC(".data.array_not_last");
+int my_int_last SEC(".data.array_not_last");
+
+int percpu_arr[1] SEC(".data.percpu_arr");
+
+/* at least one extern is included, to ensure that a specific
+ * regression is tested whereby resizing resulted in a free-after-use
+ * bug after type information is invalidated by the resize operation.
+ *
+ * There isn't a particularly good API to test for this specific condition,
+ * but by having externs for the resizing tests it will cover this path.
+ */
+extern int LINUX_KERNEL_VERSION __kconfig;
+long version_sink;
+
+SEC("tp/syscalls/sys_enter_getpid")
+int bss_array_sum(void *ctx)
+{
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	/* this will be zero, we just rely on verifier not rejecting this */
+	sum = percpu_arr[bpf_get_smp_processor_id()];
+
+	for (size_t i = 0; i < bss_array_len; ++i)
+		sum += array[i];
+
+	/* see above; ensure this is not optimized out */
+	version_sink = LINUX_KERNEL_VERSION;
+
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_getuid")
+int data_array_sum(void *ctx)
+{
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	/* this will be zero, we just rely on verifier not rejecting this */
+	sum = percpu_arr[bpf_get_smp_processor_id()];
+
+	for (size_t i = 0; i < data_array_len; ++i)
+		sum += my_array[i];
+
+	/* see above; ensure this is not optimized out */
+	version_sink = LINUX_KERNEL_VERSION;
+
+	return 0;
+}
+
+SEC("struct_ops/test_1")
+int BPF_PROG(test_1)
+{
+	return 0;
+}
+
+struct bpf_testmod_ops {
+	int (*test_1)(void);
+};
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops st_ops_resize = {
+	.test_1 = (void *)test_1
+};
diff --git a/tools/testing/selftests/bpf/progs/test_hash_large_key.c b/tools/testing/selftests/bpf/progs/test_hash_large_key.c
index 473a22794a62..8b438128f46b 100644
--- a/tools/testing/selftests/bpf/progs/test_hash_large_key.c
+++ b/tools/testing/selftests/bpf/progs/test_hash_large_key.c
@@ -28,7 +28,7 @@ struct bigelement {
 SEC("raw_tracepoint/sys_enter")
 int bpf_hash_large_key_test(void *ctx)
 {
-	int zero = 0, err = 1, value = 42;
+	int zero = 0, value = 42;
 	struct bigelement *key;
 
 	key = bpf_map_lookup_elem(&key_map, &zero);
diff --git a/tools/testing/selftests/bpf/progs/test_jhash.h b/tools/testing/selftests/bpf/progs/test_jhash.h
index c300734d26f6..ef53559bbbdf 100644
--- a/tools/testing/selftests/bpf/progs/test_jhash.h
+++ b/tools/testing/selftests/bpf/progs/test_jhash.h
@@ -69,3 +69,34 @@ u32 jhash(const void *key, u32 length, u32 initval)
 
 	return c;
 }
+
+static __always_inline u32 jhash2(const u32 *k, u32 length, u32 initval)
+{
+	u32 a, b, c;
+
+	/* Set up the internal state */
+	a = b = c = JHASH_INITVAL + (length<<2) + initval;
+
+	/* Handle most of the key */
+	while (length > 3) {
+		a += k[0];
+		b += k[1];
+		c += k[2];
+		__jhash_mix(a, b, c);
+		length -= 3;
+		k += 3;
+	}
+
+	/* Handle the last 3 u32's */
+	switch (length) {
+	case 3: c += k[2];
+	case 2: b += k[1];
+	case 1: a += k[0];
+		__jhash_final(a, b, c);
+		break;
+	case 0:	/* Nothing left to add */
+		break;
+	}
+
+	return c;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_kernel_flag.c b/tools/testing/selftests/bpf/progs/test_kernel_flag.c
new file mode 100644
index 000000000000..b45fab3be352
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_kernel_flag.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (C) 2025 Microsoft Corporation
+ *
+ * Author: Blaise Boscaccy <bboscaccy@linux.microsoft.com>
+ */
+
+#include "vmlinux.h"
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u32 monitored_tid;
+
+SEC("lsm.s/bpf")
+int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
+{
+	__u32 tid;
+
+	tid = bpf_get_current_pid_tgid() & 0xFFFFFFFF;
+	if (!kernel || tid != monitored_tid)
+		return 0;
+	else
+		return -EINVAL;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c
index f4a8250329b2..061befb004c2 100644
--- a/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c
+++ b/tools/testing/selftests/bpf/progs/test_kfunc_dynptr_param.c
@@ -10,6 +10,7 @@
 #include <errno.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
 
 extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym;
 extern void bpf_key_put(struct bpf_key *key) __ksym;
@@ -19,6 +20,7 @@ extern int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_ptr,
 
 struct {
 	__uint(type, BPF_MAP_TYPE_RINGBUF);
+	__uint(max_entries, 4096);
 } ringbuf SEC(".maps");
 
 struct {
@@ -33,7 +35,8 @@ int err, pid;
 char _license[] SEC("license") = "GPL";
 
 SEC("?lsm.s/bpf")
-int BPF_PROG(not_valid_dynptr, int cmd, union bpf_attr *attr, unsigned int size)
+__failure __msg("cannot pass in dynptr at an offset=-8")
+int BPF_PROG(not_valid_dynptr, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
 {
 	unsigned long val;
 
@@ -42,16 +45,17 @@ int BPF_PROG(not_valid_dynptr, int cmd, union bpf_attr *attr, unsigned int size)
 }
 
 SEC("?lsm.s/bpf")
-int BPF_PROG(not_ptr_to_stack, int cmd, union bpf_attr *attr, unsigned int size)
+__failure __msg("arg#0 expected pointer to stack or const struct bpf_dynptr")
+int BPF_PROG(not_ptr_to_stack, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
 {
-	unsigned long val;
+	unsigned long val = 0;
 
 	return bpf_verify_pkcs7_signature((struct bpf_dynptr *)val,
 					  (struct bpf_dynptr *)val, NULL);
 }
 
 SEC("lsm.s/bpf")
-int BPF_PROG(dynptr_data_null, int cmd, union bpf_attr *attr, unsigned int size)
+int BPF_PROG(dynptr_data_null, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
 {
 	struct bpf_key *trusted_keyring;
 	struct bpf_dynptr ptr;
diff --git a/tools/testing/selftests/bpf/progs/test_kfunc_param_nullable.c b/tools/testing/selftests/bpf/progs/test_kfunc_param_nullable.c
new file mode 100644
index 000000000000..0ad1bf1ede8d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_kfunc_param_nullable.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "bpf_kfuncs.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+SEC("tc")
+int kfunc_dynptr_nullable_test1(struct __sk_buff *skb)
+{
+	struct bpf_dynptr data;
+
+	bpf_dynptr_from_skb(skb, 0, &data);
+	bpf_kfunc_dynptr_test(&data, NULL);
+
+	return 0;
+}
+
+SEC("tc")
+int kfunc_dynptr_nullable_test2(struct __sk_buff *skb)
+{
+	struct bpf_dynptr data;
+
+	bpf_dynptr_from_skb(skb, 0, &data);
+	bpf_kfunc_dynptr_test(&data, &data);
+
+	return 0;
+}
+
+SEC("tc")
+__failure __msg("expected pointer to stack or const struct bpf_dynptr")
+int kfunc_dynptr_nullable_test3(struct __sk_buff *skb)
+{
+	struct bpf_dynptr data;
+
+	bpf_dynptr_from_skb(skb, 0, &data);
+	bpf_kfunc_dynptr_test(NULL, &data);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_ksyms_btf_write_check.c b/tools/testing/selftests/bpf/progs/test_ksyms_btf_write_check.c
index a72a5bf3812a..27109b877714 100644
--- a/tools/testing/selftests/bpf/progs/test_ksyms_btf_write_check.c
+++ b/tools/testing/selftests/bpf/progs/test_ksyms_btf_write_check.c
@@ -35,7 +35,6 @@ SEC("raw_tp/sys_enter")
 int handler2(const void *ctx)
 {
 	int *active;
-	__u32 cpu;
 
 	active = bpf_this_cpu_ptr(&bpf_prog_active);
 	write_active(active);
diff --git a/tools/testing/selftests/bpf/progs/test_ksyms_weak.c b/tools/testing/selftests/bpf/progs/test_ksyms_weak.c
index 5f8379aadb29..d00268c91e19 100644
--- a/tools/testing/selftests/bpf/progs/test_ksyms_weak.c
+++ b/tools/testing/selftests/bpf/progs/test_ksyms_weak.c
@@ -20,6 +20,8 @@ __u64 out__non_existent_typed = -1;
 /* test existing weak symbols can be resolved. */
 extern const struct rq runqueues __ksym __weak; /* typed */
 extern const void bpf_prog_active __ksym __weak; /* typeless */
+struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym __weak;
+void bpf_testmod_test_mod_kfunc(int i) __ksym __weak;
 
 
 /* non-existent weak symbols. */
@@ -29,6 +31,7 @@ extern const void bpf_link_fops1 __ksym __weak;
 
 /* typed symbols, default to zero. */
 extern const int bpf_link_fops2 __ksym __weak;
+void invalid_kfunc(void) __ksym __weak;
 
 SEC("raw_tp/sys_enter")
 int pass_handler(const void *ctx)
@@ -37,7 +40,7 @@ int pass_handler(const void *ctx)
 
 	/* tests existing symbols. */
 	rq = (struct rq *)bpf_per_cpu_ptr(&runqueues, 0);
-	if (rq)
+	if (rq && bpf_ksym_exists(&runqueues))
 		out__existing_typed = rq->cpu;
 	out__existing_typeless = (__u64)&bpf_prog_active;
 
@@ -50,6 +53,18 @@ int pass_handler(const void *ctx)
 	if (&bpf_link_fops2) /* can't happen */
 		out__non_existent_typed = (__u64)bpf_per_cpu_ptr(&bpf_link_fops2, 0);
 
+	if (!bpf_ksym_exists(bpf_task_acquire))
+		/* dead code won't be seen by the verifier */
+		bpf_task_acquire(0);
+
+	if (!bpf_ksym_exists(bpf_testmod_test_mod_kfunc))
+		/* dead code won't be seen by the verifier */
+		bpf_testmod_test_mod_kfunc(0);
+
+	if (bpf_ksym_exists(invalid_kfunc))
+		/* dead code won't be seen by the verifier */
+		invalid_kfunc();
+
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_l4lb_noinline_dynptr.c b/tools/testing/selftests/bpf/progs/test_l4lb_noinline_dynptr.c
new file mode 100644
index 000000000000..f997f5080748
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_l4lb_noinline_dynptr.c
@@ -0,0 +1,487 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2017 Facebook
+#include <stddef.h>
+#include <stdbool.h>
+#include <string.h>
+#include <linux/pkt_cls.h>
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <bpf/bpf_helpers.h>
+#include "test_iptunnel_common.h"
+#include <bpf/bpf_endian.h>
+
+#include "bpf_kfuncs.h"
+
+static __always_inline __u32 rol32(__u32 word, unsigned int shift)
+{
+	return (word << shift) | (word >> ((-shift) & 31));
+}
+
+/* copy paste of jhash from kernel sources to make sure llvm
+ * can compile it into valid sequence of bpf instructions
+ */
+#define __jhash_mix(a, b, c)			\
+{						\
+	a -= c;  a ^= rol32(c, 4);  c += b;	\
+	b -= a;  b ^= rol32(a, 6);  a += c;	\
+	c -= b;  c ^= rol32(b, 8);  b += a;	\
+	a -= c;  a ^= rol32(c, 16); c += b;	\
+	b -= a;  b ^= rol32(a, 19); a += c;	\
+	c -= b;  c ^= rol32(b, 4);  b += a;	\
+}
+
+#define __jhash_final(a, b, c)			\
+{						\
+	c ^= b; c -= rol32(b, 14);		\
+	a ^= c; a -= rol32(c, 11);		\
+	b ^= a; b -= rol32(a, 25);		\
+	c ^= b; c -= rol32(b, 16);		\
+	a ^= c; a -= rol32(c, 4);		\
+	b ^= a; b -= rol32(a, 14);		\
+	c ^= b; c -= rol32(b, 24);		\
+}
+
+#define JHASH_INITVAL		0xdeadbeef
+
+typedef unsigned int u32;
+
+static __noinline u32 jhash(const void *key, u32 length, u32 initval)
+{
+	u32 a, b, c;
+	const unsigned char *k = key;
+
+	a = b = c = JHASH_INITVAL + length + initval;
+
+	while (length > 12) {
+		a += *(u32 *)(k);
+		b += *(u32 *)(k + 4);
+		c += *(u32 *)(k + 8);
+		__jhash_mix(a, b, c);
+		length -= 12;
+		k += 12;
+	}
+	switch (length) {
+	case 12: c += (u32)k[11]<<24;
+	case 11: c += (u32)k[10]<<16;
+	case 10: c += (u32)k[9]<<8;
+	case 9:  c += k[8];
+	case 8:  b += (u32)k[7]<<24;
+	case 7:  b += (u32)k[6]<<16;
+	case 6:  b += (u32)k[5]<<8;
+	case 5:  b += k[4];
+	case 4:  a += (u32)k[3]<<24;
+	case 3:  a += (u32)k[2]<<16;
+	case 2:  a += (u32)k[1]<<8;
+	case 1:  a += k[0];
+		 __jhash_final(a, b, c);
+	case 0: /* Nothing left to add */
+		break;
+	}
+
+	return c;
+}
+
+static __noinline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval)
+{
+	a += initval;
+	b += initval;
+	c += initval;
+	__jhash_final(a, b, c);
+	return c;
+}
+
+static __noinline u32 jhash_2words(u32 a, u32 b, u32 initval)
+{
+	return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2));
+}
+
+#define PCKT_FRAGMENTED 65343
+#define IPV4_HDR_LEN_NO_OPT 20
+#define IPV4_PLUS_ICMP_HDR 28
+#define IPV6_PLUS_ICMP_HDR 48
+#define RING_SIZE 2
+#define MAX_VIPS 12
+#define MAX_REALS 5
+#define CTL_MAP_SIZE 16
+#define CH_RINGS_SIZE (MAX_VIPS * RING_SIZE)
+#define F_IPV6 (1 << 0)
+#define F_HASH_NO_SRC_PORT (1 << 0)
+#define F_ICMP (1 << 0)
+#define F_SYN_SET (1 << 1)
+
+struct packet_description {
+	union {
+		__be32 src;
+		__be32 srcv6[4];
+	};
+	union {
+		__be32 dst;
+		__be32 dstv6[4];
+	};
+	union {
+		__u32 ports;
+		__u16 port16[2];
+	};
+	__u8 proto;
+	__u8 flags;
+};
+
+struct ctl_value {
+	union {
+		__u64 value;
+		__u32 ifindex;
+		__u8 mac[6];
+	};
+};
+
+struct vip_meta {
+	__u32 flags;
+	__u32 vip_num;
+};
+
+struct real_definition {
+	union {
+		__be32 dst;
+		__be32 dstv6[4];
+	};
+	__u8 flags;
+};
+
+struct vip_stats {
+	__u64 bytes;
+	__u64 pkts;
+};
+
+struct eth_hdr {
+	unsigned char eth_dest[ETH_ALEN];
+	unsigned char eth_source[ETH_ALEN];
+	unsigned short eth_proto;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, MAX_VIPS);
+	__type(key, struct vip);
+	__type(value, struct vip_meta);
+} vip_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, CH_RINGS_SIZE);
+	__type(key, __u32);
+	__type(value, __u32);
+} ch_rings SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, MAX_REALS);
+	__type(key, __u32);
+	__type(value, struct real_definition);
+} reals SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, MAX_VIPS);
+	__type(key, __u32);
+	__type(value, struct vip_stats);
+} stats SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, CTL_MAP_SIZE);
+	__type(key, __u32);
+	__type(value, struct ctl_value);
+} ctl_array SEC(".maps");
+
+static __noinline __u32 get_packet_hash(struct packet_description *pckt, bool ipv6)
+{
+	if (ipv6)
+		return jhash_2words(jhash(pckt->srcv6, 16, MAX_VIPS),
+				    pckt->ports, CH_RINGS_SIZE);
+	else
+		return jhash_2words(pckt->src, pckt->ports, CH_RINGS_SIZE);
+}
+
+static __noinline bool get_packet_dst(struct real_definition **real,
+				      struct packet_description *pckt,
+				      struct vip_meta *vip_info,
+				      bool is_ipv6)
+{
+	__u32 hash = get_packet_hash(pckt, is_ipv6);
+	__u32 key = RING_SIZE * vip_info->vip_num + hash % RING_SIZE;
+	__u32 *real_pos;
+
+	if (hash != 0x358459b7 /* jhash of ipv4 packet */  &&
+	    hash != 0x2f4bc6bb /* jhash of ipv6 packet */)
+		return false;
+
+	real_pos = bpf_map_lookup_elem(&ch_rings, &key);
+	if (!real_pos)
+		return false;
+	key = *real_pos;
+	*real = bpf_map_lookup_elem(&reals, &key);
+	if (!(*real))
+		return false;
+	return true;
+}
+
+static __noinline int parse_icmpv6(struct bpf_dynptr *skb_ptr, __u64 off,
+				   struct packet_description *pckt)
+{
+	__u8 buffer[sizeof(struct ipv6hdr)] = {};
+	struct icmp6hdr *icmp_hdr;
+	struct ipv6hdr *ip6h;
+
+	icmp_hdr = bpf_dynptr_slice(skb_ptr, off, buffer, sizeof(buffer));
+	if (!icmp_hdr)
+		return TC_ACT_SHOT;
+
+	if (icmp_hdr->icmp6_type != ICMPV6_PKT_TOOBIG)
+		return TC_ACT_OK;
+	off += sizeof(struct icmp6hdr);
+	ip6h = bpf_dynptr_slice(skb_ptr, off, buffer, sizeof(buffer));
+	if (!ip6h)
+		return TC_ACT_SHOT;
+	pckt->proto = ip6h->nexthdr;
+	pckt->flags |= F_ICMP;
+	memcpy(pckt->srcv6, ip6h->daddr.s6_addr32, 16);
+	memcpy(pckt->dstv6, ip6h->saddr.s6_addr32, 16);
+	return TC_ACT_UNSPEC;
+}
+
+static __noinline int parse_icmp(struct bpf_dynptr *skb_ptr, __u64 off,
+				 struct packet_description *pckt)
+{
+	__u8 buffer_icmp[sizeof(struct iphdr)] = {};
+	__u8 buffer_ip[sizeof(struct iphdr)] = {};
+	struct icmphdr *icmp_hdr;
+	struct iphdr *iph;
+
+	icmp_hdr = bpf_dynptr_slice(skb_ptr, off, buffer_icmp, sizeof(buffer_icmp));
+	if (!icmp_hdr)
+		return TC_ACT_SHOT;
+	if (icmp_hdr->type != ICMP_DEST_UNREACH ||
+	    icmp_hdr->code != ICMP_FRAG_NEEDED)
+		return TC_ACT_OK;
+	off += sizeof(struct icmphdr);
+	iph = bpf_dynptr_slice(skb_ptr, off, buffer_ip, sizeof(buffer_ip));
+	if (!iph || iph->ihl != 5)
+		return TC_ACT_SHOT;
+	pckt->proto = iph->protocol;
+	pckt->flags |= F_ICMP;
+	pckt->src = iph->daddr;
+	pckt->dst = iph->saddr;
+	return TC_ACT_UNSPEC;
+}
+
+static __noinline bool parse_udp(struct bpf_dynptr *skb_ptr, __u64 off,
+				 struct packet_description *pckt)
+{
+	__u8 buffer[sizeof(struct udphdr)] = {};
+	struct udphdr *udp;
+
+	udp = bpf_dynptr_slice(skb_ptr, off, buffer, sizeof(buffer));
+	if (!udp)
+		return false;
+
+	if (!(pckt->flags & F_ICMP)) {
+		pckt->port16[0] = udp->source;
+		pckt->port16[1] = udp->dest;
+	} else {
+		pckt->port16[0] = udp->dest;
+		pckt->port16[1] = udp->source;
+	}
+	return true;
+}
+
+static __noinline bool parse_tcp(struct bpf_dynptr *skb_ptr, __u64 off,
+				 struct packet_description *pckt)
+{
+	__u8 buffer[sizeof(struct tcphdr)] = {};
+	struct tcphdr *tcp;
+
+	tcp = bpf_dynptr_slice(skb_ptr, off, buffer, sizeof(buffer));
+	if (!tcp)
+		return false;
+
+	if (tcp->syn)
+		pckt->flags |= F_SYN_SET;
+
+	if (!(pckt->flags & F_ICMP)) {
+		pckt->port16[0] = tcp->source;
+		pckt->port16[1] = tcp->dest;
+	} else {
+		pckt->port16[0] = tcp->dest;
+		pckt->port16[1] = tcp->source;
+	}
+	return true;
+}
+
+static __noinline int process_packet(struct bpf_dynptr *skb_ptr,
+				     struct eth_hdr *eth, __u64 off,
+				     bool is_ipv6, struct __sk_buff *skb)
+{
+	struct packet_description pckt = {};
+	struct bpf_tunnel_key tkey = {};
+	struct vip_stats *data_stats;
+	struct real_definition *dst;
+	struct vip_meta *vip_info;
+	struct ctl_value *cval;
+	__u32 v4_intf_pos = 1;
+	__u32 v6_intf_pos = 2;
+	struct ipv6hdr *ip6h;
+	struct vip vip = {};
+	struct iphdr *iph;
+	int tun_flag = 0;
+	__u16 pkt_bytes;
+	__u64 iph_len;
+	__u32 ifindex;
+	__u8 protocol;
+	__u32 vip_num;
+	int action;
+
+	tkey.tunnel_ttl = 64;
+	if (is_ipv6) {
+		__u8 buffer[sizeof(struct ipv6hdr)] = {};
+
+		ip6h = bpf_dynptr_slice(skb_ptr, off, buffer, sizeof(buffer));
+		if (!ip6h)
+			return TC_ACT_SHOT;
+
+		iph_len = sizeof(struct ipv6hdr);
+		protocol = ip6h->nexthdr;
+		pckt.proto = protocol;
+		pkt_bytes = bpf_ntohs(ip6h->payload_len);
+		off += iph_len;
+		if (protocol == IPPROTO_FRAGMENT) {
+			return TC_ACT_SHOT;
+		} else if (protocol == IPPROTO_ICMPV6) {
+			action = parse_icmpv6(skb_ptr, off, &pckt);
+			if (action >= 0)
+				return action;
+			off += IPV6_PLUS_ICMP_HDR;
+		} else {
+			memcpy(pckt.srcv6, ip6h->saddr.s6_addr32, 16);
+			memcpy(pckt.dstv6, ip6h->daddr.s6_addr32, 16);
+		}
+	} else {
+		__u8 buffer[sizeof(struct iphdr)] = {};
+
+		iph = bpf_dynptr_slice(skb_ptr, off, buffer, sizeof(buffer));
+		if (!iph || iph->ihl != 5)
+			return TC_ACT_SHOT;
+
+		protocol = iph->protocol;
+		pckt.proto = protocol;
+		pkt_bytes = bpf_ntohs(iph->tot_len);
+		off += IPV4_HDR_LEN_NO_OPT;
+
+		if (iph->frag_off & PCKT_FRAGMENTED)
+			return TC_ACT_SHOT;
+		if (protocol == IPPROTO_ICMP) {
+			action = parse_icmp(skb_ptr, off, &pckt);
+			if (action >= 0)
+				return action;
+			off += IPV4_PLUS_ICMP_HDR;
+		} else {
+			pckt.src = iph->saddr;
+			pckt.dst = iph->daddr;
+		}
+	}
+	protocol = pckt.proto;
+
+	if (protocol == IPPROTO_TCP) {
+		if (!parse_tcp(skb_ptr, off, &pckt))
+			return TC_ACT_SHOT;
+	} else if (protocol == IPPROTO_UDP) {
+		if (!parse_udp(skb_ptr, off, &pckt))
+			return TC_ACT_SHOT;
+	} else {
+		return TC_ACT_SHOT;
+	}
+
+	if (is_ipv6)
+		memcpy(vip.daddr.v6, pckt.dstv6, 16);
+	else
+		vip.daddr.v4 = pckt.dst;
+
+	vip.dport = pckt.port16[1];
+	vip.protocol = pckt.proto;
+	vip_info = bpf_map_lookup_elem(&vip_map, &vip);
+	if (!vip_info) {
+		vip.dport = 0;
+		vip_info = bpf_map_lookup_elem(&vip_map, &vip);
+		if (!vip_info)
+			return TC_ACT_SHOT;
+		pckt.port16[1] = 0;
+	}
+
+	if (vip_info->flags & F_HASH_NO_SRC_PORT)
+		pckt.port16[0] = 0;
+
+	if (!get_packet_dst(&dst, &pckt, vip_info, is_ipv6))
+		return TC_ACT_SHOT;
+
+	if (dst->flags & F_IPV6) {
+		cval = bpf_map_lookup_elem(&ctl_array, &v6_intf_pos);
+		if (!cval)
+			return TC_ACT_SHOT;
+		ifindex = cval->ifindex;
+		memcpy(tkey.remote_ipv6, dst->dstv6, 16);
+		tun_flag = BPF_F_TUNINFO_IPV6;
+	} else {
+		cval = bpf_map_lookup_elem(&ctl_array, &v4_intf_pos);
+		if (!cval)
+			return TC_ACT_SHOT;
+		ifindex = cval->ifindex;
+		tkey.remote_ipv4 = dst->dst;
+	}
+	vip_num = vip_info->vip_num;
+	data_stats = bpf_map_lookup_elem(&stats, &vip_num);
+	if (!data_stats)
+		return TC_ACT_SHOT;
+	data_stats->pkts++;
+	data_stats->bytes += pkt_bytes;
+	bpf_skb_set_tunnel_key(skb, &tkey, sizeof(tkey), tun_flag);
+	*(u32 *)eth->eth_dest = tkey.remote_ipv4;
+	return bpf_redirect(ifindex, 0);
+}
+
+SEC("tc")
+int balancer_ingress(struct __sk_buff *ctx)
+{
+	__u8 buffer[sizeof(struct eth_hdr)] = {};
+	struct bpf_dynptr ptr;
+	struct eth_hdr *eth;
+	__u32 eth_proto;
+	__u32 nh_off;
+	int err;
+
+	nh_off = sizeof(struct eth_hdr);
+
+	bpf_dynptr_from_skb(ctx, 0, &ptr);
+	eth = bpf_dynptr_slice_rdwr(&ptr, 0, buffer, sizeof(buffer));
+	if (!eth)
+		return TC_ACT_SHOT;
+	eth_proto = eth->eth_proto;
+	if (eth_proto == bpf_htons(ETH_P_IP))
+		err = process_packet(&ptr, eth, nh_off, false, ctx);
+	else if (eth_proto == bpf_htons(ETH_P_IPV6))
+		err = process_packet(&ptr, eth, nh_off, true, ctx);
+	else
+		return TC_ACT_SHOT;
+
+	if (eth == buffer)
+		bpf_dynptr_write(&ptr, 0, buffer, sizeof(buffer), 0);
+
+	return err;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_ldsx_insn.c b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
new file mode 100644
index 000000000000..2a2a942737d7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_ldsx_insn.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+     (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) ||       \
+     defined(__TARGET_ARCH_s390) || defined(__TARGET_ARCH_loongarch)) && \
+     __clang_major__ >= 18
+const volatile int skip = 0;
+#else
+const volatile int skip = 1;
+#endif
+
+volatile const short val1 = -1;
+volatile const int val2 = -1;
+short val3 = -1;
+int val4 = -1;
+int done1, done2, ret1, ret2;
+
+SEC("?raw_tp/sys_enter")
+int rdonly_map_prog(const void *ctx)
+{
+	if (done1)
+		return 0;
+
+	done1 = 1;
+	/* val1/val2 readonly map */
+	if (val1 == val2)
+		ret1 = 1;
+	return 0;
+
+}
+
+SEC("?raw_tp/sys_enter")
+int map_val_prog(const void *ctx)
+{
+	if (done2)
+		return 0;
+
+	done2 = 1;
+	/* val1/val2 regular read/write map */
+	if (val3 == val4)
+		ret2 = 1;
+	return 0;
+
+}
+
+struct bpf_testmod_struct_arg_1 {
+	int a;
+};
+
+long long int_member;
+
+SEC("?fentry/bpf_testmod_test_arg_ptr_to_struct")
+int BPF_PROG2(test_ptr_struct_arg, struct bpf_testmod_struct_arg_1 *, p)
+{
+	/* probed memory access */
+	int_member = p->a;
+        return 0;
+}
+
+long long set_optlen, set_retval;
+
+SEC("?cgroup/getsockopt")
+int _getsockopt(volatile struct bpf_sockopt *ctx)
+{
+	int old_optlen, old_retval;
+
+	old_optlen = ctx->optlen;
+	old_retval = ctx->retval;
+
+	ctx->optlen = -1;
+	ctx->retval = -1;
+
+	/* sign extension for ctx member */
+	set_optlen = ctx->optlen;
+	set_retval = ctx->retval;
+
+	ctx->optlen = old_optlen;
+	ctx->retval = old_retval;
+
+	return 0;
+}
+
+long long set_mark;
+
+SEC("?tc")
+int _tc(volatile struct __sk_buff *skb)
+{
+	long long tmp_mark;
+	int old_mark;
+
+	old_mark = skb->mark;
+
+	skb->mark = 0xf6fe;
+
+	/* narrowed sign extension for ctx member */
+#if __clang_major__ >= 18
+	/* force narrow one-byte signed load. Otherwise, compiler may
+	 * generate a 32-bit unsigned load followed by an s8 movsx.
+	 */
+	asm volatile ("r1 = *(s8 *)(%[ctx] + %[off_mark])\n\t"
+		      "%[tmp_mark] = r1"
+		      : [tmp_mark]"=r"(tmp_mark)
+		      : [ctx]"r"(skb),
+			[off_mark]"i"(offsetof(struct __sk_buff, mark)
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+			+ sizeof(skb->mark) - 1
+#endif
+			)
+		      : "r1");
+#else
+	tmp_mark = (char)skb->mark;
+#endif
+	set_mark = tmp_mark;
+
+	skb->mark = old_mark;
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_legacy_printk.c b/tools/testing/selftests/bpf/progs/test_legacy_printk.c
index 64c2d9ced529..42718cd8e6a4 100644
--- a/tools/testing/selftests/bpf/progs/test_legacy_printk.c
+++ b/tools/testing/selftests/bpf/progs/test_legacy_printk.c
@@ -56,7 +56,7 @@ int handle_legacy(void *ctx)
 SEC("tp/raw_syscalls/sys_enter")
 int handle_modern(void *ctx)
 {
-	int zero = 0, cur_pid;
+	int cur_pid;
 
 	cur_pid = bpf_get_current_pid_tgid() >> 32;
 	if (cur_pid != my_pid_var)
diff --git a/tools/testing/selftests/bpf/progs/test_libbpf_get_fd_by_id_opts.c b/tools/testing/selftests/bpf/progs/test_libbpf_get_fd_by_id_opts.c
index f5ac5f3e8919..568816307f71 100644
--- a/tools/testing/selftests/bpf/progs/test_libbpf_get_fd_by_id_opts.c
+++ b/tools/testing/selftests/bpf/progs/test_libbpf_get_fd_by_id_opts.c
@@ -31,6 +31,7 @@ int BPF_PROG(check_access, struct bpf_map *map, fmode_t fmode)
 
 	if (fmode & FMODE_WRITE)
 		return -EACCES;
+	barrier();
 
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_log_fixup.c b/tools/testing/selftests/bpf/progs/test_log_fixup.c
index 60450cb0e72e..1bd48feaaa42 100644
--- a/tools/testing/selftests/bpf/progs/test_log_fixup.c
+++ b/tools/testing/selftests/bpf/progs/test_log_fixup.c
@@ -61,4 +61,14 @@ int use_missing_map(const void *ctx)
 	return value != NULL;
 }
 
+extern int bpf_nonexistent_kfunc(void) __ksym __weak;
+
+SEC("?raw_tp/sys_enter")
+int use_missing_kfunc(const void *ctx)
+{
+	bpf_nonexistent_kfunc();
+
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_lookup_key.c b/tools/testing/selftests/bpf/progs/test_lookup_key.c
index c73776990ae3..1f7e1e59b073 100644
--- a/tools/testing/selftests/bpf/progs/test_lookup_key.c
+++ b/tools/testing/selftests/bpf/progs/test_lookup_key.c
@@ -14,16 +14,16 @@
 char _license[] SEC("license") = "GPL";
 
 __u32 monitored_pid;
-__u32 key_serial;
+__s32 key_serial;
 __u32 key_id;
 __u64 flags;
 
-extern struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym;
+extern struct bpf_key *bpf_lookup_user_key(__s32 serial, __u64 flags) __ksym;
 extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym;
 extern void bpf_key_put(struct bpf_key *key) __ksym;
 
 SEC("lsm.s/bpf")
-int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size)
+int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
 {
 	struct bpf_key *bkey;
 	__u32 pid;
diff --git a/tools/testing/selftests/bpf/progs/test_lwt_redirect.c b/tools/testing/selftests/bpf/progs/test_lwt_redirect.c
new file mode 100644
index 000000000000..83439b87b766
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_lwt_redirect.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+#include <linux/ip.h>
+#include <linux/if_ether.h>
+
+/* We don't care about whether the packet can be received by network stack.
+ * Just care if the packet is sent to the correct device at correct direction
+ * and not panic the kernel.
+ */
+static int prepend_dummy_mac(struct __sk_buff *skb)
+{
+	char mac[] = {0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0xf,
+		      0xe, 0xd, 0xc, 0xb, 0xa, 0x08, 0x00};
+
+	if (bpf_skb_change_head(skb, ETH_HLEN, 0))
+		return -1;
+
+	if (bpf_skb_store_bytes(skb, 0, mac, sizeof(mac), 0))
+		return -1;
+
+	return 0;
+}
+
+/* Use the last byte of IP address to redirect the packet */
+static int get_redirect_target(struct __sk_buff *skb)
+{
+	struct iphdr *iph = NULL;
+	void *start = (void *)(long)skb->data;
+	void *end = (void *)(long)skb->data_end;
+
+	if (start + sizeof(*iph) > end)
+		return -1;
+
+	iph = (struct iphdr *)start;
+	return bpf_ntohl(iph->daddr) & 0xff;
+}
+
+SEC("redir_ingress")
+int test_lwt_redirect_in(struct __sk_buff *skb)
+{
+	int target = get_redirect_target(skb);
+
+	if (target < 0)
+		return BPF_OK;
+
+	if (prepend_dummy_mac(skb))
+		return BPF_DROP;
+
+	return bpf_redirect(target, BPF_F_INGRESS);
+}
+
+SEC("redir_egress")
+int test_lwt_redirect_out(struct __sk_buff *skb)
+{
+	int target = get_redirect_target(skb);
+
+	if (target < 0)
+		return BPF_OK;
+
+	if (prepend_dummy_mac(skb))
+		return BPF_DROP;
+
+	return bpf_redirect(target, 0);
+}
+
+SEC("redir_egress_nomac")
+int test_lwt_redirect_out_nomac(struct __sk_buff *skb)
+{
+	int target = get_redirect_target(skb);
+
+	if (target < 0)
+		return BPF_OK;
+
+	return bpf_redirect(target, 0);
+}
+
+SEC("redir_ingress_nomac")
+int test_lwt_redirect_in_nomac(struct __sk_buff *skb)
+{
+	int target = get_redirect_target(skb);
+
+	if (target < 0)
+		return BPF_OK;
+
+	return bpf_redirect(target, BPF_F_INGRESS);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_lwt_reroute.c b/tools/testing/selftests/bpf/progs/test_lwt_reroute.c
new file mode 100644
index 000000000000..1dc64351929c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_lwt_reroute.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <inttypes.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+
+/* This function extracts the last byte of the daddr, and uses it
+ * as output dev index.
+ */
+SEC("lwt_xmit")
+int test_lwt_reroute(struct __sk_buff *skb)
+{
+	struct iphdr *iph = NULL;
+	void *start = (void *)(long)skb->data;
+	void *end = (void *)(long)skb->data_end;
+
+	/* set mark at most once */
+	if (skb->mark != 0)
+		return BPF_OK;
+
+	if (start + sizeof(*iph) > end)
+		return BPF_DROP;
+
+	iph = (struct iphdr *)start;
+	skb->mark = bpf_ntohl(iph->daddr) & 0xff;
+
+	/* do not reroute x.x.x.0 packets */
+	if (skb->mark == 0)
+		return BPF_OK;
+
+	return BPF_LWT_REROUTE;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
index 48ff2b2ad5e7..fed66f36adb6 100644
--- a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
+++ b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c
@@ -6,6 +6,8 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
+#include "bpf_compiler.h"
+
 /* Packet parsing state machine helpers. */
 #define cursor_advance(_cursor, _len) \
 	({ void *_tmp = _cursor; _cursor += _len; _tmp; })
@@ -131,7 +133,7 @@ int is_valid_tlv_boundary(struct __sk_buff *skb, struct ip6_srh_t *srh,
 	*pad_off = 0;
 
 	// we can only go as far as ~10 TLVs due to the BPF max stack size
-	#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (int i = 0; i < 10; i++) {
 		struct sr6_tlv_t tlv;
 
@@ -302,7 +304,7 @@ int __encap_srh(struct __sk_buff *skb)
 
 	seg = (struct ip6_addr_t *)((char *)srh + sizeof(*srh));
 
-	#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (unsigned long long lo = 0; lo < 4; lo++) {
 		seg->lo = bpf_cpu_to_be64(4 - lo);
 		seg->hi = bpf_cpu_to_be64(hi);
diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map.c b/tools/testing/selftests/bpf/progs/test_map_in_map.c
index f416032ba858..b295f9b721bf 100644
--- a/tools/testing/selftests/bpf/progs/test_map_in_map.c
+++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c
@@ -21,6 +21,32 @@ struct {
 	__type(value, __u32);
 } mim_hash SEC(".maps");
 
+/* The following three maps are used to test
+ * perf_event_array map can be an inner
+ * map of hash/array_of_maps.
+ */
+struct perf_event_array {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__type(key, __u32);
+	__type(value, __u32);
+} inner_map0 SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__array(values, struct perf_event_array);
+} mim_array_pe SEC(".maps") = {
+	.values = {&inner_map0}};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__array(values, struct perf_event_array);
+} mim_hash_pe SEC(".maps") = {
+	.values = {&inner_map0}};
+
 SEC("xdp")
 int xdp_mimtest0(struct xdp_md *ctx)
 {
diff --git a/tools/testing/selftests/bpf/progs/test_map_lock.c b/tools/testing/selftests/bpf/progs/test_map_lock.c
index acf073db9e8b..1c02511b73cd 100644
--- a/tools/testing/selftests/bpf/progs/test_map_lock.c
+++ b/tools/testing/selftests/bpf/progs/test_map_lock.c
@@ -33,7 +33,7 @@ struct {
 SEC("cgroup/skb")
 int bpf_map_lock_test(struct __sk_buff *skb)
 {
-	struct hmap_elem zero = {}, *val;
+	struct hmap_elem *val;
 	int rnd = bpf_get_prandom_u32();
 	int key = 0, err = 1, i;
 	struct array_elem *q;
diff --git a/tools/testing/selftests/bpf/progs/test_map_ops.c b/tools/testing/selftests/bpf/progs/test_map_ops.c
new file mode 100644
index 000000000000..b53b46a090c8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_map_ops.c
@@ -0,0 +1,138 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} hash_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_STACK);
+	__uint(max_entries, 1);
+	__type(value, int);
+} stack_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} array_map SEC(".maps");
+
+const volatile pid_t pid;
+long err = 0;
+
+static u64 callback(u64 map, u64 key, u64 val, u64 ctx, u64 flags)
+{
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_getpid")
+int map_update(void *ctx)
+{
+	const int key = 0;
+	const int val = 1;
+
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	err = bpf_map_update_elem(&hash_map, &key, &val, BPF_NOEXIST);
+
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_getppid")
+int map_delete(void *ctx)
+{
+	const int key = 0;
+
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	err = bpf_map_delete_elem(&hash_map, &key);
+
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_getuid")
+int map_push(void *ctx)
+{
+	const int val = 1;
+
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	err = bpf_map_push_elem(&stack_map, &val, 0);
+
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_geteuid")
+int map_pop(void *ctx)
+{
+	int val;
+
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	err = bpf_map_pop_elem(&stack_map, &val);
+
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_getgid")
+int map_peek(void *ctx)
+{
+	int val;
+
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	err = bpf_map_peek_elem(&stack_map, &val);
+
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_gettid")
+int map_for_each_pass(void *ctx)
+{
+	const int key = 0;
+	const int val = 1;
+	const u64 flags = 0;
+	int callback_ctx;
+
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	bpf_map_update_elem(&array_map, &key, &val, flags);
+
+	err = bpf_for_each_map_elem(&array_map, callback, &callback_ctx, flags);
+
+	return 0;
+}
+
+SEC("tp/syscalls/sys_enter_getpgid")
+int map_for_each_fail(void *ctx)
+{
+	const int key = 0;
+	const int val = 1;
+	const u64 flags = BPF_NOEXIST;
+	int callback_ctx;
+
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	bpf_map_update_elem(&array_map, &key, &val, flags);
+
+	/* calling for_each with non-zero flags will return error */
+	err = bpf_for_each_map_elem(&array_map, callback, &callback_ctx, flags);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_module_attach.c b/tools/testing/selftests/bpf/progs/test_module_attach.c
index 8a1b50f3a002..03d7f89787a1 100644
--- a/tools/testing/selftests/bpf/progs/test_module_attach.c
+++ b/tools/testing/selftests/bpf/progs/test_module_attach.c
@@ -5,7 +5,7 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include <bpf/bpf_core_read.h>
-#include "../bpf_testmod/bpf_testmod.h"
+#include "../test_kmods/bpf_testmod.h"
 
 __u32 raw_tp_read_sz = 0;
 
@@ -19,7 +19,7 @@ int BPF_PROG(handle_raw_tp,
 
 __u32 raw_tp_bare_write_sz = 0;
 
-SEC("raw_tp/bpf_testmod_test_write_bare")
+SEC("raw_tp/bpf_testmod_test_write_bare_tp")
 int BPF_PROG(handle_raw_tp_bare,
 	     struct task_struct *task, struct bpf_testmod_test_write_ctx *write_ctx)
 {
@@ -31,7 +31,7 @@ int raw_tp_writable_bare_in_val = 0;
 int raw_tp_writable_bare_early_ret = 0;
 int raw_tp_writable_bare_out_val = 0;
 
-SEC("raw_tp.w/bpf_testmod_test_writable_bare")
+SEC("raw_tp.w/bpf_testmod_test_writable_bare_tp")
 int BPF_PROG(handle_raw_tp_writable_bare,
 	     struct bpf_testmod_test_writable_ctx *writable)
 {
@@ -73,6 +73,29 @@ int BPF_PROG(handle_fentry_manual,
 	return 0;
 }
 
+__u32 fentry_explicit_read_sz = 0;
+
+SEC("fentry/bpf_testmod:bpf_testmod_test_read")
+int BPF_PROG(handle_fentry_explicit,
+	     struct file *file, struct kobject *kobj,
+	     struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len)
+{
+	fentry_explicit_read_sz = len;
+	return 0;
+}
+
+
+__u32 fentry_explicit_manual_read_sz = 0;
+
+SEC("fentry")
+int BPF_PROG(handle_fentry_explicit_manual,
+	     struct file *file, struct kobject *kobj,
+	     struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len)
+{
+	fentry_explicit_manual_read_sz = len;
+	return 0;
+}
+
 __u32 fexit_read_sz = 0;
 int fexit_ret = 0;
 
@@ -94,7 +117,7 @@ int BPF_PROG(handle_fexit_ret, int arg, struct file *ret)
 
 	bpf_probe_read_kernel(&buf, 8, ret);
 	bpf_probe_read_kernel(&buf, 8, (char *)ret + 256);
-	*(volatile long long *)ret;
+	*(volatile int *)ret;
 	*(volatile int *)&ret->f_mode;
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_netfilter_link_attach.c b/tools/testing/selftests/bpf/progs/test_netfilter_link_attach.c
new file mode 100644
index 000000000000..03a475160abe
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_netfilter_link_attach.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+#define NF_ACCEPT 1
+
+SEC("netfilter")
+int nf_link_attach_test(struct bpf_nf_ctx *ctx)
+{
+	return NF_ACCEPT;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c b/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c
index 0763d49f9c42..386315afad65 100644
--- a/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c
+++ b/tools/testing/selftests/bpf/progs/test_ns_current_pid_tgid.c
@@ -5,23 +5,48 @@
 #include <stdint.h>
 #include <bpf/bpf_helpers.h>
 
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 2);
+	__type(key, __u32);
+	__type(value, __u32);
+} sock_map SEC(".maps");
+
 __u64 user_pid = 0;
 __u64 user_tgid = 0;
 __u64 dev = 0;
 __u64 ino = 0;
 
-SEC("tracepoint/syscalls/sys_enter_nanosleep")
-int handler(const void *ctx)
+static void get_pid_tgid(void)
 {
 	struct bpf_pidns_info nsdata;
 
 	if (bpf_get_ns_current_pid_tgid(dev, ino, &nsdata, sizeof(struct bpf_pidns_info)))
-		return 0;
+		return;
 
 	user_pid = nsdata.pid;
 	user_tgid = nsdata.tgid;
+}
 
+SEC("?tracepoint/syscalls/sys_enter_nanosleep")
+int tp_handler(const void *ctx)
+{
+	get_pid_tgid();
 	return 0;
 }
 
+SEC("?cgroup/bind4")
+int cgroup_bind4(struct bpf_sock_addr *ctx)
+{
+	get_pid_tgid();
+	return 1;
+}
+
+SEC("?sk_msg")
+int sk_msg(struct sk_msg_md *msg)
+{
+	get_pid_tgid();
+	return SK_PASS;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_obj_id.c b/tools/testing/selftests/bpf/progs/test_obj_id.c
index ded71b3ff6b4..2850ae788a91 100644
--- a/tools/testing/selftests/bpf/progs/test_obj_id.c
+++ b/tools/testing/selftests/bpf/progs/test_obj_id.c
@@ -4,6 +4,7 @@
 #include <stddef.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
@@ -19,6 +20,7 @@ int test_obj_id(void *ctx)
 	__u64 *value;
 
 	value = bpf_map_lookup_elem(&test_map_id, &key);
+	__sink(value);
 
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c
index abb7344b531f..5edf3cdc213d 100644
--- a/tools/testing/selftests/bpf/progs/test_overhead.c
+++ b/tools/testing/selftests/bpf/progs/test_overhead.c
@@ -1,9 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 Facebook */
-#include <stdbool.h>
-#include <stddef.h>
-#include <linux/bpf.h>
-#include <linux/ptrace.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
diff --git a/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt.c b/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt.c
new file mode 100644
index 000000000000..d9b2ba7ac340
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt.c
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* This parsing logic is taken from the open source library katran, a layer 4
+ * load balancer.
+ *
+ * This code logic using dynptrs can be found in test_parse_tcp_hdr_opt_dynptr.c
+ *
+ * https://github.com/facebookincubator/katran/blob/main/katran/lib/bpf/pckt_parsing.h
+ */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <linux/tcp.h>
+#include <stdbool.h>
+#include <linux/ipv6.h>
+#include <linux/if_ether.h>
+#include "test_tcp_hdr_options.h"
+
+char _license[] SEC("license") = "GPL";
+
+/* Kind number used for experiments */
+const __u32 tcp_hdr_opt_kind_tpr = 0xFD;
+/* Length of the tcp header option */
+const __u32 tcp_hdr_opt_len_tpr = 6;
+/* maximum number of header options to check to lookup server_id */
+const __u32 tcp_hdr_opt_max_opt_checks = 15;
+
+__u32 server_id;
+
+struct hdr_opt_state {
+	__u32 server_id;
+	__u8 byte_offset;
+	__u8 hdr_bytes_remaining;
+};
+
+static int parse_hdr_opt(const struct xdp_md *xdp, struct hdr_opt_state *state)
+{
+	const void *data = (void *)(long)xdp->data;
+	const void *data_end = (void *)(long)xdp->data_end;
+	__u8 *tcp_opt, kind, hdr_len;
+
+	tcp_opt = (__u8 *)(data + state->byte_offset);
+	if (tcp_opt + 1 > data_end)
+		return -1;
+
+	kind = tcp_opt[0];
+
+	if (kind == TCPOPT_EOL)
+		return -1;
+
+	if (kind == TCPOPT_NOP) {
+		state->hdr_bytes_remaining--;
+		state->byte_offset++;
+		return 0;
+	}
+
+	if (state->hdr_bytes_remaining < 2 ||
+	    tcp_opt + sizeof(__u8) + sizeof(__u8) > data_end)
+		return -1;
+
+	hdr_len = tcp_opt[1];
+	if (hdr_len > state->hdr_bytes_remaining)
+		return -1;
+
+	if (kind == tcp_hdr_opt_kind_tpr) {
+		if (hdr_len != tcp_hdr_opt_len_tpr)
+			return -1;
+
+		if (tcp_opt + tcp_hdr_opt_len_tpr > data_end)
+			return -1;
+
+		state->server_id = *(__u32 *)&tcp_opt[2];
+		return 1;
+	}
+
+	state->hdr_bytes_remaining -= hdr_len;
+	state->byte_offset += hdr_len;
+	return 0;
+}
+
+SEC("xdp")
+int xdp_ingress_v6(struct xdp_md *xdp)
+{
+	const void *data = (void *)(long)xdp->data;
+	const void *data_end = (void *)(long)xdp->data_end;
+	struct hdr_opt_state opt_state = {};
+	__u8 tcp_hdr_opt_len = 0;
+	struct tcphdr *tcp_hdr;
+	__u64 tcp_offset = 0;
+	int err;
+
+	tcp_offset = sizeof(struct ethhdr) + sizeof(struct ipv6hdr);
+	tcp_hdr = (struct tcphdr *)(data + tcp_offset);
+	if (tcp_hdr + 1 > data_end)
+		return XDP_DROP;
+
+	tcp_hdr_opt_len = (tcp_hdr->doff * 4) - sizeof(struct tcphdr);
+	if (tcp_hdr_opt_len < tcp_hdr_opt_len_tpr)
+		return XDP_DROP;
+
+	opt_state.hdr_bytes_remaining = tcp_hdr_opt_len;
+	opt_state.byte_offset = sizeof(struct tcphdr) + tcp_offset;
+
+	/* max number of bytes of options in tcp header is 40 bytes */
+	for (int i = 0; i < tcp_hdr_opt_max_opt_checks; i++) {
+		err = parse_hdr_opt(xdp, &opt_state);
+
+		if (err || !opt_state.hdr_bytes_remaining)
+			break;
+	}
+
+	if (!opt_state.server_id)
+		return XDP_DROP;
+
+	server_id = opt_state.server_id;
+
+	return XDP_PASS;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt_dynptr.c b/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt_dynptr.c
new file mode 100644
index 000000000000..dc6e43bc6a62
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_parse_tcp_hdr_opt_dynptr.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* This logic is lifted from a real-world use case of packet parsing, used in
+ * the open source library katran, a layer 4 load balancer.
+ *
+ * This test demonstrates how to parse packet contents using dynptrs. The
+ * original code (parsing without dynptrs) can be found in test_parse_tcp_hdr_opt.c
+ */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <linux/tcp.h>
+#include <stdbool.h>
+#include <linux/ipv6.h>
+#include <linux/if_ether.h>
+#include "test_tcp_hdr_options.h"
+#include "bpf_kfuncs.h"
+
+char _license[] SEC("license") = "GPL";
+
+/* Kind number used for experiments */
+const __u32 tcp_hdr_opt_kind_tpr = 0xFD;
+/* Length of the tcp header option */
+const __u32 tcp_hdr_opt_len_tpr = 6;
+/* maximum number of header options to check to lookup server_id */
+const __u32 tcp_hdr_opt_max_opt_checks = 15;
+
+__u32 server_id;
+
+static int parse_hdr_opt(struct bpf_dynptr *ptr, __u32 *off, __u8 *hdr_bytes_remaining,
+			 __u32 *server_id)
+{
+	__u8 kind, hdr_len;
+	__u8 buffer[sizeof(kind) + sizeof(hdr_len) + sizeof(*server_id)];
+	__u8 *data;
+
+	__builtin_memset(buffer, 0, sizeof(buffer));
+
+	data = bpf_dynptr_slice(ptr, *off, buffer, sizeof(buffer));
+	if (!data)
+		return -1;
+
+	kind = data[0];
+
+	if (kind == TCPOPT_EOL)
+		return -1;
+
+	if (kind == TCPOPT_NOP) {
+		*off += 1;
+		*hdr_bytes_remaining -= 1;
+		return 0;
+	}
+
+	if (*hdr_bytes_remaining < 2)
+		return -1;
+
+	hdr_len = data[1];
+	if (hdr_len > *hdr_bytes_remaining)
+		return -1;
+
+	if (kind == tcp_hdr_opt_kind_tpr) {
+		if (hdr_len != tcp_hdr_opt_len_tpr)
+			return -1;
+
+		__builtin_memcpy(server_id, (__u32 *)(data + 2), sizeof(*server_id));
+		return 1;
+	}
+
+	*off += hdr_len;
+	*hdr_bytes_remaining -= hdr_len;
+	return 0;
+}
+
+SEC("xdp")
+int xdp_ingress_v6(struct xdp_md *xdp)
+{
+	__u8 buffer[sizeof(struct tcphdr)] = {};
+	__u8 hdr_bytes_remaining;
+	struct tcphdr *tcp_hdr;
+	__u8 tcp_hdr_opt_len;
+	int err = 0;
+	__u32 off;
+
+	struct bpf_dynptr ptr;
+
+	bpf_dynptr_from_xdp(xdp, 0, &ptr);
+
+	off = sizeof(struct ethhdr) + sizeof(struct ipv6hdr);
+
+	tcp_hdr = bpf_dynptr_slice(&ptr, off, buffer, sizeof(buffer));
+	if (!tcp_hdr)
+		return XDP_DROP;
+
+	tcp_hdr_opt_len = (tcp_hdr->doff * 4) - sizeof(struct tcphdr);
+	if (tcp_hdr_opt_len < tcp_hdr_opt_len_tpr)
+		return XDP_DROP;
+
+	hdr_bytes_remaining = tcp_hdr_opt_len;
+
+	off += sizeof(struct tcphdr);
+
+	/* max number of bytes of options in tcp header is 40 bytes */
+	for (int i = 0; i < tcp_hdr_opt_max_opt_checks; i++) {
+		err = parse_hdr_opt(&ptr, &off, &hdr_bytes_remaining, &server_id);
+
+		if (err || !hdr_bytes_remaining)
+			break;
+	}
+
+	if (!server_id)
+		return XDP_DROP;
+
+	return XDP_PASS;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_perf_branches.c b/tools/testing/selftests/bpf/progs/test_perf_branches.c
index a1ccc831c882..05ac9410cd68 100644
--- a/tools/testing/selftests/bpf/progs/test_perf_branches.c
+++ b/tools/testing/selftests/bpf/progs/test_perf_branches.c
@@ -8,6 +8,7 @@
 #include <bpf/bpf_tracing.h>
 
 int valid = 0;
+int run_cnt = 0;
 int required_size_out = 0;
 int written_stack_out = 0;
 int written_global_out = 0;
@@ -24,6 +25,8 @@ int perf_branches(void *ctx)
 	__u64 entries[4 * 3] = {0};
 	int required_size, written_stack, written_global;
 
+	++run_cnt;
+
 	/* write to stack */
 	written_stack = bpf_read_branch_records(ctx, entries, sizeof(entries), 0);
 	/* ignore spurious events */
diff --git a/tools/testing/selftests/bpf/progs/test_perf_skip.c b/tools/testing/selftests/bpf/progs/test_perf_skip.c
new file mode 100644
index 000000000000..7eb8b6de7a57
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_perf_skip.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+uintptr_t ip;
+
+SEC("perf_event")
+int handler(struct bpf_perf_event_data *data)
+{
+	/* Skip events that have the correct ip. */
+	return ip != PT_REGS_IP(&data->regs);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_pinning_devmap.c b/tools/testing/selftests/bpf/progs/test_pinning_devmap.c
new file mode 100644
index 000000000000..c855f8f87eff
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_pinning_devmap.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u32);
+	__uint(pinning, LIBBPF_PIN_BY_NAME);
+} pinmap1 SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP);
+	__uint(max_entries, 2);
+	__type(key, __u32);
+	__type(value, __u32);
+	__uint(pinning, LIBBPF_PIN_BY_NAME);
+} pinmap2 SEC(".maps");
diff --git a/tools/testing/selftests/bpf/progs/test_pinning_htab.c b/tools/testing/selftests/bpf/progs/test_pinning_htab.c
new file mode 100644
index 000000000000..ae227930c73c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_pinning_htab.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct timer_val {
+	struct bpf_timer timer;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __u32);
+	__type(value, struct timer_val);
+	__uint(max_entries, 1);
+} timer_prealloc SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __u32);
+	__type(value, struct timer_val);
+	__uint(max_entries, 1);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+} timer_no_prealloc SEC(".maps");
diff --git a/tools/testing/selftests/bpf/progs/test_pkt_access.c b/tools/testing/selftests/bpf/progs/test_pkt_access.c
index 5cd7c096f62d..bce7173152c6 100644
--- a/tools/testing/selftests/bpf/progs/test_pkt_access.c
+++ b/tools/testing/selftests/bpf/progs/test_pkt_access.c
@@ -13,6 +13,7 @@
 #include <linux/pkt_cls.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
+#include "bpf_misc.h"
 
 /* llvm will optimize both subprograms into exactly the same BPF assembly
  *
@@ -51,6 +52,8 @@ int get_skb_len(struct __sk_buff *skb)
 {
 	volatile char buf[MAX_STACK] = {};
 
+	__sink(buf[MAX_STACK - 1]);
+
 	return skb->len;
 }
 
@@ -73,6 +76,8 @@ int get_skb_ifindex(int val, struct __sk_buff *skb, int var)
 {
 	volatile char buf[MAX_STACK] = {};
 
+	__sink(buf[MAX_STACK - 1]);
+
 	return skb->ifindex * val * var;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c b/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c
new file mode 100644
index 000000000000..89b0cd5a3e06
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+
+char tp_name[128];
+
+SEC("lsm.s/bpf")
+int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
+{
+	switch (cmd) {
+	case BPF_RAW_TRACEPOINT_OPEN:
+		bpf_copy_from_user(tp_name, sizeof(tp_name) - 1,
+				   (void *)attr->raw_tracepoint.name);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+SEC("raw_tracepoint")
+int BPF_PROG(raw_tp_run)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c
index fc8e8a34a3db..7035fb4d4165 100644
--- a/tools/testing/selftests/bpf/progs/test_rdonly_maps.c
+++ b/tools/testing/selftests/bpf/progs/test_rdonly_maps.c
@@ -4,6 +4,7 @@
 #include <linux/ptrace.h>
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
 
 const struct {
 	unsigned a[4];
@@ -64,7 +65,7 @@ int full_loop(struct pt_regs *ctx)
 {
 	/* prevent compiler to optimize everything out */
 	unsigned * volatile p = (void *)&rdonly_values.a;
-	int i = sizeof(rdonly_values.a) / sizeof(rdonly_values.a[0]);
+	int i = ARRAY_SIZE(rdonly_values.a);
 	unsigned iters = 0, sum = 0;
 
 	/* validate verifier can allow full loop as well */
diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf.c b/tools/testing/selftests/bpf/progs/test_ringbuf.c
index 5bdc0d38efc0..501cefa97633 100644
--- a/tools/testing/selftests/bpf/progs/test_ringbuf.c
+++ b/tools/testing/selftests/bpf/progs/test_ringbuf.c
@@ -41,7 +41,6 @@ int test_ringbuf(void *ctx)
 {
 	int cur_pid = bpf_get_current_pid_tgid() >> 32;
 	struct sample *sample;
-	int zero = 0;
 
 	if (cur_pid != pid)
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf_map_key.c b/tools/testing/selftests/bpf/progs/test_ringbuf_map_key.c
index 2760bf60d05a..21bb7da90ea5 100644
--- a/tools/testing/selftests/bpf/progs/test_ringbuf_map_key.c
+++ b/tools/testing/selftests/bpf/progs/test_ringbuf_map_key.c
@@ -53,6 +53,7 @@ int test_ringbuf_mem_map_key(void *ctx)
 	/* test using 'sample' (PTR_TO_MEM | MEM_ALLOC) as map key arg
 	 */
 	lookup_val = (int *)bpf_map_lookup_elem(&hash_map, sample);
+	__sink(lookup_val);
 
 	/* workaround - memcpy is necessary so that verifier doesn't
 	 * complain with:
diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c b/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c
index e416e0ce12b7..9626baa6779c 100644
--- a/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c
+++ b/tools/testing/selftests/bpf/progs/test_ringbuf_multi.c
@@ -59,7 +59,6 @@ int test_ringbuf(void *ctx)
 	int cur_pid = bpf_get_current_pid_tgid() >> 32;
 	struct sample *sample;
 	void *rb;
-	int zero = 0;
 
 	if (cur_pid != pid)
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf_n.c b/tools/testing/selftests/bpf/progs/test_ringbuf_n.c
new file mode 100644
index 000000000000..8669eb42dbe0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_ringbuf_n.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2024 Andrea Righi <andrea.righi@canonical.com>
+
+#include <linux/bpf.h>
+#include <sched.h>
+#include <unistd.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define TASK_COMM_LEN 16
+
+struct sample {
+	int pid;
+	long value;
+	char comm[16];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_RINGBUF);
+} ringbuf SEC(".maps");
+
+int pid = 0;
+long value = 0;
+
+SEC("fentry/" SYS_PREFIX "sys_getpgid")
+int test_ringbuf_n(void *ctx)
+{
+	int cur_pid = bpf_get_current_pid_tgid() >> 32;
+	struct sample *sample;
+
+	if (cur_pid != pid)
+		return 0;
+
+	sample = bpf_ringbuf_reserve(&ringbuf, sizeof(*sample), 0);
+	if (!sample)
+		return 0;
+
+	sample->pid = pid;
+	sample->value = value;
+	bpf_get_current_comm(sample->comm, sizeof(sample->comm));
+
+	bpf_ringbuf_submit(sample, 0);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf_overwrite.c b/tools/testing/selftests/bpf/progs/test_ringbuf_overwrite.c
new file mode 100644
index 000000000000..ff4aa67ddacc
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_ringbuf_overwrite.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2025. Huawei Technologies Co., Ltd */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_RINGBUF);
+	__uint(map_flags, BPF_F_RB_OVERWRITE);
+} ringbuf SEC(".maps");
+
+int pid;
+
+const volatile unsigned long LEN1;
+const volatile unsigned long LEN2;
+const volatile unsigned long LEN3;
+const volatile unsigned long LEN4;
+const volatile unsigned long LEN5;
+
+long reserve1_fail = 0;
+long reserve2_fail = 0;
+long reserve3_fail = 0;
+long reserve4_fail = 0;
+long reserve5_fail = 0;
+
+unsigned long avail_data = 0;
+unsigned long ring_size = 0;
+unsigned long cons_pos = 0;
+unsigned long prod_pos = 0;
+unsigned long over_pos = 0;
+
+SEC("fentry/" SYS_PREFIX "sys_getpgid")
+int test_overwrite_ringbuf(void *ctx)
+{
+	char *rec1, *rec2, *rec3, *rec4, *rec5;
+	int cur_pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (cur_pid != pid)
+		return 0;
+
+	rec1 = bpf_ringbuf_reserve(&ringbuf, LEN1, 0);
+	if (!rec1) {
+		reserve1_fail = 1;
+		return 0;
+	}
+
+	rec2 = bpf_ringbuf_reserve(&ringbuf, LEN2, 0);
+	if (!rec2) {
+		bpf_ringbuf_discard(rec1, 0);
+		reserve2_fail = 1;
+		return 0;
+	}
+
+	rec3 = bpf_ringbuf_reserve(&ringbuf, LEN3, 0);
+	/* expect failure */
+	if (!rec3) {
+		reserve3_fail = 1;
+	} else {
+		bpf_ringbuf_discard(rec1, 0);
+		bpf_ringbuf_discard(rec2, 0);
+		bpf_ringbuf_discard(rec3, 0);
+		return 0;
+	}
+
+	rec4 = bpf_ringbuf_reserve(&ringbuf, LEN4, 0);
+	if (!rec4) {
+		reserve4_fail = 1;
+		bpf_ringbuf_discard(rec1, 0);
+		bpf_ringbuf_discard(rec2, 0);
+		return 0;
+	}
+
+	bpf_ringbuf_submit(rec1, 0);
+	bpf_ringbuf_submit(rec2, 0);
+	bpf_ringbuf_submit(rec4, 0);
+
+	rec5 = bpf_ringbuf_reserve(&ringbuf, LEN5, 0);
+	if (!rec5) {
+		reserve5_fail = 1;
+		return 0;
+	}
+
+	for (int i = 0; i < LEN3; i++)
+		rec5[i] = 0xdd;
+
+	bpf_ringbuf_submit(rec5, 0);
+
+	ring_size = bpf_ringbuf_query(&ringbuf, BPF_RB_RING_SIZE);
+	avail_data = bpf_ringbuf_query(&ringbuf, BPF_RB_AVAIL_DATA);
+	cons_pos = bpf_ringbuf_query(&ringbuf, BPF_RB_CONS_POS);
+	prod_pos = bpf_ringbuf_query(&ringbuf, BPF_RB_PROD_POS);
+	over_pos = bpf_ringbuf_query(&ringbuf, BPF_RB_OVERWRITE_POS);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf_write.c b/tools/testing/selftests/bpf/progs/test_ringbuf_write.c
new file mode 100644
index 000000000000..f063a0013f85
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_ringbuf_write.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_RINGBUF);
+} ringbuf SEC(".maps");
+
+/* inputs */
+int pid = 0;
+
+/* outputs */
+long passed = 0;
+long discarded = 0;
+
+SEC("fentry/" SYS_PREFIX "sys_getpgid")
+int test_ringbuf_write(void *ctx)
+{
+	int *foo, cur_pid = bpf_get_current_pid_tgid() >> 32;
+	void *sample1, *sample2;
+
+	if (cur_pid != pid)
+		return 0;
+
+	sample1 = bpf_ringbuf_reserve(&ringbuf, 0x30000, 0);
+	if (!sample1)
+		return 0;
+	/* first one can pass */
+	sample2 = bpf_ringbuf_reserve(&ringbuf, 0x30000, 0);
+	if (!sample2) {
+		bpf_ringbuf_discard(sample1, 0);
+		__sync_fetch_and_add(&discarded, 1);
+		return 0;
+	}
+	/* second one must not */
+	__sync_fetch_and_add(&passed, 1);
+	foo = sample2 + 4084;
+	*foo = 256;
+	bpf_ringbuf_discard(sample1, 0);
+	bpf_ringbuf_discard(sample2, 0);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_seg6_loop.c b/tools/testing/selftests/bpf/progs/test_seg6_loop.c
index a7278f064368..5059050f74f6 100644
--- a/tools/testing/selftests/bpf/progs/test_seg6_loop.c
+++ b/tools/testing/selftests/bpf/progs/test_seg6_loop.c
@@ -6,6 +6,8 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
+#include "bpf_compiler.h"
+
 /* Packet parsing state machine helpers. */
 #define cursor_advance(_cursor, _len) \
 	({ void *_tmp = _cursor; _cursor += _len; _tmp; })
@@ -134,7 +136,7 @@ static __always_inline int is_valid_tlv_boundary(struct __sk_buff *skb,
 	// we can only go as far as ~10 TLVs due to the BPF max stack size
 	// workaround: define induction variable "i" as "long" instead
 	// of "int" to prevent alu32 sub-register spilling.
-	#pragma clang loop unroll(disable)
+	__pragma_loop_no_unroll
 	for (long i = 0; i < 100; i++) {
 		struct sr6_tlv_t tlv;
 
diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
index 7d56ed47cd4d..a5be3267dbb0 100644
--- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2018 Facebook */
 
-#include <stdlib.h>
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
@@ -64,7 +63,7 @@ SEC("sk_reuseport")
 int _select_by_skb_data(struct sk_reuseport_md *reuse_md)
 {
 	__u32 linum, index = 0, flags = 0, index_zero = 0;
-	__u32 *result_cnt, *linum_value;
+	__u32 *result_cnt;
 	struct data_check data_check = {};
 	struct cmd *cmd, cmd_copy;
 	void *data, *data_end;
diff --git a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c
index 92354cd72044..176a355e3062 100644
--- a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c
@@ -1,27 +1,50 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2019 Facebook
-#include <linux/bpf.h>
+#include <vmlinux.h>
 #include <linux/version.h>
 #include <bpf/bpf_helpers.h>
 
-__u32 sig = 0, pid = 0, status = 0, signal_thread = 0;
+struct task_struct *bpf_task_from_pid(int pid) __ksym;
+void bpf_task_release(struct task_struct *p) __ksym;
+int bpf_send_signal_task(struct task_struct *task, int sig, enum pid_type type, u64 value) __ksym;
+
+__u32 sig = 0, pid = 0, status = 0, signal_thread = 0, target_pid = 0;
 
 static __always_inline int bpf_send_signal_test(void *ctx)
 {
+	struct task_struct *target_task = NULL;
 	int ret;
+	u64 value;
 
 	if (status != 0 || pid == 0)
 		return 0;
 
 	if ((bpf_get_current_pid_tgid() >> 32) == pid) {
-		if (signal_thread)
-			ret = bpf_send_signal_thread(sig);
-		else
-			ret = bpf_send_signal(sig);
+		if (target_pid) {
+			target_task = bpf_task_from_pid(target_pid);
+			if (!target_task)
+				return 0;
+			value = 8;
+		}
+
+		if (signal_thread) {
+			if (target_pid)
+				ret = bpf_send_signal_task(target_task, sig, PIDTYPE_PID, value);
+			else
+				ret = bpf_send_signal_thread(sig);
+		} else {
+			if (target_pid)
+				ret = bpf_send_signal_task(target_task, sig, PIDTYPE_TGID, value);
+			else
+				ret = bpf_send_signal(sig);
+		}
 		if (ret == 0)
 			status = 1;
 	}
 
+	if (target_task)
+		bpf_task_release(target_task);
+
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_set_remove_xattr.c b/tools/testing/selftests/bpf/progs/test_set_remove_xattr.c
new file mode 100644
index 000000000000..6a612cf168d3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_set_remove_xattr.c
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <errno.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_kfuncs.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+__u32 monitored_pid;
+
+const char xattr_foo[] = "security.bpf.foo";
+const char xattr_bar[] = "security.bpf.bar";
+static const char xattr_selinux[] = "security.selinux";
+char value_bar[] = "world";
+char read_value[32];
+
+bool set_security_bpf_bar_success;
+bool remove_security_bpf_bar_success;
+bool set_security_selinux_fail;
+bool remove_security_selinux_fail;
+
+char name_buf[32];
+
+static inline bool name_match_foo(const char *name)
+{
+	bpf_probe_read_kernel(name_buf, sizeof(name_buf), name);
+
+	return !bpf_strncmp(name_buf, sizeof(xattr_foo), xattr_foo);
+}
+
+/* Test bpf_set_dentry_xattr and bpf_remove_dentry_xattr */
+SEC("lsm.s/inode_getxattr")
+int BPF_PROG(test_inode_getxattr, struct dentry *dentry, char *name)
+{
+	struct bpf_dynptr value_ptr;
+	__u32 pid;
+	int ret;
+
+	pid = bpf_get_current_pid_tgid() >> 32;
+	if (pid != monitored_pid)
+		return 0;
+
+	/* Only do the following for security.bpf.foo */
+	if (!name_match_foo(name))
+		return 0;
+
+	bpf_dynptr_from_mem(read_value, sizeof(read_value), 0, &value_ptr);
+
+	/* read security.bpf.bar */
+	ret = bpf_get_dentry_xattr(dentry, xattr_bar, &value_ptr);
+
+	if (ret < 0) {
+		/* If security.bpf.bar doesn't exist, set it */
+		bpf_dynptr_from_mem(value_bar, sizeof(value_bar), 0, &value_ptr);
+
+		ret = bpf_set_dentry_xattr(dentry, xattr_bar, &value_ptr, 0);
+		if (!ret)
+			set_security_bpf_bar_success = true;
+		ret = bpf_set_dentry_xattr(dentry, xattr_selinux, &value_ptr, 0);
+		if (ret)
+			set_security_selinux_fail = true;
+	} else {
+		/* If security.bpf.bar exists, remove it */
+		ret = bpf_remove_dentry_xattr(dentry, xattr_bar);
+		if (!ret)
+			remove_security_bpf_bar_success = true;
+
+		ret = bpf_remove_dentry_xattr(dentry, xattr_selinux);
+		if (ret)
+			remove_security_selinux_fail = true;
+	}
+
+	return 0;
+}
+
+bool locked_set_security_bpf_bar_success;
+bool locked_remove_security_bpf_bar_success;
+bool locked_set_security_selinux_fail;
+bool locked_remove_security_selinux_fail;
+
+/* Test bpf_set_dentry_xattr_locked and bpf_remove_dentry_xattr_locked.
+ * It not necessary to differentiate the _locked version and the
+ * not-_locked version in the BPF program. The verifier will fix them up
+ * properly.
+ */
+SEC("lsm.s/inode_setxattr")
+int BPF_PROG(test_inode_setxattr, struct mnt_idmap *idmap,
+	     struct dentry *dentry, const char *name,
+	     const void *value, size_t size, int flags)
+{
+	struct bpf_dynptr value_ptr;
+	__u32 pid;
+	int ret;
+
+	pid = bpf_get_current_pid_tgid() >> 32;
+	if (pid != monitored_pid)
+		return 0;
+
+	/* Only do the following for security.bpf.foo */
+	if (!name_match_foo(name))
+		return 0;
+
+	bpf_dynptr_from_mem(read_value, sizeof(read_value), 0, &value_ptr);
+
+	/* read security.bpf.bar */
+	ret = bpf_get_dentry_xattr(dentry, xattr_bar, &value_ptr);
+
+	if (ret < 0) {
+		/* If security.bpf.bar doesn't exist, set it */
+		bpf_dynptr_from_mem(value_bar, sizeof(value_bar), 0, &value_ptr);
+
+		ret = bpf_set_dentry_xattr(dentry, xattr_bar, &value_ptr, 0);
+		if (!ret)
+			locked_set_security_bpf_bar_success = true;
+		ret = bpf_set_dentry_xattr(dentry, xattr_selinux, &value_ptr, 0);
+		if (ret)
+			locked_set_security_selinux_fail = true;
+	} else {
+		/* If security.bpf.bar exists, remove it */
+		ret = bpf_remove_dentry_xattr(dentry, xattr_bar);
+		if (!ret)
+			locked_remove_security_bpf_bar_success = true;
+
+		ret = bpf_remove_dentry_xattr(dentry, xattr_selinux);
+		if (ret)
+			locked_remove_security_selinux_fail = true;
+	}
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c b/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c
new file mode 100644
index 000000000000..34b30e2603f0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_kfuncs.h"
+#include "err.h"
+
+char _license[] SEC("license") = "GPL";
+
+#ifndef SHA256_DIGEST_SIZE
+#define SHA256_DIGEST_SIZE      32
+#endif
+
+#define MAX_SIG_SIZE 1024
+
+/* By default, "fsverity sign" signs a file with fsverity_formatted_digest
+ * of the file. fsverity_formatted_digest on the kernel side is only used
+ * with CONFIG_FS_VERITY_BUILTIN_SIGNATURES. However, BPF LSM doesn't not
+ * require CONFIG_FS_VERITY_BUILTIN_SIGNATURES, so vmlinux.h may not have
+ * fsverity_formatted_digest. In this test, we intentionally avoid using
+ * fsverity_formatted_digest.
+ *
+ * Luckily, fsverity_formatted_digest is simply 8-byte magic followed by
+ * fsverity_digest. We use a char array of size fsverity_formatted_digest
+ * plus SHA256_DIGEST_SIZE. The magic part of it is filled by user space,
+ * and the rest of it is filled by bpf_get_fsverity_digest.
+ *
+ * Note that, generating signatures based on fsverity_formatted_digest is
+ * the design choice of this selftest (and "fsverity sign"). With BPF
+ * LSM, we have the flexibility to generate signature based on other data
+ * sets, for example, fsverity_digest or only the digest[] part of it.
+ */
+#define MAGIC_SIZE 8
+#define SIZEOF_STRUCT_FSVERITY_DIGEST 4  /* sizeof(struct fsverity_digest) */
+char digest[MAGIC_SIZE + SIZEOF_STRUCT_FSVERITY_DIGEST + SHA256_DIGEST_SIZE];
+
+__u32 monitored_pid;
+char sig[MAX_SIG_SIZE];
+__u32 sig_size;
+__s32 user_keyring_serial;
+
+SEC("lsm.s/file_open")
+int BPF_PROG(test_file_open, struct file *f)
+{
+	struct bpf_dynptr digest_ptr, sig_ptr;
+	struct bpf_key *trusted_keyring;
+	__u32 pid;
+	int ret;
+
+	pid = bpf_get_current_pid_tgid() >> 32;
+	if (pid != monitored_pid)
+		return 0;
+
+	/* digest_ptr points to fsverity_digest */
+	bpf_dynptr_from_mem(digest + MAGIC_SIZE, sizeof(digest) - MAGIC_SIZE, 0, &digest_ptr);
+
+	ret = bpf_get_fsverity_digest(f, &digest_ptr);
+	/* No verity, allow access */
+	if (ret < 0)
+		return 0;
+
+	/* Move digest_ptr to fsverity_formatted_digest */
+	bpf_dynptr_from_mem(digest, sizeof(digest), 0, &digest_ptr);
+
+	/* Read signature from xattr */
+	bpf_dynptr_from_mem(sig, sizeof(sig), 0, &sig_ptr);
+	ret = bpf_get_file_xattr(f, "user.sig", &sig_ptr);
+	/* No signature, reject access */
+	if (ret < 0)
+		return -EPERM;
+
+	trusted_keyring = bpf_lookup_user_key(user_keyring_serial, 0);
+	if (!trusted_keyring)
+		return -ENOENT;
+
+	/* Verify signature */
+	ret = bpf_verify_pkcs7_signature(&digest_ptr, &sig_ptr, trusted_keyring);
+
+	bpf_key_put(trusted_keyring);
+
+	set_if_not_errno_or_zero(ret, -EFAULT);
+
+	return ret;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_siphash.h b/tools/testing/selftests/bpf/progs/test_siphash.h
new file mode 100644
index 000000000000..5d3a7ec36780
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_siphash.h
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+
+#ifndef _TEST_SIPHASH_H
+#define _TEST_SIPHASH_H
+
+/* include/linux/bitops.h */
+static inline u64 rol64(u64 word, unsigned int shift)
+{
+	return (word << (shift & 63)) | (word >> ((-shift) & 63));
+}
+
+/* include/linux/siphash.h */
+#define SIPHASH_PERMUTATION(a, b, c, d) ( \
+	(a) += (b), (b) = rol64((b), 13), (b) ^= (a), (a) = rol64((a), 32), \
+	(c) += (d), (d) = rol64((d), 16), (d) ^= (c), \
+	(a) += (d), (d) = rol64((d), 21), (d) ^= (a), \
+	(c) += (b), (b) = rol64((b), 17), (b) ^= (c), (c) = rol64((c), 32))
+
+#define SIPHASH_CONST_0 0x736f6d6570736575ULL
+#define SIPHASH_CONST_1 0x646f72616e646f6dULL
+#define SIPHASH_CONST_2 0x6c7967656e657261ULL
+#define SIPHASH_CONST_3 0x7465646279746573ULL
+
+/* lib/siphash.c */
+#define SIPROUND SIPHASH_PERMUTATION(v0, v1, v2, v3)
+
+#define PREAMBLE(len) \
+	u64 v0 = SIPHASH_CONST_0; \
+	u64 v1 = SIPHASH_CONST_1; \
+	u64 v2 = SIPHASH_CONST_2; \
+	u64 v3 = SIPHASH_CONST_3; \
+	u64 b = ((u64)(len)) << 56; \
+	v3 ^= key->key[1]; \
+	v2 ^= key->key[0]; \
+	v1 ^= key->key[1]; \
+	v0 ^= key->key[0];
+
+#define POSTAMBLE \
+	v3 ^= b; \
+	SIPROUND; \
+	SIPROUND; \
+	v0 ^= b; \
+	v2 ^= 0xff; \
+	SIPROUND; \
+	SIPROUND; \
+	SIPROUND; \
+	SIPROUND; \
+	return (v0 ^ v1) ^ (v2 ^ v3);
+
+static inline u64 siphash_2u64(const u64 first, const u64 second, const siphash_key_t *key)
+{
+	PREAMBLE(16)
+	v3 ^= first;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= first;
+	v3 ^= second;
+	SIPROUND;
+	SIPROUND;
+	v0 ^= second;
+	POSTAMBLE
+}
+#endif
diff --git a/tools/testing/selftests/bpf/progs/test_sk_assign.c b/tools/testing/selftests/bpf/progs/test_sk_assign.c
index 98c6493d9b91..3079244c7f96 100644
--- a/tools/testing/selftests/bpf/progs/test_sk_assign.c
+++ b/tools/testing/selftests/bpf/progs/test_sk_assign.c
@@ -15,7 +15,18 @@
 #include <sys/socket.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
+#include "bpf_misc.h"
 
+#if defined(IPROUTE2_HAVE_LIBBPF)
+/* Use a new-style map definition. */
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__type(key, int);
+	__type(value, __u64);
+	__uint(pinning, LIBBPF_PIN_BY_NAME);
+	__uint(max_entries, 1);
+} server_map SEC(".maps");
+#else
 /* Pin map under /sys/fs/bpf/tc/globals/<map name> */
 #define PIN_GLOBAL_NS 2
 
@@ -35,6 +46,7 @@ struct {
 	.max_elem = 1,
 	.pinning = PIN_GLOBAL_NS,
 };
+#endif
 
 char _license[] SEC("license") = "GPL";
 
@@ -46,7 +58,6 @@ get_tuple(struct __sk_buff *skb, bool *ipv4, bool *tcp)
 	void *data = (void *)(long)skb->data;
 	struct bpf_sock_tuple *result;
 	struct ethhdr *eth;
-	__u64 tuple_len;
 	__u8 proto = 0;
 	__u64 ihl_len;
 
@@ -83,6 +94,7 @@ get_tuple(struct __sk_buff *skb, bool *ipv4, bool *tcp)
 		return NULL;
 
 	*tcp = (proto == IPPROTO_TCP);
+	__sink(ihl_len);
 	return result;
 }
 
@@ -162,7 +174,6 @@ int bpf_sk_assign_test(struct __sk_buff *skb)
 	struct bpf_sock_tuple *tuple;
 	bool ipv4 = false;
 	bool tcp = false;
-	int tuple_len;
 	int ret = 0;
 
 	tuple = get_tuple(skb, &ipv4, &tcp);
diff --git a/tools/testing/selftests/bpf/progs/test_sk_assign_libbpf.c b/tools/testing/selftests/bpf/progs/test_sk_assign_libbpf.c
new file mode 100644
index 000000000000..dcf46adfda04
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sk_assign_libbpf.c
@@ -0,0 +1,3 @@
+// SPDX-License-Identifier: GPL-2.0
+#define IPROUTE2_HAVE_LIBBPF
+#include "test_sk_assign.c"
diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup.c b/tools/testing/selftests/bpf/progs/test_sk_lookup.c
index 6058dcb11b36..71f844b9b902 100644
--- a/tools/testing/selftests/bpf/progs/test_sk_lookup.c
+++ b/tools/testing/selftests/bpf/progs/test_sk_lookup.c
@@ -391,7 +391,6 @@ SEC("sk_lookup")
 int ctx_narrow_access(struct bpf_sk_lookup *ctx)
 {
 	struct bpf_sock *sk;
-	int err, family;
 	__u32 val_u32;
 	bool v4;
 
@@ -645,9 +644,7 @@ static __always_inline int select_server_a(struct bpf_sk_lookup *ctx)
 SEC("sk_lookup")
 int multi_prog_redir1(struct bpf_sk_lookup *ctx)
 {
-	int ret;
-
-	ret = select_server_a(ctx);
+	(void)select_server_a(ctx);
 	bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY);
 	return SK_PASS;
 }
@@ -655,9 +652,7 @@ int multi_prog_redir1(struct bpf_sk_lookup *ctx)
 SEC("sk_lookup")
 int multi_prog_redir2(struct bpf_sk_lookup *ctx)
 {
-	int ret;
-
-	ret = select_server_a(ctx);
+	(void)select_server_a(ctx);
 	bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY);
 	return SK_PASS;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
index b502e5c92e33..e9efc3263022 100644
--- a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
@@ -23,8 +23,8 @@ static struct bpf_sock_tuple *get_tuple(void *data, __u64 nh_off,
 					bool *ipv4)
 {
 	struct bpf_sock_tuple *result;
+	__u64 ihl_len = 0;
 	__u8 proto = 0;
-	__u64 ihl_len;
 
 	if (eth_proto == bpf_htons(ETH_P_IP)) {
 		struct iphdr *iph = (struct iphdr *)(data + nh_off);
@@ -110,7 +110,6 @@ int err_modify_sk_pointer(struct __sk_buff *skb)
 {
 	struct bpf_sock_tuple tuple = {};
 	struct bpf_sock *sk;
-	__u32 family;
 
 	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0);
 	if (sk) {
@@ -125,7 +124,6 @@ int err_modify_sk_or_null_pointer(struct __sk_buff *skb)
 {
 	struct bpf_sock_tuple tuple = {};
 	struct bpf_sock *sk;
-	__u32 family;
 
 	sk = bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0);
 	sk += 1;
diff --git a/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c b/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c
index 6dc1f28fc4b6..40531e56776e 100644
--- a/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c
+++ b/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c
@@ -84,7 +84,7 @@ int BPF_PROG(trace_tcp_connect, struct sock *sk)
 }
 
 SEC("fexit/inet_csk_accept")
-int BPF_PROG(inet_csk_accept, struct sock *sk, int flags, int *err, bool kern,
+int BPF_PROG(inet_csk_accept, struct sock *sk, struct proto_accept_arg *arg,
 	     struct sock *accepted_sk)
 {
 	set_task_info(accepted_sk);
@@ -92,4 +92,20 @@ int BPF_PROG(inet_csk_accept, struct sock *sk, int flags, int *err, bool kern,
 	return 0;
 }
 
+SEC("tp_btf/tcp_retransmit_synack")
+int BPF_PROG(tcp_retransmit_synack, struct sock* sk, struct request_sock* req)
+{
+	/* load only test */
+	bpf_sk_storage_get(&sk_stg_map, sk, 0, 0);
+	bpf_sk_storage_get(&sk_stg_map, req->sk, 0, 0);
+	return 0;
+}
+
+SEC("tp_btf/tcp_bad_csum")
+int BPF_PROG(tcp_bad_csum, struct sk_buff* skb)
+{
+	bpf_sk_storage_get(&sk_stg_map, skb->sk, 0, 0);
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c
deleted file mode 100644
index 37aacc66cd68..000000000000
--- a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c
+++ /dev/null
@@ -1,45 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright (c) 2018 Facebook
-
-#include <linux/bpf.h>
-#include <linux/pkt_cls.h>
-
-#include <string.h>
-
-#include <bpf/bpf_helpers.h>
-
-#define NUM_CGROUP_LEVELS	4
-
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__type(key, __u32);
-	__type(value, __u64);
-	__uint(max_entries, NUM_CGROUP_LEVELS);
-} cgroup_ids SEC(".maps");
-
-static __always_inline void log_nth_level(struct __sk_buff *skb, __u32 level)
-{
-	__u64 id;
-
-	/* [1] &level passed to external function that may change it, it's
-	 *     incompatible with loop unroll.
-	 */
-	id = bpf_skb_ancestor_cgroup_id(skb, level);
-	bpf_map_update_elem(&cgroup_ids, &level, &id, 0);
-}
-
-SEC("cgroup_id_logger")
-int log_cgroup_id(struct __sk_buff *skb)
-{
-	/* Loop unroll can't be used here due to [1]. Unrolling manually.
-	 * Number of calls should be in sync with NUM_CGROUP_LEVELS.
-	 */
-	log_nth_level(skb, 0);
-	log_nth_level(skb, 1);
-	log_nth_level(skb, 2);
-	log_nth_level(skb, 3);
-
-	return TC_ACT_OK;
-}
-
-char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_skb_ctx.c b/tools/testing/selftests/bpf/progs/test_skb_ctx.c
index c482110cfc95..a724a70c6700 100644
--- a/tools/testing/selftests/bpf/progs/test_skb_ctx.c
+++ b/tools/testing/selftests/bpf/progs/test_skb_ctx.c
@@ -3,12 +3,14 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
+#include "bpf_compiler.h"
+
 char _license[] SEC("license") = "GPL";
 
 SEC("tc")
 int process(struct __sk_buff *skb)
 {
-	#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (int i = 0; i < 5; i++) {
 		if (skb->cb[i] != i + 1)
 			return 1;
diff --git a/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c b/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c
index eacda9fe07eb..4cfa42aa9436 100644
--- a/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c
+++ b/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c
@@ -29,7 +29,7 @@ int BPF_PROG(unix_listen, struct socket *sock, int backlog)
 	len = unix_sk->addr->len - sizeof(short);
 	path[0] = '@';
 	for (i = 1; i < len; i++) {
-		if (i >= sizeof(struct sockaddr_un))
+		if (i >= (int)sizeof(struct sockaddr_un))
 			break;
 
 		path[i] = unix_sk->addr->name->sun_path[i];
diff --git a/tools/testing/selftests/bpf/progs/test_skmsg_load_helpers.c b/tools/testing/selftests/bpf/progs/test_skmsg_load_helpers.c
index 45e8fc75a739..996b177324ba 100644
--- a/tools/testing/selftests/bpf/progs/test_skmsg_load_helpers.c
+++ b/tools/testing/selftests/bpf/progs/test_skmsg_load_helpers.c
@@ -24,8 +24,7 @@ struct {
 	__type(value, __u64);
 } socket_storage SEC(".maps");
 
-SEC("sk_msg")
-int prog_msg_verdict(struct sk_msg_md *msg)
+static int prog_msg_verdict_common(struct sk_msg_md *msg)
 {
 	struct task_struct *task = (struct task_struct *)bpf_get_current_task();
 	int verdict = SK_PASS;
@@ -44,4 +43,28 @@ int prog_msg_verdict(struct sk_msg_md *msg)
 	return verdict;
 }
 
+SEC("sk_msg")
+int prog_msg_verdict(struct sk_msg_md *msg)
+{
+	return prog_msg_verdict_common(msg);
+}
+
+SEC("sk_msg")
+int prog_msg_verdict_clone(struct sk_msg_md *msg)
+{
+	return prog_msg_verdict_common(msg);
+}
+
+SEC("sk_msg")
+int prog_msg_verdict_clone2(struct sk_msg_md *msg)
+{
+	return prog_msg_verdict_common(msg);
+}
+
+SEC("sk_skb/stream_verdict")
+int prog_skb_verdict(struct __sk_buff *skb)
+{
+	return SK_PASS;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields.c b/tools/testing/selftests/bpf/progs/test_sock_fields.c
index 9f4b8f9f1181..196844be349c 100644
--- a/tools/testing/selftests/bpf/progs/test_sock_fields.c
+++ b/tools/testing/selftests/bpf/progs/test_sock_fields.c
@@ -7,7 +7,6 @@
 
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
-#include "bpf_tcp_helpers.h"
 
 enum bpf_linum_array_idx {
 	EGRESS_LINUM_IDX,
@@ -42,6 +41,10 @@ struct {
 	__type(value, struct bpf_spinlock_cnt);
 } sk_pkt_out_cnt10 SEC(".maps");
 
+struct tcp_sock {
+	__u32	lsndtime;
+} __attribute__((preserve_access_index));
+
 struct bpf_tcp_sock listen_tp = {};
 struct sockaddr_in6 srv_sa6 = {};
 struct bpf_tcp_sock cli_tp = {};
@@ -121,7 +124,7 @@ static void tpcpy(struct bpf_tcp_sock *dst,
 SEC("cgroup_skb/egress")
 int egress_read_sock_fields(struct __sk_buff *skb)
 {
-	struct bpf_spinlock_cnt cli_cnt_init = { .lock = 0, .cnt = 0xeB9F };
+	struct bpf_spinlock_cnt cli_cnt_init = { .lock = {}, .cnt = 0xeB9F };
 	struct bpf_spinlock_cnt *pkt_out_cnt, *pkt_out_cnt10;
 	struct bpf_tcp_sock *tp, *tp_ret;
 	struct bpf_sock *sk, *sk_ret;
@@ -265,7 +268,10 @@ static __noinline bool sk_dst_port__load_word(struct bpf_sock *sk)
 
 static __noinline bool sk_dst_port__load_half(struct bpf_sock *sk)
 {
-	__u16 *half = (__u16 *)&sk->dst_port;
+	__u16 *half;
+
+	asm volatile ("");
+	half = (__u16 *)&sk->dst_port;
 	return half[0] == bpf_htons(0xcafe);
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c b/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c
new file mode 100644
index 000000000000..1c7941a4ad00
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 ByteDance */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+#ifndef PAGE_SIZE
+#define PAGE_SIZE __PAGE_SIZE
+#endif
+#define BPF_SKB_MAX_LEN (PAGE_SIZE << 2)
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} sock_map_rx SEC(".maps");
+
+long change_tail_ret = 1;
+
+SEC("sk_skb")
+int prog_skb_verdict(struct __sk_buff *skb)
+{
+	char *data, *data_end;
+
+	bpf_skb_pull_data(skb, 1);
+	data = (char *)(unsigned long)skb->data;
+	data_end = (char *)(unsigned long)skb->data_end;
+
+	if (data + 1 > data_end)
+		return SK_PASS;
+
+	if (data[0] == 'T') { /* Trim the packet */
+		change_tail_ret = bpf_skb_change_tail(skb, skb->len - 1, 0);
+		return SK_PASS;
+	} else if (data[0] == 'G') { /* Grow the packet */
+		change_tail_ret = bpf_skb_change_tail(skb, skb->len + 1, 0);
+		return SK_PASS;
+	} else if (data[0] == 'E') { /* Error */
+		change_tail_ret = bpf_skb_change_tail(skb, BPF_SKB_MAX_LEN, 0);
+		return SK_PASS;
+	}
+	return SK_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_drop_prog.c b/tools/testing/selftests/bpf/progs/test_sockmap_drop_prog.c
new file mode 100644
index 000000000000..29314805ce42
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_drop_prog.c
@@ -0,0 +1,32 @@
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 20);
+	__type(key, int);
+	__type(value, int);
+} sock_map_rx SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 20);
+	__type(key, int);
+	__type(value, int);
+} sock_map_tx SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 20);
+	__type(key, int);
+	__type(value, int);
+} sock_map_msg SEC(".maps");
+
+SEC("sk_skb")
+int prog_skb_verdict(struct __sk_buff *skb)
+{
+	return SK_DROP;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
index 6c85b00f27b2..f48f85f1bd70 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
@@ -14,6 +14,7 @@
 #include <sys/socket.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
+#include "bpf_misc.h"
 
 /* Sockmap sample program connects a client and a backend together
  * using cgroups.
@@ -91,7 +92,7 @@ struct {
 	__uint(value_size, sizeof(int));
 } tls_sock_map SEC(".maps");
 
-SEC("sk_skb1")
+SEC("sk_skb/stream_parser")
 int bpf_prog1(struct __sk_buff *skb)
 {
 	int *f, two = 2;
@@ -103,7 +104,7 @@ int bpf_prog1(struct __sk_buff *skb)
 	return skb->len;
 }
 
-SEC("sk_skb2")
+SEC("sk_skb/stream_verdict")
 int bpf_prog2(struct __sk_buff *skb)
 {
 	__u32 lport = skb->local_port;
@@ -111,12 +112,15 @@ int bpf_prog2(struct __sk_buff *skb)
 	int len, *f, ret, zero = 0;
 	__u64 flags = 0;
 
+	__sink(rport);
 	if (lport == 10000)
 		ret = 10;
 	else
 		ret = 1;
 
 	len = (__u32)skb->data_end - (__u32)skb->data;
+	__sink(len);
+
 	f = bpf_map_lookup_elem(&sock_skb_opts, &zero);
 	if (f && *f) {
 		ret = 3;
@@ -147,7 +151,7 @@ static inline void bpf_write_pass(struct __sk_buff *skb, int offset)
 		memcpy(c + offset, "PASS", 4);
 }
 
-SEC("sk_skb3")
+SEC("sk_skb/stream_verdict")
 int bpf_prog3(struct __sk_buff *skb)
 {
 	int err, *f, ret = SK_PASS;
@@ -173,14 +177,10 @@ int bpf_prog3(struct __sk_buff *skb)
 		return bpf_sk_redirect_hash(skb, &tls_sock_map, &ret, flags);
 #endif
 	}
-	f = bpf_map_lookup_elem(&sock_skb_opts, &one);
-	if (f && *f)
-		ret = SK_DROP;
 	err = bpf_skb_adjust_room(skb, 4, 0, 0);
 	if (err)
 		return SK_DROP;
 	bpf_write_pass(skb, 13);
-tls_out:
 	return ret;
 }
 
@@ -188,8 +188,7 @@ SEC("sockops")
 int bpf_sockmap(struct bpf_sock_ops *skops)
 {
 	__u32 lport, rport;
-	int op, err = 0, index, key, ret;
-
+	int op, ret;
 
 	op = (int) skops->op;
 
@@ -201,10 +200,10 @@ int bpf_sockmap(struct bpf_sock_ops *skops)
 		if (lport == 10000) {
 			ret = 1;
 #ifdef SOCKMAP
-			err = bpf_sock_map_update(skops, &sock_map, &ret,
+			bpf_sock_map_update(skops, &sock_map, &ret,
 						  BPF_NOEXIST);
 #else
-			err = bpf_sock_hash_update(skops, &sock_map, &ret,
+			bpf_sock_hash_update(skops, &sock_map, &ret,
 						   BPF_NOEXIST);
 #endif
 		}
@@ -216,10 +215,10 @@ int bpf_sockmap(struct bpf_sock_ops *skops)
 		if (bpf_ntohl(rport) == 10001) {
 			ret = 10;
 #ifdef SOCKMAP
-			err = bpf_sock_map_update(skops, &sock_map, &ret,
+			bpf_sock_map_update(skops, &sock_map, &ret,
 						  BPF_NOEXIST);
 #else
-			err = bpf_sock_hash_update(skops, &sock_map, &ret,
+			bpf_sock_hash_update(skops, &sock_map, &ret,
 						   BPF_NOEXIST);
 #endif
 		}
@@ -231,7 +230,7 @@ int bpf_sockmap(struct bpf_sock_ops *skops)
 	return 0;
 }
 
-SEC("sk_msg1")
+SEC("sk_msg")
 int bpf_prog4(struct sk_msg_md *msg)
 {
 	int *bytes, zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5;
@@ -261,7 +260,7 @@ int bpf_prog4(struct sk_msg_md *msg)
 	return SK_PASS;
 }
 
-SEC("sk_msg2")
+SEC("sk_msg")
 int bpf_prog6(struct sk_msg_md *msg)
 {
 	int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5, key = 0;
@@ -306,7 +305,7 @@ int bpf_prog6(struct sk_msg_md *msg)
 #endif
 }
 
-SEC("sk_msg3")
+SEC("sk_msg")
 int bpf_prog8(struct sk_msg_md *msg)
 {
 	void *data_end = (void *)(long) msg->data_end;
@@ -321,9 +320,14 @@ int bpf_prog8(struct sk_msg_md *msg)
 	} else {
 		return SK_DROP;
 	}
+
+	__sink(data_end);
+	__sink(data);
+
 	return SK_PASS;
 }
-SEC("sk_msg4")
+
+SEC("sk_msg")
 int bpf_prog9(struct sk_msg_md *msg)
 {
 	void *data_end = (void *)(long) msg->data_end;
@@ -341,7 +345,7 @@ int bpf_prog9(struct sk_msg_md *msg)
 	return SK_PASS;
 }
 
-SEC("sk_msg5")
+SEC("sk_msg")
 int bpf_prog10(struct sk_msg_md *msg)
 {
 	int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop;
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c b/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c
new file mode 100644
index 000000000000..83df4919c224
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+int cork_byte;
+int push_start;
+int push_end;
+int apply_bytes;
+int pop_start;
+int pop_end;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 20);
+	__type(key, int);
+	__type(value, int);
+} sock_map SEC(".maps");
+
+SEC("sk_msg")
+int prog_sk_policy(struct sk_msg_md *msg)
+{
+	if (cork_byte > 0)
+		bpf_msg_cork_bytes(msg, cork_byte);
+	if (push_start > 0 && push_end > 0)
+		bpf_msg_push_data(msg, push_start, push_end, 0);
+	if (pop_start >= 0 && pop_end > 0)
+		bpf_msg_pop_data(msg, pop_start, pop_end, 0);
+
+	return SK_PASS;
+}
+
+SEC("sk_msg")
+int prog_sk_policy_redir(struct sk_msg_md *msg)
+{
+	int two = 2;
+
+	bpf_msg_apply_bytes(msg, apply_bytes);
+	return bpf_msg_redirect_map(msg, &sock_map, two, 0);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
index 325c9f193432..b7250eb9c30c 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
@@ -15,6 +15,13 @@ struct {
 } sock_map SEC(".maps");
 
 struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 2);
+	__type(key, __u32);
+	__type(value, __u64);
+} nop_map SEC(".maps");
+
+struct {
 	__uint(type, BPF_MAP_TYPE_SOCKHASH);
 	__uint(max_entries, 2);
 	__type(key, __u32);
@@ -28,12 +35,26 @@ struct {
 	__type(value, unsigned int);
 } verdict_map SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} parser_map SEC(".maps");
+
 bool test_sockmap = false; /* toggled by user-space */
 bool test_ingress = false; /* toggled by user-space */
 
 SEC("sk_skb/stream_parser")
 int prog_stream_parser(struct __sk_buff *skb)
 {
+	int *value;
+	__u32 key = 0;
+
+	value = bpf_map_lookup_elem(&parser_map, &key);
+	if (value && *value)
+		return *value;
+
 	return skb->len;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c b/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c
new file mode 100644
index 000000000000..69aacc96db36
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_pass_prog.c
@@ -0,0 +1,47 @@
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 20);
+	__type(key, int);
+	__type(value, int);
+} sock_map_rx SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 20);
+	__type(key, int);
+	__type(value, int);
+} sock_map_tx SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 20);
+	__type(key, int);
+	__type(value, int);
+} sock_map_msg SEC(".maps");
+
+SEC("sk_skb/stream_verdict")
+int prog_skb_verdict(struct __sk_buff *skb)
+{
+	return SK_PASS;
+}
+
+int clone_called;
+
+SEC("sk_skb/stream_verdict")
+int prog_skb_verdict_clone(struct __sk_buff *skb)
+{
+	clone_called = 1;
+	return SK_PASS;
+}
+
+SEC("sk_skb/stream_parser")
+int prog_skb_parser(struct __sk_buff *skb)
+{
+	return SK_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_redir.c b/tools/testing/selftests/bpf/progs/test_sockmap_redir.c
new file mode 100644
index 000000000000..34d9f4f2f0a2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_redir.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC(".maps") struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} nop_map, sock_map;
+
+SEC(".maps") struct {
+	__uint(type, BPF_MAP_TYPE_SOCKHASH);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} nop_hash, sock_hash;
+
+SEC(".maps") struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 2);
+	__type(key, int);
+	__type(value, unsigned int);
+} verdict_map;
+
+/* Set by user space */
+int redirect_type;
+int redirect_flags;
+
+#define redirect_map(__data)                                                   \
+	_Generic((__data),                                                     \
+		 struct __sk_buff * : bpf_sk_redirect_map,                     \
+		 struct sk_msg_md * : bpf_msg_redirect_map                     \
+	)((__data), &sock_map, (__u32){0}, redirect_flags)
+
+#define redirect_hash(__data)                                                  \
+	_Generic((__data),                                                     \
+		 struct __sk_buff * : bpf_sk_redirect_hash,                    \
+		 struct sk_msg_md * : bpf_msg_redirect_hash                    \
+	)((__data), &sock_hash, &(__u32){0}, redirect_flags)
+
+#define DEFINE_PROG(__type, __param)                                           \
+SEC("sk_" XSTR(__type))                                                        \
+int prog_ ## __type ## _verdict(__param data)                                  \
+{                                                                              \
+	unsigned int *count;                                                   \
+	int verdict;                                                           \
+									       \
+	if (redirect_type == BPF_MAP_TYPE_SOCKMAP)                             \
+		verdict = redirect_map(data);                                  \
+	else if (redirect_type == BPF_MAP_TYPE_SOCKHASH)                       \
+		verdict = redirect_hash(data);                                 \
+	else                                                                   \
+		verdict = redirect_type - __MAX_BPF_MAP_TYPE;                  \
+									       \
+	count = bpf_map_lookup_elem(&verdict_map, &verdict);                   \
+	if (count)                                                             \
+		(*count)++;                                                    \
+									       \
+	return verdict;                                                        \
+}
+
+DEFINE_PROG(skb, struct __sk_buff *);
+DEFINE_PROG(msg, struct sk_msg_md *);
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c b/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c
index 3c69aa971738..d25b0bb30fc0 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c
@@ -9,7 +9,7 @@ struct {
 	__type(value, __u64);
 } sock_map SEC(".maps");
 
-SEC("sk_skb")
+SEC("sk_skb/verdict")
 int prog_skb_verdict(struct __sk_buff *skb)
 {
 	return SK_DROP;
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_strp.c b/tools/testing/selftests/bpf/progs/test_sockmap_strp.c
new file mode 100644
index 000000000000..dde3d5bec515
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_strp.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+int verdict_max_size = 10000;
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 20);
+	__type(key, int);
+	__type(value, int);
+} sock_map SEC(".maps");
+
+SEC("sk_skb/stream_verdict")
+int prog_skb_verdict(struct __sk_buff *skb)
+{
+	__u32 one = 1;
+
+	if (skb->len > verdict_max_size)
+		return SK_PASS;
+
+	return bpf_sk_redirect_map(skb, &sock_map, one, 0);
+}
+
+SEC("sk_skb/stream_verdict")
+int prog_skb_verdict_pass(struct __sk_buff *skb)
+{
+	return SK_PASS;
+}
+
+SEC("sk_skb/stream_parser")
+int prog_skb_parser(struct __sk_buff *skb)
+{
+	return skb->len;
+}
+
+SEC("sk_skb/stream_parser")
+int prog_skb_parser_partial(struct __sk_buff *skb)
+{
+	/* agreement with the test program on a 4-byte size header
+	 * and 6-byte body.
+	 */
+	if (skb->len < 4) {
+		/* need more header to determine full length */
+		return 0;
+	}
+	/* return full length decoded from header.
+	 * the return value may be larger than skb->len which
+	 * means framework must wait body coming.
+	 */
+	return 10;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock.c b/tools/testing/selftests/bpf/progs/test_spin_lock.c
index 5bd10409285b..d8d77bdffd3d 100644
--- a/tools/testing/selftests/bpf/progs/test_spin_lock.c
+++ b/tools/testing/selftests/bpf/progs/test_spin_lock.c
@@ -3,6 +3,7 @@
 #include <linux/bpf.h>
 #include <linux/version.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
 
 struct hmap_elem {
 	volatile int cnt;
@@ -89,6 +90,8 @@ int bpf_spin_lock_test(struct __sk_buff *skb)
 	credit = q->credit;
 	bpf_spin_unlock(&q->lock);
 
+	__sink(credit);
+
 	/* spin_lock in cgroup local storage */
 	cls = bpf_get_local_storage(&cls_map, 0);
 	bpf_spin_lock(&cls->lock);
@@ -98,4 +101,69 @@ int bpf_spin_lock_test(struct __sk_buff *skb)
 err:
 	return err;
 }
+
+struct bpf_spin_lock lockA __hidden SEC(".data.A");
+
+__noinline
+static int static_subprog(struct __sk_buff *ctx)
+{
+	volatile int ret = 0;
+
+	if (ctx->protocol)
+		return ret;
+	return ret + ctx->len;
+}
+
+__noinline
+static int static_subprog_lock(struct __sk_buff *ctx)
+{
+	volatile int ret = 0;
+
+	ret = static_subprog(ctx);
+	bpf_spin_lock(&lockA);
+	return ret + ctx->len;
+}
+
+__noinline
+static int static_subprog_unlock(struct __sk_buff *ctx)
+{
+	volatile int ret = 0;
+
+	ret = static_subprog(ctx);
+	bpf_spin_unlock(&lockA);
+	return ret + ctx->len;
+}
+
+SEC("tc")
+int lock_static_subprog_call(struct __sk_buff *ctx)
+{
+	int ret = 0;
+
+	bpf_spin_lock(&lockA);
+	if (ctx->mark == 42)
+		ret = static_subprog(ctx);
+	bpf_spin_unlock(&lockA);
+	return ret;
+}
+
+SEC("tc")
+int lock_static_subprog_lock(struct __sk_buff *ctx)
+{
+	int ret = 0;
+
+	ret = static_subprog_lock(ctx);
+	bpf_spin_unlock(&lockA);
+	return ret;
+}
+
+SEC("tc")
+int lock_static_subprog_unlock(struct __sk_buff *ctx)
+{
+	int ret = 0;
+
+	bpf_spin_lock(&lockA);
+	ret = static_subprog_unlock(ctx);
+	return ret;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c b/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c
index 86cd183ef6dc..f678ee6bd7ea 100644
--- a/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c
+++ b/tools/testing/selftests/bpf/progs/test_spin_lock_fail.c
@@ -28,8 +28,8 @@ struct {
 	},
 };
 
-SEC(".data.A") struct bpf_spin_lock lockA;
-SEC(".data.B") struct bpf_spin_lock lockB;
+static struct bpf_spin_lock lockA SEC(".data.A");
+static struct bpf_spin_lock lockB SEC(".data.B");
 
 SEC("?tc")
 int lock_id_kptr_preserve(void *ctx)
@@ -201,4 +201,117 @@ CHECK(innermapval_mapval, &iv->lock, &v->lock);
 
 #undef CHECK
 
+__noinline
+int global_subprog(struct __sk_buff *ctx)
+{
+	volatile int ret = 0;
+
+	if (ctx->protocol)
+		ret += ctx->protocol;
+	return ret + ctx->mark;
+}
+
+__noinline
+static int static_subprog_call_global(struct __sk_buff *ctx)
+{
+	volatile int ret = 0;
+
+	if (ctx->protocol)
+		return ret;
+	return ret + ctx->len + global_subprog(ctx);
+}
+
+SEC("?tc")
+int lock_global_subprog_call1(struct __sk_buff *ctx)
+{
+	int ret = 0;
+
+	bpf_spin_lock(&lockA);
+	if (ctx->mark == 42)
+		ret = global_subprog(ctx);
+	bpf_spin_unlock(&lockA);
+	return ret;
+}
+
+SEC("?tc")
+int lock_global_subprog_call2(struct __sk_buff *ctx)
+{
+	int ret = 0;
+
+	bpf_spin_lock(&lockA);
+	if (ctx->mark == 42)
+		ret = static_subprog_call_global(ctx);
+	bpf_spin_unlock(&lockA);
+	return ret;
+}
+
+int __noinline
+global_subprog_int(int i)
+{
+	if (i)
+		bpf_printk("%p", &i);
+	return i;
+}
+
+int __noinline
+global_sleepable_helper_subprog(int i)
+{
+	if (i)
+		bpf_copy_from_user(&i, sizeof(i), NULL);
+	return i;
+}
+
+int __noinline
+global_sleepable_kfunc_subprog(int i)
+{
+	if (i)
+		bpf_copy_from_user_str(&i, sizeof(i), NULL, 0);
+	global_subprog_int(i);
+	return i;
+}
+
+int __noinline
+global_subprog_calling_sleepable_global(int i)
+{
+	if (!i)
+		global_sleepable_kfunc_subprog(i);
+	return i;
+}
+
+SEC("?syscall")
+int lock_global_sleepable_helper_subprog(struct __sk_buff *ctx)
+{
+	int ret = 0;
+
+	bpf_spin_lock(&lockA);
+	if (ctx->mark == 42)
+		ret = global_sleepable_helper_subprog(ctx->mark);
+	bpf_spin_unlock(&lockA);
+	return ret;
+}
+
+SEC("?syscall")
+int lock_global_sleepable_kfunc_subprog(struct __sk_buff *ctx)
+{
+	int ret = 0;
+
+	bpf_spin_lock(&lockA);
+	if (ctx->mark == 42)
+		ret = global_sleepable_kfunc_subprog(ctx->mark);
+	bpf_spin_unlock(&lockA);
+	return ret;
+}
+
+SEC("?syscall")
+int lock_global_sleepable_subprog_indirect(struct __sk_buff *ctx)
+{
+	int ret = 0;
+
+	bpf_spin_lock(&lockA);
+	if (ctx->mark == 42)
+		ret = global_subprog_calling_sleepable_global(ctx->mark);
+	bpf_spin_unlock(&lockA);
+	return ret;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_subprogs.c b/tools/testing/selftests/bpf/progs/test_subprogs.c
index f8e9256cf18d..a8d602d7c88a 100644
--- a/tools/testing/selftests/bpf/progs/test_subprogs.c
+++ b/tools/testing/selftests/bpf/progs/test_subprogs.c
@@ -47,7 +47,7 @@ static __noinline int sub5(int v)
 	return sub1(v) - 1; /* compensates sub1()'s + 1 */
 }
 
-/* unfortunately verifier rejects `struct task_struct *t` as an unkown pointer
+/* unfortunately verifier rejects `struct task_struct *t` as an unknown pointer
  * type, so we need to accept pointer as integer and then cast it inside the
  * function
  */
diff --git a/tools/testing/selftests/bpf/progs/test_subprogs_extable.c b/tools/testing/selftests/bpf/progs/test_subprogs_extable.c
new file mode 100644
index 000000000000..dcac69f5928a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_subprogs_extable.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 8);
+	__type(key, __u32);
+	__type(value, __u64);
+} test_array SEC(".maps");
+
+unsigned int triggered;
+
+static __u64 test_cb(struct bpf_map *map, __u32 *key, __u64 *val, void *data)
+{
+	return 1;
+}
+
+SEC("fexit/bpf_testmod_return_ptr")
+int BPF_PROG(handle_fexit_ret_subprogs, int arg, struct file *ret)
+{
+	*(volatile int *)ret;
+	*(volatile int *)&ret->f_mode;
+	bpf_for_each_map_elem(&test_array, test_cb, NULL, 0);
+	triggered++;
+	return 0;
+}
+
+SEC("fexit/bpf_testmod_return_ptr")
+int BPF_PROG(handle_fexit_ret_subprogs2, int arg, struct file *ret)
+{
+	*(volatile int *)ret;
+	*(volatile int *)&ret->f_mode;
+	bpf_for_each_map_elem(&test_array, test_cb, NULL, 0);
+	triggered++;
+	return 0;
+}
+
+SEC("fexit/bpf_testmod_return_ptr")
+int BPF_PROG(handle_fexit_ret_subprogs3, int arg, struct file *ret)
+{
+	*(volatile int *)ret;
+	*(volatile int *)&ret->f_mode;
+	bpf_for_each_map_elem(&test_array, test_cb, NULL, 0);
+	triggered++;
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c
index 553a282d816a..548660e299a5 100644
--- a/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c
+++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop1.c
@@ -9,9 +9,8 @@
 
 #include <bpf/bpf_helpers.h>
 
-#ifndef ARRAY_SIZE
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-#endif
+#include "bpf_compiler.h"
+#include "bpf_misc.h"
 
 /* tcp_mem sysctl has only 3 ints, but this test is doing TCP_MEM_LOOPS */
 #define TCP_MEM_LOOPS 28  /* because 30 doesn't fit into 512 bytes of stack */
@@ -30,7 +29,7 @@ static __always_inline int is_tcp_mem(struct bpf_sysctl *ctx)
 	if (ret < 0 || ret != sizeof(tcp_mem_name) - 1)
 		return 0;
 
-#pragma clang loop unroll(disable)
+	__pragma_loop_no_unroll
 	for (i = 0; i < sizeof(tcp_mem_name); ++i)
 		if (name[i] != tcp_mem_name[i])
 			return 0;
@@ -59,7 +58,7 @@ int sysctl_tcp_mem(struct bpf_sysctl *ctx)
 	if (ret < 0 || ret >= MAX_VALUE_STR_LEN)
 		return 0;
 
-#pragma clang loop unroll(disable)
+	__pragma_loop_no_unroll
 	for (i = 0; i < ARRAY_SIZE(tcp_mem); ++i) {
 		ret = bpf_strtoul(value + off, MAX_ULONG_STR_LEN, 0,
 				  tcp_mem + i);
diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c
index 2b64bc563a12..81249d119a8b 100644
--- a/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c
+++ b/tools/testing/selftests/bpf/progs/test_sysctl_loop2.c
@@ -9,9 +9,8 @@
 
 #include <bpf/bpf_helpers.h>
 
-#ifndef ARRAY_SIZE
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-#endif
+#include "bpf_compiler.h"
+#include "bpf_misc.h"
 
 /* tcp_mem sysctl has only 3 ints, but this test is doing TCP_MEM_LOOPS */
 #define TCP_MEM_LOOPS 20  /* because 30 doesn't fit into 512 bytes of stack */
@@ -30,7 +29,7 @@ static __attribute__((noinline)) int is_tcp_mem(struct bpf_sysctl *ctx)
 	if (ret < 0 || ret != sizeof(tcp_mem_name) - 1)
 		return 0;
 
-#pragma clang loop unroll(disable)
+	__pragma_loop_no_unroll
 	for (i = 0; i < sizeof(tcp_mem_name); ++i)
 		if (name[i] != tcp_mem_name[i])
 			return 0;
@@ -57,7 +56,7 @@ int sysctl_tcp_mem(struct bpf_sysctl *ctx)
 	if (ret < 0 || ret >= MAX_VALUE_STR_LEN)
 		return 0;
 
-#pragma clang loop unroll(disable)
+	__pragma_loop_no_unroll
 	for (i = 0; i < ARRAY_SIZE(tcp_mem); ++i) {
 		ret = bpf_strtoul(value + off, MAX_ULONG_STR_LEN, 0,
 				  tcp_mem + i);
diff --git a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c
index 5489823c83fc..bbdd08764789 100644
--- a/tools/testing/selftests/bpf/progs/test_sysctl_prog.c
+++ b/tools/testing/selftests/bpf/progs/test_sysctl_prog.c
@@ -9,16 +9,15 @@
 
 #include <bpf/bpf_helpers.h>
 
+#include "bpf_compiler.h"
+#include "bpf_misc.h"
+
 /* Max supported length of a string with unsigned long in base 10 (pow2 - 1). */
 #define MAX_ULONG_STR_LEN 0xF
 
 /* Max supported length of sysctl value string (pow2). */
 #define MAX_VALUE_STR_LEN 0x40
 
-#ifndef ARRAY_SIZE
-#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-#endif
-
 const char tcp_mem_name[] = "net/ipv4/tcp_mem";
 static __always_inline int is_tcp_mem(struct bpf_sysctl *ctx)
 {
@@ -31,7 +30,7 @@ static __always_inline int is_tcp_mem(struct bpf_sysctl *ctx)
 	if (ret < 0 || ret != sizeof(tcp_mem_name) - 1)
 		return 0;
 
-#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (i = 0; i < sizeof(tcp_mem_name); ++i)
 		if (name[i] != tcp_mem_name[i])
 			return 0;
@@ -57,7 +56,7 @@ int sysctl_tcp_mem(struct bpf_sysctl *ctx)
 	if (ret < 0 || ret >= MAX_VALUE_STR_LEN)
 		return 0;
 
-#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (i = 0; i < ARRAY_SIZE(tcp_mem); ++i) {
 		ret = bpf_strtoul(value + off, MAX_ULONG_STR_LEN, 0,
 				  tcp_mem + i);
diff --git a/tools/testing/selftests/bpf/progs/test_task_local_data.c b/tools/testing/selftests/bpf/progs/test_task_local_data.c
new file mode 100644
index 000000000000..fffafc013044
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_task_local_data.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+
+#include "task_local_data.bpf.h"
+
+struct tld_keys {
+	tld_key_t value0;
+	tld_key_t value1;
+	tld_key_t value2;
+	tld_key_t value_not_exist;
+};
+
+struct test_tld_struct {
+	__u64 a;
+	__u64 b;
+	__u64 c;
+	__u64 d;
+};
+
+int test_value0;
+int test_value1;
+struct test_tld_struct test_value2;
+
+SEC("syscall")
+int task_main(void *ctx)
+{
+	struct tld_object tld_obj;
+	struct test_tld_struct *struct_p;
+	struct task_struct *task;
+	int err, *int_p;
+
+	task = bpf_get_current_task_btf();
+	err = tld_object_init(task, &tld_obj);
+	if (err)
+		return 1;
+
+	int_p = tld_get_data(&tld_obj, value0, "value0", sizeof(int));
+	if (int_p)
+		test_value0 = *int_p;
+	else
+		return 2;
+
+	int_p = tld_get_data(&tld_obj, value1, "value1", sizeof(int));
+	if (int_p)
+		test_value1 = *int_p;
+	else
+		return 3;
+
+	struct_p = tld_get_data(&tld_obj, value2, "value2", sizeof(struct test_tld_struct));
+	if (struct_p)
+		test_value2 = *struct_p;
+	else
+		return 4;
+
+	int_p = tld_get_data(&tld_obj, value_not_exist, "value_not_exist", sizeof(int));
+	if (int_p)
+		return 5;
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c
new file mode 100644
index 000000000000..0b74b8bd22e8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Bytedance */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+
+struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym;
+long bpf_task_under_cgroup(struct task_struct *task, struct cgroup *ancestor) __ksym;
+void bpf_cgroup_release(struct cgroup *p) __ksym;
+struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym;
+void bpf_task_release(struct task_struct *p) __ksym;
+
+const volatile int local_pid;
+const volatile __u64 cgid;
+int remote_pid;
+
+SEC("tp_btf/task_newtask")
+int BPF_PROG(tp_btf_run, struct task_struct *task, u64 clone_flags)
+{
+	struct cgroup *cgrp = NULL;
+	struct task_struct *acquired;
+
+	if (local_pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	acquired = bpf_task_acquire(task);
+	if (!acquired)
+		return 0;
+
+	if (local_pid == acquired->tgid)
+		goto out;
+
+	cgrp = bpf_cgroup_from_id(cgid);
+	if (!cgrp)
+		goto out;
+
+	if (bpf_task_under_cgroup(acquired, cgrp))
+		remote_pid = acquired->tgid;
+
+out:
+	if (cgrp)
+		bpf_cgroup_release(cgrp);
+	bpf_task_release(acquired);
+
+	return 0;
+}
+
+SEC("lsm.s/bpf")
+int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
+{
+	struct cgroup *cgrp = NULL;
+	struct task_struct *task;
+	int ret = 0;
+
+	task = bpf_get_current_task_btf();
+	if (local_pid != task->pid)
+		return 0;
+
+	if (cmd != BPF_LINK_CREATE)
+		return 0;
+
+	/* 1 is the root cgroup */
+	cgrp = bpf_cgroup_from_id(1);
+	if (!cgrp)
+		goto out;
+	if (!bpf_task_under_cgroup(task, cgrp))
+		ret = -1;
+	bpf_cgroup_release(cgrp);
+
+out:
+	return ret;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_tc_bpf.c b/tools/testing/selftests/bpf/progs/test_tc_bpf.c
index d28ca8d1f3d0..ef7da419632a 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_bpf.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_bpf.c
@@ -2,6 +2,8 @@
 
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
 
 /* Dummy prog to test TC-BPF API */
 
@@ -10,3 +12,14 @@ int cls(struct __sk_buff *skb)
 {
 	return 0;
 }
+
+/* Prog to verify tc-bpf without cap_sys_admin and cap_perfmon */
+SEC("tcx/ingress")
+int pkt_ptr(struct __sk_buff *skb)
+{
+	struct iphdr *iph = (void *)(long)skb->data + sizeof(struct ethhdr);
+
+	if ((long)(iph + 1) > (long)skb->data_end)
+		return 1;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_tc_change_tail.c b/tools/testing/selftests/bpf/progs/test_tc_change_tail.c
new file mode 100644
index 000000000000..fcba8299f0bc
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_tc_change_tail.c
@@ -0,0 +1,106 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+#ifndef PAGE_SIZE
+#define PAGE_SIZE __PAGE_SIZE
+#endif
+#define BPF_SKB_MAX_LEN (PAGE_SIZE << 2)
+
+long change_tail_ret = 1;
+
+static __always_inline struct iphdr *parse_ip_header(struct __sk_buff *skb, int *ip_proto)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	void *data = (void *)(long)skb->data;
+	struct ethhdr *eth = data;
+	struct iphdr *iph;
+
+	/* Verify Ethernet header */
+	if ((void *)(data + sizeof(*eth)) > data_end)
+		return NULL;
+
+	/* Skip Ethernet header to get to IP header */
+	iph = (void *)(data + sizeof(struct ethhdr));
+
+	/* Verify IP header */
+	if ((void *)(data + sizeof(struct ethhdr) + sizeof(*iph)) > data_end)
+		return NULL;
+
+	/* Basic IP header validation */
+	if (iph->version != 4)  /* Only support IPv4 */
+		return NULL;
+
+	if (iph->ihl < 5)  /* Minimum IP header length */
+		return NULL;
+
+	*ip_proto = iph->protocol;
+	return iph;
+}
+
+static __always_inline struct udphdr *parse_udp_header(struct __sk_buff *skb, struct iphdr *iph)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	void *hdr = (void *)iph;
+	struct udphdr *udp;
+
+	/* Calculate UDP header position */
+	udp = hdr + (iph->ihl * 4);
+	hdr = (void *)udp;
+
+	/* Verify UDP header bounds */
+	if ((void *)(hdr + sizeof(*udp)) > data_end)
+		return NULL;
+
+	return udp;
+}
+
+SEC("tc/ingress")
+int change_tail(struct __sk_buff *skb)
+{
+	int len = skb->len;
+	struct udphdr *udp;
+	struct iphdr *iph;
+	void *data_end;
+	char *payload;
+	int ip_proto;
+
+	bpf_skb_pull_data(skb, len);
+
+	data_end = (void *)(long)skb->data_end;
+	iph = parse_ip_header(skb, &ip_proto);
+	if (!iph)
+		return TCX_PASS;
+
+	if (ip_proto != IPPROTO_UDP)
+		return TCX_PASS;
+
+	udp = parse_udp_header(skb, iph);
+	if (!udp)
+		return TCX_PASS;
+
+	payload = (char *)udp + (sizeof(struct udphdr));
+	if (payload + 1 > (char *)data_end)
+		return TCX_PASS;
+
+	if (payload[0] == 'T') { /* Trim the packet */
+		change_tail_ret = bpf_skb_change_tail(skb, len - 1, 0);
+		if (!change_tail_ret)
+			bpf_skb_change_tail(skb, len, 0);
+		return TCX_PASS;
+	} else if (payload[0] == 'G') { /* Grow the packet */
+		change_tail_ret = bpf_skb_change_tail(skb, len + 1, 0);
+		if (!change_tail_ret)
+			bpf_skb_change_tail(skb, len, 0);
+		return TCX_PASS;
+	} else if (payload[0] == 'E') { /* Error */
+		change_tail_ret = bpf_skb_change_tail(skb, BPF_SKB_MAX_LEN, 0);
+		return TCX_PASS;
+	} else if (payload[0] == 'Z') { /* Zero */
+		change_tail_ret = bpf_skb_change_tail(skb, 0, 0);
+		return TCX_PASS;
+	}
+	return TCX_DROP;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_tc_dtime.c b/tools/testing/selftests/bpf/progs/test_tc_dtime.c
index 125beec31834..ca8e8734d901 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_dtime.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_dtime.c
@@ -163,9 +163,9 @@ static int skb_get_type(struct __sk_buff *skb)
 		ip6h = data + sizeof(struct ethhdr);
 		if (ip6h + 1 > data_end)
 			return -1;
-		if (v6_equal(ip6h->saddr, (struct in6_addr)ip6_src))
+		if (v6_equal(ip6h->saddr, (struct in6_addr){{ip6_src}}))
 			ns = SRC_NS;
-		else if (v6_equal(ip6h->saddr, (struct in6_addr)ip6_dst))
+		else if (v6_equal(ip6h->saddr, (struct in6_addr){{ip6_dst}}))
 			ns = DST_NS;
 		inet_proto = ip6h->nexthdr;
 		trans = ip6h + 1;
@@ -222,17 +222,21 @@ int egress_host(struct __sk_buff *skb)
 		return TC_ACT_OK;
 
 	if (skb_proto(skb_type) == IPPROTO_TCP) {
-		if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO &&
+		if (skb->tstamp_type == BPF_SKB_CLOCK_MONOTONIC &&
 		    skb->tstamp)
 			inc_dtimes(EGRESS_ENDHOST);
 		else
 			inc_errs(EGRESS_ENDHOST);
-	} else {
-		if (skb->tstamp_type == BPF_SKB_TSTAMP_UNSPEC &&
+	} else if (skb_proto(skb_type) == IPPROTO_UDP) {
+		if (skb->tstamp_type == BPF_SKB_CLOCK_TAI &&
 		    skb->tstamp)
 			inc_dtimes(EGRESS_ENDHOST);
 		else
 			inc_errs(EGRESS_ENDHOST);
+	} else {
+		if (skb->tstamp_type == BPF_SKB_CLOCK_REALTIME &&
+		    skb->tstamp)
+			inc_errs(EGRESS_ENDHOST);
 	}
 
 	skb->tstamp = EGRESS_ENDHOST_MAGIC;
@@ -252,7 +256,7 @@ int ingress_host(struct __sk_buff *skb)
 	if (!skb_type)
 		return TC_ACT_OK;
 
-	if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO &&
+	if (skb->tstamp_type == BPF_SKB_CLOCK_MONOTONIC &&
 	    skb->tstamp == EGRESS_FWDNS_MAGIC)
 		inc_dtimes(INGRESS_ENDHOST);
 	else
@@ -315,7 +319,6 @@ int egress_fwdns_prio100(struct __sk_buff *skb)
 SEC("tc")
 int ingress_fwdns_prio101(struct __sk_buff *skb)
 {
-	__u64 expected_dtime = EGRESS_ENDHOST_MAGIC;
 	int skb_type;
 
 	skb_type = skb_get_type(skb);
@@ -323,29 +326,24 @@ int ingress_fwdns_prio101(struct __sk_buff *skb)
 		/* Should have handled in prio100 */
 		return TC_ACT_SHOT;
 
-	if (skb_proto(skb_type) == IPPROTO_UDP)
-		expected_dtime = 0;
-
 	if (skb->tstamp_type) {
 		if (fwdns_clear_dtime() ||
-		    skb->tstamp_type != BPF_SKB_TSTAMP_DELIVERY_MONO ||
-		    skb->tstamp != expected_dtime)
+		    (skb->tstamp_type != BPF_SKB_CLOCK_MONOTONIC &&
+		    skb->tstamp_type != BPF_SKB_CLOCK_TAI) ||
+		    skb->tstamp != EGRESS_ENDHOST_MAGIC)
 			inc_errs(INGRESS_FWDNS_P101);
 		else
 			inc_dtimes(INGRESS_FWDNS_P101);
 	} else {
-		if (!fwdns_clear_dtime() && expected_dtime)
+		if (!fwdns_clear_dtime())
 			inc_errs(INGRESS_FWDNS_P101);
 	}
 
-	if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO) {
+	if (skb->tstamp_type == BPF_SKB_CLOCK_MONOTONIC) {
 		skb->tstamp = INGRESS_FWDNS_MAGIC;
 	} else {
 		if (bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC,
-				       BPF_SKB_TSTAMP_DELIVERY_MONO))
-			inc_errs(SET_DTIME);
-		if (!bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC,
-					BPF_SKB_TSTAMP_UNSPEC))
+				       BPF_SKB_CLOCK_MONOTONIC))
 			inc_errs(SET_DTIME);
 	}
 
@@ -370,7 +368,7 @@ int egress_fwdns_prio101(struct __sk_buff *skb)
 
 	if (skb->tstamp_type) {
 		if (fwdns_clear_dtime() ||
-		    skb->tstamp_type != BPF_SKB_TSTAMP_DELIVERY_MONO ||
+		    skb->tstamp_type != BPF_SKB_CLOCK_MONOTONIC ||
 		    skb->tstamp != INGRESS_FWDNS_MAGIC)
 			inc_errs(EGRESS_FWDNS_P101);
 		else
@@ -380,14 +378,11 @@ int egress_fwdns_prio101(struct __sk_buff *skb)
 			inc_errs(EGRESS_FWDNS_P101);
 	}
 
-	if (skb->tstamp_type == BPF_SKB_TSTAMP_DELIVERY_MONO) {
+	if (skb->tstamp_type == BPF_SKB_CLOCK_MONOTONIC) {
 		skb->tstamp = EGRESS_FWDNS_MAGIC;
 	} else {
 		if (bpf_skb_set_tstamp(skb, EGRESS_FWDNS_MAGIC,
-				       BPF_SKB_TSTAMP_DELIVERY_MONO))
-			inc_errs(SET_DTIME);
-		if (!bpf_skb_set_tstamp(skb, INGRESS_FWDNS_MAGIC,
-					BPF_SKB_TSTAMP_UNSPEC))
+				       BPF_SKB_CLOCK_MONOTONIC))
 			inc_errs(SET_DTIME);
 	}
 
diff --git a/tools/testing/selftests/bpf/progs/test_tc_edt.c b/tools/testing/selftests/bpf/progs/test_tc_edt.c
index 950a70b61e74..4f6f03122d61 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_edt.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_edt.c
@@ -14,7 +14,6 @@
 #define TIME_HORIZON_NS (2000 * 1000 * 1000)
 #define NS_PER_SEC 1000000000
 #define ECN_HORIZON_NS 5000000
-#define THROTTLE_RATE_BPS (5 * 1000 * 1000)
 
 /* flow_key => last_tstamp timestamp used */
 struct {
@@ -24,12 +23,13 @@ struct {
 	__uint(max_entries, 1);
 } flow_map SEC(".maps");
 
+__uint64_t target_rate;
+
 static inline int throttle_flow(struct __sk_buff *skb)
 {
 	int key = 0;
 	uint64_t *last_tstamp = bpf_map_lookup_elem(&flow_map, &key);
-	uint64_t delay_ns = ((uint64_t)skb->len) * NS_PER_SEC /
-			THROTTLE_RATE_BPS;
+	uint64_t delay_ns = ((uint64_t)skb->len) * NS_PER_SEC / target_rate;
 	uint64_t now = bpf_ktime_get_ns();
 	uint64_t tstamp, next_tstamp = 0;
 
@@ -70,7 +70,7 @@ static inline int handle_tcp(struct __sk_buff *skb, struct tcphdr *tcp)
 	if ((void *)(tcp + 1) > data_end)
 		return TC_ACT_SHOT;
 
-	if (tcp->dest == bpf_htons(9000))
+	if (tcp->source == bpf_htons(9000))
 		return throttle_flow(skb);
 
 	return TC_ACT_OK;
@@ -99,7 +99,8 @@ static inline int handle_ipv4(struct __sk_buff *skb)
 	return TC_ACT_OK;
 }
 
-SEC("cls_test") int tc_prog(struct __sk_buff *skb)
+SEC("tc")
+int tc_prog(struct __sk_buff *skb)
 {
 	if (skb->protocol == bpf_htons(ETH_P_IP))
 		return handle_ipv4(skb);
diff --git a/tools/testing/selftests/bpf/progs/test_tc_link.c b/tools/testing/selftests/bpf/progs/test_tc_link.c
new file mode 100644
index 000000000000..630f12e51b07
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_tc_link.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+#include <stdbool.h>
+
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/stddef.h>
+#include <linux/if_packet.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+
+char LICENSE[] SEC("license") = "GPL";
+
+bool seen_tc1;
+bool seen_tc2;
+bool seen_tc3;
+bool seen_tc4;
+bool seen_tc5;
+bool seen_tc6;
+bool seen_tc7;
+bool seen_tc8;
+
+bool set_type;
+
+bool seen_eth;
+bool seen_host;
+bool seen_mcast;
+
+int mark, prio;
+unsigned short headroom, tailroom;
+
+SEC("tc/ingress")
+int tc1(struct __sk_buff *skb)
+{
+	struct ethhdr eth = {};
+
+	if (skb->protocol != __bpf_constant_htons(ETH_P_IP))
+		goto out;
+	if (bpf_skb_load_bytes(skb, 0, &eth, sizeof(eth)))
+		goto out;
+	seen_eth = eth.h_proto == bpf_htons(ETH_P_IP);
+	seen_host = skb->pkt_type == PACKET_HOST;
+	if (seen_host && set_type) {
+		eth.h_dest[0] = 4;
+		if (bpf_skb_store_bytes(skb, 0, &eth, sizeof(eth), 0))
+			goto fail;
+		bpf_skb_change_type(skb, PACKET_MULTICAST);
+	}
+out:
+	seen_tc1 = true;
+fail:
+	return TCX_NEXT;
+}
+
+SEC("tc/egress")
+int tc2(struct __sk_buff *skb)
+{
+	seen_tc2 = true;
+	return TCX_NEXT;
+}
+
+SEC("tc/egress")
+int tc3(struct __sk_buff *skb)
+{
+	seen_tc3 = true;
+	return TCX_NEXT;
+}
+
+SEC("tc/egress")
+int tc4(struct __sk_buff *skb)
+{
+	seen_tc4 = true;
+	return TCX_NEXT;
+}
+
+SEC("tc/egress")
+int tc5(struct __sk_buff *skb)
+{
+	seen_tc5 = true;
+	return TCX_PASS;
+}
+
+SEC("tc/egress")
+int tc6(struct __sk_buff *skb)
+{
+	seen_tc6 = true;
+	return TCX_PASS;
+}
+
+SEC("tc/ingress")
+int tc7(struct __sk_buff *skb)
+{
+	struct ethhdr eth = {};
+
+	if (skb->protocol != __bpf_constant_htons(ETH_P_IP))
+		goto out;
+	if (bpf_skb_load_bytes(skb, 0, &eth, sizeof(eth)))
+		goto out;
+	if (eth.h_dest[0] == 4 && set_type) {
+		seen_mcast = skb->pkt_type == PACKET_MULTICAST;
+		bpf_skb_change_type(skb, PACKET_HOST);
+	}
+out:
+	seen_tc7 = true;
+	return TCX_PASS;
+}
+
+struct sk_buff {
+	struct net_device *dev;
+};
+
+struct net_device {
+	unsigned short needed_headroom;
+	unsigned short needed_tailroom;
+};
+
+SEC("tc/egress")
+int tc8(struct __sk_buff *skb)
+{
+	struct net_device *dev = BPF_CORE_READ((struct sk_buff *)skb, dev);
+
+	seen_tc8 = true;
+	mark = skb->mark;
+	prio = skb->priority;
+	headroom = BPF_CORE_READ(dev, needed_headroom);
+	tailroom = BPF_CORE_READ(dev, needed_tailroom);
+	return TCX_PASS;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh.c b/tools/testing/selftests/bpf/progs/test_tc_neigh.c
index 3e32ea375ab4..de15155f2609 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_neigh.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_neigh.c
@@ -94,7 +94,7 @@ int tc_dst(struct __sk_buff *skb)
 		redirect = is_remote_ep_v4(skb, __bpf_constant_htonl(ip4_src));
 		break;
 	case __bpf_constant_htons(ETH_P_IPV6):
-		redirect = is_remote_ep_v6(skb, (struct in6_addr)ip6_src);
+		redirect = is_remote_ep_v6(skb, (struct in6_addr){{ip6_src}});
 		break;
 	}
 
@@ -119,7 +119,7 @@ int tc_src(struct __sk_buff *skb)
 		redirect = is_remote_ep_v4(skb, __bpf_constant_htonl(ip4_dst));
 		break;
 	case __bpf_constant_htons(ETH_P_IPV6):
-		redirect = is_remote_ep_v6(skb, (struct in6_addr)ip6_dst);
+		redirect = is_remote_ep_v6(skb, (struct in6_addr){{ip6_dst}});
 		break;
 	}
 
diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
index a0e7762b1e5a..7330c61b5730 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
@@ -2,28 +2,27 @@
 
 /* In-place tunneling */
 
-#include <stdbool.h>
-#include <string.h>
-
-#include <linux/stddef.h>
-#include <linux/bpf.h>
-#include <linux/if_ether.h>
-#include <linux/in.h>
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-#include <linux/mpls.h>
-#include <linux/tcp.h>
-#include <linux/udp.h>
-#include <linux/pkt_cls.h>
-#include <linux/types.h>
+#include <vmlinux.h>
 
-#include <bpf/bpf_endian.h>
 #include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include "bpf_tracing_net.h"
+#include "bpf_compiler.h"
+
+#pragma GCC diagnostic ignored "-Waddress-of-packed-member"
 
 static const int cfg_port = 8000;
 
 static const int cfg_udp_src = 20000;
 
+#define ETH_P_MPLS_UC	0x8847
+#define ETH_P_TEB	0x6558
+
+#define MPLS_LS_S_MASK	0x00000100
+#define BPF_F_ADJ_ROOM_ENCAP_L2(len)			\
+	(((__u64)len & BPF_ADJ_ROOM_ENCAP_L2_MASK)	\
+	 << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
+
 #define	L2_PAD_SZ	(sizeof(struct vxlanhdr) + ETH_HLEN)
 
 #define	UDP_PORT		5555
@@ -33,20 +32,17 @@ static const int cfg_udp_src = 20000;
 
 #define	EXTPROTO_VXLAN	0x1
 
-#define	VXLAN_N_VID     (1u << 24)
-#define	VXLAN_VNI_MASK	bpf_htonl((VXLAN_N_VID - 1) << 8)
-#define	VXLAN_FLAGS     0x8
-#define	VXLAN_VNI       1
+#define	VXLAN_FLAGS     bpf_htonl(1<<27)
+#define	VNI_ID		1
+#define	VXLAN_VNI	bpf_htonl(VNI_ID << 8)
+
+#ifndef NEXTHDR_DEST
+#define NEXTHDR_DEST	60
+#endif
 
 /* MPLS label 1000 with S bit (last label) set and ttl of 255. */
 static const __u32 mpls_label = __bpf_constant_htonl(1000 << 12 |
 						     MPLS_LS_S_MASK | 0xff);
-
-struct vxlanhdr {
-	__be32 vx_flags;
-	__be32 vx_vni;
-} __attribute__((packed));
-
 struct gre_hdr {
 	__be16 flags;
 	__be16 protocol;
@@ -77,7 +73,7 @@ static __always_inline void set_ipv4_csum(struct iphdr *iph)
 
 	iph->check = 0;
 
-#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (i = 0, csum = 0; i < sizeof(*iph) >> 1; i++)
 		csum += *iph16++;
 
@@ -87,8 +83,8 @@ static __always_inline void set_ipv4_csum(struct iphdr *iph)
 static __always_inline int __encap_ipv4(struct __sk_buff *skb, __u8 encap_proto,
 					__u16 l2_proto, __u16 ext_proto)
 {
+	struct iphdr iph_inner = {0};
 	__u16 udp_dst = UDP_PORT;
-	struct iphdr iph_inner;
 	struct v4hdr h_outer;
 	struct tcphdr tcph;
 	int olen, l2_len;
@@ -115,7 +111,6 @@ static __always_inline int __encap_ipv4(struct __sk_buff *skb, __u8 encap_proto,
 			return TC_ACT_OK;
 
 		/* Derive the IPv4 header fields from the IPv6 header */
-		memset(&iph_inner, 0, sizeof(iph_inner));
 		iph_inner.version = 4;
 		iph_inner.ihl = 5;
 		iph_inner.tot_len = bpf_htons(sizeof(iph6_inner) +
@@ -203,7 +198,7 @@ static __always_inline int __encap_ipv4(struct __sk_buff *skb, __u8 encap_proto,
 			struct vxlanhdr *vxlan_hdr = (struct vxlanhdr *)l2_hdr;
 
 			vxlan_hdr->vx_flags = VXLAN_FLAGS;
-			vxlan_hdr->vx_vni = bpf_htonl((VXLAN_VNI & VXLAN_VNI_MASK) << 8);
+			vxlan_hdr->vx_vni = VXLAN_VNI;
 
 			l2_hdr += sizeof(struct vxlanhdr);
 		}
@@ -333,7 +328,7 @@ static __always_inline int __encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
 			struct vxlanhdr *vxlan_hdr = (struct vxlanhdr *)l2_hdr;
 
 			vxlan_hdr->vx_flags = VXLAN_FLAGS;
-			vxlan_hdr->vx_vni = bpf_htonl((VXLAN_VNI & VXLAN_VNI_MASK) << 8);
+			vxlan_hdr->vx_vni = VXLAN_VNI;
 
 			l2_hdr += sizeof(struct vxlanhdr);
 		}
@@ -363,13 +358,67 @@ static __always_inline int __encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
 	return TC_ACT_OK;
 }
 
+static int encap_ipv6_ipip6(struct __sk_buff *skb)
+{
+	struct v6hdr h_outer = {0};
+	struct iphdr iph_inner;
+	struct tcphdr tcph;
+	struct ethhdr eth;
+	__u64 flags;
+	int olen;
+
+	if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner,
+			       sizeof(iph_inner)) < 0)
+		return TC_ACT_OK;
+
+	/* filter only packets we want */
+	if (bpf_skb_load_bytes(skb, ETH_HLEN + (iph_inner.ihl << 2),
+			       &tcph, sizeof(tcph)) < 0)
+		return TC_ACT_OK;
+
+	if (tcph.dest != __bpf_constant_htons(cfg_port))
+		return TC_ACT_OK;
+
+	olen = sizeof(h_outer.ip);
+
+	flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV6;
+
+	/* add room between mac and network header */
+	if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_MAC, flags))
+		return TC_ACT_SHOT;
+
+	/* prepare new outer network header */
+	h_outer.ip.version = 6;
+	h_outer.ip.hop_limit = iph_inner.ttl;
+	h_outer.ip.saddr.in6_u.u6_addr8[1] = 0xfd;
+	h_outer.ip.saddr.in6_u.u6_addr8[15] = 1;
+	h_outer.ip.daddr.in6_u.u6_addr8[1] = 0xfd;
+	h_outer.ip.daddr.in6_u.u6_addr8[15] = 2;
+	h_outer.ip.payload_len = iph_inner.tot_len;
+	h_outer.ip.nexthdr = IPPROTO_IPIP;
+
+	/* store new outer network header */
+	if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen,
+				BPF_F_INVALIDATE_HASH) < 0)
+		return TC_ACT_SHOT;
+
+	/* update eth->h_proto */
+	if (bpf_skb_load_bytes(skb, 0, &eth, sizeof(eth)) < 0)
+		return TC_ACT_SHOT;
+	eth.h_proto = bpf_htons(ETH_P_IPV6);
+	if (bpf_skb_store_bytes(skb, 0, &eth, sizeof(eth), 0) < 0)
+		return TC_ACT_SHOT;
+
+	return TC_ACT_OK;
+}
+
 static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
 				      __u16 l2_proto)
 {
 	return __encap_ipv6(skb, encap_proto, l2_proto, 0);
 }
 
-SEC("encap_ipip_none")
+SEC("tc")
 int __encap_ipip_none(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
@@ -378,7 +427,7 @@ int __encap_ipip_none(struct __sk_buff *skb)
 		return TC_ACT_OK;
 }
 
-SEC("encap_gre_none")
+SEC("tc")
 int __encap_gre_none(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
@@ -387,7 +436,7 @@ int __encap_gre_none(struct __sk_buff *skb)
 		return TC_ACT_OK;
 }
 
-SEC("encap_gre_mpls")
+SEC("tc")
 int __encap_gre_mpls(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
@@ -396,7 +445,7 @@ int __encap_gre_mpls(struct __sk_buff *skb)
 		return TC_ACT_OK;
 }
 
-SEC("encap_gre_eth")
+SEC("tc")
 int __encap_gre_eth(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
@@ -405,7 +454,7 @@ int __encap_gre_eth(struct __sk_buff *skb)
 		return TC_ACT_OK;
 }
 
-SEC("encap_udp_none")
+SEC("tc")
 int __encap_udp_none(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
@@ -414,7 +463,7 @@ int __encap_udp_none(struct __sk_buff *skb)
 		return TC_ACT_OK;
 }
 
-SEC("encap_udp_mpls")
+SEC("tc")
 int __encap_udp_mpls(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
@@ -423,7 +472,7 @@ int __encap_udp_mpls(struct __sk_buff *skb)
 		return TC_ACT_OK;
 }
 
-SEC("encap_udp_eth")
+SEC("tc")
 int __encap_udp_eth(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
@@ -432,7 +481,7 @@ int __encap_udp_eth(struct __sk_buff *skb)
 		return TC_ACT_OK;
 }
 
-SEC("encap_vxlan_eth")
+SEC("tc")
 int __encap_vxlan_eth(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
@@ -443,7 +492,7 @@ int __encap_vxlan_eth(struct __sk_buff *skb)
 		return TC_ACT_OK;
 }
 
-SEC("encap_sit_none")
+SEC("tc")
 int __encap_sit_none(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
@@ -452,7 +501,7 @@ int __encap_sit_none(struct __sk_buff *skb)
 		return TC_ACT_OK;
 }
 
-SEC("encap_ip6tnl_none")
+SEC("tc")
 int __encap_ip6tnl_none(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
@@ -461,7 +510,16 @@ int __encap_ip6tnl_none(struct __sk_buff *skb)
 		return TC_ACT_OK;
 }
 
-SEC("encap_ip6gre_none")
+SEC("tc")
+int __encap_ipip6_none(struct __sk_buff *skb)
+{
+	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
+		return encap_ipv6_ipip6(skb);
+	else
+		return TC_ACT_OK;
+}
+
+SEC("tc")
 int __encap_ip6gre_none(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
@@ -470,7 +528,7 @@ int __encap_ip6gre_none(struct __sk_buff *skb)
 		return TC_ACT_OK;
 }
 
-SEC("encap_ip6gre_mpls")
+SEC("tc")
 int __encap_ip6gre_mpls(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
@@ -479,7 +537,7 @@ int __encap_ip6gre_mpls(struct __sk_buff *skb)
 		return TC_ACT_OK;
 }
 
-SEC("encap_ip6gre_eth")
+SEC("tc")
 int __encap_ip6gre_eth(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
@@ -488,7 +546,7 @@ int __encap_ip6gre_eth(struct __sk_buff *skb)
 		return TC_ACT_OK;
 }
 
-SEC("encap_ip6udp_none")
+SEC("tc")
 int __encap_ip6udp_none(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
@@ -497,7 +555,7 @@ int __encap_ip6udp_none(struct __sk_buff *skb)
 		return TC_ACT_OK;
 }
 
-SEC("encap_ip6udp_mpls")
+SEC("tc")
 int __encap_ip6udp_mpls(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
@@ -506,7 +564,7 @@ int __encap_ip6udp_mpls(struct __sk_buff *skb)
 		return TC_ACT_OK;
 }
 
-SEC("encap_ip6udp_eth")
+SEC("tc")
 int __encap_ip6udp_eth(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
@@ -515,7 +573,7 @@ int __encap_ip6udp_eth(struct __sk_buff *skb)
 		return TC_ACT_OK;
 }
 
-SEC("encap_ip6vxlan_eth")
+SEC("tc")
 int __encap_ip6vxlan_eth(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
@@ -528,13 +586,33 @@ int __encap_ip6vxlan_eth(struct __sk_buff *skb)
 
 static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
 {
+	__u64 flags = BPF_F_ADJ_ROOM_FIXED_GSO;
+	struct ipv6_opt_hdr ip6_opt_hdr;
 	struct gre_hdr greh;
 	struct udphdr udph;
 	int olen = len;
 
 	switch (proto) {
 	case IPPROTO_IPIP:
+		flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV4;
+		break;
 	case IPPROTO_IPV6:
+		flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV6;
+		break;
+	case NEXTHDR_DEST:
+		if (bpf_skb_load_bytes(skb, off + len, &ip6_opt_hdr,
+				       sizeof(ip6_opt_hdr)) < 0)
+			return TC_ACT_OK;
+		switch (ip6_opt_hdr.nexthdr) {
+		case IPPROTO_IPIP:
+			flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV4;
+			break;
+		case IPPROTO_IPV6:
+			flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV6;
+			break;
+		default:
+			return TC_ACT_OK;
+		}
 		break;
 	case IPPROTO_GRE:
 		olen += sizeof(struct gre_hdr);
@@ -569,8 +647,7 @@ static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
 		return TC_ACT_OK;
 	}
 
-	if (bpf_skb_adjust_room(skb, -olen, BPF_ADJ_ROOM_MAC,
-				BPF_F_ADJ_ROOM_FIXED_GSO))
+	if (bpf_skb_adjust_room(skb, -olen, BPF_ADJ_ROOM_MAC, flags))
 		return TC_ACT_SHOT;
 
 	return TC_ACT_OK;
@@ -603,7 +680,7 @@ static int decap_ipv6(struct __sk_buff *skb)
 			      iph_outer.nexthdr);
 }
 
-SEC("decap")
+SEC("tc")
 int decap_f(struct __sk_buff *skb)
 {
 	switch (skb->protocol) {
diff --git a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c
deleted file mode 100644
index 6edebce563b5..000000000000
--- a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c
+++ /dev/null
@@ -1,167 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright (c) 2018 Facebook
-// Copyright (c) 2019 Cloudflare
-
-#include <string.h>
-
-#include <linux/bpf.h>
-#include <linux/pkt_cls.h>
-#include <linux/if_ether.h>
-#include <linux/in.h>
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-#include <sys/socket.h>
-#include <linux/tcp.h>
-
-#include <bpf/bpf_helpers.h>
-#include <bpf/bpf_endian.h>
-
-struct {
-	__uint(type, BPF_MAP_TYPE_ARRAY);
-	__type(key, __u32);
-	__type(value, __u32);
-	__uint(max_entries, 3);
-} results SEC(".maps");
-
-static __always_inline __s64 gen_syncookie(void *data_end, struct bpf_sock *sk,
-					   void *iph, __u32 ip_size,
-					   struct tcphdr *tcph)
-{
-	__u32 thlen = tcph->doff * 4;
-
-	if (tcph->syn && !tcph->ack) {
-		// packet should only have an MSS option
-		if (thlen != 24)
-			return 0;
-
-		if ((void *)tcph + thlen > data_end)
-			return 0;
-
-		return bpf_tcp_gen_syncookie(sk, iph, ip_size, tcph, thlen);
-	}
-	return 0;
-}
-
-static __always_inline void check_syncookie(void *ctx, void *data,
-					    void *data_end)
-{
-	struct bpf_sock_tuple tup;
-	struct bpf_sock *sk;
-	struct ethhdr *ethh;
-	struct iphdr *ipv4h;
-	struct ipv6hdr *ipv6h;
-	struct tcphdr *tcph;
-	int ret;
-	__u32 key_mss = 2;
-	__u32 key_gen = 1;
-	__u32 key = 0;
-	__s64 seq_mss;
-
-	ethh = data;
-	if (ethh + 1 > data_end)
-		return;
-
-	switch (bpf_ntohs(ethh->h_proto)) {
-	case ETH_P_IP:
-		ipv4h = data + sizeof(struct ethhdr);
-		if (ipv4h + 1 > data_end)
-			return;
-
-		if (ipv4h->ihl != 5)
-			return;
-
-		tcph = data + sizeof(struct ethhdr) + sizeof(struct iphdr);
-		if (tcph + 1 > data_end)
-			return;
-
-		tup.ipv4.saddr = ipv4h->saddr;
-		tup.ipv4.daddr = ipv4h->daddr;
-		tup.ipv4.sport = tcph->source;
-		tup.ipv4.dport = tcph->dest;
-
-		sk = bpf_skc_lookup_tcp(ctx, &tup, sizeof(tup.ipv4),
-					BPF_F_CURRENT_NETNS, 0);
-		if (!sk)
-			return;
-
-		if (sk->state != BPF_TCP_LISTEN)
-			goto release;
-
-		seq_mss = gen_syncookie(data_end, sk, ipv4h, sizeof(*ipv4h),
-					tcph);
-
-		ret = bpf_tcp_check_syncookie(sk, ipv4h, sizeof(*ipv4h),
-					      tcph, sizeof(*tcph));
-		break;
-
-	case ETH_P_IPV6:
-		ipv6h = data + sizeof(struct ethhdr);
-		if (ipv6h + 1 > data_end)
-			return;
-
-		if (ipv6h->nexthdr != IPPROTO_TCP)
-			return;
-
-		tcph = data + sizeof(struct ethhdr) + sizeof(struct ipv6hdr);
-		if (tcph + 1 > data_end)
-			return;
-
-		memcpy(tup.ipv6.saddr, &ipv6h->saddr, sizeof(tup.ipv6.saddr));
-		memcpy(tup.ipv6.daddr, &ipv6h->daddr, sizeof(tup.ipv6.daddr));
-		tup.ipv6.sport = tcph->source;
-		tup.ipv6.dport = tcph->dest;
-
-		sk = bpf_skc_lookup_tcp(ctx, &tup, sizeof(tup.ipv6),
-					BPF_F_CURRENT_NETNS, 0);
-		if (!sk)
-			return;
-
-		if (sk->state != BPF_TCP_LISTEN)
-			goto release;
-
-		seq_mss = gen_syncookie(data_end, sk, ipv6h, sizeof(*ipv6h),
-					tcph);
-
-		ret = bpf_tcp_check_syncookie(sk, ipv6h, sizeof(*ipv6h),
-					      tcph, sizeof(*tcph));
-		break;
-
-	default:
-		return;
-	}
-
-	if (seq_mss > 0) {
-		__u32 cookie = (__u32)seq_mss;
-		__u32 mss = seq_mss >> 32;
-
-		bpf_map_update_elem(&results, &key_gen, &cookie, 0);
-		bpf_map_update_elem(&results, &key_mss, &mss, 0);
-	}
-
-	if (ret == 0) {
-		__u32 cookie = bpf_ntohl(tcph->ack_seq) - 1;
-
-		bpf_map_update_elem(&results, &key, &cookie, 0);
-	}
-
-release:
-	bpf_sk_release(sk);
-}
-
-SEC("tc")
-int check_syncookie_clsact(struct __sk_buff *skb)
-{
-	check_syncookie(skb, (void *)(long)skb->data,
-			(void *)(long)skb->data_end);
-	return TC_ACT_OK;
-}
-
-SEC("xdp")
-int check_syncookie_xdp(struct xdp_md *ctx)
-{
-	check_syncookie(ctx, (void *)(long)ctx->data,
-			(void *)(long)ctx->data_end);
-	return XDP_PASS;
-}
-
-char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c b/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c
new file mode 100644
index 000000000000..7d5293de1952
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c
@@ -0,0 +1,591 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+
+#include "vmlinux.h"
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include "bpf_tracing_net.h"
+#include "bpf_kfuncs.h"
+#include "test_siphash.h"
+#include "test_tcp_custom_syncookie.h"
+#include "bpf_misc.h"
+
+#define MAX_PACKET_OFF 0xffff
+
+/* Hash is calculated for each client and split into ISN and TS.
+ *
+ *       MSB                                   LSB
+ * ISN:  | 31 ... 8 | 7 6 |   5 |    4 | 3 2 1 0 |
+ *       |   Hash_1 | MSS | ECN | SACK |  WScale |
+ *
+ * TS:   | 31 ... 8 |          7 ... 0           |
+ *       |   Random |           Hash_2           |
+ */
+#define COOKIE_BITS	8
+#define COOKIE_MASK	(((__u32)1 << COOKIE_BITS) - 1)
+
+enum {
+	/* 0xf is invalid thus means that SYN did not have WScale. */
+	BPF_SYNCOOKIE_WSCALE_MASK	= (1 << 4) - 1,
+	BPF_SYNCOOKIE_SACK		= (1 << 4),
+	BPF_SYNCOOKIE_ECN		= (1 << 5),
+};
+
+#define MSS_LOCAL_IPV4	65495
+#define MSS_LOCAL_IPV6	65476
+
+const __u16 msstab4[] = {
+	536,
+	1300,
+	1460,
+	MSS_LOCAL_IPV4,
+};
+
+const __u16 msstab6[] = {
+	1280 - 60, /* IPV6_MIN_MTU - 60 */
+	1480 - 60,
+	9000 - 60,
+	MSS_LOCAL_IPV6,
+};
+
+static siphash_key_t test_key_siphash = {
+	{ 0x0706050403020100ULL, 0x0f0e0d0c0b0a0908ULL }
+};
+
+struct tcp_syncookie {
+	struct __sk_buff *skb;
+	void *data;
+	void *data_end;
+	struct ethhdr *eth;
+	struct iphdr *ipv4;
+	struct ipv6hdr *ipv6;
+	struct tcphdr *tcp;
+	__be32 *ptr32;
+	struct bpf_tcp_req_attrs attrs;
+	u32 off;
+	u32 cookie;
+	u64 first;
+};
+
+bool handled_syn, handled_ack;
+
+static int tcp_load_headers(struct tcp_syncookie *ctx)
+{
+	ctx->data = (void *)(long)ctx->skb->data;
+	ctx->data_end = (void *)(long)ctx->skb->data_end;
+	ctx->eth = (struct ethhdr *)(long)ctx->skb->data;
+
+	if (ctx->eth + 1 > ctx->data_end)
+		goto err;
+
+	switch (bpf_ntohs(ctx->eth->h_proto)) {
+	case ETH_P_IP:
+		ctx->ipv4 = (struct iphdr *)(ctx->eth + 1);
+
+		if (ctx->ipv4 + 1 > ctx->data_end)
+			goto err;
+
+		if (ctx->ipv4->ihl != sizeof(*ctx->ipv4) / 4)
+			goto err;
+
+		if (ctx->ipv4->version != 4)
+			goto err;
+
+		if (ctx->ipv4->protocol != IPPROTO_TCP)
+			goto err;
+
+		ctx->tcp = (struct tcphdr *)(ctx->ipv4 + 1);
+		break;
+	case ETH_P_IPV6:
+		ctx->ipv6 = (struct ipv6hdr *)(ctx->eth + 1);
+
+		if (ctx->ipv6 + 1 > ctx->data_end)
+			goto err;
+
+		if (ctx->ipv6->version != 6)
+			goto err;
+
+		if (ctx->ipv6->nexthdr != NEXTHDR_TCP)
+			goto err;
+
+		ctx->tcp = (struct tcphdr *)(ctx->ipv6 + 1);
+		break;
+	default:
+		goto err;
+	}
+
+	if (ctx->tcp + 1 > ctx->data_end)
+		goto err;
+
+	return 0;
+err:
+	return -1;
+}
+
+static int tcp_reload_headers(struct tcp_syncookie *ctx)
+{
+	/* Without volatile,
+	 * R3 32-bit pointer arithmetic prohibited
+	 */
+	volatile u64 data_len = ctx->skb->data_end - ctx->skb->data;
+
+	if (ctx->tcp->doff < sizeof(*ctx->tcp) / 4)
+		goto err;
+
+	/* Needed to calculate csum and parse TCP options. */
+	if (bpf_skb_change_tail(ctx->skb, data_len + 60 - ctx->tcp->doff * 4, 0))
+		goto err;
+
+	ctx->data = (void *)(long)ctx->skb->data;
+	ctx->data_end = (void *)(long)ctx->skb->data_end;
+	ctx->eth = (struct ethhdr *)(long)ctx->skb->data;
+	if (ctx->ipv4) {
+		ctx->ipv4 = (struct iphdr *)(ctx->eth + 1);
+		ctx->ipv6 = NULL;
+		ctx->tcp = (struct tcphdr *)(ctx->ipv4 + 1);
+	} else {
+		ctx->ipv4 = NULL;
+		ctx->ipv6 = (struct ipv6hdr *)(ctx->eth + 1);
+		ctx->tcp = (struct tcphdr *)(ctx->ipv6 + 1);
+	}
+
+	if ((void *)ctx->tcp + 60 > ctx->data_end)
+		goto err;
+
+	return 0;
+err:
+	return -1;
+}
+
+static __sum16 tcp_v4_csum(struct tcp_syncookie *ctx, __wsum csum)
+{
+	return csum_tcpudp_magic(ctx->ipv4->saddr, ctx->ipv4->daddr,
+				 ctx->tcp->doff * 4, IPPROTO_TCP, csum);
+}
+
+static __sum16 tcp_v6_csum(struct tcp_syncookie *ctx, __wsum csum)
+{
+	return csum_ipv6_magic(&ctx->ipv6->saddr, &ctx->ipv6->daddr,
+			       ctx->tcp->doff * 4, IPPROTO_TCP, csum);
+}
+
+static int tcp_validate_header(struct tcp_syncookie *ctx)
+{
+	s64 csum;
+
+	if (tcp_reload_headers(ctx))
+		goto err;
+
+	csum = bpf_csum_diff(0, 0, (void *)ctx->tcp, ctx->tcp->doff * 4, 0);
+	if (csum < 0)
+		goto err;
+
+	if (ctx->ipv4) {
+		/* check tcp_v4_csum(csum) is 0 if not on lo. */
+
+		csum = bpf_csum_diff(0, 0, (void *)ctx->ipv4, ctx->ipv4->ihl * 4, 0);
+		if (csum < 0)
+			goto err;
+
+		if (csum_fold(csum) != 0)
+			goto err;
+	} else if (ctx->ipv6) {
+		/* check tcp_v6_csum(csum) is 0 if not on lo. */
+	}
+
+	return 0;
+err:
+	return -1;
+}
+
+static __always_inline void *next(struct tcp_syncookie *ctx, __u32 sz)
+{
+	__u64 off = ctx->off;
+	__u8 *data;
+
+	/* Verifier forbids access to packet when offset exceeds MAX_PACKET_OFF */
+	if (off > MAX_PACKET_OFF - sz)
+		return NULL;
+
+	data = ctx->data + off;
+	barrier_var(data);
+	if (data + sz >= ctx->data_end)
+		return NULL;
+
+	ctx->off += sz;
+	return data;
+}
+
+static int tcp_parse_option(__u32 index, struct tcp_syncookie *ctx)
+{
+	__u8 *opcode, *opsize, *wscale;
+	__u32 *tsval, *tsecr;
+	__u16 *mss;
+	__u32 off;
+
+	off = ctx->off;
+	opcode = next(ctx, 1);
+	if (!opcode)
+		goto stop;
+
+	if (*opcode == TCPOPT_EOL)
+		goto stop;
+
+	if (*opcode == TCPOPT_NOP)
+		goto next;
+
+	opsize = next(ctx, 1);
+	if (!opsize)
+		goto stop;
+
+	if (*opsize < 2)
+		goto stop;
+
+	switch (*opcode) {
+	case TCPOPT_MSS:
+		mss = next(ctx, 2);
+		if (*opsize == TCPOLEN_MSS && ctx->tcp->syn && mss)
+			ctx->attrs.mss = get_unaligned_be16(mss);
+		break;
+	case TCPOPT_WINDOW:
+		wscale = next(ctx, 1);
+		if (*opsize == TCPOLEN_WINDOW && ctx->tcp->syn && wscale) {
+			ctx->attrs.wscale_ok = 1;
+			ctx->attrs.snd_wscale = *wscale;
+		}
+		break;
+	case TCPOPT_TIMESTAMP:
+		tsval = next(ctx, 4);
+		tsecr = next(ctx, 4);
+		if (*opsize == TCPOLEN_TIMESTAMP && tsval && tsecr) {
+			ctx->attrs.rcv_tsval = get_unaligned_be32(tsval);
+			ctx->attrs.rcv_tsecr = get_unaligned_be32(tsecr);
+
+			if (ctx->tcp->syn && ctx->attrs.rcv_tsecr)
+				ctx->attrs.tstamp_ok = 0;
+			else
+				ctx->attrs.tstamp_ok = 1;
+		}
+		break;
+	case TCPOPT_SACK_PERM:
+		if (*opsize == TCPOLEN_SACK_PERM && ctx->tcp->syn)
+			ctx->attrs.sack_ok = 1;
+		break;
+	}
+
+	ctx->off = off + *opsize;
+next:
+	return 0;
+stop:
+	return 1;
+}
+
+static void tcp_parse_options(struct tcp_syncookie *ctx)
+{
+	ctx->off = (__u8 *)(ctx->tcp + 1) - (__u8 *)ctx->data,
+
+	bpf_loop(40, tcp_parse_option, ctx, 0);
+}
+
+static int tcp_validate_sysctl(struct tcp_syncookie *ctx)
+{
+	if ((ctx->ipv4 && ctx->attrs.mss != MSS_LOCAL_IPV4) ||
+	    (ctx->ipv6 && ctx->attrs.mss != MSS_LOCAL_IPV6))
+		goto err;
+
+	if (!ctx->attrs.wscale_ok ||
+	    !ctx->attrs.snd_wscale ||
+	    ctx->attrs.snd_wscale >= BPF_SYNCOOKIE_WSCALE_MASK)
+		goto err;
+
+	if (!ctx->attrs.tstamp_ok)
+		goto err;
+
+	if (!ctx->attrs.sack_ok)
+		goto err;
+
+	if (!ctx->tcp->ece || !ctx->tcp->cwr)
+		goto err;
+
+	return 0;
+err:
+	return -1;
+}
+
+static void tcp_prepare_cookie(struct tcp_syncookie *ctx)
+{
+	u32 seq = bpf_ntohl(ctx->tcp->seq);
+	u64 first = 0, second;
+	int mssind = 0;
+	u32 hash;
+
+	if (ctx->ipv4) {
+		for (mssind = ARRAY_SIZE(msstab4) - 1; mssind; mssind--)
+			if (ctx->attrs.mss >= msstab4[mssind])
+				break;
+
+		ctx->attrs.mss = msstab4[mssind];
+
+		first = (u64)ctx->ipv4->saddr << 32 | ctx->ipv4->daddr;
+	} else if (ctx->ipv6) {
+		for (mssind = ARRAY_SIZE(msstab6) - 1; mssind; mssind--)
+			if (ctx->attrs.mss >= msstab6[mssind])
+				break;
+
+		ctx->attrs.mss = msstab6[mssind];
+
+		first = (u64)ctx->ipv6->saddr.in6_u.u6_addr8[0] << 32 |
+			ctx->ipv6->daddr.in6_u.u6_addr32[0];
+	}
+
+	second = (u64)seq << 32 | ctx->tcp->source << 16 | ctx->tcp->dest;
+	hash = siphash_2u64(first, second, &test_key_siphash);
+
+	if (ctx->attrs.tstamp_ok) {
+		ctx->attrs.rcv_tsecr = bpf_get_prandom_u32();
+		ctx->attrs.rcv_tsecr &= ~COOKIE_MASK;
+		ctx->attrs.rcv_tsecr |= hash & COOKIE_MASK;
+	}
+
+	hash &= ~COOKIE_MASK;
+	hash |= mssind << 6;
+
+	if (ctx->attrs.wscale_ok)
+		hash |= ctx->attrs.snd_wscale & BPF_SYNCOOKIE_WSCALE_MASK;
+
+	if (ctx->attrs.sack_ok)
+		hash |= BPF_SYNCOOKIE_SACK;
+
+	if (ctx->attrs.tstamp_ok && ctx->tcp->ece && ctx->tcp->cwr)
+		hash |= BPF_SYNCOOKIE_ECN;
+
+	ctx->cookie = hash;
+}
+
+static void tcp_write_options(struct tcp_syncookie *ctx)
+{
+	ctx->ptr32 = (__be32 *)(ctx->tcp + 1);
+
+	*ctx->ptr32++ = bpf_htonl(TCPOPT_MSS << 24 | TCPOLEN_MSS << 16 |
+				  ctx->attrs.mss);
+
+	if (ctx->attrs.wscale_ok)
+		*ctx->ptr32++ = bpf_htonl(TCPOPT_NOP << 24 |
+					  TCPOPT_WINDOW << 16 |
+					  TCPOLEN_WINDOW << 8 |
+					  ctx->attrs.snd_wscale);
+
+	if (ctx->attrs.tstamp_ok) {
+		if (ctx->attrs.sack_ok)
+			*ctx->ptr32++ = bpf_htonl(TCPOPT_SACK_PERM << 24 |
+						  TCPOLEN_SACK_PERM << 16 |
+						  TCPOPT_TIMESTAMP << 8 |
+						  TCPOLEN_TIMESTAMP);
+		else
+			*ctx->ptr32++ = bpf_htonl(TCPOPT_NOP << 24 |
+						  TCPOPT_NOP << 16 |
+						  TCPOPT_TIMESTAMP << 8 |
+						  TCPOLEN_TIMESTAMP);
+
+		*ctx->ptr32++ = bpf_htonl(ctx->attrs.rcv_tsecr);
+		*ctx->ptr32++ = bpf_htonl(ctx->attrs.rcv_tsval);
+	} else if (ctx->attrs.sack_ok) {
+		*ctx->ptr32++ = bpf_htonl(TCPOPT_NOP << 24 |
+					  TCPOPT_NOP << 16 |
+					  TCPOPT_SACK_PERM << 8 |
+					  TCPOLEN_SACK_PERM);
+	}
+}
+
+static int tcp_handle_syn(struct tcp_syncookie *ctx)
+{
+	s64 csum;
+
+	if (tcp_validate_header(ctx))
+		goto err;
+
+	tcp_parse_options(ctx);
+
+	if (tcp_validate_sysctl(ctx))
+		goto err;
+
+	tcp_prepare_cookie(ctx);
+	tcp_write_options(ctx);
+
+	swap(ctx->tcp->source, ctx->tcp->dest);
+	ctx->tcp->check = 0;
+	ctx->tcp->ack_seq = bpf_htonl(bpf_ntohl(ctx->tcp->seq) + 1);
+	ctx->tcp->seq = bpf_htonl(ctx->cookie);
+	ctx->tcp->doff = ((long)ctx->ptr32 - (long)ctx->tcp) >> 2;
+	ctx->tcp->ack = 1;
+	if (!ctx->attrs.tstamp_ok || !ctx->tcp->ece || !ctx->tcp->cwr)
+		ctx->tcp->ece = 0;
+	ctx->tcp->cwr = 0;
+
+	csum = bpf_csum_diff(0, 0, (void *)ctx->tcp, ctx->tcp->doff * 4, 0);
+	if (csum < 0)
+		goto err;
+
+	if (ctx->ipv4) {
+		swap(ctx->ipv4->saddr, ctx->ipv4->daddr);
+		ctx->tcp->check = tcp_v4_csum(ctx, csum);
+
+		ctx->ipv4->check = 0;
+		ctx->ipv4->tos = 0;
+		ctx->ipv4->tot_len = bpf_htons((long)ctx->ptr32 - (long)ctx->ipv4);
+		ctx->ipv4->id = 0;
+		ctx->ipv4->ttl = 64;
+
+		csum = bpf_csum_diff(0, 0, (void *)ctx->ipv4, sizeof(*ctx->ipv4), 0);
+		if (csum < 0)
+			goto err;
+
+		ctx->ipv4->check = csum_fold(csum);
+	} else if (ctx->ipv6) {
+		swap(ctx->ipv6->saddr, ctx->ipv6->daddr);
+		ctx->tcp->check = tcp_v6_csum(ctx, csum);
+
+		*(__be32 *)ctx->ipv6 = bpf_htonl(0x60000000);
+		ctx->ipv6->payload_len = bpf_htons((long)ctx->ptr32 - (long)ctx->tcp);
+		ctx->ipv6->hop_limit = 64;
+	}
+
+	swap_array(ctx->eth->h_source, ctx->eth->h_dest);
+
+	if (bpf_skb_change_tail(ctx->skb, (long)ctx->ptr32 - (long)ctx->eth, 0))
+		goto err;
+
+	return bpf_redirect(ctx->skb->ifindex, 0);
+err:
+	return TC_ACT_SHOT;
+}
+
+static int tcp_validate_cookie(struct tcp_syncookie *ctx)
+{
+	u32 cookie = bpf_ntohl(ctx->tcp->ack_seq) - 1;
+	u32 seq = bpf_ntohl(ctx->tcp->seq) - 1;
+	u64 first = 0, second;
+	int mssind;
+	u32 hash;
+
+	if (ctx->ipv4)
+		first = (u64)ctx->ipv4->saddr << 32 | ctx->ipv4->daddr;
+	else if (ctx->ipv6)
+		first = (u64)ctx->ipv6->saddr.in6_u.u6_addr8[0] << 32 |
+			ctx->ipv6->daddr.in6_u.u6_addr32[0];
+
+	second = (u64)seq << 32 | ctx->tcp->source << 16 | ctx->tcp->dest;
+	hash = siphash_2u64(first, second, &test_key_siphash);
+
+	if (ctx->attrs.tstamp_ok)
+		hash -= ctx->attrs.rcv_tsecr & COOKIE_MASK;
+	else
+		hash &= ~COOKIE_MASK;
+
+	hash -= cookie & ~COOKIE_MASK;
+	if (hash)
+		goto err;
+
+	mssind = (cookie & (3 << 6)) >> 6;
+	if (ctx->ipv4)
+		ctx->attrs.mss = msstab4[mssind];
+	else
+		ctx->attrs.mss = msstab6[mssind];
+
+	ctx->attrs.snd_wscale = cookie & BPF_SYNCOOKIE_WSCALE_MASK;
+	ctx->attrs.rcv_wscale = ctx->attrs.snd_wscale;
+	ctx->attrs.wscale_ok = ctx->attrs.snd_wscale == BPF_SYNCOOKIE_WSCALE_MASK;
+	ctx->attrs.sack_ok = cookie & BPF_SYNCOOKIE_SACK;
+	ctx->attrs.ecn_ok = cookie & BPF_SYNCOOKIE_ECN;
+
+	return 0;
+err:
+	return -1;
+}
+
+static int tcp_handle_ack(struct tcp_syncookie *ctx)
+{
+	struct bpf_sock_tuple tuple;
+	struct bpf_sock *skc;
+	int ret = TC_ACT_OK;
+	struct sock *sk;
+	u32 tuple_size;
+
+	if (ctx->ipv4) {
+		tuple.ipv4.saddr = ctx->ipv4->saddr;
+		tuple.ipv4.daddr = ctx->ipv4->daddr;
+		tuple.ipv4.sport = ctx->tcp->source;
+		tuple.ipv4.dport = ctx->tcp->dest;
+		tuple_size = sizeof(tuple.ipv4);
+	} else if (ctx->ipv6) {
+		__builtin_memcpy(tuple.ipv6.saddr, &ctx->ipv6->saddr, sizeof(tuple.ipv6.saddr));
+		__builtin_memcpy(tuple.ipv6.daddr, &ctx->ipv6->daddr, sizeof(tuple.ipv6.daddr));
+		tuple.ipv6.sport = ctx->tcp->source;
+		tuple.ipv6.dport = ctx->tcp->dest;
+		tuple_size = sizeof(tuple.ipv6);
+	} else {
+		goto out;
+	}
+
+	skc = bpf_skc_lookup_tcp(ctx->skb, &tuple, tuple_size, -1, 0);
+	if (!skc)
+		goto out;
+
+	if (skc->state != TCP_LISTEN)
+		goto release;
+
+	sk = (struct sock *)bpf_skc_to_tcp_sock(skc);
+	if (!sk)
+		goto err;
+
+	if (tcp_validate_header(ctx))
+		goto err;
+
+	tcp_parse_options(ctx);
+
+	if (tcp_validate_cookie(ctx))
+		goto err;
+
+	ret = bpf_sk_assign_tcp_reqsk(ctx->skb, sk, &ctx->attrs, sizeof(ctx->attrs));
+	if (ret < 0)
+		goto err;
+
+release:
+	bpf_sk_release(skc);
+out:
+	return ret;
+
+err:
+	ret = TC_ACT_SHOT;
+	goto release;
+}
+
+SEC("tc")
+int tcp_custom_syncookie(struct __sk_buff *skb)
+{
+	struct tcp_syncookie ctx = {
+		.skb = skb,
+	};
+
+	if (tcp_load_headers(&ctx))
+		return TC_ACT_OK;
+
+	if (ctx.tcp->rst)
+		return TC_ACT_OK;
+
+	if (ctx.tcp->syn) {
+		if (ctx.tcp->ack)
+			return TC_ACT_OK;
+
+		handled_syn = true;
+
+		return tcp_handle_syn(&ctx);
+	}
+
+	handled_ack = true;
+
+	return tcp_handle_ack(&ctx);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.h b/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.h
new file mode 100644
index 000000000000..34024de6337e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.h
@@ -0,0 +1,138 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+
+#ifndef _TEST_TCP_SYNCOOKIE_H
+#define _TEST_TCP_SYNCOOKIE_H
+
+#define __packed __attribute__((__packed__))
+#define __force
+
+#define swap(a, b)				\
+	do {					\
+		typeof(a) __tmp = (a);		\
+		(a) = (b);			\
+		(b) = __tmp;			\
+	} while (0)
+
+#define swap_array(a, b)				\
+	do {						\
+		typeof(a) __tmp[sizeof(a)];		\
+		__builtin_memcpy(__tmp, a, sizeof(a));	\
+		__builtin_memcpy(a, b, sizeof(a));	\
+		__builtin_memcpy(b, __tmp, sizeof(a));	\
+	} while (0)
+
+/* linux/unaligned.h */
+#define __get_unaligned_t(type, ptr) ({						\
+	const struct { type x; } __packed * __pptr = (typeof(__pptr))(ptr);	\
+	__pptr->x;								\
+})
+
+#define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr))
+
+static inline u16 get_unaligned_be16(const void *p)
+{
+	return bpf_ntohs(__get_unaligned_t(__be16, p));
+}
+
+static inline u32 get_unaligned_be32(const void *p)
+{
+	return bpf_ntohl(__get_unaligned_t(__be32, p));
+}
+
+/* lib/checksum.c */
+static inline u32 from64to32(u64 x)
+{
+	/* add up 32-bit and 32-bit for 32+c bit */
+	x = (x & 0xffffffff) + (x >> 32);
+	/* add up carry.. */
+	x = (x & 0xffffffff) + (x >> 32);
+	return (u32)x;
+}
+
+static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
+					__u32 len, __u8 proto, __wsum sum)
+{
+	unsigned long long s = (__force u32)sum;
+
+	s += (__force u32)saddr;
+	s += (__force u32)daddr;
+#ifdef __BIG_ENDIAN
+	s += proto + len;
+#else
+	s += (proto + len) << 8;
+#endif
+	return (__force __wsum)from64to32(s);
+}
+
+/* asm-generic/checksum.h */
+static inline __sum16 csum_fold(__wsum csum)
+{
+	u32 sum = (__force u32)csum;
+
+	sum = (sum & 0xffff) + (sum >> 16);
+	sum = (sum & 0xffff) + (sum >> 16);
+	return (__force __sum16)~sum;
+}
+
+static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len,
+					__u8 proto, __wsum sum)
+{
+	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
+}
+
+/* net/ipv6/ip6_checksum.c */
+static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+				      const struct in6_addr *daddr,
+				      __u32 len, __u8 proto, __wsum csum)
+{
+	int carry;
+	__u32 ulen;
+	__u32 uproto;
+	__u32 sum = (__force u32)csum;
+
+	sum += (__force u32)saddr->in6_u.u6_addr32[0];
+	carry = (sum < (__force u32)saddr->in6_u.u6_addr32[0]);
+	sum += carry;
+
+	sum += (__force u32)saddr->in6_u.u6_addr32[1];
+	carry = (sum < (__force u32)saddr->in6_u.u6_addr32[1]);
+	sum += carry;
+
+	sum += (__force u32)saddr->in6_u.u6_addr32[2];
+	carry = (sum < (__force u32)saddr->in6_u.u6_addr32[2]);
+	sum += carry;
+
+	sum += (__force u32)saddr->in6_u.u6_addr32[3];
+	carry = (sum < (__force u32)saddr->in6_u.u6_addr32[3]);
+	sum += carry;
+
+	sum += (__force u32)daddr->in6_u.u6_addr32[0];
+	carry = (sum < (__force u32)daddr->in6_u.u6_addr32[0]);
+	sum += carry;
+
+	sum += (__force u32)daddr->in6_u.u6_addr32[1];
+	carry = (sum < (__force u32)daddr->in6_u.u6_addr32[1]);
+	sum += carry;
+
+	sum += (__force u32)daddr->in6_u.u6_addr32[2];
+	carry = (sum < (__force u32)daddr->in6_u.u6_addr32[2]);
+	sum += carry;
+
+	sum += (__force u32)daddr->in6_u.u6_addr32[3];
+	carry = (sum < (__force u32)daddr->in6_u.u6_addr32[3]);
+	sum += carry;
+
+	ulen = (__force u32)bpf_htonl((__u32)len);
+	sum += ulen;
+	carry = (sum < ulen);
+	sum += carry;
+
+	uproto = (__force u32)bpf_htonl(proto);
+	sum += uproto;
+	carry = (sum < uproto);
+	sum += carry;
+
+	return csum_fold((__force __wsum)sum);
+}
+#endif
diff --git a/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c
index 5f4e87ee949a..1ecdf4c54de4 100644
--- a/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c
+++ b/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c
@@ -14,10 +14,7 @@
 #include <bpf/bpf_endian.h>
 #define BPF_PROG_TEST_TCP_HDR_OPTIONS
 #include "test_tcp_hdr_options.h"
-
-#ifndef sizeof_field
-#define sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER))
-#endif
+#include "bpf_misc.h"
 
 __u8 test_kind = TCPOPT_EXP;
 __u16 test_magic = 0xeB9F;
diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
index 3ded05280757..6935f32eeb8f 100644
--- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
@@ -1,18 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <stddef.h>
-#include <string.h>
-#include <netinet/in.h>
-#include <linux/bpf.h>
-#include <linux/if_ether.h>
-#include <linux/if_packet.h>
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-#include <linux/types.h>
-#include <linux/socket.h>
-#include <linux/tcp.h>
+#include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
-#include "bpf_tcp_helpers.h"
 #include "test_tcpbpf.h"
 
 struct tcpbpf_globals global = {};
@@ -46,8 +35,6 @@ int bpf_testcb(struct bpf_sock_ops *skops)
 	struct bpf_sock_ops *reuse = skops;
 	struct tcphdr *thdr;
 	int window_clamp = 9216;
-	int good_call_rv = 0;
-	int bad_call_rv = 0;
 	int save_syn = 1;
 	int rv = -1;
 	int v = 0;
@@ -61,7 +48,7 @@ int bpf_testcb(struct bpf_sock_ops *skops)
 
 	asm volatile (
 		"%[op] = *(u32 *)(%[skops] +96)"
-		: [op] "+r"(op)
+		: [op] "=r"(op)
 		: [skops] "r"(skops)
 		:);
 
diff --git a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
index 540181c115a8..ef00d38b0a8d 100644
--- a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
@@ -23,7 +23,6 @@ struct {
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
-	__uint(max_entries, 2);
 	__type(key, int);
 	__type(value, __u32);
 } perf_event_map SEC(".maps");
diff --git a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c
new file mode 100644
index 000000000000..cf0547a613ff
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "../test_kmods/bpf_testmod.h"
+#include "bpf_misc.h"
+
+SEC("tp_btf/bpf_testmod_test_nullable_bare_tp")
+__failure __msg("R1 invalid mem access 'trusted_ptr_or_null_'")
+int BPF_PROG(handle_tp_btf_nullable_bare1, struct bpf_testmod_test_read_ctx *nullable_ctx)
+{
+	return nullable_ctx->len;
+}
+
+SEC("tp_btf/bpf_testmod_test_nullable_bare_tp")
+int BPF_PROG(handle_tp_btf_nullable_bare2, struct bpf_testmod_test_read_ctx *nullable_ctx)
+{
+	if (nullable_ctx)
+		return nullable_ctx->len;
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_tracepoint.c b/tools/testing/selftests/bpf/progs/test_tracepoint.c
index 43bd7a20cc50..4cb8bbb6a320 100644
--- a/tools/testing/selftests/bpf/progs/test_tracepoint.c
+++ b/tools/testing/selftests/bpf/progs/test_tracepoint.c
@@ -4,7 +4,7 @@
 #include <vmlinux.h>
 #include <bpf/bpf_helpers.h>
 
-/* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
+/* taken from /sys/kernel/tracing/events/sched/sched_switch/format */
 struct sched_switch_args {
 	unsigned long long pad;
 	char prev_comm[TASK_COMM_LEN];
diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
index 98af55f0bcd3..32127f1cd687 100644
--- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
@@ -6,51 +6,46 @@
  * modify it under the terms of version 2 of the GNU General Public
  * License as published by the Free Software Foundation.
  */
-#include <stddef.h>
-#include <string.h>
-#include <arpa/inet.h>
-#include <linux/bpf.h>
-#include <linux/if_ether.h>
-#include <linux/if_packet.h>
-#include <linux/if_tunnel.h>
-#include <linux/ip.h>
-#include <linux/ipv6.h>
-#include <linux/icmp.h>
-#include <linux/types.h>
-#include <linux/socket.h>
-#include <linux/pkt_cls.h>
-#include <linux/erspan.h>
-#include <linux/udp.h>
+#include "vmlinux.h"
+#include <bpf/bpf_core_read.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
+#include "bpf_kfuncs.h"
+#include "bpf_tracing_net.h"
 
 #define log_err(__ret) bpf_printk("ERROR line:%d ret:%d\n", __LINE__, __ret)
 
-#define VXLAN_UDP_PORT 4789
+#define VXLAN_UDP_PORT		4789
+#define ETH_P_IP		0x0800
+#define PACKET_HOST		0
+#define TUNNEL_CSUM		bpf_htons(0x01)
+#define TUNNEL_KEY		bpf_htons(0x04)
 
 /* Only IPv4 address assigned to veth1.
  * 172.16.1.200
  */
 #define ASSIGNED_ADDR_VETH1 0xac1001c8
 
-struct geneve_opt {
-	__be16	opt_class;
-	__u8	type;
-	__u8	length:5;
-	__u8	r3:1;
-	__u8	r2:1;
-	__u8	r1:1;
-	__u8	opt_data[8]; /* hard-coded to 8 byte */
+struct bpf_fou_encap___local {
+	__be16 sport;
+	__be16 dport;
+} __attribute__((preserve_access_index));
+
+enum bpf_fou_encap_type___local {
+	FOU_BPF_ENCAP_FOU___local,
+	FOU_BPF_ENCAP_GUE___local,
 };
 
-struct vxlanhdr {
-	__be32 vx_flags;
-	__be32 vx_vni;
-} __attribute__((packed));
+struct bpf_fou_encap;
 
-struct vxlan_metadata {
-	__u32     gbp;
-};
+int bpf_skb_set_fou_encap(struct __sk_buff *skb_ctx,
+			  struct bpf_fou_encap *encap, int type) __ksym;
+int bpf_skb_get_fou_encap(struct __sk_buff *skb_ctx,
+			  struct bpf_fou_encap *encap) __ksym;
+struct xfrm_state *
+bpf_xdp_get_xfrm_state(struct xdp_md *ctx, struct bpf_xfrm_state_opts *opts,
+		       u32 opts__sz) __ksym;
+void bpf_xdp_xfrm_state_release(struct xfrm_state *x) __ksym;
 
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
@@ -82,6 +77,27 @@ int gre_set_tunnel(struct __sk_buff *skb)
 }
 
 SEC("tc")
+int gre_set_tunnel_no_key(struct __sk_buff *skb)
+{
+	int ret;
+	struct bpf_tunnel_key key;
+
+	__builtin_memset(&key, 0x0, sizeof(key));
+	key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
+	key.tunnel_ttl = 64;
+
+	ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+				     BPF_F_ZERO_CSUM_TX | BPF_F_SEQ_NUMBER |
+				     BPF_F_NO_TUNNEL_KEY);
+	if (ret < 0) {
+		log_err(ret);
+		return TC_ACT_SHOT;
+	}
+
+	return TC_ACT_OK;
+}
+
+SEC("tc")
 int gre_get_tunnel(struct __sk_buff *skb)
 {
 	int ret;
@@ -169,9 +185,9 @@ int erspan_set_tunnel(struct __sk_buff *skb)
 	__u8 hwid = 7;
 
 	md.version = 2;
-	md.u.md2.dir = direction;
-	md.u.md2.hwid = hwid & 0xf;
-	md.u.md2.hwid_upper = (hwid >> 4) & 0x3;
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, dir, direction);
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid, (hwid & 0xf));
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid_upper, (hwid >> 4) & 0x3);
 #endif
 
 	ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
@@ -188,7 +204,6 @@ int erspan_get_tunnel(struct __sk_buff *skb)
 {
 	struct bpf_tunnel_key key;
 	struct erspan_metadata md;
-	__u32 index;
 	int ret;
 
 	ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
@@ -211,8 +226,9 @@ int erspan_get_tunnel(struct __sk_buff *skb)
 	bpf_printk("\tindex %x\n", index);
 #else
 	bpf_printk("\tdirection %d hwid %x timestamp %u\n",
-		   md.u.md2.dir,
-		   (md.u.md2.hwid_upper << 4) + md.u.md2.hwid,
+		   BPF_CORE_READ_BITFIELD(&md.u.md2, dir),
+		   (BPF_CORE_READ_BITFIELD(&md.u.md2, hwid_upper) << 4) +
+		   BPF_CORE_READ_BITFIELD(&md.u.md2, hwid),
 		   bpf_ntohl(md.u.md2.timestamp));
 #endif
 
@@ -249,9 +265,9 @@ int ip4ip6erspan_set_tunnel(struct __sk_buff *skb)
 	__u8 hwid = 17;
 
 	md.version = 2;
-	md.u.md2.dir = direction;
-	md.u.md2.hwid = hwid & 0xf;
-	md.u.md2.hwid_upper = (hwid >> 4) & 0x3;
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, dir, direction);
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid, (hwid & 0xf));
+	BPF_CORE_WRITE_BITFIELD(&md.u.md2, hwid_upper, (hwid >> 4) & 0x3);
 #endif
 
 	ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
@@ -268,7 +284,6 @@ int ip4ip6erspan_get_tunnel(struct __sk_buff *skb)
 {
 	struct bpf_tunnel_key key;
 	struct erspan_metadata md;
-	__u32 index;
 	int ret;
 
 	ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
@@ -292,8 +307,9 @@ int ip4ip6erspan_get_tunnel(struct __sk_buff *skb)
 	bpf_printk("\tindex %x\n", index);
 #else
 	bpf_printk("\tdirection %d hwid %x timestamp %u\n",
-		   md.u.md2.dir,
-		   (md.u.md2.hwid_upper << 4) + md.u.md2.hwid,
+		   BPF_CORE_READ_BITFIELD(&md.u.md2, dir),
+		   (BPF_CORE_READ_BITFIELD(&md.u.md2, hwid_upper) << 4) +
+		   BPF_CORE_READ_BITFIELD(&md.u.md2, hwid),
 		   bpf_ntohl(md.u.md2.timestamp));
 #endif
 
@@ -303,11 +319,11 @@ int ip4ip6erspan_get_tunnel(struct __sk_buff *skb)
 SEC("tc")
 int vxlan_set_tunnel_dst(struct __sk_buff *skb)
 {
-	int ret;
 	struct bpf_tunnel_key key;
 	struct vxlan_metadata md;
 	__u32 index = 0;
 	__u32 *local_ip = NULL;
+	int ret = 0;
 
 	local_ip = bpf_map_lookup_elem(&local_ip_map, &index);
 	if (!local_ip) {
@@ -342,11 +358,11 @@ int vxlan_set_tunnel_dst(struct __sk_buff *skb)
 SEC("tc")
 int vxlan_set_tunnel_src(struct __sk_buff *skb)
 {
-	int ret;
 	struct bpf_tunnel_key key;
 	struct vxlan_metadata md;
 	__u32 index = 0;
 	__u32 *local_ip = NULL;
+	int ret = 0;
 
 	local_ip = bpf_map_lookup_elem(&local_ip_map, &index);
 	if (!local_ip) {
@@ -384,8 +400,6 @@ int vxlan_get_tunnel_src(struct __sk_buff *skb)
 	int ret;
 	struct bpf_tunnel_key key;
 	struct vxlan_metadata md;
-	__u32 orig_daddr;
-	__u32 index = 0;
 
 	ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
 				     BPF_F_TUNINFO_FLAGS);
@@ -422,9 +436,7 @@ int veth_set_outer_dst(struct __sk_buff *skb)
 	void *data_end = (void *)(long)skb->data_end;
 	struct udphdr *udph;
 	struct iphdr *iph;
-	__u32 index = 0;
 	int ret = 0;
-	int shrink;
 	__s64 csum;
 
 	if ((void *)eth + sizeof(*eth) > data_end) {
@@ -473,9 +485,9 @@ SEC("tc")
 int ip6vxlan_set_tunnel_dst(struct __sk_buff *skb)
 {
 	struct bpf_tunnel_key key;
-	int ret;
 	__u32 index = 0;
 	__u32 *local_ip;
+	int ret = 0;
 
 	local_ip = bpf_map_lookup_elem(&local_ip_map, &index);
 	if (!local_ip) {
@@ -504,9 +516,9 @@ SEC("tc")
 int ip6vxlan_set_tunnel_src(struct __sk_buff *skb)
 {
 	struct bpf_tunnel_key key;
-	int ret;
 	__u32 index = 0;
 	__u32 *local_ip;
+	int ret = 0;
 
 	local_ip = bpf_map_lookup_elem(&local_ip_map, &index);
 	if (!local_ip) {
@@ -535,9 +547,9 @@ SEC("tc")
 int ip6vxlan_get_tunnel_src(struct __sk_buff *skb)
 {
 	struct bpf_tunnel_key key;
-	int ret;
 	__u32 index = 0;
 	__u32 *local_ip;
+	int ret = 0;
 
 	local_ip = bpf_map_lookup_elem(&local_ip_map, &index);
 	if (!local_ip) {
@@ -567,12 +579,18 @@ int ip6vxlan_get_tunnel_src(struct __sk_buff *skb)
 	return TC_ACT_OK;
 }
 
+struct local_geneve_opt {
+	struct geneve_opt gopt;
+	int data;
+};
+
 SEC("tc")
 int geneve_set_tunnel(struct __sk_buff *skb)
 {
 	int ret;
 	struct bpf_tunnel_key key;
-	struct geneve_opt gopt;
+	struct local_geneve_opt local_gopt;
+	struct geneve_opt *gopt = (struct geneve_opt *) &local_gopt;
 
 	__builtin_memset(&key, 0x0, sizeof(key));
 	key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
@@ -580,14 +598,14 @@ int geneve_set_tunnel(struct __sk_buff *skb)
 	key.tunnel_tos = 0;
 	key.tunnel_ttl = 64;
 
-	__builtin_memset(&gopt, 0x0, sizeof(gopt));
-	gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */
-	gopt.type = 0x08;
-	gopt.r1 = 0;
-	gopt.r2 = 0;
-	gopt.r3 = 0;
-	gopt.length = 2; /* 4-byte multiple */
-	*(int *) &gopt.opt_data = bpf_htonl(0xdeadbeef);
+	__builtin_memset(gopt, 0x0, sizeof(local_gopt));
+	gopt->opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */
+	gopt->type = 0x08;
+	gopt->r1 = 0;
+	gopt->r2 = 0;
+	gopt->r3 = 0;
+	gopt->length = 2; /* 4-byte multiple */
+	*(int *) &gopt->opt_data = bpf_htonl(0xdeadbeef);
 
 	ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
 				     BPF_F_ZERO_CSUM_TX);
@@ -596,7 +614,7 @@ int geneve_set_tunnel(struct __sk_buff *skb)
 		return TC_ACT_SHOT;
 	}
 
-	ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt));
+	ret = bpf_skb_set_tunnel_opt(skb, gopt, sizeof(local_gopt));
 	if (ret < 0) {
 		log_err(ret);
 		return TC_ACT_SHOT;
@@ -631,7 +649,8 @@ SEC("tc")
 int ip6geneve_set_tunnel(struct __sk_buff *skb)
 {
 	struct bpf_tunnel_key key;
-	struct geneve_opt gopt;
+	struct local_geneve_opt local_gopt;
+	struct geneve_opt *gopt = (struct geneve_opt *) &local_gopt;
 	int ret;
 
 	__builtin_memset(&key, 0x0, sizeof(key));
@@ -647,16 +666,16 @@ int ip6geneve_set_tunnel(struct __sk_buff *skb)
 		return TC_ACT_SHOT;
 	}
 
-	__builtin_memset(&gopt, 0x0, sizeof(gopt));
-	gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */
-	gopt.type = 0x08;
-	gopt.r1 = 0;
-	gopt.r2 = 0;
-	gopt.r3 = 0;
-	gopt.length = 2; /* 4-byte multiple */
-	*(int *) &gopt.opt_data = bpf_htonl(0xfeedbeef);
+	__builtin_memset(gopt, 0x0, sizeof(local_gopt));
+	gopt->opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */
+	gopt->type = 0x08;
+	gopt->r1 = 0;
+	gopt->r2 = 0;
+	gopt->r3 = 0;
+	gopt->length = 2; /* 4-byte multiple */
+	*(int *) &gopt->opt_data = bpf_htonl(0xfeedbeef);
 
-	ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt));
+	ret = bpf_skb_set_tunnel_opt(skb, gopt, sizeof(gopt));
 	if (ret < 0) {
 		log_err(ret);
 		return TC_ACT_SHOT;
@@ -735,6 +754,111 @@ int ipip_get_tunnel(struct __sk_buff *skb)
 }
 
 SEC("tc")
+int ipip_gue_set_tunnel(struct __sk_buff *skb)
+{
+	struct bpf_tunnel_key key = {};
+	struct bpf_fou_encap___local encap = {};
+	void *data = (void *)(long)skb->data;
+	struct iphdr *iph = data;
+	void *data_end = (void *)(long)skb->data_end;
+	int ret;
+
+	if (data + sizeof(*iph) > data_end) {
+		log_err(1);
+		return TC_ACT_SHOT;
+	}
+
+	key.tunnel_ttl = 64;
+	if (iph->protocol == IPPROTO_ICMP)
+		key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
+
+	ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0);
+	if (ret < 0) {
+		log_err(ret);
+		return TC_ACT_SHOT;
+	}
+
+	encap.sport = 0;
+	encap.dport = bpf_htons(5555);
+
+	ret = bpf_skb_set_fou_encap(skb, (struct bpf_fou_encap *)&encap,
+				    bpf_core_enum_value(enum bpf_fou_encap_type___local,
+							FOU_BPF_ENCAP_GUE___local));
+	if (ret < 0) {
+		log_err(ret);
+		return TC_ACT_SHOT;
+	}
+
+	return TC_ACT_OK;
+}
+
+SEC("tc")
+int ipip_fou_set_tunnel(struct __sk_buff *skb)
+{
+	struct bpf_tunnel_key key = {};
+	struct bpf_fou_encap___local encap = {};
+	void *data = (void *)(long)skb->data;
+	struct iphdr *iph = data;
+	void *data_end = (void *)(long)skb->data_end;
+	int ret;
+
+	if (data + sizeof(*iph) > data_end) {
+		log_err(1);
+		return TC_ACT_SHOT;
+	}
+
+	key.tunnel_ttl = 64;
+	if (iph->protocol == IPPROTO_ICMP)
+		key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
+
+	ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0);
+	if (ret < 0) {
+		log_err(ret);
+		return TC_ACT_SHOT;
+	}
+
+	encap.sport = 0;
+	encap.dport = bpf_htons(5555);
+
+	ret = bpf_skb_set_fou_encap(skb, (struct bpf_fou_encap *)&encap,
+				    FOU_BPF_ENCAP_FOU___local);
+	if (ret < 0) {
+		log_err(ret);
+		return TC_ACT_SHOT;
+	}
+
+	return TC_ACT_OK;
+}
+
+SEC("tc")
+int ipip_encap_get_tunnel(struct __sk_buff *skb)
+{
+	int ret;
+	struct bpf_tunnel_key key = {};
+	struct bpf_fou_encap___local encap = {};
+
+	ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
+	if (ret < 0) {
+		log_err(ret);
+		return TC_ACT_SHOT;
+	}
+
+	ret = bpf_skb_get_fou_encap(skb, (struct bpf_fou_encap *)&encap);
+	if (ret < 0) {
+		log_err(ret);
+		return TC_ACT_SHOT;
+	}
+
+	if (bpf_ntohs(encap.dport) != 5555)
+		return TC_ACT_SHOT;
+
+	bpf_printk("%d remote ip 0x%x, sport %d, dport %d\n", ret,
+		   key.remote_ipv4, bpf_ntohs(encap.sport),
+		   bpf_ntohs(encap.dport));
+	return TC_ACT_OK;
+}
+
+SEC("tc")
 int ipip6_set_tunnel(struct __sk_buff *skb)
 {
 	struct bpf_tunnel_key key = {};
@@ -831,6 +955,10 @@ int ip6ip6_get_tunnel(struct __sk_buff *skb)
 	return TC_ACT_OK;
 }
 
+volatile int xfrm_reqid = 0;
+volatile int xfrm_spi = 0;
+volatile int xfrm_remote_ip = 0;
+
 SEC("tc")
 int xfrm_get_state(struct __sk_buff *skb)
 {
@@ -841,10 +969,58 @@ int xfrm_get_state(struct __sk_buff *skb)
 	if (ret < 0)
 		return TC_ACT_OK;
 
-	bpf_printk("reqid %d spi 0x%x remote ip 0x%x\n",
-		   x.reqid, bpf_ntohl(x.spi),
-		   bpf_ntohl(x.remote_ipv4));
+	xfrm_reqid = x.reqid;
+	xfrm_spi = bpf_ntohl(x.spi);
+	xfrm_remote_ip = bpf_ntohl(x.remote_ipv4);
+
 	return TC_ACT_OK;
 }
 
+volatile int xfrm_replay_window = 0;
+
+SEC("xdp")
+int xfrm_get_state_xdp(struct xdp_md *xdp)
+{
+	struct bpf_xfrm_state_opts opts = {};
+	struct xfrm_state *x = NULL;
+	struct ip_esp_hdr *esph;
+	struct bpf_dynptr ptr;
+	u8 esph_buf[8] = {};
+	u8 iph_buf[20] = {};
+	struct iphdr *iph;
+	u32 off;
+
+	if (bpf_dynptr_from_xdp(xdp, 0, &ptr))
+		goto out;
+
+	off = sizeof(struct ethhdr);
+	iph = bpf_dynptr_slice(&ptr, off, iph_buf, sizeof(iph_buf));
+	if (!iph || iph->protocol != IPPROTO_ESP)
+		goto out;
+
+	off += sizeof(struct iphdr);
+	esph = bpf_dynptr_slice(&ptr, off, esph_buf, sizeof(esph_buf));
+	if (!esph)
+		goto out;
+
+	opts.netns_id = BPF_F_CURRENT_NETNS;
+	opts.daddr.a4 = iph->daddr;
+	opts.spi = esph->spi;
+	opts.proto = IPPROTO_ESP;
+	opts.family = AF_INET;
+
+	x = bpf_xdp_get_xfrm_state(xdp, &opts, sizeof(opts));
+	if (!x)
+		goto out;
+
+	if (!x->replay_esn)
+		goto out;
+
+	xfrm_replay_window = x->replay_esn->replay_window;
+out:
+	if (x)
+		bpf_xdp_xfrm_state_release(x);
+	return XDP_PASS;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_uprobe.c b/tools/testing/selftests/bpf/progs/test_uprobe.c
new file mode 100644
index 000000000000..12f4065fca20
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_uprobe.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Hengqi Chen */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+pid_t my_pid = 0;
+
+int test1_result = 0;
+int test2_result = 0;
+int test3_result = 0;
+int test4_result = 0;
+
+SEC("uprobe/./liburandom_read.so:urandlib_api_sameoffset")
+int BPF_UPROBE(test1)
+{
+	pid_t pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid != my_pid)
+		return 0;
+
+	test1_result = 1;
+	return 0;
+}
+
+SEC("uprobe/./liburandom_read.so:urandlib_api_sameoffset@LIBURANDOM_READ_1.0.0")
+int BPF_UPROBE(test2)
+{
+	pid_t pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid != my_pid)
+		return 0;
+
+	test2_result = 1;
+	return 0;
+}
+
+SEC("uretprobe/./liburandom_read.so:urandlib_api_sameoffset@@LIBURANDOM_READ_2.0.0")
+int BPF_URETPROBE(test3, int ret)
+{
+	pid_t pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid != my_pid)
+		return 0;
+
+	test3_result = ret;
+	return 0;
+}
+
+SEC("uprobe")
+int BPF_UPROBE(test4)
+{
+	pid_t pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid != my_pid)
+		return 0;
+
+	test4_result = 1;
+	return 0;
+}
+
+#if defined(__TARGET_ARCH_x86)
+struct pt_regs regs;
+
+SEC("uprobe")
+int BPF_UPROBE(test_regs_change)
+{
+	pid_t pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid != my_pid)
+		return 0;
+
+	ctx->ax  = regs.ax;
+	ctx->cx  = regs.cx;
+	ctx->dx  = regs.dx;
+	ctx->r8  = regs.r8;
+	ctx->r9  = regs.r9;
+	ctx->r10 = regs.r10;
+	ctx->r11 = regs.r11;
+	ctx->di  = regs.di;
+	ctx->si  = regs.si;
+	return 0;
+}
+
+unsigned long ip;
+
+SEC("uprobe")
+int BPF_UPROBE(test_regs_change_ip)
+{
+	pid_t pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid != my_pid)
+		return 0;
+
+	ctx->ip = ip;
+	return 0;
+}
+#endif
diff --git a/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c b/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c
index ab75522e2eeb..da4bf89d004c 100644
--- a/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c
+++ b/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c
@@ -6,18 +6,22 @@
 #include <bpf/bpf_core_read.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
 
 int uprobe_byname_parm1 = 0;
 int uprobe_byname_ran = 0;
 int uretprobe_byname_rc = 0;
+int uretprobe_byname_ret = 0;
 int uretprobe_byname_ran = 0;
-size_t uprobe_byname2_parm1 = 0;
+u64 uprobe_byname2_parm1 = 0;
 int uprobe_byname2_ran = 0;
-char *uretprobe_byname2_rc = NULL;
+u64 uretprobe_byname2_rc = 0;
 int uretprobe_byname2_ran = 0;
 
 int test_pid;
 
+int a[8];
+
 /* This program cannot auto-attach, but that should not stop other
  * programs from attaching.
  */
@@ -28,44 +32,84 @@ int handle_uprobe_noautoattach(struct pt_regs *ctx)
 }
 
 SEC("uprobe//proc/self/exe:autoattach_trigger_func")
-int handle_uprobe_byname(struct pt_regs *ctx)
+int BPF_UPROBE(handle_uprobe_byname
+	       , int arg1
+	       , int arg2
+	       , int arg3
+#if FUNC_REG_ARG_CNT > 3
+	       , int arg4
+#endif
+#if FUNC_REG_ARG_CNT > 4
+	       , int arg5
+#endif
+#if FUNC_REG_ARG_CNT > 5
+	       , int arg6
+#endif
+#if FUNC_REG_ARG_CNT > 6
+	       , int arg7
+#endif
+#if FUNC_REG_ARG_CNT > 7
+	       , int arg8
+#endif
+)
 {
 	uprobe_byname_parm1 = PT_REGS_PARM1_CORE(ctx);
 	uprobe_byname_ran = 1;
+
+	a[0] = arg1;
+	a[1] = arg2;
+	a[2] = arg3;
+#if FUNC_REG_ARG_CNT > 3
+	a[3] = arg4;
+#endif
+#if FUNC_REG_ARG_CNT > 4
+	a[4] = arg5;
+#endif
+#if FUNC_REG_ARG_CNT > 5
+	a[5] = arg6;
+#endif
+#if FUNC_REG_ARG_CNT > 6
+	a[6] = arg7;
+#endif
+#if FUNC_REG_ARG_CNT > 7
+	a[7] = arg8;
+#endif
 	return 0;
 }
 
 SEC("uretprobe//proc/self/exe:autoattach_trigger_func")
-int handle_uretprobe_byname(struct pt_regs *ctx)
+int BPF_URETPROBE(handle_uretprobe_byname, int ret)
 {
 	uretprobe_byname_rc = PT_REGS_RC_CORE(ctx);
+	uretprobe_byname_ret = ret;
 	uretprobe_byname_ran = 2;
+
 	return 0;
 }
 
 
-SEC("uprobe/libc.so.6:malloc")
-int handle_uprobe_byname2(struct pt_regs *ctx)
+SEC("uprobe/libc.so.6:fopen")
+int BPF_UPROBE(handle_uprobe_byname2, const char *pathname, const char *mode)
 {
 	int pid = bpf_get_current_pid_tgid() >> 32;
 
 	/* ignore irrelevant invocations */
 	if (test_pid != pid)
 		return 0;
-	uprobe_byname2_parm1 = PT_REGS_PARM1_CORE(ctx);
+	uprobe_byname2_parm1 = (u64)(long)pathname;
 	uprobe_byname2_ran = 3;
 	return 0;
 }
 
-SEC("uretprobe/libc.so.6:malloc")
-int handle_uretprobe_byname2(struct pt_regs *ctx)
+SEC("uretprobe/libc.so.6:fopen")
+int BPF_URETPROBE(handle_uretprobe_byname2, void *ret)
 {
 	int pid = bpf_get_current_pid_tgid() >> 32;
 
 	/* ignore irrelevant invocations */
 	if (test_pid != pid)
 		return 0;
-	uretprobe_byname2_rc = (char *)PT_REGS_RC_CORE(ctx);
+	uretprobe_byname2_rc = (u64)(long)ret;
 	uretprobe_byname2_ran = 4;
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_usdt.c b/tools/testing/selftests/bpf/progs/test_usdt.c
index 505aab9a5234..a78c87537b07 100644
--- a/tools/testing/selftests/bpf/progs/test_usdt.c
+++ b/tools/testing/selftests/bpf/progs/test_usdt.c
@@ -11,6 +11,7 @@ int usdt0_called;
 u64 usdt0_cookie;
 int usdt0_arg_cnt;
 int usdt0_arg_ret;
+int usdt0_arg_size;
 
 SEC("usdt")
 int usdt0(struct pt_regs *ctx)
@@ -26,6 +27,7 @@ int usdt0(struct pt_regs *ctx)
 	usdt0_arg_cnt = bpf_usdt_arg_cnt(ctx);
 	/* should return -ENOENT for any arg_num */
 	usdt0_arg_ret = bpf_usdt_arg(ctx, bpf_get_prandom_u32(), &tmp);
+	usdt0_arg_size = bpf_usdt_arg_size(ctx, bpf_get_prandom_u32());
 	return 0;
 }
 
@@ -34,6 +36,7 @@ u64 usdt3_cookie;
 int usdt3_arg_cnt;
 int usdt3_arg_rets[3];
 u64 usdt3_args[3];
+int usdt3_arg_sizes[3];
 
 SEC("usdt//proc/self/exe:test:usdt3")
 int usdt3(struct pt_regs *ctx)
@@ -50,12 +53,15 @@ int usdt3(struct pt_regs *ctx)
 
 	usdt3_arg_rets[0] = bpf_usdt_arg(ctx, 0, &tmp);
 	usdt3_args[0] = (int)tmp;
+	usdt3_arg_sizes[0] = bpf_usdt_arg_size(ctx, 0);
 
 	usdt3_arg_rets[1] = bpf_usdt_arg(ctx, 1, &tmp);
 	usdt3_args[1] = (long)tmp;
+	usdt3_arg_sizes[1] = bpf_usdt_arg_size(ctx, 1);
 
 	usdt3_arg_rets[2] = bpf_usdt_arg(ctx, 2, &tmp);
 	usdt3_args[2] = (uintptr_t)tmp;
+	usdt3_arg_sizes[2] = bpf_usdt_arg_size(ctx, 2);
 
 	return 0;
 }
@@ -64,12 +70,15 @@ int usdt12_called;
 u64 usdt12_cookie;
 int usdt12_arg_cnt;
 u64 usdt12_args[12];
+int usdt12_arg_sizes[12];
 
 SEC("usdt//proc/self/exe:test:usdt12")
 int BPF_USDT(usdt12, int a1, int a2, long a3, long a4, unsigned a5,
 		     long a6, __u64 a7, uintptr_t a8, int a9, short a10,
 		     short a11, signed char a12)
 {
+	int i;
+
 	if (my_pid != (bpf_get_current_pid_tgid() >> 32))
 		return 0;
 
@@ -90,6 +99,42 @@ int BPF_USDT(usdt12, int a1, int a2, long a3, long a4, unsigned a5,
 	usdt12_args[9] = a10;
 	usdt12_args[10] = a11;
 	usdt12_args[11] = a12;
+
+	bpf_for(i, 0, 12) {
+		usdt12_arg_sizes[i] = bpf_usdt_arg_size(ctx, i);
+	}
+
+	return 0;
+}
+
+int usdt_sib_called;
+u64 usdt_sib_cookie;
+int usdt_sib_arg_cnt;
+int usdt_sib_arg_ret;
+short usdt_sib_arg;
+int usdt_sib_arg_size;
+
+/*
+ * usdt_sib is only tested on x86-related architectures, so it requires
+ * manual attach since auto-attach will panic tests under other architectures
+ */
+SEC("usdt")
+int usdt_sib(struct pt_regs *ctx)
+{
+	long tmp;
+
+	if (my_pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	__sync_fetch_and_add(&usdt_sib_called, 1);
+
+	usdt_sib_cookie = bpf_usdt_cookie(ctx);
+	usdt_sib_arg_cnt = bpf_usdt_arg_cnt(ctx);
+
+	usdt_sib_arg_ret = bpf_usdt_arg(ctx, 0, &tmp);
+	usdt_sib_arg = (short)tmp;
+	usdt_sib_arg_size = bpf_usdt_arg_size(ctx, 0);
+
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_usdt_multispec.c b/tools/testing/selftests/bpf/progs/test_usdt_multispec.c
index aa6de32b50d1..962f3462066a 100644
--- a/tools/testing/selftests/bpf/progs/test_usdt_multispec.c
+++ b/tools/testing/selftests/bpf/progs/test_usdt_multispec.c
@@ -18,8 +18,6 @@ int usdt_100_sum;
 SEC("usdt//proc/self/exe:test:usdt_100")
 int BPF_USDT(usdt_100, int x)
 {
-	long tmp;
-
 	if (my_pid != (bpf_get_current_pid_tgid() >> 32))
 		return 0;
 
diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale1.c b/tools/testing/selftests/bpf/progs/test_verif_scale1.c
index ac6135d9374c..323a73fb2e8c 100644
--- a/tools/testing/selftests/bpf/progs/test_verif_scale1.c
+++ b/tools/testing/selftests/bpf/progs/test_verif_scale1.c
@@ -11,7 +11,7 @@ int balancer_ingress(struct __sk_buff *ctx)
 	void *data_end = (void *)(long)ctx->data_end;
 	void *data = (void *)(long)ctx->data;
 	void *ptr;
-	int ret = 0, nh_off, i = 0;
+	int nh_off, i = 0;
 
 	nh_off = 14;
 
diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale2.c b/tools/testing/selftests/bpf/progs/test_verif_scale2.c
index f90ffcafd1e8..f5318f757084 100644
--- a/tools/testing/selftests/bpf/progs/test_verif_scale2.c
+++ b/tools/testing/selftests/bpf/progs/test_verif_scale2.c
@@ -11,7 +11,7 @@ int balancer_ingress(struct __sk_buff *ctx)
 	void *data_end = (void *)(long)ctx->data_end;
 	void *data = (void *)(long)ctx->data;
 	void *ptr;
-	int ret = 0, nh_off, i = 0;
+	int nh_off, i = 0;
 
 	nh_off = 14;
 
diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale3.c b/tools/testing/selftests/bpf/progs/test_verif_scale3.c
index ca33a9b711c4..2e06dbb1ad5c 100644
--- a/tools/testing/selftests/bpf/progs/test_verif_scale3.c
+++ b/tools/testing/selftests/bpf/progs/test_verif_scale3.c
@@ -11,7 +11,7 @@ int balancer_ingress(struct __sk_buff *ctx)
 	void *data_end = (void *)(long)ctx->data_end;
 	void *data = (void *)(long)ctx->data;
 	void *ptr;
-	int ret = 0, nh_off, i = 0;
+	int nh_off, i = 0;
 
 	nh_off = 32;
 
diff --git a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c
index ce419304ff1f..ff8d755548b9 100644
--- a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c
+++ b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c
@@ -10,19 +10,14 @@
 #include <errno.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
+#include "bpf_kfuncs.h"
+#include "err.h"
 
 #define MAX_DATA_SIZE (1024 * 1024)
 #define MAX_SIG_SIZE 1024
 
-extern struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym;
-extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym;
-extern void bpf_key_put(struct bpf_key *key) __ksym;
-extern int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_ptr,
-				      struct bpf_dynptr *sig_ptr,
-				      struct bpf_key *trusted_keyring) __ksym;
-
 __u32 monitored_pid;
-__u32 user_keyring_serial;
+__s32 user_keyring_serial;
 __u64 system_keyring_id;
 
 struct data {
@@ -42,7 +37,7 @@ struct {
 char _license[] SEC("license") = "GPL";
 
 SEC("lsm.s/bpf")
-int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size)
+int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
 {
 	struct bpf_dynptr data_ptr, sig_ptr;
 	struct data *data_val;
@@ -59,10 +54,14 @@ int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size)
 	if (!data_val)
 		return 0;
 
-	bpf_probe_read(&value, sizeof(value), &attr->value);
+	ret = bpf_probe_read_kernel(&value, sizeof(value), &attr->value);
+	if (ret)
+		goto out;
 
-	bpf_copy_from_user(data_val, sizeof(struct data),
-			   (void *)(unsigned long)value);
+	ret = bpf_copy_from_user(data_val, sizeof(struct data),
+				 (void *)(unsigned long)value);
+	if (ret)
+		goto out;
 
 	if (data_val->data_len > sizeof(data_val->data))
 		return -EINVAL;
@@ -86,5 +85,8 @@ int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size)
 
 	bpf_key_put(trusted_keyring);
 
+out:
+	set_if_not_errno_or_zero(ret, -EFAULT);
+
 	return ret;
 }
diff --git a/tools/testing/selftests/bpf/progs/test_vmlinux.c b/tools/testing/selftests/bpf/progs/test_vmlinux.c
index e9dfa0313d1b..78b23934d9f8 100644
--- a/tools/testing/selftests/bpf/progs/test_vmlinux.c
+++ b/tools/testing/selftests/bpf/progs/test_vmlinux.c
@@ -16,12 +16,12 @@ bool kprobe_called = false;
 bool fentry_called = false;
 
 SEC("tp/syscalls/sys_enter_nanosleep")
-int handle__tp(struct trace_event_raw_sys_enter *args)
+int handle__tp(struct syscall_trace_enter *args)
 {
 	struct __kernel_timespec *ts;
 	long tv_nsec;
 
-	if (args->id != __NR_nanosleep)
+	if (args->nr != __NR_nanosleep)
 		return 0;
 
 	ts = (void *)args->args[0];
@@ -42,7 +42,7 @@ int BPF_PROG(handle__raw_tp, struct pt_regs *regs, long id)
 	if (id != __NR_nanosleep)
 		return 0;
 
-	ts = (void *)PT_REGS_PARM1_CORE(regs);
+	ts = (void *)PT_REGS_PARM1_CORE_SYSCALL(regs);
 	if (bpf_probe_read_user(&tv_nsec, sizeof(ts->tv_nsec), &ts->tv_nsec) ||
 	    tv_nsec != MY_TV_NSEC)
 		return 0;
@@ -60,7 +60,7 @@ int BPF_PROG(handle__tp_btf, struct pt_regs *regs, long id)
 	if (id != __NR_nanosleep)
 		return 0;
 
-	ts = (void *)PT_REGS_PARM1_CORE(regs);
+	ts = (void *)PT_REGS_PARM1_CORE_SYSCALL(regs);
 	if (bpf_probe_read_user(&tv_nsec, sizeof(ts->tv_nsec), &ts->tv_nsec) ||
 	    tv_nsec != MY_TV_NSEC)
 		return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp.c b/tools/testing/selftests/bpf/progs/test_xdp.c
index d7a9a74b7245..8caf58be5818 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp.c
@@ -19,6 +19,7 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 #include "test_iptunnel_common.h"
+#include "bpf_compiler.h"
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
@@ -137,7 +138,7 @@ static __always_inline int handle_ipv4(struct xdp_md *xdp)
 	iph->ttl = 8;
 
 	next_iph = (__u16 *)iph;
-#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (i = 0; i < sizeof(*iph) >> 1; i++)
 		csum += *next_iph++;
 
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c
index 53b64c999450..5904f45cfbc4 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c
@@ -5,26 +5,38 @@
 SEC("xdp")
 int _xdp_adjust_tail_grow(struct xdp_md *xdp)
 {
-	void *data_end = (void *)(long)xdp->data_end;
-	void *data = (void *)(long)xdp->data;
 	int data_len = bpf_xdp_get_buff_len(xdp);
 	int offset = 0;
+	/* SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) */
+#if defined(__TARGET_ARCH_s390)
+	int tailroom = 512;
+#elif defined(__TARGET_ARCH_powerpc)
+	int tailroom = 384;
+#else
+	int tailroom = 320;
+#endif
 
 	/* Data length determine test case */
 
 	if (data_len == 54) { /* sizeof(pkt_v4) */
-		offset = 4096; /* test too large offset */
+		offset = 4096; /* test too large offset, 4k page size */
+	} else if (data_len == 53) { /* sizeof(pkt_v4) - 1 */
+		offset = 65536; /* test too large offset, 64k page size */
 	} else if (data_len == 74) { /* sizeof(pkt_v6) */
 		offset = 40;
 	} else if (data_len == 64) {
 		offset = 128;
 	} else if (data_len == 128) {
 		/* Max tail grow 3520 */
-		offset = 4096 - 256 - 320 - data_len;
+		offset = 4096 - 256 - tailroom - data_len;
 	} else if (data_len == 9000) {
 		offset = 10;
 	} else if (data_len == 9001) {
 		offset = 4096;
+	} else if (data_len == 90000) {
+		offset = 10; /* test a small offset, 64k page size */
+	} else if (data_len == 90001) {
+		offset = 65536; /* test too large offset, 64k page size */
 	} else {
 		return XDP_ABORTED; /* No matching test */
 	}
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_attach_fail.c b/tools/testing/selftests/bpf/progs/test_xdp_attach_fail.c
new file mode 100644
index 000000000000..2ff1b596e87e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_xdp_attach_fail.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Leon Hwang */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+#define ERRMSG_LEN 64
+
+struct xdp_errmsg {
+	char msg[ERRMSG_LEN];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
+	__type(key, int);
+	__type(value, int);
+} xdp_errmsg_pb SEC(".maps");
+
+struct xdp_attach_error_ctx {
+	unsigned long unused;
+
+	/*
+	 * bpf does not support tracepoint __data_loc directly.
+	 *
+	 * Actually, this field is a 32 bit integer whose value encodes
+	 * information on where to find the actual data. The first 2 bytes is
+	 * the size of the data. The last 2 bytes is the offset from the start
+	 * of the tracepoint struct where the data begins.
+	 * -- https://github.com/iovisor/bpftrace/pull/1542
+	 */
+	__u32 msg; // __data_loc char[] msg;
+};
+
+/*
+ * Catch the error message at the tracepoint.
+ */
+
+SEC("tp/xdp/bpf_xdp_link_attach_failed")
+int tp__xdp__bpf_xdp_link_attach_failed(struct xdp_attach_error_ctx *ctx)
+{
+	char *msg = (void *)(__u64) ((void *) ctx + (__u16) ctx->msg);
+	struct xdp_errmsg errmsg = {};
+
+	bpf_probe_read_kernel_str(&errmsg.msg, ERRMSG_LEN, msg);
+	bpf_perf_event_output(ctx, &xdp_errmsg_pb, BPF_F_CURRENT_CPU, &errmsg,
+			      ERRMSG_LEN);
+	return 0;
+}
+
+/*
+ * Reuse the XDP program in xdp_dummy.c.
+ */
+
+char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c
index 3379d303f41a..ee48c4963971 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c
@@ -45,8 +45,6 @@ SEC("fentry/FUNC")
 int BPF_PROG(trace_on_entry, struct xdp_buff *xdp)
 {
 	struct meta meta;
-	void *data_end = (void *)(long)xdp->data_end;
-	void *data = (void *)(long)xdp->data;
 
 	meta.ifindex = xdp->rxq->dev->ifindex;
 	meta.pkt_len = bpf_xdp_get_buff_len((struct xdp_md *)xdp);
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_devmap_tailcall.c b/tools/testing/selftests/bpf/progs/test_xdp_devmap_tailcall.c
new file mode 100644
index 000000000000..814e2a980e97
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_xdp_devmap_tailcall.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+SEC("xdp")
+int xdp_devmap(struct xdp_md *ctx)
+{
+	return ctx->egress_ifindex;
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__array(values, int (void *));
+} xdp_map SEC(".maps") = {
+	.values = {
+		[0] = (void *)&xdp_devmap,
+	},
+};
+
+SEC("xdp")
+int xdp_entry(struct xdp_md *ctx)
+{
+	bpf_tail_call(ctx, &xdp_map, 0);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c
index 77a123071940..5928ed0911ca 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c
@@ -4,6 +4,19 @@
 
 #define ETH_ALEN 6
 #define HDR_SZ (sizeof(struct ethhdr) + sizeof(struct ipv6hdr) + sizeof(struct udphdr))
+
+/**
+ * enum frame_mark - magics to distinguish page/packet paths
+ * @MARK_XMIT: page was recycled due to the frame being "xmitted" by the NIC.
+ * @MARK_IN: frame is being processed by the input XDP prog.
+ * @MARK_SKB: frame did hit the TC ingress hook as an skb.
+ */
+enum frame_mark {
+	MARK_XMIT	= 0U,
+	MARK_IN		= 0x42,
+	MARK_SKB	= 0x45,
+};
+
 const volatile int ifindex_out;
 const volatile int ifindex_in;
 const volatile __u8 expect_dst[ETH_ALEN];
@@ -25,7 +38,7 @@ int xdp_redirect(struct xdp_md *xdp)
 	if (payload + 1 > data_end)
 		return XDP_ABORTED;
 
-	if (xdp->ingress_ifindex != ifindex_in)
+	if (xdp->ingress_ifindex != (__u32)ifindex_in)
 		return XDP_ABORTED;
 
 	if (metadata + 1 > data)
@@ -34,12 +47,12 @@ int xdp_redirect(struct xdp_md *xdp)
 	if (*metadata != 0x42)
 		return XDP_ABORTED;
 
-	if (*payload == 0) {
-		*payload = 0x42;
+	if (*payload == MARK_XMIT)
 		pkts_seen_zero++;
-	}
 
-	if (bpf_xdp_adjust_meta(xdp, 4))
+	*payload = MARK_IN;
+
+	if (bpf_xdp_adjust_meta(xdp, sizeof(__u64)))
 		return XDP_ABORTED;
 
 	if (retcode > XDP_PASS)
@@ -51,7 +64,7 @@ int xdp_redirect(struct xdp_md *xdp)
 	return ret;
 }
 
-static bool check_pkt(void *data, void *data_end)
+static bool check_pkt(void *data, void *data_end, const __u32 mark)
 {
 	struct ipv6hdr *iph = data + sizeof(struct ethhdr);
 	__u8 *payload = data + HDR_SZ;
@@ -59,13 +72,13 @@ static bool check_pkt(void *data, void *data_end)
 	if (payload + 1 > data_end)
 		return false;
 
-	if (iph->nexthdr != IPPROTO_UDP || *payload != 0x42)
+	if (iph->nexthdr != IPPROTO_UDP || *payload != MARK_IN)
 		return false;
 
 	/* reset the payload so the same packet doesn't get counted twice when
 	 * it cycles back through the kernel path and out the dst veth
 	 */
-	*payload = 0;
+	*payload = mark;
 	return true;
 }
 
@@ -75,25 +88,40 @@ int xdp_count_pkts(struct xdp_md *xdp)
 	void *data = (void *)(long)xdp->data;
 	void *data_end = (void *)(long)xdp->data_end;
 
-	if (check_pkt(data, data_end))
+	if (check_pkt(data, data_end, MARK_XMIT))
 		pkts_seen_xdp++;
 
-	/* Return XDP_DROP to make sure the data page is recycled, like when it
-	 * exits a physical NIC. Recycled pages will be counted in the
+	/* Return %XDP_DROP to recycle the data page with %MARK_XMIT, like
+	 * it exited a physical NIC. Those pages will be counted in the
 	 * pkts_seen_zero counter above.
 	 */
 	return XDP_DROP;
 }
 
+SEC("xdp")
+int xdp_redirect_to_111(struct xdp_md *xdp)
+{
+	return bpf_redirect(111, 0);
+}
+
+SEC("xdp")
+int xdp_redirect_to_222(struct xdp_md *xdp)
+{
+	return bpf_redirect(222, 0);
+}
+
 SEC("tc")
 int tc_count_pkts(struct __sk_buff *skb)
 {
 	void *data = (void *)(long)skb->data;
 	void *data_end = (void *)(long)skb->data_end;
 
-	if (check_pkt(data, data_end))
+	if (check_pkt(data, data_end, MARK_SKB))
 		pkts_seen_tc++;
 
+	/* Will be either recycled or freed, %MARK_SKB makes sure it won't
+	 * hit any of the counters above.
+	 */
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c b/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c
new file mode 100644
index 000000000000..67a77944ef29
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_xdp_dynptr.c
@@ -0,0 +1,256 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta */
+#include <stddef.h>
+#include <string.h>
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/udp.h>
+#include <linux/tcp.h>
+#include <linux/pkt_cls.h>
+#include <sys/socket.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include "test_iptunnel_common.h"
+#include "bpf_kfuncs.h"
+
+#define tcphdr_sz sizeof(struct tcphdr)
+#define udphdr_sz sizeof(struct udphdr)
+#define ethhdr_sz sizeof(struct ethhdr)
+#define iphdr_sz sizeof(struct iphdr)
+#define ipv6hdr_sz sizeof(struct ipv6hdr)
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, 256);
+	__type(key, __u32);
+	__type(value, __u64);
+} rxcnt SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, MAX_IPTNL_ENTRIES);
+	__type(key, struct vip);
+	__type(value, struct iptnl_info);
+} vip2tnl SEC(".maps");
+
+static __always_inline void count_tx(__u32 protocol)
+{
+	__u64 *rxcnt_count;
+
+	rxcnt_count = bpf_map_lookup_elem(&rxcnt, &protocol);
+	if (rxcnt_count)
+		*rxcnt_count += 1;
+}
+
+static __always_inline int get_dport(void *trans_data, __u8 protocol)
+{
+	struct tcphdr *th;
+	struct udphdr *uh;
+
+	switch (protocol) {
+	case IPPROTO_TCP:
+		th = (struct tcphdr *)trans_data;
+		return th->dest;
+	case IPPROTO_UDP:
+		uh = (struct udphdr *)trans_data;
+		return uh->dest;
+	default:
+		return 0;
+	}
+}
+
+static __always_inline void set_ethhdr(struct ethhdr *new_eth,
+				       const struct ethhdr *old_eth,
+				       const struct iptnl_info *tnl,
+				       __be16 h_proto)
+{
+	memcpy(new_eth->h_source, old_eth->h_dest, sizeof(new_eth->h_source));
+	memcpy(new_eth->h_dest, tnl->dmac, sizeof(new_eth->h_dest));
+	new_eth->h_proto = h_proto;
+}
+
+static __always_inline int handle_ipv4(struct xdp_md *xdp, struct bpf_dynptr *xdp_ptr)
+{
+	__u8 eth_buffer[ethhdr_sz + iphdr_sz + ethhdr_sz];
+	__u8 iph_buffer_tcp[iphdr_sz + tcphdr_sz];
+	__u8 iph_buffer_udp[iphdr_sz + udphdr_sz];
+	struct bpf_dynptr new_xdp_ptr;
+	struct iptnl_info *tnl;
+	struct ethhdr *new_eth;
+	struct ethhdr *old_eth;
+	struct iphdr *iph;
+	__u16 *next_iph;
+	__u16 payload_len;
+	struct vip vip = {};
+	int dport;
+	__u32 csum = 0;
+	int i;
+
+	__builtin_memset(eth_buffer, 0, sizeof(eth_buffer));
+	__builtin_memset(iph_buffer_tcp, 0, sizeof(iph_buffer_tcp));
+	__builtin_memset(iph_buffer_udp, 0, sizeof(iph_buffer_udp));
+
+	if (ethhdr_sz + iphdr_sz + tcphdr_sz > xdp->data_end - xdp->data)
+		iph = bpf_dynptr_slice(xdp_ptr, ethhdr_sz, iph_buffer_udp, sizeof(iph_buffer_udp));
+	else
+		iph = bpf_dynptr_slice(xdp_ptr, ethhdr_sz, iph_buffer_tcp, sizeof(iph_buffer_tcp));
+
+	if (!iph)
+		return XDP_DROP;
+
+	dport = get_dport(iph + 1, iph->protocol);
+	if (dport == -1)
+		return XDP_DROP;
+
+	vip.protocol = iph->protocol;
+	vip.family = AF_INET;
+	vip.daddr.v4 = iph->daddr;
+	vip.dport = dport;
+	payload_len = bpf_ntohs(iph->tot_len);
+
+	tnl = bpf_map_lookup_elem(&vip2tnl, &vip);
+	/* It only does v4-in-v4 */
+	if (!tnl || tnl->family != AF_INET)
+		return XDP_PASS;
+
+	if (bpf_xdp_adjust_head(xdp, 0 - (int)iphdr_sz))
+		return XDP_DROP;
+
+	bpf_dynptr_from_xdp(xdp, 0, &new_xdp_ptr);
+	new_eth = bpf_dynptr_slice_rdwr(&new_xdp_ptr, 0, eth_buffer, sizeof(eth_buffer));
+	if (!new_eth)
+		return XDP_DROP;
+
+	iph = (struct iphdr *)(new_eth + 1);
+	old_eth = (struct ethhdr *)(iph + 1);
+
+	set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IP));
+
+	if (new_eth == eth_buffer)
+		bpf_dynptr_write(&new_xdp_ptr, 0, eth_buffer, sizeof(eth_buffer), 0);
+
+	iph->version = 4;
+	iph->ihl = iphdr_sz >> 2;
+	iph->frag_off =	0;
+	iph->protocol = IPPROTO_IPIP;
+	iph->check = 0;
+	iph->tos = 0;
+	iph->tot_len = bpf_htons(payload_len + iphdr_sz);
+	iph->daddr = tnl->daddr.v4;
+	iph->saddr = tnl->saddr.v4;
+	iph->ttl = 8;
+
+	next_iph = (__u16 *)iph;
+	for (i = 0; i < iphdr_sz >> 1; i++)
+		csum += *next_iph++;
+
+	iph->check = ~((csum & 0xffff) + (csum >> 16));
+
+	count_tx(vip.protocol);
+
+	return XDP_TX;
+}
+
+static __always_inline int handle_ipv6(struct xdp_md *xdp, struct bpf_dynptr *xdp_ptr)
+{
+	__u8 eth_buffer[ethhdr_sz + ipv6hdr_sz + ethhdr_sz];
+	__u8 ip6h_buffer_tcp[ipv6hdr_sz + tcphdr_sz];
+	__u8 ip6h_buffer_udp[ipv6hdr_sz + udphdr_sz];
+	struct bpf_dynptr new_xdp_ptr;
+	struct iptnl_info *tnl;
+	struct ethhdr *new_eth;
+	struct ethhdr *old_eth;
+	struct ipv6hdr *ip6h;
+	__u16 payload_len;
+	struct vip vip = {};
+	int dport;
+
+	__builtin_memset(eth_buffer, 0, sizeof(eth_buffer));
+	__builtin_memset(ip6h_buffer_tcp, 0, sizeof(ip6h_buffer_tcp));
+	__builtin_memset(ip6h_buffer_udp, 0, sizeof(ip6h_buffer_udp));
+
+	if (ethhdr_sz + iphdr_sz + tcphdr_sz > xdp->data_end - xdp->data)
+		ip6h = bpf_dynptr_slice(xdp_ptr, ethhdr_sz, ip6h_buffer_udp, sizeof(ip6h_buffer_udp));
+	else
+		ip6h = bpf_dynptr_slice(xdp_ptr, ethhdr_sz, ip6h_buffer_tcp, sizeof(ip6h_buffer_tcp));
+
+	if (!ip6h)
+		return XDP_DROP;
+
+	dport = get_dport(ip6h + 1, ip6h->nexthdr);
+	if (dport == -1)
+		return XDP_DROP;
+
+	vip.protocol = ip6h->nexthdr;
+	vip.family = AF_INET6;
+	memcpy(vip.daddr.v6, ip6h->daddr.s6_addr32, sizeof(vip.daddr));
+	vip.dport = dport;
+	payload_len = ip6h->payload_len;
+
+	tnl = bpf_map_lookup_elem(&vip2tnl, &vip);
+	/* It only does v6-in-v6 */
+	if (!tnl || tnl->family != AF_INET6)
+		return XDP_PASS;
+
+	if (bpf_xdp_adjust_head(xdp, 0 - (int)ipv6hdr_sz))
+		return XDP_DROP;
+
+	bpf_dynptr_from_xdp(xdp, 0, &new_xdp_ptr);
+	new_eth = bpf_dynptr_slice_rdwr(&new_xdp_ptr, 0, eth_buffer, sizeof(eth_buffer));
+	if (!new_eth)
+		return XDP_DROP;
+
+	ip6h = (struct ipv6hdr *)(new_eth + 1);
+	old_eth = (struct ethhdr *)(ip6h + 1);
+
+	set_ethhdr(new_eth, old_eth, tnl, bpf_htons(ETH_P_IPV6));
+
+	if (new_eth == eth_buffer)
+		bpf_dynptr_write(&new_xdp_ptr, 0, eth_buffer, sizeof(eth_buffer), 0);
+
+	ip6h->version = 6;
+	ip6h->priority = 0;
+	memset(ip6h->flow_lbl, 0, sizeof(ip6h->flow_lbl));
+	ip6h->payload_len = bpf_htons(bpf_ntohs(payload_len) + ipv6hdr_sz);
+	ip6h->nexthdr = IPPROTO_IPV6;
+	ip6h->hop_limit = 8;
+	memcpy(ip6h->saddr.s6_addr32, tnl->saddr.v6, sizeof(tnl->saddr.v6));
+	memcpy(ip6h->daddr.s6_addr32, tnl->daddr.v6, sizeof(tnl->daddr.v6));
+
+	count_tx(vip.protocol);
+
+	return XDP_TX;
+}
+
+SEC("xdp")
+int _xdp_tx_iptunnel(struct xdp_md *xdp)
+{
+	__u8 buffer[ethhdr_sz];
+	struct bpf_dynptr ptr;
+	struct ethhdr *eth;
+	__u16 h_proto;
+
+	__builtin_memset(buffer, 0, sizeof(buffer));
+
+	bpf_dynptr_from_xdp(xdp, 0, &ptr);
+	eth = bpf_dynptr_slice(&ptr, 0, buffer, sizeof(buffer));
+	if (!eth)
+		return XDP_DROP;
+
+	h_proto = eth->h_proto;
+
+	if (h_proto == bpf_htons(ETH_P_IP))
+		return handle_ipv4(xdp, &ptr);
+	else if (h_proto == bpf_htons(ETH_P_IPV6))
+
+		return handle_ipv6(xdp, &ptr);
+	else
+		return XDP_DROP;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_loop.c b/tools/testing/selftests/bpf/progs/test_xdp_loop.c
index c98fb44156f0..93267a68825b 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_loop.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_loop.c
@@ -15,6 +15,7 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 #include "test_iptunnel_common.h"
+#include "bpf_compiler.h"
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
@@ -133,7 +134,7 @@ static __always_inline int handle_ipv4(struct xdp_md *xdp)
 	iph->ttl = 8;
 
 	next_iph = (__u16 *)iph;
-#pragma clang loop unroll(disable)
+	__pragma_loop_no_unroll
 	for (i = 0; i < sizeof(*iph) >> 1; i++)
 		csum += *next_iph++;
 
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_meta.c b/tools/testing/selftests/bpf/progs/test_xdp_meta.c
index a7c4a7d49fe6..0a0f371a2dec 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_meta.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_meta.c
@@ -1,40 +1,320 @@
+#include <stdbool.h>
 #include <linux/bpf.h>
+#include <linux/errno.h>
 #include <linux/if_ether.h>
 #include <linux/pkt_cls.h>
 
+#include <bpf/bpf_endian.h>
 #include <bpf/bpf_helpers.h>
+#include "bpf_kfuncs.h"
+
+#define META_SIZE 32
 
-#define __round_mask(x, y) ((__typeof__(x))((y) - 1))
-#define round_up(x, y) ((((x) - 1) | __round_mask(x, y)) + 1)
 #define ctx_ptr(ctx, mem) (void *)(unsigned long)ctx->mem
 
-SEC("t")
+/* Demonstrate passing metadata from XDP to TC using bpf_xdp_adjust_meta.
+ *
+ * The XDP program extracts a fixed-size payload following the Ethernet header
+ * and stores it as packet metadata to test the driver's metadata support. The
+ * TC program then verifies if the passed metadata is correct.
+ */
+
+bool test_pass;
+
+static const __u8 smac_want[ETH_ALEN] = {
+	0x12, 0x34, 0xDE, 0xAD, 0xBE, 0xEF,
+};
+
+static const __u8 meta_want[META_SIZE] = {
+	0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08,
+	0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18,
+	0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28,
+	0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38,
+};
+
+static bool check_smac(const struct ethhdr *eth)
+{
+	return !__builtin_memcmp(eth->h_source, smac_want, ETH_ALEN);
+}
+
+static bool check_metadata(const char *file, int line, __u8 *meta_have)
+{
+	if (!__builtin_memcmp(meta_have, meta_want, META_SIZE))
+		return true;
+
+	bpf_stream_printk(BPF_STREAM_STDERR,
+			  "FAIL:%s:%d: metadata mismatch\n"
+			  "  have:\n    %pI6\n    %pI6\n"
+			  "  want:\n    %pI6\n    %pI6\n",
+			  file, line,
+			  &meta_have[0x00], &meta_have[0x10],
+			  &meta_want[0x00], &meta_want[0x10]);
+	return false;
+}
+
+#define check_metadata(meta_have) check_metadata(__FILE__, __LINE__, meta_have)
+
+static bool check_skb_metadata(const char *file, int line, struct __sk_buff *skb)
+{
+	__u8 *data_meta = ctx_ptr(skb, data_meta);
+	__u8 *data = ctx_ptr(skb, data);
+
+	return data_meta + META_SIZE <= data && (check_metadata)(file, line, data_meta);
+}
+
+#define check_skb_metadata(skb) check_skb_metadata(__FILE__, __LINE__, skb)
+
+SEC("tc")
 int ing_cls(struct __sk_buff *ctx)
 {
-	__u8 *data, *data_meta, *data_end;
-	__u32 diff = 0;
+	__u8 *meta_have = ctx_ptr(ctx, data_meta);
+	__u8 *data = ctx_ptr(ctx, data);
 
-	data_meta = ctx_ptr(ctx, data_meta);
-	data_end  = ctx_ptr(ctx, data_end);
-	data      = ctx_ptr(ctx, data);
+	if (meta_have + META_SIZE > data)
+		goto out;
+
+	if (!check_metadata(meta_have))
+		goto out;
+
+	test_pass = true;
+out:
+	return TC_ACT_SHOT;
+}
+
+/* Read from metadata using bpf_dynptr_read helper */
+SEC("tc")
+int ing_cls_dynptr_read(struct __sk_buff *ctx)
+{
+	__u8 meta_have[META_SIZE];
+	struct bpf_dynptr meta;
+
+	bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+	bpf_dynptr_read(meta_have, META_SIZE, &meta, 0, 0);
+
+	if (!check_metadata(meta_have))
+		goto out;
+
+	test_pass = true;
+out:
+	return TC_ACT_SHOT;
+}
+
+/* Write to metadata using bpf_dynptr_write helper */
+SEC("tc")
+int ing_cls_dynptr_write(struct __sk_buff *ctx)
+{
+	struct bpf_dynptr data, meta;
+	__u8 *src;
+
+	bpf_dynptr_from_skb(ctx, 0, &data);
+	src = bpf_dynptr_slice(&data, sizeof(struct ethhdr), NULL, META_SIZE);
+	if (!src)
+		return TC_ACT_SHOT;
+
+	bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+	bpf_dynptr_write(&meta, 0, src, META_SIZE, 0);
+
+	return TC_ACT_UNSPEC; /* pass */
+}
+
+/* Read from metadata using read-only dynptr slice */
+SEC("tc")
+int ing_cls_dynptr_slice(struct __sk_buff *ctx)
+{
+	struct bpf_dynptr meta;
+	__u8 *meta_have;
+
+	bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+	meta_have = bpf_dynptr_slice(&meta, 0, NULL, META_SIZE);
+	if (!meta_have)
+		goto out;
+
+	if (!check_metadata(meta_have))
+		goto out;
+
+	test_pass = true;
+out:
+	return TC_ACT_SHOT;
+}
+
+/* Write to metadata using writeable dynptr slice */
+SEC("tc")
+int ing_cls_dynptr_slice_rdwr(struct __sk_buff *ctx)
+{
+	struct bpf_dynptr data, meta;
+	__u8 *src, *dst;
 
-	if (data + ETH_ALEN > data_end ||
-	    data_meta + round_up(ETH_ALEN, 4) > data)
+	bpf_dynptr_from_skb(ctx, 0, &data);
+	src = bpf_dynptr_slice(&data, sizeof(struct ethhdr), NULL, META_SIZE);
+	if (!src)
 		return TC_ACT_SHOT;
 
-	diff |= ((__u32 *)data_meta)[0] ^ ((__u32 *)data)[0];
-	diff |= ((__u16 *)data_meta)[2] ^ ((__u16 *)data)[2];
+	bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+	dst = bpf_dynptr_slice_rdwr(&meta, 0, NULL, META_SIZE);
+	if (!dst)
+		return TC_ACT_SHOT;
+
+	__builtin_memcpy(dst, src, META_SIZE);
+
+	return TC_ACT_UNSPEC; /* pass */
+}
+
+/* Read skb metadata in chunks from various offsets in different ways. */
+SEC("tc")
+int ing_cls_dynptr_offset_rd(struct __sk_buff *ctx)
+{
+	const __u32 chunk_len = META_SIZE / 4;
+	__u8 meta_have[META_SIZE];
+	struct bpf_dynptr meta;
+	__u8 *dst, *src;
+
+	dst = meta_have;
+
+	/* 1. Regular read */
+	bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+	bpf_dynptr_read(dst, chunk_len, &meta, 0, 0);
+	dst += chunk_len;
+
+	/* 2. Read from an offset-adjusted dynptr */
+	bpf_dynptr_adjust(&meta, chunk_len, bpf_dynptr_size(&meta));
+	bpf_dynptr_read(dst, chunk_len, &meta, 0, 0);
+	dst += chunk_len;
+
+	/* 3. Read at an offset */
+	bpf_dynptr_read(dst, chunk_len, &meta, chunk_len, 0);
+	dst += chunk_len;
+
+	/* 4. Read from a slice starting at an offset */
+	src = bpf_dynptr_slice(&meta, 2 * chunk_len, NULL, chunk_len);
+	if (!src)
+		goto out;
+	__builtin_memcpy(dst, src, chunk_len);
+
+	if (!check_metadata(meta_have))
+		goto out;
 
-	return diff ? TC_ACT_SHOT : TC_ACT_OK;
+	test_pass = true;
+out:
+	return TC_ACT_SHOT;
 }
 
-SEC("x")
+/* Write skb metadata in chunks at various offsets in different ways. */
+SEC("tc")
+int ing_cls_dynptr_offset_wr(struct __sk_buff *ctx)
+{
+	const __u32 chunk_len = META_SIZE / 4;
+	__u8 payload[META_SIZE];
+	struct bpf_dynptr meta;
+	__u8 *dst, *src;
+
+	bpf_skb_load_bytes(ctx, sizeof(struct ethhdr), payload, sizeof(payload));
+	src = payload;
+
+	/* 1. Regular write */
+	bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+	bpf_dynptr_write(&meta, 0, src, chunk_len, 0);
+	src += chunk_len;
+
+	/* 2. Write to an offset-adjusted dynptr */
+	bpf_dynptr_adjust(&meta, chunk_len, bpf_dynptr_size(&meta));
+	bpf_dynptr_write(&meta, 0, src, chunk_len, 0);
+	src += chunk_len;
+
+	/* 3. Write at an offset */
+	bpf_dynptr_write(&meta, chunk_len, src, chunk_len, 0);
+	src += chunk_len;
+
+	/* 4. Write to a slice starting at an offset */
+	dst = bpf_dynptr_slice_rdwr(&meta, 2 * chunk_len, NULL, chunk_len);
+	if (!dst)
+		return TC_ACT_SHOT;
+	__builtin_memcpy(dst, src, chunk_len);
+
+	return TC_ACT_UNSPEC; /* pass */
+}
+
+/* Pass an OOB offset to dynptr read, write, adjust, slice. */
+SEC("tc")
+int ing_cls_dynptr_offset_oob(struct __sk_buff *ctx)
+{
+	struct bpf_dynptr meta;
+	__u8 md, *p;
+	int err;
+
+	err = bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+	if (err)
+		goto fail;
+
+	/* read offset OOB */
+	err = bpf_dynptr_read(&md, sizeof(md), &meta, META_SIZE, 0);
+	if (err != -E2BIG)
+		goto fail;
+
+	/* write offset OOB */
+	err = bpf_dynptr_write(&meta, META_SIZE, &md, sizeof(md), 0);
+	if (err != -E2BIG)
+		goto fail;
+
+	/* adjust end offset OOB */
+	err = bpf_dynptr_adjust(&meta, 0, META_SIZE + 1);
+	if (err != -ERANGE)
+		goto fail;
+
+	/* adjust start offset OOB */
+	err = bpf_dynptr_adjust(&meta, META_SIZE + 1, META_SIZE + 1);
+	if (err != -ERANGE)
+		goto fail;
+
+	/* slice offset OOB */
+	p = bpf_dynptr_slice(&meta, META_SIZE, NULL, sizeof(*p));
+	if (p)
+		goto fail;
+
+	/* slice rdwr offset OOB */
+	p = bpf_dynptr_slice_rdwr(&meta, META_SIZE, NULL, sizeof(*p));
+	if (p)
+		goto fail;
+
+	return TC_ACT_UNSPEC;
+fail:
+	return TC_ACT_SHOT;
+}
+
+/* Reserve and clear space for metadata but don't populate it */
+SEC("xdp")
+int ing_xdp_zalloc_meta(struct xdp_md *ctx)
+{
+	struct ethhdr *eth = ctx_ptr(ctx, data);
+	__u8 *meta;
+	int ret;
+
+	/* Drop any non-test packets */
+	if (eth + 1 > ctx_ptr(ctx, data_end))
+		return XDP_DROP;
+	if (!check_smac(eth))
+		return XDP_DROP;
+
+	ret = bpf_xdp_adjust_meta(ctx, -META_SIZE);
+	if (ret < 0)
+		return XDP_DROP;
+
+	meta = ctx_ptr(ctx, data_meta);
+	if (meta + META_SIZE > ctx_ptr(ctx, data))
+		return XDP_DROP;
+
+	__builtin_memset(meta, 0, META_SIZE);
+
+	return XDP_PASS;
+}
+
+SEC("xdp")
 int ing_xdp(struct xdp_md *ctx)
 {
-	__u8 *data, *data_meta, *data_end;
+	__u8 *data, *data_meta, *data_end, *payload;
+	struct ethhdr *eth;
 	int ret;
 
-	ret = bpf_xdp_adjust_meta(ctx, -round_up(ETH_ALEN, 4));
+	ret = bpf_xdp_adjust_meta(ctx, -META_SIZE);
 	if (ret < 0)
 		return XDP_DROP;
 
@@ -42,12 +322,352 @@ int ing_xdp(struct xdp_md *ctx)
 	data_end  = ctx_ptr(ctx, data_end);
 	data      = ctx_ptr(ctx, data);
 
-	if (data + ETH_ALEN > data_end ||
-	    data_meta + round_up(ETH_ALEN, 4) > data)
+	eth = (struct ethhdr *)data;
+	payload = data + sizeof(struct ethhdr);
+
+	if (payload + META_SIZE > data_end ||
+	    data_meta + META_SIZE > data)
+		return XDP_DROP;
+
+	/* The Linux networking stack may send other packets on the test
+	 * interface that interfere with the test. Just drop them.
+	 * The test packets can be recognized by their source MAC address.
+	 */
+	if (!check_smac(eth))
 		return XDP_DROP;
 
-	__builtin_memcpy(data_meta, data, ETH_ALEN);
+	__builtin_memcpy(data_meta, payload, META_SIZE);
 	return XDP_PASS;
 }
 
+/*
+ * Check that, when operating on a cloned packet, skb->data_meta..skb->data is
+ * kept intact if prog writes to packet _payload_ using packet pointers.
+ */
+SEC("tc")
+int clone_data_meta_survives_data_write(struct __sk_buff *ctx)
+{
+	__u8 *meta_have = ctx_ptr(ctx, data_meta);
+	struct ethhdr *eth = ctx_ptr(ctx, data);
+
+	if (eth + 1 > ctx_ptr(ctx, data_end))
+		goto out;
+	/* Ignore non-test packets */
+	if (!check_smac(eth))
+		goto out;
+
+	if (meta_have + META_SIZE > eth)
+		goto out;
+
+	if (!check_metadata(meta_have))
+		goto out;
+
+	/* Packet write to trigger unclone in prologue */
+	eth->h_proto = 42;
+
+	test_pass = true;
+out:
+	return TC_ACT_SHOT;
+}
+
+/*
+ * Check that, when operating on a cloned packet, skb->data_meta..skb->data is
+ * kept intact if prog writes to packet _metadata_ using packet pointers.
+ */
+SEC("tc")
+int clone_data_meta_survives_meta_write(struct __sk_buff *ctx)
+{
+	__u8 *meta_have = ctx_ptr(ctx, data_meta);
+	struct ethhdr *eth = ctx_ptr(ctx, data);
+
+	if (eth + 1 > ctx_ptr(ctx, data_end))
+		goto out;
+	/* Ignore non-test packets */
+	if (!check_smac(eth))
+		goto out;
+
+	if (meta_have + META_SIZE > eth)
+		goto out;
+
+	if (!check_metadata(meta_have))
+		goto out;
+
+	/* Metadata write to trigger unclone in prologue */
+	*meta_have = 42;
+
+	test_pass = true;
+out:
+	return TC_ACT_SHOT;
+}
+
+/*
+ * Check that, when operating on a cloned packet, metadata remains intact if
+ * prog creates a r/w slice to packet _payload_.
+ */
+SEC("tc")
+int clone_meta_dynptr_survives_data_slice_write(struct __sk_buff *ctx)
+{
+	struct bpf_dynptr data, meta;
+	__u8 meta_have[META_SIZE];
+	struct ethhdr *eth;
+
+	bpf_dynptr_from_skb(ctx, 0, &data);
+	eth = bpf_dynptr_slice_rdwr(&data, 0, NULL, sizeof(*eth));
+	if (!eth)
+		goto out;
+	/* Ignore non-test packets */
+	if (!check_smac(eth))
+		goto out;
+
+	bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+	bpf_dynptr_read(meta_have, META_SIZE, &meta, 0, 0);
+	if (!check_metadata(meta_have))
+		goto out;
+
+	test_pass = true;
+out:
+	return TC_ACT_SHOT;
+}
+
+/*
+ * Check that, when operating on a cloned packet, metadata remains intact if
+ * prog creates an r/w slice to packet _metadata_.
+ */
+SEC("tc")
+int clone_meta_dynptr_survives_meta_slice_write(struct __sk_buff *ctx)
+{
+	struct bpf_dynptr data, meta;
+	const struct ethhdr *eth;
+	__u8 *meta_have;
+
+	bpf_dynptr_from_skb(ctx, 0, &data);
+	eth = bpf_dynptr_slice(&data, 0, NULL, sizeof(*eth));
+	if (!eth)
+		goto out;
+	/* Ignore non-test packets */
+	if (!check_smac(eth))
+		goto out;
+
+	bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+	meta_have = bpf_dynptr_slice_rdwr(&meta, 0, NULL, META_SIZE);
+	if (!meta_have)
+		goto out;
+
+	if (!check_metadata(meta_have))
+		goto out;
+
+	test_pass = true;
+out:
+	return TC_ACT_SHOT;
+}
+
+/*
+ * Check that, when operating on a cloned packet, skb_meta dynptr is read-write
+ * before prog writes to packet _payload_ using dynptr_write helper and metadata
+ * remains intact before and after the write.
+ */
+SEC("tc")
+int clone_meta_dynptr_rw_before_data_dynptr_write(struct __sk_buff *ctx)
+{
+	struct bpf_dynptr data, meta;
+	__u8 meta_have[META_SIZE];
+	const struct ethhdr *eth;
+	int err;
+
+	bpf_dynptr_from_skb(ctx, 0, &data);
+	eth = bpf_dynptr_slice(&data, 0, NULL, sizeof(*eth));
+	if (!eth)
+		goto out;
+	/* Ignore non-test packets */
+	if (!check_smac(eth))
+		goto out;
+
+	/* Expect read-write metadata before unclone */
+	bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+	if (bpf_dynptr_is_rdonly(&meta))
+		goto out;
+
+	err = bpf_dynptr_read(meta_have, META_SIZE, &meta, 0, 0);
+	if (err || !check_metadata(meta_have))
+		goto out;
+
+	/* Helper write to payload will unclone the packet */
+	bpf_dynptr_write(&data, offsetof(struct ethhdr, h_proto), "x", 1, 0);
+
+	err = bpf_dynptr_read(meta_have, META_SIZE, &meta, 0, 0);
+	if (err || !check_metadata(meta_have))
+		goto out;
+
+	test_pass = true;
+out:
+	return TC_ACT_SHOT;
+}
+
+/*
+ * Check that, when operating on a cloned packet, skb_meta dynptr is read-write
+ * before prog writes to packet _metadata_ using dynptr_write helper and
+ * metadata remains intact before and after the write.
+ */
+SEC("tc")
+int clone_meta_dynptr_rw_before_meta_dynptr_write(struct __sk_buff *ctx)
+{
+	struct bpf_dynptr data, meta;
+	__u8 meta_have[META_SIZE];
+	const struct ethhdr *eth;
+	int err;
+
+	bpf_dynptr_from_skb(ctx, 0, &data);
+	eth = bpf_dynptr_slice(&data, 0, NULL, sizeof(*eth));
+	if (!eth)
+		goto out;
+	/* Ignore non-test packets */
+	if (!check_smac(eth))
+		goto out;
+
+	/* Expect read-write metadata before unclone */
+	bpf_dynptr_from_skb_meta(ctx, 0, &meta);
+	if (bpf_dynptr_is_rdonly(&meta))
+		goto out;
+
+	err = bpf_dynptr_read(meta_have, META_SIZE, &meta, 0, 0);
+	if (err || !check_metadata(meta_have))
+		goto out;
+
+	/* Helper write to metadata will unclone the packet */
+	bpf_dynptr_write(&meta, 0, &meta_have[0], 1, 0);
+
+	err = bpf_dynptr_read(meta_have, META_SIZE, &meta, 0, 0);
+	if (err || !check_metadata(meta_have))
+		goto out;
+
+	test_pass = true;
+out:
+	return TC_ACT_SHOT;
+}
+
+SEC("tc")
+int helper_skb_vlan_push_pop(struct __sk_buff *ctx)
+{
+	int err;
+
+	/* bpf_skb_vlan_push assumes HW offload for primary VLAN tag. Only
+	 * secondary tag push triggers an actual MAC header modification.
+	 */
+	err = bpf_skb_vlan_push(ctx, 0, 42);
+	if (err)
+		goto out;
+	err = bpf_skb_vlan_push(ctx, 0, 207);
+	if (err)
+		goto out;
+
+	if (!check_skb_metadata(ctx))
+		goto out;
+
+	err = bpf_skb_vlan_pop(ctx);
+	if (err)
+		goto out;
+	err = bpf_skb_vlan_pop(ctx);
+	if (err)
+		goto out;
+
+	if (!check_skb_metadata(ctx))
+		goto out;
+
+	test_pass = true;
+out:
+	return TC_ACT_SHOT;
+}
+
+SEC("tc")
+int helper_skb_adjust_room(struct __sk_buff *ctx)
+{
+	int err;
+
+	/* Grow a 1 byte hole after the MAC header */
+	err = bpf_skb_adjust_room(ctx, 1, BPF_ADJ_ROOM_MAC, 0);
+	if (err)
+		goto out;
+
+	if (!check_skb_metadata(ctx))
+		goto out;
+
+	/* Shrink a 1 byte hole after the MAC header */
+	err = bpf_skb_adjust_room(ctx, -1, BPF_ADJ_ROOM_MAC, 0);
+	if (err)
+		goto out;
+
+	if (!check_skb_metadata(ctx))
+		goto out;
+
+	/* Grow a 256 byte hole to trigger head reallocation */
+	err = bpf_skb_adjust_room(ctx, 256, BPF_ADJ_ROOM_MAC, 0);
+	if (err)
+		goto out;
+
+	if (!check_skb_metadata(ctx))
+		goto out;
+
+	test_pass = true;
+out:
+	return TC_ACT_SHOT;
+}
+
+SEC("tc")
+int helper_skb_change_head_tail(struct __sk_buff *ctx)
+{
+	int err;
+
+	/* Reserve 1 extra in the front for packet data */
+	err = bpf_skb_change_head(ctx, 1, 0);
+	if (err)
+		goto out;
+
+	if (!check_skb_metadata(ctx))
+		goto out;
+
+	/* Reserve 256 extra bytes in the front to trigger head reallocation */
+	err = bpf_skb_change_head(ctx, 256, 0);
+	if (err)
+		goto out;
+
+	if (!check_skb_metadata(ctx))
+		goto out;
+
+	/* Reserve 4k extra bytes in the back to trigger head reallocation */
+	err = bpf_skb_change_tail(ctx, ctx->len + 4096, 0);
+	if (err)
+		goto out;
+
+	if (!check_skb_metadata(ctx))
+		goto out;
+
+	test_pass = true;
+out:
+	return TC_ACT_SHOT;
+}
+
+SEC("tc")
+int helper_skb_change_proto(struct __sk_buff *ctx)
+{
+	int err;
+
+	err = bpf_skb_change_proto(ctx, bpf_htons(ETH_P_IPV6), 0);
+	if (err)
+		goto out;
+
+	if (!check_skb_metadata(ctx))
+		goto out;
+
+	err = bpf_skb_change_proto(ctx, bpf_htons(ETH_P_IP), 0);
+	if (err)
+		goto out;
+
+	if (!check_skb_metadata(ctx))
+		goto out;
+
+	test_pass = true;
+out:
+	return TC_ACT_SHOT;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
index ba48fcb98ab2..fad94e41cef9 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
@@ -15,6 +15,7 @@
 #include <linux/udp.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
+#include "bpf_compiler.h"
 
 static __always_inline __u32 rol32(__u32 word, unsigned int shift)
 {
@@ -317,6 +318,14 @@ bool encap_v6(struct xdp_md *xdp, struct ctl_value *cval,
 	return true;
 }
 
+#ifndef __clang__
+#pragma GCC push_options
+/* GCC optimization collapses functions and increases the number of arguments
+ * beyond the compatible amount supported by BPF.
+ */
+#pragma GCC optimize("-fno-ipa-sra")
+#endif
+
 static __attribute__ ((noinline))
 bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval,
 	      struct packet_description *pckt,
@@ -362,7 +371,7 @@ bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval,
 	iph->ttl = 4;
 
 	next_iph_u16 = (__u16 *) iph;
-#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (int i = 0; i < sizeof(struct iphdr) >> 1; i++)
 		csum += *next_iph_u16++;
 	iph->check = ~((csum & 0xffff) + (csum >> 16));
@@ -371,44 +380,9 @@ bool encap_v4(struct xdp_md *xdp, struct ctl_value *cval,
 	return true;
 }
 
-static __attribute__ ((noinline))
-bool decap_v6(struct xdp_md *xdp, void **data, void **data_end, bool inner_v4)
-{
-	struct eth_hdr *new_eth;
-	struct eth_hdr *old_eth;
-
-	old_eth = *data;
-	new_eth = *data + sizeof(struct ipv6hdr);
-	memcpy(new_eth->eth_source, old_eth->eth_source, 6);
-	memcpy(new_eth->eth_dest, old_eth->eth_dest, 6);
-	if (inner_v4)
-		new_eth->eth_proto = 8;
-	else
-		new_eth->eth_proto = 56710;
-	if (bpf_xdp_adjust_head(xdp, (int)sizeof(struct ipv6hdr)))
-		return false;
-	*data = (void *)(long)xdp->data;
-	*data_end = (void *)(long)xdp->data_end;
-	return true;
-}
-
-static __attribute__ ((noinline))
-bool decap_v4(struct xdp_md *xdp, void **data, void **data_end)
-{
-	struct eth_hdr *new_eth;
-	struct eth_hdr *old_eth;
-
-	old_eth = *data;
-	new_eth = *data + sizeof(struct iphdr);
-	memcpy(new_eth->eth_source, old_eth->eth_source, 6);
-	memcpy(new_eth->eth_dest, old_eth->eth_dest, 6);
-	new_eth->eth_proto = 8;
-	if (bpf_xdp_adjust_head(xdp, (int)sizeof(struct iphdr)))
-		return false;
-	*data = (void *)(long)xdp->data;
-	*data_end = (void *)(long)xdp->data_end;
-	return true;
-}
+#ifndef __clang__
+#pragma GCC pop_options
+#endif
 
 static __attribute__ ((noinline))
 int swap_mac_and_send(void *data, void *data_end)
@@ -430,7 +404,6 @@ int send_icmp_reply(void *data, void *data_end)
 	__u16 *next_iph_u16;
 	__u32 tmp_addr = 0;
 	struct iphdr *iph;
-	__u32 csum1 = 0;
 	__u32 csum = 0;
 	__u64 off = 0;
 
@@ -449,7 +422,7 @@ int send_icmp_reply(void *data, void *data_end)
 	iph->saddr = tmp_addr;
 	iph->check = 0;
 	next_iph_u16 = (__u16 *) iph;
-#pragma clang loop unroll(full)
+	__pragma_loop_unroll_full
 	for (int i = 0; i < sizeof(struct iphdr) >> 1; i++)
 		csum += *next_iph_u16++;
 	iph->check = ~((csum & 0xffff) + (csum >> 16));
@@ -627,12 +600,13 @@ static void connection_table_lookup(struct real_definition **real,
 __attribute__ ((noinline))
 static int process_l3_headers_v6(struct packet_description *pckt,
 				 __u8 *protocol, __u64 off,
-				 __u16 *pkt_bytes, void *data,
-				 void *data_end)
+				 __u16 *pkt_bytes, void *extra_args[2])
 {
 	struct ipv6hdr *ip6h;
 	__u64 iph_len;
 	int action;
+	void *data = extra_args[0];
+	void *data_end = extra_args[1];
 
 	ip6h = data + off;
 	if (ip6h + 1 > data_end)
@@ -658,12 +632,12 @@ static int process_l3_headers_v6(struct packet_description *pckt,
 __attribute__ ((noinline))
 static int process_l3_headers_v4(struct packet_description *pckt,
 				 __u8 *protocol, __u64 off,
-				 __u16 *pkt_bytes, void *data,
-				 void *data_end)
+				 __u16 *pkt_bytes, void *extra_args[2])
 {
 	struct iphdr *iph;
-	__u64 iph_len;
 	int action;
+	void *data = extra_args[0];
+	void *data_end = extra_args[1];
 
 	iph = data + off;
 	if (iph + 1 > data_end)
@@ -696,7 +670,6 @@ static int process_packet(void *data, __u64 off, void *data_end,
 	struct packet_description pckt = { };
 	struct vip_definition vip = { };
 	struct lb_stats *data_stats;
-	struct eth_hdr *eth = data;
 	void *lru_map = &lru_cache;
 	struct vip_meta *vip_info;
 	__u32 lru_stats_key = 513;
@@ -704,17 +677,17 @@ static int process_packet(void *data, __u64 off, void *data_end,
 	__u32 stats_key = 512;
 	struct ctl_value *cval;
 	__u16 pkt_bytes;
-	__u64 iph_len;
 	__u8 protocol;
 	__u32 vip_num;
 	int action;
+	void *extra_args[2] = { data, data_end };
 
 	if (is_ipv6)
 		action = process_l3_headers_v6(&pckt, &protocol, off,
-					       &pkt_bytes, data, data_end);
+					       &pkt_bytes, extra_args);
 	else
 		action = process_l3_headers_v4(&pckt, &protocol, off,
-					       &pkt_bytes, data, data_end);
+					       &pkt_bytes, extra_args);
 	if (action >= 0)
 		return action;
 	protocol = pckt.flow.proto;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_pull_data.c b/tools/testing/selftests/bpf/progs/test_xdp_pull_data.c
new file mode 100644
index 000000000000..c41a21413eaa
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_xdp_pull_data.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+int xdpf_sz;
+int sinfo_sz;
+int data_len;
+int pull_len;
+
+#define XDP_PACKET_HEADROOM 256
+
+SEC("xdp.frags")
+int xdp_find_sizes(struct xdp_md *ctx)
+{
+	xdpf_sz = sizeof(struct xdp_frame);
+	sinfo_sz = __PAGE_SIZE - XDP_PACKET_HEADROOM -
+		   (ctx->data_end - ctx->data);
+
+	return XDP_PASS;
+}
+
+SEC("xdp.frags")
+int xdp_pull_data_prog(struct xdp_md *ctx)
+{
+	__u8 *data_end = (void *)(long)ctx->data_end;
+	__u8 *data = (void *)(long)ctx->data;
+	__u8 *val_p;
+	int err;
+
+	if (data_len != data_end - data)
+		return XDP_DROP;
+
+	err = bpf_xdp_pull_data(ctx, pull_len);
+	if (err)
+		return XDP_DROP;
+
+	val_p = (void *)(long)ctx->data + 1024;
+	if (val_p + 1 > (void *)(long)ctx->data_end)
+		return XDP_DROP;
+
+	if (*val_p != 0xbb)
+		return XDP_DROP;
+
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_redirect.c
deleted file mode 100644
index b778cad45485..000000000000
--- a/tools/testing/selftests/bpf/progs/test_xdp_redirect.c
+++ /dev/null
@@ -1,26 +0,0 @@
-/* Copyright (c) 2017 VMware
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- */
-#include <linux/bpf.h>
-#include <bpf/bpf_helpers.h>
-
-SEC("redirect_to_111")
-int xdp_redirect_to_111(struct xdp_md *xdp)
-{
-	return bpf_redirect(111, 0);
-}
-SEC("redirect_to_222")
-int xdp_redirect_to_222(struct xdp_md *xdp)
-{
-	return bpf_redirect(222, 0);
-}
-
-char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c
index 134768f6b788..a80cc5f2f4f2 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_vlan.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c
@@ -98,12 +98,12 @@ bool parse_eth_frame(struct ethhdr *eth, void *data_end, struct parse_pkt *pkt)
 	return true;
 }
 
-/* Hint, VLANs are choosen to hit network-byte-order issues */
+/* Hint, VLANs are chosen to hit network-byte-order issues */
 #define TESTVLAN 4011 /* 0xFAB */
 // #define TO_VLAN  4000 /* 0xFA0 (hint 0xOA0 = 160) */
 
-SEC("xdp_drop_vlan_4011")
-int  xdp_prognum0(struct xdp_md *ctx)
+SEC("xdp")
+int xdp_drop_vlan_4011(struct xdp_md *ctx)
 {
 	void *data_end = (void *)(long)ctx->data_end;
 	void *data     = (void *)(long)ctx->data;
@@ -144,8 +144,8 @@ Load prog with ip tool:
 /* Changing VLAN to zero, have same practical effect as removing the VLAN. */
 #define TO_VLAN	0
 
-SEC("xdp_vlan_change")
-int  xdp_prognum1(struct xdp_md *ctx)
+SEC("xdp")
+int xdp_vlan_change(struct xdp_md *ctx)
 {
 	void *data_end = (void *)(long)ctx->data_end;
 	void *data     = (void *)(long)ctx->data;
@@ -160,7 +160,7 @@ int  xdp_prognum1(struct xdp_md *ctx)
 
 		/* Modifying VLAN, preserve top 4 bits */
 		vlan_hdr->h_vlan_TCI =
-			bpf_htons((bpf_ntohs(vlan_hdr->h_vlan_TCI) & 0xf000)
+			bpf_htons((bpf_ntohs(vlan_hdr->h_vlan_TCI) & 0xf000U)
 				  | TO_VLAN);
 	}
 
@@ -178,8 +178,8 @@ int  xdp_prognum1(struct xdp_md *ctx)
 #endif
 #define VLAN_HDR_SZ	4	/* bytes */
 
-SEC("xdp_vlan_remove_outer")
-int  xdp_prognum2(struct xdp_md *ctx)
+SEC("xdp")
+int xdp_vlan_remove_outer(struct xdp_md *ctx)
 {
 	void *data_end = (void *)(long)ctx->data_end;
 	void *data     = (void *)(long)ctx->data;
@@ -195,7 +195,7 @@ int  xdp_prognum2(struct xdp_md *ctx)
 
 	/* Moving Ethernet header, dest overlap with src, memmove handle this */
 	dest = data;
-	dest+= VLAN_HDR_SZ;
+	dest += VLAN_HDR_SZ;
 	/*
 	 * Notice: Taking over vlan_hdr->h_vlan_encapsulated_proto, by
 	 * only moving two MAC addrs (12 bytes), not overwriting last 2 bytes
@@ -210,19 +210,6 @@ int  xdp_prognum2(struct xdp_md *ctx)
 }
 
 static __always_inline
-void shift_mac_4bytes_16bit(void *data)
-{
-	__u16 *p = data;
-
-	p[7] = p[5]; /* delete p[7] was vlan_hdr->h_vlan_TCI */
-	p[6] = p[4]; /* delete p[6] was ethhdr->h_proto */
-	p[5] = p[3];
-	p[4] = p[2];
-	p[3] = p[1];
-	p[2] = p[0];
-}
-
-static __always_inline
 void shift_mac_4bytes_32bit(void *data)
 {
 	__u32 *p = data;
@@ -237,8 +224,8 @@ void shift_mac_4bytes_32bit(void *data)
 	p[1] = p[0];
 }
 
-SEC("xdp_vlan_remove_outer2")
-int  xdp_prognum3(struct xdp_md *ctx)
+SEC("xdp")
+int xdp_vlan_remove_outer2(struct xdp_md *ctx)
 {
 	void *data_end = (void *)(long)ctx->data_end;
 	void *data     = (void *)(long)ctx->data;
@@ -267,8 +254,8 @@ int  xdp_prognum3(struct xdp_md *ctx)
  * The TC-clsact eBPF programs (currently) need to be attach via TC commands
  */
 
-SEC("tc_vlan_push")
-int _tc_progA(struct __sk_buff *ctx)
+SEC("tc")
+int tc_vlan_push(struct __sk_buff *ctx)
 {
 	bpf_skb_vlan_push(ctx, bpf_htons(ETH_P_8021Q), TESTVLAN);
 
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c
index 20ec6723df18..3619239b01b7 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c
@@ -12,10 +12,12 @@ struct {
 	__uint(max_entries, 4);
 } cpu_map SEC(".maps");
 
+__u32 redirect_count = 0;
+
 SEC("xdp")
 int xdp_redir_prog(struct xdp_md *ctx)
 {
-	return bpf_redirect_map(&cpu_map, 1, 0);
+	return bpf_redirect_map(&cpu_map, 0, 0);
 }
 
 SEC("xdp")
@@ -27,6 +29,9 @@ int xdp_dummy_prog(struct xdp_md *ctx)
 SEC("xdp/cpumap")
 int xdp_dummy_cm(struct xdp_md *ctx)
 {
+	if (bpf_get_smp_processor_id() == 0)
+		redirect_count++;
+
 	if (ctx->ingress_ifindex == IFINDEX_LO)
 		return XDP_DROP;
 
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c
index 4139a14f9996..92b65a485d4a 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c
@@ -12,7 +12,7 @@ struct {
 SEC("xdp")
 int xdp_redir_prog(struct xdp_md *ctx)
 {
-	return bpf_redirect_map(&dm_ports, 1, 0);
+	return bpf_redirect_map(&dm_ports, 0, 0);
 }
 
 /* invalid program on DEVMAP entry;
diff --git a/tools/testing/selftests/bpf/progs/timer.c b/tools/testing/selftests/bpf/progs/timer.c
index acda5c9cea93..4c677c001258 100644
--- a/tools/testing/selftests/bpf/progs/timer.c
+++ b/tools/testing/selftests/bpf/progs/timer.c
@@ -2,9 +2,10 @@
 /* Copyright (c) 2021 Facebook */
 #include <linux/bpf.h>
 #include <time.h>
+#include <stdbool.h>
 #include <errno.h>
 #include <bpf/bpf_helpers.h>
-#include "bpf_tcp_helpers.h"
+#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 struct hmap_elem {
@@ -46,11 +47,22 @@ struct {
 	__type(value, struct elem);
 } lru SEC(".maps");
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} abs_timer SEC(".maps"), soft_timer_pinned SEC(".maps"), abs_timer_pinned SEC(".maps"),
+	race_array SEC(".maps");
+
 __u64 bss_data;
+__u64 abs_data;
 __u64 err;
 __u64 ok;
 __u64 callback_check = 52;
 __u64 callback2_check = 52;
+__u64 pinned_callback_check;
+__s32 pinned_cpu;
 
 #define ARRAY 1
 #define HTAB 2
@@ -284,3 +296,130 @@ int BPF_PROG2(test2, int, a, int, b)
 
 	return bpf_timer_test();
 }
+
+/* callback for absolute timer */
+static int timer_cb3(void *map, int *key, struct bpf_timer *timer)
+{
+	abs_data += 6;
+
+	if (abs_data < 12) {
+		bpf_timer_start(timer, bpf_ktime_get_boot_ns() + 1000,
+				BPF_F_TIMER_ABS);
+	} else {
+		/* Re-arm timer ~35 seconds in future */
+		bpf_timer_start(timer, bpf_ktime_get_boot_ns() + (1ull << 35),
+				BPF_F_TIMER_ABS);
+	}
+
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test3")
+int BPF_PROG2(test3, int, a)
+{
+	int key = 0;
+	struct bpf_timer *timer;
+
+	bpf_printk("test3");
+
+	timer = bpf_map_lookup_elem(&abs_timer, &key);
+	if (timer) {
+		if (bpf_timer_init(timer, &abs_timer, CLOCK_BOOTTIME) != 0)
+			err |= 2048;
+		bpf_timer_set_callback(timer, timer_cb3);
+		bpf_timer_start(timer, bpf_ktime_get_boot_ns() + 1000,
+				BPF_F_TIMER_ABS);
+	}
+
+	return 0;
+}
+
+/* callback for pinned timer */
+static int timer_cb_pinned(void *map, int *key, struct bpf_timer *timer)
+{
+	__s32 cpu = bpf_get_smp_processor_id();
+
+	if (cpu != pinned_cpu)
+		err |= 16384;
+
+	pinned_callback_check++;
+	return 0;
+}
+
+static void test_pinned_timer(bool soft)
+{
+	int key = 0;
+	void *map;
+	struct bpf_timer *timer;
+	__u64 flags = BPF_F_TIMER_CPU_PIN;
+	__u64 start_time;
+
+	if (soft) {
+		map = &soft_timer_pinned;
+		start_time = 0;
+	} else {
+		map = &abs_timer_pinned;
+		start_time = bpf_ktime_get_boot_ns();
+		flags |= BPF_F_TIMER_ABS;
+	}
+
+	timer = bpf_map_lookup_elem(map, &key);
+	if (timer) {
+		if (bpf_timer_init(timer, map, CLOCK_BOOTTIME) != 0)
+			err |= 4096;
+		bpf_timer_set_callback(timer, timer_cb_pinned);
+		pinned_cpu = bpf_get_smp_processor_id();
+		bpf_timer_start(timer, start_time + 1000, flags);
+	} else {
+		err |= 8192;
+	}
+}
+
+SEC("fentry/bpf_fentry_test4")
+int BPF_PROG2(test4, int, a)
+{
+	bpf_printk("test4");
+	test_pinned_timer(true);
+
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test5")
+int BPF_PROG2(test5, int, a)
+{
+	bpf_printk("test5");
+	test_pinned_timer(false);
+
+	return 0;
+}
+
+static int race_timer_callback(void *race_array, int *race_key, struct bpf_timer *timer)
+{
+	bpf_timer_start(timer, 1000000, 0);
+	return 0;
+}
+
+SEC("syscall")
+int race(void *ctx)
+{
+	struct bpf_timer *timer;
+	int err, race_key = 0;
+	struct elem init;
+
+	__builtin_memset(&init, 0, sizeof(struct elem));
+	bpf_map_update_elem(&race_array, &race_key, &init, BPF_ANY);
+
+	timer = bpf_map_lookup_elem(&race_array, &race_key);
+	if (!timer)
+		return 1;
+
+	err = bpf_timer_init(timer, &race_array, CLOCK_MONOTONIC);
+	if (err && err != -EBUSY)
+		return 1;
+
+	bpf_timer_set_callback(timer, race_timer_callback);
+	bpf_timer_start(timer, 0, 0);
+	bpf_timer_cancel(timer);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/timer_failure.c b/tools/testing/selftests/bpf/progs/timer_failure.c
new file mode 100644
index 000000000000..5a2e9dabf1c6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/timer_failure.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <linux/bpf.h>
+#include <time.h>
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct elem {
+	struct bpf_timer t;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} timer_map SEC(".maps");
+
+__naked __noinline __used
+static unsigned long timer_cb_ret_bad()
+{
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+		"if r0 s> 1000 goto 1f;"
+		"r0 = 0;"
+	"1:"
+		"goto +0;" /* checkpoint */
+		/* async callback is expected to return 0, so branch above
+		 * skipping r0 = 0; should lead to a failure, but if exit
+		 * instruction doesn't enforce r0's precision, this callback
+		 * will be successfully verified
+		 */
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32)
+		: __clobber_common
+	);
+}
+
+SEC("fentry/bpf_fentry_test1")
+__log_level(2)
+__flag(BPF_F_TEST_STATE_FREQ)
+__failure
+/* check that fallthrough code path marks r0 as precise */
+__msg("mark_precise: frame0: regs=r0 stack= before")
+__msg(": (85) call bpf_get_prandom_u32#7") /* anchor message */
+/* check that branch code path marks r0 as precise */
+__msg("mark_precise: frame0: regs=r0 stack= before ") __msg(": (85) call bpf_get_prandom_u32#7")
+__msg("should have been in [0, 0]")
+long BPF_PROG2(test_bad_ret, int, a)
+{
+	int key = 0;
+	struct bpf_timer *timer;
+
+	timer = bpf_map_lookup_elem(&timer_map, &key);
+	if (timer) {
+		bpf_timer_init(timer, &timer_map, CLOCK_BOOTTIME);
+		bpf_timer_set_callback(timer, timer_cb_ret_bad);
+		bpf_timer_start(timer, 1000, 0);
+	}
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/timer_interrupt.c b/tools/testing/selftests/bpf/progs/timer_interrupt.c
new file mode 100644
index 000000000000..19180a455f40
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/timer_interrupt.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_experimental.h"
+
+char _license[] SEC("license") = "GPL";
+
+#define CLOCK_MONOTONIC		1
+
+int preempt_count;
+int in_interrupt;
+int in_interrupt_cb;
+
+struct elem {
+	struct bpf_timer t;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} array SEC(".maps");
+
+static int timer_in_interrupt(void *map, int *key, struct bpf_timer *timer)
+{
+	preempt_count = get_preempt_count();
+	in_interrupt_cb = bpf_in_interrupt();
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(test_timer_interrupt)
+{
+	struct bpf_timer *timer;
+	int key = 0;
+
+	timer = bpf_map_lookup_elem(&array, &key);
+	if (!timer)
+		return 0;
+
+	in_interrupt = bpf_in_interrupt();
+	bpf_timer_init(timer, &array, CLOCK_MONOTONIC);
+	bpf_timer_set_callback(timer, timer_in_interrupt);
+	bpf_timer_start(timer, 0, 0);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/timer_lockup.c b/tools/testing/selftests/bpf/progs/timer_lockup.c
new file mode 100644
index 000000000000..3e520133281e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/timer_lockup.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <time.h>
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct elem {
+	struct bpf_timer t;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} timer1_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} timer2_map SEC(".maps");
+
+int timer1_err;
+int timer2_err;
+
+static int timer_cb1(void *map, int *k, struct elem *v)
+{
+	struct bpf_timer *timer;
+	int key = 0;
+
+	timer = bpf_map_lookup_elem(&timer2_map, &key);
+	if (timer)
+		timer2_err = bpf_timer_cancel(timer);
+
+	return 0;
+}
+
+static int timer_cb2(void *map, int *k, struct elem *v)
+{
+	struct bpf_timer *timer;
+	int key = 0;
+
+	timer = bpf_map_lookup_elem(&timer1_map, &key);
+	if (timer)
+		timer1_err = bpf_timer_cancel(timer);
+
+	return 0;
+}
+
+SEC("tc")
+int timer1_prog(void *ctx)
+{
+	struct bpf_timer *timer;
+	int key = 0;
+
+	timer = bpf_map_lookup_elem(&timer1_map, &key);
+	if (timer) {
+		bpf_timer_init(timer, &timer1_map, CLOCK_BOOTTIME);
+		bpf_timer_set_callback(timer, timer_cb1);
+		bpf_timer_start(timer, 1, BPF_F_TIMER_CPU_PIN);
+	}
+
+	return 0;
+}
+
+SEC("tc")
+int timer2_prog(void *ctx)
+{
+	struct bpf_timer *timer;
+	int key = 0;
+
+	timer = bpf_map_lookup_elem(&timer2_map, &key);
+	if (timer) {
+		bpf_timer_init(timer, &timer2_map, CLOCK_BOOTTIME);
+		bpf_timer_set_callback(timer, timer_cb2);
+		bpf_timer_start(timer, 1, BPF_F_TIMER_CPU_PIN);
+	}
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/timer_mim.c b/tools/testing/selftests/bpf/progs/timer_mim.c
index 2fee7ab105ef..50ebc3f68522 100644
--- a/tools/testing/selftests/bpf/progs/timer_mim.c
+++ b/tools/testing/selftests/bpf/progs/timer_mim.c
@@ -4,7 +4,7 @@
 #include <time.h>
 #include <errno.h>
 #include <bpf/bpf_helpers.h>
-#include "bpf_tcp_helpers.h"
+#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 struct hmap_elem {
diff --git a/tools/testing/selftests/bpf/progs/timer_mim_reject.c b/tools/testing/selftests/bpf/progs/timer_mim_reject.c
index 5d648e3d8a41..dd3f1ed6d6e6 100644
--- a/tools/testing/selftests/bpf/progs/timer_mim_reject.c
+++ b/tools/testing/selftests/bpf/progs/timer_mim_reject.c
@@ -4,7 +4,7 @@
 #include <time.h>
 #include <errno.h>
 #include <bpf/bpf_helpers.h>
-#include "bpf_tcp_helpers.h"
+#include <bpf/bpf_tracing.h>
 
 char _license[] SEC("license") = "GPL";
 struct hmap_elem {
diff --git a/tools/testing/selftests/bpf/progs/token_lsm.c b/tools/testing/selftests/bpf/progs/token_lsm.c
new file mode 100644
index 000000000000..a6002d073b1b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/token_lsm.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+int my_pid;
+int reject_capable;
+int reject_cmd;
+
+SEC("lsm/bpf_token_capable")
+int BPF_PROG(token_capable, struct bpf_token *token, int cap)
+{
+	if (my_pid == 0 || my_pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+	if (reject_capable)
+		return -1;
+	return 0;
+}
+
+SEC("lsm/bpf_token_cmd")
+int BPF_PROG(token_cmd, struct bpf_token *token, enum bpf_cmd cmd)
+{
+	if (my_pid == 0 || my_pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+	if (reject_cmd)
+		return -1;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/tracing_failure.c b/tools/testing/selftests/bpf/progs/tracing_failure.c
new file mode 100644
index 000000000000..65e485c4468c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tracing_failure.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+SEC("?fentry/bpf_spin_lock")
+int BPF_PROG(test_spin_lock, struct bpf_spin_lock *lock)
+{
+	return 0;
+}
+
+SEC("?fentry/bpf_spin_unlock")
+int BPF_PROG(test_spin_unlock, struct bpf_spin_lock *lock)
+{
+	return 0;
+}
+
+SEC("?fentry/__rcu_read_lock")
+int BPF_PROG(tracing_deny)
+{
+	return 0;
+}
+
+SEC("?fexit/do_exit")
+int BPF_PROG(fexit_noreturns)
+{
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/tracing_struct.c b/tools/testing/selftests/bpf/progs/tracing_struct.c
index e718f0ebee7d..d460732e2023 100644
--- a/tools/testing/selftests/bpf/progs/tracing_struct.c
+++ b/tools/testing/selftests/bpf/progs/tracing_struct.c
@@ -13,12 +13,33 @@ struct bpf_testmod_struct_arg_2 {
 	long b;
 };
 
+struct bpf_testmod_struct_arg_3 {
+	int a;
+	int b[];
+};
+
+union bpf_testmod_union_arg_1 {
+	char a;
+	short b;
+	struct bpf_testmod_struct_arg_1 arg;
+};
+
+union bpf_testmod_union_arg_2 {
+	int a;
+	long b;
+	struct bpf_testmod_struct_arg_2 arg;
+};
+
 long t1_a_a, t1_a_b, t1_b, t1_c, t1_ret, t1_nregs;
 __u64 t1_reg0, t1_reg1, t1_reg2, t1_reg3;
 long t2_a, t2_b_a, t2_b_b, t2_c, t2_ret;
 long t3_a, t3_b, t3_c_a, t3_c_b, t3_ret;
 long t4_a_a, t4_b, t4_c, t4_d, t4_e_a, t4_e_b, t4_ret;
 long t5_ret;
+int t6;
+
+long ut1_a_a, ut1_b, ut1_c;
+long ut2_a, ut2_b_a, ut2_b_b;
 
 SEC("fentry/bpf_testmod_test_struct_arg_1")
 int BPF_PROG2(test_struct_arg_1, struct bpf_testmod_struct_arg_2, a, int, b, int, c)
@@ -117,4 +138,29 @@ int BPF_PROG2(test_struct_arg_10, int, ret)
 	return 0;
 }
 
+SEC("fentry/bpf_testmod_test_struct_arg_6")
+int BPF_PROG2(test_struct_arg_11, struct bpf_testmod_struct_arg_3 *, a)
+{
+	t6 = a->b[0];
+	return 0;
+}
+
+SEC("fexit/bpf_testmod_test_union_arg_1")
+int BPF_PROG2(test_union_arg_1, union bpf_testmod_union_arg_1, a, int, b, int, c)
+{
+	ut1_a_a = a.arg.a;
+	ut1_b = b;
+	ut1_c = c;
+	return 0;
+}
+
+SEC("fexit/bpf_testmod_test_union_arg_2")
+int BPF_PROG2(test_union_arg_2, int, a, union bpf_testmod_union_arg_2, b)
+{
+	ut2_a = a;
+	ut2_b_a = b.arg.a;
+	ut2_b_b = b.arg.b;
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/tracing_struct_many_args.c b/tools/testing/selftests/bpf/progs/tracing_struct_many_args.c
new file mode 100644
index 000000000000..4742012ace06
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tracing_struct_many_args.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+struct bpf_testmod_struct_arg_4 {
+	u64 a;
+	int b;
+};
+
+struct bpf_testmod_struct_arg_5 {
+	char a;
+	short b;
+	int c;
+	long d;
+};
+
+long t7_a, t7_b, t7_c, t7_d, t7_e, t7_f_a, t7_f_b, t7_ret;
+long t8_a, t8_b, t8_c, t8_d, t8_e, t8_f_a, t8_f_b, t8_g, t8_ret;
+long t9_a, t9_b, t9_c, t9_d, t9_e, t9_f, t9_g, t9_h_a, t9_h_b, t9_h_c, t9_h_d, t9_i, t9_ret;
+
+SEC("fentry/bpf_testmod_test_struct_arg_7")
+int BPF_PROG2(test_struct_many_args_1, __u64, a, void *, b, short, c, int, d,
+	      void *, e, struct bpf_testmod_struct_arg_4, f)
+{
+	t7_a = a;
+	t7_b = (long)b;
+	t7_c = c;
+	t7_d = d;
+	t7_e = (long)e;
+	t7_f_a = f.a;
+	t7_f_b = f.b;
+	return 0;
+}
+
+SEC("fexit/bpf_testmod_test_struct_arg_7")
+int BPF_PROG2(test_struct_many_args_2, __u64, a, void *, b, short, c, int, d,
+	      void *, e, struct bpf_testmod_struct_arg_4, f, int, ret)
+{
+	t7_ret = ret;
+	return 0;
+}
+
+SEC("fentry/bpf_testmod_test_struct_arg_8")
+int BPF_PROG2(test_struct_many_args_3, __u64, a, void *, b, short, c, int, d,
+	      void *, e, struct bpf_testmod_struct_arg_4, f, int, g)
+{
+	t8_a = a;
+	t8_b = (long)b;
+	t8_c = c;
+	t8_d = d;
+	t8_e = (long)e;
+	t8_f_a = f.a;
+	t8_f_b = f.b;
+	t8_g = g;
+	return 0;
+}
+
+SEC("fexit/bpf_testmod_test_struct_arg_8")
+int BPF_PROG2(test_struct_many_args_4, __u64, a, void *, b, short, c, int, d,
+	      void *, e, struct bpf_testmod_struct_arg_4, f, int, g,
+	      int, ret)
+{
+	t8_ret = ret;
+	return 0;
+}
+
+SEC("fentry/bpf_testmod_test_struct_arg_9")
+int BPF_PROG2(test_struct_many_args_5, __u64, a, void *, b, short, c, int, d, void *, e,
+	      char, f, short, g, struct bpf_testmod_struct_arg_5, h, long, i)
+{
+	t9_a = a;
+	t9_b = (long)b;
+	t9_c = c;
+	t9_d = d;
+	t9_e = (long)e;
+	t9_f = f;
+	t9_g = g;
+	t9_h_a = h.a;
+	t9_h_b = h.b;
+	t9_h_c = h.c;
+	t9_h_d = h.d;
+	t9_i = i;
+	return 0;
+}
+
+SEC("fexit/bpf_testmod_test_struct_arg_9")
+int BPF_PROG2(test_struct_many_args_6, __u64, a, void *, b, short, c, int, d, void *, e,
+	      char, f, short, g, struct bpf_testmod_struct_arg_5, h, long, i, int, ret)
+{
+	t9_ret = ret;
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c
index 694e7cec1823..2898b3749d07 100644
--- a/tools/testing/selftests/bpf/progs/trigger_bench.c
+++ b/tools/testing/selftests/bpf/progs/trigger_bench.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2020 Facebook
-
 #include <linux/bpf.h>
 #include <asm/unistd.h>
 #include <bpf/bpf_helpers.h>
@@ -9,54 +8,147 @@
 
 char _license[] SEC("license") = "GPL";
 
-long hits = 0;
+#define CPU_MASK 255
+#define MAX_CPUS (CPU_MASK + 1) /* should match MAX_BUCKETS in benchs/bench_trigger.c */
 
-SEC("tp/syscalls/sys_enter_getpgid")
-int bench_trigger_tp(void *ctx)
+/* matches struct counter in bench.h */
+struct counter {
+	long value;
+} __attribute__((aligned(128)));
+
+struct counter hits[MAX_CPUS];
+
+static __always_inline void inc_counter(void)
+{
+	int cpu = bpf_get_smp_processor_id();
+
+	__sync_add_and_fetch(&hits[cpu & CPU_MASK].value, 1);
+}
+
+SEC("?uprobe")
+int bench_trigger_uprobe(void *ctx)
+{
+	inc_counter();
+	return 0;
+}
+
+SEC("?uprobe.multi")
+int bench_trigger_uprobe_multi(void *ctx)
+{
+	inc_counter();
+	return 0;
+}
+
+const volatile int batch_iters = 0;
+
+SEC("?raw_tp")
+int trigger_kernel_count(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	int i;
+
+	for (i = 0; i < batch_iters; i++) {
+		inc_counter();
+		bpf_get_numa_node_id();
+	}
+
 	return 0;
 }
 
-SEC("raw_tp/sys_enter")
-int BPF_PROG(bench_trigger_raw_tp, struct pt_regs *regs, long id)
+SEC("?raw_tp")
+int trigger_driver(void *ctx)
 {
-	if (id == __NR_getpgid)
-		__sync_add_and_fetch(&hits, 1);
+	int i;
+
+	for (i = 0; i < batch_iters; i++)
+		(void)bpf_get_numa_node_id(); /* attach point for benchmarking */
+
 	return 0;
 }
 
-SEC("kprobe/" SYS_PREFIX "sys_getpgid")
+extern int bpf_modify_return_test_tp(int nonce) __ksym __weak;
+
+SEC("?raw_tp")
+int trigger_driver_kfunc(void *ctx)
+{
+	int i;
+
+	for (i = 0; i < batch_iters; i++)
+		(void)bpf_modify_return_test_tp(0); /* attach point for benchmarking */
+
+	return 0;
+}
+
+SEC("?kprobe/bpf_get_numa_node_id")
 int bench_trigger_kprobe(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
+	return 0;
+}
+
+SEC("?kretprobe/bpf_get_numa_node_id")
+int bench_trigger_kretprobe(void *ctx)
+{
+	inc_counter();
+	return 0;
+}
+
+SEC("?kprobe.multi/bpf_get_numa_node_id")
+int bench_trigger_kprobe_multi(void *ctx)
+{
+	inc_counter();
 	return 0;
 }
 
-SEC("fentry/" SYS_PREFIX "sys_getpgid")
+SEC("?kprobe.multi/bpf_get_numa_node_id")
+int bench_kprobe_multi_empty(void *ctx)
+{
+	return 0;
+}
+
+SEC("?kretprobe.multi/bpf_get_numa_node_id")
+int bench_trigger_kretprobe_multi(void *ctx)
+{
+	inc_counter();
+	return 0;
+}
+
+SEC("?kretprobe.multi/bpf_get_numa_node_id")
+int bench_kretprobe_multi_empty(void *ctx)
+{
+	return 0;
+}
+
+SEC("?fentry/bpf_get_numa_node_id")
 int bench_trigger_fentry(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return 0;
 }
 
-SEC("fentry.s/" SYS_PREFIX "sys_getpgid")
-int bench_trigger_fentry_sleep(void *ctx)
+SEC("?fexit/bpf_get_numa_node_id")
+int bench_trigger_fexit(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return 0;
 }
 
-SEC("fmod_ret/" SYS_PREFIX "sys_getpgid")
+SEC("?fmod_ret/bpf_modify_return_test_tp")
 int bench_trigger_fmodret(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return -22;
 }
 
-SEC("uprobe")
-int bench_trigger_uprobe(void *ctx)
+SEC("?tp/bpf_test_run/bpf_trigger_tp")
+int bench_trigger_tp(void *ctx)
+{
+	inc_counter();
+	return 0;
+}
+
+SEC("?raw_tp/bpf_trigger_tp")
+int bench_trigger_rawtp(void *ctx)
 {
-	__sync_add_and_fetch(&hits, 1);
+	inc_counter();
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/type_cast.c b/tools/testing/selftests/bpf/progs/type_cast.c
index eb78e6f03129..9d808b8f4ab0 100644
--- a/tools/testing/selftests/bpf/progs/type_cast.c
+++ b/tools/testing/selftests/bpf/progs/type_cast.c
@@ -4,6 +4,7 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include <bpf/bpf_core_read.h>
+#include "bpf_kfuncs.h"
 
 struct {
 	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
@@ -19,9 +20,6 @@ char name[IFNAMSIZ];
 unsigned int inum;
 unsigned int meta_len, frag0_len, kskb_len, kskb2_len;
 
-void *bpf_cast_to_kern_ctx(void *) __ksym;
-void *bpf_rdonly_cast(void *, __u32) __ksym;
-
 SEC("?xdp")
 int md_xdp(struct xdp_md *ctx)
 {
@@ -48,13 +46,12 @@ int md_skb(struct __sk_buff *skb)
 	/* Simulate the following kernel macro:
 	 *   #define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB)))
 	 */
-	shared_info = bpf_rdonly_cast(kskb->head + kskb->end,
-		bpf_core_type_id_kernel(struct skb_shared_info));
+	shared_info = bpf_core_cast(kskb->head + kskb->end, struct skb_shared_info);
 	meta_len = shared_info->meta_len;
 	frag0_len = shared_info->frag_list->len;
 
 	/* kskb2 should be equal to kskb */
-	kskb2 = bpf_rdonly_cast(kskb, bpf_core_type_id_kernel(struct sk_buff));
+	kskb2 = bpf_core_cast(kskb, typeof(*kskb2));
 	kskb2_len = kskb2->len;
 	return 0;
 }
@@ -63,10 +60,9 @@ SEC("?tp_btf/sys_enter")
 int BPF_PROG(untrusted_ptr, struct pt_regs *regs, long id)
 {
 	struct task_struct *task, *task_dup;
-	long *ptr;
 
 	task = bpf_get_current_task_btf();
-	task_dup = bpf_rdonly_cast(task, bpf_core_type_id_kernel(struct task_struct));
+	task_dup = bpf_core_cast(task, struct task_struct);
 	(void)bpf_task_storage_get(&enter_id, task_dup, 0, 0);
 	return 0;
 }
@@ -74,7 +70,7 @@ int BPF_PROG(untrusted_ptr, struct pt_regs *regs, long id)
 SEC("?tracepoint/syscalls/sys_enter_nanosleep")
 int kctx_u64(void *ctx)
 {
-	u64 *kctx = bpf_rdonly_cast(ctx, bpf_core_type_id_kernel(u64));
+	u64 *kctx = bpf_core_cast(ctx, u64);
 
 	(void)kctx;
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/udp_limit.c b/tools/testing/selftests/bpf/progs/udp_limit.c
index 165e3c2dd9a3..4767451b59ac 100644
--- a/tools/testing/selftests/bpf/progs/udp_limit.c
+++ b/tools/testing/selftests/bpf/progs/udp_limit.c
@@ -17,7 +17,6 @@ SEC("cgroup/sock_create")
 int sock(struct bpf_sock *ctx)
 {
 	int *sk_storage;
-	__u32 key;
 
 	if (ctx->type != SOCK_DGRAM)
 		return 1;
@@ -46,7 +45,6 @@ SEC("cgroup/sock_release")
 int sock_release(struct bpf_sock *ctx)
 {
 	int *sk_storage;
-	__u32 key;
 
 	if (ctx->type != SOCK_DGRAM)
 		return 1;
diff --git a/tools/testing/selftests/bpf/progs/uninit_stack.c b/tools/testing/selftests/bpf/progs/uninit_stack.c
new file mode 100644
index 000000000000..046a204c8fc6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uninit_stack.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+/* Read an uninitialized value from stack at a fixed offset */
+SEC("socket")
+__naked int read_uninit_stack_fixed_off(void *ctx)
+{
+	asm volatile ("					\
+		r0 = 0;					\
+		/* force stack depth to be 128 */	\
+		*(u64*)(r10 - 128) = r1;		\
+		r1 = *(u8 *)(r10 - 8 );			\
+		r0 += r1;				\
+		r1 = *(u8 *)(r10 - 11);			\
+		r1 = *(u8 *)(r10 - 13);			\
+		r1 = *(u8 *)(r10 - 15);			\
+		r1 = *(u16*)(r10 - 16);			\
+		r1 = *(u32*)(r10 - 32);			\
+		r1 = *(u64*)(r10 - 64);			\
+		/* read from a spill of a wrong size, it is a separate	\
+		 * branch in check_stack_read_fixed_off()		\
+		 */					\
+		*(u32*)(r10 - 72) = r1;			\
+		r1 = *(u64*)(r10 - 72);			\
+		r0 = 0;					\
+		exit;					\
+"
+		      ::: __clobber_all);
+}
+
+/* Read an uninitialized value from stack at a variable offset */
+SEC("socket")
+__naked int read_uninit_stack_var_off(void *ctx)
+{
+	asm volatile ("					\
+		call %[bpf_get_prandom_u32];		\
+		/* force stack depth to be 64 */	\
+		*(u64*)(r10 - 64) = r0;			\
+		r0 = -r0;				\
+		/* give r0 a range [-31, -1] */		\
+		if r0 s<= -32 goto exit_%=;		\
+		if r0 s>= 0 goto exit_%=;		\
+		/* access stack using r0 */		\
+		r1 = r10;				\
+		r1 += r0;				\
+		r2 = *(u8*)(r1 + 0);			\
+exit_%=:	r0 = 0;					\
+		exit;					\
+"
+		      :
+		      : __imm(bpf_get_prandom_u32)
+		      : __clobber_all);
+}
+
+static __noinline void dummy(void) {}
+
+/* Pass a pointer to uninitialized stack memory to a helper.
+ * Passed memory block should be marked as STACK_MISC after helper call.
+ */
+SEC("socket")
+__log_level(7) __msg("fp-104=mmmmmmmm")
+__naked int helper_uninit_to_misc(void *ctx)
+{
+	asm volatile ("					\
+		/* force stack depth to be 128 */	\
+		*(u64*)(r10 - 128) = r1;		\
+		r1 = r10;				\
+		r1 += -128;				\
+		r2 = 32;				\
+		r3 = 0;					\
+		call %[bpf_probe_read_user];		\
+		/* Call to dummy() forces print_verifier_state(..., true),	\
+		 * thus showing the stack state, matched by __msg().		\
+		 */					\
+		call %[dummy];				\
+		r0 = 0;					\
+		exit;					\
+"
+		      :
+		      : __imm(bpf_probe_read_user),
+			__imm(dummy)
+		      : __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/unsupported_ops.c b/tools/testing/selftests/bpf/progs/unsupported_ops.c
new file mode 100644
index 000000000000..8aa2e0dd624e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/unsupported_ops.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("struct_ops/unsupported_ops")
+__failure
+__msg("attach to unsupported member unsupported_ops of struct bpf_testmod_ops")
+int BPF_PROG(unsupported_ops)
+{
+	return 0;
+}
+
+SEC(".struct_ops.link")
+struct bpf_testmod_ops testmod = {
+	.unsupported_ops = (void *)unsupported_ops,
+};
diff --git a/tools/testing/selftests/bpf/progs/update_map_in_htab.c b/tools/testing/selftests/bpf/progs/update_map_in_htab.c
new file mode 100644
index 000000000000..c2066247cd9c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/update_map_in_htab.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2024. Huawei Technologies Co., Ltd */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+struct inner_map_type {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(key_size, 4);
+	__uint(value_size, 4);
+	__uint(max_entries, 1);
+} inner_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 2);
+	__array(values, struct inner_map_type);
+} outer_htab_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 2);
+	__array(values, struct inner_map_type);
+} outer_alloc_htab_map SEC(".maps");
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi.c b/tools/testing/selftests/bpf/progs/uprobe_multi.c
new file mode 100644
index 000000000000..44190efcdba2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi.c
@@ -0,0 +1,143 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/usdt.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u64 uprobe_multi_func_1_addr = 0;
+__u64 uprobe_multi_func_2_addr = 0;
+__u64 uprobe_multi_func_3_addr = 0;
+
+__u64 uprobe_multi_func_1_result = 0;
+__u64 uprobe_multi_func_2_result = 0;
+__u64 uprobe_multi_func_3_result = 0;
+
+__u64 uretprobe_multi_func_1_result = 0;
+__u64 uretprobe_multi_func_2_result = 0;
+__u64 uretprobe_multi_func_3_result = 0;
+
+__u64 uprobe_multi_sleep_result = 0;
+
+int pid = 0;
+int child_pid = 0;
+int child_tid = 0;
+int child_pid_usdt = 0;
+int child_tid_usdt = 0;
+
+int expect_pid = 0;
+bool bad_pid_seen = false;
+bool bad_pid_seen_usdt = false;
+
+bool test_cookie = false;
+void *user_ptr = 0;
+
+static __always_inline bool verify_sleepable_user_copy(void)
+{
+	char data[9];
+
+	bpf_copy_from_user(data, sizeof(data), user_ptr);
+	return bpf_strncmp(data, sizeof(data), "test_data") == 0;
+}
+
+static void uprobe_multi_check(void *ctx, bool is_return, bool is_sleep)
+{
+	__u64 cur_pid_tgid = bpf_get_current_pid_tgid();
+	__u32 cur_pid;
+
+	cur_pid = cur_pid_tgid >> 32;
+	if (pid && cur_pid != pid)
+		return;
+
+	if (expect_pid && cur_pid != expect_pid)
+		bad_pid_seen = true;
+
+	child_pid = cur_pid_tgid >> 32;
+	child_tid = (__u32)cur_pid_tgid;
+
+	__u64 cookie = test_cookie ? bpf_get_attach_cookie(ctx) : 0;
+	__u64 addr = bpf_get_func_ip(ctx);
+
+#define SET(__var, __addr, __cookie) ({			\
+	if (addr == __addr &&				\
+	   (!test_cookie || (cookie == __cookie)))	\
+		__var += 1;				\
+})
+
+	if (is_return) {
+		SET(uretprobe_multi_func_1_result, uprobe_multi_func_1_addr, 2);
+		SET(uretprobe_multi_func_2_result, uprobe_multi_func_2_addr, 3);
+		SET(uretprobe_multi_func_3_result, uprobe_multi_func_3_addr, 1);
+	} else {
+		SET(uprobe_multi_func_1_result, uprobe_multi_func_1_addr, 3);
+		SET(uprobe_multi_func_2_result, uprobe_multi_func_2_addr, 1);
+		SET(uprobe_multi_func_3_result, uprobe_multi_func_3_addr, 2);
+	}
+
+#undef SET
+
+	if (is_sleep && verify_sleepable_user_copy())
+		uprobe_multi_sleep_result += 1;
+}
+
+SEC("uprobe.multi//proc/self/exe:uprobe_multi_func_*")
+int uprobe(struct pt_regs *ctx)
+{
+	uprobe_multi_check(ctx, false, false);
+	return 0;
+}
+
+SEC("uretprobe.multi//proc/self/exe:uprobe_multi_func_*")
+int uretprobe(struct pt_regs *ctx)
+{
+	uprobe_multi_check(ctx, true, false);
+	return 0;
+}
+
+SEC("uprobe.multi.s//proc/self/exe:uprobe_multi_func_*")
+int uprobe_sleep(struct pt_regs *ctx)
+{
+	uprobe_multi_check(ctx, false, true);
+	return 0;
+}
+
+SEC("uretprobe.multi.s//proc/self/exe:uprobe_multi_func_*")
+int uretprobe_sleep(struct pt_regs *ctx)
+{
+	uprobe_multi_check(ctx, true, true);
+	return 0;
+}
+
+SEC("uprobe.multi//proc/self/exe:uprobe_multi_func_*")
+int uprobe_extra(struct pt_regs *ctx)
+{
+	/* we need this one just to mix PID-filtered and global uprobes */
+	return 0;
+}
+
+SEC("usdt")
+int usdt_pid(struct pt_regs *ctx)
+{
+	__u64 cur_pid_tgid = bpf_get_current_pid_tgid();
+	__u32 cur_pid;
+
+	cur_pid = cur_pid_tgid >> 32;
+	if (pid && cur_pid != pid)
+		return 0;
+
+	if (expect_pid && cur_pid != expect_pid)
+		bad_pid_seen_usdt = true;
+
+	child_pid_usdt = cur_pid_tgid >> 32;
+	child_tid_usdt = (__u32)cur_pid_tgid;
+
+	return 0;
+}
+
+SEC("usdt")
+int usdt_extra(struct pt_regs *ctx)
+{
+	/* we need this one just to mix PID-filtered and global USDT probes */
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi_bench.c b/tools/testing/selftests/bpf/progs/uprobe_multi_bench.c
new file mode 100644
index 000000000000..5367f6105e30
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi_bench.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+int count;
+
+SEC("uprobe.multi/./uprobe_multi:uprobe_multi_func_*")
+int uprobe_bench(struct pt_regs *ctx)
+{
+	count++;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi_consumers.c b/tools/testing/selftests/bpf/progs/uprobe_multi_consumers.c
new file mode 100644
index 000000000000..93752bb5690b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi_consumers.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <stdbool.h>
+#include "bpf_kfuncs.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+__u64 uprobe_result[4];
+
+SEC("uprobe.multi")
+int uprobe_0(struct pt_regs *ctx)
+{
+	uprobe_result[0]++;
+	return 0;
+}
+
+SEC("uprobe.multi")
+int uprobe_1(struct pt_regs *ctx)
+{
+	uprobe_result[1]++;
+	return 0;
+}
+
+SEC("uprobe.session")
+int uprobe_2(struct pt_regs *ctx)
+{
+	uprobe_result[2]++;
+	return 0;
+}
+
+SEC("uprobe.session")
+int uprobe_3(struct pt_regs *ctx)
+{
+	uprobe_result[3]++;
+	return 1;
+}
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi_pid_filter.c b/tools/testing/selftests/bpf/progs/uprobe_multi_pid_filter.c
new file mode 100644
index 000000000000..67fcbad36661
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi_pid_filter.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u32 pids[3];
+__u32 test[3][2];
+
+static void update_pid(int idx)
+{
+	__u32 pid = bpf_get_current_pid_tgid() >> 32;
+
+	if (pid == pids[idx])
+		test[idx][0]++;
+	else
+		test[idx][1]++;
+}
+
+SEC("uprobe.multi")
+int uprobe_multi_0(struct pt_regs *ctx)
+{
+	update_pid(0);
+	return 0;
+}
+
+SEC("uprobe.multi")
+int uprobe_multi_1(struct pt_regs *ctx)
+{
+	update_pid(1);
+	return 0;
+}
+
+SEC("uprobe.multi")
+int uprobe_multi_2(struct pt_regs *ctx)
+{
+	update_pid(2);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi_session.c b/tools/testing/selftests/bpf/progs/uprobe_multi_session.c
new file mode 100644
index 000000000000..30bff90b68dc
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi_session.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <stdbool.h>
+#include "bpf_kfuncs.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+__u64 uprobe_multi_func_1_addr = 0;
+__u64 uprobe_multi_func_2_addr = 0;
+__u64 uprobe_multi_func_3_addr = 0;
+
+__u64 uprobe_session_result[3] = {};
+__u64 uprobe_multi_sleep_result = 0;
+
+void *user_ptr = 0;
+int pid = 0;
+
+static int uprobe_multi_check(void *ctx, bool is_return)
+{
+	const __u64 funcs[] = {
+		uprobe_multi_func_1_addr,
+		uprobe_multi_func_2_addr,
+		uprobe_multi_func_3_addr,
+	};
+	unsigned int i;
+	__u64 addr;
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 1;
+
+	addr = bpf_get_func_ip(ctx);
+
+	for (i = 0; i < ARRAY_SIZE(funcs); i++) {
+		if (funcs[i] == addr) {
+			uprobe_session_result[i]++;
+			break;
+		}
+	}
+
+	/* only uprobe_multi_func_2 executes return probe */
+	if ((addr == uprobe_multi_func_1_addr) ||
+	    (addr == uprobe_multi_func_3_addr))
+		return 1;
+
+	return 0;
+}
+
+SEC("uprobe.session//proc/self/exe:uprobe_multi_func_*")
+int uprobe(struct pt_regs *ctx)
+{
+	return uprobe_multi_check(ctx, bpf_session_is_return());
+}
+
+static __always_inline bool verify_sleepable_user_copy(void)
+{
+	char data[9];
+
+	bpf_copy_from_user(data, sizeof(data), user_ptr);
+	return bpf_strncmp(data, sizeof(data), "test_data") == 0;
+}
+
+SEC("uprobe.session.s//proc/self/exe:uprobe_multi_func_*")
+int uprobe_sleepable(struct pt_regs *ctx)
+{
+	if (verify_sleepable_user_copy())
+		uprobe_multi_sleep_result++;
+	return uprobe_multi_check(ctx, bpf_session_is_return());
+}
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi_session_cookie.c b/tools/testing/selftests/bpf/progs/uprobe_multi_session_cookie.c
new file mode 100644
index 000000000000..5befdf944dc6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi_session_cookie.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <stdbool.h>
+#include "bpf_kfuncs.h"
+
+char _license[] SEC("license") = "GPL";
+
+int pid = 0;
+
+__u64 test_uprobe_1_result = 0;
+__u64 test_uprobe_2_result = 0;
+__u64 test_uprobe_3_result = 0;
+
+static int check_cookie(__u64 val, __u64 *result)
+{
+	__u64 *cookie;
+
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 1;
+
+	cookie = bpf_session_cookie();
+
+	if (bpf_session_is_return())
+		*result = *cookie == val ? val : 0;
+	else
+		*cookie = val;
+	return 0;
+}
+
+SEC("uprobe.session//proc/self/exe:uprobe_multi_func_1")
+int uprobe_1(struct pt_regs *ctx)
+{
+	return check_cookie(1, &test_uprobe_1_result);
+}
+
+SEC("uprobe.session//proc/self/exe:uprobe_multi_func_2")
+int uprobe_2(struct pt_regs *ctx)
+{
+	return check_cookie(2, &test_uprobe_2_result);
+}
+
+SEC("uprobe.session//proc/self/exe:uprobe_multi_func_3")
+int uprobe_3(struct pt_regs *ctx)
+{
+	return check_cookie(3, &test_uprobe_3_result);
+}
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi_session_recursive.c b/tools/testing/selftests/bpf/progs/uprobe_multi_session_recursive.c
new file mode 100644
index 000000000000..8fbcd69fae22
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi_session_recursive.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <stdbool.h>
+#include "bpf_kfuncs.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+int pid = 0;
+
+int idx_entry = 0;
+int idx_return = 0;
+
+__u64 test_uprobe_cookie_entry[6];
+__u64 test_uprobe_cookie_return[3];
+
+static int check_cookie(void)
+{
+	__u64 *cookie = bpf_session_cookie();
+
+	if (bpf_session_is_return()) {
+		if (idx_return >= ARRAY_SIZE(test_uprobe_cookie_return))
+			return 1;
+		test_uprobe_cookie_return[idx_return++] = *cookie;
+		return 0;
+	}
+
+	if (idx_entry >= ARRAY_SIZE(test_uprobe_cookie_entry))
+		return 1;
+	*cookie = test_uprobe_cookie_entry[idx_entry];
+	return idx_entry++ % 2;
+}
+
+
+SEC("uprobe.session//proc/self/exe:uprobe_session_recursive")
+int uprobe_recursive(struct pt_regs *ctx)
+{
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 1;
+
+	return check_cookie();
+}
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi_session_single.c b/tools/testing/selftests/bpf/progs/uprobe_multi_session_single.c
new file mode 100644
index 000000000000..7c960376ae97
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi_session_single.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <stdbool.h>
+#include "bpf_kfuncs.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+__u64 uprobe_session_result[3] = {};
+int pid = 0;
+
+static int uprobe_multi_check(void *ctx, int idx)
+{
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 1;
+
+	uprobe_session_result[idx]++;
+
+	/* only consumer 1 executes return probe */
+	if (idx == 0 || idx == 2)
+		return 1;
+
+	return 0;
+}
+
+SEC("uprobe.session//proc/self/exe:uprobe_multi_func_1")
+int uprobe_0(struct pt_regs *ctx)
+{
+	return uprobe_multi_check(ctx, 0);
+}
+
+SEC("uprobe.session//proc/self/exe:uprobe_multi_func_1")
+int uprobe_1(struct pt_regs *ctx)
+{
+	return uprobe_multi_check(ctx, 1);
+}
+
+SEC("uprobe.session//proc/self/exe:uprobe_multi_func_1")
+int uprobe_2(struct pt_regs *ctx)
+{
+	return uprobe_multi_check(ctx, 2);
+}
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi_usdt.c b/tools/testing/selftests/bpf/progs/uprobe_multi_usdt.c
new file mode 100644
index 000000000000..9e1c33d0bd2f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi_usdt.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/usdt.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+int count;
+
+SEC("usdt")
+int usdt0(struct pt_regs *ctx)
+{
+	count++;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi_verifier.c b/tools/testing/selftests/bpf/progs/uprobe_multi_verifier.c
new file mode 100644
index 000000000000..fe49f2cb5360
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi_verifier.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/usdt.bpf.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+
+SEC("uprobe.session")
+__success
+int uprobe_sesison_return_0(struct pt_regs *ctx)
+{
+	return 0;
+}
+
+SEC("uprobe.session")
+__success
+int uprobe_sesison_return_1(struct pt_regs *ctx)
+{
+	return 1;
+}
+
+SEC("uprobe.session")
+__failure
+__msg("At program exit the register R0 has smin=2 smax=2 should have been in [0, 1]")
+int uprobe_sesison_return_2(struct pt_regs *ctx)
+{
+	return 2;
+}
diff --git a/tools/testing/selftests/bpf/progs/uprobe_syscall.c b/tools/testing/selftests/bpf/progs/uprobe_syscall.c
new file mode 100644
index 000000000000..e08c31669e5a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_syscall.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <string.h>
+
+struct pt_regs regs;
+
+char _license[] SEC("license") = "GPL";
+
+SEC("uprobe")
+int probe(struct pt_regs *ctx)
+{
+	__builtin_memcpy(&regs, ctx, sizeof(regs));
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c b/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c
new file mode 100644
index 000000000000..915d38591bf6
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/usdt.bpf.h>
+#include <string.h>
+
+struct pt_regs regs;
+
+char _license[] SEC("license") = "GPL";
+
+int executed = 0;
+int pid;
+
+SEC("uprobe")
+int BPF_UPROBE(test_uprobe)
+{
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	executed++;
+	return 0;
+}
+
+SEC("uretprobe")
+int BPF_URETPROBE(test_uretprobe)
+{
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	executed++;
+	return 0;
+}
+
+SEC("uprobe.multi")
+int test_uprobe_multi(struct pt_regs *ctx)
+{
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	executed++;
+	return 0;
+}
+
+SEC("uretprobe.multi")
+int test_uretprobe_multi(struct pt_regs *ctx)
+{
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	executed++;
+	return 0;
+}
+
+SEC("uprobe.session")
+int test_uprobe_session(struct pt_regs *ctx)
+{
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	executed++;
+	return 0;
+}
+
+SEC("usdt")
+int test_usdt(struct pt_regs *ctx)
+{
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
+		return 0;
+
+	executed++;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/uptr_failure.c b/tools/testing/selftests/bpf/progs/uptr_failure.c
new file mode 100644
index 000000000000..0cfa1fd61440
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uptr_failure.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_experimental.h"
+#include "bpf_misc.h"
+#include "uptr_test_common.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct value_type);
+} datamap SEC(".maps");
+
+SEC("?syscall")
+__failure __msg("store to uptr disallowed")
+int uptr_write(const void *ctx)
+{
+	struct task_struct *task;
+	struct value_type *v;
+
+	task = bpf_get_current_task_btf();
+	v = bpf_task_storage_get(&datamap, task, 0,
+				 BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (!v)
+		return 0;
+
+	v->udata = NULL;
+	return 0;
+}
+
+SEC("?syscall")
+__failure __msg("store to uptr disallowed")
+int uptr_write_nested(const void *ctx)
+{
+	struct task_struct *task;
+	struct value_type *v;
+
+	task = bpf_get_current_task_btf();
+	v = bpf_task_storage_get(&datamap, task, 0,
+				 BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (!v)
+		return 0;
+
+	v->nested.udata = NULL;
+	return 0;
+}
+
+SEC("?syscall")
+__failure __msg("R1 invalid mem access 'mem_or_null'")
+int uptr_no_null_check(const void *ctx)
+{
+	struct task_struct *task;
+	struct value_type *v;
+
+	task = bpf_get_current_task_btf();
+	v = bpf_task_storage_get(&datamap, task, 0,
+				 BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (!v)
+		return 0;
+
+	v->udata->result = 0;
+
+	return 0;
+}
+
+SEC("?syscall")
+__failure __msg("doesn't point to kptr")
+int uptr_kptr_xchg(const void *ctx)
+{
+	struct task_struct *task;
+	struct value_type *v;
+
+	task = bpf_get_current_task_btf();
+	v = bpf_task_storage_get(&datamap, task, 0,
+				 BPF_LOCAL_STORAGE_GET_F_CREATE);
+	if (!v)
+		return 0;
+
+	bpf_kptr_xchg(&v->udata, NULL);
+
+	return 0;
+}
+
+SEC("?syscall")
+__failure __msg("invalid mem access 'scalar'")
+int uptr_obj_new(const void *ctx)
+{
+	struct value_type *v;
+
+	v = bpf_obj_new(typeof(*v));
+	if (!v)
+		return 0;
+
+	if (v->udata)
+		v->udata->result = 0;
+
+	bpf_obj_drop(v);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/uptr_map_failure.c b/tools/testing/selftests/bpf/progs/uptr_map_failure.c
new file mode 100644
index 000000000000..417b763d76b4
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uptr_map_failure.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "uptr_test_common.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct large_uptr);
+} large_uptr_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct empty_uptr);
+} empty_uptr_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct kstruct_uptr);
+} kstruct_uptr_map SEC(".maps");
diff --git a/tools/testing/selftests/bpf/progs/uptr_update_failure.c b/tools/testing/selftests/bpf/progs/uptr_update_failure.c
new file mode 100644
index 000000000000..86c3bb954abc
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uptr_update_failure.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "uptr_test_common.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct value_lock_type);
+} datamap SEC(".maps");
+
+/* load test only. not used */
+SEC("syscall")
+int not_used(void *ctx)
+{
+	struct value_lock_type *ptr;
+	struct task_struct *task;
+	struct user_data *udata;
+
+	task = bpf_get_current_task_btf();
+	ptr = bpf_task_storage_get(&datamap, task, 0, 0);
+	if (!ptr)
+		return 0;
+
+	bpf_spin_lock(&ptr->lock);
+
+	udata = ptr->udata;
+	if (!udata) {
+		bpf_spin_unlock(&ptr->lock);
+		return 0;
+	}
+	udata->result = MAGIC_VALUE + udata->a + udata->b;
+
+	bpf_spin_unlock(&ptr->lock);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/uretprobe_stack.c b/tools/testing/selftests/bpf/progs/uretprobe_stack.c
new file mode 100644
index 000000000000..a2951e2f1711
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uretprobe_stack.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/usdt.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u64 entry_stack1[32], exit_stack1[32];
+__u64 entry_stack1_recur[32], exit_stack1_recur[32];
+__u64 entry_stack2[32];
+__u64 entry_stack3[32];
+__u64 entry_stack4[32], exit_stack4[32];
+__u64 usdt_stack[32];
+
+int entry1_len, exit1_len;
+int entry1_recur_len, exit1_recur_len;
+int entry2_len, exit2_len;
+int entry3_len, exit3_len;
+int entry4_len, exit4_len;
+int usdt_len;
+
+#define SZ sizeof(usdt_stack)
+
+SEC("uprobe//proc/self/exe:target_1")
+int BPF_UPROBE(uprobe_1)
+{
+	/* target_1 is recursive with depth of 2, so we capture two separate
+	 * stack traces, depending on which occurrence it is
+	 */
+	static bool recur = false;
+
+	if (!recur)
+		entry1_len = bpf_get_stack(ctx, &entry_stack1, SZ, BPF_F_USER_STACK);
+	else
+		entry1_recur_len = bpf_get_stack(ctx, &entry_stack1_recur, SZ, BPF_F_USER_STACK);
+
+	recur = true;
+	return 0;
+}
+
+SEC("uretprobe//proc/self/exe:target_1")
+int BPF_URETPROBE(uretprobe_1)
+{
+	/* see above, target_1 is recursive */
+	static bool recur = false;
+
+	/* NOTE: order of returns is reversed to order of entries */
+	if (!recur)
+		exit1_recur_len = bpf_get_stack(ctx, &exit_stack1_recur, SZ, BPF_F_USER_STACK);
+	else
+		exit1_len = bpf_get_stack(ctx, &exit_stack1, SZ, BPF_F_USER_STACK);
+
+	recur = true;
+	return 0;
+}
+
+SEC("uprobe//proc/self/exe:target_2")
+int BPF_UPROBE(uprobe_2)
+{
+	entry2_len = bpf_get_stack(ctx, &entry_stack2, SZ, BPF_F_USER_STACK);
+	return 0;
+}
+
+/* no uretprobe for target_2 */
+
+SEC("uprobe//proc/self/exe:target_3")
+int BPF_UPROBE(uprobe_3)
+{
+	entry3_len = bpf_get_stack(ctx, &entry_stack3, SZ, BPF_F_USER_STACK);
+	return 0;
+}
+
+/* no uretprobe for target_3 */
+
+SEC("uprobe//proc/self/exe:target_4")
+int BPF_UPROBE(uprobe_4)
+{
+	entry4_len = bpf_get_stack(ctx, &entry_stack4, SZ, BPF_F_USER_STACK);
+	return 0;
+}
+
+SEC("uretprobe//proc/self/exe:target_4")
+int BPF_URETPROBE(uretprobe_4)
+{
+	exit4_len = bpf_get_stack(ctx, &exit_stack4, SZ, BPF_F_USER_STACK);
+	return 0;
+}
+
+SEC("usdt//proc/self/exe:uretprobe_stack:target")
+int BPF_USDT(usdt_probe)
+{
+	usdt_len = bpf_get_stack(ctx, &usdt_stack, SZ, BPF_F_USER_STACK);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c b/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c
index f3201dc69a60..54de0389f878 100644
--- a/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c
+++ b/tools/testing/selftests/bpf/progs/user_ringbuf_fail.c
@@ -16,6 +16,7 @@ struct sample {
 
 struct {
 	__uint(type, BPF_MAP_TYPE_USER_RINGBUF);
+	__uint(max_entries, 4096);
 } user_ringbuf SEC(".maps");
 
 struct {
@@ -39,7 +40,8 @@ bad_access1(struct bpf_dynptr *dynptr, void *context)
 /* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should
  * not be able to read before the pointer.
  */
-SEC("?raw_tp/")
+SEC("?raw_tp")
+__failure __msg("negative offset dynptr_ptr ptr")
 int user_ringbuf_callback_bad_access1(void *ctx)
 {
 	bpf_user_ringbuf_drain(&user_ringbuf, bad_access1, NULL, 0);
@@ -61,7 +63,8 @@ bad_access2(struct bpf_dynptr *dynptr, void *context)
 /* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should
  * not be able to read past the end of the pointer.
  */
-SEC("?raw_tp/")
+SEC("?raw_tp")
+__failure __msg("dereference of modified dynptr_ptr ptr")
 int user_ringbuf_callback_bad_access2(void *ctx)
 {
 	bpf_user_ringbuf_drain(&user_ringbuf, bad_access2, NULL, 0);
@@ -80,7 +83,8 @@ write_forbidden(struct bpf_dynptr *dynptr, void *context)
 /* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should
  * not be able to write to that pointer.
  */
-SEC("?raw_tp/")
+SEC("?raw_tp")
+__failure __msg("invalid mem access 'dynptr_ptr'")
 int user_ringbuf_callback_write_forbidden(void *ctx)
 {
 	bpf_user_ringbuf_drain(&user_ringbuf, write_forbidden, NULL, 0);
@@ -99,7 +103,8 @@ null_context_write(struct bpf_dynptr *dynptr, void *context)
 /* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should
  * not be able to write to that pointer.
  */
-SEC("?raw_tp/")
+SEC("?raw_tp")
+__failure __msg("invalid mem access 'scalar'")
 int user_ringbuf_callback_null_context_write(void *ctx)
 {
 	bpf_user_ringbuf_drain(&user_ringbuf, null_context_write, NULL, 0);
@@ -120,7 +125,8 @@ null_context_read(struct bpf_dynptr *dynptr, void *context)
 /* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should
  * not be able to write to that pointer.
  */
-SEC("?raw_tp/")
+SEC("?raw_tp")
+__failure __msg("invalid mem access 'scalar'")
 int user_ringbuf_callback_null_context_read(void *ctx)
 {
 	bpf_user_ringbuf_drain(&user_ringbuf, null_context_read, NULL, 0);
@@ -139,7 +145,8 @@ try_discard_dynptr(struct bpf_dynptr *dynptr, void *context)
 /* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should
  * not be able to read past the end of the pointer.
  */
-SEC("?raw_tp/")
+SEC("?raw_tp")
+__failure __msg("cannot release unowned const bpf_dynptr")
 int user_ringbuf_callback_discard_dynptr(void *ctx)
 {
 	bpf_user_ringbuf_drain(&user_ringbuf, try_discard_dynptr, NULL, 0);
@@ -158,7 +165,8 @@ try_submit_dynptr(struct bpf_dynptr *dynptr, void *context)
 /* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should
  * not be able to read past the end of the pointer.
  */
-SEC("?raw_tp/")
+SEC("?raw_tp")
+__failure __msg("cannot release unowned const bpf_dynptr")
 int user_ringbuf_callback_submit_dynptr(void *ctx)
 {
 	bpf_user_ringbuf_drain(&user_ringbuf, try_submit_dynptr, NULL, 0);
@@ -175,7 +183,8 @@ invalid_drain_callback_return(struct bpf_dynptr *dynptr, void *context)
 /* A callback that accesses a dynptr in a bpf_user_ringbuf_drain callback should
  * not be able to write to that pointer.
  */
-SEC("?raw_tp/")
+SEC("?raw_tp")
+__failure __msg("At callback return the register R0 has ")
 int user_ringbuf_callback_invalid_return(void *ctx)
 {
 	bpf_user_ringbuf_drain(&user_ringbuf, invalid_drain_callback_return, NULL, 0);
@@ -197,16 +206,40 @@ try_reinit_dynptr_ringbuf(struct bpf_dynptr *dynptr, void *context)
 	return 0;
 }
 
-SEC("?raw_tp/")
+SEC("?raw_tp")
+__failure __msg("Dynptr has to be an uninitialized dynptr")
 int user_ringbuf_callback_reinit_dynptr_mem(void *ctx)
 {
 	bpf_user_ringbuf_drain(&user_ringbuf, try_reinit_dynptr_mem, NULL, 0);
 	return 0;
 }
 
-SEC("?raw_tp/")
+SEC("?raw_tp")
+__failure __msg("Dynptr has to be an uninitialized dynptr")
 int user_ringbuf_callback_reinit_dynptr_ringbuf(void *ctx)
 {
 	bpf_user_ringbuf_drain(&user_ringbuf, try_reinit_dynptr_ringbuf, NULL, 0);
 	return 0;
 }
+
+__noinline long global_call_bpf_dynptr_data(struct bpf_dynptr *dynptr)
+{
+	bpf_dynptr_data(dynptr, 0xA, 0xA);
+	return 0;
+}
+
+static long callback_adjust_bpf_dynptr_reg_off(struct bpf_dynptr *dynptr,
+					       void *ctx)
+{
+	global_call_bpf_dynptr_data(dynptr += 1024);
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("dereference of modified dynptr_ptr ptr R1 off=16384 disallowed")
+int user_ringbuf_callback_const_ptr_to_dynptr_reg_off(void *ctx)
+{
+	bpf_user_ringbuf_drain(&user_ringbuf,
+			       callback_adjust_bpf_dynptr_reg_off, NULL, 0);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/user_ringbuf_success.c b/tools/testing/selftests/bpf/progs/user_ringbuf_success.c
index b39093dd5715..dd3bdf672633 100644
--- a/tools/testing/selftests/bpf/progs/user_ringbuf_success.c
+++ b/tools/testing/selftests/bpf/progs/user_ringbuf_success.c
@@ -162,8 +162,6 @@ SEC("fentry/" SYS_PREFIX "sys_prctl")
 int test_user_ringbuf_protocol(void *ctx)
 {
 	long status = 0;
-	struct sample *sample = NULL;
-	struct bpf_dynptr ptr;
 
 	if (!is_test_process())
 		return 0;
@@ -183,10 +181,6 @@ int test_user_ringbuf_protocol(void *ctx)
 SEC("fentry/" SYS_PREFIX "sys_getpgid")
 int test_user_ringbuf(void *ctx)
 {
-	int status = 0;
-	struct sample *sample = NULL;
-	struct bpf_dynptr ptr;
-
 	if (!is_test_process())
 		return 0;
 
@@ -202,7 +196,7 @@ do_nothing_cb(struct bpf_dynptr *dynptr, void *context)
 	return 0;
 }
 
-SEC("fentry/" SYS_PREFIX "sys_getrlimit")
+SEC("fentry/" SYS_PREFIX "sys_prlimit64")
 int test_user_ringbuf_epoll(void *ctx)
 {
 	long num_samples;
diff --git a/tools/testing/selftests/bpf/progs/verifier_and.c b/tools/testing/selftests/bpf/progs/verifier_and.c
new file mode 100644
index 000000000000..2b4fdca162be
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_and.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/and.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#define MAX_ENTRIES 11
+
+struct test_val {
+	unsigned int index;
+	int foo[MAX_ENTRIES];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, struct test_val);
+} map_hash_48b SEC(".maps");
+
+SEC("socket")
+__description("invalid and of negative number")
+__failure __msg("R0 max value is outside of the allowed memory range")
+__failure_unpriv
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void invalid_and_of_negative_number(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u8*)(r0 + 0);				\
+	r1 &= -4;					\
+	r1 <<= 2;					\
+	r0 += r1;					\
+l0_%=:	r1 = %[test_val_foo];				\
+	*(u64*)(r0 + 0) = r1;				\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("invalid range check")
+__failure __msg("R0 max value is outside of the allowed memory range")
+__failure_unpriv
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void invalid_range_check(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u32*)(r0 + 0);				\
+	r9 = 1;						\
+	w1 %%= 2;					\
+	w1 += 1;					\
+	w9 &= w1;					\
+	w9 += 1;					\
+	w9 >>= 1;					\
+	w3 = 1;						\
+	w3 -= w9;					\
+	w3 *= 0x10000000;				\
+	r0 += r3;					\
+	*(u32*)(r0 + 0) = r3;				\
+l0_%=:	r0 = r0;					\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check known subreg with unknown reg")
+__success __success_unpriv
+__retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if w0 < 0x1 goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R1 !read_ok'` */
+__xlated_unpriv("goto pc-1") /* `r1 = *(u32*)(r1 + 512)`, sanitized dead code */
+__xlated_unpriv("r0 = 0")
+#endif
+__naked void known_subreg_with_unknown_reg(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r0 <<= 32;					\
+	r0 += 1;					\
+	r0 &= 0xFFFF1234;				\
+	/* Upper bits are unknown but AND above masks out 1 zero'ing lower bits */\
+	if w0 < 1 goto l0_%=;				\
+	r1 = *(u32*)(r1 + 512);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_arena.c b/tools/testing/selftests/bpf/progs/verifier_arena.c
new file mode 100644
index 000000000000..7f4827eede3c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_arena.c
@@ -0,0 +1,257 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#define BPF_NO_KFUNC_PROTOTYPES
+#include <vmlinux.h>
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+#include "bpf_arena_common.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARENA);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__uint(max_entries, 2); /* arena of two pages close to 32-bit boundary*/
+#ifdef __TARGET_ARCH_arm64
+        __ulong(map_extra, (1ull << 32) | (~0u - __PAGE_SIZE * 2 + 1)); /* start of mmap() region */
+#else
+        __ulong(map_extra, (1ull << 44) | (~0u - __PAGE_SIZE * 2 + 1)); /* start of mmap() region */
+#endif
+} arena SEC(".maps");
+
+SEC("syscall")
+__success __retval(0)
+int basic_alloc1(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	volatile int __arena *page1, *page2, *no_page, *page3;
+
+	page1 = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (!page1)
+		return 1;
+	*page1 = 1;
+	page2 = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (!page2)
+		return 2;
+	*page2 = 2;
+	no_page = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (no_page)
+		return 3;
+	if (*page1 != 1)
+		return 4;
+	if (*page2 != 2)
+		return 5;
+	bpf_arena_free_pages(&arena, (void __arena *)page2, 1);
+	if (*page1 != 1)
+		return 6;
+	if (*page2 != 0) /* use-after-free should return 0 */
+		return 7;
+	page3 = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (!page3)
+		return 8;
+	*page3 = 3;
+	if (page2 != page3)
+		return 9;
+	if (*page1 != 1)
+		return 10;
+#endif
+	return 0;
+}
+
+SEC("syscall")
+__success __retval(0)
+int basic_alloc2(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	volatile char __arena *page1, *page2, *page3, *page4;
+
+	page1 = bpf_arena_alloc_pages(&arena, NULL, 2, NUMA_NO_NODE, 0);
+	if (!page1)
+		return 1;
+	page2 = page1 + __PAGE_SIZE;
+	page3 = page1 + __PAGE_SIZE * 2;
+	page4 = page1 - __PAGE_SIZE;
+	*page1 = 1;
+	*page2 = 2;
+	*page3 = 3;
+	*page4 = 4;
+	if (*page1 != 1)
+		return 1;
+	if (*page2 != 2)
+		return 2;
+	if (*page3 != 0)
+		return 3;
+	if (*page4 != 0)
+		return 4;
+	bpf_arena_free_pages(&arena, (void __arena *)page1, 2);
+	if (*page1 != 0)
+		return 5;
+	if (*page2 != 0)
+		return 6;
+	if (*page3 != 0)
+		return 7;
+	if (*page4 != 0)
+		return 8;
+#endif
+	return 0;
+}
+
+struct bpf_arena___l {
+        struct bpf_map map;
+} __attribute__((preserve_access_index));
+
+SEC("syscall")
+__success __retval(0) __log_level(2)
+int basic_alloc3(void *ctx)
+{
+	struct bpf_arena___l *ar = (struct bpf_arena___l *)&arena;
+	volatile char __arena *pages;
+
+	pages = bpf_arena_alloc_pages(&ar->map, NULL, ar->map.max_entries, NUMA_NO_NODE, 0);
+	if (!pages)
+		return 1;
+	return 0;
+}
+
+SEC("syscall")
+__success __retval(0)
+int basic_reserve1(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	char __arena *page;
+	int ret;
+
+	page = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (!page)
+		return 1;
+
+	page += __PAGE_SIZE;
+
+	/* Reserve the second page */
+	ret = bpf_arena_reserve_pages(&arena, page, 1);
+	if (ret)
+		return 2;
+
+	/* Try to explicitly allocate the reserved page. */
+	page = bpf_arena_alloc_pages(&arena, page, 1, NUMA_NO_NODE, 0);
+	if (page)
+		return 3;
+
+	/* Try to implicitly allocate the page (since there's only 2 of them). */
+	page = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (page)
+		return 4;
+#endif
+	return 0;
+}
+
+SEC("syscall")
+__success __retval(0)
+int basic_reserve2(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	char __arena *page;
+	int ret;
+
+	page = arena_base(&arena);
+	ret = bpf_arena_reserve_pages(&arena, page, 1);
+	if (ret)
+		return 1;
+
+	page = bpf_arena_alloc_pages(&arena, page, 1, NUMA_NO_NODE, 0);
+	if ((u64)page)
+		return 2;
+#endif
+	return 0;
+}
+
+/* Reserve the same page twice, should return -EBUSY. */
+SEC("syscall")
+__success __retval(0)
+int reserve_twice(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	char __arena *page;
+	int ret;
+
+	page = arena_base(&arena);
+
+	ret = bpf_arena_reserve_pages(&arena, page, 1);
+	if (ret)
+		return 1;
+
+	ret = bpf_arena_reserve_pages(&arena, page, 1);
+	if (ret != -EBUSY)
+		return 2;
+#endif
+	return 0;
+}
+
+/* Try to reserve past the end of the arena. */
+SEC("syscall")
+__success __retval(0)
+int reserve_invalid_region(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	char __arena *page;
+	int ret;
+
+	/* Try a NULL pointer. */
+	ret = bpf_arena_reserve_pages(&arena, NULL, 3);
+	if (ret != -EINVAL)
+		return 1;
+
+	page = arena_base(&arena);
+
+	ret = bpf_arena_reserve_pages(&arena, page, 3);
+	if (ret != -EINVAL)
+		return 2;
+
+	ret = bpf_arena_reserve_pages(&arena, page, 4096);
+	if (ret != -EINVAL)
+		return 3;
+
+	ret = bpf_arena_reserve_pages(&arena, page, (1ULL << 32) - 1);
+	if (ret != -EINVAL)
+		return 4;
+#endif
+	return 0;
+}
+
+SEC("iter.s/bpf_map")
+__success __log_level(2)
+int iter_maps1(struct bpf_iter__bpf_map *ctx)
+{
+	struct bpf_map *map = ctx->map;
+
+	if (!map)
+		return 0;
+	bpf_arena_alloc_pages(map, NULL, map->max_entries, 0, 0);
+	return 0;
+}
+
+SEC("iter.s/bpf_map")
+__failure __msg("expected pointer to STRUCT bpf_map")
+int iter_maps2(struct bpf_iter__bpf_map *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+
+	bpf_arena_alloc_pages((void *)seq, NULL, 1, 0, 0);
+	return 0;
+}
+
+SEC("iter.s/bpf_map")
+__failure __msg("untrusted_ptr_bpf_map")
+int iter_maps3(struct bpf_iter__bpf_map *ctx)
+{
+	struct bpf_map *map = ctx->map;
+
+	if (!map)
+		return 0;
+	bpf_arena_alloc_pages(map->inner_map_meta, NULL, map->max_entries, 0, 0);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_arena_large.c b/tools/testing/selftests/bpf/progs/verifier_arena_large.c
new file mode 100644
index 000000000000..f19e15400b3e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_arena_large.c
@@ -0,0 +1,274 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#define BPF_NO_KFUNC_PROTOTYPES
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+#include "bpf_arena_common.h"
+
+#define ARENA_SIZE (1ull << 32)
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARENA);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__uint(max_entries, ARENA_SIZE / PAGE_SIZE);
+} arena SEC(".maps");
+
+SEC("syscall")
+__success __retval(0)
+int big_alloc1(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	volatile char __arena *page1, *page2, *no_page, *page3;
+	void __arena *base;
+
+	page1 = base = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (!page1)
+		return 1;
+	*page1 = 1;
+	page2 = bpf_arena_alloc_pages(&arena, base + ARENA_SIZE - PAGE_SIZE * 2,
+				      1, NUMA_NO_NODE, 0);
+	if (!page2)
+		return 2;
+	*page2 = 2;
+	no_page = bpf_arena_alloc_pages(&arena, base + ARENA_SIZE - PAGE_SIZE,
+					1, NUMA_NO_NODE, 0);
+	if (no_page)
+		return 3;
+	if (*page1 != 1)
+		return 4;
+	if (*page2 != 2)
+		return 5;
+	bpf_arena_free_pages(&arena, (void __arena *)page1, 1);
+	if (*page2 != 2)
+		return 6;
+	if (*page1 != 0) /* use-after-free should return 0 */
+		return 7;
+	page3 = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (!page3)
+		return 8;
+	*page3 = 3;
+	if (page1 != page3)
+		return 9;
+	if (*page2 != 2)
+		return 10;
+	if (*(page1 + PAGE_SIZE) != 0)
+		return 11;
+	if (*(page1 - PAGE_SIZE) != 0)
+		return 12;
+	if (*(page2 + PAGE_SIZE) != 0)
+		return 13;
+	if (*(page2 - PAGE_SIZE) != 0)
+		return 14;
+#endif
+	return 0;
+}
+
+/* Try to access a reserved page. Behavior should be identical with accessing unallocated pages. */
+SEC("syscall")
+__success __retval(0)
+int access_reserved(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	volatile char __arena *page;
+	char __arena *base;
+	const size_t len = 4;
+	int ret, i;
+
+	/* Get a separate region of the arena. */
+	page = base = arena_base(&arena) + 16384 * PAGE_SIZE;
+
+	ret = bpf_arena_reserve_pages(&arena, base, len);
+	if (ret)
+		return 1;
+
+	/* Try to dirty reserved memory. */
+	for (i = 0; i < len && can_loop; i++)
+		*page = 0x5a;
+
+	for (i = 0; i < len && can_loop; i++) {
+		page = (volatile char __arena *)(base + i * PAGE_SIZE);
+
+		/*
+		 * Error out in case either the write went through,
+		 * or the address has random garbage.
+		 */
+		if (*page == 0x5a)
+			return 2 + 2 * i;
+
+		if (*page)
+			return 2 + 2 * i + 1;
+	}
+#endif
+	return 0;
+}
+
+/* Try to allocate a region overlapping with a reservation. */
+SEC("syscall")
+__success __retval(0)
+int request_partially_reserved(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	volatile char __arena *page;
+	char __arena *base;
+	int ret;
+
+	/* Add an arbitrary page offset. */
+	page = base = arena_base(&arena) + 4096 * __PAGE_SIZE;
+
+	ret = bpf_arena_reserve_pages(&arena, base + 3 * __PAGE_SIZE, 4);
+	if (ret)
+		return 1;
+
+	page = bpf_arena_alloc_pages(&arena, base, 5, NUMA_NO_NODE, 0);
+	if ((u64)page != 0ULL)
+		return 2;
+#endif
+	return 0;
+}
+
+SEC("syscall")
+__success __retval(0)
+int free_reserved(void *ctx)
+{
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+	char __arena *addr;
+	char __arena *page;
+	int ret;
+
+	/* Add an arbitrary page offset. */
+	addr = arena_base(&arena) + 32768 * __PAGE_SIZE;
+
+	page = bpf_arena_alloc_pages(&arena, addr, 2, NUMA_NO_NODE, 0);
+	if (!page)
+		return 1;
+
+	ret = bpf_arena_reserve_pages(&arena, addr + 2 * __PAGE_SIZE, 2);
+	if (ret)
+		return 2;
+
+	/*
+	 * Reserved and allocated pages should be interchangeable for
+	 * bpf_arena_free_pages(). Free a reserved and an allocated
+	 * page with a single call.
+	 */
+	bpf_arena_free_pages(&arena, addr + __PAGE_SIZE , 2);
+
+	/* The free call above should have succeeded, so this allocation should too. */
+	page = bpf_arena_alloc_pages(&arena, addr + __PAGE_SIZE, 2, NUMA_NO_NODE, 0);
+	if (!page)
+		return 3;
+#endif
+	return 0;
+}
+
+#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
+#define PAGE_CNT 100
+__u8 __arena * __arena page[PAGE_CNT]; /* occupies the first page */
+__u8 __arena *base;
+
+/*
+ * Check that arena's range_tree algorithm allocates pages sequentially
+ * on the first pass and then fills in all gaps on the second pass.
+ */
+__noinline int alloc_pages(int page_cnt, int pages_atonce, bool first_pass,
+		int max_idx, int step)
+{
+	__u8 __arena *pg;
+	int i, pg_idx;
+
+	for (i = 0; i < page_cnt; i++) {
+		pg = bpf_arena_alloc_pages(&arena, NULL, pages_atonce,
+					   NUMA_NO_NODE, 0);
+		if (!pg)
+			return step;
+		pg_idx = (unsigned long) (pg - base) / PAGE_SIZE;
+		if (first_pass) {
+			/* Pages must be allocated sequentially */
+			if (pg_idx != i)
+				return step + 100;
+		} else {
+			/* Allocator must fill into gaps */
+			if (pg_idx >= max_idx || (pg_idx & 1))
+				return step + 200;
+		}
+		*pg = pg_idx;
+		page[pg_idx] = pg;
+		cond_break;
+	}
+	return 0;
+}
+
+SEC("syscall")
+__success __retval(0)
+int big_alloc2(void *ctx)
+{
+	__u8 __arena *pg;
+	int i, err;
+
+	base = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+	if (!base)
+		return 1;
+	bpf_arena_free_pages(&arena, (void __arena *)base, 1);
+
+	err = alloc_pages(PAGE_CNT, 1, true, PAGE_CNT, 2);
+	if (err)
+		return err;
+
+	/* Clear all even pages */
+	for (i = 0; i < PAGE_CNT; i += 2) {
+		pg = page[i];
+		if (*pg != i)
+			return 3;
+		bpf_arena_free_pages(&arena, (void __arena *)pg, 1);
+		page[i] = NULL;
+		cond_break;
+	}
+
+	/* Allocate into freed gaps */
+	err = alloc_pages(PAGE_CNT / 2, 1, false, PAGE_CNT, 4);
+	if (err)
+		return err;
+
+	/* Free pairs of pages */
+	for (i = 0; i < PAGE_CNT; i += 4) {
+		pg = page[i];
+		if (*pg != i)
+			return 5;
+		bpf_arena_free_pages(&arena, (void __arena *)pg, 2);
+		page[i] = NULL;
+		barrier();
+		page[i + 1] = NULL;
+		cond_break;
+	}
+
+	/* Allocate 2 pages at a time into freed gaps */
+	err = alloc_pages(PAGE_CNT / 4, 2, false, PAGE_CNT, 6);
+	if (err)
+		return err;
+
+	/* Check pages without freeing */
+	for (i = 0; i < PAGE_CNT; i += 2) {
+		pg = page[i];
+		if (*pg != i)
+			return 7;
+		cond_break;
+	}
+
+	pg = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
+
+	if (!pg)
+		return 8;
+	/*
+	 * The first PAGE_CNT pages are occupied. The new page
+	 * must be above.
+	 */
+	if ((pg - base) / PAGE_SIZE < PAGE_CNT)
+		return 9;
+	return 0;
+}
+#endif
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_array_access.c b/tools/testing/selftests/bpf/progs/verifier_array_access.c
new file mode 100644
index 000000000000..0a187ff725cc
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_array_access.c
@@ -0,0 +1,731 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/array_access.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#define MAX_ENTRIES 11
+
+struct test_val {
+	unsigned int index;
+	int foo[MAX_ENTRIES];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct test_val);
+	__uint(map_flags, BPF_F_RDONLY_PROG);
+} map_array_ro SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct test_val);
+	__uint(map_flags, BPF_F_WRONLY_PROG);
+} map_array_wo SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, 2);
+	__type(key, __u32);
+	__type(value, struct test_val);
+} map_array_pcpu SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 2);
+	__type(key, __u32);
+	__type(value, struct test_val);
+} map_array SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, struct test_val);
+} map_hash_48b SEC(".maps");
+
+SEC("socket")
+__description("valid map access into an array with a constant")
+__success __failure_unpriv __msg_unpriv("R0 leaks addr")
+__retval(0)
+__naked void an_array_with_a_constant_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = %[test_val_foo];				\
+	*(u64*)(r0 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("valid map access into an array with a register")
+__success __failure_unpriv __msg_unpriv("R0 leaks addr")
+__retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void an_array_with_a_register_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 4;						\
+	r1 <<= 2;					\
+	r0 += r1;					\
+	r1 = %[test_val_foo];				\
+	*(u64*)(r0 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("valid map access into an array with a variable")
+__success __failure_unpriv __msg_unpriv("R0 leaks addr")
+__retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void an_array_with_a_variable_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u32*)(r0 + 0);				\
+	if r1 >= %[max_entries] goto l0_%=;		\
+	r1 <<= 2;					\
+	r0 += r1;					\
+	r1 = %[test_val_foo];				\
+	*(u64*)(r0 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(max_entries, MAX_ENTRIES),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("valid map access into an array with a signed variable")
+__success __failure_unpriv __msg_unpriv("R0 leaks addr")
+__retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void array_with_a_signed_variable(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u32*)(r0 + 0);				\
+	if w1 s> 0xffffffff goto l1_%=;			\
+	w1 = 0;						\
+l1_%=:	w2 = %[max_entries];				\
+	if r2 s> r1 goto l2_%=;				\
+	w1 = 0;						\
+l2_%=:	w1 <<= 2;					\
+	r0 += r1;					\
+	r1 = %[test_val_foo];				\
+	*(u64*)(r0 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(max_entries, MAX_ENTRIES),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("invalid map access into an array with a constant")
+__failure __msg("invalid access to map value, value_size=48 off=48 size=8")
+__failure_unpriv
+__naked void an_array_with_a_constant_2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = %[test_val_foo];				\
+	*(u64*)(r0 + %[__imm_0]) = r1;			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(__imm_0, (MAX_ENTRIES + 1) << 2),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("invalid map access into an array with a register")
+__failure __msg("R0 min value is outside of the allowed memory range")
+__failure_unpriv
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void an_array_with_a_register_2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = %[__imm_0];				\
+	r1 <<= 2;					\
+	r0 += r1;					\
+	r1 = %[test_val_foo];				\
+	*(u64*)(r0 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(__imm_0, MAX_ENTRIES + 1),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("invalid map access into an array with a variable")
+__failure
+__msg("R0 unbounded memory access, make sure to bounds check any such access")
+__failure_unpriv
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void an_array_with_a_variable_2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u32*)(r0 + 0);				\
+	r1 <<= 2;					\
+	r0 += r1;					\
+	r1 = %[test_val_foo];				\
+	*(u64*)(r0 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("invalid map access into an array with no floor check")
+__failure __msg("R0 unbounded memory access")
+__failure_unpriv __msg_unpriv("R0 leaks addr")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void array_with_no_floor_check(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u64*)(r0 + 0);				\
+	w2 = %[max_entries];				\
+	if r2 s> r1 goto l1_%=;				\
+	w1 = 0;						\
+l1_%=:	w1 <<= 2;					\
+	r0 += r1;					\
+	r1 = %[test_val_foo];				\
+	*(u64*)(r0 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(max_entries, MAX_ENTRIES),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("invalid map access into an array with a invalid max check")
+__failure __msg("invalid access to map value, value_size=48 off=44 size=8")
+__failure_unpriv __msg_unpriv("R0 leaks addr")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void with_a_invalid_max_check_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u32*)(r0 + 0);				\
+	w2 = %[__imm_0];				\
+	if r2 > r1 goto l1_%=;				\
+	w1 = 0;						\
+l1_%=:	w1 <<= 2;					\
+	r0 += r1;					\
+	r1 = %[test_val_foo];				\
+	*(u64*)(r0 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(__imm_0, MAX_ENTRIES + 1),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("invalid map access into an array with a invalid max check")
+__failure __msg("R0 pointer += pointer")
+__failure_unpriv
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void with_a_invalid_max_check_2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r8 = r0;					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r0 += r8;					\
+	r0 = *(u32*)(r0 + %[test_val_foo]);		\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("valid read map access into a read-only array 1")
+__success __success_unpriv __retval(28)
+__naked void a_read_only_array_1_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_ro] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r0 = *(u32*)(r0 + 0);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_ro)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("valid read map access into a read-only array 2")
+__success __retval(65507)
+__naked void a_read_only_array_2_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_ro] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r2 = 4;						\
+	r3 = 0;						\
+	r4 = 0;						\
+	r5 = 0;						\
+	call %[bpf_csum_diff];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_csum_diff),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_ro)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("invalid write map access into a read-only array 1")
+__failure __msg("write into map forbidden")
+__failure_unpriv
+__naked void a_read_only_array_1_2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_ro] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 42;					\
+	*(u64*)(r0 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_ro)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("invalid write map access into a read-only array 2")
+__failure __msg("write into map forbidden")
+__naked void a_read_only_array_2_2(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_ro] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r6;					\
+	r2 = 0;						\
+	r3 = r0;					\
+	r4 = 8;						\
+	call %[bpf_skb_load_bytes];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_skb_load_bytes),
+	  __imm_addr(map_array_ro)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("valid write map access into a write-only array 1")
+__success __success_unpriv __retval(1)
+__naked void a_write_only_array_1_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_wo] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 42;					\
+	*(u64*)(r0 + 0) = r1;				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_wo)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("valid write map access into a write-only array 2")
+__success __retval(0)
+__naked void a_write_only_array_2_1(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_wo] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r6;					\
+	r2 = 0;						\
+	r3 = r0;					\
+	r4 = 8;						\
+	call %[bpf_skb_load_bytes];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_skb_load_bytes),
+	  __imm_addr(map_array_wo)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("invalid read map access into a write-only array 1")
+__failure __msg("read from map forbidden")
+__failure_unpriv
+__naked void a_write_only_array_1_2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_wo] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r0 = *(u64*)(r0 + 0);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_wo)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("invalid read map access into a write-only array 2")
+__failure __msg("read from map forbidden")
+__naked void a_write_only_array_2_2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_wo] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r2 = 4;						\
+	r3 = 0;						\
+	r4 = 0;						\
+	r5 = 0;						\
+	call %[bpf_csum_diff];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_csum_diff),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_wo)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("valid map access into an array using constant without nullness")
+__success __retval(4) __log_level(2)
+__msg("mark_precise: frame0: regs= stack=-8 before {{[0-9]}}: ({{[a-f0-9]+}}) *(u32 *)(r10 -8) = {{(1|r[0-9])}}")
+unsigned int an_array_with_a_constant_no_nullness(void)
+{
+	/* Need 8-byte alignment for spill tracking */
+	__u32 __attribute__((aligned(8))) key = 1;
+	struct test_val *val;
+
+	val = bpf_map_lookup_elem(&map_array, &key);
+	val->index = offsetof(struct test_val, foo);
+
+	return val->index;
+}
+
+SEC("socket")
+__description("valid multiple map access into an array using constant without nullness")
+__success __retval(8) __log_level(2)
+__msg("mark_precise: frame0: regs= stack=-8 before {{[0-9]}}: ({{[a-f0-9]+}}) *(u32 *)(r10 -16) = {{(0|r[0-9])}}")
+__msg("mark_precise: frame0: regs= stack=-8 before {{[0-9]}}: ({{[a-f0-9]+}}) *(u32 *)(r10 -8) = {{(1|r[0-9])}}")
+unsigned int multiple_array_with_a_constant_no_nullness(void)
+{
+	__u32 __attribute__((aligned(8))) key = 1;
+	__u32 __attribute__((aligned(8))) key2 = 0;
+	struct test_val *val, *val2;
+
+	val = bpf_map_lookup_elem(&map_array, &key);
+	val->index = offsetof(struct test_val, foo);
+
+	val2 = bpf_map_lookup_elem(&map_array, &key2);
+	val2->index = offsetof(struct test_val, foo);
+
+	return val->index + val2->index;
+}
+
+SEC("socket")
+__description("valid map access into an array using natural aligned 32-bit constant 0 without nullness")
+__success __retval(4)
+unsigned int an_array_with_a_32bit_constant_0_no_nullness(void)
+{
+	/* Unlike the above tests, 32-bit zeroing is precisely tracked even
+	 * if writes are not aligned to BPF_REG_SIZE. This tests that our
+	 * STACK_ZERO handling functions.
+	 */
+	struct test_val *val;
+	__u32 key = 0;
+
+	val = bpf_map_lookup_elem(&map_array, &key);
+	val->index = offsetof(struct test_val, foo);
+
+	return val->index;
+}
+
+SEC("socket")
+__description("valid map access into a pcpu array using constant without nullness")
+__success __retval(4) __log_level(2)
+__msg("mark_precise: frame0: regs= stack=-8 before {{[0-9]}}: ({{[a-f0-9]+}}) *(u32 *)(r10 -8) = {{(1|r[0-9])}}")
+unsigned int a_pcpu_array_with_a_constant_no_nullness(void)
+{
+	__u32 __attribute__((aligned(8))) key = 1;
+	struct test_val *val;
+
+	val = bpf_map_lookup_elem(&map_array_pcpu, &key);
+	val->index = offsetof(struct test_val, foo);
+
+	return val->index;
+}
+
+SEC("socket")
+__description("invalid map access into an array using constant without nullness")
+__failure __msg("R0 invalid mem access 'map_value_or_null'")
+unsigned int an_array_with_a_constant_no_nullness_out_of_bounds(void)
+{
+	/* Out of bounds */
+	__u32 __attribute__((aligned(8))) key = 3;
+	struct test_val *val;
+
+	val = bpf_map_lookup_elem(&map_array, &key);
+	val->index = offsetof(struct test_val, foo);
+
+	return val->index;
+}
+
+SEC("socket")
+__description("invalid map access into an array using constant smaller than key_size")
+__failure __msg("R0 invalid mem access 'map_value_or_null'")
+unsigned int an_array_with_a_constant_too_small(void)
+{
+	__u32 __attribute__((aligned(8))) key;
+	struct test_val *val;
+
+	/* Mark entire key as STACK_MISC */
+	bpf_probe_read_user(&key, sizeof(key), NULL);
+
+	/* Spilling only the bottom byte results in a tnum const of 1.
+	 * We want to check that the verifier rejects it, as the spill is < 4B.
+	 */
+	*(__u8 *)&key = 1;
+	val = bpf_map_lookup_elem(&map_array, &key);
+
+	/* Should fail, as verifier cannot prove in-bound lookup */
+	val->index = offsetof(struct test_val, foo);
+
+	return val->index;
+}
+
+SEC("socket")
+__description("invalid map access into an array using constant larger than key_size")
+__failure __msg("R0 invalid mem access 'map_value_or_null'")
+unsigned int an_array_with_a_constant_too_big(void)
+{
+	struct test_val *val;
+	__u64 key = 1;
+
+	/* Even if the constant value is < max_entries, if the spill size is
+	 * larger than the key size, the set bits may not be where we expect them
+	 * to be on different endian architectures.
+	 */
+	val = bpf_map_lookup_elem(&map_array, &key);
+	val->index = offsetof(struct test_val, foo);
+
+	return val->index;
+}
+
+SEC("socket")
+__description("invalid elided lookup using const and non-const key")
+__failure __msg("R0 invalid mem access 'map_value_or_null'")
+unsigned int mixed_const_and_non_const_key_lookup(void)
+{
+	__u32 __attribute__((aligned(8))) key;
+	struct test_val *val;
+	__u32 rand;
+
+	rand = bpf_get_prandom_u32();
+	key = rand > 42 ? 1 : rand;
+	val = bpf_map_lookup_elem(&map_array, &key);
+
+	return val->index;
+}
+
+SEC("socket")
+__failure __msg("invalid read from stack R2 off=4096 size=4")
+__naked void key_lookup_at_invalid_fp(void)
+{
+	asm volatile ("					\
+	r1 = %[map_array] ll;				\
+	r2 = r10;					\
+	r2 += 4096;					\
+	call %[bpf_map_lookup_elem];			\
+	r0 = *(u64*)(r0 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array)
+	: __clobber_all);
+}
+
+volatile __u32 __attribute__((aligned(8))) global_key;
+
+SEC("socket")
+__description("invalid elided lookup using non-stack key")
+__failure __msg("R0 invalid mem access 'map_value_or_null'")
+unsigned int non_stack_key_lookup(void)
+{
+	struct test_val *val;
+
+	global_key = 1;
+	val = bpf_map_lookup_elem(&map_array, (void *)&global_key);
+	val->index = offsetof(struct test_val, foo);
+
+	return val->index;
+}
+
+SEC("socket")
+__description("doesn't reject UINT64_MAX as s64 for irrelevant maps")
+__success __retval(42)
+unsigned int doesnt_reject_irrelevant_maps(void)
+{
+	__u64 key = 0xFFFFFFFFFFFFFFFF;
+	struct test_val *val;
+
+	val = bpf_map_lookup_elem(&map_hash_48b, &key);
+	if (val)
+		return val->index;
+
+	return 42;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c b/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c
new file mode 100644
index 000000000000..7efa9521105e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_async_cb_context.c
@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+char _license[] SEC("license") = "GPL";
+
+/* Timer tests */
+
+struct timer_elem {
+	struct bpf_timer t;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct timer_elem);
+} timer_map SEC(".maps");
+
+static int timer_cb(void *map, int *key, struct bpf_timer *timer)
+{
+	u32 data;
+	/* Timer callbacks are never sleepable, even from non-sleepable programs */
+	bpf_copy_from_user(&data, sizeof(data), NULL);
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test1")
+__failure __msg("helper call might sleep in a non-sleepable prog")
+int timer_non_sleepable_prog(void *ctx)
+{
+	struct timer_elem *val;
+	int key = 0;
+
+	val = bpf_map_lookup_elem(&timer_map, &key);
+	if (!val)
+		return 0;
+
+	bpf_timer_init(&val->t, &timer_map, 0);
+	bpf_timer_set_callback(&val->t, timer_cb);
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("helper call might sleep in a non-sleepable prog")
+int timer_sleepable_prog(void *ctx)
+{
+	struct timer_elem *val;
+	int key = 0;
+
+	val = bpf_map_lookup_elem(&timer_map, &key);
+	if (!val)
+		return 0;
+
+	bpf_timer_init(&val->t, &timer_map, 0);
+	bpf_timer_set_callback(&val->t, timer_cb);
+	return 0;
+}
+
+/* Workqueue tests */
+
+struct wq_elem {
+	struct bpf_wq w;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct wq_elem);
+} wq_map SEC(".maps");
+
+static int wq_cb(void *map, int *key, void *value)
+{
+	u32 data;
+	/* Workqueue callbacks are always sleepable, even from non-sleepable programs */
+	bpf_copy_from_user(&data, sizeof(data), NULL);
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test1")
+__success
+int wq_non_sleepable_prog(void *ctx)
+{
+	struct wq_elem *val;
+	int key = 0;
+
+	val = bpf_map_lookup_elem(&wq_map, &key);
+	if (!val)
+		return 0;
+
+	if (bpf_wq_init(&val->w, &wq_map, 0) != 0)
+		return 0;
+	if (bpf_wq_set_callback_impl(&val->w, wq_cb, 0, NULL) != 0)
+		return 0;
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__success
+int wq_sleepable_prog(void *ctx)
+{
+	struct wq_elem *val;
+	int key = 0;
+
+	val = bpf_map_lookup_elem(&wq_map, &key);
+	if (!val)
+		return 0;
+
+	if (bpf_wq_init(&val->w, &wq_map, 0) != 0)
+		return 0;
+	if (bpf_wq_set_callback_impl(&val->w, wq_cb, 0, NULL) != 0)
+		return 0;
+	return 0;
+}
+
+/* Task work tests */
+
+struct task_work_elem {
+	struct bpf_task_work tw;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct task_work_elem);
+} task_work_map SEC(".maps");
+
+static int task_work_cb(struct bpf_map *map, void *key, void *value)
+{
+	u32 data;
+	/* Task work callbacks are always sleepable, even from non-sleepable programs */
+	bpf_copy_from_user(&data, sizeof(data), NULL);
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test1")
+__success
+int task_work_non_sleepable_prog(void *ctx)
+{
+	struct task_work_elem *val;
+	struct task_struct *task;
+	int key = 0;
+
+	val = bpf_map_lookup_elem(&task_work_map, &key);
+	if (!val)
+		return 0;
+
+	task = bpf_get_current_task_btf();
+	if (!task)
+		return 0;
+
+	bpf_task_work_schedule_resume_impl(task, &val->tw, &task_work_map, task_work_cb, NULL);
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__success
+int task_work_sleepable_prog(void *ctx)
+{
+	struct task_work_elem *val;
+	struct task_struct *task;
+	int key = 0;
+
+	val = bpf_map_lookup_elem(&task_work_map, &key);
+	if (!val)
+		return 0;
+
+	task = bpf_get_current_task_btf();
+	if (!task)
+		return 0;
+
+	bpf_task_work_schedule_resume_impl(task, &val->tw, &task_work_map, task_work_cb, NULL);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/verifier_basic_stack.c b/tools/testing/selftests/bpf/progs/verifier_basic_stack.c
new file mode 100644
index 000000000000..fb62e09f2114
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_basic_stack.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/basic_stack.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, long long);
+} map_hash_8b SEC(".maps");
+
+SEC("socket")
+__description("stack out of bounds")
+__failure __msg("invalid write to stack")
+__failure_unpriv
+__naked void stack_out_of_bounds(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 + 8) = r1;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("uninitialized stack1")
+__success __log_level(4) __msg("stack depth 8")
+__failure_unpriv __msg_unpriv("invalid read from stack")
+__naked void uninitialized_stack1(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("uninitialized stack2")
+__success __log_level(4) __msg("stack depth 8")
+__failure_unpriv __msg_unpriv("invalid read from stack")
+__naked void uninitialized_stack2(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r0 = *(u64*)(r2 - 8);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("invalid fp arithmetic")
+__failure __msg("R1 subtraction from stack pointer")
+__failure_unpriv
+__naked void invalid_fp_arithmetic(void)
+{
+	/* If this gets ever changed, make sure JITs can deal with it. */
+	asm volatile ("					\
+	r0 = 0;						\
+	r1 = r10;					\
+	r1 -= 8;					\
+	*(u64*)(r1 + 0) = r0;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("non-invalid fp arithmetic")
+__success __success_unpriv __retval(0)
+__naked void non_invalid_fp_arithmetic(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	*(u64*)(r10 - 8) = r0;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("misaligned read from stack")
+__failure __msg("misaligned stack access")
+__failure_unpriv
+__naked void misaligned_read_from_stack(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r0 = *(u64*)(r2 - 4);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_bitfield_write.c b/tools/testing/selftests/bpf/progs/verifier_bitfield_write.c
new file mode 100644
index 000000000000..623f130a3198
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_bitfield_write.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <stdint.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+
+#include "bpf_misc.h"
+
+struct core_reloc_bitfields {
+	/* unsigned bitfields */
+	uint8_t		ub1: 1;
+	uint8_t		ub2: 2;
+	uint32_t	ub7: 7;
+	/* signed bitfields */
+	int8_t		sb4: 4;
+	int32_t		sb20: 20;
+	/* non-bitfields */
+	uint32_t	u32;
+	int32_t		s32;
+} __attribute__((preserve_access_index));
+
+SEC("tc")
+__description("single CO-RE bitfield roundtrip")
+__btf_path("btf__core_reloc_bitfields.bpf.o")
+__success
+__retval(3)
+int single_field_roundtrip(struct __sk_buff *ctx)
+{
+	struct core_reloc_bitfields bitfields;
+
+	__builtin_memset(&bitfields, 0, sizeof(bitfields));
+	BPF_CORE_WRITE_BITFIELD(&bitfields, ub2, 3);
+	return BPF_CORE_READ_BITFIELD(&bitfields, ub2);
+}
+
+SEC("tc")
+__description("multiple CO-RE bitfield roundtrip")
+__btf_path("btf__core_reloc_bitfields.bpf.o")
+__success
+__retval(0x3FD)
+int multiple_field_roundtrip(struct __sk_buff *ctx)
+{
+	struct core_reloc_bitfields bitfields;
+	uint8_t ub2;
+	int8_t sb4;
+
+	__builtin_memset(&bitfields, 0, sizeof(bitfields));
+	BPF_CORE_WRITE_BITFIELD(&bitfields, ub2, 1);
+	BPF_CORE_WRITE_BITFIELD(&bitfields, sb4, -1);
+
+	ub2 = BPF_CORE_READ_BITFIELD(&bitfields, ub2);
+	sb4 = BPF_CORE_READ_BITFIELD(&bitfields, sb4);
+
+	return (((uint8_t)sb4) << 2) | ub2;
+}
+
+SEC("tc")
+__description("adjacent CO-RE bitfield roundtrip")
+__btf_path("btf__core_reloc_bitfields.bpf.o")
+__success
+__retval(7)
+int adjacent_field_roundtrip(struct __sk_buff *ctx)
+{
+	struct core_reloc_bitfields bitfields;
+	uint8_t ub1, ub2;
+
+	__builtin_memset(&bitfields, 0, sizeof(bitfields));
+	BPF_CORE_WRITE_BITFIELD(&bitfields, ub1, 1);
+	BPF_CORE_WRITE_BITFIELD(&bitfields, ub2, 3);
+
+	ub1 = BPF_CORE_READ_BITFIELD(&bitfields, ub1);
+	ub2 = BPF_CORE_READ_BITFIELD(&bitfields, ub2);
+
+	return (ub2 << 1) | ub1;
+}
+
+SEC("tc")
+__description("multibyte CO-RE bitfield roundtrip")
+__btf_path("btf__core_reloc_bitfields.bpf.o")
+__success
+__retval(0x21)
+int multibyte_field_roundtrip(struct __sk_buff *ctx)
+{
+	struct core_reloc_bitfields bitfields;
+	uint32_t ub7;
+	uint8_t ub1;
+
+	__builtin_memset(&bitfields, 0, sizeof(bitfields));
+	BPF_CORE_WRITE_BITFIELD(&bitfields, ub1, 1);
+	BPF_CORE_WRITE_BITFIELD(&bitfields, ub7, 16);
+
+	ub1 = BPF_CORE_READ_BITFIELD(&bitfields, ub1);
+	ub7 = BPF_CORE_READ_BITFIELD(&bitfields, ub7);
+
+	return (ub7 << 1) | ub1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_bits_iter.c b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c
new file mode 100644
index 000000000000..8bcddadfc4da
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_bits_iter.c
@@ -0,0 +1,232 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2024 Yafang Shao <laoar.shao@gmail.com> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#include "bpf_misc.h"
+#include "task_kfunc_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+int bpf_iter_bits_new(struct bpf_iter_bits *it, const u64 *unsafe_ptr__ign,
+		      u32 nr_bits) __ksym __weak;
+int *bpf_iter_bits_next(struct bpf_iter_bits *it) __ksym __weak;
+void bpf_iter_bits_destroy(struct bpf_iter_bits *it) __ksym __weak;
+
+u64 bits_array[511] = {};
+
+SEC("iter.s/cgroup")
+__description("bits iter without destroy")
+__failure __msg("Unreleased reference")
+int BPF_PROG(no_destroy, struct bpf_iter_meta *meta, struct cgroup *cgrp)
+{
+	struct bpf_iter_bits it;
+	u64 data = 1;
+
+	bpf_iter_bits_new(&it, &data, 1);
+	bpf_iter_bits_next(&it);
+	return 0;
+}
+
+SEC("iter/cgroup")
+__description("uninitialized iter in ->next()")
+__failure __msg("expected an initialized iter_bits as arg #0")
+int BPF_PROG(next_uninit, struct bpf_iter_meta *meta, struct cgroup *cgrp)
+{
+	struct bpf_iter_bits it = {};
+
+	bpf_iter_bits_next(&it);
+	return 0;
+}
+
+SEC("iter/cgroup")
+__description("uninitialized iter in ->destroy()")
+__failure __msg("expected an initialized iter_bits as arg #0")
+int BPF_PROG(destroy_uninit, struct bpf_iter_meta *meta, struct cgroup *cgrp)
+{
+	struct bpf_iter_bits it = {};
+
+	bpf_iter_bits_destroy(&it);
+	return 0;
+}
+
+SEC("syscall")
+__description("null pointer")
+__success __retval(0)
+int null_pointer(void)
+{
+	struct bpf_iter_bits iter;
+	int err, nr = 0;
+	int *bit;
+
+	err = bpf_iter_bits_new(&iter, NULL, 1);
+	bpf_iter_bits_destroy(&iter);
+	if (err != -EINVAL)
+		return 1;
+
+	bpf_for_each(bits, bit, NULL, 1)
+		nr++;
+	return nr;
+}
+
+SEC("syscall")
+__description("bits copy")
+__success __retval(10)
+int bits_copy(void)
+{
+	u64 data = 0xf7310UL; /* 4 + 3 + 2 + 1 + 0*/
+	int nr = 0;
+	int *bit;
+
+	bpf_for_each(bits, bit, &data, 1)
+		nr++;
+	return nr;
+}
+
+SEC("syscall")
+__description("bits memalloc")
+__success __retval(64)
+int bits_memalloc(void)
+{
+	u64 data[2];
+	int nr = 0;
+	int *bit;
+
+	__builtin_memset(&data, 0xf0, sizeof(data)); /* 4 * 16 */
+	bpf_for_each(bits, bit, &data[0], ARRAY_SIZE(data))
+		nr++;
+	return nr;
+}
+
+SEC("syscall")
+__description("bit index")
+__success __retval(8)
+int bit_index(void)
+{
+	u64 data = 0x100;
+	int bit_idx = 0;
+	int *bit;
+
+	bpf_for_each(bits, bit, &data, 1) {
+		if (*bit == 0)
+			continue;
+		bit_idx = *bit;
+	}
+	return bit_idx;
+}
+
+SEC("syscall")
+__description("bits too big")
+__success __retval(0)
+int bits_too_big(void)
+{
+	u64 data[4];
+	int nr = 0;
+	int *bit;
+
+	__builtin_memset(&data, 0xff, sizeof(data));
+	bpf_for_each(bits, bit, &data[0], 512) /* Be greater than 511 */
+		nr++;
+	return nr;
+}
+
+SEC("syscall")
+__description("fewer words")
+__success __retval(1)
+int fewer_words(void)
+{
+	u64 data[2] = {0x1, 0xff};
+	int nr = 0;
+	int *bit;
+
+	bpf_for_each(bits, bit, &data[0], 1)
+		nr++;
+	return nr;
+}
+
+SEC("syscall")
+__description("zero words")
+__success __retval(0)
+int zero_words(void)
+{
+	u64 data[2] = {0x1, 0xff};
+	int nr = 0;
+	int *bit;
+
+	bpf_for_each(bits, bit, &data[0], 0)
+		nr++;
+	return nr;
+}
+
+SEC("syscall")
+__description("huge words")
+__success __retval(0)
+int huge_words(void)
+{
+	u64 data[8] = {0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1};
+	int nr = 0;
+	int *bit;
+
+	bpf_for_each(bits, bit, &data[0], 67108865)
+		nr++;
+	return nr;
+}
+
+SEC("syscall")
+__description("max words")
+__success __retval(4)
+int max_words(void)
+{
+	volatile int nr = 0;
+	int *bit;
+
+	bits_array[0] = (1ULL << 63) | 1U;
+	bits_array[510] = (1ULL << 33) | (1ULL << 32);
+
+	bpf_for_each(bits, bit, bits_array, 511) {
+		if (nr == 0 && *bit != 0)
+			break;
+		if (nr == 2 && *bit != 32672)
+			break;
+		nr++;
+	}
+	return nr;
+}
+
+SEC("syscall")
+__description("bad words")
+__success __retval(0)
+int bad_words(void)
+{
+	void *bad_addr = (void *)-4095;
+	struct bpf_iter_bits iter;
+	volatile int nr;
+	int *bit;
+	int err;
+
+	err = bpf_iter_bits_new(&iter, bad_addr, 1);
+	bpf_iter_bits_destroy(&iter);
+	if (err != -EFAULT)
+		return 1;
+
+	nr = 0;
+	bpf_for_each(bits, bit, bad_addr, 1)
+		nr++;
+	if (nr != 0)
+		return 2;
+
+	err = bpf_iter_bits_new(&iter, bad_addr, 4);
+	bpf_iter_bits_destroy(&iter);
+	if (err != -EFAULT)
+		return 3;
+
+	nr = 0;
+	bpf_for_each(bits, bit, bad_addr, 4)
+		nr++;
+	if (nr != 0)
+		return 4;
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c
new file mode 100644
index 000000000000..411a18437d7e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c
@@ -0,0 +1,1866 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/bounds.c */
+
+#include <linux/bpf.h>
+#include <../../../include/linux/filter.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, long long);
+} map_hash_8b SEC(".maps");
+
+SEC("socket")
+__description("subtraction bounds (map value) variant 1")
+__failure __msg("R0 max value is outside of the allowed memory range")
+__failure_unpriv
+__naked void bounds_map_value_variant_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u8*)(r0 + 0);				\
+	if r1 > 0xff goto l0_%=;			\
+	r3 = *(u8*)(r0 + 1);				\
+	if r3 > 0xff goto l0_%=;			\
+	r1 -= r3;					\
+	r1 >>= 56;					\
+	r0 += r1;					\
+	r0 = *(u8*)(r0 + 0);				\
+	exit;						\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("subtraction bounds (map value) variant 2")
+__failure
+__msg("R0 min value is negative, either use unsigned index or do a if (index >=0) check.")
+__msg_unpriv("R1 has unknown scalar with mixed signed bounds")
+__naked void bounds_map_value_variant_2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u8*)(r0 + 0);				\
+	if r1 > 0xff goto l0_%=;			\
+	r3 = *(u8*)(r0 + 1);				\
+	if r3 > 0xff goto l0_%=;			\
+	r1 -= r3;					\
+	r0 += r1;					\
+	r0 = *(u8*)(r0 + 0);				\
+	exit;						\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check subtraction on pointers for unpriv")
+__success __failure_unpriv __msg_unpriv("R9 pointer -= pointer prohibited")
+__retval(0)
+__naked void subtraction_on_pointers_for_unpriv(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	r1 = %[map_hash_8b] ll;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r6 = 9;						\
+	*(u64*)(r2 + 0) = r6;				\
+	call %[bpf_map_lookup_elem];			\
+	r9 = r10;					\
+	r9 -= r0;					\
+	r1 = %[map_hash_8b] ll;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r6 = 0;						\
+	*(u64*)(r2 + 0) = r6;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	*(u64*)(r0 + 0) = r9;				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check based on zero-extended MOV")
+__success __success_unpriv __retval(0)
+__naked void based_on_zero_extended_mov(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	/* r2 = 0x0000'0000'ffff'ffff */		\
+	w2 = 0xffffffff;				\
+	/* r2 = 0 */					\
+	r2 >>= 32;					\
+	/* no-op */					\
+	r0 += r2;					\
+	/* access at offset 0 */			\
+	r0 = *(u8*)(r0 + 0);				\
+l0_%=:	/* exit */					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check based on sign-extended MOV. test1")
+__failure __msg("map_value pointer and 4294967295")
+__failure_unpriv
+__naked void on_sign_extended_mov_test1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	/* r2 = 0xffff'ffff'ffff'ffff */		\
+	r2 = 0xffffffff;				\
+	/* r2 = 0xffff'ffff */				\
+	r2 >>= 32;					\
+	/* r0 = <oob pointer> */			\
+	r0 += r2;					\
+	/* access to OOB pointer */			\
+	r0 = *(u8*)(r0 + 0);				\
+l0_%=:	/* exit */					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check based on sign-extended MOV. test2")
+__failure __msg("R0 min value is outside of the allowed memory range")
+__failure_unpriv
+__naked void on_sign_extended_mov_test2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	/* r2 = 0xffff'ffff'ffff'ffff */		\
+	r2 = 0xffffffff;				\
+	/* r2 = 0xfff'ffff */				\
+	r2 >>= 36;					\
+	/* r0 = <oob pointer> */			\
+	r0 += r2;					\
+	/* access to OOB pointer */			\
+	r0 = *(u8*)(r0 + 0);				\
+l0_%=:	/* exit */					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("bounds check based on reg_off + var_off + insn_off. test1")
+__failure __msg("value_size=8 off=1073741825")
+__naked void var_off_insn_off_test1(void)
+{
+	asm volatile ("					\
+	r6 = *(u32*)(r1 + %[__sk_buff_mark]);		\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r6 &= 1;					\
+	r6 += %[__imm_0];				\
+	r0 += r6;					\
+	r0 += %[__imm_0];				\
+l0_%=:	r0 = *(u8*)(r0 + 3);				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b),
+	  __imm_const(__imm_0, (1 << 29) - 1),
+	  __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("bounds check based on reg_off + var_off + insn_off. test2")
+__failure __msg("value 1073741823")
+__naked void var_off_insn_off_test2(void)
+{
+	asm volatile ("					\
+	r6 = *(u32*)(r1 + %[__sk_buff_mark]);		\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r6 &= 1;					\
+	r6 += %[__imm_0];				\
+	r0 += r6;					\
+	r0 += %[__imm_1];				\
+l0_%=:	r0 = *(u8*)(r0 + 3);				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b),
+	  __imm_const(__imm_0, (1 << 30) - 1),
+	  __imm_const(__imm_1, (1 << 29) - 1),
+	  __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check after truncation of non-boundary-crossing range")
+__success __success_unpriv __retval(0)
+__naked void of_non_boundary_crossing_range(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	/* r1 = [0x00, 0xff] */				\
+	r1 = *(u8*)(r0 + 0);				\
+	r2 = 1;						\
+	/* r2 = 0x10'0000'0000 */			\
+	r2 <<= 36;					\
+	/* r1 = [0x10'0000'0000, 0x10'0000'00ff] */	\
+	r1 += r2;					\
+	/* r1 = [0x10'7fff'ffff, 0x10'8000'00fe] */	\
+	r1 += 0x7fffffff;				\
+	/* r1 = [0x00, 0xff] */				\
+	w1 -= 0x7fffffff;				\
+	/* r1 = 0 */					\
+	r1 >>= 8;					\
+	/* no-op */					\
+	r0 += r1;					\
+	/* access at offset 0 */			\
+	r0 = *(u8*)(r0 + 0);				\
+l0_%=:	/* exit */					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check after truncation of boundary-crossing range (1)")
+__failure
+/* not actually fully unbounded, but the bound is very high */
+__msg("value -4294967168 makes map_value pointer be out of bounds")
+__failure_unpriv
+__naked void of_boundary_crossing_range_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	/* r1 = [0x00, 0xff] */				\
+	r1 = *(u8*)(r0 + 0);				\
+	r1 += %[__imm_0];				\
+	/* r1 = [0xffff'ff80, 0x1'0000'007f] */		\
+	r1 += %[__imm_0];				\
+	/* r1 = [0xffff'ff80, 0xffff'ffff] or		\
+	 *      [0x0000'0000, 0x0000'007f]		\
+	 */						\
+	w1 += 0;					\
+	r1 -= %[__imm_0];				\
+	/* r1 = [0x00, 0xff] or				\
+	 *      [0xffff'ffff'0000'0080, 0xffff'ffff'ffff'ffff]\
+	 */						\
+	r1 -= %[__imm_0];				\
+	/* error on OOB pointer computation */		\
+	r0 += r1;					\
+	/* exit */					\
+	r0 = 0;						\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b),
+	  __imm_const(__imm_0, 0xffffff80 >> 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check after truncation of boundary-crossing range (2)")
+__failure __msg("value -4294967168 makes map_value pointer be out of bounds")
+__failure_unpriv
+__naked void of_boundary_crossing_range_2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	/* r1 = [0x00, 0xff] */				\
+	r1 = *(u8*)(r0 + 0);				\
+	r1 += %[__imm_0];				\
+	/* r1 = [0xffff'ff80, 0x1'0000'007f] */		\
+	r1 += %[__imm_0];				\
+	/* r1 = [0xffff'ff80, 0xffff'ffff] or		\
+	 *      [0x0000'0000, 0x0000'007f]		\
+	 * difference to previous test: truncation via MOV32\
+	 * instead of ALU32.				\
+	 */						\
+	w1 = w1;					\
+	r1 -= %[__imm_0];				\
+	/* r1 = [0x00, 0xff] or				\
+	 *      [0xffff'ffff'0000'0080, 0xffff'ffff'ffff'ffff]\
+	 */						\
+	r1 -= %[__imm_0];				\
+	/* error on OOB pointer computation */		\
+	r0 += r1;					\
+	/* exit */					\
+	r0 = 0;						\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b),
+	  __imm_const(__imm_0, 0xffffff80 >> 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check after wrapping 32-bit addition")
+__success __success_unpriv __retval(0)
+__naked void after_wrapping_32_bit_addition(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	/* r1 = 0x7fff'ffff */				\
+	r1 = 0x7fffffff;				\
+	/* r1 = 0xffff'fffe */				\
+	r1 += 0x7fffffff;				\
+	/* r1 = 0 */					\
+	w1 += 2;					\
+	/* no-op */					\
+	r0 += r1;					\
+	/* access at offset 0 */			\
+	r0 = *(u8*)(r0 + 0);				\
+l0_%=:	/* exit */					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check after shift with oversized count operand")
+__failure __msg("R0 max value is outside of the allowed memory range")
+__failure_unpriv
+__naked void shift_with_oversized_count_operand(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r2 = 32;					\
+	r1 = 1;						\
+	/* r1 = (u32)1 << (u32)32 = ? */		\
+	w1 <<= w2;					\
+	/* r1 = [0x0000, 0xffff] */			\
+	r1 &= 0xffff;					\
+	/* computes unknown pointer, potentially OOB */	\
+	r0 += r1;					\
+	/* potentially OOB access */			\
+	r0 = *(u8*)(r0 + 0);				\
+l0_%=:	/* exit */					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check after right shift of maybe-negative number")
+__failure __msg("R0 unbounded memory access")
+__failure_unpriv
+__naked void shift_of_maybe_negative_number(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	/* r1 = [0x00, 0xff] */				\
+	r1 = *(u8*)(r0 + 0);				\
+	/* r1 = [-0x01, 0xfe] */			\
+	r1 -= 1;					\
+	/* r1 = 0 or 0xff'ffff'ffff'ffff */		\
+	r1 >>= 8;					\
+	/* r1 = 0 or 0xffff'ffff'ffff */		\
+	r1 >>= 8;					\
+	/* computes unknown pointer, potentially OOB */	\
+	r0 += r1;					\
+	/* potentially OOB access */			\
+	r0 = *(u8*)(r0 + 0);				\
+l0_%=:	/* exit */					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check after 32-bit right shift with 64-bit input")
+__failure __msg("math between map_value pointer and 4294967294 is not allowed")
+__failure_unpriv
+__naked void shift_with_64_bit_input(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 2;						\
+	/* r1 = 1<<32 */				\
+	r1 <<= 31;					\
+	/* r1 = 0 (NOT 2!) */				\
+	w1 >>= 31;					\
+	/* r1 = 0xffff'fffe (NOT 0!) */			\
+	w1 -= 2;					\
+	/* error on computing OOB pointer */		\
+	r0 += r1;					\
+	/* exit */					\
+	r0 = 0;						\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check map access with off+size signed 32bit overflow. test1")
+__failure __msg("map_value pointer and 2147483646")
+__failure_unpriv
+__naked void size_signed_32bit_overflow_test1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r0 += 0x7ffffffe;				\
+	r0 = *(u64*)(r0 + 0);				\
+	goto l1_%=;					\
+l1_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check map access with off+size signed 32bit overflow. test2")
+__failure __msg("pointer offset 1073741822")
+__msg_unpriv("R0 pointer arithmetic of map value goes out of range")
+__naked void size_signed_32bit_overflow_test2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r0 += 0x1fffffff;				\
+	r0 += 0x1fffffff;				\
+	r0 += 0x1fffffff;				\
+	r0 = *(u64*)(r0 + 0);				\
+	goto l1_%=;					\
+l1_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check map access with off+size signed 32bit overflow. test3")
+__failure __msg("pointer offset -1073741822")
+__msg_unpriv("R0 pointer arithmetic of map value goes out of range")
+__naked void size_signed_32bit_overflow_test3(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r0 -= 0x1fffffff;				\
+	r0 -= 0x1fffffff;				\
+	r0 = *(u64*)(r0 + 2);				\
+	goto l1_%=;					\
+l1_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check map access with off+size signed 32bit overflow. test4")
+__failure __msg("map_value pointer and 1000000000000")
+__failure_unpriv
+__naked void size_signed_32bit_overflow_test4(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r1 = 1000000;					\
+	r1 *= 1000000;					\
+	r0 += r1;					\
+	r0 = *(u64*)(r0 + 2);				\
+	goto l1_%=;					\
+l1_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check mixed 32bit and 64bit arithmetic. test1")
+__success __success_unpriv
+__retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 invalid mem access 'scalar'` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("exit")
+#endif
+__naked void _32bit_and_64bit_arithmetic_test1(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	r1 = -1;					\
+	r1 <<= 32;					\
+	r1 += 1;					\
+	/* r1 = 0xffffFFFF00000001 */			\
+	if w1 > 1 goto l0_%=;				\
+	/* check ALU64 op keeps 32bit bounds */		\
+	r1 += 1;					\
+	if w1 > 2 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	/* invalid ldx if bounds are lost above */	\
+	r0 = *(u64*)(r0 - 1);				\
+l1_%=:	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check mixed 32bit and 64bit arithmetic. test2")
+__success __success_unpriv
+__retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 invalid mem access 'scalar'` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("exit")
+#endif
+__naked void _32bit_and_64bit_arithmetic_test2(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	r1 = -1;					\
+	r1 <<= 32;					\
+	r1 += 1;					\
+	/* r1 = 0xffffFFFF00000001 */			\
+	r2 = 3;						\
+	/* r1 = 0x2 */					\
+	w1 += 1;					\
+	/* check ALU32 op zero extends 64bit bounds */	\
+	if r1 > r2 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	/* invalid ldx if bounds are lost above */	\
+	r0 = *(u64*)(r0 - 1);				\
+l1_%=:	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tc")
+__description("assigning 32bit bounds to 64bit for wA = 0, wB = wA")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void for_wa_0_wb_wa(void)
+{
+	asm volatile ("					\
+	r8 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r7 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	w9 = 0;						\
+	w2 = w9;					\
+	r6 = r7;					\
+	r6 += r2;					\
+	r3 = r6;					\
+	r3 += 8;					\
+	if r3 > r8 goto l0_%=;				\
+	r5 = *(u32*)(r6 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check for reg = 0, reg xor 1")
+__success __success_unpriv
+__retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if r1 != 0x0 goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 min value is outside of the allowed memory range` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("r0 = 0")
+#endif
+__naked void reg_0_reg_xor_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r1 = 0;						\
+	r1 ^= 1;					\
+	if r1 != 0 goto l1_%=;				\
+	r0 = *(u64*)(r0 + 8);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check for reg32 = 0, reg32 xor 1")
+__success __success_unpriv
+__retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if w1 != 0x0 goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 min value is outside of the allowed memory range` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("r0 = 0")
+#endif
+__naked void reg32_0_reg32_xor_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	w1 = 0;						\
+	w1 ^= 1;					\
+	if w1 != 0 goto l1_%=;				\
+	r0 = *(u64*)(r0 + 8);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check for reg = 2, reg xor 3")
+__success __success_unpriv
+__retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if r1 > 0x0 goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 min value is outside of the allowed memory range` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("r0 = 0")
+#endif
+__naked void reg_2_reg_xor_3(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r1 = 2;						\
+	r1 ^= 3;					\
+	if r1 > 0 goto l1_%=;				\
+	r0 = *(u64*)(r0 + 8);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check for reg = any, reg xor 3")
+__failure __msg("invalid access to map value")
+__msg_unpriv("invalid access to map value")
+__naked void reg_any_reg_xor_3(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r1 = *(u64*)(r0 + 0);				\
+	r1 ^= 3;					\
+	if r1 != 0 goto l1_%=;				\
+	r0 = *(u64*)(r0 + 8);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check for reg32 = any, reg32 xor 3")
+__failure __msg("invalid access to map value")
+__msg_unpriv("invalid access to map value")
+__naked void reg32_any_reg32_xor_3(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r1 = *(u64*)(r0 + 0);				\
+	w1 ^= 3;					\
+	if w1 != 0 goto l1_%=;				\
+	r0 = *(u64*)(r0 + 8);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check for reg > 0, reg xor 3")
+__success __success_unpriv
+__retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if r1 >= 0x0 goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 min value is outside of the allowed memory range` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("r0 = 0")
+#endif
+__naked void reg_0_reg_xor_3(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r1 = *(u64*)(r0 + 0);				\
+	if r1 <= 0 goto l1_%=;				\
+	r1 ^= 3;					\
+	if r1 >= 0 goto l1_%=;				\
+	r0 = *(u64*)(r0 + 8);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check for reg32 > 0, reg32 xor 3")
+__success __success_unpriv
+__retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if w1 >= 0x0 goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 min value is outside of the allowed memory range` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("r0 = 0")
+#endif
+__naked void reg32_0_reg32_xor_3(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r1 = *(u64*)(r0 + 0);				\
+	if w1 <= 0 goto l1_%=;				\
+	w1 ^= 3;					\
+	if w1 >= 0 goto l1_%=;				\
+	r0 = *(u64*)(r0 + 8);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check for non const xor src dst")
+__success __log_level(2)
+__msg("5: (af) r0 ^= r6                      ; R0=scalar(smin=smin32=0,smax=umax=smax32=umax32=431,var_off=(0x0; 0x1af))")
+__naked void non_const_xor_src_dst(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];                    \
+	r6 = r0;					\
+	call %[bpf_get_prandom_u32];                    \
+	r6 &= 0xaf;					\
+	r0 &= 0x1a0;					\
+	r0 ^= r6;					\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	__imm_addr(map_hash_8b),
+	__imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check for non const or src dst")
+__success __log_level(2)
+__msg("5: (4f) r0 |= r6                      ; R0=scalar(smin=smin32=0,smax=umax=smax32=umax32=431,var_off=(0x0; 0x1af))")
+__naked void non_const_or_src_dst(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];                    \
+	r6 = r0;					\
+	call %[bpf_get_prandom_u32];                    \
+	r6 &= 0xaf;					\
+	r0 &= 0x1a0;					\
+	r0 |= r6;					\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	__imm_addr(map_hash_8b),
+	__imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds check for non const mul regs")
+__success __log_level(2)
+__msg("5: (2f) r0 *= r6                      ; R0=scalar(smin=smin32=0,smax=umax=smax32=umax32=3825,var_off=(0x0; 0xfff))")
+__naked void non_const_mul_regs(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];                    \
+	r6 = r0;					\
+	call %[bpf_get_prandom_u32];                    \
+	r6 &= 0xff;					\
+	r0 &= 0x0f;					\
+	r0 *= r6;					\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	__imm_addr(map_hash_8b),
+	__imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds checks after 32-bit truncation. test 1")
+__success __failure_unpriv __msg_unpriv("R0 leaks addr")
+__retval(0)
+__naked void _32_bit_truncation_test_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u32*)(r0 + 0);				\
+	/* This used to reduce the max bound to 0x7fffffff */\
+	if r1 == 0 goto l1_%=;				\
+	if r1 > 0x7fffffff goto l0_%=;			\
+l1_%=:	r0 = 0;						\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds checks after 32-bit truncation. test 2")
+__success __failure_unpriv __msg_unpriv("R0 leaks addr")
+__retval(0)
+__naked void _32_bit_truncation_test_2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u32*)(r0 + 0);				\
+	if r1 s< 1 goto l1_%=;				\
+	if w1 s< 0 goto l0_%=;				\
+l1_%=:	r0 = 0;						\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("bound check with JMP_JLT for crossing 64-bit signed boundary")
+__success __retval(0)
+__naked void crossing_64_bit_signed_boundary_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 1;					\
+	if r1 > r3 goto l0_%=;				\
+	r1 = *(u8*)(r2 + 0);				\
+	r0 = 0x7fffffffffffff10 ll;			\
+	r1 += r0;					\
+	r0 = 0x8000000000000000 ll;			\
+l1_%=:	r0 += 1;					\
+	/* r1 unsigned range is [0x7fffffffffffff10, 0x800000000000000f] */\
+	if r0 < r1 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("bound check with JMP_JSLT for crossing 64-bit signed boundary")
+__success __retval(0)
+__flag(BPF_F_TEST_REG_INVARIANTS)
+__naked void crossing_64_bit_signed_boundary_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 1;					\
+	if r1 > r3 goto l0_%=;				\
+	r1 = *(u8*)(r2 + 0);				\
+	r0 = 0x7fffffffffffff10 ll;			\
+	r1 += r0;					\
+	r2 = 0x8000000000000fff ll;			\
+	r0 = 0x8000000000000000 ll;			\
+l1_%=:	r0 += 1;					\
+	if r0 s> r2 goto l0_%=;				\
+	/* r1 signed range is [S64_MIN, S64_MAX] */	\
+	if r0 s< r1 goto l1_%=;				\
+	r0 = 1;						\
+	exit;						\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("bound check for loop upper bound greater than U32_MAX")
+__success __retval(0)
+__naked void bound_greater_than_u32_max(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 1;					\
+	if r1 > r3 goto l0_%=;				\
+	r1 = *(u8*)(r2 + 0);				\
+	r0 = 0x100000000 ll;				\
+	r1 += r0;					\
+	r0 = 0x100000000 ll;				\
+l1_%=:	r0 += 1;					\
+	if r0 < r1 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("bound check with JMP32_JLT for crossing 32-bit signed boundary")
+__success __retval(0)
+__naked void crossing_32_bit_signed_boundary_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 1;					\
+	if r1 > r3 goto l0_%=;				\
+	r1 = *(u8*)(r2 + 0);				\
+	w0 = 0x7fffff10;				\
+	w1 += w0;					\
+	w0 = 0x80000000;				\
+l1_%=:	w0 += 1;					\
+	/* r1 unsigned range is [0, 0x8000000f] */	\
+	if w0 < w1 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("bound check with JMP32_JSLT for crossing 32-bit signed boundary")
+__success __retval(0)
+__flag(!BPF_F_TEST_REG_INVARIANTS) /* known invariants violation */
+__naked void crossing_32_bit_signed_boundary_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 1;					\
+	if r1 > r3 goto l0_%=;				\
+	r1 = *(u8*)(r2 + 0);				\
+	w0 = 0x7fffff10;				\
+	w1 += w0;					\
+	w2 = 0x80000fff;				\
+	w0 = 0x80000000;				\
+l1_%=:	w0 += 1;					\
+	if w0 s> w2 goto l0_%=;				\
+	/* r1 signed range is [S32_MIN, S32_MAX] */	\
+	if w0 s< w1 goto l1_%=;				\
+	r0 = 1;						\
+	exit;						\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("bounds check with JMP_NE for reg edge")
+__success __retval(0)
+__naked void reg_not_equal_const(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	call %[bpf_get_prandom_u32];			\
+	r4 = r0;					\
+	r4 &= 7;					\
+	if r4 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r1 = r6;					\
+	r2 = 0;						\
+	r3 = r10;					\
+	r3 += -8;					\
+	r5 = 0;						\
+	/* The 4th argument of bpf_skb_store_bytes is defined as \
+	 * ARG_CONST_SIZE, so 0 is not allowed. The 'r4 != 0' \
+	 * is providing us this exclusion of zero from initial \
+	 * [0, 7] range.				\
+	 */						\
+	call %[bpf_skb_store_bytes];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_skb_store_bytes)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("bounds check with JMP_EQ for reg edge")
+__success __retval(0)
+__naked void reg_equal_const(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	call %[bpf_get_prandom_u32];			\
+	r4 = r0;					\
+	r4 &= 7;					\
+	if r4 == 0 goto l0_%=;				\
+	r1 = r6;					\
+	r2 = 0;						\
+	r3 = r10;					\
+	r3 += -8;					\
+	r5 = 0;						\
+	/* Just the same as what we do in reg_not_equal_const() */ \
+	call %[bpf_skb_store_bytes];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_skb_store_bytes)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("multiply mixed sign bounds. test 1")
+__success __log_level(2)
+__msg("r6 *= r7 {{.*}}; R6=scalar(smin=umin=0x1bc16d5cd4927ee1,smax=umax=0x1bc16d674ec80000,smax32=0x7ffffeff,umax32=0xfffffeff,var_off=(0x1bc16d4000000000; 0x3ffffffeff))")
+__naked void mult_mixed0_sign(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"r6 = r0;"
+	"call %[bpf_get_prandom_u32];"
+	"r7 = r0;"
+	"r6 &= 0xf;"
+	"r6 -= 1000000000;"
+	"r7 &= 0xf;"
+	"r7 -= 2000000000;"
+	"r6 *= r7;"
+	"exit"
+	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_skb_store_bytes)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("multiply mixed sign bounds. test 2")
+__success __log_level(2)
+__msg("r6 *= r7 {{.*}}; R6=scalar(smin=smin32=-100,smax=smax32=200)")
+__naked void mult_mixed1_sign(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"r6 = r0;"
+	"call %[bpf_get_prandom_u32];"
+	"r7 = r0;"
+	"r6 &= 0xf;"
+	"r6 -= 0xa;"
+	"r7 &= 0xf;"
+	"r7 -= 0x14;"
+	"r6 *= r7;"
+	"exit"
+	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_skb_store_bytes)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("multiply negative bounds")
+__success __log_level(2)
+__msg("r6 *= r7 {{.*}}; R6=scalar(smin=umin=smin32=umin32=0x3ff280b0,smax=umax=smax32=umax32=0x3fff0001,var_off=(0x3ff00000; 0xf81ff))")
+__naked void mult_sign_bounds(void)
+{
+	asm volatile (
+	"r8 = 0x7fff;"
+	"call %[bpf_get_prandom_u32];"
+	"r6 = r0;"
+	"call %[bpf_get_prandom_u32];"
+	"r7 = r0;"
+	"r6 &= 0xa;"
+	"r6 -= r8;"
+	"r7 &= 0xf;"
+	"r7 -= r8;"
+	"r6 *= r7;"
+	"exit"
+	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_skb_store_bytes)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("multiply bounds that don't cross signed boundary")
+__success __log_level(2)
+__msg("r8 *= r6 {{.*}}; R6=scalar(smin=smin32=0,smax=umax=smax32=umax32=11,var_off=(0x0; 0xb)) R8=scalar(smin=0,smax=umax=0x7b96bb0a94a3a7cd,var_off=(0x0; 0x7fffffffffffffff))")
+__naked void mult_no_sign_crossing(void)
+{
+	asm volatile (
+	"r6 = 0xb;"
+	"r8 = 0xb3c3f8c99262687 ll;"
+	"call %[bpf_get_prandom_u32];"
+	"r7 = r0;"
+	"r6 &= r7;"
+	"r8 *= r6;"
+	"exit"
+	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_skb_store_bytes)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("multiplication overflow, result in unbounded reg. test 1")
+__success __log_level(2)
+__msg("r6 *= r7 {{.*}}; R6=scalar()")
+__naked void mult_unsign_ovf(void)
+{
+	asm volatile (
+	"r8 = 0x7ffffffffff ll;"
+	"call %[bpf_get_prandom_u32];"
+	"r6 = r0;"
+	"call %[bpf_get_prandom_u32];"
+	"r7 = r0;"
+	"r6 &= 0x7fffffff;"
+	"r7 &= r8;"
+	"r6 *= r7;"
+	"exit"
+	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_skb_store_bytes)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("multiplication overflow, result in unbounded reg. test 2")
+__success __log_level(2)
+__msg("r6 *= r7 {{.*}}; R6=scalar()")
+__naked void mult_sign_ovf(void)
+{
+	asm volatile (
+	"r8 = 0x7ffffffff ll;"
+	"call %[bpf_get_prandom_u32];"
+	"r6 = r0;"
+	"call %[bpf_get_prandom_u32];"
+	"r7 = r0;"
+	"r6 &= 0xa;"
+	"r6 -= r8;"
+	"r7 &= 0x7fffffff;"
+	"r6 *= r7;"
+	"exit"
+	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_skb_store_bytes)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("64-bit addition, all outcomes overflow")
+__success __log_level(2)
+__msg("5: (0f) r3 += r3 {{.*}} R3=scalar(umin=0x4000000000000000,umax=0xfffffffffffffffe)")
+__retval(0)
+__naked void add64_full_overflow(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"r4 = r0;"
+	"r3 = 0xa000000000000000 ll;"
+	"r3 |= r4;"
+	"r3 += r3;"
+	"r0 = 0;"
+	"exit"
+	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("64-bit addition, partial overflow, result in unbounded reg")
+__success __log_level(2)
+__msg("4: (0f) r3 += r3 {{.*}} R3=scalar()")
+__retval(0)
+__naked void add64_partial_overflow(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"r4 = r0;"
+	"r3 = 2;"
+	"r3 |= r4;"
+	"r3 += r3;"
+	"r0 = 0;"
+	"exit"
+	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("32-bit addition overflow, all outcomes overflow")
+__success __log_level(2)
+__msg("4: (0c) w3 += w3 {{.*}} R3=scalar(smin=umin=umin32=0x40000000,smax=umax=umax32=0xfffffffe,var_off=(0x0; 0xffffffff))")
+__retval(0)
+__naked void add32_full_overflow(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"w4 = w0;"
+	"w3 = 0xa0000000;"
+	"w3 |= w4;"
+	"w3 += w3;"
+	"r0 = 0;"
+	"exit"
+	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("32-bit addition, partial overflow, result in unbounded u32 bounds")
+__success __log_level(2)
+__msg("4: (0c) w3 += w3 {{.*}} R3=scalar(smin=0,smax=umax=0xffffffff,var_off=(0x0; 0xffffffff))")
+__retval(0)
+__naked void add32_partial_overflow(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"w4 = w0;"
+	"w3 = 2;"
+	"w3 |= w4;"
+	"w3 += w3;"
+	"r0 = 0;"
+	"exit"
+	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("64-bit subtraction, all outcomes underflow")
+__success __log_level(2)
+__msg("6: (1f) r3 -= r1 {{.*}} R3=scalar(umin=1,umax=0x8000000000000000)")
+__retval(0)
+__naked void sub64_full_overflow(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"r1 = r0;"
+	"r2 = 0x8000000000000000 ll;"
+	"r1 |= r2;"
+	"r3 = 0;"
+	"r3 -= r1;"
+	"r0 = 0;"
+	"exit"
+	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("64-bit subtraction, partial overflow, result in unbounded reg")
+__success __log_level(2)
+__msg("3: (1f) r3 -= r2 {{.*}} R3=scalar()")
+__retval(0)
+__naked void sub64_partial_overflow(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"r3 = r0;"
+	"r2 = 1;"
+	"r3 -= r2;"
+	"r0 = 0;"
+	"exit"
+	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("32-bit subtraction overflow, all outcomes underflow")
+__success __log_level(2)
+__msg("5: (1c) w3 -= w1 {{.*}} R3=scalar(smin=umin=umin32=1,smax=umax=umax32=0x80000000,var_off=(0x0; 0xffffffff))")
+__retval(0)
+__naked void sub32_full_overflow(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"w1 = w0;"
+	"w2 = 0x80000000;"
+	"w1 |= w2;"
+	"w3 = 0;"
+	"w3 -= w1;"
+	"r0 = 0;"
+	"exit"
+	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("32-bit subtraction, partial overflow, result in unbounded u32 bounds")
+__success __log_level(2)
+__msg("3: (1c) w3 -= w2 {{.*}} R3=scalar(smin=0,smax=umax=0xffffffff,var_off=(0x0; 0xffffffff))")
+__retval(0)
+__naked void sub32_partial_overflow(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"w3 = w0;"
+	"w2 = 1;"
+	"w3 -= w2;"
+	"r0 = 0;"
+	"exit"
+	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("dead branch on jset, does not result in invariants violation error")
+__success __log_level(2)
+__retval(0) __flag(BPF_F_TEST_REG_INVARIANTS)
+__naked void jset_range_analysis(void)
+{
+	asm volatile ("			\
+	call %[bpf_get_netns_cookie];	\
+	if r0 == 0 goto l0_%=;		\
+	if r0 & 0xffffffff goto +0; 	\
+l0_%=:	r0 = 0;				\
+	exit;				\
+"	:
+	: __imm(bpf_get_netns_cookie)
+	: __clobber_all);
+}
+
+/* This test covers the bounds deduction on 64bits when the s64 and u64 ranges
+ * overlap on the negative side. At instruction 7, the ranges look as follows:
+ *
+ * 0          umin=0xfffffcf1                 umax=0xff..ff6e  U64_MAX
+ * |                [xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx]        |
+ * |----------------------------|------------------------------|
+ * |xxxxxxxxxx]                                   [xxxxxxxxxxxx|
+ * 0    smax=0xeffffeee                       smin=-655        -1
+ *
+ * We should therefore deduce the following new bounds:
+ *
+ * 0                             u64=[0xff..ffd71;0xff..ff6e]  U64_MAX
+ * |                                              [xxx]        |
+ * |----------------------------|------------------------------|
+ * |                                              [xxx]        |
+ * 0                                        s64=[-655;-146]    -1
+ *
+ * Without the deduction cross sign boundary, we end up with an invariant
+ * violation error.
+ */
+SEC("socket")
+__description("bounds deduction cross sign boundary, negative overlap")
+__success __log_level(2) __flag(BPF_F_TEST_REG_INVARIANTS)
+__msg("7: (1f) r0 -= r6 {{.*}} R0=scalar(smin=smin32=-655,smax=smax32=-146,umin=0xfffffffffffffd71,umax=0xffffffffffffff6e,umin32=0xfffffd71,umax32=0xffffff6e,var_off=(0xfffffffffffffc00; 0x3ff))")
+__retval(0)
+__naked void bounds_deduct_negative_overlap(void)
+{
+	asm volatile("			\
+	call %[bpf_get_prandom_u32];	\
+	w3 = w0;			\
+	w6 = (s8)w0;			\
+	r0 = (s8)r0;			\
+	if w6 >= 0xf0000000 goto l0_%=;	\
+	r0 += r6;			\
+	r6 += 400;			\
+	r0 -= r6;			\
+	if r3 < r0 goto l0_%=;		\
+l0_%=:	r0 = 0;				\
+	exit;				\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* This test covers the bounds deduction on 64bits when the s64 and u64 ranges
+ * overlap on the positive side. At instruction 3, the ranges look as follows:
+ *
+ * 0 umin=0                      umax=0xffffffffffffff00       U64_MAX
+ * [xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx]            |
+ * |----------------------------|------------------------------|
+ * |xxxxxxxx]                                         [xxxxxxxx|
+ * 0      smax=127                                smin=-128    -1
+ *
+ * We should therefore deduce the following new bounds:
+ *
+ * 0  u64=[0;127]                                              U64_MAX
+ * [xxxxxxxx]                                                  |
+ * |----------------------------|------------------------------|
+ * [xxxxxxxx]                                                  |
+ * 0  s64=[0;127]                                              -1
+ *
+ * Without the deduction cross sign boundary, the program is rejected due to
+ * the frame pointer write.
+ */
+SEC("socket")
+__description("bounds deduction cross sign boundary, positive overlap")
+__success __log_level(2) __flag(BPF_F_TEST_REG_INVARIANTS)
+__msg("3: (2d) if r0 > r1 {{.*}} R0=scalar(smin=smin32=0,smax=umax=smax32=umax32=127,var_off=(0x0; 0x7f))")
+__retval(0)
+__naked void bounds_deduct_positive_overlap(void)
+{
+	asm volatile("			\
+	call %[bpf_get_prandom_u32];	\
+	r0 = (s8)r0;			\
+	r1 = 0xffffffffffffff00;	\
+	if r0 > r1 goto l0_%=;		\
+	if r0 < 128 goto l0_%=;		\
+	r10 = 0;			\
+l0_%=:	r0 = 0;				\
+	exit;				\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* This test is the same as above, but the s64 and u64 ranges overlap in two
+ * places. At instruction 3, the ranges look as follows:
+ *
+ * 0 umin=0                           umax=0xffffffffffffff80  U64_MAX
+ * [xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx]        |
+ * |----------------------------|------------------------------|
+ * |xxxxxxxx]                                         [xxxxxxxx|
+ * 0      smax=127                                smin=-128    -1
+ *
+ * 0xffffffffffffff80 = (u64)-128. We therefore can't deduce anything new and
+ * the program should fail due to the frame pointer write.
+ */
+SEC("socket")
+__description("bounds deduction cross sign boundary, two overlaps")
+__failure __flag(BPF_F_TEST_REG_INVARIANTS)
+__msg("3: (2d) if r0 > r1 {{.*}} R0=scalar(smin=smin32=-128,smax=smax32=127,umax=0xffffffffffffff80)")
+__msg("frame pointer is read only")
+__naked void bounds_deduct_two_overlaps(void)
+{
+	asm volatile("			\
+	call %[bpf_get_prandom_u32];	\
+	r0 = (s8)r0;			\
+	r1 = 0xffffffffffffff80;	\
+	if r0 > r1 goto l0_%=;		\
+	if r0 < 128 goto l0_%=;		\
+	r10 = 0;			\
+l0_%=:	r0 = 0;				\
+	exit;				\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("dead jne branch due to disagreeing tnums")
+__success __log_level(2)
+__naked void jne_disagreeing_tnums(void *ctx)
+{
+	asm volatile("			\
+	call %[bpf_get_prandom_u32];	\
+	w0 = w0;			\
+	r0 >>= 30;			\
+	r0 <<= 30;			\
+	r1 = r0;			\
+	r1 += 1024;			\
+	if r1 != r0 goto +1;		\
+	r10 = 0;			\
+	exit;				\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("dead jeq branch due to disagreeing tnums")
+__success __log_level(2)
+__naked void jeq_disagreeing_tnums(void *ctx)
+{
+	asm volatile("			\
+	call %[bpf_get_prandom_u32];	\
+	w0 = w0;			\
+	r0 >>= 30;			\
+	r0 <<= 30;			\
+	r1 = r0;			\
+	r1 += 1024;			\
+	if r1 == r0 goto +1;		\
+	exit;				\
+	r10 = 0;			\
+	exit;				\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("conditional jump on same register, branch taken")
+__not_msg("20: (b7) r0 = 1 {{.*}} R0=1")
+__success __log_level(2)
+__retval(0) __flag(BPF_F_TEST_REG_INVARIANTS)
+__naked void condition_jump_on_same_register(void *ctx)
+{
+	asm volatile("			\
+	call %[bpf_get_prandom_u32];	\
+	w8 = 0x80000000;		\
+	r0 &= r8;			\
+	if r0 == r0 goto +1;		\
+	goto l1_%=;			\
+	if r0 >= r0 goto +1;		\
+	goto l1_%=;			\
+	if r0 s>= r0 goto +1;		\
+	goto l1_%=;			\
+	if r0 <= r0 goto +1;		\
+	goto l1_%=;			\
+	if r0 s<= r0 goto +1;		\
+	goto l1_%=;			\
+	if r0 != r0 goto l1_%=;		\
+	if r0 >  r0 goto l1_%=;		\
+	if r0 s> r0 goto l1_%=;		\
+	if r0 <  r0 goto l1_%=;		\
+	if r0 s< r0 goto l1_%=;		\
+l0_%=:	r0 = 0;				\
+	exit;				\
+l1_%=:	r0 = 1;				\
+	exit;				\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("jset on same register, constant value branch taken")
+__not_msg("7: (b7) r0 = 1 {{.*}} R0=1")
+__success __log_level(2)
+__retval(0) __flag(BPF_F_TEST_REG_INVARIANTS)
+__naked void jset_on_same_register_1(void *ctx)
+{
+	asm volatile("			\
+	r0 = 0;				\
+	if r0 & r0 goto l1_%=;		\
+	r0 = 1;				\
+	if r0 & r0 goto +1;		\
+	goto l1_%=;			\
+l0_%=:	r0 = 0;				\
+	exit;				\
+l1_%=:	r0 = 1;				\
+	exit;				\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("jset on same register, scalar value branch taken")
+__not_msg("12: (b7) r0 = 1 {{.*}} R0=1")
+__success __log_level(2)
+__retval(0) __flag(BPF_F_TEST_REG_INVARIANTS)
+__naked void jset_on_same_register_2(void *ctx)
+{
+	asm volatile("			\
+	/* range [1;2] */		\
+	call %[bpf_get_prandom_u32];	\
+	r0 &= 0x1;			\
+	r0 += 1;			\
+	if r0 & r0 goto +1;		\
+	goto l1_%=;			\
+	/* range [-2;-1] */		\
+	call %[bpf_get_prandom_u32];	\
+	r0 &= 0x1;			\
+	r0 -= 2;			\
+	if r0 & r0 goto +1;		\
+	goto l1_%=;			\
+l0_%=:	r0 = 0;				\
+	exit;				\
+l1_%=:	r0 = 1;				\
+	exit;				\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("jset on same register, scalar value unknown branch 1")
+__msg("3: (b7) r0 = 0 {{.*}} R0=0")
+__msg("5: (b7) r0 = 1 {{.*}} R0=1")
+__success __log_level(2)
+__flag(BPF_F_TEST_REG_INVARIANTS)
+__naked void jset_on_same_register_3(void *ctx)
+{
+	asm volatile("			\
+	/* range [0;1] */		\
+	call %[bpf_get_prandom_u32];	\
+	r0 &= 0x1;			\
+	if r0 & r0 goto l1_%=;		\
+l0_%=:	r0 = 0;				\
+	exit;				\
+l1_%=:	r0 = 1;				\
+	exit;				\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("jset on same register, scalar value unknown branch 2")
+__msg("4: (b7) r0 = 0 {{.*}} R0=0")
+__msg("6: (b7) r0 = 1 {{.*}} R0=1")
+__success __log_level(2)
+__flag(BPF_F_TEST_REG_INVARIANTS)
+__naked void jset_on_same_register_4(void *ctx)
+{
+	asm volatile("			\
+	/* range [-1;0] */		\
+	call %[bpf_get_prandom_u32];	\
+	r0 &= 0x1;			\
+	r0 -= 1;			\
+	if r0 & r0 goto l1_%=;		\
+l0_%=:	r0 = 0;				\
+	exit;				\
+l1_%=:	r0 = 1;				\
+	exit;				\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("jset on same register, scalar value unknown branch 3")
+__msg("4: (b7) r0 = 0 {{.*}} R0=0")
+__msg("6: (b7) r0 = 1 {{.*}} R0=1")
+__success __log_level(2)
+__flag(BPF_F_TEST_REG_INVARIANTS)
+__naked void jset_on_same_register_5(void *ctx)
+{
+	asm volatile("			\
+	/* range [-1;1] */		\
+	call %[bpf_get_prandom_u32];	\
+	r0 &= 0x2;			\
+	r0 -= 1;			\
+	if r0 & r0 goto l1_%=;		\
+l0_%=:	r0 = 0;				\
+	exit;				\
+l1_%=:	r0 = 1;				\
+	exit;				\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds_deduction.c b/tools/testing/selftests/bpf/progs/verifier_bounds_deduction.c
new file mode 100644
index 000000000000..260a6df264e3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_bounds_deduction.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/bounds_deduction.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("socket")
+__description("check deducing bounds from const, 1")
+__failure __msg("R0 tried to subtract pointer from scalar")
+__msg_unpriv("R1 has pointer with unsupported alu operation")
+__naked void deducing_bounds_from_const_1(void)
+{
+	asm volatile ("					\
+	r0 = 1;						\
+	if r0 s>= 1 goto l0_%=;				\
+l0_%=:	r0 -= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from const, 2")
+__success __failure_unpriv
+__msg_unpriv("R1 has pointer with unsupported alu operation")
+__retval(1)
+__naked void deducing_bounds_from_const_2(void)
+{
+	asm volatile ("					\
+	r0 = 1;						\
+	if r0 s>= 1 goto l0_%=;				\
+	exit;						\
+l0_%=:	if r0 s<= 1 goto l1_%=;				\
+	exit;						\
+l1_%=:	r1 -= r0;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from const, 3")
+__failure __msg("R0 tried to subtract pointer from scalar")
+__msg_unpriv("R1 has pointer with unsupported alu operation")
+__naked void deducing_bounds_from_const_3(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	if r0 s<= 0 goto l0_%=;				\
+l0_%=:	r0 -= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from const, 4")
+__success __failure_unpriv
+__msg_unpriv("R6 has pointer with unsupported alu operation")
+__retval(0)
+__naked void deducing_bounds_from_const_4(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r0 = 0;						\
+	if r0 s<= 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	if r0 s>= 0 goto l1_%=;				\
+	exit;						\
+l1_%=:	r6 -= r0;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from const, 5")
+__failure __msg("R0 tried to subtract pointer from scalar")
+__msg_unpriv("R1 has pointer with unsupported alu operation")
+__naked void deducing_bounds_from_const_5(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	if r0 s>= 1 goto l0_%=;				\
+	r0 -= r1;					\
+l0_%=:	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from const, 6")
+__failure __msg("R0 tried to subtract pointer from scalar")
+__msg_unpriv("R1 has pointer with unsupported alu operation")
+__naked void deducing_bounds_from_const_6(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	if r0 s>= 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r0 -= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from const, 7")
+__failure __msg("dereference of modified ctx ptr")
+__msg_unpriv("R1 has pointer with unsupported alu operation")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void deducing_bounds_from_const_7(void)
+{
+	asm volatile ("					\
+	r0 = %[__imm_0];				\
+	if r0 s>= 0 goto l0_%=;				\
+l0_%=:	r1 -= r0;					\
+	r0 = *(u32*)(r1 + %[__sk_buff_mark]);		\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, ~0),
+	  __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from const, 8")
+__failure __msg("negative offset ctx ptr R1 off=-1 disallowed")
+__msg_unpriv("R1 has pointer with unsupported alu operation")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void deducing_bounds_from_const_8(void)
+{
+	asm volatile ("					\
+	r0 = %[__imm_0];				\
+	if r0 s>= 0 goto l0_%=;				\
+	r1 += r0;					\
+l0_%=:	r0 = *(u32*)(r1 + %[__sk_buff_mark]);		\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, ~0),
+	  __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from const, 9")
+__failure __msg("R0 tried to subtract pointer from scalar")
+__msg_unpriv("R1 has pointer with unsupported alu operation")
+__naked void deducing_bounds_from_const_9(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	if r0 s>= 0 goto l0_%=;				\
+l0_%=:	r0 -= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from const, 10")
+__failure
+__msg("math between ctx pointer and register with unbounded min value is not allowed")
+__failure_unpriv
+__naked void deducing_bounds_from_const_10(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r0 = 0;						\
+	if r0 s<= 0 goto l0_%=;				\
+l0_%=: /* Marks r0 as unknown. */			\
+	call %[bpf_get_prandom_u32];			\
+	r0 -= r6;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds_deduction_non_const.c b/tools/testing/selftests/bpf/progs/verifier_bounds_deduction_non_const.c
new file mode 100644
index 000000000000..823f727cf210
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_bounds_deduction_non_const.c
@@ -0,0 +1,639 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp64, <non_const> == <const>, 1")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_1(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if r0 < 3 goto l0_%=;				\
+	r2 = 2;						\
+	if r0 == r2 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp64, <non_const> == <const>, 2")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_2(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if r0 > 3 goto l0_%=;				\
+	r2 = 4;						\
+	if r0 == r2 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp64, <non_const> != <const>, 1")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_3(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if r0 < 3 goto l0_%=;				\
+	r2 = 2;						\
+	if r0 != r2 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp64, <non_const> != <const>, 2")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_4(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if r0 > 3 goto l0_%=;				\
+	r2 = 4;						\
+	if r0 != r2 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp32, <non_const> == <const>, 1")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_5(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if w0 < 4 goto l0_%=;				\
+	w2 = 3;						\
+	if w0 == w2 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp32, <non_const> == <const>, 2")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_6(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if w0 > 4 goto l0_%=;				\
+	w2 = 5;						\
+	if w0 == w2 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp32, <non_const> != <const>, 1")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_7(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if w0 < 3 goto l0_%=;				\
+	w2 = 2;						\
+	if w0 != w2 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp32, <non_const> != <const>, 2")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_8(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if w0 > 3 goto l0_%=;				\
+	w2 = 4;						\
+	if w0 != w2 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp64, <const> > <non_const>, 1")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_9(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	r2 = 0;						\
+	if r2 > r0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp64, <const> > <non_const>, 2")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_10(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if r0 < 4 goto l0_%=;				\
+	r2 = 4;						\
+	if r2 > r0 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp64, <const> >= <non_const>")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_11(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if r0 < 4 goto l0_%=;				\
+	r2 = 3;						\
+	if r2 >= r0 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp64, <const> < <non_const>")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_12(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if r0 > 4 goto l0_%=;				\
+	r2 = 4;						\
+	if r2 < r0 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp64, <const> <= <non_const>")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_13(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if r0 >= 4 goto l0_%=;				\
+	r2 = 4;						\
+	if r2 <= r0 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp64, <const> == <non_const>")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_14(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if r0 < 3 goto l0_%=;				\
+	r2 = 2;						\
+	if r2 == r0 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp64, <const> s> <non_const>")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_15(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if r0 s< 4 goto l0_%=;				\
+	r2 = 4;						\
+	if r2 s> r0 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp64, <const> s>= <non_const>")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_16(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if r0 s< 4 goto l0_%=;				\
+	r2 = 3;						\
+	if r2 s>= r0 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp64, <const> s< <non_const>")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_17(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if r0 s> 4 goto l0_%=;				\
+	r2 = 4;						\
+	if r2 s< r0 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp64, <const> s<= <non_const>")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_18(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if r0 s> 4 goto l0_%=;				\
+	r2 = 5;						\
+	if r2 s<= r0 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp64, <const> != <non_const>")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_19(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if r0 < 3 goto l0_%=;				\
+	r2 = 2;						\
+	if r2 != r0 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp32, <const> > <non_const>, 1")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_20(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	w2 = 0;						\
+	if w2 > w0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp32, <const> > <non_const>, 2")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_21(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if w0 < 4 goto l0_%=;				\
+	w2 = 4;						\
+	if w2 > w0 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp32, <const> >= <non_const>")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_22(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if w0 < 4 goto l0_%=;				\
+	w2 = 3;						\
+	if w2 >= w0 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp32, <const> < <non_const>")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_23(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if w0 > 4 goto l0_%=;				\
+	w2 = 4;						\
+	if w2 < w0 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp32, <const> <= <non_const>")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_24(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if w0 >= 4 goto l0_%=;				\
+	w2 = 4;						\
+	if w2 <= w0 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp32, <const> == <non_const>")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_25(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if w0 < 4 goto l0_%=;				\
+	w2 = 3;						\
+	if w2 == w0 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp32, <const> s> <non_const>")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_26(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if w0 s< 4 goto l0_%=;				\
+	w2 = 4;						\
+	if w2 s> w0 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp32, <const> s>= <non_const>")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_27(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if w0 s< 4 goto l0_%=;				\
+	w2 = 3;						\
+	if w2 s>= w0 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp32, <const> s< <non_const>")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_28(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if w0 s> 4 goto l0_%=;				\
+	w2 = 5;						\
+	if w2 s< w0 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp32, <const> s<= <non_const>")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_29(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if w0 s>= 4 goto l0_%=;				\
+	w2 = 4;						\
+	if w2 s<= w0 goto l1_%=;				\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check deducing bounds from non-const, jmp32, <const> != <non_const>")
+__success __retval(0)
+__naked void deducing_bounds_from_non_const_30(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if w0 < 3 goto l0_%=;				\
+	w2 = 2;						\
+	if w2 != w0 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:							\
+	r0 = 0;						\
+	exit;						\
+l1_%=:							\
+	r0 -= r1;					\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds_mix_sign_unsign.c b/tools/testing/selftests/bpf/progs/verifier_bounds_mix_sign_unsign.c
new file mode 100644
index 000000000000..4f40144748a5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_bounds_mix_sign_unsign.c
@@ -0,0 +1,554 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, long long);
+} map_hash_8b SEC(".maps");
+
+SEC("socket")
+__description("bounds checks mixing signed and unsigned, positive bounds")
+__failure __msg("unbounded min value")
+__failure_unpriv
+__naked void signed_and_unsigned_positive_bounds(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	*(u64*)(r10 - 16) = r0;				\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u64*)(r10 - 16);				\
+	r2 = 2;						\
+	if r2 >= r1 goto l0_%=;				\
+	if r1 s> 4 goto l0_%=;				\
+	r0 += r1;					\
+	r1 = 0;						\
+	*(u8*)(r0 + 0) = r1;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds checks mixing signed and unsigned")
+__failure __msg("unbounded min value")
+__failure_unpriv
+__naked void checks_mixing_signed_and_unsigned(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	*(u64*)(r10 - 16) = r0;				\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u64*)(r10 - 16);				\
+	r2 = -1;					\
+	if r1 > r2 goto l0_%=;				\
+	if r1 s> 1 goto l0_%=;				\
+	r0 += r1;					\
+	r1 = 0;						\
+	*(u8*)(r0 + 0) = r1;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds checks mixing signed and unsigned, variant 2")
+__failure __msg("unbounded min value")
+__failure_unpriv
+__naked void signed_and_unsigned_variant_2(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	*(u64*)(r10 - 16) = r0;				\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u64*)(r10 - 16);				\
+	r2 = -1;					\
+	if r1 > r2 goto l0_%=;				\
+	r8 = 0;						\
+	r8 += r1;					\
+	if r8 s> 1 goto l0_%=;				\
+	r0 += r8;					\
+	r0 = 0;						\
+	*(u8*)(r8 + 0) = r0;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds checks mixing signed and unsigned, variant 3")
+__failure __msg("unbounded min value")
+__failure_unpriv
+__naked void signed_and_unsigned_variant_3(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	*(u64*)(r10 - 16) = r0;				\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u64*)(r10 - 16);				\
+	r2 = -1;					\
+	if r1 > r2 goto l0_%=;				\
+	r8 = r1;					\
+	if r8 s> 1 goto l0_%=;				\
+	r0 += r8;					\
+	r0 = 0;						\
+	*(u8*)(r8 + 0) = r0;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds checks mixing signed and unsigned, variant 4")
+__success __success_unpriv __retval(0)
+__naked void signed_and_unsigned_variant_4(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	*(u64*)(r10 - 16) = r0;				\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u64*)(r10 - 16);				\
+	r2 = 1;						\
+	r1 &= r2;					\
+	if r1 s> 1 goto l0_%=;				\
+	r0 += r1;					\
+	r1 = 0;						\
+	*(u8*)(r0 + 0) = r1;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds checks mixing signed and unsigned, variant 5")
+__failure __msg("unbounded min value")
+__failure_unpriv
+__naked void signed_and_unsigned_variant_5(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	*(u64*)(r10 - 16) = r0;				\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u64*)(r10 - 16);				\
+	r2 = -1;					\
+	if r1 > r2 goto l0_%=;				\
+	if r1 s> 1 goto l0_%=;				\
+	r0 += 4;					\
+	r0 -= r1;					\
+	r1 = 0;						\
+	*(u8*)(r0 + 0) = r1;				\
+	r0 = 0;						\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds checks mixing signed and unsigned, variant 6")
+__failure __msg("R4 min value is negative, either use unsigned")
+__failure_unpriv
+__naked void signed_and_unsigned_variant_6(void)
+{
+	asm volatile ("					\
+	r9 = r1;					\
+	call %[bpf_ktime_get_ns];			\
+	*(u64*)(r10 - 16) = r0;				\
+	r1 = r9;					\
+	r2 = 0;						\
+	r3 = r10;					\
+	r3 += -512;					\
+	r4 = *(u64*)(r10 - 16);				\
+	r6 = -1;					\
+	if r4 > r6 goto l0_%=;				\
+	if r4 s> 1 goto l0_%=;				\
+	r4 += 1;					\
+	r5 = 0;						\
+	r6 = 0;						\
+	*(u16*)(r10 - 512) = r6;			\
+	call %[bpf_skb_load_bytes];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm(bpf_skb_load_bytes)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds checks mixing signed and unsigned, variant 7")
+__success __success_unpriv __retval(0)
+__naked void signed_and_unsigned_variant_7(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	*(u64*)(r10 - 16) = r0;				\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u64*)(r10 - 16);				\
+	r2 = %[__imm_0];				\
+	if r1 > r2 goto l0_%=;				\
+	if r1 s> 1 goto l0_%=;				\
+	r0 += r1;					\
+	r1 = 0;						\
+	*(u8*)(r0 + 0) = r1;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b),
+	  __imm_const(__imm_0, 1024 * 1024 * 1024)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds checks mixing signed and unsigned, variant 8")
+__failure __msg("unbounded min value")
+__failure_unpriv
+__naked void signed_and_unsigned_variant_8(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	*(u64*)(r10 - 16) = r0;				\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u64*)(r10 - 16);				\
+	r2 = -1;					\
+	if r2 > r1 goto l1_%=;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	if r1 s> 1 goto l0_%=;				\
+	r0 += r1;					\
+	r1 = 0;						\
+	*(u8*)(r0 + 0) = r1;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds checks mixing signed and unsigned, variant 9")
+__success __success_unpriv __retval(0)
+__naked void signed_and_unsigned_variant_9(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	*(u64*)(r10 - 16) = r0;				\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u64*)(r10 - 16);				\
+	r2 = -9223372036854775808ULL ll;		\
+	if r2 > r1 goto l1_%=;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	if r1 s> 1 goto l0_%=;				\
+	r0 += r1;					\
+	r1 = 0;						\
+	*(u8*)(r0 + 0) = r1;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds checks mixing signed and unsigned, variant 10")
+__failure __msg("unbounded min value")
+__failure_unpriv
+__naked void signed_and_unsigned_variant_10(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	*(u64*)(r10 - 16) = r0;				\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u64*)(r10 - 16);				\
+	r2 = -1;						\
+	if r2 > r1 goto l1_%=;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	if r1 s> 1 goto l0_%=;				\
+	r0 += r1;					\
+	r1 = 0;						\
+	*(u8*)(r0 + 0) = r1;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds checks mixing signed and unsigned, variant 11")
+__failure __msg("unbounded min value")
+__failure_unpriv
+__naked void signed_and_unsigned_variant_11(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	*(u64*)(r10 - 16) = r0;				\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u64*)(r10 - 16);				\
+	r2 = -1;					\
+	if r2 >= r1 goto l1_%=;				\
+	/* Dead branch. */				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	if r1 s> 1 goto l0_%=;				\
+	r0 += r1;					\
+	r1 = 0;						\
+	*(u8*)(r0 + 0) = r1;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds checks mixing signed and unsigned, variant 12")
+__failure __msg("unbounded min value")
+__failure_unpriv
+__naked void signed_and_unsigned_variant_12(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	*(u64*)(r10 - 16) = r0;				\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u64*)(r10 - 16);				\
+	r2 = -6;					\
+	if r2 >= r1 goto l1_%=;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	if r1 s> 1 goto l0_%=;				\
+	r0 += r1;					\
+	r1 = 0;						\
+	*(u8*)(r0 + 0) = r1;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds checks mixing signed and unsigned, variant 13")
+__failure __msg("unbounded min value")
+__failure_unpriv
+__naked void signed_and_unsigned_variant_13(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	*(u64*)(r10 - 16) = r0;				\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u64*)(r10 - 16);				\
+	r2 = 2;						\
+	if r2 >= r1 goto l0_%=;				\
+	r7 = 1;						\
+	if r7 s> 0 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r7 += r1;					\
+	if r7 s> 4 goto l2_%=;				\
+	r0 += r7;					\
+	r1 = 0;						\
+	*(u8*)(r0 + 0) = r1;				\
+l2_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds checks mixing signed and unsigned, variant 14")
+__failure __msg("unbounded min value")
+__failure_unpriv
+__naked void signed_and_unsigned_variant_14(void)
+{
+	asm volatile ("					\
+	r9 = *(u32*)(r1 + %[__sk_buff_mark]);		\
+	call %[bpf_ktime_get_ns];			\
+	*(u64*)(r10 - 16) = r0;				\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u64*)(r10 - 16);				\
+	r2 = -1;					\
+	r8 = 2;						\
+	if r9 == 42 goto l1_%=;				\
+	if r8 s> r1 goto l2_%=;				\
+l3_%=:	if r1 s> 1 goto l2_%=;				\
+	r0 += r1;					\
+l0_%=:	r1 = 0;						\
+	*(u8*)(r0 + 0) = r1;				\
+l2_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	if r1 > r2 goto l2_%=;				\
+	goto l3_%=;					\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b),
+	  __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bounds checks mixing signed and unsigned, variant 15")
+__failure __msg("unbounded min value")
+__failure_unpriv
+__naked void signed_and_unsigned_variant_15(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	*(u64*)(r10 - 16) = r0;				\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u64*)(r10 - 16);				\
+	r2 = -6;					\
+	if r2 >= r1 goto l1_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 += r1;					\
+	if r0 > 1 goto l2_%=;				\
+	r0 = 0;						\
+	exit;						\
+l2_%=:	r1 = 0;						\
+	*(u8*)(r0 + 0) = r1;				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
new file mode 100644
index 000000000000..fb4fa465d67c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_bpf_fastcall.c
@@ -0,0 +1,888 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include "../../../include/linux/filter.h"
+#include "bpf_misc.h"
+#include <stdbool.h>
+#include "bpf_kfuncs.h"
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4) __msg("stack depth 8")
+__xlated("4: r5 = 5")
+__xlated("5: r0 = ")
+__xlated("6: r0 = &(void __percpu *)(r0)")
+__xlated("7: r0 = *(u32 *)(r0 +0)")
+__xlated("8: exit")
+__success
+__naked void simple(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"r2 = 2;"
+	"r3 = 3;"
+	"r4 = 4;"
+	"r5 = 5;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"*(u64 *)(r10 - 24) = r2;"
+	"*(u64 *)(r10 - 32) = r3;"
+	"*(u64 *)(r10 - 40) = r4;"
+	"*(u64 *)(r10 - 48) = r5;"
+	"call %[bpf_get_smp_processor_id];"
+	"r5 = *(u64 *)(r10 - 48);"
+	"r4 = *(u64 *)(r10 - 40);"
+	"r3 = *(u64 *)(r10 - 32);"
+	"r2 = *(u64 *)(r10 - 24);"
+	"r1 = *(u64 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+/* The logic for detecting and verifying bpf_fastcall pattern is the same for
+ * any arch, however x86 differs from arm64 or riscv64 in a way
+ * bpf_get_smp_processor_id is rewritten:
+ * - on x86 it is done by verifier
+ * - on arm64 and riscv64 it is done by jit
+ *
+ * Which leads to different xlated patterns for different archs:
+ * - on x86 the call is expanded as 3 instructions
+ * - on arm64 and riscv64 the call remains as is
+ *   (but spills/fills are still removed)
+ *
+ * It is really desirable to check instruction indexes in the xlated
+ * patterns, so add this canary test to check that function rewrite by
+ * jit is correctly processed by bpf_fastcall logic, keep the rest of the
+ * tests as x86.
+ */
+SEC("raw_tp")
+__arch_arm64
+__arch_riscv64
+__xlated("0: r1 = 1")
+__xlated("1: call bpf_get_smp_processor_id")
+__xlated("2: exit")
+__success
+__naked void canary_arm64_riscv64(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("3: exit")
+__success
+__naked void canary_zero_spills(void)
+{
+	asm volatile (
+	"call %[bpf_get_smp_processor_id];"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4) __msg("stack depth 16")
+__xlated("1: *(u64 *)(r10 -16) = r1")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r2 = *(u64 *)(r10 -16)")
+__success
+__naked void wrong_reg_in_pattern1(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r2 = *(u64 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u64 *)(r10 -16) = r6")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r6 = *(u64 *)(r10 -16)")
+__success
+__naked void wrong_reg_in_pattern2(void)
+{
+	asm volatile (
+	"r6 = 1;"
+	"*(u64 *)(r10 - 16) = r6;"
+	"call %[bpf_get_smp_processor_id];"
+	"r6 = *(u64 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u64 *)(r10 -16) = r0")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r0 = *(u64 *)(r10 -16)")
+__success
+__naked void wrong_reg_in_pattern3(void)
+{
+	asm volatile (
+	"r0 = 1;"
+	"*(u64 *)(r10 - 16) = r0;"
+	"call %[bpf_get_smp_processor_id];"
+	"r0 = *(u64 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("2: *(u64 *)(r2 -16) = r1")
+__xlated("...")
+__xlated("4: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("6: r1 = *(u64 *)(r10 -16)")
+__success
+__naked void wrong_base_in_pattern(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"r2 = r10;"
+	"*(u64 *)(r2 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u64 *)(r10 -16) = r1")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r2 = 1")
+__success
+__naked void wrong_insn_in_pattern(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r2 = 1;"
+	"r1 = *(u64 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("2: *(u64 *)(r10 -16) = r1")
+__xlated("...")
+__xlated("4: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("6: r1 = *(u64 *)(r10 -8)")
+__success
+__naked void wrong_off_in_pattern1(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u32 *)(r10 -4) = r1")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r1 = *(u32 *)(r10 -4)")
+__success
+__naked void wrong_off_in_pattern2(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u32 *)(r10 - 4) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u32 *)(r10 - 4);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u32 *)(r10 -16) = r1")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r1 = *(u32 *)(r10 -16)")
+__success
+__naked void wrong_size_in_pattern(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u32 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u32 *)(r10 - 16);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("2: *(u32 *)(r10 -8) = r1")
+__xlated("...")
+__xlated("4: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("6: r1 = *(u32 *)(r10 -8)")
+__success
+__naked void partial_pattern(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"r2 = 2;"
+	"*(u32 *)(r10 - 8) = r1;"
+	"*(u64 *)(r10 - 16) = r2;"
+	"call %[bpf_get_smp_processor_id];"
+	"r2 = *(u64 *)(r10 - 16);"
+	"r1 = *(u32 *)(r10 - 8);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("0: r1 = 1")
+__xlated("1: r2 = 2")
+/* not patched, spills for -8, -16 not removed */
+__xlated("2: *(u64 *)(r10 -8) = r1")
+__xlated("3: *(u64 *)(r10 -16) = r2")
+__xlated("...")
+__xlated("5: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("7: r2 = *(u64 *)(r10 -16)")
+__xlated("8: r1 = *(u64 *)(r10 -8)")
+/* patched, spills for -24, -32 removed */
+__xlated("...")
+__xlated("10: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("12: exit")
+__success
+__naked void min_stack_offset(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"r2 = 2;"
+	/* this call won't be patched */
+	"*(u64 *)(r10 - 8) = r1;"
+	"*(u64 *)(r10 - 16) = r2;"
+	"call %[bpf_get_smp_processor_id];"
+	"r2 = *(u64 *)(r10 - 16);"
+	"r1 = *(u64 *)(r10 - 8);"
+	/* this call would be patched */
+	"*(u64 *)(r10 - 24) = r1;"
+	"*(u64 *)(r10 - 32) = r2;"
+	"call %[bpf_get_smp_processor_id];"
+	"r2 = *(u64 *)(r10 - 32);"
+	"r1 = *(u64 *)(r10 - 24);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u64 *)(r10 -8) = r1")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r1 = *(u64 *)(r10 -8)")
+__success
+__naked void bad_fixed_read(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"r1 = r10;"
+	"r1 += -8;"
+	"r1 = *(u64 *)(r1 - 0);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u64 *)(r10 -8) = r1")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r1 = *(u64 *)(r10 -8)")
+__success
+__naked void bad_fixed_write(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"r1 = r10;"
+	"r1 += -8;"
+	"*(u64 *)(r1 - 0) = r1;"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("6: *(u64 *)(r10 -16) = r1")
+__xlated("...")
+__xlated("8: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("10: r1 = *(u64 *)(r10 -16)")
+__success
+__naked void bad_varying_read(void)
+{
+	asm volatile (
+	"r6 = *(u64 *)(r1 + 0);" /* random scalar value */
+	"r6 &= 0x7;"		 /* r6 range [0..7] */
+	"r6 += 0x2;"		 /* r6 range [2..9] */
+	"r7 = 0;"
+	"r7 -= r6;"		 /* r7 range [-9..-2] */
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"r1 = r10;"
+	"r1 += r7;"
+	"r1 = *(u8 *)(r1 - 0);" /* touches slot [-16..-9] where spills are stored */
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("6: *(u64 *)(r10 -16) = r1")
+__xlated("...")
+__xlated("8: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("10: r1 = *(u64 *)(r10 -16)")
+__success
+__naked void bad_varying_write(void)
+{
+	asm volatile (
+	"r6 = *(u64 *)(r1 + 0);" /* random scalar value */
+	"r6 &= 0x7;"		 /* r6 range [0..7] */
+	"r6 += 0x2;"		 /* r6 range [2..9] */
+	"r7 = 0;"
+	"r7 -= r6;"		 /* r7 range [-9..-2] */
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"r1 = r10;"
+	"r1 += r7;"
+	"*(u8 *)(r1 - 0) = r7;" /* touches slot [-16..-9] where spills are stored */
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u64 *)(r10 -8) = r1")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r1 = *(u64 *)(r10 -8)")
+__success
+__naked void bad_write_in_subprog(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"r1 = r10;"
+	"r1 += -8;"
+	"call bad_write_in_subprog_aux;"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+__used
+__naked static void bad_write_in_subprog_aux(void)
+{
+	asm volatile (
+	"r0 = 1;"
+	"*(u64 *)(r1 - 0) = r0;"	/* invalidates bpf_fastcall contract for caller: */
+	"exit;"				/* caller stack at -8 used outside of the pattern */
+	::: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__xlated("1: *(u64 *)(r10 -8) = r1")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r1 = *(u64 *)(r10 -8)")
+__success
+__naked void bad_helper_write(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	/* bpf_fastcall pattern with stack offset -8 */
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"r1 = r10;"
+	"r1 += -8;"
+	"r2 = 1;"
+	"r3 = 42;"
+	/* read dst is fp[-8], thus bpf_fastcall rewrite not applied */
+	"call %[bpf_probe_read_kernel];"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id),
+	  __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+/* main, not patched */
+__xlated("1: *(u64 *)(r10 -8) = r1")
+__xlated("...")
+__xlated("3: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("5: r1 = *(u64 *)(r10 -8)")
+__xlated("...")
+__xlated("9: call pc+1")
+__xlated("...")
+__xlated("10: exit")
+/* subprogram, patched */
+__xlated("11: r1 = 1")
+__xlated("...")
+__xlated("13: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("15: exit")
+__success
+__naked void invalidate_one_subprog(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"r1 = r10;"
+	"r1 += -8;"
+	"r1 = *(u64 *)(r1 - 0);"
+	"call invalidate_one_subprog_aux;"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+__used
+__naked static void invalidate_one_subprog_aux(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+/* main */
+__xlated("0: r1 = 1")
+__xlated("...")
+__xlated("2: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("4: call pc+1")
+__xlated("5: exit")
+/* subprogram */
+__xlated("6: r1 = 1")
+__xlated("...")
+__xlated("8: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+__xlated("10: *(u64 *)(r10 -16) = r1")
+__xlated("11: exit")
+__success
+__naked void subprogs_use_independent_offsets(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"call subprogs_use_independent_offsets_aux;"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+__used
+__naked static void subprogs_use_independent_offsets_aux(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 24) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 24);"
+	"*(u64 *)(r10 - 16) = r1;"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4) __msg("stack depth 8")
+__xlated("2: r0 = &(void __percpu *)(r0)")
+__success
+__naked void helper_call_does_not_prevent_bpf_fastcall(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_prandom_u32];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id),
+	  __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4) __msg("stack depth 24")
+/* may_goto counter at -24 */
+__xlated("0: *(u64 *)(r10 -24) =")
+/* may_goto timestamp at -16 */
+__xlated("1: *(u64 *)(r10 -16) =")
+__xlated("2: r1 = 1")
+__xlated("...")
+__xlated("4: r0 = &(void __percpu *)(r0)")
+__xlated("...")
+/* may_goto expansion starts */
+__xlated("6: r11 = *(u64 *)(r10 -24)")
+__xlated("7: if r11 == 0x0 goto pc+6")
+__xlated("8: r11 -= 1")
+__xlated("9: if r11 != 0x0 goto pc+2")
+__xlated("10: r11 = -24")
+__xlated("11: call unknown")
+__xlated("12: *(u64 *)(r10 -24) = r11")
+/* may_goto expansion ends */
+__xlated("13: *(u64 *)(r10 -8) = r1")
+__xlated("14: exit")
+__success
+__naked void may_goto_interaction_x86_64(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	".8byte %[may_goto];"
+	/* just touch some stack at -8 */
+	"*(u64 *)(r10 - 8) = r1;"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id),
+	  __imm_insn(may_goto, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, +1 /* offset */, 0))
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_arm64
+__log_level(4) __msg("stack depth 24")
+/* may_goto counter at -24 */
+__xlated("0: *(u64 *)(r10 -24) =")
+/* may_goto timestamp at -16 */
+__xlated("1: *(u64 *)(r10 -16) =")
+__xlated("2: r1 = 1")
+__xlated("3: call bpf_get_smp_processor_id")
+/* may_goto expansion starts */
+__xlated("4: r11 = *(u64 *)(r10 -24)")
+__xlated("5: if r11 == 0x0 goto pc+6")
+__xlated("6: r11 -= 1")
+__xlated("7: if r11 != 0x0 goto pc+2")
+__xlated("8: r11 = -24")
+__xlated("9: call unknown")
+__xlated("10: *(u64 *)(r10 -24) = r11")
+/* may_goto expansion ends */
+__xlated("11: *(u64 *)(r10 -8) = r1")
+__xlated("12: exit")
+__success
+__naked void may_goto_interaction_arm64(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	".8byte %[may_goto];"
+	/* just touch some stack at -8 */
+	"*(u64 *)(r10 - 8) = r1;"
+	"exit;"
+	:
+	: __imm(bpf_get_smp_processor_id),
+	  __imm_insn(may_goto, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, +1 /* offset */, 0))
+	: __clobber_all);
+}
+
+__used
+__naked static void dummy_loop_callback(void)
+{
+	asm volatile (
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4) __msg("stack depth 32+0")
+__xlated("2: r1 = 1")
+__xlated("3: r0 =")
+__xlated("4: r0 = &(void __percpu *)(r0)")
+__xlated("5: r0 = *(u32 *)(r0 +0)")
+/* bpf_loop params setup */
+__xlated("6: r2 =")
+__xlated("7: r3 = 0")
+__xlated("8: r4 = 0")
+__xlated("...")
+/* ... part of the inlined bpf_loop */
+__xlated("12: *(u64 *)(r10 -32) = r6")
+__xlated("13: *(u64 *)(r10 -24) = r7")
+__xlated("14: *(u64 *)(r10 -16) = r8")
+__xlated("...")
+__xlated("21: call pc+8") /* dummy_loop_callback */
+/* ... last insns of the bpf_loop_interaction1 */
+__xlated("...")
+__xlated("28: r0 = 0")
+__xlated("29: exit")
+/* dummy_loop_callback */
+__xlated("30: r0 = 0")
+__xlated("31: exit")
+__success
+__naked int bpf_loop_interaction1(void)
+{
+	asm volatile (
+	"r1 = 1;"
+	/* bpf_fastcall stack region at -16, but could be removed */
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"r2 = %[dummy_loop_callback];"
+	"r3 = 0;"
+	"r4 = 0;"
+	"call %[bpf_loop];"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_ptr(dummy_loop_callback),
+	  __imm(bpf_get_smp_processor_id),
+	  __imm(bpf_loop)
+	: __clobber_common
+	);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4) __msg("stack depth 40+0")
+/* call bpf_get_smp_processor_id */
+__xlated("2: r1 = 42")
+__xlated("3: r0 =")
+__xlated("4: r0 = &(void __percpu *)(r0)")
+__xlated("5: r0 = *(u32 *)(r0 +0)")
+/* call bpf_get_prandom_u32 */
+__xlated("6: *(u64 *)(r10 -16) = r1")
+__xlated("7: call")
+__xlated("8: r1 = *(u64 *)(r10 -16)")
+__xlated("...")
+/* ... part of the inlined bpf_loop */
+__xlated("15: *(u64 *)(r10 -40) = r6")
+__xlated("16: *(u64 *)(r10 -32) = r7")
+__xlated("17: *(u64 *)(r10 -24) = r8")
+__success
+__naked int bpf_loop_interaction2(void)
+{
+	asm volatile (
+	"r1 = 42;"
+	/* bpf_fastcall stack region at -16, cannot be removed */
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"*(u64 *)(r10 - 16) = r1;"
+	"call %[bpf_get_prandom_u32];"
+	"r1 = *(u64 *)(r10 - 16);"
+	"r2 = %[dummy_loop_callback];"
+	"r3 = 0;"
+	"r4 = 0;"
+	"call %[bpf_loop];"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_ptr(dummy_loop_callback),
+	  __imm(bpf_get_smp_processor_id),
+	  __imm(bpf_get_prandom_u32),
+	  __imm(bpf_loop)
+	: __clobber_common
+	);
+}
+
+SEC("raw_tp")
+__arch_x86_64
+__log_level(4)
+__msg("stack depth 512+0")
+/* just to print xlated version when debugging */
+__xlated("r0 = &(void __percpu *)(r0)")
+__success
+/* cumulative_stack_depth() stack usage is MAX_BPF_STACK,
+ * called subprogram uses an additional slot for bpf_fastcall spill/fill,
+ * since bpf_fastcall spill/fill could be removed the program still fits
+ * in MAX_BPF_STACK and should be accepted.
+ */
+__naked int cumulative_stack_depth(void)
+{
+	asm volatile(
+	"r1 = 42;"
+	"*(u64 *)(r10 - %[max_bpf_stack]) = r1;"
+	"call cumulative_stack_depth_subprog;"
+	"exit;"
+	:
+	: __imm_const(max_bpf_stack, MAX_BPF_STACK)
+	: __clobber_all
+	);
+}
+
+__used
+__naked static void cumulative_stack_depth_subprog(void)
+{
+	asm volatile (
+	"*(u64 *)(r10 - 8) = r1;"
+	"call %[bpf_get_smp_processor_id];"
+	"r1 = *(u64 *)(r10 - 8);"
+	"exit;"
+	:: __imm(bpf_get_smp_processor_id) : __clobber_all);
+}
+
+SEC("cgroup/getsockname_unix")
+__xlated("0: r2 = 1")
+/* bpf_cast_to_kern_ctx is replaced by a single assignment */
+__xlated("1: r0 = r1")
+__xlated("2: r0 = r2")
+__xlated("3: exit")
+__success
+__naked void kfunc_bpf_cast_to_kern_ctx(void)
+{
+	asm volatile (
+	"r2 = 1;"
+	"*(u64 *)(r10 - 32) = r2;"
+	"call %[bpf_cast_to_kern_ctx];"
+	"r2 = *(u64 *)(r10 - 32);"
+	"r0 = r2;"
+	"exit;"
+	:
+	: __imm(bpf_cast_to_kern_ctx)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__xlated("3: r3 = 1")
+/* bpf_rdonly_cast is replaced by a single assignment */
+__xlated("4: r0 = r1")
+__xlated("5: r0 = r3")
+void kfunc_bpf_rdonly_cast(void)
+{
+	asm volatile (
+	"r2 = %[btf_id];"
+	"r3 = 1;"
+	"*(u64 *)(r10 - 32) = r3;"
+	"call %[bpf_rdonly_cast];"
+	"r3 = *(u64 *)(r10 - 32);"
+	"r0 = r3;"
+	:
+	: __imm(bpf_rdonly_cast),
+	 [btf_id]"r"(bpf_core_type_id_kernel(union bpf_attr))
+	: __clobber_common);
+}
+
+/* BTF FUNC records are not generated for kfuncs referenced
+ * from inline assembly. These records are necessary for
+ * libbpf to link the program. The function below is a hack
+ * to ensure that BTF FUNC records are generated.
+ */
+void kfunc_root(void)
+{
+	bpf_cast_to_kern_ctx(0);
+	bpf_rdonly_cast(0, 0);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_bpf_get_stack.c b/tools/testing/selftests/bpf/progs/verifier_bpf_get_stack.c
new file mode 100644
index 000000000000..325a2bab4a71
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_bpf_get_stack.c
@@ -0,0 +1,124 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/bpf_get_stack.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#define MAX_ENTRIES 11
+
+struct test_val {
+	unsigned int index;
+	int foo[MAX_ENTRIES];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct test_val);
+} map_array_48b SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, struct test_val);
+} map_hash_48b SEC(".maps");
+
+SEC("tracepoint")
+__description("bpf_get_stack return R0 within range")
+__success
+__naked void stack_return_r0_within_range(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r7 = r0;					\
+	r9 = %[__imm_0];				\
+	r1 = r6;					\
+	r2 = r7;					\
+	r3 = %[__imm_0];				\
+	r4 = 256;					\
+	call %[bpf_get_stack];				\
+	r1 = 0;						\
+	r8 = r0;					\
+	r8 <<= 32;					\
+	r8 s>>= 32;					\
+	if r1 s> r8 goto l0_%=;				\
+	r9 -= r8;					\
+	r2 = r7;					\
+	r2 += r8;					\
+	r1 = r9;					\
+	r1 <<= 32;					\
+	r1 s>>= 32;					\
+	r3 = r2;					\
+	r3 += r1;					\
+	r1 = r7;					\
+	r5 = %[__imm_0];				\
+	r1 += r5;					\
+	if r3 >= r1 goto l0_%=;				\
+	r1 = r6;					\
+	r3 = r9;					\
+	r4 = 0;						\
+	call %[bpf_get_stack];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_get_stack),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(__imm_0, sizeof(struct test_val) / 2)
+	: __clobber_all);
+}
+
+SEC("iter/task")
+__description("bpf_get_task_stack return R0 range is refined")
+__success
+__naked void return_r0_range_is_refined(void)
+{
+	asm volatile ("					\
+	r6 = *(u64*)(r1 + 0);				\
+	r6 = *(u64*)(r6 + 0);		/* ctx->meta->seq */\
+	r7 = *(u64*)(r1 + 8);		/* ctx->task */\
+	r1 = %[map_array_48b] ll;	/* fixup_map_array_48b */\
+	r2 = 0;						\
+	*(u64*)(r10 - 8) = r2;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	if r7 != 0 goto l1_%=;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	r1 = r7;					\
+	r2 = r0;					\
+	r9 = r0;			/* keep buf for seq_write */\
+	r3 = 48;					\
+	r4 = 0;						\
+	call %[bpf_get_task_stack];			\
+	if r0 s> 0 goto l2_%=;				\
+	r0 = 0;						\
+	exit;						\
+l2_%=:	r1 = r6;					\
+	r2 = r9;					\
+	r3 = r0;					\
+	call %[bpf_seq_write];				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_task_stack),
+	  __imm(bpf_map_lookup_elem),
+	  __imm(bpf_seq_write),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_bpf_trap.c b/tools/testing/selftests/bpf/progs/verifier_bpf_trap.c
new file mode 100644
index 000000000000..35e2cdc00a01
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_bpf_trap.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#if __clang_major__ >= 21 && 0
+SEC("socket")
+__description("__builtin_trap with simple c code")
+__failure __msg("unexpected __bpf_trap() due to uninitialized variable?")
+void bpf_builtin_trap_with_simple_c(void)
+{
+	__builtin_trap();
+}
+#endif
+
+SEC("socket")
+__description("__bpf_trap with simple c code")
+__failure __msg("unexpected __bpf_trap() due to uninitialized variable?")
+void bpf_trap_with_simple_c(void)
+{
+	__bpf_trap();
+}
+
+SEC("socket")
+__description("__bpf_trap as the second-from-last insn")
+__failure __msg("unexpected __bpf_trap() due to uninitialized variable?")
+__naked void bpf_trap_at_func_end(void)
+{
+	asm volatile (
+	"r0 = 0;"
+	"call %[__bpf_trap];"
+	"exit;"
+	:
+	: __imm(__bpf_trap)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("dead code __bpf_trap in the middle of code")
+__success
+__naked void dead_bpf_trap_in_middle(void)
+{
+	asm volatile (
+	"r0 = 0;"
+	"if r0 == 0 goto +1;"
+	"call %[__bpf_trap];"
+	"r0 = 2;"
+	"exit;"
+	:
+	: __imm(__bpf_trap)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("reachable __bpf_trap in the middle of code")
+__failure __msg("unexpected __bpf_trap() due to uninitialized variable?")
+__naked void live_bpf_trap_in_middle(void)
+{
+	asm volatile (
+	"r0 = 0;"
+	"if r0 == 1 goto +1;"
+	"call %[__bpf_trap];"
+	"r0 = 2;"
+	"exit;"
+	:
+	: __imm(__bpf_trap)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_bswap.c b/tools/testing/selftests/bpf/progs/verifier_bswap.c
new file mode 100644
index 000000000000..e61755656e8d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_bswap.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
+	defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390) || \
+	defined(__TARGET_ARCH_loongarch)) && \
+	__clang_major__ >= 18
+
+SEC("socket")
+__description("BSWAP, 16")
+__success __success_unpriv __retval(0x23ff)
+__naked void bswap_16(void)
+{
+	asm volatile ("					\
+	r0 = 0xff23;					\
+	r0 = bswap16 r0;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("BSWAP, 32")
+__success __success_unpriv __retval(0x23ff0000)
+__naked void bswap_32(void)
+{
+	asm volatile ("					\
+	r0 = 0xff23;					\
+	r0 = bswap32 r0;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("BSWAP, 64")
+__success __success_unpriv __retval(0x34ff12ff)
+__naked void bswap_64(void)
+{
+	asm volatile ("					\
+	r0 = %[u64_val] ll;					\
+	r0 = bswap64 r0;				\
+	exit;						\
+"	:
+	: [u64_val]"i"(0xff12ff34ff56ff78ull)
+	: __clobber_all);
+}
+
+#else
+
+SEC("socket")
+__description("cpuv4 is not supported by compiler or jit, use a dummy test")
+__success
+int dummy_test(void)
+{
+	return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c b/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c
new file mode 100644
index 000000000000..03942cec07e5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_btf_ctx_access.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/btf_ctx_access.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("fentry/bpf_modify_return_test")
+__description("btf_ctx_access accept")
+__success __retval(0)
+__naked void btf_ctx_access_accept(void)
+{
+	asm volatile ("					\
+	r2 = *(u64 *)(r1 + 8);		/* load 2nd argument value (int pointer) */\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("fentry/bpf_fentry_test9")
+__description("btf_ctx_access u32 pointer accept")
+__success __retval(0)
+__naked void ctx_access_u32_pointer_accept(void)
+{
+	asm volatile ("					\
+	r2 = *(u64 *)(r1 + 0);		/* load 1nd argument value (u32 pointer) */\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("fentry/bpf_fentry_test9")
+__description("btf_ctx_access u32 pointer reject u32")
+__failure __msg("size 4 must be 8")
+__naked void ctx_access_u32_pointer_reject_32(void)
+{
+	asm volatile ("					\
+	r2 = *(u32 *)(r1 + 0);		/* load 1st argument with narrow load */\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("fentry/bpf_fentry_test9")
+__description("btf_ctx_access u32 pointer reject u16")
+__failure __msg("size 2 must be 8")
+__naked void ctx_access_u32_pointer_reject_16(void)
+{
+	asm volatile ("					\
+	r2 = *(u16 *)(r1 + 0);		/* load 1st argument with narrow load */\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("fentry/bpf_fentry_test9")
+__description("btf_ctx_access u32 pointer reject u8")
+__failure __msg("size 1 must be 8")
+__naked void ctx_access_u32_pointer_reject_8(void)
+{
+	asm volatile ("					\
+	r2 = *(u8 *)(r1 + 0);		/* load 1st argument with narrow load */\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("fentry/bpf_fentry_test10")
+__description("btf_ctx_access const void pointer accept")
+__success __retval(0)
+__naked void ctx_access_const_void_pointer_accept(void)
+{
+	asm volatile ("					\
+	r2 = *(u64 *)(r1 + 0);		/* load 1st argument value (const void pointer) */\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_btf_unreliable_prog.c b/tools/testing/selftests/bpf/progs/verifier_btf_unreliable_prog.c
new file mode 100644
index 000000000000..36e033a2e02c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_btf_unreliable_prog.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2017 Facebook
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_misc.h"
+
+struct whatever {};
+
+SEC("kprobe")
+__success __log_level(2)
+/* context type is wrong, making it impossible to freplace this program */
+int btf_unreliable_kprobe(struct whatever *ctx)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_cfg.c b/tools/testing/selftests/bpf/progs/verifier_cfg.c
new file mode 100644
index 000000000000..c1f55e1d80a4
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_cfg.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/cfg.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("socket")
+__description("unreachable")
+__failure __msg("unreachable")
+__failure_unpriv
+__naked void unreachable(void)
+{
+	asm volatile ("					\
+	exit;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unreachable2")
+__failure __msg("unreachable")
+__failure_unpriv
+__naked void unreachable2(void)
+{
+	asm volatile ("					\
+	goto l0_%=;					\
+	goto l0_%=;					\
+l0_%=:	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("out of range jump")
+__failure __msg("jump out of range")
+__failure_unpriv
+__naked void out_of_range_jump(void)
+{
+	asm volatile ("					\
+	goto l0_%=;					\
+	exit;						\
+l0_%=:							\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("out of range jump2")
+__failure __msg("jump out of range")
+__failure_unpriv
+__naked void out_of_range_jump2(void)
+{
+	asm volatile ("					\
+	goto -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("loop (back-edge)")
+__failure __msg("unreachable insn 1")
+__msg_unpriv("back-edge")
+__naked void loop_back_edge(void)
+{
+	asm volatile ("					\
+l0_%=:	goto l0_%=;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("loop2 (back-edge)")
+__failure __msg("unreachable insn 4")
+__msg_unpriv("back-edge")
+__naked void loop2_back_edge(void)
+{
+	asm volatile ("					\
+l0_%=:	r1 = r0;					\
+	r2 = r0;					\
+	r3 = r0;					\
+	goto l0_%=;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("conditional loop")
+__failure __msg("infinite loop detected")
+__msg_unpriv("back-edge")
+__naked void conditional_loop(void)
+{
+	asm volatile ("					\
+	r0 = r1;					\
+l0_%=:	r2 = r0;					\
+	r3 = r0;					\
+	if r1 == 0 goto l0_%=;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("conditional loop (2)")
+__success
+__failure_unpriv __msg_unpriv("back-edge from insn 10 to 11")
+__naked void conditional_loop2(void)
+{
+	asm volatile ("					\
+	r9 = 2 ll;					\
+	r3 = 0x20 ll;					\
+	r4 = 0x35 ll;					\
+	r8 = r4;					\
+	goto l1_%=;					\
+l0_%=:	r9 -= r3;					\
+	r9 -= r4;					\
+	r9 -= r8;					\
+l1_%=:	r8 += r4;					\
+	if r8 < 0x64 goto l0_%=;			\
+	r0 = r9;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unconditional loop after conditional jump")
+__failure __msg("infinite loop detected")
+__failure_unpriv __msg_unpriv("back-edge from insn 3 to 2")
+__naked void uncond_loop_after_cond_jmp(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	if r0 > 0 goto l1_%=;				\
+l0_%=:	r0 = 1;						\
+	goto l0_%=;					\
+l1_%=:	exit;						\
+"	::: __clobber_all);
+}
+
+
+__naked __noinline __used
+static unsigned long never_ending_subprog()
+{
+	asm volatile ("					\
+	r0 = r1;					\
+	goto -1;					\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unconditional loop after conditional jump")
+/* infinite loop is detected *after* check_cfg() */
+__failure __msg("infinite loop detected")
+__naked void uncond_loop_in_subprog_after_cond_jmp(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	if r0 > 0 goto l1_%=;				\
+l0_%=:	r0 += 1;					\
+	call never_ending_subprog;			\
+l1_%=:	exit;						\
+"	::: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_cgroup_inv_retcode.c b/tools/testing/selftests/bpf/progs/verifier_cgroup_inv_retcode.c
new file mode 100644
index 000000000000..6e0f349f8f15
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_cgroup_inv_retcode.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/cgroup_inv_retcode.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("cgroup/sock")
+__description("bpf_exit with invalid return code. test1")
+__failure __msg("smin=0 smax=4294967295 should have been in [0, 1]")
+__naked void with_invalid_return_code_test1(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + 0);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("cgroup/sock")
+__description("bpf_exit with invalid return code. test2")
+__success
+__naked void with_invalid_return_code_test2(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + 0);				\
+	r0 &= 1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("cgroup/sock")
+__description("bpf_exit with invalid return code. test3")
+__failure __msg("smin=0 smax=3 should have been in [0, 1]")
+__naked void with_invalid_return_code_test3(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + 0);				\
+	r0 &= 3;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("cgroup/sock")
+__description("bpf_exit with invalid return code. test4")
+__success
+__naked void with_invalid_return_code_test4(void)
+{
+	asm volatile ("					\
+	r0 = 1;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("cgroup/sock")
+__description("bpf_exit with invalid return code. test5")
+__failure __msg("smin=2 smax=2 should have been in [0, 1]")
+__naked void with_invalid_return_code_test5(void)
+{
+	asm volatile ("					\
+	r0 = 2;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("cgroup/sock")
+__description("bpf_exit with invalid return code. test6")
+__failure __msg("R0 is not a known value (ctx)")
+__naked void with_invalid_return_code_test6(void)
+{
+	asm volatile ("					\
+	r0 = r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("cgroup/sock")
+__description("bpf_exit with invalid return code. test7")
+__failure __msg("R0 has unknown scalar value should have been in [0, 1]")
+__naked void with_invalid_return_code_test7(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + 0);				\
+	r2 = *(u32*)(r1 + 4);				\
+	r0 *= r2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_cgroup_skb.c b/tools/testing/selftests/bpf/progs/verifier_cgroup_skb.c
new file mode 100644
index 000000000000..5ee3d349d6d0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_cgroup_skb.c
@@ -0,0 +1,227 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/cgroup_skb.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("cgroup/skb")
+__description("direct packet read test#1 for CGROUP_SKB")
+__success __failure_unpriv
+__msg_unpriv("invalid bpf_context access off=76 size=4")
+__retval(0)
+__naked void test_1_for_cgroup_skb(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r4 = *(u32*)(r1 + %[__sk_buff_len]);		\
+	r5 = *(u32*)(r1 + %[__sk_buff_pkt_type]);	\
+	r6 = *(u32*)(r1 + %[__sk_buff_mark]);		\
+	*(u32*)(r1 + %[__sk_buff_mark]) = r6;		\
+	r7 = *(u32*)(r1 + %[__sk_buff_queue_mapping]);	\
+	r8 = *(u32*)(r1 + %[__sk_buff_protocol]);	\
+	r9 = *(u32*)(r1 + %[__sk_buff_vlan_present]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r0 > r3 goto l0_%=;				\
+	r0 = *(u8*)(r2 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)),
+	  __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)),
+	  __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)),
+	  __imm_const(__sk_buff_pkt_type, offsetof(struct __sk_buff, pkt_type)),
+	  __imm_const(__sk_buff_protocol, offsetof(struct __sk_buff, protocol)),
+	  __imm_const(__sk_buff_queue_mapping, offsetof(struct __sk_buff, queue_mapping)),
+	  __imm_const(__sk_buff_vlan_present, offsetof(struct __sk_buff, vlan_present))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("direct packet read test#2 for CGROUP_SKB")
+__success __success_unpriv __retval(0)
+__naked void test_2_for_cgroup_skb(void)
+{
+	asm volatile ("					\
+	r4 = *(u32*)(r1 + %[__sk_buff_vlan_tci]);	\
+	r5 = *(u32*)(r1 + %[__sk_buff_vlan_proto]);	\
+	r6 = *(u32*)(r1 + %[__sk_buff_priority]);	\
+	*(u32*)(r1 + %[__sk_buff_priority]) = r6;	\
+	r7 = *(u32*)(r1 + %[__sk_buff_ingress_ifindex]);\
+	r8 = *(u32*)(r1 + %[__sk_buff_tc_index]);	\
+	r9 = *(u32*)(r1 + %[__sk_buff_hash]);		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_hash, offsetof(struct __sk_buff, hash)),
+	  __imm_const(__sk_buff_ingress_ifindex, offsetof(struct __sk_buff, ingress_ifindex)),
+	  __imm_const(__sk_buff_priority, offsetof(struct __sk_buff, priority)),
+	  __imm_const(__sk_buff_tc_index, offsetof(struct __sk_buff, tc_index)),
+	  __imm_const(__sk_buff_vlan_proto, offsetof(struct __sk_buff, vlan_proto)),
+	  __imm_const(__sk_buff_vlan_tci, offsetof(struct __sk_buff, vlan_tci))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("direct packet read test#3 for CGROUP_SKB")
+__success __success_unpriv __retval(0)
+__naked void test_3_for_cgroup_skb(void)
+{
+	asm volatile ("					\
+	r4 = *(u32*)(r1 + %[__sk_buff_cb_0]);		\
+	r5 = *(u32*)(r1 + %[__sk_buff_cb_1]);		\
+	r6 = *(u32*)(r1 + %[__sk_buff_cb_2]);		\
+	r7 = *(u32*)(r1 + %[__sk_buff_cb_3]);		\
+	r8 = *(u32*)(r1 + %[__sk_buff_cb_4]);		\
+	r9 = *(u32*)(r1 + %[__sk_buff_napi_id]);	\
+	*(u32*)(r1 + %[__sk_buff_cb_0]) = r4;		\
+	*(u32*)(r1 + %[__sk_buff_cb_1]) = r5;		\
+	*(u32*)(r1 + %[__sk_buff_cb_2]) = r6;		\
+	*(u32*)(r1 + %[__sk_buff_cb_3]) = r7;		\
+	*(u32*)(r1 + %[__sk_buff_cb_4]) = r8;		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_cb_0, offsetof(struct __sk_buff, cb[0])),
+	  __imm_const(__sk_buff_cb_1, offsetof(struct __sk_buff, cb[1])),
+	  __imm_const(__sk_buff_cb_2, offsetof(struct __sk_buff, cb[2])),
+	  __imm_const(__sk_buff_cb_3, offsetof(struct __sk_buff, cb[3])),
+	  __imm_const(__sk_buff_cb_4, offsetof(struct __sk_buff, cb[4])),
+	  __imm_const(__sk_buff_napi_id, offsetof(struct __sk_buff, napi_id))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("direct packet read test#4 for CGROUP_SKB")
+__success __success_unpriv __retval(0)
+__naked void test_4_for_cgroup_skb(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_family]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_remote_ip4]);	\
+	r4 = *(u32*)(r1 + %[__sk_buff_local_ip4]);	\
+	r5 = *(u32*)(r1 + %[__sk_buff_remote_ip6_0]);	\
+	r5 = *(u32*)(r1 + %[__sk_buff_remote_ip6_1]);	\
+	r5 = *(u32*)(r1 + %[__sk_buff_remote_ip6_2]);	\
+	r5 = *(u32*)(r1 + %[__sk_buff_remote_ip6_3]);	\
+	r6 = *(u32*)(r1 + %[__sk_buff_local_ip6_0]);	\
+	r6 = *(u32*)(r1 + %[__sk_buff_local_ip6_1]);	\
+	r6 = *(u32*)(r1 + %[__sk_buff_local_ip6_2]);	\
+	r6 = *(u32*)(r1 + %[__sk_buff_local_ip6_3]);	\
+	r7 = *(u32*)(r1 + %[__sk_buff_remote_port]);	\
+	r8 = *(u32*)(r1 + %[__sk_buff_local_port]);	\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_family, offsetof(struct __sk_buff, family)),
+	  __imm_const(__sk_buff_local_ip4, offsetof(struct __sk_buff, local_ip4)),
+	  __imm_const(__sk_buff_local_ip6_0, offsetof(struct __sk_buff, local_ip6[0])),
+	  __imm_const(__sk_buff_local_ip6_1, offsetof(struct __sk_buff, local_ip6[1])),
+	  __imm_const(__sk_buff_local_ip6_2, offsetof(struct __sk_buff, local_ip6[2])),
+	  __imm_const(__sk_buff_local_ip6_3, offsetof(struct __sk_buff, local_ip6[3])),
+	  __imm_const(__sk_buff_local_port, offsetof(struct __sk_buff, local_port)),
+	  __imm_const(__sk_buff_remote_ip4, offsetof(struct __sk_buff, remote_ip4)),
+	  __imm_const(__sk_buff_remote_ip6_0, offsetof(struct __sk_buff, remote_ip6[0])),
+	  __imm_const(__sk_buff_remote_ip6_1, offsetof(struct __sk_buff, remote_ip6[1])),
+	  __imm_const(__sk_buff_remote_ip6_2, offsetof(struct __sk_buff, remote_ip6[2])),
+	  __imm_const(__sk_buff_remote_ip6_3, offsetof(struct __sk_buff, remote_ip6[3])),
+	  __imm_const(__sk_buff_remote_port, offsetof(struct __sk_buff, remote_port))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("invalid access of tc_classid for CGROUP_SKB")
+__failure __msg("invalid bpf_context access")
+__failure_unpriv
+__naked void tc_classid_for_cgroup_skb(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[__sk_buff_tc_classid]);	\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_tc_classid, offsetof(struct __sk_buff, tc_classid))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("invalid access of data_meta for CGROUP_SKB")
+__failure __msg("invalid bpf_context access")
+__failure_unpriv
+__naked void data_meta_for_cgroup_skb(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[__sk_buff_data_meta]);	\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data_meta, offsetof(struct __sk_buff, data_meta))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("invalid access of flow_keys for CGROUP_SKB")
+__failure __msg("invalid bpf_context access")
+__failure_unpriv
+__naked void flow_keys_for_cgroup_skb(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[__sk_buff_flow_keys]);	\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_flow_keys, offsetof(struct __sk_buff, flow_keys))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("invalid write access to napi_id for CGROUP_SKB")
+__failure __msg("invalid bpf_context access")
+__failure_unpriv
+__naked void napi_id_for_cgroup_skb(void)
+{
+	asm volatile ("					\
+	r9 = *(u32*)(r1 + %[__sk_buff_napi_id]);	\
+	*(u32*)(r1 + %[__sk_buff_napi_id]) = r9;	\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_napi_id, offsetof(struct __sk_buff, napi_id))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("write tstamp from CGROUP_SKB")
+__success __failure_unpriv
+__msg_unpriv("invalid bpf_context access off=152 size=8")
+__retval(0)
+__naked void write_tstamp_from_cgroup_skb(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	*(u64*)(r1 + %[__sk_buff_tstamp]) = r0;		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_tstamp, offsetof(struct __sk_buff, tstamp))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("read tstamp from CGROUP_SKB")
+__success __success_unpriv __retval(0)
+__naked void read_tstamp_from_cgroup_skb(void)
+{
+	asm volatile ("					\
+	r0 = *(u64*)(r1 + %[__sk_buff_tstamp]);		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_tstamp, offsetof(struct __sk_buff, tstamp))
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_cgroup_storage.c b/tools/testing/selftests/bpf/progs/verifier_cgroup_storage.c
new file mode 100644
index 000000000000..9a13f5c11ac7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_cgroup_storage.c
@@ -0,0 +1,308 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/cgroup_storage.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_CGROUP_STORAGE);
+	__uint(max_entries, 0);
+	__type(key, struct bpf_cgroup_storage_key);
+	__type(value, char[TEST_DATA_LEN]);
+} cgroup_storage SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, long long);
+} map_hash_8b SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE);
+	__uint(max_entries, 0);
+	__type(key, struct bpf_cgroup_storage_key);
+	__type(value, char[64]);
+} percpu_cgroup_storage SEC(".maps");
+
+SEC("cgroup/skb")
+__description("valid cgroup storage access")
+__success __success_unpriv __retval(0)
+__naked void valid_cgroup_storage_access(void)
+{
+	asm volatile ("					\
+	r2 = 0;						\
+	r1 = %[cgroup_storage] ll;			\
+	call %[bpf_get_local_storage];			\
+	r1 = *(u32*)(r0 + 0);				\
+	r0 = r1;					\
+	r0 &= 1;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_local_storage),
+	  __imm_addr(cgroup_storage)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("invalid cgroup storage access 1")
+__failure __msg("cannot pass map_type 1 into func bpf_get_local_storage")
+__failure_unpriv
+__naked void invalid_cgroup_storage_access_1(void)
+{
+	asm volatile ("					\
+	r2 = 0;						\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_get_local_storage];			\
+	r1 = *(u32*)(r0 + 0);				\
+	r0 = r1;					\
+	r0 &= 1;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_local_storage),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("invalid cgroup storage access 2")
+__failure __msg("fd 1 is not pointing to valid bpf_map")
+__failure_unpriv
+__naked void invalid_cgroup_storage_access_2(void)
+{
+	asm volatile ("					\
+	r2 = 0;						\
+	.8byte %[ld_map_fd];				\
+	.8byte 0;					\
+	call %[bpf_get_local_storage];			\
+	r0 &= 1;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_local_storage),
+	  __imm_insn(ld_map_fd, BPF_RAW_INSN(BPF_LD | BPF_DW | BPF_IMM, BPF_REG_1, BPF_PSEUDO_MAP_FD, 0, 1))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("invalid cgroup storage access 3")
+__failure __msg("invalid access to map value, value_size=64 off=256 size=4")
+__failure_unpriv
+__naked void invalid_cgroup_storage_access_3(void)
+{
+	asm volatile ("					\
+	r2 = 0;						\
+	r1 = %[cgroup_storage] ll;			\
+	call %[bpf_get_local_storage];			\
+	r1 = *(u32*)(r0 + 256);				\
+	r1 += 1;					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_local_storage),
+	  __imm_addr(cgroup_storage)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("invalid cgroup storage access 4")
+__failure __msg("invalid access to map value, value_size=64 off=-2 size=4")
+__failure_unpriv
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void invalid_cgroup_storage_access_4(void)
+{
+	asm volatile ("					\
+	r2 = 0;						\
+	r1 = %[cgroup_storage] ll;			\
+	call %[bpf_get_local_storage];			\
+	r1 = *(u32*)(r0 - 2);				\
+	r0 = r1;					\
+	r1 += 1;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_local_storage),
+	  __imm_addr(cgroup_storage)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("invalid cgroup storage access 5")
+__failure __msg("get_local_storage() doesn't support non-zero flags")
+__failure_unpriv
+__naked void invalid_cgroup_storage_access_5(void)
+{
+	asm volatile ("					\
+	r2 = 7;						\
+	r1 = %[cgroup_storage] ll;			\
+	call %[bpf_get_local_storage];			\
+	r1 = *(u32*)(r0 + 0);				\
+	r0 = r1;					\
+	r0 &= 1;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_local_storage),
+	  __imm_addr(cgroup_storage)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("invalid cgroup storage access 6")
+__failure __msg("get_local_storage() doesn't support non-zero flags")
+__msg_unpriv("R2 leaks addr into helper function")
+__naked void invalid_cgroup_storage_access_6(void)
+{
+	asm volatile ("					\
+	r2 = r1;					\
+	r1 = %[cgroup_storage] ll;			\
+	call %[bpf_get_local_storage];			\
+	r1 = *(u32*)(r0 + 0);				\
+	r0 = r1;					\
+	r0 &= 1;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_local_storage),
+	  __imm_addr(cgroup_storage)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("valid per-cpu cgroup storage access")
+__success __success_unpriv __retval(0)
+__naked void per_cpu_cgroup_storage_access(void)
+{
+	asm volatile ("					\
+	r2 = 0;						\
+	r1 = %[percpu_cgroup_storage] ll;		\
+	call %[bpf_get_local_storage];			\
+	r1 = *(u32*)(r0 + 0);				\
+	r0 = r1;					\
+	r0 &= 1;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_local_storage),
+	  __imm_addr(percpu_cgroup_storage)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("invalid per-cpu cgroup storage access 1")
+__failure __msg("cannot pass map_type 1 into func bpf_get_local_storage")
+__failure_unpriv
+__naked void cpu_cgroup_storage_access_1(void)
+{
+	asm volatile ("					\
+	r2 = 0;						\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_get_local_storage];			\
+	r1 = *(u32*)(r0 + 0);				\
+	r0 = r1;					\
+	r0 &= 1;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_local_storage),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("invalid per-cpu cgroup storage access 2")
+__failure __msg("fd 1 is not pointing to valid bpf_map")
+__failure_unpriv
+__naked void cpu_cgroup_storage_access_2(void)
+{
+	asm volatile ("					\
+	r2 = 0;						\
+	.8byte %[ld_map_fd];				\
+	.8byte 0;					\
+	call %[bpf_get_local_storage];			\
+	r0 &= 1;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_local_storage),
+	  __imm_insn(ld_map_fd, BPF_RAW_INSN(BPF_LD | BPF_DW | BPF_IMM, BPF_REG_1, BPF_PSEUDO_MAP_FD, 0, 1))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("invalid per-cpu cgroup storage access 3")
+__failure __msg("invalid access to map value, value_size=64 off=256 size=4")
+__failure_unpriv
+__naked void cpu_cgroup_storage_access_3(void)
+{
+	asm volatile ("					\
+	r2 = 0;						\
+	r1 = %[percpu_cgroup_storage] ll;		\
+	call %[bpf_get_local_storage];			\
+	r1 = *(u32*)(r0 + 256);				\
+	r1 += 1;					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_local_storage),
+	  __imm_addr(percpu_cgroup_storage)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("invalid per-cpu cgroup storage access 4")
+__failure __msg("invalid access to map value, value_size=64 off=-2 size=4")
+__failure_unpriv
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void cpu_cgroup_storage_access_4(void)
+{
+	asm volatile ("					\
+	r2 = 0;						\
+	r1 = %[cgroup_storage] ll;			\
+	call %[bpf_get_local_storage];			\
+	r1 = *(u32*)(r0 - 2);				\
+	r0 = r1;					\
+	r1 += 1;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_local_storage),
+	  __imm_addr(cgroup_storage)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("invalid per-cpu cgroup storage access 5")
+__failure __msg("get_local_storage() doesn't support non-zero flags")
+__failure_unpriv
+__naked void cpu_cgroup_storage_access_5(void)
+{
+	asm volatile ("					\
+	r2 = 7;						\
+	r1 = %[percpu_cgroup_storage] ll;		\
+	call %[bpf_get_local_storage];			\
+	r1 = *(u32*)(r0 + 0);				\
+	r0 = r1;					\
+	r0 &= 1;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_local_storage),
+	  __imm_addr(percpu_cgroup_storage)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("invalid per-cpu cgroup storage access 6")
+__failure __msg("get_local_storage() doesn't support non-zero flags")
+__msg_unpriv("R2 leaks addr into helper function")
+__naked void cpu_cgroup_storage_access_6(void)
+{
+	asm volatile ("					\
+	r2 = r1;					\
+	r1 = %[percpu_cgroup_storage] ll;		\
+	call %[bpf_get_local_storage];			\
+	r1 = *(u32*)(r0 + 0);				\
+	r0 = r1;					\
+	r0 &= 1;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_local_storage),
+	  __imm_addr(percpu_cgroup_storage)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_const.c b/tools/testing/selftests/bpf/progs/verifier_const.c
new file mode 100644
index 000000000000..e118dbb768bf
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_const.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Isovalent */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+
+const volatile long foo = 42;
+long bar;
+long bart = 96;
+
+SEC("tc/ingress")
+__description("rodata/strtol: write rejected")
+__failure __msg("write into map forbidden")
+int tcx1(struct __sk_buff *skb)
+{
+	char buff[] = { '8', '4', '\0' };
+	bpf_strtol(buff, sizeof(buff), 0, (long *)&foo);
+	return TCX_PASS;
+}
+
+SEC("tc/ingress")
+__description("bss/strtol: write accepted")
+__success
+int tcx2(struct __sk_buff *skb)
+{
+	char buff[] = { '8', '4', '\0' };
+	bpf_strtol(buff, sizeof(buff), 0, &bar);
+	return TCX_PASS;
+}
+
+SEC("tc/ingress")
+__description("data/strtol: write accepted")
+__success
+int tcx3(struct __sk_buff *skb)
+{
+	char buff[] = { '8', '4', '\0' };
+	bpf_strtol(buff, sizeof(buff), 0, &bart);
+	return TCX_PASS;
+}
+
+SEC("tc/ingress")
+__description("rodata/mtu: write rejected")
+__failure __msg("write into map forbidden")
+int tcx4(struct __sk_buff *skb)
+{
+	bpf_check_mtu(skb, skb->ifindex, (__u32 *)&foo, 0, 0);
+	return TCX_PASS;
+}
+
+SEC("tc/ingress")
+__description("bss/mtu: write accepted")
+__success
+int tcx5(struct __sk_buff *skb)
+{
+	bpf_check_mtu(skb, skb->ifindex, (__u32 *)&bar, 0, 0);
+	return TCX_PASS;
+}
+
+SEC("tc/ingress")
+__description("data/mtu: write accepted")
+__success
+int tcx6(struct __sk_buff *skb)
+{
+	bpf_check_mtu(skb, skb->ifindex, (__u32 *)&bart, 0, 0);
+	return TCX_PASS;
+}
+
+static inline void write_fixed(volatile void *p, __u32 val)
+{
+	*(volatile __u32 *)p = val;
+}
+
+static inline void write_dyn(void *p, void *val, int len)
+{
+	bpf_copy_from_user(p, len, val);
+}
+
+SEC("tc/ingress")
+__description("rodata/mark: write with unknown reg rejected")
+__failure __msg("write into map forbidden")
+int tcx7(struct __sk_buff *skb)
+{
+	write_fixed((void *)&foo, skb->mark);
+	return TCX_PASS;
+}
+
+SEC("lsm.s/bprm_committed_creds")
+__description("rodata/mark: write with unknown reg rejected")
+__failure __msg("write into map forbidden")
+int BPF_PROG(bprm, struct linux_binprm *bprm)
+{
+	write_dyn((void *)&foo, &bart, bpf_get_prandom_u32() & 3);
+	return 0;
+}
+
+char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_const_or.c b/tools/testing/selftests/bpf/progs/verifier_const_or.c
new file mode 100644
index 000000000000..68c568c3c3a0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_const_or.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/const_or.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("tracepoint")
+__description("constant register |= constant should keep constant type")
+__success
+__naked void constant_should_keep_constant_type(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -48;					\
+	r2 = 34;					\
+	r2 |= 13;					\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+	exit;						\
+"	:
+	: __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("constant register |= constant should not bypass stack boundary checks")
+__failure __msg("invalid write to stack R1 off=-48 size=58")
+__naked void not_bypass_stack_boundary_checks_1(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -48;					\
+	r2 = 34;					\
+	r2 |= 24;					\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+	exit;						\
+"	:
+	: __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("constant register |= constant register should keep constant type")
+__success
+__naked void register_should_keep_constant_type(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -48;					\
+	r2 = 34;					\
+	r4 = 13;					\
+	r2 |= r4;					\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+	exit;						\
+"	:
+	: __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("constant register |= constant register should not bypass stack boundary checks")
+__failure __msg("invalid write to stack R1 off=-48 size=58")
+__naked void not_bypass_stack_boundary_checks_2(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -48;					\
+	r2 = 34;					\
+	r4 = 24;					\
+	r2 |= r4;					\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+	exit;						\
+"	:
+	: __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_ctx.c b/tools/testing/selftests/bpf/progs/verifier_ctx.c
new file mode 100644
index 000000000000..5ebf7d9bcc55
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_ctx.c
@@ -0,0 +1,295 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/ctx.c */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("tc")
+__description("context stores via BPF_ATOMIC")
+__failure __msg("BPF_ATOMIC stores into R1 ctx is not allowed")
+__naked void context_stores_via_bpf_atomic(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	lock *(u32 *)(r1 + %[__sk_buff_mark]) += w0;	\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("arithmetic ops make PTR_TO_CTX unusable")
+__failure __msg("dereference of modified ctx ptr")
+__naked void make_ptr_to_ctx_unusable(void)
+{
+	asm volatile ("					\
+	r1 += %[__imm_0];				\
+	r0 = *(u32*)(r1 + %[__sk_buff_mark]);		\
+	exit;						\
+"	:
+	: __imm_const(__imm_0,
+		      offsetof(struct __sk_buff, data) - offsetof(struct __sk_buff, mark)),
+	  __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("pass unmodified ctx pointer to helper")
+__success __retval(0)
+__naked void unmodified_ctx_pointer_to_helper(void)
+{
+	asm volatile ("					\
+	r2 = 0;						\
+	call %[bpf_csum_update];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_csum_update)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("pass modified ctx pointer to helper, 1")
+__failure __msg("negative offset ctx ptr R1 off=-612 disallowed")
+__naked void ctx_pointer_to_helper_1(void)
+{
+	asm volatile ("					\
+	r1 += -612;					\
+	r2 = 0;						\
+	call %[bpf_csum_update];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_csum_update)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("pass modified ctx pointer to helper, 2")
+__failure __msg("negative offset ctx ptr R1 off=-612 disallowed")
+__failure_unpriv __msg_unpriv("negative offset ctx ptr R1 off=-612 disallowed")
+__naked void ctx_pointer_to_helper_2(void)
+{
+	asm volatile ("					\
+	r1 += -612;					\
+	call %[bpf_get_socket_cookie];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_socket_cookie)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("pass modified ctx pointer to helper, 3")
+__failure __msg("variable ctx access var_off=(0x0; 0x4)")
+__naked void ctx_pointer_to_helper_3(void)
+{
+	asm volatile ("					\
+	r3 = *(u32*)(r1 + 0);				\
+	r3 &= 4;					\
+	r1 += r3;					\
+	r2 = 0;						\
+	call %[bpf_csum_update];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_csum_update)
+	: __clobber_all);
+}
+
+SEC("cgroup/sendmsg6")
+__description("pass ctx or null check, 1: ctx")
+__success
+__naked void or_null_check_1_ctx(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_netns_cookie];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_netns_cookie)
+	: __clobber_all);
+}
+
+SEC("cgroup/sendmsg6")
+__description("pass ctx or null check, 2: null")
+__success
+__naked void or_null_check_2_null(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	call %[bpf_get_netns_cookie];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_netns_cookie)
+	: __clobber_all);
+}
+
+SEC("cgroup/sendmsg6")
+__description("pass ctx or null check, 3: 1")
+__failure __msg("R1 type=scalar expected=ctx")
+__naked void or_null_check_3_1(void)
+{
+	asm volatile ("					\
+	r1 = 1;						\
+	call %[bpf_get_netns_cookie];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_netns_cookie)
+	: __clobber_all);
+}
+
+SEC("cgroup/sendmsg6")
+__description("pass ctx or null check, 4: ctx - const")
+__failure __msg("negative offset ctx ptr R1 off=-612 disallowed")
+__naked void null_check_4_ctx_const(void)
+{
+	asm volatile ("					\
+	r1 += -612;					\
+	call %[bpf_get_netns_cookie];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_netns_cookie)
+	: __clobber_all);
+}
+
+SEC("cgroup/connect4")
+__description("pass ctx or null check, 5: null (connect)")
+__success
+__naked void null_check_5_null_connect(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	call %[bpf_get_netns_cookie];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_netns_cookie)
+	: __clobber_all);
+}
+
+SEC("cgroup/post_bind4")
+__description("pass ctx or null check, 6: null (bind)")
+__success
+__naked void null_check_6_null_bind(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	call %[bpf_get_netns_cookie];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_netns_cookie)
+	: __clobber_all);
+}
+
+SEC("cgroup/post_bind4")
+__description("pass ctx or null check, 7: ctx (bind)")
+__success
+__naked void null_check_7_ctx_bind(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_socket_cookie];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_socket_cookie)
+	: __clobber_all);
+}
+
+SEC("cgroup/post_bind4")
+__description("pass ctx or null check, 8: null (bind)")
+__failure __msg("R1 type=scalar expected=ctx")
+__naked void null_check_8_null_bind(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	call %[bpf_get_socket_cookie];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_socket_cookie)
+	: __clobber_all);
+}
+
+#define narrow_load(type, ctx, field)					\
+	SEC(type)							\
+	__description("narrow load on field " #field " of " #ctx)	\
+	__failure __msg("invalid bpf_context access")			\
+	__naked void invalid_narrow_load##ctx##field(void)		\
+	{								\
+		asm volatile ("						\
+		r1 = *(u32 *)(r1 + %[off]);				\
+		r0 = 0;							\
+		exit;"							\
+		:							\
+		: __imm_const(off, offsetof(struct ctx, field) + 4)	\
+		: __clobber_all);					\
+	}
+
+narrow_load("cgroup/getsockopt", bpf_sockopt, sk);
+narrow_load("cgroup/getsockopt", bpf_sockopt, optval);
+narrow_load("cgroup/getsockopt", bpf_sockopt, optval_end);
+narrow_load("tc", __sk_buff, sk);
+narrow_load("cgroup/bind4", bpf_sock_addr, sk);
+narrow_load("sockops", bpf_sock_ops, sk);
+narrow_load("sockops", bpf_sock_ops, skb_data);
+narrow_load("sockops", bpf_sock_ops, skb_data_end);
+narrow_load("sockops", bpf_sock_ops, skb_hwtstamp);
+
+#define unaligned_access(type, ctx, field)					\
+	SEC(type)								\
+	__description("unaligned access on field " #field " of " #ctx)		\
+	__failure __msg("invalid bpf_context access")				\
+	__naked void unaligned_ctx_access_##ctx##field(void)			\
+	{									\
+		asm volatile ("							\
+		r1 = *(u%[size] *)(r1 + %[off]);				\
+		r0 = 0;								\
+		exit;"								\
+		:								\
+		: __imm_const(size, sizeof_field(struct ctx, field) * 8),	\
+		  __imm_const(off, offsetof(struct ctx, field) + 1)		\
+		: __clobber_all);						\
+	}
+
+unaligned_access("flow_dissector", __sk_buff, data);
+unaligned_access("netfilter", bpf_nf_ctx, skb);
+
+#define padding_access(type, ctx, prev_field, sz)			\
+	SEC(type)							\
+	__description("access on " #ctx " padding after " #prev_field)	\
+	__naked void padding_ctx_access_##ctx(void)			\
+	{								\
+		asm volatile ("						\
+		r1 = *(u%[size] *)(r1 + %[off]);			\
+		r0 = 0;							\
+		exit;"							\
+		:							\
+		: __imm_const(size, sz * 8),				\
+		  __imm_const(off, offsetofend(struct ctx, prev_field))	\
+		: __clobber_all);					\
+	}
+
+__failure __msg("invalid bpf_context access")
+padding_access("cgroup/bind4", bpf_sock_addr, msg_src_ip6[3], 4);
+
+__success
+padding_access("sk_lookup", bpf_sk_lookup, remote_port, 2);
+
+__failure __msg("invalid bpf_context access")
+padding_access("tc", __sk_buff, tstamp_type, 2);
+
+__failure __msg("invalid bpf_context access")
+padding_access("cgroup/post_bind4", bpf_sock, dst_port, 2);
+
+__failure __msg("invalid bpf_context access")
+padding_access("sk_reuseport", sk_reuseport_md, hash, 4);
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_ctx_sk_msg.c b/tools/testing/selftests/bpf/progs/verifier_ctx_sk_msg.c
new file mode 100644
index 000000000000..65edc89799f9
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_ctx_sk_msg.c
@@ -0,0 +1,228 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/ctx_sk_msg.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("sk_msg")
+__description("valid access family in SK_MSG")
+__success
+__naked void access_family_in_sk_msg(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[sk_msg_md_family]);		\
+	exit;						\
+"	:
+	: __imm_const(sk_msg_md_family, offsetof(struct sk_msg_md, family))
+	: __clobber_all);
+}
+
+SEC("sk_msg")
+__description("valid access remote_ip4 in SK_MSG")
+__success
+__naked void remote_ip4_in_sk_msg(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[sk_msg_md_remote_ip4]);	\
+	exit;						\
+"	:
+	: __imm_const(sk_msg_md_remote_ip4, offsetof(struct sk_msg_md, remote_ip4))
+	: __clobber_all);
+}
+
+SEC("sk_msg")
+__description("valid access local_ip4 in SK_MSG")
+__success
+__naked void local_ip4_in_sk_msg(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[sk_msg_md_local_ip4]);	\
+	exit;						\
+"	:
+	: __imm_const(sk_msg_md_local_ip4, offsetof(struct sk_msg_md, local_ip4))
+	: __clobber_all);
+}
+
+SEC("sk_msg")
+__description("valid access remote_port in SK_MSG")
+__success
+__naked void remote_port_in_sk_msg(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[sk_msg_md_remote_port]);	\
+	exit;						\
+"	:
+	: __imm_const(sk_msg_md_remote_port, offsetof(struct sk_msg_md, remote_port))
+	: __clobber_all);
+}
+
+SEC("sk_msg")
+__description("valid access local_port in SK_MSG")
+__success
+__naked void local_port_in_sk_msg(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[sk_msg_md_local_port]);	\
+	exit;						\
+"	:
+	: __imm_const(sk_msg_md_local_port, offsetof(struct sk_msg_md, local_port))
+	: __clobber_all);
+}
+
+SEC("sk_skb")
+__description("valid access remote_ip6 in SK_MSG")
+__success
+__naked void remote_ip6_in_sk_msg(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[sk_msg_md_remote_ip6_0]);	\
+	r0 = *(u32*)(r1 + %[sk_msg_md_remote_ip6_1]);	\
+	r0 = *(u32*)(r1 + %[sk_msg_md_remote_ip6_2]);	\
+	r0 = *(u32*)(r1 + %[sk_msg_md_remote_ip6_3]);	\
+	exit;						\
+"	:
+	: __imm_const(sk_msg_md_remote_ip6_0, offsetof(struct sk_msg_md, remote_ip6[0])),
+	  __imm_const(sk_msg_md_remote_ip6_1, offsetof(struct sk_msg_md, remote_ip6[1])),
+	  __imm_const(sk_msg_md_remote_ip6_2, offsetof(struct sk_msg_md, remote_ip6[2])),
+	  __imm_const(sk_msg_md_remote_ip6_3, offsetof(struct sk_msg_md, remote_ip6[3]))
+	: __clobber_all);
+}
+
+SEC("sk_skb")
+__description("valid access local_ip6 in SK_MSG")
+__success
+__naked void local_ip6_in_sk_msg(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[sk_msg_md_local_ip6_0]);	\
+	r0 = *(u32*)(r1 + %[sk_msg_md_local_ip6_1]);	\
+	r0 = *(u32*)(r1 + %[sk_msg_md_local_ip6_2]);	\
+	r0 = *(u32*)(r1 + %[sk_msg_md_local_ip6_3]);	\
+	exit;						\
+"	:
+	: __imm_const(sk_msg_md_local_ip6_0, offsetof(struct sk_msg_md, local_ip6[0])),
+	  __imm_const(sk_msg_md_local_ip6_1, offsetof(struct sk_msg_md, local_ip6[1])),
+	  __imm_const(sk_msg_md_local_ip6_2, offsetof(struct sk_msg_md, local_ip6[2])),
+	  __imm_const(sk_msg_md_local_ip6_3, offsetof(struct sk_msg_md, local_ip6[3]))
+	: __clobber_all);
+}
+
+SEC("sk_msg")
+__description("valid access size in SK_MSG")
+__success
+__naked void access_size_in_sk_msg(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[sk_msg_md_size]);		\
+	exit;						\
+"	:
+	: __imm_const(sk_msg_md_size, offsetof(struct sk_msg_md, size))
+	: __clobber_all);
+}
+
+SEC("sk_msg")
+__description("invalid 64B read of size in SK_MSG")
+__failure __msg("invalid bpf_context access")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void of_size_in_sk_msg(void)
+{
+	asm volatile ("					\
+	r2 = *(u64*)(r1 + %[sk_msg_md_size]);		\
+	exit;						\
+"	:
+	: __imm_const(sk_msg_md_size, offsetof(struct sk_msg_md, size))
+	: __clobber_all);
+}
+
+SEC("sk_msg")
+__description("invalid read past end of SK_MSG")
+__failure __msg("invalid bpf_context access")
+__naked void past_end_of_sk_msg(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__imm_0]);			\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, offsetof(struct sk_msg_md, size) + 4)
+	: __clobber_all);
+}
+
+SEC("sk_msg")
+__description("invalid read offset in SK_MSG")
+__failure __msg("invalid bpf_context access")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void read_offset_in_sk_msg(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__imm_0]);			\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, offsetof(struct sk_msg_md, family) + 1)
+	: __clobber_all);
+}
+
+SEC("sk_msg")
+__description("direct packet read for SK_MSG")
+__success
+__naked void packet_read_for_sk_msg(void)
+{
+	asm volatile ("					\
+	r2 = *(u64*)(r1 + %[sk_msg_md_data]);		\
+	r3 = *(u64*)(r1 + %[sk_msg_md_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r0 > r3 goto l0_%=;				\
+	r0 = *(u8*)(r2 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(sk_msg_md_data, offsetof(struct sk_msg_md, data)),
+	  __imm_const(sk_msg_md_data_end, offsetof(struct sk_msg_md, data_end))
+	: __clobber_all);
+}
+
+SEC("sk_msg")
+__description("direct packet write for SK_MSG")
+__success
+__naked void packet_write_for_sk_msg(void)
+{
+	asm volatile ("					\
+	r2 = *(u64*)(r1 + %[sk_msg_md_data]);		\
+	r3 = *(u64*)(r1 + %[sk_msg_md_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r0 > r3 goto l0_%=;				\
+	*(u8*)(r2 + 0) = r2;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(sk_msg_md_data, offsetof(struct sk_msg_md, data)),
+	  __imm_const(sk_msg_md_data_end, offsetof(struct sk_msg_md, data_end))
+	: __clobber_all);
+}
+
+SEC("sk_msg")
+__description("overlapping checks for direct packet access SK_MSG")
+__success
+__naked void direct_packet_access_sk_msg(void)
+{
+	asm volatile ("					\
+	r2 = *(u64*)(r1 + %[sk_msg_md_data]);		\
+	r3 = *(u64*)(r1 + %[sk_msg_md_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r0 > r3 goto l0_%=;				\
+	r1 = r2;					\
+	r1 += 6;					\
+	if r1 > r3 goto l0_%=;				\
+	r0 = *(u16*)(r2 + 6);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(sk_msg_md_data, offsetof(struct sk_msg_md, data)),
+	  __imm_const(sk_msg_md_data_end, offsetof(struct sk_msg_md, data_end))
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_d_path.c b/tools/testing/selftests/bpf/progs/verifier_d_path.c
new file mode 100644
index 000000000000..87e51a215558
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_d_path.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/d_path.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("fentry/dentry_open")
+__description("d_path accept")
+__success __retval(0)
+__naked void d_path_accept(void)
+{
+	asm volatile ("					\
+	r1 = *(u64 *)(r1 + 0);				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r6 = 0;						\
+	*(u64*)(r2 + 0) = r6;				\
+	r3 = 8 ll;					\
+	call %[bpf_d_path];				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_d_path)
+	: __clobber_all);
+}
+
+SEC("fentry/d_path")
+__description("d_path reject")
+__failure __msg("helper call is not allowed in probe")
+__naked void d_path_reject(void)
+{
+	asm volatile ("					\
+	r1 = *(u64 *)(r1 + 0);				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r6 = 0;						\
+	*(u64*)(r2 + 0) = r6;				\
+	r3 = 8 ll;					\
+	call %[bpf_d_path];				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_d_path)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c b/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c
new file mode 100644
index 000000000000..911caa8fd1b7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_direct_packet_access.c
@@ -0,0 +1,862 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/direct_packet_access.c */
+
+#include <linux/if_ether.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("tc")
+__description("pkt_end - pkt_start is allowed")
+__success __retval(TEST_DATA_LEN)
+__naked void end_pkt_start_is_allowed(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r0 -= r2;					\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test1")
+__success __retval(0)
+__naked void direct_packet_access_test1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r0 > r3 goto l0_%=;				\
+	r0 = *(u8*)(r2 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test2")
+__success __retval(0)
+__naked void direct_packet_access_test2(void)
+{
+	asm volatile ("					\
+	r0 = 1;						\
+	r4 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r3 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r5 = r3;					\
+	r5 += 14;					\
+	if r5 > r4 goto l0_%=;				\
+	r0 = *(u8*)(r3 + 7);				\
+	r4 = *(u8*)(r3 + 12);				\
+	r4 *= 14;					\
+	r3 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 += r4;					\
+	r2 = *(u32*)(r1 + %[__sk_buff_len]);		\
+	r2 <<= 49;					\
+	r2 >>= 49;					\
+	r3 += r2;					\
+	r2 = r3;					\
+	r2 += 8;					\
+	r1 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	if r2 > r1 goto l1_%=;				\
+	r1 = *(u8*)(r3 + 4);				\
+l1_%=:	r0 = 0;						\
+l0_%=:	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)),
+	  __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("direct packet access: test3")
+__failure __msg("invalid bpf_context access off=76")
+__failure_unpriv
+__naked void direct_packet_access_test3(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test4 (write)")
+__success __retval(0)
+__naked void direct_packet_access_test4_write(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r0 > r3 goto l0_%=;				\
+	*(u8*)(r2 + 0) = r2;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test5 (pkt_end >= reg, good access)")
+__success __retval(0)
+__naked void pkt_end_reg_good_access(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r3 >= r0 goto l0_%=;				\
+	r0 = 1;						\
+	exit;						\
+l0_%=:	r0 = *(u8*)(r2 + 0);				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test6 (pkt_end >= reg, bad access)")
+__failure __msg("invalid access to packet")
+__naked void pkt_end_reg_bad_access(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r3 >= r0 goto l0_%=;				\
+	r0 = *(u8*)(r2 + 0);				\
+	r0 = 1;						\
+	exit;						\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test7 (pkt_end >= reg, both accesses)")
+__failure __msg("invalid access to packet")
+__naked void pkt_end_reg_both_accesses(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r3 >= r0 goto l0_%=;				\
+	r0 = *(u8*)(r2 + 0);				\
+	r0 = 1;						\
+	exit;						\
+l0_%=:	r0 = *(u8*)(r2 + 0);				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test8 (double test, variant 1)")
+__success __retval(0)
+__naked void test8_double_test_variant_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r3 >= r0 goto l0_%=;				\
+	if r0 > r3 goto l1_%=;				\
+	r0 = *(u8*)(r2 + 0);				\
+l1_%=:	r0 = 1;						\
+	exit;						\
+l0_%=:	r0 = *(u8*)(r2 + 0);				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test9 (double test, variant 2)")
+__success __retval(0)
+__naked void test9_double_test_variant_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r3 >= r0 goto l0_%=;				\
+	r0 = 1;						\
+	exit;						\
+l0_%=:	if r0 > r3 goto l1_%=;				\
+	r0 = *(u8*)(r2 + 0);				\
+l1_%=:	r0 = *(u8*)(r2 + 0);				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test10 (write invalid)")
+__failure __msg("invalid access to packet")
+__naked void packet_access_test10_write_invalid(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r0 > r3 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	*(u8*)(r2 + 0) = r2;				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test11 (shift, good access)")
+__success __retval(1)
+__naked void access_test11_shift_good_access(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 22;					\
+	if r0 > r3 goto l0_%=;				\
+	r3 = 144;					\
+	r5 = r3;					\
+	r5 += 23;					\
+	r5 >>= 3;					\
+	r6 = r2;					\
+	r6 += r5;					\
+	r0 = 1;						\
+	exit;						\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test12 (and, good access)")
+__success __retval(1)
+__naked void access_test12_and_good_access(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 22;					\
+	if r0 > r3 goto l0_%=;				\
+	r3 = 144;					\
+	r5 = r3;					\
+	r5 += 23;					\
+	r5 &= 15;					\
+	r6 = r2;					\
+	r6 += r5;					\
+	r0 = 1;						\
+	exit;						\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test13 (branches, good access)")
+__success __retval(1)
+__naked void access_test13_branches_good_access(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 22;					\
+	if r0 > r3 goto l0_%=;				\
+	r3 = *(u32*)(r1 + %[__sk_buff_mark]);		\
+	r4 = 1;						\
+	if r3 > r4 goto l1_%=;				\
+	r3 = 14;					\
+	goto l2_%=;					\
+l1_%=:	r3 = 24;					\
+l2_%=:	r5 = r3;					\
+	r5 += 23;					\
+	r5 &= 15;					\
+	r6 = r2;					\
+	r6 += r5;					\
+	r0 = 1;						\
+	exit;						\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)),
+	  __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test14 (pkt_ptr += 0, CONST_IMM, good access)")
+__success __retval(1)
+__naked void _0_const_imm_good_access(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 22;					\
+	if r0 > r3 goto l0_%=;				\
+	r5 = 12;					\
+	r5 >>= 4;					\
+	r6 = r2;					\
+	r6 += r5;					\
+	r0 = *(u8*)(r6 + 0);				\
+	r0 = 1;						\
+	exit;						\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test15 (spill with xadd)")
+__failure __msg("R2 invalid mem access 'scalar'")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void access_test15_spill_with_xadd(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r0 > r3 goto l0_%=;				\
+	r5 = 4096;					\
+	r4 = r10;					\
+	r4 += -8;					\
+	*(u64*)(r4 + 0) = r2;				\
+	lock *(u64 *)(r4 + 0) += r5;			\
+	r2 = *(u64*)(r4 + 0);				\
+	*(u32*)(r2 + 0) = r5;				\
+	r0 = 0;						\
+l0_%=:	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test16 (arith on data_end)")
+__failure __msg("R3 pointer arithmetic on pkt_end")
+__naked void test16_arith_on_data_end(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	r3 += 16;					\
+	if r0 > r3 goto l0_%=;				\
+	*(u8*)(r2 + 0) = r2;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test17 (pruning, alignment)")
+__failure __msg("misaligned packet access off 2+0+15+-4 size 4")
+__flag(BPF_F_STRICT_ALIGNMENT)
+__naked void packet_access_test17_pruning_alignment(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r7 = *(u32*)(r1 + %[__sk_buff_mark]);		\
+	r0 = r2;					\
+	r0 += 14;					\
+	if r7 > 1 goto l0_%=;				\
+l2_%=:	if r0 > r3 goto l1_%=;				\
+	*(u32*)(r0 - 4) = r0;				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+l0_%=:	r0 += 1;					\
+	goto l2_%=;					\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)),
+	  __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test18 (imm += pkt_ptr, 1)")
+__success __retval(0)
+__naked void test18_imm_pkt_ptr_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = 8;						\
+	r0 += r2;					\
+	if r0 > r3 goto l0_%=;				\
+	*(u8*)(r2 + 0) = r2;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test19 (imm += pkt_ptr, 2)")
+__success __retval(0)
+__naked void test19_imm_pkt_ptr_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r0 > r3 goto l0_%=;				\
+	r4 = 4;						\
+	r4 += r2;					\
+	*(u8*)(r4 + 0) = r4;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test20 (x += pkt_ptr, 1)")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void test20_x_pkt_ptr_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = 0xffffffff;				\
+	*(u64*)(r10 - 8) = r0;				\
+	r0 = *(u64*)(r10 - 8);				\
+	r0 &= 0x7fff;					\
+	r4 = r0;					\
+	r4 += r2;					\
+	r5 = r4;					\
+	r4 += %[__imm_0];				\
+	if r4 > r3 goto l0_%=;				\
+	*(u64*)(r5 + 0) = r4;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 0x7fff - 1),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test21 (x += pkt_ptr, 2)")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void test21_x_pkt_ptr_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r0 > r3 goto l0_%=;				\
+	r4 = 0xffffffff;				\
+	*(u64*)(r10 - 8) = r4;				\
+	r4 = *(u64*)(r10 - 8);				\
+	r4 &= 0x7fff;					\
+	r4 += r2;					\
+	r5 = r4;					\
+	r4 += %[__imm_0];				\
+	if r4 > r3 goto l0_%=;				\
+	*(u64*)(r5 + 0) = r4;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 0x7fff - 1),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test22 (x += pkt_ptr, 3)")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void test22_x_pkt_ptr_3(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	*(u64*)(r10 - 8) = r2;				\
+	*(u64*)(r10 - 16) = r3;				\
+	r3 = *(u64*)(r10 - 16);				\
+	if r0 > r3 goto l0_%=;				\
+	r2 = *(u64*)(r10 - 8);				\
+	r4 = 0xffffffff;				\
+	lock *(u64 *)(r10 - 8) += r4;			\
+	r4 = *(u64*)(r10 - 8);				\
+	r4 >>= 49;					\
+	r4 += r2;					\
+	r0 = r4;					\
+	r0 += 2;					\
+	if r0 > r3 goto l0_%=;				\
+	r2 = 1;						\
+	*(u16*)(r4 + 0) = r2;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test23 (x += pkt_ptr, 4)")
+__failure __msg("invalid access to packet, off=0 size=8, R5(id=3,off=0,r=0)")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void test23_x_pkt_ptr_4(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = *(u32*)(r1 + %[__sk_buff_mark]);		\
+	*(u64*)(r10 - 8) = r0;				\
+	r0 = *(u64*)(r10 - 8);				\
+	r0 &= 0xffff;					\
+	r4 = r0;					\
+	r0 = 31;					\
+	r0 += r4;					\
+	r0 += r2;					\
+	r5 = r0;					\
+	r0 += %[__imm_0];				\
+	if r0 > r3 goto l0_%=;				\
+	*(u64*)(r5 + 0) = r0;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 0xffff - 1),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)),
+	  __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test24 (x += pkt_ptr, 5)")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void test24_x_pkt_ptr_5(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = 0xffffffff;				\
+	*(u64*)(r10 - 8) = r0;				\
+	r0 = *(u64*)(r10 - 8);				\
+	r0 &= 0xff;					\
+	r4 = r0;					\
+	r0 = 64;					\
+	r0 += r4;					\
+	r0 += r2;					\
+	r5 = r0;					\
+	r0 += %[__imm_0];				\
+	if r0 > r3 goto l0_%=;				\
+	*(u64*)(r5 + 0) = r0;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 0x7fff - 1),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test25 (marking on <, good access)")
+__success __retval(0)
+__naked void test25_marking_on_good_access(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r0 < r3 goto l0_%=;				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+l0_%=:	r0 = *(u8*)(r2 + 0);				\
+	goto l1_%=;					\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test26 (marking on <, bad access)")
+__failure __msg("invalid access to packet")
+__naked void test26_marking_on_bad_access(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r0 < r3 goto l0_%=;				\
+	r0 = *(u8*)(r2 + 0);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+l0_%=:	goto l1_%=;					\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test27 (marking on <=, good access)")
+__success __retval(1)
+__naked void test27_marking_on_good_access(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r3 <= r0 goto l0_%=;				\
+	r0 = *(u8*)(r2 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test28 (marking on <=, bad access)")
+__failure __msg("invalid access to packet")
+__naked void test28_marking_on_bad_access(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r3 <= r0 goto l0_%=;				\
+l1_%=:	r0 = 1;						\
+	exit;						\
+l0_%=:	r0 = *(u8*)(r2 + 0);				\
+	goto l1_%=;					\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test29 (reg > pkt_end in subprog)")
+__success __retval(0)
+__naked void reg_pkt_end_in_subprog(void)
+{
+	asm volatile ("					\
+	r6 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r2 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r3 = r6;					\
+	r3 += 8;					\
+	call reg_pkt_end_in_subprog__1;			\
+	if r0 == 0 goto l0_%=;				\
+	r0 = *(u8*)(r6 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+static __naked __noinline __attribute__((used))
+void reg_pkt_end_in_subprog__1(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	if r3 > r2 goto l0_%=;				\
+	r0 = 1;						\
+l0_%=:	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tc")
+__description("direct packet access: test30 (check_id() in regsafe(), bad access)")
+__failure __msg("invalid access to packet, off=0 size=1, R2")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void id_in_regsafe_bad_access(void)
+{
+	asm volatile ("					\
+	/* r9 = ctx */					\
+	r9 = r1;					\
+	/* r7 = ktime_get_ns() */			\
+	call %[bpf_ktime_get_ns];			\
+	r7 = r0;					\
+	/* r6 = ktime_get_ns() */			\
+	call %[bpf_ktime_get_ns];			\
+	r6 = r0;					\
+	/* r2 = ctx->data				\
+	 * r3 = ctx->data				\
+	 * r4 = ctx->data_end				\
+	 */						\
+	r2 = *(u32*)(r9 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r9 + %[__sk_buff_data]);		\
+	r4 = *(u32*)(r9 + %[__sk_buff_data_end]);	\
+	/* if r6 > 100 goto exit			\
+	 * if r7 > 100 goto exit			\
+	 */						\
+	if r6 > 100 goto l0_%=;				\
+	if r7 > 100 goto l0_%=;				\
+	/* r2 += r6              ; this forces assignment of ID to r2\
+	 * r2 += 1               ; get some fixed off for r2\
+	 * r3 += r7              ; this forces assignment of ID to r3\
+	 * r3 += 1               ; get some fixed off for r3\
+	 */						\
+	r2 += r6;					\
+	r2 += 1;					\
+	r3 += r7;					\
+	r3 += 1;					\
+	/* if r6 > r7 goto +1    ; no new information about the state is derived from\
+	 *                       ; this check, thus produced verifier states differ\
+	 *                       ; only in 'insn_idx'	\
+	 * r2 = r3               ; optionally share ID between r2 and r3\
+	 */						\
+	if r6 != r7 goto l1_%=;				\
+	r2 = r3;					\
+l1_%=:	/* if r3 > ctx->data_end goto exit */		\
+	if r3 > r4 goto l0_%=;				\
+	/* r5 = *(u8 *) (r2 - 1) ; access packet memory using r2,\
+	 *                       ; this is not always safe\
+	 */						\
+	r5 = *(u8*)(r2 - 1);				\
+l0_%=:	/* exit(0) */					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+#define access_test_non_linear(name, type, desc, retval, linear_sz, off)			\
+	SEC(type)										\
+	__description("direct packet access: " #name " (non-linear, " type ", " desc ")")	\
+	__success __retval(retval)								\
+	__linear_size(linear_sz)								\
+	__naked void access_non_linear_##name(void)						\
+	{											\
+		asm volatile ("									\
+		r2 = *(u32*)(r1 + %[skb_data]);							\
+		r3 = *(u32*)(r1 + %[skb_data_end]);						\
+		r0 = r2;									\
+		r0 += %[offset];								\
+		if r0 > r3 goto l0_%=;								\
+		r0 = *(u8*)(r0 - 1);								\
+		r0 = 0;										\
+		exit;										\
+	l0_%=:	r0 = 1;										\
+		exit;										\
+	"	:										\
+		: __imm_const(skb_data, offsetof(struct __sk_buff, data)),			\
+		  __imm_const(skb_data_end, offsetof(struct __sk_buff, data_end)),		\
+		  __imm_const(offset, off)							\
+		: __clobber_all);								\
+	}
+
+access_test_non_linear(test31, "tc", "too short eth", 1, ETH_HLEN, 22);
+access_test_non_linear(test32, "tc", "too short 1", 1, 1, 22);
+access_test_non_linear(test33, "tc", "long enough", 0, 22, 22);
+access_test_non_linear(test34, "cgroup_skb/ingress", "too short eth", 1, ETH_HLEN, 8);
+access_test_non_linear(test35, "cgroup_skb/ingress", "too short 1", 1, 1, 8);
+access_test_non_linear(test36, "cgroup_skb/ingress", "long enough", 0, 22, 8);
+
+SEC("tc")
+__description("direct packet access: test37 (non-linear, linearized)")
+__success __retval(0)
+__linear_size(ETH_HLEN)
+__naked void access_non_linear_linearized(void)
+{
+	asm volatile ("				\
+	r6 = r1;				\
+	r2 = 22;				\
+	call %[bpf_skb_pull_data];		\
+	r2 = *(u32*)(r6 + %[skb_data]);		\
+	r3 = *(u32*)(r6 + %[skb_data_end]);	\
+	r0 = r2;				\
+	r0 += 22;				\
+	if r0 > r3 goto l0_%=;			\
+	r0 = *(u8*)(r0 - 1);			\
+	exit;					\
+l0_%=:	r0 = 1;					\
+	exit;					\
+"	:
+	: __imm(bpf_skb_pull_data),
+	  __imm_const(skb_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(skb_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_direct_stack_access_wraparound.c b/tools/testing/selftests/bpf/progs/verifier_direct_stack_access_wraparound.c
new file mode 100644
index 000000000000..c538c6893552
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_direct_stack_access_wraparound.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/direct_stack_access_wraparound.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("socket")
+__description("direct stack access with 32-bit wraparound. test1")
+__failure __msg("fp pointer and 2147483647")
+__failure_unpriv
+__naked void with_32_bit_wraparound_test1(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += 0x7fffffff;				\
+	r1 += 0x7fffffff;				\
+	w0 = 0;						\
+	*(u8*)(r1 + 0) = r0;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("direct stack access with 32-bit wraparound. test2")
+__failure __msg("fp pointer and 1073741823")
+__failure_unpriv
+__naked void with_32_bit_wraparound_test2(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += 0x3fffffff;				\
+	r1 += 0x3fffffff;				\
+	w0 = 0;						\
+	*(u8*)(r1 + 0) = r0;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("direct stack access with 32-bit wraparound. test3")
+__failure __msg("fp pointer offset 1073741822")
+__msg_unpriv("R1 stack pointer arithmetic goes out of range")
+__naked void with_32_bit_wraparound_test3(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += 0x1fffffff;				\
+	r1 += 0x1fffffff;				\
+	w0 = 0;						\
+	*(u8*)(r1 + 0) = r0;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_div0.c b/tools/testing/selftests/bpf/progs/verifier_div0.c
new file mode 100644
index 000000000000..cca5ea18fc28
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_div0.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/div0.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("socket")
+__description("DIV32 by 0, zero check 1")
+__success __success_unpriv __retval(42)
+__naked void by_0_zero_check_1_1(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w1 = 0;						\
+	w2 = 1;						\
+	w2 /= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("DIV32 by 0, zero check 2")
+__success __success_unpriv __retval(42)
+__naked void by_0_zero_check_2_1(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	r1 = 0xffffffff00000000LL ll;			\
+	w2 = 1;						\
+	w2 /= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("DIV64 by 0, zero check")
+__success __success_unpriv __retval(42)
+__naked void div64_by_0_zero_check(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w1 = 0;						\
+	w2 = 1;						\
+	r2 /= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("MOD32 by 0, zero check 1")
+__success __success_unpriv __retval(42)
+__naked void by_0_zero_check_1_2(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w1 = 0;						\
+	w2 = 1;						\
+	w2 %%= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("MOD32 by 0, zero check 2")
+__success __success_unpriv __retval(42)
+__naked void by_0_zero_check_2_2(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	r1 = 0xffffffff00000000LL ll;			\
+	w2 = 1;						\
+	w2 %%= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("MOD64 by 0, zero check")
+__success __success_unpriv __retval(42)
+__naked void mod64_by_0_zero_check(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w1 = 0;						\
+	w2 = 1;						\
+	r2 %%= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tc")
+__description("DIV32 by 0, zero check ok, cls")
+__success __retval(8)
+__naked void _0_zero_check_ok_cls_1(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w1 = 2;						\
+	w2 = 16;					\
+	w2 /= w1;					\
+	r0 = r2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tc")
+__description("DIV32 by 0, zero check 1, cls")
+__success __retval(0)
+__naked void _0_zero_check_1_cls_1(void)
+{
+	asm volatile ("					\
+	w1 = 0;						\
+	w0 = 1;						\
+	w0 /= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tc")
+__description("DIV32 by 0, zero check 2, cls")
+__success __retval(0)
+__naked void _0_zero_check_2_cls_1(void)
+{
+	asm volatile ("					\
+	r1 = 0xffffffff00000000LL ll;			\
+	w0 = 1;						\
+	w0 /= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tc")
+__description("DIV64 by 0, zero check, cls")
+__success __retval(0)
+__naked void by_0_zero_check_cls(void)
+{
+	asm volatile ("					\
+	w1 = 0;						\
+	w0 = 1;						\
+	r0 /= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tc")
+__description("MOD32 by 0, zero check ok, cls")
+__success __retval(2)
+__naked void _0_zero_check_ok_cls_2(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w1 = 3;						\
+	w2 = 5;						\
+	w2 %%= w1;					\
+	r0 = r2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tc")
+__description("MOD32 by 0, zero check 1, cls")
+__success __retval(1)
+__naked void _0_zero_check_1_cls_2(void)
+{
+	asm volatile ("					\
+	w1 = 0;						\
+	w0 = 1;						\
+	w0 %%= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tc")
+__description("MOD32 by 0, zero check 2, cls")
+__success __retval(1)
+__naked void _0_zero_check_2_cls_2(void)
+{
+	asm volatile ("					\
+	r1 = 0xffffffff00000000LL ll;			\
+	w0 = 1;						\
+	w0 %%= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tc")
+__description("MOD64 by 0, zero check 1, cls")
+__success __retval(2)
+__naked void _0_zero_check_1_cls_3(void)
+{
+	asm volatile ("					\
+	w1 = 0;						\
+	w0 = 2;						\
+	r0 %%= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tc")
+__description("MOD64 by 0, zero check 2, cls")
+__success __retval(-1)
+__naked void _0_zero_check_2_cls_3(void)
+{
+	asm volatile ("					\
+	w1 = 0;						\
+	w0 = -1;					\
+	r0 %%= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_div_overflow.c b/tools/testing/selftests/bpf/progs/verifier_div_overflow.c
new file mode 100644
index 000000000000..34e0c012ee76
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_div_overflow.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/div_overflow.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <limits.h>
+#include "bpf_misc.h"
+
+/* Just make sure that JITs used udiv/umod as otherwise we get
+ * an exception from INT_MIN/-1 overflow similarly as with div
+ * by zero.
+ */
+
+SEC("tc")
+__description("DIV32 overflow, check 1")
+__success __retval(0)
+__naked void div32_overflow_check_1(void)
+{
+	asm volatile ("					\
+	w1 = -1;					\
+	w0 = %[int_min];				\
+	w0 /= w1;					\
+	exit;						\
+"	:
+	: __imm_const(int_min, INT_MIN)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("DIV32 overflow, check 2")
+__success __retval(0)
+__naked void div32_overflow_check_2(void)
+{
+	asm volatile ("					\
+	w0 = %[int_min];				\
+	w0 /= -1;					\
+	exit;						\
+"	:
+	: __imm_const(int_min, INT_MIN)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("DIV64 overflow, check 1")
+__success __retval(0)
+__naked void div64_overflow_check_1(void)
+{
+	asm volatile ("					\
+	r1 = -1;					\
+	r2 = %[llong_min] ll;				\
+	r2 /= r1;					\
+	w0 = 0;						\
+	if r0 == r2 goto l0_%=;				\
+	w0 = 1;						\
+l0_%=:	exit;						\
+"	:
+	: __imm_const(llong_min, LLONG_MIN)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("DIV64 overflow, check 2")
+__success __retval(0)
+__naked void div64_overflow_check_2(void)
+{
+	asm volatile ("					\
+	r1 = %[llong_min] ll;				\
+	r1 /= -1;					\
+	w0 = 0;						\
+	if r0 == r1 goto l0_%=;				\
+	w0 = 1;						\
+l0_%=:	exit;						\
+"	:
+	: __imm_const(llong_min, LLONG_MIN)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("MOD32 overflow, check 1")
+__success __retval(_INT_MIN)
+__naked void mod32_overflow_check_1(void)
+{
+	asm volatile ("					\
+	w1 = -1;					\
+	w0 = %[int_min];				\
+	w0 %%= w1;					\
+	exit;						\
+"	:
+	: __imm_const(int_min, INT_MIN)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("MOD32 overflow, check 2")
+__success __retval(_INT_MIN)
+__naked void mod32_overflow_check_2(void)
+{
+	asm volatile ("					\
+	w0 = %[int_min];				\
+	w0 %%= -1;					\
+	exit;						\
+"	:
+	: __imm_const(int_min, INT_MIN)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("MOD64 overflow, check 1")
+__success __retval(1)
+__naked void mod64_overflow_check_1(void)
+{
+	asm volatile ("					\
+	r1 = -1;					\
+	r2 = %[llong_min] ll;				\
+	r3 = r2;					\
+	r2 %%= r1;					\
+	w0 = 0;						\
+	if r3 != r2 goto l0_%=;				\
+	w0 = 1;						\
+l0_%=:	exit;						\
+"	:
+	: __imm_const(llong_min, LLONG_MIN)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("MOD64 overflow, check 2")
+__success __retval(1)
+__naked void mod64_overflow_check_2(void)
+{
+	asm volatile ("					\
+	r2 = %[llong_min] ll;				\
+	r3 = r2;					\
+	r2 %%= -1;					\
+	w0 = 0;						\
+	if r3 != r2 goto l0_%=;				\
+	w0 = 1;						\
+l0_%=:	exit;						\
+"	:
+	: __imm_const(llong_min, LLONG_MIN)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c b/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c
new file mode 100644
index 000000000000..1204fbc58178
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_global_ptr_args.c
@@ -0,0 +1,310 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_misc.h"
+#include "xdp_metadata.h"
+#include "bpf_kfuncs.h"
+
+extern struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym __weak;
+extern void bpf_task_release(struct task_struct *p) __ksym __weak;
+
+__weak int subprog_trusted_task_nullable(struct task_struct *task __arg_trusted __arg_nullable)
+{
+	if (!task)
+		return 0;
+	return task->pid + task->tgid;
+}
+
+__weak int subprog_trusted_task_nullable_extra_layer(struct task_struct *task __arg_trusted __arg_nullable)
+{
+	return subprog_trusted_task_nullable(task) + subprog_trusted_task_nullable(NULL);
+}
+
+SEC("?tp_btf/task_newtask")
+__success __log_level(2)
+__msg("Validating subprog_trusted_task_nullable() func#1...")
+__msg(": R1=trusted_ptr_or_null_task_struct(")
+int trusted_task_arg_nullable(void *ctx)
+{
+	struct task_struct *t1 = bpf_get_current_task_btf();
+	struct task_struct *t2 = bpf_task_acquire(t1);
+	int res = 0;
+
+	/* known NULL */
+	res += subprog_trusted_task_nullable(NULL);
+
+	/* known non-NULL */
+	res += subprog_trusted_task_nullable(t1);
+	res += subprog_trusted_task_nullable_extra_layer(t1);
+
+	/* unknown if NULL or not */
+	res += subprog_trusted_task_nullable(t2);
+	res += subprog_trusted_task_nullable_extra_layer(t2);
+
+	if (t2) {
+		/* known non-NULL after explicit NULL check, just in case */
+		res += subprog_trusted_task_nullable(t2);
+		res += subprog_trusted_task_nullable_extra_layer(t2);
+
+		bpf_task_release(t2);
+	}
+
+	return res;
+}
+
+__weak int subprog_trusted_task_nonnull(struct task_struct *task __arg_trusted)
+{
+	return task->pid + task->tgid;
+}
+
+SEC("?kprobe")
+__failure __log_level(2)
+__msg("R1 type=scalar expected=ptr_, trusted_ptr_, rcu_ptr_")
+__msg("Caller passes invalid args into func#1 ('subprog_trusted_task_nonnull')")
+int trusted_task_arg_nonnull_fail1(void *ctx)
+{
+	return subprog_trusted_task_nonnull(NULL);
+}
+
+SEC("?tp_btf/task_newtask")
+__failure __log_level(2)
+__msg("R1 type=ptr_or_null_ expected=ptr_, trusted_ptr_, rcu_ptr_")
+__msg("Caller passes invalid args into func#1 ('subprog_trusted_task_nonnull')")
+int trusted_task_arg_nonnull_fail2(void *ctx)
+{
+	struct task_struct *t = bpf_get_current_task_btf();
+	struct task_struct *nullable;
+	int res;
+
+	nullable = bpf_task_acquire(t);
+
+	 /* should fail, PTR_TO_BTF_ID_OR_NULL */
+	res = subprog_trusted_task_nonnull(nullable);
+
+	if (nullable)
+		bpf_task_release(nullable);
+
+	return res;
+}
+
+SEC("?kprobe")
+__success __log_level(2)
+__msg("Validating subprog_trusted_task_nonnull() func#1...")
+__msg(": R1=trusted_ptr_task_struct(")
+int trusted_task_arg_nonnull(void *ctx)
+{
+	struct task_struct *t = bpf_get_current_task_btf();
+
+	return subprog_trusted_task_nonnull(t);
+}
+
+struct task_struct___local {} __attribute__((preserve_access_index));
+
+__weak int subprog_nullable_task_flavor(
+	struct task_struct___local *task __arg_trusted __arg_nullable)
+{
+	char buf[16];
+
+	if (!task)
+		return 0;
+
+	return bpf_copy_from_user_task(&buf, sizeof(buf), NULL, (void *)task, 0);
+}
+
+SEC("?uprobe.s")
+__success __log_level(2)
+__msg("Validating subprog_nullable_task_flavor() func#1...")
+__msg(": R1=trusted_ptr_or_null_task_struct(")
+int flavor_ptr_nullable(void *ctx)
+{
+	struct task_struct___local *t = (void *)bpf_get_current_task_btf();
+
+	return subprog_nullable_task_flavor(t);
+}
+
+__weak int subprog_nonnull_task_flavor(struct task_struct___local *task __arg_trusted)
+{
+	char buf[16];
+
+	return bpf_copy_from_user_task(&buf, sizeof(buf), NULL, (void *)task, 0);
+}
+
+SEC("?uprobe.s")
+__success __log_level(2)
+__msg("Validating subprog_nonnull_task_flavor() func#1...")
+__msg(": R1=trusted_ptr_task_struct(")
+int flavor_ptr_nonnull(void *ctx)
+{
+	struct task_struct *t = bpf_get_current_task_btf();
+
+	return subprog_nonnull_task_flavor((void *)t);
+}
+
+__weak int subprog_trusted_destroy(struct task_struct *task __arg_trusted)
+{
+	bpf_task_release(task); /* should be rejected */
+
+	return 0;
+}
+
+SEC("?tp_btf/task_newtask")
+__failure __log_level(2)
+__msg("release kernel function bpf_task_release expects refcounted PTR_TO_BTF_ID")
+int BPF_PROG(trusted_destroy_fail, struct task_struct *task, u64 clone_flags)
+{
+	return subprog_trusted_destroy(task);
+}
+
+__weak int subprog_trusted_acq_rel(struct task_struct *task __arg_trusted)
+{
+	struct task_struct *owned;
+
+	owned = bpf_task_acquire(task);
+	if (!owned)
+		return 0;
+
+	bpf_task_release(owned); /* this one is OK, we acquired it locally */
+
+	return 0;
+}
+
+SEC("?tp_btf/task_newtask")
+__success __log_level(2)
+int BPF_PROG(trusted_acq_rel, struct task_struct *task, u64 clone_flags)
+{
+	return subprog_trusted_acq_rel(task);
+}
+
+__weak int subprog_untrusted_bad_tags(struct task_struct *task __arg_untrusted __arg_nullable)
+{
+	return task->pid;
+}
+
+SEC("tp_btf/sys_enter")
+__failure
+__msg("arg#0 untrusted cannot be combined with any other tags")
+int untrusted_bad_tags(void *ctx)
+{
+	return subprog_untrusted_bad_tags(0);
+}
+
+struct local_type_wont_be_accepted {};
+
+__weak int subprog_untrusted_bad_type(struct local_type_wont_be_accepted *p __arg_untrusted)
+{
+	return 0;
+}
+
+SEC("tp_btf/sys_enter")
+__failure
+__msg("arg#0 reference type('STRUCT local_type_wont_be_accepted') has no matches")
+int untrusted_bad_type(void *ctx)
+{
+	return subprog_untrusted_bad_type(bpf_rdonly_cast(0, 0));
+}
+
+__weak int subprog_untrusted(const volatile struct task_struct *restrict task __arg_untrusted)
+{
+	return task->pid;
+}
+
+SEC("tp_btf/sys_enter")
+__success
+__log_level(2)
+__msg("r1 = {{.*}}; {{.*}}R1=trusted_ptr_task_struct()")
+__msg("Func#1 ('subprog_untrusted') is global and assumed valid.")
+__msg("Validating subprog_untrusted() func#1...")
+__msg(": R1=untrusted_ptr_task_struct")
+int trusted_to_untrusted(void *ctx)
+{
+	return subprog_untrusted(bpf_get_current_task_btf());
+}
+
+char mem[16];
+u32 offset;
+
+SEC("tp_btf/sys_enter")
+__success
+int anything_to_untrusted(void *ctx)
+{
+	/* untrusted to untrusted */
+	subprog_untrusted(bpf_core_cast(0, struct task_struct));
+	/* wrong type to untrusted */
+	subprog_untrusted((void *)bpf_core_cast(0, struct bpf_verifier_env));
+	/* map value to untrusted */
+	subprog_untrusted((void *)mem);
+	/* scalar to untrusted */
+	subprog_untrusted(0);
+	/* variable offset to untrusted (map) */
+	subprog_untrusted((void *)mem + offset);
+	/* variable offset to untrusted (trusted) */
+	subprog_untrusted((void *)bpf_get_current_task_btf() + offset);
+	return 0;
+}
+
+__weak int subprog_untrusted2(struct task_struct *task __arg_untrusted)
+{
+	return subprog_trusted_task_nullable(task);
+}
+
+SEC("tp_btf/sys_enter")
+__failure
+__msg("R1 type=untrusted_ptr_ expected=ptr_, trusted_ptr_, rcu_ptr_")
+__msg("Caller passes invalid args into func#{{.*}} ('subprog_trusted_task_nullable')")
+int untrusted_to_trusted(void *ctx)
+{
+	return subprog_untrusted2(bpf_get_current_task_btf());
+}
+
+__weak int subprog_void_untrusted(void *p __arg_untrusted)
+{
+	return *(int *)p;
+}
+
+__weak int subprog_char_untrusted(char *p __arg_untrusted)
+{
+	return *(int *)p;
+}
+
+__weak int subprog_enum_untrusted(enum bpf_attach_type *p __arg_untrusted)
+{
+	return *(int *)p;
+}
+
+SEC("tp_btf/sys_enter")
+__success
+__log_level(2)
+__msg("r1 = {{.*}}; {{.*}}R1=trusted_ptr_task_struct()")
+__msg("Func#1 ('subprog_void_untrusted') is global and assumed valid.")
+__msg("Validating subprog_void_untrusted() func#1...")
+__msg(": R1=rdonly_untrusted_mem(sz=0)")
+int trusted_to_untrusted_mem(void *ctx)
+{
+	return subprog_void_untrusted(bpf_get_current_task_btf());
+}
+
+SEC("tp_btf/sys_enter")
+__success
+int anything_to_untrusted_mem(void *ctx)
+{
+	/* untrusted to untrusted mem */
+	subprog_void_untrusted(bpf_core_cast(0, struct task_struct));
+	/* map value to untrusted mem */
+	subprog_void_untrusted(mem);
+	/* scalar to untrusted mem */
+	subprog_void_untrusted(0);
+	/* variable offset to untrusted mem (map) */
+	subprog_void_untrusted((void *)mem + offset);
+	/* variable offset to untrusted mem (trusted) */
+	subprog_void_untrusted(bpf_get_current_task_btf() + offset);
+	/* variable offset to untrusted char/enum (map) */
+	subprog_char_untrusted(mem + offset);
+	subprog_enum_untrusted((void *)mem + offset);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
new file mode 100644
index 000000000000..20904cd2baa2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_global_subprogs.c
@@ -0,0 +1,391 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "xdp_metadata.h"
+#include "bpf_kfuncs.h"
+#include "err.h"
+
+/* The compiler may be able to detect the access to uninitialized
+   memory in the routines performing out of bound memory accesses and
+   emit warnings about it.  This is the case of GCC. */
+#if !defined(__clang__)
+#pragma GCC diagnostic ignored "-Wmaybe-uninitialized"
+#endif
+
+int arr[1];
+int unkn_idx;
+const volatile bool call_dead_subprog = false;
+
+__noinline long global_bad(void)
+{
+	return arr[unkn_idx]; /* BOOM */
+}
+
+__noinline long global_good(void)
+{
+	return arr[0];
+}
+
+__noinline long global_calls_bad(void)
+{
+	return global_good() + global_bad() /* does BOOM indirectly */;
+}
+
+__noinline long global_calls_good_only(void)
+{
+	return global_good();
+}
+
+__noinline long global_dead(void)
+{
+	return arr[0] * 2;
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+/* main prog is validated completely first */
+__msg("('global_calls_good_only') is global and assumed valid.")
+/* eventually global_good() is transitively validated as well */
+__msg("Validating global_good() func")
+__msg("('global_good') is safe for any args that match its prototype")
+int chained_global_func_calls_success(void)
+{
+	int sum = 0;
+
+	if (call_dead_subprog)
+		sum += global_dead();
+	return global_calls_good_only() + sum;
+}
+
+SEC("?raw_tp")
+__failure __log_level(2)
+/* main prog validated successfully first */
+__msg("('global_calls_bad') is global and assumed valid.")
+/* eventually we validate global_bad() and fail */
+__msg("Validating global_bad() func")
+__msg("math between map_value pointer and register") /* BOOM */
+int chained_global_func_calls_bad(void)
+{
+	return global_calls_bad();
+}
+
+/* do out of bounds access forcing verifier to fail verification if this
+ * global func is called
+ */
+__noinline int global_unsupp(const int *mem)
+{
+	if (!mem)
+		return 0;
+	return mem[100]; /* BOOM */
+}
+
+const volatile bool skip_unsupp_global = true;
+
+SEC("?raw_tp")
+__success
+int guarded_unsupp_global_called(void)
+{
+	if (!skip_unsupp_global)
+		return global_unsupp(NULL);
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __log_level(2)
+__msg("Func#1 ('global_unsupp') is global and assumed valid.")
+__msg("Validating global_unsupp() func#1...")
+__msg("value is outside of the allowed memory range")
+int unguarded_unsupp_global_called(void)
+{
+	int x = 0;
+
+	return global_unsupp(&x);
+}
+
+long stack[128];
+
+__weak int subprog_nullable_ptr_bad(int *p)
+{
+	return (*p) * 2; /* bad, missing null check */
+}
+
+SEC("?raw_tp")
+__failure __log_level(2)
+__msg("invalid mem access 'mem_or_null'")
+int arg_tag_nullable_ptr_fail(void *ctx)
+{
+	int x = 42;
+
+	return subprog_nullable_ptr_bad(&x);
+}
+
+typedef struct {
+	int x;
+} user_struct_t;
+
+__noinline __weak int subprog_user_anon_mem(user_struct_t *t)
+{
+	return t ? t->x : 0;
+}
+
+SEC("?tracepoint")
+__failure __log_level(2)
+__msg("invalid bpf_context access")
+__msg("Caller passes invalid args into func#1 ('subprog_user_anon_mem')")
+int anon_user_mem_invalid(void *ctx)
+{
+	/* can't pass PTR_TO_CTX as user memory */
+	return subprog_user_anon_mem(ctx);
+}
+
+SEC("?tracepoint")
+__success __log_level(2)
+__msg("Func#1 ('subprog_user_anon_mem') is safe for any args that match its prototype")
+int anon_user_mem_valid(void *ctx)
+{
+	user_struct_t t = { .x = 42 };
+
+	return subprog_user_anon_mem(&t);
+}
+
+__noinline __weak int subprog_nonnull_ptr_good(int *p1 __arg_nonnull, int *p2 __arg_nonnull)
+{
+	return (*p1) * (*p2); /* good, no need for NULL checks */
+}
+
+int x = 47;
+
+SEC("?raw_tp")
+__success __log_level(2)
+int arg_tag_nonnull_ptr_good(void *ctx)
+{
+	int y = 74;
+
+	return subprog_nonnull_ptr_good(&x, &y);
+}
+
+/* this global subprog can be now called from many types of entry progs, each
+ * with different context type
+ */
+__weak int subprog_ctx_tag(void *ctx __arg_ctx)
+{
+	return bpf_get_stack(ctx, stack, sizeof(stack), 0);
+}
+
+__weak int raw_tp_canonical(struct bpf_raw_tracepoint_args *ctx __arg_ctx)
+{
+	return 0;
+}
+
+__weak int raw_tp_u64_array(u64 *ctx __arg_ctx)
+{
+	return 0;
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+int arg_tag_ctx_raw_tp(void *ctx)
+{
+	return subprog_ctx_tag(ctx) + raw_tp_canonical(ctx) + raw_tp_u64_array(ctx);
+}
+
+SEC("?raw_tp.w")
+__success __log_level(2)
+int arg_tag_ctx_raw_tp_writable(void *ctx)
+{
+	return subprog_ctx_tag(ctx) + raw_tp_canonical(ctx) + raw_tp_u64_array(ctx);
+}
+
+SEC("?tp_btf/sys_enter")
+__success __log_level(2)
+int arg_tag_ctx_raw_tp_btf(void *ctx)
+{
+	return subprog_ctx_tag(ctx) + raw_tp_canonical(ctx) + raw_tp_u64_array(ctx);
+}
+
+struct whatever { };
+
+__weak int tp_whatever(struct whatever *ctx __arg_ctx)
+{
+	return 0;
+}
+
+SEC("?tp")
+__success __log_level(2)
+int arg_tag_ctx_tp(void *ctx)
+{
+	return subprog_ctx_tag(ctx) + tp_whatever(ctx);
+}
+
+__weak int kprobe_subprog_pt_regs(struct pt_regs *ctx __arg_ctx)
+{
+	return 0;
+}
+
+__weak int kprobe_subprog_typedef(bpf_user_pt_regs_t *ctx __arg_ctx)
+{
+	return 0;
+}
+
+SEC("?kprobe")
+__success __log_level(2)
+int arg_tag_ctx_kprobe(void *ctx)
+{
+	return subprog_ctx_tag(ctx) +
+	       kprobe_subprog_pt_regs(ctx) +
+	       kprobe_subprog_typedef(ctx);
+}
+
+__weak int perf_subprog_regs(
+#if defined(bpf_target_riscv)
+	struct user_regs_struct *ctx __arg_ctx
+#elif defined(bpf_target_s390)
+	/* user_pt_regs typedef is anonymous struct, so only `void *` works */
+	void *ctx __arg_ctx
+#elif defined(bpf_target_loongarch) || defined(bpf_target_arm64) || defined(bpf_target_powerpc)
+	struct user_pt_regs *ctx __arg_ctx
+#else
+	struct pt_regs *ctx __arg_ctx
+#endif
+)
+{
+	return 0;
+}
+
+__weak int perf_subprog_typedef(bpf_user_pt_regs_t *ctx __arg_ctx)
+{
+	return 0;
+}
+
+__weak int perf_subprog_canonical(struct bpf_perf_event_data *ctx __arg_ctx)
+{
+	return 0;
+}
+
+SEC("?perf_event")
+__success __log_level(2)
+int arg_tag_ctx_perf(void *ctx)
+{
+	return subprog_ctx_tag(ctx) +
+	       perf_subprog_regs(ctx) +
+	       perf_subprog_typedef(ctx) +
+	       perf_subprog_canonical(ctx);
+}
+
+__weak int iter_subprog_void(void *ctx __arg_ctx)
+{
+	return 0;
+}
+
+__weak int iter_subprog_typed(struct bpf_iter__task *ctx __arg_ctx)
+{
+	return 0;
+}
+
+SEC("?iter/task")
+__success __log_level(2)
+int arg_tag_ctx_iter_task(struct bpf_iter__task *ctx)
+{
+	return (iter_subprog_void(ctx) + iter_subprog_typed(ctx)) & 1;
+}
+
+__weak int tracing_subprog_void(void *ctx __arg_ctx)
+{
+	return 0;
+}
+
+__weak int tracing_subprog_u64(u64 *ctx __arg_ctx)
+{
+	return 0;
+}
+
+int acc;
+
+SEC("?fentry/" SYS_PREFIX "sys_nanosleep")
+__success __log_level(2)
+int BPF_PROG(arg_tag_ctx_fentry)
+{
+	acc += tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+	return 0;
+}
+
+SEC("?fexit/" SYS_PREFIX "sys_nanosleep")
+__success __log_level(2)
+int BPF_PROG(arg_tag_ctx_fexit)
+{
+	acc += tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+	return 0;
+}
+
+SEC("?fmod_ret/" SYS_PREFIX "sys_nanosleep")
+__success __log_level(2)
+int BPF_PROG(arg_tag_ctx_fmod_ret)
+{
+	return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+}
+
+SEC("?lsm/bpf")
+__success __log_level(2)
+int BPF_PROG(arg_tag_ctx_lsm)
+{
+	int ret;
+
+	ret = tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+	set_if_not_errno_or_zero(ret, -1);
+	return ret;
+}
+
+SEC("?struct_ops/test_1")
+__success __log_level(2)
+int BPF_PROG(arg_tag_ctx_struct_ops)
+{
+	return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx);
+}
+
+SEC(".struct_ops")
+struct bpf_dummy_ops dummy_1 = {
+	.test_1 = (void *)arg_tag_ctx_struct_ops,
+};
+
+SEC("?syscall")
+__success __log_level(2)
+int arg_tag_ctx_syscall(void *ctx)
+{
+	return tracing_subprog_void(ctx) + tracing_subprog_u64(ctx) + tp_whatever(ctx);
+}
+
+__weak int subprog_dynptr(struct bpf_dynptr *dptr)
+{
+	long *d, t, buf[1] = {};
+
+	d = bpf_dynptr_data(dptr, 0, sizeof(long));
+	if (!d)
+		return 0;
+
+	t = *d + 1;
+
+	d = bpf_dynptr_slice(dptr, 0, &buf, sizeof(long));
+	if (!d)
+		return t;
+
+	t = *d + 2;
+
+	return t;
+}
+
+SEC("?xdp")
+__success __log_level(2)
+int arg_tag_dynptr(struct xdp_md *ctx)
+{
+	struct bpf_dynptr dptr;
+
+	bpf_dynptr_from_xdp(ctx, 0, &dptr);
+
+	return subprog_dynptr(&dptr);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_gotol.c b/tools/testing/selftests/bpf/progs/verifier_gotol.c
new file mode 100644
index 000000000000..d5d8f24df394
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_gotol.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#ifdef CAN_USE_GOTOL
+
+SEC("socket")
+__description("gotol, small_imm")
+__success __success_unpriv __retval(1)
+__naked void gotol_small_imm(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	if r0 == 0 goto l0_%=;				\
+	gotol l1_%=;					\
+l2_%=:							\
+	gotol l3_%=;					\
+l1_%=:							\
+	r0 = 1;						\
+	gotol l2_%=;					\
+l0_%=:							\
+	r0 = 2;						\
+l3_%=:							\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("gotol, large_imm")
+__success __failure_unpriv __retval(40000)
+__naked void gotol_large_imm(void)
+{
+	asm volatile ("					\
+	gotol 1f;					\
+0:							\
+	r0 = 0;						\
+	.rept 40000;					\
+	r0 += 1;					\
+	.endr;						\
+	exit;						\
+1:	gotol 0b;					\
+"	:
+	:
+	: __clobber_all);
+}
+
+#else
+
+SEC("socket")
+__description("cpuv4 is not supported by compiler or jit, use a dummy test")
+__success
+int dummy_test(void)
+{
+	return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_gotox.c b/tools/testing/selftests/bpf/progs/verifier_gotox.c
new file mode 100644
index 000000000000..607dad058ca1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_gotox.c
@@ -0,0 +1,389 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Isovalent */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "../../../include/linux/filter.h"
+
+#if defined(__TARGET_ARCH_x86) || defined(__TARGET_ARCH_arm64)
+
+#define DEFINE_SIMPLE_JUMP_TABLE_PROG(NAME, SRC_REG, OFF, IMM, OUTCOME)	\
+									\
+	SEC("socket")							\
+	OUTCOME								\
+	__naked void jump_table_ ## NAME(void)				\
+	{								\
+		asm volatile ("						\
+		.pushsection .jumptables,\"\",@progbits;		\
+	jt0_%=:								\
+		.quad ret0_%= - socket;					\
+		.quad ret1_%= - socket;					\
+		.size jt0_%=, 16;					\
+		.global jt0_%=;						\
+		.popsection;						\
+									\
+		r0 = jt0_%= ll;						\
+		r0 += 8;						\
+		r0 = *(u64 *)(r0 + 0);					\
+		.8byte %[gotox_r0];					\
+		ret0_%=:						\
+		r0 = 0;							\
+		exit;							\
+		ret1_%=:						\
+		r0 = 1;							\
+		exit;							\
+	"	:							\
+		: __imm_insn(gotox_r0, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_0, (SRC_REG), (OFF) , (IMM))) \
+		: __clobber_all);					\
+	}
+
+/*
+ * The first program which doesn't use reserved fields
+ * loads and works properly. The rest fail to load.
+ */
+DEFINE_SIMPLE_JUMP_TABLE_PROG(ok,                          BPF_REG_0, 0, 0, __success __retval(1))
+DEFINE_SIMPLE_JUMP_TABLE_PROG(reserved_field_src_reg,      BPF_REG_1, 0, 0, __failure __msg("BPF_JA|BPF_X uses reserved fields"))
+DEFINE_SIMPLE_JUMP_TABLE_PROG(reserved_field_non_zero_off, BPF_REG_0, 1, 0, __failure __msg("BPF_JA|BPF_X uses reserved fields"))
+DEFINE_SIMPLE_JUMP_TABLE_PROG(reserved_field_non_zero_imm, BPF_REG_0, 0, 1, __failure __msg("BPF_JA|BPF_X uses reserved fields"))
+
+/*
+ * Gotox is forbidden when there is no jump table loaded
+ * which points to the sub-function where the gotox is used
+ */
+SEC("socket")
+__failure __msg("no jump tables found for subprog starting at 0")
+__naked void jump_table_no_jump_table(void)
+{
+	asm volatile ("						\
+	.8byte %[gotox_r0];					\
+	r0 = 1;							\
+	exit;							\
+"	:							\
+	: __imm_insn(gotox_r0, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_0, 0, 0 , 0))
+	: __clobber_all);
+}
+
+/*
+ * Incorrect type of the target register, only PTR_TO_INSN allowed
+ */
+SEC("socket")
+__failure __msg("R1 has type scalar, expected PTR_TO_INSN")
+__naked void jump_table_incorrect_dst_reg_type(void)
+{
+	asm volatile ("						\
+	.pushsection .jumptables,\"\",@progbits;		\
+jt0_%=:								\
+	.quad ret0_%= - socket;					\
+	.quad ret1_%= - socket;					\
+	.size jt0_%=, 16;					\
+	.global jt0_%=;						\
+	.popsection;						\
+								\
+	r0 = jt0_%= ll;						\
+	r0 += 8;						\
+	r0 = *(u64 *)(r0 + 0);					\
+	r1 = 42;						\
+	.8byte %[gotox_r1];					\
+	ret0_%=:						\
+	r0 = 0;							\
+	exit;							\
+	ret1_%=:						\
+	r0 = 1;							\
+	exit;							\
+"	:							\
+	: __imm_insn(gotox_r1, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_1, 0, 0 , 0))
+	: __clobber_all);
+}
+
+#define DEFINE_INVALID_SIZE_PROG(READ_SIZE, OUTCOME)			\
+									\
+	SEC("socket")							\
+	OUTCOME								\
+	__naked void jump_table_invalid_read_size_ ## READ_SIZE(void)	\
+	{								\
+		asm volatile ("						\
+		.pushsection .jumptables,\"\",@progbits;		\
+	jt0_%=:								\
+		.quad ret0_%= - socket;					\
+		.quad ret1_%= - socket;					\
+		.size jt0_%=, 16;					\
+		.global jt0_%=;						\
+		.popsection;						\
+									\
+		r0 = jt0_%= ll;						\
+		r0 += 8;						\
+		r0 = *(" #READ_SIZE " *)(r0 + 0);			\
+		.8byte %[gotox_r0];					\
+		ret0_%=:						\
+		r0 = 0;							\
+		exit;							\
+		ret1_%=:						\
+		r0 = 1;							\
+		exit;							\
+	"	:							\
+		: __imm_insn(gotox_r0, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_0, 0, 0 , 0)) \
+		: __clobber_all);					\
+	}
+
+DEFINE_INVALID_SIZE_PROG(u32, __failure __msg("Invalid read of 4 bytes from insn_array"))
+DEFINE_INVALID_SIZE_PROG(u16, __failure __msg("Invalid read of 2 bytes from insn_array"))
+DEFINE_INVALID_SIZE_PROG(u8,  __failure __msg("Invalid read of 1 bytes from insn_array"))
+
+SEC("socket")
+__failure __msg("misaligned value access off 0+1+0 size 8")
+__naked void jump_table_misaligned_access(void)
+{
+	asm volatile ("						\
+	.pushsection .jumptables,\"\",@progbits;		\
+jt0_%=:								\
+	.quad ret0_%= - socket;					\
+	.quad ret1_%= - socket;					\
+	.size jt0_%=, 16;					\
+	.global jt0_%=;						\
+	.popsection;						\
+								\
+	r0 = jt0_%= ll;						\
+	r0 += 1;						\
+	r0 = *(u64 *)(r0 + 0);					\
+	.8byte %[gotox_r0];					\
+	ret0_%=:						\
+	r0 = 0;							\
+	exit;							\
+	ret1_%=:						\
+	r0 = 1;							\
+	exit;							\
+"	:							\
+	: __imm_insn(gotox_r0, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_0, 0, 0 , 0))
+	: __clobber_all);
+}
+
+SEC("socket")
+__failure __msg("invalid access to map value, value_size=16 off=24 size=8")
+__naked void jump_table_invalid_mem_acceess_pos(void)
+{
+	asm volatile ("						\
+	.pushsection .jumptables,\"\",@progbits;		\
+jt0_%=:								\
+	.quad ret0_%= - socket;					\
+	.quad ret1_%= - socket;					\
+	.size jt0_%=, 16;					\
+	.global jt0_%=;						\
+	.popsection;						\
+								\
+	r0 = jt0_%= ll;						\
+	r0 += 24;						\
+	r0 = *(u64 *)(r0 + 0);					\
+	.8byte %[gotox_r0];					\
+	ret0_%=:						\
+	r0 = 0;							\
+	exit;							\
+	ret1_%=:						\
+	r0 = 1;							\
+	exit;							\
+"	:							\
+	: __imm_insn(gotox_r0, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_0, 0, 0 , 0))
+	: __clobber_all);
+}
+
+SEC("socket")
+__failure __msg("invalid access to map value, value_size=16 off=-24 size=8")
+__naked void jump_table_invalid_mem_acceess_neg(void)
+{
+	asm volatile ("						\
+	.pushsection .jumptables,\"\",@progbits;		\
+jt0_%=:								\
+	.quad ret0_%= - socket;					\
+	.quad ret1_%= - socket;					\
+	.size jt0_%=, 16;					\
+	.global jt0_%=;						\
+	.popsection;						\
+								\
+	r0 = jt0_%= ll;						\
+	r0 -= 24;						\
+	r0 = *(u64 *)(r0 + 0);					\
+	.8byte %[gotox_r0];					\
+	ret0_%=:						\
+	r0 = 0;							\
+	exit;							\
+	ret1_%=:						\
+	r0 = 1;							\
+	exit;							\
+"	:							\
+	: __imm_insn(gotox_r0, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_0, 0, 0 , 0))
+	: __clobber_all);
+}
+
+SEC("socket")
+__success __retval(1)
+__naked void jump_table_add_sub_ok(void)
+{
+	asm volatile ("						\
+	.pushsection .jumptables,\"\",@progbits;		\
+jt0_%=:								\
+	.quad ret0_%= - socket;					\
+	.quad ret1_%= - socket;					\
+	.size jt0_%=, 16;					\
+	.global jt0_%=;						\
+	.popsection;						\
+								\
+	r0 = jt0_%= ll;						\
+	r0 -= 24;						\
+	r0 += 32;						\
+	r0 = *(u64 *)(r0 + 0);					\
+	.8byte %[gotox_r0];					\
+	ret0_%=:						\
+	r0 = 0;							\
+	exit;							\
+	ret1_%=:						\
+	r0 = 1;							\
+	exit;							\
+"	:							\
+	: __imm_insn(gotox_r0, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_0, 0, 0 , 0))
+	: __clobber_all);
+}
+
+SEC("socket")
+__failure __msg("write into map forbidden, value_size=16 off=8 size=8")
+__naked void jump_table_no_writes(void)
+{
+	asm volatile ("						\
+	.pushsection .jumptables,\"\",@progbits;		\
+jt0_%=:								\
+	.quad ret0_%= - socket;					\
+	.quad ret1_%= - socket;					\
+	.size jt0_%=, 16;					\
+	.global jt0_%=;						\
+	.popsection;						\
+								\
+	r0 = jt0_%= ll;						\
+	r0 += 8;						\
+	r1 = 0xbeef;						\
+	*(u64 *)(r0 + 0) = r1;					\
+	.8byte %[gotox_r0];					\
+	ret0_%=:						\
+	r0 = 0;							\
+	exit;							\
+	ret1_%=:						\
+	r0 = 1;							\
+	exit;							\
+"	:							\
+	: __imm_insn(gotox_r0, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_0, 0, 0 , 0))
+	: __clobber_all);
+}
+
+#define DEFINE_JUMP_TABLE_USE_REG(REG)					\
+	SEC("socket")							\
+	__success __retval(1)						\
+	__naked void jump_table_use_reg_r ## REG(void)			\
+	{								\
+		asm volatile ("						\
+		.pushsection .jumptables,\"\",@progbits;		\
+	jt0_%=:								\
+		.quad ret0_%= - socket;					\
+		.quad ret1_%= - socket;					\
+		.size jt0_%=, 16;					\
+		.global jt0_%=;						\
+		.popsection;						\
+									\
+		r0 = jt0_%= ll;						\
+		r0 += 8;						\
+		r" #REG " = *(u64 *)(r0 + 0);				\
+		.8byte %[gotox_rX];					\
+		ret0_%=:						\
+		r0 = 0;							\
+		exit;							\
+		ret1_%=:						\
+		r0 = 1;							\
+		exit;							\
+	"	:							\
+		: __imm_insn(gotox_rX, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_ ## REG, 0, 0 , 0)) \
+		: __clobber_all);					\
+	}
+
+DEFINE_JUMP_TABLE_USE_REG(0)
+DEFINE_JUMP_TABLE_USE_REG(1)
+DEFINE_JUMP_TABLE_USE_REG(2)
+DEFINE_JUMP_TABLE_USE_REG(3)
+DEFINE_JUMP_TABLE_USE_REG(4)
+DEFINE_JUMP_TABLE_USE_REG(5)
+DEFINE_JUMP_TABLE_USE_REG(6)
+DEFINE_JUMP_TABLE_USE_REG(7)
+DEFINE_JUMP_TABLE_USE_REG(8)
+DEFINE_JUMP_TABLE_USE_REG(9)
+
+__used static int test_subprog(void)
+{
+	return 0;
+}
+
+SEC("socket")
+__failure __msg("jump table for insn 4 points outside of the subprog [0,10]")
+__naked void jump_table_outside_subprog(void)
+{
+	asm volatile ("						\
+	.pushsection .jumptables,\"\",@progbits;		\
+jt0_%=:								\
+	.quad ret0_%= - socket;					\
+	.quad ret1_%= - socket;					\
+	.quad ret_out_%= - socket;				\
+	.size jt0_%=, 24;					\
+	.global jt0_%=;						\
+	.popsection;						\
+								\
+	r0 = jt0_%= ll;						\
+	r0 += 8;						\
+	r0 = *(u64 *)(r0 + 0);					\
+	.8byte %[gotox_r0];					\
+	ret0_%=:						\
+	r0 = 0;							\
+	exit;							\
+	ret1_%=:						\
+	r0 = 1;							\
+	call test_subprog;					\
+	exit;							\
+	ret_out_%=:						\
+"	:							\
+	: __imm_insn(gotox_r0, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_0, 0, 0 , 0))
+	: __clobber_all);
+}
+
+SEC("socket")
+__success __retval(1)
+__naked void jump_table_contains_non_unique_values(void)
+{
+	asm volatile ("						\
+	.pushsection .jumptables,\"\",@progbits;		\
+jt0_%=:								\
+	.quad ret0_%= - socket;					\
+	.quad ret1_%= - socket;					\
+	.quad ret0_%= - socket;					\
+	.quad ret1_%= - socket;					\
+	.quad ret0_%= - socket;					\
+	.quad ret1_%= - socket;					\
+	.quad ret0_%= - socket;					\
+	.quad ret1_%= - socket;					\
+	.quad ret0_%= - socket;					\
+	.quad ret1_%= - socket;					\
+	.size jt0_%=, 80;					\
+	.global jt0_%=;						\
+	.popsection;						\
+								\
+	r0 = jt0_%= ll;						\
+	r0 += 8;						\
+	r0 = *(u64 *)(r0 + 0);					\
+	.8byte %[gotox_r0];					\
+	ret0_%=:						\
+	r0 = 0;							\
+	exit;							\
+	ret1_%=:						\
+	r0 = 1;							\
+	exit;							\
+"	:							\
+	: __imm_insn(gotox_r0, BPF_RAW_INSN(BPF_JMP | BPF_JA | BPF_X, BPF_REG_0, 0, 0 , 0))
+	: __clobber_all);
+}
+
+#endif /* __TARGET_ARCH_x86 || __TARGET_ARCH_arm64 */
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_helper_access_var_len.c b/tools/testing/selftests/bpf/progs/verifier_helper_access_var_len.c
new file mode 100644
index 000000000000..f2c54e4d89eb
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_helper_access_var_len.c
@@ -0,0 +1,825 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/helper_access_var_len.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#define MAX_ENTRIES 11
+
+struct test_val {
+	unsigned int index;
+	int foo[MAX_ENTRIES];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, struct test_val);
+} map_hash_48b SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, long long);
+} map_hash_8b SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_RINGBUF);
+	__uint(max_entries, 4096);
+} map_ringbuf SEC(".maps");
+
+SEC("tracepoint")
+__description("helper access to variable memory: stack, bitwise AND + JMP, correct bounds")
+__success
+__naked void bitwise_and_jmp_correct_bounds(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -64;					\
+	r0 = 0;						\
+	*(u64*)(r10 - 64) = r0;				\
+	*(u64*)(r10 - 56) = r0;				\
+	*(u64*)(r10 - 48) = r0;				\
+	*(u64*)(r10 - 40) = r0;				\
+	*(u64*)(r10 - 32) = r0;				\
+	*(u64*)(r10 - 24) = r0;				\
+	*(u64*)(r10 - 16) = r0;				\
+	*(u64*)(r10 - 8) = r0;				\
+	r2 = 16;					\
+	*(u64*)(r1 - 128) = r2;				\
+	r2 = *(u64*)(r1 - 128);				\
+	r2 &= 64;					\
+	r4 = 0;						\
+	if r4 >= r2 goto l0_%=;				\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("helper access to variable memory: stack, bitwise AND, zero included")
+/* in privileged mode reads from uninitialized stack locations are permitted */
+__success __failure_unpriv
+__msg_unpriv("invalid read from stack R2 off -64+0 size 64")
+__retval(0)
+__naked void stack_bitwise_and_zero_included(void)
+{
+	asm volatile ("					\
+	/* set max stack size */			\
+	r6 = 0;						\
+	*(u64*)(r10 - 128) = r6;			\
+	/* set r3 to a random value */			\
+	call %[bpf_get_prandom_u32];			\
+	r3 = r0;					\
+	/* use bitwise AND to limit r3 range to [0, 64] */\
+	r3 &= 64;					\
+	r1 = %[map_ringbuf] ll;				\
+	r2 = r10;					\
+	r2 += -64;					\
+	r4 = 0;						\
+	/* Call bpf_ringbuf_output(), it is one of a few helper functions with\
+	 * ARG_CONST_SIZE_OR_ZERO parameter allowed in unpriv mode.\
+	 * For unpriv this should signal an error, because memory at &fp[-64] is\
+	 * not initialized.				\
+	 */						\
+	call %[bpf_ringbuf_output];			\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_ringbuf_output),
+	  __imm_addr(map_ringbuf)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to variable memory: stack, bitwise AND + JMP, wrong max")
+__failure __msg("invalid write to stack R1 off=-64 size=65")
+__naked void bitwise_and_jmp_wrong_max(void)
+{
+	asm volatile ("					\
+	r2 = *(u64*)(r1 + 8);				\
+	r1 = r10;					\
+	r1 += -64;					\
+	*(u64*)(r1 - 128) = r2;				\
+	r2 = *(u64*)(r1 - 128);				\
+	r2 &= 65;					\
+	r4 = 0;						\
+	if r4 >= r2 goto l0_%=;				\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to variable memory: stack, JMP, correct bounds")
+__success
+__naked void memory_stack_jmp_correct_bounds(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -64;					\
+	r0 = 0;						\
+	*(u64*)(r10 - 64) = r0;				\
+	*(u64*)(r10 - 56) = r0;				\
+	*(u64*)(r10 - 48) = r0;				\
+	*(u64*)(r10 - 40) = r0;				\
+	*(u64*)(r10 - 32) = r0;				\
+	*(u64*)(r10 - 24) = r0;				\
+	*(u64*)(r10 - 16) = r0;				\
+	*(u64*)(r10 - 8) = r0;				\
+	r2 = 16;					\
+	*(u64*)(r1 - 128) = r2;				\
+	r2 = *(u64*)(r1 - 128);				\
+	if r2 > 64 goto l0_%=;				\
+	r4 = 0;						\
+	if r4 >= r2 goto l0_%=;				\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to variable memory: stack, JMP (signed), correct bounds")
+__success
+__naked void stack_jmp_signed_correct_bounds(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -64;					\
+	r0 = 0;						\
+	*(u64*)(r10 - 64) = r0;				\
+	*(u64*)(r10 - 56) = r0;				\
+	*(u64*)(r10 - 48) = r0;				\
+	*(u64*)(r10 - 40) = r0;				\
+	*(u64*)(r10 - 32) = r0;				\
+	*(u64*)(r10 - 24) = r0;				\
+	*(u64*)(r10 - 16) = r0;				\
+	*(u64*)(r10 - 8) = r0;				\
+	r2 = 16;					\
+	*(u64*)(r1 - 128) = r2;				\
+	r2 = *(u64*)(r1 - 128);				\
+	if r2 s> 64 goto l0_%=;				\
+	r4 = 0;						\
+	if r4 s>= r2 goto l0_%=;			\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to variable memory: stack, JMP, bounds + offset")
+__failure __msg("invalid write to stack R1 off=-64 size=65")
+__naked void memory_stack_jmp_bounds_offset(void)
+{
+	asm volatile ("					\
+	r2 = *(u64*)(r1 + 8);				\
+	r1 = r10;					\
+	r1 += -64;					\
+	*(u64*)(r1 - 128) = r2;				\
+	r2 = *(u64*)(r1 - 128);				\
+	if r2 > 64 goto l0_%=;				\
+	r4 = 0;						\
+	if r4 >= r2 goto l0_%=;				\
+	r2 += 1;					\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to variable memory: stack, JMP, wrong max")
+__failure __msg("invalid write to stack R1 off=-64 size=65")
+__naked void memory_stack_jmp_wrong_max(void)
+{
+	asm volatile ("					\
+	r2 = *(u64*)(r1 + 8);				\
+	r1 = r10;					\
+	r1 += -64;					\
+	*(u64*)(r1 - 128) = r2;				\
+	r2 = *(u64*)(r1 - 128);				\
+	if r2 > 65 goto l0_%=;				\
+	r4 = 0;						\
+	if r4 >= r2 goto l0_%=;				\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to variable memory: stack, JMP, no max check")
+__failure
+/* because max wasn't checked, signed min is negative */
+__msg("R2 min value is negative, either use unsigned or 'var &= const'")
+__naked void stack_jmp_no_max_check(void)
+{
+	asm volatile ("					\
+	r2 = *(u64*)(r1 + 8);				\
+	r1 = r10;					\
+	r1 += -64;					\
+	*(u64*)(r1 - 128) = r2;				\
+	r2 = *(u64*)(r1 - 128);				\
+	r4 = 0;						\
+	if r4 >= r2 goto l0_%=;				\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("helper access to variable memory: stack, JMP, no min check")
+/* in privileged mode reads from uninitialized stack locations are permitted */
+__success __failure_unpriv
+__msg_unpriv("invalid read from stack R2 off -64+0 size 64")
+__retval(0)
+__naked void stack_jmp_no_min_check(void)
+{
+	asm volatile ("					\
+	/* set max stack size */			\
+	r6 = 0;						\
+	*(u64*)(r10 - 128) = r6;			\
+	/* set r3 to a random value */			\
+	call %[bpf_get_prandom_u32];			\
+	r3 = r0;					\
+	/* use JMP to limit r3 range to [0, 64] */	\
+	if r3 > 64 goto l0_%=;				\
+	r1 = %[map_ringbuf] ll;				\
+	r2 = r10;					\
+	r2 += -64;					\
+	r4 = 0;						\
+	/* Call bpf_ringbuf_output(), it is one of a few helper functions with\
+	 * ARG_CONST_SIZE_OR_ZERO parameter allowed in unpriv mode.\
+	 * For unpriv this should signal an error, because memory at &fp[-64] is\
+	 * not initialized.				\
+	 */						\
+	call %[bpf_ringbuf_output];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_ringbuf_output),
+	  __imm_addr(map_ringbuf)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to variable memory: stack, JMP (signed), no min check")
+__failure __msg("R2 min value is negative")
+__naked void jmp_signed_no_min_check(void)
+{
+	asm volatile ("					\
+	r2 = *(u64*)(r1 + 8);				\
+	r1 = r10;					\
+	r1 += -64;					\
+	*(u64*)(r1 - 128) = r2;				\
+	r2 = *(u64*)(r1 - 128);				\
+	if r2 s> 64 goto l0_%=;				\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+	r0 = 0;						\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to variable memory: map, JMP, correct bounds")
+__success
+__naked void memory_map_jmp_correct_bounds(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r2 = %[sizeof_test_val];			\
+	*(u64*)(r10 - 128) = r2;			\
+	r2 = *(u64*)(r10 - 128);			\
+	if r2 s> %[sizeof_test_val] goto l1_%=;		\
+	r4 = 0;						\
+	if r4 s>= r2 goto l1_%=;			\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l1_%=:	r0 = 0;						\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(sizeof_test_val, sizeof(struct test_val))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to variable memory: map, JMP, wrong max")
+__failure __msg("invalid access to map value, value_size=48 off=0 size=49")
+__naked void memory_map_jmp_wrong_max(void)
+{
+	asm volatile ("					\
+	r6 = *(u64*)(r1 + 8);				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r2 = r6;					\
+	*(u64*)(r10 - 128) = r2;			\
+	r2 = *(u64*)(r10 - 128);			\
+	if r2 s> %[__imm_0] goto l1_%=;			\
+	r4 = 0;						\
+	if r4 s>= r2 goto l1_%=;			\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l1_%=:	r0 = 0;						\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(__imm_0, sizeof(struct test_val) + 1)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to variable memory: map adjusted, JMP, correct bounds")
+__success
+__naked void map_adjusted_jmp_correct_bounds(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r1 += 20;					\
+	r2 = %[sizeof_test_val];			\
+	*(u64*)(r10 - 128) = r2;			\
+	r2 = *(u64*)(r10 - 128);			\
+	if r2 s> %[__imm_0] goto l1_%=;			\
+	r4 = 0;						\
+	if r4 s>= r2 goto l1_%=;			\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l1_%=:	r0 = 0;						\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(__imm_0, sizeof(struct test_val) - 20),
+	  __imm_const(sizeof_test_val, sizeof(struct test_val))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to variable memory: map adjusted, JMP, wrong max")
+__failure __msg("R1 min value is outside of the allowed memory range")
+__naked void map_adjusted_jmp_wrong_max(void)
+{
+	asm volatile ("					\
+	r6 = *(u64*)(r1 + 8);				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r1 += 20;					\
+	r2 = r6;					\
+	*(u64*)(r10 - 128) = r2;			\
+	r2 = *(u64*)(r10 - 128);			\
+	if r2 s> %[__imm_0] goto l1_%=;			\
+	r4 = 0;						\
+	if r4 s>= r2 goto l1_%=;			\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l1_%=:	r0 = 0;						\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(__imm_0, sizeof(struct test_val) - 19)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to variable memory: size = 0 allowed on NULL (ARG_PTR_TO_MEM_OR_NULL)")
+__success __retval(0)
+__naked void ptr_to_mem_or_null_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	r2 = 0;						\
+	r3 = 0;						\
+	r4 = 0;						\
+	r5 = 0;						\
+	call %[bpf_csum_diff];				\
+	exit;						\
+"	:
+	: __imm(bpf_csum_diff)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to variable memory: size > 0 not allowed on NULL (ARG_PTR_TO_MEM_OR_NULL)")
+__failure __msg("R1 type=scalar expected=fp")
+__naked void ptr_to_mem_or_null_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + 0);				\
+	r1 = 0;						\
+	*(u64*)(r10 - 128) = r2;			\
+	r2 = *(u64*)(r10 - 128);			\
+	r2 &= 64;					\
+	r3 = 0;						\
+	r4 = 0;						\
+	r5 = 0;						\
+	call %[bpf_csum_diff];				\
+	exit;						\
+"	:
+	: __imm(bpf_csum_diff)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to variable memory: size = 0 allowed on != NULL stack pointer (ARG_PTR_TO_MEM_OR_NULL)")
+__success __retval(0)
+__naked void ptr_to_mem_or_null_3(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -8;					\
+	r2 = 0;						\
+	*(u64*)(r1 + 0) = r2;				\
+	r2 &= 8;					\
+	r3 = 0;						\
+	r4 = 0;						\
+	r5 = 0;						\
+	call %[bpf_csum_diff];				\
+	exit;						\
+"	:
+	: __imm(bpf_csum_diff)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to variable memory: size = 0 allowed on != NULL map pointer (ARG_PTR_TO_MEM_OR_NULL)")
+__success __retval(0)
+__naked void ptr_to_mem_or_null_4(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r2 = 0;						\
+	r3 = 0;						\
+	r4 = 0;						\
+	r5 = 0;						\
+	call %[bpf_csum_diff];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_csum_diff),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to variable memory: size possible = 0 allowed on != NULL stack pointer (ARG_PTR_TO_MEM_OR_NULL)")
+__success __retval(0)
+__naked void ptr_to_mem_or_null_5(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r2 = *(u64*)(r0 + 0);				\
+	if r2 > 8 goto l0_%=;				\
+	r1 = r10;					\
+	r1 += -8;					\
+	*(u64*)(r1 + 0) = r2;				\
+	r3 = 0;						\
+	r4 = 0;						\
+	r5 = 0;						\
+	call %[bpf_csum_diff];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_csum_diff),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to variable memory: size possible = 0 allowed on != NULL map pointer (ARG_PTR_TO_MEM_OR_NULL)")
+__success __retval(0)
+__naked void ptr_to_mem_or_null_6(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r2 = *(u64*)(r0 + 0);				\
+	if r2 > 8 goto l0_%=;				\
+	r3 = 0;						\
+	r4 = 0;						\
+	r5 = 0;						\
+	call %[bpf_csum_diff];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_csum_diff),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to variable memory: size possible = 0 allowed on != NULL packet pointer (ARG_PTR_TO_MEM_OR_NULL)")
+__success __retval(0)
+/* csum_diff of 64-byte packet */
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void ptr_to_mem_or_null_7(void)
+{
+	asm volatile ("					\
+	r6 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r6;					\
+	r0 += 8;					\
+	if r0 > r3 goto l0_%=;				\
+	r1 = r6;					\
+	r2 = *(u64*)(r6 + 0);				\
+	if r2 > 8 goto l0_%=;				\
+	r3 = 0;						\
+	r4 = 0;						\
+	r5 = 0;						\
+	call %[bpf_csum_diff];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_csum_diff),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to variable memory: size = 0 not allowed on NULL (!ARG_PTR_TO_MEM_OR_NULL)")
+__failure __msg("R1 type=scalar expected=fp")
+__naked void ptr_to_mem_or_null_8(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	r2 = 0;						\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+	exit;						\
+"	:
+	: __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to variable memory: size > 0 not allowed on NULL (!ARG_PTR_TO_MEM_OR_NULL)")
+__failure __msg("R1 type=scalar expected=fp")
+__naked void ptr_to_mem_or_null_9(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	r2 = 1;						\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+	exit;						\
+"	:
+	: __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to variable memory: size = 0 allowed on != NULL stack pointer (!ARG_PTR_TO_MEM_OR_NULL)")
+__success
+__naked void ptr_to_mem_or_null_10(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -8;					\
+	r2 = 0;						\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+	exit;						\
+"	:
+	: __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to variable memory: size = 0 allowed on != NULL map pointer (!ARG_PTR_TO_MEM_OR_NULL)")
+__success
+__naked void ptr_to_mem_or_null_11(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r2 = 0;						\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to variable memory: size possible = 0 allowed on != NULL stack pointer (!ARG_PTR_TO_MEM_OR_NULL)")
+__success
+__naked void ptr_to_mem_or_null_12(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r2 = *(u64*)(r0 + 0);				\
+	if r2 > 8 goto l0_%=;				\
+	r1 = r10;					\
+	r1 += -8;					\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to variable memory: size possible = 0 allowed on != NULL map pointer (!ARG_PTR_TO_MEM_OR_NULL)")
+__success
+__naked void ptr_to_mem_or_null_13(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r2 = *(u64*)(r0 + 0);				\
+	if r2 > 8 goto l0_%=;				\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("helper access to variable memory: 8 bytes leak")
+/* in privileged mode reads from uninitialized stack locations are permitted */
+__success __failure_unpriv
+__msg_unpriv("invalid read from stack R2 off -64+32 size 64")
+__retval(0)
+__naked void variable_memory_8_bytes_leak(void)
+{
+	asm volatile ("					\
+	/* set max stack size */			\
+	r6 = 0;						\
+	*(u64*)(r10 - 128) = r6;			\
+	/* set r3 to a random value */			\
+	call %[bpf_get_prandom_u32];			\
+	r3 = r0;					\
+	r1 = %[map_ringbuf] ll;				\
+	r2 = r10;					\
+	r2 += -64;					\
+	r0 = 0;						\
+	*(u64*)(r10 - 64) = r0;				\
+	*(u64*)(r10 - 56) = r0;				\
+	*(u64*)(r10 - 48) = r0;				\
+	*(u64*)(r10 - 40) = r0;				\
+	/* Note: fp[-32] left uninitialized */		\
+	*(u64*)(r10 - 24) = r0;				\
+	*(u64*)(r10 - 16) = r0;				\
+	*(u64*)(r10 - 8) = r0;				\
+	/* Limit r3 range to [1, 64] */			\
+	r3 &= 63;					\
+	r3 += 1;					\
+	r4 = 0;						\
+	/* Call bpf_ringbuf_output(), it is one of a few helper functions with\
+	 * ARG_CONST_SIZE_OR_ZERO parameter allowed in unpriv mode.\
+	 * For unpriv this should signal an error, because memory region [1, 64]\
+	 * at &fp[-64] is not fully initialized.	\
+	 */						\
+	call %[bpf_ringbuf_output];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_ringbuf_output),
+	  __imm_addr(map_ringbuf)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to variable memory: 8 bytes no leak (init memory)")
+__success
+__naked void bytes_no_leak_init_memory(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r0 = 0;						\
+	r0 = 0;						\
+	*(u64*)(r10 - 64) = r0;				\
+	*(u64*)(r10 - 56) = r0;				\
+	*(u64*)(r10 - 48) = r0;				\
+	*(u64*)(r10 - 40) = r0;				\
+	*(u64*)(r10 - 32) = r0;				\
+	*(u64*)(r10 - 24) = r0;				\
+	*(u64*)(r10 - 16) = r0;				\
+	*(u64*)(r10 - 8) = r0;				\
+	r1 += -64;					\
+	r2 = 0;						\
+	r2 &= 32;					\
+	r2 += 32;					\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+	r1 = *(u64*)(r10 - 16);				\
+	exit;						\
+"	:
+	: __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_helper_packet_access.c b/tools/testing/selftests/bpf/progs/verifier_helper_packet_access.c
new file mode 100644
index 000000000000..74f5f9cd153d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_helper_packet_access.c
@@ -0,0 +1,550 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/helper_packet_access.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, long long);
+} map_hash_8b SEC(".maps");
+
+SEC("xdp")
+__description("helper access to packet: test1, valid packet_ptr range")
+__success __retval(0)
+__naked void test1_valid_packet_ptr_range(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 > r3 goto l0_%=;				\
+	r1 = %[map_hash_8b] ll;				\
+	r3 = r2;					\
+	r4 = 0;						\
+	call %[bpf_map_update_elem];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_update_elem),
+	  __imm_addr(map_hash_8b),
+	  __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("helper access to packet: test2, unchecked packet_ptr")
+__failure __msg("invalid access to packet")
+__naked void packet_test2_unchecked_packet_ptr(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b),
+	  __imm_const(xdp_md_data, offsetof(struct xdp_md, data))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("helper access to packet: test3, variable add")
+__success __retval(0)
+__naked void to_packet_test3_variable_add(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r4 = r2;					\
+	r4 += 8;					\
+	if r4 > r3 goto l0_%=;				\
+	r5 = *(u8*)(r2 + 0);				\
+	r4 = r2;					\
+	r4 += r5;					\
+	r5 = r4;					\
+	r5 += 8;					\
+	if r5 > r3 goto l0_%=;				\
+	r1 = %[map_hash_8b] ll;				\
+	r2 = r4;					\
+	call %[bpf_map_lookup_elem];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b),
+	  __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("helper access to packet: test4, packet_ptr with bad range")
+__failure __msg("invalid access to packet")
+__naked void packet_ptr_with_bad_range_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r4 = r2;					\
+	r4 += 4;					\
+	if r4 > r3 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b),
+	  __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("helper access to packet: test5, packet_ptr with too short range")
+__failure __msg("invalid access to packet")
+__naked void ptr_with_too_short_range_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r2 += 1;					\
+	r4 = r2;					\
+	r4 += 7;					\
+	if r4 > r3 goto l0_%=;				\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b),
+	  __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to packet: test6, cls valid packet_ptr range")
+__success __retval(0)
+__naked void cls_valid_packet_ptr_range(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 > r3 goto l0_%=;				\
+	r1 = %[map_hash_8b] ll;				\
+	r3 = r2;					\
+	r4 = 0;						\
+	call %[bpf_map_update_elem];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_update_elem),
+	  __imm_addr(map_hash_8b),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to packet: test7, cls unchecked packet_ptr")
+__failure __msg("invalid access to packet")
+__naked void test7_cls_unchecked_packet_ptr(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to packet: test8, cls variable add")
+__success __retval(0)
+__naked void packet_test8_cls_variable_add(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r4 = r2;					\
+	r4 += 8;					\
+	if r4 > r3 goto l0_%=;				\
+	r5 = *(u8*)(r2 + 0);				\
+	r4 = r2;					\
+	r4 += r5;					\
+	r5 = r4;					\
+	r5 += 8;					\
+	if r5 > r3 goto l0_%=;				\
+	r1 = %[map_hash_8b] ll;				\
+	r2 = r4;					\
+	call %[bpf_map_lookup_elem];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to packet: test9, cls packet_ptr with bad range")
+__failure __msg("invalid access to packet")
+__naked void packet_ptr_with_bad_range_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r4 = r2;					\
+	r4 += 4;					\
+	if r4 > r3 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to packet: test10, cls packet_ptr with too short range")
+__failure __msg("invalid access to packet")
+__naked void ptr_with_too_short_range_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r2 += 1;					\
+	r4 = r2;					\
+	r4 += 7;					\
+	if r4 > r3 goto l0_%=;				\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to packet: test11, cls unsuitable helper 1")
+__failure __msg("helper access to the packet")
+__naked void test11_cls_unsuitable_helper_1(void)
+{
+	asm volatile ("					\
+	r6 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r7 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r6 += 1;					\
+	r3 = r6;					\
+	r3 += 7;					\
+	if r3 > r7 goto l0_%=;				\
+	r2 = 0;						\
+	r4 = 42;					\
+	r5 = 0;						\
+	call %[bpf_skb_store_bytes];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_skb_store_bytes),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to packet: test12, cls unsuitable helper 2")
+__failure __msg("helper access to the packet")
+__naked void test12_cls_unsuitable_helper_2(void)
+{
+	asm volatile ("					\
+	r6 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r7 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r3 = r6;					\
+	r6 += 8;					\
+	if r6 > r7 goto l0_%=;				\
+	r2 = 0;						\
+	r4 = 4;						\
+	call %[bpf_skb_load_bytes];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_skb_load_bytes),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to packet: test13, cls helper ok")
+__success __retval(0)
+__naked void packet_test13_cls_helper_ok(void)
+{
+	asm volatile ("					\
+	r6 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r7 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r6 += 1;					\
+	r1 = r6;					\
+	r1 += 7;					\
+	if r1 > r7 goto l0_%=;				\
+	r1 = r6;					\
+	r2 = 4;						\
+	r3 = 0;						\
+	r4 = 0;						\
+	r5 = 0;						\
+	call %[bpf_csum_diff];				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_csum_diff),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to packet: test14, cls helper ok sub")
+__success __retval(0)
+__naked void test14_cls_helper_ok_sub(void)
+{
+	asm volatile ("					\
+	r6 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r7 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r6 += 1;					\
+	r1 = r6;					\
+	r1 += 7;					\
+	if r1 > r7 goto l0_%=;				\
+	r1 -= 4;					\
+	r2 = 4;						\
+	r3 = 0;						\
+	r4 = 0;						\
+	r5 = 0;						\
+	call %[bpf_csum_diff];				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_csum_diff),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to packet: test15, cls helper fail sub")
+__failure __msg("invalid access to packet")
+__naked void test15_cls_helper_fail_sub(void)
+{
+	asm volatile ("					\
+	r6 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r7 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r6 += 1;					\
+	r1 = r6;					\
+	r1 += 7;					\
+	if r1 > r7 goto l0_%=;				\
+	r1 -= 12;					\
+	r2 = 4;						\
+	r3 = 0;						\
+	r4 = 0;						\
+	r5 = 0;						\
+	call %[bpf_csum_diff];				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_csum_diff),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to packet: test16, cls helper fail range 1")
+__failure __msg("invalid access to packet")
+__naked void cls_helper_fail_range_1(void)
+{
+	asm volatile ("					\
+	r6 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r7 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r6 += 1;					\
+	r1 = r6;					\
+	r1 += 7;					\
+	if r1 > r7 goto l0_%=;				\
+	r1 = r6;					\
+	r2 = 8;						\
+	r3 = 0;						\
+	r4 = 0;						\
+	r5 = 0;						\
+	call %[bpf_csum_diff];				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_csum_diff),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to packet: test17, cls helper fail range 2")
+__failure __msg("R2 min value is negative")
+__naked void cls_helper_fail_range_2(void)
+{
+	asm volatile ("					\
+	r6 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r7 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r6 += 1;					\
+	r1 = r6;					\
+	r1 += 7;					\
+	if r1 > r7 goto l0_%=;				\
+	r1 = r6;					\
+	r2 = -9;					\
+	r3 = 0;						\
+	r4 = 0;						\
+	r5 = 0;						\
+	call %[bpf_csum_diff];				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_csum_diff),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to packet: test18, cls helper fail range 3")
+__failure __msg("R2 min value is negative")
+__naked void cls_helper_fail_range_3(void)
+{
+	asm volatile ("					\
+	r6 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r7 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r6 += 1;					\
+	r1 = r6;					\
+	r1 += 7;					\
+	if r1 > r7 goto l0_%=;				\
+	r1 = r6;					\
+	r2 = %[__imm_0];				\
+	r3 = 0;						\
+	r4 = 0;						\
+	r5 = 0;						\
+	call %[bpf_csum_diff];				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_csum_diff),
+	  __imm_const(__imm_0, ~0),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to packet: test19, cls helper range zero")
+__success __retval(0)
+__naked void test19_cls_helper_range_zero(void)
+{
+	asm volatile ("					\
+	r6 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r7 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r6 += 1;					\
+	r1 = r6;					\
+	r1 += 7;					\
+	if r1 > r7 goto l0_%=;				\
+	r1 = r6;					\
+	r2 = 0;						\
+	r3 = 0;						\
+	r4 = 0;						\
+	r5 = 0;						\
+	call %[bpf_csum_diff];				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_csum_diff),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to packet: test20, pkt end as input")
+__failure __msg("R1 type=pkt_end expected=fp")
+__naked void test20_pkt_end_as_input(void)
+{
+	asm volatile ("					\
+	r6 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r7 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r6 += 1;					\
+	r1 = r6;					\
+	r1 += 7;					\
+	if r1 > r7 goto l0_%=;				\
+	r1 = r7;					\
+	r2 = 4;						\
+	r3 = 0;						\
+	r4 = 0;						\
+	r5 = 0;						\
+	call %[bpf_csum_diff];				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_csum_diff),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("helper access to packet: test21, wrong reg")
+__failure __msg("invalid access to packet")
+__naked void to_packet_test21_wrong_reg(void)
+{
+	asm volatile ("					\
+	r6 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r7 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r6 += 1;					\
+	r1 = r6;					\
+	r1 += 7;					\
+	if r1 > r7 goto l0_%=;				\
+	r2 = 4;						\
+	r3 = 0;						\
+	r4 = 0;						\
+	r5 = 0;						\
+	call %[bpf_csum_diff];				\
+	r0 = 0;						\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_csum_diff),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_helper_restricted.c b/tools/testing/selftests/bpf/progs/verifier_helper_restricted.c
new file mode 100644
index 000000000000..059aa716e3d0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_helper_restricted.c
@@ -0,0 +1,279 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/helper_restricted.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct val {
+	int cnt;
+	struct bpf_spin_lock l;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct val);
+} map_spin_lock SEC(".maps");
+
+struct timer {
+	struct bpf_timer t;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct timer);
+} map_timer SEC(".maps");
+
+SEC("kprobe")
+__description("bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_KPROBE")
+__failure __msg("program of this type cannot use helper bpf_ktime_get_coarse_ns")
+__naked void in_bpf_prog_type_kprobe_1(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_coarse_ns];		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_coarse_ns)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_TRACEPOINT")
+__failure __msg("program of this type cannot use helper bpf_ktime_get_coarse_ns")
+__naked void in_bpf_prog_type_tracepoint_1(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_coarse_ns];		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_coarse_ns)
+	: __clobber_all);
+}
+
+SEC("perf_event")
+__description("bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_PERF_EVENT")
+__failure __msg("program of this type cannot use helper bpf_ktime_get_coarse_ns")
+__naked void bpf_prog_type_perf_event_1(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_coarse_ns];		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_coarse_ns)
+	: __clobber_all);
+}
+
+SEC("raw_tracepoint")
+__description("bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT")
+__failure __msg("program of this type cannot use helper bpf_ktime_get_coarse_ns")
+__naked void bpf_prog_type_raw_tracepoint_1(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_coarse_ns];		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_coarse_ns)
+	: __clobber_all);
+}
+
+SEC("kprobe")
+__description("bpf_timer_init isn restricted in BPF_PROG_TYPE_KPROBE")
+__failure __msg("tracing progs cannot use bpf_timer yet")
+__naked void in_bpf_prog_type_kprobe_2(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_timer] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r2 = %[map_timer] ll;				\
+	r3 = 1;						\
+l0_%=:	call %[bpf_timer_init];				\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_timer_init),
+	  __imm_addr(map_timer)
+	: __clobber_all);
+}
+
+SEC("perf_event")
+__description("bpf_timer_init is forbidden in BPF_PROG_TYPE_PERF_EVENT")
+__failure __msg("tracing progs cannot use bpf_timer yet")
+__naked void bpf_prog_type_perf_event_2(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_timer] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r2 = %[map_timer] ll;				\
+	r3 = 1;						\
+l0_%=:	call %[bpf_timer_init];				\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_timer_init),
+	  __imm_addr(map_timer)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("bpf_timer_init is forbidden in BPF_PROG_TYPE_TRACEPOINT")
+__failure __msg("tracing progs cannot use bpf_timer yet")
+__naked void in_bpf_prog_type_tracepoint_2(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_timer] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r2 = %[map_timer] ll;				\
+	r3 = 1;						\
+l0_%=:	call %[bpf_timer_init];				\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_timer_init),
+	  __imm_addr(map_timer)
+	: __clobber_all);
+}
+
+SEC("raw_tracepoint")
+__description("bpf_timer_init is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT")
+__failure __msg("tracing progs cannot use bpf_timer yet")
+__naked void bpf_prog_type_raw_tracepoint_2(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_timer] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r2 = %[map_timer] ll;				\
+	r3 = 1;						\
+l0_%=:	call %[bpf_timer_init];				\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_timer_init),
+	  __imm_addr(map_timer)
+	: __clobber_all);
+}
+
+SEC("kprobe")
+__description("bpf_spin_lock is forbidden in BPF_PROG_TYPE_KPROBE")
+__failure __msg("tracing progs cannot use bpf_spin_lock yet")
+__naked void in_bpf_prog_type_kprobe_3(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_spin_lock] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	call %[bpf_spin_lock];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_spin_lock),
+	  __imm_addr(map_spin_lock)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("bpf_spin_lock is forbidden in BPF_PROG_TYPE_TRACEPOINT")
+__failure __msg("tracing progs cannot use bpf_spin_lock yet")
+__naked void in_bpf_prog_type_tracepoint_3(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_spin_lock] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	call %[bpf_spin_lock];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_spin_lock),
+	  __imm_addr(map_spin_lock)
+	: __clobber_all);
+}
+
+SEC("perf_event")
+__description("bpf_spin_lock is forbidden in BPF_PROG_TYPE_PERF_EVENT")
+__failure __msg("tracing progs cannot use bpf_spin_lock yet")
+__naked void bpf_prog_type_perf_event_3(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_spin_lock] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	call %[bpf_spin_lock];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_spin_lock),
+	  __imm_addr(map_spin_lock)
+	: __clobber_all);
+}
+
+SEC("raw_tracepoint")
+__description("bpf_spin_lock is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT")
+__failure __msg("tracing progs cannot use bpf_spin_lock yet")
+__naked void bpf_prog_type_raw_tracepoint_3(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_spin_lock] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	call %[bpf_spin_lock];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_spin_lock),
+	  __imm_addr(map_spin_lock)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c b/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c
new file mode 100644
index 000000000000..886498b5e6f3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_helper_value_access.c
@@ -0,0 +1,1282 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/helper_value_access.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct other_val {
+	long long foo;
+	long long bar;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, struct other_val);
+} map_hash_16b SEC(".maps");
+
+#define MAX_ENTRIES 11
+
+struct test_val {
+	unsigned int index;
+	int foo[MAX_ENTRIES];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, struct test_val);
+} map_hash_48b SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, long long);
+} map_hash_8b SEC(".maps");
+
+SEC("tracepoint")
+__description("helper access to map: full range")
+__success
+__naked void access_to_map_full_range(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r2 = %[sizeof_test_val];			\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(sizeof_test_val, sizeof(struct test_val))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to map: partial range")
+__success
+__naked void access_to_map_partial_range(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r2 = 8;						\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+/* Call a function taking a pointer and a size which doesn't allow the size to
+ * be zero (i.e. bpf_trace_printk() declares the second argument to be
+ * ARG_CONST_SIZE, not ARG_CONST_SIZE_OR_ZERO). We attempt to pass zero for the
+ * size and expect to fail.
+ */
+SEC("tracepoint")
+__description("helper access to map: empty range")
+__failure __msg("R2 invalid zero-sized read: u64=[0,0]")
+__naked void access_to_map_empty_range(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r2 = 0;						\
+	call %[bpf_trace_printk];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_trace_printk),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+/* Like the test above, but this time the size register is not known to be zero;
+ * its lower-bound is zero though, which is still unacceptable.
+ */
+SEC("tracepoint")
+__description("helper access to map: possibly-empty ange")
+__failure __msg("R2 invalid zero-sized read: u64=[0,4]")
+__naked void access_to_map_possibly_empty_range(void)
+{
+	asm volatile ("                                         \
+	r2 = r10;                                               \
+	r2 += -8;                                               \
+	r1 = 0;                                                 \
+	*(u64*)(r2 + 0) = r1;                                   \
+	r1 = %[map_hash_48b] ll;                                \
+	call %[bpf_map_lookup_elem];                            \
+	if r0 == 0 goto l0_%=;                                  \
+	r1 = r0;                                                \
+	/* Read an unknown value */                             \
+	r7 = *(u64*)(r0 + 0);                                   \
+	/* Make it small and positive, to avoid other errors */ \
+	r7 &= 4;                                                \
+	r2 = 0;                                                 \
+	r2 += r7;                                               \
+	call %[bpf_trace_printk];                               \
+l0_%=:	exit;                                               \
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_trace_printk),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to map: out-of-bound range")
+__failure __msg("invalid access to map value, value_size=48 off=0 size=56")
+__naked void map_out_of_bound_range(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r2 = %[__imm_0];				\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(__imm_0, sizeof(struct test_val) + 8)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to map: negative range")
+__failure __msg("R2 min value is negative")
+__naked void access_to_map_negative_range(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r2 = -8;					\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to adjusted map (via const imm): full range")
+__success
+__naked void via_const_imm_full_range(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r1 += %[test_val_foo];				\
+	r2 = %[__imm_0];				\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(__imm_0, sizeof(struct test_val) - offsetof(struct test_val, foo)),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to adjusted map (via const imm): partial range")
+__success
+__naked void via_const_imm_partial_range(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r1 += %[test_val_foo];				\
+	r2 = 8;						\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to adjusted map (via const imm): empty range")
+__failure __msg("R2 invalid zero-sized read")
+__naked void via_const_imm_empty_range(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r1 += %[test_val_foo];				\
+	r2 = 0;						\
+	call %[bpf_trace_printk];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_trace_printk),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to adjusted map (via const imm): out-of-bound range")
+__failure __msg("invalid access to map value, value_size=48 off=4 size=52")
+__naked void imm_out_of_bound_range(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r1 += %[test_val_foo];				\
+	r2 = %[__imm_0];				\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(__imm_0, sizeof(struct test_val) - offsetof(struct test_val, foo) + 8),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to adjusted map (via const imm): negative range (> adjustment)")
+__failure __msg("R2 min value is negative")
+__naked void const_imm_negative_range_adjustment_1(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r1 += %[test_val_foo];				\
+	r2 = -8;					\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to adjusted map (via const imm): negative range (< adjustment)")
+__failure __msg("R2 min value is negative")
+__naked void const_imm_negative_range_adjustment_2(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r1 += %[test_val_foo];				\
+	r2 = -1;					\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to adjusted map (via const reg): full range")
+__success
+__naked void via_const_reg_full_range(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r3 = %[test_val_foo];				\
+	r1 += r3;					\
+	r2 = %[__imm_0];				\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(__imm_0, sizeof(struct test_val) - offsetof(struct test_val, foo)),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to adjusted map (via const reg): partial range")
+__success
+__naked void via_const_reg_partial_range(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r3 = %[test_val_foo];				\
+	r1 += r3;					\
+	r2 = 8;						\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to adjusted map (via const reg): empty range")
+__failure __msg("R2 invalid zero-sized read")
+__naked void via_const_reg_empty_range(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r3 = 0;						\
+	r1 += r3;					\
+	r2 = 0;						\
+	call %[bpf_trace_printk];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_trace_printk),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to adjusted map (via const reg): out-of-bound range")
+__failure __msg("invalid access to map value, value_size=48 off=4 size=52")
+__naked void reg_out_of_bound_range(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r3 = %[test_val_foo];				\
+	r1 += r3;					\
+	r2 = %[__imm_0];				\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(__imm_0, sizeof(struct test_val) - offsetof(struct test_val, foo) + 8),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to adjusted map (via const reg): negative range (> adjustment)")
+__failure __msg("R2 min value is negative")
+__naked void const_reg_negative_range_adjustment_1(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r3 = %[test_val_foo];				\
+	r1 += r3;					\
+	r2 = -8;					\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to adjusted map (via const reg): negative range (< adjustment)")
+__failure __msg("R2 min value is negative")
+__naked void const_reg_negative_range_adjustment_2(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r3 = %[test_val_foo];				\
+	r1 += r3;					\
+	r2 = -1;					\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to adjusted map (via variable): full range")
+__success
+__naked void map_via_variable_full_range(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r3 = *(u32*)(r0 + 0);				\
+	if r3 > %[test_val_foo] goto l0_%=;		\
+	r1 += r3;					\
+	r2 = %[__imm_0];				\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(__imm_0, sizeof(struct test_val) - offsetof(struct test_val, foo)),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to adjusted map (via variable): partial range")
+__success
+__naked void map_via_variable_partial_range(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r3 = *(u32*)(r0 + 0);				\
+	if r3 > %[test_val_foo] goto l0_%=;		\
+	r1 += r3;					\
+	r2 = 8;						\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to adjusted map (via variable): empty range")
+__failure __msg("R2 invalid zero-sized read")
+__naked void map_via_variable_empty_range(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r3 = *(u32*)(r0 + 0);				\
+	if r3 > %[test_val_foo] goto l0_%=;		\
+	r1 += r3;					\
+	r2 = 0;						\
+	call %[bpf_trace_printk];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_trace_printk),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to adjusted map (via variable): no max check")
+__failure __msg("R1 unbounded memory access")
+__naked void via_variable_no_max_check_1(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r3 = *(u32*)(r0 + 0);				\
+	r1 += r3;					\
+	r2 = 1;						\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to adjusted map (via variable): wrong max check")
+__failure __msg("invalid access to map value, value_size=48 off=4 size=45")
+__naked void via_variable_wrong_max_check_1(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r3 = *(u32*)(r0 + 0);				\
+	if r3 > %[test_val_foo] goto l0_%=;		\
+	r1 += r3;					\
+	r2 = %[__imm_0];				\
+	r3 = 0;						\
+	call %[bpf_probe_read_kernel];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_probe_read_kernel),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(__imm_0, sizeof(struct test_val) - offsetof(struct test_val, foo) + 1),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to map: bounds check using <, good access")
+__success
+__naked void bounds_check_using_good_access_1(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r3 = *(u32*)(r0 + 0);				\
+	if r3 < 32 goto l1_%=;				\
+	r0 = 0;						\
+l0_%=:	exit;						\
+l1_%=:	r1 += r3;					\
+	r0 = 0;						\
+	*(u8*)(r1 + 0) = r0;				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to map: bounds check using <, bad access")
+__failure __msg("R1 unbounded memory access")
+__naked void bounds_check_using_bad_access_1(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r3 = *(u32*)(r0 + 0);				\
+	if r3 < 32 goto l1_%=;				\
+	r1 += r3;					\
+l0_%=:	r0 = 0;						\
+	*(u8*)(r1 + 0) = r0;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to map: bounds check using <=, good access")
+__success
+__naked void bounds_check_using_good_access_2(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r3 = *(u32*)(r0 + 0);				\
+	if r3 <= 32 goto l1_%=;				\
+	r0 = 0;						\
+l0_%=:	exit;						\
+l1_%=:	r1 += r3;					\
+	r0 = 0;						\
+	*(u8*)(r1 + 0) = r0;				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to map: bounds check using <=, bad access")
+__failure __msg("R1 unbounded memory access")
+__naked void bounds_check_using_bad_access_2(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r3 = *(u32*)(r0 + 0);				\
+	if r3 <= 32 goto l1_%=;				\
+	r1 += r3;					\
+l0_%=:	r0 = 0;						\
+	*(u8*)(r1 + 0) = r0;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to map: bounds check using s<, good access")
+__success
+__naked void check_using_s_good_access_1(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r3 = *(u32*)(r0 + 0);				\
+	if r3 s< 32 goto l1_%=;				\
+l2_%=:	r0 = 0;						\
+l0_%=:	exit;						\
+l1_%=:	if r3 s< 0 goto l2_%=;				\
+	r1 += r3;					\
+	r0 = 0;						\
+	*(u8*)(r1 + 0) = r0;				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to map: bounds check using s<, good access 2")
+__success
+__naked void using_s_good_access_2_1(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r3 = *(u32*)(r0 + 0);				\
+	if r3 s< 32 goto l1_%=;				\
+l2_%=:	r0 = 0;						\
+l0_%=:	exit;						\
+l1_%=:	if r3 s< -3 goto l2_%=;				\
+	r1 += r3;					\
+	r0 = 0;						\
+	*(u8*)(r1 + 0) = r0;				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to map: bounds check using s<, bad access")
+__failure __msg("R1 min value is negative")
+__naked void check_using_s_bad_access_1(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r3 = *(u64*)(r0 + 0);				\
+	if r3 s< 32 goto l1_%=;				\
+l2_%=:	r0 = 0;						\
+l0_%=:	exit;						\
+l1_%=:	if r3 s< -3 goto l2_%=;				\
+	r1 += r3;					\
+	r0 = 0;						\
+	*(u8*)(r1 + 0) = r0;				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to map: bounds check using s<=, good access")
+__success
+__naked void check_using_s_good_access_2(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r3 = *(u32*)(r0 + 0);				\
+	if r3 s<= 32 goto l1_%=;			\
+l2_%=:	r0 = 0;						\
+l0_%=:	exit;						\
+l1_%=:	if r3 s<= 0 goto l2_%=;				\
+	r1 += r3;					\
+	r0 = 0;						\
+	*(u8*)(r1 + 0) = r0;				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to map: bounds check using s<=, good access 2")
+__success
+__naked void using_s_good_access_2_2(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r3 = *(u32*)(r0 + 0);				\
+	if r3 s<= 32 goto l1_%=;			\
+l2_%=:	r0 = 0;						\
+l0_%=:	exit;						\
+l1_%=:	if r3 s<= -3 goto l2_%=;			\
+	r1 += r3;					\
+	r0 = 0;						\
+	*(u8*)(r1 + 0) = r0;				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("helper access to map: bounds check using s<=, bad access")
+__failure __msg("R1 min value is negative")
+__naked void check_using_s_bad_access_2(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	r3 = *(u64*)(r0 + 0);				\
+	if r3 s<= 32 goto l1_%=;			\
+l2_%=:	r0 = 0;						\
+l0_%=:	exit;						\
+l1_%=:	if r3 s<= -3 goto l2_%=;			\
+	r1 += r3;					\
+	r0 = 0;						\
+	*(u8*)(r1 + 0) = r0;				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("map lookup helper access to map")
+__success
+__naked void lookup_helper_access_to_map(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r2 = r0;					\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_16b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("map update helper access to map")
+__success
+__naked void update_helper_access_to_map(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r4 = 0;						\
+	r3 = r0;					\
+	r2 = r0;					\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_update_elem];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_map_update_elem),
+	  __imm_addr(map_hash_16b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("map update helper access to map: wrong size")
+__failure __msg("invalid access to map value, value_size=8 off=0 size=16")
+__naked void access_to_map_wrong_size(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r4 = 0;						\
+	r3 = r0;					\
+	r2 = r0;					\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_update_elem];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_map_update_elem),
+	  __imm_addr(map_hash_16b),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("map helper access to adjusted map (via const imm)")
+__success
+__naked void adjusted_map_via_const_imm(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r2 = r0;					\
+	r2 += %[other_val_bar];				\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_16b),
+	  __imm_const(other_val_bar, offsetof(struct other_val, bar))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("map helper access to adjusted map (via const imm): out-of-bound 1")
+__failure __msg("invalid access to map value, value_size=16 off=12 size=8")
+__naked void imm_out_of_bound_1(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r2 = r0;					\
+	r2 += %[__imm_0];				\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_16b),
+	  __imm_const(__imm_0, sizeof(struct other_val) - 4)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("map helper access to adjusted map (via const imm): out-of-bound 2")
+__failure __msg("invalid access to map value, value_size=16 off=-4 size=8")
+__naked void imm_out_of_bound_2(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r2 = r0;					\
+	r2 += -4;					\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_16b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("map helper access to adjusted map (via const reg)")
+__success
+__naked void adjusted_map_via_const_reg(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r2 = r0;					\
+	r3 = %[other_val_bar];				\
+	r2 += r3;					\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_16b),
+	  __imm_const(other_val_bar, offsetof(struct other_val, bar))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("map helper access to adjusted map (via const reg): out-of-bound 1")
+__failure __msg("invalid access to map value, value_size=16 off=12 size=8")
+__naked void reg_out_of_bound_1(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r2 = r0;					\
+	r3 = %[__imm_0];				\
+	r2 += r3;					\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_16b),
+	  __imm_const(__imm_0, sizeof(struct other_val) - 4)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("map helper access to adjusted map (via const reg): out-of-bound 2")
+__failure __msg("invalid access to map value, value_size=16 off=-4 size=8")
+__naked void reg_out_of_bound_2(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r2 = r0;					\
+	r3 = -4;					\
+	r2 += r3;					\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_16b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("map helper access to adjusted map (via variable)")
+__success
+__naked void to_adjusted_map_via_variable(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r2 = r0;					\
+	r3 = *(u32*)(r0 + 0);				\
+	if r3 > %[other_val_bar] goto l0_%=;		\
+	r2 += r3;					\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_16b),
+	  __imm_const(other_val_bar, offsetof(struct other_val, bar))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("map helper access to adjusted map (via variable): no max check")
+__failure
+__msg("R2 unbounded memory access, make sure to bounds check any such access")
+__naked void via_variable_no_max_check_2(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r2 = r0;					\
+	r3 = *(u32*)(r0 + 0);				\
+	r2 += r3;					\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_16b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("map helper access to adjusted map (via variable): wrong max check")
+__failure __msg("invalid access to map value, value_size=16 off=9 size=8")
+__naked void via_variable_wrong_max_check_2(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r2 = r0;					\
+	r3 = *(u32*)(r0 + 0);				\
+	if r3 > %[__imm_0] goto l0_%=;			\
+	r2 += r3;					\
+	r1 = %[map_hash_16b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_16b),
+	  __imm_const(__imm_0, offsetof(struct other_val, bar) + 1)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_int_ptr.c b/tools/testing/selftests/bpf/progs/verifier_int_ptr.c
new file mode 100644
index 000000000000..59e34d558654
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_int_ptr.c
@@ -0,0 +1,155 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/int_ptr.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("socket")
+__description("arg pointer to long uninitialized")
+__success
+__naked void arg_ptr_to_long_uninitialized(void)
+{
+	asm volatile ("					\
+	/* bpf_strtoul arg1 (buf) */			\
+	r7 = r10;					\
+	r7 += -8;					\
+	r0 = 0x00303036;				\
+	*(u64*)(r7 + 0) = r0;				\
+	r1 = r7;					\
+	/* bpf_strtoul arg2 (buf_len) */		\
+	r2 = 4;						\
+	/* bpf_strtoul arg3 (flags) */			\
+	r3 = 0;						\
+	/* bpf_strtoul arg4 (res) */			\
+	r7 += -8;					\
+	r4 = r7;					\
+	/* bpf_strtoul() */				\
+	call %[bpf_strtoul];				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_strtoul)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("arg pointer to long half-uninitialized")
+__success
+__retval(0)
+__naked void ptr_to_long_half_uninitialized(void)
+{
+	asm volatile ("					\
+	/* bpf_strtoul arg1 (buf) */			\
+	r7 = r10;					\
+	r7 += -8;					\
+	r0 = 0x00303036;				\
+	*(u64*)(r7 + 0) = r0;				\
+	r1 = r7;					\
+	/* bpf_strtoul arg2 (buf_len) */		\
+	r2 = 4;						\
+	/* bpf_strtoul arg3 (flags) */			\
+	r3 = 0;						\
+	/* bpf_strtoul arg4 (res) */			\
+	r7 += -8;					\
+	*(u32*)(r7 + 0) = r0;				\
+	r4 = r7;					\
+	/* bpf_strtoul() */				\
+	call %[bpf_strtoul];				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_strtoul)
+	: __clobber_all);
+}
+
+SEC("cgroup/sysctl")
+__description("arg pointer to long misaligned")
+__failure __msg("misaligned stack access off 0+-20+0 size 8")
+__naked void arg_ptr_to_long_misaligned(void)
+{
+	asm volatile ("					\
+	/* bpf_strtoul arg1 (buf) */			\
+	r7 = r10;					\
+	r7 += -8;					\
+	r0 = 0x00303036;				\
+	*(u64*)(r7 + 0) = r0;				\
+	r1 = r7;					\
+	/* bpf_strtoul arg2 (buf_len) */		\
+	r2 = 4;						\
+	/* bpf_strtoul arg3 (flags) */			\
+	r3 = 0;						\
+	/* bpf_strtoul arg4 (res) */			\
+	r7 += -12;					\
+	r0 = 0;						\
+	*(u32*)(r7 + 0) = r0;				\
+	*(u64*)(r7 + 4) = r0;				\
+	r4 = r7;					\
+	/* bpf_strtoul() */				\
+	call %[bpf_strtoul];				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_strtoul)
+	: __clobber_all);
+}
+
+SEC("cgroup/sysctl")
+__description("arg pointer to long size < sizeof(long)")
+__failure __msg("invalid write to stack R4 off=-4 size=8")
+__naked void to_long_size_sizeof_long(void)
+{
+	asm volatile ("					\
+	/* bpf_strtoul arg1 (buf) */			\
+	r7 = r10;					\
+	r7 += -16;					\
+	r0 = 0x00303036;				\
+	*(u64*)(r7 + 0) = r0;				\
+	r1 = r7;					\
+	/* bpf_strtoul arg2 (buf_len) */		\
+	r2 = 4;						\
+	/* bpf_strtoul arg3 (flags) */			\
+	r3 = 0;						\
+	/* bpf_strtoul arg4 (res) */			\
+	r7 += 12;					\
+	*(u32*)(r7 + 0) = r0;				\
+	r4 = r7;					\
+	/* bpf_strtoul() */				\
+	call %[bpf_strtoul];				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_strtoul)
+	: __clobber_all);
+}
+
+SEC("cgroup/sysctl")
+__description("arg pointer to long initialized")
+__success
+__naked void arg_ptr_to_long_initialized(void)
+{
+	asm volatile ("					\
+	/* bpf_strtoul arg1 (buf) */			\
+	r7 = r10;					\
+	r7 += -8;					\
+	r0 = 0x00303036;				\
+	*(u64*)(r7 + 0) = r0;				\
+	r1 = r7;					\
+	/* bpf_strtoul arg2 (buf_len) */		\
+	r2 = 4;						\
+	/* bpf_strtoul arg3 (flags) */			\
+	r3 = 0;						\
+	/* bpf_strtoul arg4 (res) */			\
+	r7 += -8;					\
+	*(u64*)(r7 + 0) = r0;				\
+	r4 = r7;					\
+	/* bpf_strtoul() */				\
+	call %[bpf_strtoul];				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_strtoul)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
new file mode 100644
index 000000000000..75dd922e4e9f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c
@@ -0,0 +1,786 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 8);
+	__type(key, __u32);
+	__type(value, __u64);
+} map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_USER_RINGBUF);
+	__uint(max_entries, 8);
+} ringbuf SEC(".maps");
+
+struct vm_area_struct;
+struct bpf_map;
+
+struct buf_context {
+	char *buf;
+};
+
+struct num_context {
+	__u64 i;
+	__u64 j;
+};
+
+__u8 choice_arr[2] = { 0, 1 };
+
+static int unsafe_on_2nd_iter_cb(__u32 idx, struct buf_context *ctx)
+{
+	if (idx == 0) {
+		ctx->buf = (char *)(0xDEAD);
+		return 0;
+	}
+
+	if (bpf_probe_read_user(ctx->buf, 8, (void *)(0xBADC0FFEE)))
+		return 1;
+
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("R1 type=scalar expected=fp")
+int unsafe_on_2nd_iter(void *unused)
+{
+	char buf[4];
+	struct buf_context loop_ctx = { .buf = buf };
+
+	bpf_loop(100, unsafe_on_2nd_iter_cb, &loop_ctx, 0);
+	return 0;
+}
+
+static int unsafe_on_zero_iter_cb(__u32 idx, struct num_context *ctx)
+{
+	ctx->i = 0;
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("invalid access to map value, value_size=2 off=32 size=1")
+int unsafe_on_zero_iter(void *unused)
+{
+	struct num_context loop_ctx = { .i = 32 };
+
+	bpf_loop(100, unsafe_on_zero_iter_cb, &loop_ctx, 0);
+	return choice_arr[loop_ctx.i];
+}
+
+static int widening_cb(__u32 idx, struct num_context *ctx)
+{
+	++ctx->i;
+	return 0;
+}
+
+SEC("?raw_tp")
+__success
+int widening(void *unused)
+{
+	struct num_context loop_ctx = { .i = 0, .j = 1 };
+
+	bpf_loop(100, widening_cb, &loop_ctx, 0);
+	/* loop_ctx.j is not changed during callback iteration,
+	 * verifier should not apply widening to it.
+	 */
+	return choice_arr[loop_ctx.j];
+}
+
+static int loop_detection_cb(__u32 idx, struct num_context *ctx)
+{
+	for (;;) {}
+	return 0;
+}
+
+SEC("?raw_tp")
+__failure __msg("infinite loop detected")
+int loop_detection(void *unused)
+{
+	struct num_context loop_ctx = { .i = 0 };
+
+	bpf_loop(100, loop_detection_cb, &loop_ctx, 0);
+	return 0;
+}
+
+static __always_inline __u64 oob_state_machine(struct num_context *ctx)
+{
+	switch (ctx->i) {
+	case 0:
+		ctx->i = 1;
+		break;
+	case 1:
+		ctx->i = 32;
+		break;
+	}
+	return 0;
+}
+
+static __u64 for_each_map_elem_cb(struct bpf_map *map, __u32 *key, __u64 *val, void *data)
+{
+	return oob_state_machine(data);
+}
+
+SEC("?raw_tp")
+__failure __msg("invalid access to map value, value_size=2 off=32 size=1")
+int unsafe_for_each_map_elem(void *unused)
+{
+	struct num_context loop_ctx = { .i = 0 };
+
+	bpf_for_each_map_elem(&map, for_each_map_elem_cb, &loop_ctx, 0);
+	return choice_arr[loop_ctx.i];
+}
+
+static __u64 ringbuf_drain_cb(struct bpf_dynptr *dynptr, void *data)
+{
+	return oob_state_machine(data);
+}
+
+SEC("?raw_tp")
+__failure __msg("invalid access to map value, value_size=2 off=32 size=1")
+int unsafe_ringbuf_drain(void *unused)
+{
+	struct num_context loop_ctx = { .i = 0 };
+
+	bpf_user_ringbuf_drain(&ringbuf, ringbuf_drain_cb, &loop_ctx, 0);
+	return choice_arr[loop_ctx.i];
+}
+
+static __u64 find_vma_cb(struct task_struct *task, struct vm_area_struct *vma, void *data)
+{
+	return oob_state_machine(data);
+}
+
+SEC("?raw_tp")
+__failure __msg("invalid access to map value, value_size=2 off=32 size=1")
+int unsafe_find_vma(void *unused)
+{
+	struct task_struct *task = bpf_get_current_task_btf();
+	struct num_context loop_ctx = { .i = 0 };
+
+	bpf_find_vma(task, 0, find_vma_cb, &loop_ctx, 0);
+	return choice_arr[loop_ctx.i];
+}
+
+static int iter_limit_cb(__u32 idx, struct num_context *ctx)
+{
+	ctx->i++;
+	return 0;
+}
+
+SEC("?raw_tp")
+__success
+int bpf_loop_iter_limit_ok(void *unused)
+{
+	struct num_context ctx = { .i = 0 };
+
+	bpf_loop(1, iter_limit_cb, &ctx, 0);
+	return choice_arr[ctx.i];
+}
+
+SEC("?raw_tp")
+__failure __msg("invalid access to map value, value_size=2 off=2 size=1")
+int bpf_loop_iter_limit_overflow(void *unused)
+{
+	struct num_context ctx = { .i = 0 };
+
+	bpf_loop(2, iter_limit_cb, &ctx, 0);
+	return choice_arr[ctx.i];
+}
+
+static int iter_limit_level2a_cb(__u32 idx, struct num_context *ctx)
+{
+	ctx->i += 100;
+	return 0;
+}
+
+static int iter_limit_level2b_cb(__u32 idx, struct num_context *ctx)
+{
+	ctx->i += 10;
+	return 0;
+}
+
+static int iter_limit_level1_cb(__u32 idx, struct num_context *ctx)
+{
+	ctx->i += 1;
+	bpf_loop(1, iter_limit_level2a_cb, ctx, 0);
+	bpf_loop(1, iter_limit_level2b_cb, ctx, 0);
+	return 0;
+}
+
+/* Check that path visiting every callback function once had been
+ * reached by verifier. Variables 'ctx{1,2}i' below serve as flags,
+ * with each decimal digit corresponding to a callback visit marker.
+ */
+SEC("socket")
+__success __retval(111111)
+int bpf_loop_iter_limit_nested(void *unused)
+{
+	struct num_context ctx1 = { .i = 0 };
+	struct num_context ctx2 = { .i = 0 };
+	__u64 a, b, c;
+
+	bpf_loop(1, iter_limit_level1_cb, &ctx1, 0);
+	bpf_loop(1, iter_limit_level1_cb, &ctx2, 0);
+	a = ctx1.i;
+	b = ctx2.i;
+	/* Force 'ctx1.i' and 'ctx2.i' precise. */
+	c = choice_arr[(a + b) % 2];
+	/* This makes 'c' zero, but neither clang nor verifier know it. */
+	c /= 10;
+	/* Make sure that verifier does not visit 'impossible' states:
+	 * enumerate all possible callback visit masks.
+	 */
+	if (a != 0 && a != 1 && a != 11 && a != 101 && a != 111 &&
+	    b != 0 && b != 1 && b != 11 && b != 101 && b != 111)
+		asm volatile ("r0 /= 0;" ::: "r0");
+	return 1000 * a + b + c;
+}
+
+struct iter_limit_bug_ctx {
+	__u64 a;
+	__u64 b;
+	__u64 c;
+};
+
+static __naked void iter_limit_bug_cb(void)
+{
+	/* This is the same as C code below, but written
+	 * in assembly to control which branches are fall-through.
+	 *
+	 *   switch (bpf_get_prandom_u32()) {
+	 *   case 1:  ctx->a = 42; break;
+	 *   case 2:  ctx->b = 42; break;
+	 *   default: ctx->c = 42; break;
+	 *   }
+	 */
+	asm volatile (
+	"r9 = r2;"
+	"call %[bpf_get_prandom_u32];"
+	"r1 = r0;"
+	"r2 = 42;"
+	"r0 = 0;"
+	"if r1 == 0x1 goto 1f;"
+	"if r1 == 0x2 goto 2f;"
+	"*(u64 *)(r9 + 16) = r2;"
+	"exit;"
+	"1: *(u64 *)(r9 + 0) = r2;"
+	"exit;"
+	"2: *(u64 *)(r9 + 8) = r2;"
+	"exit;"
+	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all
+	);
+}
+
+int tmp_var;
+SEC("socket")
+__failure __msg("infinite loop detected at insn 2")
+__naked void jgt_imm64_and_may_goto(void)
+{
+	asm volatile ("			\
+	r0 = %[tmp_var] ll;		\
+l0_%=:	.byte 0xe5; /* may_goto */	\
+	.byte 0; /* regs */		\
+	.short -3; /* off -3 */		\
+	.long 0; /* imm */		\
+	if r0 > 10 goto l0_%=;		\
+	r0 = 0;				\
+	exit;				\
+"	:: __imm_addr(tmp_var)
+	: __clobber_all);
+}
+
+SEC("socket")
+__failure __msg("infinite loop detected at insn 1")
+__naked void may_goto_self(void)
+{
+	asm volatile ("			\
+	r0 = *(u32 *)(r10 - 4);		\
+l0_%=:	.byte 0xe5; /* may_goto */	\
+	.byte 0; /* regs */		\
+	.short -1; /* off -1 */		\
+	.long 0; /* imm */		\
+	if r0 > 10 goto l0_%=;		\
+	r0 = 0;				\
+	exit;				\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__success __retval(0)
+__naked void may_goto_neg_off(void)
+{
+	asm volatile ("			\
+	r0 = *(u32 *)(r10 - 4);		\
+	goto l0_%=;			\
+	goto l1_%=;			\
+l0_%=:	.byte 0xe5; /* may_goto */	\
+	.byte 0; /* regs */		\
+	.short -2; /* off -2 */		\
+	.long 0; /* imm */		\
+	if r0 > 10 goto l0_%=;		\
+l1_%=:	r0 = 0;				\
+	exit;				\
+"	::: __clobber_all);
+}
+
+SEC("tc")
+__failure
+__flag(BPF_F_TEST_STATE_FREQ)
+int iter_limit_bug(struct __sk_buff *skb)
+{
+	struct iter_limit_bug_ctx ctx = { 7, 7, 7 };
+
+	bpf_loop(2, iter_limit_bug_cb, &ctx, 0);
+
+	/* This is the same as C code below,
+	 * written in assembly to guarantee checks order.
+	 *
+	 *   if (ctx.a == 42 && ctx.b == 42 && ctx.c == 7)
+	 *     asm volatile("r1 /= 0;":::"r1");
+	 */
+	asm volatile (
+	"r1 = *(u64 *)%[ctx_a];"
+	"if r1 != 42 goto 1f;"
+	"r1 = *(u64 *)%[ctx_b];"
+	"if r1 != 42 goto 1f;"
+	"r1 = *(u64 *)%[ctx_c];"
+	"if r1 != 7 goto 1f;"
+	"r1 /= 0;"
+	"1:"
+	:
+	: [ctx_a]"m"(ctx.a),
+	  [ctx_b]"m"(ctx.b),
+	  [ctx_c]"m"(ctx.c)
+	: "r1"
+	);
+	return 0;
+}
+
+SEC("socket")
+__success __retval(0)
+__naked void ja_and_may_goto(void)
+{
+	asm volatile ("			\
+l0_%=:	.byte 0xe5; /* may_goto */	\
+	.byte 0; /* regs */		\
+	.short 1; /* off 1 */		\
+	.long 0; /* imm */		\
+	goto l0_%=;			\
+	r0 = 0;				\
+	exit;				\
+"	::: __clobber_common);
+}
+
+SEC("socket")
+__success __retval(0)
+__naked void ja_and_may_goto2(void)
+{
+	asm volatile ("			\
+l0_%=:	r0 = 0;				\
+	.byte 0xe5; /* may_goto */	\
+	.byte 0; /* regs */		\
+	.short 1; /* off 1 */		\
+	.long 0; /* imm */		\
+	goto l0_%=;			\
+	r0 = 0;				\
+	exit;				\
+"	::: __clobber_common);
+}
+
+SEC("socket")
+__success __retval(0)
+__naked void jlt_and_may_goto(void)
+{
+	asm volatile ("			\
+l0_%=:	call %[bpf_jiffies64];		\
+	.byte 0xe5; /* may_goto */	\
+	.byte 0; /* regs */		\
+	.short 1; /* off 1 */		\
+	.long 0; /* imm */		\
+	if r0 < 10 goto l0_%=;		\
+	r0 = 0;				\
+	exit;				\
+"	:: __imm(bpf_jiffies64)
+	: __clobber_all);
+}
+
+#ifdef CAN_USE_GOTOL
+SEC("socket")
+__success __retval(0)
+__naked void gotol_and_may_goto(void)
+{
+	asm volatile ("			\
+l0_%=:	r0 = 0;				\
+	.byte 0xe5; /* may_goto */	\
+	.byte 0; /* regs */		\
+	.short 1; /* off 1 */		\
+	.long 0; /* imm */		\
+	gotol l0_%=;			\
+	r0 = 0;				\
+	exit;				\
+"	::: __clobber_common);
+}
+#endif
+
+SEC("socket")
+__success __retval(0)
+__naked void ja_and_may_goto_subprog(void)
+{
+	asm volatile ("			\
+	call subprog_with_may_goto;	\
+	exit;				\
+"	::: __clobber_all);
+}
+
+static __naked __noinline __used
+void subprog_with_may_goto(void)
+{
+	asm volatile ("			\
+l0_%=:	.byte 0xe5; /* may_goto */	\
+	.byte 0; /* regs */		\
+	.short 1; /* off 1 */		\
+	.long 0; /* imm */		\
+	goto l0_%=;			\
+	r0 = 0;				\
+	exit;				\
+"	::: __clobber_all);
+}
+
+#define ARR_SZ 1000000
+int zero;
+char arr[ARR_SZ];
+
+SEC("socket")
+__success __retval(0xd495cdc0)
+int cond_break1(const void *ctx)
+{
+	unsigned long i;
+	unsigned int sum = 0;
+
+	for (i = zero; i < ARR_SZ && can_loop; i++)
+		sum += i;
+	for (i = zero; i < ARR_SZ; i++) {
+		barrier_var(i);
+		sum += i + arr[i];
+		cond_break;
+	}
+
+	return sum;
+}
+
+SEC("socket")
+__success __retval(999000000)
+int cond_break2(const void *ctx)
+{
+	int i, j;
+	int sum = 0;
+
+	for (i = zero; i < 1000 && can_loop; i++)
+		for (j = zero; j < 1000; j++) {
+			sum += i + j;
+			cond_break;
+	}
+	return sum;
+}
+
+static __noinline int loop(void)
+{
+	int i, sum = 0;
+
+	for (i = zero; i <= 1000000 && can_loop; i++)
+		sum += i;
+
+	return sum;
+}
+
+SEC("socket")
+__success __retval(0x6a5a2920)
+int cond_break3(const void *ctx)
+{
+	return loop();
+}
+
+SEC("socket")
+__success __retval(1)
+int cond_break4(const void *ctx)
+{
+	int cnt = zero;
+
+	for (;;) {
+		/* should eventually break out of the loop */
+		cond_break;
+		cnt++;
+	}
+	/* if we looped a bit, it's a success */
+	return cnt > 1 ? 1 : 0;
+}
+
+static __noinline int static_subprog(void)
+{
+	int cnt = zero;
+
+	for (;;) {
+		cond_break;
+		cnt++;
+	}
+
+	return cnt;
+}
+
+SEC("socket")
+__success __retval(1)
+int cond_break5(const void *ctx)
+{
+	int cnt1 = zero, cnt2;
+
+	for (;;) {
+		cond_break;
+		cnt1++;
+	}
+
+	cnt2 = static_subprog();
+
+	/* main and subprog have to loop a bit */
+	return cnt1 > 1 && cnt2 > 1 ? 1 : 0;
+}
+
+#define ARR2_SZ 1000
+SEC(".data.arr2")
+char arr2[ARR2_SZ];
+
+SEC("socket")
+__success __flag(BPF_F_TEST_STATE_FREQ)
+int loop_inside_iter(const void *ctx)
+{
+	struct bpf_iter_num it;
+	int *v, sum = 0;
+	__u64 i = 0;
+
+	bpf_iter_num_new(&it, 0, ARR2_SZ);
+	while ((v = bpf_iter_num_next(&it))) {
+		if (i < ARR2_SZ)
+			sum += arr2[i++];
+	}
+	bpf_iter_num_destroy(&it);
+	return sum;
+}
+
+SEC("socket")
+__success __flag(BPF_F_TEST_STATE_FREQ)
+int loop_inside_iter_signed(const void *ctx)
+{
+	struct bpf_iter_num it;
+	int *v, sum = 0;
+	long i = 0;
+
+	bpf_iter_num_new(&it, 0, ARR2_SZ);
+	while ((v = bpf_iter_num_next(&it))) {
+		if (i < ARR2_SZ && i >= 0)
+			sum += arr2[i++];
+	}
+	bpf_iter_num_destroy(&it);
+	return sum;
+}
+
+volatile const int limit = ARR2_SZ;
+
+SEC("socket")
+__success __flag(BPF_F_TEST_STATE_FREQ)
+int loop_inside_iter_volatile_limit(const void *ctx)
+{
+	struct bpf_iter_num it;
+	int *v, sum = 0;
+	__u64 i = 0;
+
+	bpf_iter_num_new(&it, 0, ARR2_SZ);
+	while ((v = bpf_iter_num_next(&it))) {
+		if (i < limit)
+			sum += arr2[i++];
+	}
+	bpf_iter_num_destroy(&it);
+	return sum;
+}
+
+#define ARR_LONG_SZ 1000
+
+SEC(".data.arr_long")
+long arr_long[ARR_LONG_SZ];
+
+SEC("socket")
+__success
+int test1(const void *ctx)
+{
+	long i;
+
+	for (i = 0; i < ARR_LONG_SZ && can_loop; i++)
+		arr_long[i] = i;
+	return 0;
+}
+
+SEC("socket")
+__success
+int test2(const void *ctx)
+{
+	__u64 i;
+
+	for (i = zero; i < ARR_LONG_SZ && can_loop; i++) {
+		barrier_var(i);
+		arr_long[i] = i;
+	}
+	return 0;
+}
+
+SEC(".data.arr_foo")
+struct {
+	int a;
+	int b;
+} arr_foo[ARR_LONG_SZ];
+
+SEC("socket")
+__success
+int test3(const void *ctx)
+{
+	__u64 i;
+
+	for (i = zero; i < ARR_LONG_SZ && can_loop; i++) {
+		barrier_var(i);
+		arr_foo[i].a = i;
+		arr_foo[i].b = i;
+	}
+	return 0;
+}
+
+SEC("socket")
+__success
+int test4(const void *ctx)
+{
+	long i;
+
+	for (i = zero + ARR_LONG_SZ - 1; i < ARR_LONG_SZ && i >= 0 && can_loop; i--) {
+		barrier_var(i);
+		arr_foo[i].a = i;
+		arr_foo[i].b = i;
+	}
+	return 0;
+}
+
+char buf[10] SEC(".data.buf");
+
+SEC("socket")
+__description("check add const")
+__success
+__naked void check_add_const(void)
+{
+	/* typical LLVM generated loop with may_goto */
+	asm volatile ("			\
+	call %[bpf_ktime_get_ns];	\
+	if r0 > 9 goto l1_%=;		\
+l0_%=:	r1 = %[buf];			\
+	r2 = r0;			\
+	r1 += r2;			\
+	r3 = *(u8 *)(r1 +0);		\
+	.byte 0xe5; /* may_goto */	\
+	.byte 0; /* regs */		\
+	.short 4; /* off of l1_%=: */	\
+	.long 0; /* imm */		\
+	r0 = r2;			\
+	r0 += 1;			\
+	if r2 < 9 goto l0_%=;		\
+	exit;				\
+l1_%=:	r0 = 0;				\
+	exit;				\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm_ptr(buf)
+	: __clobber_common);
+}
+
+SEC("socket")
+__failure
+__msg("*(u8 *)(r7 +0) = r0")
+__msg("invalid access to map value, value_size=10 off=10 size=1")
+__naked void check_add_const_3regs(void)
+{
+	asm volatile (
+	"r6 = %[buf];"
+	"r7 = %[buf];"
+	"call %[bpf_ktime_get_ns];"
+	"r1 = r0;"              /* link r0.id == r1.id == r2.id */
+	"r2 = r0;"
+	"r1 += 1;"              /* r1 == r0+1 */
+	"r2 += 2;"              /* r2 == r0+2 */
+	"if r0 > 8 goto 1f;"    /* r0 range [0, 8]  */
+	"r6 += r1;"             /* r1 range [1, 9]  */
+	"r7 += r2;"             /* r2 range [2, 10] */
+	"*(u8 *)(r6 +0) = r0;"  /* safe, within bounds   */
+	"*(u8 *)(r7 +0) = r0;"  /* unsafe, out of bounds */
+	"1: exit;"
+	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm_ptr(buf)
+	: __clobber_common);
+}
+
+SEC("socket")
+__failure
+__msg("*(u8 *)(r8 -1) = r0")
+__msg("invalid access to map value, value_size=10 off=10 size=1")
+__naked void check_add_const_3regs_2if(void)
+{
+	asm volatile (
+	"r6 = %[buf];"
+	"r7 = %[buf];"
+	"r8 = %[buf];"
+	"call %[bpf_ktime_get_ns];"
+	"if r0 < 2 goto 1f;"
+	"r1 = r0;"              /* link r0.id == r1.id == r2.id */
+	"r2 = r0;"
+	"r1 += 1;"              /* r1 == r0+1 */
+	"r2 += 2;"              /* r2 == r0+2 */
+	"if r2 > 11 goto 1f;"   /* r2 range [0, 11] -> r0 range [-2, 9]; r1 range [-1, 10] */
+	"if r0 s< 0 goto 1f;"   /* r0 range [0, 9] -> r1 range [1, 10]; r2 range [2, 11]; */
+	"r6 += r0;"             /* r0 range [0, 9]  */
+	"r7 += r1;"             /* r1 range [1, 10] */
+	"r8 += r2;"             /* r2 range [2, 11] */
+	"*(u8 *)(r6 +0) = r0;"  /* safe, within bounds   */
+	"*(u8 *)(r7 -1) = r0;"  /* safe */
+	"*(u8 *)(r8 -1) = r0;"  /* unsafe */
+	"1: exit;"
+	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm_ptr(buf)
+	: __clobber_common);
+}
+
+SEC("socket")
+__failure
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void check_add_const_regsafe_off(void)
+{
+	asm volatile (
+	"r8 = %[buf];"
+	"call %[bpf_ktime_get_ns];"
+	"r6 = r0;"
+	"call %[bpf_ktime_get_ns];"
+	"r7 = r0;"
+	"call %[bpf_ktime_get_ns];"
+	"r1 = r0;"              /* same ids for r1 and r0 */
+	"if r6 > r7 goto 1f;"   /* this jump can't be predicted */
+	"r1 += 1;"              /* r1.off == +1 */
+	"goto 2f;"
+	"1: r1 += 100;"         /* r1.off == +100 */
+	"goto +0;"              /* verify r1.off in regsafe() after this insn */
+	"2: if r0 > 8 goto 3f;" /* r0 range [0,8], r1 range either [1,9] or [100,108]*/
+	"r8 += r1;"
+	"*(u8 *)(r8 +0) = r0;"  /* potentially unsafe, buf size is 10 */
+	"3: exit;"
+	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm_ptr(buf)
+	: __clobber_common);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c b/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c
new file mode 100644
index 000000000000..bf16b00502f2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_jeq_infer_not_null.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/jeq_infer_not_null.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_XSKMAP);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} map_xskmap SEC(".maps");
+
+/* This is equivalent to the following program:
+ *
+ *   r6 = skb->sk;
+ *   r7 = sk_fullsock(r6);
+ *   r0 = sk_fullsock(r6);
+ *   if (r0 == 0) return 0;    (a)
+ *   if (r0 != r7) return 0;   (b)
+ *   *r7->type;                (c)
+ *   return 0;
+ *
+ * It is safe to dereference r7 at point (c), because of (a) and (b).
+ * The test verifies that relation r0 == r7 is propagated from (b) to (c).
+ */
+SEC("cgroup/skb")
+__description("jne/jeq infer not null, PTR_TO_SOCKET_OR_NULL -> PTR_TO_SOCKET for JNE false branch")
+__success __failure_unpriv __msg_unpriv("R7 pointer comparison")
+__retval(0)
+__naked void socket_for_jne_false_branch(void)
+{
+	asm volatile ("					\
+	/* r6 = skb->sk; */				\
+	r6 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	/* if (r6 == 0) return 0; */			\
+	if r6 == 0 goto l0_%=;				\
+	/* r7 = sk_fullsock(skb); */			\
+	r1 = r6;					\
+	call %[bpf_sk_fullsock];			\
+	r7 = r0;					\
+	/* r0 = sk_fullsock(skb); */			\
+	r1 = r6;					\
+	call %[bpf_sk_fullsock];			\
+	/* if (r0 == null) return 0; */			\
+	if r0 == 0 goto l0_%=;				\
+	/* if (r0 == r7) r0 = *(r7->type); */		\
+	if r0 != r7 goto l0_%=;		/* Use ! JNE ! */\
+	r0 = *(u32*)(r7 + %[bpf_sock_type]);		\
+l0_%=:	/* return 0 */					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type))
+	: __clobber_all);
+}
+
+/* Same as above, but verify that another branch of JNE still
+ * prohibits access to PTR_MAYBE_NULL.
+ */
+SEC("cgroup/skb")
+__description("jne/jeq infer not null, PTR_TO_SOCKET_OR_NULL unchanged for JNE true branch")
+__failure __msg("R7 invalid mem access 'sock_or_null'")
+__failure_unpriv __msg_unpriv("R7 pointer comparison")
+__naked void unchanged_for_jne_true_branch(void)
+{
+	asm volatile ("					\
+	/* r6 = skb->sk */				\
+	r6 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	/* if (r6 == 0) return 0; */			\
+	if r6 == 0 goto l0_%=;				\
+	/* r7 = sk_fullsock(skb); */			\
+	r1 = r6;					\
+	call %[bpf_sk_fullsock];			\
+	r7 = r0;					\
+	/* r0 = sk_fullsock(skb); */			\
+	r1 = r6;					\
+	call %[bpf_sk_fullsock];			\
+	/* if (r0 == null) return 0; */			\
+	if r0 != 0 goto l0_%=;				\
+	/* if (r0 == r7) return 0; */			\
+	if r0 != r7 goto l1_%=;		/* Use ! JNE ! */\
+	goto l0_%=;					\
+l1_%=:	/* r0 = *(r7->type); */				\
+	r0 = *(u32*)(r7 + %[bpf_sock_type]);		\
+l0_%=:	/* return 0 */					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type))
+	: __clobber_all);
+}
+
+/* Same as a first test, but not null should be inferred for JEQ branch */
+SEC("cgroup/skb")
+__description("jne/jeq infer not null, PTR_TO_SOCKET_OR_NULL -> PTR_TO_SOCKET for JEQ true branch")
+__success __failure_unpriv __msg_unpriv("R7 pointer comparison")
+__retval(0)
+__naked void socket_for_jeq_true_branch(void)
+{
+	asm volatile ("					\
+	/* r6 = skb->sk; */				\
+	r6 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	/* if (r6 == null) return 0; */			\
+	if r6 == 0 goto l0_%=;				\
+	/* r7 = sk_fullsock(skb); */			\
+	r1 = r6;					\
+	call %[bpf_sk_fullsock];			\
+	r7 = r0;					\
+	/* r0 = sk_fullsock(skb); */			\
+	r1 = r6;					\
+	call %[bpf_sk_fullsock];			\
+	/* if (r0 == null) return 0; */			\
+	if r0 == 0 goto l0_%=;				\
+	/* if (r0 != r7) return 0; */			\
+	if r0 == r7 goto l1_%=;		/* Use ! JEQ ! */\
+	goto l0_%=;					\
+l1_%=:	/* r0 = *(r7->type); */				\
+	r0 = *(u32*)(r7 + %[bpf_sock_type]);		\
+l0_%=:	/* return 0; */					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type))
+	: __clobber_all);
+}
+
+/* Same as above, but verify that another branch of JNE still
+ * prohibits access to PTR_MAYBE_NULL.
+ */
+SEC("cgroup/skb")
+__description("jne/jeq infer not null, PTR_TO_SOCKET_OR_NULL unchanged for JEQ false branch")
+__failure __msg("R7 invalid mem access 'sock_or_null'")
+__failure_unpriv __msg_unpriv("R7 pointer comparison")
+__naked void unchanged_for_jeq_false_branch(void)
+{
+	asm volatile ("					\
+	/* r6 = skb->sk; */				\
+	r6 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	/* if (r6 == null) return 0; */			\
+	if r6 == 0 goto l0_%=;				\
+	/* r7 = sk_fullsock(skb); */			\
+	r1 = r6;					\
+	call %[bpf_sk_fullsock];			\
+	r7 = r0;					\
+	/* r0 = sk_fullsock(skb); */			\
+	r1 = r6;					\
+	call %[bpf_sk_fullsock];			\
+	/* if (r0 == null) return 0; */			\
+	if r0 == 0 goto l0_%=;				\
+	/* if (r0 != r7) r0 = *(r7->type); */		\
+	if r0 == r7 goto l0_%=;		/* Use ! JEQ ! */\
+	r0 = *(u32*)(r7 + %[bpf_sock_type]);		\
+l0_%=:	/* return 0; */					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type))
+	: __clobber_all);
+}
+
+/* Maps are treated in a different branch of `mark_ptr_not_null_reg`,
+ * so separate test for maps case.
+ */
+SEC("xdp")
+__description("jne/jeq infer not null, PTR_TO_MAP_VALUE_OR_NULL -> PTR_TO_MAP_VALUE")
+__success __retval(0)
+__naked void null_ptr_to_map_value(void)
+{
+	asm volatile ("					\
+	/* r9 = &some stack to use as key */		\
+	r1 = 0;						\
+	*(u32*)(r10 - 8) = r1;				\
+	r9 = r10;					\
+	r9 += -8;					\
+	/* r8 = process local map */			\
+	r8 = %[map_xskmap] ll;				\
+	/* r6 = map_lookup_elem(r8, r9); */		\
+	r1 = r8;					\
+	r2 = r9;					\
+	call %[bpf_map_lookup_elem];			\
+	r6 = r0;					\
+	/* r7 = map_lookup_elem(r8, r9); */		\
+	r1 = r8;					\
+	r2 = r9;					\
+	call %[bpf_map_lookup_elem];			\
+	r7 = r0;					\
+	/* if (r6 == 0) return 0; */			\
+	if r6 == 0 goto l0_%=;				\
+	/* if (r6 != r7) return 0; */			\
+	if r6 != r7 goto l0_%=;				\
+	/* read *r7; */					\
+	r0 = *(u32*)(r7 + %[bpf_xdp_sock_queue_id]);	\
+l0_%=:	/* return 0; */					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_xskmap),
+	  __imm_const(bpf_xdp_sock_queue_id, offsetof(struct bpf_xdp_sock, queue_id))
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_jit_convergence.c b/tools/testing/selftests/bpf/progs/verifier_jit_convergence.c
new file mode 100644
index 000000000000..9f3f2b7db450
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_jit_convergence.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct value_t {
+	long long a[32];
+};
+
+struct {
+        __uint(type, BPF_MAP_TYPE_HASH);
+        __uint(max_entries, 1);
+        __type(key, long long);
+        __type(value, struct value_t);
+} map_hash SEC(".maps");
+
+SEC("socket")
+__description("bpf_jit_convergence je <-> jmp")
+__success __retval(0)
+__arch_x86_64
+__jited("	pushq	%rbp")
+__naked void btf_jit_convergence_je_jmp(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"if r0 == 0 goto l20_%=;"
+	"if r0 == 1 goto l21_%=;"
+	"if r0 == 2 goto l22_%=;"
+	"if r0 == 3 goto l23_%=;"
+	"if r0 == 4 goto l24_%=;"
+	"call %[bpf_get_prandom_u32];"
+	"call %[bpf_get_prandom_u32];"
+"l20_%=:"
+"l21_%=:"
+"l22_%=:"
+"l23_%=:"
+"l24_%=:"
+	"r1 = 0;"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r2 = r10;"
+	"r2 += -8;"
+	"r1 = %[map_hash] ll;"
+	"call %[bpf_map_lookup_elem];"
+	"if r0 == 0 goto l1_%=;"
+	"r6 = r0;"
+	"call %[bpf_get_prandom_u32];"
+	"r7 = r0;"
+	"r5 = r6;"
+	"if r0 != 0x0 goto l12_%=;"
+	"call %[bpf_get_prandom_u32];"
+	"r1 = r0;"
+	"r2 = r6;"
+	"if r1 == 0x0 goto l0_%=;"
+"l9_%=:"
+	"r2 = *(u64 *)(r6 + 0x0);"
+	"r2 += 0x1;"
+	"*(u64 *)(r6 + 0x0) = r2;"
+	"goto l1_%=;"
+"l12_%=:"
+	"r1 = r7;"
+	"r1 += 0x98;"
+	"r2 = r5;"
+	"r2 += 0x90;"
+	"r2 = *(u32 *)(r2 + 0x0);"
+	"r3 = r7;"
+	"r3 &= 0x1;"
+	"r2 *= 0xa8;"
+	"if r3 == 0x0 goto l2_%=;"
+	"r1 += r2;"
+	"r1 -= r7;"
+	"r1 += 0x8;"
+	"if r1 <= 0xb20 goto l3_%=;"
+	"r1 = 0x0;"
+	"goto l4_%=;"
+"l3_%=:"
+	"r1 += r7;"
+"l4_%=:"
+	"if r1 == 0x0 goto l8_%=;"
+	"goto l9_%=;"
+"l2_%=:"
+	"r1 += r2;"
+	"r1 -= r7;"
+	"r1 += 0x10;"
+	"if r1 <= 0xb20 goto l6_%=;"
+	"r1 = 0x0;"
+	"goto l7_%=;"
+"l6_%=:"
+	"r1 += r7;"
+"l7_%=:"
+	"if r1 == 0x0 goto l8_%=;"
+	"goto l9_%=;"
+"l0_%=:"
+	"r1 = 0x3;"
+	"*(u64 *)(r10 - 0x10) = r1;"
+	"r2 = r1;"
+	"goto l1_%=;"
+"l8_%=:"
+	"r1 = r5;"
+	"r1 += 0x4;"
+	"r1 = *(u32 *)(r1 + 0x0);"
+	"*(u64 *)(r10 - 0x8) = r1;"
+"l1_%=:"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_kfunc_prog_types.c b/tools/testing/selftests/bpf/progs/verifier_kfunc_prog_types.c
new file mode 100644
index 000000000000..a509cad97e69
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_kfunc_prog_types.c
@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+#include "cgrp_kfunc_common.h"
+#include "cpumask_common.h"
+#include "task_kfunc_common.h"
+
+char _license[] SEC("license") = "GPL";
+
+/***************
+ * Task kfuncs *
+ ***************/
+
+static void task_kfunc_load_test(void)
+{
+	struct task_struct *current, *ref_1, *ref_2;
+
+	current = bpf_get_current_task_btf();
+	ref_1 = bpf_task_from_pid(current->pid);
+	if (!ref_1)
+		return;
+
+	ref_2 = bpf_task_acquire(ref_1);
+	if (ref_2)
+		bpf_task_release(ref_2);
+	bpf_task_release(ref_1);
+}
+
+SEC("raw_tp")
+__failure __msg("calling kernel function")
+int BPF_PROG(task_kfunc_raw_tp)
+{
+	task_kfunc_load_test();
+	return 0;
+}
+
+SEC("syscall")
+__success
+int BPF_PROG(task_kfunc_syscall)
+{
+	task_kfunc_load_test();
+	return 0;
+}
+
+SEC("tracepoint")
+__success
+int BPF_PROG(task_kfunc_tracepoint)
+{
+	task_kfunc_load_test();
+	return 0;
+}
+
+SEC("perf_event")
+__success
+int BPF_PROG(task_kfunc_perf_event)
+{
+	task_kfunc_load_test();
+	return 0;
+}
+
+/*****************
+ * cgroup kfuncs *
+ *****************/
+
+static void cgrp_kfunc_load_test(void)
+{
+	struct cgroup *cgrp, *ref;
+
+	cgrp = bpf_cgroup_from_id(0);
+	if (!cgrp)
+		return;
+
+	ref = bpf_cgroup_acquire(cgrp);
+	if (!ref) {
+		bpf_cgroup_release(cgrp);
+		return;
+	}
+
+	bpf_cgroup_release(ref);
+	bpf_cgroup_release(cgrp);
+}
+
+SEC("raw_tp")
+__failure __msg("calling kernel function")
+int BPF_PROG(cgrp_kfunc_raw_tp)
+{
+	cgrp_kfunc_load_test();
+	return 0;
+}
+
+SEC("syscall")
+__success
+int BPF_PROG(cgrp_kfunc_syscall)
+{
+	cgrp_kfunc_load_test();
+	return 0;
+}
+
+SEC("tracepoint")
+__success
+int BPF_PROG(cgrp_kfunc_tracepoint)
+{
+	cgrp_kfunc_load_test();
+	return 0;
+}
+
+SEC("perf_event")
+__success
+int BPF_PROG(cgrp_kfunc_perf_event)
+{
+	cgrp_kfunc_load_test();
+	return 0;
+}
+
+/******************
+ * cpumask kfuncs *
+ ******************/
+
+static void cpumask_kfunc_load_test(void)
+{
+	struct bpf_cpumask *alloc, *ref;
+
+	alloc = bpf_cpumask_create();
+	if (!alloc)
+		return;
+
+	ref = bpf_cpumask_acquire(alloc);
+	bpf_cpumask_set_cpu(0, alloc);
+	bpf_cpumask_test_cpu(0, (const struct cpumask *)ref);
+
+	bpf_cpumask_release(ref);
+	bpf_cpumask_release(alloc);
+}
+
+SEC("raw_tp")
+__failure __msg("calling kernel function")
+int BPF_PROG(cpumask_kfunc_raw_tp)
+{
+	cpumask_kfunc_load_test();
+	return 0;
+}
+
+SEC("syscall")
+__success
+int BPF_PROG(cpumask_kfunc_syscall)
+{
+	cpumask_kfunc_load_test();
+	return 0;
+}
+
+SEC("tracepoint")
+__success
+int BPF_PROG(cpumask_kfunc_tracepoint)
+{
+	cpumask_kfunc_load_test();
+	return 0;
+}
+
+SEC("perf_event")
+__success
+int BPF_PROG(cpumask_kfunc_perf_event)
+{
+	cpumask_kfunc_load_test();
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/verifier_ld_ind.c b/tools/testing/selftests/bpf/progs/verifier_ld_ind.c
new file mode 100644
index 000000000000..c925ba9a2e74
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_ld_ind.c
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/ld_ind.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
+#include "bpf_misc.h"
+
+SEC("socket")
+__description("ld_ind: check calling conv, r1")
+__failure __msg("R1 !read_ok")
+__failure_unpriv
+__naked void ind_check_calling_conv_r1(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 1;						\
+	.8byte %[ld_ind];				\
+	r0 = r1;					\
+	exit;						\
+"	:
+	: __imm_insn(ld_ind, BPF_LD_IND(BPF_W, BPF_REG_1, -0x200000))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("ld_ind: check calling conv, r2")
+__failure __msg("R2 !read_ok")
+__failure_unpriv
+__naked void ind_check_calling_conv_r2(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r2 = 1;						\
+	.8byte %[ld_ind];				\
+	r0 = r2;					\
+	exit;						\
+"	:
+	: __imm_insn(ld_ind, BPF_LD_IND(BPF_W, BPF_REG_2, -0x200000))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("ld_ind: check calling conv, r3")
+__failure __msg("R3 !read_ok")
+__failure_unpriv
+__naked void ind_check_calling_conv_r3(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r3 = 1;						\
+	.8byte %[ld_ind];				\
+	r0 = r3;					\
+	exit;						\
+"	:
+	: __imm_insn(ld_ind, BPF_LD_IND(BPF_W, BPF_REG_3, -0x200000))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("ld_ind: check calling conv, r4")
+__failure __msg("R4 !read_ok")
+__failure_unpriv
+__naked void ind_check_calling_conv_r4(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r4 = 1;						\
+	.8byte %[ld_ind];				\
+	r0 = r4;					\
+	exit;						\
+"	:
+	: __imm_insn(ld_ind, BPF_LD_IND(BPF_W, BPF_REG_4, -0x200000))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("ld_ind: check calling conv, r5")
+__failure __msg("R5 !read_ok")
+__failure_unpriv
+__naked void ind_check_calling_conv_r5(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r5 = 1;						\
+	.8byte %[ld_ind];				\
+	r0 = r5;					\
+	exit;						\
+"	:
+	: __imm_insn(ld_ind, BPF_LD_IND(BPF_W, BPF_REG_5, -0x200000))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("ld_ind: check calling conv, r7")
+__success __success_unpriv __retval(1)
+__naked void ind_check_calling_conv_r7(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r7 = 1;						\
+	.8byte %[ld_ind];				\
+	r0 = r7;					\
+	exit;						\
+"	:
+	: __imm_insn(ld_ind, BPF_LD_IND(BPF_W, BPF_REG_7, -0x200000))
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_ldsx.c b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
new file mode 100644
index 000000000000..c8494b682c31
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_ldsx.c
@@ -0,0 +1,447 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "bpf_arena_common.h"
+
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
+	defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390) || \
+	defined(__TARGET_ARCH_loongarch)) && \
+	__clang_major__ >= 18
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARENA);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__uint(max_entries, 1);
+} arena SEC(".maps");
+
+SEC("socket")
+__description("LDSX, S8")
+__success __success_unpriv __retval(-2)
+__naked void ldsx_s8(void)
+{
+	asm volatile (
+	"r1 = 0x3fe;"
+	"*(u64 *)(r10 - 8) = r1;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r0 = *(s8 *)(r10 - 8);"
+#else
+	"r0 = *(s8 *)(r10 - 1);"
+#endif
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("socket")
+__description("LDSX, S16")
+__success __success_unpriv __retval(-2)
+__naked void ldsx_s16(void)
+{
+	asm volatile (
+	"r1 = 0x3fffe;"
+	"*(u64 *)(r10 - 8) = r1;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r0 = *(s16 *)(r10 - 8);"
+#else
+	"r0 = *(s16 *)(r10 - 2);"
+#endif
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("socket")
+__description("LDSX, S32")
+__success __success_unpriv __retval(-1)
+__naked void ldsx_s32(void)
+{
+	asm volatile (
+	"r1 = 0xfffffffe;"
+	"*(u64 *)(r10 - 8) = r1;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r0 = *(s32 *)(r10 - 8);"
+#else
+	"r0 = *(s32 *)(r10 - 4);"
+#endif
+	"r0 >>= 1;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("socket")
+__description("LDSX, S8 range checking, privileged")
+__log_level(2) __success __retval(1)
+__msg("R1=scalar(smin=smin32=-128,smax=smax32=127)")
+__naked void ldsx_s8_range_priv(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"*(u64 *)(r10 - 8) = r0;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r1 = *(s8 *)(r10 - 8);"
+#else
+	"r1 = *(s8 *)(r10 - 1);"
+#endif
+	/* r1 with s8 range */
+	"if r1 s> 0x7f goto l0_%=;"
+	"if r1 s< -0x80 goto l0_%=;"
+	"r0 = 1;"
+"l1_%=:"
+	"exit;"
+"l0_%=:"
+	"r0 = 2;"
+	"goto l1_%=;"
+	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("LDSX, S16 range checking")
+__success __success_unpriv __retval(1)
+__naked void ldsx_s16_range(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"*(u64 *)(r10 - 8) = r0;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r1 = *(s16 *)(r10 - 8);"
+#else
+	"r1 = *(s16 *)(r10 - 2);"
+#endif
+	/* r1 with s16 range */
+	"if r1 s> 0x7fff goto l0_%=;"
+	"if r1 s< -0x8000 goto l0_%=;"
+	"r0 = 1;"
+"l1_%=:"
+	"exit;"
+"l0_%=:"
+	"r0 = 2;"
+	"goto l1_%=;"
+	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("LDSX, S32 range checking")
+__success __success_unpriv __retval(1)
+__naked void ldsx_s32_range(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"*(u64 *)(r10 - 8) = r0;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r1 = *(s32 *)(r10 - 8);"
+#else
+	"r1 = *(s32 *)(r10 - 4);"
+#endif
+	/* r1 with s16 range */
+	"if r1 s> 0x7fffFFFF goto l0_%=;"
+	"if r1 s< -0x80000000 goto l0_%=;"
+	"r0 = 1;"
+"l1_%=:"
+	"exit;"
+"l0_%=:"
+	"r0 = 2;"
+	"goto l1_%=;"
+	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("LDSX, xdp s32 xdp_md->data")
+__failure __msg("invalid bpf_context access")
+__naked void ldsx_ctx_1(void)
+{
+	asm volatile (
+	"r2 = *(s32 *)(r1 + %[xdp_md_data]);"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("LDSX, xdp s32 xdp_md->data_end")
+__failure __msg("invalid bpf_context access")
+__naked void ldsx_ctx_2(void)
+{
+	asm volatile (
+	"r2 = *(s32 *)(r1 + %[xdp_md_data_end]);"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("LDSX, xdp s32 xdp_md->data_meta")
+__failure __msg("invalid bpf_context access")
+__naked void ldsx_ctx_3(void)
+{
+	asm volatile (
+	"r2 = *(s32 *)(r1 + %[xdp_md_data_meta]);"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("tcx/ingress")
+__description("LDSX, tcx s32 __sk_buff->data")
+__failure __msg("invalid bpf_context access")
+__naked void ldsx_ctx_4(void)
+{
+	asm volatile (
+	"r2 = *(s32 *)(r1 + %[sk_buff_data]);"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_const(sk_buff_data, offsetof(struct __sk_buff, data))
+	: __clobber_all);
+}
+
+SEC("tcx/ingress")
+__description("LDSX, tcx s32 __sk_buff->data_end")
+__failure __msg("invalid bpf_context access")
+__naked void ldsx_ctx_5(void)
+{
+	asm volatile (
+	"r2 = *(s32 *)(r1 + %[sk_buff_data_end]);"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_const(sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tcx/ingress")
+__description("LDSX, tcx s32 __sk_buff->data_meta")
+__failure __msg("invalid bpf_context access")
+__naked void ldsx_ctx_6(void)
+{
+	asm volatile (
+	"r2 = *(s32 *)(r1 + %[sk_buff_data_meta]);"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_const(sk_buff_data_meta, offsetof(struct __sk_buff, data_meta))
+	: __clobber_all);
+}
+
+SEC("flow_dissector")
+__description("LDSX, flow_dissector s32 __sk_buff->data")
+__failure __msg("invalid bpf_context access")
+__naked void ldsx_ctx_7(void)
+{
+	asm volatile (
+	"r2 = *(s32 *)(r1 + %[sk_buff_data]);"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_const(sk_buff_data, offsetof(struct __sk_buff, data))
+	: __clobber_all);
+}
+
+SEC("flow_dissector")
+__description("LDSX, flow_dissector s32 __sk_buff->data_end")
+__failure __msg("invalid bpf_context access")
+__naked void ldsx_ctx_8(void)
+{
+	asm volatile (
+	"r2 = *(s32 *)(r1 + %[sk_buff_data_end]);"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_const(sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("syscall")
+__description("Arena LDSX Disasm")
+__success
+__arch_x86_64
+__jited("movslq	0x10(%rax,%r12), %r14")
+__jited("movswq	0x18(%rax,%r12), %r14")
+__jited("movsbq	0x20(%rax,%r12), %r14")
+__jited("movslq	0x10(%rdi,%r12), %r15")
+__jited("movswq	0x18(%rdi,%r12), %r15")
+__jited("movsbq	0x20(%rdi,%r12), %r15")
+__arch_arm64
+__jited("add	x11, x7, x28")
+__jited("ldrsw	x21, [x11, #0x10]")
+__jited("add	x11, x7, x28")
+__jited("ldrsh	x21, [x11, #0x18]")
+__jited("add	x11, x7, x28")
+__jited("ldrsb	x21, [x11, #0x20]")
+__jited("add	x11, x0, x28")
+__jited("ldrsw	x22, [x11, #0x10]")
+__jited("add	x11, x0, x28")
+__jited("ldrsh	x22, [x11, #0x18]")
+__jited("add	x11, x0, x28")
+__jited("ldrsb	x22, [x11, #0x20]")
+__naked void arena_ldsx_disasm(void *ctx)
+{
+	asm volatile (
+	"r1 = %[arena] ll;"
+	"r2 = 0;"
+	"r3 = 1;"
+	"r4 = %[numa_no_node];"
+	"r5 = 0;"
+	"call %[bpf_arena_alloc_pages];"
+	"r0 = addr_space_cast(r0, 0x0, 0x1);"
+	"r1 = r0;"
+	"r8 = *(s32 *)(r0 + 16);"
+	"r8 = *(s16 *)(r0 + 24);"
+	"r8 = *(s8  *)(r0 + 32);"
+	"r9 = *(s32 *)(r1 + 16);"
+	"r9 = *(s16 *)(r1 + 24);"
+	"r9 = *(s8  *)(r1 + 32);"
+	"r0 = 0;"
+	"exit;"
+	:: __imm(bpf_arena_alloc_pages),
+	   __imm_addr(arena),
+	   __imm_const(numa_no_node, NUMA_NO_NODE)
+	:  __clobber_all
+	);
+}
+
+SEC("syscall")
+__description("Arena LDSX Exception")
+__success __retval(0)
+__arch_x86_64
+__arch_arm64
+__naked void arena_ldsx_exception(void *ctx)
+{
+	asm volatile (
+	"r1 = %[arena] ll;"
+	"r0 = 0xdeadbeef;"
+	"r0 = addr_space_cast(r0, 0x0, 0x1);"
+	"r1 = 0x3fe;"
+	"*(u64 *)(r0 + 0) = r1;"
+	"r0 = *(s8 *)(r0 + 0);"
+	"exit;"
+	:
+	:  __imm_addr(arena)
+	:  __clobber_all
+	);
+}
+
+SEC("syscall")
+__description("Arena LDSX, S8")
+__success __retval(-1)
+__arch_x86_64
+__arch_arm64
+__naked void arena_ldsx_s8(void *ctx)
+{
+	asm volatile (
+	"r1 = %[arena] ll;"
+	"r2 = 0;"
+	"r3 = 1;"
+	"r4 = %[numa_no_node];"
+	"r5 = 0;"
+	"call %[bpf_arena_alloc_pages];"
+	"r0 = addr_space_cast(r0, 0x0, 0x1);"
+	"r1 = 0x3fe;"
+	"*(u64 *)(r0 + 0) = r1;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r0 = *(s8 *)(r0 + 0);"
+#else
+	"r0 = *(s8 *)(r0 + 7);"
+#endif
+	"r0 >>= 1;"
+	"exit;"
+	:: __imm(bpf_arena_alloc_pages),
+	   __imm_addr(arena),
+	   __imm_const(numa_no_node, NUMA_NO_NODE)
+	:  __clobber_all
+	);
+}
+
+SEC("syscall")
+__description("Arena LDSX, S16")
+__success __retval(-1)
+__arch_x86_64
+__arch_arm64
+__naked void arena_ldsx_s16(void *ctx)
+{
+	asm volatile (
+	"r1 = %[arena] ll;"
+	"r2 = 0;"
+	"r3 = 1;"
+	"r4 = %[numa_no_node];"
+	"r5 = 0;"
+	"call %[bpf_arena_alloc_pages];"
+	"r0 = addr_space_cast(r0, 0x0, 0x1);"
+	"r1 = 0x3fffe;"
+	"*(u64 *)(r0 + 0) = r1;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r0 = *(s16 *)(r0 + 0);"
+#else
+	"r0 = *(s16 *)(r0 + 6);"
+#endif
+	"r0 >>= 1;"
+	"exit;"
+	:: __imm(bpf_arena_alloc_pages),
+	   __imm_addr(arena),
+	   __imm_const(numa_no_node, NUMA_NO_NODE)
+	:  __clobber_all
+	);
+}
+
+SEC("syscall")
+__description("Arena LDSX, S32")
+__success __retval(-1)
+__arch_x86_64
+__arch_arm64
+__naked void arena_ldsx_s32(void *ctx)
+{
+	asm volatile (
+	"r1 = %[arena] ll;"
+	"r2 = 0;"
+	"r3 = 1;"
+	"r4 = %[numa_no_node];"
+	"r5 = 0;"
+	"call %[bpf_arena_alloc_pages];"
+	"r0 = addr_space_cast(r0, 0x0, 0x1);"
+	"r1 = 0xfffffffe;"
+	"*(u64 *)(r0 + 0) = r1;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r0 = *(s32 *)(r0 + 0);"
+#else
+	"r0 = *(s32 *)(r0 + 4);"
+#endif
+	"r0 >>= 1;"
+	"exit;"
+	:: __imm(bpf_arena_alloc_pages),
+	   __imm_addr(arena),
+	   __imm_const(numa_no_node, NUMA_NO_NODE)
+	:  __clobber_all
+	);
+}
+
+/* to retain debug info for BTF generation */
+void kfunc_root(void)
+{
+	bpf_arena_alloc_pages(0, 0, 0, 0, 0);
+}
+
+#else
+
+SEC("socket")
+__description("cpuv4 is not supported by compiler or jit, use a dummy test")
+__success
+int dummy_test(void)
+{
+	return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_leak_ptr.c b/tools/testing/selftests/bpf/progs/verifier_leak_ptr.c
new file mode 100644
index 000000000000..d153fbe50055
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_leak_ptr.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/leak_ptr.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, long long);
+} map_hash_8b SEC(".maps");
+
+SEC("socket")
+__description("leak pointer into ctx 1")
+__failure __msg("BPF_ATOMIC stores into R1 ctx is not allowed")
+__failure_unpriv __msg_unpriv("R2 leaks addr into mem")
+__naked void leak_pointer_into_ctx_1(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	*(u64*)(r1 + %[__sk_buff_cb_0]) = r0;		\
+	r2 = %[map_hash_8b] ll;				\
+	lock *(u64 *)(r1 + %[__sk_buff_cb_0]) += r2;	\
+	exit;						\
+"	:
+	: __imm_addr(map_hash_8b),
+	  __imm_const(__sk_buff_cb_0, offsetof(struct __sk_buff, cb[0]))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("leak pointer into ctx 2")
+__failure __msg("BPF_ATOMIC stores into R1 ctx is not allowed")
+__failure_unpriv __msg_unpriv("R10 leaks addr into mem")
+__naked void leak_pointer_into_ctx_2(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	*(u64*)(r1 + %[__sk_buff_cb_0]) = r0;		\
+	lock *(u64 *)(r1 + %[__sk_buff_cb_0]) += r10;	\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_cb_0, offsetof(struct __sk_buff, cb[0]))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("leak pointer into ctx 3")
+__success __failure_unpriv __msg_unpriv("R2 leaks addr into ctx")
+__retval(0)
+__naked void leak_pointer_into_ctx_3(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	r2 = %[map_hash_8b] ll;				\
+	*(u64*)(r1 + %[__sk_buff_cb_0]) = r2;		\
+	exit;						\
+"	:
+	: __imm_addr(map_hash_8b),
+	  __imm_const(__sk_buff_cb_0, offsetof(struct __sk_buff, cb[0]))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("leak pointer into map val")
+__success __failure_unpriv __msg_unpriv("R6 leaks addr into mem")
+__retval(0)
+__naked void leak_pointer_into_map_val(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r3 = 0;						\
+	*(u64*)(r0 + 0) = r3;				\
+	lock *(u64 *)(r0 + 0) += r6;			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c b/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c
new file mode 100644
index 000000000000..8f755d2464cf
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_linked_scalars.c
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("socket")
+__description("scalars: find linked scalars")
+__failure
+__msg("math between fp pointer and 2147483647 is not allowed")
+__naked void scalars(void)
+{
+	asm volatile ("				\
+	r0 = 0;					\
+	r1 = 0x80000001 ll;			\
+	r1 /= 1;				\
+	r2 = r1;				\
+	r4 = r1;				\
+	w2 += 0x7FFFFFFF;			\
+	w4 += 0;				\
+	if r2 == 0 goto l1;			\
+	exit;					\
+l1:						\
+	r4 >>= 63;				\
+	r3 = 1;					\
+	r3 -= r4;				\
+	r3 *= 0x7FFFFFFF;			\
+	r3 += r10;				\
+	*(u8*)(r3 - 1) = r0;			\
+	exit;					\
+"	::: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_live_stack.c b/tools/testing/selftests/bpf/progs/verifier_live_stack.c
new file mode 100644
index 000000000000..2de105057bbc
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_live_stack.c
@@ -0,0 +1,344 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, long long);
+} map SEC(".maps");
+
+SEC("socket")
+__log_level(2)
+__msg("(0) frame 0 insn 2 +written -8")
+__msg("(0) frame 0 insn 1 +live -24")
+__msg("(0) frame 0 insn 1 +written -8")
+__msg("(0) frame 0 insn 0 +live -8,-24")
+__msg("(0) frame 0 insn 0 +written -8")
+__msg("(0) live stack update done in 2 iterations")
+__naked void simple_read_simple_write(void)
+{
+	asm volatile (
+	"r1 = *(u64 *)(r10 - 8);"
+	"r2 = *(u64 *)(r10 - 24);"
+	"*(u64 *)(r10 - 8) = r1;"
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("(0) frame 0 insn 1 +live -8")
+__not_msg("(0) frame 0 insn 1 +written")
+__msg("(0) live stack update done in 2 iterations")
+__msg("(0) frame 0 insn 1 +live -16")
+__msg("(0) frame 0 insn 1 +written -32")
+__msg("(0) live stack update done in 2 iterations")
+__naked void read_write_join(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"if r0 > 42 goto 1f;"
+	"r0 = *(u64 *)(r10 - 8);"
+	"*(u64 *)(r10 - 32) = r0;"
+	"*(u64 *)(r10 - 40) = r0;"
+	"exit;"
+"1:"
+	"r0 = *(u64 *)(r10 - 16);"
+	"*(u64 *)(r10 - 32) = r0;"
+	"exit;"
+	:: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("2: (25) if r0 > 0x2a goto pc+1")
+__msg("7: (95) exit")
+__msg("(0) frame 0 insn 2 +written -16")
+__msg("(0) live stack update done in 2 iterations")
+__msg("7: (95) exit")
+__not_msg("(0) frame 0 insn 2")
+__msg("(0) live stack update done in 1 iterations")
+__naked void must_write_not_same_slot(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"r1 = -8;"
+	"if r0 > 42 goto 1f;"
+	"r1 = -16;"
+"1:"
+	"r2 = r10;"
+	"r2 += r1;"
+	"*(u64 *)(r2 + 0) = r0;"
+	"exit;"
+	:: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("(0) frame 0 insn 0 +written -8,-16")
+__msg("(0) live stack update done in 2 iterations")
+__msg("(0) frame 0 insn 0 +written -8")
+__msg("(0) live stack update done in 2 iterations")
+__naked void must_write_not_same_type(void)
+{
+	asm volatile (
+	"*(u64*)(r10 - 8) = 0;"
+	"r2 = r10;"
+	"r2 += -8;"
+	"r1 = %[map] ll;"
+	"call %[bpf_map_lookup_elem];"
+	"if r0 != 0 goto 1f;"
+	"r0 = r10;"
+	"r0 += -16;"
+"1:"
+	"*(u64 *)(r0 + 0) = 42;"
+	"exit;"
+	:
+        : __imm(bpf_get_prandom_u32),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map)
+	: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+__msg("(2,4) frame 0 insn 4 +written -8")
+__msg("(2,4) live stack update done in 2 iterations")
+__msg("(0) frame 0 insn 2 +written -8")
+__msg("(0) live stack update done in 2 iterations")
+__naked void caller_stack_write(void)
+{
+	asm volatile (
+	"r1 = r10;"
+	"r1 += -8;"
+	"call write_first_param;"
+	"exit;"
+	::: __clobber_all);
+}
+
+static __used __naked void write_first_param(void)
+{
+	asm volatile (
+	"*(u64 *)(r1 + 0) = 7;"
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("socket")
+__log_level(2)
+/* caller_stack_read() function */
+__msg("2: .12345.... (85) call pc+4")
+__msg("5: .12345.... (85) call pc+1")
+__msg("6: 0......... (95) exit")
+/* read_first_param() function */
+__msg("7: .1........ (79) r0 = *(u64 *)(r1 +0)")
+__msg("8: 0......... (95) exit")
+/* update for callsite at (2) */
+__msg("(2,7) frame 0 insn 7 +live -8")
+__msg("(2,7) live stack update done in 2 iterations")
+__msg("(0) frame 0 insn 2 +live -8")
+__msg("(0) live stack update done in 2 iterations")
+/* update for callsite at (5) */
+__msg("(5,7) frame 0 insn 7 +live -16")
+__msg("(5,7) live stack update done in 2 iterations")
+__msg("(0) frame 0 insn 5 +live -16")
+__msg("(0) live stack update done in 2 iterations")
+__naked void caller_stack_read(void)
+{
+	asm volatile (
+	"r1 = r10;"
+	"r1 += -8;"
+	"call read_first_param;"
+	"r1 = r10;"
+	"r1 += -16;"
+	"call read_first_param;"
+	"exit;"
+	::: __clobber_all);
+}
+
+static __used __naked void read_first_param(void)
+{
+	asm volatile (
+	"r0 = *(u64 *)(r1 + 0);"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("socket")
+__flag(BPF_F_TEST_STATE_FREQ)
+__log_level(2)
+/* read_first_param2() function */
+__msg(" 9: .1........ (79) r0 = *(u64 *)(r1 +0)")
+__msg("10: .......... (b7) r0 = 0")
+__msg("11: 0......... (05) goto pc+0")
+__msg("12: 0......... (95) exit")
+/*
+ * The purpose of the test is to check that checkpoint in
+ * read_first_param2() stops path traversal. This will only happen if
+ * verifier understands that fp[0]-8 at insn (12) is not alive.
+ */
+__msg("12: safe")
+__msg("processed 20 insns")
+__naked void caller_stack_pruning(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"if r0 == 42 goto 1f;"
+	"r0 = %[map] ll;"
+"1:"
+	"*(u64 *)(r10 - 8) = r0;"
+	"r1 = r10;"
+	"r1 += -8;"
+	/*
+	 * fp[0]-8 is either pointer to map or a scalar,
+	 * preventing state pruning at checkpoint created for call.
+	 */
+	"call read_first_param2;"
+	"exit;"
+	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm_addr(map)
+	: __clobber_all);
+}
+
+static __used __naked void read_first_param2(void)
+{
+	asm volatile (
+	"r0 = *(u64 *)(r1 + 0);"
+	"r0 = 0;"
+	/*
+	 * Checkpoint at goto +0 should fire,
+	 * as caller stack fp[0]-8 is not alive at this point.
+	 */
+	"goto +0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("socket")
+__flag(BPF_F_TEST_STATE_FREQ)
+__failure
+__msg("R1 type=scalar expected=map_ptr")
+__naked void caller_stack_pruning_callback(void)
+{
+	asm volatile (
+	"r0 = %[map] ll;"
+	"*(u64 *)(r10 - 8) = r0;"
+	"r1 = 2;"
+	"r2 = loop_cb ll;"
+	"r3 = r10;"
+	"r3 += -8;"
+	"r4 = 0;"
+	/*
+	 * fp[0]-8 is either pointer to map or a scalar,
+	 * preventing state pruning at checkpoint created for call.
+	 */
+	"call %[bpf_loop];"
+	"r0 = 42;"
+	"exit;"
+	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_loop),
+	  __imm_addr(map)
+	: __clobber_all);
+}
+
+static __used __naked void loop_cb(void)
+{
+	asm volatile (
+	/*
+	 * Checkpoint at function entry should not fire, as caller
+	 * stack fp[0]-8 is alive at this point.
+	 */
+	"r6 = r2;"
+	"r1 = *(u64 *)(r6 + 0);"
+	"*(u64*)(r10 - 8) = 7;"
+	"r2 = r10;"
+	"r2 += -8;"
+	"call %[bpf_map_lookup_elem];"
+	/*
+	 * This should stop verifier on a second loop iteration,
+	 * but only if verifier correctly maintains that fp[0]-8
+	 * is still alive.
+	 */
+	"*(u64 *)(r6 + 0) = 0;"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/*
+ * Because of a bug in verifier.c:compute_postorder()
+ * the program below overflowed traversal queue in that function.
+ */
+SEC("socket")
+__naked void syzbot_postorder_bug1(void)
+{
+	asm volatile (
+	"r0 = 0;"
+	"if r0 != 0 goto -1;"
+	"exit;"
+	::: __clobber_all);
+}
+
+struct {
+        __uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+        __uint(max_entries, 1);
+        __type(key, __u32);
+        __type(value, __u32);
+} map_array SEC(".maps");
+
+SEC("socket")
+__failure __msg("invalid read from stack R2 off=-1024 size=8")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked unsigned long caller_stack_write_tail_call(void)
+{
+        asm volatile (
+	"r6 = r1;"
+	"*(u64 *)(r10 - 8) = -8;"
+        "call %[bpf_get_prandom_u32];"
+        "if r0 != 42 goto 1f;"
+        "goto 2f;"
+  "1:"
+        "*(u64 *)(r10 - 8) = -1024;"
+  "2:"
+        "r1 = r6;"
+        "r2 = r10;"
+        "r2 += -8;"
+        "call write_tail_call;"
+        "r1 = *(u64 *)(r10 - 8);"
+        "r2 = r10;"
+        "r2 += r1;"
+        "r0 = *(u64 *)(r2 + 0);"
+        "exit;"
+        :: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+static __used __naked unsigned long write_tail_call(void)
+{
+        asm volatile (
+        "r6 = r2;"
+        "r2 = %[map_array] ll;"
+        "r3 = 0;"
+        "call %[bpf_tail_call];"
+        "*(u64 *)(r6 + 0) = -16;"
+        "r0 = 0;"
+        "exit;"
+	:
+	: __imm(bpf_tail_call),
+          __imm_addr(map_array)
+        : __clobber_all);
+}
diff --git a/tools/testing/selftests/bpf/progs/verifier_load_acquire.c b/tools/testing/selftests/bpf/progs/verifier_load_acquire.c
new file mode 100644
index 000000000000..74f4f19c10b8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_load_acquire.c
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Google LLC. */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
+#include "bpf_misc.h"
+
+#ifdef CAN_USE_LOAD_ACQ_STORE_REL
+
+SEC("socket")
+__description("load-acquire, 8-bit")
+__success __success_unpriv __retval(0)
+__naked void load_acquire_8(void)
+{
+	asm volatile (
+	"r0 = 0;"
+	"w1 = 0xfe;"
+	"*(u8 *)(r10 - 1) = w1;"
+	".8byte %[load_acquire_insn];" // w2 = load_acquire((u8 *)(r10 - 1));
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
+	"exit;"
+	:
+	: __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_2, BPF_REG_10, -1))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("load-acquire, 16-bit")
+__success __success_unpriv __retval(0)
+__naked void load_acquire_16(void)
+{
+	asm volatile (
+	"r0 = 0;"
+	"w1 = 0xfedc;"
+	"*(u16 *)(r10 - 2) = w1;"
+	".8byte %[load_acquire_insn];" // w2 = load_acquire((u16 *)(r10 - 2));
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
+	"exit;"
+	:
+	: __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_H, BPF_LOAD_ACQ, BPF_REG_2, BPF_REG_10, -2))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("load-acquire, 32-bit")
+__success __success_unpriv __retval(0)
+__naked void load_acquire_32(void)
+{
+	asm volatile (
+	"r0 = 0;"
+	"w1 = 0xfedcba09;"
+	"*(u32 *)(r10 - 4) = w1;"
+	".8byte %[load_acquire_insn];" // w2 = load_acquire((u32 *)(r10 - 4));
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
+	"exit;"
+	:
+	: __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_W, BPF_LOAD_ACQ, BPF_REG_2, BPF_REG_10, -4))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("load-acquire, 64-bit")
+__success __success_unpriv __retval(0)
+__naked void load_acquire_64(void)
+{
+	asm volatile (
+	"r0 = 0;"
+	"r1 = 0xfedcba0987654321 ll;"
+	"*(u64 *)(r10 - 8) = r1;"
+	".8byte %[load_acquire_insn];" // r2 = load_acquire((u64 *)(r10 - 8));
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
+	"exit;"
+	:
+	: __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_2, BPF_REG_10, -8))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("load-acquire with uninitialized src_reg")
+__failure __failure_unpriv __msg("R2 !read_ok")
+__naked void load_acquire_with_uninitialized_src_reg(void)
+{
+	asm volatile (
+	".8byte %[load_acquire_insn];" // r0 = load_acquire((u64 *)(r2 + 0));
+	"exit;"
+	:
+	: __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_2, 0))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("load-acquire with non-pointer src_reg")
+__failure __failure_unpriv __msg("R1 invalid mem access 'scalar'")
+__naked void load_acquire_with_non_pointer_src_reg(void)
+{
+	asm volatile (
+	"r1 = 0;"
+	".8byte %[load_acquire_insn];" // r0 = load_acquire((u64 *)(r1 + 0));
+	"exit;"
+	:
+	: __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_1, 0))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("misaligned load-acquire")
+__failure __failure_unpriv __msg("misaligned stack access off")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void load_acquire_misaligned(void)
+{
+	asm volatile (
+	"r1 = 0;"
+	"*(u64 *)(r10 - 8) = r1;"
+	".8byte %[load_acquire_insn];" // w0 = load_acquire((u32 *)(r10 - 5));
+	"exit;"
+	:
+	: __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_W, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_10, -5))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("load-acquire from ctx pointer")
+__failure __failure_unpriv __msg("BPF_ATOMIC loads from R1 ctx is not allowed")
+__naked void load_acquire_from_ctx_pointer(void)
+{
+	asm volatile (
+	".8byte %[load_acquire_insn];" // w0 = load_acquire((u8 *)(r1 + 0));
+	"exit;"
+	:
+	: __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_1, 0))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("load-acquire from pkt pointer")
+__failure __msg("BPF_ATOMIC loads from R2 pkt is not allowed")
+__naked void load_acquire_from_pkt_pointer(void)
+{
+	asm volatile (
+	"r2 = *(u32 *)(r1 + %[xdp_md_data]);"
+	"r3 = *(u32 *)(r1 + %[xdp_md_data_end]);"
+	"r1 = r2;"
+	"r1 += 8;"
+	"if r1 >= r3 goto l0_%=;"
+	".8byte %[load_acquire_insn];" // w0 = load_acquire((u8 *)(r2 + 0));
+"l0_%=:  r0 = 0;"
+	"exit;"
+	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)),
+	  __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_2, 0))
+	: __clobber_all);
+}
+
+SEC("flow_dissector")
+__description("load-acquire from flow_keys pointer")
+__failure __msg("BPF_ATOMIC loads from R2 flow_keys is not allowed")
+__naked void load_acquire_from_flow_keys_pointer(void)
+{
+	asm volatile (
+	"r2 = *(u64 *)(r1 + %[__sk_buff_flow_keys]);"
+	".8byte %[load_acquire_insn];" // w0 = load_acquire((u8 *)(r2 + 0));
+	"exit;"
+	:
+	: __imm_const(__sk_buff_flow_keys,
+		      offsetof(struct __sk_buff, flow_keys)),
+	  __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_2, 0))
+	: __clobber_all);
+}
+
+SEC("sk_reuseport")
+__description("load-acquire from sock pointer")
+__failure __msg("BPF_ATOMIC loads from R2 sock is not allowed")
+__naked void load_acquire_from_sock_pointer(void)
+{
+	asm volatile (
+	"r2 = *(u64 *)(r1 + %[sk_reuseport_md_sk]);"
+	// w0 = load_acquire((u8 *)(r2 + offsetof(struct bpf_sock, family)));
+	".8byte %[load_acquire_insn];"
+	"exit;"
+	:
+	: __imm_const(sk_reuseport_md_sk, offsetof(struct sk_reuseport_md, sk)),
+	  __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_B, BPF_LOAD_ACQ, BPF_REG_0, BPF_REG_2,
+				   offsetof(struct bpf_sock, family)))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("load-acquire with invalid register R15")
+__failure __failure_unpriv __msg("R15 is invalid")
+__naked void load_acquire_with_invalid_reg(void)
+{
+	asm volatile (
+	".8byte %[load_acquire_insn];" // r0 = load_acquire((u64 *)(r15 + 0));
+	"exit;"
+	:
+	: __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_0, 15 /* invalid reg */, 0))
+	: __clobber_all);
+}
+
+#else /* CAN_USE_LOAD_ACQ_STORE_REL */
+
+SEC("socket")
+__description("Clang version < 18, ENABLE_ATOMICS_TESTS not defined, and/or JIT doesn't support load-acquire, use a dummy test")
+__success
+int dummy_test(void)
+{
+	return 0;
+}
+
+#endif /* CAN_USE_LOAD_ACQ_STORE_REL */
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_loops1.c b/tools/testing/selftests/bpf/progs/verifier_loops1.c
new file mode 100644
index 000000000000..fbdde80e7b90
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_loops1.c
@@ -0,0 +1,307 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/loops1.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("xdp")
+__description("bounded loop, count to 4")
+__success __retval(4)
+__naked void bounded_loop_count_to_4(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+l0_%=:	r0 += 1;					\
+	if r0 < 4 goto l0_%=;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("bounded loop, count to 20")
+__success
+__naked void bounded_loop_count_to_20(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+l0_%=:	r0 += 3;					\
+	if r0 < 20 goto l0_%=;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("bounded loop, count from positive unknown to 4")
+__success
+__naked void from_positive_unknown_to_4(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	if r0 s< 0 goto l0_%=;				\
+l1_%=:	r0 += 1;					\
+	if r0 < 4 goto l1_%=;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("bounded loop, count from totally unknown to 4")
+__success
+__naked void from_totally_unknown_to_4(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+l0_%=:	r0 += 1;					\
+	if r0 < 4 goto l0_%=;				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("bounded loop, count to 4 with equality")
+__success
+__naked void count_to_4_with_equality(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+l0_%=:	r0 += 1;					\
+	if r0 != 4 goto l0_%=;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("bounded loop, start in the middle")
+__success
+__failure_unpriv __msg_unpriv("back-edge")
+__naked void loop_start_in_the_middle(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	goto l0_%=;					\
+l1_%=:	r0 += 1;					\
+l0_%=:	if r0 < 4 goto l1_%=;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("xdp")
+__description("bounded loop containing a forward jump")
+__success __retval(4)
+__naked void loop_containing_a_forward_jump(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+l1_%=:	r0 += 1;					\
+	if r0 == r0 goto l0_%=;				\
+l0_%=:	if r0 < 4 goto l1_%=;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("bounded loop that jumps out rather than in")
+__success
+__naked void jumps_out_rather_than_in(void)
+{
+	asm volatile ("					\
+	r6 = 0;						\
+l1_%=:	r6 += 1;					\
+	if r6 > 10000 goto l0_%=;			\
+	call %[bpf_get_prandom_u32];			\
+	goto l1_%=;					\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("infinite loop after a conditional jump")
+__failure __msg("program is too large")
+__naked void loop_after_a_conditional_jump(void)
+{
+	asm volatile ("					\
+	r0 = 5;						\
+	if r0 < 4 goto l0_%=;				\
+l1_%=:	r0 += 1;					\
+	goto l1_%=;					\
+l0_%=:	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("bounded recursion")
+__failure
+/* verifier limitation in detecting max stack depth */
+__msg("the call stack of 8 frames is too deep !")
+__naked void bounded_recursion(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	call bounded_recursion__1;			\
+	exit;						\
+"	::: __clobber_all);
+}
+
+static __naked __noinline __attribute__((used))
+void bounded_recursion__1(void)
+{
+	asm volatile ("					\
+	r1 += 1;					\
+	r0 = r1;					\
+	if r1 < 4 goto l0_%=;				\
+	exit;						\
+l0_%=:	call bounded_recursion__1;			\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("infinite loop in two jumps")
+__failure __msg("loop detected")
+__naked void infinite_loop_in_two_jumps(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+l1_%=:	goto l0_%=;					\
+l0_%=:	if r0 < 4 goto l1_%=;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("infinite loop: three-jump trick")
+__failure __msg("loop detected")
+__naked void infinite_loop_three_jump_trick(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+l2_%=:	r0 += 1;					\
+	r0 &= 1;					\
+	if r0 < 2 goto l0_%=;				\
+	exit;						\
+l0_%=:	r0 += 1;					\
+	r0 &= 1;					\
+	if r0 < 2 goto l1_%=;				\
+	exit;						\
+l1_%=:	r0 += 1;					\
+	r0 &= 1;					\
+	if r0 < 2 goto l2_%=;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("xdp")
+__description("not-taken loop with back jump to 1st insn")
+__success __retval(123)
+__naked void back_jump_to_1st_insn_1(void)
+{
+	asm volatile ("					\
+l0_%=:	r0 = 123;					\
+	if r0 == 4 goto l0_%=;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("xdp")
+__description("taken loop with back jump to 1st insn")
+__success __retval(55)
+__naked void back_jump_to_1st_insn_2(void)
+{
+	asm volatile ("					\
+	r1 = 10;					\
+	r2 = 0;						\
+	call back_jump_to_1st_insn_2__1;		\
+	exit;						\
+"	::: __clobber_all);
+}
+
+static __naked __noinline __attribute__((used))
+void back_jump_to_1st_insn_2__1(void)
+{
+	asm volatile ("					\
+l0_%=:	r2 += r1;					\
+	r1 -= 1;					\
+	if r1 != 0 goto l0_%=;				\
+	r0 = r2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("xdp")
+__description("taken loop with back jump to 1st insn, 2")
+__success __retval(55)
+__naked void jump_to_1st_insn_2(void)
+{
+	asm volatile ("					\
+	r1 = 10;					\
+	r2 = 0;						\
+	call jump_to_1st_insn_2__1;			\
+	exit;						\
+"	::: __clobber_all);
+}
+
+static __naked __noinline __attribute__((used))
+void jump_to_1st_insn_2__1(void)
+{
+	asm volatile ("					\
+l0_%=:	r2 += r1;					\
+	r1 -= 1;					\
+	if w1 != 0 goto l0_%=;				\
+	r0 = r2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("xdp")
+__success
+__naked void not_an_inifinite_loop(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0xff;					\
+	*(u64 *)(r10 - 8) = r0;				\
+	r0 = 0;						\
+loop_%=:						\
+	r0 = *(u64 *)(r10 - 8);				\
+	if r0 > 10 goto exit_%=;			\
+	r0 += 1;					\
+	*(u64 *)(r10 - 8) = r0;				\
+	r0 = 0;						\
+	goto loop_%=;					\
+exit_%=:						\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/*
+ * This test case triggered a bug in verifier.c:maybe_exit_scc().
+ * Speculative execution path reaches stack access instruction,
+ * stops and triggers maybe_exit_scc() w/o accompanying maybe_enter_scc() call.
+ */
+SEC("socket")
+__arch_x86_64
+__caps_unpriv(CAP_BPF)
+__naked void maybe_exit_scc_bug1(void)
+{
+	asm volatile (
+	"r0 = 100;"
+"1:"
+	/* Speculative execution path reaches and stops here. */
+	"*(u64 *)(r10 - 512) = r0;"
+	/* Condition is always false, but verifier speculatively executes the true branch. */
+	"if r0 <= 0x0 goto 1b;"
+	"exit;"
+	::: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_lsm.c b/tools/testing/selftests/bpf/progs/verifier_lsm.c
new file mode 100644
index 000000000000..6af9100a37ff
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_lsm.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("lsm/file_permission")
+__description("lsm bpf prog with -4095~0 retval. test 1")
+__success
+__naked int errno_zero_retval_test1(void *ctx)
+{
+	asm volatile (
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/file_permission")
+__description("lsm bpf prog with -4095~0 retval. test 2")
+__success
+__naked int errno_zero_retval_test2(void *ctx)
+{
+	asm volatile (
+	"r0 = -4095;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/file_mprotect")
+__description("lsm bpf prog with -4095~0 retval. test 4")
+__failure __msg("R0 has smin=-4096 smax=-4096 should have been in [-4095, 0]")
+__naked int errno_zero_retval_test4(void *ctx)
+{
+	asm volatile (
+	"r0 = -4096;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/file_mprotect")
+__description("lsm bpf prog with -4095~0 retval. test 5")
+__failure __msg("R0 has smin=4096 smax=4096 should have been in [-4095, 0]")
+__naked int errno_zero_retval_test5(void *ctx)
+{
+	asm volatile (
+	"r0 = 4096;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/file_mprotect")
+__description("lsm bpf prog with -4095~0 retval. test 6")
+__failure __msg("R0 has smin=1 smax=1 should have been in [-4095, 0]")
+__naked int errno_zero_retval_test6(void *ctx)
+{
+	asm volatile (
+	"r0 = 1;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/audit_rule_known")
+__description("lsm bpf prog with bool retval. test 1")
+__success
+__naked int bool_retval_test1(void *ctx)
+{
+	asm volatile (
+	"r0 = 1;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/audit_rule_known")
+__description("lsm bpf prog with bool retval. test 2")
+__success
+__success
+__naked int bool_retval_test2(void *ctx)
+{
+	asm volatile (
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/audit_rule_known")
+__description("lsm bpf prog with bool retval. test 3")
+__failure __msg("R0 has smin=-1 smax=-1 should have been in [0, 1]")
+__naked int bool_retval_test3(void *ctx)
+{
+	asm volatile (
+	"r0 = -1;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/audit_rule_known")
+__description("lsm bpf prog with bool retval. test 4")
+__failure __msg("R0 has smin=2 smax=2 should have been in [0, 1]")
+__naked int bool_retval_test4(void *ctx)
+{
+	asm volatile (
+	"r0 = 2;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/file_free_security")
+__success
+__description("lsm bpf prog with void retval. test 1")
+__naked int void_retval_test1(void *ctx)
+{
+	asm volatile (
+	"r0 = -4096;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/file_free_security")
+__success
+__description("lsm bpf prog with void retval. test 2")
+__naked int void_retval_test2(void *ctx)
+{
+	asm volatile (
+	"r0 = 4096;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/getprocattr")
+__description("lsm disabled hook: getprocattr")
+__failure __msg("points to disabled hook")
+__naked int disabled_hook_test1(void *ctx)
+{
+	asm volatile (
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/setprocattr")
+__description("lsm disabled hook: setprocattr")
+__failure __msg("points to disabled hook")
+__naked int disabled_hook_test2(void *ctx)
+{
+	asm volatile (
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm/ismaclabel")
+__description("lsm disabled hook: ismaclabel")
+__failure __msg("points to disabled hook")
+__naked int disabled_hook_test3(void *ctx)
+{
+	asm volatile (
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_lwt.c b/tools/testing/selftests/bpf/progs/verifier_lwt.c
new file mode 100644
index 000000000000..5ab746307309
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_lwt.c
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/lwt.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("lwt_in")
+__description("invalid direct packet write for LWT_IN")
+__failure __msg("cannot write into packet")
+__naked void packet_write_for_lwt_in(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r0 > r3 goto l0_%=;				\
+	*(u8*)(r2 + 0) = r2;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("lwt_out")
+__description("invalid direct packet write for LWT_OUT")
+__failure __msg("cannot write into packet")
+__naked void packet_write_for_lwt_out(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r0 > r3 goto l0_%=;				\
+	*(u8*)(r2 + 0) = r2;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("lwt_xmit")
+__description("direct packet write for LWT_XMIT")
+__success __retval(0)
+__naked void packet_write_for_lwt_xmit(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r0 > r3 goto l0_%=;				\
+	*(u8*)(r2 + 0) = r2;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("lwt_in")
+__description("direct packet read for LWT_IN")
+__success __retval(0)
+__naked void packet_read_for_lwt_in(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r0 > r3 goto l0_%=;				\
+	r0 = *(u8*)(r2 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("lwt_out")
+__description("direct packet read for LWT_OUT")
+__success __retval(0)
+__naked void packet_read_for_lwt_out(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r0 > r3 goto l0_%=;				\
+	r0 = *(u8*)(r2 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("lwt_xmit")
+__description("direct packet read for LWT_XMIT")
+__success __retval(0)
+__naked void packet_read_for_lwt_xmit(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r0 > r3 goto l0_%=;				\
+	r0 = *(u8*)(r2 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("lwt_xmit")
+__description("overlapping checks for direct packet access")
+__success __retval(0)
+__naked void checks_for_direct_packet_access(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r0 > r3 goto l0_%=;				\
+	r1 = r2;					\
+	r1 += 6;					\
+	if r1 > r3 goto l0_%=;				\
+	r0 = *(u16*)(r2 + 6);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("lwt_xmit")
+__description("make headroom for LWT_XMIT")
+__success __retval(0)
+__naked void make_headroom_for_lwt_xmit(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r2 = 34;					\
+	r3 = 0;						\
+	call %[bpf_skb_change_head];			\
+	/* split for s390 to succeed */			\
+	r1 = r6;					\
+	r2 = 42;					\
+	r3 = 0;						\
+	call %[bpf_skb_change_head];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_skb_change_head)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("invalid access of tc_classid for LWT_IN")
+__failure __msg("invalid bpf_context access")
+__failure_unpriv
+__naked void tc_classid_for_lwt_in(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[__sk_buff_tc_classid]);	\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_tc_classid, offsetof(struct __sk_buff, tc_classid))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("invalid access of tc_classid for LWT_OUT")
+__failure __msg("invalid bpf_context access")
+__failure_unpriv
+__naked void tc_classid_for_lwt_out(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[__sk_buff_tc_classid]);	\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_tc_classid, offsetof(struct __sk_buff, tc_classid))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("invalid access of tc_classid for LWT_XMIT")
+__failure __msg("invalid bpf_context access")
+__failure_unpriv
+__naked void tc_classid_for_lwt_xmit(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[__sk_buff_tc_classid]);	\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_tc_classid, offsetof(struct __sk_buff, tc_classid))
+	: __clobber_all);
+}
+
+SEC("lwt_in")
+__description("check skb->tc_classid half load not permitted for lwt prog")
+__failure __msg("invalid bpf_context access")
+__naked void not_permitted_for_lwt_prog(void)
+{
+	asm volatile (
+	"r0 = 0;"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r0 = *(u16*)(r1 + %[__sk_buff_tc_classid]);"
+#else
+	"r0 = *(u16*)(r1 + %[__imm_0]);"
+#endif
+	"exit;"
+	:
+	: __imm_const(__imm_0, offsetof(struct __sk_buff, tc_classid) + 2),
+	  __imm_const(__sk_buff_tc_classid, offsetof(struct __sk_buff, tc_classid))
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_map_in_map.c b/tools/testing/selftests/bpf/progs/verifier_map_in_map.c
new file mode 100644
index 000000000000..16b761e510f0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_map_in_map.c
@@ -0,0 +1,260 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/map_in_map.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+	__array(values, struct {
+		__uint(type, BPF_MAP_TYPE_ARRAY);
+		__uint(max_entries, 1);
+		__type(key, int);
+		__type(value, int);
+	});
+} map_in_map SEC(".maps");
+
+SEC("socket")
+__description("map in map access")
+__success __success_unpriv __retval(0)
+__naked void map_in_map_access(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_in_map] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = r0;					\
+	call %[bpf_map_lookup_elem];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_in_map)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("map in map state pruning")
+__success __msg("processed 15 insns")
+__log_level(2) __retval(0) __flag(BPF_F_TEST_STATE_FREQ)
+__naked void map_in_map_state_pruning(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r6 = r10;					\
+	r6 += -4;					\
+	r2 = r6;					\
+	r1 = %[map_in_map] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r2 = r6;					\
+	r1 = r0;					\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l1_%=;				\
+	r2 = r6;					\
+	r1 = %[map_in_map] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l2_%=;				\
+	exit;						\
+l2_%=:	r2 = r6;					\
+	r1 = r0;					\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l1_%=;				\
+	exit;						\
+l1_%=:	r0 = *(u32*)(r0 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_in_map)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("invalid inner map pointer")
+__failure __msg("R1 pointer arithmetic on map_ptr prohibited")
+__failure_unpriv
+__naked void invalid_inner_map_pointer(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_in_map] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = r0;					\
+	r1 += 8;					\
+	call %[bpf_map_lookup_elem];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_in_map)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("forgot null checking on the inner map pointer")
+__failure __msg("R1 type=map_value_or_null expected=map_ptr")
+__failure_unpriv
+__naked void on_the_inner_map_pointer(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_in_map] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = r0;					\
+	call %[bpf_map_lookup_elem];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_in_map)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map_ptr is never null")
+__success
+__naked void map_ptr_is_never_null(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	r1 = %[map_in_map] ll;				\
+	if r1 != 0 goto l0_%=;				\
+	r10 = 42;					\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_in_map)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map_ptr is never null inner")
+__success
+__naked void map_ptr_is_never_null_inner(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_in_map] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	if r0 != 0 goto l0_%=;				\
+	r10 = 42;					\
+l0_%=:  exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_in_map)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map_ptr is never null inner spill fill")
+__success
+__naked void map_ptr_is_never_null_inner_spill_fill(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_in_map] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	*(u64 *)(r10 -16) = r0;				\
+	r1 = *(u64 *)(r10 -16);				\
+	if r1 == 0 goto l1_%=;				\
+	exit;						\
+l1_%=:	r10 = 42;					\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_in_map)
+	: __clobber_all);
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+	__array(values, struct {
+		__uint(type, BPF_MAP_TYPE_RINGBUF);
+		__uint(max_entries, 64 * 1024);
+	});
+} rb_in_map SEC(".maps");
+
+struct rb_ctx {
+	void *rb;
+	struct bpf_dynptr dptr;
+};
+
+static __always_inline struct rb_ctx __rb_event_reserve(__u32 sz)
+{
+	struct rb_ctx rb_ctx = {};
+	void *rb;
+	__u32 cpu = bpf_get_smp_processor_id();
+	__u32 rb_slot = cpu & 1;
+
+	rb = bpf_map_lookup_elem(&rb_in_map, &rb_slot);
+	if (!rb)
+		return rb_ctx;
+
+	rb_ctx.rb = rb;
+	bpf_ringbuf_reserve_dynptr(rb, sz, 0, &rb_ctx.dptr);
+
+	return rb_ctx;
+}
+
+static __noinline void __rb_event_submit(struct rb_ctx *ctx)
+{
+	if (!ctx->rb)
+		return;
+
+	/* If the verifier (incorrectly) concludes that ctx->rb can be
+	 * NULL at this point, we'll get "BPF_EXIT instruction in main
+	 * prog would lead to reference leak" error
+	 */
+	bpf_ringbuf_submit_dynptr(&ctx->dptr, 0);
+}
+
+SEC("socket")
+int map_ptr_is_never_null_rb(void *ctx)
+{
+	struct rb_ctx event_ctx = __rb_event_reserve(256);
+	__rb_event_submit(&event_ctx);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_map_ptr.c b/tools/testing/selftests/bpf/progs/verifier_map_ptr.c
new file mode 100644
index 000000000000..e2767d27d8aa
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_map_ptr.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/map_ptr.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#define MAX_ENTRIES 11
+
+struct test_val {
+	unsigned int index;
+	int foo[MAX_ENTRIES];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct test_val);
+} map_array_48b SEC(".maps");
+
+struct other_val {
+	long long foo;
+	long long bar;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, struct other_val);
+} map_hash_16b SEC(".maps");
+
+SEC("socket")
+__description("bpf_map_ptr: read with negative offset rejected")
+__failure __msg("R1 is bpf_array invalid negative access: off=-8")
+__failure_unpriv
+__msg_unpriv("access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN")
+__naked void read_with_negative_offset_rejected(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 = %[map_array_48b] ll;			\
+	r6 = *(u64*)(r1 - 8);				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bpf_map_ptr: write rejected")
+__failure __msg("only read from bpf_array is supported")
+__failure_unpriv
+__msg_unpriv("access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN")
+__naked void bpf_map_ptr_write_rejected(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	*(u64*)(r10 - 8) = r0;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	*(u64*)(r1 + 0) = r2;				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+/* The first element of struct bpf_map is a SHA256 hash of 32 bytes, accessing
+ * into this array is valid. The opts field is now at offset 33.
+ */
+SEC("socket")
+__description("bpf_map_ptr: read non-existent field rejected")
+__failure
+__msg("cannot access ptr member ops with moff 32 in struct bpf_map with off 33 size 4")
+__failure_unpriv
+__msg_unpriv("access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void read_non_existent_field_rejected(void)
+{
+	asm volatile ("					\
+	r6 = 0;						\
+	r1 = %[map_array_48b] ll;			\
+	r6 = *(u32*)(r1 + 33);				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bpf_map_ptr: read ops field accepted")
+__success __failure_unpriv
+__msg_unpriv("access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN")
+__retval(1)
+__naked void ptr_read_ops_field_accepted(void)
+{
+	asm volatile ("					\
+	r6 = 0;						\
+	r1 = %[map_array_48b] ll;			\
+	r6 = *(u64*)(r1 + 0);				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bpf_map_ptr: r = 0, map_ptr = map_ptr + r")
+__success __failure_unpriv
+__msg_unpriv("R1 has pointer with unsupported alu operation")
+__retval(0)
+__naked void map_ptr_map_ptr_r(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	*(u64*)(r10 - 8) = r0;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r0 = 0;						\
+	r1 = %[map_hash_16b] ll;			\
+	r1 += r0;					\
+	call %[bpf_map_lookup_elem];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_16b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("bpf_map_ptr: r = 0, r = r + map_ptr")
+__success __failure_unpriv
+__msg_unpriv("R0 has pointer with unsupported alu operation")
+__retval(0)
+__naked void _0_r_r_map_ptr(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	*(u64*)(r10 - 8) = r0;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	r0 = %[map_hash_16b] ll;			\
+	r1 += r0;					\
+	call %[bpf_map_lookup_elem];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_16b)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_map_ptr_mixing.c b/tools/testing/selftests/bpf/progs/verifier_map_ptr_mixing.c
new file mode 100644
index 000000000000..c5a7c1ddc562
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_map_ptr_mixing.c
@@ -0,0 +1,265 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/map_ptr_mixing.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#define MAX_ENTRIES 11
+
+struct test_val {
+	unsigned int index;
+	int foo[MAX_ENTRIES];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct test_val);
+} map_array_48b SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, struct test_val);
+} map_hash_48b SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+	__array(values, struct {
+		__uint(type, BPF_MAP_TYPE_ARRAY);
+		__uint(max_entries, 1);
+		__type(key, int);
+		__type(value, int);
+	});
+} map_in_map SEC(".maps");
+
+void dummy_prog_42_socket(void);
+void dummy_prog_24_socket(void);
+void dummy_prog_loop1_socket(void);
+void dummy_prog_loop2_socket(void);
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 4);
+	__uint(key_size, sizeof(int));
+	__array(values, void (void));
+} map_prog1_socket SEC(".maps") = {
+	.values = {
+		[0] = (void *)&dummy_prog_42_socket,
+		[1] = (void *)&dummy_prog_loop1_socket,
+		[2] = (void *)&dummy_prog_24_socket,
+	},
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 8);
+	__uint(key_size, sizeof(int));
+	__array(values, void (void));
+} map_prog2_socket SEC(".maps") = {
+	.values = {
+		[1] = (void *)&dummy_prog_loop2_socket,
+		[2] = (void *)&dummy_prog_24_socket,
+		[7] = (void *)&dummy_prog_42_socket,
+	},
+};
+
+SEC("socket")
+__auxiliary __auxiliary_unpriv
+__naked void dummy_prog_42_socket(void)
+{
+	asm volatile ("r0 = 42; exit;");
+}
+
+SEC("socket")
+__auxiliary __auxiliary_unpriv
+__naked void dummy_prog_24_socket(void)
+{
+	asm volatile ("r0 = 24; exit;");
+}
+
+SEC("socket")
+__auxiliary __auxiliary_unpriv
+__naked void dummy_prog_loop1_socket(void)
+{
+	asm volatile ("			\
+	r3 = 1;				\
+	r2 = %[map_prog1_socket] ll;	\
+	call %[bpf_tail_call];		\
+	r0 = 41;			\
+	exit;				\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_socket)
+	: __clobber_all);
+}
+
+SEC("socket")
+__auxiliary __auxiliary_unpriv
+__naked void dummy_prog_loop2_socket(void)
+{
+	asm volatile ("			\
+	r3 = 1;				\
+	r2 = %[map_prog2_socket] ll;	\
+	call %[bpf_tail_call];		\
+	r0 = 41;			\
+	exit;				\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog2_socket)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("calls: two calls returning different map pointers for lookup (hash, array)")
+__success __retval(1)
+__naked void pointers_for_lookup_hash_array(void)
+{
+	asm volatile ("					\
+	/* main prog */					\
+	if r1 != 0 goto l0_%=;				\
+	call pointers_for_lookup_hash_array__1;		\
+	goto l1_%=;					\
+l0_%=:	call pointers_for_lookup_hash_array__2;		\
+l1_%=:	r1 = r0;					\
+	r2 = 0;						\
+	*(u64*)(r10 - 8) = r2;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l2_%=;				\
+	r1 = %[test_val_foo];				\
+	*(u64*)(r0 + 0) = r1;				\
+	r0 = 1;						\
+l2_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+static __naked __noinline __attribute__((used))
+void pointers_for_lookup_hash_array__1(void)
+{
+	asm volatile ("					\
+	r0 = %[map_hash_48b] ll;			\
+	exit;						\
+"	:
+	: __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+static __naked __noinline __attribute__((used))
+void pointers_for_lookup_hash_array__2(void)
+{
+	asm volatile ("					\
+	r0 = %[map_array_48b] ll;			\
+	exit;						\
+"	:
+	: __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("calls: two calls returning different map pointers for lookup (hash, map in map)")
+__failure __msg("only read from bpf_array is supported")
+__naked void lookup_hash_map_in_map(void)
+{
+	asm volatile ("					\
+	/* main prog */					\
+	if r1 != 0 goto l0_%=;				\
+	call lookup_hash_map_in_map__1;			\
+	goto l1_%=;					\
+l0_%=:	call lookup_hash_map_in_map__2;			\
+l1_%=:	r1 = r0;					\
+	r2 = 0;						\
+	*(u64*)(r10 - 8) = r2;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l2_%=;				\
+	r1 = %[test_val_foo];				\
+	*(u64*)(r0 + 0) = r1;				\
+	r0 = 1;						\
+l2_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+static __naked __noinline __attribute__((used))
+void lookup_hash_map_in_map__1(void)
+{
+	asm volatile ("					\
+	r0 = %[map_array_48b] ll;			\
+	exit;						\
+"	:
+	: __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+static __naked __noinline __attribute__((used))
+void lookup_hash_map_in_map__2(void)
+{
+	asm volatile ("					\
+	r0 = %[map_in_map] ll;				\
+	exit;						\
+"	:
+	: __imm_addr(map_in_map)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("cond: two branches returning different map pointers for lookup (tail, tail)")
+__success __failure_unpriv __msg_unpriv("tail_call abusing map_ptr")
+__retval(42)
+__naked void pointers_for_lookup_tail_tail_1(void)
+{
+	asm volatile ("					\
+	r6 = *(u32*)(r1 + %[__sk_buff_mark]);		\
+	if r6 != 0 goto l0_%=;				\
+	r2 = %[map_prog2_socket] ll;			\
+	goto l1_%=;					\
+l0_%=:	r2 = %[map_prog1_socket] ll;			\
+l1_%=:	r3 = 7;						\
+	call %[bpf_tail_call];				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_socket),
+	  __imm_addr(map_prog2_socket),
+	  __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("cond: two branches returning same map pointers for lookup (tail, tail)")
+__success __success_unpriv __retval(42)
+__naked void pointers_for_lookup_tail_tail_2(void)
+{
+	asm volatile ("					\
+	r6 = *(u32*)(r1 + %[__sk_buff_mark]);		\
+	if r6 == 0 goto l0_%=;				\
+	r2 = %[map_prog2_socket] ll;			\
+	goto l1_%=;					\
+l0_%=:	r2 = %[map_prog2_socket] ll;			\
+l1_%=:	r3 = 7;						\
+	call %[bpf_tail_call];				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog2_socket),
+	  __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark))
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_map_ret_val.c b/tools/testing/selftests/bpf/progs/verifier_map_ret_val.c
new file mode 100644
index 000000000000..1639628b832d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_map_ret_val.c
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/map_ret_val.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, long long);
+} map_hash_8b SEC(".maps");
+
+SEC("socket")
+__description("invalid map_fd for function call")
+__failure __msg("fd 0 is not pointing to valid bpf_map")
+__failure_unpriv
+__naked void map_fd_for_function_call(void)
+{
+	asm volatile ("					\
+	r2 = 0;						\
+	*(u64*)(r10 - 8) = r2;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	.8byte %[ld_map_fd];				\
+	.8byte 0;					\
+	call %[bpf_map_delete_elem];			\
+	exit;						\
+"	:
+	: __imm(bpf_map_delete_elem),
+	  __imm_insn(ld_map_fd, BPF_RAW_INSN(BPF_LD | BPF_DW | BPF_IMM, BPF_REG_1, BPF_PSEUDO_MAP_FD, 0, 0))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("don't check return value before access")
+__failure __msg("R0 invalid mem access 'map_value_or_null'")
+__failure_unpriv
+__naked void check_return_value_before_access(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r1 = 0;						\
+	*(u64*)(r0 + 0) = r1;				\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("access memory with incorrect alignment")
+__failure __msg("misaligned value access")
+__failure_unpriv
+__flag(BPF_F_STRICT_ALIGNMENT)
+__naked void access_memory_with_incorrect_alignment_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 0;						\
+	*(u64*)(r0 + 4) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("sometimes access memory with incorrect alignment")
+__failure __msg("R0 invalid mem access")
+__msg_unpriv("R0 leaks addr")
+__flag(BPF_F_STRICT_ALIGNMENT)
+__naked void access_memory_with_incorrect_alignment_2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 0;						\
+	*(u64*)(r0 + 0) = r1;				\
+	exit;						\
+l0_%=:	r1 = 1;						\
+	*(u64*)(r0 + 0) = r1;				\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_masking.c b/tools/testing/selftests/bpf/progs/verifier_masking.c
new file mode 100644
index 000000000000..5732cc1b4c47
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_masking.c
@@ -0,0 +1,410 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/masking.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("socket")
+__description("masking, test out of bounds 1")
+__success __success_unpriv __retval(0)
+__naked void test_out_of_bounds_1(void)
+{
+	asm volatile ("					\
+	w1 = 5;						\
+	w2 = %[__imm_0];				\
+	r2 -= r1;					\
+	r2 |= r1;					\
+	r2 = -r2;					\
+	r2 s>>= 63;					\
+	r1 &= r2;					\
+	r0 = r1;					\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 5 - 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("masking, test out of bounds 2")
+__success __success_unpriv __retval(0)
+__naked void test_out_of_bounds_2(void)
+{
+	asm volatile ("					\
+	w1 = 1;						\
+	w2 = %[__imm_0];				\
+	r2 -= r1;					\
+	r2 |= r1;					\
+	r2 = -r2;					\
+	r2 s>>= 63;					\
+	r1 &= r2;					\
+	r0 = r1;					\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 1 - 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("masking, test out of bounds 3")
+__success __success_unpriv __retval(0)
+__naked void test_out_of_bounds_3(void)
+{
+	asm volatile ("					\
+	w1 = 0xffffffff;				\
+	w2 = %[__imm_0];				\
+	r2 -= r1;					\
+	r2 |= r1;					\
+	r2 = -r2;					\
+	r2 s>>= 63;					\
+	r1 &= r2;					\
+	r0 = r1;					\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 0xffffffff - 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("masking, test out of bounds 4")
+__success __success_unpriv __retval(0)
+__naked void test_out_of_bounds_4(void)
+{
+	asm volatile ("					\
+	w1 = 0xffffffff;				\
+	w2 = %[__imm_0];				\
+	r2 -= r1;					\
+	r2 |= r1;					\
+	r2 = -r2;					\
+	r2 s>>= 63;					\
+	r1 &= r2;					\
+	r0 = r1;					\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 1 - 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("masking, test out of bounds 5")
+__success __success_unpriv __retval(0)
+__naked void test_out_of_bounds_5(void)
+{
+	asm volatile ("					\
+	w1 = -1;					\
+	w2 = %[__imm_0];				\
+	r2 -= r1;					\
+	r2 |= r1;					\
+	r2 = -r2;					\
+	r2 s>>= 63;					\
+	r1 &= r2;					\
+	r0 = r1;					\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 1 - 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("masking, test out of bounds 6")
+__success __success_unpriv __retval(0)
+__naked void test_out_of_bounds_6(void)
+{
+	asm volatile ("					\
+	w1 = -1;					\
+	w2 = %[__imm_0];				\
+	r2 -= r1;					\
+	r2 |= r1;					\
+	r2 = -r2;					\
+	r2 s>>= 63;					\
+	r1 &= r2;					\
+	r0 = r1;					\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 0xffffffff - 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("masking, test out of bounds 7")
+__success __success_unpriv __retval(0)
+__naked void test_out_of_bounds_7(void)
+{
+	asm volatile ("					\
+	r1 = 5;						\
+	w2 = %[__imm_0];				\
+	r2 -= r1;					\
+	r2 |= r1;					\
+	r2 = -r2;					\
+	r2 s>>= 63;					\
+	r1 &= r2;					\
+	r0 = r1;					\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 5 - 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("masking, test out of bounds 8")
+__success __success_unpriv __retval(0)
+__naked void test_out_of_bounds_8(void)
+{
+	asm volatile ("					\
+	r1 = 1;						\
+	w2 = %[__imm_0];				\
+	r2 -= r1;					\
+	r2 |= r1;					\
+	r2 = -r2;					\
+	r2 s>>= 63;					\
+	r1 &= r2;					\
+	r0 = r1;					\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 1 - 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("masking, test out of bounds 9")
+__success __success_unpriv __retval(0)
+__naked void test_out_of_bounds_9(void)
+{
+	asm volatile ("					\
+	r1 = 0xffffffff;				\
+	w2 = %[__imm_0];				\
+	r2 -= r1;					\
+	r2 |= r1;					\
+	r2 = -r2;					\
+	r2 s>>= 63;					\
+	r1 &= r2;					\
+	r0 = r1;					\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 0xffffffff - 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("masking, test out of bounds 10")
+__success __success_unpriv __retval(0)
+__naked void test_out_of_bounds_10(void)
+{
+	asm volatile ("					\
+	r1 = 0xffffffff;				\
+	w2 = %[__imm_0];				\
+	r2 -= r1;					\
+	r2 |= r1;					\
+	r2 = -r2;					\
+	r2 s>>= 63;					\
+	r1 &= r2;					\
+	r0 = r1;					\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 1 - 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("masking, test out of bounds 11")
+__success __success_unpriv __retval(0)
+__naked void test_out_of_bounds_11(void)
+{
+	asm volatile ("					\
+	r1 = -1;					\
+	w2 = %[__imm_0];				\
+	r2 -= r1;					\
+	r2 |= r1;					\
+	r2 = -r2;					\
+	r2 s>>= 63;					\
+	r1 &= r2;					\
+	r0 = r1;					\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 1 - 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("masking, test out of bounds 12")
+__success __success_unpriv __retval(0)
+__naked void test_out_of_bounds_12(void)
+{
+	asm volatile ("					\
+	r1 = -1;					\
+	w2 = %[__imm_0];				\
+	r2 -= r1;					\
+	r2 |= r1;					\
+	r2 = -r2;					\
+	r2 s>>= 63;					\
+	r1 &= r2;					\
+	r0 = r1;					\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 0xffffffff - 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("masking, test in bounds 1")
+__success __success_unpriv __retval(4)
+__naked void masking_test_in_bounds_1(void)
+{
+	asm volatile ("					\
+	w1 = 4;						\
+	w2 = %[__imm_0];				\
+	r2 -= r1;					\
+	r2 |= r1;					\
+	r2 = -r2;					\
+	r2 s>>= 63;					\
+	r1 &= r2;					\
+	r0 = r1;					\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 5 - 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("masking, test in bounds 2")
+__success __success_unpriv __retval(0)
+__naked void masking_test_in_bounds_2(void)
+{
+	asm volatile ("					\
+	w1 = 0;						\
+	w2 = %[__imm_0];				\
+	r2 -= r1;					\
+	r2 |= r1;					\
+	r2 = -r2;					\
+	r2 s>>= 63;					\
+	r1 &= r2;					\
+	r0 = r1;					\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 0xffffffff - 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("masking, test in bounds 3")
+__success __success_unpriv __retval(0xfffffffe)
+__naked void masking_test_in_bounds_3(void)
+{
+	asm volatile ("					\
+	w1 = 0xfffffffe;				\
+	w2 = %[__imm_0];				\
+	r2 -= r1;					\
+	r2 |= r1;					\
+	r2 = -r2;					\
+	r2 s>>= 63;					\
+	r1 &= r2;					\
+	r0 = r1;					\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 0xffffffff - 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("masking, test in bounds 4")
+__success __success_unpriv __retval(0xabcde)
+__naked void masking_test_in_bounds_4(void)
+{
+	asm volatile ("					\
+	w1 = 0xabcde;					\
+	w2 = %[__imm_0];				\
+	r2 -= r1;					\
+	r2 |= r1;					\
+	r2 = -r2;					\
+	r2 s>>= 63;					\
+	r1 &= r2;					\
+	r0 = r1;					\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 0xabcdef - 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("masking, test in bounds 5")
+__success __success_unpriv __retval(0)
+__naked void masking_test_in_bounds_5(void)
+{
+	asm volatile ("					\
+	w1 = 0;						\
+	w2 = %[__imm_0];				\
+	r2 -= r1;					\
+	r2 |= r1;					\
+	r2 = -r2;					\
+	r2 s>>= 63;					\
+	r1 &= r2;					\
+	r0 = r1;					\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 1 - 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("masking, test in bounds 6")
+__success __success_unpriv __retval(46)
+__naked void masking_test_in_bounds_6(void)
+{
+	asm volatile ("					\
+	w1 = 46;					\
+	w2 = %[__imm_0];				\
+	r2 -= r1;					\
+	r2 |= r1;					\
+	r2 = -r2;					\
+	r2 s>>= 63;					\
+	r1 &= r2;					\
+	r0 = r1;					\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 47 - 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("masking, test in bounds 7")
+__success __success_unpriv __retval(46)
+__naked void masking_test_in_bounds_7(void)
+{
+	asm volatile ("					\
+	r3 = -46;					\
+	r3 *= -1;					\
+	w2 = %[__imm_0];				\
+	r2 -= r3;					\
+	r2 |= r3;					\
+	r2 = -r2;					\
+	r2 s>>= 63;					\
+	r3 &= r2;					\
+	r0 = r3;					\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 47 - 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("masking, test in bounds 8")
+__success __success_unpriv __retval(0)
+__naked void masking_test_in_bounds_8(void)
+{
+	asm volatile ("					\
+	r3 = -47;					\
+	r3 *= -1;					\
+	w2 = %[__imm_0];				\
+	r2 -= r3;					\
+	r2 |= r3;					\
+	r2 = -r2;					\
+	r2 s>>= 63;					\
+	r3 &= r2;					\
+	r0 = r3;					\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, 47 - 1)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c b/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c
new file mode 100644
index 000000000000..6d1edaef9213
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c
@@ -0,0 +1,109 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
+#include "bpf_misc.h"
+
+SEC("raw_tp")
+__description("may_goto 0")
+__arch_x86_64
+__arch_s390x
+__arch_arm64
+__xlated("0: r0 = 1")
+__xlated("1: exit")
+__success
+__naked void may_goto_simple(void)
+{
+	asm volatile (
+	".8byte %[may_goto];"
+	"r0 = 1;"
+	".8byte %[may_goto];"
+	"exit;"
+	:
+	: __imm_insn(may_goto, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 0 /* offset */, 0))
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__description("batch 2 of may_goto 0")
+__arch_x86_64
+__arch_s390x
+__arch_arm64
+__xlated("0: r0 = 1")
+__xlated("1: exit")
+__success
+__naked void may_goto_batch_0(void)
+{
+	asm volatile (
+	".8byte %[may_goto1];"
+	".8byte %[may_goto1];"
+	"r0 = 1;"
+	".8byte %[may_goto1];"
+	".8byte %[may_goto1];"
+	"exit;"
+	:
+	: __imm_insn(may_goto1, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 0 /* offset */, 0))
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__description("may_goto batch with offsets 2/1/0")
+__arch_x86_64
+__arch_s390x
+__arch_arm64
+__xlated("0: r0 = 1")
+__xlated("1: exit")
+__success
+__naked void may_goto_batch_1(void)
+{
+	asm volatile (
+	".8byte %[may_goto1];"
+	".8byte %[may_goto2];"
+	".8byte %[may_goto3];"
+	"r0 = 1;"
+	".8byte %[may_goto1];"
+	".8byte %[may_goto2];"
+	".8byte %[may_goto3];"
+	"exit;"
+	:
+	: __imm_insn(may_goto1, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 2 /* offset */, 0)),
+	  __imm_insn(may_goto2, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 1 /* offset */, 0)),
+	  __imm_insn(may_goto3, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 0 /* offset */, 0))
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__description("may_goto batch with offsets 2/0")
+__arch_x86_64
+__arch_s390x
+__arch_arm64
+__xlated("0: *(u64 *)(r10 -16) = 65535")
+__xlated("1: *(u64 *)(r10 -8) = 0")
+__xlated("2: r11 = *(u64 *)(r10 -16)")
+__xlated("3: if r11 == 0x0 goto pc+6")
+__xlated("4: r11 -= 1")
+__xlated("5: if r11 != 0x0 goto pc+2")
+__xlated("6: r11 = -16")
+__xlated("7: call unknown")
+__xlated("8: *(u64 *)(r10 -16) = r11")
+__xlated("9: r0 = 1")
+__xlated("10: r0 = 2")
+__xlated("11: exit")
+__success
+__naked void may_goto_batch_2(void)
+{
+	asm volatile (
+	".8byte %[may_goto1];"
+	".8byte %[may_goto3];"
+	"r0 = 1;"
+	"r0 = 2;"
+	"exit;"
+	:
+	: __imm_insn(may_goto1, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 2 /* offset */, 0)),
+	  __imm_insn(may_goto3, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 0 /* offset */, 0))
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_may_goto_2.c b/tools/testing/selftests/bpf/progs/verifier_may_goto_2.c
new file mode 100644
index 000000000000..b891faf50660
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_may_goto_2.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+int gvar;
+
+SEC("raw_tp")
+__description("C code with may_goto 0")
+__success
+int may_goto_c_code(void)
+{
+	int i, tmp[3];
+
+	for (i = 0; i < 3 && can_loop; i++)
+		tmp[i] = 0;
+
+	for (i = 0; i < 3 && can_loop; i++)
+		tmp[i] = gvar - i;
+
+	for (i = 0; i < 3 && can_loop; i++)
+		gvar += tmp[i];
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_meta_access.c b/tools/testing/selftests/bpf/progs/verifier_meta_access.c
new file mode 100644
index 000000000000..d81722fb5f19
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_meta_access.c
@@ -0,0 +1,284 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/meta_access.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("xdp")
+__description("meta access, test1")
+__success __retval(0)
+__naked void meta_access_test1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r0 > r3 goto l0_%=;				\
+	r0 = *(u8*)(r2 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("meta access, test2")
+__failure __msg("invalid access to packet, off=-8")
+__naked void meta_access_test2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r0 = r2;					\
+	r0 -= 8;					\
+	r4 = r2;					\
+	r4 += 8;					\
+	if r4 > r3 goto l0_%=;				\
+	r0 = *(u8*)(r0 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("meta access, test3")
+__failure __msg("invalid access to packet")
+__naked void meta_access_test3(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r0 = r2;					\
+	r0 += 8;					\
+	if r0 > r3 goto l0_%=;				\
+	r0 = *(u8*)(r2 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("meta access, test4")
+__failure __msg("invalid access to packet")
+__naked void meta_access_test4(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r4 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r0 = r4;					\
+	r0 += 8;					\
+	if r0 > r3 goto l0_%=;				\
+	r0 = *(u8*)(r2 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("meta access, test5")
+__failure __msg("R3 !read_ok")
+__naked void meta_access_test5(void)
+{
+	asm volatile ("					\
+	r3 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r4 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r0 = r3;					\
+	r0 += 8;					\
+	if r0 > r4 goto l0_%=;				\
+	r2 = -8;					\
+	call %[bpf_xdp_adjust_meta];			\
+	r0 = *(u8*)(r3 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_xdp_adjust_meta),
+	  __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("meta access, test6")
+__failure __msg("invalid access to packet")
+__naked void meta_access_test6(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r0 = r3;					\
+	r0 += 8;					\
+	r4 = r2;					\
+	r4 += 8;					\
+	if r4 > r0 goto l0_%=;				\
+	r0 = *(u8*)(r2 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("meta access, test7")
+__success __retval(0)
+__naked void meta_access_test7(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r0 = r3;					\
+	r0 += 8;					\
+	r4 = r2;					\
+	r4 += 8;					\
+	if r4 > r3 goto l0_%=;				\
+	r0 = *(u8*)(r2 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("meta access, test8")
+__success __retval(0)
+__naked void meta_access_test8(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r4 = r2;					\
+	r4 += 0xFFFF;					\
+	if r4 > r3 goto l0_%=;				\
+	r0 = *(u8*)(r2 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("meta access, test9")
+__failure __msg("invalid access to packet")
+__naked void meta_access_test9(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r4 = r2;					\
+	r4 += 0xFFFF;					\
+	r4 += 1;					\
+	if r4 > r3 goto l0_%=;				\
+	r0 = *(u8*)(r2 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("meta access, test10")
+__failure __msg("invalid access to packet")
+__naked void meta_access_test10(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r4 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r5 = 42;					\
+	r6 = 24;					\
+	*(u64*)(r10 - 8) = r5;				\
+	lock *(u64 *)(r10 - 8) += r6;			\
+	r5 = *(u64*)(r10 - 8);				\
+	if r5 > 100 goto l0_%=;				\
+	r3 += r5;					\
+	r5 = r3;					\
+	r6 = r2;					\
+	r6 += 8;					\
+	if r6 > r5 goto l0_%=;				\
+	r2 = *(u8*)(r2 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("meta access, test11")
+__success __retval(0)
+__naked void meta_access_test11(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r5 = 42;					\
+	r6 = 24;					\
+	*(u64*)(r10 - 8) = r5;				\
+	lock *(u64 *)(r10 - 8) += r6;			\
+	r5 = *(u64*)(r10 - 8);				\
+	if r5 > 100 goto l0_%=;				\
+	r2 += r5;					\
+	r5 = r2;					\
+	r6 = r2;					\
+	r6 += 8;					\
+	if r6 > r3 goto l0_%=;				\
+	r5 = *(u8*)(r5 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("meta access, test12")
+__success __retval(0)
+__naked void meta_access_test12(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r4 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r5 = r3;					\
+	r5 += 16;					\
+	if r5 > r4 goto l0_%=;				\
+	r0 = *(u8*)(r3 + 0);				\
+	r5 = r2;					\
+	r5 += 16;					\
+	if r5 > r3 goto l0_%=;				\
+	r0 = *(u8*)(r2 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_movsx.c b/tools/testing/selftests/bpf/progs/verifier_movsx.c
new file mode 100644
index 000000000000..a4d8814eb5ed
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_movsx.c
@@ -0,0 +1,354 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
+	defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390) || \
+	defined(__TARGET_ARCH_loongarch)) && \
+	__clang_major__ >= 18
+
+SEC("socket")
+__description("MOV32SX, S8")
+__success __success_unpriv __retval(0x23)
+__naked void mov32sx_s8(void)
+{
+	asm volatile ("					\
+	w0 = 0xff23;					\
+	w0 = (s8)w0;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV32SX, S16")
+__success __success_unpriv __retval(0xFFFFff23)
+__naked void mov32sx_s16(void)
+{
+	asm volatile ("					\
+	w0 = 0xff23;					\
+	w0 = (s16)w0;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV64SX, S8")
+__success __success_unpriv __retval(-2)
+__naked void mov64sx_s8(void)
+{
+	asm volatile ("					\
+	r0 = 0x1fe;					\
+	r0 = (s8)r0;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV64SX, S16")
+__success __success_unpriv __retval(0xf23)
+__naked void mov64sx_s16(void)
+{
+	asm volatile ("					\
+	r0 = 0xf0f23;					\
+	r0 = (s16)r0;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV64SX, S32")
+__success __success_unpriv __retval(-1)
+__naked void mov64sx_s32(void)
+{
+	asm volatile ("					\
+	r0 = 0xfffffffe;				\
+	r0 = (s32)r0;					\
+	r0 >>= 1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV32SX, S8, range_check")
+__success __success_unpriv __retval(1)
+__naked void mov32sx_s8_range(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = (s8)w0;					\
+	/* w1 with s8 range */				\
+	if w1 s> 0x7f goto l0_%=;			\
+	if w1 s< -0x80 goto l0_%=;			\
+	r0 = 1;						\
+l1_%=:							\
+	exit;						\
+l0_%=:							\
+	r0 = 2;						\
+	goto l1_%=;					\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV32SX, S16, range_check")
+__success __success_unpriv __retval(1)
+__naked void mov32sx_s16_range(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	w1 = (s16)w0;					\
+	/* w1 with s16 range */				\
+	if w1 s> 0x7fff goto l0_%=;			\
+	if w1 s< -0x80ff goto l0_%=;			\
+	r0 = 1;						\
+l1_%=:							\
+	exit;						\
+l0_%=:							\
+	r0 = 2;						\
+	goto l1_%=;					\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV32SX, S16, range_check 2")
+__success __success_unpriv __retval(1)
+__naked void mov32sx_s16_range_2(void)
+{
+	asm volatile ("					\
+	r1 = 65535;					\
+	w2 = (s16)w1;					\
+	r2 >>= 1;					\
+	if r2 != 0x7fffFFFF goto l0_%=;			\
+	r0 = 1;						\
+l1_%=:							\
+	exit;						\
+l0_%=:							\
+	r0 = 0;						\
+	goto l1_%=;					\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV64SX, S8, range_check")
+__success __success_unpriv __retval(1)
+__naked void mov64sx_s8_range(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = (s8)r0;					\
+	/* r1 with s8 range */				\
+	if r1 s> 0x7f goto l0_%=;			\
+	if r1 s< -0x80 goto l0_%=;			\
+	r0 = 1;						\
+l1_%=:							\
+	exit;						\
+l0_%=:							\
+	r0 = 2;						\
+	goto l1_%=;					\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV64SX, S16, range_check")
+__success __success_unpriv __retval(1)
+__naked void mov64sx_s16_range(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = (s16)r0;					\
+	/* r1 with s16 range */				\
+	if r1 s> 0x7fff goto l0_%=;			\
+	if r1 s< -0x8000 goto l0_%=;			\
+	r0 = 1;						\
+l1_%=:							\
+	exit;						\
+l0_%=:							\
+	r0 = 2;						\
+	goto l1_%=;					\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV64SX, S32, range_check")
+__success __success_unpriv __retval(1)
+__naked void mov64sx_s32_range(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = (s32)r0;					\
+	/* r1 with s32 range */				\
+	if r1 s> 0x7fffffff goto l0_%=;			\
+	if r1 s< -0x80000000 goto l0_%=;		\
+	r0 = 1;						\
+l1_%=:							\
+	exit;						\
+l0_%=:							\
+	r0 = 2;						\
+	goto l1_%=;					\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV64SX, S16, R10 Sign Extension")
+__failure __msg("R1 type=scalar expected=fp, pkt, pkt_meta, map_key, map_value, mem, ringbuf_mem, buf, trusted_ptr_")
+__failure_unpriv __msg_unpriv("R10 sign-extension part of pointer")
+__naked void mov64sx_s16_r10(void)
+{
+	asm volatile ("					\
+	r1 = 553656332;					\
+	*(u32 *)(r10 - 8) = r1; 			\
+	r1 = (s16)r10;					\
+	r1 += -8;					\
+	r2 = 3;						\
+	if r2 <= r1 goto l0_%=;				\
+l0_%=:							\
+	call %[bpf_trace_printk];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_trace_printk)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV32SX, S8, var_off u32_max")
+__failure __msg("infinite loop detected")
+__failure_unpriv __msg_unpriv("back-edge from insn 2 to 0")
+__naked void mov64sx_s32_varoff_1(void)
+{
+	asm volatile ("					\
+l0_%=:							\
+	r3 = *(u8 *)(r10 -387);				\
+	w7 = (s8)w3;					\
+	if w7 >= 0x2533823b goto l0_%=;			\
+	w0 = 0;						\
+	exit;						\
+"	:
+	:
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV32SX, S8, var_off not u32_max, positive after s8 extension")
+__success __retval(0)
+__success_unpriv
+#ifdef SPEC_V1
+__xlated_unpriv("w0 = 0")
+__xlated_unpriv("exit")
+__xlated_unpriv("nospec") /* inserted to prevent `frame pointer is read only` */
+__xlated_unpriv("goto pc-1")
+#endif
+__naked void mov64sx_s32_varoff_2(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r3 = r0;					\
+	r3 &= 0xf;					\
+	w7 = (s8)w3;					\
+	if w7 s>= 16 goto l0_%=;			\
+	w0 = 0;						\
+	exit;						\
+l0_%=:							\
+	r10 = 1;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV32SX, S8, var_off not u32_max, negative after s8 extension")
+__success __retval(0)
+__success_unpriv
+#ifdef SPEC_V1
+__xlated_unpriv("w0 = 0")
+__xlated_unpriv("exit")
+__xlated_unpriv("nospec") /* inserted to prevent `frame pointer is read only` */
+__xlated_unpriv("goto pc-1")
+#endif
+__naked void mov64sx_s32_varoff_3(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r3 = r0;					\
+	r3 &= 0xf;					\
+	r3 |= 0x80;					\
+	w7 = (s8)w3;					\
+	if w7 s>= -5 goto l0_%=;			\
+	w0 = 0;						\
+	exit;						\
+l0_%=:							\
+	r10 = 1;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV64SX, S8, unsigned range_check")
+__success __retval(0)
+__naked void mov64sx_s8_range_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0x1;					\
+	r0 += 0xfe;					\
+	r0 = (s8)r0;					\
+	if r0 < 0xfffffffffffffffe goto label_%=;	\
+	r0 = 0;						\
+	exit;						\
+label_%=:						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("MOV32SX, S8, unsigned range_check")
+__success __retval(0)
+__naked void mov32sx_s8_range_check(void)
+{
+	asm volatile ("                                 \
+	call %[bpf_get_prandom_u32];                    \
+	w0 &= 0x1;                                      \
+	w0 += 0xfe;                                     \
+	w0 = (s8)w0;                                    \
+	if w0 < 0xfffffffe goto label_%=;               \
+	r0 = 0;                                         \
+	exit;                                           \
+label_%=: 	                                        \
+	exit;                                           \
+	"      :
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+#else
+
+SEC("socket")
+__description("cpuv4 is not supported by compiler or jit, use a dummy test")
+__success
+int dummy_test(void)
+{
+	return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_mtu.c b/tools/testing/selftests/bpf/progs/verifier_mtu.c
new file mode 100644
index 000000000000..256956ea1ac5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_mtu.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("tc/ingress")
+__description("uninit/mtu: write rejected")
+__success
+__caps_unpriv(CAP_BPF|CAP_NET_ADMIN)
+__failure_unpriv __msg_unpriv("invalid read from stack")
+int tc_uninit_mtu(struct __sk_buff *ctx)
+{
+	__u32 mtu;
+
+	bpf_check_mtu(ctx, 0, &mtu, 0, 0);
+	return TCX_PASS;
+}
+
+char LICENSE[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_mul.c b/tools/testing/selftests/bpf/progs/verifier_mul.c
new file mode 100644
index 000000000000..7145fe3351d5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_mul.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Nandakumar Edamana */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+
+/* Intended to test the abstract multiplication technique(s) used by
+ * the verifier. Using assembly to avoid compiler optimizations.
+ */
+SEC("fentry/bpf_fentry_test1")
+void BPF_PROG(mul_precise, int x)
+{
+	/* First, force the verifier to be uncertain about the value:
+	 *     unsigned int a = (bpf_get_prandom_u32() & 0x2) | 0x1;
+	 *
+	 * Assuming the verifier is using tnum, a must be tnum{.v=0x1, .m=0x2}.
+	 * Then a * 0x3 would be m0m1 (m for uncertain). Added imprecision
+	 * would cause the following to fail, because the required return value
+	 * is 0:
+	 *     return (a * 0x3) & 0x4);
+	 */
+	asm volatile ("\
+	call %[bpf_get_prandom_u32];\
+	r0 &= 0x2;\
+	r0 |= 0x1;\
+	r0 *= 0x3;\
+	r0 &= 0x4;\
+	if r0 != 0 goto l0_%=;\
+	r0 = 0;\
+	goto l1_%=;\
+l0_%=:\
+	r0 = 1;\
+l1_%=:\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
diff --git a/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c b/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c
new file mode 100644
index 000000000000..e2cbc5bda65e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_netfilter_ctx.c
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+
+#include "bpf_misc.h"
+
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+SEC("netfilter")
+__description("netfilter invalid context access, size too short")
+__failure __msg("invalid bpf_context access")
+__naked void with_invalid_ctx_access_test1(void)
+{
+	asm volatile ("					\
+	r2 = *(u8*)(r1 + %[__bpf_nf_ctx_state]);	\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__bpf_nf_ctx_state, offsetof(struct bpf_nf_ctx, state))
+	: __clobber_all);
+}
+
+SEC("netfilter")
+__description("netfilter invalid context access, size too short")
+__failure __msg("invalid bpf_context access")
+__naked void with_invalid_ctx_access_test2(void)
+{
+	asm volatile ("					\
+	r2 = *(u16*)(r1 + %[__bpf_nf_ctx_skb]);	\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__bpf_nf_ctx_skb, offsetof(struct bpf_nf_ctx, skb))
+	: __clobber_all);
+}
+
+SEC("netfilter")
+__description("netfilter invalid context access, past end of ctx")
+__failure __msg("invalid bpf_context access")
+__naked void with_invalid_ctx_access_test3(void)
+{
+	asm volatile ("					\
+	r2 = *(u64*)(r1 + %[__bpf_nf_ctx_size]);	\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__bpf_nf_ctx_size, sizeof(struct bpf_nf_ctx))
+	: __clobber_all);
+}
+
+SEC("netfilter")
+__description("netfilter invalid context, write")
+__failure __msg("invalid bpf_context access")
+__naked void with_invalid_ctx_access_test4(void)
+{
+	asm volatile ("					\
+	r2 = r1;					\
+	*(u64*)(r2 + 0) = r1;				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm_const(__bpf_nf_ctx_skb, offsetof(struct bpf_nf_ctx, skb))
+	: __clobber_all);
+}
+
+#define NF_DROP 0
+#define NF_ACCEPT 1
+
+SEC("netfilter")
+__description("netfilter valid context read and invalid write")
+__failure __msg("only read is supported")
+int with_invalid_ctx_access_test5(struct bpf_nf_ctx *ctx)
+{
+	struct nf_hook_state *state = (void *)ctx->state;
+
+	state->sk = NULL;
+	return NF_ACCEPT;
+}
+
+SEC("netfilter")
+__description("netfilter test prog with skb and state read access")
+__success __failure_unpriv
+__retval(0)
+int with_valid_ctx_access_test6(struct bpf_nf_ctx *ctx)
+{
+	struct __sk_buff *skb = (struct __sk_buff *)ctx->skb;
+	const struct nf_hook_state *state = ctx->state;
+	const struct iphdr *iph;
+	const struct tcphdr *th;
+	u8 buffer_iph[20] = {};
+	u8 buffer_th[40] = {};
+	struct bpf_dynptr ptr;
+	uint8_t ihl;
+
+	if (ctx->skb->len <= 20 || bpf_dynptr_from_skb(skb, 0, &ptr))
+		return NF_ACCEPT;
+
+	iph = bpf_dynptr_slice(&ptr, 0, buffer_iph, sizeof(buffer_iph));
+	if (!iph)
+		return NF_ACCEPT;
+
+	if (state->pf != 2)
+		return NF_ACCEPT;
+
+	ihl = iph->ihl << 2;
+
+	th = bpf_dynptr_slice(&ptr, ihl, buffer_th, sizeof(buffer_th));
+	if (!th)
+		return NF_ACCEPT;
+
+	return th->dest == bpf_htons(22) ? NF_ACCEPT : NF_DROP;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_netfilter_retcode.c b/tools/testing/selftests/bpf/progs/verifier_netfilter_retcode.c
new file mode 100644
index 000000000000..e1ffa5d32ff0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_netfilter_retcode.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("netfilter")
+__description("bpf_exit with invalid return code. test1")
+__failure __msg("R0 is not a known value")
+__naked void with_invalid_return_code_test1(void)
+{
+	asm volatile ("					\
+	r0 = *(u64*)(r1 + 0);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("netfilter")
+__description("bpf_exit with valid return code. test2")
+__success
+__naked void with_valid_return_code_test2(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("netfilter")
+__description("bpf_exit with valid return code. test3")
+__success
+__naked void with_valid_return_code_test3(void)
+{
+	asm volatile ("					\
+	r0 = 1;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("netfilter")
+__description("bpf_exit with invalid return code. test4")
+__failure __msg("R0 has smin=2 smax=2 should have been in [0, 1]")
+__naked void with_invalid_return_code_test4(void)
+{
+	asm volatile ("					\
+	r0 = 2;						\
+	exit;						\
+"	::: __clobber_all);
+}
diff --git a/tools/testing/selftests/bpf/progs/verifier_or_jmp32_k.c b/tools/testing/selftests/bpf/progs/verifier_or_jmp32_k.c
new file mode 100644
index 000000000000..f37713a265ac
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_or_jmp32_k.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("socket")
+__description("or_jmp32_k: bit ops + branch on unknown value")
+__failure
+__msg("R0 invalid mem access 'scalar'")
+__naked void or_jmp32_k(void)
+{
+	asm volatile ("					\
+	r0 = 0xffffffff;				\
+	r0 /= 1;					\
+	r1 = 0;						\
+	w1 = -1;					\
+	w1 >>= 1;					\
+	w0 &= w1;					\
+	w0 |= 2;					\
+	if w0 != 0x7ffffffd goto l1;			\
+	r0 = 1;						\
+	exit;						\
+l3:							\
+	r0 = 5;						\
+	*(u64*)(r0 - 8) = r0;				\
+	exit;						\
+l2:							\
+	w0 -= 0xe;					\
+	if w0 == 1 goto l3;				\
+	r0 = 4;						\
+	exit;						\
+l1:							\
+	w0 -= 0x7ffffff0;				\
+	if w0 s>= 0xe goto l2;				\
+	r0 = 3;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_precision.c b/tools/testing/selftests/bpf/progs/verifier_precision.c
new file mode 100644
index 000000000000..1fe090cd6744
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_precision.c
@@ -0,0 +1,304 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 SUSE LLC */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
+#include "bpf_misc.h"
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (55) if r2 != 0xfffffff8 goto pc+2")
+__msg("mark_precise: frame0: regs=r2 stack= before 1: (87) r2 = -r2")
+__msg("mark_precise: frame0: regs=r2 stack= before 0: (b7) r2 = 8")
+__naked int bpf_neg(void)
+{
+	asm volatile (
+		"r2 = 8;"
+		"r2 = -r2;"
+		"if r2 != -8 goto 1f;"
+		"r1 = r10;"
+		"r1 += r2;"
+	"1:"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (55) if r2 != 0x0 goto pc+2")
+__msg("mark_precise: frame0: regs=r2 stack= before 1: (d4) r2 = le16 r2")
+__msg("mark_precise: frame0: regs=r2 stack= before 0: (b7) r2 = 0")
+__naked int bpf_end_to_le(void)
+{
+	asm volatile (
+		"r2 = 0;"
+		"r2 = le16 r2;"
+		"if r2 != 0 goto 1f;"
+		"r1 = r10;"
+		"r1 += r2;"
+	"1:"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (55) if r2 != 0x0 goto pc+2")
+__msg("mark_precise: frame0: regs=r2 stack= before 1: (dc) r2 = be16 r2")
+__msg("mark_precise: frame0: regs=r2 stack= before 0: (b7) r2 = 0")
+__naked int bpf_end_to_be(void)
+{
+	asm volatile (
+		"r2 = 0;"
+		"r2 = be16 r2;"
+		"if r2 != 0 goto 1f;"
+		"r1 = r10;"
+		"r1 += r2;"
+	"1:"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
+	defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390)) && \
+	__clang_major__ >= 18
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (55) if r2 != 0x0 goto pc+2")
+__msg("mark_precise: frame0: regs=r2 stack= before 1: (d7) r2 = bswap16 r2")
+__msg("mark_precise: frame0: regs=r2 stack= before 0: (b7) r2 = 0")
+__naked int bpf_end_bswap(void)
+{
+	asm volatile (
+		"r2 = 0;"
+		"r2 = bswap16 r2;"
+		"if r2 != 0 goto 1f;"
+		"r1 = r10;"
+		"r1 += r2;"
+	"1:"
+		"r0 = 0;"
+		"exit;"
+		::: __clobber_all);
+}
+
+#ifdef CAN_USE_LOAD_ACQ_STORE_REL
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r3 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (db) r2 = load_acquire((u64 *)(r10 -8))")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (7b) *(u64 *)(r10 -8) = r1")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_load_acquire(void)
+{
+	asm volatile (
+	"r1 = 8;"
+	"*(u64 *)(r10 - 8) = r1;"
+	".8byte %[load_acquire_insn];" /* r2 = load_acquire((u64 *)(r10 - 8)); */
+	"r3 = r10;"
+	"r3 += r2;" /* mark_precise */
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(load_acquire_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_LOAD_ACQ, BPF_REG_2, BPF_REG_10, -8))
+	: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r1 stack= before 3: (bf) r2 = r10")
+__msg("mark_precise: frame0: regs=r1 stack= before 2: (79) r1 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: regs= stack=-8 before 1: (db) store_release((u64 *)(r10 -8), r1)")
+__msg("mark_precise: frame0: regs=r1 stack= before 0: (b7) r1 = 8")
+__naked int bpf_store_release(void)
+{
+	asm volatile (
+	"r1 = 8;"
+	".8byte %[store_release_insn];" /* store_release((u64 *)(r10 - 8), r1); */
+	"r1 = *(u64 *)(r10 - 8);"
+	"r2 = r10;"
+	"r2 += r1;" /* mark_precise */
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -8))
+	: __clobber_all);
+}
+
+#endif /* CAN_USE_LOAD_ACQ_STORE_REL */
+#endif /* v4 instruction */
+
+SEC("?raw_tp")
+__success __log_level(2)
+/*
+ * Without the bug fix there will be no history between "last_idx 3 first_idx 3"
+ * and "parent state regs=" lines. "R0=6" parts are here to help anchor
+ * expected log messages to the one specific mark_chain_precision operation.
+ *
+ * This is quite fragile: if verifier checkpointing heuristic changes, this
+ * might need adjusting.
+ */
+__msg("2: (07) r0 += 1                       ; R0=6")
+__msg("3: (35) if r0 >= 0xa goto pc+1")
+__msg("mark_precise: frame0: last_idx 3 first_idx 3 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r0 stack= before 2: (07) r0 += 1")
+__msg("mark_precise: frame0: regs=r0 stack= before 1: (07) r0 += 1")
+__msg("mark_precise: frame0: regs=r0 stack= before 4: (05) goto pc-4")
+__msg("mark_precise: frame0: regs=r0 stack= before 3: (35) if r0 >= 0xa goto pc+1")
+__msg("mark_precise: frame0: parent state regs= stack=:  R0=P4")
+__msg("3: R0=6")
+__naked int state_loop_first_last_equal(void)
+{
+	asm volatile (
+		"r0 = 0;"
+	"l0_%=:"
+		"r0 += 1;"
+		"r0 += 1;"
+		/* every few iterations we'll have a checkpoint here with
+		 * first_idx == last_idx, potentially confusing precision
+		 * backtracking logic
+		 */
+		"if r0 >= 10 goto l1_%=;"	/* checkpoint + mark_precise */
+		"goto l0_%=;"
+	"l1_%=:"
+		"exit;"
+		::: __clobber_common
+	);
+}
+
+__used __naked static void __bpf_cond_op_r10(void)
+{
+	asm volatile (
+	"r2 = 2314885393468386424 ll;"
+	"goto +0;"
+	"if r2 <= r10 goto +3;"
+	"if r1 >= -1835016 goto +0;"
+	"if r2 <= 8 goto +0;"
+	"if r3 <= 0 goto +0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("8: (bd) if r2 <= r10 goto pc+3")
+__msg("9: (35) if r1 >= 0xffe3fff8 goto pc+0")
+__msg("10: (b5) if r2 <= 0x8 goto pc+0")
+__msg("mark_precise: frame1: last_idx 10 first_idx 0 subseq_idx -1")
+__msg("mark_precise: frame1: regs=r2 stack= before 9: (35) if r1 >= 0xffe3fff8 goto pc+0")
+__msg("mark_precise: frame1: regs=r2 stack= before 8: (bd) if r2 <= r10 goto pc+3")
+__msg("mark_precise: frame1: regs=r2 stack= before 7: (05) goto pc+0")
+__naked void bpf_cond_op_r10(void)
+{
+	asm volatile (
+	"r3 = 0 ll;"
+	"call __bpf_cond_op_r10;"
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("3: (bf) r3 = r10")
+__msg("4: (bd) if r3 <= r2 goto pc+1")
+__msg("5: (b5) if r2 <= 0x8 goto pc+2")
+__msg("mark_precise: frame0: last_idx 5 first_idx 0 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r2 stack= before 4: (bd) if r3 <= r2 goto pc+1")
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r3 = r10")
+__naked void bpf_cond_op_not_r10(void)
+{
+	asm volatile (
+	"r0 = 0;"
+	"r2 = 2314885393468386424 ll;"
+	"r3 = r10;"
+	"if r3 <= r2 goto +1;"
+	"if r2 <= 8 goto +2;"
+	"r0 = 2 ll;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm.s/socket_connect")
+__success __log_level(2)
+__msg("0: (b7) r0 = 1                        ; R0=1")
+__msg("1: (84) w0 = -w0                      ; R0=0xffffffff")
+__msg("mark_precise: frame0: last_idx 2 first_idx 0 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r0 stack= before 1: (84) w0 = -w0")
+__msg("mark_precise: frame0: regs=r0 stack= before 0: (b7) r0 = 1")
+__naked int bpf_neg_2(void)
+{
+	/*
+	 * lsm.s/socket_connect requires a return value within [-4095, 0].
+	 * Returning -1 is allowed
+	 */
+	asm volatile (
+	"r0 = 1;"
+	"w0 = -w0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm.s/socket_connect")
+__failure __msg("At program exit the register R0 has")
+__naked int bpf_neg_3(void)
+{
+	/*
+	 * lsm.s/socket_connect requires a return value within [-4095, 0].
+	 * Returning -10000 is not allowed.
+	 */
+	asm volatile (
+	"r0 = 10000;"
+	"w0 = -w0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm.s/socket_connect")
+__success __log_level(2)
+__msg("0: (b7) r0 = 1                        ; R0=1")
+__msg("1: (87) r0 = -r0                      ; R0=-1")
+__msg("mark_precise: frame0: last_idx 2 first_idx 0 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r0 stack= before 1: (87) r0 = -r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 0: (b7) r0 = 1")
+__naked int bpf_neg_4(void)
+{
+	/*
+	 * lsm.s/socket_connect requires a return value within [-4095, 0].
+	 * Returning -1 is allowed
+	 */
+	asm volatile (
+	"r0 = 1;"
+	"r0 = -r0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+SEC("lsm.s/socket_connect")
+__failure __msg("At program exit the register R0 has")
+__naked int bpf_neg_5(void)
+{
+	/*
+	 * lsm.s/socket_connect requires a return value within [-4095, 0].
+	 * Returning -10000 is not allowed.
+	 */
+	asm volatile (
+	"r0 = 10000;"
+	"r0 = -r0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_prevent_map_lookup.c b/tools/testing/selftests/bpf/progs/verifier_prevent_map_lookup.c
new file mode 100644
index 000000000000..8d27c780996f
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_prevent_map_lookup.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/prevent_map_lookup.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} map_stacktrace SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 8);
+	__uint(key_size, sizeof(int));
+	__array(values, void (void));
+} map_prog2_socket SEC(".maps");
+
+SEC("perf_event")
+__description("prevent map lookup in stack trace")
+__failure __msg("cannot pass map_type 7 into func bpf_map_lookup_elem")
+__naked void map_lookup_in_stack_trace(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_stacktrace] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_stacktrace)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("prevent map lookup in prog array")
+__failure __msg("cannot pass map_type 3 into func bpf_map_lookup_elem")
+__failure_unpriv
+__naked void map_lookup_in_prog_array(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_prog2_socket] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_prog2_socket)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_private_stack.c b/tools/testing/selftests/bpf/progs/verifier_private_stack.c
new file mode 100644
index 000000000000..1ecd34ebde19
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_private_stack.c
@@ -0,0 +1,359 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+/* From include/linux/filter.h */
+#define MAX_BPF_STACK    512
+
+#if defined(__TARGET_ARCH_x86) || defined(__TARGET_ARCH_arm64)
+
+struct elem {
+	struct bpf_timer t;
+	char pad[256];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct elem);
+} array SEC(".maps");
+
+SEC("kprobe")
+__description("Private stack, single prog")
+__success
+__arch_x86_64
+__jited("	movabsq	$0x{{.*}}, %r9")
+__jited("	addq	%gs:{{.*}}, %r9")
+__jited("	movl	$0x2a, %edi")
+__jited("	movq	%rdi, -0x100(%r9)")
+__arch_arm64
+__jited("	stp	x25, x27, [sp, {{.*}}]!")
+__jited("	mov	x27, {{.*}}")
+__jited("	movk	x27, {{.*}}, lsl #16")
+__jited("	movk	x27, {{.*}}")
+__jited("	mrs	x10, TPIDR_EL{{[0-1]}}")
+__jited("	add	x27, x27, x10")
+__jited("	add	x25, x27, {{.*}}")
+__jited("	mov	x0, #0x2a")
+__jited("	str	x0, [x27]")
+__jited("...")
+__jited("	ldp	x25, x27, [sp], {{.*}}")
+__naked void private_stack_single_prog(void)
+{
+	asm volatile ("			\
+	r1 = 42;			\
+	*(u64 *)(r10 - 256) = r1;	\
+	r0 = 0;				\
+	exit;				\
+"	::: __clobber_all);
+}
+
+SEC("raw_tp")
+__description("No private stack")
+__success
+__arch_x86_64
+__jited("	subq	$0x8, %rsp")
+__arch_arm64
+__jited("	mov	x25, sp")
+__jited("	sub	sp, sp, #0x10")
+__naked void no_private_stack_nested(void)
+{
+	asm volatile ("			\
+	r1 = 42;			\
+	*(u64 *)(r10 - 8) = r1;		\
+	r0 = 0;				\
+	exit;				\
+"	::: __clobber_all);
+}
+
+__used
+__naked static void cumulative_stack_depth_subprog(void)
+{
+	asm volatile ("				\
+	r1 = 41;				\
+	*(u64 *)(r10 - 32) = r1;		\
+	call %[bpf_get_smp_processor_id];	\
+	exit;					\
+"	:
+	: __imm(bpf_get_smp_processor_id)
+	: __clobber_all);
+}
+
+SEC("kprobe")
+__description("Private stack, subtree > MAX_BPF_STACK")
+__success
+__arch_x86_64
+/* private stack fp for the main prog */
+__jited("	movabsq	$0x{{.*}}, %r9")
+__jited("	addq	%gs:{{.*}}, %r9")
+__jited("	movl	$0x2a, %edi")
+__jited("	movq	%rdi, -0x200(%r9)")
+__jited("	pushq	%r9")
+__jited("	callq	0x{{.*}}")
+__jited("	popq	%r9")
+__jited("	xorl	%eax, %eax")
+__arch_arm64
+__jited("	stp	x25, x27, [sp, {{.*}}]!")
+__jited("	mov	x27, {{.*}}")
+__jited("	movk	x27, {{.*}}, lsl #16")
+__jited("	movk	x27, {{.*}}")
+__jited("	mrs	x10, TPIDR_EL{{[0-1]}}")
+__jited("	add	x27, x27, x10")
+__jited("	add	x25, x27, {{.*}}")
+__jited("	mov	x0, #0x2a")
+__jited("	str	x0, [x27]")
+__jited("	bl	{{.*}}")
+__jited("...")
+__jited("	ldp	x25, x27, [sp], {{.*}}")
+__naked void private_stack_nested_1(void)
+{
+	asm volatile ("				\
+	r1 = 42;				\
+	*(u64 *)(r10 - %[max_bpf_stack]) = r1;	\
+	call cumulative_stack_depth_subprog;	\
+	r0 = 0;					\
+	exit;					\
+"	:
+	: __imm_const(max_bpf_stack, MAX_BPF_STACK)
+	: __clobber_all);
+}
+
+__naked __noinline __used
+static unsigned long loop_callback(void)
+{
+	asm volatile ("				\
+	call %[bpf_get_prandom_u32];		\
+	r1 = 42;				\
+	*(u64 *)(r10 - 512) = r1;		\
+	call cumulative_stack_depth_subprog;	\
+	r0 = 0;					\
+	exit;					\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_common);
+}
+
+SEC("raw_tp")
+__description("Private stack, callback")
+__success
+__arch_x86_64
+/* for func loop_callback */
+__jited("func #1")
+__jited("	endbr64")
+__jited("	nopl	(%rax,%rax)")
+__jited("	nopl	(%rax)")
+__jited("	pushq	%rbp")
+__jited("	movq	%rsp, %rbp")
+__jited("	endbr64")
+__jited("	movabsq	$0x{{.*}}, %r9")
+__jited("	addq	%gs:{{.*}}, %r9")
+__jited("	pushq	%r9")
+__jited("	callq")
+__jited("	popq	%r9")
+__jited("	movl	$0x2a, %edi")
+__jited("	movq	%rdi, -0x200(%r9)")
+__jited("	pushq	%r9")
+__jited("	callq")
+__jited("	popq	%r9")
+__arch_arm64
+__jited("func #1")
+__jited("...")
+__jited("	stp	x25, x27, [sp, {{.*}}]!")
+__jited("	mov	x27, {{.*}}")
+__jited("	movk	x27, {{.*}}, lsl #16")
+__jited("	movk	x27, {{.*}}")
+__jited("	mrs	x10, TPIDR_EL{{[0-1]}}")
+__jited("	add	x27, x27, x10")
+__jited("	add	x25, x27, {{.*}}")
+__jited("	bl	0x{{.*}}")
+__jited("	add	x7, x0, #0x0")
+__jited("	mov	x0, #0x2a")
+__jited("	str	x0, [x27]")
+__jited("	bl	0x{{.*}}")
+__jited("	add	x7, x0, #0x0")
+__jited("	mov	x7, #0x0")
+__jited("	ldp	x25, x27, [sp], {{.*}}")
+__naked void private_stack_callback(void)
+{
+	asm volatile ("			\
+	r1 = 1;				\
+	r2 = %[loop_callback];		\
+	r3 = 0;				\
+	r4 = 0;				\
+	call %[bpf_loop];		\
+	r0 = 0;				\
+	exit;				\
+"	:
+	: __imm_ptr(loop_callback),
+	  __imm(bpf_loop)
+	: __clobber_common);
+}
+
+SEC("fentry/bpf_fentry_test9")
+__description("Private stack, exception in main prog")
+__success __retval(0)
+__arch_x86_64
+__jited("	pushq	%r9")
+__jited("	callq")
+__jited("	popq	%r9")
+__arch_arm64
+__jited("	stp	x29, x30, [sp, #-0x10]!")
+__jited("	mov	x29, sp")
+__jited("	stp	xzr, x26, [sp, #-0x10]!")
+__jited("	mov	x26, sp")
+__jited("	stp	x19, x20, [sp, #-0x10]!")
+__jited("	stp	x21, x22, [sp, #-0x10]!")
+__jited("	stp	x23, x24, [sp, #-0x10]!")
+__jited("	stp	x25, x26, [sp, #-0x10]!")
+__jited("	stp	x27, x28, [sp, #-0x10]!")
+__jited("	mov	x27, {{.*}}")
+__jited("	movk	x27, {{.*}}, lsl #16")
+__jited("	movk	x27, {{.*}}")
+__jited("	mrs	x10, TPIDR_EL{{[0-1]}}")
+__jited("	add	x27, x27, x10")
+__jited("	add	x25, x27, {{.*}}")
+__jited("	mov	x0, #0x2a")
+__jited("	str	x0, [x27]")
+__jited("	mov	x0, #0x0")
+__jited("	bl	0x{{.*}}")
+__jited("	add	x7, x0, #0x0")
+__jited("	ldp	x27, x28, [sp], #0x10")
+int private_stack_exception_main_prog(void)
+{
+	asm volatile ("			\
+	r1 = 42;			\
+	*(u64 *)(r10 - 512) = r1;	\
+"	::: __clobber_common);
+
+	bpf_throw(0);
+	return 0;
+}
+
+__used static int subprog_exception(void)
+{
+	bpf_throw(0);
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test9")
+__description("Private stack, exception in subprog")
+__success __retval(0)
+__arch_x86_64
+__jited("	movq	%rdi, -0x200(%r9)")
+__jited("	pushq	%r9")
+__jited("	callq")
+__jited("	popq	%r9")
+__arch_arm64
+__jited("	stp	x27, x28, [sp, #-0x10]!")
+__jited("	mov	x27, {{.*}}")
+__jited("	movk	x27, {{.*}}, lsl #16")
+__jited("	movk	x27, {{.*}}")
+__jited("	mrs	x10, TPIDR_EL{{[0-1]}}")
+__jited("	add	x27, x27, x10")
+__jited("	add	x25, x27, {{.*}}")
+__jited("	mov	x0, #0x2a")
+__jited("	str	x0, [x27]")
+__jited("	bl	0x{{.*}}")
+__jited("	add	x7, x0, #0x0")
+__jited("	ldp	x27, x28, [sp], #0x10")
+int private_stack_exception_sub_prog(void)
+{
+	asm volatile ("			\
+	r1 = 42;			\
+	*(u64 *)(r10 - 512) = r1;	\
+	call subprog_exception;		\
+"	::: __clobber_common);
+
+	return 0;
+}
+
+int glob;
+__noinline static void subprog2(int *val)
+{
+	glob += val[0] * 2;
+}
+
+__noinline static void subprog1(int *val)
+{
+	int tmp[64] = {};
+
+	tmp[0] = *val;
+	subprog2(tmp);
+}
+
+__noinline static int timer_cb1(void *map, int *key, struct bpf_timer *timer)
+{
+	subprog1(key);
+	return 0;
+}
+
+__noinline static int timer_cb2(void *map, int *key, struct bpf_timer *timer)
+{
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test9")
+__description("Private stack, async callback, not nested")
+__success __retval(0)
+__arch_x86_64
+__jited("	movabsq	$0x{{.*}}, %r9")
+__arch_arm64
+__jited("	mrs	x10, TPIDR_EL{{[0-1]}}")
+__jited("	add	x27, x27, x10")
+__jited("	add	x25, x27, {{.*}}")
+int private_stack_async_callback_1(void)
+{
+	struct bpf_timer *arr_timer;
+	int array_key = 0;
+
+	arr_timer = bpf_map_lookup_elem(&array, &array_key);
+	if (!arr_timer)
+		return 0;
+
+	bpf_timer_init(arr_timer, &array, 1);
+	bpf_timer_set_callback(arr_timer, timer_cb2);
+	bpf_timer_start(arr_timer, 0, 0);
+	subprog1(&array_key);
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test9")
+__description("Private stack, async callback, potential nesting")
+__success __retval(0)
+__arch_x86_64
+__jited("	subq	$0x100, %rsp")
+__arch_arm64
+__jited("	sub	sp, sp, #0x100")
+int private_stack_async_callback_2(void)
+{
+	struct bpf_timer *arr_timer;
+	int array_key = 0;
+
+	arr_timer = bpf_map_lookup_elem(&array, &array_key);
+	if (!arr_timer)
+		return 0;
+
+	bpf_timer_init(arr_timer, &array, 1);
+	bpf_timer_set_callback(arr_timer, timer_cb1);
+	bpf_timer_start(arr_timer, 0, 0);
+	subprog1(&array_key);
+	return 0;
+}
+
+#else
+
+SEC("kprobe")
+__description("private stack is not supported, use a dummy test")
+__success
+int dummy_test(void)
+{
+	return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_raw_stack.c b/tools/testing/selftests/bpf/progs/verifier_raw_stack.c
new file mode 100644
index 000000000000..c689665e07b9
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_raw_stack.c
@@ -0,0 +1,372 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/raw_stack.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("socket")
+__description("raw_stack: no skb_load_bytes")
+__success
+__failure_unpriv __msg_unpriv("invalid read from stack R6 off=-8 size=8")
+__naked void stack_no_skb_load_bytes(void)
+{
+	asm volatile ("					\
+	r2 = 4;						\
+	r6 = r10;					\
+	r6 += -8;					\
+	r3 = r6;					\
+	r4 = 8;						\
+	/* Call to skb_load_bytes() omitted. */		\
+	r0 = *(u64*)(r6 + 0);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tc")
+__description("raw_stack: skb_load_bytes, negative len")
+__failure __msg("R4 min value is negative")
+__naked void skb_load_bytes_negative_len(void)
+{
+	asm volatile ("					\
+	r2 = 4;						\
+	r6 = r10;					\
+	r6 += -8;					\
+	r3 = r6;					\
+	r4 = -8;					\
+	call %[bpf_skb_load_bytes];			\
+	r0 = *(u64*)(r6 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_skb_load_bytes)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("raw_stack: skb_load_bytes, negative len 2")
+__failure __msg("R4 min value is negative")
+__naked void load_bytes_negative_len_2(void)
+{
+	asm volatile ("					\
+	r2 = 4;						\
+	r6 = r10;					\
+	r6 += -8;					\
+	r3 = r6;					\
+	r4 = %[__imm_0];				\
+	call %[bpf_skb_load_bytes];			\
+	r0 = *(u64*)(r6 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_skb_load_bytes),
+	  __imm_const(__imm_0, ~0)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("raw_stack: skb_load_bytes, zero len")
+__failure __msg("R4 invalid zero-sized read: u64=[0,0]")
+__naked void skb_load_bytes_zero_len(void)
+{
+	asm volatile ("					\
+	r2 = 4;						\
+	r6 = r10;					\
+	r6 += -8;					\
+	r3 = r6;					\
+	r4 = 0;						\
+	call %[bpf_skb_load_bytes];			\
+	r0 = *(u64*)(r6 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_skb_load_bytes)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("raw_stack: skb_load_bytes, no init")
+__success __retval(0)
+__naked void skb_load_bytes_no_init(void)
+{
+	asm volatile ("					\
+	r2 = 4;						\
+	r6 = r10;					\
+	r6 += -8;					\
+	r3 = r6;					\
+	r4 = 8;						\
+	call %[bpf_skb_load_bytes];			\
+	r0 = *(u64*)(r6 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_skb_load_bytes)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("raw_stack: skb_load_bytes, init")
+__success __retval(0)
+__naked void stack_skb_load_bytes_init(void)
+{
+	asm volatile ("					\
+	r2 = 4;						\
+	r6 = r10;					\
+	r6 += -8;					\
+	r3 = 0xcafe;					\
+	*(u64*)(r6 + 0) = r3;				\
+	r3 = r6;					\
+	r4 = 8;						\
+	call %[bpf_skb_load_bytes];			\
+	r0 = *(u64*)(r6 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_skb_load_bytes)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("raw_stack: skb_load_bytes, spilled regs around bounds")
+__success __retval(0)
+__naked void bytes_spilled_regs_around_bounds(void)
+{
+	asm volatile ("					\
+	r2 = 4;						\
+	r6 = r10;					\
+	r6 += -16;					\
+	*(u64*)(r6 - 8) = r1;				\
+	*(u64*)(r6 + 8) = r1;				\
+	r3 = r6;					\
+	r4 = 8;						\
+	call %[bpf_skb_load_bytes];			\
+	r0 = *(u64*)(r6 - 8);				\
+	r2 = *(u64*)(r6 + 8);				\
+	r0 = *(u32*)(r0 + %[__sk_buff_mark]);		\
+	r2 = *(u32*)(r2 + %[__sk_buff_priority]);	\
+	r0 += r2;					\
+	exit;						\
+"	:
+	: __imm(bpf_skb_load_bytes),
+	  __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)),
+	  __imm_const(__sk_buff_priority, offsetof(struct __sk_buff, priority))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("raw_stack: skb_load_bytes, spilled regs corruption")
+__failure __msg("R0 invalid mem access 'scalar'")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void load_bytes_spilled_regs_corruption(void)
+{
+	asm volatile ("					\
+	r2 = 4;						\
+	r6 = r10;					\
+	r6 += -8;					\
+	*(u64*)(r6 + 0) = r1;				\
+	r3 = r6;					\
+	r4 = 8;						\
+	call %[bpf_skb_load_bytes];			\
+	r0 = *(u64*)(r6 + 0);				\
+	r0 = *(u32*)(r0 + %[__sk_buff_mark]);		\
+	exit;						\
+"	:
+	: __imm(bpf_skb_load_bytes),
+	  __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("raw_stack: skb_load_bytes, spilled regs corruption 2")
+__failure __msg("R3 invalid mem access 'scalar'")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void bytes_spilled_regs_corruption_2(void)
+{
+	asm volatile ("					\
+	r2 = 4;						\
+	r6 = r10;					\
+	r6 += -16;					\
+	*(u64*)(r6 - 8) = r1;				\
+	*(u64*)(r6 + 0) = r1;				\
+	*(u64*)(r6 + 8) = r1;				\
+	r3 = r6;					\
+	r4 = 8;						\
+	call %[bpf_skb_load_bytes];			\
+	r0 = *(u64*)(r6 - 8);				\
+	r2 = *(u64*)(r6 + 8);				\
+	r3 = *(u64*)(r6 + 0);				\
+	r0 = *(u32*)(r0 + %[__sk_buff_mark]);		\
+	r2 = *(u32*)(r2 + %[__sk_buff_priority]);	\
+	r0 += r2;					\
+	r3 = *(u32*)(r3 + %[__sk_buff_pkt_type]);	\
+	r0 += r3;					\
+	exit;						\
+"	:
+	: __imm(bpf_skb_load_bytes),
+	  __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)),
+	  __imm_const(__sk_buff_pkt_type, offsetof(struct __sk_buff, pkt_type)),
+	  __imm_const(__sk_buff_priority, offsetof(struct __sk_buff, priority))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("raw_stack: skb_load_bytes, spilled regs + data")
+__success __retval(0)
+__naked void load_bytes_spilled_regs_data(void)
+{
+	asm volatile ("					\
+	r2 = 4;						\
+	r6 = r10;					\
+	r6 += -16;					\
+	*(u64*)(r6 - 8) = r1;				\
+	*(u64*)(r6 + 0) = r1;				\
+	*(u64*)(r6 + 8) = r1;				\
+	r3 = r6;					\
+	r4 = 8;						\
+	call %[bpf_skb_load_bytes];			\
+	r0 = *(u64*)(r6 - 8);				\
+	r2 = *(u64*)(r6 + 8);				\
+	r3 = *(u64*)(r6 + 0);				\
+	r0 = *(u32*)(r0 + %[__sk_buff_mark]);		\
+	r2 = *(u32*)(r2 + %[__sk_buff_priority]);	\
+	r0 += r2;					\
+	r0 += r3;					\
+	exit;						\
+"	:
+	: __imm(bpf_skb_load_bytes),
+	  __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)),
+	  __imm_const(__sk_buff_priority, offsetof(struct __sk_buff, priority))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("raw_stack: skb_load_bytes, invalid access 1")
+__failure __msg("invalid write to stack R3 off=-513 size=8")
+__naked void load_bytes_invalid_access_1(void)
+{
+	asm volatile ("					\
+	r2 = 4;						\
+	r6 = r10;					\
+	r6 += -513;					\
+	r3 = r6;					\
+	r4 = 8;						\
+	call %[bpf_skb_load_bytes];			\
+	r0 = *(u64*)(r6 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_skb_load_bytes)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("raw_stack: skb_load_bytes, invalid access 2")
+__failure __msg("invalid write to stack R3 off=-1 size=8")
+__naked void load_bytes_invalid_access_2(void)
+{
+	asm volatile ("					\
+	r2 = 4;						\
+	r6 = r10;					\
+	r6 += -1;					\
+	r3 = r6;					\
+	r4 = 8;						\
+	call %[bpf_skb_load_bytes];			\
+	r0 = *(u64*)(r6 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_skb_load_bytes)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("raw_stack: skb_load_bytes, invalid access 3")
+__failure __msg("R4 min value is negative")
+__naked void load_bytes_invalid_access_3(void)
+{
+	asm volatile ("					\
+	r2 = 4;						\
+	r6 = r10;					\
+	r6 += 0xffffffff;				\
+	r3 = r6;					\
+	r4 = 0xffffffff;				\
+	call %[bpf_skb_load_bytes];			\
+	r0 = *(u64*)(r6 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_skb_load_bytes)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("raw_stack: skb_load_bytes, invalid access 4")
+__failure
+__msg("R4 unbounded memory access, use 'var &= const' or 'if (var < const)'")
+__naked void load_bytes_invalid_access_4(void)
+{
+	asm volatile ("					\
+	r2 = 4;						\
+	r6 = r10;					\
+	r6 += -1;					\
+	r3 = r6;					\
+	r4 = 0x7fffffff;				\
+	call %[bpf_skb_load_bytes];			\
+	r0 = *(u64*)(r6 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_skb_load_bytes)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("raw_stack: skb_load_bytes, invalid access 5")
+__failure
+__msg("R4 unbounded memory access, use 'var &= const' or 'if (var < const)'")
+__naked void load_bytes_invalid_access_5(void)
+{
+	asm volatile ("					\
+	r2 = 4;						\
+	r6 = r10;					\
+	r6 += -512;					\
+	r3 = r6;					\
+	r4 = 0x7fffffff;				\
+	call %[bpf_skb_load_bytes];			\
+	r0 = *(u64*)(r6 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_skb_load_bytes)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("raw_stack: skb_load_bytes, invalid access 6")
+__failure __msg("invalid zero-sized read")
+__naked void load_bytes_invalid_access_6(void)
+{
+	asm volatile ("					\
+	r2 = 4;						\
+	r6 = r10;					\
+	r6 += -512;					\
+	r3 = r6;					\
+	r4 = 0;						\
+	call %[bpf_skb_load_bytes];			\
+	r0 = *(u64*)(r6 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_skb_load_bytes)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("raw_stack: skb_load_bytes, large access")
+__success __retval(0)
+__naked void skb_load_bytes_large_access(void)
+{
+	asm volatile ("					\
+	r2 = 4;						\
+	r6 = r10;					\
+	r6 += -512;					\
+	r3 = r6;					\
+	r4 = 512;					\
+	call %[bpf_skb_load_bytes];			\
+	r0 = *(u64*)(r6 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_skb_load_bytes)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_raw_tp_writable.c b/tools/testing/selftests/bpf/progs/verifier_raw_tp_writable.c
new file mode 100644
index 000000000000..14a0172e2141
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_raw_tp_writable.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/raw_tp_writable.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, long long);
+} map_hash_8b SEC(".maps");
+
+SEC("raw_tracepoint.w")
+__description("raw_tracepoint_writable: reject variable offset")
+__failure
+__msg("R6 invalid variable buffer offset: off=0, var_off=(0x0; 0xffffffff)")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void tracepoint_writable_reject_variable_offset(void)
+{
+	asm volatile ("					\
+	/* r6 is our tp buffer */			\
+	r6 = *(u64*)(r1 + 0);				\
+	r1 = %[map_hash_8b] ll;				\
+	/* move the key (== 0) to r10-8 */		\
+	w0 = 0;						\
+	r2 = r10;					\
+	r2 += -8;					\
+	*(u64*)(r2 + 0) = r0;				\
+	/* lookup in the map */				\
+	call %[bpf_map_lookup_elem];			\
+	/* exit clean if null */			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	/* shift the buffer pointer to a variable location */\
+	r0 = *(u32*)(r0 + 0);				\
+	r6 += r0;					\
+	/* clobber whatever's there */			\
+	r7 = 4242;					\
+	*(u64*)(r6 + 0) = r7;				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_ref_tracking.c b/tools/testing/selftests/bpf/progs/verifier_ref_tracking.c
new file mode 100644
index 000000000000..910365201f68
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_ref_tracking.c
@@ -0,0 +1,1495 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/ref_tracking.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
+#include "bpf_misc.h"
+
+#define BPF_SK_LOOKUP(func) \
+	/* struct bpf_sock_tuple tuple = {} */ \
+	"r2 = 0;"			\
+	"*(u32*)(r10 - 8) = r2;"	\
+	"*(u64*)(r10 - 16) = r2;"	\
+	"*(u64*)(r10 - 24) = r2;"	\
+	"*(u64*)(r10 - 32) = r2;"	\
+	"*(u64*)(r10 - 40) = r2;"	\
+	"*(u64*)(r10 - 48) = r2;"	\
+	/* sk = func(ctx, &tuple, sizeof tuple, 0, 0) */ \
+	"r2 = r10;"			\
+	"r2 += -48;"			\
+	"r3 = %[sizeof_bpf_sock_tuple];"\
+	"r4 = 0;"			\
+	"r5 = 0;"			\
+	"call %[" #func "];"
+
+struct bpf_key {} __attribute__((preserve_access_index));
+
+extern void bpf_key_put(struct bpf_key *key) __ksym;
+extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym;
+extern struct bpf_key *bpf_lookup_user_key(__s32 serial, __u64 flags) __ksym;
+
+/* BTF FUNC records are not generated for kfuncs referenced
+ * from inline assembly. These records are necessary for
+ * libbpf to link the program. The function below is a hack
+ * to ensure that BTF FUNC records are generated.
+ */
+void __kfunc_btf_root(void)
+{
+	bpf_key_put(0);
+	bpf_lookup_system_key(0);
+	bpf_lookup_user_key(0, 0);
+}
+
+#define MAX_ENTRIES 11
+
+struct test_val {
+	unsigned int index;
+	int foo[MAX_ENTRIES];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct test_val);
+} map_array_48b SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_RINGBUF);
+	__uint(max_entries, 4096);
+} map_ringbuf SEC(".maps");
+
+void dummy_prog_42_tc(void);
+void dummy_prog_24_tc(void);
+void dummy_prog_loop1_tc(void);
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 4);
+	__uint(key_size, sizeof(int));
+	__array(values, void (void));
+} map_prog1_tc SEC(".maps") = {
+	.values = {
+		[0] = (void *)&dummy_prog_42_tc,
+		[1] = (void *)&dummy_prog_loop1_tc,
+		[2] = (void *)&dummy_prog_24_tc,
+	},
+};
+
+SEC("tc")
+__auxiliary
+__naked void dummy_prog_42_tc(void)
+{
+	asm volatile ("r0 = 42; exit;");
+}
+
+SEC("tc")
+__auxiliary
+__naked void dummy_prog_24_tc(void)
+{
+	asm volatile ("r0 = 24; exit;");
+}
+
+SEC("tc")
+__auxiliary
+__naked void dummy_prog_loop1_tc(void)
+{
+	asm volatile ("			\
+	r3 = 1;				\
+	r2 = %[map_prog1_tc] ll;	\
+	call %[bpf_tail_call];		\
+	r0 = 41;			\
+	exit;				\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_tc)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: leak potential reference")
+__failure __msg("Unreleased reference")
+__naked void reference_tracking_leak_potential_reference(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r6 = r0;		/* leak reference */	\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: leak potential reference to sock_common")
+__failure __msg("Unreleased reference")
+__naked void potential_reference_to_sock_common_1(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_skc_lookup_tcp)
+"	r6 = r0;		/* leak reference */	\
+	exit;						\
+"	:
+	: __imm(bpf_skc_lookup_tcp),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: leak potential reference on stack")
+__failure __msg("Unreleased reference")
+__naked void leak_potential_reference_on_stack(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r4 = r10;					\
+	r4 += -8;					\
+	*(u64*)(r4 + 0) = r0;				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: leak potential reference on stack 2")
+__failure __msg("Unreleased reference")
+__naked void potential_reference_on_stack_2(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r4 = r10;					\
+	r4 += -8;					\
+	*(u64*)(r4 + 0) = r0;				\
+	r0 = 0;						\
+	r1 = 0;						\
+	*(u64*)(r4 + 0) = r1;				\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: zero potential reference")
+__failure __msg("Unreleased reference")
+__naked void reference_tracking_zero_potential_reference(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r0 = 0;			/* leak reference */	\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: zero potential reference to sock_common")
+__failure __msg("Unreleased reference")
+__naked void potential_reference_to_sock_common_2(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_skc_lookup_tcp)
+"	r0 = 0;			/* leak reference */	\
+	exit;						\
+"	:
+	: __imm(bpf_skc_lookup_tcp),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: copy and zero potential references")
+__failure __msg("Unreleased reference")
+__naked void copy_and_zero_potential_references(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r7 = r0;					\
+	r0 = 0;						\
+	r7 = 0;			/* leak reference */	\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("lsm.s/bpf")
+__description("reference tracking: acquire/release user key reference")
+__success
+__naked void acquire_release_user_key_reference(void)
+{
+	asm volatile ("					\
+	r1 = -3;					\
+	r2 = 0;						\
+	call %[bpf_lookup_user_key];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	call %[bpf_key_put];				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_key_put),
+	  __imm(bpf_lookup_user_key)
+	: __clobber_all);
+}
+
+SEC("lsm.s/bpf")
+__description("reference tracking: acquire/release system key reference")
+__success
+__naked void acquire_release_system_key_reference(void)
+{
+	asm volatile ("					\
+	r1 = 1;						\
+	call %[bpf_lookup_system_key];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r0;					\
+	call %[bpf_key_put];				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_key_put),
+	  __imm(bpf_lookup_system_key)
+	: __clobber_all);
+}
+
+SEC("lsm.s/bpf")
+__description("reference tracking: release user key reference without check")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
+__naked void user_key_reference_without_check(void)
+{
+	asm volatile ("					\
+	r1 = -3;					\
+	r2 = 0;						\
+	call %[bpf_lookup_user_key];			\
+	r1 = r0;					\
+	call %[bpf_key_put];				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_key_put),
+	  __imm(bpf_lookup_user_key)
+	: __clobber_all);
+}
+
+SEC("lsm.s/bpf")
+__description("reference tracking: release system key reference without check")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
+__naked void system_key_reference_without_check(void)
+{
+	asm volatile ("					\
+	r1 = 1;						\
+	call %[bpf_lookup_system_key];			\
+	r1 = r0;					\
+	call %[bpf_key_put];				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_key_put),
+	  __imm(bpf_lookup_system_key)
+	: __clobber_all);
+}
+
+SEC("lsm.s/bpf")
+__description("reference tracking: release with NULL key pointer")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
+__naked void release_with_null_key_pointer(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	call %[bpf_key_put];				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_key_put)
+	: __clobber_all);
+}
+
+SEC("lsm.s/bpf")
+__description("reference tracking: leak potential reference to user key")
+__failure __msg("Unreleased reference")
+__naked void potential_reference_to_user_key(void)
+{
+	asm volatile ("					\
+	r1 = -3;					\
+	r2 = 0;						\
+	call %[bpf_lookup_user_key];			\
+	exit;						\
+"	:
+	: __imm(bpf_lookup_user_key)
+	: __clobber_all);
+}
+
+SEC("lsm.s/bpf")
+__description("reference tracking: leak potential reference to system key")
+__failure __msg("Unreleased reference")
+__naked void potential_reference_to_system_key(void)
+{
+	asm volatile ("					\
+	r1 = 1;						\
+	call %[bpf_lookup_system_key];			\
+	exit;						\
+"	:
+	: __imm(bpf_lookup_system_key)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: release reference without check")
+__failure __msg("type=sock_or_null expected=sock")
+__naked void tracking_release_reference_without_check(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	/* reference in r0 may be NULL */		\
+	r1 = r0;					\
+	r2 = 0;						\
+	call %[bpf_sk_release];				\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: release reference to sock_common without check")
+__failure __msg("type=sock_common_or_null expected=sock")
+__naked void to_sock_common_without_check(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_skc_lookup_tcp)
+"	/* reference in r0 may be NULL */		\
+	r1 = r0;					\
+	r2 = 0;						\
+	call %[bpf_sk_release];				\
+	exit;						\
+"	:
+	: __imm(bpf_sk_release),
+	  __imm(bpf_skc_lookup_tcp),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: release reference")
+__success __retval(0)
+__naked void reference_tracking_release_reference(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r1 = r0;					\
+	if r0 == 0 goto l0_%=;				\
+	call %[bpf_sk_release];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: release reference to sock_common")
+__success __retval(0)
+__naked void release_reference_to_sock_common(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_skc_lookup_tcp)
+"	r1 = r0;					\
+	if r0 == 0 goto l0_%=;				\
+	call %[bpf_sk_release];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_sk_release),
+	  __imm(bpf_skc_lookup_tcp),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: release reference 2")
+__success __retval(0)
+__naked void reference_tracking_release_reference_2(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r1 = r0;					\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	call %[bpf_sk_release];				\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: release reference twice")
+__failure __msg("type=scalar expected=sock")
+__naked void reference_tracking_release_reference_twice(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r1 = r0;					\
+	r6 = r0;					\
+	if r0 == 0 goto l0_%=;				\
+	call %[bpf_sk_release];				\
+l0_%=:	r1 = r6;					\
+	call %[bpf_sk_release];				\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: release reference twice inside branch")
+__failure __msg("type=scalar expected=sock")
+__naked void release_reference_twice_inside_branch(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r1 = r0;					\
+	r6 = r0;					\
+	if r0 == 0 goto l0_%=;		/* goto end */	\
+	call %[bpf_sk_release];				\
+	r1 = r6;					\
+	call %[bpf_sk_release];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: alloc, check, free in one subbranch")
+__failure __msg("Unreleased reference")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void check_free_in_one_subbranch(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 16;					\
+	/* if (offsetof(skb, mark) > data_len) exit; */	\
+	if r0 <= r3 goto l0_%=;				\
+	exit;						\
+l0_%=:	r6 = *(u32*)(r2 + %[__sk_buff_mark]);		\
+"	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	if r6 == 0 goto l1_%=;		/* mark == 0? */\
+	/* Leak reference in R0 */			\
+	exit;						\
+l1_%=:	if r0 == 0 goto l2_%=;		/* sk NULL? */	\
+	r1 = r0;					\
+	call %[bpf_sk_release];				\
+l2_%=:	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)),
+	  __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: alloc, check, free in both subbranches")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void check_free_in_both_subbranches(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 16;					\
+	/* if (offsetof(skb, mark) > data_len) exit; */	\
+	if r0 <= r3 goto l0_%=;				\
+	exit;						\
+l0_%=:	r6 = *(u32*)(r2 + %[__sk_buff_mark]);		\
+"	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	if r6 == 0 goto l1_%=;		/* mark == 0? */\
+	if r0 == 0 goto l2_%=;		/* sk NULL? */	\
+	r1 = r0;					\
+	call %[bpf_sk_release];				\
+l2_%=:	exit;						\
+l1_%=:	if r0 == 0 goto l3_%=;		/* sk NULL? */	\
+	r1 = r0;					\
+	call %[bpf_sk_release];				\
+l3_%=:	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)),
+	  __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking in call: free reference in subprog")
+__success __retval(0)
+__naked void call_free_reference_in_subprog(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r1 = r0;	/* unchecked reference */	\
+	call call_free_reference_in_subprog__1;		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+static __naked __noinline __attribute__((used))
+void call_free_reference_in_subprog__1(void)
+{
+	asm volatile ("					\
+	/* subprog 1 */					\
+	r2 = r1;					\
+	if r2 == 0 goto l0_%=;				\
+	call %[bpf_sk_release];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_sk_release)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking in call: free reference in subprog and outside")
+__failure __msg("type=scalar expected=sock")
+__naked void reference_in_subprog_and_outside(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r1 = r0;	/* unchecked reference */	\
+	r6 = r0;					\
+	call reference_in_subprog_and_outside__1;	\
+	r1 = r6;					\
+	call %[bpf_sk_release];				\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+static __naked __noinline __attribute__((used))
+void reference_in_subprog_and_outside__1(void)
+{
+	asm volatile ("					\
+	/* subprog 1 */					\
+	r2 = r1;					\
+	if r2 == 0 goto l0_%=;				\
+	call %[bpf_sk_release];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_sk_release)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking in call: alloc & leak reference in subprog")
+__failure __msg("Unreleased reference")
+__naked void alloc_leak_reference_in_subprog(void)
+{
+	asm volatile ("					\
+	r4 = r10;					\
+	r4 += -8;					\
+	call alloc_leak_reference_in_subprog__1;	\
+	r1 = r0;					\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+static __naked __noinline __attribute__((used))
+void alloc_leak_reference_in_subprog__1(void)
+{
+	asm volatile ("					\
+	/* subprog 1 */					\
+	r6 = r4;					\
+"	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	/* spill unchecked sk_ptr into stack of caller */\
+	*(u64*)(r6 + 0) = r0;				\
+	r1 = r0;					\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking in call: alloc in subprog, release outside")
+__success __retval(POINTER_VALUE)
+__naked void alloc_in_subprog_release_outside(void)
+{
+	asm volatile ("					\
+	r4 = r10;					\
+	call alloc_in_subprog_release_outside__1;	\
+	r1 = r0;					\
+	if r0 == 0 goto l0_%=;				\
+	call %[bpf_sk_release];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_sk_release)
+	: __clobber_all);
+}
+
+static __naked __noinline __attribute__((used))
+void alloc_in_subprog_release_outside__1(void)
+{
+	asm volatile ("					\
+	/* subprog 1 */					\
+"	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	exit;				/* return sk */	\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking in call: sk_ptr leak into caller stack")
+__failure __msg("Unreleased reference")
+__naked void ptr_leak_into_caller_stack(void)
+{
+	asm volatile ("					\
+	r4 = r10;					\
+	r4 += -8;					\
+	call ptr_leak_into_caller_stack__1;		\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+static __naked __noinline __attribute__((used))
+void ptr_leak_into_caller_stack__1(void)
+{
+	asm volatile ("					\
+	/* subprog 1 */					\
+	r5 = r10;					\
+	r5 += -8;					\
+	*(u64*)(r5 + 0) = r4;				\
+	call ptr_leak_into_caller_stack__2;		\
+	/* spill unchecked sk_ptr into stack of caller */\
+	r5 = r10;					\
+	r5 += -8;					\
+	r4 = *(u64*)(r5 + 0);				\
+	*(u64*)(r4 + 0) = r0;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+static __naked __noinline __attribute__((used))
+void ptr_leak_into_caller_stack__2(void)
+{
+	asm volatile ("					\
+	/* subprog 2 */					\
+"	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking in call: sk_ptr spill into caller stack")
+__success __retval(0)
+__naked void ptr_spill_into_caller_stack(void)
+{
+	asm volatile ("					\
+	r4 = r10;					\
+	r4 += -8;					\
+	call ptr_spill_into_caller_stack__1;		\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+static __naked __noinline __attribute__((used))
+void ptr_spill_into_caller_stack__1(void)
+{
+	asm volatile ("					\
+	/* subprog 1 */					\
+	r5 = r10;					\
+	r5 += -8;					\
+	*(u64*)(r5 + 0) = r4;				\
+	call ptr_spill_into_caller_stack__2;		\
+	/* spill unchecked sk_ptr into stack of caller */\
+	r5 = r10;					\
+	r5 += -8;					\
+	r4 = *(u64*)(r5 + 0);				\
+	*(u64*)(r4 + 0) = r0;				\
+	if r0 == 0 goto l0_%=;				\
+	/* now the sk_ptr is verified, free the reference */\
+	r1 = *(u64*)(r4 + 0);				\
+	call %[bpf_sk_release];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_sk_release)
+	: __clobber_all);
+}
+
+static __naked __noinline __attribute__((used))
+void ptr_spill_into_caller_stack__2(void)
+{
+	asm volatile ("					\
+	/* subprog 2 */					\
+"	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: allow LD_ABS")
+__success __retval(0)
+__naked void reference_tracking_allow_ld_abs(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+"	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r1 = r0;					\
+	if r0 == 0 goto l0_%=;				\
+	call %[bpf_sk_release];				\
+l0_%=:	r0 = *(u8*)skb[0];				\
+	r0 = *(u16*)skb[0];				\
+	r0 = *(u32*)skb[0];				\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: forbid LD_ABS while holding reference")
+__failure __msg("BPF_LD_[ABS|IND] would lead to reference leak")
+__naked void ld_abs_while_holding_reference(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+"	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r0 = *(u8*)skb[0];				\
+	r0 = *(u16*)skb[0];				\
+	r0 = *(u32*)skb[0];				\
+	r1 = r0;					\
+	if r0 == 0 goto l0_%=;				\
+	call %[bpf_sk_release];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: allow LD_IND")
+__success __retval(1)
+__naked void reference_tracking_allow_ld_ind(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+"	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r1 = r0;					\
+	if r0 == 0 goto l0_%=;				\
+	call %[bpf_sk_release];				\
+l0_%=:	r7 = 1;						\
+	.8byte %[ld_ind];				\
+	r0 = r7;					\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)),
+	  __imm_insn(ld_ind, BPF_LD_IND(BPF_W, BPF_REG_7, -0x200000))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: forbid LD_IND while holding reference")
+__failure __msg("BPF_LD_[ABS|IND] would lead to reference leak")
+__naked void ld_ind_while_holding_reference(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+"	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r4 = r0;					\
+	r7 = 1;						\
+	.8byte %[ld_ind];				\
+	r0 = r7;					\
+	r1 = r4;					\
+	if r1 == 0 goto l0_%=;				\
+	call %[bpf_sk_release];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple)),
+	  __imm_insn(ld_ind, BPF_LD_IND(BPF_W, BPF_REG_7, -0x200000))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: check reference or tail call")
+__success __retval(0)
+__naked void check_reference_or_tail_call(void)
+{
+	asm volatile ("					\
+	r7 = r1;					\
+"	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	/* if (sk) bpf_sk_release() */			\
+	r1 = r0;					\
+	if r1 != 0 goto l0_%=;				\
+	/* bpf_tail_call() */				\
+	r3 = 3;						\
+	r2 = %[map_prog1_tc] ll;			\
+	r1 = r7;					\
+	call %[bpf_tail_call];				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_sk_release];				\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_tc),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: release reference then tail call")
+__success __retval(0)
+__naked void release_reference_then_tail_call(void)
+{
+	asm volatile ("					\
+	r7 = r1;					\
+"	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	/* if (sk) bpf_sk_release() */			\
+	r1 = r0;					\
+	if r1 == 0 goto l0_%=;				\
+	call %[bpf_sk_release];				\
+l0_%=:	/* bpf_tail_call() */				\
+	r3 = 3;						\
+	r2 = %[map_prog1_tc] ll;			\
+	r1 = r7;					\
+	call %[bpf_tail_call];				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_tc),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: leak possible reference over tail call")
+__failure __msg("tail_call would lead to reference leak")
+__naked void possible_reference_over_tail_call(void)
+{
+	asm volatile ("					\
+	r7 = r1;					\
+	/* Look up socket and store in REG_6 */		\
+"	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	/* bpf_tail_call() */				\
+	r6 = r0;					\
+	r3 = 3;						\
+	r2 = %[map_prog1_tc] ll;			\
+	r1 = r7;					\
+	call %[bpf_tail_call];				\
+	r0 = 0;						\
+	/* if (sk) bpf_sk_release() */			\
+	r1 = r6;					\
+	if r1 == 0 goto l0_%=;				\
+	call %[bpf_sk_release];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_tc),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: leak checked reference over tail call")
+__failure __msg("tail_call would lead to reference leak")
+__naked void checked_reference_over_tail_call(void)
+{
+	asm volatile ("					\
+	r7 = r1;					\
+	/* Look up socket and store in REG_6 */		\
+"	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r6 = r0;					\
+	/* if (!sk) goto end */				\
+	if r0 == 0 goto l0_%=;				\
+	/* bpf_tail_call() */				\
+	r3 = 0;						\
+	r2 = %[map_prog1_tc] ll;			\
+	r1 = r7;					\
+	call %[bpf_tail_call];				\
+	r0 = 0;						\
+	r1 = r6;					\
+l0_%=:	call %[bpf_sk_release];				\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_tc),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: mangle and release sock_or_null")
+__failure __msg("R1 pointer arithmetic on sock_or_null prohibited")
+__naked void and_release_sock_or_null(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r1 = r0;					\
+	r1 += 5;					\
+	if r0 == 0 goto l0_%=;				\
+	call %[bpf_sk_release];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: mangle and release sock")
+__failure __msg("R1 pointer arithmetic on sock prohibited")
+__naked void tracking_mangle_and_release_sock(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r1 = r0;					\
+	if r0 == 0 goto l0_%=;				\
+	r1 += 5;					\
+	call %[bpf_sk_release];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: access member")
+__success __retval(0)
+__naked void reference_tracking_access_member(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r6 = r0;					\
+	if r0 == 0 goto l0_%=;				\
+	r2 = *(u32*)(r0 + 4);				\
+	r1 = r6;					\
+	call %[bpf_sk_release];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: write to member")
+__failure __msg("cannot write into sock")
+__naked void reference_tracking_write_to_member(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r6 = r0;					\
+	if r0 == 0 goto l0_%=;				\
+	r1 = r6;					\
+	r2 = 42 ll;					\
+	*(u32*)(r1 + %[bpf_sock_mark]) = r2;		\
+	r1 = r6;					\
+l0_%=:	call %[bpf_sk_release];				\
+	r0 = 0 ll;					\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(bpf_sock_mark, offsetof(struct bpf_sock, mark)),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: invalid 64-bit access of member")
+__failure __msg("invalid sock access off=0 size=8")
+__naked void _64_bit_access_of_member(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r6 = r0;					\
+	if r0 == 0 goto l0_%=;				\
+	r2 = *(u64*)(r0 + 0);				\
+	r1 = r6;					\
+	call %[bpf_sk_release];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: access after release")
+__failure __msg("!read_ok")
+__naked void reference_tracking_access_after_release(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r1 = r0;					\
+	if r0 == 0 goto l0_%=;				\
+	call %[bpf_sk_release];				\
+	r2 = *(u32*)(r1 + 0);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: direct access for lookup")
+__success __retval(0)
+__naked void tracking_direct_access_for_lookup(void)
+{
+	asm volatile ("					\
+	/* Check that the packet is at least 64B long */\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r0 = r2;					\
+	r0 += 64;					\
+	if r0 > r3 goto l0_%=;				\
+	/* sk = sk_lookup_tcp(ctx, skb->data, ...) */	\
+	r3 = %[sizeof_bpf_sock_tuple];			\
+	r4 = 0;						\
+	r5 = 0;						\
+	call %[bpf_sk_lookup_tcp];			\
+	r6 = r0;					\
+	if r0 == 0 goto l0_%=;				\
+	r2 = *(u32*)(r0 + 4);				\
+	r1 = r6;					\
+	call %[bpf_sk_release];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: use ptr from bpf_tcp_sock() after release")
+__failure __msg("invalid mem access")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void bpf_tcp_sock_after_release(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r6 = r0;					\
+	r1 = r0;					\
+	call %[bpf_tcp_sock];				\
+	if r0 != 0 goto l1_%=;				\
+	r1 = r6;					\
+	call %[bpf_sk_release];				\
+	exit;						\
+l1_%=:	r7 = r0;					\
+	r1 = r6;					\
+	call %[bpf_sk_release];				\
+	r0 = *(u32*)(r7 + %[bpf_tcp_sock_snd_cwnd]);	\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm(bpf_tcp_sock),
+	  __imm_const(bpf_tcp_sock_snd_cwnd, offsetof(struct bpf_tcp_sock, snd_cwnd)),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: use ptr from bpf_sk_fullsock() after release")
+__failure __msg("invalid mem access")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void bpf_sk_fullsock_after_release(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r6 = r0;					\
+	r1 = r0;					\
+	call %[bpf_sk_fullsock];			\
+	if r0 != 0 goto l1_%=;				\
+	r1 = r6;					\
+	call %[bpf_sk_release];				\
+	exit;						\
+l1_%=:	r7 = r0;					\
+	r1 = r6;					\
+	call %[bpf_sk_release];				\
+	r0 = *(u32*)(r7 + %[bpf_sock_type]);		\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type)),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: use ptr from bpf_sk_fullsock(tp) after release")
+__failure __msg("invalid mem access")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void sk_fullsock_tp_after_release(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r6 = r0;					\
+	r1 = r0;					\
+	call %[bpf_tcp_sock];				\
+	if r0 != 0 goto l1_%=;				\
+	r1 = r6;					\
+	call %[bpf_sk_release];				\
+	exit;						\
+l1_%=:	r1 = r0;					\
+	call %[bpf_sk_fullsock];			\
+	r1 = r6;					\
+	r6 = r0;					\
+	call %[bpf_sk_release];				\
+	if r6 != 0 goto l2_%=;				\
+	exit;						\
+l2_%=:	r0 = *(u32*)(r6 + %[bpf_sock_type]);		\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm(bpf_tcp_sock),
+	  __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type)),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: use sk after bpf_sk_release(tp)")
+__failure __msg("invalid mem access")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void after_bpf_sk_release_tp(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r6 = r0;					\
+	r1 = r0;					\
+	call %[bpf_tcp_sock];				\
+	if r0 != 0 goto l1_%=;				\
+	r1 = r6;					\
+	call %[bpf_sk_release];				\
+	exit;						\
+l1_%=:	r1 = r0;					\
+	call %[bpf_sk_release];				\
+	r0 = *(u32*)(r6 + %[bpf_sock_type]);		\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm(bpf_tcp_sock),
+	  __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type)),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: use ptr from bpf_get_listener_sock() after bpf_sk_release(sk)")
+__success __retval(0)
+__naked void after_bpf_sk_release_sk(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r6 = r0;					\
+	r1 = r0;					\
+	call %[bpf_get_listener_sock];			\
+	if r0 != 0 goto l1_%=;				\
+	r1 = r6;					\
+	call %[bpf_sk_release];				\
+	exit;						\
+l1_%=:	r1 = r6;					\
+	r6 = r0;					\
+	call %[bpf_sk_release];				\
+	r0 = *(u32*)(r6 + %[bpf_sock_src_port]);	\
+	exit;						\
+"	:
+	: __imm(bpf_get_listener_sock),
+	  __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(bpf_sock_src_port, offsetof(struct bpf_sock, src_port)),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: bpf_sk_release(listen_sk)")
+__failure __msg("R1 must be referenced when passed to release function")
+__naked void bpf_sk_release_listen_sk(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r6 = r0;					\
+	r1 = r0;					\
+	call %[bpf_get_listener_sock];			\
+	if r0 != 0 goto l1_%=;				\
+	r1 = r6;					\
+	call %[bpf_sk_release];				\
+	exit;						\
+l1_%=:	r1 = r0;					\
+	call %[bpf_sk_release];				\
+	r0 = *(u32*)(r6 + %[bpf_sock_type]);		\
+	r1 = r6;					\
+	call %[bpf_sk_release];				\
+	exit;						\
+"	:
+	: __imm(bpf_get_listener_sock),
+	  __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type)),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+/* !bpf_sk_fullsock(sk) is checked but !bpf_tcp_sock(sk) is not checked */
+SEC("tc")
+__description("reference tracking: tp->snd_cwnd after bpf_sk_fullsock(sk) and bpf_tcp_sock(sk)")
+__failure __msg("invalid mem access")
+__naked void and_bpf_tcp_sock_sk(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r6 = r0;					\
+	r1 = r0;					\
+	call %[bpf_sk_fullsock];			\
+	r7 = r0;					\
+	r1 = r6;					\
+	call %[bpf_tcp_sock];				\
+	r8 = r0;					\
+	if r7 != 0 goto l1_%=;				\
+	r1 = r6;					\
+	call %[bpf_sk_release];				\
+	exit;						\
+l1_%=:	r0 = *(u32*)(r8 + %[bpf_tcp_sock_snd_cwnd]);	\
+	r1 = r6;					\
+	call %[bpf_sk_release];				\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm(bpf_tcp_sock),
+	  __imm_const(bpf_tcp_sock_snd_cwnd, offsetof(struct bpf_tcp_sock, snd_cwnd)),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: branch tracking valid pointer null comparison")
+__success __retval(0)
+__naked void tracking_valid_pointer_null_comparison(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r6 = r0;					\
+	r3 = 1;						\
+	if r6 != 0 goto l0_%=;				\
+	r3 = 0;						\
+l0_%=:	if r6 == 0 goto l1_%=;				\
+	r1 = r6;					\
+	call %[bpf_sk_release];				\
+l1_%=:	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: branch tracking valid pointer value comparison")
+__failure __msg("Unreleased reference")
+__naked void tracking_valid_pointer_value_comparison(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r6 = r0;					\
+	r3 = 1;						\
+	if r6 == 0 goto l0_%=;				\
+	r3 = 0;						\
+	if r6 == 1234 goto l0_%=;			\
+	r1 = r6;					\
+	call %[bpf_sk_release];				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: bpf_sk_release(btf_tcp_sock)")
+__success
+__retval(0)
+__naked void sk_release_btf_tcp_sock(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r6 = r0;					\
+	r1 = r0;					\
+	call %[bpf_skc_to_tcp_sock];			\
+	if r0 != 0 goto l1_%=;				\
+	r1 = r6;					\
+	call %[bpf_sk_release];				\
+	exit;						\
+l1_%=:	r1 = r0;					\
+	call %[bpf_sk_release];				\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm(bpf_skc_to_tcp_sock),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("reference tracking: use ptr from bpf_skc_to_tcp_sock() after release")
+__failure __msg("invalid mem access")
+__naked void to_tcp_sock_after_release(void)
+{
+	asm volatile (
+	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r6 = r0;					\
+	r1 = r0;					\
+	call %[bpf_skc_to_tcp_sock];			\
+	if r0 != 0 goto l1_%=;				\
+	r1 = r6;					\
+	call %[bpf_sk_release];				\
+	exit;						\
+l1_%=:	r7 = r0;					\
+	r1 = r6;					\
+	call %[bpf_sk_release];				\
+	r0 = *(u8*)(r7 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm(bpf_skc_to_tcp_sock),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("reference tracking: try to leak released ptr reg")
+__success __failure_unpriv __msg_unpriv("R8 !read_ok")
+__retval(0)
+__naked void to_leak_released_ptr_reg(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	*(u32*)(r10 - 4) = r0;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r9 = r0;					\
+	r0 = 0;						\
+	r1 = %[map_ringbuf] ll;				\
+	r2 = 8;						\
+	r3 = 0;						\
+	call %[bpf_ringbuf_reserve];			\
+	if r0 != 0 goto l1_%=;				\
+	exit;						\
+l1_%=:	r8 = r0;					\
+	r1 = r8;					\
+	r2 = 0;						\
+	call %[bpf_ringbuf_discard];			\
+	r0 = 0;						\
+	*(u64*)(r9 + 0) = r8;				\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_ringbuf_discard),
+	  __imm(bpf_ringbuf_reserve),
+	  __imm_addr(map_array_48b),
+	  __imm_addr(map_ringbuf)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_reg_equal.c b/tools/testing/selftests/bpf/progs/verifier_reg_equal.c
new file mode 100644
index 000000000000..dc1d8c30fb0e
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_reg_equal.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("socket")
+__description("check w reg equal if r reg upper32 bits 0")
+__success
+__naked void subreg_equality_1(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	*(u64 *)(r10 - 8) = r0;				\
+	r2 = *(u32 *)(r10 - 8);				\
+	/* At this point upper 4-bytes of r2 are 0,	\
+	 * thus insn w3 = w2 should propagate reg id,	\
+	 * and w2 < 9 comparison would also propagate	\
+	 * the range for r3.				\
+	 */						\
+	w3 = w2;					\
+	if w2 < 9 goto l0_%=;				\
+	exit;						\
+l0_%=:	if r3 < 9 goto l1_%=;				\
+	/* r1 read is illegal at this point */		\
+	r0 -= r1;					\
+l1_%=:	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check w reg not equal if r reg upper32 bits not 0")
+__failure __msg("R1 !read_ok")
+__naked void subreg_equality_2(void)
+{
+	asm volatile ("					\
+	call %[bpf_ktime_get_ns];			\
+	r2 = r0;					\
+	/* Upper 4-bytes of r2 may not be 0, thus insn	\
+	 * w3 = w2 should not propagate reg id,	and	\
+	 * w2 < 9 comparison should not propagate	\
+	 * the range for r3 either.			\
+	 */						\
+	w3 = w2;					\
+	if w2 < 9 goto l0_%=;				\
+	exit;						\
+l0_%=:	if r3 < 9 goto l1_%=;				\
+	/* r1 read is illegal at this point */		\
+	r0 -= r1;					\
+l1_%=:	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_regalloc.c b/tools/testing/selftests/bpf/progs/verifier_regalloc.c
new file mode 100644
index 000000000000..ee5ddea87c91
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_regalloc.c
@@ -0,0 +1,364 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/regalloc.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#define MAX_ENTRIES 11
+
+struct test_val {
+	unsigned int index;
+	int foo[MAX_ENTRIES];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, struct test_val);
+} map_hash_48b SEC(".maps");
+
+SEC("tracepoint")
+__description("regalloc basic")
+__success __flag(BPF_F_ANY_ALIGNMENT)
+__naked void regalloc_basic(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r7 = r0;					\
+	call %[bpf_get_prandom_u32];			\
+	r2 = r0;					\
+	if r0 s> 20 goto l0_%=;				\
+	if r2 s< 0 goto l0_%=;				\
+	r7 += r0;					\
+	r7 += r2;					\
+	r0 = *(u64*)(r7 + 0);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("regalloc negative")
+__failure __msg("invalid access to map value, value_size=48 off=48 size=1")
+__naked void regalloc_negative(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r7 = r0;					\
+	call %[bpf_get_prandom_u32];			\
+	r2 = r0;					\
+	if r0 s> 24 goto l0_%=;				\
+	if r2 s< 0 goto l0_%=;				\
+	r7 += r0;					\
+	r7 += r2;					\
+	r0 = *(u8*)(r7 + 0);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("regalloc src_reg mark")
+__success __flag(BPF_F_ANY_ALIGNMENT)
+__naked void regalloc_src_reg_mark(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r7 = r0;					\
+	call %[bpf_get_prandom_u32];			\
+	r2 = r0;					\
+	if r0 s> 20 goto l0_%=;				\
+	r3 = 0;						\
+	if r3 s>= r2 goto l0_%=;			\
+	r7 += r0;					\
+	r7 += r2;					\
+	r0 = *(u64*)(r7 + 0);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("regalloc src_reg negative")
+__failure __msg("invalid access to map value, value_size=48 off=44 size=8")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void regalloc_src_reg_negative(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r7 = r0;					\
+	call %[bpf_get_prandom_u32];			\
+	r2 = r0;					\
+	if r0 s> 22 goto l0_%=;				\
+	r3 = 0;						\
+	if r3 s>= r2 goto l0_%=;			\
+	r7 += r0;					\
+	r7 += r2;					\
+	r0 = *(u64*)(r7 + 0);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("regalloc and spill")
+__success __flag(BPF_F_ANY_ALIGNMENT)
+__naked void regalloc_and_spill(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r7 = r0;					\
+	call %[bpf_get_prandom_u32];			\
+	r2 = r0;					\
+	if r0 s> 20 goto l0_%=;				\
+	/* r0 has upper bound that should propagate into r2 */\
+	*(u64*)(r10 - 8) = r2;		/* spill r2 */	\
+	r0 = 0;						\
+	r2 = 0;				/* clear r0 and r2 */\
+	r3 = *(u64*)(r10 - 8);		/* fill r3 */	\
+	if r0 s>= r3 goto l0_%=;			\
+	/* r3 has lower and upper bounds */		\
+	r7 += r3;					\
+	r0 = *(u64*)(r7 + 0);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("regalloc and spill negative")
+__failure __msg("invalid access to map value, value_size=48 off=48 size=8")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void regalloc_and_spill_negative(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r7 = r0;					\
+	call %[bpf_get_prandom_u32];			\
+	r2 = r0;					\
+	if r0 s> 48 goto l0_%=;				\
+	/* r0 has upper bound that should propagate into r2 */\
+	*(u64*)(r10 - 8) = r2;		/* spill r2 */	\
+	r0 = 0;						\
+	r2 = 0;				/* clear r0 and r2 */\
+	r3 = *(u64*)(r10 - 8);		/* fill r3 */\
+	if r0 s>= r3 goto l0_%=;			\
+	/* r3 has lower and upper bounds */		\
+	r7 += r3;					\
+	r0 = *(u64*)(r7 + 0);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("regalloc three regs")
+__success __flag(BPF_F_ANY_ALIGNMENT)
+__naked void regalloc_three_regs(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r7 = r0;					\
+	call %[bpf_get_prandom_u32];			\
+	r2 = r0;					\
+	r4 = r2;					\
+	if r0 s> 12 goto l0_%=;				\
+	if r2 s< 0 goto l0_%=;				\
+	r7 += r0;					\
+	r7 += r2;					\
+	r7 += r4;					\
+	r0 = *(u64*)(r7 + 0);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("regalloc after call")
+__success __flag(BPF_F_ANY_ALIGNMENT)
+__naked void regalloc_after_call(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r7 = r0;					\
+	call %[bpf_get_prandom_u32];			\
+	r8 = r0;					\
+	r9 = r0;					\
+	call regalloc_after_call__1;			\
+	if r8 s> 20 goto l0_%=;				\
+	if r9 s< 0 goto l0_%=;				\
+	r7 += r8;					\
+	r7 += r9;					\
+	r0 = *(u64*)(r7 + 0);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+static __naked __noinline __attribute__((used))
+void regalloc_after_call__1(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("regalloc in callee")
+__success __flag(BPF_F_ANY_ALIGNMENT)
+__naked void regalloc_in_callee(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r7 = r0;					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	r2 = r0;					\
+	r3 = r7;					\
+	call regalloc_in_callee__1;			\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+static __naked __noinline __attribute__((used))
+void regalloc_in_callee__1(void)
+{
+	asm volatile ("					\
+	if r1 s> 20 goto l0_%=;				\
+	if r2 s< 0 goto l0_%=;				\
+	r3 += r1;					\
+	r3 += r2;					\
+	r0 = *(u64*)(r3 + 0);				\
+	exit;						\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("regalloc, spill, JEQ")
+__success
+__naked void regalloc_spill_jeq(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	*(u64*)(r10 - 8) = r0;		/* spill r0 */	\
+	if r0 == 0 goto l0_%=;				\
+l0_%=:	/* The verifier will walk the rest twice with r0 == 0 and r0 == map_value */\
+	call %[bpf_get_prandom_u32];			\
+	r2 = r0;					\
+	if r2 == 20 goto l1_%=;				\
+l1_%=:	/* The verifier will walk the rest two more times with r0 == 20 and r0 == unknown */\
+	r3 = *(u64*)(r10 - 8);		/* fill r3 with map_value */\
+	if r3 == 0 goto l2_%=;		/* skip ldx if map_value == NULL */\
+	/* Buggy verifier will think that r3 == 20 here */\
+	r0 = *(u64*)(r3 + 0);		/* read from map_value */\
+l2_%=:	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_ringbuf.c b/tools/testing/selftests/bpf/progs/verifier_ringbuf.c
new file mode 100644
index 000000000000..ae1d521f326c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_ringbuf.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/ringbuf.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_RINGBUF);
+	__uint(max_entries, 4096);
+} map_ringbuf SEC(".maps");
+
+SEC("socket")
+__description("ringbuf: invalid reservation offset 1")
+__failure __msg("R1 must have zero offset when passed to release func")
+__failure_unpriv
+__naked void ringbuf_invalid_reservation_offset_1(void)
+{
+	asm volatile ("					\
+	/* reserve 8 byte ringbuf memory */		\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r1 = %[map_ringbuf] ll;				\
+	r2 = 8;						\
+	r3 = 0;						\
+	call %[bpf_ringbuf_reserve];			\
+	/* store a pointer to the reserved memory in R6 */\
+	r6 = r0;					\
+	/* check whether the reservation was successful */\
+	if r0 == 0 goto l0_%=;				\
+	/* spill R6(mem) into the stack */		\
+	*(u64*)(r10 - 8) = r6;				\
+	/* fill it back in R7 */			\
+	r7 = *(u64*)(r10 - 8);				\
+	/* should be able to access *(R7) = 0 */	\
+	r1 = 0;						\
+	*(u64*)(r7 + 0) = r1;				\
+	/* submit the reserved ringbuf memory */	\
+	r1 = r7;					\
+	/* add invalid offset to reserved ringbuf memory */\
+	r1 += 0xcafe;					\
+	r2 = 0;						\
+	call %[bpf_ringbuf_submit];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ringbuf_reserve),
+	  __imm(bpf_ringbuf_submit),
+	  __imm_addr(map_ringbuf)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("ringbuf: invalid reservation offset 2")
+__failure __msg("R7 min value is outside of the allowed memory range")
+__failure_unpriv
+__naked void ringbuf_invalid_reservation_offset_2(void)
+{
+	asm volatile ("					\
+	/* reserve 8 byte ringbuf memory */		\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r1 = %[map_ringbuf] ll;				\
+	r2 = 8;						\
+	r3 = 0;						\
+	call %[bpf_ringbuf_reserve];			\
+	/* store a pointer to the reserved memory in R6 */\
+	r6 = r0;					\
+	/* check whether the reservation was successful */\
+	if r0 == 0 goto l0_%=;				\
+	/* spill R6(mem) into the stack */		\
+	*(u64*)(r10 - 8) = r6;				\
+	/* fill it back in R7 */			\
+	r7 = *(u64*)(r10 - 8);				\
+	/* add invalid offset to reserved ringbuf memory */\
+	r7 += 0xcafe;					\
+	/* should be able to access *(R7) = 0 */	\
+	r1 = 0;						\
+	*(u64*)(r7 + 0) = r1;				\
+	/* submit the reserved ringbuf memory */	\
+	r1 = r7;					\
+	r2 = 0;						\
+	call %[bpf_ringbuf_submit];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ringbuf_reserve),
+	  __imm(bpf_ringbuf_submit),
+	  __imm_addr(map_ringbuf)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("ringbuf: check passing rb mem to helpers")
+__success __retval(0)
+__naked void passing_rb_mem_to_helpers(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	/* reserve 8 byte ringbuf memory */		\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r1 = %[map_ringbuf] ll;				\
+	r2 = 8;						\
+	r3 = 0;						\
+	call %[bpf_ringbuf_reserve];			\
+	r7 = r0;					\
+	/* check whether the reservation was successful */\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	/* pass allocated ring buffer memory to fib lookup */\
+	r1 = r6;					\
+	r2 = r0;					\
+	r3 = 8;						\
+	r4 = 0;						\
+	call %[bpf_fib_lookup];				\
+	/* submit the ringbuf memory */			\
+	r1 = r7;					\
+	r2 = 0;						\
+	call %[bpf_ringbuf_submit];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_fib_lookup),
+	  __imm(bpf_ringbuf_reserve),
+	  __imm(bpf_ringbuf_submit),
+	  __imm_addr(map_ringbuf)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_runtime_jit.c b/tools/testing/selftests/bpf/progs/verifier_runtime_jit.c
new file mode 100644
index 000000000000..27ebfc1fd9ee
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_runtime_jit.c
@@ -0,0 +1,360 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/runtime_jit.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+void dummy_prog_42_socket(void);
+void dummy_prog_24_socket(void);
+void dummy_prog_loop1_socket(void);
+void dummy_prog_loop2_socket(void);
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 4);
+	__uint(key_size, sizeof(int));
+	__array(values, void (void));
+} map_prog1_socket SEC(".maps") = {
+	.values = {
+		[0] = (void *)&dummy_prog_42_socket,
+		[1] = (void *)&dummy_prog_loop1_socket,
+		[2] = (void *)&dummy_prog_24_socket,
+	},
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 8);
+	__uint(key_size, sizeof(int));
+	__array(values, void (void));
+} map_prog2_socket SEC(".maps") = {
+	.values = {
+		[1] = (void *)&dummy_prog_loop2_socket,
+		[2] = (void *)&dummy_prog_24_socket,
+		[7] = (void *)&dummy_prog_42_socket,
+	},
+};
+
+SEC("socket")
+__auxiliary __auxiliary_unpriv
+__naked void dummy_prog_42_socket(void)
+{
+	asm volatile ("r0 = 42; exit;");
+}
+
+SEC("socket")
+__auxiliary __auxiliary_unpriv
+__naked void dummy_prog_24_socket(void)
+{
+	asm volatile ("r0 = 24; exit;");
+}
+
+SEC("socket")
+__auxiliary __auxiliary_unpriv
+__naked void dummy_prog_loop1_socket(void)
+{
+	asm volatile ("			\
+	r3 = 1;				\
+	r2 = %[map_prog1_socket] ll;	\
+	call %[bpf_tail_call];		\
+	r0 = 41;			\
+	exit;				\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_socket)
+	: __clobber_all);
+}
+
+SEC("socket")
+__auxiliary __auxiliary_unpriv
+__naked void dummy_prog_loop2_socket(void)
+{
+	asm volatile ("			\
+	r3 = 1;				\
+	r2 = %[map_prog2_socket] ll;	\
+	call %[bpf_tail_call];		\
+	r0 = 41;			\
+	exit;				\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog2_socket)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("runtime/jit: tail_call within bounds, prog once")
+__success __success_unpriv __retval(42)
+__naked void call_within_bounds_prog_once(void)
+{
+	asm volatile ("					\
+	r3 = 0;						\
+	r2 = %[map_prog1_socket] ll;			\
+	call %[bpf_tail_call];				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_socket)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("runtime/jit: tail_call within bounds, prog loop")
+__success __success_unpriv __retval(41)
+__naked void call_within_bounds_prog_loop(void)
+{
+	asm volatile ("					\
+	r3 = 1;						\
+	r2 = %[map_prog1_socket] ll;			\
+	call %[bpf_tail_call];				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_socket)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("runtime/jit: tail_call within bounds, no prog")
+__success __success_unpriv __retval(1)
+__naked void call_within_bounds_no_prog(void)
+{
+	asm volatile ("					\
+	r3 = 3;						\
+	r2 = %[map_prog1_socket] ll;			\
+	call %[bpf_tail_call];				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_socket)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("runtime/jit: tail_call within bounds, key 2")
+__success __success_unpriv __retval(24)
+__naked void call_within_bounds_key_2(void)
+{
+	asm volatile ("					\
+	r3 = 2;						\
+	r2 = %[map_prog1_socket] ll;			\
+	call %[bpf_tail_call];				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_socket)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("runtime/jit: tail_call within bounds, key 2 / key 2, first branch")
+__success __success_unpriv __retval(24)
+__naked void _2_key_2_first_branch(void)
+{
+	asm volatile ("					\
+	r0 = 13;					\
+	*(u8*)(r1 + %[__sk_buff_cb_0]) = r0;		\
+	r0 = *(u8*)(r1 + %[__sk_buff_cb_0]);		\
+	if r0 == 13 goto l0_%=;				\
+	r3 = 2;						\
+	r2 = %[map_prog1_socket] ll;			\
+	goto l1_%=;					\
+l0_%=:	r3 = 2;						\
+	r2 = %[map_prog1_socket] ll;			\
+l1_%=:	call %[bpf_tail_call];				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_socket),
+	  __imm_const(__sk_buff_cb_0, offsetof(struct __sk_buff, cb[0]))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("runtime/jit: tail_call within bounds, key 2 / key 2, second branch")
+__success __success_unpriv __retval(24)
+__naked void _2_key_2_second_branch(void)
+{
+	asm volatile ("					\
+	r0 = 14;					\
+	*(u8*)(r1 + %[__sk_buff_cb_0]) = r0;		\
+	r0 = *(u8*)(r1 + %[__sk_buff_cb_0]);		\
+	if r0 == 13 goto l0_%=;				\
+	r3 = 2;						\
+	r2 = %[map_prog1_socket] ll;			\
+	goto l1_%=;					\
+l0_%=:	r3 = 2;						\
+	r2 = %[map_prog1_socket] ll;			\
+l1_%=:	call %[bpf_tail_call];				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_socket),
+	  __imm_const(__sk_buff_cb_0, offsetof(struct __sk_buff, cb[0]))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("runtime/jit: tail_call within bounds, key 0 / key 2, first branch")
+__success __success_unpriv __retval(24)
+__naked void _0_key_2_first_branch(void)
+{
+	asm volatile ("					\
+	r0 = 13;					\
+	*(u8*)(r1 + %[__sk_buff_cb_0]) = r0;		\
+	r0 = *(u8*)(r1 + %[__sk_buff_cb_0]);		\
+	if r0 == 13 goto l0_%=;				\
+	r3 = 0;						\
+	r2 = %[map_prog1_socket] ll;			\
+	goto l1_%=;					\
+l0_%=:	r3 = 2;						\
+	r2 = %[map_prog1_socket] ll;			\
+l1_%=:	call %[bpf_tail_call];				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_socket),
+	  __imm_const(__sk_buff_cb_0, offsetof(struct __sk_buff, cb[0]))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("runtime/jit: tail_call within bounds, key 0 / key 2, second branch")
+__success __success_unpriv __retval(42)
+__naked void _0_key_2_second_branch(void)
+{
+	asm volatile ("					\
+	r0 = 14;					\
+	*(u8*)(r1 + %[__sk_buff_cb_0]) = r0;		\
+	r0 = *(u8*)(r1 + %[__sk_buff_cb_0]);		\
+	if r0 == 13 goto l0_%=;				\
+	r3 = 0;						\
+	r2 = %[map_prog1_socket] ll;			\
+	goto l1_%=;					\
+l0_%=:	r3 = 2;						\
+	r2 = %[map_prog1_socket] ll;			\
+l1_%=:	call %[bpf_tail_call];				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_socket),
+	  __imm_const(__sk_buff_cb_0, offsetof(struct __sk_buff, cb[0]))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("runtime/jit: tail_call within bounds, different maps, first branch")
+__success __failure_unpriv __msg_unpriv("tail_call abusing map_ptr")
+__retval(1)
+__naked void bounds_different_maps_first_branch(void)
+{
+	asm volatile ("					\
+	r0 = 13;					\
+	*(u8*)(r1 + %[__sk_buff_cb_0]) = r0;		\
+	r0 = *(u8*)(r1 + %[__sk_buff_cb_0]);		\
+	if r0 == 13 goto l0_%=;				\
+	r3 = 0;						\
+	r2 = %[map_prog1_socket] ll;			\
+	goto l1_%=;					\
+l0_%=:	r3 = 0;						\
+	r2 = %[map_prog2_socket] ll;			\
+l1_%=:	call %[bpf_tail_call];				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_socket),
+	  __imm_addr(map_prog2_socket),
+	  __imm_const(__sk_buff_cb_0, offsetof(struct __sk_buff, cb[0]))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("runtime/jit: tail_call within bounds, different maps, second branch")
+__success __failure_unpriv __msg_unpriv("tail_call abusing map_ptr")
+__retval(42)
+__naked void bounds_different_maps_second_branch(void)
+{
+	asm volatile ("					\
+	r0 = 14;					\
+	*(u8*)(r1 + %[__sk_buff_cb_0]) = r0;		\
+	r0 = *(u8*)(r1 + %[__sk_buff_cb_0]);		\
+	if r0 == 13 goto l0_%=;				\
+	r3 = 0;						\
+	r2 = %[map_prog1_socket] ll;			\
+	goto l1_%=;					\
+l0_%=:	r3 = 0;						\
+	r2 = %[map_prog2_socket] ll;			\
+l1_%=:	call %[bpf_tail_call];				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_socket),
+	  __imm_addr(map_prog2_socket),
+	  __imm_const(__sk_buff_cb_0, offsetof(struct __sk_buff, cb[0]))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("runtime/jit: tail_call out of bounds")
+__success __success_unpriv __retval(2)
+__naked void tail_call_out_of_bounds(void)
+{
+	asm volatile ("					\
+	r3 = 256;					\
+	r2 = %[map_prog1_socket] ll;			\
+	call %[bpf_tail_call];				\
+	r0 = 2;						\
+	exit;						\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_socket)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("runtime/jit: pass negative index to tail_call")
+__success __success_unpriv __retval(2)
+__naked void negative_index_to_tail_call(void)
+{
+	asm volatile ("					\
+	r3 = -1;					\
+	r2 = %[map_prog1_socket] ll;			\
+	call %[bpf_tail_call];				\
+	r0 = 2;						\
+	exit;						\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_socket)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("runtime/jit: pass > 32bit index to tail_call")
+__success __success_unpriv __retval(42)
+/* Verifier rewrite for unpriv skips tail call here. */
+__retval_unpriv(2)
+__naked void _32bit_index_to_tail_call(void)
+{
+	asm volatile ("					\
+	r3 = 0x100000000 ll;				\
+	r2 = %[map_prog1_socket] ll;			\
+	call %[bpf_tail_call];				\
+	r0 = 2;						\
+	exit;						\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_socket)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
new file mode 100644
index 000000000000..c0ce690ddb68
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_scalar_ids.c
@@ -0,0 +1,830 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+/* Check that precision marks propagate through scalar IDs.
+ * Registers r{0,1,2} have the same scalar ID.
+ * Range information is propagated for scalars sharing same ID.
+ * Check that precision mark for r0 causes precision marks for r{1,2}
+ * when range information is propagated for 'if <reg> <op> <const>' insn.
+ */
+SEC("socket")
+__success __log_level(2)
+/* first 'if' branch */
+__msg("6: (0f) r3 += r0")
+__msg("frame0: regs=r0 stack= before 4: (25) if r1 > 0x7 goto pc+0")
+__msg("frame0: parent state regs=r0,r1,r2 stack=:")
+__msg("frame0: regs=r0,r1,r2 stack= before 3: (bf) r2 = r0")
+/* second 'if' branch */
+__msg("from 4 to 5: ")
+__msg("6: (0f) r3 += r0")
+__msg("frame0: regs=r0 stack= before 5: (bf) r3 = r10")
+__msg("frame0: regs=r0 stack= before 4: (25) if r1 > 0x7 goto pc+0")
+/* parent state already has r{0,1,2} as precise */
+__msg("frame0: parent state regs= stack=:")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void linked_regs_bpf_k(void)
+{
+	asm volatile (
+	/* r0 = random number up to 0xff */
+	"call %[bpf_ktime_get_ns];"
+	"r0 &= 0xff;"
+	/* tie r0.id == r1.id == r2.id */
+	"r1 = r0;"
+	"r2 = r0;"
+	"if r1 > 7 goto +0;"
+	/* force r0 to be precise, this eventually marks r1 and r2 as
+	 * precise as well because of shared IDs
+	 */
+	"r3 = r10;"
+	"r3 += r0;"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+/* Registers r{0,1,2} share same ID when 'if r1 > ...' insn is processed,
+ * check that verifier marks r{1,2} as precise while backtracking
+ * 'if r1 > ...' with r0 already marked.
+ */
+SEC("socket")
+__success __log_level(2)
+__flag(BPF_F_TEST_STATE_FREQ)
+__msg("frame0: regs=r0 stack= before 5: (2d) if r1 > r3 goto pc+0")
+__msg("frame0: parent state regs=r0,r1,r2,r3 stack=:")
+__msg("frame0: regs=r0,r1,r2,r3 stack= before 4: (b7) r3 = 7")
+__naked void linked_regs_bpf_x_src(void)
+{
+	asm volatile (
+	/* r0 = random number up to 0xff */
+	"call %[bpf_ktime_get_ns];"
+	"r0 &= 0xff;"
+	/* tie r0.id == r1.id == r2.id */
+	"r1 = r0;"
+	"r2 = r0;"
+	"r3 = 7;"
+	"if r1 > r3 goto +0;"
+	/* force r0 to be precise, this eventually marks r1 and r2 as
+	 * precise as well because of shared IDs
+	 */
+	"r4 = r10;"
+	"r4 += r0;"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+/* Registers r{0,1,2} share same ID when 'if r1 > r3' insn is processed,
+ * check that verifier marks r{0,1,2} as precise while backtracking
+ * 'if r1 > r3' with r3 already marked.
+ */
+SEC("socket")
+__success __log_level(2)
+__flag(BPF_F_TEST_STATE_FREQ)
+__msg("frame0: regs=r3 stack= before 5: (2d) if r1 > r3 goto pc+0")
+__msg("frame0: parent state regs=r0,r1,r2,r3 stack=:")
+__msg("frame0: regs=r0,r1,r2,r3 stack= before 4: (b7) r3 = 7")
+__naked void linked_regs_bpf_x_dst(void)
+{
+	asm volatile (
+	/* r0 = random number up to 0xff */
+	"call %[bpf_ktime_get_ns];"
+	"r0 &= 0xff;"
+	/* tie r0.id == r1.id == r2.id */
+	"r1 = r0;"
+	"r2 = r0;"
+	"r3 = 7;"
+	"if r1 > r3 goto +0;"
+	/* force r0 to be precise, this eventually marks r1 and r2 as
+	 * precise as well because of shared IDs
+	 */
+	"r4 = r10;"
+	"r4 += r3;"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+/* Same as linked_regs_bpf_k, but break one of the
+ * links, note that r1 is absent from regs=... in __msg below.
+ */
+SEC("socket")
+__success __log_level(2)
+__msg("7: (0f) r3 += r0")
+__msg("frame0: regs=r0 stack= before 6: (bf) r3 = r10")
+__msg("frame0: parent state regs=r0 stack=:")
+__msg("frame0: regs=r0 stack= before 5: (25) if r0 > 0x7 goto pc+0")
+__msg("frame0: parent state regs=r0,r2 stack=:")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void linked_regs_broken_link(void)
+{
+	asm volatile (
+	/* r0 = random number up to 0xff */
+	"call %[bpf_ktime_get_ns];"
+	"r0 &= 0xff;"
+	/* tie r0.id == r1.id == r2.id */
+	"r1 = r0;"
+	"r2 = r0;"
+	/* break link for r1, this is the only line that differs
+	 * compared to the previous test
+	 */
+	"r1 = 0;"
+	"if r0 > 7 goto +0;"
+	/* force r0 to be precise,
+	 * this eventually marks r2 as precise because of shared IDs
+	 */
+	"r3 = r10;"
+	"r3 += r0;"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+/* Check that precision marks propagate through scalar IDs.
+ * Use the same scalar ID in multiple stack frames, check that
+ * precision information is propagated up the call stack.
+ */
+SEC("socket")
+__success __log_level(2)
+__msg("12: (0f) r2 += r1")
+/* Current state */
+__msg("frame2: last_idx 12 first_idx 11 subseq_idx -1 ")
+__msg("frame2: regs=r1 stack= before 11: (bf) r2 = r10")
+__msg("frame2: parent state regs=r1 stack=")
+__msg("frame1: parent state regs= stack=")
+__msg("frame0: parent state regs= stack=")
+/* Parent state */
+__msg("frame2: last_idx 10 first_idx 10 subseq_idx 11 ")
+__msg("frame2: regs=r1 stack= before 10: (25) if r1 > 0x7 goto pc+0")
+__msg("frame2: parent state regs=r1 stack=")
+/* frame1.r{6,7} are marked because mark_precise_scalar_ids()
+ * looks for all registers with frame2.r1.id in the current state
+ */
+__msg("frame1: parent state regs=r6,r7 stack=")
+__msg("frame0: parent state regs=r6 stack=")
+/* Parent state */
+__msg("frame2: last_idx 8 first_idx 8 subseq_idx 10")
+__msg("frame2: regs=r1 stack= before 8: (85) call pc+1")
+/* frame1.r1 is marked because of backtracking of call instruction */
+__msg("frame1: parent state regs=r1,r6,r7 stack=")
+__msg("frame0: parent state regs=r6 stack=")
+/* Parent state */
+__msg("frame1: last_idx 7 first_idx 6 subseq_idx 8")
+__msg("frame1: regs=r1,r6,r7 stack= before 7: (bf) r7 = r1")
+__msg("frame1: regs=r1,r6 stack= before 6: (bf) r6 = r1")
+__msg("frame1: parent state regs=r1 stack=")
+__msg("frame0: parent state regs=r6 stack=")
+/* Parent state */
+__msg("frame1: last_idx 4 first_idx 4 subseq_idx 6")
+__msg("frame1: regs=r1 stack= before 4: (85) call pc+1")
+__msg("frame0: parent state regs=r1,r6 stack=")
+/* Parent state */
+__msg("frame0: last_idx 3 first_idx 1 subseq_idx 4")
+__msg("frame0: regs=r1,r6 stack= before 3: (bf) r6 = r0")
+__msg("frame0: regs=r0,r1 stack= before 2: (bf) r1 = r0")
+__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void precision_many_frames(void)
+{
+	asm volatile (
+	/* r0 = random number up to 0xff */
+	"call %[bpf_ktime_get_ns];"
+	"r0 &= 0xff;"
+	/* tie r0.id == r1.id == r6.id */
+	"r1 = r0;"
+	"r6 = r0;"
+	"call precision_many_frames__foo;"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+static __naked __noinline __used
+void precision_many_frames__foo(void)
+{
+	asm volatile (
+	/* conflate one of the register numbers (r6) with outer frame,
+	 * to verify that those are tracked independently
+	 */
+	"r6 = r1;"
+	"r7 = r1;"
+	"call precision_many_frames__bar;"
+	"exit"
+	::: __clobber_all);
+}
+
+static __naked __noinline __used
+void precision_many_frames__bar(void)
+{
+	asm volatile (
+	"if r1 > 7 goto +0;"
+	/* force r1 to be precise, this eventually marks:
+	 * - bar frame r1
+	 * - foo frame r{1,6,7}
+	 * - main frame r{1,6}
+	 */
+	"r2 = r10;"
+	"r2 += r1;"
+	"r0 = 0;"
+	"exit;"
+	::: __clobber_all);
+}
+
+/* Check that scalars with the same IDs are marked precise on stack as
+ * well as in registers.
+ */
+SEC("socket")
+__success __log_level(2)
+__msg("11: (0f) r2 += r1")
+/* foo frame */
+__msg("frame1: regs=r1 stack= before 10: (bf) r2 = r10")
+__msg("frame1: regs=r1 stack= before 9: (25) if r1 > 0x7 goto pc+0")
+__msg("frame1: regs=r1 stack=-8,-16 before 8: (7b) *(u64 *)(r10 -16) = r1")
+__msg("frame1: regs=r1 stack=-8 before 7: (7b) *(u64 *)(r10 -8) = r1")
+__msg("frame1: regs=r1 stack= before 4: (85) call pc+2")
+/* main frame */
+__msg("frame0: regs=r1 stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r1")
+__msg("frame0: regs=r1 stack= before 2: (bf) r1 = r0")
+__msg("frame0: regs=r0 stack= before 1: (57) r0 &= 255")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void precision_stack(void)
+{
+	asm volatile (
+	/* r0 = random number up to 0xff */
+	"call %[bpf_ktime_get_ns];"
+	"r0 &= 0xff;"
+	/* tie r0.id == r1.id == fp[-8].id */
+	"r1 = r0;"
+	"*(u64*)(r10 - 8) = r1;"
+	"call precision_stack__foo;"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+static __naked __noinline __used
+void precision_stack__foo(void)
+{
+	asm volatile (
+	/* conflate one of the register numbers (r6) with outer frame,
+	 * to verify that those are tracked independently
+	 */
+	"*(u64*)(r10 - 8) = r1;"
+	"*(u64*)(r10 - 16) = r1;"
+	"if r1 > 7 goto +0;"
+	/* force r1 to be precise, this eventually marks:
+	 * - foo frame r1,fp{-8,-16}
+	 * - main frame r1,fp{-8}
+	 */
+	"r2 = r10;"
+	"r2 += r1;"
+	"exit"
+	::: __clobber_all);
+}
+
+/* Use two separate scalar IDs to check that these are propagated
+ * independently.
+ */
+SEC("socket")
+__success __log_level(2)
+/* r{6,7} */
+__msg("12: (0f) r3 += r7")
+__msg("frame0: regs=r7 stack= before 11: (bf) r3 = r10")
+__msg("frame0: regs=r7 stack= before 9: (25) if r7 > 0x7 goto pc+0")
+/* ... skip some insns ... */
+__msg("frame0: regs=r6,r7 stack= before 3: (bf) r7 = r0")
+__msg("frame0: regs=r0,r6 stack= before 2: (bf) r6 = r0")
+/* r{8,9} */
+__msg("13: (0f) r3 += r9")
+__msg("frame0: regs=r9 stack= before 12: (0f) r3 += r7")
+/* ... skip some insns ... */
+__msg("frame0: regs=r9 stack= before 10: (25) if r9 > 0x7 goto pc+0")
+__msg("frame0: regs=r8,r9 stack= before 7: (bf) r9 = r0")
+__msg("frame0: regs=r0,r8 stack= before 6: (bf) r8 = r0")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void precision_two_ids(void)
+{
+	asm volatile (
+	/* r6 = random number up to 0xff
+	 * r6.id == r7.id
+	 */
+	"call %[bpf_ktime_get_ns];"
+	"r0 &= 0xff;"
+	"r6 = r0;"
+	"r7 = r0;"
+	/* same, but for r{8,9} */
+	"call %[bpf_ktime_get_ns];"
+	"r0 &= 0xff;"
+	"r8 = r0;"
+	"r9 = r0;"
+	/* clear r0 id */
+	"r0 = 0;"
+	/* propagate equal scalars precision */
+	"if r7 > 7 goto +0;"
+	"if r9 > 7 goto +0;"
+	"r3 = r10;"
+	/* force r7 to be precise, this also marks r6 */
+	"r3 += r7;"
+	/* force r9 to be precise, this also marks r8 */
+	"r3 += r9;"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__success __log_level(2)
+__flag(BPF_F_TEST_STATE_FREQ)
+/* check that r0 and r6 have different IDs after 'if',
+ * collect_linked_regs() can't tie more than 6 registers for a single insn.
+ */
+__msg("8: (25) if r0 > 0x7 goto pc+0         ; R0=scalar(id=1")
+__msg("9: (bf) r6 = r6                       ; R6=scalar(id=2")
+/* check that r{0-5} are marked precise after 'if' */
+__msg("frame0: regs=r0 stack= before 8: (25) if r0 > 0x7 goto pc+0")
+__msg("frame0: parent state regs=r0,r1,r2,r3,r4,r5 stack=:")
+__naked void linked_regs_too_many_regs(void)
+{
+	asm volatile (
+	/* r0 = random number up to 0xff */
+	"call %[bpf_ktime_get_ns];"
+	"r0 &= 0xff;"
+	/* tie r{0-6} IDs */
+	"r1 = r0;"
+	"r2 = r0;"
+	"r3 = r0;"
+	"r4 = r0;"
+	"r5 = r0;"
+	"r6 = r0;"
+	/* propagate range for r{0-6} */
+	"if r0 > 7 goto +0;"
+	/* make r6 appear in the log */
+	"r6 = r6;"
+	/* force r0 to be precise,
+	 * this would cause r{0-4} to be precise because of shared IDs
+	 */
+	"r7 = r10;"
+	"r7 += r0;"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__failure __log_level(2)
+__flag(BPF_F_TEST_STATE_FREQ)
+__msg("regs=r7 stack= before 5: (3d) if r8 >= r0")
+__msg("parent state regs=r0,r7,r8")
+__msg("regs=r0,r7,r8 stack= before 4: (25) if r0 > 0x1")
+__msg("div by zero")
+__naked void linked_regs_broken_link_2(void)
+{
+	asm volatile (
+	"call %[bpf_get_prandom_u32];"
+	"r7 = r0;"
+	"r8 = r0;"
+	"call %[bpf_get_prandom_u32];"
+	"if r0 > 1 goto +0;"
+	/* r7.id == r8.id,
+	 * thus r7 precision implies r8 precision,
+	 * which implies r0 precision because of the conditional below.
+	 */
+	"if r8 >= r0 goto 1f;"
+	/* break id relation between r7 and r8 */
+	"r8 += r8;"
+	/* make r7 precise */
+	"if r7 == 0 goto 1f;"
+	"r0 /= 0;"
+"1:"
+	"r0 = 42;"
+	"exit;"
+	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* Check that mark_chain_precision() for one of the conditional jump
+ * operands does not trigger equal scalars precision propagation.
+ */
+SEC("socket")
+__success __log_level(2)
+__msg("3: (25) if r1 > 0x100 goto pc+0")
+__msg("frame0: regs=r1 stack= before 2: (bf) r1 = r0")
+__naked void cjmp_no_linked_regs_trigger(void)
+{
+	asm volatile (
+	/* r0 = random number up to 0xff */
+	"call %[bpf_ktime_get_ns];"
+	"r0 &= 0xff;"
+	/* tie r0.id == r1.id */
+	"r1 = r0;"
+	/* the jump below would be predicted, thus r1 would be marked precise,
+	 * this should not imply precision mark for r0
+	 */
+	"if r1 > 256 goto +0;"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+/* Verify that check_ids() is used by regsafe() for scalars.
+ *
+ * r9 = ... some pointer with range X ...
+ * r6 = ... unbound scalar ID=a ...
+ * r7 = ... unbound scalar ID=b ...
+ * if (r6 > r7) goto +1
+ * r7 = r6
+ * if (r7 > X) goto exit
+ * r9 += r6
+ * ... access memory using r9 ...
+ *
+ * The memory access is safe only if r7 is bounded,
+ * which is true for one branch and not true for another.
+ */
+SEC("socket")
+__failure __msg("register with unbounded min value")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void check_ids_in_regsafe(void)
+{
+	asm volatile (
+	/* Bump allocated stack */
+	"r1 = 0;"
+	"*(u64*)(r10 - 8) = r1;"
+	/* r9 = pointer to stack */
+	"r9 = r10;"
+	"r9 += -8;"
+	/* r7 = ktime_get_ns() */
+	"call %[bpf_ktime_get_ns];"
+	"r7 = r0;"
+	/* r6 = ktime_get_ns() */
+	"call %[bpf_ktime_get_ns];"
+	"r6 = r0;"
+	/* if r6 > r7 is an unpredictable jump */
+	"if r6 > r7 goto l1_%=;"
+	"r7 = r6;"
+"l1_%=:"
+	/* if r7 > 4 ...; transfers range to r6 on one execution path
+	 * but does not transfer on another
+	 */
+	"if r7 > 4 goto l2_%=;"
+	/* Access memory at r9[r6], r6 is not always bounded */
+	"r9 += r6;"
+	"r0 = *(u8*)(r9 + 0);"
+"l2_%=:"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+/* Similar to check_ids_in_regsafe.
+ * The l0 could be reached in two states:
+ *
+ *   (1) r6{.id=A}, r7{.id=A}, r8{.id=B}
+ *   (2) r6{.id=B}, r7{.id=A}, r8{.id=B}
+ *
+ * Where (2) is not safe, as "r7 > 4" check won't propagate range for it.
+ * This example would be considered safe without changes to
+ * mark_chain_precision() to track scalar values with equal IDs.
+ */
+SEC("socket")
+__failure __msg("register with unbounded min value")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void check_ids_in_regsafe_2(void)
+{
+	asm volatile (
+	/* Bump allocated stack */
+	"r1 = 0;"
+	"*(u64*)(r10 - 8) = r1;"
+	/* r9 = pointer to stack */
+	"r9 = r10;"
+	"r9 += -8;"
+	/* r8 = ktime_get_ns() */
+	"call %[bpf_ktime_get_ns];"
+	"r8 = r0;"
+	/* r7 = ktime_get_ns() */
+	"call %[bpf_ktime_get_ns];"
+	"r7 = r0;"
+	/* r6 = ktime_get_ns() */
+	"call %[bpf_ktime_get_ns];"
+	"r6 = r0;"
+	/* scratch .id from r0 */
+	"r0 = 0;"
+	/* if r6 > r7 is an unpredictable jump */
+	"if r6 > r7 goto l1_%=;"
+	/* tie r6 and r7 .id */
+	"r6 = r7;"
+"l0_%=:"
+	/* if r7 > 4 exit(0) */
+	"if r7 > 4 goto l2_%=;"
+	/* Access memory at r9[r6] */
+	"r9 += r6;"
+	"r0 = *(u8*)(r9 + 0);"
+"l2_%=:"
+	"r0 = 0;"
+	"exit;"
+"l1_%=:"
+	/* tie r6 and r8 .id */
+	"r6 = r8;"
+	"goto l0_%=;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+/* Check that scalar IDs *are not* generated on register to register
+ * assignments if source register is a constant.
+ *
+ * If such IDs *are* generated the 'l1' below would be reached in
+ * two states:
+ *
+ *   (1) r1{.id=A}, r2{.id=A}
+ *   (2) r1{.id=C}, r2{.id=C}
+ *
+ * Thus forcing 'if r1 == r2' verification twice.
+ */
+SEC("socket")
+__success __log_level(2)
+__msg("11: (1d) if r3 == r4 goto pc+0")
+__msg("frame 0: propagating r3,r4")
+__msg("11: safe")
+__msg("processed 15 insns")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void no_scalar_id_for_const(void)
+{
+	asm volatile (
+	"call %[bpf_ktime_get_ns];"
+	/* unpredictable jump */
+	"if r0 > 7 goto l0_%=;"
+	/* possibly generate same scalar ids for r3 and r4 */
+	"r1 = 0;"
+	"r1 = r1;"
+	"r3 = r1;"
+	"r4 = r1;"
+	"goto l1_%=;"
+"l0_%=:"
+	/* possibly generate different scalar ids for r3 and r4 */
+	"r1 = 0;"
+	"r2 = 0;"
+	"r3 = r1;"
+	"r4 = r2;"
+"l1_%=:"
+	/* predictable jump, marks r3 and r4 precise */
+	"if r3 == r4 goto +0;"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+/* Same as no_scalar_id_for_const() but for 32-bit values */
+SEC("socket")
+__success __log_level(2)
+__msg("11: (1e) if w3 == w4 goto pc+0")
+__msg("frame 0: propagating r3,r4")
+__msg("11: safe")
+__msg("processed 15 insns")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void no_scalar_id_for_const32(void)
+{
+	asm volatile (
+	"call %[bpf_ktime_get_ns];"
+	/* unpredictable jump */
+	"if r0 > 7 goto l0_%=;"
+	/* possibly generate same scalar ids for r3 and r4 */
+	"w1 = 0;"
+	"w1 = w1;"
+	"w3 = w1;"
+	"w4 = w1;"
+	"goto l1_%=;"
+"l0_%=:"
+	/* possibly generate different scalar ids for r3 and r4 */
+	"w1 = 0;"
+	"w2 = 0;"
+	"w3 = w1;"
+	"w4 = w2;"
+"l1_%=:"
+	/* predictable jump, marks r1 and r2 precise */
+	"if w3 == w4 goto +0;"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+/* Check that unique scalar IDs are ignored when new verifier state is
+ * compared to cached verifier state. For this test:
+ * - cached state has no id on r1
+ * - new state has a unique id on r1
+ */
+SEC("socket")
+__success __log_level(2)
+__msg("6: (25) if r6 > 0x7 goto pc+1")
+__msg("7: (57) r1 &= 255")
+__msg("8: (bf) r2 = r10")
+__msg("from 6 to 8: safe")
+__msg("processed 12 insns")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void ignore_unique_scalar_ids_cur(void)
+{
+	asm volatile (
+	"call %[bpf_ktime_get_ns];"
+	"r6 = r0;"
+	"call %[bpf_ktime_get_ns];"
+	"r0 &= 0xff;"
+	/* r1.id == r0.id */
+	"r1 = r0;"
+	/* make r1.id unique */
+	"r0 = 0;"
+	"if r6 > 7 goto l0_%=;"
+	/* clear r1 id, but keep the range compatible */
+	"r1 &= 0xff;"
+"l0_%=:"
+	/* get here in two states:
+	 * - first: r1 has no id (cached state)
+	 * - second: r1 has a unique id (should be considered equivalent)
+	 */
+	"r2 = r10;"
+	"r2 += r1;"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+/* Check that unique scalar IDs are ignored when new verifier state is
+ * compared to cached verifier state. For this test:
+ * - cached state has a unique id on r1
+ * - new state has no id on r1
+ */
+SEC("socket")
+__success __log_level(2)
+__msg("6: (25) if r6 > 0x7 goto pc+1")
+__msg("7: (05) goto pc+1")
+__msg("9: (bf) r2 = r10")
+__msg("9: safe")
+__msg("processed 13 insns")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void ignore_unique_scalar_ids_old(void)
+{
+	asm volatile (
+	"call %[bpf_ktime_get_ns];"
+	"r6 = r0;"
+	"call %[bpf_ktime_get_ns];"
+	"r0 &= 0xff;"
+	/* r1.id == r0.id */
+	"r1 = r0;"
+	/* make r1.id unique */
+	"r0 = 0;"
+	"if r6 > 7 goto l1_%=;"
+	"goto l0_%=;"
+"l1_%=:"
+	/* clear r1 id, but keep the range compatible */
+	"r1 &= 0xff;"
+"l0_%=:"
+	/* get here in two states:
+	 * - first: r1 has a unique id (cached state)
+	 * - second: r1 has no id (should be considered equivalent)
+	 */
+	"r2 = r10;"
+	"r2 += r1;"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+/* Check that two different scalar IDs in a verified state can't be
+ * mapped to the same scalar ID in current state.
+ */
+SEC("socket")
+__success __log_level(2)
+/* The exit instruction should be reachable from two states,
+ * use two matches and "processed .. insns" to ensure this.
+ */
+__msg("13: (95) exit")
+__msg("13: (95) exit")
+__msg("processed 18 insns")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void two_old_ids_one_cur_id(void)
+{
+	asm volatile (
+	/* Give unique scalar IDs to r{6,7} */
+	"call %[bpf_ktime_get_ns];"
+	"r0 &= 0xff;"
+	"r6 = r0;"
+	"call %[bpf_ktime_get_ns];"
+	"r0 &= 0xff;"
+	"r7 = r0;"
+	"r0 = 0;"
+	/* Maybe make r{6,7} IDs identical */
+	"if r6 > r7 goto l0_%=;"
+	"goto l1_%=;"
+"l0_%=:"
+	"r6 = r7;"
+"l1_%=:"
+	/* Mark r{6,7} precise.
+	 * Get here in two states:
+	 * - first:  r6{.id=A}, r7{.id=B} (cached state)
+	 * - second: r6{.id=A}, r7{.id=A}
+	 * Currently we don't want to consider such states equivalent.
+	 * Thus "exit;" would be verified twice.
+	 */
+	"r2 = r10;"
+	"r2 += r6;"
+	"r2 += r7;"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+/* Note the flag, see verifier.c:opt_subreg_zext_lo32_rnd_hi32() */
+__flag(BPF_F_TEST_RND_HI32)
+__success
+/* This test was added because of a bug in verifier.c:sync_linked_regs(),
+ * upon range propagation it destroyed subreg_def marks for registers.
+ * The subreg_def mark is used to decide whether zero extension instructions
+ * are needed when register is read. When BPF_F_TEST_RND_HI32 is set it
+ * also causes generation of statements to randomize upper halves of
+ * read registers.
+ *
+ * The test is written in a way to return an upper half of a register
+ * that is affected by range propagation and must have it's subreg_def
+ * preserved. This gives a return value of 0 and leads to undefined
+ * return value if subreg_def mark is not preserved.
+ */
+__retval(0)
+/* Check that verifier believes r1/r0 are zero at exit */
+__log_level(2)
+__msg("4: (77) r1 >>= 32                     ; R1=0")
+__msg("5: (bf) r0 = r1                       ; R0=0 R1=0")
+__msg("6: (95) exit")
+__msg("from 3 to 4")
+__msg("4: (77) r1 >>= 32                     ; R1=0")
+__msg("5: (bf) r0 = r1                       ; R0=0 R1=0")
+__msg("6: (95) exit")
+/* Verify that statements to randomize upper half of r1 had not been
+ * generated.
+ */
+__xlated("call unknown")
+__xlated("r0 &= 2147483647")
+__xlated("w1 = w0")
+/* This is how disasm.c prints BPF_ZEXT_REG at the moment, x86 and arm
+ * are the only CI archs that do not need zero extension for subregs.
+ */
+#if !defined(__TARGET_ARCH_x86) && !defined(__TARGET_ARCH_arm64)
+__xlated("w1 = w1")
+#endif
+__xlated("if w0 < 0xa goto pc+0")
+__xlated("r1 >>= 32")
+__xlated("r0 = r1")
+__xlated("exit")
+__naked void linked_regs_and_subreg_def(void)
+{
+	asm volatile (
+	"call %[bpf_ktime_get_ns];"
+	/* make sure r0 is in 32-bit range, otherwise w1 = w0 won't
+	 * assign same IDs to registers.
+	 */
+	"r0 &= 0x7fffffff;"
+	/* link w1 and w0 via ID */
+	"w1 = w0;"
+	/* 'if' statement propagates range info from w0 to w1,
+	 * but should not affect w1->subreg_def property.
+	 */
+	"if w0 < 10 goto +0;"
+	/* r1 is read here, on archs that require subreg zero
+	 * extension this would cause zext patch generation.
+	 */
+	"r1 >>= 32;"
+	"r0 = r1;"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_sdiv.c b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
new file mode 100644
index 000000000000..148d2299e5b4
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_sdiv.c
@@ -0,0 +1,1224 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <limits.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+	(defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
+	defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390) || \
+	defined(__TARGET_ARCH_loongarch)) && \
+	__clang_major__ >= 18
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 1")
+__success __success_unpriv __retval(-20)
+__naked void sdiv32_non_zero_imm_1(void)
+{
+	asm volatile ("					\
+	w0 = -41;					\
+	w0 s/= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 2")
+__success __success_unpriv __retval(-20)
+__naked void sdiv32_non_zero_imm_2(void)
+{
+	asm volatile ("					\
+	w0 = 41;					\
+	w0 s/= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 3")
+__success __success_unpriv __retval(20)
+__naked void sdiv32_non_zero_imm_3(void)
+{
+	asm volatile ("					\
+	w0 = -41;					\
+	w0 s/= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 4")
+__success __success_unpriv __retval(-21)
+__naked void sdiv32_non_zero_imm_4(void)
+{
+	asm volatile ("					\
+	w0 = -42;					\
+	w0 s/= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 5")
+__success __success_unpriv __retval(-21)
+__naked void sdiv32_non_zero_imm_5(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w0 s/= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 6")
+__success __success_unpriv __retval(21)
+__naked void sdiv32_non_zero_imm_6(void)
+{
+	asm volatile ("					\
+	w0 = -42;					\
+	w0 s/= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 7")
+__success __success_unpriv __retval(21)
+__naked void sdiv32_non_zero_imm_7(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w0 s/= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero imm divisor, check 8")
+__success __success_unpriv __retval(20)
+__naked void sdiv32_non_zero_imm_8(void)
+{
+	asm volatile ("					\
+	w0 = 41;					\
+	w0 s/= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 1")
+__success __success_unpriv __retval(-20)
+__naked void sdiv32_non_zero_reg_1(void)
+{
+	asm volatile ("					\
+	w0 = -41;					\
+	w1 = 2;						\
+	w0 s/= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 2")
+__success __success_unpriv __retval(-20)
+__naked void sdiv32_non_zero_reg_2(void)
+{
+	asm volatile ("					\
+	w0 = 41;					\
+	w1 = -2;					\
+	w0 s/= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 3")
+__success __success_unpriv __retval(20)
+__naked void sdiv32_non_zero_reg_3(void)
+{
+	asm volatile ("					\
+	w0 = -41;					\
+	w1 = -2;					\
+	w0 s/= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 4")
+__success __success_unpriv __retval(-21)
+__naked void sdiv32_non_zero_reg_4(void)
+{
+	asm volatile ("					\
+	w0 = -42;					\
+	w1 = 2;						\
+	w0 s/= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 5")
+__success __success_unpriv __retval(-21)
+__naked void sdiv32_non_zero_reg_5(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w1 = -2;					\
+	w0 s/= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 6")
+__success __success_unpriv __retval(21)
+__naked void sdiv32_non_zero_reg_6(void)
+{
+	asm volatile ("					\
+	w0 = -42;					\
+	w1 = -2;					\
+	w0 s/= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 7")
+__success __success_unpriv __retval(21)
+__naked void sdiv32_non_zero_reg_7(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w1 = 2;						\
+	w0 s/= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, non-zero reg divisor, check 8")
+__success __success_unpriv __retval(20)
+__naked void sdiv32_non_zero_reg_8(void)
+{
+	asm volatile ("					\
+	w0 = 41;					\
+	w1 = 2;						\
+	w0 s/= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero imm divisor, check 1")
+__success __success_unpriv __retval(-20)
+__naked void sdiv64_non_zero_imm_1(void)
+{
+	asm volatile ("					\
+	r0 = -41;					\
+	r0 s/= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero imm divisor, check 2")
+__success __success_unpriv __retval(-20)
+__naked void sdiv64_non_zero_imm_2(void)
+{
+	asm volatile ("					\
+	r0 = 41;					\
+	r0 s/= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero imm divisor, check 3")
+__success __success_unpriv __retval(20)
+__naked void sdiv64_non_zero_imm_3(void)
+{
+	asm volatile ("					\
+	r0 = -41;					\
+	r0 s/= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero imm divisor, check 4")
+__success __success_unpriv __retval(-21)
+__naked void sdiv64_non_zero_imm_4(void)
+{
+	asm volatile ("					\
+	r0 = -42;					\
+	r0 s/= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero imm divisor, check 5")
+__success __success_unpriv __retval(-21)
+__naked void sdiv64_non_zero_imm_5(void)
+{
+	asm volatile ("					\
+	r0 = 42;					\
+	r0 s/= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero imm divisor, check 6")
+__success __success_unpriv __retval(21)
+__naked void sdiv64_non_zero_imm_6(void)
+{
+	asm volatile ("					\
+	r0 = -42;					\
+	r0 s/= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero reg divisor, check 1")
+__success __success_unpriv __retval(-20)
+__naked void sdiv64_non_zero_reg_1(void)
+{
+	asm volatile ("					\
+	r0 = -41;					\
+	r1 = 2;						\
+	r0 s/= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero reg divisor, check 2")
+__success __success_unpriv __retval(-20)
+__naked void sdiv64_non_zero_reg_2(void)
+{
+	asm volatile ("					\
+	r0 = 41;					\
+	r1 = -2;					\
+	r0 s/= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero reg divisor, check 3")
+__success __success_unpriv __retval(20)
+__naked void sdiv64_non_zero_reg_3(void)
+{
+	asm volatile ("					\
+	r0 = -41;					\
+	r1 = -2;					\
+	r0 s/= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero reg divisor, check 4")
+__success __success_unpriv __retval(-21)
+__naked void sdiv64_non_zero_reg_4(void)
+{
+	asm volatile ("					\
+	r0 = -42;					\
+	r1 = 2;						\
+	r0 s/= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero reg divisor, check 5")
+__success __success_unpriv __retval(-21)
+__naked void sdiv64_non_zero_reg_5(void)
+{
+	asm volatile ("					\
+	r0 = 42;					\
+	r1 = -2;					\
+	r0 s/= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, non-zero reg divisor, check 6")
+__success __success_unpriv __retval(21)
+__naked void sdiv64_non_zero_reg_6(void)
+{
+	asm volatile ("					\
+	r0 = -42;					\
+	r1 = -2;					\
+	r0 s/= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero imm divisor, check 1")
+__success __success_unpriv __retval(-1)
+__naked void smod32_non_zero_imm_1(void)
+{
+	asm volatile ("					\
+	w0 = -41;					\
+	w0 s%%= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero imm divisor, check 2")
+__success __success_unpriv __retval(1)
+__naked void smod32_non_zero_imm_2(void)
+{
+	asm volatile ("					\
+	w0 = 41;					\
+	w0 s%%= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero imm divisor, check 3")
+__success __success_unpriv __retval(-1)
+__naked void smod32_non_zero_imm_3(void)
+{
+	asm volatile ("					\
+	w0 = -41;					\
+	w0 s%%= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero imm divisor, check 4")
+__success __success_unpriv __retval(0)
+__naked void smod32_non_zero_imm_4(void)
+{
+	asm volatile ("					\
+	w0 = -42;					\
+	w0 s%%= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero imm divisor, check 5")
+__success __success_unpriv __retval(0)
+__naked void smod32_non_zero_imm_5(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w0 s%%= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero imm divisor, check 6")
+__success __success_unpriv __retval(0)
+__naked void smod32_non_zero_imm_6(void)
+{
+	asm volatile ("					\
+	w0 = -42;					\
+	w0 s%%= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero reg divisor, check 1")
+__success __success_unpriv __retval(-1)
+__naked void smod32_non_zero_reg_1(void)
+{
+	asm volatile ("					\
+	w0 = -41;					\
+	w1 = 2;						\
+	w0 s%%= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero reg divisor, check 2")
+__success __success_unpriv __retval(1)
+__naked void smod32_non_zero_reg_2(void)
+{
+	asm volatile ("					\
+	w0 = 41;					\
+	w1 = -2;					\
+	w0 s%%= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero reg divisor, check 3")
+__success __success_unpriv __retval(-1)
+__naked void smod32_non_zero_reg_3(void)
+{
+	asm volatile ("					\
+	w0 = -41;					\
+	w1 = -2;					\
+	w0 s%%= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero reg divisor, check 4")
+__success __success_unpriv __retval(0)
+__naked void smod32_non_zero_reg_4(void)
+{
+	asm volatile ("					\
+	w0 = -42;					\
+	w1 = 2;						\
+	w0 s%%= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero reg divisor, check 5")
+__success __success_unpriv __retval(0)
+__naked void smod32_non_zero_reg_5(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w1 = -2;					\
+	w0 s%%= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, non-zero reg divisor, check 6")
+__success __success_unpriv __retval(0)
+__naked void smod32_non_zero_reg_6(void)
+{
+	asm volatile ("					\
+	w0 = -42;					\
+	w1 = -2;					\
+	w0 s%%= w1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 1")
+__success __success_unpriv __retval(-1)
+__naked void smod64_non_zero_imm_1(void)
+{
+	asm volatile ("					\
+	r0 = -41;					\
+	r0 s%%= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 2")
+__success __success_unpriv __retval(1)
+__naked void smod64_non_zero_imm_2(void)
+{
+	asm volatile ("					\
+	r0 = 41;					\
+	r0 s%%= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 3")
+__success __success_unpriv __retval(-1)
+__naked void smod64_non_zero_imm_3(void)
+{
+	asm volatile ("					\
+	r0 = -41;					\
+	r0 s%%= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 4")
+__success __success_unpriv __retval(0)
+__naked void smod64_non_zero_imm_4(void)
+{
+	asm volatile ("					\
+	r0 = -42;					\
+	r0 s%%= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 5")
+__success __success_unpriv __retval(-0)
+__naked void smod64_non_zero_imm_5(void)
+{
+	asm volatile ("					\
+	r0 = 42;					\
+	r0 s%%= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 6")
+__success __success_unpriv __retval(0)
+__naked void smod64_non_zero_imm_6(void)
+{
+	asm volatile ("					\
+	r0 = -42;					\
+	r0 s%%= -2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 7")
+__success __success_unpriv __retval(0)
+__naked void smod64_non_zero_imm_7(void)
+{
+	asm volatile ("					\
+	r0 = 42;					\
+	r0 s%%= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero imm divisor, check 8")
+__success __success_unpriv __retval(1)
+__naked void smod64_non_zero_imm_8(void)
+{
+	asm volatile ("					\
+	r0 = 41;					\
+	r0 s%%= 2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 1")
+__success __success_unpriv __retval(-1)
+__naked void smod64_non_zero_reg_1(void)
+{
+	asm volatile ("					\
+	r0 = -41;					\
+	r1 = 2;						\
+	r0 s%%= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 2")
+__success __success_unpriv __retval(1)
+__naked void smod64_non_zero_reg_2(void)
+{
+	asm volatile ("					\
+	r0 = 41;					\
+	r1 = -2;					\
+	r0 s%%= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 3")
+__success __success_unpriv __retval(-1)
+__naked void smod64_non_zero_reg_3(void)
+{
+	asm volatile ("					\
+	r0 = -41;					\
+	r1 = -2;					\
+	r0 s%%= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 4")
+__success __success_unpriv __retval(0)
+__naked void smod64_non_zero_reg_4(void)
+{
+	asm volatile ("					\
+	r0 = -42;					\
+	r1 = 2;						\
+	r0 s%%= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 5")
+__success __success_unpriv __retval(0)
+__naked void smod64_non_zero_reg_5(void)
+{
+	asm volatile ("					\
+	r0 = 42;					\
+	r1 = -2;					\
+	r0 s%%= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 6")
+__success __success_unpriv __retval(0)
+__naked void smod64_non_zero_reg_6(void)
+{
+	asm volatile ("					\
+	r0 = -42;					\
+	r1 = -2;					\
+	r0 s%%= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 7")
+__success __success_unpriv __retval(0)
+__naked void smod64_non_zero_reg_7(void)
+{
+	asm volatile ("					\
+	r0 = 42;					\
+	r1 = 2;						\
+	r0 s%%= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, non-zero reg divisor, check 8")
+__success __success_unpriv __retval(1)
+__naked void smod64_non_zero_reg_8(void)
+{
+	asm volatile ("					\
+	r0 = 41;					\
+	r1 = 2;						\
+	r0 s%%= r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, zero divisor")
+__success __success_unpriv __retval(0)
+__naked void sdiv32_zero_divisor(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w1 = 0;						\
+	w2 = -1;					\
+	w2 s/= w1;					\
+	w0 = w2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, zero divisor")
+__success __success_unpriv __retval(0)
+__naked void sdiv64_zero_divisor(void)
+{
+	asm volatile ("					\
+	r0 = 42;					\
+	r1 = 0;						\
+	r2 = -1;					\
+	r2 s/= r1;					\
+	r0 = r2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, zero divisor")
+__success __success_unpriv __retval(-1)
+__naked void smod32_zero_divisor(void)
+{
+	asm volatile ("					\
+	w0 = 42;					\
+	w1 = 0;						\
+	w2 = -1;					\
+	w2 s%%= w1;					\
+	w0 = w2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, zero divisor")
+__success __success_unpriv __retval(-1)
+__naked void smod64_zero_divisor(void)
+{
+	asm volatile ("					\
+	r0 = 42;					\
+	r1 = 0;						\
+	r2 = -1;					\
+	r2 s%%= r1;					\
+	r0 = r2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, overflow r/r, LLONG_MIN/-1")
+__success __retval(1)
+__arch_x86_64
+__xlated("0: r2 = 0x8000000000000000")
+__xlated("2: r3 = -1")
+__xlated("3: r4 = r2")
+__xlated("4: r11 = r3")
+__xlated("5: r11 += 1")
+__xlated("6: if r11 > 0x1 goto pc+4")
+__xlated("7: if r11 == 0x0 goto pc+1")
+__xlated("8: r2 = 0")
+__xlated("9: r2 = -r2")
+__xlated("10: goto pc+1")
+__xlated("11: r2 s/= r3")
+__xlated("12: r0 = 0")
+__xlated("13: if r2 != r4 goto pc+1")
+__xlated("14: r0 = 1")
+__xlated("15: exit")
+__naked void sdiv64_overflow_rr(void)
+{
+	asm volatile ("					\
+	r2 = %[llong_min] ll;				\
+	r3 = -1;					\
+	r4 = r2;					\
+	r2 s/= r3;					\
+	r0 = 0;						\
+	if r2 != r4 goto +1;				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm_const(llong_min, LLONG_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, r/r, small_val/-1")
+__success __retval(-5)
+__arch_x86_64
+__xlated("0: r2 = 5")
+__xlated("1: r3 = -1")
+__xlated("2: r11 = r3")
+__xlated("3: r11 += 1")
+__xlated("4: if r11 > 0x1 goto pc+4")
+__xlated("5: if r11 == 0x0 goto pc+1")
+__xlated("6: r2 = 0")
+__xlated("7: r2 = -r2")
+__xlated("8: goto pc+1")
+__xlated("9: r2 s/= r3")
+__xlated("10: r0 = r2")
+__xlated("11: exit")
+__naked void sdiv64_rr_divisor_neg_1(void)
+{
+	asm volatile ("					\
+	r2 = 5;						\
+	r3 = -1;					\
+	r2 s/= r3;					\
+	r0 = r2;					\
+	exit;						\
+"	:
+	:
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, overflow r/i, LLONG_MIN/-1")
+__success __retval(1)
+__arch_x86_64
+__xlated("0: r2 = 0x8000000000000000")
+__xlated("2: r4 = r2")
+__xlated("3: r2 = -r2")
+__xlated("4: r0 = 0")
+__xlated("5: if r2 != r4 goto pc+1")
+__xlated("6: r0 = 1")
+__xlated("7: exit")
+__naked void sdiv64_overflow_ri(void)
+{
+	asm volatile ("					\
+	r2 = %[llong_min] ll;				\
+	r4 = r2;					\
+	r2 s/= -1;					\
+	r0 = 0;						\
+	if r2 != r4 goto +1;				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm_const(llong_min, LLONG_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV64, r/i, small_val/-1")
+__success __retval(-5)
+__arch_x86_64
+__xlated("0: r2 = 5")
+__xlated("1: r4 = r2")
+__xlated("2: r2 = -r2")
+__xlated("3: r0 = r2")
+__xlated("4: exit")
+__naked void sdiv64_ri_divisor_neg_1(void)
+{
+	asm volatile ("					\
+	r2 = 5;						\
+	r4 = r2;					\
+	r2 s/= -1;					\
+	r0 = r2;					\
+	exit;						\
+"	:
+	:
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, overflow r/r, INT_MIN/-1")
+__success __retval(1)
+__arch_x86_64
+__xlated("0: w2 = -2147483648")
+__xlated("1: w3 = -1")
+__xlated("2: w4 = w2")
+__xlated("3: r11 = r3")
+__xlated("4: w11 += 1")
+__xlated("5: if w11 > 0x1 goto pc+4")
+__xlated("6: if w11 == 0x0 goto pc+1")
+__xlated("7: w2 = 0")
+__xlated("8: w2 = -w2")
+__xlated("9: goto pc+1")
+__xlated("10: w2 s/= w3")
+__xlated("11: r0 = 0")
+__xlated("12: if w2 != w4 goto pc+1")
+__xlated("13: r0 = 1")
+__xlated("14: exit")
+__naked void sdiv32_overflow_rr(void)
+{
+	asm volatile ("					\
+	w2 = %[int_min];				\
+	w3 = -1;					\
+	w4 = w2;					\
+	w2 s/= w3;					\
+	r0 = 0;						\
+	if w2 != w4 goto +1;				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm_const(int_min, INT_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, r/r, small_val/-1")
+__success __retval(5)
+__arch_x86_64
+__xlated("0: w2 = -5")
+__xlated("1: w3 = -1")
+__xlated("2: w4 = w2")
+__xlated("3: r11 = r3")
+__xlated("4: w11 += 1")
+__xlated("5: if w11 > 0x1 goto pc+4")
+__xlated("6: if w11 == 0x0 goto pc+1")
+__xlated("7: w2 = 0")
+__xlated("8: w2 = -w2")
+__xlated("9: goto pc+1")
+__xlated("10: w2 s/= w3")
+__xlated("11: w0 = w2")
+__xlated("12: exit")
+__naked void sdiv32_rr_divisor_neg_1(void)
+{
+	asm volatile ("					\
+	w2 = -5;					\
+	w3 = -1;					\
+	w4 = w2;					\
+	w2 s/= w3;					\
+	w0 = w2;					\
+	exit;						\
+"	:
+	:
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, overflow r/i, INT_MIN/-1")
+__success __retval(1)
+__arch_x86_64
+__xlated("0: w2 = -2147483648")
+__xlated("1: w4 = w2")
+__xlated("2: w2 = -w2")
+__xlated("3: r0 = 0")
+__xlated("4: if w2 != w4 goto pc+1")
+__xlated("5: r0 = 1")
+__xlated("6: exit")
+__naked void sdiv32_overflow_ri(void)
+{
+	asm volatile ("					\
+	w2 = %[int_min];				\
+	w4 = w2;					\
+	w2 s/= -1;					\
+	r0 = 0;						\
+	if w2 != w4 goto +1;				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm_const(int_min, INT_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SDIV32, r/i, small_val/-1")
+__success __retval(-5)
+__arch_x86_64
+__xlated("0: w2 = 5")
+__xlated("1: w4 = w2")
+__xlated("2: w2 = -w2")
+__xlated("3: w0 = w2")
+__xlated("4: exit")
+__naked void sdiv32_ri_divisor_neg_1(void)
+{
+	asm volatile ("					\
+	w2 = 5;						\
+	w4 = w2;					\
+	w2 s/= -1;					\
+	w0 = w2;					\
+	exit;						\
+"	:
+	:
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, overflow r/r, LLONG_MIN/-1")
+__success __retval(0)
+__arch_x86_64
+__xlated("0: r2 = 0x8000000000000000")
+__xlated("2: r3 = -1")
+__xlated("3: r4 = r2")
+__xlated("4: r11 = r3")
+__xlated("5: r11 += 1")
+__xlated("6: if r11 > 0x1 goto pc+3")
+__xlated("7: if r11 == 0x1 goto pc+3")
+__xlated("8: w2 = 0")
+__xlated("9: goto pc+1")
+__xlated("10: r2 s%= r3")
+__xlated("11: r0 = r2")
+__xlated("12: exit")
+__naked void smod64_overflow_rr(void)
+{
+	asm volatile ("					\
+	r2 = %[llong_min] ll;				\
+	r3 = -1;					\
+	r4 = r2;					\
+	r2 s%%= r3;					\
+	r0 = r2;					\
+	exit;						\
+"	:
+	: __imm_const(llong_min, LLONG_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, r/r, small_val/-1")
+__success __retval(0)
+__arch_x86_64
+__xlated("0: r2 = 5")
+__xlated("1: r3 = -1")
+__xlated("2: r4 = r2")
+__xlated("3: r11 = r3")
+__xlated("4: r11 += 1")
+__xlated("5: if r11 > 0x1 goto pc+3")
+__xlated("6: if r11 == 0x1 goto pc+3")
+__xlated("7: w2 = 0")
+__xlated("8: goto pc+1")
+__xlated("9: r2 s%= r3")
+__xlated("10: r0 = r2")
+__xlated("11: exit")
+__naked void smod64_rr_divisor_neg_1(void)
+{
+	asm volatile ("					\
+	r2 = 5;						\
+	r3 = -1;					\
+	r4 = r2;					\
+	r2 s%%= r3;					\
+	r0 = r2;					\
+	exit;						\
+"	:
+	:
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, overflow r/i, LLONG_MIN/-1")
+__success __retval(0)
+__arch_x86_64
+__xlated("0: r2 = 0x8000000000000000")
+__xlated("2: r4 = r2")
+__xlated("3: w2 = 0")
+__xlated("4: r0 = r2")
+__xlated("5: exit")
+__naked void smod64_overflow_ri(void)
+{
+	asm volatile ("					\
+	r2 = %[llong_min] ll;				\
+	r4 = r2;					\
+	r2 s%%= -1;					\
+	r0 = r2;					\
+	exit;						\
+"	:
+	: __imm_const(llong_min, LLONG_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD64, r/i, small_val/-1")
+__success __retval(0)
+__arch_x86_64
+__xlated("0: r2 = 5")
+__xlated("1: r4 = r2")
+__xlated("2: w2 = 0")
+__xlated("3: r0 = r2")
+__xlated("4: exit")
+__naked void smod64_ri_divisor_neg_1(void)
+{
+	asm volatile ("					\
+	r2 = 5;						\
+	r4 = r2;					\
+	r2 s%%= -1;					\
+	r0 = r2;					\
+	exit;						\
+"	:
+	:
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, overflow r/r, INT_MIN/-1")
+__success __retval(0)
+__arch_x86_64
+__xlated("0: w2 = -2147483648")
+__xlated("1: w3 = -1")
+__xlated("2: w4 = w2")
+__xlated("3: r11 = r3")
+__xlated("4: w11 += 1")
+__xlated("5: if w11 > 0x1 goto pc+3")
+__xlated("6: if w11 == 0x1 goto pc+4")
+__xlated("7: w2 = 0")
+__xlated("8: goto pc+1")
+__xlated("9: w2 s%= w3")
+__xlated("10: goto pc+1")
+__xlated("11: w2 = w2")
+__xlated("12: r0 = r2")
+__xlated("13: exit")
+__naked void smod32_overflow_rr(void)
+{
+	asm volatile ("					\
+	w2 = %[int_min];				\
+	w3 = -1;					\
+	w4 = w2;					\
+	w2 s%%= w3;					\
+	r0 = r2;					\
+	exit;						\
+"	:
+	: __imm_const(int_min, INT_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, r/r, small_val/-1")
+__success __retval(0)
+__arch_x86_64
+__xlated("0: w2 = -5")
+__xlated("1: w3 = -1")
+__xlated("2: w4 = w2")
+__xlated("3: r11 = r3")
+__xlated("4: w11 += 1")
+__xlated("5: if w11 > 0x1 goto pc+3")
+__xlated("6: if w11 == 0x1 goto pc+4")
+__xlated("7: w2 = 0")
+__xlated("8: goto pc+1")
+__xlated("9: w2 s%= w3")
+__xlated("10: goto pc+1")
+__xlated("11: w2 = w2")
+__xlated("12: r0 = r2")
+__xlated("13: exit")
+__naked void smod32_rr_divisor_neg_1(void)
+{
+	asm volatile ("					\
+	w2 = -5;				\
+	w3 = -1;					\
+	w4 = w2;					\
+	w2 s%%= w3;					\
+	r0 = r2;					\
+	exit;						\
+"	:
+	:
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, overflow r/i, INT_MIN/-1")
+__success __retval(0)
+__arch_x86_64
+__xlated("0: w2 = -2147483648")
+__xlated("1: w4 = w2")
+__xlated("2: w2 = 0")
+__xlated("3: r0 = r2")
+__xlated("4: exit")
+__naked void smod32_overflow_ri(void)
+{
+	asm volatile ("					\
+	w2 = %[int_min];				\
+	w4 = w2;					\
+	w2 s%%= -1;					\
+	r0 = r2;					\
+	exit;						\
+"	:
+	: __imm_const(int_min, INT_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("SMOD32, r/i, small_val/-1")
+__success __retval(0)
+__arch_x86_64
+__xlated("0: w2 = 5")
+__xlated("1: w4 = w2")
+__xlated("2: w2 = 0")
+__xlated("3: w0 = w2")
+__xlated("4: exit")
+__naked void smod32_ri_divisor_neg_1(void)
+{
+	asm volatile ("					\
+	w2 = 5;						\
+	w4 = w2;					\
+	w2 s%%= -1;					\
+	w0 = w2;					\
+	exit;						\
+"	:
+	:
+	: __clobber_all);
+}
+
+#else
+
+SEC("socket")
+__description("cpuv4 is not supported by compiler or jit, use a dummy test")
+__success
+int dummy_test(void)
+{
+	return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_search_pruning.c b/tools/testing/selftests/bpf/progs/verifier_search_pruning.c
new file mode 100644
index 000000000000..f40e57251e94
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_search_pruning.c
@@ -0,0 +1,362 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/search_pruning.c */
+
+#include <linux/bpf.h>
+#include <../../../include/linux/filter.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#define MAX_ENTRIES 11
+
+struct test_val {
+	unsigned int index;
+	int foo[MAX_ENTRIES];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, struct test_val);
+} map_hash_48b SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, long long);
+} map_hash_8b SEC(".maps");
+
+SEC("socket")
+__description("pointer/scalar confusion in state equality check (way 1)")
+__success __failure_unpriv __msg_unpriv("R0 leaks addr as return value")
+__retval(POINTER_VALUE)
+__naked void state_equality_check_way_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r0 = *(u64*)(r0 + 0);				\
+	goto l1_%=;					\
+l0_%=:	r0 = r10;					\
+l1_%=:	goto l2_%=;					\
+l2_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("pointer/scalar confusion in state equality check (way 2)")
+__success __failure_unpriv __msg_unpriv("R0 leaks addr as return value")
+__retval(POINTER_VALUE)
+__naked void state_equality_check_way_2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	r0 = r10;					\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r0 + 0);				\
+l1_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("lwt_in")
+__description("liveness pruning and write screening")
+__failure __msg("R0 !read_ok")
+__naked void liveness_pruning_and_write_screening(void)
+{
+	asm volatile ("					\
+	/* Get an unknown value */			\
+	r2 = *(u32*)(r1 + 0);				\
+	/* branch conditions teach us nothing about R2 */\
+	if r2 >= 0 goto l0_%=;				\
+	r0 = 0;						\
+l0_%=:	if r2 >= 0 goto l1_%=;				\
+	r0 = 0;						\
+l1_%=:	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("varlen_map_value_access pruning")
+__failure __msg("R0 unbounded memory access")
+__failure_unpriv __msg_unpriv("R0 leaks addr")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void varlen_map_value_access_pruning(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u64*)(r0 + 0);				\
+	w2 = %[max_entries];				\
+	if r2 s> r1 goto l1_%=;				\
+	w1 = 0;						\
+l1_%=:	w1 <<= 2;					\
+	r0 += r1;					\
+	goto l2_%=;					\
+l2_%=:	r1 = %[test_val_foo];				\
+	*(u64*)(r0 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(max_entries, MAX_ENTRIES),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("search pruning: all branches should be verified (nop operation)")
+__failure __msg("R6 invalid mem access 'scalar'")
+__naked void should_be_verified_nop_operation(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r3 = *(u64*)(r0 + 0);				\
+	if r3 == 0xbeef goto l1_%=;			\
+	r4 = 0;						\
+	goto l2_%=;					\
+l1_%=:	r4 = 1;						\
+l2_%=:	*(u64*)(r10 - 16) = r4;				\
+	call %[bpf_ktime_get_ns];			\
+	r5 = *(u64*)(r10 - 16);				\
+	if r5 == 0 goto l0_%=;				\
+	r6 = 0;						\
+	r1 = 0xdead;					\
+	*(u64*)(r6 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("search pruning: all branches should be verified (invalid stack access)")
+/* in privileged mode reads from uninitialized stack locations are permitted */
+__success __failure_unpriv
+__msg_unpriv("invalid read from stack off -16+0 size 8")
+__retval(0)
+__naked void be_verified_invalid_stack_access(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r3 = *(u64*)(r0 + 0);				\
+	r4 = 0;						\
+	if r3 == 0xbeef goto l1_%=;			\
+	*(u64*)(r10 - 16) = r4;				\
+	goto l2_%=;					\
+l1_%=:	*(u64*)(r10 - 24) = r4;				\
+l2_%=:	call %[bpf_ktime_get_ns];			\
+	r5 = *(u64*)(r10 - 16);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("precision tracking for u32 spill/fill")
+__failure __msg("R0 min value is outside of the allowed memory range")
+__naked void tracking_for_u32_spill_fill(void)
+{
+	asm volatile ("					\
+	r7 = r1;					\
+	call %[bpf_get_prandom_u32];			\
+	w6 = 32;					\
+	if r0 == 0 goto l0_%=;				\
+	w6 = 4;						\
+l0_%=:	/* Additional insns to introduce a pruning point. */\
+	call %[bpf_get_prandom_u32];			\
+	r3 = 0;						\
+	r3 = 0;						\
+	if r0 == 0 goto l1_%=;				\
+	r3 = 0;						\
+l1_%=:	/* u32 spill/fill */				\
+	*(u32*)(r10 - 8) = r6;				\
+	r8 = *(u32*)(r10 - 8);				\
+	/* out-of-bound map value access for r6=32 */	\
+	r1 = 0;						\
+	*(u64*)(r10 - 16) = r1;				\
+	r2 = r10;					\
+	r2 += -16;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l2_%=;				\
+	r0 += r8;					\
+	r1 = *(u32*)(r0 + 0);				\
+l2_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("precision tracking for u32 spills, u64 fill")
+__failure __msg("div by zero")
+__naked void for_u32_spills_u64_fill(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r6 = r0;					\
+	w7 = 0xffffffff;				\
+	/* Additional insns to introduce a pruning point. */\
+	r3 = 1;						\
+	r3 = 1;						\
+	r3 = 1;						\
+	r3 = 1;						\
+	call %[bpf_get_prandom_u32];			\
+	if r0 == 0 goto l0_%=;				\
+	r3 = 1;						\
+l0_%=:	w3 /= 0;					\
+	/* u32 spills, u64 fill */			\
+	*(u32*)(r10 - 4) = r6;				\
+	*(u32*)(r10 - 8) = r7;				\
+	r8 = *(u64*)(r10 - 8);				\
+	/* if r8 != X goto pc+1  r8 known in fallthrough branch */\
+	if r8 != 0xffffffff goto l1_%=;			\
+	r3 = 1;						\
+l1_%=:	/* if r8 == X goto pc+1  condition always true on first\
+	 * traversal, so starts backtracking to mark r8 as requiring\
+	 * precision. r7 marked as needing precision. r6 not marked\
+	 * since it's not tracked.			\
+	 */						\
+	if r8 == 0xffffffff goto l2_%=;			\
+	/* fails if r8 correctly marked unknown after fill. */\
+	w3 /= 0;					\
+l2_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("allocated_stack")
+__success __msg("processed 15 insns")
+__success_unpriv __msg_unpriv("") __log_level(1) __retval(0)
+__naked void allocated_stack(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	call %[bpf_get_prandom_u32];			\
+	r7 = r0;					\
+	if r0 == 0 goto l0_%=;				\
+	r0 = 0;						\
+	*(u64*)(r10 - 8) = r6;				\
+	r6 = *(u64*)(r10 - 8);				\
+	*(u8*)(r10 - 9) = r7;				\
+	r7 = *(u8*)(r10 - 9);				\
+l0_%=:	if r0 != 0 goto l1_%=;				\
+l1_%=:	if r0 != 0 goto l2_%=;				\
+l2_%=:	if r0 != 0 goto l3_%=;				\
+l3_%=:	if r0 != 0 goto l4_%=;				\
+l4_%=:	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* The test performs a conditional 64-bit write to a stack location
+ * fp[-8], this is followed by an unconditional 8-bit write to fp[-8],
+ * then data is read from fp[-8]. This sequence is unsafe.
+ *
+ * The test would be mistakenly marked as safe w/o dst register parent
+ * preservation in verifier.c:copy_register_state() function.
+ *
+ * Note the usage of BPF_F_TEST_STATE_FREQ to force creation of the
+ * checkpoint state after conditional 64-bit assignment.
+ */
+
+SEC("socket")
+__description("write tracking and register parent chain bug")
+/* in privileged mode reads from uninitialized stack locations are permitted */
+__success __failure_unpriv
+__msg_unpriv("invalid read from stack off -8+1 size 8")
+__retval(0) __flag(BPF_F_TEST_STATE_FREQ)
+__naked void and_register_parent_chain_bug(void)
+{
+	asm volatile ("					\
+	/* r6 = ktime_get_ns() */			\
+	call %[bpf_ktime_get_ns];			\
+	r6 = r0;					\
+	/* r0 = ktime_get_ns() */			\
+	call %[bpf_ktime_get_ns];			\
+	/* if r0 > r6 goto +1 */			\
+	if r0 > r6 goto l0_%=;				\
+	/* *(u64 *)(r10 - 8) = 0xdeadbeef */		\
+	r0 = 0xdeadbeef;				\
+	*(u64*)(r10 - 8) = r0;				\
+l0_%=:	r1 = 42;					\
+	*(u8*)(r10 - 8) = r1;				\
+	r2 = *(u64*)(r10 - 8);				\
+	/* exit(0) */					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+/* Without checkpoint forcibly inserted at the back-edge a loop this
+ * test would take a very long time to verify.
+ */
+SEC("kprobe")
+__failure __log_level(4)
+__msg("BPF program is too large.")
+__naked void short_loop1(void)
+{
+	asm volatile (
+	"   r7 = *(u16 *)(r1 +0);"
+	"1: r7 += 0x1ab064b9;"
+	"   .8byte %[jset];" /* same as 'if r7 & 0x702000 goto 1b;' */
+	"   r7 &= 0x1ee60e;"
+	"   r7 += r1;"
+	"   if r7 s> 0x37d2 goto +0;"
+	"   r0 = 0;"
+	"   exit;"
+	:
+	: __imm_insn(jset, BPF_JMP_IMM(BPF_JSET, BPF_REG_7, 0x702000, -2))
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_sock.c b/tools/testing/selftests/bpf/progs/verifier_sock.c
new file mode 100644
index 000000000000..a2132c72d3b8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_sock.c
@@ -0,0 +1,1169 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/sock.c */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} map_reuseport_array SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKHASH);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} map_sockhash SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} map_sockmap SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_XSKMAP);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} map_xskmap SEC(".maps");
+
+struct val {
+	int cnt;
+	struct bpf_spin_lock l;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(max_entries, 0);
+	__type(key, int);
+	__type(value, struct val);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+} sk_storage_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+SEC("cgroup/skb")
+__description("skb->sk: no NULL check")
+__failure __msg("invalid mem access 'sock_common_or_null'")
+__failure_unpriv
+__naked void skb_sk_no_null_check(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	r0 = *(u32*)(r1 + 0);				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("skb->sk: sk->family [non fullsock field]")
+__success __success_unpriv __retval(0)
+__naked void sk_family_non_fullsock_field_1(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r0 = *(u32*)(r1 + %[bpf_sock_family]);		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_sock_family, offsetof(struct bpf_sock, family))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("skb->sk: sk->type [fullsock field]")
+__failure __msg("invalid sock_common access")
+__failure_unpriv
+__naked void sk_sk_type_fullsock_field_1(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r0 = *(u32*)(r1 + %[bpf_sock_type]);		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("bpf_sk_fullsock(skb->sk): no !skb->sk check")
+__failure __msg("type=sock_common_or_null expected=sock_common")
+__failure_unpriv
+__naked void sk_no_skb_sk_check_1(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	call %[bpf_sk_fullsock];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("sk_fullsock(skb->sk): no NULL check on ret")
+__failure __msg("invalid mem access 'sock_or_null'")
+__failure_unpriv
+__naked void no_null_check_on_ret_1(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_sk_fullsock];			\
+	r0 = *(u32*)(r0 + %[bpf_sock_type]);		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("sk_fullsock(skb->sk): sk->type [fullsock field]")
+__success __success_unpriv __retval(0)
+__naked void sk_sk_type_fullsock_field_2(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_sk_fullsock];			\
+	if r0 != 0 goto l1_%=;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u32*)(r0 + %[bpf_sock_type]);		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("sk_fullsock(skb->sk): sk->family [non fullsock field]")
+__success __success_unpriv __retval(0)
+__naked void sk_family_non_fullsock_field_2(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_sk_fullsock];			\
+	if r0 != 0 goto l1_%=;				\
+	exit;						\
+l1_%=:	r0 = *(u32*)(r0 + %[bpf_sock_family]);		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_sock_family, offsetof(struct bpf_sock, family))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("sk_fullsock(skb->sk): sk->state [narrow load]")
+__success __success_unpriv __retval(0)
+__naked void sk_sk_state_narrow_load(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_sk_fullsock];			\
+	if r0 != 0 goto l1_%=;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u8*)(r0 + %[bpf_sock_state]);		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_sock_state, offsetof(struct bpf_sock, state))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("sk_fullsock(skb->sk): sk->dst_port [word load] (backward compatibility)")
+__success __success_unpriv __retval(0)
+__naked void port_word_load_backward_compatibility(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_sk_fullsock];			\
+	if r0 != 0 goto l1_%=;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u32*)(r0 + %[bpf_sock_dst_port]);	\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_sock_dst_port, offsetof(struct bpf_sock, dst_port))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("sk_fullsock(skb->sk): sk->dst_port [half load]")
+__success __success_unpriv __retval(0)
+__naked void sk_dst_port_half_load(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_sk_fullsock];			\
+	if r0 != 0 goto l1_%=;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u16*)(r0 + %[bpf_sock_dst_port]);	\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_sock_dst_port, offsetof(struct bpf_sock, dst_port))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("sk_fullsock(skb->sk): sk->dst_port [half load] (invalid)")
+__failure __msg("invalid sock access")
+__failure_unpriv
+__naked void dst_port_half_load_invalid_1(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_sk_fullsock];			\
+	if r0 != 0 goto l1_%=;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u16*)(r0 + %[__imm_0]);			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm_const(__imm_0, offsetof(struct bpf_sock, dst_port) + 2),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("sk_fullsock(skb->sk): sk->dst_port [byte load]")
+__success __success_unpriv __retval(0)
+__naked void sk_dst_port_byte_load(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_sk_fullsock];			\
+	if r0 != 0 goto l1_%=;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	r2 = *(u8*)(r0 + %[bpf_sock_dst_port]);		\
+	r2 = *(u8*)(r0 + %[__imm_0]);			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm_const(__imm_0, offsetof(struct bpf_sock, dst_port) + 1),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_sock_dst_port, offsetof(struct bpf_sock, dst_port))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("sk_fullsock(skb->sk): sk->dst_port [byte load] (invalid)")
+__failure __msg("invalid sock access")
+__failure_unpriv
+__naked void dst_port_byte_load_invalid(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_sk_fullsock];			\
+	if r0 != 0 goto l1_%=;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u8*)(r0 + %[__imm_0]);			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm_const(__imm_0, offsetof(struct bpf_sock, dst_port) + 2),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("sk_fullsock(skb->sk): past sk->dst_port [half load] (invalid)")
+__failure __msg("invalid sock access")
+__failure_unpriv
+__naked void dst_port_half_load_invalid_2(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_sk_fullsock];			\
+	if r0 != 0 goto l1_%=;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u16*)(r0 + %[bpf_sock_dst_port__end]);	\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_sock_dst_port__end, offsetofend(struct bpf_sock, dst_port))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("sk_fullsock(skb->sk): sk->dst_ip6 [load 2nd byte]")
+__success __success_unpriv __retval(0)
+__naked void dst_ip6_load_2nd_byte(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_sk_fullsock];			\
+	if r0 != 0 goto l1_%=;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u8*)(r0 + %[__imm_0]);			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm_const(__imm_0, offsetof(struct bpf_sock, dst_ip6[0]) + 1),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("sk_fullsock(skb->sk): sk->type [narrow load]")
+__success __success_unpriv __retval(0)
+__naked void sk_sk_type_narrow_load(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_sk_fullsock];			\
+	if r0 != 0 goto l1_%=;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u8*)(r0 + %[bpf_sock_type]);		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("sk_fullsock(skb->sk): sk->protocol [narrow load]")
+__success __success_unpriv __retval(0)
+__naked void sk_sk_protocol_narrow_load(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_sk_fullsock];			\
+	if r0 != 0 goto l1_%=;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u8*)(r0 + %[bpf_sock_protocol]);		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_sock_protocol, offsetof(struct bpf_sock, protocol))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("sk_fullsock(skb->sk): beyond last field")
+__failure __msg("invalid sock access")
+__failure_unpriv
+__naked void skb_sk_beyond_last_field_1(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_sk_fullsock];			\
+	if r0 != 0 goto l1_%=;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u32*)(r0 + %[bpf_sock_rx_queue_mapping__end]);\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_sock_rx_queue_mapping__end, offsetofend(struct bpf_sock, rx_queue_mapping))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("bpf_tcp_sock(skb->sk): no !skb->sk check")
+__failure __msg("type=sock_common_or_null expected=sock_common")
+__failure_unpriv
+__naked void sk_no_skb_sk_check_2(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	call %[bpf_tcp_sock];				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_tcp_sock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("bpf_tcp_sock(skb->sk): no NULL check on ret")
+__failure __msg("invalid mem access 'tcp_sock_or_null'")
+__failure_unpriv
+__naked void no_null_check_on_ret_2(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_tcp_sock];				\
+	r0 = *(u32*)(r0 + %[bpf_tcp_sock_snd_cwnd]);	\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_tcp_sock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_tcp_sock_snd_cwnd, offsetof(struct bpf_tcp_sock, snd_cwnd))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("bpf_tcp_sock(skb->sk): tp->snd_cwnd")
+__success __success_unpriv __retval(0)
+__naked void skb_sk_tp_snd_cwnd_1(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_tcp_sock];				\
+	if r0 != 0 goto l1_%=;				\
+	exit;						\
+l1_%=:	r0 = *(u32*)(r0 + %[bpf_tcp_sock_snd_cwnd]);	\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_tcp_sock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_tcp_sock_snd_cwnd, offsetof(struct bpf_tcp_sock, snd_cwnd))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("bpf_tcp_sock(skb->sk): tp->bytes_acked")
+__success __success_unpriv __retval(0)
+__naked void skb_sk_tp_bytes_acked(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_tcp_sock];				\
+	if r0 != 0 goto l1_%=;				\
+	exit;						\
+l1_%=:	r0 = *(u64*)(r0 + %[bpf_tcp_sock_bytes_acked]);	\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_tcp_sock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_tcp_sock_bytes_acked, offsetof(struct bpf_tcp_sock, bytes_acked))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("bpf_tcp_sock(skb->sk): beyond last field")
+__failure __msg("invalid tcp_sock access")
+__failure_unpriv
+__naked void skb_sk_beyond_last_field_2(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_tcp_sock];				\
+	if r0 != 0 goto l1_%=;				\
+	exit;						\
+l1_%=:	r0 = *(u64*)(r0 + %[bpf_tcp_sock_bytes_acked__end]);\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_tcp_sock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_tcp_sock_bytes_acked__end, offsetofend(struct bpf_tcp_sock, bytes_acked))
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("bpf_tcp_sock(bpf_sk_fullsock(skb->sk)): tp->snd_cwnd")
+__success __success_unpriv __retval(0)
+__naked void skb_sk_tp_snd_cwnd_2(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_sk_fullsock];			\
+	if r0 != 0 goto l1_%=;				\
+	exit;						\
+l1_%=:	r1 = r0;					\
+	call %[bpf_tcp_sock];				\
+	if r0 != 0 goto l2_%=;				\
+	exit;						\
+l2_%=:	r0 = *(u32*)(r0 + %[bpf_tcp_sock_snd_cwnd]);	\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm(bpf_tcp_sock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk)),
+	  __imm_const(bpf_tcp_sock_snd_cwnd, offsetof(struct bpf_tcp_sock, snd_cwnd))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("bpf_sk_release(skb->sk)")
+__failure __msg("R1 must be referenced when passed to release function")
+__naked void bpf_sk_release_skb_sk(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 == 0 goto l0_%=;				\
+	call %[bpf_sk_release];				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_release),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("bpf_sk_release(bpf_sk_fullsock(skb->sk))")
+__failure __msg("R1 must be referenced when passed to release function")
+__naked void bpf_sk_fullsock_skb_sk(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_sk_fullsock];			\
+	if r0 != 0 goto l1_%=;				\
+	exit;						\
+l1_%=:	r1 = r0;					\
+	call %[bpf_sk_release];				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm(bpf_sk_release),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("bpf_sk_release(bpf_tcp_sock(skb->sk))")
+__failure __msg("R1 must be referenced when passed to release function")
+__naked void bpf_tcp_sock_skb_sk(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_tcp_sock];				\
+	if r0 != 0 goto l1_%=;				\
+	exit;						\
+l1_%=:	r1 = r0;					\
+	call %[bpf_sk_release];				\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_release),
+	  __imm(bpf_tcp_sock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("sk_storage_get(map, skb->sk, NULL, 0): value == NULL")
+__success __retval(0)
+__naked void sk_null_0_value_null(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_sk_fullsock];			\
+	if r0 != 0 goto l1_%=;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	r4 = 0;						\
+	r3 = 0;						\
+	r2 = r0;					\
+	r1 = %[sk_storage_map] ll;			\
+	call %[bpf_sk_storage_get];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm(bpf_sk_storage_get),
+	  __imm_addr(sk_storage_map),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("sk_storage_get(map, skb->sk, 1, 1): value == 1")
+__failure __msg("R3 type=scalar expected=fp")
+__naked void sk_1_1_value_1(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_sk_fullsock];			\
+	if r0 != 0 goto l1_%=;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	r4 = 1;						\
+	r3 = 1;						\
+	r2 = r0;					\
+	r1 = %[sk_storage_map] ll;			\
+	call %[bpf_sk_storage_get];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm(bpf_sk_storage_get),
+	  __imm_addr(sk_storage_map),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("sk_storage_get(map, skb->sk, &stack_value, 1): stack_value")
+__success __retval(0)
+__naked void stack_value_1_stack_value(void)
+{
+	asm volatile ("					\
+	r2 = 0;						\
+	*(u64*)(r10 - 8) = r2;				\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	call %[bpf_sk_fullsock];			\
+	if r0 != 0 goto l1_%=;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	r4 = 1;						\
+	r3 = r10;					\
+	r3 += -8;					\
+	r2 = r0;					\
+	r1 = %[sk_storage_map] ll;			\
+	call %[bpf_sk_storage_get];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_fullsock),
+	  __imm(bpf_sk_storage_get),
+	  __imm_addr(sk_storage_map),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("bpf_map_lookup_elem(smap, &key)")
+__failure __msg("cannot pass map_type 24 into func bpf_map_lookup_elem")
+__naked void map_lookup_elem_smap_key(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[sk_storage_map] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(sk_storage_map)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("bpf_map_lookup_elem(xskmap, &key); xs->queue_id")
+__success __retval(0)
+__naked void xskmap_key_xs_queue_id(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_xskmap] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r0 = *(u32*)(r0 + %[bpf_xdp_sock_queue_id]);	\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_xskmap),
+	  __imm_const(bpf_xdp_sock_queue_id, offsetof(struct bpf_xdp_sock, queue_id))
+	: __clobber_all);
+}
+
+SEC("sk_skb")
+__description("bpf_map_lookup_elem(sockmap, &key)")
+__failure __msg("Unreleased reference id=2 alloc_insn=6")
+__naked void map_lookup_elem_sockmap_key(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_sockmap] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_sockmap)
+	: __clobber_all);
+}
+
+SEC("sk_skb")
+__description("bpf_map_lookup_elem(sockhash, &key)")
+__failure __msg("Unreleased reference id=2 alloc_insn=6")
+__naked void map_lookup_elem_sockhash_key(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_sockhash] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_sockhash)
+	: __clobber_all);
+}
+
+SEC("sk_skb")
+__description("bpf_map_lookup_elem(sockmap, &key); sk->type [fullsock field]; bpf_sk_release(sk)")
+__success
+__naked void field_bpf_sk_release_sk_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_sockmap] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r1 = r0;					\
+	r0 = *(u32*)(r0 + %[bpf_sock_type]);		\
+	call %[bpf_sk_release];				\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_sk_release),
+	  __imm_addr(map_sockmap),
+	  __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type))
+	: __clobber_all);
+}
+
+SEC("sk_skb")
+__description("bpf_map_lookup_elem(sockhash, &key); sk->type [fullsock field]; bpf_sk_release(sk)")
+__success
+__naked void field_bpf_sk_release_sk_2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_sockhash] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r1 = r0;					\
+	r0 = *(u32*)(r0 + %[bpf_sock_type]);		\
+	call %[bpf_sk_release];				\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_sk_release),
+	  __imm_addr(map_sockhash),
+	  __imm_const(bpf_sock_type, offsetof(struct bpf_sock, type))
+	: __clobber_all);
+}
+
+SEC("sk_reuseport")
+__description("bpf_sk_select_reuseport(ctx, reuseport_array, &key, flags)")
+__success
+__naked void ctx_reuseport_array_key_flags(void)
+{
+	asm volatile ("					\
+	r4 = 0;						\
+	r2 = 0;						\
+	*(u32*)(r10 - 4) = r2;				\
+	r3 = r10;					\
+	r3 += -4;					\
+	r2 = %[map_reuseport_array] ll;			\
+	call %[bpf_sk_select_reuseport];		\
+	exit;						\
+"	:
+	: __imm(bpf_sk_select_reuseport),
+	  __imm_addr(map_reuseport_array)
+	: __clobber_all);
+}
+
+SEC("sk_reuseport")
+__description("bpf_sk_select_reuseport(ctx, sockmap, &key, flags)")
+__success
+__naked void reuseport_ctx_sockmap_key_flags(void)
+{
+	asm volatile ("					\
+	r4 = 0;						\
+	r2 = 0;						\
+	*(u32*)(r10 - 4) = r2;				\
+	r3 = r10;					\
+	r3 += -4;					\
+	r2 = %[map_sockmap] ll;				\
+	call %[bpf_sk_select_reuseport];		\
+	exit;						\
+"	:
+	: __imm(bpf_sk_select_reuseport),
+	  __imm_addr(map_sockmap)
+	: __clobber_all);
+}
+
+SEC("sk_reuseport")
+__description("bpf_sk_select_reuseport(ctx, sockhash, &key, flags)")
+__success
+__naked void reuseport_ctx_sockhash_key_flags(void)
+{
+	asm volatile ("					\
+	r4 = 0;						\
+	r2 = 0;						\
+	*(u32*)(r10 - 4) = r2;				\
+	r3 = r10;					\
+	r3 += -4;					\
+	r2 = %[map_sockmap] ll;				\
+	call %[bpf_sk_select_reuseport];		\
+	exit;						\
+"	:
+	: __imm(bpf_sk_select_reuseport),
+	  __imm_addr(map_sockmap)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("mark null check on return value of bpf_skc_to helpers")
+__failure __msg("invalid mem access")
+__naked void of_bpf_skc_to_helpers(void)
+{
+	asm volatile ("					\
+	r1 = *(u64*)(r1 + %[__sk_buff_sk]);		\
+	if r1 != 0 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	r6 = r1;					\
+	call %[bpf_skc_to_tcp_sock];			\
+	r7 = r0;					\
+	r1 = r6;					\
+	call %[bpf_skc_to_tcp_request_sock];		\
+	r8 = r0;					\
+	if r8 != 0 goto l1_%=;				\
+	r0 = 0;						\
+	exit;						\
+l1_%=:	r0 = *(u8*)(r7 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_skc_to_tcp_request_sock),
+	  __imm(bpf_skc_to_tcp_sock),
+	  __imm_const(__sk_buff_sk, offsetof(struct __sk_buff, sk))
+	: __clobber_all);
+}
+
+SEC("cgroup/post_bind4")
+__description("sk->src_ip6[0] [load 1st byte]")
+__failure __msg("invalid bpf_context access off=28 size=2")
+__naked void post_bind4_read_src_ip6(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r7 = *(u16*)(r6 + %[bpf_sock_src_ip6_0]);	\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm_const(bpf_sock_src_ip6_0, offsetof(struct bpf_sock, src_ip6[0]))
+	: __clobber_all);
+}
+
+SEC("cgroup/post_bind4")
+__description("sk->mark [load mark]")
+__failure __msg("invalid bpf_context access off=16 size=2")
+__naked void post_bind4_read_mark(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r7 = *(u16*)(r6 + %[bpf_sock_mark]);		\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm_const(bpf_sock_mark, offsetof(struct bpf_sock, mark))
+	: __clobber_all);
+}
+
+SEC("cgroup/post_bind6")
+__description("sk->src_ip4 [load src_ip4]")
+__failure __msg("invalid bpf_context access off=24 size=2")
+__naked void post_bind6_read_src_ip4(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r7 = *(u16*)(r6 + %[bpf_sock_src_ip4]);		\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm_const(bpf_sock_src_ip4, offsetof(struct bpf_sock, src_ip4))
+	: __clobber_all);
+}
+
+SEC("cgroup/sock_create")
+__description("sk->src_port [word load]")
+__failure __msg("invalid bpf_context access off=44 size=2")
+__naked void sock_create_read_src_port(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r7 = *(u16*)(r6 + %[bpf_sock_src_port]);	\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm_const(bpf_sock_src_port, offsetof(struct bpf_sock, src_port))
+	: __clobber_all);
+}
+
+__noinline
+long skb_pull_data2(struct __sk_buff *sk, __u32 len)
+{
+	return bpf_skb_pull_data(sk, len);
+}
+
+__noinline
+long skb_pull_data1(struct __sk_buff *sk, __u32 len)
+{
+	return skb_pull_data2(sk, len);
+}
+
+/* global function calls bpf_skb_pull_data(), which invalidates packet
+ * pointers established before global function call.
+ */
+SEC("tc")
+__failure __msg("invalid mem access")
+int invalidate_pkt_pointers_from_global_func(struct __sk_buff *sk)
+{
+	int *p = (void *)(long)sk->data;
+
+	if ((void *)(p + 1) > (void *)(long)sk->data_end)
+		return TCX_DROP;
+	skb_pull_data1(sk, 0);
+	*p = 42; /* this is unsafe */
+	return TCX_PASS;
+}
+
+__noinline
+long xdp_pull_data2(struct xdp_md *x, __u32 len)
+{
+	return bpf_xdp_pull_data(x, len);
+}
+
+__noinline
+long xdp_pull_data1(struct xdp_md *x, __u32 len)
+{
+	return xdp_pull_data2(x, len);
+}
+
+/* global function calls bpf_xdp_pull_data(), which invalidates packet
+ * pointers established before global function call.
+ */
+SEC("xdp")
+__failure __msg("invalid mem access")
+int invalidate_xdp_pkt_pointers_from_global_func(struct xdp_md *x)
+{
+	int *p = (void *)(long)x->data;
+
+	if ((void *)(p + 1) > (void *)(long)x->data_end)
+		return XDP_DROP;
+	xdp_pull_data1(x, 0);
+	*p = 42; /* this is unsafe */
+	return XDP_PASS;
+}
+
+/* XDP packet changing kfunc calls invalidate packet pointers */
+SEC("xdp")
+__failure __msg("invalid mem access")
+int invalidate_xdp_pkt_pointers(struct xdp_md *x)
+{
+	int *p = (void *)(long)x->data;
+
+	if ((void *)(p + 1) > (void *)(long)x->data_end)
+		return XDP_DROP;
+	bpf_xdp_pull_data(x, 0);
+	*p = 42; /* this is unsafe */
+	return XDP_PASS;
+}
+
+__noinline
+int tail_call(struct __sk_buff *sk)
+{
+	bpf_tail_call_static(sk, &jmp_table, 0);
+	return 0;
+}
+
+static __noinline
+int static_tail_call(struct __sk_buff *sk)
+{
+	bpf_tail_call_static(sk, &jmp_table, 0);
+	return 0;
+}
+
+/* Tail calls in sub-programs invalidate packet pointers. */
+SEC("tc")
+__failure __msg("invalid mem access")
+int invalidate_pkt_pointers_by_global_tail_call(struct __sk_buff *sk)
+{
+	int *p = (void *)(long)sk->data;
+
+	if ((void *)(p + 1) > (void *)(long)sk->data_end)
+		return TCX_DROP;
+	tail_call(sk);
+	*p = 42; /* this is unsafe */
+	return TCX_PASS;
+}
+
+/* Tail calls in static sub-programs invalidate packet pointers. */
+SEC("tc")
+__failure __msg("invalid mem access")
+int invalidate_pkt_pointers_by_static_tail_call(struct __sk_buff *sk)
+{
+	int *p = (void *)(long)sk->data;
+
+	if ((void *)(p + 1) > (void *)(long)sk->data_end)
+		return TCX_DROP;
+	static_tail_call(sk);
+	*p = 42; /* this is unsafe */
+	return TCX_PASS;
+}
+
+/* Direct tail calls do not invalidate packet pointers. */
+SEC("tc")
+__success
+int invalidate_pkt_pointers_by_tail_call(struct __sk_buff *sk)
+{
+	int *p = (void *)(long)sk->data;
+
+	if ((void *)(p + 1) > (void *)(long)sk->data_end)
+		return TCX_DROP;
+	bpf_tail_call_static(sk, &jmp_table, 0);
+	*p = 42; /* this is NOT unsafe: tail calls don't return */
+	return TCX_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_sock_addr.c b/tools/testing/selftests/bpf/progs/verifier_sock_addr.c
new file mode 100644
index 000000000000..9c31448a0f52
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_sock_addr.c
@@ -0,0 +1,331 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Google LLC */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf_sockopt_helpers.h>
+#include "bpf_misc.h"
+
+SEC("cgroup/recvmsg4")
+__success
+int recvmsg4_good_return_code(struct bpf_sock_addr *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/recvmsg4")
+__failure __msg("At program exit the register R0 has smin=0 smax=0 should have been in [1, 1]")
+int recvmsg4_bad_return_code(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
+SEC("cgroup/recvmsg6")
+__success
+int recvmsg6_good_return_code(struct bpf_sock_addr *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/recvmsg6")
+__failure __msg("At program exit the register R0 has smin=0 smax=0 should have been in [1, 1]")
+int recvmsg6_bad_return_code(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
+SEC("cgroup/recvmsg_unix")
+__success
+int recvmsg_unix_good_return_code(struct bpf_sock_addr *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/recvmsg_unix")
+__failure __msg("At program exit the register R0 has smin=0 smax=0 should have been in [1, 1]")
+int recvmsg_unix_bad_return_code(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
+SEC("cgroup/sendmsg4")
+__success
+int sendmsg4_good_return_code_0(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
+SEC("cgroup/sendmsg4")
+__success
+int sendmsg4_good_return_code_1(struct bpf_sock_addr *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/sendmsg4")
+__failure __msg("At program exit the register R0 has smin=2 smax=2 should have been in [0, 1]")
+int sendmsg4_bad_return_code(struct bpf_sock_addr *ctx)
+{
+	return 2;
+}
+
+SEC("cgroup/sendmsg6")
+__success
+int sendmsg6_good_return_code_0(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
+SEC("cgroup/sendmsg6")
+__success
+int sendmsg6_good_return_code_1(struct bpf_sock_addr *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/sendmsg6")
+__failure __msg("At program exit the register R0 has smin=2 smax=2 should have been in [0, 1]")
+int sendmsg6_bad_return_code(struct bpf_sock_addr *ctx)
+{
+	return 2;
+}
+
+SEC("cgroup/sendmsg_unix")
+__success
+int sendmsg_unix_good_return_code_0(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
+SEC("cgroup/sendmsg_unix")
+__success
+int sendmsg_unix_good_return_code_1(struct bpf_sock_addr *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/sendmsg_unix")
+__failure __msg("At program exit the register R0 has smin=2 smax=2 should have been in [0, 1]")
+int sendmsg_unix_bad_return_code(struct bpf_sock_addr *ctx)
+{
+	return 2;
+}
+
+SEC("cgroup/getpeername4")
+__success
+int getpeername4_good_return_code(struct bpf_sock_addr *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/getpeername4")
+__failure __msg("At program exit the register R0 has smin=0 smax=0 should have been in [1, 1]")
+int getpeername4_bad_return_code(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
+SEC("cgroup/getpeername6")
+__success
+int getpeername6_good_return_code(struct bpf_sock_addr *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/getpeername6")
+__failure __msg("At program exit the register R0 has smin=0 smax=0 should have been in [1, 1]")
+int getpeername6_bad_return_code(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
+SEC("cgroup/getpeername_unix")
+__success
+int getpeername_unix_good_return_code(struct bpf_sock_addr *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/getpeername_unix")
+__failure __msg("At program exit the register R0 has smin=0 smax=0 should have been in [1, 1]")
+int getpeername_unix_bad_return_code(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
+SEC("cgroup/getsockname4")
+__success
+int getsockname4_good_return_code(struct bpf_sock_addr *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/getsockname4")
+__failure __msg("At program exit the register R0 has smin=0 smax=0 should have been in [1, 1]")
+int getsockname4_bad_return_code(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
+SEC("cgroup/getsockname6")
+__success
+int getsockname6_good_return_code(struct bpf_sock_addr *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/getsockname6")
+__failure __msg("At program exit the register R0 has smin=0 smax=0 should have been in [1, 1]")
+int getsockname6_bad_return_code(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
+SEC("cgroup/getsockname_unix")
+__success
+int getsockname_unix_good_return_code(struct bpf_sock_addr *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/getsockname_unix")
+__failure __msg("At program exit the register R0 has smin=0 smax=0 should have been in [1, 1]")
+int getsockname_unix_unix_bad_return_code(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
+SEC("cgroup/bind4")
+__success
+int bind4_good_return_code_0(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
+SEC("cgroup/bind4")
+__success
+int bind4_good_return_code_1(struct bpf_sock_addr *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/bind4")
+__success
+int bind4_good_return_code_2(struct bpf_sock_addr *ctx)
+{
+	return 2;
+}
+
+SEC("cgroup/bind4")
+__success
+int bind4_good_return_code_3(struct bpf_sock_addr *ctx)
+{
+	return 3;
+}
+
+SEC("cgroup/bind4")
+__failure __msg("At program exit the register R0 has smin=4 smax=4 should have been in [0, 3]")
+int bind4_bad_return_code(struct bpf_sock_addr *ctx)
+{
+	return 4;
+}
+
+SEC("cgroup/bind6")
+__success
+int bind6_good_return_code_0(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
+SEC("cgroup/bind6")
+__success
+int bind6_good_return_code_1(struct bpf_sock_addr *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/bind6")
+__success
+int bind6_good_return_code_2(struct bpf_sock_addr *ctx)
+{
+	return 2;
+}
+
+SEC("cgroup/bind6")
+__success
+int bind6_good_return_code_3(struct bpf_sock_addr *ctx)
+{
+	return 3;
+}
+
+SEC("cgroup/bind6")
+__failure __msg("At program exit the register R0 has smin=4 smax=4 should have been in [0, 3]")
+int bind6_bad_return_code(struct bpf_sock_addr *ctx)
+{
+	return 4;
+}
+
+SEC("cgroup/connect4")
+__success
+int connect4_good_return_code_0(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
+SEC("cgroup/connect4")
+__success
+int connect4_good_return_code_1(struct bpf_sock_addr *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/connect4")
+__failure __msg("At program exit the register R0 has smin=2 smax=2 should have been in [0, 1]")
+int connect4_bad_return_code(struct bpf_sock_addr *ctx)
+{
+	return 2;
+}
+
+SEC("cgroup/connect6")
+__success
+int connect6_good_return_code_0(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
+SEC("cgroup/connect6")
+__success
+int connect6_good_return_code_1(struct bpf_sock_addr *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/connect6")
+__failure __msg("At program exit the register R0 has smin=2 smax=2 should have been in [0, 1]")
+int connect6_bad_return_code(struct bpf_sock_addr *ctx)
+{
+	return 2;
+}
+
+SEC("cgroup/connect_unix")
+__success
+int connect_unix_good_return_code_0(struct bpf_sock_addr *ctx)
+{
+	return 0;
+}
+
+SEC("cgroup/connect_unix")
+__success
+int connect_unix_good_return_code_1(struct bpf_sock_addr *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/connect_unix")
+__failure __msg("At program exit the register R0 has smin=2 smax=2 should have been in [0, 1]")
+int connect_unix_bad_return_code(struct bpf_sock_addr *ctx)
+{
+	return 2;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_sockmap_mutate.c b/tools/testing/selftests/bpf/progs/verifier_sockmap_mutate.c
new file mode 100644
index 000000000000..fe4b123187b8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_sockmap_mutate.c
@@ -0,0 +1,187 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#include "bpf_misc.h"
+
+#define __always_unused __attribute__((unused))
+
+char _license[] SEC("license") = "GPL";
+
+struct sock {
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__sockmap {
+	union {
+		struct sock *sk;
+	};
+} __attribute__((preserve_access_index));
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKHASH);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} sockhash SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} sockmap SEC(".maps");
+
+enum { CG_OK = 1 };
+
+int zero = 0;
+
+static __always_inline void test_sockmap_delete(void)
+{
+	bpf_map_delete_elem(&sockmap, &zero);
+	bpf_map_delete_elem(&sockhash, &zero);
+}
+
+static __always_inline void test_sockmap_update(void *sk)
+{
+	if (sk) {
+		bpf_map_update_elem(&sockmap, &zero, sk, BPF_ANY);
+		bpf_map_update_elem(&sockhash, &zero, sk, BPF_ANY);
+	}
+}
+
+static __always_inline void test_sockmap_lookup_and_update(void)
+{
+	struct bpf_sock *sk = bpf_map_lookup_elem(&sockmap, &zero);
+
+	if (sk) {
+		test_sockmap_update(sk);
+		bpf_sk_release(sk);
+	}
+}
+
+static __always_inline void test_sockmap_mutate(void *sk)
+{
+	test_sockmap_delete();
+	test_sockmap_update(sk);
+}
+
+static __always_inline void test_sockmap_lookup_and_mutate(void)
+{
+	test_sockmap_delete();
+	test_sockmap_lookup_and_update();
+}
+
+SEC("action")
+__success
+int test_sched_act(struct __sk_buff *skb)
+{
+	test_sockmap_mutate(skb->sk);
+	return 0;
+}
+
+SEC("classifier")
+__success
+int test_sched_cls(struct __sk_buff *skb)
+{
+	test_sockmap_mutate(skb->sk);
+	return 0;
+}
+
+SEC("flow_dissector")
+__success
+int test_flow_dissector_delete(struct __sk_buff *skb __always_unused)
+{
+	test_sockmap_delete();
+	return 0;
+}
+
+SEC("flow_dissector")
+__failure __msg("program of this type cannot use helper bpf_sk_release")
+int test_flow_dissector_update(struct __sk_buff *skb __always_unused)
+{
+	test_sockmap_lookup_and_update(); /* no access to skb->sk */
+	return 0;
+}
+
+SEC("iter/sockmap")
+__success
+int test_trace_iter(struct bpf_iter__sockmap *ctx)
+{
+	test_sockmap_mutate(ctx->sk);
+	return 0;
+}
+
+SEC("raw_tp/kfree")
+__failure __msg("cannot update sockmap in this context")
+int test_raw_tp_delete(const void *ctx __always_unused)
+{
+	test_sockmap_delete();
+	return 0;
+}
+
+SEC("raw_tp/kfree")
+__failure __msg("cannot update sockmap in this context")
+int test_raw_tp_update(const void *ctx __always_unused)
+{
+	test_sockmap_lookup_and_update();
+	return 0;
+}
+
+SEC("sk_lookup")
+__success
+int test_sk_lookup(struct bpf_sk_lookup *ctx)
+{
+	test_sockmap_mutate(ctx->sk);
+	return 0;
+}
+
+SEC("sk_reuseport")
+__success
+int test_sk_reuseport(struct sk_reuseport_md *ctx)
+{
+	test_sockmap_mutate(ctx->sk);
+	return 0;
+}
+
+SEC("socket")
+__success
+int test_socket_filter(struct __sk_buff *skb)
+{
+	test_sockmap_mutate(skb->sk);
+	return 0;
+}
+
+SEC("sockops")
+__success
+int test_sockops_delete(struct bpf_sock_ops *ctx __always_unused)
+{
+	test_sockmap_delete();
+	return CG_OK;
+}
+
+SEC("sockops")
+__failure __msg("cannot update sockmap in this context")
+int test_sockops_update(struct bpf_sock_ops *ctx)
+{
+	test_sockmap_update(ctx->sk);
+	return CG_OK;
+}
+
+SEC("sockops")
+__success
+int test_sockops_update_dedicated(struct bpf_sock_ops *ctx)
+{
+	bpf_sock_map_update(ctx, &sockmap, &zero, BPF_ANY);
+	bpf_sock_hash_update(ctx, &sockhash, &zero, BPF_ANY);
+	return CG_OK;
+}
+
+SEC("xdp")
+__success
+int test_xdp(struct xdp_md *ctx __always_unused)
+{
+	test_sockmap_lookup_and_mutate();
+	return XDP_PASS;
+}
diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
new file mode 100644
index 000000000000..7a13dbd794b2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
@@ -0,0 +1,1282 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/spill_fill.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include <../../../tools/include/linux/filter.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_RINGBUF);
+	__uint(max_entries, 4096);
+} map_ringbuf SEC(".maps");
+
+SEC("socket")
+__description("check valid spill/fill")
+__success __failure_unpriv __msg_unpriv("R0 leaks addr")
+__retval(POINTER_VALUE)
+__naked void check_valid_spill_fill(void)
+{
+	asm volatile ("					\
+	/* spill R1(ctx) into stack */			\
+	*(u64*)(r10 - 8) = r1;				\
+	/* fill it back into R2 */			\
+	r2 = *(u64*)(r10 - 8);				\
+	/* should be able to access R0 = *(R2 + 8) */	\
+	/* BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 8), */\
+	r0 = r2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("check valid spill/fill, skb mark")
+__success __success_unpriv __retval(0)
+__naked void valid_spill_fill_skb_mark(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	*(u64*)(r10 - 8) = r6;				\
+	r0 = *(u64*)(r10 - 8);				\
+	r0 = *(u32*)(r0 + %[__sk_buff_mark]);		\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check valid spill/fill, ptr to mem")
+__success __success_unpriv __retval(0)
+__naked void spill_fill_ptr_to_mem(void)
+{
+	asm volatile ("					\
+	/* reserve 8 byte ringbuf memory */		\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r1 = %[map_ringbuf] ll;				\
+	r2 = 8;						\
+	r3 = 0;						\
+	call %[bpf_ringbuf_reserve];			\
+	/* store a pointer to the reserved memory in R6 */\
+	r6 = r0;					\
+	/* check whether the reservation was successful */\
+	if r0 == 0 goto l0_%=;				\
+	/* spill R6(mem) into the stack */		\
+	*(u64*)(r10 - 8) = r6;				\
+	/* fill it back in R7 */			\
+	r7 = *(u64*)(r10 - 8);				\
+	/* should be able to access *(R7) = 0 */	\
+	r1 = 0;						\
+	*(u64*)(r7 + 0) = r1;				\
+	/* submit the reserved ringbuf memory */	\
+	r1 = r7;					\
+	r2 = 0;						\
+	call %[bpf_ringbuf_submit];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ringbuf_reserve),
+	  __imm(bpf_ringbuf_submit),
+	  __imm_addr(map_ringbuf)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check with invalid reg offset 0")
+__failure __msg("R0 pointer arithmetic on ringbuf_mem_or_null prohibited")
+__failure_unpriv
+__naked void with_invalid_reg_offset_0(void)
+{
+	asm volatile ("					\
+	/* reserve 8 byte ringbuf memory */		\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r1 = %[map_ringbuf] ll;				\
+	r2 = 8;						\
+	r3 = 0;						\
+	call %[bpf_ringbuf_reserve];			\
+	/* store a pointer to the reserved memory in R6 */\
+	r6 = r0;					\
+	/* add invalid offset to memory or NULL */	\
+	r0 += 1;					\
+	/* check whether the reservation was successful */\
+	if r0 == 0 goto l0_%=;				\
+	/* should not be able to access *(R7) = 0 */	\
+	r1 = 0;						\
+	*(u32*)(r6 + 0) = r1;				\
+	/* submit the reserved ringbuf memory */	\
+	r1 = r6;					\
+	r2 = 0;						\
+	call %[bpf_ringbuf_submit];			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ringbuf_reserve),
+	  __imm(bpf_ringbuf_submit),
+	  __imm_addr(map_ringbuf)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("check corrupted spill/fill")
+__failure __msg("R0 invalid mem access 'scalar'")
+__msg_unpriv("attempt to corrupt spilled")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void check_corrupted_spill_fill(void)
+{
+	asm volatile ("					\
+	/* spill R1(ctx) into stack */			\
+	*(u64*)(r10 - 8) = r1;				\
+	/* mess up with R1 pointer on stack */		\
+	r0 = 0x23;					\
+	*(u8*)(r10 - 7) = r0;				\
+	/* fill back into R0 is fine for priv.		\
+	 * R0 now becomes SCALAR_VALUE.			\
+	 */						\
+	r0 = *(u64*)(r10 - 8);				\
+	/* Load from R0 should fail. */			\
+	r0 = *(u64*)(r0 + 8);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("check corrupted spill/fill, LSB")
+__success __failure_unpriv __msg_unpriv("attempt to corrupt spilled")
+__retval(POINTER_VALUE)
+__naked void check_corrupted_spill_fill_lsb(void)
+{
+	asm volatile ("					\
+	*(u64*)(r10 - 8) = r1;				\
+	r0 = 0xcafe;					\
+	*(u16*)(r10 - 8) = r0;				\
+	r0 = *(u64*)(r10 - 8);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("check corrupted spill/fill, MSB")
+__success __failure_unpriv __msg_unpriv("attempt to corrupt spilled")
+__retval(POINTER_VALUE)
+__naked void check_corrupted_spill_fill_msb(void)
+{
+	asm volatile ("					\
+	*(u64*)(r10 - 8) = r1;				\
+	r0 = 0x12345678;				\
+	*(u32*)(r10 - 4) = r0;				\
+	r0 = *(u64*)(r10 - 8);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tc")
+__description("Spill and refill a u32 const scalar.  Offset to skb->data")
+__success __retval(0)
+__naked void scalar_offset_to_skb_data_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	w4 = 20;					\
+	*(u32*)(r10 - 8) = r4;				\
+	r4 = *(u32*)(r10 - 8);				\
+	r0 = r2;					\
+	/* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=20 */	\
+	r0 += r4;					\
+	/* if (r0 > r3) R0=pkt,off=20 R2=pkt R3=pkt_end R4=20 */\
+	if r0 > r3 goto l0_%=;				\
+	/* r0 = *(u32 *)r2 R0=pkt,off=20,r=20 R2=pkt,r=20 R3=pkt_end R4=20 */\
+	r0 = *(u32*)(r2 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("Spill a u32 const, refill from another half of the uninit u32 from the stack")
+/* in privileged mode reads from uninitialized stack locations are permitted */
+__success __failure_unpriv
+__msg_unpriv("invalid read from stack off -4+0 size 4")
+__retval(0)
+__naked void uninit_u32_from_the_stack(void)
+{
+	asm volatile ("					\
+	w4 = 20;					\
+	*(u32*)(r10 - 8) = r4;				\
+	/* r4 = *(u32 *)(r10 -4) fp-8=????rrrr*/	\
+	r4 = *(u32*)(r10 - 4);				\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tc")
+__description("Spill a u32 const scalar.  Refill as u16.  Offset to skb->data")
+__success __retval(0)
+__naked void u16_offset_to_skb_data(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	w4 = 20;					\
+	*(u32*)(r10 - 8) = r4;				\
+	"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r4 = *(u16*)(r10 - 8);"
+#else
+	"r4 = *(u16*)(r10 - 6);"
+#endif
+	"						\
+	r0 = r2;					\
+	/* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=20 */\
+	r0 += r4;					\
+	/* if (r0 > r3) R0=pkt,off=20 R2=pkt R3=pkt_end R4=20 */\
+	if r0 > r3 goto l0_%=;				\
+	/* r0 = *(u32 *)r2 R0=pkt,off=20 R2=pkt R3=pkt_end R4=20 */\
+	r0 = *(u32*)(r2 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("Spill u32 const scalars.  Refill as u64.  Offset to skb->data")
+__failure __msg("math between pkt pointer and register with unbounded min value is not allowed")
+__naked void u64_offset_to_skb_data(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	w6 = 0;						\
+	w7 = 20;					\
+	*(u32*)(r10 - 4) = r6;				\
+	*(u32*)(r10 - 8) = r7;				\
+	r4 = *(u64*)(r10 - 8);				\
+	r0 = r2;					\
+	/* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4= */	\
+	r0 += r4;					\
+	if r0 > r3 goto l0_%=;				\
+	r0 = *(u32*)(r2 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("Spill a u32 const scalar.  Refill as u16 from MSB.  Offset to skb->data")
+__failure __msg("invalid access to packet")
+__naked void _6_offset_to_skb_data(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	w4 = 20;					\
+	*(u32*)(r10 - 8) = r4;				\
+	"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r4 = *(u16*)(r10 - 6);"
+#else
+	"r4 = *(u16*)(r10 - 8);"
+#endif
+	"						\
+	r0 = r2;					\
+	/* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=65535 */\
+	r0 += r4;					\
+	/* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=umax=65535 */\
+	if r0 > r3 goto l0_%=;				\
+	/* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=20 */\
+	r0 = *(u32*)(r2 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("Spill and refill a u32 const scalar at non 8byte aligned stack addr.  Offset to skb->data")
+__failure __msg("invalid access to packet")
+__naked void addr_offset_to_skb_data(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	w4 = 20;					\
+	*(u32*)(r10 - 8) = r4;				\
+	*(u32*)(r10 - 4) = r4;				\
+	r4 = *(u32*)(r10 - 4);				\
+	r0 = r2;					\
+	/* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=U32_MAX */\
+	r0 += r4;					\
+	/* if (r0 > r3) R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4= */\
+	if r0 > r3 goto l0_%=;				\
+	/* r0 = *(u32 *)r2 R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4= */\
+	r0 = *(u32*)(r2 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("Spill and refill a umax=40 bounded scalar.  Offset to skb->data")
+__success __retval(0)
+__naked void scalar_offset_to_skb_data_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r3 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r4 = *(u64*)(r1 + %[__sk_buff_tstamp]);		\
+	if r4 <= 40 goto l0_%=;				\
+	r0 = 0;						\
+	exit;						\
+l0_%=:	/* *(u32 *)(r10 -8) = r4 R4=umax=40 */		\
+	*(u32*)(r10 - 8) = r4;				\
+	/* r4 = (*u32 *)(r10 - 8) */			\
+	r4 = *(u32*)(r10 - 8);				\
+	/* r2 += r4 R2=pkt R4=umax=40 */		\
+	r2 += r4;					\
+	/* r0 = r2 R2=pkt,umax=40 R4=umax=40 */		\
+	r0 = r2;					\
+	/* r2 += 20 R0=pkt,umax=40 R2=pkt,umax=40 */	\
+	r2 += 20;					\
+	/* if (r2 > r3) R0=pkt,umax=40 R2=pkt,off=20,umax=40 */\
+	if r2 > r3 goto l1_%=;				\
+	/* r0 = *(u32 *)r0 R0=pkt,r=20,umax=40 R2=pkt,off=20,r=20,umax=40 */\
+	r0 = *(u32*)(r0 + 0);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end)),
+	  __imm_const(__sk_buff_tstamp, offsetof(struct __sk_buff, tstamp))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("Spill a u32 scalar at fp-4 and then at fp-8")
+__success __retval(0)
+__naked void and_then_at_fp_8(void)
+{
+	asm volatile ("					\
+	w4 = 4321;					\
+	*(u32*)(r10 - 4) = r4;				\
+	*(u32*)(r10 - 8) = r4;				\
+	r4 = *(u64*)(r10 - 8);				\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("xdp")
+__description("32-bit spill of 64-bit reg should clear ID")
+__failure __msg("math between ctx pointer and 4294967295 is not allowed")
+__naked void spill_32bit_of_64bit_fail(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	/* Roll one bit to force the verifier to track both branches. */\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0x8;					\
+	/* Put a large number into r1. */		\
+	r1 = 0xffffffff;				\
+	r1 <<= 32;					\
+	r1 += r0;					\
+	/* Assign an ID to r1. */			\
+	r2 = r1;					\
+	/* 32-bit spill r1 to stack - should clear the ID! */\
+	*(u32*)(r10 - 8) = r1;				\
+	/* 32-bit fill r2 from stack. */		\
+	r2 = *(u32*)(r10 - 8);				\
+	/* Compare r2 with another register to trigger sync_linked_regs.\
+	 * Having one random bit is important here, otherwise the verifier cuts\
+	 * the corners. If the ID was mistakenly preserved on spill, this would\
+	 * cause the verifier to think that r1 is also equal to zero in one of\
+	 * the branches, and equal to eight on the other branch.\
+	 */						\
+	r3 = 0;						\
+	if r2 != r3 goto l0_%=;				\
+l0_%=:	r1 >>= 32;					\
+	/* At this point, if the verifier thinks that r1 is 0, an out-of-bounds\
+	 * read will happen, because it actually contains 0xffffffff.\
+	 */						\
+	r6 += r1;					\
+	r0 = *(u32*)(r6 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("16-bit spill of 32-bit reg should clear ID")
+__failure __msg("dereference of modified ctx ptr R6 off=65535 disallowed")
+__naked void spill_16bit_of_32bit_fail(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	/* Roll one bit to force the verifier to track both branches. */\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0x8;					\
+	/* Put a large number into r1. */		\
+	w1 = 0xffff0000;				\
+	r1 += r0;					\
+	/* Assign an ID to r1. */			\
+	r2 = r1;					\
+	/* 16-bit spill r1 to stack - should clear the ID! */\
+	*(u16*)(r10 - 8) = r1;				\
+	/* 16-bit fill r2 from stack. */		\
+	r2 = *(u16*)(r10 - 8);				\
+	/* Compare r2 with another register to trigger sync_linked_regs.\
+	 * Having one random bit is important here, otherwise the verifier cuts\
+	 * the corners. If the ID was mistakenly preserved on spill, this would\
+	 * cause the verifier to think that r1 is also equal to zero in one of\
+	 * the branches, and equal to eight on the other branch.\
+	 */						\
+	r3 = 0;						\
+	if r2 != r3 goto l0_%=;				\
+l0_%=:	r1 >>= 16;					\
+	/* At this point, if the verifier thinks that r1 is 0, an out-of-bounds\
+	 * read will happen, because it actually contains 0xffff.\
+	 */						\
+	r6 += r1;					\
+	r0 = *(u32*)(r6 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("raw_tp")
+__log_level(2)
+__success
+__msg("fp-8=0m??scalar()")
+__msg("fp-16=00mm??scalar()")
+__msg("fp-24=00mm???scalar()")
+__naked void spill_subregs_preserve_stack_zero(void)
+{
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+
+		/* 32-bit subreg spill with ZERO, MISC, and INVALID */
+		".8byte %[fp1_u8_st_zero];"   /* ZERO, LLVM-18+: *(u8 *)(r10 -1) = 0; */
+		"*(u8 *)(r10 -2) = r0;"       /* MISC */
+		/* fp-3 and fp-4 stay INVALID */
+		"*(u32 *)(r10 -8) = r0;"
+
+		/* 16-bit subreg spill with ZERO, MISC, and INVALID */
+		".8byte %[fp10_u16_st_zero];" /* ZERO, LLVM-18+: *(u16 *)(r10 -10) = 0; */
+		"*(u16 *)(r10 -12) = r0;"     /* MISC */
+		/* fp-13 and fp-14 stay INVALID */
+		"*(u16 *)(r10 -16) = r0;"
+
+		/* 8-bit subreg spill with ZERO, MISC, and INVALID */
+		".8byte %[fp18_u16_st_zero];" /* ZERO, LLVM-18+: *(u16 *)(r18 -10) = 0; */
+		"*(u16 *)(r10 -20) = r0;"     /* MISC */
+		/* fp-21, fp-22, and fp-23 stay INVALID */
+		"*(u8 *)(r10 -24) = r0;"
+
+		"r0 = 0;"
+		"exit;"
+	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm_insn(fp1_u8_st_zero, BPF_ST_MEM(BPF_B, BPF_REG_FP, -1, 0)),
+	  __imm_insn(fp10_u16_st_zero, BPF_ST_MEM(BPF_H, BPF_REG_FP, -10, 0)),
+	  __imm_insn(fp18_u16_st_zero, BPF_ST_MEM(BPF_H, BPF_REG_FP, -18, 0))
+	: __clobber_all);
+}
+
+char single_byte_buf[1] SEC(".data.single_byte_buf");
+
+SEC("raw_tp")
+__log_level(2)
+__success
+/* fp-8 is spilled IMPRECISE value zero (represented by a zero value fake reg) */
+__msg("2: (7a) *(u64 *)(r10 -8) = 0          ; R10=fp0 fp-8=0")
+/* but fp-16 is spilled IMPRECISE zero const reg */
+__msg("4: (7b) *(u64 *)(r10 -16) = r0        ; R0=0 R10=fp0 fp-16=0")
+/* validate that assigning R2 from STACK_SPILL with zero value  doesn't mark register
+ * precise immediately; if necessary, it will be marked precise later
+ */
+__msg("6: (71) r2 = *(u8 *)(r10 -1)          ; R2=0 R10=fp0 fp-8=0")
+/* similarly, when R2 is assigned from spilled register, it is initially
+ * imprecise, but will be marked precise later once it is used in precise context
+ */
+__msg("10: (71) r2 = *(u8 *)(r10 -9)         ; R2=0 R10=fp0 fp-16=0")
+__msg("11: (0f) r1 += r2")
+__msg("mark_precise: frame0: last_idx 11 first_idx 0 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r2 stack= before 10: (71) r2 = *(u8 *)(r10 -9)")
+__msg("mark_precise: frame0: regs= stack=-16 before 9: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs= stack=-16 before 8: (73) *(u8 *)(r1 +0) = r2")
+__msg("mark_precise: frame0: regs= stack=-16 before 7: (0f) r1 += r2")
+__msg("mark_precise: frame0: regs= stack=-16 before 6: (71) r2 = *(u8 *)(r10 -1)")
+__msg("mark_precise: frame0: regs= stack=-16 before 5: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs= stack=-16 before 4: (7b) *(u64 *)(r10 -16) = r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 3: (b7) r0 = 0")
+__naked void partial_stack_load_preserves_zeros(void)
+{
+	asm volatile (
+		/* fp-8 is value zero (represented by a zero value fake reg) */
+		".8byte %[fp8_st_zero];" /* LLVM-18+: *(u64 *)(r10 -8) = 0; */
+
+		/* fp-16 is const zero register */
+		"r0 = 0;"
+		"*(u64 *)(r10 -16) = r0;"
+
+		/* load single U8 from non-aligned spilled value zero slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u8 *)(r10 -1);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U8 from non-aligned ZERO REG slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u8 *)(r10 -9);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U16 from non-aligned spilled value zero slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u16 *)(r10 -2);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U16 from non-aligned ZERO REG slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u16 *)(r10 -10);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U32 from non-aligned spilled value zero slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u32 *)(r10 -4);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U32 from non-aligned ZERO REG slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u32 *)(r10 -12);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* for completeness, load U64 from STACK_ZERO slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u64 *)(r10 -8);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* for completeness, load U64 from ZERO REG slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u64 *)(r10 -16);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		"r0 = 0;"
+		"exit;"
+	:
+	: __imm_ptr(single_byte_buf),
+	  __imm_insn(fp8_st_zero, BPF_ST_MEM(BPF_DW, BPF_REG_FP, -8, 0))
+	: __clobber_common);
+}
+
+SEC("raw_tp")
+__log_level(2)
+__success
+/* fp-4 is STACK_ZERO */
+__msg("2: (62) *(u32 *)(r10 -4) = 0          ; R10=fp0 fp-8=0000????")
+__msg("4: (71) r2 = *(u8 *)(r10 -1)          ; R2=0 R10=fp0 fp-8=0000????")
+__msg("5: (0f) r1 += r2")
+__msg("mark_precise: frame0: last_idx 5 first_idx 0 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r2 stack= before 4: (71) r2 = *(u8 *)(r10 -1)")
+__naked void partial_stack_load_preserves_partial_zeros(void)
+{
+	asm volatile (
+		/* fp-4 is value zero */
+		".8byte %[fp4_st_zero];" /* LLVM-18+: *(u32 *)(r10 -4) = 0; */
+
+		/* load single U8 from non-aligned stack zero slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u8 *)(r10 -1);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U16 from non-aligned stack zero slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u16 *)(r10 -2);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U32 from non-aligned stack zero slot */
+		"r1 = %[single_byte_buf];"
+		"r2 = *(u32 *)(r10 -4);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		"r0 = 0;"
+		"exit;"
+	:
+	: __imm_ptr(single_byte_buf),
+	  __imm_insn(fp4_st_zero, BPF_ST_MEM(BPF_W, BPF_REG_FP, -4, 0))
+	: __clobber_common);
+}
+
+char two_byte_buf[2] SEC(".data.two_byte_buf");
+
+SEC("raw_tp")
+__log_level(2) __flag(BPF_F_TEST_STATE_FREQ)
+__success
+/* make sure fp-8 is IMPRECISE fake register spill */
+__msg("3: (7a) *(u64 *)(r10 -8) = 1          ; R10=fp0 fp-8=1")
+/* and fp-16 is spilled IMPRECISE const reg */
+__msg("5: (7b) *(u64 *)(r10 -16) = r0        ; R0=1 R10=fp0 fp-16=1")
+/* validate load from fp-8, which was initialized using BPF_ST_MEM */
+__msg("8: (79) r2 = *(u64 *)(r10 -8)         ; R2=1 R10=fp0 fp-8=1")
+__msg("9: (0f) r1 += r2")
+__msg("mark_precise: frame0: last_idx 9 first_idx 7 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r2 stack= before 8: (79) r2 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r1 = r6")
+/* note, fp-8 is precise, fp-16 is not yet precise, we'll get there */
+__msg("mark_precise: frame0: parent state regs= stack=-8:  R0=1 R1=ctx() R6=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8=P1 fp-16=1")
+__msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7")
+__msg("mark_precise: frame0: regs= stack=-8 before 6: (05) goto pc+0")
+__msg("mark_precise: frame0: regs= stack=-8 before 5: (7b) *(u64 *)(r10 -16) = r0")
+__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r0 = 1")
+__msg("mark_precise: frame0: regs= stack=-8 before 3: (7a) *(u64 *)(r10 -8) = 1")
+__msg("10: R1=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2=1")
+/* validate load from fp-16, which was initialized using BPF_STX_MEM */
+__msg("12: (79) r2 = *(u64 *)(r10 -16)       ; R2=1 R10=fp0 fp-16=1")
+__msg("13: (0f) r1 += r2")
+__msg("mark_precise: frame0: last_idx 13 first_idx 7 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r2 stack= before 12: (79) r2 = *(u64 *)(r10 -16)")
+__msg("mark_precise: frame0: regs= stack=-16 before 11: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs= stack=-16 before 10: (73) *(u8 *)(r1 +0) = r2")
+__msg("mark_precise: frame0: regs= stack=-16 before 9: (0f) r1 += r2")
+__msg("mark_precise: frame0: regs= stack=-16 before 8: (79) r2 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: regs= stack=-16 before 7: (bf) r1 = r6")
+/* now both fp-8 and fp-16 are precise, very good */
+__msg("mark_precise: frame0: parent state regs= stack=-16:  R0=1 R1=ctx() R6=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8=P1 fp-16=P1")
+__msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7")
+__msg("mark_precise: frame0: regs= stack=-16 before 6: (05) goto pc+0")
+__msg("mark_precise: frame0: regs= stack=-16 before 5: (7b) *(u64 *)(r10 -16) = r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 4: (b7) r0 = 1")
+__msg("14: R1=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2=1")
+__naked void stack_load_preserves_const_precision(void)
+{
+	asm volatile (
+		/* establish checkpoint with state that has no stack slots;
+		 * if we bubble up to this state without finding desired stack
+		 * slot, then it's a bug and should be caught
+		 */
+		"goto +0;"
+
+		/* fp-8 is const 1 *fake* register */
+		".8byte %[fp8_st_one];" /* LLVM-18+: *(u64 *)(r10 -8) = 1; */
+
+		/* fp-16 is const 1 register */
+		"r0 = 1;"
+		"*(u64 *)(r10 -16) = r0;"
+
+		/* force checkpoint to check precision marks preserved in parent states */
+		"goto +0;"
+
+		/* load single U64 from aligned FAKE_REG=1 slot */
+		"r1 = %[two_byte_buf];"
+		"r2 = *(u64 *)(r10 -8);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U64 from aligned REG=1 slot */
+		"r1 = %[two_byte_buf];"
+		"r2 = *(u64 *)(r10 -16);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		"r0 = 0;"
+		"exit;"
+	:
+	: __imm_ptr(two_byte_buf),
+	  __imm_insn(fp8_st_one, BPF_ST_MEM(BPF_DW, BPF_REG_FP, -8, 1))
+	: __clobber_common);
+}
+
+SEC("raw_tp")
+__log_level(2) __flag(BPF_F_TEST_STATE_FREQ)
+__success
+/* make sure fp-8 is 32-bit FAKE subregister spill */
+__msg("3: (62) *(u32 *)(r10 -8) = 1          ; R10=fp0 fp-8=????1")
+/* but fp-16 is spilled IMPRECISE zero const reg */
+__msg("5: (63) *(u32 *)(r10 -16) = r0        ; R0=1 R10=fp0 fp-16=????1")
+/* validate load from fp-8, which was initialized using BPF_ST_MEM */
+__msg("8: (61) r2 = *(u32 *)(r10 -8)         ; R2=1 R10=fp0 fp-8=????1")
+__msg("9: (0f) r1 += r2")
+__msg("mark_precise: frame0: last_idx 9 first_idx 7 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r2 stack= before 8: (61) r2 = *(u32 *)(r10 -8)")
+__msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r1 = r6")
+__msg("mark_precise: frame0: parent state regs= stack=-8:  R0=1 R1=ctx() R6=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8=????P1 fp-16=????1")
+__msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7")
+__msg("mark_precise: frame0: regs= stack=-8 before 6: (05) goto pc+0")
+__msg("mark_precise: frame0: regs= stack=-8 before 5: (63) *(u32 *)(r10 -16) = r0")
+__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r0 = 1")
+__msg("mark_precise: frame0: regs= stack=-8 before 3: (62) *(u32 *)(r10 -8) = 1")
+__msg("10: R1=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2=1")
+/* validate load from fp-16, which was initialized using BPF_STX_MEM */
+__msg("12: (61) r2 = *(u32 *)(r10 -16)       ; R2=1 R10=fp0 fp-16=????1")
+__msg("13: (0f) r1 += r2")
+__msg("mark_precise: frame0: last_idx 13 first_idx 7 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r2 stack= before 12: (61) r2 = *(u32 *)(r10 -16)")
+__msg("mark_precise: frame0: regs= stack=-16 before 11: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs= stack=-16 before 10: (73) *(u8 *)(r1 +0) = r2")
+__msg("mark_precise: frame0: regs= stack=-16 before 9: (0f) r1 += r2")
+__msg("mark_precise: frame0: regs= stack=-16 before 8: (61) r2 = *(u32 *)(r10 -8)")
+__msg("mark_precise: frame0: regs= stack=-16 before 7: (bf) r1 = r6")
+__msg("mark_precise: frame0: parent state regs= stack=-16:  R0=1 R1=ctx() R6=map_value(map=.data.two_byte_,ks=4,vs=2) R10=fp0 fp-8=????P1 fp-16=????P1")
+__msg("mark_precise: frame0: last_idx 6 first_idx 3 subseq_idx 7")
+__msg("mark_precise: frame0: regs= stack=-16 before 6: (05) goto pc+0")
+__msg("mark_precise: frame0: regs= stack=-16 before 5: (63) *(u32 *)(r10 -16) = r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 4: (b7) r0 = 1")
+__msg("14: R1=map_value(map=.data.two_byte_,ks=4,vs=2,off=1) R2=1")
+__naked void stack_load_preserves_const_precision_subreg(void)
+{
+	asm volatile (
+		/* establish checkpoint with state that has no stack slots;
+		 * if we bubble up to this state without finding desired stack
+		 * slot, then it's a bug and should be caught
+		 */
+		"goto +0;"
+
+		/* fp-8 is const 1 *fake* SUB-register */
+		".8byte %[fp8_st_one];" /* LLVM-18+: *(u32 *)(r10 -8) = 1; */
+
+		/* fp-16 is const 1 SUB-register */
+		"r0 = 1;"
+		"*(u32 *)(r10 -16) = r0;"
+
+		/* force checkpoint to check precision marks preserved in parent states */
+		"goto +0;"
+
+		/* load single U32 from aligned FAKE_REG=1 slot */
+		"r1 = %[two_byte_buf];"
+		"r2 = *(u32 *)(r10 -8);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		/* load single U32 from aligned REG=1 slot */
+		"r1 = %[two_byte_buf];"
+		"r2 = *(u32 *)(r10 -16);"
+		"r1 += r2;"
+		"*(u8 *)(r1 + 0) = r2;" /* this should be fine */
+
+		"r0 = 0;"
+		"exit;"
+	:
+	: __imm_ptr(two_byte_buf),
+	  __imm_insn(fp8_st_one, BPF_ST_MEM(BPF_W, BPF_REG_FP, -8, 1)) /* 32-bit spill */
+	: __clobber_common);
+}
+
+SEC("xdp")
+__description("32-bit spilled reg range should be tracked")
+__success __retval(0)
+__naked void spill_32bit_range_track(void)
+{
+	asm volatile("					\
+	call %[bpf_ktime_get_ns];			\
+	/* Make r0 bounded. */				\
+	r0 &= 65535;					\
+	/* Assign an ID to r0. */			\
+	r1 = r0;					\
+	/* 32-bit spill r0 to stack. */			\
+	*(u32*)(r10 - 8) = r0;				\
+	/* Boundary check on r0. */			\
+	if r0 < 1 goto l0_%=;				\
+	/* 32-bit fill r1 from stack. */		\
+	r1 = *(u32*)(r10 - 8);				\
+	/* r1 == r0 => r1 >= 1 always. */		\
+	if r1 >= 1 goto l0_%=;				\
+	/* Dead branch: the verifier should prune it.   \
+	 * Do an invalid memory access if the verifier	\
+	 * follows it.					\
+	 */						\
+	r0 = *(u64*)(r9 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("64-bit spill of 64-bit reg should assign ID")
+__success __retval(0)
+__naked void spill_64bit_of_64bit_ok(void)
+{
+	asm volatile ("					\
+	/* Roll one bit to make the register inexact. */\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0x80000000;				\
+	r0 <<= 32;					\
+	/* 64-bit spill r0 to stack - should assign an ID. */\
+	*(u64*)(r10 - 8) = r0;				\
+	/* 64-bit fill r1 from stack - should preserve the ID. */\
+	r1 = *(u64*)(r10 - 8);				\
+	/* Compare r1 with another register to trigger sync_linked_regs.\
+	 * Having one random bit is important here, otherwise the verifier cuts\
+	 * the corners.					\
+	 */						\
+	r2 = 0;						\
+	if r1 != r2 goto l0_%=;				\
+	/* The result of this comparison is predefined. */\
+	if r0 == r2 goto l0_%=;				\
+	/* Dead branch: the verifier should prune it. Do an invalid memory\
+	 * access if the verifier follows it.		\
+	 */						\
+	r0 = *(u64*)(r9 + 0);				\
+	exit;						\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("32-bit spill of 32-bit reg should assign ID")
+__success __retval(0)
+__naked void spill_32bit_of_32bit_ok(void)
+{
+	asm volatile ("					\
+	/* Roll one bit to make the register inexact. */\
+	call %[bpf_get_prandom_u32];			\
+	w0 &= 0x80000000;				\
+	/* 32-bit spill r0 to stack - should assign an ID. */\
+	*(u32*)(r10 - 8) = r0;				\
+	/* 32-bit fill r1 from stack - should preserve the ID. */\
+	r1 = *(u32*)(r10 - 8);				\
+	/* Compare r1 with another register to trigger sync_linked_regs.\
+	 * Having one random bit is important here, otherwise the verifier cuts\
+	 * the corners.					\
+	 */						\
+	r2 = 0;						\
+	if r1 != r2 goto l0_%=;				\
+	/* The result of this comparison is predefined. */\
+	if r0 == r2 goto l0_%=;				\
+	/* Dead branch: the verifier should prune it. Do an invalid memory\
+	 * access if the verifier follows it.		\
+	 */						\
+	r0 = *(u64*)(r9 + 0);				\
+	exit;						\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("16-bit spill of 16-bit reg should assign ID")
+__success __retval(0)
+__naked void spill_16bit_of_16bit_ok(void)
+{
+	asm volatile ("					\
+	/* Roll one bit to make the register inexact. */\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0x8000;					\
+	/* 16-bit spill r0 to stack - should assign an ID. */\
+	*(u16*)(r10 - 8) = r0;				\
+	/* 16-bit fill r1 from stack - should preserve the ID. */\
+	r1 = *(u16*)(r10 - 8);				\
+	/* Compare r1 with another register to trigger sync_linked_regs.\
+	 * Having one random bit is important here, otherwise the verifier cuts\
+	 * the corners.					\
+	 */						\
+	r2 = 0;						\
+	if r1 != r2 goto l0_%=;				\
+	/* The result of this comparison is predefined. */\
+	if r0 == r2 goto l0_%=;				\
+	/* Dead branch: the verifier should prune it. Do an invalid memory\
+	 * access if the verifier follows it.		\
+	 */						\
+	r0 = *(u64*)(r9 + 0);				\
+	exit;						\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("8-bit spill of 8-bit reg should assign ID")
+__success __retval(0)
+__naked void spill_8bit_of_8bit_ok(void)
+{
+	asm volatile ("					\
+	/* Roll one bit to make the register inexact. */\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0x80;					\
+	/* 8-bit spill r0 to stack - should assign an ID. */\
+	*(u8*)(r10 - 8) = r0;				\
+	/* 8-bit fill r1 from stack - should preserve the ID. */\
+	r1 = *(u8*)(r10 - 8);				\
+	/* Compare r1 with another register to trigger sync_linked_regs.\
+	 * Having one random bit is important here, otherwise the verifier cuts\
+	 * the corners.					\
+	 */						\
+	r2 = 0;						\
+	if r1 != r2 goto l0_%=;				\
+	/* The result of this comparison is predefined. */\
+	if r0 == r2 goto l0_%=;				\
+	/* Dead branch: the verifier should prune it. Do an invalid memory\
+	 * access if the verifier follows it.		\
+	 */						\
+	r0 = *(u64*)(r9 + 0);				\
+	exit;						\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("spill unbounded reg, then range check src")
+__success __retval(0)
+__naked void spill_unbounded(void)
+{
+	asm volatile ("					\
+	/* Produce an unbounded scalar. */		\
+	call %[bpf_get_prandom_u32];			\
+	/* Spill r0 to stack. */			\
+	*(u64*)(r10 - 8) = r0;				\
+	/* Boundary check on r0. */			\
+	if r0 > 16 goto l0_%=;				\
+	/* Fill r0 from stack. */			\
+	r0 = *(u64*)(r10 - 8);				\
+	/* Boundary check on r0 with predetermined result. */\
+	if r0 <= 16 goto l0_%=;				\
+	/* Dead branch: the verifier should prune it. Do an invalid memory\
+	 * access if the verifier follows it.		\
+	 */						\
+	r0 = *(u64*)(r9 + 0);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("32-bit fill after 64-bit spill")
+__success __retval(0)
+__naked void fill_32bit_after_spill_64bit(void)
+{
+	asm volatile("					\
+	/* Randomize the upper 32 bits. */		\
+	call %[bpf_get_prandom_u32];			\
+	r0 <<= 32;					\
+	/* 64-bit spill r0 to stack. */			\
+	*(u64*)(r10 - 8) = r0;				\
+	/* 32-bit fill r0 from stack. */		\
+	"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r0 = *(u32*)(r10 - 8);"
+#else
+	"r0 = *(u32*)(r10 - 4);"
+#endif
+	"						\
+	/* Boundary check on r0 with predetermined result. */\
+	if r0 == 0 goto l0_%=;				\
+	/* Dead branch: the verifier should prune it. Do an invalid memory\
+	 * access if the verifier follows it.		\
+	 */						\
+	r0 = *(u64*)(r9 + 0);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("32-bit fill after 64-bit spill of 32-bit value should preserve ID")
+__success __retval(0)
+__naked void fill_32bit_after_spill_64bit_preserve_id(void)
+{
+	asm volatile ("					\
+	/* Randomize the lower 32 bits. */		\
+	call %[bpf_get_prandom_u32];			\
+	w0 &= 0xffffffff;				\
+	/* 64-bit spill r0 to stack - should assign an ID. */\
+	*(u64*)(r10 - 8) = r0;				\
+	/* 32-bit fill r1 from stack - should preserve the ID. */\
+	"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r1 = *(u32*)(r10 - 8);"
+#else
+	"r1 = *(u32*)(r10 - 4);"
+#endif
+	"						\
+	/* Compare r1 with another register to trigger sync_linked_regs. */\
+	r2 = 0;						\
+	if r1 != r2 goto l0_%=;				\
+	/* The result of this comparison is predefined. */\
+	if r0 == r2 goto l0_%=;				\
+	/* Dead branch: the verifier should prune it. Do an invalid memory\
+	 * access if the verifier follows it.		\
+	 */						\
+	r0 = *(u64*)(r9 + 0);				\
+	exit;						\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("32-bit fill after 64-bit spill should clear ID")
+__failure __msg("math between ctx pointer and 4294967295 is not allowed")
+__naked void fill_32bit_after_spill_64bit_clear_id(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	/* Roll one bit to force the verifier to track both branches. */\
+	call %[bpf_get_prandom_u32];			\
+	r0 &= 0x8;					\
+	/* Put a large number into r1. */		\
+	r1 = 0xffffffff;				\
+	r1 <<= 32;					\
+	r1 += r0;					\
+	/* 64-bit spill r1 to stack - should assign an ID. */\
+	*(u64*)(r10 - 8) = r1;				\
+	/* 32-bit fill r2 from stack - should clear the ID. */\
+	"
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	"r2 = *(u32*)(r10 - 8);"
+#else
+	"r2 = *(u32*)(r10 - 4);"
+#endif
+	"						\
+	/* Compare r2 with another register to trigger sync_linked_regs.\
+	 * Having one random bit is important here, otherwise the verifier cuts\
+	 * the corners. If the ID was mistakenly preserved on fill, this would\
+	 * cause the verifier to think that r1 is also equal to zero in one of\
+	 * the branches, and equal to eight on the other branch.\
+	 */						\
+	r3 = 0;						\
+	if r2 != r3 goto l0_%=;				\
+l0_%=:	r1 >>= 32;					\
+	/* The verifier shouldn't propagate r2's range to r1, so it should\
+	 * still remember r1 = 0xffffffff and reject the below.\
+	 */						\
+	r6 += r1;					\
+	r0 = *(u32*)(r6 + 0);				\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+/* stacksafe(): check if stack spill of an imprecise scalar in old state
+ * is considered equivalent to STACK_{MISC,INVALID} in cur state.
+ */
+SEC("socket")
+__success __log_level(2)
+__msg("8: (79) r1 = *(u64 *)(r10 -8)")
+__msg("8: safe")
+__msg("processed 11 insns")
+/* STACK_INVALID should prevent verifier in unpriv mode from
+ * considering states equivalent and force an error on second
+ * verification path (entry - label 1 - label 2).
+ */
+__failure_unpriv
+__msg_unpriv("8: (79) r1 = *(u64 *)(r10 -8)")
+__msg_unpriv("9: (95) exit")
+__msg_unpriv("8: (79) r1 = *(u64 *)(r10 -8)")
+__msg_unpriv("invalid read from stack off -8+2 size 8")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void old_imprecise_scalar_vs_cur_stack_misc(void)
+{
+	asm volatile(
+	/* get a random value for branching */
+	"call %[bpf_ktime_get_ns];"
+	"if r0 == 0 goto 1f;"
+	/* conjure scalar at fp-8 */
+	"r0 = 42;"
+	"*(u64*)(r10 - 8) = r0;"
+	"goto 2f;"
+"1:"
+	/* conjure STACK_{MISC,INVALID} at fp-8 */
+	"call %[bpf_ktime_get_ns];"
+	"*(u16*)(r10 - 8) = r0;"
+	"*(u16*)(r10 - 4) = r0;"
+"2:"
+	/* read fp-8, should be considered safe on second visit */
+	"r1 = *(u64*)(r10 - 8);"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+/* stacksafe(): check that stack spill of a precise scalar in old state
+ * is not considered equivalent to STACK_MISC in cur state.
+ */
+SEC("socket")
+__success __log_level(2)
+/* verifier should visit 'if r1 == 0x2a ...' two times:
+ * - once for path entry - label 2;
+ * - once for path entry - label 1 - label 2.
+ */
+__msg("if r1 == 0x2a goto pc+0")
+__msg("if r1 == 0x2a goto pc+0")
+__msg("processed 15 insns")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void old_precise_scalar_vs_cur_stack_misc(void)
+{
+	asm volatile(
+	/* get a random value for branching */
+	"call %[bpf_ktime_get_ns];"
+	"if r0 == 0 goto 1f;"
+	/* conjure scalar at fp-8 */
+	"r0 = 42;"
+	"*(u64*)(r10 - 8) = r0;"
+	"goto 2f;"
+"1:"
+	/* conjure STACK_MISC at fp-8 */
+	"call %[bpf_ktime_get_ns];"
+	"*(u64*)(r10 - 8) = r0;"
+	"*(u32*)(r10 - 4) = r0;"
+"2:"
+	/* read fp-8, should not be considered safe on second visit */
+	"r1 = *(u64*)(r10 - 8);"
+	/* use r1 in precise context */
+	"if r1 == 42 goto +0;"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+/* stacksafe(): check if STACK_MISC in old state is considered
+ * equivalent to stack spill of a scalar in cur state.
+ */
+SEC("socket")
+__success  __log_level(2)
+__msg("8: (79) r0 = *(u64 *)(r10 -8)")
+__msg("8: safe")
+__msg("processed 11 insns")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void old_stack_misc_vs_cur_scalar(void)
+{
+	asm volatile(
+	/* get a random value for branching */
+	"call %[bpf_ktime_get_ns];"
+	"if r0 == 0 goto 1f;"
+	/* conjure STACK_{MISC,INVALID} at fp-8 */
+	"call %[bpf_ktime_get_ns];"
+	"*(u16*)(r10 - 8) = r0;"
+	"*(u16*)(r10 - 4) = r0;"
+	"goto 2f;"
+"1:"
+	/* conjure scalar at fp-8 */
+	"r0 = 42;"
+	"*(u64*)(r10 - 8) = r0;"
+"2:"
+	/* read fp-8, should be considered safe on second visit */
+	"r0 = *(u64*)(r10 - 8);"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+/* stacksafe(): check that STACK_MISC in old state is not considered
+ * equivalent to stack spill of a non-scalar in cur state.
+ */
+SEC("socket")
+__success  __log_level(2)
+/* verifier should process exit instructions twice:
+ * - once for path entry - label 2;
+ * - once for path entry - label 1 - label 2.
+ */
+__msg("8: (79) r1 = *(u64 *)(r10 -8)")
+__msg("9: (95) exit")
+__msg("from 2 to 7")
+__msg("8: safe")
+__msg("processed 11 insns")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void old_stack_misc_vs_cur_ctx_ptr(void)
+{
+	asm volatile(
+	/* remember context pointer in r9 */
+	"r9 = r1;"
+	/* get a random value for branching */
+	"call %[bpf_ktime_get_ns];"
+	"if r0 == 0 goto 1f;"
+	/* conjure STACK_MISC at fp-8 */
+	"call %[bpf_ktime_get_ns];"
+	"*(u64*)(r10 - 8) = r0;"
+	"*(u32*)(r10 - 4) = r0;"
+	"goto 2f;"
+"1:"
+	/* conjure context pointer in fp-8 */
+	"*(u64*)(r10 - 8) = r9;"
+"2:"
+	/* read fp-8, should not be considered safe on second visit */
+	"r1 = *(u64*)(r10 - 8);"
+	"exit;"
+	:
+	: __imm(bpf_ktime_get_ns)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("stack_noperfmon: reject read of invalid slots")
+__success
+__caps_unpriv(CAP_BPF)
+__failure_unpriv __msg_unpriv("invalid read from stack off -8+1 size 8")
+__naked void stack_noperfmon_reject_invalid_read(void)
+{
+	asm volatile ("					\
+	r2 = 1;						\
+	r6 = r10;					\
+	r6 += -8;					\
+	*(u8 *)(r6 + 0) = r2;				\
+	r2 = *(u64 *)(r6 + 0);				\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("stack_noperfmon: narrow spill onto 64-bit scalar spilled slots")
+__success
+__caps_unpriv(CAP_BPF)
+__success_unpriv
+__naked void stack_noperfmon_spill_32bit_onto_64bit_slot(void)
+{
+	asm volatile("					\
+	r0 = 0;						\
+	*(u64 *)(r10 - 8) = r0;				\
+	*(u32 *)(r10 - 8) = r0;				\
+	exit;						\
+"	:
+	:
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_spin_lock.c b/tools/testing/selftests/bpf/progs/verifier_spin_lock.c
new file mode 100644
index 000000000000..d9d7b05cf6d2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_spin_lock.c
@@ -0,0 +1,559 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/spin_lock.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct val {
+	int cnt;
+	struct bpf_spin_lock l;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct val);
+} map_spin_lock SEC(".maps");
+
+SEC("cgroup/skb")
+__description("spin_lock: test1 success")
+__success __failure_unpriv __msg_unpriv("")
+__retval(0)
+__naked void spin_lock_test1_success(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_spin_lock] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r6 = r0;					\
+	r1 = r0;					\
+	r1 += 4;					\
+	call %[bpf_spin_lock];				\
+	r1 = r6;					\
+	r1 += 4;					\
+	r0 = *(u32*)(r6 + 0);				\
+	call %[bpf_spin_unlock];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_spin_lock),
+	  __imm(bpf_spin_unlock),
+	  __imm_addr(map_spin_lock)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("spin_lock: test2 direct ld/st")
+__failure __msg("cannot be accessed directly")
+__failure_unpriv __msg_unpriv("")
+__naked void lock_test2_direct_ld_st(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_spin_lock] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r6 = r0;					\
+	r1 = r0;					\
+	r1 += 4;					\
+	call %[bpf_spin_lock];				\
+	r1 = r6;					\
+	r1 += 4;					\
+	r0 = *(u32*)(r1 + 0);				\
+	call %[bpf_spin_unlock];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_spin_lock),
+	  __imm(bpf_spin_unlock),
+	  __imm_addr(map_spin_lock)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("spin_lock: test3 direct ld/st")
+__failure __msg("cannot be accessed directly")
+__failure_unpriv __msg_unpriv("")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void lock_test3_direct_ld_st(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_spin_lock] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r6 = r0;					\
+	r1 = r0;					\
+	r1 += 4;					\
+	call %[bpf_spin_lock];				\
+	r1 = r6;					\
+	r1 += 4;					\
+	r0 = *(u32*)(r6 + 1);				\
+	call %[bpf_spin_unlock];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_spin_lock),
+	  __imm(bpf_spin_unlock),
+	  __imm_addr(map_spin_lock)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("spin_lock: test4 direct ld/st")
+__failure __msg("cannot be accessed directly")
+__failure_unpriv __msg_unpriv("")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void lock_test4_direct_ld_st(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_spin_lock] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r6 = r0;					\
+	r1 = r0;					\
+	r1 += 4;					\
+	call %[bpf_spin_lock];				\
+	r1 = r6;					\
+	r1 += 4;					\
+	r0 = *(u16*)(r6 + 3);				\
+	call %[bpf_spin_unlock];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_spin_lock),
+	  __imm(bpf_spin_unlock),
+	  __imm_addr(map_spin_lock)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("spin_lock: test5 call within a locked region")
+__failure __msg("calls are not allowed")
+__failure_unpriv __msg_unpriv("")
+__naked void call_within_a_locked_region(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_spin_lock] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r6 = r0;					\
+	r1 = r0;					\
+	r1 += 4;					\
+	call %[bpf_spin_lock];				\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r6;					\
+	r1 += 4;					\
+	call %[bpf_spin_unlock];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32),
+	  __imm(bpf_map_lookup_elem),
+	  __imm(bpf_spin_lock),
+	  __imm(bpf_spin_unlock),
+	  __imm_addr(map_spin_lock)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("spin_lock: test6 missing unlock")
+__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_spin_lock-ed region")
+__failure_unpriv __msg_unpriv("")
+__naked void spin_lock_test6_missing_unlock(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_spin_lock] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r6 = r0;					\
+	r1 = r0;					\
+	r1 += 4;					\
+	call %[bpf_spin_lock];				\
+	r1 = r6;					\
+	r1 += 4;					\
+	r0 = *(u32*)(r6 + 0);				\
+	if r0 != 0 goto l1_%=;				\
+	call %[bpf_spin_unlock];			\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_spin_lock),
+	  __imm(bpf_spin_unlock),
+	  __imm_addr(map_spin_lock)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("spin_lock: test7 unlock without lock")
+__failure __msg("without taking a lock")
+__failure_unpriv __msg_unpriv("")
+__naked void lock_test7_unlock_without_lock(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_spin_lock] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r6 = r0;					\
+	r1 = r0;					\
+	r1 += 4;					\
+	if r1 != 0 goto l1_%=;				\
+	call %[bpf_spin_lock];				\
+l1_%=:	r1 = r6;					\
+	r1 += 4;					\
+	r0 = *(u32*)(r6 + 0);				\
+	call %[bpf_spin_unlock];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_spin_lock),
+	  __imm(bpf_spin_unlock),
+	  __imm_addr(map_spin_lock)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("spin_lock: test8 double lock")
+__failure __msg("calls are not allowed")
+__failure_unpriv __msg_unpriv("")
+__naked void spin_lock_test8_double_lock(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_spin_lock] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r6 = r0;					\
+	r1 = r0;					\
+	r1 += 4;					\
+	call %[bpf_spin_lock];				\
+	r1 = r6;					\
+	r1 += 4;					\
+	call %[bpf_spin_lock];				\
+	r1 = r6;					\
+	r1 += 4;					\
+	r0 = *(u32*)(r6 + 0);				\
+	call %[bpf_spin_unlock];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_spin_lock),
+	  __imm(bpf_spin_unlock),
+	  __imm_addr(map_spin_lock)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("spin_lock: test9 different lock")
+__failure __msg("unlock of different lock")
+__failure_unpriv __msg_unpriv("")
+__naked void spin_lock_test9_different_lock(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_spin_lock] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r6 = r0;					\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_spin_lock] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l1_%=;				\
+	exit;						\
+l1_%=:	r7 = r0;					\
+	r1 = r6;					\
+	r1 += 4;					\
+	call %[bpf_spin_lock];				\
+	r1 = r7;					\
+	r1 += 4;					\
+	call %[bpf_spin_unlock];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_spin_lock),
+	  __imm(bpf_spin_unlock),
+	  __imm_addr(map_spin_lock)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("spin_lock: test10 lock in subprog without unlock")
+__success
+__failure_unpriv __msg_unpriv("")
+__naked void lock_in_subprog_without_unlock(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_spin_lock] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r6 = r0;					\
+	r1 = r0;					\
+	r1 += 4;					\
+	call lock_in_subprog_without_unlock__1;		\
+	r1 = r6;					\
+	r1 += 4;					\
+	call %[bpf_spin_unlock];			\
+	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_spin_unlock),
+	  __imm_addr(map_spin_lock)
+	: __clobber_all);
+}
+
+static __naked __noinline __attribute__((used))
+void lock_in_subprog_without_unlock__1(void)
+{
+	asm volatile ("					\
+	call %[bpf_spin_lock];				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_spin_lock)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("spin_lock: test11 ld_abs under lock")
+__failure __msg("inside bpf_spin_lock")
+__naked void test11_ld_abs_under_lock(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_spin_lock] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r7 = r0;					\
+	r1 = r0;					\
+	r1 += 4;					\
+	call %[bpf_spin_lock];				\
+	r0 = *(u8*)skb[0];				\
+	r1 = r7;					\
+	r1 += 4;					\
+	call %[bpf_spin_unlock];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_spin_lock),
+	  __imm(bpf_spin_unlock),
+	  __imm_addr(map_spin_lock)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("spin_lock: regsafe compare reg->id for map value")
+__failure __msg("bpf_spin_unlock of different lock")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void reg_id_for_map_value(void)
+{
+	asm volatile ("					\
+	r6 = r1;					\
+	r6 = *(u32*)(r6 + %[__sk_buff_mark]);		\
+	r1 = %[map_spin_lock] ll;			\
+	r9 = r1;					\
+	r2 = 0;						\
+	*(u32*)(r10 - 4) = r2;				\
+	r2 = r10;					\
+	r2 += -4;					\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r7 = r0;					\
+	r1 = r9;					\
+	r2 = r10;					\
+	r2 += -4;					\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l1_%=;				\
+	exit;						\
+l1_%=:	r8 = r0;					\
+	r1 = r7;					\
+	r1 += 4;					\
+	call %[bpf_spin_lock];				\
+	if r6 == 0 goto l2_%=;				\
+	goto l3_%=;					\
+l2_%=:	r7 = r8;					\
+l3_%=:	r1 = r7;					\
+	r1 += 4;					\
+	call %[bpf_spin_unlock];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm(bpf_spin_lock),
+	  __imm(bpf_spin_unlock),
+	  __imm_addr(map_spin_lock),
+	  __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark))
+	: __clobber_all);
+}
+
+/* Make sure that regsafe() compares ids for spin lock records using
+ * check_ids():
+ *  1: r9 = map_lookup_elem(...)  ; r9.id == 1
+ *  2: r8 = map_lookup_elem(...)  ; r8.id == 2
+ *  3: r7 = ktime_get_ns()
+ *  4: r6 = ktime_get_ns()
+ *  5: if r6 > r7 goto <9>
+ *  6: spin_lock(r8)
+ *  7: r9 = r8
+ *  8: goto <10>
+ *  9: spin_lock(r9)
+ * 10: spin_unlock(r9)             ; r9.id == 1 || r9.id == 2 and lock is active,
+ *                                 ; second visit to (10) should be considered safe
+ *                                 ; if check_ids() is used.
+ * 11: exit(0)
+ */
+
+SEC("cgroup/skb")
+__description("spin_lock: regsafe() check_ids() similar id mappings")
+__success __msg("29: safe")
+__failure_unpriv __msg_unpriv("")
+__log_level(2) __retval(0) __flag(BPF_F_TEST_STATE_FREQ)
+__naked void check_ids_similar_id_mappings(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u32*)(r10 - 4) = r1;				\
+	/* r9 = map_lookup_elem(...) */			\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_spin_lock] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r9 = r0;					\
+	/* r8 = map_lookup_elem(...) */			\
+	r2 = r10;					\
+	r2 += -4;					\
+	r1 = %[map_spin_lock] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l1_%=;				\
+	r8 = r0;					\
+	/* r7 = ktime_get_ns() */			\
+	call %[bpf_ktime_get_ns];			\
+	r7 = r0;					\
+	/* r6 = ktime_get_ns() */			\
+	call %[bpf_ktime_get_ns];			\
+	r6 = r0;					\
+	/* if r6 > r7 goto +5      ; no new information about the state is derived from\
+	 *                         ; this check, thus produced verifier states differ\
+	 *                         ; only in 'insn_idx'	\
+	 * spin_lock(r8)				\
+	 * r9 = r8					\
+	 * goto unlock					\
+	 */						\
+	if r6 > r7 goto l2_%=;				\
+	r1 = r8;					\
+	r1 += 4;					\
+	call %[bpf_spin_lock];				\
+	r9 = r8;					\
+	goto l3_%=;					\
+l2_%=:	/* spin_lock(r9) */				\
+	r1 = r9;					\
+	r1 += 4;					\
+	call %[bpf_spin_lock];				\
+l3_%=:	/* spin_unlock(r9) */				\
+	r1 = r9;					\
+	r1 += 4;					\
+	call %[bpf_spin_unlock];			\
+l0_%=:	/* exit(0) */					\
+	r0 = 0;						\
+l1_%=:	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm(bpf_map_lookup_elem),
+	  __imm(bpf_spin_lock),
+	  __imm(bpf_spin_unlock),
+	  __imm_addr(map_spin_lock)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("spin_lock: loop within a locked region")
+__success __failure_unpriv __msg_unpriv("")
+__retval(0)
+int bpf_loop_inside_locked_region(void)
+{
+	const int zero = 0;
+	struct val *val;
+	int i, j = 0;
+
+	val = bpf_map_lookup_elem(&map_spin_lock, &zero);
+	if (!val)
+		return -1;
+
+	bpf_spin_lock(&val->l);
+	bpf_for(i, 0, 10) {
+		j++;
+		/* Silence "unused variable" warnings. */
+		if (j == 10)
+			break;
+	}
+	bpf_spin_unlock(&val->l);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c b/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c
new file mode 100644
index 000000000000..24aabc6083fd
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_stack_ptr.c
@@ -0,0 +1,536 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/stack_ptr.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <limits.h>
+#include "bpf_misc.h"
+
+#define MAX_ENTRIES 11
+
+struct test_val {
+	unsigned int index;
+	int foo[MAX_ENTRIES];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct test_val);
+} map_array_48b SEC(".maps");
+
+SEC("socket")
+__description("PTR_TO_STACK store/load")
+__success __success_unpriv __retval(0xfaceb00c)
+__naked void ptr_to_stack_store_load(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -10;					\
+	r0 = 0xfaceb00c;				\
+	*(u64*)(r1 + 2) = r0;				\
+	r0 = *(u64*)(r1 + 2);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK store/load - bad alignment on off")
+__failure __msg("misaligned stack access off 0+-8+2 size 8")
+__failure_unpriv
+__naked void load_bad_alignment_on_off(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -8;					\
+	r0 = 0xfaceb00c;				\
+	*(u64*)(r1 + 2) = r0;				\
+	r0 = *(u64*)(r1 + 2);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK store/load - bad alignment on reg")
+__failure __msg("misaligned stack access off 0+-10+8 size 8")
+__failure_unpriv
+__naked void load_bad_alignment_on_reg(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -10;					\
+	r0 = 0xfaceb00c;				\
+	*(u64*)(r1 + 8) = r0;				\
+	r0 = *(u64*)(r1 + 8);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK store/load - out of bounds low")
+__failure __msg("invalid write to stack R1 off=-79992 size=8")
+__msg_unpriv("R1 stack pointer arithmetic goes out of range")
+__naked void load_out_of_bounds_low(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -80000;					\
+	r0 = 0xfaceb00c;				\
+	*(u64*)(r1 + 8) = r0;				\
+	r0 = *(u64*)(r1 + 8);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK store/load - out of bounds high")
+__failure __msg("invalid write to stack R1 off=0 size=8")
+__failure_unpriv
+__naked void load_out_of_bounds_high(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -8;					\
+	r0 = 0xfaceb00c;				\
+	*(u64*)(r1 + 8) = r0;				\
+	r0 = *(u64*)(r1 + 8);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK check high 1")
+__success __success_unpriv __retval(42)
+__naked void to_stack_check_high_1(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -1;					\
+	r0 = 42;					\
+	*(u8*)(r1 + 0) = r0;				\
+	r0 = *(u8*)(r1 + 0);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK check high 2")
+__success __success_unpriv __retval(42)
+__naked void to_stack_check_high_2(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r0 = 42;					\
+	*(u8*)(r1 - 1) = r0;				\
+	r0 = *(u8*)(r1 - 1);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK check high 3")
+__success __failure_unpriv
+__msg_unpriv("R1 stack pointer arithmetic goes out of range")
+__retval(42)
+__naked void to_stack_check_high_3(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += 0;					\
+	r0 = 42;					\
+	*(u8*)(r1 - 1) = r0;				\
+	r0 = *(u8*)(r1 - 1);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK check high 4")
+__failure __msg("invalid write to stack R1 off=0 size=1")
+__msg_unpriv("R1 stack pointer arithmetic goes out of range")
+__naked void to_stack_check_high_4(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += 0;					\
+	r0 = 42;					\
+	*(u8*)(r1 + 0) = r0;				\
+	r0 = *(u8*)(r1 + 0);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK check high 5")
+__failure __msg("invalid write to stack R1")
+__msg_unpriv("R1 stack pointer arithmetic goes out of range")
+__naked void to_stack_check_high_5(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += %[__imm_0];				\
+	r0 = 42;					\
+	*(u8*)(r1 + 0) = r0;				\
+	r0 = *(u8*)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, (1 << 29) - 1)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK check high 6")
+__failure __msg("invalid write to stack")
+__msg_unpriv("R1 stack pointer arithmetic goes out of range")
+__naked void to_stack_check_high_6(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += %[__imm_0];				\
+	r0 = 42;					\
+	*(u8*)(r1 + %[shrt_max]) = r0;			\
+	r0 = *(u8*)(r1 + %[shrt_max]);			\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, (1 << 29) - 1),
+	  __imm_const(shrt_max, SHRT_MAX)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK check high 7")
+__failure __msg("fp pointer offset")
+__msg_unpriv("R1 stack pointer arithmetic goes out of range")
+__naked void to_stack_check_high_7(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += %[__imm_0];				\
+	r1 += %[__imm_0];				\
+	r0 = 42;					\
+	*(u8*)(r1 + %[shrt_max]) = r0;			\
+	r0 = *(u8*)(r1 + %[shrt_max]);			\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, (1 << 29) - 1),
+	  __imm_const(shrt_max, SHRT_MAX)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK check low 1")
+__success __success_unpriv __retval(42)
+__naked void to_stack_check_low_1(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -512;					\
+	r0 = 42;					\
+	*(u8*)(r1 + 0) = r0;				\
+	r0 = *(u8*)(r1 + 0);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK check low 2")
+__success __failure_unpriv
+__msg_unpriv("R1 stack pointer arithmetic goes out of range")
+__retval(42)
+__naked void to_stack_check_low_2(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -513;					\
+	r0 = 42;					\
+	*(u8*)(r1 + 1) = r0;				\
+	r0 = *(u8*)(r1 + 1);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK check low 3")
+__failure __msg("invalid write to stack R1 off=-513 size=1")
+__msg_unpriv("R1 stack pointer arithmetic goes out of range")
+__naked void to_stack_check_low_3(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -513;					\
+	r0 = 42;					\
+	*(u8*)(r1 + 0) = r0;				\
+	r0 = *(u8*)(r1 + 0);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK check low 4")
+__failure __msg("math between fp pointer")
+__failure_unpriv
+__naked void to_stack_check_low_4(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += %[int_min];				\
+	r0 = 42;					\
+	*(u8*)(r1 + 0) = r0;				\
+	r0 = *(u8*)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm_const(int_min, INT_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK check low 5")
+__failure __msg("invalid write to stack")
+__msg_unpriv("R1 stack pointer arithmetic goes out of range")
+__naked void to_stack_check_low_5(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += %[__imm_0];				\
+	r0 = 42;					\
+	*(u8*)(r1 + 0) = r0;				\
+	r0 = *(u8*)(r1 + 0);				\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, -((1 << 29) - 1))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK check low 6")
+__failure __msg("invalid write to stack")
+__msg_unpriv("R1 stack pointer arithmetic goes out of range")
+__naked void to_stack_check_low_6(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += %[__imm_0];				\
+	r0 = 42;					\
+	*(u8*)(r1  %[shrt_min]) = r0;			\
+	r0 = *(u8*)(r1  %[shrt_min]);			\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, -((1 << 29) - 1)),
+	  __imm_const(shrt_min, SHRT_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK check low 7")
+__failure __msg("fp pointer offset")
+__msg_unpriv("R1 stack pointer arithmetic goes out of range")
+__naked void to_stack_check_low_7(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += %[__imm_0];				\
+	r1 += %[__imm_0];				\
+	r0 = 42;					\
+	*(u8*)(r1  %[shrt_min]) = r0;			\
+	r0 = *(u8*)(r1  %[shrt_min]);			\
+	exit;						\
+"	:
+	: __imm_const(__imm_0, -((1 << 29) - 1)),
+	  __imm_const(shrt_min, SHRT_MIN)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK mixed reg/k, 1")
+__success __success_unpriv __retval(42)
+__naked void stack_mixed_reg_k_1(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -3;					\
+	r2 = -3;					\
+	r1 += r2;					\
+	r0 = 42;					\
+	*(u8*)(r1 + 0) = r0;				\
+	r0 = *(u8*)(r1 + 0);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK mixed reg/k, 2")
+__success __success_unpriv __retval(42)
+__naked void stack_mixed_reg_k_2(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	*(u64*)(r10 - 8) = r0;				\
+	r0 = 0;						\
+	*(u64*)(r10 - 16) = r0;				\
+	r1 = r10;					\
+	r1 += -3;					\
+	r2 = -3;					\
+	r1 += r2;					\
+	r0 = 42;					\
+	*(u8*)(r1 + 0) = r0;				\
+	r5 = r10;					\
+	r0 = *(u8*)(r5 - 6);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK mixed reg/k, 3")
+__success __success_unpriv __retval(-3)
+__naked void stack_mixed_reg_k_3(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -3;					\
+	r2 = -3;					\
+	r1 += r2;					\
+	r0 = 42;					\
+	*(u8*)(r1 + 0) = r0;				\
+	r0 = r2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK reg")
+__success __success_unpriv __retval(42)
+__naked void ptr_to_stack_reg(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r2 = -3;					\
+	r1 += r2;					\
+	r0 = 42;					\
+	*(u8*)(r1 + 0) = r0;				\
+	r0 = *(u8*)(r1 + 0);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("stack pointer arithmetic")
+__success __success_unpriv __retval(0)
+__naked void stack_pointer_arithmetic(void)
+{
+	asm volatile ("					\
+	r1 = 4;						\
+	goto l0_%=;					\
+l0_%=:	r7 = r10;					\
+	r7 += -10;					\
+	r7 += -10;					\
+	r2 = r7;					\
+	r2 += r1;					\
+	r0 = 0;						\
+	*(u32*)(r2 + 4) = r0;				\
+	r2 = r7;					\
+	r2 += 8;					\
+	r0 = 0;						\
+	*(u32*)(r2 + 4) = r0;				\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tc")
+__description("store PTR_TO_STACK in R10 to array map using BPF_B")
+__success __retval(42)
+__naked void array_map_using_bpf_b(void)
+{
+	asm volatile ("					\
+	/* Load pointer to map. */			\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	r0 = 2;						\
+	exit;						\
+l0_%=:	r1 = r0;					\
+	/* Copy R10 to R9. */				\
+	r9 = r10;					\
+	/* Pollute other registers with unaligned values. */\
+	r2 = -1;					\
+	r3 = -1;					\
+	r4 = -1;					\
+	r5 = -1;					\
+	r6 = -1;					\
+	r7 = -1;					\
+	r8 = -1;					\
+	/* Store both R9 and R10 with BPF_B and read back. */\
+	*(u8*)(r1 + 0) = r10;				\
+	r2 = *(u8*)(r1 + 0);				\
+	*(u8*)(r1 + 0) = r9;				\
+	r3 = *(u8*)(r1 + 0);				\
+	/* Should read back as same value. */		\
+	if r2 == r3 goto l1_%=;				\
+	r0 = 1;						\
+	exit;						\
+l1_%=:	r0 = 42;					\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK stack size > 512")
+__failure __msg("invalid write to stack R1 off=-520 size=8")
+__naked void stack_check_size_gt_512(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -520;					\
+	r0 = 42;					\
+	*(u64*)(r1 + 0) = r0;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+#ifdef __BPF_FEATURE_MAY_GOTO
+SEC("socket")
+__description("PTR_TO_STACK stack size 512 with may_goto with jit")
+__load_if_JITed()
+__success __retval(42)
+__naked void stack_check_size_512_with_may_goto_jit(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -512;					\
+	r0 = 42;					\
+	*(u32*)(r1 + 0) = r0;				\
+	may_goto l0_%=;					\
+	r2 = 100;					\
+	l0_%=:						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("PTR_TO_STACK stack size 512 with may_goto without jit")
+__load_if_no_JITed()
+__failure __msg("stack size 520(extra 8) is too large")
+__naked void stack_check_size_512_with_may_goto(void)
+{
+	asm volatile ("					\
+	r1 = r10;					\
+	r1 += -512;					\
+	r0 = 42;					\
+	*(u32*)(r1 + 0) = r0;				\
+	may_goto l0_%=;					\
+	r2 = 100;					\
+	l0_%=:						\
+	exit;						\
+"	::: __clobber_all);
+}
+#endif
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_store_release.c b/tools/testing/selftests/bpf/progs/verifier_store_release.c
new file mode 100644
index 000000000000..72f1eb006074
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_store_release.c
@@ -0,0 +1,301 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Google LLC. */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
+#include "bpf_misc.h"
+
+#ifdef CAN_USE_LOAD_ACQ_STORE_REL
+
+SEC("socket")
+__description("store-release, 8-bit")
+__success __success_unpriv __retval(0)
+__naked void store_release_8(void)
+{
+	asm volatile (
+	"r0 = 0;"
+	"w1 = 0x12;"
+	".8byte %[store_release_insn];" // store_release((u8 *)(r10 - 1), w1);
+	"w2 = *(u8 *)(r10 - 1);"
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_B, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -1))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("store-release, 16-bit")
+__success __success_unpriv __retval(0)
+__naked void store_release_16(void)
+{
+	asm volatile (
+	"r0 = 0;"
+	"w1 = 0x1234;"
+	".8byte %[store_release_insn];" // store_release((u16 *)(r10 - 2), w1);
+	"w2 = *(u16 *)(r10 - 2);"
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_H, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -2))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("store-release, 32-bit")
+__success __success_unpriv __retval(0)
+__naked void store_release_32(void)
+{
+	asm volatile (
+	"r0 = 0;"
+	"w1 = 0x12345678;"
+	".8byte %[store_release_insn];" // store_release((u32 *)(r10 - 4), w1);
+	"w2 = *(u32 *)(r10 - 4);"
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_W, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -4))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("store-release, 64-bit")
+__success __success_unpriv __retval(0)
+__naked void store_release_64(void)
+{
+	asm volatile (
+	"r0 = 0;"
+	"r1 = 0x1234567890abcdef ll;"
+	".8byte %[store_release_insn];" // store_release((u64 *)(r10 - 8), r1);
+	"r2 = *(u64 *)(r10 - 8);"
+	"if r2 == r1 goto 1f;"
+	"r0 = 1;"
+"1:"
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -8))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("store-release with uninitialized src_reg")
+__failure __failure_unpriv __msg("R2 !read_ok")
+__naked void store_release_with_uninitialized_src_reg(void)
+{
+	asm volatile (
+	".8byte %[store_release_insn];" // store_release((u64 *)(r10 - 8), r2);
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_10, BPF_REG_2, -8))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("store-release with uninitialized dst_reg")
+__failure __failure_unpriv __msg("R2 !read_ok")
+__naked void store_release_with_uninitialized_dst_reg(void)
+{
+	asm volatile (
+	"r1 = 0;"
+	".8byte %[store_release_insn];" // store_release((u64 *)(r2 - 8), r1);
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_2, BPF_REG_1, -8))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("store-release with non-pointer dst_reg")
+__failure __failure_unpriv __msg("R1 invalid mem access 'scalar'")
+__naked void store_release_with_non_pointer_dst_reg(void)
+{
+	asm volatile (
+	"r1 = 0;"
+	".8byte %[store_release_insn];" // store_release((u64 *)(r1 + 0), r1);
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_1, BPF_REG_1, 0))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("misaligned store-release")
+__failure __failure_unpriv __msg("misaligned stack access off")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void store_release_misaligned(void)
+{
+	asm volatile (
+	"w0 = 0;"
+	".8byte %[store_release_insn];" // store_release((u32 *)(r10 - 5), w0);
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_W, BPF_STORE_REL, BPF_REG_10, BPF_REG_0, -5))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("store-release to ctx pointer")
+__failure __failure_unpriv __msg("BPF_ATOMIC stores into R1 ctx is not allowed")
+__naked void store_release_to_ctx_pointer(void)
+{
+	asm volatile (
+	"w0 = 0;"
+	// store_release((u8 *)(r1 + offsetof(struct __sk_buff, cb[0])), w0);
+	".8byte %[store_release_insn];"
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_B, BPF_STORE_REL, BPF_REG_1, BPF_REG_0,
+				   offsetof(struct __sk_buff, cb[0])))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("store-release to pkt pointer")
+__failure __msg("BPF_ATOMIC stores into R2 pkt is not allowed")
+__naked void store_release_to_pkt_pointer(void)
+{
+	asm volatile (
+	"w0 = 0;"
+	"r2 = *(u32 *)(r1 + %[xdp_md_data]);"
+	"r3 = *(u32 *)(r1 + %[xdp_md_data_end]);"
+	"r1 = r2;"
+	"r1 += 8;"
+	"if r1 >= r3 goto l0_%=;"
+	".8byte %[store_release_insn];" // store_release((u8 *)(r2 + 0), w0);
+"l0_%=:  r0 = 0;"
+	"exit;"
+	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end)),
+	  __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_B, BPF_STORE_REL, BPF_REG_2, BPF_REG_0, 0))
+	: __clobber_all);
+}
+
+SEC("flow_dissector")
+__description("store-release to flow_keys pointer")
+__failure __msg("BPF_ATOMIC stores into R2 flow_keys is not allowed")
+__naked void store_release_to_flow_keys_pointer(void)
+{
+	asm volatile (
+	"w0 = 0;"
+	"r2 = *(u64 *)(r1 + %[__sk_buff_flow_keys]);"
+	".8byte %[store_release_insn];" // store_release((u8 *)(r2 + 0), w0);
+	"exit;"
+	:
+	: __imm_const(__sk_buff_flow_keys,
+		      offsetof(struct __sk_buff, flow_keys)),
+	  __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_B, BPF_STORE_REL, BPF_REG_2, BPF_REG_0, 0))
+	: __clobber_all);
+}
+
+SEC("sk_reuseport")
+__description("store-release to sock pointer")
+__failure __msg("R2 cannot write into sock")
+__naked void store_release_to_sock_pointer(void)
+{
+	asm volatile (
+	"w0 = 0;"
+	"r2 = *(u64 *)(r1 + %[sk_reuseport_md_sk]);"
+	".8byte %[store_release_insn];" // store_release((u8 *)(r2 + 0), w0);
+	"exit;"
+	:
+	: __imm_const(sk_reuseport_md_sk, offsetof(struct sk_reuseport_md, sk)),
+	  __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_B, BPF_STORE_REL, BPF_REG_2, BPF_REG_0, 0))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("store-release, leak pointer to stack")
+__success __success_unpriv __retval(0)
+__naked void store_release_leak_pointer_to_stack(void)
+{
+	asm volatile (
+	".8byte %[store_release_insn];" // store_release((u64 *)(r10 - 8), r1);
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_10, BPF_REG_1, -8))
+	: __clobber_all);
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, long long);
+} map_hash_8b SEC(".maps");
+
+SEC("socket")
+__description("store-release, leak pointer to map")
+__success __retval(0)
+__failure_unpriv __msg_unpriv("R6 leaks addr into map")
+__naked void store_release_leak_pointer_to_map(void)
+{
+	asm volatile (
+	"r6 = r1;"
+	"r1 = %[map_hash_8b] ll;"
+	"r2 = 0;"
+	"*(u64 *)(r10 - 8) = r2;"
+	"r2 = r10;"
+	"r2 += -8;"
+	"call %[bpf_map_lookup_elem];"
+	"if r0 == 0 goto l0_%=;"
+	".8byte %[store_release_insn];" // store_release((u64 *)(r0 + 0), r6);
+"l0_%=:"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm_addr(map_hash_8b),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, BPF_REG_0, BPF_REG_6, 0))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("store-release with invalid register R15")
+__failure __failure_unpriv __msg("R15 is invalid")
+__naked void store_release_with_invalid_reg(void)
+{
+	asm volatile (
+	".8byte %[store_release_insn];" // store_release((u64 *)(r15 + 0), r1);
+	"exit;"
+	:
+	: __imm_insn(store_release_insn,
+		     BPF_ATOMIC_OP(BPF_DW, BPF_STORE_REL, 15 /* invalid reg */, BPF_REG_1, 0))
+	: __clobber_all);
+}
+
+#else /* CAN_USE_LOAD_ACQ_STORE_REL */
+
+SEC("socket")
+__description("Clang version < 18, ENABLE_ATOMICS_TESTS not defined, and/or JIT doesn't support store-release, use a dummy test")
+__success
+int dummy_test(void)
+{
+	return 0;
+}
+
+#endif /* CAN_USE_LOAD_ACQ_STORE_REL */
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
new file mode 100644
index 000000000000..61886ed554de
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c
@@ -0,0 +1,849 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+#include <errno.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include <../../../tools/include/linux/filter.h>
+
+int vals[] SEC(".data.vals") = {1, 2, 3, 4};
+
+__naked __noinline __used
+static unsigned long identity_subprog()
+{
+	/* the simplest *static* 64-bit identity function */
+	asm volatile (
+		"r0 = r1;"
+		"exit;"
+	);
+}
+
+__noinline __used
+unsigned long global_identity_subprog(__u64 x)
+{
+	/* the simplest *global* 64-bit identity function */
+	return x;
+}
+
+__naked __noinline __used
+static unsigned long callback_subprog()
+{
+	/* the simplest callback function */
+	asm volatile (
+		"r0 = 0;"
+		"exit;"
+	);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("7: (0f) r1 += r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 6: (bf) r1 = r7")
+__msg("mark_precise: frame0: regs=r0 stack= before 5: (27) r0 *= 4")
+__msg("mark_precise: frame0: regs=r0 stack= before 11: (95) exit")
+__msg("mark_precise: frame1: regs=r0 stack= before 10: (bf) r0 = r1")
+__msg("mark_precise: frame1: regs=r1 stack= before 4: (85) call pc+5")
+__msg("mark_precise: frame0: regs=r1 stack= before 3: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3")
+__naked int subprog_result_precise(void)
+{
+	asm volatile (
+		"r6 = 3;"
+		/* pass r6 through r1 into subprog to get it back as r0;
+		 * this whole chain will have to be marked as precise later
+		 */
+		"r1 = r6;"
+		"call identity_subprog;"
+		/* now use subprog's returned value (which is a
+		 * r6 -> r1 -> r0 chain), as index into vals array, forcing
+		 * all of that to be known precisely
+		 */
+		"r0 *= 4;"
+		"r1 = %[vals];"
+		/* here r0->r1->r6 chain is forced to be precise and has to be
+		 * propagated back to the beginning, including through the
+		 * subprog call
+		 */
+		"r1 += r0;"
+		"r0 = *(u32 *)(r1 + 0);"
+		"exit;"
+		:
+		: __imm_ptr(vals)
+		: __clobber_common, "r6"
+	);
+}
+
+__naked __noinline __used
+static unsigned long fp_leaking_subprog()
+{
+	asm volatile (
+		".8byte %[r0_eq_r10_cast_s8];"
+		"exit;"
+		:: __imm_insn(r0_eq_r10_cast_s8, BPF_MOVSX64_REG(BPF_REG_0, BPF_REG_10, 8))
+	);
+}
+
+__naked __noinline __used
+static unsigned long sneaky_fp_leaking_subprog()
+{
+	asm volatile (
+		"r1 = r10;"
+		".8byte %[r0_eq_r1_cast_s8];"
+		"exit;"
+		:: __imm_insn(r0_eq_r1_cast_s8, BPF_MOVSX64_REG(BPF_REG_0, BPF_REG_1, 8))
+	);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("6: (0f) r1 += r0")
+__msg("mark_precise: frame0: last_idx 6 first_idx 0 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r0 stack= before 5: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs=r0 stack= before 4: (27) r0 *= 4")
+__msg("mark_precise: frame0: regs=r0 stack= before 3: (57) r0 &= 3")
+__msg("mark_precise: frame0: regs=r0 stack= before 10: (95) exit")
+__msg("mark_precise: frame1: regs=r0 stack= before 9: (bf) r0 = (s8)r10")
+__msg("7: R0=scalar")
+__naked int fp_precise_subprog_result(void)
+{
+	asm volatile (
+		"call fp_leaking_subprog;"
+		/* use subprog's returned value (which is derived from r10=fp
+		 * register), as index into vals array, forcing all of that to
+		 * be known precisely
+		 */
+		"r0 &= 3;"
+		"r0 *= 4;"
+		"r1 = %[vals];"
+		/* force precision marking */
+		"r1 += r0;"
+		"r0 = *(u32 *)(r1 + 0);"
+		"exit;"
+		:
+		: __imm_ptr(vals)
+		: __clobber_common
+	);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("6: (0f) r1 += r0")
+__msg("mark_precise: frame0: last_idx 6 first_idx 0 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r0 stack= before 5: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs=r0 stack= before 4: (27) r0 *= 4")
+__msg("mark_precise: frame0: regs=r0 stack= before 3: (57) r0 &= 3")
+__msg("mark_precise: frame0: regs=r0 stack= before 11: (95) exit")
+__msg("mark_precise: frame1: regs=r0 stack= before 10: (bf) r0 = (s8)r1")
+/* here r1 is marked precise, even though it's fp register, but that's fine
+ * because by the time we get out of subprogram it has to be derived from r10
+ * anyways, at which point we'll break precision chain
+ */
+__msg("mark_precise: frame1: regs=r1 stack= before 9: (bf) r1 = r10")
+__msg("7: R0=scalar")
+__naked int sneaky_fp_precise_subprog_result(void)
+{
+	asm volatile (
+		"call sneaky_fp_leaking_subprog;"
+		/* use subprog's returned value (which is derived from r10=fp
+		 * register), as index into vals array, forcing all of that to
+		 * be known precisely
+		 */
+		"r0 &= 3;"
+		"r0 *= 4;"
+		"r1 = %[vals];"
+		/* force precision marking */
+		"r1 += r0;"
+		"r0 = *(u32 *)(r1 + 0);"
+		"exit;"
+		:
+		: __imm_ptr(vals)
+		: __clobber_common
+	);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("9: (0f) r1 += r0")
+__msg("mark_precise: frame0: last_idx 9 first_idx 0")
+__msg("mark_precise: frame0: regs=r0 stack= before 8: (bf) r1 = r7")
+__msg("mark_precise: frame0: regs=r0 stack= before 7: (27) r0 *= 4")
+__msg("mark_precise: frame0: regs=r0 stack= before 5: (a5) if r0 < 0x4 goto pc+1")
+__msg("mark_precise: frame0: regs=r0 stack= before 4: (85) call pc+7")
+__naked int global_subprog_result_precise(void)
+{
+	asm volatile (
+		"r6 = 3;"
+		/* pass r6 through r1 into subprog to get it back as r0;
+		 * given global_identity_subprog is global, precision won't
+		 * propagate all the way back to r6
+		 */
+		"r1 = r6;"
+		"call global_identity_subprog;"
+		/* now use subprog's returned value (which is unknown now, so
+		 * we need to clamp it), as index into vals array, forcing r0
+		 * to be marked precise (with no effect on r6, though)
+		 */
+		"if r0 < %[vals_arr_sz] goto 1f;"
+		"r0 = %[vals_arr_sz] - 1;"
+	"1:"
+		"r0 *= 4;"
+		"r1 = %[vals];"
+		/* here r0 is forced to be precise and has to be
+		 * propagated back to the global subprog call, but it
+		 * shouldn't go all the way to mark r6 as precise
+		 */
+		"r1 += r0;"
+		"r0 = *(u32 *)(r1 + 0);"
+		"exit;"
+		:
+		: __imm_ptr(vals),
+		  __imm_const(vals_arr_sz, ARRAY_SIZE(vals))
+		: __clobber_common, "r6"
+	);
+}
+
+__naked __noinline __used
+static unsigned long loop_callback_bad()
+{
+	/* bpf_loop() callback that can return values outside of [0, 1] range */
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+		"if r0 s> 1000 goto 1f;"
+		"r0 = 0;"
+	"1:"
+		"goto +0;" /* checkpoint */
+		/* bpf_loop() expects [0, 1] values, so branch above skipping
+		 * r0 = 0; should lead to a failure, but if exit instruction
+		 * doesn't enforce r0's precision, this callback will be
+		 * successfully verified
+		 */
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32)
+		: __clobber_common
+	);
+}
+
+SEC("?raw_tp")
+__failure __log_level(2)
+__flag(BPF_F_TEST_STATE_FREQ)
+/* check that fallthrough code path marks r0 as precise */
+__msg("mark_precise: frame1: regs=r0 stack= before 11: (b7) r0 = 0")
+/* check that we have branch code path doing its own validation */
+__msg("from 10 to 12: frame1: R0=scalar(smin=umin=1001")
+/* check that branch code path marks r0 as precise, before failing */
+__msg("mark_precise: frame1: regs=r0 stack= before 9: (85) call bpf_get_prandom_u32#7")
+__msg("At callback return the register R0 has smin=1001 should have been in [0, 1]")
+__naked int callback_precise_return_fail(void)
+{
+	asm volatile (
+		"r1 = 1;"			/* nr_loops */
+		"r2 = %[loop_callback_bad];"	/* callback_fn */
+		"r3 = 0;"			/* callback_ctx */
+		"r4 = 0;"			/* flags */
+		"call %[bpf_loop];"
+
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm_ptr(loop_callback_bad),
+		  __imm(bpf_loop)
+		: __clobber_common
+	);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+/* First simulated path does not include callback body,
+ * r1 and r4 are always precise for bpf_loop() calls.
+ */
+__msg("9: (85) call bpf_loop#181")
+__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1")
+__msg("mark_precise: frame0: parent state regs=r4 stack=:")
+__msg("mark_precise: frame0: last_idx 8 first_idx 0 subseq_idx 9")
+__msg("mark_precise: frame0: regs=r4 stack= before 8: (b7) r4 = 0")
+__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1")
+__msg("mark_precise: frame0: parent state regs=r1 stack=:")
+__msg("mark_precise: frame0: last_idx 8 first_idx 0 subseq_idx 9")
+__msg("mark_precise: frame0: regs=r1 stack= before 8: (b7) r4 = 0")
+__msg("mark_precise: frame0: regs=r1 stack= before 7: (b7) r3 = 0")
+__msg("mark_precise: frame0: regs=r1 stack= before 6: (bf) r2 = r8")
+__msg("mark_precise: frame0: regs=r1 stack= before 5: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3")
+/* r6 precision propagation */
+__msg("14: (0f) r1 += r6")
+__msg("mark_precise: frame0: last_idx 14 first_idx 9")
+__msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7")
+__msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4")
+__msg("mark_precise: frame0: regs=r6 stack= before 11: (25) if r6 > 0x3 goto pc+4")
+__msg("mark_precise: frame0: regs=r0,r6 stack= before 10: (bf) r6 = r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 9: (85) call bpf_loop")
+/* State entering callback body popped from states stack */
+__msg("from 9 to 17: frame1:")
+__msg("17: frame1: R1=scalar() R2=0 R10=fp0 cb")
+__msg("17: (b7) r0 = 0")
+__msg("18: (95) exit")
+__msg("returning from callee:")
+__msg("to caller at 9:")
+__msg("frame 0: propagating r1,r4")
+__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r1,r4 stack= before 18: (95) exit")
+__msg("from 18 to 9: safe")
+__naked int callback_result_precise(void)
+{
+	asm volatile (
+		"r6 = 3;"
+
+		/* call subprog and use result; r0 shouldn't propagate back to
+		 * callback_subprog
+		 */
+		"r1 = r6;"			/* nr_loops */
+		"r2 = %[callback_subprog];"	/* callback_fn */
+		"r3 = 0;"			/* callback_ctx */
+		"r4 = 0;"			/* flags */
+		"call %[bpf_loop];"
+
+		"r6 = r0;"
+		"if r6 > 3 goto 1f;"
+		"r6 *= 4;"
+		"r1 = %[vals];"
+		/* here r6 is forced to be precise and has to be propagated
+		 * back to the bpf_loop() call, but not beyond
+		 */
+		"r1 += r6;"
+		"r0 = *(u32 *)(r1 + 0);"
+	"1:"
+		"exit;"
+		:
+		: __imm_ptr(vals),
+		  __imm_ptr(callback_subprog),
+		  __imm(bpf_loop)
+		: __clobber_common, "r6"
+	);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("7: (0f) r1 += r6")
+__msg("mark_precise: frame0: last_idx 7 first_idx 0")
+__msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r1 = r7")
+__msg("mark_precise: frame0: regs=r6 stack= before 5: (27) r6 *= 4")
+__msg("mark_precise: frame0: regs=r6 stack= before 11: (95) exit")
+__msg("mark_precise: frame1: regs= stack= before 10: (bf) r0 = r1")
+__msg("mark_precise: frame1: regs= stack= before 4: (85) call pc+5")
+__msg("mark_precise: frame0: regs=r6 stack= before 3: (b7) r1 = 0")
+__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3")
+__naked int parent_callee_saved_reg_precise(void)
+{
+	asm volatile (
+		"r6 = 3;"
+
+		/* call subprog and ignore result; we need this call only to
+		 * complicate jump history
+		 */
+		"r1 = 0;"
+		"call identity_subprog;"
+
+		"r6 *= 4;"
+		"r1 = %[vals];"
+		/* here r6 is forced to be precise and has to be propagated
+		 * back to the beginning, handling (and ignoring) subprog call
+		 */
+		"r1 += r6;"
+		"r0 = *(u32 *)(r1 + 0);"
+		"exit;"
+		:
+		: __imm_ptr(vals)
+		: __clobber_common, "r6"
+	);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("7: (0f) r1 += r6")
+__msg("mark_precise: frame0: last_idx 7 first_idx 0")
+__msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r1 = r7")
+__msg("mark_precise: frame0: regs=r6 stack= before 5: (27) r6 *= 4")
+__msg("mark_precise: frame0: regs=r6 stack= before 4: (85) call pc+5")
+__msg("mark_precise: frame0: regs=r6 stack= before 3: (b7) r1 = 0")
+__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3")
+__naked int parent_callee_saved_reg_precise_global(void)
+{
+	asm volatile (
+		"r6 = 3;"
+
+		/* call subprog and ignore result; we need this call only to
+		 * complicate jump history
+		 */
+		"r1 = 0;"
+		"call global_identity_subprog;"
+
+		"r6 *= 4;"
+		"r1 = %[vals];"
+		/* here r6 is forced to be precise and has to be propagated
+		 * back to the beginning, handling (and ignoring) subprog call
+		 */
+		"r1 += r6;"
+		"r0 = *(u32 *)(r1 + 0);"
+		"exit;"
+		:
+		: __imm_ptr(vals)
+		: __clobber_common, "r6"
+	);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+/* First simulated path does not include callback body */
+__msg("12: (0f) r1 += r6")
+__msg("mark_precise: frame0: last_idx 12 first_idx 9")
+__msg("mark_precise: frame0: regs=r6 stack= before 11: (bf) r1 = r7")
+__msg("mark_precise: frame0: regs=r6 stack= before 10: (27) r6 *= 4")
+__msg("mark_precise: frame0: regs=r6 stack= before 9: (85) call bpf_loop")
+__msg("mark_precise: frame0: parent state regs=r6 stack=:")
+__msg("mark_precise: frame0: last_idx 8 first_idx 0 subseq_idx 9")
+__msg("mark_precise: frame0: regs=r6 stack= before 8: (b7) r4 = 0")
+__msg("mark_precise: frame0: regs=r6 stack= before 7: (b7) r3 = 0")
+__msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r2 = r8")
+__msg("mark_precise: frame0: regs=r6 stack= before 5: (b7) r1 = 1")
+__msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3")
+/* State entering callback body popped from states stack */
+__msg("from 9 to 15: frame1:")
+__msg("15: frame1: R1=scalar() R2=0 R10=fp0 cb")
+__msg("15: (b7) r0 = 0")
+__msg("16: (95) exit")
+__msg("returning from callee:")
+__msg("to caller at 9:")
+/* r1, r4 are always precise for bpf_loop(),
+ * r6 was marked before backtracking to callback body.
+ */
+__msg("frame 0: propagating r1,r4,r6")
+__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r1,r4,r6 stack= before 16: (95) exit")
+__msg("mark_precise: frame1: regs= stack= before 15: (b7) r0 = 0")
+__msg("mark_precise: frame1: regs= stack= before 9: (85) call bpf_loop")
+__msg("mark_precise: frame0: parent state regs= stack=:")
+__msg("from 16 to 9: safe")
+__naked int parent_callee_saved_reg_precise_with_callback(void)
+{
+	asm volatile (
+		"r6 = 3;"
+
+		/* call subprog and ignore result; we need this call only to
+		 * complicate jump history
+		 */
+		"r1 = 1;"			/* nr_loops */
+		"r2 = %[callback_subprog];"	/* callback_fn */
+		"r3 = 0;"			/* callback_ctx */
+		"r4 = 0;"			/* flags */
+		"call %[bpf_loop];"
+
+		"r6 *= 4;"
+		"r1 = %[vals];"
+		/* here r6 is forced to be precise and has to be propagated
+		 * back to the beginning, handling (and ignoring) callback call
+		 */
+		"r1 += r6;"
+		"r0 = *(u32 *)(r1 + 0);"
+		"exit;"
+		:
+		: __imm_ptr(vals),
+		  __imm_ptr(callback_subprog),
+		  __imm(bpf_loop)
+		: __clobber_common, "r6"
+	);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("9: (0f) r1 += r6")
+__msg("mark_precise: frame0: last_idx 9 first_idx 6")
+__msg("mark_precise: frame0: regs=r6 stack= before 8: (bf) r1 = r7")
+__msg("mark_precise: frame0: regs=r6 stack= before 7: (27) r6 *= 4")
+__msg("mark_precise: frame0: regs=r6 stack= before 6: (79) r6 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: parent state regs= stack=-8:")
+__msg("mark_precise: frame0: last_idx 13 first_idx 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 13: (95) exit")
+__msg("mark_precise: frame1: regs= stack= before 12: (bf) r0 = r1")
+__msg("mark_precise: frame1: regs= stack= before 5: (85) call pc+6")
+__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r1 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r6")
+__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3")
+__naked int parent_stack_slot_precise(void)
+{
+	asm volatile (
+		/* spill reg */
+		"r6 = 3;"
+		"*(u64 *)(r10 - 8) = r6;"
+
+		/* call subprog and ignore result; we need this call only to
+		 * complicate jump history
+		 */
+		"r1 = 0;"
+		"call identity_subprog;"
+
+		/* restore reg from stack; in this case we'll be carrying
+		 * stack mask when going back into subprog through jump
+		 * history
+		 */
+		"r6 = *(u64 *)(r10 - 8);"
+
+		"r6 *= 4;"
+		"r1 = %[vals];"
+		/* here r6 is forced to be precise and has to be propagated
+		 * back to the beginning, handling (and ignoring) subprog call
+		 */
+		"r1 += r6;"
+		"r0 = *(u32 *)(r1 + 0);"
+		"exit;"
+		:
+		: __imm_ptr(vals)
+		: __clobber_common, "r6"
+	);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("9: (0f) r1 += r6")
+__msg("mark_precise: frame0: last_idx 9 first_idx 0")
+__msg("mark_precise: frame0: regs=r6 stack= before 8: (bf) r1 = r7")
+__msg("mark_precise: frame0: regs=r6 stack= before 7: (27) r6 *= 4")
+__msg("mark_precise: frame0: regs=r6 stack= before 6: (79) r6 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: regs= stack=-8 before 5: (85) call pc+6")
+__msg("mark_precise: frame0: regs= stack=-8 before 4: (b7) r1 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 3: (7b) *(u64 *)(r10 -8) = r6")
+__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 3")
+__naked int parent_stack_slot_precise_global(void)
+{
+	asm volatile (
+		/* spill reg */
+		"r6 = 3;"
+		"*(u64 *)(r10 - 8) = r6;"
+
+		/* call subprog and ignore result; we need this call only to
+		 * complicate jump history
+		 */
+		"r1 = 0;"
+		"call global_identity_subprog;"
+
+		/* restore reg from stack; in this case we'll be carrying
+		 * stack mask when going back into subprog through jump
+		 * history
+		 */
+		"r6 = *(u64 *)(r10 - 8);"
+
+		"r6 *= 4;"
+		"r1 = %[vals];"
+		/* here r6 is forced to be precise and has to be propagated
+		 * back to the beginning, handling (and ignoring) subprog call
+		 */
+		"r1 += r6;"
+		"r0 = *(u32 *)(r1 + 0);"
+		"exit;"
+		:
+		: __imm_ptr(vals)
+		: __clobber_common, "r6"
+	);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+/* First simulated path does not include callback body */
+__msg("14: (0f) r1 += r6")
+__msg("mark_precise: frame0: last_idx 14 first_idx 10")
+__msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7")
+__msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4")
+__msg("mark_precise: frame0: regs=r6 stack= before 11: (79) r6 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: regs= stack=-8 before 10: (85) call bpf_loop")
+__msg("mark_precise: frame0: parent state regs= stack=-8:")
+__msg("mark_precise: frame0: last_idx 9 first_idx 0 subseq_idx 10")
+__msg("mark_precise: frame0: regs= stack=-8 before 9: (b7) r4 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 8: (b7) r3 = 0")
+__msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r2 = r8")
+__msg("mark_precise: frame0: regs= stack=-8 before 6: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs= stack=-8 before 5: (7b) *(u64 *)(r10 -8) = r6")
+__msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3")
+/* State entering callback body popped from states stack */
+__msg("from 10 to 17: frame1:")
+__msg("17: frame1: R1=scalar() R2=0 R10=fp0 cb")
+__msg("17: (b7) r0 = 0")
+__msg("18: (95) exit")
+__msg("returning from callee:")
+__msg("to caller at 10:")
+/* r1, r4 are always precise for bpf_loop(),
+ * fp-8 was marked before backtracking to callback body.
+ */
+__msg("frame 0: propagating r1,r4,fp-8")
+__msg("mark_precise: frame0: last_idx 10 first_idx 10 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r1,r4 stack=-8 before 18: (95) exit")
+__msg("mark_precise: frame1: regs= stack= before 17: (b7) r0 = 0")
+__msg("mark_precise: frame1: regs= stack= before 10: (85) call bpf_loop#181")
+__msg("mark_precise: frame0: parent state regs= stack=:")
+__msg("from 18 to 10: safe")
+__naked int parent_stack_slot_precise_with_callback(void)
+{
+	asm volatile (
+		/* spill reg */
+		"r6 = 3;"
+		"*(u64 *)(r10 - 8) = r6;"
+
+		/* ensure we have callback frame in jump history */
+		"r1 = r6;"			/* nr_loops */
+		"r2 = %[callback_subprog];"	/* callback_fn */
+		"r3 = 0;"			/* callback_ctx */
+		"r4 = 0;"			/* flags */
+		"call %[bpf_loop];"
+
+		/* restore reg from stack; in this case we'll be carrying
+		 * stack mask when going back into subprog through jump
+		 * history
+		 */
+		"r6 = *(u64 *)(r10 - 8);"
+
+		"r6 *= 4;"
+		"r1 = %[vals];"
+		/* here r6 is forced to be precise and has to be propagated
+		 * back to the beginning, handling (and ignoring) subprog call
+		 */
+		"r1 += r6;"
+		"r0 = *(u32 *)(r1 + 0);"
+		"exit;"
+		:
+		: __imm_ptr(vals),
+		  __imm_ptr(callback_subprog),
+		  __imm(bpf_loop)
+		: __clobber_common, "r6"
+	);
+}
+
+__noinline __used
+static __u64 subprog_with_precise_arg(__u64 x)
+{
+	return vals[x]; /* x is forced to be precise */
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("8: (0f) r2 += r1")
+__msg("mark_precise: frame1: last_idx 8 first_idx 0")
+__msg("mark_precise: frame1: regs=r1 stack= before 6: (18) r2 = ")
+__msg("mark_precise: frame1: regs=r1 stack= before 5: (67) r1 <<= 2")
+__msg("mark_precise: frame1: regs=r1 stack= before 2: (85) call pc+2")
+__msg("mark_precise: frame0: regs=r1 stack= before 1: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs=r6 stack= before 0: (b7) r6 = 3")
+__naked int subprog_arg_precise(void)
+{
+	asm volatile (
+		"r6 = 3;"
+		"r1 = r6;"
+		/* subprog_with_precise_arg expects its argument to be
+		 * precise, so r1->r6 will be marked precise from inside the
+		 * subprog
+		 */
+		"call subprog_with_precise_arg;"
+		"r0 += r6;"
+		"exit;"
+		:
+		:
+		: __clobber_common, "r6"
+	);
+}
+
+/* r1 is pointer to stack slot;
+ * r2 is a register to spill into that slot
+ * subprog also spills r2 into its own stack slot
+ */
+__naked __noinline __used
+static __u64 subprog_spill_reg_precise(void)
+{
+	asm volatile (
+		/* spill to parent stack */
+		"*(u64 *)(r1 + 0) = r2;"
+		/* spill to subprog stack (we use -16 offset to avoid
+		 * accidental confusion with parent's -8 stack slot in
+		 * verifier log output)
+		 */
+		"*(u64 *)(r10 - 16) = r2;"
+		/* use both spills as return result to propagete precision everywhere */
+		"r0 = *(u64 *)(r10 - 16);"
+		"r2 = *(u64 *)(r1 + 0);"
+		"r0 += r2;"
+		"exit;"
+	);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("10: (0f) r1 += r7")
+__msg("mark_precise: frame0: last_idx 10 first_idx 7 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r7 stack= before 9: (bf) r1 = r8")
+__msg("mark_precise: frame0: regs=r7 stack= before 8: (27) r7 *= 4")
+__msg("mark_precise: frame0: regs=r7 stack= before 7: (79) r7 = *(u64 *)(r10 -8)")
+__msg("mark_precise: frame0: parent state regs= stack=-8:  R0=2 R6=1 R8=map_value(map=.data.vals,ks=4,vs=16) R10=fp0 fp-8=P1")
+__msg("mark_precise: frame0: last_idx 18 first_idx 0 subseq_idx 7")
+__msg("mark_precise: frame0: regs= stack=-8 before 18: (95) exit")
+__msg("mark_precise: frame1: regs= stack= before 17: (0f) r0 += r2")
+__msg("mark_precise: frame1: regs= stack= before 16: (79) r2 = *(u64 *)(r1 +0)")
+__msg("mark_precise: frame1: regs= stack= before 15: (79) r0 = *(u64 *)(r10 -16)")
+__msg("mark_precise: frame1: regs= stack= before 14: (7b) *(u64 *)(r10 -16) = r2")
+__msg("mark_precise: frame1: regs= stack= before 13: (7b) *(u64 *)(r1 +0) = r2")
+__msg("mark_precise: frame1: regs=r2 stack= before 6: (85) call pc+6")
+__msg("mark_precise: frame0: regs=r2 stack= before 5: (bf) r2 = r6")
+__msg("mark_precise: frame0: regs=r6 stack= before 4: (07) r1 += -8")
+__msg("mark_precise: frame0: regs=r6 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 1")
+__naked int subprog_spill_into_parent_stack_slot_precise(void)
+{
+	asm volatile (
+		"r6 = 1;"
+
+		/* pass pointer to stack slot and r6 to subprog;
+		 * r6 will be marked precise and spilled into fp-8 slot, which
+		 * also should be marked precise
+		 */
+		"r1 = r10;"
+		"r1 += -8;"
+		"r2 = r6;"
+		"call subprog_spill_reg_precise;"
+
+		/* restore reg from stack; in this case we'll be carrying
+		 * stack mask when going back into subprog through jump
+		 * history
+		 */
+		"r7 = *(u64 *)(r10 - 8);"
+
+		"r7 *= 4;"
+		"r1 = %[vals];"
+		/* here r7 is forced to be precise and has to be propagated
+		 * back to the beginning, handling subprog call and logic
+		 */
+		"r1 += r7;"
+		"r0 = *(u32 *)(r1 + 0);"
+		"exit;"
+		:
+		: __imm_ptr(vals)
+		: __clobber_common, "r6", "r7"
+	);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("17: (0f) r1 += r0")
+__msg("mark_precise: frame0: last_idx 17 first_idx 0 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r0 stack= before 16: (bf) r1 = r7")
+__msg("mark_precise: frame0: regs=r0 stack= before 15: (27) r0 *= 4")
+__msg("mark_precise: frame0: regs=r0 stack= before 14: (79) r0 = *(u64 *)(r10 -16)")
+__msg("mark_precise: frame0: regs= stack=-16 before 13: (7b) *(u64 *)(r7 -8) = r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 12: (79) r0 = *(u64 *)(r8 +16)")
+__msg("mark_precise: frame0: regs= stack=-16 before 11: (7b) *(u64 *)(r8 +16) = r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 10: (79) r0 = *(u64 *)(r7 -8)")
+__msg("mark_precise: frame0: regs= stack=-16 before 9: (7b) *(u64 *)(r10 -16) = r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 8: (07) r8 += -32")
+__msg("mark_precise: frame0: regs=r0 stack= before 7: (bf) r8 = r10")
+__msg("mark_precise: frame0: regs=r0 stack= before 6: (07) r7 += -8")
+__msg("mark_precise: frame0: regs=r0 stack= before 5: (bf) r7 = r10")
+__msg("mark_precise: frame0: regs=r0 stack= before 21: (95) exit")
+__msg("mark_precise: frame1: regs=r0 stack= before 20: (bf) r0 = r1")
+__msg("mark_precise: frame1: regs=r1 stack= before 4: (85) call pc+15")
+__msg("mark_precise: frame0: regs=r1 stack= before 3: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs=r6 stack= before 2: (b7) r6 = 1")
+__naked int stack_slot_aliases_precision(void)
+{
+	asm volatile (
+		"r6 = 1;"
+		/* pass r6 through r1 into subprog to get it back as r0;
+		 * this whole chain will have to be marked as precise later
+		 */
+		"r1 = r6;"
+		"call identity_subprog;"
+		/* let's setup two registers that are aliased to r10 */
+		"r7 = r10;"
+		"r7 += -8;"			/* r7 = r10 - 8 */
+		"r8 = r10;"
+		"r8 += -32;"			/* r8 = r10 - 32 */
+		/* now spill subprog's return value (a r6 -> r1 -> r0 chain)
+		 * a few times through different stack pointer regs, making
+		 * sure to use r10, r7, and r8 both in LDX and STX insns, and
+		 * *importantly* also using a combination of const var_off and
+		 * insn->off to validate that we record final stack slot
+		 * correctly, instead of relying on just insn->off derivation,
+		 * which is only valid for r10-based stack offset
+		 */
+		"*(u64 *)(r10 - 16) = r0;"
+		"r0 = *(u64 *)(r7 - 8);"	/* r7 - 8 == r10 - 16 */
+		"*(u64 *)(r8 + 16) = r0;"	/* r8 + 16 = r10 - 16 */
+		"r0 = *(u64 *)(r8 + 16);"
+		"*(u64 *)(r7 - 8) = r0;"
+		"r0 = *(u64 *)(r10 - 16);"
+		/* get ready to use r0 as an index into array to force precision */
+		"r0 *= 4;"
+		"r1 = %[vals];"
+		/* here r0->r1->r6 chain is forced to be precise and has to be
+		 * propagated back to the beginning, including through the
+		 * subprog call and all the stack spills and loads
+		 */
+		"r1 += r0;"
+		"r0 = *(u32 *)(r1 + 0);"
+		"exit;"
+		:
+		: __imm_ptr(vals)
+		: __clobber_common, "r6"
+	);
+}
+
+struct {
+        __uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+        __uint(max_entries, 1);
+        __type(key, __u32);
+        __type(value, __u32);
+} map_array SEC(".maps");
+
+__naked __noinline __used
+static unsigned long identity_tail_call(void)
+{
+	/* the simplest identity function involving a tail call */
+        asm volatile (
+		"r6 = r2;"
+		"r2 = %[map_array] ll;"
+		"r3 = 0;"
+		"call %[bpf_tail_call];"
+		"r0 = r6;"
+		"exit;"
+		:
+		: __imm(bpf_tail_call),
+		  __imm_addr(map_array)
+		: __clobber_all);
+}
+
+SEC("?raw_tp")
+__failure __log_level(2)
+__msg("13: (85) call bpf_tail_call#12")
+__msg("mark_precise: frame1: last_idx 13 first_idx 0 subseq_idx -1 ")
+__msg("returning from callee:")
+__msg("frame1: R0=scalar() R6=3 R10=fp0")
+__msg("to caller at 4:")
+__msg("R0=scalar() R6=map_value(map=.data.vals,ks=4,vs=16) R10=fp0")
+__msg("6: (0f) r1 += r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 5: (bf) r1 = r6")
+__msg("mark_precise: frame0: regs=r0 stack= before 4: (27) r0 *= 4")
+__msg("mark_precise: frame0: parent state regs=r0 stack=:  R0=Pscalar() R6=map_value(map=.data.vals,ks=4,vs=16) R10=fp0")
+__msg("math between map_value pointer and register with unbounded min value is not allowed")
+__naked int subprog_result_tail_call(void)
+{
+	asm volatile (
+		"r2 = 3;"
+		"call identity_tail_call;"
+		"r0 *= 4;"
+		"r1 = %[vals];"
+		"r1 += r0;"
+		"r0 = *(u32 *)(r1 + 0);"
+		"exit;"
+		:
+		: __imm_ptr(vals)
+		: __clobber_common
+	);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_subreg.c b/tools/testing/selftests/bpf/progs/verifier_subreg.c
new file mode 100644
index 000000000000..8613ea160dcd
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_subreg.c
@@ -0,0 +1,673 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/subreg.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+/* This file contains sub-register zero extension checks for insns defining
+ * sub-registers, meaning:
+ *   - All insns under BPF_ALU class. Their BPF_ALU32 variants or narrow width
+ *     forms (BPF_END) could define sub-registers.
+ *   - Narrow direct loads, BPF_B/H/W | BPF_LDX.
+ *   - BPF_LD is not exposed to JIT back-ends, so no need for testing.
+ *
+ * "get_prandom_u32" is used to initialize low 32-bit of some registers to
+ * prevent potential optimizations done by verifier or JIT back-ends which could
+ * optimize register back into constant when range info shows one register is a
+ * constant.
+ */
+
+SEC("socket")
+__description("add32 reg zero extend check")
+__success __success_unpriv __retval(0)
+__naked void add32_reg_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	r0 = 0x100000000 ll;				\
+	w0 += w1;					\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("add32 imm zero extend check")
+__success __success_unpriv __retval(0)
+__naked void add32_imm_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	/* An insn could have no effect on the low 32-bit, for example:\
+	 *   a = a + 0					\
+	 *   a = a | 0					\
+	 *   a = a & -1					\
+	 * But, they should still zero high 32-bit.	\
+	 */						\
+	w0 += 0;					\
+	r0 >>= 32;					\
+	r6 = r0;					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 += -2;					\
+	r0 >>= 32;					\
+	r0 |= r6;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("sub32 reg zero extend check")
+__success __success_unpriv __retval(0)
+__naked void sub32_reg_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	r0 = 0x1ffffffff ll;				\
+	w0 -= w1;					\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("sub32 imm zero extend check")
+__success __success_unpriv __retval(0)
+__naked void sub32_imm_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 -= 0;					\
+	r0 >>= 32;					\
+	r6 = r0;					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 -= 1;					\
+	r0 >>= 32;					\
+	r0 |= r6;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("mul32 reg zero extend check")
+__success __success_unpriv __retval(0)
+__naked void mul32_reg_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	r0 = 0x100000001 ll;				\
+	w0 *= w1;					\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("mul32 imm zero extend check")
+__success __success_unpriv __retval(0)
+__naked void mul32_imm_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 *= 1;					\
+	r0 >>= 32;					\
+	r6 = r0;					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 *= -1;					\
+	r0 >>= 32;					\
+	r0 |= r6;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("div32 reg zero extend check")
+__success __success_unpriv __retval(0)
+__naked void div32_reg_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	r0 = -1;					\
+	w0 /= w1;					\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("div32 imm zero extend check")
+__success __success_unpriv __retval(0)
+__naked void div32_imm_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 /= 1;					\
+	r0 >>= 32;					\
+	r6 = r0;					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 /= 2;					\
+	r0 >>= 32;					\
+	r0 |= r6;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("or32 reg zero extend check")
+__success __success_unpriv __retval(0)
+__naked void or32_reg_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	r0 = 0x100000001 ll;				\
+	w0 |= w1;					\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("or32 imm zero extend check")
+__success __success_unpriv __retval(0)
+__naked void or32_imm_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 |= 0;					\
+	r0 >>= 32;					\
+	r6 = r0;					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 |= 1;					\
+	r0 >>= 32;					\
+	r0 |= r6;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("and32 reg zero extend check")
+__success __success_unpriv __retval(0)
+__naked void and32_reg_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x100000000 ll;				\
+	r1 |= r0;					\
+	r0 = 0x1ffffffff ll;				\
+	w0 &= w1;					\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("and32 imm zero extend check")
+__success __success_unpriv __retval(0)
+__naked void and32_imm_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 &= -1;					\
+	r0 >>= 32;					\
+	r6 = r0;					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 &= -2;					\
+	r0 >>= 32;					\
+	r0 |= r6;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("lsh32 reg zero extend check")
+__success __success_unpriv __retval(0)
+__naked void lsh32_reg_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x100000000 ll;				\
+	r0 |= r1;					\
+	r1 = 1;						\
+	w0 <<= w1;					\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("lsh32 imm zero extend check")
+__success __success_unpriv __retval(0)
+__naked void lsh32_imm_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 <<= 0;					\
+	r0 >>= 32;					\
+	r6 = r0;					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 <<= 1;					\
+	r0 >>= 32;					\
+	r0 |= r6;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("rsh32 reg zero extend check")
+__success __success_unpriv __retval(0)
+__naked void rsh32_reg_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	r1 = 1;						\
+	w0 >>= w1;					\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("rsh32 imm zero extend check")
+__success __success_unpriv __retval(0)
+__naked void rsh32_imm_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 >>= 0;					\
+	r0 >>= 32;					\
+	r6 = r0;					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 >>= 1;					\
+	r0 >>= 32;					\
+	r0 |= r6;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("neg32 reg zero extend check")
+__success __success_unpriv __retval(0)
+__naked void neg32_reg_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 = -w0;					\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("mod32 reg zero extend check")
+__success __success_unpriv __retval(0)
+__naked void mod32_reg_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	r0 = -1;					\
+	w0 %%= w1;					\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("mod32 imm zero extend check")
+__success __success_unpriv __retval(0)
+__naked void mod32_imm_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 %%= 1;					\
+	r0 >>= 32;					\
+	r6 = r0;					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 %%= 2;					\
+	r0 >>= 32;					\
+	r0 |= r6;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("xor32 reg zero extend check")
+__success __success_unpriv __retval(0)
+__naked void xor32_reg_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = r0;					\
+	r0 = 0x100000000 ll;				\
+	w0 ^= w1;					\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("xor32 imm zero extend check")
+__success __success_unpriv __retval(0)
+__naked void xor32_imm_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 ^= 1;					\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("mov32 reg zero extend check")
+__success __success_unpriv __retval(0)
+__naked void mov32_reg_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x100000000 ll;				\
+	r1 |= r0;					\
+	r0 = 0x100000000 ll;				\
+	w0 = w1;					\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("mov32 imm zero extend check")
+__success __success_unpriv __retval(0)
+__naked void mov32_imm_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 = 0;						\
+	r0 >>= 32;					\
+	r6 = r0;					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 = 1;						\
+	r0 >>= 32;					\
+	r0 |= r6;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("arsh32 reg zero extend check")
+__success __success_unpriv __retval(0)
+__naked void arsh32_reg_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	r1 = 1;						\
+	w0 s>>= w1;					\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("arsh32 imm zero extend check")
+__success __success_unpriv __retval(0)
+__naked void arsh32_imm_zero_extend_check(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 s>>= 0;					\
+	r0 >>= 32;					\
+	r6 = r0;					\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	w0 s>>= 1;					\
+	r0 >>= 32;					\
+	r0 |= r6;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("end16 (to_le) reg zero extend check")
+__success __success_unpriv __retval(0)
+__naked void le_reg_zero_extend_check_1(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r6 = r0;					\
+	r6 <<= 32;					\
+	call %[bpf_get_prandom_u32];			\
+	r0 |= r6;					\
+	r0 = le16 r0;					\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("end32 (to_le) reg zero extend check")
+__success __success_unpriv __retval(0)
+__naked void le_reg_zero_extend_check_2(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r6 = r0;					\
+	r6 <<= 32;					\
+	call %[bpf_get_prandom_u32];			\
+	r0 |= r6;					\
+	r0 = le32 r0;					\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("end16 (to_be) reg zero extend check")
+__success __success_unpriv __retval(0)
+__naked void be_reg_zero_extend_check_1(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r6 = r0;					\
+	r6 <<= 32;					\
+	call %[bpf_get_prandom_u32];			\
+	r0 |= r6;					\
+	r0 = be16 r0;					\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("end32 (to_be) reg zero extend check")
+__success __success_unpriv __retval(0)
+__naked void be_reg_zero_extend_check_2(void)
+{
+	asm volatile ("					\
+	call %[bpf_get_prandom_u32];			\
+	r6 = r0;					\
+	r6 <<= 32;					\
+	call %[bpf_get_prandom_u32];			\
+	r0 |= r6;					\
+	r0 = be32 r0;					\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("ldx_b zero extend check")
+__success __success_unpriv __retval(0)
+__naked void ldx_b_zero_extend_check(void)
+{
+	asm volatile ("					\
+	r6 = r10;					\
+	r6 += -4;					\
+	r7 = 0xfaceb00c;				\
+	*(u32*)(r6 + 0) = r7;				\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	r0 = *(u8*)(r6 + 0);				\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("ldx_h zero extend check")
+__success __success_unpriv __retval(0)
+__naked void ldx_h_zero_extend_check(void)
+{
+	asm volatile ("					\
+	r6 = r10;					\
+	r6 += -4;					\
+	r7 = 0xfaceb00c;				\
+	*(u32*)(r6 + 0) = r7;				\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	r0 = *(u16*)(r6 + 0);				\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("ldx_w zero extend check")
+__success __success_unpriv __retval(0)
+__naked void ldx_w_zero_extend_check(void)
+{
+	asm volatile ("					\
+	r6 = r10;					\
+	r6 += -4;					\
+	r7 = 0xfaceb00c;				\
+	*(u32*)(r6 + 0) = r7;				\
+	call %[bpf_get_prandom_u32];			\
+	r1 = 0x1000000000 ll;				\
+	r0 |= r1;					\
+	r0 = *(u32*)(r6 + 0);				\
+	r0 >>= 32;					\
+	exit;						\
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_tailcall.c b/tools/testing/selftests/bpf/progs/verifier_tailcall.c
new file mode 100644
index 000000000000..b4acce60fb9b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_tailcall.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u32);
+} map_array SEC(".maps");
+
+SEC("socket")
+__description("invalid map type for tail call")
+__failure __msg("expected prog array map for tail call")
+__failure_unpriv
+__naked void invalid_map_for_tail_call(void)
+{
+	asm volatile ("			\
+	r2 = %[map_array] ll;	\
+	r3 = 0;				\
+	call %[bpf_tail_call];		\
+	exit;				\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_array)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_tailcall_jit.c b/tools/testing/selftests/bpf/progs/verifier_tailcall_jit.c
new file mode 100644
index 000000000000..8d60c634a114
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_tailcall_jit.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+int main(void);
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__array(values, void (void));
+} jmp_table SEC(".maps") = {
+	.values = {
+		[0] = (void *) &main,
+	},
+};
+
+__noinline __auxiliary
+static __naked int sub(void)
+{
+	asm volatile (
+	"r2 = %[jmp_table] ll;"
+	"r3 = 0;"
+	"call 12;"
+	"exit;"
+	:
+	: __imm_addr(jmp_table)
+	: __clobber_all);
+}
+
+__success
+__arch_x86_64
+/* program entry for main(), regular function prologue */
+__jited("	endbr64")
+__jited("	nopl	(%rax,%rax)")
+__jited("	xorq	%rax, %rax")
+__jited("	pushq	%rbp")
+__jited("	movq	%rsp, %rbp")
+/* tail call prologue for program:
+ * - establish memory location for tail call counter at &rbp[-8];
+ * - spill tail_call_cnt_ptr at &rbp[-16];
+ * - expect tail call counter to be passed in rax;
+ * - for entry program rax is a raw counter, value < 33;
+ * - for tail called program rax is tail_call_cnt_ptr (value > 33).
+ */
+__jited("	endbr64")
+__jited("	cmpq	$0x21, %rax")
+__jited("	ja	L0")
+__jited("	pushq	%rax")
+__jited("	movq	%rsp, %rax")
+__jited("	jmp	L1")
+__jited("L0:	pushq	%rax")			/* rbp[-8]  = rax         */
+__jited("L1:	pushq	%rax")			/* rbp[-16] = rax         */
+/* on subprogram call restore rax to be tail_call_cnt_ptr from rbp[-16]
+ * (cause original rax might be clobbered by this point)
+ */
+__jited("	movq	-0x10(%rbp), %rax")
+__jited("	callq	0x{{.*}}")		/* call to sub()          */
+__jited("	xorl	%eax, %eax")
+__jited("	leave")
+__jited("	{{(retq|jmp	0x)}}")		/* return or jump to rethunk */
+__jited("...")
+/* subprogram entry for sub(), regular function prologue */
+__jited("	endbr64")
+__jited("	nopl	(%rax,%rax)")
+__jited("	nopl	(%rax)")
+__jited("	pushq	%rbp")
+__jited("	movq	%rsp, %rbp")
+/* tail call prologue for subprogram address of tail call counter
+ * stored at rbp[-16].
+ */
+__jited("	endbr64")
+__jited("	pushq	%rax")			/* rbp[-8]  = rax          */
+__jited("	pushq	%rax")			/* rbp[-16] = rax          */
+__jited("	movabsq	${{.*}}, %rsi")		/* r2 = &jmp_table         */
+__jited("	xorl	%edx, %edx")		/* r3 = 0                  */
+/* bpf_tail_call implementation:
+ * - load tail_call_cnt_ptr from rbp[-16];
+ * - if *tail_call_cnt_ptr < 33, increment it and jump to target;
+ * - otherwise do nothing.
+ */
+__jited("	movq	-0x10(%rbp), %rax")
+__jited("	cmpq	$0x21, (%rax)")
+__jited("	jae	L0")
+__jited("	nopl	(%rax,%rax)")
+__jited("	addq	$0x1, (%rax)")		/* *tail_call_cnt_ptr += 1 */
+__jited("	popq	%rax")
+__jited("	popq	%rax")
+__jited("	jmp	{{.*}}")		/* jump to tail call tgt   */
+__jited("L0:	leave")
+__jited("	{{(retq|jmp	0x)}}")		/* return or jump to rethunk */
+SEC("tc")
+__naked int main(void)
+{
+	asm volatile (
+	"call %[sub];"
+	"r0 = 0;"
+	"exit;"
+	:
+	: __imm(sub)
+	: __clobber_all);
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_typedef.c b/tools/testing/selftests/bpf/progs/verifier_typedef.c
new file mode 100644
index 000000000000..08481cfaac4b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_typedef.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("fentry/bpf_fentry_test_sinfo")
+__description("typedef: resolve")
+__success __retval(0)
+__naked void resolve_typedef(void)
+{
+	asm volatile ("					\
+	r1 = *(u64 *)(r1 +0);				\
+	r2 = *(u64 *)(r1 +%[frags_offs]);		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(frags_offs,
+		      offsetof(struct skb_shared_info, frags))
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_uninit.c b/tools/testing/selftests/bpf/progs/verifier_uninit.c
new file mode 100644
index 000000000000..7718cd7d19ce
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_uninit.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/uninit.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
+#include "bpf_misc.h"
+
+SEC("socket")
+__description("read uninitialized register")
+__failure __msg("R2 !read_ok")
+__failure_unpriv
+__naked void read_uninitialized_register(void)
+{
+	asm volatile ("					\
+	r0 = r2;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("read invalid register")
+__failure __msg("R15 is invalid")
+__failure_unpriv
+__naked void read_invalid_register(void)
+{
+	asm volatile ("					\
+	.8byte %[mov64_reg];				\
+	exit;						\
+"	:
+	: __imm_insn(mov64_reg, BPF_MOV64_REG(BPF_REG_0, -1))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("program doesn't init R0 before exit")
+__failure __msg("R0 !read_ok")
+__failure_unpriv
+__naked void t_init_r0_before_exit(void)
+{
+	asm volatile ("					\
+	r2 = r1;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("program doesn't init R0 before exit in all branches")
+__failure __msg("R0 !read_ok")
+__msg_unpriv("R1 pointer comparison")
+__naked void before_exit_in_all_branches(void)
+{
+	asm volatile ("					\
+	if r1 >= 0 goto l0_%=;				\
+	r0 = 1;						\
+	r0 += 2;					\
+l0_%=:	exit;						\
+"	::: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_unpriv.c b/tools/testing/selftests/bpf/progs/verifier_unpriv.c
new file mode 100644
index 000000000000..28b4f7035ceb
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_unpriv.c
@@ -0,0 +1,953 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/unpriv.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
+#include "bpf_misc.h"
+
+#define BPF_SK_LOOKUP(func) \
+	/* struct bpf_sock_tuple tuple = {} */ \
+	"r2 = 0;"			\
+	"*(u32*)(r10 - 8) = r2;"	\
+	"*(u64*)(r10 - 16) = r2;"	\
+	"*(u64*)(r10 - 24) = r2;"	\
+	"*(u64*)(r10 - 32) = r2;"	\
+	"*(u64*)(r10 - 40) = r2;"	\
+	"*(u64*)(r10 - 48) = r2;"	\
+	/* sk = func(ctx, &tuple, sizeof tuple, 0, 0) */ \
+	"r2 = r10;"			\
+	"r2 += -48;"			\
+	"r3 = %[sizeof_bpf_sock_tuple];"\
+	"r4 = 0;"			\
+	"r5 = 0;"			\
+	"call %[" #func "];"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, long long);
+} map_hash_8b SEC(".maps");
+
+void dummy_prog_42_socket(void);
+void dummy_prog_24_socket(void);
+void dummy_prog_loop1_socket(void);
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 4);
+	__uint(key_size, sizeof(int));
+	__array(values, void (void));
+} map_prog1_socket SEC(".maps") = {
+	.values = {
+		[0] = (void *)&dummy_prog_42_socket,
+		[1] = (void *)&dummy_prog_loop1_socket,
+		[2] = (void *)&dummy_prog_24_socket,
+	},
+};
+
+SEC("socket")
+__auxiliary __auxiliary_unpriv
+__naked void dummy_prog_42_socket(void)
+{
+	asm volatile ("r0 = 42; exit;");
+}
+
+SEC("socket")
+__auxiliary __auxiliary_unpriv
+__naked void dummy_prog_24_socket(void)
+{
+	asm volatile ("r0 = 24; exit;");
+}
+
+SEC("socket")
+__auxiliary __auxiliary_unpriv
+__naked void dummy_prog_loop1_socket(void)
+{
+	asm volatile ("			\
+	r3 = 1;				\
+	r2 = %[map_prog1_socket] ll;	\
+	call %[bpf_tail_call];		\
+	r0 = 41;			\
+	exit;				\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_socket)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: return pointer")
+__success __failure_unpriv __msg_unpriv("R0 leaks addr")
+__retval(POINTER_VALUE)
+__naked void unpriv_return_pointer(void)
+{
+	asm volatile ("					\
+	r0 = r10;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: add const to pointer")
+__success __success_unpriv __retval(0)
+__naked void unpriv_add_const_to_pointer(void)
+{
+	asm volatile ("					\
+	r1 += 8;					\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: add pointer to pointer")
+__failure __msg("R1 pointer += pointer")
+__failure_unpriv
+__naked void unpriv_add_pointer_to_pointer(void)
+{
+	asm volatile ("					\
+	r1 += r10;					\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: neg pointer")
+__success __failure_unpriv __msg_unpriv("R1 pointer arithmetic")
+__retval(0)
+__naked void unpriv_neg_pointer(void)
+{
+	asm volatile ("					\
+	r1 = -r1;					\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: cmp pointer with const")
+__success __failure_unpriv __msg_unpriv("R1 pointer comparison")
+__retval(0)
+__naked void unpriv_cmp_pointer_with_const(void)
+{
+	asm volatile ("					\
+	if r1 == 0 goto l0_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: cmp pointer with pointer")
+__success __failure_unpriv __msg_unpriv("R10 pointer comparison")
+__retval(0)
+__naked void unpriv_cmp_pointer_with_pointer(void)
+{
+	asm volatile ("					\
+	if r1 == r10 goto l0_%=;			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tracepoint")
+__description("unpriv: check that printk is disallowed")
+__success
+__naked void check_that_printk_is_disallowed(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r1 = r10;					\
+	r1 += -8;					\
+	r2 = 8;						\
+	r3 = r1;					\
+	call %[bpf_trace_printk];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_trace_printk)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: pass pointer to helper function")
+__success __failure_unpriv __msg_unpriv("R4 leaks addr")
+__retval(0)
+__naked void pass_pointer_to_helper_function(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	r3 = r2;					\
+	r4 = r2;					\
+	call %[bpf_map_update_elem];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_update_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: indirectly pass pointer on stack to helper function")
+__success __failure_unpriv
+__msg_unpriv("invalid read from stack R2 off -8+0 size 8")
+__retval(0)
+__naked void on_stack_to_helper_function(void)
+{
+	asm volatile ("					\
+	*(u64*)(r10 - 8) = r10;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: mangle pointer on stack 1")
+__success __failure_unpriv __msg_unpriv("attempt to corrupt spilled")
+__retval(0)
+__naked void mangle_pointer_on_stack_1(void)
+{
+	asm volatile ("					\
+	*(u64*)(r10 - 8) = r10;				\
+	r0 = 0;						\
+	*(u32*)(r10 - 8) = r0;				\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: mangle pointer on stack 2")
+__success __failure_unpriv __msg_unpriv("attempt to corrupt spilled")
+__retval(0)
+__naked void mangle_pointer_on_stack_2(void)
+{
+	asm volatile ("					\
+	*(u64*)(r10 - 8) = r10;				\
+	r0 = 0;						\
+	*(u8*)(r10 - 1) = r0;				\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: read pointer from stack in small chunks")
+__failure __msg("invalid size")
+__failure_unpriv
+__naked void from_stack_in_small_chunks(void)
+{
+	asm volatile ("					\
+	*(u64*)(r10 - 8) = r10;				\
+	r0 = *(u32*)(r10 - 8);				\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: write pointer into ctx")
+__failure __msg("invalid bpf_context access")
+__failure_unpriv __msg_unpriv("R1 leaks addr")
+__naked void unpriv_write_pointer_into_ctx(void)
+{
+	asm volatile ("					\
+	*(u64*)(r1 + 0) = r1;				\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: spill/fill of ctx")
+__success __success_unpriv __retval(0)
+__naked void unpriv_spill_fill_of_ctx(void)
+{
+	asm volatile ("					\
+	r6 = r10;					\
+	r6 += -8;					\
+	*(u64*)(r6 + 0) = r1;				\
+	r1 = *(u64*)(r6 + 0);				\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tc")
+__description("unpriv: spill/fill of ctx 2")
+__success __retval(0)
+__naked void spill_fill_of_ctx_2(void)
+{
+	asm volatile ("					\
+	r6 = r10;					\
+	r6 += -8;					\
+	*(u64*)(r6 + 0) = r1;				\
+	r1 = *(u64*)(r6 + 0);				\
+	call %[bpf_get_hash_recalc];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_get_hash_recalc)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("unpriv: spill/fill of ctx 3")
+__failure __msg("R1 type=fp expected=ctx")
+__naked void spill_fill_of_ctx_3(void)
+{
+	asm volatile ("					\
+	r6 = r10;					\
+	r6 += -8;					\
+	*(u64*)(r6 + 0) = r1;				\
+	*(u64*)(r6 + 0) = r10;				\
+	r1 = *(u64*)(r6 + 0);				\
+	call %[bpf_get_hash_recalc];			\
+	exit;						\
+"	:
+	: __imm(bpf_get_hash_recalc)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("unpriv: spill/fill of ctx 4")
+__failure __msg("R1 type=scalar expected=ctx")
+__naked void spill_fill_of_ctx_4(void)
+{
+	asm volatile ("					\
+	r6 = r10;					\
+	r6 += -8;					\
+	*(u64*)(r6 + 0) = r1;				\
+	r0 = 1;						\
+	lock *(u64 *)(r10 - 8) += r0;			\
+	r1 = *(u64*)(r6 + 0);				\
+	call %[bpf_get_hash_recalc];			\
+	exit;						\
+"	:
+	: __imm(bpf_get_hash_recalc)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("unpriv: spill/fill of different pointers stx")
+__failure __msg("same insn cannot be used with different pointers")
+__naked void fill_of_different_pointers_stx(void)
+{
+	asm volatile ("					\
+	r3 = 42;					\
+	r6 = r10;					\
+	r6 += -8;					\
+	if r1 == 0 goto l0_%=;				\
+	r2 = r10;					\
+	r2 += -16;					\
+	*(u64*)(r6 + 0) = r2;				\
+l0_%=:	if r1 != 0 goto l1_%=;				\
+	*(u64*)(r6 + 0) = r1;				\
+l1_%=:	r1 = *(u64*)(r6 + 0);				\
+	*(u32*)(r1 + %[__sk_buff_mark]) = r3;		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark))
+	: __clobber_all);
+}
+
+/* Same as above, but use BPF_ST_MEM to save 42
+ * instead of BPF_STX_MEM.
+ */
+SEC("tc")
+__description("unpriv: spill/fill of different pointers st")
+__failure __msg("same insn cannot be used with different pointers")
+__naked void fill_of_different_pointers_st(void)
+{
+	asm volatile ("					\
+	r6 = r10;					\
+	r6 += -8;					\
+	if r1 == 0 goto l0_%=;				\
+	r2 = r10;					\
+	r2 += -16;					\
+	*(u64*)(r6 + 0) = r2;				\
+l0_%=:	if r1 != 0 goto l1_%=;				\
+	*(u64*)(r6 + 0) = r1;				\
+l1_%=:	r1 = *(u64*)(r6 + 0);				\
+	.8byte %[st_mem];				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)),
+	  __imm_insn(st_mem,
+		     BPF_ST_MEM(BPF_W, BPF_REG_1, offsetof(struct __sk_buff, mark), 42))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("unpriv: spill/fill of different pointers stx - ctx and sock")
+__failure __msg("type=ctx expected=sock")
+__naked void pointers_stx_ctx_and_sock(void)
+{
+	asm volatile ("					\
+	r8 = r1;					\
+	/* struct bpf_sock *sock = bpf_sock_lookup(...); */\
+"	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r2 = r0;					\
+	/* u64 foo; */					\
+	/* void *target = &foo; */			\
+	r6 = r10;					\
+	r6 += -8;					\
+	r1 = r8;					\
+	/* if (skb == NULL) *target = sock; */		\
+	if r1 == 0 goto l0_%=;				\
+	*(u64*)(r6 + 0) = r2;				\
+l0_%=:	/* else *target = skb; */			\
+	if r1 != 0 goto l1_%=;				\
+	*(u64*)(r6 + 0) = r1;				\
+l1_%=:	/* struct __sk_buff *skb = *target; */		\
+	r1 = *(u64*)(r6 + 0);				\
+	/* skb->mark = 42; */				\
+	r3 = 42;					\
+	*(u32*)(r1 + %[__sk_buff_mark]) = r3;		\
+	/* if (sk) bpf_sk_release(sk) */		\
+	if r1 == 0 goto l2_%=;				\
+	call %[bpf_sk_release];				\
+l2_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("unpriv: spill/fill of different pointers stx - leak sock")
+__failure
+//.errstr = "same insn cannot be used with different pointers",
+__msg("Unreleased reference")
+__naked void different_pointers_stx_leak_sock(void)
+{
+	asm volatile ("					\
+	r8 = r1;					\
+	/* struct bpf_sock *sock = bpf_sock_lookup(...); */\
+"	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r2 = r0;					\
+	/* u64 foo; */					\
+	/* void *target = &foo; */			\
+	r6 = r10;					\
+	r6 += -8;					\
+	r1 = r8;					\
+	/* if (skb == NULL) *target = sock; */		\
+	if r1 == 0 goto l0_%=;				\
+	*(u64*)(r6 + 0) = r2;				\
+l0_%=:	/* else *target = skb; */			\
+	if r1 != 0 goto l1_%=;				\
+	*(u64*)(r6 + 0) = r1;				\
+l1_%=:	/* struct __sk_buff *skb = *target; */		\
+	r1 = *(u64*)(r6 + 0);				\
+	/* skb->mark = 42; */				\
+	r3 = 42;					\
+	*(u32*)(r1 + %[__sk_buff_mark]) = r3;		\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm_const(__sk_buff_mark, offsetof(struct __sk_buff, mark)),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("unpriv: spill/fill of different pointers stx - sock and ctx (read)")
+__failure __msg("same insn cannot be used with different pointers")
+__naked void stx_sock_and_ctx_read(void)
+{
+	asm volatile ("					\
+	r8 = r1;					\
+	/* struct bpf_sock *sock = bpf_sock_lookup(...); */\
+"	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r2 = r0;					\
+	/* u64 foo; */					\
+	/* void *target = &foo; */			\
+	r6 = r10;					\
+	r6 += -8;					\
+	r1 = r8;					\
+	/* if (skb) *target = skb */			\
+	if r1 == 0 goto l0_%=;				\
+	*(u64*)(r6 + 0) = r1;				\
+l0_%=:	/* else *target = sock */			\
+	if r1 != 0 goto l1_%=;				\
+	*(u64*)(r6 + 0) = r2;				\
+l1_%=:	/* struct bpf_sock *sk = *target; */		\
+	r1 = *(u64*)(r6 + 0);				\
+	/* if (sk) u32 foo = sk->mark; bpf_sk_release(sk); */\
+	if r1 == 0 goto l2_%=;				\
+	r3 = *(u32*)(r1 + %[bpf_sock_mark]);		\
+	call %[bpf_sk_release];				\
+l2_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(bpf_sock_mark, offsetof(struct bpf_sock, mark)),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("unpriv: spill/fill of different pointers stx - sock and ctx (write)")
+__failure
+//.errstr = "same insn cannot be used with different pointers",
+__msg("cannot write into sock")
+__naked void stx_sock_and_ctx_write(void)
+{
+	asm volatile ("					\
+	r8 = r1;					\
+	/* struct bpf_sock *sock = bpf_sock_lookup(...); */\
+"	BPF_SK_LOOKUP(bpf_sk_lookup_tcp)
+"	r2 = r0;					\
+	/* u64 foo; */					\
+	/* void *target = &foo; */			\
+	r6 = r10;					\
+	r6 += -8;					\
+	r1 = r8;					\
+	/* if (skb) *target = skb */			\
+	if r1 == 0 goto l0_%=;				\
+	*(u64*)(r6 + 0) = r1;				\
+l0_%=:	/* else *target = sock */			\
+	if r1 != 0 goto l1_%=;				\
+	*(u64*)(r6 + 0) = r2;				\
+l1_%=:	/* struct bpf_sock *sk = *target; */		\
+	r1 = *(u64*)(r6 + 0);				\
+	/* if (sk) sk->mark = 42; bpf_sk_release(sk); */\
+	if r1 == 0 goto l2_%=;				\
+	r3 = 42;					\
+	*(u32*)(r1 + %[bpf_sock_mark]) = r3;		\
+	call %[bpf_sk_release];				\
+l2_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_sk_lookup_tcp),
+	  __imm(bpf_sk_release),
+	  __imm_const(bpf_sock_mark, offsetof(struct bpf_sock, mark)),
+	  __imm_const(sizeof_bpf_sock_tuple, sizeof(struct bpf_sock_tuple))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: write pointer into map elem value")
+__success __failure_unpriv __msg_unpriv("R0 leaks addr")
+__retval(0)
+__naked void pointer_into_map_elem_value(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	*(u64*)(r0 + 0) = r0;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("alu32: mov u32 const")
+__success __success_unpriv
+__retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if r0 == 0x0 goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R7 invalid mem access 'scalar'` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("exit")
+#endif
+__naked void alu32_mov_u32_const(void)
+{
+	asm volatile ("					\
+	w7 = 0;						\
+	w7 &= 1;					\
+	w0 = w7;					\
+	if r0 == 0 goto l0_%=;				\
+	r0 = *(u64*)(r7 + 0);				\
+l0_%=:	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: partial copy of pointer")
+__success __failure_unpriv __msg_unpriv("R10 partial copy")
+__retval(0)
+__naked void unpriv_partial_copy_of_pointer(void)
+{
+	asm volatile ("					\
+	w1 = w10;					\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: pass pointer to tail_call")
+__success __failure_unpriv __msg_unpriv("R3 leaks addr into helper")
+__retval(0)
+__naked void pass_pointer_to_tail_call(void)
+{
+	asm volatile ("					\
+	r3 = r1;					\
+	r2 = %[map_prog1_socket] ll;			\
+	call %[bpf_tail_call];				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_tail_call),
+	  __imm_addr(map_prog1_socket)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: cmp map pointer with zero")
+__success __success_unpriv
+__retval(0)
+__naked void cmp_map_pointer_with_zero(void)
+{
+	asm volatile ("					\
+	r1 = %[map_hash_8b] ll;				\
+	if r1 == 0 goto l0_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: cmp map pointer with const")
+__success __failure_unpriv __msg_unpriv("R1 pointer comparison prohibited")
+__retval(0)
+__naked void cmp_map_pointer_with_const(void)
+{
+	asm volatile ("					\
+	r1 = %[map_hash_8b] ll;				\
+	if r1 == 0x0000beef goto l0_%=;			\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: write into frame pointer")
+__failure __msg("frame pointer is read only")
+__failure_unpriv
+__naked void unpriv_write_into_frame_pointer(void)
+{
+	asm volatile ("					\
+	r10 = r1;					\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: spill/fill frame pointer")
+__failure __msg("frame pointer is read only")
+__failure_unpriv
+__naked void unpriv_spill_fill_frame_pointer(void)
+{
+	asm volatile ("					\
+	r6 = r10;					\
+	r6 += -8;					\
+	*(u64*)(r6 + 0) = r10;				\
+	r10 = *(u64*)(r6 + 0);				\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: cmp of frame pointer")
+__success __failure_unpriv __msg_unpriv("R10 pointer comparison")
+__retval(0)
+__naked void unpriv_cmp_of_frame_pointer(void)
+{
+	asm volatile ("					\
+	if r10 == 0 goto l0_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: adding of fp, reg")
+__success __failure_unpriv
+__msg_unpriv("R1 stack pointer arithmetic goes out of range")
+__retval(0)
+__naked void unpriv_adding_of_fp_reg(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	r1 = 0;						\
+	r1 += r10;					\
+	*(u64*)(r1 - 8) = r0;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: adding of fp, imm")
+__success __failure_unpriv
+__msg_unpriv("R1 stack pointer arithmetic goes out of range")
+__retval(0)
+__naked void unpriv_adding_of_fp_imm(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	r1 = r10;					\
+	r1 += 0;					\
+	*(u64*)(r1 - 8) = r0;				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: cmp of stack pointer")
+__success __failure_unpriv __msg_unpriv("R2 pointer comparison")
+__retval(0)
+__naked void unpriv_cmp_of_stack_pointer(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	if r2 == 0 goto l0_%=;				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: Spectre v1 path-based type confusion of scalar as stack-ptr")
+__success __success_unpriv __retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if r0 != 0x1 goto pc+2")
+/* This nospec prevents the exploit because it forces the mispredicted (not
+ * taken) `if r0 != 0x0 goto l0_%=` to resolve before using r6 as a pointer.
+ * This causes the CPU to realize that `r6 = r9` should have never executed. It
+ * ensures that r6 always contains a readable stack slot ptr when the insn after
+ * the nospec executes.
+ */
+__xlated_unpriv("nospec")
+__xlated_unpriv("r9 = *(u8 *)(r6 +0)")
+#endif
+__naked void unpriv_spec_v1_type_confusion(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l2_%=;				\
+	/* r0: pointer to a map array entry */		\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	/* r1, r2: prepared call args */		\
+	r6 = r10;					\
+	r6 += -8;					\
+	/* r6: pointer to readable stack slot */	\
+	r9 = 0xffffc900;				\
+	r9 <<= 32;					\
+	/* r9: scalar controlled by attacker */		\
+	r0 = *(u64 *)(r0 + 0); /* cache miss */		\
+	if r0 != 0x0 goto l0_%=;			\
+	r6 = r9;					\
+l0_%=:	if r0 != 0x1 goto l1_%=;			\
+	r9 = *(u8 *)(r6 + 0);				\
+l1_%=:  /* leak r9 */					\
+	r9 &= 1;					\
+	r9 <<= 9;					\
+	*(u64*)(r10 - 8) = r9;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l2_%=;				\
+	/* leak secret into is_cached(map[0|512]): */	\
+	r0 = *(u64 *)(r0 + 0);				\
+l2_%=:							\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: ldimm64 before Spectre v4 barrier")
+__success __success_unpriv
+__retval(0)
+#ifdef SPEC_V4
+__xlated_unpriv("r1 = 0x2020200005642020") /* should not matter */
+__xlated_unpriv("*(u64 *)(r10 -8) = r1")
+__xlated_unpriv("nospec")
+#endif
+__naked void unpriv_ldimm64_spectre_v4(void)
+{
+	asm volatile ("					\
+	r1 = 0x2020200005642020 ll;			\
+	*(u64 *)(r10 -8) = r1;				\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: Spectre v1 and v4 barrier")
+__success __success_unpriv
+__retval(0)
+#ifdef SPEC_V1
+#ifdef SPEC_V4
+/* starts with r0 == r8 == r9 == 0 */
+__xlated_unpriv("if r8 != 0x0 goto pc+1")
+__xlated_unpriv("goto pc+2")
+__xlated_unpriv("if r9 == 0x0 goto pc+4")
+__xlated_unpriv("r2 = r0")
+/* Following nospec required to prevent following dangerous `*(u64 *)(NOT_FP -64)
+ * = r1` iff `if r9 == 0 goto pc+4` was mispredicted because of Spectre v1. The
+ * test therefore ensures the Spectre-v4--induced nospec does not prevent the
+ * Spectre-v1--induced speculative path from being fully analyzed.
+ */
+__xlated_unpriv("nospec") /* Spectre v1 */
+__xlated_unpriv("*(u64 *)(r2 -64) = r1") /* could be used to leak r2 */
+__xlated_unpriv("nospec") /* Spectre v4 */
+#endif
+#endif
+__naked void unpriv_spectre_v1_and_v4(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r8 = r0;					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r9 = r0;					\
+	r0 = r10;					\
+	r1 = 0;						\
+	r2 = r10;					\
+	if r8 != 0 goto l0_%=;				\
+	if r9 != 0 goto l0_%=;				\
+	r0 = 0;						\
+l0_%=:	if r8 != 0 goto l1_%=;				\
+	goto l2_%=;					\
+l1_%=:	if r9 == 0 goto l3_%=;				\
+	r2 = r0;					\
+l2_%=:	*(u64 *)(r2 -64) = r1;				\
+l3_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: Spectre v1 and v4 barrier (simple)")
+__success __success_unpriv
+__retval(0)
+#ifdef SPEC_V1
+#ifdef SPEC_V4
+__xlated_unpriv("if r8 != 0x0 goto pc+1")
+__xlated_unpriv("goto pc+2")
+__xlated_unpriv("goto pc-1") /* if r9 == 0 goto l3_%= */
+__xlated_unpriv("goto pc-1") /* r2 = r0 */
+__xlated_unpriv("nospec")
+__xlated_unpriv("*(u64 *)(r2 -64) = r1")
+__xlated_unpriv("nospec")
+#endif
+#endif
+__naked void unpriv_spectre_v1_and_v4_simple(void)
+{
+	asm volatile ("					\
+	r8 = 0;						\
+	r9 = 0;						\
+	r0 = r10;					\
+	r1 = 0;						\
+	r2 = r10;					\
+	if r8 != 0 goto l0_%=;				\
+	if r9 != 0 goto l0_%=;				\
+	r0 = 0;						\
+l0_%=:	if r8 != 0 goto l1_%=;				\
+	goto l2_%=;					\
+l1_%=:	if r9 == 0 goto l3_%=;				\
+	r2 = r0;					\
+l2_%=:	*(u64 *)(r2 -64) = r1;				\
+l3_%=:	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("unpriv: ldimm64 before Spectre v1 and v4 barrier (simple)")
+__success __success_unpriv
+__retval(0)
+#ifdef SPEC_V1
+#ifdef SPEC_V4
+__xlated_unpriv("if r8 != 0x0 goto pc+1")
+__xlated_unpriv("goto pc+4")
+__xlated_unpriv("goto pc-1") /* if r9 == 0 goto l3_%= */
+__xlated_unpriv("goto pc-1") /* r2 = r0 */
+__xlated_unpriv("goto pc-1") /* r1 = 0x2020200005642020 ll */
+__xlated_unpriv("goto pc-1") /* second part of ldimm64 */
+__xlated_unpriv("nospec")
+__xlated_unpriv("*(u64 *)(r2 -64) = r1")
+__xlated_unpriv("nospec")
+#endif
+#endif
+__naked void unpriv_ldimm64_spectre_v1_and_v4_simple(void)
+{
+	asm volatile ("					\
+	r8 = 0;						\
+	r9 = 0;						\
+	r0 = r10;					\
+	r1 = 0;						\
+	r2 = r10;					\
+	if r8 != 0 goto l0_%=;				\
+	if r9 != 0 goto l0_%=;				\
+	r0 = 0;						\
+l0_%=:	if r8 != 0 goto l1_%=;				\
+	goto l2_%=;					\
+l1_%=:	if r9 == 0 goto l3_%=;				\
+	r2 = r0;					\
+	r1 = 0x2020200005642020 ll;			\
+l2_%=:	*(u64 *)(r2 -64) = r1;				\
+l3_%=:	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_unpriv_perf.c b/tools/testing/selftests/bpf/progs/verifier_unpriv_perf.c
new file mode 100644
index 000000000000..4d77407a0a79
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_unpriv_perf.c
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/unpriv.c */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("perf_event")
+__description("unpriv: spill/fill of different pointers ldx")
+__failure __msg("same insn cannot be used with different pointers")
+__naked void fill_of_different_pointers_ldx(void)
+{
+	asm volatile ("					\
+	r6 = r10;					\
+	r6 += -8;					\
+	if r1 == 0 goto l0_%=;				\
+	r2 = r10;					\
+	r2 += %[__imm_0];				\
+	*(u64*)(r6 + 0) = r2;				\
+l0_%=:	if r1 != 0 goto l1_%=;				\
+	*(u64*)(r6 + 0) = r1;				\
+l1_%=:	r1 = *(u64*)(r6 + 0);				\
+	r1 = *(u64*)(r1 + %[sample_period]);		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__imm_0,
+		      -(__s32) offsetof(struct bpf_perf_event_data, sample_period) - 8),
+	  __imm_const(sample_period,
+		      offsetof(struct bpf_perf_event_data, sample_period))
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_value.c b/tools/testing/selftests/bpf/progs/verifier_value.c
new file mode 100644
index 000000000000..b5af6b6f5acd
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_value.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/value.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#define MAX_ENTRIES 11
+
+struct test_val {
+	unsigned int index;
+	int foo[MAX_ENTRIES];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, struct test_val);
+} map_hash_48b SEC(".maps");
+
+SEC("socket")
+__description("map element value store of cleared call register")
+__failure __msg("R1 !read_ok")
+__failure_unpriv __msg_unpriv("R1 !read_ok")
+__naked void store_of_cleared_call_register(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	*(u64*)(r0 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map element value with unaligned store")
+__success __failure_unpriv __msg_unpriv("R0 leaks addr")
+__retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void element_value_with_unaligned_store(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r0 += 3;					\
+	r1 = 42;					\
+	*(u64*)(r0 + 0) = r1;				\
+	r1 = 43;					\
+	*(u64*)(r0 + 2) = r1;				\
+	r1 = 44;					\
+	*(u64*)(r0 - 2) = r1;				\
+	r8 = r0;					\
+	r1 = 32;					\
+	*(u64*)(r8 + 0) = r1;				\
+	r1 = 33;					\
+	*(u64*)(r8 + 2) = r1;				\
+	r1 = 34;					\
+	*(u64*)(r8 - 2) = r1;				\
+	r8 += 5;					\
+	r1 = 22;					\
+	*(u64*)(r8 + 0) = r1;				\
+	r1 = 23;					\
+	*(u64*)(r8 + 4) = r1;				\
+	r1 = 24;					\
+	*(u64*)(r8 - 7) = r1;				\
+	r7 = r8;					\
+	r7 += 3;					\
+	r1 = 22;					\
+	*(u64*)(r7 + 0) = r1;				\
+	r1 = 23;					\
+	*(u64*)(r7 + 4) = r1;				\
+	r1 = 24;					\
+	*(u64*)(r7 - 4) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map element value with unaligned load")
+__success __failure_unpriv __msg_unpriv("R0 leaks addr")
+__retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void element_value_with_unaligned_load(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u32*)(r0 + 0);				\
+	if r1 >= %[max_entries] goto l0_%=;		\
+	r0 += 3;					\
+	r7 = *(u64*)(r0 + 0);				\
+	r7 = *(u64*)(r0 + 2);				\
+	r8 = r0;					\
+	r7 = *(u64*)(r8 + 0);				\
+	r7 = *(u64*)(r8 + 2);				\
+	r0 += 5;					\
+	r7 = *(u64*)(r0 + 0);				\
+	r7 = *(u64*)(r0 + 4);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(max_entries, MAX_ENTRIES)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map element value is preserved across register spilling")
+__success __failure_unpriv __msg_unpriv("R0 leaks addr")
+__retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void is_preserved_across_register_spilling(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r0 += %[test_val_foo];				\
+	r1 = 42;					\
+	*(u64*)(r0 + 0) = r1;				\
+	r1 = r10;					\
+	r1 += -184;					\
+	*(u64*)(r1 + 0) = r0;				\
+	r3 = *(u64*)(r1 + 0);				\
+	r1 = 42;					\
+	*(u64*)(r3 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_value_adj_spill.c b/tools/testing/selftests/bpf/progs/verifier_value_adj_spill.c
new file mode 100644
index 000000000000..d7a5ba9bbe6a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_value_adj_spill.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/value_adj_spill.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#define MAX_ENTRIES 11
+
+struct test_val {
+	unsigned int index;
+	int foo[MAX_ENTRIES];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, struct test_val);
+} map_hash_48b SEC(".maps");
+
+SEC("socket")
+__description("map element value is preserved across register spilling")
+__success __failure_unpriv __msg_unpriv("R0 leaks addr")
+__retval(0)
+__naked void is_preserved_across_register_spilling(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 42;					\
+	*(u64*)(r0 + 0) = r1;				\
+	r1 = r10;					\
+	r1 += -184;					\
+	*(u64*)(r1 + 0) = r0;				\
+	r3 = *(u64*)(r1 + 0);				\
+	r1 = 42;					\
+	*(u64*)(r3 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map element value or null is marked on register spilling")
+__success __failure_unpriv __msg_unpriv("R0 leaks addr")
+__retval(0)
+__naked void is_marked_on_register_spilling(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	r1 = r10;					\
+	r1 += -152;					\
+	*(u64*)(r1 + 0) = r0;				\
+	if r0 == 0 goto l0_%=;				\
+	r3 = *(u64*)(r1 + 0);				\
+	r1 = 42;					\
+	*(u64*)(r3 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c b/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c
new file mode 100644
index 000000000000..2129e4353fd9
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_value_illegal_alu.c
@@ -0,0 +1,215 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/value_illegal_alu.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "../../../include/linux/filter.h"
+#include "bpf_misc.h"
+
+#define MAX_ENTRIES 11
+
+struct test_val {
+	unsigned int index;
+	int foo[MAX_ENTRIES];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, struct test_val);
+} map_hash_48b SEC(".maps");
+
+SEC("socket")
+__description("map element value illegal alu op, 1")
+__failure __msg("R0 bitwise operator &= on pointer")
+__failure_unpriv
+__naked void value_illegal_alu_op_1(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r0 &= 8;					\
+	r1 = 22;					\
+	*(u64*)(r0 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map element value illegal alu op, 2")
+__failure __msg("R0 32-bit pointer arithmetic prohibited")
+__failure_unpriv
+__naked void value_illegal_alu_op_2(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	w0 += 0;					\
+	r1 = 22;					\
+	*(u64*)(r0 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map element value illegal alu op, 3")
+__failure __msg("R0 pointer arithmetic with /= operator")
+__failure_unpriv
+__naked void value_illegal_alu_op_3(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r0 /= 42;					\
+	r1 = 22;					\
+	*(u64*)(r0 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map element value illegal alu op, 4")
+__failure __msg("invalid mem access 'scalar'")
+__failure_unpriv __msg_unpriv("R0 pointer arithmetic prohibited")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void value_illegal_alu_op_4(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r0 = be64 r0;					\
+	r1 = 22;					\
+	*(u64*)(r0 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map element value illegal alu op, 5")
+__failure __msg("R0 invalid mem access 'scalar'")
+__msg_unpriv("leaking pointer from stack off -8")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void value_illegal_alu_op_5(void)
+{
+	asm volatile ("					\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = 0;						\
+	*(u64*)(r2 + 0) = r1;				\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r3 = 4096;					\
+	r2 = r10;					\
+	r2 += -8;					\
+	*(u64*)(r2 + 0) = r0;				\
+	lock *(u64 *)(r2 + 0) += r3;			\
+	r0 = *(u64*)(r2 + 0);				\
+	r1 = 22;					\
+	*(u64*)(r0 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map_ptr illegal alu op, map_ptr = -map_ptr")
+__failure __msg("R0 invalid mem access 'scalar'")
+__failure_unpriv __msg_unpriv("R0 pointer arithmetic prohibited")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void map_ptr_illegal_alu_op(void)
+{
+	asm volatile ("					\
+	r0 = %[map_hash_48b] ll;			\
+	r0 = -r0;					\
+	r1 = 22;					\
+	*(u64*)(r0 + 0) = r1;				\
+	exit;						\
+"	:
+	: __imm_addr(map_hash_48b)
+	: __clobber_all);
+}
+
+SEC("flow_dissector")
+__description("flow_keys illegal alu op with variable offset")
+__failure __msg("R7 pointer arithmetic on flow_keys prohibited")
+__naked void flow_keys_illegal_variable_offset_alu(void)
+{
+	asm volatile("					\
+	r6 = r1;					\
+	r7 = *(u64*)(r6 + %[flow_keys_off]);		\
+	r8 = 8;						\
+	r8 /= 1;					\
+	r8 &= 8;					\
+	r7 += r8;					\
+	r0 = *(u64*)(r7 + 0);				\
+	exit;						\
+"	:
+	: __imm_const(flow_keys_off, offsetof(struct __sk_buff, flow_keys))
+	: __clobber_all);
+}
+
+#define DEFINE_BAD_OFFSET_TEST(name, op, off, imm)	\
+	SEC("socket")					\
+	__failure __msg("BPF_ALU uses reserved fields") \
+	__naked void name(void)				\
+	{						\
+		asm volatile(				\
+			"r0 = 1;"			\
+			".8byte %[insn];"		\
+			"r0 = 0;"			\
+			"exit;"				\
+		:					\
+		: __imm_insn(insn, BPF_RAW_INSN((op), 0, 0, (off), (imm))) \
+		: __clobber_all);			\
+	}
+
+/*
+ * Offset fields of 0 and 1 are legal for BPF_{DIV,MOD} instructions.
+ * Offset fields of 0 are legal for the rest of ALU instructions.
+ * Test that error is reported for illegal offsets, assuming that tests
+ * for legal offsets exist.
+ */
+DEFINE_BAD_OFFSET_TEST(bad_offset_divx, BPF_ALU64 | BPF_DIV | BPF_X, -1, 0)
+DEFINE_BAD_OFFSET_TEST(bad_offset_modk, BPF_ALU64 | BPF_MOD | BPF_K, -1, 1)
+DEFINE_BAD_OFFSET_TEST(bad_offset_addx, BPF_ALU64 | BPF_ADD | BPF_X, -1, 0)
+DEFINE_BAD_OFFSET_TEST(bad_offset_divx2, BPF_ALU64 | BPF_DIV | BPF_X, 2, 0)
+DEFINE_BAD_OFFSET_TEST(bad_offset_modk2, BPF_ALU64 | BPF_MOD | BPF_K, 2, 1)
+DEFINE_BAD_OFFSET_TEST(bad_offset_addx2, BPF_ALU64 | BPF_ADD | BPF_X, 1, 0)
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_value_or_null.c b/tools/testing/selftests/bpf/progs/verifier_value_or_null.c
new file mode 100644
index 000000000000..8ff668a242eb
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_value_or_null.c
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/value_or_null.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+#define MAX_ENTRIES 11
+
+struct test_val {
+	unsigned int index;
+	int foo[MAX_ENTRIES];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, struct test_val);
+} map_hash_48b SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, long long);
+} map_hash_8b SEC(".maps");
+
+SEC("tc")
+__description("multiple registers share map_lookup_elem result")
+__success __retval(0)
+__naked void share_map_lookup_elem_result(void)
+{
+	asm volatile ("					\
+	r1 = 10;					\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r4 = r0;					\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 0;						\
+	*(u64*)(r4 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("alu ops on ptr_to_map_value_or_null, 1")
+__failure __msg("R4 pointer arithmetic on map_value_or_null")
+__naked void map_value_or_null_1(void)
+{
+	asm volatile ("					\
+	r1 = 10;					\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r4 = r0;					\
+	r4 += -2;					\
+	r4 += 2;					\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 0;						\
+	*(u64*)(r4 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("alu ops on ptr_to_map_value_or_null, 2")
+__failure __msg("R4 pointer arithmetic on map_value_or_null")
+__naked void map_value_or_null_2(void)
+{
+	asm volatile ("					\
+	r1 = 10;					\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r4 = r0;					\
+	r4 &= -1;					\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 0;						\
+	*(u64*)(r4 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("alu ops on ptr_to_map_value_or_null, 3")
+__failure __msg("R4 pointer arithmetic on map_value_or_null")
+__naked void map_value_or_null_3(void)
+{
+	asm volatile ("					\
+	r1 = 10;					\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r4 = r0;					\
+	r4 <<= 1;					\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 0;						\
+	*(u64*)(r4 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("invalid memory access with multiple map_lookup_elem calls")
+__failure __msg("R4 !read_ok")
+__naked void multiple_map_lookup_elem_calls(void)
+{
+	asm volatile ("					\
+	r1 = 10;					\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	r8 = r1;					\
+	r7 = r2;					\
+	call %[bpf_map_lookup_elem];			\
+	r4 = r0;					\
+	r1 = r8;					\
+	r2 = r7;					\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 0;						\
+	*(u64*)(r4 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("valid indirect map_lookup_elem access with 2nd lookup in branch")
+__success __retval(0)
+__naked void with_2nd_lookup_in_branch(void)
+{
+	asm volatile ("					\
+	r1 = 10;					\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	r8 = r1;					\
+	r7 = r2;					\
+	call %[bpf_map_lookup_elem];			\
+	r2 = 10;					\
+	if r2 != 0 goto l0_%=;				\
+	r1 = r8;					\
+	r2 = r7;					\
+	call %[bpf_map_lookup_elem];			\
+l0_%=:	r4 = r0;					\
+	if r0 == 0 goto l1_%=;				\
+	r1 = 0;						\
+	*(u64*)(r4 + 0) = r1;				\
+l1_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("invalid map access from else condition")
+__failure __msg("R0 unbounded memory access")
+__failure_unpriv __msg_unpriv("R0 leaks addr")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void map_access_from_else_condition(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u32*)(r0 + 0);				\
+	if r1 >= %[__imm_0] goto l1_%=;			\
+	r1 += 1;					\
+l1_%=:	r1 <<= 2;					\
+	r0 += r1;					\
+	r1 = %[test_val_foo];				\
+	*(u64*)(r0 + 0) = r1;				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(__imm_0, MAX_ENTRIES-1),
+	  __imm_const(test_val_foo, offsetof(struct test_val, foo))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("map lookup and null branch prediction")
+__success __retval(0)
+__naked void lookup_and_null_branch_prediction(void)
+{
+	asm volatile ("					\
+	r1 = 10;					\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r6 = r0;					\
+	if r6 == 0 goto l0_%=;				\
+	if r6 != 0 goto l0_%=;				\
+	r10 += 10;					\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("MAP_VALUE_OR_NULL check_ids() in regsafe()")
+__failure __msg("R8 invalid mem access 'map_value_or_null'")
+__failure_unpriv __msg_unpriv("")
+__flag(BPF_F_TEST_STATE_FREQ)
+__naked void null_check_ids_in_regsafe(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	/* r9 = map_lookup_elem(...) */			\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r9 = r0;					\
+	/* r8 = map_lookup_elem(...) */			\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r8 = r0;					\
+	/* r7 = ktime_get_ns() */			\
+	call %[bpf_ktime_get_ns];			\
+	r7 = r0;					\
+	/* r6 = ktime_get_ns() */			\
+	call %[bpf_ktime_get_ns];			\
+	r6 = r0;					\
+	/* if r6 > r7 goto +1    ; no new information about the state is derived from\
+	 *                       ; this check, thus produced verifier states differ\
+	 *                       ; only in 'insn_idx'	\
+	 * r9 = r8               ; optionally share ID between r9 and r8\
+	 */						\
+	if r6 > r7 goto l0_%=;				\
+	r9 = r8;					\
+l0_%=:	/* if r9 == 0 goto <exit> */			\
+	if r9 == 0 goto l1_%=;				\
+	/* read map value via r8, this is not always	\
+	 * safe because r8 might be not equal to r9.	\
+	 */						\
+	r0 = *(u64*)(r8 + 0);				\
+l1_%=:	/* exit 0 */					\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_ktime_get_ns),
+	  __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c b/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c
new file mode 100644
index 000000000000..af7938ce56cb
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c
@@ -0,0 +1,1441 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/value_ptr_arith.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <errno.h>
+#include "bpf_misc.h"
+
+#define MAX_ENTRIES 11
+
+struct test_val {
+	unsigned int index;
+	int foo[MAX_ENTRIES];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, struct test_val);
+} map_array_48b SEC(".maps");
+
+struct other_val {
+	long long foo;
+	long long bar;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, struct other_val);
+} map_hash_16b SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, struct test_val);
+} map_hash_48b SEC(".maps");
+
+SEC("socket")
+__description("map access: known scalar += value_ptr unknown vs const")
+__success __failure_unpriv
+__msg_unpriv("R1 tried to add from different maps, paths or scalars")
+__retval(1)
+__naked void value_ptr_unknown_vs_const(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[__sk_buff_len]);		\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	if r0 == 1 goto l0_%=;				\
+	r1 = %[map_hash_16b] ll;			\
+	if r0 != 1 goto l1_%=;				\
+l0_%=:	r1 = %[map_array_48b] ll;			\
+l1_%=:	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l2_%=;				\
+	r4 = *(u8*)(r0 + 0);				\
+	if r4 == 1 goto l3_%=;				\
+	r1 = 6;						\
+	r1 = -r1;					\
+	r1 &= 0x7;					\
+	goto l4_%=;					\
+l3_%=:	r1 = 3;						\
+l4_%=:	r1 += r0;					\
+	r0 = *(u8*)(r1 + 0);				\
+l2_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b),
+	  __imm_addr(map_hash_16b),
+	  __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: known scalar += value_ptr const vs unknown")
+__success __failure_unpriv
+__msg_unpriv("R1 tried to add from different maps, paths or scalars")
+__retval(1)
+__naked void value_ptr_const_vs_unknown(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[__sk_buff_len]);		\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	if r0 == 1 goto l0_%=;				\
+	r1 = %[map_hash_16b] ll;			\
+	if r0 != 1 goto l1_%=;				\
+l0_%=:	r1 = %[map_array_48b] ll;			\
+l1_%=:	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l2_%=;				\
+	r4 = *(u8*)(r0 + 0);				\
+	if r4 == 1 goto l3_%=;				\
+	r1 = 3;						\
+	goto l4_%=;					\
+l3_%=:	r1 = 6;						\
+	r1 = -r1;					\
+	r1 &= 0x7;					\
+l4_%=:	r1 += r0;					\
+	r0 = *(u8*)(r1 + 0);				\
+l2_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b),
+	  __imm_addr(map_hash_16b),
+	  __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: known scalar += value_ptr const vs const (ne)")
+__success __failure_unpriv
+__msg_unpriv("R1 tried to add from different maps, paths or scalars")
+__retval(1)
+__naked void ptr_const_vs_const_ne(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[__sk_buff_len]);		\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	if r0 == 1 goto l0_%=;				\
+	r1 = %[map_hash_16b] ll;			\
+	if r0 != 1 goto l1_%=;				\
+l0_%=:	r1 = %[map_array_48b] ll;			\
+l1_%=:	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l2_%=;				\
+	r4 = *(u8*)(r0 + 0);				\
+	if r4 == 1 goto l3_%=;				\
+	r1 = 3;						\
+	goto l4_%=;					\
+l3_%=:	r1 = 5;						\
+l4_%=:	r1 += r0;					\
+	r0 = *(u8*)(r1 + 0);				\
+l2_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b),
+	  __imm_addr(map_hash_16b),
+	  __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: known scalar += value_ptr const vs const (eq)")
+__success __success_unpriv __retval(1)
+__naked void ptr_const_vs_const_eq(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[__sk_buff_len]);		\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	if r0 == 1 goto l0_%=;				\
+	r1 = %[map_hash_16b] ll;			\
+	if r0 != 1 goto l1_%=;				\
+l0_%=:	r1 = %[map_array_48b] ll;			\
+l1_%=:	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l2_%=;				\
+	r4 = *(u8*)(r0 + 0);				\
+	if r4 == 1 goto l3_%=;				\
+	r1 = 5;						\
+	goto l4_%=;					\
+l3_%=:	r1 = 5;						\
+l4_%=:	r1 += r0;					\
+	r0 = *(u8*)(r1 + 0);				\
+l2_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b),
+	  __imm_addr(map_hash_16b),
+	  __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: known scalar += value_ptr unknown vs unknown (eq)")
+__success __success_unpriv __retval(1)
+__naked void ptr_unknown_vs_unknown_eq(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[__sk_buff_len]);		\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	if r0 == 1 goto l0_%=;				\
+	r1 = %[map_hash_16b] ll;			\
+	if r0 != 1 goto l1_%=;				\
+l0_%=:	r1 = %[map_array_48b] ll;			\
+l1_%=:	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l2_%=;				\
+	r4 = *(u8*)(r0 + 0);				\
+	if r4 == 1 goto l3_%=;				\
+	r1 = 6;						\
+	r1 = -r1;					\
+	r1 &= 0x7;					\
+	goto l4_%=;					\
+l3_%=:	r1 = 6;						\
+	r1 = -r1;					\
+	r1 &= 0x7;					\
+l4_%=:	r1 += r0;					\
+	r0 = *(u8*)(r1 + 0);				\
+l2_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b),
+	  __imm_addr(map_hash_16b),
+	  __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: known scalar += value_ptr unknown vs unknown (lt)")
+__success __failure_unpriv
+__msg_unpriv("R1 tried to add from different maps, paths or scalars")
+__retval(1)
+__naked void ptr_unknown_vs_unknown_lt(void)
+{
+	asm volatile ("					\
+	r8 = r1;					\
+	call %[bpf_get_prandom_u32];			\
+	r9 = r0;					\
+	r1 = r8;					\
+	r0 = *(u32*)(r1 + %[__sk_buff_len]);		\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	if r0 == 1 goto l0_%=;				\
+	r1 = %[map_hash_16b] ll;			\
+	if r0 != 1 goto l1_%=;				\
+l0_%=:	r1 = %[map_array_48b] ll;			\
+l1_%=:	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l2_%=;				\
+	r4 = *(u8*)(r0 + 0);				\
+	if r4 == 1 goto l3_%=;				\
+	r1 = 6;						\
+	r1 = r9;					\
+	r1 &= 0x3;					\
+	goto l4_%=;					\
+l3_%=:	r1 = 6;						\
+	r1 = r9;					\
+	r1 &= 0x7;					\
+l4_%=:	r1 += r0;					\
+	r0 = *(u8*)(r1 + 0);				\
+l2_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b),
+	  __imm_addr(map_hash_16b),
+	  __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)),
+	  __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: known scalar += value_ptr unknown vs unknown (gt)")
+__success __failure_unpriv
+__msg_unpriv("R1 tried to add from different maps, paths or scalars")
+__retval(1)
+__naked void ptr_unknown_vs_unknown_gt(void)
+{
+	asm volatile ("					\
+	r8 = r1;					\
+	call %[bpf_get_prandom_u32];			\
+	r9 = r0;					\
+	r1 = r8;					\
+	r0 = *(u32*)(r1 + %[__sk_buff_len]);		\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	if r0 == 1 goto l0_%=;				\
+	r1 = %[map_hash_16b] ll;			\
+	if r0 != 1 goto l1_%=;				\
+l0_%=:	r1 = %[map_array_48b] ll;			\
+l1_%=:	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l2_%=;				\
+	r4 = *(u8*)(r0 + 0);				\
+	if r4 == 1 goto l3_%=;				\
+	r1 = 6;						\
+	r1 = r9;					\
+	r1 &= 0x7;					\
+	goto l4_%=;					\
+l3_%=:	r1 = 6;						\
+	r1 = r9;					\
+	r1 &= 0x3;					\
+l4_%=:	r1 += r0;					\
+	r0 = *(u8*)(r1 + 0);				\
+l2_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b),
+	  __imm_addr(map_hash_16b),
+	  __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)),
+	  __imm(bpf_get_prandom_u32)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: known scalar += value_ptr from different maps")
+__success __success_unpriv __retval(1)
+__naked void value_ptr_from_different_maps(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[__sk_buff_len]);		\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	if r0 == 1 goto l0_%=;				\
+	r1 = %[map_hash_16b] ll;			\
+	if r0 != 1 goto l1_%=;				\
+l0_%=:	r1 = %[map_array_48b] ll;			\
+l1_%=:	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l2_%=;				\
+	r1 = 4;						\
+	r1 += r0;					\
+	r0 = *(u8*)(r1 + 0);				\
+l2_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b),
+	  __imm_addr(map_hash_16b),
+	  __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr -= known scalar from different maps")
+__success __failure_unpriv
+__msg_unpriv("R0 min value is outside of the allowed memory range")
+__retval(1)
+__naked void known_scalar_from_different_maps(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[__sk_buff_len]);		\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	if r0 == 1 goto l0_%=;				\
+	r1 = %[map_hash_16b] ll;			\
+	if r0 != 1 goto l1_%=;				\
+l0_%=:	r1 = %[map_array_48b] ll;			\
+l1_%=:	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l2_%=;				\
+	r1 = 4;						\
+	r0 -= r1;					\
+	r0 += r1;					\
+	r0 = *(u8*)(r0 + 0);				\
+l2_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b),
+	  __imm_addr(map_hash_16b),
+	  __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: known scalar += value_ptr from different maps, but same value properties")
+__success __success_unpriv __retval(1)
+__naked void maps_but_same_value_properties(void)
+{
+	asm volatile ("					\
+	r0 = *(u32*)(r1 + %[__sk_buff_len]);		\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	if r0 == 1 goto l0_%=;				\
+	r1 = %[map_hash_48b] ll;			\
+	if r0 != 1 goto l1_%=;				\
+l0_%=:	r1 = %[map_array_48b] ll;			\
+l1_%=:	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l2_%=;				\
+	r1 = 4;						\
+	r1 += r0;					\
+	r0 = *(u8*)(r1 + 0);				\
+l2_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b),
+	  __imm_addr(map_hash_48b),
+	  __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: mixing value pointer and scalar, 1")
+__success __failure_unpriv
+__msg_unpriv("R2 tried to add from different maps, paths or scalars, pointer arithmetic with it prohibited for !root")
+__retval(0)
+__naked void value_pointer_and_scalar_1(void)
+{
+	asm volatile ("					\
+	/* load map value pointer into r0 and r2 */	\
+	r0 = 1;						\
+	r1 = %[map_array_48b] ll;			\
+	r2 = r10;					\
+	r2 += -16;					\
+	r6 = 0;						\
+	*(u64*)(r10 - 16) = r6;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	/* load some number from the map into r1 */	\
+	r1 = *(u8*)(r0 + 0);				\
+	/* depending on r1, branch: */			\
+	if r1 != 0 goto l1_%=;				\
+	/* branch A */					\
+	r2 = r0;					\
+	r3 = 0;						\
+	goto l2_%=;					\
+l1_%=:	/* branch B */					\
+	r2 = 0;						\
+	r3 = 0x100000;					\
+l2_%=:	/* common instruction */			\
+	r2 += r3;					\
+	/* depending on r1, branch: */			\
+	if r1 != 0 goto l3_%=;				\
+	/* branch A */					\
+	goto l4_%=;					\
+l3_%=:	/* branch B */					\
+	r0 = 0x13371337;				\
+	/* verifier follows fall-through */		\
+	/* unpriv: nospec (inserted to prevent `R2 pointer comparison prohibited`) */\
+	if r2 != 0x100000 goto l4_%=;			\
+	r0 = 0;						\
+	exit;						\
+l4_%=:	/* fake-dead code; targeted from branch A to	\
+	 * prevent dead code sanitization		\
+	 */						\
+	r0 = *(u8*)(r0 + 0);				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: mixing value pointer and scalar, 2")
+__success __failure_unpriv
+__msg_unpriv("R2 tried to add from different maps, paths or scalars, pointer arithmetic with it prohibited for !root")
+__retval(0)
+__naked void value_pointer_and_scalar_2(void)
+{
+	asm volatile ("					\
+	/* load map value pointer into r0 and r2 */	\
+	r0 = 1;						\
+	r1 = %[map_array_48b] ll;			\
+	r2 = r10;					\
+	r2 += -16;					\
+	r6 = 0;						\
+	*(u64*)(r10 - 16) = r6;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	/* load some number from the map into r1 */	\
+	r1 = *(u8*)(r0 + 0);				\
+	/* depending on r1, branch: */			\
+	if r1 == 0 goto l1_%=;				\
+	/* branch A */					\
+	r2 = 0;						\
+	r3 = 0x100000;					\
+	goto l2_%=;					\
+l1_%=:	/* branch B */					\
+	r2 = r0;					\
+	r3 = 0;						\
+l2_%=:	/* common instruction */			\
+	r2 += r3;					\
+	/* depending on r1, branch: */			\
+	if r1 != 0 goto l3_%=;				\
+	/* branch A */					\
+	goto l4_%=;					\
+l3_%=:	/* branch B */					\
+	r0 = 0x13371337;				\
+	/* verifier follows fall-through */		\
+	if r2 != 0x100000 goto l4_%=;			\
+	r0 = 0;						\
+	exit;						\
+l4_%=:	/* fake-dead code; targeted from branch A to	\
+	 * prevent dead code sanitization, rejected	\
+	 * via branch B however				\
+	 */						\
+	/* unpriv: nospec (inserted to prevent `R0 invalid mem access 'scalar'`) */\
+	r0 = *(u8*)(r0 + 0);				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("sanitation: alu with different scalars 1")
+__success __success_unpriv __retval(0x100000)
+__naked void alu_with_different_scalars_1(void)
+{
+	asm volatile ("					\
+	r0 = 1;						\
+	r1 = %[map_array_48b] ll;			\
+	r2 = r10;					\
+	r2 += -16;					\
+	r6 = 0;						\
+	*(u64*)(r10 - 16) = r6;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r1 = *(u32*)(r0 + 0);				\
+	if r1 == 0 goto l1_%=;				\
+	r2 = 0;						\
+	r3 = 0x100000;					\
+	goto l2_%=;					\
+l1_%=:	r2 = 42;					\
+	r3 = 0x100001;					\
+l2_%=:	r2 += r3;					\
+	r0 = r2;					\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("sanitation: alu with different scalars 2")
+__success __success_unpriv __retval(0)
+__naked void alu_with_different_scalars_2(void)
+{
+	asm volatile ("					\
+	r0 = 1;						\
+	r1 = %[map_array_48b] ll;			\
+	r6 = r1;					\
+	r2 = r10;					\
+	r2 += -16;					\
+	r7 = 0;						\
+	*(u64*)(r10 - 16) = r7;				\
+	call %[bpf_map_delete_elem];			\
+	r7 = r0;					\
+	r1 = r6;					\
+	r2 = r10;					\
+	r2 += -16;					\
+	call %[bpf_map_delete_elem];			\
+	r6 = r0;					\
+	r8 = r6;					\
+	r8 += r7;					\
+	r0 = r8;					\
+	r0 += %[einval];				\
+	r0 += %[einval];				\
+	exit;						\
+"	:
+	: __imm(bpf_map_delete_elem),
+	  __imm_addr(map_array_48b),
+	  __imm_const(einval, EINVAL)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("sanitation: alu with different scalars 3")
+__success __success_unpriv __retval(0)
+__naked void alu_with_different_scalars_3(void)
+{
+	asm volatile ("					\
+	r0 = %[einval];					\
+	r0 *= -1;					\
+	r7 = r0;					\
+	r0 = %[einval];					\
+	r0 *= -1;					\
+	r6 = r0;					\
+	r8 = r6;					\
+	r8 += r7;					\
+	r0 = r8;					\
+	r0 += %[einval];				\
+	r0 += %[einval];				\
+	exit;						\
+"	:
+	: __imm_const(einval, EINVAL)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr += known scalar, upper oob arith, test 1")
+__success __failure_unpriv
+__msg_unpriv("R0 pointer arithmetic of map value goes out of range")
+__retval(1)
+__naked void upper_oob_arith_test_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 48;					\
+	r0 += r1;					\
+	r0 -= r1;					\
+	r0 = *(u8*)(r0 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr += known scalar, upper oob arith, test 2")
+__success __failure_unpriv
+__msg_unpriv("R0 pointer arithmetic of map value goes out of range")
+__retval(1)
+__naked void upper_oob_arith_test_2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 49;					\
+	r0 += r1;					\
+	r0 -= r1;					\
+	r0 = *(u8*)(r0 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr += known scalar, upper oob arith, test 3")
+__success __success_unpriv __retval(1)
+__naked void upper_oob_arith_test_3(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 47;					\
+	r0 += r1;					\
+	r0 -= r1;					\
+	r0 = *(u8*)(r0 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr -= known scalar, lower oob arith, test 1")
+__failure __msg("R0 min value is outside of the allowed memory range")
+__failure_unpriv
+__msg_unpriv("R0 pointer arithmetic of map value goes out of range")
+__naked void lower_oob_arith_test_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 47;					\
+	r0 += r1;					\
+	r1 = 48;					\
+	r0 -= r1;					\
+	r0 = *(u8*)(r0 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr -= known scalar, lower oob arith, test 2")
+__success __failure_unpriv
+__msg_unpriv("R0 pointer arithmetic of map value goes out of range")
+__retval(1)
+__naked void lower_oob_arith_test_2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 47;					\
+	r0 += r1;					\
+	r1 = 48;					\
+	r0 -= r1;					\
+	r1 = 1;						\
+	r0 += r1;					\
+	r0 = *(u8*)(r0 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr -= known scalar, lower oob arith, test 3")
+__success __success_unpriv __retval(1)
+__naked void lower_oob_arith_test_3(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 47;					\
+	r0 += r1;					\
+	r1 = 47;					\
+	r0 -= r1;					\
+	r0 = *(u8*)(r0 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: known scalar += value_ptr")
+__success __success_unpriv __retval(1)
+__naked void access_known_scalar_value_ptr_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 4;						\
+	r1 += r0;					\
+	r0 = *(u8*)(r1 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr += known scalar, 1")
+__success __success_unpriv __retval(1)
+__naked void value_ptr_known_scalar_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 4;						\
+	r0 += r1;					\
+	r1 = *(u8*)(r0 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr += known scalar, 2")
+__failure __msg("invalid access to map value")
+__failure_unpriv
+__naked void value_ptr_known_scalar_2_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 49;					\
+	r0 += r1;					\
+	r1 = *(u8*)(r0 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr += known scalar, 3")
+__failure __msg("invalid access to map value")
+__failure_unpriv
+__naked void value_ptr_known_scalar_3(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = -1;					\
+	r0 += r1;					\
+	r1 = *(u8*)(r0 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr += known scalar, 4")
+__success __success_unpriv __retval(1)
+__naked void value_ptr_known_scalar_4(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 5;						\
+	r0 += r1;					\
+	r1 = -2;					\
+	r0 += r1;					\
+	r1 = -1;					\
+	r0 += r1;					\
+	r1 = *(u8*)(r0 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr += known scalar, 5")
+__success __success_unpriv __retval(0xabcdef12)
+__naked void value_ptr_known_scalar_5(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = %[__imm_0];				\
+	r1 += r0;					\
+	r0 = *(u32*)(r1 + 0);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b),
+	  __imm_const(__imm_0, (6 + 1) * sizeof(int))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr += known scalar, 6")
+__success __success_unpriv __retval(0xabcdef12)
+__naked void value_ptr_known_scalar_6(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = %[__imm_0];				\
+	r0 += r1;					\
+	r1 = %[__imm_1];				\
+	r0 += r1;					\
+	r0 = *(u32*)(r0 + 0);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b),
+	  __imm_const(__imm_0, (3 + 1) * sizeof(int)),
+	  __imm_const(__imm_1, 3 * sizeof(int))
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr += N, value_ptr -= N known scalar")
+__success __success_unpriv __retval(0x12345678)
+__naked void value_ptr_n_known_scalar(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	w1 = 0x12345678;				\
+	*(u32*)(r0 + 0) = r1;				\
+	r0 += 2;					\
+	r1 = 2;						\
+	r0 -= r1;					\
+	r0 = *(u32*)(r0 + 0);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: unknown scalar += value_ptr, 1")
+__success __success_unpriv __retval(1)
+__naked void unknown_scalar_value_ptr_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u8*)(r0 + 0);				\
+	r1 &= 0xf;					\
+	r1 += r0;					\
+	r0 = *(u8*)(r1 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: unknown scalar += value_ptr, 2")
+__success __success_unpriv __retval(0xabcdef12) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void unknown_scalar_value_ptr_2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u32*)(r0 + 0);				\
+	r1 &= 31;					\
+	r1 += r0;					\
+	r0 = *(u32*)(r1 + 0);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: unknown scalar += value_ptr, 3")
+__success __failure_unpriv
+__msg_unpriv("R0 pointer arithmetic of map value goes out of range")
+__retval(0xabcdef12) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void unknown_scalar_value_ptr_3(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = -1;					\
+	r0 += r1;					\
+	r1 = 1;						\
+	r0 += r1;					\
+	r1 = *(u32*)(r0 + 0);				\
+	r1 &= 31;					\
+	r1 += r0;					\
+	r0 = *(u32*)(r1 + 0);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: unknown scalar += value_ptr, 4")
+__failure __msg("R1 max value is outside of the allowed memory range")
+__msg_unpriv("R1 pointer arithmetic of map value goes out of range")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void unknown_scalar_value_ptr_4(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 19;					\
+	r0 += r1;					\
+	r1 = *(u32*)(r0 + 0);				\
+	r1 &= 31;					\
+	r1 += r0;					\
+	r0 = *(u32*)(r1 + 0);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr += unknown scalar, 1")
+__success __success_unpriv __retval(1)
+__naked void value_ptr_unknown_scalar_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u8*)(r0 + 0);				\
+	r1 &= 0xf;					\
+	r0 += r1;					\
+	r1 = *(u8*)(r0 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr += unknown scalar, 2")
+__success __success_unpriv __retval(0xabcdef12) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void value_ptr_unknown_scalar_2_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u32*)(r0 + 0);				\
+	r1 &= 31;					\
+	r0 += r1;					\
+	r0 = *(u32*)(r0 + 0);				\
+l0_%=:	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr += unknown scalar, 3")
+__success __success_unpriv __retval(1)
+__naked void value_ptr_unknown_scalar_3(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u64*)(r0 + 0);				\
+	r2 = *(u64*)(r0 + 8);				\
+	r3 = *(u64*)(r0 + 16);				\
+	r1 &= 0xf;					\
+	r3 &= 1;					\
+	r3 |= 1;					\
+	if r2 > r3 goto l0_%=;				\
+	r0 += r3;					\
+	r0 = *(u8*)(r0 + 0);				\
+	r0 = 1;						\
+l1_%=:	exit;						\
+l0_%=:	r0 = 2;						\
+	goto l1_%=;					\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr += value_ptr")
+__failure __msg("R0 pointer += pointer prohibited")
+__failure_unpriv
+__naked void access_value_ptr_value_ptr_1(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r0 += r0;					\
+	r1 = *(u8*)(r0 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: known scalar -= value_ptr")
+__failure __msg("R1 tried to subtract pointer from scalar")
+__failure_unpriv
+__naked void access_known_scalar_value_ptr_2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 4;						\
+	r1 -= r0;					\
+	r0 = *(u8*)(r1 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr -= known scalar")
+__failure __msg("R0 min value is outside of the allowed memory range")
+__failure_unpriv
+__naked void access_value_ptr_known_scalar(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 4;						\
+	r0 -= r1;					\
+	r1 = *(u8*)(r0 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr -= known scalar, 2")
+__success __success_unpriv __retval(1)
+__naked void value_ptr_known_scalar_2_2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = 6;						\
+	r2 = 4;						\
+	r0 += r1;					\
+	r0 -= r2;					\
+	r1 = *(u8*)(r0 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: unknown scalar -= value_ptr")
+__failure __msg("R1 tried to subtract pointer from scalar")
+__failure_unpriv
+__naked void access_unknown_scalar_value_ptr(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u8*)(r0 + 0);				\
+	r1 &= 0xf;					\
+	r1 -= r0;					\
+	r0 = *(u8*)(r1 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr -= unknown scalar")
+__failure __msg("R0 min value is negative")
+__failure_unpriv
+__naked void access_value_ptr_unknown_scalar(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u8*)(r0 + 0);				\
+	r1 &= 0xf;					\
+	r0 -= r1;					\
+	r1 = *(u8*)(r0 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr -= unknown scalar, 2")
+__success __success_unpriv
+__retval(1)
+#ifdef SPEC_V1
+__xlated_unpriv("r1 &= 7")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 pointer arithmetic of map value goes out of range` */
+__xlated_unpriv("r0 -= r1")
+#endif
+__naked void value_ptr_unknown_scalar_2_2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r1 = *(u8*)(r0 + 0);				\
+	r1 &= 0xf;					\
+	r1 |= 0x7;					\
+	r0 += r1;					\
+	r1 = *(u8*)(r0 + 0);				\
+	r1 &= 0x7;					\
+	r0 -= r1;					\
+	r1 = *(u8*)(r0 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: value_ptr -= value_ptr")
+__failure __msg("R0 invalid mem access 'scalar'")
+__msg_unpriv("R0 pointer -= pointer prohibited")
+__naked void access_value_ptr_value_ptr_2(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 == 0 goto l0_%=;				\
+	r0 -= r0;					\
+	r1 = *(u8*)(r0 + 0);				\
+l0_%=:	r0 = 1;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("socket")
+__description("map access: trying to leak tainted dst reg")
+__failure __msg("math between map_value pointer and 4294967295 is not allowed")
+__failure_unpriv
+__naked void to_leak_tainted_dst_reg(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_array_48b] ll;			\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r2 = r0;					\
+	w1 = 0xFFFFFFFF;				\
+	w1 = w1;					\
+	r2 -= r1;					\
+	*(u64*)(r0 + 0) = r2;				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_array_48b)
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("32bit pkt_ptr -= scalar")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void _32bit_pkt_ptr_scalar(void)
+{
+	asm volatile ("					\
+	r8 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r7 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r6 = r7;					\
+	r6 += 40;					\
+	if r6 > r8 goto l0_%=;				\
+	w4 = w7;					\
+	w6 -= w4;					\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("32bit scalar -= pkt_ptr")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void _32bit_scalar_pkt_ptr(void)
+{
+	asm volatile ("					\
+	r8 = *(u32*)(r1 + %[__sk_buff_data_end]);	\
+	r7 = *(u32*)(r1 + %[__sk_buff_data]);		\
+	r6 = r7;					\
+	r6 += 40;					\
+	if r6 > r8 goto l0_%=;				\
+	w4 = w6;					\
+	w4 -= w7;					\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(__sk_buff_data, offsetof(struct __sk_buff, data)),
+	  __imm_const(__sk_buff_data_end, offsetof(struct __sk_buff, data_end))
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_var_off.c b/tools/testing/selftests/bpf/progs/verifier_var_off.c
new file mode 100644
index 000000000000..f345466bca68
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_var_off.c
@@ -0,0 +1,418 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/var_off.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, long long);
+} map_hash_8b SEC(".maps");
+
+SEC("lwt_in")
+__description("variable-offset ctx access")
+__failure __msg("variable ctx access var_off=(0x0; 0x4)")
+__naked void variable_offset_ctx_access(void)
+{
+	asm volatile ("					\
+	/* Get an unknown value */			\
+	r2 = *(u32*)(r1 + 0);				\
+	/* Make it small and 4-byte aligned */		\
+	r2 &= 4;					\
+	/* add it to skb.  We now have either &skb->len or\
+	 * &skb->pkt_type, but we don't know which	\
+	 */						\
+	r1 += r2;					\
+	/* dereference it */				\
+	r0 = *(u32*)(r1 + 0);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("variable-offset stack read, priv vs unpriv")
+__success __failure_unpriv
+__msg_unpriv("R2 variable stack access prohibited for !root")
+__retval(0)
+__naked void stack_read_priv_vs_unpriv(void)
+{
+	asm volatile ("					\
+	/* Fill the top 8 bytes of the stack */		\
+	r0 = 0;						\
+	*(u64*)(r10 - 8) = r0;				\
+	/* Get an unknown value */			\
+	r2 = *(u32*)(r1 + 0);				\
+	/* Make it small and 4-byte aligned */		\
+	r2 &= 4;					\
+	r2 -= 8;					\
+	/* add it to fp.  We now have either fp-4 or fp-8, but\
+	 * we don't know which				\
+	 */						\
+	r2 += r10;					\
+	/* dereference it for a stack read */		\
+	r0 = *(u32*)(r2 + 0);				\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("variable-offset stack read, uninitialized")
+__success
+__failure_unpriv __msg_unpriv("R2 variable stack access prohibited for !root")
+__naked void variable_offset_stack_read_uninitialized(void)
+{
+	asm volatile ("					\
+	/* Get an unknown value */			\
+	r2 = *(u32*)(r1 + 0);				\
+	/* Make it small and 4-byte aligned */		\
+	r2 &= 4;					\
+	r2 -= 8;					\
+	/* add it to fp.  We now have either fp-4 or fp-8, but\
+	 * we don't know which				\
+	 */						\
+	r2 += r10;					\
+	/* dereference it for a stack read */		\
+	r0 = *(u32*)(r2 + 0);				\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("variable-offset stack write, priv vs unpriv")
+__success
+/* Check that the maximum stack depth is correctly maintained according to the
+ * maximum possible variable offset.
+ */
+__log_level(4) __msg("stack depth 16")
+__failure_unpriv
+/* Variable stack access is rejected for unprivileged.
+ */
+__msg_unpriv("R2 variable stack access prohibited for !root")
+__retval(0)
+__naked void stack_write_priv_vs_unpriv(void)
+{
+	asm volatile ("                               \
+	/* Get an unknown value */                    \
+	r2 = *(u32*)(r1 + 0);                         \
+	/* Make it small and 8-byte aligned */        \
+	r2 &= 8;                                      \
+	r2 -= 16;                                     \
+	/* Add it to fp. We now have either fp-8 or   \
+	 * fp-16, but we don't know which             \
+	 */                                           \
+	r2 += r10;                                    \
+	/* Dereference it for a stack write */        \
+	r0 = 0;                                       \
+	*(u64*)(r2 + 0) = r0;                         \
+	exit;                                         \
+"	::: __clobber_all);
+}
+
+/* Similar to the previous test, but this time also perform a read from the
+ * address written to with a variable offet. The read is allowed, showing that,
+ * after a variable-offset write, a privileged program can read the slots that
+ * were in the range of that write (even if the verifier doesn't actually know if
+ * the slot being read was really written to or not.
+ *
+ * Despite this test being mostly a superset, the previous test is also kept for
+ * the sake of it checking the stack depth in the case where there is no read.
+ */
+SEC("socket")
+__description("variable-offset stack write followed by read")
+__success
+/* Check that the maximum stack depth is correctly maintained according to the
+ * maximum possible variable offset.
+ */
+__log_level(4) __msg("stack depth 16")
+__failure_unpriv
+__msg_unpriv("R2 variable stack access prohibited for !root")
+__retval(0)
+__naked void stack_write_followed_by_read(void)
+{
+	asm volatile ("					\
+	/* Get an unknown value */			\
+	r2 = *(u32*)(r1 + 0);				\
+	/* Make it small and 8-byte aligned */		\
+	r2 &= 8;					\
+	r2 -= 16;					\
+	/* Add it to fp.  We now have either fp-8 or fp-16, but\
+	 * we don't know which				\
+	 */						\
+	r2 += r10;					\
+	/* Dereference it for a stack write */		\
+	r0 = 0;						\
+	*(u64*)(r2 + 0) = r0;				\
+	/* Now read from the address we just wrote. */ \
+	r3 = *(u64*)(r2 + 0);				\
+	r0 = 0;						\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("socket")
+__description("variable-offset stack write clobbers spilled regs")
+__failure
+/* In the privileged case, dereferencing a spilled-and-then-filled
+ * register is rejected because the previous variable offset stack
+ * write might have overwritten the spilled pointer (i.e. we lose track
+ * of the spilled register when we analyze the write).
+ */
+__msg("R2 invalid mem access 'scalar'")
+__failure_unpriv
+/* The unprivileged case is not too interesting; variable
+ * stack access is rejected.
+ */
+__msg_unpriv("R2 variable stack access prohibited for !root")
+__naked void stack_write_clobbers_spilled_regs(void)
+{
+	asm volatile ("					\
+	/* Dummy instruction; needed because we need to patch the next one\
+	 * and we can't patch the first instruction.	\
+	 */						\
+	r6 = 0;						\
+	/* Make R0 a map ptr */				\
+	r0 = %[map_hash_8b] ll;				\
+	/* Get an unknown value */			\
+	r2 = *(u32*)(r1 + 0);				\
+	/* Make it small and 8-byte aligned */		\
+	r2 &= 8;					\
+	r2 -= 16;					\
+	/* Add it to fp. We now have either fp-8 or fp-16, but\
+	 * we don't know which.				\
+	 */						\
+	r2 += r10;					\
+	/* Spill R0(map ptr) into stack */		\
+	*(u64*)(r10 - 8) = r0;				\
+	/* Dereference the unknown value for a stack write */\
+	r0 = 0;						\
+	*(u64*)(r2 + 0) = r0;				\
+	/* Fill the register back into R2 */		\
+	r2 = *(u64*)(r10 - 8);				\
+	/* Try to dereference R2 for a memory load */	\
+	r0 = *(u64*)(r2 + 8);				\
+	exit;						\
+"	:
+	: __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("sockops")
+__description("indirect variable-offset stack access, unbounded")
+__failure __msg("invalid unbounded variable-offset write to stack R4")
+__naked void variable_offset_stack_access_unbounded(void)
+{
+	asm volatile ("					\
+	r2 = 6;						\
+	r3 = 28;					\
+	/* Fill the top 16 bytes of the stack. */	\
+	r4 = 0;						\
+	*(u64*)(r10 - 16) = r4;				\
+	r4 = 0;						\
+	*(u64*)(r10 - 8) = r4;				\
+	/* Get an unknown value. */			\
+	r4 = *(u64*)(r1 + %[bpf_sock_ops_bytes_received]);\
+	/* Check the lower bound but don't check the upper one. */\
+	if r4 s< 0 goto l0_%=;				\
+	/* Point the lower bound to initialized stack. Offset is now in range\
+	 * from fp-16 to fp+0x7fffffffffffffef, i.e. max value is unbounded.\
+	 */						\
+	r4 -= 16;					\
+	r4 += r10;					\
+	r5 = 8;						\
+	/* Dereference it indirectly. */		\
+	call %[bpf_getsockopt];				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_getsockopt),
+	  __imm_const(bpf_sock_ops_bytes_received, offsetof(struct bpf_sock_ops, bytes_received))
+	: __clobber_all);
+}
+
+SEC("lwt_in")
+__description("indirect variable-offset stack access, max out of bound")
+__failure __msg("invalid variable-offset read from stack R2")
+__naked void access_max_out_of_bound(void)
+{
+	asm volatile ("					\
+	/* Fill the top 8 bytes of the stack */		\
+	r2 = 0;						\
+	*(u64*)(r10 - 8) = r2;				\
+	/* Get an unknown value */			\
+	r2 = *(u32*)(r1 + 0);				\
+	/* Make it small and 4-byte aligned */		\
+	r2 &= 4;					\
+	r2 -= 8;					\
+	/* add it to fp.  We now have either fp-4 or fp-8, but\
+	 * we don't know which				\
+	 */						\
+	r2 += r10;					\
+	/* dereference it indirectly */			\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+/* Similar to the test above, but this time check the special case of a
+ * zero-sized stack access. We used to have a bug causing crashes for zero-sized
+ * out-of-bounds accesses.
+ */
+SEC("socket")
+__description("indirect variable-offset stack access, zero-sized, max out of bound")
+__failure __msg("invalid variable-offset write to stack R1")
+__naked void zero_sized_access_max_out_of_bound(void)
+{
+	asm volatile ("                      \
+	r0 = 0;                              \
+	/* Fill some stack */                \
+	*(u64*)(r10 - 16) = r0;              \
+	*(u64*)(r10 - 8) = r0;               \
+	/* Get an unknown value */           \
+	r1 = *(u32*)(r1 + 0);                \
+	r1 &= 63;                            \
+	r1 += -16;                           \
+	/* r1 is now anywhere in [-16,48) */ \
+	r1 += r10;                           \
+	r2 = 0;                              \
+	r3 = 0;                              \
+	call %[bpf_probe_read_kernel];       \
+	exit;                                \
+"	:
+	: __imm(bpf_probe_read_kernel)
+	: __clobber_all);
+}
+
+SEC("lwt_in")
+__description("indirect variable-offset stack access, min out of bound")
+__failure __msg("invalid variable-offset read from stack R2")
+__naked void access_min_out_of_bound(void)
+{
+	asm volatile ("					\
+	/* Fill the top 8 bytes of the stack */		\
+	r2 = 0;						\
+	*(u64*)(r10 - 8) = r2;				\
+	/* Get an unknown value */			\
+	r2 = *(u32*)(r1 + 0);				\
+	/* Make it small and 4-byte aligned */		\
+	r2 &= 4;					\
+	r2 -= 516;					\
+	/* add it to fp.  We now have either fp-516 or fp-512, but\
+	 * we don't know which				\
+	 */						\
+	r2 += r10;					\
+	/* dereference it indirectly */			\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("indirect variable-offset stack access, min_off < min_initialized")
+__success
+__failure_unpriv __msg_unpriv("R2 variable stack access prohibited for !root")
+__naked void access_min_off_min_initialized(void)
+{
+	asm volatile ("					\
+	/* Fill only the top 8 bytes of the stack. */	\
+	r2 = 0;						\
+	*(u64*)(r10 - 8) = r2;				\
+	/* Get an unknown value */			\
+	r2 = *(u32*)(r1 + 0);				\
+	/* Make it small and 4-byte aligned. */		\
+	r2 &= 4;					\
+	r2 -= 16;					\
+	/* Add it to fp.  We now have either fp-12 or fp-16, but we don't know\
+	 * which. fp-16 size 8 is partially uninitialized stack.\
+	 */						\
+	r2 += r10;					\
+	/* Dereference it indirectly. */		\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("cgroup/skb")
+__description("indirect variable-offset stack access, priv vs unpriv")
+__success __failure_unpriv
+__msg_unpriv("R2 variable stack access prohibited for !root")
+__retval(0)
+__naked void stack_access_priv_vs_unpriv(void)
+{
+	asm volatile ("					\
+	/* Fill the top 16 bytes of the stack. */	\
+	r2 = 0;						\
+	*(u64*)(r10 - 16) = r2;				\
+	r2 = 0;						\
+	*(u64*)(r10 - 8) = r2;				\
+	/* Get an unknown value. */			\
+	r2 = *(u32*)(r1 + 0);				\
+	/* Make it small and 4-byte aligned. */		\
+	r2 &= 4;					\
+	r2 -= 16;					\
+	/* Add it to fp.  We now have either fp-12 or fp-16, we don't know\
+	 * which, but either way it points to initialized stack.\
+	 */						\
+	r2 += r10;					\
+	/* Dereference it indirectly. */		\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("lwt_in")
+__description("indirect variable-offset stack access, ok")
+__success __retval(0)
+__naked void variable_offset_stack_access_ok(void)
+{
+	asm volatile ("					\
+	/* Fill the top 16 bytes of the stack. */	\
+	r2 = 0;						\
+	*(u64*)(r10 - 16) = r2;				\
+	r2 = 0;						\
+	*(u64*)(r10 - 8) = r2;				\
+	/* Get an unknown value. */			\
+	r2 = *(u32*)(r1 + 0);				\
+	/* Make it small and 4-byte aligned. */		\
+	r2 &= 4;					\
+	r2 -= 16;					\
+	/* Add it to fp.  We now have either fp-12 or fp-16, we don't know\
+	 * which, but either way it points to initialized stack.\
+	 */						\
+	r2 += r10;					\
+	/* Dereference it indirectly. */		\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c b/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c
new file mode 100644
index 000000000000..55398c04290a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Google LLC. */
+
+#include <vmlinux.h>
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+static char buf[64];
+
+SEC("lsm.s/file_open")
+__success
+int BPF_PROG(get_task_exe_file_and_put_kfunc_from_current_sleepable)
+{
+	struct file *acquired;
+
+	acquired = bpf_get_task_exe_file(bpf_get_current_task_btf());
+	if (!acquired)
+		return 0;
+
+	bpf_put_file(acquired);
+	return 0;
+}
+
+SEC("lsm/file_open")
+__success
+int BPF_PROG(get_task_exe_file_and_put_kfunc_from_current_non_sleepable, struct file *file)
+{
+	struct file *acquired;
+
+	acquired = bpf_get_task_exe_file(bpf_get_current_task_btf());
+	if (!acquired)
+		return 0;
+
+	bpf_put_file(acquired);
+	return 0;
+}
+
+SEC("lsm.s/task_alloc")
+__success
+int BPF_PROG(get_task_exe_file_and_put_kfunc_from_argument,
+	     struct task_struct *task)
+{
+	struct file *acquired;
+
+	acquired = bpf_get_task_exe_file(task);
+	if (!acquired)
+		return 0;
+
+	bpf_put_file(acquired);
+	return 0;
+}
+
+SEC("lsm.s/inode_getattr")
+__success
+int BPF_PROG(path_d_path_from_path_argument, struct path *path)
+{
+	int ret;
+
+	ret = bpf_path_d_path(path, buf, sizeof(buf));
+	__sink(ret);
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__success
+int BPF_PROG(path_d_path_from_file_argument, struct file *file)
+{
+	int ret;
+	const struct path *path;
+
+	/* The f_path member is a path which is embedded directly within a
+	 * file. Therefore, a pointer to such embedded members are still
+	 * recognized by the BPF verifier as being PTR_TRUSTED as it's
+	 * essentially PTR_TRUSTED w/ a non-zero fixed offset.
+	 */
+	path = &file->f_path;
+	ret = bpf_path_d_path(path, buf, sizeof(buf));
+	__sink(ret);
+	return 0;
+}
+
+SEC("lsm.s/inode_rename")
+__success
+int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry,
+	     struct inode *new_dir, struct dentry *new_dentry,
+	     unsigned int flags)
+{
+	struct inode *inode = new_dentry->d_inode;
+	ino_t ino;
+
+	if (!inode)
+		return 0;
+	ino = inode->i_ino;
+	if (ino == 0)
+		return -EACCES;
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c b/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c
new file mode 100644
index 000000000000..4b392c6c8fc4
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c
@@ -0,0 +1,176 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Google LLC. */
+
+#include <vmlinux.h>
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <linux/limits.h>
+
+#include "bpf_misc.h"
+#include "bpf_experimental.h"
+
+static char buf[PATH_MAX];
+
+SEC("lsm.s/file_open")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
+int BPF_PROG(get_task_exe_file_kfunc_null)
+{
+	struct file *acquired;
+
+	/* Can't pass a NULL pointer to bpf_get_task_exe_file(). */
+	acquired = bpf_get_task_exe_file(NULL);
+	if (!acquired)
+		return 0;
+
+	bpf_put_file(acquired);
+	return 0;
+}
+
+SEC("lsm.s/inode_getxattr")
+__failure __msg("arg#0 pointer type STRUCT task_struct must point to scalar, or struct with scalar")
+int BPF_PROG(get_task_exe_file_kfunc_fp)
+{
+	u64 x;
+	struct file *acquired;
+	struct task_struct *task;
+
+	task = (struct task_struct *)&x;
+	/* Can't pass random frame pointer to bpf_get_task_exe_file(). */
+	acquired = bpf_get_task_exe_file(task);
+	if (!acquired)
+		return 0;
+
+	bpf_put_file(acquired);
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("R1 must be referenced or trusted")
+int BPF_PROG(get_task_exe_file_kfunc_untrusted)
+{
+	struct file *acquired;
+	struct task_struct *parent;
+
+	/* Walking a trusted struct task_struct returned from
+	 * bpf_get_current_task_btf() yields an untrusted pointer.
+	 */
+	parent = bpf_get_current_task_btf()->parent;
+	/* Can't pass untrusted pointer to bpf_get_task_exe_file(). */
+	acquired = bpf_get_task_exe_file(parent);
+	if (!acquired)
+		return 0;
+
+	bpf_put_file(acquired);
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("Unreleased reference")
+int BPF_PROG(get_task_exe_file_kfunc_unreleased)
+{
+	struct file *acquired;
+
+	acquired = bpf_get_task_exe_file(bpf_get_current_task_btf());
+	if (!acquired)
+		return 0;
+
+	/* Acquired but never released. */
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("release kernel function bpf_put_file expects")
+int BPF_PROG(put_file_kfunc_unacquired, struct file *file)
+{
+	/* Can't release an unacquired pointer. */
+	bpf_put_file(file);
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("Possibly NULL pointer passed to trusted arg0")
+int BPF_PROG(path_d_path_kfunc_null)
+{
+	/* Can't pass NULL value to bpf_path_d_path() kfunc. */
+	bpf_path_d_path(NULL, buf, sizeof(buf));
+	return 0;
+}
+
+SEC("lsm.s/task_alloc")
+__failure __msg("R1 must be referenced or trusted")
+int BPF_PROG(path_d_path_kfunc_untrusted_from_argument, struct task_struct *task)
+{
+	struct path *root;
+
+	/* Walking a trusted argument typically yields an untrusted
+	 * pointer. This is one example of that.
+	 */
+	root = &task->fs->root;
+	bpf_path_d_path(root, buf, sizeof(buf));
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("R1 must be referenced or trusted")
+int BPF_PROG(path_d_path_kfunc_untrusted_from_current)
+{
+	struct path *pwd;
+	struct task_struct *current;
+
+	current = bpf_get_current_task_btf();
+	/* Walking a trusted pointer returned from bpf_get_current_task_btf()
+	 * yields an untrusted pointer.
+	 */
+	pwd = &current->fs->pwd;
+	bpf_path_d_path(pwd, buf, sizeof(buf));
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("kernel function bpf_path_d_path args#0 expected pointer to STRUCT path but R1 has a pointer to STRUCT file")
+int BPF_PROG(path_d_path_kfunc_type_mismatch, struct file *file)
+{
+	bpf_path_d_path((struct path *)&file->f_task_work, buf, sizeof(buf));
+	return 0;
+}
+
+SEC("lsm.s/file_open")
+__failure __msg("invalid access to map value, value_size=4096 off=0 size=8192")
+int BPF_PROG(path_d_path_kfunc_invalid_buf_sz, struct file *file)
+{
+	/* bpf_path_d_path() enforces a constraint on the buffer size supplied
+	 * by the BPF LSM program via the __sz annotation. buf here is set to
+	 * PATH_MAX, so let's ensure that the BPF verifier rejects BPF_PROG_LOAD
+	 * attempts if the supplied size and the actual size of the buffer
+	 * mismatches.
+	 */
+	bpf_path_d_path(&file->f_path, buf, PATH_MAX * 2);
+	return 0;
+}
+
+SEC("fentry/vfs_open")
+__failure __msg("calling kernel function bpf_path_d_path is not allowed")
+int BPF_PROG(path_d_path_kfunc_non_lsm, struct path *path, struct file *f)
+{
+	/* Calling bpf_path_d_path() from a non-LSM BPF program isn't permitted.
+	 */
+	bpf_path_d_path(path, buf, sizeof(buf));
+	return 0;
+}
+
+SEC("lsm.s/inode_rename")
+__failure __msg("invalid mem access 'trusted_ptr_or_null_'")
+int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry,
+	     struct inode *new_dir, struct dentry *new_dentry,
+	     unsigned int flags)
+{
+	struct inode *inode = new_dentry->d_inode;
+	ino_t ino;
+
+	ino = inode->i_ino;
+	if (ino == 0)
+		return -EACCES;
+	return 0;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_xadd.c b/tools/testing/selftests/bpf/progs/verifier_xadd.c
new file mode 100644
index 000000000000..05a0a55adb45
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_xadd.c
@@ -0,0 +1,124 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/xadd.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, long long);
+	__type(value, long long);
+} map_hash_8b SEC(".maps");
+
+SEC("tc")
+__description("xadd/w check unaligned stack")
+__failure __msg("misaligned stack access off")
+__naked void xadd_w_check_unaligned_stack(void)
+{
+	asm volatile ("					\
+	r0 = 1;						\
+	*(u64*)(r10 - 8) = r0;				\
+	lock *(u32 *)(r10 - 7) += w0;			\
+	r0 = *(u64*)(r10 - 8);				\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tc")
+__description("xadd/w check unaligned map")
+__failure __msg("misaligned value access off")
+__naked void xadd_w_check_unaligned_map(void)
+{
+	asm volatile ("					\
+	r1 = 0;						\
+	*(u64*)(r10 - 8) = r1;				\
+	r2 = r10;					\
+	r2 += -8;					\
+	r1 = %[map_hash_8b] ll;				\
+	call %[bpf_map_lookup_elem];			\
+	if r0 != 0 goto l0_%=;				\
+	exit;						\
+l0_%=:	r1 = 1;						\
+	lock *(u32 *)(r0 + 3) += w1;			\
+	r0 = *(u32*)(r0 + 3);				\
+	exit;						\
+"	:
+	: __imm(bpf_map_lookup_elem),
+	  __imm_addr(map_hash_8b)
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("xadd/w check unaligned pkt")
+__failure __msg("BPF_ATOMIC stores into R2 pkt is not allowed")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void xadd_w_check_unaligned_pkt(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 < r3 goto l0_%=;				\
+	r0 = 99;					\
+	goto l1_%=;					\
+l0_%=:	r0 = 1;						\
+	r1 = 0;						\
+	*(u32*)(r2 + 0) = r1;				\
+	r1 = 0;						\
+	*(u32*)(r2 + 3) = r1;				\
+	lock *(u32 *)(r2 + 1) += w0;			\
+	lock *(u32 *)(r2 + 2) += w0;			\
+	r0 = *(u32*)(r2 + 1);				\
+l1_%=:	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("tc")
+__description("xadd/w check whether src/dst got mangled, 1")
+__success __retval(3)
+__naked void src_dst_got_mangled_1(void)
+{
+	asm volatile ("					\
+	r0 = 1;						\
+	r6 = r0;					\
+	r7 = r10;					\
+	*(u64*)(r10 - 8) = r0;				\
+	lock *(u64 *)(r10 - 8) += r0;			\
+	lock *(u64 *)(r10 - 8) += r0;			\
+	if r6 != r0 goto l0_%=;				\
+	if r7 != r10 goto l0_%=;			\
+	r0 = *(u64*)(r10 - 8);				\
+	exit;						\
+l0_%=:	r0 = 42;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+SEC("tc")
+__description("xadd/w check whether src/dst got mangled, 2")
+__success __retval(3)
+__naked void src_dst_got_mangled_2(void)
+{
+	asm volatile ("					\
+	r0 = 1;						\
+	r6 = r0;					\
+	r7 = r10;					\
+	*(u32*)(r10 - 8) = r0;				\
+	lock *(u32 *)(r10 - 8) += w0;			\
+	lock *(u32 *)(r10 - 8) += w0;			\
+	if r6 != r0 goto l0_%=;				\
+	if r7 != r10 goto l0_%=;			\
+	r0 = *(u32*)(r10 - 8);				\
+	exit;						\
+l0_%=:	r0 = 42;					\
+	exit;						\
+"	::: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_xdp.c b/tools/testing/selftests/bpf/progs/verifier_xdp.c
new file mode 100644
index 000000000000..50768ed179b3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_xdp.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/xdp.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("xdp")
+__description("XDP, using ifindex from netdev")
+__success __retval(1)
+__naked void xdp_using_ifindex_from_netdev(void)
+{
+	asm volatile ("					\
+	r0 = 0;						\
+	r2 = *(u32*)(r1 + %[xdp_md_ingress_ifindex]);	\
+	if r2 < 1 goto l0_%=;				\
+	r0 = 1;						\
+l0_%=:	exit;						\
+"	:
+	: __imm_const(xdp_md_ingress_ifindex, offsetof(struct xdp_md, ingress_ifindex))
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_xdp_direct_packet_access.c b/tools/testing/selftests/bpf/progs/verifier_xdp_direct_packet_access.c
new file mode 100644
index 000000000000..df2dfd1b15d1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_xdp_direct_packet_access.c
@@ -0,0 +1,1722 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Converted from tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end mangling, bad access 1")
+__failure __msg("R3 pointer arithmetic on pkt_end")
+__naked void end_mangling_bad_access_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	r3 += 8;					\
+	if r1 > r3 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 8);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end mangling, bad access 2")
+__failure __msg("R3 pointer arithmetic on pkt_end")
+__naked void end_mangling_bad_access_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	r3 -= 8;					\
+	if r1 > r3 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 8);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data' > pkt_end, corner case, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void end_corner_case_good_access_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 > r3 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 8);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data' > pkt_end, bad access 1")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_end_bad_access_1_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 > r3 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 4);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data' > pkt_end, bad access 2")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_end_bad_access_2_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 > r3 goto l0_%=;				\
+l0_%=:	r0 = *(u64*)(r1 - 8);				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data' > pkt_end, corner case +1, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_good_access_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 9;					\
+	if r1 > r3 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 9);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data' > pkt_end, corner case -1, bad access")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_bad_access_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 7;					\
+	if r1 > r3 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 7);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end > pkt_data', good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void end_pkt_data_good_access_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 > r1 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u32*)(r1 - 5);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end > pkt_data', corner case -1, bad access")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_bad_access_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 6;					\
+	if r3 > r1 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 6);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end > pkt_data', bad access 2")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_data_bad_access_2_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 > r1 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 8);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end > pkt_data', corner case, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void data_corner_case_good_access_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 7;					\
+	if r3 > r1 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 7);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end > pkt_data', corner case +1, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_good_access_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 > r1 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 8);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data' < pkt_end, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void data_pkt_end_good_access_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 < r3 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u32*)(r1 - 5);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data' < pkt_end, corner case -1, bad access")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_bad_access_3(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 6;					\
+	if r1 < r3 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 6);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data' < pkt_end, bad access 2")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_end_bad_access_2_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 < r3 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 8);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data' < pkt_end, corner case, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void end_corner_case_good_access_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 7;					\
+	if r1 < r3 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 7);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data' < pkt_end, corner case +1, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_good_access_3(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 < r3 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 8);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end < pkt_data', corner case, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void data_corner_case_good_access_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 < r1 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 8);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end < pkt_data', bad access 1")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_data_bad_access_1_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 < r1 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 4);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end < pkt_data', bad access 2")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_data_bad_access_2_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 < r1 goto l0_%=;				\
+l0_%=:	r0 = *(u64*)(r1 - 8);				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end < pkt_data', corner case +1, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_good_access_4(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 9;					\
+	if r3 < r1 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 9);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end < pkt_data', corner case -1, bad access")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_bad_access_4(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 7;					\
+	if r3 < r1 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 7);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data' >= pkt_end, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void data_pkt_end_good_access_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 >= r3 goto l0_%=;				\
+	r0 = *(u32*)(r1 - 5);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data' >= pkt_end, corner case -1, bad access")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_bad_access_5(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 6;					\
+	if r1 >= r3 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 6);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data' >= pkt_end, bad access 2")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_end_bad_access_2_3(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 >= r3 goto l0_%=;				\
+l0_%=:	r0 = *(u32*)(r1 - 5);				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data' >= pkt_end, corner case, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void end_corner_case_good_access_3(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 7;					\
+	if r1 >= r3 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 7);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data' >= pkt_end, corner case +1, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_good_access_5(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 >= r3 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 8);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end >= pkt_data', corner case, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void data_corner_case_good_access_3(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 >= r1 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 8);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end >= pkt_data', bad access 1")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_data_bad_access_1_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 >= r1 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 4);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end >= pkt_data', bad access 2")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_data_bad_access_2_3(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 >= r1 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 8);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end >= pkt_data', corner case +1, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_good_access_6(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 9;					\
+	if r3 >= r1 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 9);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end >= pkt_data', corner case -1, bad access")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_bad_access_6(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 7;					\
+	if r3 >= r1 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 7);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data' <= pkt_end, corner case, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void end_corner_case_good_access_4(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 <= r3 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 8);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data' <= pkt_end, bad access 1")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_end_bad_access_1_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 <= r3 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 4);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data' <= pkt_end, bad access 2")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_end_bad_access_2_4(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 <= r3 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 8);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data' <= pkt_end, corner case +1, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_good_access_7(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 9;					\
+	if r1 <= r3 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 9);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data' <= pkt_end, corner case -1, bad access")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_bad_access_7(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 7;					\
+	if r1 <= r3 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 7);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end <= pkt_data', good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void end_pkt_data_good_access_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 <= r1 goto l0_%=;				\
+	r0 = *(u32*)(r1 - 5);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end <= pkt_data', corner case -1, bad access")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_bad_access_8(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 6;					\
+	if r3 <= r1 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 6);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end <= pkt_data', bad access 2")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_data_bad_access_2_4(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 <= r1 goto l0_%=;				\
+l0_%=:	r0 = *(u32*)(r1 - 5);				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end <= pkt_data', corner case, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void data_corner_case_good_access_4(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 7;					\
+	if r3 <= r1 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 7);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_end <= pkt_data', corner case +1, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_good_access_8(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data_end]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 <= r1 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 8);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_end, offsetof(struct xdp_md, data_end))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_meta' > pkt_data, corner case, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void data_corner_case_good_access_5(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 > r3 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 8);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_meta' > pkt_data, bad access 1")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_data_bad_access_1_3(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 > r3 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 4);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_meta' > pkt_data, bad access 2")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_data_bad_access_2_5(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 > r3 goto l0_%=;				\
+l0_%=:	r0 = *(u64*)(r1 - 8);				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_meta' > pkt_data, corner case +1, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_good_access_9(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 9;					\
+	if r1 > r3 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 9);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_meta' > pkt_data, corner case -1, bad access")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_bad_access_9(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 7;					\
+	if r1 > r3 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 7);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data > pkt_meta', good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void data_pkt_meta_good_access_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 > r1 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u32*)(r1 - 5);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data > pkt_meta', corner case -1, bad access")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_bad_access_10(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 6;					\
+	if r3 > r1 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 6);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data > pkt_meta', bad access 2")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_meta_bad_access_2_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 > r1 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 8);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data > pkt_meta', corner case, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void meta_corner_case_good_access_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 7;					\
+	if r3 > r1 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 7);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data > pkt_meta', corner case +1, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_good_access_10(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 > r1 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 8);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_meta' < pkt_data, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void meta_pkt_data_good_access_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 < r3 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u32*)(r1 - 5);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_meta' < pkt_data, corner case -1, bad access")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_bad_access_11(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 6;					\
+	if r1 < r3 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 6);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_meta' < pkt_data, bad access 2")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_data_bad_access_2_6(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 < r3 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 8);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_meta' < pkt_data, corner case, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void data_corner_case_good_access_6(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 7;					\
+	if r1 < r3 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 7);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_meta' < pkt_data, corner case +1, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_good_access_11(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 < r3 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 8);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data < pkt_meta', corner case, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void meta_corner_case_good_access_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 < r1 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 8);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data < pkt_meta', bad access 1")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_meta_bad_access_1_1(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 < r1 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 4);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data < pkt_meta', bad access 2")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_meta_bad_access_2_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 < r1 goto l0_%=;				\
+l0_%=:	r0 = *(u64*)(r1 - 8);				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data < pkt_meta', corner case +1, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_good_access_12(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 9;					\
+	if r3 < r1 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 9);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data < pkt_meta', corner case -1, bad access")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_bad_access_12(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 7;					\
+	if r3 < r1 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 7);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_meta' >= pkt_data, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void meta_pkt_data_good_access_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 >= r3 goto l0_%=;				\
+	r0 = *(u32*)(r1 - 5);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_meta' >= pkt_data, corner case -1, bad access")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_bad_access_13(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 6;					\
+	if r1 >= r3 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 6);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_meta' >= pkt_data, bad access 2")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_data_bad_access_2_7(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 >= r3 goto l0_%=;				\
+l0_%=:	r0 = *(u32*)(r1 - 5);				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_meta' >= pkt_data, corner case, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void data_corner_case_good_access_7(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 7;					\
+	if r1 >= r3 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 7);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_meta' >= pkt_data, corner case +1, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_good_access_13(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 >= r3 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 8);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data >= pkt_meta', corner case, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void meta_corner_case_good_access_3(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 >= r1 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 8);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data >= pkt_meta', bad access 1")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_meta_bad_access_1_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 >= r1 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 4);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data >= pkt_meta', bad access 2")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_meta_bad_access_2_3(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 >= r1 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 8);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data >= pkt_meta', corner case +1, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_good_access_14(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 9;					\
+	if r3 >= r1 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 9);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data >= pkt_meta', corner case -1, bad access")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_bad_access_14(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 7;					\
+	if r3 >= r1 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 7);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_meta' <= pkt_data, corner case, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void data_corner_case_good_access_8(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 <= r3 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 8);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_meta' <= pkt_data, bad access 1")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_data_bad_access_1_4(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 <= r3 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 4);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_meta' <= pkt_data, bad access 2")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_data_bad_access_2_8(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r1 <= r3 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 8);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_meta' <= pkt_data, corner case +1, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_good_access_15(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 9;					\
+	if r1 <= r3 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 9);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_meta' <= pkt_data, corner case -1, bad access")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_bad_access_15(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 7;					\
+	if r1 <= r3 goto l0_%=;				\
+	goto l1_%=;					\
+l0_%=:	r0 = *(u64*)(r1 - 7);				\
+l1_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data <= pkt_meta', good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void data_pkt_meta_good_access_2(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 <= r1 goto l0_%=;				\
+	r0 = *(u32*)(r1 - 5);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data <= pkt_meta', corner case -1, bad access")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_bad_access_16(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 6;					\
+	if r3 <= r1 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 6);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data <= pkt_meta', bad access 2")
+__failure __msg("R1 offset is outside of the packet")
+__flag(BPF_F_ANY_ALIGNMENT)
+__naked void pkt_meta_bad_access_2_4(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 <= r1 goto l0_%=;				\
+l0_%=:	r0 = *(u32*)(r1 - 5);				\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data <= pkt_meta', corner case, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void meta_corner_case_good_access_4(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 7;					\
+	if r3 <= r1 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 7);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+SEC("xdp")
+__description("XDP pkt read, pkt_data <= pkt_meta', corner case +1, good access")
+__success __retval(0) __flag(BPF_F_ANY_ALIGNMENT)
+__naked void corner_case_1_good_access_16(void)
+{
+	asm volatile ("					\
+	r2 = *(u32*)(r1 + %[xdp_md_data_meta]);		\
+	r3 = *(u32*)(r1 + %[xdp_md_data]);		\
+	r1 = r2;					\
+	r1 += 8;					\
+	if r3 <= r1 goto l0_%=;				\
+	r0 = *(u64*)(r1 - 8);				\
+l0_%=:	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(xdp_md_data, offsetof(struct xdp_md, data)),
+	  __imm_const(xdp_md_data_meta, offsetof(struct xdp_md, data_meta))
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/vrf_socket_lookup.c b/tools/testing/selftests/bpf/progs/vrf_socket_lookup.c
new file mode 100644
index 000000000000..bcfb6feb38c0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/vrf_socket_lookup.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#include <linux/ip.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/pkt_cls.h>
+#include <stdbool.h>
+
+int lookup_status;
+bool test_xdp;
+bool tcp_skc;
+
+#define CUR_NS BPF_F_CURRENT_NETNS
+
+static void socket_lookup(void *ctx, void *data_end, void *data)
+{
+	struct ethhdr *eth = data;
+	struct bpf_sock_tuple *tp;
+	struct bpf_sock *sk;
+	struct iphdr *iph;
+	int tplen;
+
+	if (eth + 1 > data_end)
+		return;
+
+	if (eth->h_proto != bpf_htons(ETH_P_IP))
+		return;
+
+	iph = (struct iphdr *)(eth + 1);
+	if (iph + 1 > data_end)
+		return;
+
+	tp = (struct bpf_sock_tuple *)&iph->saddr;
+	tplen = sizeof(tp->ipv4);
+	if ((void *)tp + tplen > data_end)
+		return;
+
+	switch (iph->protocol) {
+	case IPPROTO_TCP:
+		if (tcp_skc)
+			sk = bpf_skc_lookup_tcp(ctx, tp, tplen, CUR_NS, 0);
+		else
+			sk = bpf_sk_lookup_tcp(ctx, tp, tplen, CUR_NS, 0);
+		break;
+	case IPPROTO_UDP:
+		sk = bpf_sk_lookup_udp(ctx, tp, tplen, CUR_NS, 0);
+		break;
+	default:
+		return;
+	}
+
+	lookup_status = 0;
+
+	if (sk) {
+		bpf_sk_release(sk);
+		lookup_status = 1;
+	}
+}
+
+SEC("tc")
+int tc_socket_lookup(struct __sk_buff *skb)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	void *data = (void *)(long)skb->data;
+
+	if (test_xdp)
+		return TC_ACT_UNSPEC;
+
+	socket_lookup(skb, data_end, data);
+	return TC_ACT_UNSPEC;
+}
+
+SEC("xdp")
+int xdp_socket_lookup(struct xdp_md *xdp)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+
+	if (!test_xdp)
+		return XDP_PASS;
+
+	socket_lookup(xdp, data_end, data);
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/wq.c b/tools/testing/selftests/bpf/progs/wq.c
new file mode 100644
index 000000000000..25be2cd9d42c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/wq.c
@@ -0,0 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Benjamin Tissoires
+ */
+
+#include "bpf_experimental.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct hmap_elem {
+	int counter;
+	struct bpf_timer timer; /* unused */
+	struct bpf_spin_lock lock; /* unused */
+	struct bpf_wq work;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1000);
+	__type(key, int);
+	__type(value, struct hmap_elem);
+} hmap SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__uint(max_entries, 1000);
+	__type(key, int);
+	__type(value, struct hmap_elem);
+} hmap_malloc SEC(".maps");
+
+struct elem {
+	int ok_offset;
+	struct bpf_wq w;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 2);
+	__type(key, int);
+	__type(value, struct elem);
+} array SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_LRU_HASH);
+	__uint(max_entries, 4);
+	__type(key, int);
+	__type(value, struct elem);
+} lru SEC(".maps");
+
+__u32 ok;
+__u32 ok_sleepable;
+
+static int test_elem_callback(void *map, int *key,
+		int (callback_fn)(void *map, int *key, void *value))
+{
+	struct elem init = {}, *val;
+	struct bpf_wq *wq;
+
+	if ((ok & (1 << *key) ||
+	    (ok_sleepable & (1 << *key))))
+		return -22;
+
+	if (map == &lru &&
+	    bpf_map_update_elem(map, key, &init, 0))
+		return -1;
+
+	val = bpf_map_lookup_elem(map, key);
+	if (!val)
+		return -2;
+
+	val->ok_offset = *key;
+
+	wq = &val->w;
+	if (bpf_wq_init(wq, map, 0) != 0)
+		return -3;
+
+	if (bpf_wq_set_callback(wq, callback_fn, 0))
+		return -4;
+
+	if (bpf_wq_start(wq, 0))
+		return -5;
+
+	return 0;
+}
+
+static int test_hmap_elem_callback(void *map, int *key,
+		int (callback_fn)(void *map, int *key, void *value))
+{
+	struct hmap_elem init = {}, *val;
+	struct bpf_wq *wq;
+
+	if ((ok & (1 << *key) ||
+	    (ok_sleepable & (1 << *key))))
+		return -22;
+
+	if (bpf_map_update_elem(map, key, &init, 0))
+		return -1;
+
+	val = bpf_map_lookup_elem(map, key);
+	if (!val)
+		return -2;
+
+	wq = &val->work;
+	if (bpf_wq_init(wq, map, 0) != 0)
+		return -3;
+
+	if (bpf_wq_set_callback(wq, callback_fn, 0))
+		return -4;
+
+	if (bpf_wq_start(wq, 0))
+		return -5;
+
+	return 0;
+}
+
+/* callback for non sleepable workqueue */
+static int wq_callback(void *map, int *key, void *value)
+{
+	bpf_kfunc_common_test();
+	ok |= (1 << *key);
+	return 0;
+}
+
+/* callback for sleepable workqueue */
+static int wq_cb_sleepable(void *map, int *key, void *value)
+{
+	struct elem *data = (struct elem *)value;
+	int offset = data->ok_offset;
+
+	if (*key != offset)
+		return 0;
+
+	bpf_kfunc_call_test_sleepable();
+	ok_sleepable |= (1 << offset);
+	return 0;
+}
+
+SEC("tc")
+/* test that workqueues can be used from an array */
+__retval(0)
+long test_call_array_sleepable(void *ctx)
+{
+	int key = 0;
+
+	return test_elem_callback(&array, &key, wq_cb_sleepable);
+}
+
+SEC("syscall")
+/* Same test than above but from a sleepable context. */
+__retval(0)
+long test_syscall_array_sleepable(void *ctx)
+{
+	int key = 1;
+
+	return test_elem_callback(&array, &key, wq_cb_sleepable);
+}
+
+SEC("tc")
+/* test that workqueues can be used from a hashmap */
+__retval(0)
+long test_call_hash_sleepable(void *ctx)
+{
+	int key = 2;
+
+	return test_hmap_elem_callback(&hmap, &key, wq_callback);
+}
+
+SEC("tc")
+/* test that workqueues can be used from a hashmap with NO_PREALLOC. */
+__retval(0)
+long test_call_hash_malloc_sleepable(void *ctx)
+{
+	int key = 3;
+
+	return test_hmap_elem_callback(&hmap_malloc, &key, wq_callback);
+}
+
+SEC("tc")
+/* test that workqueues can be used from a LRU map */
+__retval(0)
+long test_call_lru_sleepable(void *ctx)
+{
+	int key = 4;
+
+	return test_elem_callback(&lru, &key, wq_callback);
+}
+
+SEC("tc")
+long test_map_no_btf(void *ctx)
+{
+	struct elem *val;
+	struct bpf_wq *wq;
+	int key = 42;
+
+	val = bpf_map_lookup_elem(&array, &key);
+	if (!val)
+		return -2;
+
+	wq = &val->w;
+	if (bpf_wq_init(wq, &array, 0) != 0)
+		return -3;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/wq_failures.c b/tools/testing/selftests/bpf/progs/wq_failures.c
new file mode 100644
index 000000000000..d06f6d40594a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/wq_failures.c
@@ -0,0 +1,167 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Benjamin Tissoires
+ */
+
+#include "bpf_experimental.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct elem {
+	struct bpf_wq w;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 2);
+	__type(key, int);
+	__type(value, struct elem);
+} array SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_LRU_HASH);
+	__uint(max_entries, 4);
+	__type(key, int);
+	__type(value, struct elem);
+} lru SEC(".maps");
+
+/* callback for non sleepable workqueue */
+static int wq_callback(void *map, int *key, void *value)
+{
+	bpf_kfunc_common_test();
+	return 0;
+}
+
+/* callback for sleepable workqueue */
+static int wq_cb_sleepable(void *map, int *key, void *value)
+{
+	bpf_kfunc_call_test_sleepable();
+	return 0;
+}
+
+SEC("tc")
+/* test that bpf_wq_init takes a map as a second argument
+ */
+__log_level(2)
+__flag(BPF_F_TEST_STATE_FREQ)
+__failure
+__msg(": (85) call bpf_wq_init#") /* anchor message */
+__msg("pointer in R2 isn't map pointer")
+long test_wq_init_nomap(void *ctx)
+{
+	struct bpf_wq *wq;
+	struct elem *val;
+	int key = 0;
+
+	val = bpf_map_lookup_elem(&array, &key);
+	if (!val)
+		return -1;
+
+	wq = &val->w;
+	if (bpf_wq_init(wq, &key, 0) != 0)
+		return -3;
+
+	return 0;
+}
+
+SEC("tc")
+/* test that the workqueue is part of the map in bpf_wq_init
+ */
+__log_level(2)
+__flag(BPF_F_TEST_STATE_FREQ)
+__failure
+__msg(": (85) call bpf_wq_init#") /* anchor message */
+__msg("workqueue pointer in R1 map_uid=0 doesn't match map pointer in R2 map_uid=0")
+long test_wq_init_wrong_map(void *ctx)
+{
+	struct bpf_wq *wq;
+	struct elem *val;
+	int key = 0;
+
+	val = bpf_map_lookup_elem(&array, &key);
+	if (!val)
+		return -1;
+
+	wq = &val->w;
+	if (bpf_wq_init(wq, &lru, 0) != 0)
+		return -3;
+
+	return 0;
+}
+
+SEC("?tc")
+__log_level(2)
+__failure
+/* check that the first argument of bpf_wq_set_callback()
+ * is a correct bpf_wq pointer.
+ */
+__msg(": (85) call bpf_wq_set_callback_impl#") /* anchor message */
+__msg("arg#0 doesn't point to a map value")
+long test_wrong_wq_pointer(void *ctx)
+{
+	int key = 0;
+	struct bpf_wq *wq;
+
+	wq = bpf_map_lookup_elem(&array, &key);
+	if (!wq)
+		return 1;
+
+	if (bpf_wq_init(wq, &array, 0))
+		return 2;
+
+	if (bpf_wq_set_callback((void *)&wq, wq_callback, 0))
+		return 3;
+
+	return -22;
+}
+
+SEC("?tc")
+__log_level(2)
+__failure
+/* check that the first argument of bpf_wq_set_callback()
+ * is a correct bpf_wq pointer.
+ */
+__msg(": (85) call bpf_wq_set_callback_impl#") /* anchor message */
+__msg("off 1 doesn't point to 'struct bpf_wq' that is at 0")
+long test_wrong_wq_pointer_offset(void *ctx)
+{
+	int key = 0;
+	struct bpf_wq *wq;
+
+	wq = bpf_map_lookup_elem(&array, &key);
+	if (!wq)
+		return 1;
+
+	if (bpf_wq_init(wq, &array, 0))
+		return 2;
+
+	if (bpf_wq_set_callback((void *)wq + 1, wq_cb_sleepable, 0))
+		return 3;
+
+	return -22;
+}
+
+SEC("tc")
+__log_level(2)
+__failure
+__msg(": (85) call bpf_wq_init#")
+__msg("R1 doesn't have constant offset. bpf_wq has to be at the constant offset")
+long test_bad_wq_off(void *ctx)
+{
+	struct elem *val;
+	struct bpf_wq *wq;
+	int key = 42;
+	u64 unknown;
+
+	val = bpf_map_lookup_elem(&array, &key);
+	if (!val)
+		return -2;
+
+	unknown = bpf_get_prandom_u32();
+	wq = &val->w + unknown;
+	if (bpf_wq_init(wq, &array, 0) != 0)
+		return -3;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/xdp_features.c b/tools/testing/selftests/bpf/progs/xdp_features.c
new file mode 100644
index 000000000000..67424084a38a
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/xdp_features.c
@@ -0,0 +1,268 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include <linux/netdev.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_tracing.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/udp.h>
+#include <asm-generic/errno-base.h>
+
+#include "xdp_features.h"
+
+#define ipv6_addr_equal(a, b)	((a).s6_addr32[0] == (b).s6_addr32[0] &&	\
+				 (a).s6_addr32[1] == (b).s6_addr32[1] &&	\
+				 (a).s6_addr32[2] == (b).s6_addr32[2] &&	\
+				 (a).s6_addr32[3] == (b).s6_addr32[3])
+
+struct net_device;
+struct bpf_prog;
+
+struct xdp_cpumap_stats {
+	unsigned int redirect;
+	unsigned int pass;
+	unsigned int drop;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, __u32);
+	__type(value, __u32);
+	__uint(max_entries, 1);
+} stats SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, __u32);
+	__type(value, __u32);
+	__uint(max_entries, 1);
+} dut_stats SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_CPUMAP);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_cpumap_val));
+	__uint(max_entries, 1);
+} cpu_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_devmap_val));
+	__uint(max_entries, 1);
+} dev_map SEC(".maps");
+
+const volatile struct in6_addr tester_addr;
+const volatile struct in6_addr dut_addr;
+
+static __always_inline int
+xdp_process_echo_packet(struct xdp_md *xdp, bool dut)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+	struct ethhdr *eh = data;
+	struct tlv_hdr *tlv;
+	struct udphdr *uh;
+	__be16 port;
+
+	if (eh + 1 > (struct ethhdr *)data_end)
+		return -EINVAL;
+
+	if (eh->h_proto == bpf_htons(ETH_P_IP)) {
+		struct iphdr *ih = (struct iphdr *)(eh + 1);
+		__be32 saddr = dut ? tester_addr.s6_addr32[3]
+				   : dut_addr.s6_addr32[3];
+		__be32 daddr = dut ? dut_addr.s6_addr32[3]
+				   : tester_addr.s6_addr32[3];
+
+		ih = (struct iphdr *)(eh + 1);
+		if (ih + 1 > (struct iphdr *)data_end)
+			return -EINVAL;
+
+		if (saddr != ih->saddr)
+			return -EINVAL;
+
+		if (daddr != ih->daddr)
+			return -EINVAL;
+
+		if (ih->protocol != IPPROTO_UDP)
+			return -EINVAL;
+
+		uh = (struct udphdr *)(ih + 1);
+	} else if (eh->h_proto == bpf_htons(ETH_P_IPV6)) {
+		struct in6_addr saddr = dut ? tester_addr : dut_addr;
+		struct in6_addr daddr = dut ? dut_addr : tester_addr;
+		struct ipv6hdr *ih6 = (struct ipv6hdr *)(eh + 1);
+
+		if (ih6 + 1 > (struct ipv6hdr *)data_end)
+			return -EINVAL;
+
+		if (!ipv6_addr_equal(saddr, ih6->saddr))
+			return -EINVAL;
+
+		if (!ipv6_addr_equal(daddr, ih6->daddr))
+			return -EINVAL;
+
+		if (ih6->nexthdr != IPPROTO_UDP)
+			return -EINVAL;
+
+		uh = (struct udphdr *)(ih6 + 1);
+	} else {
+		return -EINVAL;
+	}
+
+	if (uh + 1 > (struct udphdr *)data_end)
+		return -EINVAL;
+
+	port = dut ? uh->dest : uh->source;
+	if (port != bpf_htons(DUT_ECHO_PORT))
+		return -EINVAL;
+
+	tlv = (struct tlv_hdr *)(uh + 1);
+	if (tlv + 1 > data_end)
+		return -EINVAL;
+
+	return bpf_htons(tlv->type) == CMD_ECHO ? 0 : -EINVAL;
+}
+
+static __always_inline int
+xdp_update_stats(struct xdp_md *xdp, bool tx, bool dut)
+{
+	__u32 *val, key = 0;
+
+	if (xdp_process_echo_packet(xdp, tx))
+		return -EINVAL;
+
+	if (dut)
+		val = bpf_map_lookup_elem(&dut_stats, &key);
+	else
+		val = bpf_map_lookup_elem(&stats, &key);
+
+	if (val)
+		__sync_add_and_fetch(val, 1);
+
+	return 0;
+}
+
+/* Tester */
+
+SEC("xdp")
+int xdp_tester_check_tx(struct xdp_md *xdp)
+{
+	xdp_update_stats(xdp, true, false);
+
+	return XDP_PASS;
+}
+
+SEC("xdp")
+int xdp_tester_check_rx(struct xdp_md *xdp)
+{
+	xdp_update_stats(xdp, false, false);
+
+	return XDP_PASS;
+}
+
+/* DUT */
+
+SEC("xdp")
+int xdp_do_pass(struct xdp_md *xdp)
+{
+	xdp_update_stats(xdp, true, true);
+
+	return XDP_PASS;
+}
+
+SEC("xdp")
+int xdp_do_drop(struct xdp_md *xdp)
+{
+	if (xdp_update_stats(xdp, true, true))
+		return XDP_PASS;
+
+	return XDP_DROP;
+}
+
+SEC("xdp")
+int xdp_do_aborted(struct xdp_md *xdp)
+{
+	if (xdp_process_echo_packet(xdp, true))
+		return XDP_PASS;
+
+	return XDP_ABORTED;
+}
+
+SEC("xdp")
+int xdp_do_tx(struct xdp_md *xdp)
+{
+	void *data = (void *)(long)xdp->data;
+	struct ethhdr *eh = data;
+	__u8 tmp_mac[ETH_ALEN];
+
+	if (xdp_update_stats(xdp, true, true))
+		return XDP_PASS;
+
+	__builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN);
+	__builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN);
+	__builtin_memcpy(eh->h_dest, tmp_mac, ETH_ALEN);
+
+	return XDP_TX;
+}
+
+SEC("xdp")
+int xdp_do_redirect(struct xdp_md *xdp)
+{
+	if (xdp_process_echo_packet(xdp, true))
+		return XDP_PASS;
+
+	return bpf_redirect_map(&cpu_map, 0, 0);
+}
+
+SEC("tp_btf/xdp_exception")
+int BPF_PROG(xdp_exception, const struct net_device *dev,
+	     const struct bpf_prog *xdp, __u32 act)
+{
+	__u32 *val, key = 0;
+
+	val = bpf_map_lookup_elem(&dut_stats, &key);
+	if (val)
+		__sync_add_and_fetch(val, 1);
+
+	return 0;
+}
+
+SEC("tp_btf/xdp_cpumap_kthread")
+int BPF_PROG(tp_xdp_cpumap_kthread, int map_id, unsigned int processed,
+	     unsigned int drops, int sched, struct xdp_cpumap_stats *xdp_stats)
+{
+	__u32 *val, key = 0;
+
+	val = bpf_map_lookup_elem(&dut_stats, &key);
+	if (val)
+		__sync_add_and_fetch(val, 1);
+
+	return 0;
+}
+
+SEC("xdp/cpumap")
+int xdp_do_redirect_cpumap(struct xdp_md *xdp)
+{
+	void *data = (void *)(long)xdp->data;
+	struct ethhdr *eh = data;
+	__u8 tmp_mac[ETH_ALEN];
+
+	if (xdp_process_echo_packet(xdp, true))
+		return XDP_PASS;
+
+	__builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN);
+	__builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN);
+	__builtin_memcpy(eh->h_dest, tmp_mac, ETH_ALEN);
+
+	return bpf_redirect_map(&dev_map, 0, 0);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/xdp_flowtable.c b/tools/testing/selftests/bpf/progs/xdp_flowtable.c
new file mode 100644
index 000000000000..7fdc7b23ee74
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/xdp_flowtable.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0
+#define BPF_NO_KFUNC_PROTOTYPES
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define ETH_P_IP	0x0800
+#define ETH_P_IPV6	0x86dd
+#define IP_MF		0x2000	/* "More Fragments" */
+#define IP_OFFSET	0x1fff	/* "Fragment Offset" */
+#define AF_INET		2
+#define AF_INET6	10
+
+struct bpf_flowtable_opts___local {
+	s32 error;
+};
+
+struct flow_offload_tuple_rhash *
+bpf_xdp_flow_lookup(struct xdp_md *, struct bpf_fib_lookup *,
+		    struct bpf_flowtable_opts___local *, u32) __ksym;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, __u32);
+	__type(value, __u32);
+	__uint(max_entries, 1);
+} stats SEC(".maps");
+
+static bool xdp_flowtable_offload_check_iphdr(struct iphdr *iph)
+{
+	/* ip fragmented traffic */
+	if (iph->frag_off & bpf_htons(IP_MF | IP_OFFSET))
+		return false;
+
+	/* ip options */
+	if (iph->ihl * 4 != sizeof(*iph))
+		return false;
+
+	if (iph->ttl <= 1)
+		return false;
+
+	return true;
+}
+
+static bool xdp_flowtable_offload_check_tcp_state(void *ports, void *data_end,
+						  u8 proto)
+{
+	if (proto == IPPROTO_TCP) {
+		struct tcphdr *tcph = ports;
+
+		if (tcph + 1 > data_end)
+			return false;
+
+		if (tcph->fin || tcph->rst)
+			return false;
+	}
+
+	return true;
+}
+
+struct flow_ports___local {
+	__be16 source, dest;
+} __attribute__((preserve_access_index));
+
+SEC("xdp.frags")
+int xdp_flowtable_do_lookup(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	struct bpf_flowtable_opts___local opts = {};
+	struct flow_offload_tuple_rhash *tuplehash;
+	struct bpf_fib_lookup tuple = {
+		.ifindex = ctx->ingress_ifindex,
+	};
+	void *data = (void *)(long)ctx->data;
+	struct ethhdr *eth = data;
+	struct flow_ports___local *ports;
+	__u32 *val, key = 0;
+
+	if (eth + 1 > data_end)
+		return XDP_DROP;
+
+	switch (eth->h_proto) {
+	case bpf_htons(ETH_P_IP): {
+		struct iphdr *iph = data + sizeof(*eth);
+
+		ports = (struct flow_ports___local *)(iph + 1);
+		if (ports + 1 > data_end)
+			return XDP_PASS;
+
+		/* sanity check on ip header */
+		if (!xdp_flowtable_offload_check_iphdr(iph))
+			return XDP_PASS;
+
+		if (!xdp_flowtable_offload_check_tcp_state(ports, data_end,
+							   iph->protocol))
+			return XDP_PASS;
+
+		tuple.family		= AF_INET;
+		tuple.tos		= iph->tos;
+		tuple.l4_protocol	= iph->protocol;
+		tuple.tot_len		= bpf_ntohs(iph->tot_len);
+		tuple.ipv4_src		= iph->saddr;
+		tuple.ipv4_dst		= iph->daddr;
+		tuple.sport		= ports->source;
+		tuple.dport		= ports->dest;
+		break;
+	}
+	case bpf_htons(ETH_P_IPV6): {
+		struct in6_addr *src = (struct in6_addr *)tuple.ipv6_src;
+		struct in6_addr *dst = (struct in6_addr *)tuple.ipv6_dst;
+		struct ipv6hdr *ip6h = data + sizeof(*eth);
+
+		ports = (struct flow_ports___local *)(ip6h + 1);
+		if (ports + 1 > data_end)
+			return XDP_PASS;
+
+		if (ip6h->hop_limit <= 1)
+			return XDP_PASS;
+
+		if (!xdp_flowtable_offload_check_tcp_state(ports, data_end,
+							   ip6h->nexthdr))
+			return XDP_PASS;
+
+		tuple.family		= AF_INET6;
+		tuple.l4_protocol	= ip6h->nexthdr;
+		tuple.tot_len		= bpf_ntohs(ip6h->payload_len);
+		*src			= ip6h->saddr;
+		*dst			= ip6h->daddr;
+		tuple.sport		= ports->source;
+		tuple.dport		= ports->dest;
+		break;
+	}
+	default:
+		return XDP_PASS;
+	}
+
+	tuplehash = bpf_xdp_flow_lookup(ctx, &tuple, &opts, sizeof(opts));
+	if (!tuplehash)
+		return XDP_PASS;
+
+	val = bpf_map_lookup_elem(&stats, &key);
+	if (val)
+		__sync_add_and_fetch(val, 1);
+
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
new file mode 100644
index 000000000000..330ece2eabdb
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include "xdp_metadata.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_XSKMAP);
+	__uint(max_entries, 256);
+	__type(key, __u32);
+	__type(value, __u32);
+} xsk SEC(".maps");
+
+__u64 pkts_skip = 0;
+__u64 pkts_fail = 0;
+__u64 pkts_redir = 0;
+
+extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx,
+					 __u64 *timestamp) __ksym;
+extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash,
+				    enum xdp_rss_hash_type *rss_type) __ksym;
+extern int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx,
+					__be16 *vlan_proto,
+					__u16 *vlan_tci) __ksym;
+
+SEC("xdp.frags")
+int rx(struct xdp_md *ctx)
+{
+	void *data, *data_meta, *data_end;
+	struct ipv6hdr *ip6h = NULL;
+	struct udphdr *udp = NULL;
+	struct iphdr *iph = NULL;
+	struct xdp_meta *meta;
+	struct ethhdr *eth;
+	int err;
+
+	data = (void *)(long)ctx->data;
+	data_end = (void *)(long)ctx->data_end;
+	eth = data;
+
+	if (eth + 1 < data_end && (eth->h_proto == bpf_htons(ETH_P_8021AD) ||
+				   eth->h_proto == bpf_htons(ETH_P_8021Q)))
+		eth = (void *)eth + sizeof(struct vlan_hdr);
+
+	if (eth + 1 < data_end && eth->h_proto == bpf_htons(ETH_P_8021Q))
+		eth = (void *)eth + sizeof(struct vlan_hdr);
+
+	if (eth + 1 < data_end) {
+		if (eth->h_proto == bpf_htons(ETH_P_IP)) {
+			iph = (void *)(eth + 1);
+			if (iph + 1 < data_end && iph->protocol == IPPROTO_UDP)
+				udp = (void *)(iph + 1);
+		}
+		if (eth->h_proto == bpf_htons(ETH_P_IPV6)) {
+			ip6h = (void *)(eth + 1);
+			if (ip6h + 1 < data_end && ip6h->nexthdr == IPPROTO_UDP)
+				udp = (void *)(ip6h + 1);
+		}
+		if (udp && udp + 1 > data_end)
+			udp = NULL;
+	}
+
+	if (!udp) {
+		__sync_add_and_fetch(&pkts_skip, 1);
+		return XDP_PASS;
+	}
+
+	/* Forwarding UDP:9091 to AF_XDP */
+	if (udp->dest != bpf_htons(9091)) {
+		__sync_add_and_fetch(&pkts_skip, 1);
+		return XDP_PASS;
+	}
+
+	err = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta));
+	if (err) {
+		__sync_add_and_fetch(&pkts_fail, 1);
+		return XDP_PASS;
+	}
+
+	data = (void *)(long)ctx->data;
+	data_meta = (void *)(long)ctx->data_meta;
+	meta = data_meta;
+
+	if (meta + 1 > data) {
+		__sync_add_and_fetch(&pkts_fail, 1);
+		return XDP_PASS;
+	}
+
+	meta->hint_valid = 0;
+
+	meta->xdp_timestamp = bpf_ktime_get_tai_ns();
+	err = bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp);
+	if (err)
+		meta->rx_timestamp_err = err;
+	else
+		meta->hint_valid |= XDP_META_FIELD_TS;
+
+	err = bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash,
+				       &meta->rx_hash_type);
+	if (err)
+		meta->rx_hash_err = err;
+	else
+		meta->hint_valid |= XDP_META_FIELD_RSS;
+
+	err = bpf_xdp_metadata_rx_vlan_tag(ctx, &meta->rx_vlan_proto,
+					   &meta->rx_vlan_tci);
+	if (err)
+		meta->rx_vlan_tag_err = err;
+	else
+		meta->hint_valid |= XDP_META_FIELD_VLAN_TAG;
+
+	__sync_add_and_fetch(&pkts_redir, 1);
+	return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata.c b/tools/testing/selftests/bpf/progs/xdp_metadata.c
new file mode 100644
index 000000000000..09bb8a038d52
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/xdp_metadata.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include "xdp_metadata.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_XSKMAP);
+	__uint(max_entries, 4);
+	__type(key, __u32);
+	__type(value, __u32);
+} xsk SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u32);
+} prog_arr SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct bpf_devmap_val));
+	__uint(max_entries, 1);
+} dev_map SEC(".maps");
+
+extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx,
+					 __u64 *timestamp) __ksym;
+extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash,
+				    enum xdp_rss_hash_type *rss_type) __ksym;
+extern int bpf_xdp_metadata_rx_vlan_tag(const struct xdp_md *ctx,
+					__be16 *vlan_proto,
+					__u16 *vlan_tci) __ksym;
+
+SEC("xdp")
+int rx(struct xdp_md *ctx)
+{
+	void *data, *data_meta, *data_end;
+	struct ipv6hdr *ip6h = NULL;
+	struct ethhdr *eth = NULL;
+	struct udphdr *udp = NULL;
+	struct iphdr *iph = NULL;
+	struct xdp_meta *meta;
+	u64 timestamp = -1;
+	int ret;
+
+	data = (void *)(long)ctx->data;
+	data_end = (void *)(long)ctx->data_end;
+	eth = data;
+	if (eth + 1 < data_end) {
+		if (eth->h_proto == bpf_htons(ETH_P_IP)) {
+			iph = (void *)(eth + 1);
+			if (iph + 1 < data_end && iph->protocol == IPPROTO_UDP)
+				udp = (void *)(iph + 1);
+		}
+		if (eth->h_proto == bpf_htons(ETH_P_IPV6)) {
+			ip6h = (void *)(eth + 1);
+			if (ip6h + 1 < data_end && ip6h->nexthdr == IPPROTO_UDP)
+				udp = (void *)(ip6h + 1);
+		}
+		if (udp && udp + 1 > data_end)
+			udp = NULL;
+	}
+
+	if (!udp)
+		return XDP_PASS;
+
+	/* Forwarding UDP:8080 to AF_XDP */
+	if (udp->dest != bpf_htons(8080))
+		return XDP_PASS;
+
+	/* Reserve enough for all custom metadata. */
+
+	ret = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta));
+	if (ret != 0)
+		return XDP_DROP;
+
+	data = (void *)(long)ctx->data;
+	data_meta = (void *)(long)ctx->data_meta;
+
+	if (data_meta + sizeof(struct xdp_meta) > data)
+		return XDP_DROP;
+
+	meta = data_meta;
+
+	/* Export metadata. */
+
+	/* We expect veth bpf_xdp_metadata_rx_timestamp to return 0 HW
+	 * timestamp, so put some non-zero value into AF_XDP frame for
+	 * the userspace.
+	 */
+	bpf_xdp_metadata_rx_timestamp(ctx, &timestamp);
+	if (timestamp == 0)
+		meta->rx_timestamp = 1;
+
+	bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type);
+	bpf_xdp_metadata_rx_vlan_tag(ctx, &meta->rx_vlan_proto,
+				     &meta->rx_vlan_tci);
+
+	return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS);
+}
+
+SEC("xdp")
+int redirect(struct xdp_md *ctx)
+{
+	return bpf_redirect_map(&dev_map, ctx->rx_queue_index, XDP_PASS);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata2.c b/tools/testing/selftests/bpf/progs/xdp_metadata2.c
new file mode 100644
index 000000000000..85f88d9d7a78
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/xdp_metadata2.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include "xdp_metadata.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash,
+				    enum xdp_rss_hash_type *rss_type) __ksym;
+
+int called;
+
+SEC("freplace/rx")
+int freplace_rx(struct xdp_md *ctx)
+{
+	enum xdp_rss_hash_type type = 0;
+	u32 hash = 0;
+	/* Call _any_ metadata function to make sure we don't crash. */
+	bpf_xdp_metadata_rx_hash(ctx, &hash, &type);
+	called++;
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
index d037262c8937..50c8958f94e5 100644
--- a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
+++ b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c
@@ -1,7 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 
+#include <linux/if_ether.h>
+
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
 
 struct {
 	__uint(type, BPF_MAP_TYPE_DEVMAP);
@@ -10,22 +13,107 @@ struct {
 	__uint(value_size, sizeof(int));
 } tx_port SEC(".maps");
 
-SEC("redirect_map_0")
+SEC("xdp")
 int xdp_redirect_map_0(struct xdp_md *xdp)
 {
 	return bpf_redirect_map(&tx_port, 0, 0);
 }
 
-SEC("redirect_map_1")
+SEC("xdp")
 int xdp_redirect_map_1(struct xdp_md *xdp)
 {
 	return bpf_redirect_map(&tx_port, 1, 0);
 }
 
-SEC("redirect_map_2")
+SEC("xdp")
 int xdp_redirect_map_2(struct xdp_md *xdp)
 {
 	return bpf_redirect_map(&tx_port, 2, 0);
 }
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 3);
+	__type(key, __u32);
+	__type(value, __u64);
+} rxcnt SEC(".maps");
+
+static int xdp_count(struct xdp_md *xdp, __u32 key)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+	struct ethhdr *eth = data;
+	__u64 *count;
+
+	if (data + sizeof(*eth) > data_end)
+		return XDP_DROP;
+
+	if (bpf_htons(eth->h_proto) == ETH_P_IP) {
+		/* We only count IPv4 packets */
+		count = bpf_map_lookup_elem(&rxcnt, &key);
+		if (count)
+			*count += 1;
+	}
+
+	return XDP_PASS;
+}
+
+SEC("xdp")
+int xdp_count_0(struct xdp_md *xdp)
+{
+	return xdp_count(xdp, 0);
+}
+
+SEC("xdp")
+int xdp_count_1(struct xdp_md *xdp)
+{
+	return xdp_count(xdp, 1);
+}
+
+SEC("xdp")
+int xdp_count_2(struct xdp_md *xdp)
+{
+	return xdp_count(xdp, 2);
+}
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 2);
+	__type(key, __u32);
+	__type(value, __be64);
+} rx_mac SEC(".maps");
+
+static int store_mac(struct xdp_md *xdp, __u32 id)
+{
+	void *data_end = (void *)(long)xdp->data_end;
+	void *data = (void *)(long)xdp->data;
+	struct ethhdr *eth = data;
+	__u32 key = id;
+	__be64 mac = 0;
+
+	if (data + sizeof(*eth) > data_end)
+		return XDP_DROP;
+
+	/* Only store IPv4 MAC to avoid being polluted by IPv6 packets */
+	if (eth->h_proto == bpf_htons(ETH_P_IP)) {
+		__builtin_memcpy(&mac, eth->h_source, ETH_ALEN);
+		bpf_map_update_elem(&rx_mac, &key, &mac, 0);
+		bpf_printk("%s - %x", __func__, mac);
+	}
+
+	return XDP_PASS;
+}
+
+SEC("xdp")
+int store_mac_1(struct xdp_md *xdp)
+{
+	return store_mac(xdp, 0);
+}
+
+SEC("xdp")
+int store_mac_2(struct xdp_md *xdp)
+{
+	return store_mac(xdp, 1);
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c
index 97b26a30b59a..bc2945ed8a80 100644
--- a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c
+++ b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c
@@ -34,6 +34,14 @@ struct {
 	__uint(max_entries, 128);
 } mac_map SEC(".maps");
 
+/* map to store redirect flags for each protocol*/
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, __u16);
+	__type(value, __u64);
+	__uint(max_entries, 16);
+} redirect_flags SEC(".maps");
+
 SEC("xdp")
 int xdp_redirect_map_multi_prog(struct xdp_md *ctx)
 {
@@ -41,25 +49,34 @@ int xdp_redirect_map_multi_prog(struct xdp_md *ctx)
 	void *data = (void *)(long)ctx->data;
 	int if_index = ctx->ingress_ifindex;
 	struct ethhdr *eth = data;
+	__u64 *flags_from_map;
 	__u16 h_proto;
 	__u64 nh_off;
+	__u64 flags;
 
 	nh_off = sizeof(*eth);
 	if (data + nh_off > data_end)
 		return XDP_DROP;
 
-	h_proto = eth->h_proto;
-
-	/* Using IPv4 for (BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS) testing */
-	if (h_proto == bpf_htons(ETH_P_IP))
-		return bpf_redirect_map(&map_all, 0,
-					BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS);
-	/* Using IPv6 for none flag testing */
-	else if (h_proto == bpf_htons(ETH_P_IPV6))
-		return bpf_redirect_map(&map_all, if_index, 0);
-	/* All others for BPF_F_BROADCAST testing */
-	else
-		return bpf_redirect_map(&map_all, 0, BPF_F_BROADCAST);
+	h_proto = bpf_htons(eth->h_proto);
+
+	flags_from_map = bpf_map_lookup_elem(&redirect_flags, &h_proto);
+
+	/* Default flags for IPv4 : (BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS) */
+	if (h_proto == ETH_P_IP) {
+		flags = flags_from_map ? *flags_from_map : BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS;
+		return bpf_redirect_map(&map_all, 0, flags);
+	}
+	/* Default flags for IPv6 : 0 */
+	if (h_proto == ETH_P_IPV6) {
+		flags = flags_from_map ? *flags_from_map : 0;
+		return bpf_redirect_map(&map_all, if_index, flags);
+	}
+	/* Default flags for others BPF_F_BROADCAST : 0 */
+	else {
+		flags = flags_from_map ? *flags_from_map : BPF_F_BROADCAST;
+		return bpf_redirect_map(&map_all, 0, flags);
+	}
 }
 
 /* The following 2 progs are for 2nd devmap prog testing */
diff --git a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
index 736686e903f6..62b8e29ced9f 100644
--- a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
+++ b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c
@@ -1,12 +1,15 @@
 // SPDX-License-Identifier: LGPL-2.1 OR BSD-2-Clause
 /* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
 
+#define BPF_NO_KFUNC_PROTOTYPES
 #include "vmlinux.h"
 
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 #include <asm/errno.h>
 
+#include "bpf_compiler.h"
+
 #define TC_ACT_OK 0
 #define TC_ACT_SHOT 2
 
@@ -18,7 +21,6 @@
 
 #define tcp_flag_word(tp) (((union tcp_word_hdr *)(tp))->words[3])
 
-#define IP_DF 0x4000
 #define IP_MF 0x2000
 #define IP_OFFSET 0x1fff
 
@@ -53,6 +55,8 @@
 #define DEFAULT_TTL 64
 #define MAX_ALLOWED_PORTS 8
 
+#define MAX_PACKET_OFF 0xffff
+
 #define swap(a, b) \
 	do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
 
@@ -149,11 +153,11 @@ static __always_inline __u16 csum_ipv6_magic(const struct in6_addr *saddr,
 	__u64 sum = csum;
 	int i;
 
-#pragma unroll
+	__pragma_loop_unroll
 	for (i = 0; i < 4; i++)
 		sum += (__u32)saddr->in6_u.u6_addr32[i];
 
-#pragma unroll
+	__pragma_loop_unroll
 	for (i = 0; i < 4; i++)
 		sum += (__u32)daddr->in6_u.u6_addr32[i];
 
@@ -177,69 +181,82 @@ static __always_inline __u32 tcp_ns_to_ts(__u64 ns)
 	return ns / (NSEC_PER_SEC / TCP_TS_HZ);
 }
 
-static __always_inline __u32 tcp_time_stamp_raw(void)
+static __always_inline __u32 tcp_clock_ms(void)
 {
 	return tcp_ns_to_ts(tcp_clock_ns());
 }
 
 struct tcpopt_context {
-	__u8 *ptr;
-	__u8 *end;
+	void *data;
 	void *data_end;
 	__be32 *tsecr;
 	__u8 wscale;
 	bool option_timestamp;
 	bool option_sack;
+	__u32 off;
 };
 
-static int tscookie_tcpopt_parse(struct tcpopt_context *ctx)
+static __always_inline u8 *next(struct tcpopt_context *ctx, __u32 sz)
 {
-	__u8 opcode, opsize;
+	__u64 off = ctx->off;
+	__u8 *data;
 
-	if (ctx->ptr >= ctx->end)
-		return 1;
-	if (ctx->ptr >= ctx->data_end)
-		return 1;
+	/* Verifier forbids access to packet when offset exceeds MAX_PACKET_OFF */
+	if (off > MAX_PACKET_OFF - sz)
+		return NULL;
 
-	opcode = ctx->ptr[0];
+	data = ctx->data + off;
+	barrier_var(data);
+	if (data + sz >= ctx->data_end)
+		return NULL;
 
-	if (opcode == TCPOPT_EOL)
-		return 1;
-	if (opcode == TCPOPT_NOP) {
-		++ctx->ptr;
-		return 0;
-	}
+	ctx->off += sz;
+	return data;
+}
 
-	if (ctx->ptr + 1 >= ctx->end)
-		return 1;
-	if (ctx->ptr + 1 >= ctx->data_end)
+static int tscookie_tcpopt_parse(struct tcpopt_context *ctx)
+{
+	__u8 *opcode, *opsize, *wscale, *tsecr;
+	__u32 off = ctx->off;
+
+	opcode = next(ctx, 1);
+	if (!opcode)
 		return 1;
-	opsize = ctx->ptr[1];
-	if (opsize < 2)
+
+	if (*opcode == TCPOPT_EOL)
 		return 1;
+	if (*opcode == TCPOPT_NOP)
+		return 0;
 
-	if (ctx->ptr + opsize > ctx->end)
+	opsize = next(ctx, 1);
+	if (!opsize || *opsize < 2)
 		return 1;
 
-	switch (opcode) {
+	switch (*opcode) {
 	case TCPOPT_WINDOW:
-		if (opsize == TCPOLEN_WINDOW && ctx->ptr + TCPOLEN_WINDOW <= ctx->data_end)
-			ctx->wscale = ctx->ptr[2] < TCP_MAX_WSCALE ? ctx->ptr[2] : TCP_MAX_WSCALE;
+		wscale = next(ctx, 1);
+		if (!wscale)
+			return 1;
+		if (*opsize == TCPOLEN_WINDOW)
+			ctx->wscale = *wscale < TCP_MAX_WSCALE ? *wscale : TCP_MAX_WSCALE;
 		break;
 	case TCPOPT_TIMESTAMP:
-		if (opsize == TCPOLEN_TIMESTAMP && ctx->ptr + TCPOLEN_TIMESTAMP <= ctx->data_end) {
+		tsecr = next(ctx, 4);
+		if (!tsecr)
+			return 1;
+		if (*opsize == TCPOLEN_TIMESTAMP) {
 			ctx->option_timestamp = true;
 			/* Client's tsval becomes our tsecr. */
-			*ctx->tsecr = get_unaligned((__be32 *)(ctx->ptr + 2));
+			*ctx->tsecr = get_unaligned((__be32 *)tsecr);
 		}
 		break;
 	case TCPOPT_SACK_PERM:
-		if (opsize == TCPOLEN_SACK_PERM)
+		if (*opsize == TCPOLEN_SACK_PERM)
 			ctx->option_sack = true;
 		break;
 	}
 
-	ctx->ptr += opsize;
+	ctx->off = off + *opsize;
 
 	return 0;
 }
@@ -256,16 +273,21 @@ static int tscookie_tcpopt_parse_batch(__u32 index, void *context)
 
 static __always_inline bool tscookie_init(struct tcphdr *tcp_header,
 					  __u16 tcp_len, __be32 *tsval,
-					  __be32 *tsecr, void *data_end)
+					  __be32 *tsecr, void *data, void *data_end)
 {
 	struct tcpopt_context loop_ctx = {
-		.ptr = (__u8 *)(tcp_header + 1),
-		.end = (__u8 *)tcp_header + tcp_len,
+		.data = data,
 		.data_end = data_end,
 		.tsecr = tsecr,
 		.wscale = TS_OPT_WSCALE_MASK,
 		.option_timestamp = false,
 		.option_sack = false,
+		/* Note: currently verifier would track .off as unbound scalar.
+		 *       In case if verifier would at some point get smarter and
+		 *       compute bounded value for this var, beware that it might
+		 *       hinder bpf_loop() convergence validation.
+		 */
+		.off = (__u8 *)(tcp_header + 1) - (__u8 *)data,
 	};
 	u32 cookie;
 
@@ -274,7 +296,7 @@ static __always_inline bool tscookie_init(struct tcphdr *tcp_header,
 	if (!loop_ctx.option_timestamp)
 		return false;
 
-	cookie = tcp_time_stamp_raw() & ~TSMASK;
+	cookie = tcp_clock_ms() & ~TSMASK;
 	cookie |= loop_ctx.wscale & TS_OPT_WSCALE_MASK;
 	if (loop_ctx.option_sack)
 		cookie |= TS_OPT_SACK;
@@ -310,7 +332,7 @@ static __always_inline void values_get_tcpipopts(__u16 *mss, __u8 *wscale,
 static __always_inline void values_inc_synacks(void)
 {
 	__u32 key = 1;
-	__u32 *value;
+	__u64 *value;
 
 	value = bpf_map_lookup_elem(&values, &key);
 	if (value)
@@ -419,7 +441,7 @@ static __always_inline int tcp_lookup(void *ctx, struct header_pointers *hdr, bo
 		/* TCP doesn't normally use fragments, and XDP can't reassemble
 		 * them.
 		 */
-		if ((hdr->ipv4->frag_off & bpf_htons(IP_DF | IP_MF | IP_OFFSET)) != bpf_htons(IP_DF))
+		if ((hdr->ipv4->frag_off & bpf_htons(IP_MF | IP_OFFSET)) != 0)
 			return XDP_DROP;
 
 		tup.ipv4.saddr = hdr->ipv4->saddr;
@@ -447,13 +469,13 @@ static __always_inline int tcp_lookup(void *ctx, struct header_pointers *hdr, bo
 		unsigned long status = ct->status;
 
 		bpf_ct_release(ct);
-		if (status & IPS_CONFIRMED_BIT)
+		if (status & IPS_CONFIRMED)
 			return XDP_PASS;
 	} else if (ct_lookup_opts.error != -ENOENT) {
 		return XDP_ABORTED;
 	}
 
-	/* error == -ENOENT || !(status & IPS_CONFIRMED_BIT) */
+	/* error == -ENOENT || !(status & IPS_CONFIRMED) */
 	return XDP_TX;
 }
 
@@ -635,7 +657,7 @@ static __always_inline int syncookie_handle_syn(struct header_pointers *hdr,
 	cookie = (__u32)value;
 
 	if (tscookie_init((void *)hdr->tcp, hdr->tcp_len,
-			  &tsopt_buf[0], &tsopt_buf[1], data_end))
+			  &tsopt_buf[0], &tsopt_buf[1], data, data_end))
 		tsopt = tsopt_buf;
 
 	/* Check that there is enough space for a SYNACK. It also covers
diff --git a/tools/testing/selftests/bpf/progs/xdping_kern.c b/tools/testing/selftests/bpf/progs/xdping_kern.c
index 4ad73847b8a5..44e2b0ef23ae 100644
--- a/tools/testing/selftests/bpf/progs/xdping_kern.c
+++ b/tools/testing/selftests/bpf/progs/xdping_kern.c
@@ -15,6 +15,7 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
+#include "bpf_compiler.h"
 #include "xdping.h"
 
 struct {
@@ -89,7 +90,6 @@ static __always_inline int icmp_check(struct xdp_md *ctx, int type)
 SEC("xdp")
 int xdping_client(struct xdp_md *ctx)
 {
-	void *data_end = (void *)(long)ctx->data_end;
 	void *data = (void *)(long)ctx->data;
 	struct pinginfo *pinginfo = NULL;
 	struct ethhdr *eth = data;
@@ -117,7 +117,7 @@ int xdping_client(struct xdp_md *ctx)
 		return XDP_PASS;
 
 	if (pinginfo->start) {
-#pragma clang loop unroll(full)
+		__pragma_loop_unroll_full
 		for (i = 0; i < XDPING_MAX_COUNT; i++) {
 			if (pinginfo->times[i] == 0)
 				break;
@@ -153,7 +153,6 @@ int xdping_client(struct xdp_md *ctx)
 SEC("xdp")
 int xdping_server(struct xdp_md *ctx)
 {
-	void *data_end = (void *)(long)ctx->data_end;
 	void *data = (void *)(long)ctx->data;
 	struct ethhdr *eth = data;
 	struct icmphdr *icmph;
diff --git a/tools/testing/selftests/bpf/progs/xdpwall.c b/tools/testing/selftests/bpf/progs/xdpwall.c
index 7a891a0c3a39..c2dd0c28237a 100644
--- a/tools/testing/selftests/bpf/progs/xdpwall.c
+++ b/tools/testing/selftests/bpf/progs/xdpwall.c
@@ -321,7 +321,6 @@ int edgewall(struct xdp_md *ctx)
 	void *data = (void *)(long)(ctx->data);
 	struct fw_match_info match_info = {};
 	struct pkt_info info = {};
-	__u8 parse_err = NO_ERR;
 	void *transport_hdr;
 	struct ethhdr *eth;
 	bool filter_res;
diff --git a/tools/testing/selftests/bpf/progs/xfrm_info.c b/tools/testing/selftests/bpf/progs/xfrm_info.c
index f6a501fbba2b..a1d9f106c3f0 100644
--- a/tools/testing/selftests/bpf/progs/xfrm_info.c
+++ b/tools/testing/selftests/bpf/progs/xfrm_info.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#define BPF_NO_KFUNC_PROTOTYPES
 #include "vmlinux.h"
 #include "bpf_tracing_net.h"
 #include <bpf/bpf_helpers.h>
diff --git a/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
new file mode 100644
index 000000000000..683306db8594
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/xsk_xdp_progs.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Intel */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/errno.h>
+#include "xsk_xdp_common.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_XSKMAP);
+	__uint(max_entries, 2);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(int));
+} xsk SEC(".maps");
+
+static unsigned int idx;
+int adjust_value = 0;
+int count = 0;
+
+SEC("xdp.frags") int xsk_def_prog(struct xdp_md *xdp)
+{
+	return bpf_redirect_map(&xsk, 0, XDP_DROP);
+}
+
+SEC("xdp.frags") int xsk_xdp_drop(struct xdp_md *xdp)
+{
+	/* Drop every other packet */
+	if (idx++ % 2)
+		return XDP_DROP;
+
+	return bpf_redirect_map(&xsk, 0, XDP_DROP);
+}
+
+SEC("xdp.frags") int xsk_xdp_populate_metadata(struct xdp_md *xdp)
+{
+	void *data, *data_meta;
+	struct xdp_info *meta;
+	int err;
+
+	/* Reserve enough for all custom metadata. */
+	err = bpf_xdp_adjust_meta(xdp, -(int)sizeof(struct xdp_info));
+	if (err)
+		return XDP_DROP;
+
+	data = (void *)(long)xdp->data;
+	data_meta = (void *)(long)xdp->data_meta;
+
+	if (data_meta + sizeof(struct xdp_info) > data)
+		return XDP_DROP;
+
+	meta = data_meta;
+	meta->count = count++;
+
+	return bpf_redirect_map(&xsk, 0, XDP_DROP);
+}
+
+SEC("xdp") int xsk_xdp_shared_umem(struct xdp_md *xdp)
+{
+	void *data = (void *)(long)xdp->data;
+	void *data_end = (void *)(long)xdp->data_end;
+	struct ethhdr *eth = data;
+
+	if (eth + 1 > data_end)
+		return XDP_DROP;
+
+	/* Redirecting packets based on the destination MAC address */
+	idx = ((unsigned int)(eth->h_dest[5])) / 2;
+	if (idx > MAX_SOCKETS)
+		return XDP_DROP;
+
+	return bpf_redirect_map(&xsk, idx, XDP_DROP);
+}
+
+SEC("xdp.frags") int xsk_xdp_adjust_tail(struct xdp_md *xdp)
+{
+	__u32 buff_len, curr_buff_len;
+	int ret;
+
+	buff_len = bpf_xdp_get_buff_len(xdp);
+	if (buff_len == 0)
+		return XDP_DROP;
+
+	ret = bpf_xdp_adjust_tail(xdp, adjust_value);
+	if (ret < 0) {
+		/* Handle unsupported cases */
+		if (ret == -EOPNOTSUPP) {
+			/* Set adjust_value to -EOPNOTSUPP to indicate to userspace that this case
+			 * is unsupported
+			 */
+			adjust_value = -EOPNOTSUPP;
+			return bpf_redirect_map(&xsk, 0, XDP_DROP);
+		}
+
+		return XDP_DROP;
+	}
+
+	curr_buff_len = bpf_xdp_get_buff_len(xdp);
+	if (curr_buff_len != buff_len + adjust_value)
+		return XDP_DROP;
+
+	if (curr_buff_len > buff_len) {
+		__u32 *pkt_data = (void *)(long)xdp->data;
+		__u32 len, words_to_end, seq_num;
+
+		len = curr_buff_len - PKT_HDR_ALIGN;
+		words_to_end = len / sizeof(*pkt_data) - 1;
+		seq_num = words_to_end;
+
+		/* Convert sequence number to network byte order. Store this in the last 4 bytes of
+		 * the packet. Use 'adjust_value' to determine the position at the end of the
+		 * packet for storing the sequence number.
+		 */
+		seq_num = __constant_htonl(words_to_end);
+		bpf_xdp_store_bytes(xdp, curr_buff_len - sizeof(seq_num), &seq_num,
+				    sizeof(seq_num));
+	}
+
+	return bpf_redirect_map(&xsk, 0, XDP_DROP);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/sdt.h b/tools/testing/selftests/bpf/sdt.h
index ca0162b4dc57..1fcfa5160231 100644
--- a/tools/testing/selftests/bpf/sdt.h
+++ b/tools/testing/selftests/bpf/sdt.h
@@ -102,6 +102,8 @@
 # define STAP_SDT_ARG_CONSTRAINT        nZr
 # elif defined __arm__
 # define STAP_SDT_ARG_CONSTRAINT        g
+# elif defined __loongarch__
+# define STAP_SDT_ARG_CONSTRAINT        nmr
 # else
 # define STAP_SDT_ARG_CONSTRAINT        nor
 # endif
diff --git a/tools/testing/selftests/bpf/test_bpftool_build.sh b/tools/testing/selftests/bpf/test_bpftool_build.sh
index 1453a53ed547..b03a87571592 100755
--- a/tools/testing/selftests/bpf/test_bpftool_build.sh
+++ b/tools/testing/selftests/bpf/test_bpftool_build.sh
@@ -90,10 +90,6 @@ echo -e "... through kbuild\n"
 
 if [ -f ".config" ] ; then
 	make_and_clean tools/bpf
-	## "make tools/bpf" sets $(OUTPUT) to ...tools/bpf/runqslower for
-	## runqslower, but the default (used for the "clean" target) is .output.
-	## Let's make sure we clean runqslower's directory properly.
-	make -C tools/bpf/runqslower OUTPUT=${KDIR_ROOT_DIR}/tools/bpf/runqslower/ clean
 
 	## $OUTPUT is overwritten in kbuild Makefile, and thus cannot be passed
 	## down from toplevel Makefile to bpftool's Makefile.
diff --git a/tools/testing/selftests/bpf/test_bpftool_map.sh b/tools/testing/selftests/bpf/test_bpftool_map.sh
new file mode 100755
index 000000000000..515b1df0501e
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_bpftool_map.sh
@@ -0,0 +1,398 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+TESTNAME="bpftool_map"
+BPF_FILE="security_bpf_map.bpf.o"
+BPF_ITER_FILE="bpf_iter_map_elem.bpf.o"
+PROTECTED_MAP_NAME="prot_map"
+NOT_PROTECTED_MAP_NAME="not_prot_map"
+BPF_FS_TMP_PARENT="/tmp"
+BPF_FS_PARENT=$(awk '$3 == "bpf" {print $2; exit}' /proc/mounts)
+BPF_FS_PARENT=${BPF_FS_PARENT:-$BPF_FS_TMP_PARENT}
+# bpftool will mount bpf file system under BPF_DIR if it is not mounted
+# under BPF_FS_PARENT.
+BPF_DIR="$BPF_FS_PARENT/test_$TESTNAME"
+SCRIPT_DIR=$(dirname $(realpath "$0"))
+BPF_FILE_PATH="$SCRIPT_DIR/$BPF_FILE"
+BPF_ITER_FILE_PATH="$SCRIPT_DIR/$BPF_ITER_FILE"
+BPFTOOL_PATH="bpftool"
+# Assume the script is located under tools/testing/selftests/bpf/
+KDIR_ROOT_DIR=$(realpath "$SCRIPT_DIR"/../../../../)
+
+_cleanup()
+{
+	set +eu
+
+	# If BPF_DIR is a mount point this will not remove the mount point itself.
+	[ -d "$BPF_DIR" ] && rm -rf "$BPF_DIR" 2> /dev/null
+
+	# Unmount if BPF filesystem was temporarily created.
+	if [ "$BPF_FS_PARENT" = "$BPF_FS_TMP_PARENT" ]; then
+		# A loop and recursive unmount are required as bpftool might
+		# create multiple mounts. For example, a bind mount of the directory
+		# to itself. The bind mount is created to change mount propagation
+		# flags on an actual mount point.
+		max_attempts=3
+		attempt=0
+		while mountpoint -q "$BPF_DIR" && [ $attempt -lt $max_attempts ]; do
+			umount -R "$BPF_DIR" 2>/dev/null
+			attempt=$((attempt+1))
+		done
+
+		# The directory still exists. Remove it now.
+		[ -d "$BPF_DIR" ] && rm -rf "$BPF_DIR" 2>/dev/null
+	fi
+}
+
+cleanup_skip()
+{
+	echo "selftests: $TESTNAME [SKIP]"
+	_cleanup
+
+	exit $ksft_skip
+}
+
+cleanup()
+{
+	if [ "$?" = 0 ]; then
+		echo "selftests: $TESTNAME [PASS]"
+	else
+		echo "selftests: $TESTNAME [FAILED]"
+	fi
+	_cleanup
+}
+
+check_root_privileges() {
+	if [ $(id -u) -ne 0 ]; then
+		echo "Need root privileges"
+		exit $ksft_skip
+	fi
+}
+
+# Function to verify bpftool path.
+# Parameters:
+#   $1: bpftool path
+verify_bpftool_path() {
+	local bpftool_path="$1"
+	if ! "$bpftool_path" version > /dev/null 2>&1; then
+		echo "Could not run test without bpftool"
+		exit $ksft_skip
+	fi
+}
+
+# Function to verify BTF support.
+# The test requires BTF support for fmod_ret programs.
+verify_btf_support() {
+	if [ ! -f /sys/kernel/btf/vmlinux ]; then
+		echo "Could not run test without BTF support"
+		exit $ksft_skip
+	fi
+}
+
+# Function to initialize map entries with keys [0..2] and values set to 0.
+# Parameters:
+#  $1: Map name
+#  $2: bpftool path
+initialize_map_entries() {
+	local map_name="$1"
+	local bpftool_path="$2"
+
+	for key in 0 1 2; do
+		"$bpftool_path" map update name "$map_name" key $key 0 0 0 value 0 0 0 $key
+	done
+}
+
+# Test read access to the map.
+# Parameters:
+#   $1: Name command (name/pinned)
+#   $2: Map name
+#   $3: bpftool path
+#   $4: key
+access_for_read() {
+	local name_cmd="$1"
+	local map_name="$2"
+	local bpftool_path="$3"
+	local key="$4"
+
+	# Test read access to the map.
+	if ! "$bpftool_path" map lookup "$name_cmd" "$map_name" key $key 1>/dev/null; then
+		echo " Read access to $key in $map_name failed"
+		exit 1
+	fi
+
+	# Test read access to map's BTF data.
+	if ! "$bpftool_path" btf dump map "$name_cmd" "$map_name" 1>/dev/null; then
+		echo " Read access to $map_name for BTF data failed"
+		exit 1
+	fi
+}
+
+# Test write access to the map.
+# Parameters:
+#   $1: Name command (name/pinned)
+#   $2: Map name
+#   $3: bpftool path
+#   $4: key
+#   $5: Whether write should succeed (true/false)
+access_for_write() {
+	local name_cmd="$1"
+	local map_name="$2"
+	local bpftool_path="$3"
+	local key="$4"
+	local write_should_succeed="$5"
+	local value="1 1 1 1"
+
+	if "$bpftool_path" map update "$name_cmd" "$map_name" key $key value \
+			$value 2>/dev/null; then
+		if [ "$write_should_succeed" = "false" ]; then
+			echo " Write access to $key in $map_name succeeded but should have failed"
+			exit 1
+		fi
+	else
+		if [ "$write_should_succeed" = "true" ]; then
+			echo " Write access to $key in $map_name failed but should have succeeded"
+			exit 1
+		fi
+	fi
+}
+
+# Test entry deletion for the map.
+# Parameters:
+#   $1: Name command (name/pinned)
+#   $2: Map name
+#   $3: bpftool path
+#   $4: key
+#   $5: Whether write should succeed (true/false)
+access_for_deletion() {
+	local name_cmd="$1"
+	local map_name="$2"
+	local bpftool_path="$3"
+	local key="$4"
+	local write_should_succeed="$5"
+	local value="1 1 1 1"
+
+	# Test deletion by key for the map.
+	# Before deleting, check the key exists.
+	if ! "$bpftool_path" map lookup "$name_cmd" "$map_name" key $key 1>/dev/null; then
+		echo " Key $key does not exist in $map_name"
+		exit 1
+	fi
+
+	# Delete by key.
+	if "$bpftool_path" map delete "$name_cmd" "$map_name" key $key 2>/dev/null; then
+		if [ "$write_should_succeed" = "false" ]; then
+			echo " Deletion for $key in $map_name succeeded but should have failed"
+			exit 1
+		fi
+	else
+		if [ "$write_should_succeed" = "true" ]; then
+			echo " Deletion for $key in $map_name failed but should have succeeded"
+			exit 1
+		fi
+	fi
+
+	# After deleting, check the entry existence according to the expected status.
+	if "$bpftool_path" map lookup "$name_cmd" "$map_name" key $key 1>/dev/null; then
+		if [ "$write_should_succeed" = "true" ]; then
+			echo " Key $key for $map_name was not deleted but should have been deleted"
+			exit 1
+		fi
+	else
+		if [ "$write_should_succeed" = "false" ]; then
+			echo "Key $key for $map_name was deleted but should have not been deleted"
+			exit 1
+		fi
+	fi
+
+	# Test creation of map's deleted entry, if deletion was successful.
+	# Otherwise, the entry exists.
+	if "$bpftool_path" map update "$name_cmd" "$map_name" key $key value \
+				$value 2>/dev/null; then
+		if [ "$write_should_succeed" = "false" ]; then
+			echo " Write access to $key in $map_name succeeded after deletion attempt but should have failed"
+			exit 1
+		fi
+	else
+		if [ "$write_should_succeed" = "true" ]; then
+			echo " Write access to $key in $map_name failed after deletion attempt but should have succeeded"
+			exit 1
+		fi
+	fi
+}
+
+# Test map elements iterator.
+# Parameters:
+#   $1: Name command (name/pinned)
+#   $2: Map name
+#   $3: bpftool path
+#   $4: BPF_DIR
+#   $5: bpf iterator object file path
+iterate_map_elem() {
+	local name_cmd="$1"
+	local map_name="$2"
+	local bpftool_path="$3"
+	local bpf_dir="$4"
+	local bpf_file="$5"
+	local pin_path="$bpf_dir/map_iterator"
+
+	"$bpftool_path" iter pin "$bpf_file" "$pin_path" map "$name_cmd" "$map_name"
+	if [ ! -f "$pin_path" ]; then
+		echo " Failed to pin iterator to $pin_path"
+		exit 1
+	fi
+
+	cat "$pin_path" 1>/dev/null
+	rm "$pin_path" 2>/dev/null
+}
+
+# Function to test map access with configurable write expectations
+# Parameters:
+#   $1: Name command (name/pinned)
+#   $2: Map name
+#   $3: bpftool path
+#   $4: key for rw
+#   $5: key to delete
+#   $6: Whether write should succeed (true/false)
+#   $7: BPF_DIR
+#   $8: bpf iterator object file path
+access_map() {
+	local name_cmd="$1"
+	local map_name="$2"
+	local bpftool_path="$3"
+	local key_for_rw="$4"
+	local key_to_del="$5"
+	local write_should_succeed="$6"
+	local bpf_dir="$7"
+	local bpf_iter_file_path="$8"
+
+	access_for_read "$name_cmd" "$map_name" "$bpftool_path" "$key_for_rw"
+	access_for_write "$name_cmd" "$map_name" "$bpftool_path" "$key_for_rw" \
+		"$write_should_succeed"
+	access_for_deletion "$name_cmd" "$map_name" "$bpftool_path" "$key_to_del" \
+		"$write_should_succeed"
+	iterate_map_elem "$name_cmd" "$map_name" "$bpftool_path" "$bpf_dir" \
+		"$bpf_iter_file_path"
+}
+
+# Function to test map access with configurable write expectations
+# Parameters:
+#   $1: Map name
+#   $2: bpftool path
+#   $3: BPF_DIR
+#   $4: Whether write should succeed (true/false)
+#   $5: bpf iterator object file path
+test_map_access() {
+	local map_name="$1"
+	local bpftool_path="$2"
+	local bpf_dir="$3"
+	local pin_path="$bpf_dir/${map_name}_pinned"
+	local write_should_succeed="$4"
+	local bpf_iter_file_path="$5"
+
+	# Test access to the map by name.
+	access_map "name" "$map_name" "$bpftool_path" "0 0 0 0" "1 0 0 0" \
+		"$write_should_succeed" "$bpf_dir" "$bpf_iter_file_path"
+
+	# Pin the map to the BPF filesystem
+	"$bpftool_path" map pin name "$map_name" "$pin_path"
+	if [ ! -e "$pin_path" ]; then
+		echo " Failed to pin $map_name"
+		exit 1
+	fi
+
+	# Test access to the pinned map.
+	access_map "pinned" "$pin_path" "$bpftool_path" "0 0 0 0" "2 0 0 0" \
+		"$write_should_succeed" "$bpf_dir" "$bpf_iter_file_path"
+}
+
+# Function to test map creation and map-of-maps
+# Parameters:
+#   $1: bpftool path
+#   $2: BPF_DIR
+test_map_creation_and_map_of_maps() {
+	local bpftool_path="$1"
+	local bpf_dir="$2"
+	local outer_map_name="outer_map_tt"
+	local inner_map_name="inner_map_tt"
+
+	"$bpftool_path" map create "$bpf_dir/$inner_map_name" type array key 4 \
+		value 4 entries 4 name "$inner_map_name"
+	if [ ! -f "$bpf_dir/$inner_map_name" ]; then
+		echo " Failed to create inner map file at $bpf_dir/$outer_map_name"
+		return 1
+	fi
+
+	"$bpftool_path" map create "$bpf_dir/$outer_map_name" type hash_of_maps \
+		key 4 value 4 entries 2 name "$outer_map_name" inner_map name "$inner_map_name"
+	if [ ! -f "$bpf_dir/$outer_map_name" ]; then
+		echo " Failed to create outer map file at $bpf_dir/$outer_map_name"
+		return 1
+	fi
+
+	# Add entries to the outer map by name and by pinned path.
+	"$bpftool_path" map update pinned "$bpf_dir/$outer_map_name" key 0 0 0 0 \
+		value pinned "$bpf_dir/$inner_map_name"
+	"$bpftool_path" map update name "$outer_map_name" key 1 0 0 0 value \
+		name "$inner_map_name"
+
+	# The outer map should be full by now.
+	# The following map update command is expected to fail.
+	if "$bpftool_path" map update name "$outer_map_name" key 2 0 0 0 value name \
+		"$inner_map_name" 2>/dev/null; then
+		echo " Update for $outer_map_name succeeded but should have failed"
+		exit 1
+	fi
+}
+
+# Function to test map access with the btf list command
+# Parameters:
+#   $1: bpftool path
+test_map_access_with_btf_list() {
+	local bpftool_path="$1"
+
+	# The btf list command iterates over maps for
+	# loaded BPF programs.
+	if ! "$bpftool_path" btf list 1>/dev/null; then
+		echo " Failed to access btf data"
+		exit 1
+	fi
+}
+
+set -eu
+
+trap cleanup_skip EXIT
+
+check_root_privileges
+
+verify_bpftool_path "$BPFTOOL_PATH"
+
+verify_btf_support
+
+trap cleanup EXIT
+
+# Load and attach the BPF programs to control maps access.
+"$BPFTOOL_PATH" prog loadall "$BPF_FILE_PATH" "$BPF_DIR" autoattach
+
+initialize_map_entries "$PROTECTED_MAP_NAME" "$BPFTOOL_PATH"
+initialize_map_entries "$NOT_PROTECTED_MAP_NAME" "$BPFTOOL_PATH"
+
+# Activate the map protection mechanism. Protection status is controlled
+# by a value stored in the prot_status_map at index 0.
+"$BPFTOOL_PATH" map update name prot_status_map key 0 0 0 0 value 1 0 0 0
+
+# Test protected map (write should fail).
+test_map_access "$PROTECTED_MAP_NAME" "$BPFTOOL_PATH" "$BPF_DIR" "false" \
+ "$BPF_ITER_FILE_PATH"
+
+# Test not protected map (write should succeed).
+test_map_access "$NOT_PROTECTED_MAP_NAME" "$BPFTOOL_PATH" "$BPF_DIR" "true" \
+ "$BPF_ITER_FILE_PATH"
+
+test_map_creation_and_map_of_maps "$BPFTOOL_PATH" "$BPF_DIR"
+
+test_map_access_with_btf_list "$BPFTOOL_PATH"
+
+exit 0
diff --git a/tools/testing/selftests/bpf/test_bpftool_synctypes.py b/tools/testing/selftests/bpf/test_bpftool_synctypes.py
index 0cfece7ff4f8..238121fda5b6 100755
--- a/tools/testing/selftests/bpf/test_bpftool_synctypes.py
+++ b/tools/testing/selftests/bpf/test_bpftool_synctypes.py
@@ -66,7 +66,7 @@ class ArrayParser(BlockParser):
 
     def __init__(self, reader, array_name):
         self.array_name = array_name
-        self.start_marker = re.compile(f'(static )?const bool {self.array_name}\[.*\] = {{\n')
+        self.start_marker = re.compile(fr'(static )?const bool {self.array_name}\[.*\] = {{\n')
         super().__init__(reader)
 
     def search_block(self):
@@ -80,7 +80,7 @@ class ArrayParser(BlockParser):
         Parse a block and return data as a dictionary. Items to extract must be
         on separate lines in the file.
         """
-        pattern = re.compile('\[(BPF_\w*)\]\s*= (true|false),?$')
+        pattern = re.compile(r'\[(BPF_\w*)\]\s*= (true|false),?$')
         entries = set()
         while True:
             line = self.reader.readline()
@@ -178,7 +178,7 @@ class FileExtractor(object):
         @enum_name: name of the enum to parse
         """
         start_marker = re.compile(f'enum {enum_name} {{\n')
-        pattern = re.compile('^\s*(BPF_\w+),?(\s+/\*.*\*/)?$')
+        pattern = re.compile(r'^\s*(BPF_\w+),?(\s+/\*.*\*/)?$')
         end_marker = re.compile('^};')
         parser = BlockParser(self.reader)
         parser.search_block(start_marker)
@@ -226,8 +226,8 @@ class FileExtractor(object):
 
         @block_name: name of the blog to parse, 'TYPE' in the example
         """
-        start_marker = re.compile(f'\*{block_name}\* := {{')
-        pattern = re.compile('\*\*([\w/-]+)\*\*')
+        start_marker = re.compile(fr'\*{block_name}\* := {{')
+        pattern = re.compile(r'\*\*([\w/-]+)\*\*')
         end_marker = re.compile('}\n')
         return self.__get_description_list(start_marker, pattern, end_marker)
 
@@ -245,8 +245,8 @@ class FileExtractor(object):
 
         @block_name: name of the blog to parse, 'TYPE' in the example
         """
-        start_marker = re.compile(f'"\s*{block_name} := {{')
-        pattern = re.compile('([\w/]+) [|}]')
+        start_marker = re.compile(fr'"\s*{block_name} := {{')
+        pattern = re.compile(r'([\w/]+) [|}]')
         end_marker = re.compile('}')
         return self.__get_description_list(start_marker, pattern, end_marker)
 
@@ -264,8 +264,8 @@ class FileExtractor(object):
 
         @macro: macro starting the block, 'HELP_SPEC_OPTIONS' in the example
         """
-        start_marker = re.compile(f'"\s*{macro}\s*" [|}}]')
-        pattern = re.compile('([\w-]+) ?(?:\||}[ }\]])')
+        start_marker = re.compile(fr'"\s*{macro}\s*" [|}}]')
+        pattern = re.compile(r'([\w-]+) ?(?:\||}[ }\]])')
         end_marker = re.compile('}\\\\n')
         return self.__get_description_list(start_marker, pattern, end_marker)
 
@@ -283,8 +283,8 @@ class FileExtractor(object):
 
         @block_name: name of the blog to parse, 'TYPE' in the example
         """
-        start_marker = re.compile(f'local {block_name}=\'')
-        pattern = re.compile('(?:.*=\')?([\w/]+)')
+        start_marker = re.compile(fr'local {block_name}=\'')
+        pattern = re.compile(r'(?:.*=\')?([\w/]+)')
         end_marker = re.compile('\'$')
         return self.__get_description_list(start_marker, pattern, end_marker)
 
@@ -316,7 +316,7 @@ class MainHeaderFileExtractor(SourceFileExtractor):
             {'-p', '-d', '--pretty', '--debug', '--json', '-j'}
         """
         start_marker = re.compile(f'"OPTIONS :=')
-        pattern = re.compile('([\w-]+) ?(?:\||}[ }\]"])')
+        pattern = re.compile(r'([\w-]+) ?(?:\||}[ }\]"])')
         end_marker = re.compile('#define')
 
         parser = InlineListParser(self.reader)
@@ -338,8 +338,8 @@ class ManSubstitutionsExtractor(SourceFileExtractor):
 
             {'-p', '-d', '--pretty', '--debug', '--json', '-j'}
         """
-        start_marker = re.compile('\|COMMON_OPTIONS\| replace:: {')
-        pattern = re.compile('\*\*([\w/-]+)\*\*')
+        start_marker = re.compile(r'\|COMMON_OPTIONS\| replace:: {')
+        pattern = re.compile(r'\*\*([\w/-]+)\*\*')
         end_marker = re.compile('}$')
 
         parser = InlineListParser(self.reader)
@@ -509,6 +509,15 @@ def main():
     source_map_types.remove('cgroup_storage_deprecated')
     source_map_types.add('cgroup_storage')
 
+    # The same applied to BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED and
+    # BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE which share the same enum value
+    # and source_map_types picks
+    # BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED/percpu_cgroup_storage_deprecated.
+    # Replace 'percpu_cgroup_storage_deprecated' with 'percpu_cgroup_storage'
+    # so it aligns with what `bpftool map help` shows.
+    source_map_types.remove('percpu_cgroup_storage_deprecated')
+    source_map_types.add('percpu_cgroup_storage')
+
     help_map_types = map_info.get_map_help()
     help_map_options = map_info.get_options()
     map_info.close()
diff --git a/tools/testing/selftests/bpf/test_btf.h b/tools/testing/selftests/bpf/test_btf.h
index fb4f4714eeb4..e65889ab4adf 100644
--- a/tools/testing/selftests/bpf/test_btf.h
+++ b/tools/testing/selftests/bpf/test_btf.h
@@ -72,9 +72,15 @@
 #define BTF_TYPE_FLOAT_ENC(name, sz) \
 	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz)
 
+#define BTF_DECL_ATTR_ENC(value, type, component_idx)	\
+	BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 1, 0), type), (component_idx)
+
 #define BTF_DECL_TAG_ENC(value, type, component_idx)	\
 	BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 0), type), (component_idx)
 
+#define BTF_TYPE_ATTR_ENC(value, type)	\
+	BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TYPE_TAG, 1, 0), type)
+
 #define BTF_TYPE_TAG_ENC(value, type)	\
 	BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TYPE_TAG, 0, 0), type)
 
diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c
deleted file mode 100644
index 0861ea60dcdd..000000000000
--- a/tools/testing/selftests/bpf/test_cgroup_storage.c
+++ /dev/null
@@ -1,174 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <assert.h>
-#include <bpf/bpf.h>
-#include <linux/filter.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <sys/sysinfo.h>
-
-#include "bpf_util.h"
-#include "cgroup_helpers.h"
-#include "testing_helpers.h"
-
-char bpf_log_buf[BPF_LOG_BUF_SIZE];
-
-#define TEST_CGROUP "/test-bpf-cgroup-storage-buf/"
-
-int main(int argc, char **argv)
-{
-	struct bpf_insn prog[] = {
-		BPF_LD_MAP_FD(BPF_REG_1, 0), /* percpu map fd */
-		BPF_MOV64_IMM(BPF_REG_2, 0), /* flags, not used */
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-			     BPF_FUNC_get_local_storage),
-		BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0),
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 0x1),
-		BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0),
-
-		BPF_LD_MAP_FD(BPF_REG_1, 0), /* map fd */
-		BPF_MOV64_IMM(BPF_REG_2, 0), /* flags, not used */
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-			     BPF_FUNC_get_local_storage),
-		BPF_MOV64_IMM(BPF_REG_1, 1),
-		BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_0, BPF_REG_1, 0),
-		BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
-		BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x1),
-		BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-		BPF_EXIT_INSN(),
-	};
-	size_t insns_cnt = ARRAY_SIZE(prog);
-	int error = EXIT_FAILURE;
-	int map_fd, percpu_map_fd, prog_fd, cgroup_fd;
-	struct bpf_cgroup_storage_key key;
-	unsigned long long value;
-	unsigned long long *percpu_value;
-	int cpu, nproc;
-
-	nproc = bpf_num_possible_cpus();
-	percpu_value = malloc(sizeof(*percpu_value) * nproc);
-	if (!percpu_value) {
-		printf("Not enough memory for per-cpu area (%d cpus)\n", nproc);
-		goto err;
-	}
-
-	/* Use libbpf 1.0 API mode */
-	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
-
-	map_fd = bpf_map_create(BPF_MAP_TYPE_CGROUP_STORAGE, NULL, sizeof(key),
-				sizeof(value), 0, NULL);
-	if (map_fd < 0) {
-		printf("Failed to create map: %s\n", strerror(errno));
-		goto out;
-	}
-
-	percpu_map_fd = bpf_map_create(BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, NULL,
-				       sizeof(key), sizeof(value), 0, NULL);
-	if (percpu_map_fd < 0) {
-		printf("Failed to create map: %s\n", strerror(errno));
-		goto out;
-	}
-
-	prog[0].imm = percpu_map_fd;
-	prog[7].imm = map_fd;
-	prog_fd = bpf_test_load_program(BPF_PROG_TYPE_CGROUP_SKB,
-				   prog, insns_cnt, "GPL", 0,
-				   bpf_log_buf, BPF_LOG_BUF_SIZE);
-	if (prog_fd < 0) {
-		printf("Failed to load bpf program: %s\n", bpf_log_buf);
-		goto out;
-	}
-
-	cgroup_fd = cgroup_setup_and_join(TEST_CGROUP);
-
-	/* Attach the bpf program */
-	if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0)) {
-		printf("Failed to attach bpf program\n");
-		goto err;
-	}
-
-	if (bpf_map_get_next_key(map_fd, NULL, &key)) {
-		printf("Failed to get the first key in cgroup storage\n");
-		goto err;
-	}
-
-	if (bpf_map_lookup_elem(map_fd, &key, &value)) {
-		printf("Failed to lookup cgroup storage 0\n");
-		goto err;
-	}
-
-	for (cpu = 0; cpu < nproc; cpu++)
-		percpu_value[cpu] = 1000;
-
-	if (bpf_map_update_elem(percpu_map_fd, &key, percpu_value, 0)) {
-		printf("Failed to update the data in the cgroup storage\n");
-		goto err;
-	}
-
-	/* Every second packet should be dropped */
-	assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
-	assert(system("ping localhost -c 1 -W 1 -q > /dev/null"));
-	assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
-
-	/* Check the counter in the cgroup local storage */
-	if (bpf_map_lookup_elem(map_fd, &key, &value)) {
-		printf("Failed to lookup cgroup storage\n");
-		goto err;
-	}
-
-	if (value != 3) {
-		printf("Unexpected data in the cgroup storage: %llu\n", value);
-		goto err;
-	}
-
-	/* Bump the counter in the cgroup local storage */
-	value++;
-	if (bpf_map_update_elem(map_fd, &key, &value, 0)) {
-		printf("Failed to update the data in the cgroup storage\n");
-		goto err;
-	}
-
-	/* Every second packet should be dropped */
-	assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
-	assert(system("ping localhost -c 1 -W 1 -q > /dev/null"));
-	assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
-
-	/* Check the final value of the counter in the cgroup local storage */
-	if (bpf_map_lookup_elem(map_fd, &key, &value)) {
-		printf("Failed to lookup the cgroup storage\n");
-		goto err;
-	}
-
-	if (value != 7) {
-		printf("Unexpected data in the cgroup storage: %llu\n", value);
-		goto err;
-	}
-
-	/* Check the final value of the counter in the percpu local storage */
-
-	for (cpu = 0; cpu < nproc; cpu++)
-		percpu_value[cpu] = 0;
-
-	if (bpf_map_lookup_elem(percpu_map_fd, &key, percpu_value)) {
-		printf("Failed to lookup the per-cpu cgroup storage\n");
-		goto err;
-	}
-
-	value = 0;
-	for (cpu = 0; cpu < nproc; cpu++)
-		value += percpu_value[cpu];
-
-	if (value != nproc * 1000 + 6) {
-		printf("Unexpected data in the per-cpu cgroup storage\n");
-		goto err;
-	}
-
-	error = 0;
-	printf("test_cgroup_storage:PASS\n");
-
-err:
-	cleanup_cgroup_environment();
-	free(percpu_value);
-
-out:
-	return error;
-}
diff --git a/tools/testing/selftests/bpf/test_cpp.cpp b/tools/testing/selftests/bpf/test_cpp.cpp
index 0bd9990e83fa..abc2a56ab261 100644
--- a/tools/testing/selftests/bpf/test_cpp.cpp
+++ b/tools/testing/selftests/bpf/test_cpp.cpp
@@ -6,7 +6,12 @@
 #include <bpf/libbpf.h>
 #include <bpf/bpf.h>
 #include <bpf/btf.h>
+
+#ifndef _Bool
+#define _Bool bool
+#endif
 #include "test_core_extern.skel.h"
+#include "struct_ops_module.skel.h"
 
 template <typename T>
 class Skeleton {
@@ -91,13 +96,14 @@ static void try_skeleton_template()
 
 	skel.detach();
 
-	/* destructor will destory underlying skeleton */
+	/* destructor will destroy underlying skeleton */
 }
 
 int main(int argc, char *argv[])
 {
 	struct btf_dump_opts opts = { };
 	struct test_core_extern *skel;
+	struct struct_ops_module *skel2;
 	struct btf *btf;
 	int fd;
 
@@ -118,6 +124,9 @@ int main(int argc, char *argv[])
 	skel = test_core_extern__open_and_load();
 	test_core_extern__destroy(skel);
 
+	skel2 = struct_ops_module__open_and_load();
+	struct_ops_module__destroy(skel2);
+
 	fd = bpf_enable_stats(BPF_STATS_RUN_TIME);
 	if (fd < 0)
 		std::cout << "FAILED to enable stats: " << fd << std::endl;
diff --git a/tools/testing/selftests/bpf/test_dev_cgroup.c b/tools/testing/selftests/bpf/test_dev_cgroup.c
deleted file mode 100644
index adeaf63cb6fa..000000000000
--- a/tools/testing/selftests/bpf/test_dev_cgroup.c
+++ /dev/null
@@ -1,85 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/* Copyright (c) 2017 Facebook
- */
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <errno.h>
-#include <assert.h>
-#include <sys/time.h>
-
-#include <linux/bpf.h>
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-#include "cgroup_helpers.h"
-#include "testing_helpers.h"
-
-#define DEV_CGROUP_PROG "./dev_cgroup.bpf.o"
-
-#define TEST_CGROUP "/test-bpf-based-device-cgroup/"
-
-int main(int argc, char **argv)
-{
-	struct bpf_object *obj;
-	int error = EXIT_FAILURE;
-	int prog_fd, cgroup_fd;
-	__u32 prog_cnt;
-
-	/* Use libbpf 1.0 API mode */
-	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
-
-	if (bpf_prog_test_load(DEV_CGROUP_PROG, BPF_PROG_TYPE_CGROUP_DEVICE,
-			  &obj, &prog_fd)) {
-		printf("Failed to load DEV_CGROUP program\n");
-		goto out;
-	}
-
-	cgroup_fd = cgroup_setup_and_join(TEST_CGROUP);
-	if (cgroup_fd < 0) {
-		printf("Failed to create test cgroup\n");
-		goto out;
-	}
-
-	/* Attach bpf program */
-	if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_DEVICE, 0)) {
-		printf("Failed to attach DEV_CGROUP program");
-		goto err;
-	}
-
-	if (bpf_prog_query(cgroup_fd, BPF_CGROUP_DEVICE, 0, NULL, NULL,
-			   &prog_cnt)) {
-		printf("Failed to query attached programs");
-		goto err;
-	}
-
-	/* All operations with /dev/zero and and /dev/urandom are allowed,
-	 * everything else is forbidden.
-	 */
-	assert(system("rm -f /tmp/test_dev_cgroup_null") == 0);
-	assert(system("mknod /tmp/test_dev_cgroup_null c 1 3"));
-	assert(system("rm -f /tmp/test_dev_cgroup_null") == 0);
-
-	/* /dev/zero is whitelisted */
-	assert(system("rm -f /tmp/test_dev_cgroup_zero") == 0);
-	assert(system("mknod /tmp/test_dev_cgroup_zero c 1 5") == 0);
-	assert(system("rm -f /tmp/test_dev_cgroup_zero") == 0);
-
-	assert(system("dd if=/dev/urandom of=/dev/zero count=64") == 0);
-
-	/* src is allowed, target is forbidden */
-	assert(system("dd if=/dev/urandom of=/dev/full count=64"));
-
-	/* src is forbidden, target is allowed */
-	assert(system("dd if=/dev/random of=/dev/zero count=64"));
-
-	error = 0;
-	printf("test_dev_cgroup:PASS\n");
-
-err:
-	cleanup_cgroup_environment();
-
-out:
-	return error;
-}
diff --git a/tools/testing/selftests/bpf/test_flow_dissector.c b/tools/testing/selftests/bpf/test_flow_dissector.c
deleted file mode 100644
index 571cc076dd7d..000000000000
--- a/tools/testing/selftests/bpf/test_flow_dissector.c
+++ /dev/null
@@ -1,780 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Inject packets with all sorts of encapsulation into the kernel.
- *
- * IPv4/IPv6	outer layer 3
- * GRE/GUE/BARE outer layer 4, where bare is IPIP/SIT/IPv4-in-IPv6/..
- * IPv4/IPv6    inner layer 3
- */
-
-#define _GNU_SOURCE
-
-#include <stddef.h>
-#include <arpa/inet.h>
-#include <asm/byteorder.h>
-#include <error.h>
-#include <errno.h>
-#include <linux/if_packet.h>
-#include <linux/if_ether.h>
-#include <linux/ipv6.h>
-#include <netinet/ip.h>
-#include <netinet/in.h>
-#include <netinet/udp.h>
-#include <poll.h>
-#include <stdbool.h>
-#include <stdlib.h>
-#include <stdio.h>
-#include <string.h>
-#include <sys/ioctl.h>
-#include <sys/socket.h>
-#include <sys/stat.h>
-#include <sys/time.h>
-#include <sys/types.h>
-#include <unistd.h>
-
-#define CFG_PORT_INNER	8000
-
-/* Add some protocol definitions that do not exist in userspace */
-
-struct grehdr {
-	uint16_t unused;
-	uint16_t protocol;
-} __attribute__((packed));
-
-struct guehdr {
-	union {
-		struct {
-#if defined(__LITTLE_ENDIAN_BITFIELD)
-			__u8	hlen:5,
-				control:1,
-				version:2;
-#elif defined (__BIG_ENDIAN_BITFIELD)
-			__u8	version:2,
-				control:1,
-				hlen:5;
-#else
-#error  "Please fix <asm/byteorder.h>"
-#endif
-			__u8	proto_ctype;
-			__be16	flags;
-		};
-		__be32	word;
-	};
-};
-
-static uint8_t	cfg_dsfield_inner;
-static uint8_t	cfg_dsfield_outer;
-static uint8_t	cfg_encap_proto;
-static bool	cfg_expect_failure = false;
-static int	cfg_l3_extra = AF_UNSPEC;	/* optional SIT prefix */
-static int	cfg_l3_inner = AF_UNSPEC;
-static int	cfg_l3_outer = AF_UNSPEC;
-static int	cfg_num_pkt = 10;
-static int	cfg_num_secs = 0;
-static char	cfg_payload_char = 'a';
-static int	cfg_payload_len = 100;
-static int	cfg_port_gue = 6080;
-static bool	cfg_only_rx;
-static bool	cfg_only_tx;
-static int	cfg_src_port = 9;
-
-static char	buf[ETH_DATA_LEN];
-
-#define INIT_ADDR4(name, addr4, port)				\
-	static struct sockaddr_in name = {			\
-		.sin_family = AF_INET,				\
-		.sin_port = __constant_htons(port),		\
-		.sin_addr.s_addr = __constant_htonl(addr4),	\
-	};
-
-#define INIT_ADDR6(name, addr6, port)				\
-	static struct sockaddr_in6 name = {			\
-		.sin6_family = AF_INET6,			\
-		.sin6_port = __constant_htons(port),		\
-		.sin6_addr = addr6,				\
-	};
-
-INIT_ADDR4(in_daddr4, INADDR_LOOPBACK, CFG_PORT_INNER)
-INIT_ADDR4(in_saddr4, INADDR_LOOPBACK + 2, 0)
-INIT_ADDR4(out_daddr4, INADDR_LOOPBACK, 0)
-INIT_ADDR4(out_saddr4, INADDR_LOOPBACK + 1, 0)
-INIT_ADDR4(extra_daddr4, INADDR_LOOPBACK, 0)
-INIT_ADDR4(extra_saddr4, INADDR_LOOPBACK + 1, 0)
-
-INIT_ADDR6(in_daddr6, IN6ADDR_LOOPBACK_INIT, CFG_PORT_INNER)
-INIT_ADDR6(in_saddr6, IN6ADDR_LOOPBACK_INIT, 0)
-INIT_ADDR6(out_daddr6, IN6ADDR_LOOPBACK_INIT, 0)
-INIT_ADDR6(out_saddr6, IN6ADDR_LOOPBACK_INIT, 0)
-INIT_ADDR6(extra_daddr6, IN6ADDR_LOOPBACK_INIT, 0)
-INIT_ADDR6(extra_saddr6, IN6ADDR_LOOPBACK_INIT, 0)
-
-static unsigned long util_gettime(void)
-{
-	struct timeval tv;
-
-	gettimeofday(&tv, NULL);
-	return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
-}
-
-static void util_printaddr(const char *msg, struct sockaddr *addr)
-{
-	unsigned long off = 0;
-	char nbuf[INET6_ADDRSTRLEN];
-
-	switch (addr->sa_family) {
-	case PF_INET:
-		off = __builtin_offsetof(struct sockaddr_in, sin_addr);
-		break;
-	case PF_INET6:
-		off = __builtin_offsetof(struct sockaddr_in6, sin6_addr);
-		break;
-	default:
-		error(1, 0, "printaddr: unsupported family %u\n",
-		      addr->sa_family);
-	}
-
-	if (!inet_ntop(addr->sa_family, ((void *) addr) + off, nbuf,
-		       sizeof(nbuf)))
-		error(1, errno, "inet_ntop");
-
-	fprintf(stderr, "%s: %s\n", msg, nbuf);
-}
-
-static unsigned long add_csum_hword(const uint16_t *start, int num_u16)
-{
-	unsigned long sum = 0;
-	int i;
-
-	for (i = 0; i < num_u16; i++)
-		sum += start[i];
-
-	return sum;
-}
-
-static uint16_t build_ip_csum(const uint16_t *start, int num_u16,
-			      unsigned long sum)
-{
-	sum += add_csum_hword(start, num_u16);
-
-	while (sum >> 16)
-		sum = (sum & 0xffff) + (sum >> 16);
-
-	return ~sum;
-}
-
-static void build_ipv4_header(void *header, uint8_t proto,
-			      uint32_t src, uint32_t dst,
-			      int payload_len, uint8_t tos)
-{
-	struct iphdr *iph = header;
-
-	iph->ihl = 5;
-	iph->version = 4;
-	iph->tos = tos;
-	iph->ttl = 8;
-	iph->tot_len = htons(sizeof(*iph) + payload_len);
-	iph->id = htons(1337);
-	iph->protocol = proto;
-	iph->saddr = src;
-	iph->daddr = dst;
-	iph->check = build_ip_csum((void *) iph, iph->ihl << 1, 0);
-}
-
-static void ipv6_set_dsfield(struct ipv6hdr *ip6h, uint8_t dsfield)
-{
-	uint16_t val, *ptr = (uint16_t *)ip6h;
-
-	val = ntohs(*ptr);
-	val &= 0xF00F;
-	val |= ((uint16_t) dsfield) << 4;
-	*ptr = htons(val);
-}
-
-static void build_ipv6_header(void *header, uint8_t proto,
-			      struct sockaddr_in6 *src,
-			      struct sockaddr_in6 *dst,
-			      int payload_len, uint8_t dsfield)
-{
-	struct ipv6hdr *ip6h = header;
-
-	ip6h->version = 6;
-	ip6h->payload_len = htons(payload_len);
-	ip6h->nexthdr = proto;
-	ip6h->hop_limit = 8;
-	ipv6_set_dsfield(ip6h, dsfield);
-
-	memcpy(&ip6h->saddr, &src->sin6_addr, sizeof(ip6h->saddr));
-	memcpy(&ip6h->daddr, &dst->sin6_addr, sizeof(ip6h->daddr));
-}
-
-static uint16_t build_udp_v4_csum(const struct iphdr *iph,
-				  const struct udphdr *udph,
-				  int num_words)
-{
-	unsigned long pseudo_sum;
-	int num_u16 = sizeof(iph->saddr);	/* halfwords: twice byte len */
-
-	pseudo_sum = add_csum_hword((void *) &iph->saddr, num_u16);
-	pseudo_sum += htons(IPPROTO_UDP);
-	pseudo_sum += udph->len;
-	return build_ip_csum((void *) udph, num_words, pseudo_sum);
-}
-
-static uint16_t build_udp_v6_csum(const struct ipv6hdr *ip6h,
-				  const struct udphdr *udph,
-				  int num_words)
-{
-	unsigned long pseudo_sum;
-	int num_u16 = sizeof(ip6h->saddr);	/* halfwords: twice byte len */
-
-	pseudo_sum = add_csum_hword((void *) &ip6h->saddr, num_u16);
-	pseudo_sum += htons(ip6h->nexthdr);
-	pseudo_sum += ip6h->payload_len;
-	return build_ip_csum((void *) udph, num_words, pseudo_sum);
-}
-
-static void build_udp_header(void *header, int payload_len,
-			     uint16_t dport, int family)
-{
-	struct udphdr *udph = header;
-	int len = sizeof(*udph) + payload_len;
-
-	udph->source = htons(cfg_src_port);
-	udph->dest = htons(dport);
-	udph->len = htons(len);
-	udph->check = 0;
-	if (family == AF_INET)
-		udph->check = build_udp_v4_csum(header - sizeof(struct iphdr),
-						udph, len >> 1);
-	else
-		udph->check = build_udp_v6_csum(header - sizeof(struct ipv6hdr),
-						udph, len >> 1);
-}
-
-static void build_gue_header(void *header, uint8_t proto)
-{
-	struct guehdr *gueh = header;
-
-	gueh->proto_ctype = proto;
-}
-
-static void build_gre_header(void *header, uint16_t proto)
-{
-	struct grehdr *greh = header;
-
-	greh->protocol = htons(proto);
-}
-
-static int l3_length(int family)
-{
-	if (family == AF_INET)
-		return sizeof(struct iphdr);
-	else
-		return sizeof(struct ipv6hdr);
-}
-
-static int build_packet(void)
-{
-	int ol3_len = 0, ol4_len = 0, il3_len = 0, il4_len = 0;
-	int el3_len = 0;
-
-	if (cfg_l3_extra)
-		el3_len = l3_length(cfg_l3_extra);
-
-	/* calculate header offsets */
-	if (cfg_encap_proto) {
-		ol3_len = l3_length(cfg_l3_outer);
-
-		if (cfg_encap_proto == IPPROTO_GRE)
-			ol4_len = sizeof(struct grehdr);
-		else if (cfg_encap_proto == IPPROTO_UDP)
-			ol4_len = sizeof(struct udphdr) + sizeof(struct guehdr);
-	}
-
-	il3_len = l3_length(cfg_l3_inner);
-	il4_len = sizeof(struct udphdr);
-
-	if (el3_len + ol3_len + ol4_len + il3_len + il4_len + cfg_payload_len >=
-	    sizeof(buf))
-		error(1, 0, "packet too large\n");
-
-	/*
-	 * Fill packet from inside out, to calculate correct checksums.
-	 * But create ip before udp headers, as udp uses ip for pseudo-sum.
-	 */
-	memset(buf + el3_len + ol3_len + ol4_len + il3_len + il4_len,
-	       cfg_payload_char, cfg_payload_len);
-
-	/* add zero byte for udp csum padding */
-	buf[el3_len + ol3_len + ol4_len + il3_len + il4_len + cfg_payload_len] = 0;
-
-	switch (cfg_l3_inner) {
-	case PF_INET:
-		build_ipv4_header(buf + el3_len + ol3_len + ol4_len,
-				  IPPROTO_UDP,
-				  in_saddr4.sin_addr.s_addr,
-				  in_daddr4.sin_addr.s_addr,
-				  il4_len + cfg_payload_len,
-				  cfg_dsfield_inner);
-		break;
-	case PF_INET6:
-		build_ipv6_header(buf + el3_len + ol3_len + ol4_len,
-				  IPPROTO_UDP,
-				  &in_saddr6, &in_daddr6,
-				  il4_len + cfg_payload_len,
-				  cfg_dsfield_inner);
-		break;
-	}
-
-	build_udp_header(buf + el3_len + ol3_len + ol4_len + il3_len,
-			 cfg_payload_len, CFG_PORT_INNER, cfg_l3_inner);
-
-	if (!cfg_encap_proto)
-		return il3_len + il4_len + cfg_payload_len;
-
-	switch (cfg_l3_outer) {
-	case PF_INET:
-		build_ipv4_header(buf + el3_len, cfg_encap_proto,
-				  out_saddr4.sin_addr.s_addr,
-				  out_daddr4.sin_addr.s_addr,
-				  ol4_len + il3_len + il4_len + cfg_payload_len,
-				  cfg_dsfield_outer);
-		break;
-	case PF_INET6:
-		build_ipv6_header(buf + el3_len, cfg_encap_proto,
-				  &out_saddr6, &out_daddr6,
-				  ol4_len + il3_len + il4_len + cfg_payload_len,
-				  cfg_dsfield_outer);
-		break;
-	}
-
-	switch (cfg_encap_proto) {
-	case IPPROTO_UDP:
-		build_gue_header(buf + el3_len + ol3_len + ol4_len -
-				 sizeof(struct guehdr),
-				 cfg_l3_inner == PF_INET ? IPPROTO_IPIP
-							 : IPPROTO_IPV6);
-		build_udp_header(buf + el3_len + ol3_len,
-				 sizeof(struct guehdr) + il3_len + il4_len +
-				 cfg_payload_len,
-				 cfg_port_gue, cfg_l3_outer);
-		break;
-	case IPPROTO_GRE:
-		build_gre_header(buf + el3_len + ol3_len,
-				 cfg_l3_inner == PF_INET ? ETH_P_IP
-							 : ETH_P_IPV6);
-		break;
-	}
-
-	switch (cfg_l3_extra) {
-	case PF_INET:
-		build_ipv4_header(buf,
-				  cfg_l3_outer == PF_INET ? IPPROTO_IPIP
-							  : IPPROTO_IPV6,
-				  extra_saddr4.sin_addr.s_addr,
-				  extra_daddr4.sin_addr.s_addr,
-				  ol3_len + ol4_len + il3_len + il4_len +
-				  cfg_payload_len, 0);
-		break;
-	case PF_INET6:
-		build_ipv6_header(buf,
-				  cfg_l3_outer == PF_INET ? IPPROTO_IPIP
-							  : IPPROTO_IPV6,
-				  &extra_saddr6, &extra_daddr6,
-				  ol3_len + ol4_len + il3_len + il4_len +
-				  cfg_payload_len, 0);
-		break;
-	}
-
-	return el3_len + ol3_len + ol4_len + il3_len + il4_len +
-	       cfg_payload_len;
-}
-
-/* sender transmits encapsulated over RAW or unencap'd over UDP */
-static int setup_tx(void)
-{
-	int family, fd, ret;
-
-	if (cfg_l3_extra)
-		family = cfg_l3_extra;
-	else if (cfg_l3_outer)
-		family = cfg_l3_outer;
-	else
-		family = cfg_l3_inner;
-
-	fd = socket(family, SOCK_RAW, IPPROTO_RAW);
-	if (fd == -1)
-		error(1, errno, "socket tx");
-
-	if (cfg_l3_extra) {
-		if (cfg_l3_extra == PF_INET)
-			ret = connect(fd, (void *) &extra_daddr4,
-				      sizeof(extra_daddr4));
-		else
-			ret = connect(fd, (void *) &extra_daddr6,
-				      sizeof(extra_daddr6));
-		if (ret)
-			error(1, errno, "connect tx");
-	} else if (cfg_l3_outer) {
-		/* connect to destination if not encapsulated */
-		if (cfg_l3_outer == PF_INET)
-			ret = connect(fd, (void *) &out_daddr4,
-				      sizeof(out_daddr4));
-		else
-			ret = connect(fd, (void *) &out_daddr6,
-				      sizeof(out_daddr6));
-		if (ret)
-			error(1, errno, "connect tx");
-	} else {
-		/* otherwise using loopback */
-		if (cfg_l3_inner == PF_INET)
-			ret = connect(fd, (void *) &in_daddr4,
-				      sizeof(in_daddr4));
-		else
-			ret = connect(fd, (void *) &in_daddr6,
-				      sizeof(in_daddr6));
-		if (ret)
-			error(1, errno, "connect tx");
-	}
-
-	return fd;
-}
-
-/* receiver reads unencapsulated UDP */
-static int setup_rx(void)
-{
-	int fd, ret;
-
-	fd = socket(cfg_l3_inner, SOCK_DGRAM, 0);
-	if (fd == -1)
-		error(1, errno, "socket rx");
-
-	if (cfg_l3_inner == PF_INET)
-		ret = bind(fd, (void *) &in_daddr4, sizeof(in_daddr4));
-	else
-		ret = bind(fd, (void *) &in_daddr6, sizeof(in_daddr6));
-	if (ret)
-		error(1, errno, "bind rx");
-
-	return fd;
-}
-
-static int do_tx(int fd, const char *pkt, int len)
-{
-	int ret;
-
-	ret = write(fd, pkt, len);
-	if (ret == -1)
-		error(1, errno, "send");
-	if (ret != len)
-		error(1, errno, "send: len (%d < %d)\n", ret, len);
-
-	return 1;
-}
-
-static int do_poll(int fd, short events, int timeout)
-{
-	struct pollfd pfd;
-	int ret;
-
-	pfd.fd = fd;
-	pfd.events = events;
-
-	ret = poll(&pfd, 1, timeout);
-	if (ret == -1)
-		error(1, errno, "poll");
-	if (ret && !(pfd.revents & POLLIN))
-		error(1, errno, "poll: unexpected event 0x%x\n", pfd.revents);
-
-	return ret;
-}
-
-static int do_rx(int fd)
-{
-	char rbuf;
-	int ret, num = 0;
-
-	while (1) {
-		ret = recv(fd, &rbuf, 1, MSG_DONTWAIT);
-		if (ret == -1 && errno == EAGAIN)
-			break;
-		if (ret == -1)
-			error(1, errno, "recv");
-		if (rbuf != cfg_payload_char)
-			error(1, 0, "recv: payload mismatch");
-		num++;
-	}
-
-	return num;
-}
-
-static int do_main(void)
-{
-	unsigned long tstop, treport, tcur;
-	int fdt = -1, fdr = -1, len, tx = 0, rx = 0;
-
-	if (!cfg_only_tx)
-		fdr = setup_rx();
-	if (!cfg_only_rx)
-		fdt = setup_tx();
-
-	len = build_packet();
-
-	tcur = util_gettime();
-	treport = tcur + 1000;
-	tstop = tcur + (cfg_num_secs * 1000);
-
-	while (1) {
-		if (!cfg_only_rx)
-			tx += do_tx(fdt, buf, len);
-
-		if (!cfg_only_tx)
-			rx += do_rx(fdr);
-
-		if (cfg_num_secs) {
-			tcur = util_gettime();
-			if (tcur >= tstop)
-				break;
-			if (tcur >= treport) {
-				fprintf(stderr, "pkts: tx=%u rx=%u\n", tx, rx);
-				tx = 0;
-				rx = 0;
-				treport = tcur + 1000;
-			}
-		} else {
-			if (tx == cfg_num_pkt)
-				break;
-		}
-	}
-
-	/* read straggler packets, if any */
-	if (rx < tx) {
-		tstop = util_gettime() + 100;
-		while (rx < tx) {
-			tcur = util_gettime();
-			if (tcur >= tstop)
-				break;
-
-			do_poll(fdr, POLLIN, tstop - tcur);
-			rx += do_rx(fdr);
-		}
-	}
-
-	fprintf(stderr, "pkts: tx=%u rx=%u\n", tx, rx);
-
-	if (fdr != -1 && close(fdr))
-		error(1, errno, "close rx");
-	if (fdt != -1 && close(fdt))
-		error(1, errno, "close tx");
-
-	/*
-	 * success (== 0) only if received all packets
-	 * unless failure is expected, in which case none must arrive.
-	 */
-	if (cfg_expect_failure)
-		return rx != 0;
-	else
-		return rx != tx;
-}
-
-
-static void __attribute__((noreturn)) usage(const char *filepath)
-{
-	fprintf(stderr, "Usage: %s [-e gre|gue|bare|none] [-i 4|6] [-l len] "
-			"[-O 4|6] [-o 4|6] [-n num] [-t secs] [-R] [-T] "
-			"[-s <osrc> [-d <odst>] [-S <isrc>] [-D <idst>] "
-			"[-x <otos>] [-X <itos>] [-f <isport>] [-F]\n",
-		filepath);
-	exit(1);
-}
-
-static void parse_addr(int family, void *addr, const char *optarg)
-{
-	int ret;
-
-	ret = inet_pton(family, optarg, addr);
-	if (ret == -1)
-		error(1, errno, "inet_pton");
-	if (ret == 0)
-		error(1, 0, "inet_pton: bad string");
-}
-
-static void parse_addr4(struct sockaddr_in *addr, const char *optarg)
-{
-	parse_addr(AF_INET, &addr->sin_addr, optarg);
-}
-
-static void parse_addr6(struct sockaddr_in6 *addr, const char *optarg)
-{
-	parse_addr(AF_INET6, &addr->sin6_addr, optarg);
-}
-
-static int parse_protocol_family(const char *filepath, const char *optarg)
-{
-	if (!strcmp(optarg, "4"))
-		return PF_INET;
-	if (!strcmp(optarg, "6"))
-		return PF_INET6;
-
-	usage(filepath);
-}
-
-static void parse_opts(int argc, char **argv)
-{
-	int c;
-
-	while ((c = getopt(argc, argv, "d:D:e:f:Fhi:l:n:o:O:Rs:S:t:Tx:X:")) != -1) {
-		switch (c) {
-		case 'd':
-			if (cfg_l3_outer == AF_UNSPEC)
-				error(1, 0, "-d must be preceded by -o");
-			if (cfg_l3_outer == AF_INET)
-				parse_addr4(&out_daddr4, optarg);
-			else
-				parse_addr6(&out_daddr6, optarg);
-			break;
-		case 'D':
-			if (cfg_l3_inner == AF_UNSPEC)
-				error(1, 0, "-D must be preceded by -i");
-			if (cfg_l3_inner == AF_INET)
-				parse_addr4(&in_daddr4, optarg);
-			else
-				parse_addr6(&in_daddr6, optarg);
-			break;
-		case 'e':
-			if (!strcmp(optarg, "gre"))
-				cfg_encap_proto = IPPROTO_GRE;
-			else if (!strcmp(optarg, "gue"))
-				cfg_encap_proto = IPPROTO_UDP;
-			else if (!strcmp(optarg, "bare"))
-				cfg_encap_proto = IPPROTO_IPIP;
-			else if (!strcmp(optarg, "none"))
-				cfg_encap_proto = IPPROTO_IP;	/* == 0 */
-			else
-				usage(argv[0]);
-			break;
-		case 'f':
-			cfg_src_port = strtol(optarg, NULL, 0);
-			break;
-		case 'F':
-			cfg_expect_failure = true;
-			break;
-		case 'h':
-			usage(argv[0]);
-			break;
-		case 'i':
-			if (!strcmp(optarg, "4"))
-				cfg_l3_inner = PF_INET;
-			else if (!strcmp(optarg, "6"))
-				cfg_l3_inner = PF_INET6;
-			else
-				usage(argv[0]);
-			break;
-		case 'l':
-			cfg_payload_len = strtol(optarg, NULL, 0);
-			break;
-		case 'n':
-			cfg_num_pkt = strtol(optarg, NULL, 0);
-			break;
-		case 'o':
-			cfg_l3_outer = parse_protocol_family(argv[0], optarg);
-			break;
-		case 'O':
-			cfg_l3_extra = parse_protocol_family(argv[0], optarg);
-			break;
-		case 'R':
-			cfg_only_rx = true;
-			break;
-		case 's':
-			if (cfg_l3_outer == AF_INET)
-				parse_addr4(&out_saddr4, optarg);
-			else
-				parse_addr6(&out_saddr6, optarg);
-			break;
-		case 'S':
-			if (cfg_l3_inner == AF_INET)
-				parse_addr4(&in_saddr4, optarg);
-			else
-				parse_addr6(&in_saddr6, optarg);
-			break;
-		case 't':
-			cfg_num_secs = strtol(optarg, NULL, 0);
-			break;
-		case 'T':
-			cfg_only_tx = true;
-			break;
-		case 'x':
-			cfg_dsfield_outer = strtol(optarg, NULL, 0);
-			break;
-		case 'X':
-			cfg_dsfield_inner = strtol(optarg, NULL, 0);
-			break;
-		}
-	}
-
-	if (cfg_only_rx && cfg_only_tx)
-		error(1, 0, "options: cannot combine rx-only and tx-only");
-
-	if (cfg_encap_proto && cfg_l3_outer == AF_UNSPEC)
-		error(1, 0, "options: must specify outer with encap");
-	else if ((!cfg_encap_proto) && cfg_l3_outer != AF_UNSPEC)
-		error(1, 0, "options: cannot combine no-encap and outer");
-	else if ((!cfg_encap_proto) && cfg_l3_extra != AF_UNSPEC)
-		error(1, 0, "options: cannot combine no-encap and extra");
-
-	if (cfg_l3_inner == AF_UNSPEC)
-		cfg_l3_inner = AF_INET6;
-	if (cfg_l3_inner == AF_INET6 && cfg_encap_proto == IPPROTO_IPIP)
-		cfg_encap_proto = IPPROTO_IPV6;
-
-	/* RFC 6040 4.2:
-	 *   on decap, if outer encountered congestion (CE == 0x3),
-	 *   but inner cannot encode ECN (NoECT == 0x0), then drop packet.
-	 */
-	if (((cfg_dsfield_outer & 0x3) == 0x3) &&
-	    ((cfg_dsfield_inner & 0x3) == 0x0))
-		cfg_expect_failure = true;
-}
-
-static void print_opts(void)
-{
-	if (cfg_l3_inner == PF_INET6) {
-		util_printaddr("inner.dest6", (void *) &in_daddr6);
-		util_printaddr("inner.source6", (void *) &in_saddr6);
-	} else {
-		util_printaddr("inner.dest4", (void *) &in_daddr4);
-		util_printaddr("inner.source4", (void *) &in_saddr4);
-	}
-
-	if (!cfg_l3_outer)
-		return;
-
-	fprintf(stderr, "encap proto:   %u\n", cfg_encap_proto);
-
-	if (cfg_l3_outer == PF_INET6) {
-		util_printaddr("outer.dest6", (void *) &out_daddr6);
-		util_printaddr("outer.source6", (void *) &out_saddr6);
-	} else {
-		util_printaddr("outer.dest4", (void *) &out_daddr4);
-		util_printaddr("outer.source4", (void *) &out_saddr4);
-	}
-
-	if (!cfg_l3_extra)
-		return;
-
-	if (cfg_l3_outer == PF_INET6) {
-		util_printaddr("extra.dest6", (void *) &extra_daddr6);
-		util_printaddr("extra.source6", (void *) &extra_saddr6);
-	} else {
-		util_printaddr("extra.dest4", (void *) &extra_daddr4);
-		util_printaddr("extra.source4", (void *) &extra_saddr4);
-	}
-
-}
-
-int main(int argc, char **argv)
-{
-	parse_opts(argc, argv);
-	print_opts();
-	return do_main();
-}
diff --git a/tools/testing/selftests/bpf/test_flow_dissector.sh b/tools/testing/selftests/bpf/test_flow_dissector.sh
deleted file mode 100755
index 4b298863797a..000000000000
--- a/tools/testing/selftests/bpf/test_flow_dissector.sh
+++ /dev/null
@@ -1,178 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-#
-# Load BPF flow dissector and verify it correctly dissects traffic
-
-BPF_FILE="bpf_flow.bpf.o"
-export TESTNAME=test_flow_dissector
-unmount=0
-
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
-msg="skip all tests:"
-if [ $UID != 0 ]; then
-	echo $msg please run this as root >&2
-	exit $ksft_skip
-fi
-
-# This test needs to be run in a network namespace with in_netns.sh. Check if
-# this is the case and run it with in_netns.sh if it is being run in the root
-# namespace.
-if [[ -z $(ip netns identify $$) ]]; then
-	err=0
-	if bpftool="$(which bpftool)"; then
-		echo "Testing global flow dissector..."
-
-		$bpftool prog loadall $BPF_FILE /sys/fs/bpf/flow \
-			type flow_dissector
-
-		if ! unshare --net $bpftool prog attach pinned \
-			/sys/fs/bpf/flow/_dissect flow_dissector; then
-			echo "Unexpected unsuccessful attach in namespace" >&2
-			err=1
-		fi
-
-		$bpftool prog attach pinned /sys/fs/bpf/flow/_dissect \
-			flow_dissector
-
-		if unshare --net $bpftool prog attach pinned \
-			/sys/fs/bpf/flow/_dissect flow_dissector; then
-			echo "Unexpected successful attach in namespace" >&2
-			err=1
-		fi
-
-		if ! $bpftool prog detach pinned \
-			/sys/fs/bpf/flow/_dissect flow_dissector; then
-			echo "Failed to detach flow dissector" >&2
-			err=1
-		fi
-
-		rm -rf /sys/fs/bpf/flow
-	else
-		echo "Skipping root flow dissector test, bpftool not found" >&2
-	fi
-
-	# Run the rest of the tests in a net namespace.
-	../net/in_netns.sh "$0" "$@"
-	err=$(( $err + $? ))
-
-	if (( $err == 0 )); then
-		echo "selftests: $TESTNAME [PASS]";
-	else
-		echo "selftests: $TESTNAME [FAILED]";
-	fi
-
-	exit $err
-fi
-
-# Determine selftest success via shell exit code
-exit_handler()
-{
-	set +e
-
-	# Cleanup
-	tc filter del dev lo ingress pref 1337 2> /dev/null
-	tc qdisc del dev lo ingress 2> /dev/null
-	./flow_dissector_load -d 2> /dev/null
-	if [ $unmount -ne 0 ]; then
-		umount bpffs 2> /dev/null
-	fi
-}
-
-# Exit script immediately (well catched by trap handler) if any
-# program/thing exits with a non-zero status.
-set -e
-
-# (Use 'trap -l' to list meaning of numbers)
-trap exit_handler 0 2 3 6 9
-
-# Mount BPF file system
-if /bin/mount | grep /sys/fs/bpf > /dev/null; then
-	echo "bpffs already mounted"
-else
-	echo "bpffs not mounted. Mounting..."
-	unmount=1
-	/bin/mount bpffs /sys/fs/bpf -t bpf
-fi
-
-# Attach BPF program
-./flow_dissector_load -p $BPF_FILE -s _dissect
-
-# Setup
-tc qdisc add dev lo ingress
-echo 0 > /proc/sys/net/ipv4/conf/default/rp_filter
-echo 0 > /proc/sys/net/ipv4/conf/all/rp_filter
-echo 0 > /proc/sys/net/ipv4/conf/lo/rp_filter
-
-echo "Testing IPv4..."
-# Drops all IP/UDP packets coming from port 9
-tc filter add dev lo parent ffff: protocol ip pref 1337 flower ip_proto \
-	udp src_port 9 action drop
-
-# Send 10 IPv4/UDP packets from port 8. Filter should not drop any.
-./test_flow_dissector -i 4 -f 8
-# Send 10 IPv4/UDP packets from port 9. Filter should drop all.
-./test_flow_dissector -i 4 -f 9 -F
-# Send 10 IPv4/UDP packets from port 10. Filter should not drop any.
-./test_flow_dissector -i 4 -f 10
-
-echo "Testing IPv4 from 127.0.0.127 (fallback to generic dissector)..."
-# Send 10 IPv4/UDP packets from port 8. Filter should not drop any.
-./test_flow_dissector -i 4 -S 127.0.0.127 -f 8
-# Send 10 IPv4/UDP packets from port 9. Filter should drop all.
-./test_flow_dissector -i 4 -S 127.0.0.127 -f 9 -F
-# Send 10 IPv4/UDP packets from port 10. Filter should not drop any.
-./test_flow_dissector -i 4 -S 127.0.0.127 -f 10
-
-echo "Testing IPIP..."
-# Send 10 IPv4/IPv4/UDP packets from port 8. Filter should not drop any.
-./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e bare -i 4 \
-	-D 192.168.0.1 -S 1.1.1.1 -f 8
-# Send 10 IPv4/IPv4/UDP packets from port 9. Filter should drop all.
-./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e bare -i 4 \
-	-D 192.168.0.1 -S 1.1.1.1 -f 9 -F
-# Send 10 IPv4/IPv4/UDP packets from port 10. Filter should not drop any.
-./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e bare -i 4 \
-	-D 192.168.0.1 -S 1.1.1.1 -f 10
-
-echo "Testing IPv4 + GRE..."
-# Send 10 IPv4/GRE/IPv4/UDP packets from port 8. Filter should not drop any.
-./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e gre -i 4 \
-	-D 192.168.0.1 -S 1.1.1.1 -f 8
-# Send 10 IPv4/GRE/IPv4/UDP packets from port 9. Filter should drop all.
-./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e gre -i 4 \
-	-D 192.168.0.1 -S 1.1.1.1 -f 9 -F
-# Send 10 IPv4/GRE/IPv4/UDP packets from port 10. Filter should not drop any.
-./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e gre -i 4 \
-	-D 192.168.0.1 -S 1.1.1.1 -f 10
-
-tc filter del dev lo ingress pref 1337
-
-echo "Testing port range..."
-# Drops all IP/UDP packets coming from port 8-10
-tc filter add dev lo parent ffff: protocol ip pref 1337 flower ip_proto \
-	udp src_port 8-10 action drop
-
-# Send 10 IPv4/UDP packets from port 7. Filter should not drop any.
-./test_flow_dissector -i 4 -f 7
-# Send 10 IPv4/UDP packets from port 9. Filter should drop all.
-./test_flow_dissector -i 4 -f 9 -F
-# Send 10 IPv4/UDP packets from port 11. Filter should not drop any.
-./test_flow_dissector -i 4 -f 11
-
-tc filter del dev lo ingress pref 1337
-
-echo "Testing IPv6..."
-# Drops all IPv6/UDP packets coming from port 9
-tc filter add dev lo parent ffff: protocol ipv6 pref 1337 flower ip_proto \
-	udp src_port 9 action drop
-
-# Send 10 IPv6/UDP packets from port 8. Filter should not drop any.
-./test_flow_dissector -i 6 -f 8
-# Send 10 IPv6/UDP packets from port 9. Filter should drop all.
-./test_flow_dissector -i 6 -f 9 -F
-# Send 10 IPv6/UDP packets from port 10. Filter should not drop any.
-./test_flow_dissector -i 6 -f 10
-
-exit 0
diff --git a/tools/testing/selftests/bpf/test_ftrace.sh b/tools/testing/selftests/bpf/test_ftrace.sh
index 20de7bb873bc..f5109eb0e951 100755
--- a/tools/testing/selftests/bpf/test_ftrace.sh
+++ b/tools/testing/selftests/bpf/test_ftrace.sh
@@ -1,6 +1,11 @@
 #!/bin/bash
 
-TR=/sys/kernel/debug/tracing/
+if [[ -e /sys/kernel/tracing/trace ]]; then
+    TR=/sys/kernel/tracing/
+else
+    TR=/sys/kernel/debug/tracing/
+fi
+
 clear_trace() { # reset trace output
     echo > $TR/trace
 }
diff --git a/tools/testing/selftests/bpf/bpf_testmod/.gitignore b/tools/testing/selftests/bpf/test_kmods/.gitignore
index ded513777281..ded513777281 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/.gitignore
+++ b/tools/testing/selftests/bpf/test_kmods/.gitignore
diff --git a/tools/testing/selftests/bpf/test_kmods/Makefile b/tools/testing/selftests/bpf/test_kmods/Makefile
new file mode 100644
index 000000000000..63c4d3f6a12f
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_kmods/Makefile
@@ -0,0 +1,21 @@
+TEST_KMOD_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST)))))
+KDIR ?= $(abspath $(TEST_KMOD_DIR)/../../../../..)
+
+ifeq ($(V),1)
+Q =
+else
+Q = @
+endif
+
+MODULES = bpf_testmod.ko bpf_test_no_cfi.ko bpf_test_modorder_x.ko \
+	bpf_test_modorder_y.ko bpf_test_rqspinlock.ko
+
+$(foreach m,$(MODULES),$(eval obj-m += $(m:.ko=.o)))
+
+CFLAGS_bpf_testmod.o = -I$(src)
+
+all:
+	$(Q)$(MAKE) -C $(KDIR) M=$(TEST_KMOD_DIR) modules
+
+clean:
+	$(Q)$(MAKE) -C $(KDIR) M=$(TEST_KMOD_DIR) clean
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_test_modorder_x.c b/tools/testing/selftests/bpf/test_kmods/bpf_test_modorder_x.c
new file mode 100644
index 000000000000..0cc747fa912f
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_test_modorder_x.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_test_modorder_retx(void)
+{
+	return 'x';
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(bpf_test_modorder_kfunc_x_ids)
+BTF_ID_FLAGS(func, bpf_test_modorder_retx);
+BTF_KFUNCS_END(bpf_test_modorder_kfunc_x_ids)
+
+static const struct btf_kfunc_id_set bpf_test_modorder_x_set = {
+	.owner = THIS_MODULE,
+	.set = &bpf_test_modorder_kfunc_x_ids,
+};
+
+static int __init bpf_test_modorder_x_init(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS,
+					 &bpf_test_modorder_x_set);
+}
+
+static void __exit bpf_test_modorder_x_exit(void)
+{
+}
+
+module_init(bpf_test_modorder_x_init);
+module_exit(bpf_test_modorder_x_exit);
+
+MODULE_DESCRIPTION("BPF selftest ordertest module X");
+MODULE_LICENSE("GPL");
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_test_modorder_y.c b/tools/testing/selftests/bpf/test_kmods/bpf_test_modorder_y.c
new file mode 100644
index 000000000000..c627ee085d13
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_test_modorder_y.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_test_modorder_rety(void)
+{
+	return 'y';
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(bpf_test_modorder_kfunc_y_ids)
+BTF_ID_FLAGS(func, bpf_test_modorder_rety);
+BTF_KFUNCS_END(bpf_test_modorder_kfunc_y_ids)
+
+static const struct btf_kfunc_id_set bpf_test_modorder_y_set = {
+	.owner = THIS_MODULE,
+	.set = &bpf_test_modorder_kfunc_y_ids,
+};
+
+static int __init bpf_test_modorder_y_init(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS,
+					 &bpf_test_modorder_y_set);
+}
+
+static void __exit bpf_test_modorder_y_exit(void)
+{
+}
+
+module_init(bpf_test_modorder_y_init);
+module_exit(bpf_test_modorder_y_exit);
+
+MODULE_DESCRIPTION("BPF selftest ordertest module Y");
+MODULE_LICENSE("GPL");
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_test_no_cfi.c b/tools/testing/selftests/bpf/test_kmods/bpf_test_no_cfi.c
new file mode 100644
index 000000000000..948eb3962732
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_test_no_cfi.c
@@ -0,0 +1,84 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/init.h>
+#include <linux/module.h>
+
+struct bpf_test_no_cfi_ops {
+	void (*fn_1)(void);
+	void (*fn_2)(void);
+};
+
+static int dummy_init(struct btf *btf)
+{
+	return 0;
+}
+
+static int dummy_init_member(const struct btf_type *t,
+			     const struct btf_member *member,
+			     void *kdata, const void *udata)
+{
+	return 0;
+}
+
+static int dummy_reg(void *kdata, struct bpf_link *link)
+{
+	return 0;
+}
+
+static void dummy_unreg(void *kdata, struct bpf_link *link)
+{
+}
+
+static const struct bpf_verifier_ops dummy_verifier_ops;
+
+static void bpf_test_no_cfi_ops__fn_1(void)
+{
+}
+
+static void bpf_test_no_cfi_ops__fn_2(void)
+{
+}
+
+static struct bpf_test_no_cfi_ops __test_no_cif_ops = {
+	.fn_1 = bpf_test_no_cfi_ops__fn_1,
+	.fn_2 = bpf_test_no_cfi_ops__fn_2,
+};
+
+static struct bpf_struct_ops test_no_cif_ops = {
+	.verifier_ops = &dummy_verifier_ops,
+	.init = dummy_init,
+	.init_member = dummy_init_member,
+	.reg = dummy_reg,
+	.unreg = dummy_unreg,
+	.name = "bpf_test_no_cfi_ops",
+	.owner = THIS_MODULE,
+};
+
+static int bpf_test_no_cfi_init(void)
+{
+	int ret;
+
+	ret = register_bpf_struct_ops(&test_no_cif_ops,
+				      bpf_test_no_cfi_ops);
+	if (!ret)
+		return -EINVAL;
+
+	test_no_cif_ops.cfi_stubs = &__test_no_cif_ops;
+	ret = register_bpf_struct_ops(&test_no_cif_ops,
+				      bpf_test_no_cfi_ops);
+	return ret;
+}
+
+static void bpf_test_no_cfi_exit(void)
+{
+}
+
+module_init(bpf_test_no_cfi_init);
+module_exit(bpf_test_no_cfi_exit);
+
+MODULE_AUTHOR("Kuifeng Lee");
+MODULE_DESCRIPTION("BPF no cfi_stubs test module");
+MODULE_LICENSE("Dual BSD/GPL");
+
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_test_rqspinlock.c b/tools/testing/selftests/bpf/test_kmods/bpf_test_rqspinlock.c
new file mode 100644
index 000000000000..7b4ae5e81d32
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_test_rqspinlock.c
@@ -0,0 +1,393 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/prandom.h>
+#include <linux/ktime.h>
+#include <asm/rqspinlock.h>
+#include <linux/perf_event.h>
+#include <linux/kthread.h>
+#include <linux/atomic.h>
+#include <linux/slab.h>
+
+static struct perf_event_attr hw_attr = {
+	.type		= PERF_TYPE_HARDWARE,
+	.config		= PERF_COUNT_HW_CPU_CYCLES,
+	.size		= sizeof(struct perf_event_attr),
+	.pinned		= 1,
+	.disabled	= 1,
+	.sample_period	= 100000,
+};
+
+static rqspinlock_t lock_a;
+static rqspinlock_t lock_b;
+static rqspinlock_t lock_c;
+
+#define RQSL_SLOW_THRESHOLD_MS 10
+static const unsigned int rqsl_hist_ms[] = {
+	1, 2, 3, 4, 5, 6, 7, 8, 9, 10,
+	12, 14, 16, 18, 20, 25, 30, 40, 50, 75,
+	100, 150, 200, 250, 1000,
+};
+#define RQSL_NR_HIST_BUCKETS ARRAY_SIZE(rqsl_hist_ms)
+
+enum rqsl_context {
+	RQSL_CTX_NORMAL = 0,
+	RQSL_CTX_NMI,
+	RQSL_CTX_MAX,
+};
+
+struct rqsl_cpu_hist {
+	atomic64_t hist[RQSL_CTX_MAX][RQSL_NR_HIST_BUCKETS];
+	atomic64_t success[RQSL_CTX_MAX];
+	atomic64_t failure[RQSL_CTX_MAX];
+};
+
+static DEFINE_PER_CPU(struct rqsl_cpu_hist, rqsl_cpu_hists);
+
+enum rqsl_mode {
+	RQSL_MODE_AA = 0,
+	RQSL_MODE_ABBA,
+	RQSL_MODE_ABBCCA,
+};
+
+static int test_mode = RQSL_MODE_AA;
+module_param(test_mode, int, 0644);
+MODULE_PARM_DESC(test_mode,
+		 "rqspinlock test mode: 0 = AA, 1 = ABBA, 2 = ABBCCA");
+
+static int normal_delay = 20;
+module_param(normal_delay, int, 0644);
+MODULE_PARM_DESC(normal_delay,
+		 "rqspinlock critical section length for normal context (20ms default)");
+
+static int nmi_delay = 10;
+module_param(nmi_delay, int, 0644);
+MODULE_PARM_DESC(nmi_delay,
+		 "rqspinlock critical section length for NMI context (10ms default)");
+
+static struct perf_event **rqsl_evts;
+static int rqsl_nevts;
+
+static struct task_struct **rqsl_threads;
+static int rqsl_nthreads;
+static atomic_t rqsl_ready_cpus = ATOMIC_INIT(0);
+
+static int pause = 0;
+
+static const char *rqsl_mode_names[] = {
+	[RQSL_MODE_AA] = "AA",
+	[RQSL_MODE_ABBA] = "ABBA",
+	[RQSL_MODE_ABBCCA] = "ABBCCA",
+};
+
+struct rqsl_lock_pair {
+	rqspinlock_t *worker_lock;
+	rqspinlock_t *nmi_lock;
+};
+
+static struct rqsl_lock_pair rqsl_get_lock_pair(int cpu)
+{
+	int mode = READ_ONCE(test_mode);
+
+	switch (mode) {
+	default:
+	case RQSL_MODE_AA:
+		return (struct rqsl_lock_pair){ &lock_a, &lock_a };
+	case RQSL_MODE_ABBA:
+		if (cpu & 1)
+			return (struct rqsl_lock_pair){ &lock_b, &lock_a };
+		return (struct rqsl_lock_pair){ &lock_a, &lock_b };
+	case RQSL_MODE_ABBCCA:
+		switch (cpu % 3) {
+		case 0:
+			return (struct rqsl_lock_pair){ &lock_a, &lock_b };
+		case 1:
+			return (struct rqsl_lock_pair){ &lock_b, &lock_c };
+		default:
+			return (struct rqsl_lock_pair){ &lock_c, &lock_a };
+		}
+	}
+}
+
+static u32 rqsl_hist_bucket_idx(u32 delta_ms)
+{
+	int i;
+
+	for (i = 0; i < RQSL_NR_HIST_BUCKETS; i++) {
+		if (delta_ms <= rqsl_hist_ms[i])
+			return i;
+	}
+
+	return RQSL_NR_HIST_BUCKETS - 1;
+}
+
+static void rqsl_record_lock_result(u64 delta_ns, enum rqsl_context ctx, int ret)
+{
+	struct rqsl_cpu_hist *hist = this_cpu_ptr(&rqsl_cpu_hists);
+	u32 delta_ms = DIV_ROUND_UP_ULL(delta_ns, NSEC_PER_MSEC);
+	u32 bucket = rqsl_hist_bucket_idx(delta_ms);
+	atomic64_t *buckets = hist->hist[ctx];
+
+	atomic64_inc(&buckets[bucket]);
+	if (!ret)
+		atomic64_inc(&hist->success[ctx]);
+	else
+		atomic64_inc(&hist->failure[ctx]);
+}
+
+static int rqspinlock_worker_fn(void *arg)
+{
+	int cpu = smp_processor_id();
+	unsigned long flags;
+	u64 start_ns;
+	int ret;
+
+	if (cpu) {
+		atomic_inc(&rqsl_ready_cpus);
+
+		while (!kthread_should_stop()) {
+			struct rqsl_lock_pair locks = rqsl_get_lock_pair(cpu);
+			rqspinlock_t *worker_lock = locks.worker_lock;
+
+			if (READ_ONCE(pause)) {
+				msleep(1000);
+				continue;
+			}
+			start_ns = ktime_get_mono_fast_ns();
+			ret = raw_res_spin_lock_irqsave(worker_lock, flags);
+			rqsl_record_lock_result(ktime_get_mono_fast_ns() - start_ns,
+						RQSL_CTX_NORMAL, ret);
+			mdelay(normal_delay);
+			if (!ret)
+				raw_res_spin_unlock_irqrestore(worker_lock, flags);
+			cpu_relax();
+		}
+		return 0;
+	}
+
+	while (!kthread_should_stop()) {
+		int expected = rqsl_nthreads > 0 ? rqsl_nthreads - 1 : 0;
+		int ready = atomic_read(&rqsl_ready_cpus);
+
+		if (ready == expected && !READ_ONCE(pause)) {
+			for (int i = 0; i < rqsl_nevts; i++)
+				perf_event_enable(rqsl_evts[i]);
+			pr_err("Waiting 5 secs to pause the test\n");
+			msleep(1000 * 5);
+			WRITE_ONCE(pause, 1);
+			pr_err("Paused the test\n");
+		} else {
+			msleep(1000);
+			cpu_relax();
+		}
+	}
+	return 0;
+}
+
+static void nmi_cb(struct perf_event *event, struct perf_sample_data *data,
+		   struct pt_regs *regs)
+{
+	struct rqsl_lock_pair locks;
+	int cpu = smp_processor_id();
+	unsigned long flags;
+	u64 start_ns;
+	int ret;
+
+	if (!cpu || READ_ONCE(pause))
+		return;
+
+	locks = rqsl_get_lock_pair(cpu);
+	start_ns = ktime_get_mono_fast_ns();
+	ret = raw_res_spin_lock_irqsave(locks.nmi_lock, flags);
+	rqsl_record_lock_result(ktime_get_mono_fast_ns() - start_ns,
+				RQSL_CTX_NMI, ret);
+
+	mdelay(nmi_delay);
+
+	if (!ret)
+		raw_res_spin_unlock_irqrestore(locks.nmi_lock, flags);
+}
+
+static void free_rqsl_threads(void)
+{
+	int i;
+
+	if (rqsl_threads) {
+		for_each_online_cpu(i) {
+			if (rqsl_threads[i])
+				kthread_stop(rqsl_threads[i]);
+		}
+		kfree(rqsl_threads);
+	}
+}
+
+static void free_rqsl_evts(void)
+{
+	int i;
+
+	if (rqsl_evts) {
+		for (i = 0; i < rqsl_nevts; i++) {
+			if (rqsl_evts[i])
+				perf_event_release_kernel(rqsl_evts[i]);
+		}
+		kfree(rqsl_evts);
+	}
+}
+
+static int bpf_test_rqspinlock_init(void)
+{
+	int i, ret;
+	int ncpus = num_online_cpus();
+
+	if (test_mode < RQSL_MODE_AA || test_mode > RQSL_MODE_ABBCCA) {
+		pr_err("Invalid mode %d\n", test_mode);
+		return -EINVAL;
+	}
+
+	pr_err("Mode = %s\n", rqsl_mode_names[test_mode]);
+
+	if (ncpus < test_mode + 2)
+		return -ENOTSUPP;
+
+	raw_res_spin_lock_init(&lock_a);
+	raw_res_spin_lock_init(&lock_b);
+	raw_res_spin_lock_init(&lock_c);
+
+	rqsl_evts = kcalloc(ncpus - 1, sizeof(*rqsl_evts), GFP_KERNEL);
+	if (!rqsl_evts)
+		return -ENOMEM;
+	rqsl_nevts = ncpus - 1;
+
+	for (i = 1; i < ncpus; i++) {
+		struct perf_event *e;
+
+		e = perf_event_create_kernel_counter(&hw_attr, i, NULL, nmi_cb, NULL);
+		if (IS_ERR(e)) {
+			ret = PTR_ERR(e);
+			goto err_perf_events;
+		}
+		rqsl_evts[i - 1] = e;
+	}
+
+	rqsl_threads = kcalloc(ncpus, sizeof(*rqsl_threads), GFP_KERNEL);
+	if (!rqsl_threads) {
+		ret = -ENOMEM;
+		goto err_perf_events;
+	}
+	rqsl_nthreads = ncpus;
+
+	for_each_online_cpu(i) {
+		struct task_struct *t;
+
+		t = kthread_create(rqspinlock_worker_fn, NULL, "rqsl_w/%d", i);
+		if (IS_ERR(t)) {
+			ret = PTR_ERR(t);
+			goto err_threads_create;
+		}
+		kthread_bind(t, i);
+		rqsl_threads[i] = t;
+		wake_up_process(t);
+	}
+	return 0;
+
+err_threads_create:
+	free_rqsl_threads();
+err_perf_events:
+	free_rqsl_evts();
+	return ret;
+}
+
+module_init(bpf_test_rqspinlock_init);
+
+static void rqsl_print_histograms(void)
+{
+	int cpu, i;
+
+	pr_err("rqspinlock acquisition latency histogram (ms):\n");
+
+	for_each_online_cpu(cpu) {
+		struct rqsl_cpu_hist *hist = per_cpu_ptr(&rqsl_cpu_hists, cpu);
+		u64 norm_counts[RQSL_NR_HIST_BUCKETS];
+		u64 nmi_counts[RQSL_NR_HIST_BUCKETS];
+		u64 total_counts[RQSL_NR_HIST_BUCKETS];
+		u64 norm_success, nmi_success, success_total;
+		u64 norm_failure, nmi_failure, failure_total;
+		u64 norm_total = 0, nmi_total = 0, total = 0;
+		bool has_slow = false;
+
+		for (i = 0; i < RQSL_NR_HIST_BUCKETS; i++) {
+			norm_counts[i] = atomic64_read(&hist->hist[RQSL_CTX_NORMAL][i]);
+			nmi_counts[i] = atomic64_read(&hist->hist[RQSL_CTX_NMI][i]);
+			total_counts[i] = norm_counts[i] + nmi_counts[i];
+			norm_total += norm_counts[i];
+			nmi_total += nmi_counts[i];
+			total += total_counts[i];
+			if (rqsl_hist_ms[i] > RQSL_SLOW_THRESHOLD_MS &&
+			    total_counts[i])
+				has_slow = true;
+		}
+
+		norm_success = atomic64_read(&hist->success[RQSL_CTX_NORMAL]);
+		nmi_success = atomic64_read(&hist->success[RQSL_CTX_NMI]);
+		norm_failure = atomic64_read(&hist->failure[RQSL_CTX_NORMAL]);
+		nmi_failure = atomic64_read(&hist->failure[RQSL_CTX_NMI]);
+		success_total = norm_success + nmi_success;
+		failure_total = norm_failure + nmi_failure;
+
+		if (!total)
+			continue;
+
+		if (!has_slow) {
+			pr_err(" cpu%d: total %llu (normal %llu, nmi %llu) | "
+			       "success %llu (normal %llu, nmi %llu) | "
+			       "failure %llu (normal %llu, nmi %llu), all within 0-%ums\n",
+			       cpu, total, norm_total, nmi_total,
+			       success_total, norm_success, nmi_success,
+			       failure_total, norm_failure, nmi_failure,
+			       RQSL_SLOW_THRESHOLD_MS);
+			continue;
+		}
+
+		pr_err(" cpu%d: total %llu (normal %llu, nmi %llu) | "
+		       "success %llu (normal %llu, nmi %llu) | "
+		       "failure %llu (normal %llu, nmi %llu)\n",
+		       cpu, total, norm_total, nmi_total,
+		       success_total, norm_success, nmi_success,
+		       failure_total, norm_failure, nmi_failure);
+		for (i = 0; i < RQSL_NR_HIST_BUCKETS; i++) {
+			unsigned int start_ms;
+
+			if (!total_counts[i])
+				continue;
+
+			start_ms = i == 0 ? 0 : rqsl_hist_ms[i - 1] + 1;
+			if (i == RQSL_NR_HIST_BUCKETS - 1) {
+				pr_err("   >= %ums: total %llu (normal %llu, nmi %llu)\n",
+				       start_ms, total_counts[i],
+				       norm_counts[i], nmi_counts[i]);
+			} else {
+				pr_err("   %u-%ums: total %llu (normal %llu, nmi %llu)\n",
+				       start_ms, rqsl_hist_ms[i],
+				       total_counts[i],
+				       norm_counts[i], nmi_counts[i]);
+			}
+		}
+	}
+}
+
+static void bpf_test_rqspinlock_exit(void)
+{
+	WRITE_ONCE(pause, 1);
+	free_rqsl_threads();
+	free_rqsl_evts();
+	rqsl_print_histograms();
+}
+
+module_exit(bpf_test_rqspinlock_exit);
+
+MODULE_AUTHOR("Kumar Kartikeya Dwivedi");
+MODULE_DESCRIPTION("BPF rqspinlock stress test module");
+MODULE_LICENSE("GPL");
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h b/tools/testing/selftests/bpf/test_kmods/bpf_testmod-events.h
index 11ee801e75e7..aeef86b3da74 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod-events.h
@@ -34,6 +34,20 @@ DECLARE_TRACE(bpf_testmod_test_write_bare,
 	TP_ARGS(task, ctx)
 );
 
+/* Used in bpf_testmod_test_read() to test __nullable suffix */
+DECLARE_TRACE(bpf_testmod_test_nullable_bare,
+	TP_PROTO(struct bpf_testmod_test_read_ctx *ctx__nullable),
+	TP_ARGS(ctx__nullable)
+);
+
+struct sk_buff;
+
+DECLARE_TRACE(bpf_testmod_test_raw_tp_null,
+	TP_PROTO(struct sk_buff *skb),
+	TP_ARGS(skb)
+);
+
+
 #undef BPF_TESTMOD_DECLARE_TRACE
 #ifdef DECLARE_TRACE_WRITABLE
 #define BPF_TESTMOD_DECLARE_TRACE(call, proto, args, size) \
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
new file mode 100644
index 000000000000..1669a7eeda26
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
@@ -0,0 +1,1787 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/btf_ids.h>
+#include <linux/delay.h>
+#include <linux/error-injection.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/percpu-defs.h>
+#include <linux/sysfs.h>
+#include <linux/tracepoint.h>
+#include <linux/net.h>
+#include <linux/socket.h>
+#include <linux/nsproxy.h>
+#include <linux/inet.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/un.h>
+#include <linux/filter.h>
+#include <net/sock.h>
+#include <linux/namei.h>
+#include "bpf_testmod.h"
+#include "bpf_testmod_kfunc.h"
+
+#define CREATE_TRACE_POINTS
+#include "bpf_testmod-events.h"
+
+#define CONNECT_TIMEOUT_SEC 1
+
+typedef int (*func_proto_typedef)(long);
+typedef int (*func_proto_typedef_nested1)(func_proto_typedef);
+typedef int (*func_proto_typedef_nested2)(func_proto_typedef_nested1);
+
+DEFINE_PER_CPU(int, bpf_testmod_ksym_percpu) = 123;
+long bpf_testmod_test_struct_arg_result;
+static DEFINE_MUTEX(sock_lock);
+static struct socket *sock;
+
+struct bpf_testmod_struct_arg_1 {
+	int a;
+};
+struct bpf_testmod_struct_arg_2 {
+	long a;
+	long b;
+};
+
+struct bpf_testmod_struct_arg_3 {
+	int a;
+	int b[];
+};
+
+struct bpf_testmod_struct_arg_4 {
+	u64 a;
+	int b;
+};
+
+struct bpf_testmod_struct_arg_5 {
+	char a;
+	short b;
+	int c;
+	long d;
+};
+
+union bpf_testmod_union_arg_1 {
+	char a;
+	short b;
+	struct bpf_testmod_struct_arg_1 arg;
+};
+
+union bpf_testmod_union_arg_2 {
+	int a;
+	long b;
+	struct bpf_testmod_struct_arg_2 arg;
+};
+
+__bpf_hook_start();
+
+noinline int
+bpf_testmod_test_struct_arg_1(struct bpf_testmod_struct_arg_2 a, int b, int c) {
+	bpf_testmod_test_struct_arg_result = a.a + a.b  + b + c;
+	return bpf_testmod_test_struct_arg_result;
+}
+
+noinline int
+bpf_testmod_test_struct_arg_2(int a, struct bpf_testmod_struct_arg_2 b, int c) {
+	bpf_testmod_test_struct_arg_result = a + b.a + b.b + c;
+	return bpf_testmod_test_struct_arg_result;
+}
+
+noinline int
+bpf_testmod_test_struct_arg_3(int a, int b, struct bpf_testmod_struct_arg_2 c) {
+	bpf_testmod_test_struct_arg_result = a + b + c.a + c.b;
+	return bpf_testmod_test_struct_arg_result;
+}
+
+noinline int
+bpf_testmod_test_struct_arg_4(struct bpf_testmod_struct_arg_1 a, int b,
+			      int c, int d, struct bpf_testmod_struct_arg_2 e) {
+	bpf_testmod_test_struct_arg_result = a.a + b + c + d + e.a + e.b;
+	return bpf_testmod_test_struct_arg_result;
+}
+
+noinline int
+bpf_testmod_test_struct_arg_5(void) {
+	bpf_testmod_test_struct_arg_result = 1;
+	return bpf_testmod_test_struct_arg_result;
+}
+
+noinline int
+bpf_testmod_test_struct_arg_6(struct bpf_testmod_struct_arg_3 *a) {
+	bpf_testmod_test_struct_arg_result = a->b[0];
+	return bpf_testmod_test_struct_arg_result;
+}
+
+noinline int
+bpf_testmod_test_struct_arg_7(u64 a, void *b, short c, int d, void *e,
+			      struct bpf_testmod_struct_arg_4 f)
+{
+	bpf_testmod_test_struct_arg_result = a + (long)b + c + d +
+		(long)e + f.a + f.b;
+	return bpf_testmod_test_struct_arg_result;
+}
+
+noinline int
+bpf_testmod_test_struct_arg_8(u64 a, void *b, short c, int d, void *e,
+			      struct bpf_testmod_struct_arg_4 f, int g)
+{
+	bpf_testmod_test_struct_arg_result = a + (long)b + c + d +
+		(long)e + f.a + f.b + g;
+	return bpf_testmod_test_struct_arg_result;
+}
+
+noinline int
+bpf_testmod_test_struct_arg_9(u64 a, void *b, short c, int d, void *e, char f,
+			      short g, struct bpf_testmod_struct_arg_5 h, long i)
+{
+	bpf_testmod_test_struct_arg_result = a + (long)b + c + d + (long)e +
+		f + g + h.a + h.b + h.c + h.d + i;
+	return bpf_testmod_test_struct_arg_result;
+}
+
+noinline int
+bpf_testmod_test_union_arg_1(union bpf_testmod_union_arg_1 a, int b, int c)
+{
+	bpf_testmod_test_struct_arg_result = a.arg.a + b + c;
+	return bpf_testmod_test_struct_arg_result;
+}
+
+noinline int
+bpf_testmod_test_union_arg_2(int a, union bpf_testmod_union_arg_2 b)
+{
+	bpf_testmod_test_struct_arg_result = a + b.arg.a + b.arg.b;
+	return bpf_testmod_test_struct_arg_result;
+}
+
+noinline int
+bpf_testmod_test_arg_ptr_to_struct(struct bpf_testmod_struct_arg_1 *a) {
+	bpf_testmod_test_struct_arg_result = a->a;
+	return bpf_testmod_test_struct_arg_result;
+}
+
+__weak noinline void bpf_testmod_looooooooooooooooooooooooooooooong_name(void)
+{
+}
+
+__bpf_kfunc void
+bpf_testmod_test_mod_kfunc(int i)
+{
+	*(int *)this_cpu_ptr(&bpf_testmod_ksym_percpu) = i;
+}
+
+__bpf_kfunc int bpf_iter_testmod_seq_new(struct bpf_iter_testmod_seq *it, s64 value, int cnt)
+{
+	it->cnt = cnt;
+
+	if (cnt < 0)
+		return -EINVAL;
+
+	it->value = value;
+
+	return 0;
+}
+
+__bpf_kfunc s64 *bpf_iter_testmod_seq_next(struct bpf_iter_testmod_seq* it)
+{
+	if (it->cnt <= 0)
+		return NULL;
+
+	it->cnt--;
+
+	return &it->value;
+}
+
+__bpf_kfunc s64 bpf_iter_testmod_seq_value(int val, struct bpf_iter_testmod_seq* it__iter)
+{
+	if (it__iter->cnt < 0)
+		return 0;
+
+	return val + it__iter->value;
+}
+
+__bpf_kfunc void bpf_iter_testmod_seq_destroy(struct bpf_iter_testmod_seq *it)
+{
+	it->cnt = 0;
+}
+
+__bpf_kfunc void bpf_kfunc_common_test(void)
+{
+}
+
+__bpf_kfunc void bpf_kfunc_dynptr_test(struct bpf_dynptr *ptr,
+				       struct bpf_dynptr *ptr__nullable)
+{
+}
+
+__bpf_kfunc struct sk_buff *bpf_kfunc_nested_acquire_nonzero_offset_test(struct sk_buff_head *ptr)
+{
+	return NULL;
+}
+
+__bpf_kfunc struct sk_buff *bpf_kfunc_nested_acquire_zero_offset_test(struct sock_common *ptr)
+{
+	return NULL;
+}
+
+__bpf_kfunc void bpf_kfunc_nested_release_test(struct sk_buff *ptr)
+{
+}
+
+__bpf_kfunc void bpf_kfunc_trusted_vma_test(struct vm_area_struct *ptr)
+{
+}
+
+__bpf_kfunc void bpf_kfunc_trusted_task_test(struct task_struct *ptr)
+{
+}
+
+__bpf_kfunc void bpf_kfunc_trusted_num_test(int *ptr)
+{
+}
+
+__bpf_kfunc void bpf_kfunc_rcu_task_test(struct task_struct *ptr)
+{
+}
+
+__bpf_kfunc struct task_struct *bpf_kfunc_ret_rcu_test(void)
+{
+	return NULL;
+}
+
+__bpf_kfunc int *bpf_kfunc_ret_rcu_test_nostruct(int rdonly_buf_size)
+{
+	return NULL;
+}
+
+__bpf_kfunc struct bpf_testmod_ctx *
+bpf_testmod_ctx_create(int *err)
+{
+	struct bpf_testmod_ctx *ctx;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC);
+	if (!ctx) {
+		*err = -ENOMEM;
+		return NULL;
+	}
+	refcount_set(&ctx->usage, 1);
+
+	return ctx;
+}
+
+static void testmod_free_cb(struct rcu_head *head)
+{
+	struct bpf_testmod_ctx *ctx;
+
+	ctx = container_of(head, struct bpf_testmod_ctx, rcu);
+	kfree(ctx);
+}
+
+__bpf_kfunc void bpf_testmod_ctx_release(struct bpf_testmod_ctx *ctx)
+{
+	if (!ctx)
+		return;
+	if (refcount_dec_and_test(&ctx->usage))
+		call_rcu(&ctx->rcu, testmod_free_cb);
+}
+
+static struct bpf_testmod_ops3 *st_ops3;
+
+static int bpf_testmod_test_3(void)
+{
+	return 0;
+}
+
+static int bpf_testmod_test_4(void)
+{
+	return 0;
+}
+
+static struct bpf_testmod_ops3 __bpf_testmod_ops3 = {
+	.test_1 = bpf_testmod_test_3,
+	.test_2 = bpf_testmod_test_4,
+};
+
+static void bpf_testmod_test_struct_ops3(void)
+{
+	if (st_ops3)
+		st_ops3->test_1();
+}
+
+__bpf_kfunc void bpf_testmod_ops3_call_test_1(void)
+{
+	st_ops3->test_1();
+}
+
+__bpf_kfunc void bpf_testmod_ops3_call_test_2(void)
+{
+	st_ops3->test_2();
+}
+
+struct bpf_testmod_btf_type_tag_1 {
+	int a;
+};
+
+struct bpf_testmod_btf_type_tag_2 {
+	struct bpf_testmod_btf_type_tag_1 __user *p;
+};
+
+struct bpf_testmod_btf_type_tag_3 {
+	struct bpf_testmod_btf_type_tag_1 __percpu *p;
+};
+
+noinline int
+bpf_testmod_test_btf_type_tag_user_1(struct bpf_testmod_btf_type_tag_1 __user *arg) {
+	BTF_TYPE_EMIT(func_proto_typedef);
+	BTF_TYPE_EMIT(func_proto_typedef_nested1);
+	BTF_TYPE_EMIT(func_proto_typedef_nested2);
+	return arg->a;
+}
+
+noinline int
+bpf_testmod_test_btf_type_tag_user_2(struct bpf_testmod_btf_type_tag_2 *arg) {
+	return arg->p->a;
+}
+
+noinline int
+bpf_testmod_test_btf_type_tag_percpu_1(struct bpf_testmod_btf_type_tag_1 __percpu *arg) {
+	return arg->a;
+}
+
+noinline int
+bpf_testmod_test_btf_type_tag_percpu_2(struct bpf_testmod_btf_type_tag_3 *arg) {
+	return arg->p->a;
+}
+
+noinline int bpf_testmod_loop_test(int n)
+{
+	/* Make sum volatile, so smart compilers, such as clang, will not
+	 * optimize the code by removing the loop.
+	 */
+	volatile int sum = 0;
+	int i;
+
+	/* the primary goal of this test is to test LBR. Create a lot of
+	 * branches in the function, so we can catch it easily.
+	 */
+	for (i = 0; i < n; i++)
+		sum += i;
+	return sum;
+}
+
+__weak noinline struct file *bpf_testmod_return_ptr(int arg)
+{
+	static struct file f = {};
+
+	switch (arg) {
+	case 1: return (void *)EINVAL;		/* user addr */
+	case 2: return (void *)0xcafe4a11;	/* user addr */
+	case 3: return (void *)-EINVAL;		/* canonical, but invalid */
+	case 4: return (void *)(1ull << 60);	/* non-canonical and invalid */
+	case 5: return (void *)~(1ull << 30);	/* trigger extable */
+	case 6: return &f;			/* valid addr */
+	case 7: return (void *)((long)&f | 1);	/* kernel tricks */
+#ifdef CONFIG_X86_64
+	case 8: return (void *)VSYSCALL_ADDR;   /* vsyscall page address */
+#endif
+	default: return NULL;
+	}
+}
+
+noinline int bpf_testmod_fentry_test1(int a)
+{
+	return a + 1;
+}
+
+noinline int bpf_testmod_fentry_test2(int a, u64 b)
+{
+	return a + b;
+}
+
+noinline int bpf_testmod_fentry_test3(char a, int b, u64 c)
+{
+	return a + b + c;
+}
+
+noinline int bpf_testmod_fentry_test7(u64 a, void *b, short c, int d,
+				      void *e, char f, int g)
+{
+	return a + (long)b + c + d + (long)e + f + g;
+}
+
+noinline int bpf_testmod_fentry_test11(u64 a, void *b, short c, int d,
+				       void *e, char f, int g,
+				       unsigned int h, long i, __u64 j,
+				       unsigned long k)
+{
+	return a + (long)b + c + d + (long)e + f + g + h + i + j + k;
+}
+
+noinline void bpf_testmod_stacktrace_test(void)
+{
+	/* used for stacktrace test as attach function */
+	asm volatile ("");
+}
+
+noinline void bpf_testmod_stacktrace_test_3(void)
+{
+	bpf_testmod_stacktrace_test();
+	asm volatile ("");
+}
+
+noinline void bpf_testmod_stacktrace_test_2(void)
+{
+	bpf_testmod_stacktrace_test_3();
+	asm volatile ("");
+}
+
+noinline void bpf_testmod_stacktrace_test_1(void)
+{
+	bpf_testmod_stacktrace_test_2();
+	asm volatile ("");
+}
+
+int bpf_testmod_fentry_ok;
+
+noinline ssize_t
+bpf_testmod_test_read(struct file *file, struct kobject *kobj,
+		      const struct bin_attribute *bin_attr,
+		      char *buf, loff_t off, size_t len)
+{
+	struct bpf_testmod_test_read_ctx ctx = {
+		.buf = buf,
+		.off = off,
+		.len = len,
+	};
+	struct bpf_testmod_struct_arg_1 struct_arg1 = {10}, struct_arg1_2 = {-1};
+	struct bpf_testmod_struct_arg_2 struct_arg2 = {2, 3};
+	struct bpf_testmod_struct_arg_3 *struct_arg3;
+	struct bpf_testmod_struct_arg_4 struct_arg4 = {21, 22};
+	struct bpf_testmod_struct_arg_5 struct_arg5 = {23, 24, 25, 26};
+	union bpf_testmod_union_arg_1 union_arg1 = { .arg = {1} };
+	union bpf_testmod_union_arg_2 union_arg2 = { .arg = {2, 3} };
+	int i = 1;
+
+	while (bpf_testmod_return_ptr(i))
+		i++;
+
+	(void)bpf_testmod_test_struct_arg_1(struct_arg2, 1, 4);
+	(void)bpf_testmod_test_struct_arg_2(1, struct_arg2, 4);
+	(void)bpf_testmod_test_struct_arg_3(1, 4, struct_arg2);
+	(void)bpf_testmod_test_struct_arg_4(struct_arg1, 1, 2, 3, struct_arg2);
+	(void)bpf_testmod_test_struct_arg_5();
+	(void)bpf_testmod_test_struct_arg_7(16, (void *)17, 18, 19,
+					    (void *)20, struct_arg4);
+	(void)bpf_testmod_test_struct_arg_8(16, (void *)17, 18, 19,
+					    (void *)20, struct_arg4, 23);
+	(void)bpf_testmod_test_struct_arg_9(16, (void *)17, 18, 19, (void *)20,
+					    21, 22, struct_arg5, 27);
+
+	(void)bpf_testmod_test_union_arg_1(union_arg1, 4, 5);
+	(void)bpf_testmod_test_union_arg_2(6, union_arg2);
+
+	(void)bpf_testmod_test_arg_ptr_to_struct(&struct_arg1_2);
+
+	(void)trace_bpf_testmod_test_raw_tp_null_tp(NULL);
+
+	bpf_testmod_test_struct_ops3();
+
+	struct_arg3 = kmalloc((sizeof(struct bpf_testmod_struct_arg_3) +
+				sizeof(int)), GFP_KERNEL);
+	if (struct_arg3 != NULL) {
+		struct_arg3->b[0] = 1;
+		(void)bpf_testmod_test_struct_arg_6(struct_arg3);
+		kfree(struct_arg3);
+	}
+
+	/* This is always true. Use the check to make sure the compiler
+	 * doesn't remove bpf_testmod_loop_test.
+	 */
+	if (bpf_testmod_loop_test(101) > 100)
+		trace_bpf_testmod_test_read(current, &ctx);
+
+	trace_bpf_testmod_test_nullable_bare_tp(NULL);
+
+	/* Magic number to enable writable tp */
+	if (len == 64) {
+		struct bpf_testmod_test_writable_ctx writable = {
+			.val = 1024,
+		};
+		trace_bpf_testmod_test_writable_bare_tp(&writable);
+		if (writable.early_ret)
+			return snprintf(buf, len, "%d\n", writable.val);
+	}
+
+	if (bpf_testmod_fentry_test1(1) != 2 ||
+	    bpf_testmod_fentry_test2(2, 3) != 5 ||
+	    bpf_testmod_fentry_test3(4, 5, 6) != 15 ||
+	    bpf_testmod_fentry_test7(16, (void *)17, 18, 19, (void *)20,
+			21, 22) != 133 ||
+	    bpf_testmod_fentry_test11(16, (void *)17, 18, 19, (void *)20,
+			21, 22, 23, 24, 25, 26) != 231)
+		goto out;
+
+	bpf_testmod_stacktrace_test_1();
+
+	bpf_testmod_fentry_ok = 1;
+out:
+	return -EIO; /* always fail */
+}
+EXPORT_SYMBOL(bpf_testmod_test_read);
+ALLOW_ERROR_INJECTION(bpf_testmod_test_read, ERRNO);
+
+noinline ssize_t
+bpf_testmod_test_write(struct file *file, struct kobject *kobj,
+		      const struct bin_attribute *bin_attr,
+		      char *buf, loff_t off, size_t len)
+{
+	struct bpf_testmod_test_write_ctx ctx = {
+		.buf = buf,
+		.off = off,
+		.len = len,
+	};
+
+	trace_bpf_testmod_test_write_bare_tp(current, &ctx);
+
+	return -EIO; /* always fail */
+}
+EXPORT_SYMBOL(bpf_testmod_test_write);
+ALLOW_ERROR_INJECTION(bpf_testmod_test_write, ERRNO);
+
+noinline int bpf_fentry_shadow_test(int a)
+{
+	return a + 2;
+}
+EXPORT_SYMBOL_GPL(bpf_fentry_shadow_test);
+
+__bpf_hook_end();
+
+static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = {
+	.attr = { .name = "bpf_testmod", .mode = 0666, },
+	.read = bpf_testmod_test_read,
+	.write = bpf_testmod_test_write,
+};
+
+/* bpf_testmod_uprobe sysfs attribute is so far enabled for x86_64 only,
+ * please see test_uretprobe_regs_change test
+ */
+#ifdef __x86_64__
+
+static int
+uprobe_handler(struct uprobe_consumer *self, struct pt_regs *regs, __u64 *data)
+{
+	regs->cx = 0x87654321feebdaed;
+	return 0;
+}
+
+static int
+uprobe_ret_handler(struct uprobe_consumer *self, unsigned long func,
+		   struct pt_regs *regs, __u64 *data)
+
+{
+	regs->ax  = 0x12345678deadbeef;
+	regs->r11 = (u64) -1;
+	return 0;
+}
+
+struct testmod_uprobe {
+	struct path path;
+	struct uprobe *uprobe;
+	struct uprobe_consumer consumer;
+};
+
+static DEFINE_MUTEX(testmod_uprobe_mutex);
+
+static struct testmod_uprobe uprobe = {
+	.consumer.handler = uprobe_handler,
+	.consumer.ret_handler = uprobe_ret_handler,
+};
+
+static int testmod_register_uprobe(loff_t offset)
+{
+	int err = -EBUSY;
+
+	if (uprobe.uprobe)
+		return -EBUSY;
+
+	mutex_lock(&testmod_uprobe_mutex);
+
+	if (uprobe.uprobe)
+		goto out;
+
+	err = kern_path("/proc/self/exe", LOOKUP_FOLLOW, &uprobe.path);
+	if (err)
+		goto out;
+
+	uprobe.uprobe = uprobe_register(d_real_inode(uprobe.path.dentry),
+					offset, 0, &uprobe.consumer);
+	if (IS_ERR(uprobe.uprobe)) {
+		err = PTR_ERR(uprobe.uprobe);
+		path_put(&uprobe.path);
+		uprobe.uprobe = NULL;
+	}
+out:
+	mutex_unlock(&testmod_uprobe_mutex);
+	return err;
+}
+
+static void testmod_unregister_uprobe(void)
+{
+	mutex_lock(&testmod_uprobe_mutex);
+
+	if (uprobe.uprobe) {
+		uprobe_unregister_nosync(uprobe.uprobe, &uprobe.consumer);
+		uprobe_unregister_sync();
+		path_put(&uprobe.path);
+		uprobe.uprobe = NULL;
+	}
+
+	mutex_unlock(&testmod_uprobe_mutex);
+}
+
+static ssize_t
+bpf_testmod_uprobe_write(struct file *file, struct kobject *kobj,
+			 const struct bin_attribute *bin_attr,
+			 char *buf, loff_t off, size_t len)
+{
+	unsigned long offset = 0;
+	int err = 0;
+
+	if (kstrtoul(buf, 0, &offset))
+		return -EINVAL;
+
+	if (offset)
+		err = testmod_register_uprobe(offset);
+	else
+		testmod_unregister_uprobe();
+
+	return err ?: strlen(buf);
+}
+
+static struct bin_attribute bin_attr_bpf_testmod_uprobe_file __ro_after_init = {
+	.attr = { .name = "bpf_testmod_uprobe", .mode = 0666, },
+	.write = bpf_testmod_uprobe_write,
+};
+
+static int register_bpf_testmod_uprobe(void)
+{
+	return sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_uprobe_file);
+}
+
+static void unregister_bpf_testmod_uprobe(void)
+{
+	testmod_unregister_uprobe();
+	sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_uprobe_file);
+}
+
+#else
+static int register_bpf_testmod_uprobe(void)
+{
+	return 0;
+}
+
+static void unregister_bpf_testmod_uprobe(void) { }
+#endif
+
+BTF_KFUNCS_START(bpf_testmod_common_kfunc_ids)
+BTF_ID_FLAGS(func, bpf_iter_testmod_seq_new, KF_ITER_NEW)
+BTF_ID_FLAGS(func, bpf_iter_testmod_seq_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_testmod_seq_destroy, KF_ITER_DESTROY)
+BTF_ID_FLAGS(func, bpf_iter_testmod_seq_value)
+BTF_ID_FLAGS(func, bpf_kfunc_common_test)
+BTF_ID_FLAGS(func, bpf_kfunc_dynptr_test)
+BTF_ID_FLAGS(func, bpf_kfunc_nested_acquire_nonzero_offset_test, KF_ACQUIRE)
+BTF_ID_FLAGS(func, bpf_kfunc_nested_acquire_zero_offset_test, KF_ACQUIRE)
+BTF_ID_FLAGS(func, bpf_kfunc_nested_release_test, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_kfunc_trusted_vma_test, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_kfunc_trusted_task_test, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_kfunc_trusted_num_test, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_kfunc_rcu_task_test, KF_RCU)
+BTF_ID_FLAGS(func, bpf_kfunc_ret_rcu_test, KF_RET_NULL | KF_RCU_PROTECTED)
+BTF_ID_FLAGS(func, bpf_kfunc_ret_rcu_test_nostruct, KF_RET_NULL | KF_RCU_PROTECTED)
+BTF_ID_FLAGS(func, bpf_testmod_ctx_create, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_testmod_ctx_release, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_testmod_ops3_call_test_1)
+BTF_ID_FLAGS(func, bpf_testmod_ops3_call_test_2)
+BTF_KFUNCS_END(bpf_testmod_common_kfunc_ids)
+
+BTF_ID_LIST(bpf_testmod_dtor_ids)
+BTF_ID(struct, bpf_testmod_ctx)
+BTF_ID(func, bpf_testmod_ctx_release)
+
+static const struct btf_kfunc_id_set bpf_testmod_common_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set   = &bpf_testmod_common_kfunc_ids,
+};
+
+__bpf_kfunc u64 bpf_kfunc_call_test1(struct sock *sk, u32 a, u64 b, u32 c, u64 d)
+{
+	return a + b + c + d;
+}
+
+__bpf_kfunc int bpf_kfunc_call_test2(struct sock *sk, u32 a, u32 b)
+{
+	return a + b;
+}
+
+__bpf_kfunc struct sock *bpf_kfunc_call_test3(struct sock *sk)
+{
+	return sk;
+}
+
+__bpf_kfunc long noinline bpf_kfunc_call_test4(signed char a, short b, int c, long d)
+{
+	/* Provoke the compiler to assume that the caller has sign-extended a,
+	 * b and c on platforms where this is required (e.g. s390x).
+	 */
+	return (long)a + (long)b + (long)c + d;
+}
+
+static struct prog_test_ref_kfunc prog_test_struct = {
+	.a = 42,
+	.b = 108,
+	.next = &prog_test_struct,
+	.cnt = REFCOUNT_INIT(1),
+};
+
+__bpf_kfunc struct prog_test_ref_kfunc *
+bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr)
+{
+	refcount_inc(&prog_test_struct.cnt);
+	return &prog_test_struct;
+}
+
+__bpf_kfunc void bpf_kfunc_call_test_offset(struct prog_test_ref_kfunc *p)
+{
+	WARN_ON_ONCE(1);
+}
+
+__bpf_kfunc struct prog_test_member *
+bpf_kfunc_call_memb_acquire(void)
+{
+	WARN_ON_ONCE(1);
+	return NULL;
+}
+
+__bpf_kfunc void bpf_kfunc_call_memb1_release(struct prog_test_member1 *p)
+{
+	WARN_ON_ONCE(1);
+}
+
+static int *__bpf_kfunc_call_test_get_mem(struct prog_test_ref_kfunc *p, const int size)
+{
+	if (size > 2 * sizeof(int))
+		return NULL;
+
+	return (int *)p;
+}
+
+__bpf_kfunc int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p,
+						  const int rdwr_buf_size)
+{
+	return __bpf_kfunc_call_test_get_mem(p, rdwr_buf_size);
+}
+
+__bpf_kfunc int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p,
+						    const int rdonly_buf_size)
+{
+	return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size);
+}
+
+/* the next 2 ones can't be really used for testing expect to ensure
+ * that the verifier rejects the call.
+ * Acquire functions must return struct pointers, so these ones are
+ * failing.
+ */
+__bpf_kfunc int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p,
+						    const int rdonly_buf_size)
+{
+	return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size);
+}
+
+__bpf_kfunc void bpf_kfunc_call_int_mem_release(int *p)
+{
+}
+
+__bpf_kfunc void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb)
+{
+}
+
+__bpf_kfunc void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p)
+{
+}
+
+__bpf_kfunc void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p)
+{
+}
+
+__bpf_kfunc void bpf_kfunc_call_test_fail1(struct prog_test_fail1 *p)
+{
+}
+
+__bpf_kfunc void bpf_kfunc_call_test_fail2(struct prog_test_fail2 *p)
+{
+}
+
+__bpf_kfunc void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p)
+{
+}
+
+__bpf_kfunc void bpf_kfunc_call_test_mem_len_pass1(void *mem, int mem__sz)
+{
+}
+
+__bpf_kfunc void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len)
+{
+}
+
+__bpf_kfunc void bpf_kfunc_call_test_mem_len_fail2(u64 *mem, int len)
+{
+}
+
+__bpf_kfunc void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p)
+{
+	/* p != NULL, but p->cnt could be 0 */
+}
+
+__bpf_kfunc void bpf_kfunc_call_test_destructive(void)
+{
+}
+
+__bpf_kfunc static u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused)
+{
+	return arg;
+}
+
+__bpf_kfunc void bpf_kfunc_call_test_sleepable(void)
+{
+}
+
+__bpf_kfunc int bpf_kfunc_init_sock(struct init_sock_args *args)
+{
+	int proto;
+	int err;
+
+	mutex_lock(&sock_lock);
+
+	if (sock) {
+		pr_err("%s called without releasing old sock", __func__);
+		err = -EPERM;
+		goto out;
+	}
+
+	switch (args->af) {
+	case AF_INET:
+	case AF_INET6:
+		proto = args->type == SOCK_STREAM ? IPPROTO_TCP : IPPROTO_UDP;
+		break;
+	case AF_UNIX:
+		proto = PF_UNIX;
+		break;
+	default:
+		pr_err("invalid address family %d\n", args->af);
+		err = -EINVAL;
+		goto out;
+	}
+
+	err = sock_create_kern(current->nsproxy->net_ns, args->af, args->type,
+			       proto, &sock);
+
+	if (!err)
+		/* Set timeout for call to kernel_connect() to prevent it from hanging,
+		 * and consider the connection attempt failed if it returns
+		 * -EINPROGRESS.
+		 */
+		sock->sk->sk_sndtimeo = CONNECT_TIMEOUT_SEC * HZ;
+out:
+	mutex_unlock(&sock_lock);
+
+	return err;
+}
+
+__bpf_kfunc void bpf_kfunc_close_sock(void)
+{
+	mutex_lock(&sock_lock);
+
+	if (sock) {
+		sock_release(sock);
+		sock = NULL;
+	}
+
+	mutex_unlock(&sock_lock);
+}
+
+__bpf_kfunc int bpf_kfunc_call_kernel_connect(struct addr_args *args)
+{
+	int err;
+
+	if (args->addrlen > sizeof(args->addr))
+		return -EINVAL;
+
+	mutex_lock(&sock_lock);
+
+	if (!sock) {
+		pr_err("%s called without initializing sock", __func__);
+		err = -EPERM;
+		goto out;
+	}
+
+	err = kernel_connect(sock, (struct sockaddr_unsized *)&args->addr,
+			     args->addrlen, 0);
+out:
+	mutex_unlock(&sock_lock);
+
+	return err;
+}
+
+__bpf_kfunc int bpf_kfunc_call_kernel_bind(struct addr_args *args)
+{
+	int err;
+
+	if (args->addrlen > sizeof(args->addr))
+		return -EINVAL;
+
+	mutex_lock(&sock_lock);
+
+	if (!sock) {
+		pr_err("%s called without initializing sock", __func__);
+		err = -EPERM;
+		goto out;
+	}
+
+	err = kernel_bind(sock, (struct sockaddr_unsized *)&args->addr, args->addrlen);
+out:
+	mutex_unlock(&sock_lock);
+
+	return err;
+}
+
+__bpf_kfunc int bpf_kfunc_call_kernel_listen(void)
+{
+	int err;
+
+	mutex_lock(&sock_lock);
+
+	if (!sock) {
+		pr_err("%s called without initializing sock", __func__);
+		err = -EPERM;
+		goto out;
+	}
+
+	err = kernel_listen(sock, 128);
+out:
+	mutex_unlock(&sock_lock);
+
+	return err;
+}
+
+__bpf_kfunc int bpf_kfunc_call_kernel_sendmsg(struct sendmsg_args *args)
+{
+	struct msghdr msg = {
+		.msg_name	= &args->addr.addr,
+		.msg_namelen	= args->addr.addrlen,
+	};
+	struct kvec iov;
+	int err;
+
+	if (args->addr.addrlen > sizeof(args->addr.addr) ||
+	    args->msglen > sizeof(args->msg))
+		return -EINVAL;
+
+	iov.iov_base = args->msg;
+	iov.iov_len  = args->msglen;
+
+	mutex_lock(&sock_lock);
+
+	if (!sock) {
+		pr_err("%s called without initializing sock", __func__);
+		err = -EPERM;
+		goto out;
+	}
+
+	err = kernel_sendmsg(sock, &msg, &iov, 1, args->msglen);
+	args->addr.addrlen = msg.msg_namelen;
+out:
+	mutex_unlock(&sock_lock);
+
+	return err;
+}
+
+__bpf_kfunc int bpf_kfunc_call_sock_sendmsg(struct sendmsg_args *args)
+{
+	struct msghdr msg = {
+		.msg_name	= &args->addr.addr,
+		.msg_namelen	= args->addr.addrlen,
+	};
+	struct kvec iov;
+	int err;
+
+	if (args->addr.addrlen > sizeof(args->addr.addr) ||
+	    args->msglen > sizeof(args->msg))
+		return -EINVAL;
+
+	iov.iov_base = args->msg;
+	iov.iov_len  = args->msglen;
+
+	iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &iov, 1, args->msglen);
+	mutex_lock(&sock_lock);
+
+	if (!sock) {
+		pr_err("%s called without initializing sock", __func__);
+		err = -EPERM;
+		goto out;
+	}
+
+	err = sock_sendmsg(sock, &msg);
+	args->addr.addrlen = msg.msg_namelen;
+out:
+	mutex_unlock(&sock_lock);
+
+	return err;
+}
+
+__bpf_kfunc int bpf_kfunc_call_kernel_getsockname(struct addr_args *args)
+{
+	int err;
+
+	mutex_lock(&sock_lock);
+
+	if (!sock) {
+		pr_err("%s called without initializing sock", __func__);
+		err = -EPERM;
+		goto out;
+	}
+
+	err = kernel_getsockname(sock, (struct sockaddr *)&args->addr);
+	if (err < 0)
+		goto out;
+
+	args->addrlen = err;
+	err = 0;
+out:
+	mutex_unlock(&sock_lock);
+
+	return err;
+}
+
+__bpf_kfunc int bpf_kfunc_call_kernel_getpeername(struct addr_args *args)
+{
+	int err;
+
+	mutex_lock(&sock_lock);
+
+	if (!sock) {
+		pr_err("%s called without initializing sock", __func__);
+		err = -EPERM;
+		goto out;
+	}
+
+	err = kernel_getpeername(sock, (struct sockaddr *)&args->addr);
+	if (err < 0)
+		goto out;
+
+	args->addrlen = err;
+	err = 0;
+out:
+	mutex_unlock(&sock_lock);
+
+	return err;
+}
+
+static DEFINE_MUTEX(st_ops_mutex);
+static struct bpf_testmod_st_ops *st_ops;
+
+__bpf_kfunc int bpf_kfunc_st_ops_test_prologue(struct st_ops_args *args)
+{
+	int ret = -1;
+
+	mutex_lock(&st_ops_mutex);
+	if (st_ops && st_ops->test_prologue)
+		ret = st_ops->test_prologue(args);
+	mutex_unlock(&st_ops_mutex);
+
+	return ret;
+}
+
+__bpf_kfunc int bpf_kfunc_st_ops_test_epilogue(struct st_ops_args *args)
+{
+	int ret = -1;
+
+	mutex_lock(&st_ops_mutex);
+	if (st_ops && st_ops->test_epilogue)
+		ret = st_ops->test_epilogue(args);
+	mutex_unlock(&st_ops_mutex);
+
+	return ret;
+}
+
+__bpf_kfunc int bpf_kfunc_st_ops_test_pro_epilogue(struct st_ops_args *args)
+{
+	int ret = -1;
+
+	mutex_lock(&st_ops_mutex);
+	if (st_ops && st_ops->test_pro_epilogue)
+		ret = st_ops->test_pro_epilogue(args);
+	mutex_unlock(&st_ops_mutex);
+
+	return ret;
+}
+
+__bpf_kfunc int bpf_kfunc_st_ops_inc10(struct st_ops_args *args)
+{
+	args->a += 10;
+	return args->a;
+}
+
+__bpf_kfunc int bpf_kfunc_multi_st_ops_test_1(struct st_ops_args *args, u32 id);
+
+BTF_KFUNCS_START(bpf_testmod_check_kfunc_ids)
+BTF_ID_FLAGS(func, bpf_testmod_test_mod_kfunc)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test1)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test2)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test3)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test4)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_pass1)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail1)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail2)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_acquire, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_kfunc_call_memb_acquire, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_kfunc_call_memb1_release, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_get_rdwr_mem, KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_get_rdonly_mem, KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_acq_rdonly_mem, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_kfunc_call_int_mem_release, KF_RELEASE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass_ctx)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass1)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_pass2)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail1)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail2)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_fail3)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_ref, KF_TRUSTED_ARGS | KF_RCU)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_destructive, KF_DESTRUCTIVE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_static_unused_arg)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_offset)
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_sleepable, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_init_sock, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_close_sock, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_connect, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_bind, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_listen, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_sendmsg, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_sock_sendmsg, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_getsockname, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_call_kernel_getpeername, KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_st_ops_test_prologue, KF_TRUSTED_ARGS | KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_st_ops_test_epilogue, KF_TRUSTED_ARGS | KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_st_ops_test_pro_epilogue, KF_TRUSTED_ARGS | KF_SLEEPABLE)
+BTF_ID_FLAGS(func, bpf_kfunc_st_ops_inc10, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, bpf_kfunc_multi_st_ops_test_1, KF_TRUSTED_ARGS)
+BTF_KFUNCS_END(bpf_testmod_check_kfunc_ids)
+
+static int bpf_testmod_ops_init(struct btf *btf)
+{
+	return 0;
+}
+
+static bool bpf_testmod_ops_is_valid_access(int off, int size,
+					    enum bpf_access_type type,
+					    const struct bpf_prog *prog,
+					    struct bpf_insn_access_aux *info)
+{
+	return bpf_tracing_btf_ctx_access(off, size, type, prog, info);
+}
+
+static int bpf_testmod_ops_init_member(const struct btf_type *t,
+				       const struct btf_member *member,
+				       void *kdata, const void *udata)
+{
+	if (member->offset == offsetof(struct bpf_testmod_ops, data) * 8) {
+		/* For data fields, this function has to copy it and return
+		 * 1 to indicate that the data has been handled by the
+		 * struct_ops type, or the verifier will reject the map if
+		 * the value of the data field is not zero.
+		 */
+		((struct bpf_testmod_ops *)kdata)->data = ((struct bpf_testmod_ops *)udata)->data;
+		return 1;
+	}
+	return 0;
+}
+
+static const struct btf_kfunc_id_set bpf_testmod_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set   = &bpf_testmod_check_kfunc_ids,
+};
+
+static const struct bpf_verifier_ops bpf_testmod_verifier_ops = {
+	.get_func_proto	 = bpf_base_func_proto,
+	.is_valid_access = bpf_testmod_ops_is_valid_access,
+};
+
+static const struct bpf_verifier_ops bpf_testmod_verifier_ops3 = {
+	.is_valid_access = bpf_testmod_ops_is_valid_access,
+};
+
+static int bpf_dummy_reg(void *kdata, struct bpf_link *link)
+{
+	struct bpf_testmod_ops *ops = kdata;
+
+	if (ops->test_1)
+		ops->test_1();
+	/* Some test cases (ex. struct_ops_maybe_null) may not have test_2
+	 * initialized, so we need to check for NULL.
+	 */
+	if (ops->test_2)
+		ops->test_2(4, ops->data);
+
+	return 0;
+}
+
+static void bpf_dummy_unreg(void *kdata, struct bpf_link *link)
+{
+}
+
+static int bpf_testmod_test_1(void)
+{
+	return 0;
+}
+
+static void bpf_testmod_test_2(int a, int b)
+{
+}
+
+static int bpf_testmod_tramp(int value)
+{
+	return 0;
+}
+
+static int bpf_testmod_ops__test_maybe_null(int dummy,
+					    struct task_struct *task__nullable)
+{
+	return 0;
+}
+
+static int bpf_testmod_ops__test_refcounted(int dummy,
+					    struct task_struct *task__ref)
+{
+	return 0;
+}
+
+static struct task_struct *
+bpf_testmod_ops__test_return_ref_kptr(int dummy, struct task_struct *task__ref,
+				      struct cgroup *cgrp)
+{
+	return NULL;
+}
+
+static struct bpf_testmod_ops __bpf_testmod_ops = {
+	.test_1 = bpf_testmod_test_1,
+	.test_2 = bpf_testmod_test_2,
+	.test_maybe_null = bpf_testmod_ops__test_maybe_null,
+	.test_refcounted = bpf_testmod_ops__test_refcounted,
+	.test_return_ref_kptr = bpf_testmod_ops__test_return_ref_kptr,
+};
+
+struct bpf_struct_ops bpf_bpf_testmod_ops = {
+	.verifier_ops = &bpf_testmod_verifier_ops,
+	.init = bpf_testmod_ops_init,
+	.init_member = bpf_testmod_ops_init_member,
+	.reg = bpf_dummy_reg,
+	.unreg = bpf_dummy_unreg,
+	.cfi_stubs = &__bpf_testmod_ops,
+	.name = "bpf_testmod_ops",
+	.owner = THIS_MODULE,
+};
+
+static int bpf_dummy_reg2(void *kdata, struct bpf_link *link)
+{
+	struct bpf_testmod_ops2 *ops = kdata;
+
+	ops->test_1();
+	return 0;
+}
+
+static struct bpf_testmod_ops2 __bpf_testmod_ops2 = {
+	.test_1 = bpf_testmod_test_1,
+};
+
+struct bpf_struct_ops bpf_testmod_ops2 = {
+	.verifier_ops = &bpf_testmod_verifier_ops,
+	.init = bpf_testmod_ops_init,
+	.init_member = bpf_testmod_ops_init_member,
+	.reg = bpf_dummy_reg2,
+	.unreg = bpf_dummy_unreg,
+	.cfi_stubs = &__bpf_testmod_ops2,
+	.name = "bpf_testmod_ops2",
+	.owner = THIS_MODULE,
+};
+
+static int st_ops3_reg(void *kdata, struct bpf_link *link)
+{
+	int err = 0;
+
+	mutex_lock(&st_ops_mutex);
+	if (st_ops3) {
+		pr_err("st_ops has already been registered\n");
+		err = -EEXIST;
+		goto unlock;
+	}
+	st_ops3 = kdata;
+
+unlock:
+	mutex_unlock(&st_ops_mutex);
+	return err;
+}
+
+static void st_ops3_unreg(void *kdata, struct bpf_link *link)
+{
+	mutex_lock(&st_ops_mutex);
+	st_ops3 = NULL;
+	mutex_unlock(&st_ops_mutex);
+}
+
+static void test_1_recursion_detected(struct bpf_prog *prog)
+{
+	struct bpf_prog_stats *stats;
+
+	stats = this_cpu_ptr(prog->stats);
+	printk("bpf_testmod: oh no, recursing into test_1, recursion_misses %llu",
+	       u64_stats_read(&stats->misses));
+}
+
+static int st_ops3_check_member(const struct btf_type *t,
+				const struct btf_member *member,
+				const struct bpf_prog *prog)
+{
+	u32 moff = __btf_member_bit_offset(t, member) / 8;
+
+	switch (moff) {
+	case offsetof(struct bpf_testmod_ops3, test_1):
+		prog->aux->priv_stack_requested = true;
+		prog->aux->recursion_detected = test_1_recursion_detected;
+		fallthrough;
+	default:
+		break;
+	}
+	return 0;
+}
+
+struct bpf_struct_ops bpf_testmod_ops3 = {
+	.verifier_ops = &bpf_testmod_verifier_ops3,
+	.init = bpf_testmod_ops_init,
+	.init_member = bpf_testmod_ops_init_member,
+	.reg = st_ops3_reg,
+	.unreg = st_ops3_unreg,
+	.check_member = st_ops3_check_member,
+	.cfi_stubs = &__bpf_testmod_ops3,
+	.name = "bpf_testmod_ops3",
+	.owner = THIS_MODULE,
+};
+
+static int bpf_test_mod_st_ops__test_prologue(struct st_ops_args *args)
+{
+	return 0;
+}
+
+static int bpf_test_mod_st_ops__test_epilogue(struct st_ops_args *args)
+{
+	return 0;
+}
+
+static int bpf_test_mod_st_ops__test_pro_epilogue(struct st_ops_args *args)
+{
+	return 0;
+}
+
+static int bpf_cgroup_from_id_id;
+static int bpf_cgroup_release_id;
+
+static int st_ops_gen_prologue_with_kfunc(struct bpf_insn *insn_buf, bool direct_write,
+					  const struct bpf_prog *prog)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	/* r8 = r1; // r8 will be "u64 *ctx".
+	 * r1 = 0;
+	 * r0 = bpf_cgroup_from_id(r1);
+	 * if r0 != 0 goto pc+5;
+	 * r6 = r8[0]; // r6 will be "struct st_ops *args".
+	 * r7 = r6->a;
+	 * r7 += 1000;
+	 * r6->a = r7;
+	 * goto pc+2;
+	 * r1 = r0;
+	 * bpf_cgroup_release(r1);
+	 * r1 = r8;
+	 */
+	*insn++ = BPF_MOV64_REG(BPF_REG_8, BPF_REG_1);
+	*insn++ = BPF_MOV64_IMM(BPF_REG_1, 0);
+	*insn++ = BPF_CALL_KFUNC(0, bpf_cgroup_from_id_id);
+	*insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 5);
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_8, 0);
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_6, offsetof(struct st_ops_args, a));
+	*insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 1000);
+	*insn++ = BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_7, offsetof(struct st_ops_args, a));
+	*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 2);
+	*insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_0);
+	*insn++ = BPF_CALL_KFUNC(0, bpf_cgroup_release_id);
+	*insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_8);
+	*insn++ = prog->insnsi[0];
+
+	return insn - insn_buf;
+}
+
+static int st_ops_gen_epilogue_with_kfunc(struct bpf_insn *insn_buf, const struct bpf_prog *prog,
+					  s16 ctx_stack_off)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	/* r1 = 0;
+	 * r6 = 0;
+	 * r0 = bpf_cgroup_from_id(r1);
+	 * if r0 != 0 goto pc+6;
+	 * r1 = stack[ctx_stack_off]; // r1 will be "u64 *ctx"
+	 * r1 = r1[0]; // r1 will be "struct st_ops *args"
+	 * r6 = r1->a;
+	 * r6 += 10000;
+	 * r1->a = r6;
+	 * goto pc+2
+	 * r1 = r0;
+	 * bpf_cgroup_release(r1);
+	 * r0 = r6;
+	 * r0 *= 2;
+	 * BPF_EXIT;
+	 */
+	*insn++ = BPF_MOV64_IMM(BPF_REG_1, 0);
+	*insn++ = BPF_MOV64_IMM(BPF_REG_6, 0);
+	*insn++ = BPF_CALL_KFUNC(0, bpf_cgroup_from_id_id);
+	*insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 6);
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_FP, ctx_stack_off);
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0);
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, offsetof(struct st_ops_args, a));
+	*insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 10000);
+	*insn++ = BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, offsetof(struct st_ops_args, a));
+	*insn++ = BPF_JMP_IMM(BPF_JA, 0, 0, 2);
+	*insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_0);
+	*insn++ = BPF_CALL_KFUNC(0, bpf_cgroup_release_id);
+	*insn++ = BPF_MOV64_REG(BPF_REG_0, BPF_REG_6);
+	*insn++ = BPF_ALU64_IMM(BPF_MUL, BPF_REG_0, 2);
+	*insn++ = BPF_EXIT_INSN();
+
+	return insn - insn_buf;
+}
+
+#define KFUNC_PRO_EPI_PREFIX "test_kfunc_"
+static int st_ops_gen_prologue(struct bpf_insn *insn_buf, bool direct_write,
+			       const struct bpf_prog *prog)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	if (strcmp(prog->aux->attach_func_name, "test_prologue") &&
+	    strcmp(prog->aux->attach_func_name, "test_pro_epilogue"))
+		return 0;
+
+	if (!strncmp(prog->aux->name, KFUNC_PRO_EPI_PREFIX, strlen(KFUNC_PRO_EPI_PREFIX)))
+		return st_ops_gen_prologue_with_kfunc(insn_buf, direct_write, prog);
+
+	/* r6 = r1[0]; // r6 will be "struct st_ops *args". r1 is "u64 *ctx".
+	 * r7 = r6->a;
+	 * r7 += 1000;
+	 * r6->a = r7;
+	 */
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0);
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_6, offsetof(struct st_ops_args, a));
+	*insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 1000);
+	*insn++ = BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_7, offsetof(struct st_ops_args, a));
+	*insn++ = prog->insnsi[0];
+
+	return insn - insn_buf;
+}
+
+static int st_ops_gen_epilogue(struct bpf_insn *insn_buf, const struct bpf_prog *prog,
+			       s16 ctx_stack_off)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	if (strcmp(prog->aux->attach_func_name, "test_epilogue") &&
+	    strcmp(prog->aux->attach_func_name, "test_pro_epilogue"))
+		return 0;
+
+	if (!strncmp(prog->aux->name, KFUNC_PRO_EPI_PREFIX, strlen(KFUNC_PRO_EPI_PREFIX)))
+		return st_ops_gen_epilogue_with_kfunc(insn_buf, prog, ctx_stack_off);
+
+	/* r1 = stack[ctx_stack_off]; // r1 will be "u64 *ctx"
+	 * r1 = r1[0]; // r1 will be "struct st_ops *args"
+	 * r6 = r1->a;
+	 * r6 += 10000;
+	 * r1->a = r6;
+	 * r0 = r6;
+	 * r0 *= 2;
+	 * BPF_EXIT;
+	 */
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_FP, ctx_stack_off);
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0);
+	*insn++ = BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, offsetof(struct st_ops_args, a));
+	*insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 10000);
+	*insn++ = BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, offsetof(struct st_ops_args, a));
+	*insn++ = BPF_MOV64_REG(BPF_REG_0, BPF_REG_6);
+	*insn++ = BPF_ALU64_IMM(BPF_MUL, BPF_REG_0, 2);
+	*insn++ = BPF_EXIT_INSN();
+
+	return insn - insn_buf;
+}
+
+static int st_ops_btf_struct_access(struct bpf_verifier_log *log,
+				    const struct bpf_reg_state *reg,
+				    int off, int size)
+{
+	if (off < 0 || off + size > sizeof(struct st_ops_args))
+		return -EACCES;
+	return 0;
+}
+
+static const struct bpf_verifier_ops st_ops_verifier_ops = {
+	.is_valid_access = bpf_testmod_ops_is_valid_access,
+	.btf_struct_access = st_ops_btf_struct_access,
+	.gen_prologue = st_ops_gen_prologue,
+	.gen_epilogue = st_ops_gen_epilogue,
+	.get_func_proto = bpf_base_func_proto,
+};
+
+static struct bpf_testmod_st_ops st_ops_cfi_stubs = {
+	.test_prologue = bpf_test_mod_st_ops__test_prologue,
+	.test_epilogue = bpf_test_mod_st_ops__test_epilogue,
+	.test_pro_epilogue = bpf_test_mod_st_ops__test_pro_epilogue,
+};
+
+static int st_ops_reg(void *kdata, struct bpf_link *link)
+{
+	int err = 0;
+
+	mutex_lock(&st_ops_mutex);
+	if (st_ops) {
+		pr_err("st_ops has already been registered\n");
+		err = -EEXIST;
+		goto unlock;
+	}
+	st_ops = kdata;
+
+unlock:
+	mutex_unlock(&st_ops_mutex);
+	return err;
+}
+
+static void st_ops_unreg(void *kdata, struct bpf_link *link)
+{
+	mutex_lock(&st_ops_mutex);
+	st_ops = NULL;
+	mutex_unlock(&st_ops_mutex);
+}
+
+static int st_ops_init(struct btf *btf)
+{
+	struct btf *kfunc_btf;
+
+	bpf_cgroup_from_id_id = bpf_find_btf_id("bpf_cgroup_from_id", BTF_KIND_FUNC, &kfunc_btf);
+	bpf_cgroup_release_id = bpf_find_btf_id("bpf_cgroup_release", BTF_KIND_FUNC, &kfunc_btf);
+	if (bpf_cgroup_from_id_id < 0 || bpf_cgroup_release_id < 0)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int st_ops_init_member(const struct btf_type *t,
+			      const struct btf_member *member,
+			      void *kdata, const void *udata)
+{
+	return 0;
+}
+
+static struct bpf_struct_ops testmod_st_ops = {
+	.verifier_ops = &st_ops_verifier_ops,
+	.init = st_ops_init,
+	.init_member = st_ops_init_member,
+	.reg = st_ops_reg,
+	.unreg = st_ops_unreg,
+	.cfi_stubs = &st_ops_cfi_stubs,
+	.name = "bpf_testmod_st_ops",
+	.owner = THIS_MODULE,
+};
+
+struct hlist_head multi_st_ops_list;
+static DEFINE_SPINLOCK(multi_st_ops_lock);
+
+static int multi_st_ops_init(struct btf *btf)
+{
+	spin_lock_init(&multi_st_ops_lock);
+	INIT_HLIST_HEAD(&multi_st_ops_list);
+
+	return 0;
+}
+
+static int multi_st_ops_init_member(const struct btf_type *t,
+				    const struct btf_member *member,
+				    void *kdata, const void *udata)
+{
+	return 0;
+}
+
+static struct bpf_testmod_multi_st_ops *multi_st_ops_find_nolock(u32 id)
+{
+	struct bpf_testmod_multi_st_ops *st_ops;
+
+	hlist_for_each_entry(st_ops, &multi_st_ops_list, node) {
+		if (st_ops->id == id)
+			return st_ops;
+	}
+
+	return NULL;
+}
+
+int bpf_kfunc_multi_st_ops_test_1(struct st_ops_args *args, u32 id)
+{
+	struct bpf_testmod_multi_st_ops *st_ops;
+	unsigned long flags;
+	int ret = -1;
+
+	spin_lock_irqsave(&multi_st_ops_lock, flags);
+	st_ops = multi_st_ops_find_nolock(id);
+	if (st_ops)
+		ret = st_ops->test_1(args);
+	spin_unlock_irqrestore(&multi_st_ops_lock, flags);
+
+	return ret;
+}
+
+static int multi_st_ops_reg(void *kdata, struct bpf_link *link)
+{
+	struct bpf_testmod_multi_st_ops *st_ops =
+		(struct bpf_testmod_multi_st_ops *)kdata;
+	unsigned long flags;
+	int err = 0;
+	u32 id;
+
+	if (!st_ops->test_1)
+		return -EINVAL;
+
+	id = bpf_struct_ops_id(kdata);
+
+	spin_lock_irqsave(&multi_st_ops_lock, flags);
+	if (multi_st_ops_find_nolock(id)) {
+		pr_err("multi_st_ops(id:%d) has already been registered\n", id);
+		err = -EEXIST;
+		goto unlock;
+	}
+
+	st_ops->id = id;
+	hlist_add_head(&st_ops->node, &multi_st_ops_list);
+unlock:
+	spin_unlock_irqrestore(&multi_st_ops_lock, flags);
+
+	return err;
+}
+
+static void multi_st_ops_unreg(void *kdata, struct bpf_link *link)
+{
+	struct bpf_testmod_multi_st_ops *st_ops;
+	unsigned long flags;
+	u32 id;
+
+	id = bpf_struct_ops_id(kdata);
+
+	spin_lock_irqsave(&multi_st_ops_lock, flags);
+	st_ops = multi_st_ops_find_nolock(id);
+	if (st_ops)
+		hlist_del(&st_ops->node);
+	spin_unlock_irqrestore(&multi_st_ops_lock, flags);
+}
+
+static int bpf_testmod_multi_st_ops__test_1(struct st_ops_args *args)
+{
+	return 0;
+}
+
+static struct bpf_testmod_multi_st_ops multi_st_ops_cfi_stubs = {
+	.test_1 = bpf_testmod_multi_st_ops__test_1,
+};
+
+struct bpf_struct_ops testmod_multi_st_ops = {
+	.verifier_ops = &bpf_testmod_verifier_ops,
+	.init = multi_st_ops_init,
+	.init_member = multi_st_ops_init_member,
+	.reg = multi_st_ops_reg,
+	.unreg = multi_st_ops_unreg,
+	.cfi_stubs = &multi_st_ops_cfi_stubs,
+	.name = "bpf_testmod_multi_st_ops",
+	.owner = THIS_MODULE,
+};
+
+extern int bpf_fentry_test1(int a);
+
+static int bpf_testmod_init(void)
+{
+	const struct btf_id_dtor_kfunc bpf_testmod_dtors[] = {
+		{
+			.btf_id		= bpf_testmod_dtor_ids[0],
+			.kfunc_btf_id	= bpf_testmod_dtor_ids[1]
+		},
+	};
+	void **tramp;
+	int ret;
+
+	ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &bpf_testmod_common_kfunc_set);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_testmod_kfunc_set);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_testmod_kfunc_set);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &bpf_testmod_kfunc_set);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &bpf_testmod_kfunc_set);
+	ret = ret ?: register_bpf_struct_ops(&bpf_bpf_testmod_ops, bpf_testmod_ops);
+	ret = ret ?: register_bpf_struct_ops(&bpf_testmod_ops2, bpf_testmod_ops2);
+	ret = ret ?: register_bpf_struct_ops(&bpf_testmod_ops3, bpf_testmod_ops3);
+	ret = ret ?: register_bpf_struct_ops(&testmod_st_ops, bpf_testmod_st_ops);
+	ret = ret ?: register_bpf_struct_ops(&testmod_multi_st_ops, bpf_testmod_multi_st_ops);
+	ret = ret ?: register_btf_id_dtor_kfuncs(bpf_testmod_dtors,
+						 ARRAY_SIZE(bpf_testmod_dtors),
+						 THIS_MODULE);
+	if (ret < 0)
+		return ret;
+	if (bpf_fentry_test1(0) < 0)
+		return -EINVAL;
+	sock = NULL;
+	mutex_init(&sock_lock);
+	ret = sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
+	if (ret < 0)
+		return ret;
+	ret = register_bpf_testmod_uprobe();
+	if (ret < 0)
+		return ret;
+
+	/* Ensure nothing is between tramp_1..tramp_40 */
+	BUILD_BUG_ON(offsetof(struct bpf_testmod_ops, tramp_1) + 40 * sizeof(long) !=
+		     offsetofend(struct bpf_testmod_ops, tramp_40));
+	tramp = (void **)&__bpf_testmod_ops.tramp_1;
+	while (tramp <= (void **)&__bpf_testmod_ops.tramp_40)
+		*tramp++ = bpf_testmod_tramp;
+
+	return 0;
+}
+
+static void bpf_testmod_exit(void)
+{
+        /* Need to wait for all references to be dropped because
+         * bpf_kfunc_call_test_release() which currently resides in kernel can
+         * be called after bpf_testmod is unloaded. Once release function is
+         * moved into the module this wait can be removed.
+         */
+	while (refcount_read(&prog_test_struct.cnt) > 1)
+		msleep(20);
+
+	bpf_kfunc_close_sock();
+	sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
+	unregister_bpf_testmod_uprobe();
+}
+
+module_init(bpf_testmod_init);
+module_exit(bpf_testmod_exit);
+
+MODULE_AUTHOR("Andrii Nakryiko");
+MODULE_DESCRIPTION("BPF selftests module");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h
new file mode 100644
index 000000000000..f6e492f9d042
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h
@@ -0,0 +1,125 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2020 Facebook */
+#ifndef _BPF_TESTMOD_H
+#define _BPF_TESTMOD_H
+
+#include <linux/types.h>
+
+struct task_struct;
+struct cgroup;
+
+struct bpf_testmod_test_read_ctx {
+	char *buf;
+	loff_t off;
+	size_t len;
+};
+
+struct bpf_testmod_test_write_ctx {
+	char *buf;
+	loff_t off;
+	size_t len;
+};
+
+struct bpf_testmod_test_writable_ctx {
+	bool early_ret;
+	int val;
+};
+
+/* BPF iter that returns *value* *n* times in a row */
+struct bpf_iter_testmod_seq {
+	s64 value;
+	int cnt;
+};
+
+struct bpf_testmod_ops {
+	int (*test_1)(void);
+	void (*test_2)(int a, int b);
+	/* Used to test nullable arguments. */
+	int (*test_maybe_null)(int dummy, struct task_struct *task);
+	int (*unsupported_ops)(void);
+	/* Used to test ref_acquired arguments. */
+	int (*test_refcounted)(int dummy, struct task_struct *task);
+	/* Used to test returning referenced kptr. */
+	struct task_struct *(*test_return_ref_kptr)(int dummy, struct task_struct *task,
+						    struct cgroup *cgrp);
+
+	/* The following fields are used to test shadow copies. */
+	char onebyte;
+	struct {
+		int a;
+		int b;
+	} unsupported;
+	int data;
+
+	/* The following pointers are used to test the maps having multiple
+	 * pages of trampolines.
+	 */
+	int (*tramp_1)(int value);
+	int (*tramp_2)(int value);
+	int (*tramp_3)(int value);
+	int (*tramp_4)(int value);
+	int (*tramp_5)(int value);
+	int (*tramp_6)(int value);
+	int (*tramp_7)(int value);
+	int (*tramp_8)(int value);
+	int (*tramp_9)(int value);
+	int (*tramp_10)(int value);
+	int (*tramp_11)(int value);
+	int (*tramp_12)(int value);
+	int (*tramp_13)(int value);
+	int (*tramp_14)(int value);
+	int (*tramp_15)(int value);
+	int (*tramp_16)(int value);
+	int (*tramp_17)(int value);
+	int (*tramp_18)(int value);
+	int (*tramp_19)(int value);
+	int (*tramp_20)(int value);
+	int (*tramp_21)(int value);
+	int (*tramp_22)(int value);
+	int (*tramp_23)(int value);
+	int (*tramp_24)(int value);
+	int (*tramp_25)(int value);
+	int (*tramp_26)(int value);
+	int (*tramp_27)(int value);
+	int (*tramp_28)(int value);
+	int (*tramp_29)(int value);
+	int (*tramp_30)(int value);
+	int (*tramp_31)(int value);
+	int (*tramp_32)(int value);
+	int (*tramp_33)(int value);
+	int (*tramp_34)(int value);
+	int (*tramp_35)(int value);
+	int (*tramp_36)(int value);
+	int (*tramp_37)(int value);
+	int (*tramp_38)(int value);
+	int (*tramp_39)(int value);
+	int (*tramp_40)(int value);
+};
+
+struct bpf_testmod_ops2 {
+	int (*test_1)(void);
+};
+
+struct bpf_testmod_ops3 {
+	int (*test_1)(void);
+	int (*test_2)(void);
+};
+
+struct st_ops_args {
+	u64 a;
+};
+
+struct bpf_testmod_st_ops {
+	int (*test_prologue)(struct st_ops_args *args);
+	int (*test_epilogue)(struct st_ops_args *args);
+	int (*test_pro_epilogue)(struct st_ops_args *args);
+	struct module *owner;
+};
+
+struct bpf_testmod_multi_st_ops {
+	int (*test_1)(struct st_ops_args *args);
+	struct hlist_node node;
+	int id;
+};
+
+#endif /* _BPF_TESTMOD_H */
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h b/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h
new file mode 100644
index 000000000000..4df6fa6a92cb
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h
@@ -0,0 +1,166 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _BPF_TESTMOD_KFUNC_H
+#define _BPF_TESTMOD_KFUNC_H
+
+#ifndef __KERNEL__
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#else
+#define __ksym
+struct prog_test_member1 {
+	int a;
+};
+
+struct prog_test_member {
+	struct prog_test_member1 m;
+	int c;
+};
+
+struct prog_test_ref_kfunc {
+	int a;
+	int b;
+	struct prog_test_member memb;
+	struct prog_test_ref_kfunc *next;
+	refcount_t cnt;
+};
+#endif
+
+struct prog_test_pass1 {
+	int x0;
+	struct {
+		int x1;
+		struct {
+			int x2;
+			struct {
+				int x3;
+			};
+		};
+	};
+};
+
+struct prog_test_pass2 {
+	int len;
+	short arr1[4];
+	struct {
+		char arr2[4];
+		unsigned long arr3[8];
+	} x;
+};
+
+struct prog_test_fail1 {
+	void *p;
+	int x;
+};
+
+struct prog_test_fail2 {
+	int x8;
+	struct prog_test_pass1 x;
+};
+
+struct prog_test_fail3 {
+	int len;
+	char arr1[2];
+	char arr2[];
+};
+
+struct init_sock_args {
+	int af;
+	int type;
+};
+
+struct addr_args {
+	char addr[sizeof(struct __kernel_sockaddr_storage)];
+	int addrlen;
+};
+
+struct sendmsg_args {
+	struct addr_args addr;
+	char msg[10];
+	int msglen;
+};
+
+struct bpf_testmod_ctx {
+	struct callback_head	rcu;
+	refcount_t		usage;
+};
+
+struct prog_test_ref_kfunc *
+bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr) __ksym;
+void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) __ksym;
+void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p) __ksym;
+
+void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym;
+int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size) __ksym;
+int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym;
+int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym;
+void bpf_kfunc_call_int_mem_release(int *p) __ksym;
+
+/* The bpf_kfunc_call_test_static_unused_arg is defined as static,
+ * but bpf program compilation needs to see it as global symbol.
+ */
+#ifndef __KERNEL__
+u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused) __ksym;
+#endif
+
+void bpf_testmod_test_mod_kfunc(int i) __ksym;
+
+__u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b,
+				__u32 c, __u64 d) __ksym;
+int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym;
+struct sock *bpf_kfunc_call_test3(struct sock *sk) __ksym;
+long bpf_kfunc_call_test4(signed char a, short b, int c, long d) __ksym;
+
+void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) __ksym;
+void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) __ksym;
+void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) __ksym;
+void bpf_kfunc_call_test_mem_len_fail2(__u64 *mem, int len) __ksym;
+
+void bpf_kfunc_call_test_destructive(void) __ksym;
+void bpf_kfunc_call_test_sleepable(void) __ksym;
+
+void bpf_kfunc_call_test_offset(struct prog_test_ref_kfunc *p);
+struct prog_test_member *bpf_kfunc_call_memb_acquire(void);
+void bpf_kfunc_call_memb1_release(struct prog_test_member1 *p);
+void bpf_kfunc_call_test_fail1(struct prog_test_fail1 *p);
+void bpf_kfunc_call_test_fail2(struct prog_test_fail2 *p);
+void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p);
+void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len);
+
+void bpf_kfunc_common_test(void) __ksym;
+
+int bpf_kfunc_init_sock(struct init_sock_args *args) __ksym;
+void bpf_kfunc_close_sock(void) __ksym;
+int bpf_kfunc_call_kernel_connect(struct addr_args *args) __ksym;
+int bpf_kfunc_call_kernel_bind(struct addr_args *args) __ksym;
+int bpf_kfunc_call_kernel_listen(void) __ksym;
+int bpf_kfunc_call_kernel_sendmsg(struct sendmsg_args *args) __ksym;
+int bpf_kfunc_call_sock_sendmsg(struct sendmsg_args *args) __ksym;
+int bpf_kfunc_call_kernel_getsockname(struct addr_args *args) __ksym;
+int bpf_kfunc_call_kernel_getpeername(struct addr_args *args) __ksym;
+
+void bpf_kfunc_dynptr_test(struct bpf_dynptr *ptr, struct bpf_dynptr *ptr__nullable) __ksym;
+
+struct bpf_testmod_ctx *bpf_testmod_ctx_create(int *err) __ksym;
+void bpf_testmod_ctx_release(struct bpf_testmod_ctx *ctx) __ksym;
+
+struct sk_buff *bpf_kfunc_nested_acquire_nonzero_offset_test(struct sk_buff_head *ptr) __ksym;
+struct sk_buff *bpf_kfunc_nested_acquire_zero_offset_test(struct sock_common *ptr) __ksym;
+void bpf_kfunc_nested_release_test(struct sk_buff *ptr) __ksym;
+
+struct st_ops_args;
+int bpf_kfunc_st_ops_test_prologue(struct st_ops_args *args) __ksym;
+int bpf_kfunc_st_ops_test_epilogue(struct st_ops_args *args) __ksym;
+int bpf_kfunc_st_ops_test_pro_epilogue(struct st_ops_args *args) __ksym;
+int bpf_kfunc_st_ops_inc10(struct st_ops_args *args) __ksym;
+
+void bpf_kfunc_trusted_vma_test(struct vm_area_struct *ptr) __ksym;
+void bpf_kfunc_trusted_task_test(struct task_struct *ptr) __ksym;
+void bpf_kfunc_trusted_num_test(int *ptr) __ksym;
+void bpf_kfunc_rcu_task_test(struct task_struct *ptr) __ksym;
+struct task_struct *bpf_kfunc_ret_rcu_test(void) __ksym;
+int *bpf_kfunc_ret_rcu_test_nostruct(int rdonly_buf_size) __ksym;
+
+int bpf_kfunc_multi_st_ops_test_1(struct st_ops_args *args, u32 id) __ksym;
+
+#endif /* _BPF_TESTMOD_KFUNC_H */
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_user.c b/tools/testing/selftests/bpf/test_lirc_mode2_user.c
index 4694422aa76c..88e4aeab21b7 100644
--- a/tools/testing/selftests/bpf/test_lirc_mode2_user.c
+++ b/tools/testing/selftests/bpf/test_lirc_mode2_user.c
@@ -74,7 +74,7 @@ int main(int argc, char **argv)
 
 	/* Let's try detach it before it was ever attached */
 	ret = bpf_prog_detach2(progfd, lircfd, BPF_LIRC_MODE2);
-	if (ret != -1 || errno != ENOENT) {
+	if (ret != -ENOENT) {
 		printf("bpf_prog_detach2 not attached should fail: %m\n");
 		return 1;
 	}
diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
index 679efb3aa785..338c035c3688 100644
--- a/tools/testing/selftests/bpf/test_loader.c
+++ b/tools/testing/selftests/bpf/test_loader.c
@@ -1,31 +1,105 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+#include <linux/capability.h>
 #include <stdlib.h>
 #include <test_progs.h>
 #include <bpf/btf.h>
 
+#include "autoconf_helper.h"
+#include "disasm_helpers.h"
+#include "unpriv_helpers.h"
+#include "cap_helpers.h"
+#include "jit_disasm_helpers.h"
+
 #define str_has_pfx(str, pfx) \
 	(strncmp(str, pfx, __builtin_constant_p(pfx) ? sizeof(pfx) - 1 : strlen(pfx)) == 0)
 
-#define TEST_LOADER_LOG_BUF_SZ 1048576
+#define TEST_LOADER_LOG_BUF_SZ 2097152
 
 #define TEST_TAG_EXPECT_FAILURE "comment:test_expect_failure"
 #define TEST_TAG_EXPECT_SUCCESS "comment:test_expect_success"
 #define TEST_TAG_EXPECT_MSG_PFX "comment:test_expect_msg="
+#define TEST_TAG_EXPECT_NOT_MSG_PFX "comment:test_expect_not_msg="
+#define TEST_TAG_EXPECT_XLATED_PFX "comment:test_expect_xlated="
+#define TEST_TAG_EXPECT_FAILURE_UNPRIV "comment:test_expect_failure_unpriv"
+#define TEST_TAG_EXPECT_SUCCESS_UNPRIV "comment:test_expect_success_unpriv"
+#define TEST_TAG_EXPECT_MSG_PFX_UNPRIV "comment:test_expect_msg_unpriv="
+#define TEST_TAG_EXPECT_NOT_MSG_PFX_UNPRIV "comment:test_expect_not_msg_unpriv="
+#define TEST_TAG_EXPECT_XLATED_PFX_UNPRIV "comment:test_expect_xlated_unpriv="
 #define TEST_TAG_LOG_LEVEL_PFX "comment:test_log_level="
+#define TEST_TAG_PROG_FLAGS_PFX "comment:test_prog_flags="
+#define TEST_TAG_DESCRIPTION_PFX "comment:test_description="
+#define TEST_TAG_RETVAL_PFX "comment:test_retval="
+#define TEST_TAG_RETVAL_PFX_UNPRIV "comment:test_retval_unpriv="
+#define TEST_TAG_AUXILIARY "comment:test_auxiliary"
+#define TEST_TAG_AUXILIARY_UNPRIV "comment:test_auxiliary_unpriv"
+#define TEST_BTF_PATH "comment:test_btf_path="
+#define TEST_TAG_ARCH "comment:test_arch="
+#define TEST_TAG_JITED_PFX "comment:test_jited="
+#define TEST_TAG_JITED_PFX_UNPRIV "comment:test_jited_unpriv="
+#define TEST_TAG_CAPS_UNPRIV "comment:test_caps_unpriv="
+#define TEST_TAG_LOAD_MODE_PFX "comment:load_mode="
+#define TEST_TAG_EXPECT_STDERR_PFX "comment:test_expect_stderr="
+#define TEST_TAG_EXPECT_STDERR_PFX_UNPRIV "comment:test_expect_stderr_unpriv="
+#define TEST_TAG_EXPECT_STDOUT_PFX "comment:test_expect_stdout="
+#define TEST_TAG_EXPECT_STDOUT_PFX_UNPRIV "comment:test_expect_stdout_unpriv="
+#define TEST_TAG_LINEAR_SIZE "comment:test_linear_size="
 
-struct test_spec {
-	const char *name;
+/* Warning: duplicated in bpf_misc.h */
+#define POINTER_VALUE	0xbadcafe
+#define TEST_DATA_LEN	64
+
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+#define EFFICIENT_UNALIGNED_ACCESS 1
+#else
+#define EFFICIENT_UNALIGNED_ACCESS 0
+#endif
+
+static int sysctl_unpriv_disabled = -1;
+
+enum mode {
+	PRIV = 1,
+	UNPRIV = 2
+};
+
+enum load_mode {
+	JITED		= 1 << 0,
+	NO_JITED	= 1 << 1,
+};
+
+struct test_subspec {
+	char *name;
 	bool expect_failure;
-	const char *expect_msg;
+	struct expected_msgs expect_msgs;
+	struct expected_msgs expect_xlated;
+	struct expected_msgs jited;
+	struct expected_msgs stderr;
+	struct expected_msgs stdout;
+	int retval;
+	bool execute;
+	__u64 caps;
+};
+
+struct test_spec {
+	const char *prog_name;
+	struct test_subspec priv;
+	struct test_subspec unpriv;
+	const char *btf_custom_path;
 	int log_level;
+	int prog_flags;
+	int mode_mask;
+	int arch_mask;
+	int load_mask;
+	int linear_sz;
+	bool auxiliary;
+	bool valid;
 };
 
 static int tester_init(struct test_loader *tester)
 {
 	if (!tester->log_buf) {
 		tester->log_buf_sz = TEST_LOADER_LOG_BUF_SZ;
-		tester->log_buf = malloc(tester->log_buf_sz);
+		tester->log_buf = calloc(tester->log_buf_sz, 1);
 		if (!ASSERT_OK_PTR(tester->log_buf, "tester_log_buf"))
 			return -ENOMEM;
 	}
@@ -41,17 +115,316 @@ void test_loader_fini(struct test_loader *tester)
 	free(tester->log_buf);
 }
 
+static void free_msgs(struct expected_msgs *msgs)
+{
+	int i;
+
+	for (i = 0; i < msgs->cnt; i++)
+		if (msgs->patterns[i].is_regex)
+			regfree(&msgs->patterns[i].regex);
+	free(msgs->patterns);
+	msgs->patterns = NULL;
+	msgs->cnt = 0;
+}
+
+static void free_test_spec(struct test_spec *spec)
+{
+	/* Deallocate expect_msgs arrays. */
+	free_msgs(&spec->priv.expect_msgs);
+	free_msgs(&spec->unpriv.expect_msgs);
+	free_msgs(&spec->priv.expect_xlated);
+	free_msgs(&spec->unpriv.expect_xlated);
+	free_msgs(&spec->priv.jited);
+	free_msgs(&spec->unpriv.jited);
+	free_msgs(&spec->unpriv.stderr);
+	free_msgs(&spec->priv.stderr);
+	free_msgs(&spec->unpriv.stdout);
+	free_msgs(&spec->priv.stdout);
+
+	free(spec->priv.name);
+	free(spec->unpriv.name);
+	spec->priv.name = NULL;
+	spec->unpriv.name = NULL;
+}
+
+/* Compiles regular expression matching pattern.
+ * Pattern has a special syntax:
+ *
+ *   pattern := (<verbatim text> | regex)*
+ *   regex := "{{" <posix extended regular expression> "}}"
+ *
+ * In other words, pattern is a verbatim text with inclusion
+ * of regular expressions enclosed in "{{" "}}" pairs.
+ * For example, pattern "foo{{[0-9]+}}" matches strings like
+ * "foo0", "foo007", etc.
+ */
+static int compile_regex(const char *pattern, regex_t *regex)
+{
+	char err_buf[256], buf[256] = {}, *ptr, *buf_end;
+	const char *original_pattern = pattern;
+	bool in_regex = false;
+	int err;
+
+	buf_end = buf + sizeof(buf);
+	ptr = buf;
+	while (*pattern && ptr < buf_end - 2) {
+		if (!in_regex && str_has_pfx(pattern, "{{")) {
+			in_regex = true;
+			pattern += 2;
+			continue;
+		}
+		if (in_regex && str_has_pfx(pattern, "}}")) {
+			in_regex = false;
+			pattern += 2;
+			continue;
+		}
+		if (in_regex) {
+			*ptr++ = *pattern++;
+			continue;
+		}
+		/* list of characters that need escaping for extended posix regex */
+		if (strchr(".[]\\()*+?{}|^$", *pattern)) {
+			*ptr++ = '\\';
+			*ptr++ = *pattern++;
+			continue;
+		}
+		*ptr++ = *pattern++;
+	}
+	if (*pattern) {
+		PRINT_FAIL("Regexp too long: '%s'\n", original_pattern);
+		return -EINVAL;
+	}
+	if (in_regex) {
+		PRINT_FAIL("Regexp has open '{{' but no closing '}}': '%s'\n", original_pattern);
+		return -EINVAL;
+	}
+	err = regcomp(regex, buf, REG_EXTENDED | REG_NEWLINE);
+	if (err != 0) {
+		regerror(err, regex, err_buf, sizeof(err_buf));
+		PRINT_FAIL("Regexp compilation error in '%s': '%s'\n", buf, err_buf);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int __push_msg(const char *pattern, bool on_next_line, bool negative,
+		      struct expected_msgs *msgs)
+{
+	struct expect_msg *msg;
+	void *tmp;
+	int err;
+
+	tmp = realloc(msgs->patterns,
+		      (1 + msgs->cnt) * sizeof(struct expect_msg));
+	if (!tmp) {
+		ASSERT_FAIL("failed to realloc memory for messages\n");
+		return -ENOMEM;
+	}
+	msgs->patterns = tmp;
+	msg = &msgs->patterns[msgs->cnt];
+	msg->on_next_line = on_next_line;
+	msg->substr = pattern;
+	msg->negative = negative;
+	msg->is_regex = false;
+	if (strstr(pattern, "{{")) {
+		err = compile_regex(pattern, &msg->regex);
+		if (err)
+			return err;
+		msg->is_regex = true;
+	}
+	msgs->cnt += 1;
+	return 0;
+}
+
+static int clone_msgs(struct expected_msgs *from, struct expected_msgs *to)
+{
+	struct expect_msg *msg;
+	int i, err;
+
+	for (i = 0; i < from->cnt; i++) {
+		msg = &from->patterns[i];
+		err = __push_msg(msg->substr, msg->on_next_line, msg->negative, to);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+static int push_msg(const char *substr, bool negative, struct expected_msgs *msgs)
+{
+	return __push_msg(substr, false, negative, msgs);
+}
+
+static int push_disasm_msg(const char *regex_str, bool *on_next_line, struct expected_msgs *msgs)
+{
+	int err;
+
+	if (strcmp(regex_str, "...") == 0) {
+		*on_next_line = false;
+		return 0;
+	}
+	err = __push_msg(regex_str, *on_next_line, false, msgs);
+	if (err)
+		return err;
+	*on_next_line = true;
+	return 0;
+}
+
+static int parse_int(const char *str, int *val, const char *name)
+{
+	char *end;
+	long tmp;
+
+	errno = 0;
+	if (str_has_pfx(str, "0x"))
+		tmp = strtol(str + 2, &end, 16);
+	else
+		tmp = strtol(str, &end, 10);
+	if (errno || end[0] != '\0') {
+		PRINT_FAIL("failed to parse %s from '%s'\n", name, str);
+		return -EINVAL;
+	}
+	*val = tmp;
+	return 0;
+}
+
+static int parse_caps(const char *str, __u64 *val, const char *name)
+{
+	int cap_flag = 0;
+	char *token = NULL, *saveptr = NULL;
+
+	char *str_cpy = strdup(str);
+	if (str_cpy == NULL) {
+		PRINT_FAIL("Memory allocation failed\n");
+		return -EINVAL;
+	}
+
+	token = strtok_r(str_cpy, "|", &saveptr);
+	while (token != NULL) {
+		errno = 0;
+		if (!strncmp("CAP_", token, sizeof("CAP_") - 1)) {
+			PRINT_FAIL("define %s constant in bpf_misc.h, failed to parse caps\n", token);
+			return -EINVAL;
+		}
+		cap_flag = strtol(token, NULL, 10);
+		if (!cap_flag || errno) {
+			PRINT_FAIL("failed to parse caps %s\n", name);
+			return -EINVAL;
+		}
+		*val |= (1ULL << cap_flag);
+		token = strtok_r(NULL, "|", &saveptr);
+	}
+
+	free(str_cpy);
+	return 0;
+}
+
+static int parse_retval(const char *str, int *val, const char *name)
+{
+	/*
+	 * INT_MIN is defined as (-INT_MAX -1), i.e. it doesn't expand to a
+	 * single int and cannot be parsed with strtol, so we handle it
+	 * separately here. In addition, it expands to different expressions in
+	 * different compilers so we use a prefixed _INT_MIN instead.
+	 */
+	if (strcmp(str, "_INT_MIN") == 0) {
+		*val = INT_MIN;
+		return 0;
+	}
+
+	return parse_int(str, val, name);
+}
+
+static void update_flags(int *flags, int flag, bool clear)
+{
+	if (clear)
+		*flags &= ~flag;
+	else
+		*flags |= flag;
+}
+
+/* Matches a string of form '<pfx>[^=]=.*' and returns it's suffix.
+ * Used to parse btf_decl_tag values.
+ * Such values require unique prefix because compiler does not add
+ * same __attribute__((btf_decl_tag(...))) twice.
+ * Test suite uses two-component tags for such cases:
+ *
+ *   <pfx> __COUNTER__ '='
+ *
+ * For example, two consecutive __msg tags '__msg("foo") __msg("foo")'
+ * would be encoded as:
+ *
+ *   [18] DECL_TAG 'comment:test_expect_msg=0=foo' type_id=15 component_idx=-1
+ *   [19] DECL_TAG 'comment:test_expect_msg=1=foo' type_id=15 component_idx=-1
+ *
+ * And the purpose of this function is to extract 'foo' from the above.
+ */
+static const char *skip_dynamic_pfx(const char *s, const char *pfx)
+{
+	const char *msg;
+
+	if (strncmp(s, pfx, strlen(pfx)) != 0)
+		return NULL;
+	msg = s + strlen(pfx);
+	msg = strchr(msg, '=');
+	if (!msg)
+		return NULL;
+	return msg + 1;
+}
+
+enum arch {
+	ARCH_UNKNOWN	= 0x1,
+	ARCH_X86_64	= 0x2,
+	ARCH_ARM64	= 0x4,
+	ARCH_RISCV64	= 0x8,
+	ARCH_S390X	= 0x10,
+};
+
+static int get_current_arch(void)
+{
+#if defined(__x86_64__)
+	return ARCH_X86_64;
+#elif defined(__aarch64__)
+	return ARCH_ARM64;
+#elif defined(__riscv) && __riscv_xlen == 64
+	return ARCH_RISCV64;
+#elif defined(__s390x__)
+	return ARCH_S390X;
+#endif
+	return ARCH_UNKNOWN;
+}
+
+/* Uses btf_decl_tag attributes to describe the expected test
+ * behavior, see bpf_misc.h for detailed description of each attribute
+ * and attribute combinations.
+ */
 static int parse_test_spec(struct test_loader *tester,
 			   struct bpf_object *obj,
 			   struct bpf_program *prog,
 			   struct test_spec *spec)
 {
+	const char *description = NULL;
+	bool has_unpriv_result = false;
+	bool has_unpriv_retval = false;
+	bool unpriv_xlated_on_next_line = true;
+	bool xlated_on_next_line = true;
+	bool unpriv_jit_on_next_line;
+	bool jit_on_next_line;
+	bool stderr_on_next_line = true;
+	bool unpriv_stderr_on_next_line = true;
+	bool stdout_on_next_line = true;
+	bool unpriv_stdout_on_next_line = true;
+	bool collect_jit = false;
+	int func_id, i, err = 0;
+	u32 arch_mask = 0;
+	u32 load_mask = 0;
 	struct btf *btf;
-	int func_id, i;
+	enum arch arch;
 
 	memset(spec, 0, sizeof(*spec));
 
-	spec->name = bpf_program__name(prog);
+	spec->prog_name = bpf_program__name(prog);
+	spec->prog_flags = testing_prog_flags();
 
 	btf = bpf_object__btf(obj);
 	if (!btf) {
@@ -59,15 +432,17 @@ static int parse_test_spec(struct test_loader *tester,
 		return -EINVAL;
 	}
 
-	func_id = btf__find_by_name_kind(btf, spec->name, BTF_KIND_FUNC);
+	func_id = btf__find_by_name_kind(btf, spec->prog_name, BTF_KIND_FUNC);
 	if (func_id < 0) {
-		ASSERT_FAIL("failed to find FUNC BTF type for '%s'", spec->name);
+		ASSERT_FAIL("failed to find FUNC BTF type for '%s'", spec->prog_name);
 		return -EINVAL;
 	}
 
 	for (i = 1; i < btf__type_cnt(btf); i++) {
+		const char *s, *val, *msg;
 		const struct btf_type *t;
-		const char *s;
+		bool clear;
+		int flags;
 
 		t = btf__type_by_id(btf, i);
 		if (!btf_is_decl_tag(t))
@@ -77,23 +452,270 @@ static int parse_test_spec(struct test_loader *tester,
 			continue;
 
 		s = btf__str_by_offset(btf, t->name_off);
-		if (strcmp(s, TEST_TAG_EXPECT_FAILURE) == 0) {
-			spec->expect_failure = true;
+		if (str_has_pfx(s, TEST_TAG_DESCRIPTION_PFX)) {
+			description = s + sizeof(TEST_TAG_DESCRIPTION_PFX) - 1;
+		} else if (strcmp(s, TEST_TAG_EXPECT_FAILURE) == 0) {
+			spec->priv.expect_failure = true;
+			spec->mode_mask |= PRIV;
 		} else if (strcmp(s, TEST_TAG_EXPECT_SUCCESS) == 0) {
-			spec->expect_failure = false;
-		} else if (str_has_pfx(s, TEST_TAG_EXPECT_MSG_PFX)) {
-			spec->expect_msg = s + sizeof(TEST_TAG_EXPECT_MSG_PFX) - 1;
+			spec->priv.expect_failure = false;
+			spec->mode_mask |= PRIV;
+		} else if (strcmp(s, TEST_TAG_EXPECT_FAILURE_UNPRIV) == 0) {
+			spec->unpriv.expect_failure = true;
+			spec->mode_mask |= UNPRIV;
+			has_unpriv_result = true;
+		} else if (strcmp(s, TEST_TAG_EXPECT_SUCCESS_UNPRIV) == 0) {
+			spec->unpriv.expect_failure = false;
+			spec->mode_mask |= UNPRIV;
+			has_unpriv_result = true;
+		} else if (strcmp(s, TEST_TAG_AUXILIARY) == 0) {
+			spec->auxiliary = true;
+			spec->mode_mask |= PRIV;
+		} else if (strcmp(s, TEST_TAG_AUXILIARY_UNPRIV) == 0) {
+			spec->auxiliary = true;
+			spec->mode_mask |= UNPRIV;
+		} else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_MSG_PFX))) {
+			err = push_msg(msg, false, &spec->priv.expect_msgs);
+			if (err)
+				goto cleanup;
+			spec->mode_mask |= PRIV;
+		} else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_NOT_MSG_PFX))) {
+			err = push_msg(msg, true, &spec->priv.expect_msgs);
+			if (err)
+				goto cleanup;
+			spec->mode_mask |= PRIV;
+		} else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_MSG_PFX_UNPRIV))) {
+			err = push_msg(msg, false, &spec->unpriv.expect_msgs);
+			if (err)
+				goto cleanup;
+			spec->mode_mask |= UNPRIV;
+		} else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_NOT_MSG_PFX_UNPRIV))) {
+			err = push_msg(msg, true, &spec->unpriv.expect_msgs);
+			if (err)
+				goto cleanup;
+			spec->mode_mask |= UNPRIV;
+		} else if ((msg = skip_dynamic_pfx(s, TEST_TAG_JITED_PFX))) {
+			if (arch_mask == 0) {
+				PRINT_FAIL("__jited used before __arch_*");
+				goto cleanup;
+			}
+			if (collect_jit) {
+				err = push_disasm_msg(msg, &jit_on_next_line,
+						      &spec->priv.jited);
+				if (err)
+					goto cleanup;
+				spec->mode_mask |= PRIV;
+			}
+		} else if ((msg = skip_dynamic_pfx(s, TEST_TAG_JITED_PFX_UNPRIV))) {
+			if (arch_mask == 0) {
+				PRINT_FAIL("__unpriv_jited used before __arch_*");
+				goto cleanup;
+			}
+			if (collect_jit) {
+				err = push_disasm_msg(msg, &unpriv_jit_on_next_line,
+						      &spec->unpriv.jited);
+				if (err)
+					goto cleanup;
+				spec->mode_mask |= UNPRIV;
+			}
+		} else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_XLATED_PFX))) {
+			err = push_disasm_msg(msg, &xlated_on_next_line,
+					      &spec->priv.expect_xlated);
+			if (err)
+				goto cleanup;
+			spec->mode_mask |= PRIV;
+		} else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_XLATED_PFX_UNPRIV))) {
+			err = push_disasm_msg(msg, &unpriv_xlated_on_next_line,
+					      &spec->unpriv.expect_xlated);
+			if (err)
+				goto cleanup;
+			spec->mode_mask |= UNPRIV;
+		} else if (str_has_pfx(s, TEST_TAG_RETVAL_PFX)) {
+			val = s + sizeof(TEST_TAG_RETVAL_PFX) - 1;
+			err = parse_retval(val, &spec->priv.retval, "__retval");
+			if (err)
+				goto cleanup;
+			spec->priv.execute = true;
+			spec->mode_mask |= PRIV;
+		} else if (str_has_pfx(s, TEST_TAG_RETVAL_PFX_UNPRIV)) {
+			val = s + sizeof(TEST_TAG_RETVAL_PFX_UNPRIV) - 1;
+			err = parse_retval(val, &spec->unpriv.retval, "__retval_unpriv");
+			if (err)
+				goto cleanup;
+			spec->mode_mask |= UNPRIV;
+			spec->unpriv.execute = true;
+			has_unpriv_retval = true;
 		} else if (str_has_pfx(s, TEST_TAG_LOG_LEVEL_PFX)) {
-			errno = 0;
-			spec->log_level = strtol(s + sizeof(TEST_TAG_LOG_LEVEL_PFX) - 1, NULL, 0);
-			if (errno) {
-				ASSERT_FAIL("failed to parse test log level from '%s'", s);
-				return -EINVAL;
+			val = s + sizeof(TEST_TAG_LOG_LEVEL_PFX) - 1;
+			err = parse_int(val, &spec->log_level, "test log level");
+			if (err)
+				goto cleanup;
+		} else if (str_has_pfx(s, TEST_TAG_PROG_FLAGS_PFX)) {
+			val = s + sizeof(TEST_TAG_PROG_FLAGS_PFX) - 1;
+
+			clear = val[0] == '!';
+			if (clear)
+				val++;
+
+			if (strcmp(val, "BPF_F_STRICT_ALIGNMENT") == 0) {
+				update_flags(&spec->prog_flags, BPF_F_STRICT_ALIGNMENT, clear);
+			} else if (strcmp(val, "BPF_F_ANY_ALIGNMENT") == 0) {
+				update_flags(&spec->prog_flags, BPF_F_ANY_ALIGNMENT, clear);
+			} else if (strcmp(val, "BPF_F_TEST_RND_HI32") == 0) {
+				update_flags(&spec->prog_flags, BPF_F_TEST_RND_HI32, clear);
+			} else if (strcmp(val, "BPF_F_TEST_STATE_FREQ") == 0) {
+				update_flags(&spec->prog_flags, BPF_F_TEST_STATE_FREQ, clear);
+			} else if (strcmp(val, "BPF_F_SLEEPABLE") == 0) {
+				update_flags(&spec->prog_flags, BPF_F_SLEEPABLE, clear);
+			} else if (strcmp(val, "BPF_F_XDP_HAS_FRAGS") == 0) {
+				update_flags(&spec->prog_flags, BPF_F_XDP_HAS_FRAGS, clear);
+			} else if (strcmp(val, "BPF_F_TEST_REG_INVARIANTS") == 0) {
+				update_flags(&spec->prog_flags, BPF_F_TEST_REG_INVARIANTS, clear);
+			} else /* assume numeric value */ {
+				err = parse_int(val, &flags, "test prog flags");
+				if (err)
+					goto cleanup;
+				update_flags(&spec->prog_flags, flags, clear);
+			}
+		} else if (str_has_pfx(s, TEST_TAG_ARCH)) {
+			val = s + sizeof(TEST_TAG_ARCH) - 1;
+			if (strcmp(val, "X86_64") == 0) {
+				arch = ARCH_X86_64;
+			} else if (strcmp(val, "ARM64") == 0) {
+				arch = ARCH_ARM64;
+			} else if (strcmp(val, "RISCV64") == 0) {
+				arch = ARCH_RISCV64;
+			} else if (strcmp(val, "s390x") == 0) {
+				arch = ARCH_S390X;
+			} else {
+				PRINT_FAIL("bad arch spec: '%s'\n", val);
+				err = -EINVAL;
+				goto cleanup;
+			}
+			arch_mask |= arch;
+			collect_jit = get_current_arch() == arch;
+			unpriv_jit_on_next_line = true;
+			jit_on_next_line = true;
+		} else if (str_has_pfx(s, TEST_BTF_PATH)) {
+			spec->btf_custom_path = s + sizeof(TEST_BTF_PATH) - 1;
+		} else if (str_has_pfx(s, TEST_TAG_CAPS_UNPRIV)) {
+			val = s + sizeof(TEST_TAG_CAPS_UNPRIV) - 1;
+			err = parse_caps(val, &spec->unpriv.caps, "test caps");
+			if (err)
+				goto cleanup;
+			spec->mode_mask |= UNPRIV;
+		} else if (str_has_pfx(s, TEST_TAG_LOAD_MODE_PFX)) {
+			val = s + sizeof(TEST_TAG_LOAD_MODE_PFX) - 1;
+			if (strcmp(val, "jited") == 0) {
+				load_mask = JITED;
+			} else if (strcmp(val, "no_jited") == 0) {
+				load_mask = NO_JITED;
+			} else {
+				PRINT_FAIL("bad load spec: '%s'", val);
+				err = -EINVAL;
+				goto cleanup;
+			}
+		} else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_STDERR_PFX))) {
+			err = push_disasm_msg(msg, &stderr_on_next_line,
+					      &spec->priv.stderr);
+			if (err)
+				goto cleanup;
+		} else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_STDERR_PFX_UNPRIV))) {
+			err = push_disasm_msg(msg, &unpriv_stderr_on_next_line,
+					      &spec->unpriv.stderr);
+			if (err)
+				goto cleanup;
+		} else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_STDOUT_PFX))) {
+			err = push_disasm_msg(msg, &stdout_on_next_line,
+					      &spec->priv.stdout);
+			if (err)
+				goto cleanup;
+		} else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_STDOUT_PFX_UNPRIV))) {
+			err = push_disasm_msg(msg, &unpriv_stdout_on_next_line,
+					      &spec->unpriv.stdout);
+			if (err)
+				goto cleanup;
+		} else if (str_has_pfx(s, TEST_TAG_LINEAR_SIZE)) {
+			switch (bpf_program__type(prog)) {
+			case BPF_PROG_TYPE_SCHED_ACT:
+			case BPF_PROG_TYPE_SCHED_CLS:
+			case BPF_PROG_TYPE_CGROUP_SKB:
+				val = s + sizeof(TEST_TAG_LINEAR_SIZE) - 1;
+				err = parse_int(val, &spec->linear_sz, "test linear size");
+				if (err)
+					goto cleanup;
+				break;
+			default:
+				PRINT_FAIL("__linear_size for unsupported program type");
+				err = -EINVAL;
+				goto cleanup;
 			}
 		}
 	}
 
+	spec->arch_mask = arch_mask ?: -1;
+	spec->load_mask = load_mask ?: (JITED | NO_JITED);
+
+	if (spec->mode_mask == 0)
+		spec->mode_mask = PRIV;
+
+	if (!description)
+		description = spec->prog_name;
+
+	if (spec->mode_mask & PRIV) {
+		spec->priv.name = strdup(description);
+		if (!spec->priv.name) {
+			PRINT_FAIL("failed to allocate memory for priv.name\n");
+			err = -ENOMEM;
+			goto cleanup;
+		}
+	}
+
+	if (spec->mode_mask & UNPRIV) {
+		int descr_len = strlen(description);
+		const char *suffix = " @unpriv";
+		char *name;
+
+		name = malloc(descr_len + strlen(suffix) + 1);
+		if (!name) {
+			PRINT_FAIL("failed to allocate memory for unpriv.name\n");
+			err = -ENOMEM;
+			goto cleanup;
+		}
+
+		strcpy(name, description);
+		strcpy(&name[descr_len], suffix);
+		spec->unpriv.name = name;
+	}
+
+	if (spec->mode_mask & (PRIV | UNPRIV)) {
+		if (!has_unpriv_result)
+			spec->unpriv.expect_failure = spec->priv.expect_failure;
+
+		if (!has_unpriv_retval) {
+			spec->unpriv.retval = spec->priv.retval;
+			spec->unpriv.execute = spec->priv.execute;
+		}
+
+		if (spec->unpriv.expect_msgs.cnt == 0)
+			clone_msgs(&spec->priv.expect_msgs, &spec->unpriv.expect_msgs);
+		if (spec->unpriv.expect_xlated.cnt == 0)
+			clone_msgs(&spec->priv.expect_xlated, &spec->unpriv.expect_xlated);
+		if (spec->unpriv.jited.cnt == 0)
+			clone_msgs(&spec->priv.jited, &spec->unpriv.jited);
+		if (spec->unpriv.stderr.cnt == 0)
+			clone_msgs(&spec->priv.stderr, &spec->unpriv.stderr);
+		if (spec->unpriv.stdout.cnt == 0)
+			clone_msgs(&spec->priv.stdout, &spec->unpriv.stdout);
+	}
+
+	spec->valid = true;
+
 	return 0;
+
+cleanup:
+	free_test_spec(spec);
+	return err;
 }
 
 static void prepare_case(struct test_loader *tester,
@@ -101,7 +723,7 @@ static void prepare_case(struct test_loader *tester,
 			 struct bpf_object *obj,
 			 struct bpf_program *prog)
 {
-	int min_log_level = 0;
+	int min_log_level = 0, prog_flags;
 
 	if (env.verbosity > VERBOSE_NONE)
 		min_log_level = 1;
@@ -110,7 +732,7 @@ static void prepare_case(struct test_loader *tester,
 
 	bpf_program__set_log_buf(prog, tester->log_buf, tester->log_buf_sz);
 
-	/* Make sure we set at least minimal log level, unless test requirest
+	/* Make sure we set at least minimal log level, unless test requires
 	 * even higher level already. Make sure to preserve independent log
 	 * level 4 (verifier stats), though.
 	 */
@@ -119,6 +741,9 @@ static void prepare_case(struct test_loader *tester,
 	else
 		bpf_program__set_log_level(prog, spec->log_level);
 
+	prog_flags = bpf_program__flags(prog);
+	bpf_program__set_flags(prog, prog_flags | spec->prog_flags);
+
 	tester->log_buf[0] = '\0';
 }
 
@@ -129,98 +754,646 @@ static void emit_verifier_log(const char *log_buf, bool force)
 	fprintf(stdout, "VERIFIER LOG:\n=============\n%s=============\n", log_buf);
 }
 
-static void validate_case(struct test_loader *tester,
-			  struct test_spec *spec,
-			  struct bpf_object *obj,
-			  struct bpf_program *prog,
-			  int load_err)
+static void emit_xlated(const char *xlated, bool force)
+{
+	if (!force && env.verbosity == VERBOSE_NONE)
+		return;
+	fprintf(stdout, "XLATED:\n=============\n%s=============\n", xlated);
+}
+
+static void emit_jited(const char *jited, bool force)
+{
+	if (!force && env.verbosity == VERBOSE_NONE)
+		return;
+	fprintf(stdout, "JITED:\n=============\n%s=============\n", jited);
+}
+
+static void emit_stderr(const char *stderr, bool force)
+{
+	if (!force && env.verbosity == VERBOSE_NONE)
+		return;
+	fprintf(stdout, "STDERR:\n=============\n%s=============\n", stderr);
+}
+
+static void emit_stdout(const char *bpf_stdout, bool force)
+{
+	if (!force && env.verbosity == VERBOSE_NONE)
+		return;
+	fprintf(stdout, "STDOUT:\n=============\n%s=============\n", bpf_stdout);
+}
+
+static const char *match_msg(struct expect_msg *msg, const char **log)
+{
+	const char *match = NULL;
+	regmatch_t reg_match[1];
+	int err;
+
+	if (!msg->is_regex) {
+		match = strstr(*log, msg->substr);
+		if (match)
+			*log = match + strlen(msg->substr);
+	} else {
+		err = regexec(&msg->regex, *log, 1, reg_match, 0);
+		if (err == 0) {
+			match = *log + reg_match[0].rm_so;
+			*log += reg_match[0].rm_eo;
+		}
+	}
+	return match;
+}
+
+static int count_lines(const char *start, const char *end)
+{
+	const char *tmp;
+	int n = 0;
+
+	for (tmp = start; tmp < end; ++tmp)
+		if (*tmp == '\n')
+			n++;
+	return n;
+}
+
+struct match {
+	const char *start;
+	const char *end;
+	int line;
+};
+
+/*
+ * Positive messages are matched sequentially, each next message
+ * is looked for starting from the end of a previous matched one.
+ */
+static void match_positive_msgs(const char *log, struct expected_msgs *msgs, struct match *matches)
+{
+	const char *prev_match;
+	int i, line;
+
+	prev_match = log;
+	line = 0;
+	for (i = 0; i < msgs->cnt; i++) {
+		struct expect_msg *msg = &msgs->patterns[i];
+		const char *match = NULL;
+
+		if (msg->negative)
+			continue;
+
+		match = match_msg(msg, &log);
+		if (match) {
+			line += count_lines(prev_match, match);
+			matches[i].start = match;
+			matches[i].end   = log;
+			matches[i].line  = line;
+			prev_match = match;
+		}
+	}
+}
+
+/*
+ * Each negative messages N located between positive messages P1 and P2
+ * is matched in the span P1.end .. P2.start. Consequently, negative messages
+ * are unordered within the span.
+ */
+static void match_negative_msgs(const char *log, struct expected_msgs *msgs, struct match *matches)
 {
-	if (spec->expect_msg) {
-		char *match;
+	const char *start = log, *end, *next, *match;
+	const char *log_end = log + strlen(log);
+	int i, j, next_positive;
+
+	for (i = 0; i < msgs->cnt; i++) {
+		struct expect_msg *msg = &msgs->patterns[i];
 
-		match = strstr(tester->log_buf, spec->expect_msg);
-		if (!ASSERT_OK_PTR(match, "expect_msg")) {
-			/* if we are in verbose mode, we've already emitted log */
+		/* positive message bumps span start */
+		if (!msg->negative) {
+			start = matches[i].end ?: start;
+			continue;
+		}
+
+		/* count stride of negative patterns and adjust span end */
+		end = log_end;
+		for (next_positive = i + 1; next_positive < msgs->cnt; next_positive++) {
+			if (!msgs->patterns[next_positive].negative) {
+				end = matches[next_positive].start;
+				break;
+			}
+		}
+
+		/* try matching negative messages within identified span */
+		for (j = i; j < next_positive; j++) {
+			next = start;
+			match = match_msg(msg, &next);
+			if (match && next <= end) {
+				matches[j].start = match;
+				matches[j].end = next;
+			}
+		}
+
+		/* -1 to account for i++ */
+		i = next_positive - 1;
+	}
+}
+
+void validate_msgs(const char *log_buf, struct expected_msgs *msgs,
+		   void (*emit_fn)(const char *buf, bool force))
+{
+	struct match matches[msgs->cnt];
+	struct match *prev_match = NULL;
+	int i, j;
+
+	memset(matches, 0, sizeof(*matches) * msgs->cnt);
+	match_positive_msgs(log_buf, msgs, matches);
+	match_negative_msgs(log_buf, msgs, matches);
+
+	for (i = 0; i < msgs->cnt; i++) {
+		struct expect_msg *msg = &msgs->patterns[i];
+		struct match *match = &matches[i];
+		const char *pat_status;
+		bool unexpected;
+		bool wrong_line;
+		bool no_match;
+
+		no_match   = !msg->negative && !match->start;
+		wrong_line = !msg->negative &&
+			     msg->on_next_line &&
+			     prev_match && prev_match->line + 1 != match->line;
+		unexpected = msg->negative && match->start;
+		if (no_match || wrong_line || unexpected) {
+			PRINT_FAIL("expect_msg\n");
 			if (env.verbosity == VERBOSE_NONE)
-				emit_verifier_log(tester->log_buf, true /*force*/);
-			fprintf(stderr, "EXPECTED MSG: '%s'\n", spec->expect_msg);
-			return;
+				emit_fn(log_buf, true /*force*/);
+			for (j = 0; j <= i; j++) {
+				msg = &msgs->patterns[j];
+				if (j < i)
+					pat_status = "MATCHED   ";
+				else if (wrong_line)
+					pat_status = "WRONG LINE";
+				else if (no_match)
+					pat_status = "EXPECTED  ";
+				else
+					pat_status = "UNEXPECTED";
+				msg = &msgs->patterns[j];
+				fprintf(stderr, "%s %s: '%s'\n",
+					pat_status,
+					msg->is_regex ? " REGEX" : "SUBSTR",
+					msg->substr);
+			}
+			if (wrong_line) {
+				fprintf(stderr,
+					"expecting match at line %d, actual match is at line %d\n",
+					prev_match->line + 1, match->line);
+			}
+			break;
 		}
+
+		if (!msg->negative)
+			prev_match = match;
 	}
 }
 
+struct cap_state {
+	__u64 old_caps;
+	bool initialized;
+};
+
+static int drop_capabilities(struct cap_state *caps)
+{
+	const __u64 caps_to_drop = (1ULL << CAP_SYS_ADMIN | 1ULL << CAP_NET_ADMIN |
+				    1ULL << CAP_PERFMON   | 1ULL << CAP_BPF);
+	int err;
+
+	err = cap_disable_effective(caps_to_drop, &caps->old_caps);
+	if (err) {
+		PRINT_FAIL("failed to drop capabilities: %i, %s\n", err, strerror(-err));
+		return err;
+	}
+
+	caps->initialized = true;
+	return 0;
+}
+
+static int restore_capabilities(struct cap_state *caps)
+{
+	int err;
+
+	if (!caps->initialized)
+		return 0;
+
+	err = cap_enable_effective(caps->old_caps, NULL);
+	if (err)
+		PRINT_FAIL("failed to restore capabilities: %i, %s\n", err, strerror(-err));
+	caps->initialized = false;
+	return err;
+}
+
+static bool can_execute_unpriv(struct test_loader *tester, struct test_spec *spec)
+{
+	if (sysctl_unpriv_disabled < 0)
+		sysctl_unpriv_disabled = get_unpriv_disabled() ? 1 : 0;
+	if (sysctl_unpriv_disabled)
+		return false;
+	if ((spec->prog_flags & BPF_F_ANY_ALIGNMENT) && !EFFICIENT_UNALIGNED_ACCESS)
+		return false;
+	return true;
+}
+
+static bool is_unpriv_capable_map(struct bpf_map *map)
+{
+	enum bpf_map_type type;
+	__u32 flags;
+
+	type = bpf_map__type(map);
+
+	switch (type) {
+	case BPF_MAP_TYPE_HASH:
+	case BPF_MAP_TYPE_PERCPU_HASH:
+	case BPF_MAP_TYPE_HASH_OF_MAPS:
+		flags = bpf_map__map_flags(map);
+		return !(flags & BPF_F_ZERO_SEED);
+	case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE:
+	case BPF_MAP_TYPE_ARRAY:
+	case BPF_MAP_TYPE_RINGBUF:
+	case BPF_MAP_TYPE_PROG_ARRAY:
+	case BPF_MAP_TYPE_CGROUP_ARRAY:
+	case BPF_MAP_TYPE_PERCPU_ARRAY:
+	case BPF_MAP_TYPE_USER_RINGBUF:
+	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
+	case BPF_MAP_TYPE_CGROUP_STORAGE:
+	case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static int do_prog_test_run(int fd_prog, int *retval, bool empty_opts, int linear_sz)
+{
+	__u8 tmp_out[TEST_DATA_LEN << 2] = {};
+	__u8 tmp_in[TEST_DATA_LEN] = {};
+	struct __sk_buff ctx = {};
+	int err, saved_errno;
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		.data_in = tmp_in,
+		.data_size_in = sizeof(tmp_in),
+		.data_out = tmp_out,
+		.data_size_out = sizeof(tmp_out),
+		.repeat = 1,
+	);
+
+	if (linear_sz) {
+		ctx.data_end = linear_sz;
+		topts.ctx_in = &ctx;
+		topts.ctx_size_in = sizeof(ctx);
+	}
+
+	if (empty_opts) {
+		memset(&topts, 0, sizeof(struct bpf_test_run_opts));
+		topts.sz = sizeof(struct bpf_test_run_opts);
+	}
+	err = bpf_prog_test_run_opts(fd_prog, &topts);
+	saved_errno = errno;
+
+	if (err) {
+		PRINT_FAIL("FAIL: Unexpected bpf_prog_test_run error: %d (%s) ",
+			   saved_errno, strerror(saved_errno));
+		return err;
+	}
+
+	ASSERT_OK(0, "bpf_prog_test_run");
+	*retval = topts.retval;
+
+	return 0;
+}
+
+static bool should_do_test_run(struct test_spec *spec, struct test_subspec *subspec)
+{
+	if (!subspec->execute)
+		return false;
+
+	if (subspec->expect_failure)
+		return false;
+
+	if ((spec->prog_flags & BPF_F_ANY_ALIGNMENT) && !EFFICIENT_UNALIGNED_ACCESS) {
+		if (env.verbosity != VERBOSE_NONE)
+			printf("alignment prevents execution\n");
+		return false;
+	}
+
+	return true;
+}
+
+/* Get a disassembly of BPF program after verifier applies all rewrites */
+static int get_xlated_program_text(int prog_fd, char *text, size_t text_sz)
+{
+	struct bpf_insn *insn_start = NULL, *insn, *insn_end;
+	__u32 insns_cnt = 0, i;
+	char buf[64];
+	FILE *out = NULL;
+	int err;
+
+	err = get_xlated_program(prog_fd, &insn_start, &insns_cnt);
+	if (!ASSERT_OK(err, "get_xlated_program"))
+		goto out;
+	out = fmemopen(text, text_sz, "w");
+	if (!ASSERT_OK_PTR(out, "open_memstream"))
+		goto out;
+	insn_end = insn_start + insns_cnt;
+	insn = insn_start;
+	while (insn < insn_end) {
+		i = insn - insn_start;
+		insn = disasm_insn(insn, buf, sizeof(buf));
+		fprintf(out, "%d: %s\n", i, buf);
+	}
+	fflush(out);
+
+out:
+	free(insn_start);
+	if (out)
+		fclose(out);
+	return err;
+}
+
+/* Read the bpf stream corresponding to the stream_id */
+static int get_stream(int stream_id, int prog_fd, char *text, size_t text_sz)
+{
+	LIBBPF_OPTS(bpf_prog_stream_read_opts, ropts);
+	int ret;
+
+	ret = bpf_prog_stream_read(prog_fd, stream_id, text, text_sz, &ropts);
+	ASSERT_GT(ret, 0, "stream read");
+	text[ret] = '\0';
+
+	return ret;
+}
+
 /* this function is forced noinline and has short generic name to look better
  * in test_progs output (in case of a failure)
  */
 static noinline
 void run_subtest(struct test_loader *tester,
-		 const char *skel_name,
-		 skel_elf_bytes_fn elf_bytes_factory)
+		 struct bpf_object_open_opts *open_opts,
+		 const void *obj_bytes,
+		 size_t obj_byte_cnt,
+		 struct test_spec *specs,
+		 struct test_spec *spec,
+		 bool unpriv)
 {
-	LIBBPF_OPTS(bpf_object_open_opts, open_opts, .object_name = skel_name);
-	struct bpf_object *obj = NULL, *tobj;
-	struct bpf_program *prog, *tprog;
-	const void *obj_bytes;
-	size_t obj_byte_cnt;
-	int err;
+	struct test_subspec *subspec = unpriv ? &spec->unpriv : &spec->priv;
+	int current_runtime = is_jit_enabled() ? JITED : NO_JITED;
+	struct bpf_program *tprog = NULL, *tprog_iter;
+	struct bpf_link *link, *links[32] = {};
+	struct test_spec *spec_iter;
+	struct cap_state caps = {};
+	struct bpf_object *tobj;
+	struct bpf_map *map;
+	int retval, err, i;
+	int links_cnt = 0;
+	bool should_load;
 
-	if (tester_init(tester) < 0)
-		return; /* failed to initialize tester */
+	if (!test__start_subtest(subspec->name))
+		return;
 
-	obj_bytes = elf_bytes_factory(&obj_byte_cnt);
-	obj = bpf_object__open_mem(obj_bytes, obj_byte_cnt, &open_opts);
-	if (!ASSERT_OK_PTR(obj, "obj_open_mem"))
+	if ((get_current_arch() & spec->arch_mask) == 0) {
+		test__skip();
 		return;
+	}
 
-	bpf_object__for_each_program(prog, obj) {
-		const char *prog_name = bpf_program__name(prog);
-		struct test_spec spec;
+	if ((current_runtime & spec->load_mask) == 0) {
+		test__skip();
+		return;
+	}
 
-		if (!test__start_subtest(prog_name))
-			continue;
+	if (unpriv) {
+		if (!can_execute_unpriv(tester, spec)) {
+			test__skip();
+			test__end_subtest();
+			return;
+		}
+		if (drop_capabilities(&caps)) {
+			test__end_subtest();
+			return;
+		}
+		if (subspec->caps) {
+			err = cap_enable_effective(subspec->caps, NULL);
+			if (err) {
+				PRINT_FAIL("failed to set capabilities: %i, %s\n", err, strerror(-err));
+				goto subtest_cleanup;
+			}
+		}
+	}
 
-		/* if we can't derive test specification, go to the next test */
-		err = parse_test_spec(tester, obj, prog, &spec);
-		if (!ASSERT_OK(err, "parse_test_spec"))
-			continue;
+	/* Implicitly reset to NULL if next test case doesn't specify */
+	open_opts->btf_custom_path = spec->btf_custom_path;
 
-		tobj = bpf_object__open_mem(obj_bytes, obj_byte_cnt, &open_opts);
-		if (!ASSERT_OK_PTR(tobj, "obj_open_mem")) /* shouldn't happen */
-			continue;
+	tobj = bpf_object__open_mem(obj_bytes, obj_byte_cnt, open_opts);
+	if (!ASSERT_OK_PTR(tobj, "obj_open_mem")) /* shouldn't happen */
+		goto subtest_cleanup;
 
-		bpf_object__for_each_program(tprog, tobj)
-			bpf_program__set_autoload(tprog, false);
+	i = 0;
+	bpf_object__for_each_program(tprog_iter, tobj) {
+		spec_iter = &specs[i++];
+		should_load = false;
 
-		bpf_object__for_each_program(tprog, tobj) {
-			/* only load specified program */
-			if (strcmp(bpf_program__name(tprog), prog_name) == 0) {
-				bpf_program__set_autoload(tprog, true);
-				break;
+		if (spec_iter->valid) {
+			if (strcmp(bpf_program__name(tprog_iter), spec->prog_name) == 0) {
+				tprog = tprog_iter;
+				should_load = true;
 			}
+
+			if (spec_iter->auxiliary &&
+			    spec_iter->mode_mask & (unpriv ? UNPRIV : PRIV))
+				should_load = true;
 		}
 
-		prepare_case(tester, &spec, tobj, tprog);
+		bpf_program__set_autoload(tprog_iter, should_load);
+	}
+
+	prepare_case(tester, spec, tobj, tprog);
+
+	/* By default bpf_object__load() automatically creates all
+	 * maps declared in the skeleton. Some map types are only
+	 * allowed in priv mode. Disable autoload for such maps in
+	 * unpriv mode.
+	 */
+	bpf_object__for_each_map(map, tobj)
+		bpf_map__set_autocreate(map, !unpriv || is_unpriv_capable_map(map));
 
-		err = bpf_object__load(tobj);
-		if (spec.expect_failure) {
-			if (!ASSERT_ERR(err, "unexpected_load_success")) {
-				emit_verifier_log(tester->log_buf, false /*force*/);
+	err = bpf_object__load(tobj);
+	if (subspec->expect_failure) {
+		if (!ASSERT_ERR(err, "unexpected_load_success")) {
+			emit_verifier_log(tester->log_buf, false /*force*/);
+			goto tobj_cleanup;
+		}
+	} else {
+		if (!ASSERT_OK(err, "unexpected_load_failure")) {
+			emit_verifier_log(tester->log_buf, true /*force*/);
+			goto tobj_cleanup;
+		}
+	}
+	emit_verifier_log(tester->log_buf, false /*force*/);
+	validate_msgs(tester->log_buf, &subspec->expect_msgs, emit_verifier_log);
+
+	/* Restore capabilities because the kernel will silently ignore requests
+	 * for program info (such as xlated program text) if we are not
+	 * bpf-capable. Also, for some reason test_verifier executes programs
+	 * with all capabilities restored. Do the same here.
+	 */
+	if (restore_capabilities(&caps))
+		goto tobj_cleanup;
+
+	if (subspec->expect_xlated.cnt) {
+		err = get_xlated_program_text(bpf_program__fd(tprog),
+					      tester->log_buf, tester->log_buf_sz);
+		if (err)
+			goto tobj_cleanup;
+		emit_xlated(tester->log_buf, false /*force*/);
+		validate_msgs(tester->log_buf, &subspec->expect_xlated, emit_xlated);
+	}
+
+	if (subspec->jited.cnt) {
+		err = get_jited_program_text(bpf_program__fd(tprog),
+					     tester->log_buf, tester->log_buf_sz);
+		if (err == -EOPNOTSUPP) {
+			printf("%s:SKIP: jited programs disassembly is not supported,\n", __func__);
+			printf("%s:SKIP: tests are built w/o LLVM development libs\n", __func__);
+			test__skip();
+			goto tobj_cleanup;
+		}
+		if (!ASSERT_EQ(err, 0, "get_jited_program_text"))
+			goto tobj_cleanup;
+		emit_jited(tester->log_buf, false /*force*/);
+		validate_msgs(tester->log_buf, &subspec->jited, emit_jited);
+	}
+
+	if (should_do_test_run(spec, subspec)) {
+		/* Do bpf_map__attach_struct_ops() for each struct_ops map.
+		 * This should trigger bpf_struct_ops->reg callback on kernel side.
+		 */
+		bpf_object__for_each_map(map, tobj) {
+			if (!bpf_map__autocreate(map) ||
+			    bpf_map__type(map) != BPF_MAP_TYPE_STRUCT_OPS)
+				continue;
+			if (links_cnt >= ARRAY_SIZE(links)) {
+				PRINT_FAIL("too many struct_ops maps");
+				goto tobj_cleanup;
+			}
+			link = bpf_map__attach_struct_ops(map);
+			if (!link) {
+				PRINT_FAIL("bpf_map__attach_struct_ops failed for map %s: err=%d\n",
+					   bpf_map__name(map), -errno);
 				goto tobj_cleanup;
 			}
-		} else {
-			if (!ASSERT_OK(err, "unexpected_load_failure")) {
-				emit_verifier_log(tester->log_buf, true /*force*/);
+			links[links_cnt++] = link;
+		}
+
+		if (tester->pre_execution_cb) {
+			err = tester->pre_execution_cb(tobj);
+			if (err) {
+				PRINT_FAIL("pre_execution_cb failed: %d\n", err);
 				goto tobj_cleanup;
 			}
 		}
 
-		emit_verifier_log(tester->log_buf, false /*force*/);
-		validate_case(tester, &spec, tobj, tprog, err);
+		err = do_prog_test_run(bpf_program__fd(tprog), &retval,
+				       bpf_program__type(tprog) == BPF_PROG_TYPE_SYSCALL ? true : false,
+				       spec->linear_sz);
+		if (!err && retval != subspec->retval && subspec->retval != POINTER_VALUE) {
+			PRINT_FAIL("Unexpected retval: %d != %d\n", retval, subspec->retval);
+			goto tobj_cleanup;
+		}
+
+		if (subspec->stderr.cnt) {
+			err = get_stream(2, bpf_program__fd(tprog),
+					 tester->log_buf, tester->log_buf_sz);
+			if (err <= 0) {
+				PRINT_FAIL("Unexpected retval from get_stream(): %d, errno = %d\n",
+					   err, errno);
+				goto tobj_cleanup;
+			}
+			emit_stderr(tester->log_buf, false /*force*/);
+			validate_msgs(tester->log_buf, &subspec->stderr, emit_stderr);
+		}
+
+		if (subspec->stdout.cnt) {
+			err = get_stream(1, bpf_program__fd(tprog),
+					 tester->log_buf, tester->log_buf_sz);
+			if (err <= 0) {
+				PRINT_FAIL("Unexpected retval from get_stream(): %d, errno = %d\n",
+					   err, errno);
+				goto tobj_cleanup;
+			}
+			emit_stdout(tester->log_buf, false /*force*/);
+			validate_msgs(tester->log_buf, &subspec->stdout, emit_stdout);
+		}
+
+		/* redo bpf_map__attach_struct_ops for each test */
+		while (links_cnt > 0)
+			bpf_link__destroy(links[--links_cnt]);
+	}
 
 tobj_cleanup:
-		bpf_object__close(tobj);
+	while (links_cnt > 0)
+		bpf_link__destroy(links[--links_cnt]);
+	bpf_object__close(tobj);
+subtest_cleanup:
+	test__end_subtest();
+	restore_capabilities(&caps);
+}
+
+static void process_subtest(struct test_loader *tester,
+			    const char *skel_name,
+			    skel_elf_bytes_fn elf_bytes_factory)
+{
+	LIBBPF_OPTS(bpf_object_open_opts, open_opts, .object_name = skel_name);
+	struct test_spec *specs = NULL;
+	struct bpf_object *obj = NULL;
+	struct bpf_program *prog;
+	const void *obj_bytes;
+	int err, i, nr_progs;
+	size_t obj_byte_cnt;
+
+	if (tester_init(tester) < 0)
+		return; /* failed to initialize tester */
+
+	obj_bytes = elf_bytes_factory(&obj_byte_cnt);
+	obj = bpf_object__open_mem(obj_bytes, obj_byte_cnt, &open_opts);
+	if (!ASSERT_OK_PTR(obj, "obj_open_mem"))
+		return;
+
+	nr_progs = 0;
+	bpf_object__for_each_program(prog, obj)
+		++nr_progs;
+
+	specs = calloc(nr_progs, sizeof(struct test_spec));
+	if (!ASSERT_OK_PTR(specs, "specs_alloc"))
+		return;
+
+	i = 0;
+	bpf_object__for_each_program(prog, obj) {
+		/* ignore tests for which  we can't derive test specification */
+		err = parse_test_spec(tester, obj, prog, &specs[i++]);
+		if (err)
+			PRINT_FAIL("Can't parse test spec for program '%s'\n",
+				   bpf_program__name(prog));
+	}
+
+	i = 0;
+	bpf_object__for_each_program(prog, obj) {
+		struct test_spec *spec = &specs[i++];
+
+		if (!spec->valid || spec->auxiliary)
+			continue;
+
+		if (spec->mode_mask & PRIV)
+			run_subtest(tester, &open_opts, obj_bytes, obj_byte_cnt,
+				    specs, spec, false);
+		if (spec->mode_mask & UNPRIV)
+			run_subtest(tester, &open_opts, obj_bytes, obj_byte_cnt,
+				    specs, spec, true);
+
 	}
 
+	for (i = 0; i < nr_progs; ++i)
+		free_test_spec(&specs[i]);
+	free(specs);
 	bpf_object__close(obj);
 }
 
@@ -229,5 +1402,5 @@ void test_loader__run_subtests(struct test_loader *tester,
 			       skel_elf_bytes_fn elf_bytes_factory)
 {
 	/* see comment in run_subtest() for why we do this function nesting */
-	run_subtest(tester, skel_name, elf_bytes_factory);
+	process_subtest(tester, skel_name, elf_bytes_factory);
 }
diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c
index 4d0650cfb5cd..0921939532c6 100644
--- a/tools/testing/selftests/bpf/test_lru_map.c
+++ b/tools/testing/selftests/bpf/test_lru_map.c
@@ -126,7 +126,8 @@ static int sched_next_online(int pid, int *next_to_try)
 
 	while (next < nr_cpus) {
 		CPU_ZERO(&cpuset);
-		CPU_SET(next++, &cpuset);
+		CPU_SET(next, &cpuset);
+		next++;
 		if (!sched_setaffinity(pid, sizeof(cpuset), &cpuset)) {
 			ret = 0;
 			break;
@@ -137,6 +138,18 @@ static int sched_next_online(int pid, int *next_to_try)
 	return ret;
 }
 
+/* Derive target_free from map_size, same as bpf_common_lru_populate */
+static unsigned int __tgt_size(unsigned int map_size)
+{
+	return (map_size / nr_cpus) / 2;
+}
+
+/* Inverse of how bpf_common_lru_populate derives target_free from map_size. */
+static unsigned int __map_size(unsigned int tgt_free)
+{
+	return tgt_free * nr_cpus * 2;
+}
+
 /* Size of the LRU map is 2
  * Add key=1 (+1 key)
  * Add key=2 (+1 key)
@@ -230,11 +243,11 @@ static void test_lru_sanity0(int map_type, int map_flags)
 	printf("Pass\n");
 }
 
-/* Size of the LRU map is 1.5*tgt_free
- * Insert 1 to tgt_free (+tgt_free keys)
- * Lookup 1 to tgt_free/2
- * Insert 1+tgt_free to 2*tgt_free (+tgt_free keys)
- * => 1+tgt_free/2 to LOCALFREE_TARGET will be removed by LRU
+/* Verify that unreferenced elements are recycled before referenced ones.
+ * Insert elements.
+ * Reference a subset of these.
+ * Insert more, enough to trigger recycling.
+ * Verify that unreferenced are recycled.
  */
 static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
 {
@@ -256,7 +269,7 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
 	batch_size = tgt_free / 2;
 	assert(batch_size * 2 == tgt_free);
 
-	map_size = tgt_free + batch_size;
+	map_size = __map_size(tgt_free) + batch_size;
 	lru_map_fd = create_map(map_type, map_flags, map_size);
 	assert(lru_map_fd != -1);
 
@@ -265,13 +278,13 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
 
 	value[0] = 1234;
 
-	/* Insert 1 to tgt_free (+tgt_free keys) */
-	end_key = 1 + tgt_free;
+	/* Insert map_size - batch_size keys */
+	end_key = 1 + __map_size(tgt_free);
 	for (key = 1; key < end_key; key++)
 		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
 					    BPF_NOEXIST));
 
-	/* Lookup 1 to tgt_free/2 */
+	/* Lookup 1 to batch_size */
 	end_key = 1 + batch_size;
 	for (key = 1; key < end_key; key++) {
 		assert(!bpf_map_lookup_elem_with_ref_bit(lru_map_fd, key, value));
@@ -279,12 +292,13 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
 					    BPF_NOEXIST));
 	}
 
-	/* Insert 1+tgt_free to 2*tgt_free
-	 * => 1+tgt_free/2 to LOCALFREE_TARGET will be
+	/* Insert another map_size - batch_size keys
+	 * Map will contain 1 to batch_size plus these latest, i.e.,
+	 * => previous 1+batch_size to map_size - batch_size will have been
 	 * removed by LRU
 	 */
-	key = 1 + tgt_free;
-	end_key = key + tgt_free;
+	key = 1 + __map_size(tgt_free);
+	end_key = key + __map_size(tgt_free);
 	for (; key < end_key; key++) {
 		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
 					    BPF_NOEXIST));
@@ -300,17 +314,8 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
 	printf("Pass\n");
 }
 
-/* Size of the LRU map 1.5 * tgt_free
- * Insert 1 to tgt_free (+tgt_free keys)
- * Update 1 to tgt_free/2
- *   => The original 1 to tgt_free/2 will be removed due to
- *      the LRU shrink process
- * Re-insert 1 to tgt_free/2 again and do a lookup immeidately
- * Insert 1+tgt_free to tgt_free*3/2
- * Insert 1+tgt_free*3/2 to tgt_free*5/2
- *   => Key 1+tgt_free to tgt_free*3/2
- *      will be removed from LRU because it has never
- *      been lookup and ref bit is not set
+/* Verify that insertions exceeding map size will recycle the oldest.
+ * Verify that unreferenced elements are recycled before referenced.
  */
 static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 {
@@ -333,7 +338,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 	batch_size = tgt_free / 2;
 	assert(batch_size * 2 == tgt_free);
 
-	map_size = tgt_free + batch_size;
+	map_size = __map_size(tgt_free) + batch_size;
 	lru_map_fd = create_map(map_type, map_flags, map_size);
 	assert(lru_map_fd != -1);
 
@@ -342,8 +347,8 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 
 	value[0] = 1234;
 
-	/* Insert 1 to tgt_free (+tgt_free keys) */
-	end_key = 1 + tgt_free;
+	/* Insert map_size - batch_size keys */
+	end_key = 1 + __map_size(tgt_free);
 	for (key = 1; key < end_key; key++)
 		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
 					    BPF_NOEXIST));
@@ -356,8 +361,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 	 * shrink the inactive list to get tgt_free
 	 * number of free nodes.
 	 *
-	 * Hence, the oldest key 1 to tgt_free/2
-	 * are removed from the LRU list.
+	 * Hence, the oldest key is removed from the LRU list.
 	 */
 	key = 1;
 	if (map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
@@ -369,8 +373,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 					   BPF_EXIST));
 	}
 
-	/* Re-insert 1 to tgt_free/2 again and do a lookup
-	 * immeidately.
+	/* Re-insert 1 to batch_size again and do a lookup immediately.
 	 */
 	end_key = 1 + batch_size;
 	value[0] = 4321;
@@ -386,17 +389,18 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 
 	value[0] = 1234;
 
-	/* Insert 1+tgt_free to tgt_free*3/2 */
-	end_key = 1 + tgt_free + batch_size;
-	for (key = 1 + tgt_free; key < end_key; key++)
+	/* Insert batch_size new elements */
+	key = 1 + __map_size(tgt_free);
+	end_key = key + batch_size;
+	for (; key < end_key; key++)
 		/* These newly added but not referenced keys will be
 		 * gone during the next LRU shrink.
 		 */
 		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
 					    BPF_NOEXIST));
 
-	/* Insert 1+tgt_free*3/2 to  tgt_free*5/2 */
-	end_key = key + tgt_free;
+	/* Insert map_size - batch_size elements */
+	end_key += __map_size(tgt_free);
 	for (; key < end_key; key++) {
 		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
 					    BPF_NOEXIST));
@@ -412,12 +416,12 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 	printf("Pass\n");
 }
 
-/* Size of the LRU map is 2*tgt_free
- * It is to test the active/inactive list rotation
- * Insert 1 to 2*tgt_free (+2*tgt_free keys)
- * Lookup key 1 to tgt_free*3/2
- * Add 1+2*tgt_free to tgt_free*5/2 (+tgt_free/2 keys)
- *  => key 1+tgt_free*3/2 to 2*tgt_free are removed from LRU
+/* Test the active/inactive list rotation
+ *
+ * Fill the whole map, deplete the free list.
+ * Reference all except the last lru->target_free elements.
+ * Insert lru->target_free new elements. This triggers one shrink.
+ * Verify that the non-referenced elements are replaced.
  */
 static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
 {
@@ -436,8 +440,7 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
 
 	assert(sched_next_online(0, &next_cpu) != -1);
 
-	batch_size = tgt_free / 2;
-	assert(batch_size * 2 == tgt_free);
+	batch_size = __tgt_size(tgt_free);
 
 	map_size = tgt_free * 2;
 	lru_map_fd = create_map(map_type, map_flags, map_size);
@@ -448,23 +451,21 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
 
 	value[0] = 1234;
 
-	/* Insert 1 to 2*tgt_free (+2*tgt_free keys) */
-	end_key = 1 + (2 * tgt_free);
+	/* Fill the map */
+	end_key = 1 + map_size;
 	for (key = 1; key < end_key; key++)
 		assert(!bpf_map_update_elem(lru_map_fd, &key, value,
 					    BPF_NOEXIST));
 
-	/* Lookup key 1 to tgt_free*3/2 */
-	end_key = tgt_free + batch_size;
+	/* Reference all but the last batch_size */
+	end_key = 1 + map_size - batch_size;
 	for (key = 1; key < end_key; key++) {
 		assert(!bpf_map_lookup_elem_with_ref_bit(lru_map_fd, key, value));
 		assert(!bpf_map_update_elem(expected_map_fd, &key, value,
 					    BPF_NOEXIST));
 	}
 
-	/* Add 1+2*tgt_free to tgt_free*5/2
-	 * (+tgt_free/2 keys)
-	 */
+	/* Insert new batch_size: replaces the non-referenced elements */
 	key = 2 * tgt_free + 1;
 	end_key = key + batch_size;
 	for (; key < end_key; key++) {
@@ -499,7 +500,8 @@ static void test_lru_sanity4(int map_type, int map_flags, unsigned int tgt_free)
 		lru_map_fd = create_map(map_type, map_flags,
 					3 * tgt_free * nr_cpus);
 	else
-		lru_map_fd = create_map(map_type, map_flags, 3 * tgt_free);
+		lru_map_fd = create_map(map_type, map_flags,
+					3 * __map_size(tgt_free));
 	assert(lru_map_fd != -1);
 
 	expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0,
diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh
deleted file mode 100755
index 1e565f47aca9..000000000000
--- a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh
+++ /dev/null
@@ -1,476 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-#
-# Setup/topology:
-#
-#    NS1             NS2             NS3
-#   veth1 <---> veth2   veth3 <---> veth4 (the top route)
-#   veth5 <---> veth6   veth7 <---> veth8 (the bottom route)
-#
-#   each vethN gets IPv[4|6]_N address
-#
-#   IPv*_SRC = IPv*_1
-#   IPv*_DST = IPv*_4
-#
-#   all tests test pings from IPv*_SRC to IPv*_DST
-#
-#   by default, routes are configured to allow packets to go
-#   IP*_1 <=> IP*_2 <=> IP*_3 <=> IP*_4 (the top route)
-#
-#   a GRE device is installed in NS3 with IPv*_GRE, and
-#   NS1/NS2 are configured to route packets to IPv*_GRE via IP*_8
-#   (the bottom route)
-#
-# Tests:
-#
-#   1. routes NS2->IPv*_DST are brought down, so the only way a ping
-#      from IP*_SRC to IP*_DST can work is via IPv*_GRE
-#
-#   2a. in an egress test, a bpf LWT_XMIT program is installed on veth1
-#       that encaps the packets with an IP/GRE header to route to IPv*_GRE
-#
-#       ping: SRC->[encap at veth1:egress]->GRE:decap->DST
-#       ping replies go DST->SRC directly
-#
-#   2b. in an ingress test, a bpf LWT_IN program is installed on veth2
-#       that encaps the packets with an IP/GRE header to route to IPv*_GRE
-#
-#       ping: SRC->[encap at veth2:ingress]->GRE:decap->DST
-#       ping replies go DST->SRC directly
-
-BPF_FILE="test_lwt_ip_encap.bpf.o"
-if [[ $EUID -ne 0 ]]; then
-	echo "This script must be run as root"
-	echo "FAIL"
-	exit 1
-fi
-
-readonly NS1="ns1-$(mktemp -u XXXXXX)"
-readonly NS2="ns2-$(mktemp -u XXXXXX)"
-readonly NS3="ns3-$(mktemp -u XXXXXX)"
-
-readonly IPv4_1="172.16.1.100"
-readonly IPv4_2="172.16.2.100"
-readonly IPv4_3="172.16.3.100"
-readonly IPv4_4="172.16.4.100"
-readonly IPv4_5="172.16.5.100"
-readonly IPv4_6="172.16.6.100"
-readonly IPv4_7="172.16.7.100"
-readonly IPv4_8="172.16.8.100"
-readonly IPv4_GRE="172.16.16.100"
-
-readonly IPv4_SRC=$IPv4_1
-readonly IPv4_DST=$IPv4_4
-
-readonly IPv6_1="fb01::1"
-readonly IPv6_2="fb02::1"
-readonly IPv6_3="fb03::1"
-readonly IPv6_4="fb04::1"
-readonly IPv6_5="fb05::1"
-readonly IPv6_6="fb06::1"
-readonly IPv6_7="fb07::1"
-readonly IPv6_8="fb08::1"
-readonly IPv6_GRE="fb10::1"
-
-readonly IPv6_SRC=$IPv6_1
-readonly IPv6_DST=$IPv6_4
-
-TEST_STATUS=0
-TESTS_SUCCEEDED=0
-TESTS_FAILED=0
-
-TMPFILE=""
-
-process_test_results()
-{
-	if [[ "${TEST_STATUS}" -eq 0 ]] ; then
-		echo "PASS"
-		TESTS_SUCCEEDED=$((TESTS_SUCCEEDED+1))
-	else
-		echo "FAIL"
-		TESTS_FAILED=$((TESTS_FAILED+1))
-	fi
-}
-
-print_test_summary_and_exit()
-{
-	echo "passed tests: ${TESTS_SUCCEEDED}"
-	echo "failed tests: ${TESTS_FAILED}"
-	if [ "${TESTS_FAILED}" -eq "0" ] ; then
-		exit 0
-	else
-		exit 1
-	fi
-}
-
-setup()
-{
-	set -e  # exit on error
-	TEST_STATUS=0
-
-	# create devices and namespaces
-	ip netns add "${NS1}"
-	ip netns add "${NS2}"
-	ip netns add "${NS3}"
-
-	# rp_filter gets confused by what these tests are doing, so disable it
-	ip netns exec ${NS1} sysctl -wq net.ipv4.conf.all.rp_filter=0
-	ip netns exec ${NS2} sysctl -wq net.ipv4.conf.all.rp_filter=0
-	ip netns exec ${NS3} sysctl -wq net.ipv4.conf.all.rp_filter=0
-	ip netns exec ${NS1} sysctl -wq net.ipv4.conf.default.rp_filter=0
-	ip netns exec ${NS2} sysctl -wq net.ipv4.conf.default.rp_filter=0
-	ip netns exec ${NS3} sysctl -wq net.ipv4.conf.default.rp_filter=0
-
-	# disable IPv6 DAD because it sometimes takes too long and fails tests
-	ip netns exec ${NS1} sysctl -wq net.ipv6.conf.all.accept_dad=0
-	ip netns exec ${NS2} sysctl -wq net.ipv6.conf.all.accept_dad=0
-	ip netns exec ${NS3} sysctl -wq net.ipv6.conf.all.accept_dad=0
-	ip netns exec ${NS1} sysctl -wq net.ipv6.conf.default.accept_dad=0
-	ip netns exec ${NS2} sysctl -wq net.ipv6.conf.default.accept_dad=0
-	ip netns exec ${NS3} sysctl -wq net.ipv6.conf.default.accept_dad=0
-
-	ip link add veth1 type veth peer name veth2
-	ip link add veth3 type veth peer name veth4
-	ip link add veth5 type veth peer name veth6
-	ip link add veth7 type veth peer name veth8
-
-	ip netns exec ${NS2} sysctl -wq net.ipv4.ip_forward=1
-	ip netns exec ${NS2} sysctl -wq net.ipv6.conf.all.forwarding=1
-
-	ip link set veth1 netns ${NS1}
-	ip link set veth2 netns ${NS2}
-	ip link set veth3 netns ${NS2}
-	ip link set veth4 netns ${NS3}
-	ip link set veth5 netns ${NS1}
-	ip link set veth6 netns ${NS2}
-	ip link set veth7 netns ${NS2}
-	ip link set veth8 netns ${NS3}
-
-	if [ ! -z "${VRF}" ] ; then
-		ip -netns ${NS1} link add red type vrf table 1001
-		ip -netns ${NS1} link set red up
-		ip -netns ${NS1} route add table 1001 unreachable default metric 8192
-		ip -netns ${NS1} -6 route add table 1001 unreachable default metric 8192
-		ip -netns ${NS1} link set veth1 vrf red
-		ip -netns ${NS1} link set veth5 vrf red
-
-		ip -netns ${NS2} link add red type vrf table 1001
-		ip -netns ${NS2} link set red up
-		ip -netns ${NS2} route add table 1001 unreachable default metric 8192
-		ip -netns ${NS2} -6 route add table 1001 unreachable default metric 8192
-		ip -netns ${NS2} link set veth2 vrf red
-		ip -netns ${NS2} link set veth3 vrf red
-		ip -netns ${NS2} link set veth6 vrf red
-		ip -netns ${NS2} link set veth7 vrf red
-	fi
-
-	# configure addesses: the top route (1-2-3-4)
-	ip -netns ${NS1}    addr add ${IPv4_1}/24  dev veth1
-	ip -netns ${NS2}    addr add ${IPv4_2}/24  dev veth2
-	ip -netns ${NS2}    addr add ${IPv4_3}/24  dev veth3
-	ip -netns ${NS3}    addr add ${IPv4_4}/24  dev veth4
-	ip -netns ${NS1} -6 addr add ${IPv6_1}/128 nodad dev veth1
-	ip -netns ${NS2} -6 addr add ${IPv6_2}/128 nodad dev veth2
-	ip -netns ${NS2} -6 addr add ${IPv6_3}/128 nodad dev veth3
-	ip -netns ${NS3} -6 addr add ${IPv6_4}/128 nodad dev veth4
-
-	# configure addresses: the bottom route (5-6-7-8)
-	ip -netns ${NS1}    addr add ${IPv4_5}/24  dev veth5
-	ip -netns ${NS2}    addr add ${IPv4_6}/24  dev veth6
-	ip -netns ${NS2}    addr add ${IPv4_7}/24  dev veth7
-	ip -netns ${NS3}    addr add ${IPv4_8}/24  dev veth8
-	ip -netns ${NS1} -6 addr add ${IPv6_5}/128 nodad dev veth5
-	ip -netns ${NS2} -6 addr add ${IPv6_6}/128 nodad dev veth6
-	ip -netns ${NS2} -6 addr add ${IPv6_7}/128 nodad dev veth7
-	ip -netns ${NS3} -6 addr add ${IPv6_8}/128 nodad dev veth8
-
-	ip -netns ${NS1} link set dev veth1 up
-	ip -netns ${NS2} link set dev veth2 up
-	ip -netns ${NS2} link set dev veth3 up
-	ip -netns ${NS3} link set dev veth4 up
-	ip -netns ${NS1} link set dev veth5 up
-	ip -netns ${NS2} link set dev veth6 up
-	ip -netns ${NS2} link set dev veth7 up
-	ip -netns ${NS3} link set dev veth8 up
-
-	# configure routes: IP*_SRC -> veth1/IP*_2 (= top route) default;
-	# the bottom route to specific bottom addresses
-
-	# NS1
-	# top route
-	ip -netns ${NS1}    route add ${IPv4_2}/32  dev veth1 ${VRF}
-	ip -netns ${NS1}    route add default dev veth1 via ${IPv4_2} ${VRF}  # go top by default
-	ip -netns ${NS1} -6 route add ${IPv6_2}/128 dev veth1 ${VRF}
-	ip -netns ${NS1} -6 route add default dev veth1 via ${IPv6_2} ${VRF}  # go top by default
-	# bottom route
-	ip -netns ${NS1}    route add ${IPv4_6}/32  dev veth5 ${VRF}
-	ip -netns ${NS1}    route add ${IPv4_7}/32  dev veth5 via ${IPv4_6} ${VRF}
-	ip -netns ${NS1}    route add ${IPv4_8}/32  dev veth5 via ${IPv4_6} ${VRF}
-	ip -netns ${NS1} -6 route add ${IPv6_6}/128 dev veth5 ${VRF}
-	ip -netns ${NS1} -6 route add ${IPv6_7}/128 dev veth5 via ${IPv6_6} ${VRF}
-	ip -netns ${NS1} -6 route add ${IPv6_8}/128 dev veth5 via ${IPv6_6} ${VRF}
-
-	# NS2
-	# top route
-	ip -netns ${NS2}    route add ${IPv4_1}/32  dev veth2 ${VRF}
-	ip -netns ${NS2}    route add ${IPv4_4}/32  dev veth3 ${VRF}
-	ip -netns ${NS2} -6 route add ${IPv6_1}/128 dev veth2 ${VRF}
-	ip -netns ${NS2} -6 route add ${IPv6_4}/128 dev veth3 ${VRF}
-	# bottom route
-	ip -netns ${NS2}    route add ${IPv4_5}/32  dev veth6 ${VRF}
-	ip -netns ${NS2}    route add ${IPv4_8}/32  dev veth7 ${VRF}
-	ip -netns ${NS2} -6 route add ${IPv6_5}/128 dev veth6 ${VRF}
-	ip -netns ${NS2} -6 route add ${IPv6_8}/128 dev veth7 ${VRF}
-
-	# NS3
-	# top route
-	ip -netns ${NS3}    route add ${IPv4_3}/32  dev veth4
-	ip -netns ${NS3}    route add ${IPv4_1}/32  dev veth4 via ${IPv4_3}
-	ip -netns ${NS3}    route add ${IPv4_2}/32  dev veth4 via ${IPv4_3}
-	ip -netns ${NS3} -6 route add ${IPv6_3}/128 dev veth4
-	ip -netns ${NS3} -6 route add ${IPv6_1}/128 dev veth4 via ${IPv6_3}
-	ip -netns ${NS3} -6 route add ${IPv6_2}/128 dev veth4 via ${IPv6_3}
-	# bottom route
-	ip -netns ${NS3}    route add ${IPv4_7}/32  dev veth8
-	ip -netns ${NS3}    route add ${IPv4_5}/32  dev veth8 via ${IPv4_7}
-	ip -netns ${NS3}    route add ${IPv4_6}/32  dev veth8 via ${IPv4_7}
-	ip -netns ${NS3} -6 route add ${IPv6_7}/128 dev veth8
-	ip -netns ${NS3} -6 route add ${IPv6_5}/128 dev veth8 via ${IPv6_7}
-	ip -netns ${NS3} -6 route add ${IPv6_6}/128 dev veth8 via ${IPv6_7}
-
-	# configure IPv4 GRE device in NS3, and a route to it via the "bottom" route
-	ip -netns ${NS3} tunnel add gre_dev mode gre remote ${IPv4_1} local ${IPv4_GRE} ttl 255
-	ip -netns ${NS3} link set gre_dev up
-	ip -netns ${NS3} addr add ${IPv4_GRE} dev gre_dev
-	ip -netns ${NS1} route add ${IPv4_GRE}/32 dev veth5 via ${IPv4_6} ${VRF}
-	ip -netns ${NS2} route add ${IPv4_GRE}/32 dev veth7 via ${IPv4_8} ${VRF}
-
-
-	# configure IPv6 GRE device in NS3, and a route to it via the "bottom" route
-	ip -netns ${NS3} -6 tunnel add name gre6_dev mode ip6gre remote ${IPv6_1} local ${IPv6_GRE} ttl 255
-	ip -netns ${NS3} link set gre6_dev up
-	ip -netns ${NS3} -6 addr add ${IPv6_GRE} nodad dev gre6_dev
-	ip -netns ${NS1} -6 route add ${IPv6_GRE}/128 dev veth5 via ${IPv6_6} ${VRF}
-	ip -netns ${NS2} -6 route add ${IPv6_GRE}/128 dev veth7 via ${IPv6_8} ${VRF}
-
-	TMPFILE=$(mktemp /tmp/test_lwt_ip_encap.XXXXXX)
-
-	sleep 1  # reduce flakiness
-	set +e
-}
-
-cleanup()
-{
-	if [ -f ${TMPFILE} ] ; then
-		rm ${TMPFILE}
-	fi
-
-	ip netns del ${NS1} 2> /dev/null
-	ip netns del ${NS2} 2> /dev/null
-	ip netns del ${NS3} 2> /dev/null
-}
-
-trap cleanup EXIT
-
-remove_routes_to_gredev()
-{
-	ip -netns ${NS1} route del ${IPv4_GRE} dev veth5 ${VRF}
-	ip -netns ${NS2} route del ${IPv4_GRE} dev veth7 ${VRF}
-	ip -netns ${NS1} -6 route del ${IPv6_GRE}/128 dev veth5 ${VRF}
-	ip -netns ${NS2} -6 route del ${IPv6_GRE}/128 dev veth7 ${VRF}
-}
-
-add_unreachable_routes_to_gredev()
-{
-	ip -netns ${NS1} route add unreachable ${IPv4_GRE}/32 ${VRF}
-	ip -netns ${NS2} route add unreachable ${IPv4_GRE}/32 ${VRF}
-	ip -netns ${NS1} -6 route add unreachable ${IPv6_GRE}/128 ${VRF}
-	ip -netns ${NS2} -6 route add unreachable ${IPv6_GRE}/128 ${VRF}
-}
-
-test_ping()
-{
-	local readonly PROTO=$1
-	local readonly EXPECTED=$2
-	local RET=0
-
-	if [ "${PROTO}" == "IPv4" ] ; then
-		ip netns exec ${NS1} ping  -c 1 -W 1 -I veth1 ${IPv4_DST} 2>&1 > /dev/null
-		RET=$?
-	elif [ "${PROTO}" == "IPv6" ] ; then
-		ip netns exec ${NS1} ping6 -c 1 -W 1 -I veth1 ${IPv6_DST} 2>&1 > /dev/null
-		RET=$?
-	else
-		echo "    test_ping: unknown PROTO: ${PROTO}"
-		TEST_STATUS=1
-	fi
-
-	if [ "0" != "${RET}" ]; then
-		RET=1
-	fi
-
-	if [ "${EXPECTED}" != "${RET}" ] ; then
-		echo "    test_ping failed: expected: ${EXPECTED}; got ${RET}"
-		TEST_STATUS=1
-	fi
-}
-
-test_gso()
-{
-	local readonly PROTO=$1
-	local readonly PKT_SZ=5000
-	local IP_DST=""
-	: > ${TMPFILE}  # trim the capture file
-
-	# check that nc is present
-	command -v nc >/dev/null 2>&1 || \
-		{ echo >&2 "nc is not available: skipping TSO tests"; return; }
-
-	# listen on port 9000, capture TCP into $TMPFILE
-	if [ "${PROTO}" == "IPv4" ] ; then
-		IP_DST=${IPv4_DST}
-		ip netns exec ${NS3} bash -c \
-			"nc -4 -l -p 9000 > ${TMPFILE} &"
-	elif [ "${PROTO}" == "IPv6" ] ; then
-		IP_DST=${IPv6_DST}
-		ip netns exec ${NS3} bash -c \
-			"nc -6 -l -p 9000 > ${TMPFILE} &"
-		RET=$?
-	else
-		echo "    test_gso: unknown PROTO: ${PROTO}"
-		TEST_STATUS=1
-	fi
-	sleep 1  # let nc start listening
-
-	# send a packet larger than MTU
-	ip netns exec ${NS1} bash -c \
-		"dd if=/dev/zero bs=$PKT_SZ count=1 > /dev/tcp/${IP_DST}/9000 2>/dev/null"
-	sleep 2 # let the packet get delivered
-
-	# verify we received all expected bytes
-	SZ=$(stat -c %s ${TMPFILE})
-	if [ "$SZ" != "$PKT_SZ" ] ; then
-		echo "    test_gso failed: ${PROTO}"
-		TEST_STATUS=1
-	fi
-}
-
-test_egress()
-{
-	local readonly ENCAP=$1
-	echo "starting egress ${ENCAP} encap test ${VRF}"
-	setup
-
-	# by default, pings work
-	test_ping IPv4 0
-	test_ping IPv6 0
-
-	# remove NS2->DST routes, ping fails
-	ip -netns ${NS2}    route del ${IPv4_DST}/32  dev veth3 ${VRF}
-	ip -netns ${NS2} -6 route del ${IPv6_DST}/128 dev veth3 ${VRF}
-	test_ping IPv4 1
-	test_ping IPv6 1
-
-	# install replacement routes (LWT/eBPF), pings succeed
-	if [ "${ENCAP}" == "IPv4" ] ; then
-		ip -netns ${NS1} route add ${IPv4_DST} encap bpf xmit obj \
-			${BPF_FILE} sec encap_gre dev veth1 ${VRF}
-		ip -netns ${NS1} -6 route add ${IPv6_DST} encap bpf xmit obj \
-			${BPF_FILE} sec encap_gre dev veth1 ${VRF}
-	elif [ "${ENCAP}" == "IPv6" ] ; then
-		ip -netns ${NS1} route add ${IPv4_DST} encap bpf xmit obj \
-			${BPF_FILE} sec encap_gre6 dev veth1 ${VRF}
-		ip -netns ${NS1} -6 route add ${IPv6_DST} encap bpf xmit obj \
-			${BPF_FILE} sec encap_gre6 dev veth1 ${VRF}
-	else
-		echo "    unknown encap ${ENCAP}"
-		TEST_STATUS=1
-	fi
-	test_ping IPv4 0
-	test_ping IPv6 0
-
-	# skip GSO tests with VRF: VRF routing needs properly assigned
-	# source IP/device, which is easy to do with ping and hard with dd/nc.
-	if [ -z "${VRF}" ] ; then
-		test_gso IPv4
-		test_gso IPv6
-	fi
-
-	# a negative test: remove routes to GRE devices: ping fails
-	remove_routes_to_gredev
-	test_ping IPv4 1
-	test_ping IPv6 1
-
-	# another negative test
-	add_unreachable_routes_to_gredev
-	test_ping IPv4 1
-	test_ping IPv6 1
-
-	cleanup
-	process_test_results
-}
-
-test_ingress()
-{
-	local readonly ENCAP=$1
-	echo "starting ingress ${ENCAP} encap test ${VRF}"
-	setup
-
-	# need to wait a bit for IPv6 to autoconf, otherwise
-	# ping6 sometimes fails with "unable to bind to address"
-
-	# by default, pings work
-	test_ping IPv4 0
-	test_ping IPv6 0
-
-	# remove NS2->DST routes, pings fail
-	ip -netns ${NS2}    route del ${IPv4_DST}/32  dev veth3 ${VRF}
-	ip -netns ${NS2} -6 route del ${IPv6_DST}/128 dev veth3 ${VRF}
-	test_ping IPv4 1
-	test_ping IPv6 1
-
-	# install replacement routes (LWT/eBPF), pings succeed
-	if [ "${ENCAP}" == "IPv4" ] ; then
-		ip -netns ${NS2} route add ${IPv4_DST} encap bpf in obj \
-			${BPF_FILE} sec encap_gre dev veth2 ${VRF}
-		ip -netns ${NS2} -6 route add ${IPv6_DST} encap bpf in obj \
-			${BPF_FILE} sec encap_gre dev veth2 ${VRF}
-	elif [ "${ENCAP}" == "IPv6" ] ; then
-		ip -netns ${NS2} route add ${IPv4_DST} encap bpf in obj \
-			${BPF_FILE} sec encap_gre6 dev veth2 ${VRF}
-		ip -netns ${NS2} -6 route add ${IPv6_DST} encap bpf in obj \
-			${BPF_FILE} sec encap_gre6 dev veth2 ${VRF}
-	else
-		echo "FAIL: unknown encap ${ENCAP}"
-		TEST_STATUS=1
-	fi
-	test_ping IPv4 0
-	test_ping IPv6 0
-
-	# a negative test: remove routes to GRE devices: ping fails
-	remove_routes_to_gredev
-	test_ping IPv4 1
-	test_ping IPv6 1
-
-	# another negative test
-	add_unreachable_routes_to_gredev
-	test_ping IPv4 1
-	test_ping IPv6 1
-
-	cleanup
-	process_test_results
-}
-
-VRF=""
-test_egress IPv4
-test_egress IPv6
-test_ingress IPv4
-test_ingress IPv6
-
-VRF="vrf red"
-test_egress IPv4
-test_egress IPv6
-test_ingress IPv4
-test_ingress IPv6
-
-print_test_summary_and_exit
diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh
deleted file mode 100755
index 0efea2292d6a..000000000000
--- a/tools/testing/selftests/bpf/test_lwt_seg6local.sh
+++ /dev/null
@@ -1,156 +0,0 @@
-#!/bin/bash
-# Connects 6 network namespaces through veths.
-# Each NS may have different IPv6 global scope addresses :
-#   NS1 ---- NS2 ---- NS3 ---- NS4 ---- NS5 ---- NS6
-# fb00::1           fd00::1  fd00::2  fd00::3  fb00::6
-#                   fc42::1           fd00::4
-#
-# All IPv6 packets going to fb00::/16 through NS2 will be encapsulated in a
-# IPv6 header with a Segment Routing Header, with segments :
-# 	fd00::1 -> fd00::2 -> fd00::3 -> fd00::4
-#
-# 3 fd00::/16 IPv6 addresses are binded to seg6local End.BPF actions :
-# - fd00::1 : add a TLV, change the flags and apply a End.X action to fc42::1
-# - fd00::2 : remove the TLV, change the flags, add a tag
-# - fd00::3 : apply an End.T action to fd00::4, through routing table 117
-#
-# fd00::4 is a simple Segment Routing node decapsulating the inner IPv6 packet.
-# Each End.BPF action will validate the operations applied on the SRH by the
-# previous BPF program in the chain, otherwise the packet is dropped.
-#
-# An UDP datagram is sent from fb00::1 to fb00::6. The test succeeds if this
-# datagram can be read on NS6 when binding to fb00::6.
-
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-BPF_FILE="test_lwt_seg6local.bpf.o"
-readonly NS1="ns1-$(mktemp -u XXXXXX)"
-readonly NS2="ns2-$(mktemp -u XXXXXX)"
-readonly NS3="ns3-$(mktemp -u XXXXXX)"
-readonly NS4="ns4-$(mktemp -u XXXXXX)"
-readonly NS5="ns5-$(mktemp -u XXXXXX)"
-readonly NS6="ns6-$(mktemp -u XXXXXX)"
-
-msg="skip all tests:"
-if [ $UID != 0 ]; then
-	echo $msg please run this as root >&2
-	exit $ksft_skip
-fi
-
-TMP_FILE="/tmp/selftest_lwt_seg6local.txt"
-
-cleanup()
-{
-	if [ "$?" = "0" ]; then
-		echo "selftests: test_lwt_seg6local [PASS]";
-	else
-		echo "selftests: test_lwt_seg6local [FAILED]";
-	fi
-
-	set +e
-	ip netns del ${NS1} 2> /dev/null
-	ip netns del ${NS2} 2> /dev/null
-	ip netns del ${NS3} 2> /dev/null
-	ip netns del ${NS4} 2> /dev/null
-	ip netns del ${NS5} 2> /dev/null
-	ip netns del ${NS6} 2> /dev/null
-	rm -f $TMP_FILE
-}
-
-set -e
-
-ip netns add ${NS1}
-ip netns add ${NS2}
-ip netns add ${NS3}
-ip netns add ${NS4}
-ip netns add ${NS5}
-ip netns add ${NS6}
-
-trap cleanup 0 2 3 6 9
-
-ip link add veth1 type veth peer name veth2
-ip link add veth3 type veth peer name veth4
-ip link add veth5 type veth peer name veth6
-ip link add veth7 type veth peer name veth8
-ip link add veth9 type veth peer name veth10
-
-ip link set veth1 netns ${NS1}
-ip link set veth2 netns ${NS2}
-ip link set veth3 netns ${NS2}
-ip link set veth4 netns ${NS3}
-ip link set veth5 netns ${NS3}
-ip link set veth6 netns ${NS4}
-ip link set veth7 netns ${NS4}
-ip link set veth8 netns ${NS5}
-ip link set veth9 netns ${NS5}
-ip link set veth10 netns ${NS6}
-
-ip netns exec ${NS1} ip link set dev veth1 up
-ip netns exec ${NS2} ip link set dev veth2 up
-ip netns exec ${NS2} ip link set dev veth3 up
-ip netns exec ${NS3} ip link set dev veth4 up
-ip netns exec ${NS3} ip link set dev veth5 up
-ip netns exec ${NS4} ip link set dev veth6 up
-ip netns exec ${NS4} ip link set dev veth7 up
-ip netns exec ${NS5} ip link set dev veth8 up
-ip netns exec ${NS5} ip link set dev veth9 up
-ip netns exec ${NS6} ip link set dev veth10 up
-ip netns exec ${NS6} ip link set dev lo up
-
-# All link scope addresses and routes required between veths
-ip netns exec ${NS1} ip -6 addr add fb00::12/16 dev veth1 scope link
-ip netns exec ${NS1} ip -6 route add fb00::21 dev veth1 scope link
-ip netns exec ${NS2} ip -6 addr add fb00::21/16 dev veth2 scope link
-ip netns exec ${NS2} ip -6 addr add fb00::34/16 dev veth3 scope link
-ip netns exec ${NS2} ip -6 route add fb00::43 dev veth3 scope link
-ip netns exec ${NS3} ip -6 route add fb00::65 dev veth5 scope link
-ip netns exec ${NS3} ip -6 addr add fb00::43/16 dev veth4 scope link
-ip netns exec ${NS3} ip -6 addr add fb00::56/16 dev veth5 scope link
-ip netns exec ${NS4} ip -6 addr add fb00::65/16 dev veth6 scope link
-ip netns exec ${NS4} ip -6 addr add fb00::78/16 dev veth7 scope link
-ip netns exec ${NS4} ip -6 route add fb00::87 dev veth7 scope link
-ip netns exec ${NS5} ip -6 addr add fb00::87/16 dev veth8 scope link
-ip netns exec ${NS5} ip -6 addr add fb00::910/16 dev veth9 scope link
-ip netns exec ${NS5} ip -6 route add fb00::109 dev veth9 scope link
-ip netns exec ${NS5} ip -6 route add fb00::109 table 117 dev veth9 scope link
-ip netns exec ${NS6} ip -6 addr add fb00::109/16 dev veth10 scope link
-
-ip netns exec ${NS1} ip -6 addr add fb00::1/16 dev lo
-ip netns exec ${NS1} ip -6 route add fb00::6 dev veth1 via fb00::21
-
-ip netns exec ${NS2} ip -6 route add fb00::6 encap bpf in obj ${BPF_FILE} sec encap_srh dev veth2
-ip netns exec ${NS2} ip -6 route add fd00::1 dev veth3 via fb00::43 scope link
-
-ip netns exec ${NS3} ip -6 route add fc42::1 dev veth5 via fb00::65
-ip netns exec ${NS3} ip -6 route add fd00::1 encap seg6local action End.BPF endpoint obj ${BPF_FILE} sec add_egr_x dev veth4
-
-ip netns exec ${NS4} ip -6 route add fd00::2 encap seg6local action End.BPF endpoint obj ${BPF_FILE} sec pop_egr dev veth6
-ip netns exec ${NS4} ip -6 addr add fc42::1 dev lo
-ip netns exec ${NS4} ip -6 route add fd00::3 dev veth7 via fb00::87
-
-ip netns exec ${NS5} ip -6 route add fd00::4 table 117 dev veth9 via fb00::109
-ip netns exec ${NS5} ip -6 route add fd00::3 encap seg6local action End.BPF endpoint obj ${BPF_FILE} sec inspect_t dev veth8
-
-ip netns exec ${NS6} ip -6 addr add fb00::6/16 dev lo
-ip netns exec ${NS6} ip -6 addr add fd00::4/16 dev lo
-
-ip netns exec ${NS1} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
-ip netns exec ${NS2} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
-ip netns exec ${NS3} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
-ip netns exec ${NS4} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
-ip netns exec ${NS5} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
-
-ip netns exec ${NS6} sysctl net.ipv6.conf.all.seg6_enabled=1 > /dev/null
-ip netns exec ${NS6} sysctl net.ipv6.conf.lo.seg6_enabled=1 > /dev/null
-ip netns exec ${NS6} sysctl net.ipv6.conf.veth10.seg6_enabled=1 > /dev/null
-
-ip netns exec ${NS6} nc -l -6 -u -d 7330 > $TMP_FILE &
-ip netns exec ${NS1} bash -c "echo 'foobar' | nc -w0 -6 -u -p 2121 -s fb00::1 fb00::6 7330"
-sleep 5 # wait enough time to ensure the UDP datagram arrived to the last segment
-kill -TERM $!
-
-if [[ $(< $TMP_FILE) != "foobar" ]]; then
-	exit 1
-fi
-
-exit 0
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index b73152822aa2..ccc5acd55ff9 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -26,10 +26,6 @@
 #include "test_maps.h"
 #include "testing_helpers.h"
 
-#ifndef ENOTSUPP
-#define ENOTSUPP 524
-#endif
-
 int skips;
 
 static struct bpf_map_create_opts map_opts = { .sz = sizeof(map_opts) };
@@ -539,7 +535,7 @@ static void test_devmap_hash(unsigned int task, void *data)
 static void test_queuemap(unsigned int task, void *data)
 {
 	const int MAP_SIZE = 32;
-	__u32 vals[MAP_SIZE + MAP_SIZE/2], val;
+	__u32 vals[MAP_SIZE + MAP_SIZE/2], val = 0;
 	int fd, i;
 
 	/* Fill test values to be used */
@@ -595,7 +591,7 @@ static void test_queuemap(unsigned int task, void *data)
 static void test_stackmap(unsigned int task, void *data)
 {
 	const int MAP_SIZE = 32;
-	__u32 vals[MAP_SIZE + MAP_SIZE/2], val;
+	__u32 vals[MAP_SIZE + MAP_SIZE/2], val = 0;
 	int fd, i;
 
 	/* Fill test values to be used */
@@ -1190,7 +1186,11 @@ static void test_map_in_map(void)
 		goto out_map_in_map;
 	}
 
-	bpf_object__load(obj);
+	err = bpf_object__load(obj);
+	if (err) {
+		printf("Failed to load test prog\n");
+		goto out_map_in_map;
+	}
 
 	map = bpf_object__find_map_by_name(obj, "mim_array");
 	if (!map) {
@@ -1275,7 +1275,7 @@ static void test_map_in_map(void)
 			goto out_map_in_map;
 		}
 
-		err = bpf_obj_get_info_by_fd(fd, &info, &len);
+		err = bpf_map_get_info_by_fd(fd, &info, &len);
 		if (err) {
 			printf("Failed to get map info by fd %d: %d", fd,
 			       errno);
@@ -1396,13 +1396,20 @@ static void test_map_stress(void)
 #define MAX_DELAY_US 50000
 #define MIN_DELAY_RANGE_US 5000
 
-static int map_update_retriable(int map_fd, const void *key, const void *value,
-				int flags, int attempts)
+static bool can_retry(int err)
+{
+	return (err == EAGAIN || err == EBUSY ||
+		((err == ENOMEM || err == E2BIG) &&
+		 map_opts.map_flags == BPF_F_NO_PREALLOC));
+}
+
+int map_update_retriable(int map_fd, const void *key, const void *value, int flags, int attempts,
+			 retry_for_error_fn need_retry)
 {
 	int delay = rand() % MIN_DELAY_RANGE_US;
 
 	while (bpf_map_update_elem(map_fd, key, value, flags)) {
-		if (!attempts || (errno != EAGAIN && errno != EBUSY))
+		if (!attempts || !need_retry(errno))
 			return -errno;
 
 		if (delay <= MAX_DELAY_US / 2)
@@ -1445,11 +1452,13 @@ static void test_update_delete(unsigned int fn, void *data)
 		key = value = i;
 
 		if (do_update) {
-			err = map_update_retriable(fd, &key, &value, BPF_NOEXIST, MAP_RETRIES);
+			err = map_update_retriable(fd, &key, &value, BPF_NOEXIST, MAP_RETRIES,
+						   can_retry);
 			if (err)
 				printf("error %d %d\n", err, errno);
 			assert(err == 0);
-			err = map_update_retriable(fd, &key, &value, BPF_EXIST, MAP_RETRIES);
+			err = map_update_retriable(fd, &key, &value, BPF_EXIST, MAP_RETRIES,
+						   can_retry);
 			if (err)
 				printf("error %d %d\n", err, errno);
 			assert(err == 0);
@@ -1504,7 +1513,7 @@ again:
 		       value == key);
 	}
 
-	/* Now let's delete all elemenets in parallel. */
+	/* Now let's delete all elements in parallel. */
 	data[1] = DO_DELETE;
 	run_parallel(TASKS, test_update_delete, data);
 
diff --git a/tools/testing/selftests/bpf/test_maps.h b/tools/testing/selftests/bpf/test_maps.h
index f6fbca761732..e4ac704a536c 100644
--- a/tools/testing/selftests/bpf/test_maps.h
+++ b/tools/testing/selftests/bpf/test_maps.h
@@ -4,6 +4,7 @@
 
 #include <stdio.h>
 #include <stdlib.h>
+#include <stdbool.h>
 
 #define CHECK(condition, tag, format...) ({				\
 	int __ret = !!(condition);					\
@@ -16,4 +17,8 @@
 
 extern int skips;
 
+typedef bool (*retry_for_error_fn)(int err);
+int map_update_retriable(int map_fd, const void *key, const void *value, int flags, int attempts,
+			 retry_for_error_fn need_retry);
+
 #endif
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 4716e38e153a..02a85dda30e6 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -10,13 +10,38 @@
 #include <sched.h>
 #include <signal.h>
 #include <string.h>
-#include <execinfo.h> /* backtrace */
-#include <linux/membarrier.h>
 #include <sys/sysinfo.h> /* get_nprocs */
 #include <netinet/in.h>
 #include <sys/select.h>
 #include <sys/socket.h>
+#include <linux/keyctl.h>
 #include <sys/un.h>
+#include <bpf/btf.h>
+#include <time.h>
+#include "json_writer.h"
+
+#include "network_helpers.h"
+#include "verification_cert.h"
+
+/* backtrace() and backtrace_symbols_fd() are glibc specific,
+ * use header file when glibc is available and provide stub
+ * implementations when another libc implementation is used.
+ */
+#ifdef __GLIBC__
+#include <execinfo.h> /* backtrace */
+#else
+__weak int backtrace(void **buffer, int size)
+{
+	return 0;
+}
+
+__weak void backtrace_symbols_fd(void *const *buffer, int size, int fd)
+{
+	dprintf(fd, "<backtrace not supported>\n");
+}
+#endif /*__GLIBC__ */
+
+int env_verbosity = 0;
 
 static bool verbose(void)
 {
@@ -36,15 +61,15 @@ static void stdio_hijack_init(char **log_buf, size_t *log_cnt)
 
 	stdout = open_memstream(log_buf, log_cnt);
 	if (!stdout) {
-		stdout = env.stdout;
+		stdout = env.stdout_saved;
 		perror("open_memstream");
 		return;
 	}
 
 	if (env.subtest_state)
-		env.subtest_state->stdout = stdout;
+		env.subtest_state->stdout_saved = stdout;
 	else
-		env.test_state->stdout = stdout;
+		env.test_state->stdout_saved = stdout;
 
 	stderr = stdout;
 #endif
@@ -58,14 +83,16 @@ static void stdio_hijack(char **log_buf, size_t *log_cnt)
 		return;
 	}
 
-	env.stdout = stdout;
-	env.stderr = stderr;
+	env.stdout_saved = stdout;
+	env.stderr_saved = stderr;
 
 	stdio_hijack_init(log_buf, log_cnt);
 #endif
 }
 
-static void stdio_restore_cleanup(void)
+static pthread_mutex_t stdout_lock = PTHREAD_MUTEX_INITIALIZER;
+
+static void stdio_restore(void)
 {
 #ifdef __GLIBC__
 	if (verbose() && env.worker_id == -1) {
@@ -75,34 +102,33 @@ static void stdio_restore_cleanup(void)
 
 	fflush(stdout);
 
+	pthread_mutex_lock(&stdout_lock);
+
 	if (env.subtest_state) {
-		fclose(env.subtest_state->stdout);
-		env.subtest_state->stdout = NULL;
-		stdout = env.test_state->stdout;
-		stderr = env.test_state->stdout;
+		if (env.subtest_state->stdout_saved)
+			fclose(env.subtest_state->stdout_saved);
+		env.subtest_state->stdout_saved = NULL;
+		stdout = env.test_state->stdout_saved;
+		stderr = env.test_state->stdout_saved;
 	} else {
-		fclose(env.test_state->stdout);
-		env.test_state->stdout = NULL;
+		if (env.test_state->stdout_saved)
+			fclose(env.test_state->stdout_saved);
+		env.test_state->stdout_saved = NULL;
+		stdout = env.stdout_saved;
+		stderr = env.stderr_saved;
 	}
+
+	pthread_mutex_unlock(&stdout_lock);
 #endif
 }
 
-static void stdio_restore(void)
+static int traffic_monitor_print_fn(const char *format, va_list args)
 {
-#ifdef __GLIBC__
-	if (verbose() && env.worker_id == -1) {
-		/* nothing to do, output to stdout by default */
-		return;
-	}
-
-	if (stdout == env.stdout)
-		return;
-
-	stdio_restore_cleanup();
+	pthread_mutex_lock(&stdout_lock);
+	vfprintf(stdout, format, args);
+	pthread_mutex_unlock(&stdout_lock);
 
-	stdout = env.stdout;
-	stderr = env.stderr;
-#endif
+	return 0;
 }
 
 /* Adapted from perf/util/string.c */
@@ -140,6 +166,7 @@ struct prog_test_def {
 	void (*run_serial_test)(void);
 	bool should_run;
 	bool need_cgroup_cleanup;
+	bool should_tmon;
 };
 
 /* Override C runtime library's usleep() implementation to ensure nanosleep()
@@ -156,6 +183,88 @@ int usleep(useconds_t usec)
 	return syscall(__NR_nanosleep, &ts, NULL);
 }
 
+/* Watchdog timer is started by watchdog_start() and stopped by watchdog_stop().
+ * If timer is active for longer than env.secs_till_notify,
+ * it prints the name of the current test to the stderr.
+ * If timer is active for longer than env.secs_till_kill,
+ * it kills the thread executing the test by sending a SIGSEGV signal to it.
+ */
+static void watchdog_timer_func(union sigval sigval)
+{
+	struct itimerspec timeout = {};
+	char test_name[256];
+	int err;
+
+	if (env.subtest_state)
+		snprintf(test_name, sizeof(test_name), "%s/%s",
+			 env.test->test_name, env.subtest_state->name);
+	else
+		snprintf(test_name, sizeof(test_name), "%s",
+			 env.test->test_name);
+
+	switch (env.watchdog_state) {
+	case WD_NOTIFY:
+		fprintf(env.stderr_saved, "WATCHDOG: test case %s executes for %d seconds...\n",
+			test_name, env.secs_till_notify);
+		timeout.it_value.tv_sec = env.secs_till_kill - env.secs_till_notify;
+		env.watchdog_state = WD_KILL;
+		err = timer_settime(env.watchdog, 0, &timeout, NULL);
+		if (err)
+			fprintf(env.stderr_saved, "Failed to arm watchdog timer\n");
+		break;
+	case WD_KILL:
+		fprintf(env.stderr_saved,
+			"WATCHDOG: test case %s executes for %d seconds, terminating with SIGSEGV\n",
+			test_name, env.secs_till_kill);
+		pthread_kill(env.main_thread, SIGSEGV);
+		break;
+	}
+}
+
+static void watchdog_start(void)
+{
+	struct itimerspec timeout = {};
+	int err;
+
+	if (env.secs_till_kill == 0)
+		return;
+	if (env.secs_till_notify > 0) {
+		env.watchdog_state = WD_NOTIFY;
+		timeout.it_value.tv_sec = env.secs_till_notify;
+	} else {
+		env.watchdog_state = WD_KILL;
+		timeout.it_value.tv_sec = env.secs_till_kill;
+	}
+	err = timer_settime(env.watchdog, 0, &timeout, NULL);
+	if (err)
+		fprintf(env.stderr_saved, "Failed to start watchdog timer\n");
+}
+
+static void watchdog_stop(void)
+{
+	struct itimerspec timeout = {};
+	int err;
+
+	env.watchdog_state = WD_NOTIFY;
+	err = timer_settime(env.watchdog, 0, &timeout, NULL);
+	if (err)
+		fprintf(env.stderr_saved, "Failed to stop watchdog timer\n");
+}
+
+static void watchdog_init(void)
+{
+	struct sigevent watchdog_sev = {
+		.sigev_notify = SIGEV_THREAD,
+		.sigev_notify_function = watchdog_timer_func,
+	};
+	int err;
+
+	env.main_thread = pthread_self();
+	err = timer_create(CLOCK_MONOTONIC, &watchdog_sev, &env.watchdog);
+	if (err)
+		fprintf(stderr, "Failed to initialize watchdog timer\n");
+}
+
 static bool should_run(struct test_selector *sel, int num, const char *name)
 {
 	int i;
@@ -177,46 +286,59 @@ static bool should_run(struct test_selector *sel, int num, const char *name)
 	return num < sel->num_set_len && sel->num_set[num];
 }
 
-static bool should_run_subtest(struct test_selector *sel,
-			       struct test_selector *subtest_sel,
-			       int subtest_num,
-			       const char *test_name,
-			       const char *subtest_name)
+static bool match_subtest(struct test_filter_set *filter,
+			  const char *test_name,
+			  const char *subtest_name)
 {
 	int i, j;
 
-	for (i = 0; i < sel->blacklist.cnt; i++) {
-		if (glob_match(test_name, sel->blacklist.tests[i].name)) {
-			if (!sel->blacklist.tests[i].subtest_cnt)
-				return false;
-
-			for (j = 0; j < sel->blacklist.tests[i].subtest_cnt; j++) {
-				if (glob_match(subtest_name,
-					       sel->blacklist.tests[i].subtests[j]))
-					return false;
-			}
-		}
-	}
-
-	for (i = 0; i < sel->whitelist.cnt; i++) {
-		if (glob_match(test_name, sel->whitelist.tests[i].name)) {
-			if (!sel->whitelist.tests[i].subtest_cnt)
+	for (i = 0; i < filter->cnt; i++) {
+		if (glob_match(test_name, filter->tests[i].name)) {
+			if (!filter->tests[i].subtest_cnt)
 				return true;
 
-			for (j = 0; j < sel->whitelist.tests[i].subtest_cnt; j++) {
+			for (j = 0; j < filter->tests[i].subtest_cnt; j++) {
 				if (glob_match(subtest_name,
-					       sel->whitelist.tests[i].subtests[j]))
+					       filter->tests[i].subtests[j]))
 					return true;
 			}
 		}
 	}
 
+	return false;
+}
+
+static bool should_run_subtest(struct test_selector *sel,
+			       struct test_selector *subtest_sel,
+			       int subtest_num,
+			       const char *test_name,
+			       const char *subtest_name)
+{
+	if (match_subtest(&sel->blacklist, test_name, subtest_name))
+		return false;
+
+	if (match_subtest(&sel->whitelist, test_name, subtest_name))
+		return true;
+
 	if (!sel->whitelist.cnt && !subtest_sel->num_set)
 		return true;
 
 	return subtest_num < subtest_sel->num_set_len && subtest_sel->num_set[subtest_num];
 }
 
+static bool should_tmon(struct test_selector *sel, const char *name)
+{
+	int i;
+
+	for (i = 0; i < sel->whitelist.cnt; i++) {
+		if (glob_match(name, sel->whitelist.tests[i].name) &&
+		    !sel->whitelist.tests[i].subtest_cnt)
+			return true;
+	}
+
+	return false;
+}
+
 static char *test_result(bool failed, bool skipped)
 {
 	return failed ? "FAIL" : (skipped ? "SKIP" : "OK");
@@ -229,49 +351,62 @@ static void print_test_result(const struct prog_test_def *test, const struct tes
 	int skipped_cnt = test_state->skip_cnt;
 	int subtests_cnt = test_state->subtest_num;
 
-	fprintf(env.stdout, "#%-*d %s:", TEST_NUM_WIDTH, test->test_num, test->test_name);
+	fprintf(env.stdout_saved, "#%-*d %s:", TEST_NUM_WIDTH, test->test_num, test->test_name);
 	if (test_state->error_cnt)
-		fprintf(env.stdout, "FAIL");
+		fprintf(env.stdout_saved, "FAIL");
 	else if (!skipped_cnt)
-		fprintf(env.stdout, "OK");
+		fprintf(env.stdout_saved, "OK");
 	else if (skipped_cnt == subtests_cnt || !subtests_cnt)
-		fprintf(env.stdout, "SKIP");
+		fprintf(env.stdout_saved, "SKIP");
 	else
-		fprintf(env.stdout, "OK (SKIP: %d/%d)", skipped_cnt, subtests_cnt);
+		fprintf(env.stdout_saved, "OK (SKIP: %d/%d)", skipped_cnt, subtests_cnt);
 
-	fprintf(env.stdout, "\n");
+	fprintf(env.stdout_saved, "\n");
 }
 
 static void print_test_log(char *log_buf, size_t log_cnt)
 {
 	log_buf[log_cnt] = '\0';
-	fprintf(env.stdout, "%s", log_buf);
+	fprintf(env.stdout_saved, "%s", log_buf);
 	if (log_buf[log_cnt - 1] != '\n')
-		fprintf(env.stdout, "\n");
+		fprintf(env.stdout_saved, "\n");
 }
 
 static void print_subtest_name(int test_num, int subtest_num,
 			       const char *test_name, char *subtest_name,
 			       char *result)
 {
-	char test_num_str[TEST_NUM_WIDTH + 1];
+	char test_num_str[32];
 
 	snprintf(test_num_str, sizeof(test_num_str), "%d/%d", test_num, subtest_num);
 
-	fprintf(env.stdout, "#%-*s %s/%s",
+	fprintf(env.stdout_saved, "#%-*s %s/%s",
 		TEST_NUM_WIDTH, test_num_str,
 		test_name, subtest_name);
 
 	if (result)
-		fprintf(env.stdout, ":%s", result);
+		fprintf(env.stdout_saved, ":%s", result);
+
+	fprintf(env.stdout_saved, "\n");
+}
 
-	fprintf(env.stdout, "\n");
+static void jsonw_write_log_message(json_writer_t *w, char *log_buf, size_t log_cnt)
+{
+	/* open_memstream (from stdio_hijack_init) ensures that log_bug is terminated by a
+	 * null byte. Yet in parallel mode, log_buf will be NULL if there is no message.
+	 */
+	if (log_cnt) {
+		jsonw_string_field(w, "message", log_buf);
+	} else {
+		jsonw_string_field(w, "message", "");
+	}
 }
 
 static void dump_test_log(const struct prog_test_def *test,
 			  const struct test_state *test_state,
 			  bool skip_ok_subtests,
-			  bool par_exec_result)
+			  bool par_exec_result,
+			  json_writer_t *w)
 {
 	bool test_failed = test_state->error_cnt > 0;
 	bool force_log = test_state->force_log;
@@ -295,6 +430,16 @@ static void dump_test_log(const struct prog_test_def *test,
 	if (test_state->log_cnt && print_test)
 		print_test_log(test_state->log_buf, test_state->log_cnt);
 
+	if (w && print_test) {
+		jsonw_start_object(w);
+		jsonw_string_field(w, "name", test->test_name);
+		jsonw_uint_field(w, "number", test->test_num);
+		jsonw_write_log_message(w, test_state->log_buf, test_state->log_cnt);
+		jsonw_bool_field(w, "failed", test_failed);
+		jsonw_name(w, "subtests");
+		jsonw_start_array(w);
+	}
+
 	for (i = 0; i < test_state->subtest_num; i++) {
 		subtest_state = &test_state->subtest_states[i];
 		subtest_failed = subtest_state->error_cnt;
@@ -313,13 +458,25 @@ static void dump_test_log(const struct prog_test_def *test,
 				   test->test_name, subtest_state->name,
 				   test_result(subtest_state->error_cnt,
 					       subtest_state->skipped));
+
+		if (w && print_subtest) {
+			jsonw_start_object(w);
+			jsonw_string_field(w, "name", subtest_state->name);
+			jsonw_uint_field(w, "number", i+1);
+			jsonw_write_log_message(w, subtest_state->log_buf, subtest_state->log_cnt);
+			jsonw_bool_field(w, "failed", subtest_failed);
+			jsonw_end_object(w);
+		}
+	}
+
+	if (w && print_test) {
+		jsonw_end_array(w);
+		jsonw_end_object(w);
 	}
 
 	print_test_result(test, test_state);
 }
 
-static void stdio_restore(void);
-
 /* A bunch of tests set custom affinity per-thread and/or per-process. Reset
  * it after each test/sub-test.
  */
@@ -334,13 +491,11 @@ static void reset_affinity(void)
 
 	err = sched_setaffinity(0, sizeof(cpuset), &cpuset);
 	if (err < 0) {
-		stdio_restore();
 		fprintf(stderr, "Failed to reset process affinity: %d!\n", err);
 		exit(EXIT_ERR_SETUP_INFRA);
 	}
 	err = pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset);
 	if (err < 0) {
-		stdio_restore();
 		fprintf(stderr, "Failed to reset thread affinity: %d!\n", err);
 		exit(EXIT_ERR_SETUP_INFRA);
 	}
@@ -358,7 +513,6 @@ static void save_netns(void)
 static void restore_netns(void)
 {
 	if (setns(env.saved_netns_fd, CLONE_NEWNET) == -1) {
-		stdio_restore();
 		perror("setns(CLONE_NEWNS)");
 		exit(EXIT_ERR_SETUP_INFRA);
 	}
@@ -385,7 +539,8 @@ void test__end_subtest(void)
 				   test_result(subtest_state->error_cnt,
 					       subtest_state->skipped));
 
-	stdio_restore_cleanup();
+	stdio_restore();
+
 	env.subtest_state = NULL;
 }
 
@@ -413,7 +568,7 @@ bool test__start_subtest(const char *subtest_name)
 	memset(subtest_state, 0, sub_state_size);
 
 	if (!subtest_name || !subtest_name[0]) {
-		fprintf(env.stderr,
+		fprintf(env.stderr_saved,
 			"Subtest #%d didn't provide sub-test name!\n",
 			state->subtest_num);
 		return false;
@@ -421,7 +576,7 @@ bool test__start_subtest(const char *subtest_name)
 
 	subtest_state->name = strdup(subtest_name);
 	if (!subtest_state->name) {
-		fprintf(env.stderr,
+		fprintf(env.stderr_saved,
 			"Subtest #%d: failed to copy subtest name!\n",
 			state->subtest_num);
 		return false;
@@ -436,8 +591,13 @@ bool test__start_subtest(const char *subtest_name)
 		return false;
 	}
 
+	subtest_state->should_tmon = match_subtest(&env.tmon_selector.whitelist,
+						   test->test_name,
+						   subtest_name);
+
 	env.subtest_state = subtest_state;
 	stdio_hijack_init(&subtest_state->log_buf, &subtest_state->log_cnt);
+	watchdog_start();
 
 	return true;
 }
@@ -509,24 +669,6 @@ int bpf_find_map(const char *test, struct bpf_object *obj, const char *name)
 	return bpf_map__fd(map);
 }
 
-static bool is_jit_enabled(void)
-{
-	const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable";
-	bool enabled = false;
-	int sysctl_fd;
-
-	sysctl_fd = open(jit_sysctl, 0, O_RDONLY);
-	if (sysctl_fd != -1) {
-		char tmpc;
-
-		if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1)
-			enabled = (tmpc != '0');
-		close(sysctl_fd);
-	}
-
-	return enabled;
-}
-
 int compare_map_keys(int map1_fd, int map2_fd)
 {
 	__u32 key, next_key;
@@ -590,91 +732,90 @@ out:
 	return err;
 }
 
-int extract_build_id(char *build_id, size_t size)
-{
-	FILE *fp;
-	char *line = NULL;
-	size_t len = 0;
-
-	fp = popen("readelf -n ./urandom_read | grep 'Build ID'", "r");
-	if (fp == NULL)
-		return -1;
-
-	if (getline(&line, &len, fp) == -1)
-		goto err;
-	pclose(fp);
-
-	if (len > size)
-		len = size;
-	memcpy(build_id, line, len);
-	build_id[len] = '\0';
-	free(line);
-	return 0;
-err:
-	pclose(fp);
-	return -1;
-}
-
-static int finit_module(int fd, const char *param_values, int flags)
-{
-	return syscall(__NR_finit_module, fd, param_values, flags);
-}
-
-static int delete_module(const char *name, int flags)
-{
-	return syscall(__NR_delete_module, name, flags);
-}
+struct netns_obj {
+	char *nsname;
+	struct tmonitor_ctx *tmon;
+	struct nstoken *nstoken;
+};
 
-/*
- * Trigger synchronize_rcu() in kernel.
+/* Create a new network namespace with the given name.
+ *
+ * Create a new network namespace and set the network namespace of the
+ * current process to the new network namespace if the argument "open" is
+ * true. This function should be paired with netns_free() to release the
+ * resource and delete the network namespace.
+ *
+ * It also implements the functionality of the option "-m" by starting
+ * traffic monitor on the background to capture the packets in this network
+ * namespace if the current test or subtest matching the pattern.
+ *
+ * nsname: the name of the network namespace to create.
+ * open: open the network namespace if true.
+ *
+ * Return: the network namespace object on success, NULL on failure.
  */
-int kern_sync_rcu(void)
-{
-	return syscall(__NR_membarrier, MEMBARRIER_CMD_SHARED, 0, 0);
-}
-
-static void unload_bpf_testmod(void)
+struct netns_obj *netns_new(const char *nsname, bool open)
 {
-	if (kern_sync_rcu())
-		fprintf(env.stderr, "Failed to trigger kernel-side RCU sync!\n");
-	if (delete_module("bpf_testmod", 0)) {
-		if (errno == ENOENT) {
-			if (verbose())
-				fprintf(stdout, "bpf_testmod.ko is already unloaded.\n");
-			return;
+	struct netns_obj *netns_obj = malloc(sizeof(*netns_obj));
+	const char *test_name, *subtest_name;
+	int r;
+
+	if (!netns_obj)
+		return NULL;
+	memset(netns_obj, 0, sizeof(*netns_obj));
+
+	netns_obj->nsname = strdup(nsname);
+	if (!netns_obj->nsname)
+		goto fail;
+
+	/* Create the network namespace */
+	r = make_netns(nsname);
+	if (r)
+		goto fail;
+
+	/* Start traffic monitor */
+	if (env.test->should_tmon ||
+	    (env.subtest_state && env.subtest_state->should_tmon)) {
+		test_name = env.test->test_name;
+		subtest_name = env.subtest_state ? env.subtest_state->name : NULL;
+		netns_obj->tmon = traffic_monitor_start(nsname, test_name, subtest_name);
+		if (!netns_obj->tmon) {
+			fprintf(stderr, "Failed to start traffic monitor for %s\n", nsname);
+			goto fail;
 		}
-		fprintf(env.stderr, "Failed to unload bpf_testmod.ko from kernel: %d\n", -errno);
-		return;
+	} else {
+		netns_obj->tmon = NULL;
 	}
-	if (verbose())
-		fprintf(stdout, "Successfully unloaded bpf_testmod.ko.\n");
-}
-
-static int load_bpf_testmod(void)
-{
-	int fd;
-
-	/* ensure previous instance of the module is unloaded */
-	unload_bpf_testmod();
 
-	if (verbose())
-		fprintf(stdout, "Loading bpf_testmod.ko...\n");
-
-	fd = open("bpf_testmod.ko", O_RDONLY);
-	if (fd < 0) {
-		fprintf(env.stderr, "Can't find bpf_testmod.ko kernel module: %d\n", -errno);
-		return -ENOENT;
-	}
-	if (finit_module(fd, "", 0)) {
-		fprintf(env.stderr, "Failed to load bpf_testmod.ko into the kernel: %d\n", -errno);
-		close(fd);
-		return -EINVAL;
+	if (open) {
+		netns_obj->nstoken = open_netns(nsname);
+		if (!netns_obj->nstoken)
+			goto fail;
 	}
-	close(fd);
 
-	if (verbose())
-		fprintf(stdout, "Successfully loaded bpf_testmod.ko.\n");
-	return 0;
+	return netns_obj;
+fail:
+	traffic_monitor_stop(netns_obj->tmon);
+	remove_netns(nsname);
+	free(netns_obj->nsname);
+	free(netns_obj);
+	return NULL;
+}
+
+/* Delete the network namespace.
+ *
+ * This function should be paired with netns_new() to delete the namespace
+ * created by netns_new().
+ */
+void netns_free(struct netns_obj *netns_obj)
+{
+	if (!netns_obj)
+		return;
+	traffic_monitor_stop(netns_obj->tmon);
+	close_netns(netns_obj->nstoken);
+	remove_netns(netns_obj->nsname);
+	free(netns_obj->nsname);
+	free(netns_obj);
 }
 
 /* extern declarations for test funcs */
@@ -700,7 +841,13 @@ static struct test_state test_states[ARRAY_SIZE(prog_test_defs)];
 
 const char *argp_program_version = "test_progs 0.1";
 const char *argp_program_bug_address = "<bpf@vger.kernel.org>";
-static const char argp_program_doc[] = "BPF selftests test runner";
+static const char argp_program_doc[] =
+"BPF selftests test runner\v"
+"Options accepting the NAMES parameter take either a comma-separated list\n"
+"of test names, or a filename prefixed with @. The file contains one name\n"
+"(or wildcard pattern) per line, and comments beginning with # are ignored.\n"
+"\n"
+"These options can be passed repeatedly to read multiple files.\n";
 
 enum ARG_KEYS {
 	ARG_TEST_NUM = 'n',
@@ -714,6 +861,9 @@ enum ARG_KEYS {
 	ARG_TEST_NAME_GLOB_DENYLIST = 'd',
 	ARG_NUM_WORKERS = 'j',
 	ARG_DEBUG = -1,
+	ARG_JSON_SUMMARY = 'J',
+	ARG_TRAFFIC_MONITOR = 'm',
+	ARG_WATCHDOG_TIMEOUT = 'w',
 };
 
 static const struct argp_option opts[] = {
@@ -739,14 +889,80 @@ static const struct argp_option opts[] = {
 	  "Number of workers to run in parallel, default to number of cpus." },
 	{ "debug", ARG_DEBUG, NULL, 0,
 	  "print extra debug information for test_progs." },
+	{ "json-summary", ARG_JSON_SUMMARY, "FILE", 0, "Write report in json format to this file."},
+#ifdef TRAFFIC_MONITOR
+	{ "traffic-monitor", ARG_TRAFFIC_MONITOR, "NAMES", 0,
+	  "Monitor network traffic of tests with name matching the pattern (supports '*' wildcard)." },
+#endif
+	{ "watchdog-timeout", ARG_WATCHDOG_TIMEOUT, "SECONDS", 0,
+	  "Kill the process if tests are not making progress for specified number of seconds." },
 	{},
 };
 
+static FILE *libbpf_capture_stream;
+
+static struct {
+	char *buf;
+	size_t buf_sz;
+} libbpf_output_capture;
+
+/* Creates a global memstream capturing INFO and WARN level output
+ * passed to libbpf_print_fn.
+ * Returns 0 on success, negative value on failure.
+ * On failure the description is printed using PRINT_FAIL and
+ * current test case is marked as fail.
+ */
+int start_libbpf_log_capture(void)
+{
+	if (libbpf_capture_stream) {
+		PRINT_FAIL("%s: libbpf_capture_stream != NULL\n", __func__);
+		return -EINVAL;
+	}
+
+	libbpf_capture_stream = open_memstream(&libbpf_output_capture.buf,
+					       &libbpf_output_capture.buf_sz);
+	if (!libbpf_capture_stream) {
+		PRINT_FAIL("%s: open_memstream failed errno=%d\n", __func__, errno);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/* Destroys global memstream created by start_libbpf_log_capture().
+ * Returns a pointer to captured data which has to be freed.
+ * Returned buffer is null terminated.
+ */
+char *stop_libbpf_log_capture(void)
+{
+	char *buf;
+
+	if (!libbpf_capture_stream)
+		return NULL;
+
+	fputc(0, libbpf_capture_stream);
+	fclose(libbpf_capture_stream);
+	libbpf_capture_stream = NULL;
+	/* get 'buf' after fclose(), see open_memstream() documentation */
+	buf = libbpf_output_capture.buf;
+	memset(&libbpf_output_capture, 0, sizeof(libbpf_output_capture));
+	return buf;
+}
+
 static int libbpf_print_fn(enum libbpf_print_level level,
 			   const char *format, va_list args)
 {
+	if (libbpf_capture_stream && level != LIBBPF_DEBUG) {
+		va_list args2;
+
+		va_copy(args2, args);
+		vfprintf(libbpf_capture_stream, format, args2);
+		va_end(args2);
+	}
+
 	if (env.verbosity < VERBOSE_VERY && level == LIBBPF_DEBUG)
 		return 0;
+
 	vfprintf(stdout, format, args);
 	return 0;
 }
@@ -781,6 +997,7 @@ extern int extra_prog_load_log_flags;
 static error_t parse_arg(int key, char *arg, struct argp_state *state)
 {
 	struct test_env *env = state->input;
+	int err = 0;
 
 	switch (key) {
 	case ARG_TEST_NUM: {
@@ -805,18 +1022,28 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 	}
 	case ARG_TEST_NAME_GLOB_ALLOWLIST:
 	case ARG_TEST_NAME: {
-		if (parse_test_list(arg,
-				    &env->test_selector.whitelist,
-				    key == ARG_TEST_NAME_GLOB_ALLOWLIST))
-			return -ENOMEM;
+		if (arg[0] == '@')
+			err = parse_test_list_file(arg + 1,
+						   &env->test_selector.whitelist,
+						   key == ARG_TEST_NAME_GLOB_ALLOWLIST);
+		else
+			err = parse_test_list(arg,
+					      &env->test_selector.whitelist,
+					      key == ARG_TEST_NAME_GLOB_ALLOWLIST);
+
 		break;
 	}
 	case ARG_TEST_NAME_GLOB_DENYLIST:
 	case ARG_TEST_NAME_BLACKLIST: {
-		if (parse_test_list(arg,
-				    &env->test_selector.blacklist,
-				    key == ARG_TEST_NAME_GLOB_DENYLIST))
-			return -ENOMEM;
+		if (arg[0] == '@')
+			err = parse_test_list_file(arg + 1,
+						   &env->test_selector.blacklist,
+						   key == ARG_TEST_NAME_GLOB_DENYLIST);
+		else
+			err = parse_test_list(arg,
+					      &env->test_selector.blacklist,
+					      key == ARG_TEST_NAME_GLOB_DENYLIST);
+
 		break;
 	}
 	case ARG_VERIFIER_STATS:
@@ -838,6 +1065,7 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 				return -EINVAL;
 			}
 		}
+		env_verbosity = env->verbosity;
 
 		if (verbose()) {
 			if (setenv("SELFTESTS_VERBOSE", "1", 1) == -1) {
@@ -869,15 +1097,44 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 	case ARG_DEBUG:
 		env->debug = true;
 		break;
+	case ARG_JSON_SUMMARY:
+		env->json = fopen(arg, "w");
+		if (env->json == NULL) {
+			perror("Failed to open json summary file");
+			return -errno;
+		}
+		break;
 	case ARGP_KEY_ARG:
 		argp_usage(state);
 		break;
 	case ARGP_KEY_END:
 		break;
+#ifdef TRAFFIC_MONITOR
+	case ARG_TRAFFIC_MONITOR:
+		if (arg[0] == '@')
+			err = parse_test_list_file(arg + 1,
+						   &env->tmon_selector.whitelist,
+						   true);
+		else
+			err = parse_test_list(arg,
+					      &env->tmon_selector.whitelist,
+					      true);
+		break;
+#endif
+	case ARG_WATCHDOG_TIMEOUT:
+		env->secs_till_kill = atoi(arg);
+		if (env->secs_till_kill < 0) {
+			fprintf(stderr, "Invalid watchdog timeout: %s.\n", arg);
+			return -EINVAL;
+		}
+		if (env->secs_till_kill < env->secs_till_notify) {
+			env->secs_till_notify = 0;
+		}
+		break;
 	default:
 		return ARGP_ERR_UNKNOWN;
 	}
-	return 0;
+	return err;
 }
 
 /*
@@ -967,6 +1224,43 @@ int write_sysctl(const char *sysctl, const char *value)
 	return 0;
 }
 
+int get_bpf_max_tramp_links_from(struct btf *btf)
+{
+	const struct btf_enum *e;
+	const struct btf_type *t;
+	__u32 i, type_cnt;
+	const char *name;
+	__u16 j, vlen;
+
+	for (i = 1, type_cnt = btf__type_cnt(btf); i < type_cnt; i++) {
+		t = btf__type_by_id(btf, i);
+		if (!t || !btf_is_enum(t) || t->name_off)
+			continue;
+		e = btf_enum(t);
+		for (j = 0, vlen = btf_vlen(t); j < vlen; j++, e++) {
+			name = btf__str_by_offset(btf, e->name_off);
+			if (name && !strcmp(name, "BPF_MAX_TRAMP_LINKS"))
+				return e->val;
+		}
+	}
+
+	return -1;
+}
+
+int get_bpf_max_tramp_links(void)
+{
+	struct btf *vmlinux_btf;
+	int ret;
+
+	vmlinux_btf = btf__load_vmlinux_btf();
+	if (!ASSERT_OK_PTR(vmlinux_btf, "vmlinux btf"))
+		return -1;
+	ret = get_bpf_max_tramp_links_from(vmlinux_btf);
+	btf__free(vmlinux_btf);
+
+	return ret;
+}
+
 #define MAX_BACKTRACE_SZ 128
 void crash_handler(int signum)
 {
@@ -975,18 +1269,35 @@ void crash_handler(int signum)
 
 	sz = backtrace(bt, ARRAY_SIZE(bt));
 
+	fflush(stdout);
+	stdout = env.stdout_saved;
+	stderr = env.stderr_saved;
+
 	if (env.test) {
 		env.test_state->error_cnt++;
-		dump_test_log(env.test, env.test_state, true, false);
+		dump_test_log(env.test, env.test_state, true, false, NULL);
 	}
-	if (env.stdout)
-		stdio_restore();
 	if (env.worker_id != -1)
 		fprintf(stderr, "[%d]: ", env.worker_id);
 	fprintf(stderr, "Caught signal #%d!\nStack trace:\n", signum);
 	backtrace_symbols_fd(bt, sz, STDERR_FILENO);
 }
 
+void hexdump(const char *prefix, const void *buf, size_t len)
+{
+	for (int i = 0; i < len; i++) {
+		if (!(i % 16)) {
+			if (i)
+				fprintf(stdout, "\n");
+			fprintf(stdout, "%s", prefix);
+		}
+		if (i && !(i % 8) && (i % 16))
+			fprintf(stdout, "\t");
+		fprintf(stdout, "%02X ", ((uint8_t *)(buf))[i]);
+	}
+	fprintf(stdout, "\n");
+}
+
 static void sigint_handler(int signum)
 {
 	int i;
@@ -1055,20 +1366,34 @@ static int recv_message(int sock, struct msg *msg)
 	return ret;
 }
 
+static bool ns_is_needed(const char *test_name)
+{
+	if (strlen(test_name) < 3)
+		return false;
+
+	return !strncmp(test_name, "ns_", 3);
+}
+
 static void run_one_test(int test_num)
 {
 	struct prog_test_def *test = &prog_test_defs[test_num];
 	struct test_state *state = &test_states[test_num];
+	struct netns_obj *ns = NULL;
 
 	env.test = test;
 	env.test_state = state;
 
 	stdio_hijack(&state->log_buf, &state->log_cnt);
 
+	watchdog_start();
+	if (ns_is_needed(test->test_name))
+		ns = netns_new(test->test_name, true);
 	if (test->run_test)
 		test->run_test();
 	else if (test->run_serial_test)
 		test->run_serial_test();
+	netns_free(ns);
+	watchdog_stop();
 
 	/* ensure last sub-test is finalized properly */
 	if (env.subtest_state)
@@ -1076,6 +1401,8 @@ static void run_one_test(int test_num)
 
 	state->tested = true;
 
+	stdio_restore();
+
 	if (verbose() && env.worker_id == -1)
 		print_test_result(test, state);
 
@@ -1084,9 +1411,9 @@ static void run_one_test(int test_num)
 	if (test->need_cgroup_cleanup)
 		cleanup_cgroup_environment();
 
-	stdio_restore();
+	free(stop_libbpf_log_capture());
 
-	dump_test_log(test, state, false, false);
+	dump_test_log(test, state, false, false, NULL);
 }
 
 struct dispatch_data {
@@ -1245,7 +1572,7 @@ static void *dispatch_thread(void *ctx)
 		} while (false);
 
 		pthread_mutex_lock(&stdout_output_lock);
-		dump_test_log(test, state, false, true);
+		dump_test_log(test, state, false, true, NULL);
 		pthread_mutex_unlock(&stdout_output_lock);
 	} /* while (true) */
 error:
@@ -1270,6 +1597,7 @@ static void calculate_summary_and_print_errors(struct test_env *env)
 {
 	int i;
 	int succ_cnt = 0, fail_cnt = 0, sub_succ_cnt = 0, skip_cnt = 0;
+	json_writer_t *w = NULL;
 
 	for (i = 0; i < prog_test_cnt; i++) {
 		struct test_state *state = &test_states[i];
@@ -1286,9 +1614,25 @@ static void calculate_summary_and_print_errors(struct test_env *env)
 			succ_cnt++;
 	}
 
+	if (env->json) {
+		w = jsonw_new(env->json);
+		if (!w)
+			fprintf(env->stderr_saved, "Failed to create new JSON stream.");
+	}
+
+	if (w) {
+		jsonw_start_object(w);
+		jsonw_uint_field(w, "success", succ_cnt);
+		jsonw_uint_field(w, "success_subtest", sub_succ_cnt);
+		jsonw_uint_field(w, "skipped", skip_cnt);
+		jsonw_uint_field(w, "failed", fail_cnt);
+		jsonw_name(w, "results");
+		jsonw_start_array(w);
+	}
+
 	/*
 	 * We only print error logs summary when there are failed tests and
-	 * verbose mode is not enabled. Otherwise, results may be incosistent.
+	 * verbose mode is not enabled. Otherwise, results may be inconsistent.
 	 *
 	 */
 	if (!verbose() && fail_cnt) {
@@ -1302,10 +1646,19 @@ static void calculate_summary_and_print_errors(struct test_env *env)
 			if (!state->tested || !state->error_cnt)
 				continue;
 
-			dump_test_log(test, state, true, true);
+			dump_test_log(test, state, true, true, w);
 		}
 	}
 
+	if (w) {
+		jsonw_end_array(w);
+		jsonw_end_object(w);
+		jsonw_destroy(&w);
+	}
+
+	if (env->json)
+		fclose(env->json);
+
 	printf("Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n",
 	       succ_cnt, sub_succ_cnt, skip_cnt, fail_cnt);
 
@@ -1482,6 +1835,7 @@ out:
 static int worker_main(int sock)
 {
 	save_netns();
+	watchdog_init();
 
 	while (true) {
 		/* receive command */
@@ -1576,6 +1930,13 @@ static void free_test_states(void)
 	}
 }
 
+static __u32 register_session_key(const char *key_data, size_t key_data_size)
+{
+	return syscall(__NR_add_key, "asymmetric", "libbpf_session_key",
+			(const void *)key_data, key_data_size,
+			KEY_SPEC_SESSION_KEYRING);
+}
+
 int main(int argc, char **argv)
 {
 	static const struct argp argp = {
@@ -1591,6 +1952,11 @@ int main(int argc, char **argv)
 
 	sigaction(SIGSEGV, &sigact, NULL);
 
+	env.stdout_saved = stdout;
+	env.stderr_saved = stderr;
+
+	env.secs_till_notify = 10;
+	env.secs_till_kill = 120;
 	err = argp_parse(&argp, argc, argv, 0, NULL, &env);
 	if (err)
 		return err;
@@ -1599,9 +1965,17 @@ int main(int argc, char **argv)
 	if (err)
 		return err;
 
+	watchdog_init();
+
 	/* Use libbpf 1.0 API mode */
 	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
 	libbpf_set_print(libbpf_print_fn);
+	err = register_session_key((const char *)test_progs_verification_cert,
+				   test_progs_verification_cert_len);
+	if (err < 0)
+		return err;
+
+	traffic_monitor_set_print(traffic_monitor_print_fn);
 
 	srand(time(NULL));
 
@@ -1613,13 +1987,15 @@ int main(int argc, char **argv)
 		return -1;
 	}
 
-	env.stdout = stdout;
-	env.stderr = stderr;
-
 	env.has_testmod = true;
-	if (!env.list_test_names && load_bpf_testmod()) {
-		fprintf(env.stderr, "WARNING! Selftests relying on bpf_testmod.ko will be skipped.\n");
-		env.has_testmod = false;
+	if (!env.list_test_names) {
+		/* ensure previous instance of the module is unloaded */
+		unload_bpf_testmod(verbose());
+
+		if (load_bpf_testmod(verbose())) {
+			fprintf(env.stderr_saved, "WARNING! Selftests relying on bpf_testmod.ko will be skipped.\n");
+			env.has_testmod = false;
+		}
 	}
 
 	/* initializing tests */
@@ -1636,6 +2012,8 @@ int main(int argc, char **argv)
 				test->test_num, test->test_name, test->test_name, test->test_name);
 			exit(EXIT_ERR_SETUP_INFRA);
 		}
+		if (test->should_run)
+			test->should_tmon = should_tmon(&env.tmon_selector, test->test_name);
 	}
 
 	/* ignore workers if we are just listing */
@@ -1645,7 +2023,7 @@ int main(int argc, char **argv)
 	/* launch workers if requested */
 	env.worker_id = -1; /* main process */
 	if (env.workers) {
-		env.worker_pids = calloc(sizeof(__pid_t), env.workers);
+		env.worker_pids = calloc(sizeof(pid_t), env.workers);
 		env.worker_socks = calloc(sizeof(int), env.workers);
 		if (env.debug)
 			fprintf(stdout, "Launching %d workers.\n", env.workers);
@@ -1695,7 +2073,7 @@ int main(int argc, char **argv)
 		}
 
 		if (env.list_test_names) {
-			fprintf(env.stdout, "%s\n", test->test_name);
+			fprintf(env.stdout_saved, "%s\n", test->test_name);
 			env.succ_cnt++;
 			continue;
 		}
@@ -1716,10 +2094,11 @@ int main(int argc, char **argv)
 	close(env.saved_netns_fd);
 out:
 	if (!env.list_test_names && env.has_testmod)
-		unload_bpf_testmod();
+		unload_bpf_testmod(verbose());
 
 	free_test_selector(&env.test_selector);
 	free_test_selector(&env.subtest_selector);
+	free_test_selector(&env.tmon_selector);
 	free_test_states();
 
 	if (env.succ_cnt + env.fail_cnt + env.skip_cnt == 0)
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index 3f058dfadbaf..eebfc18cdcd2 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -7,6 +7,7 @@
 #include <errno.h>
 #include <string.h>
 #include <assert.h>
+#include <regex.h>
 #include <stdlib.h>
 #include <stdarg.h>
 #include <time.h>
@@ -74,8 +75,9 @@ struct subtest_state {
 	int error_cnt;
 	bool skipped;
 	bool filtered;
+	bool should_tmon;
 
-	FILE *stdout;
+	FILE *stdout_saved;
 };
 
 struct test_state {
@@ -92,12 +94,15 @@ struct test_state {
 	size_t log_cnt;
 	char *log_buf;
 
-	FILE *stdout;
+	FILE *stdout_saved;
 };
 
+extern int env_verbosity;
+
 struct test_env {
 	struct test_selector test_selector;
 	struct test_selector subtest_selector;
+	struct test_selector tmon_selector;
 	bool verifier_stats;
 	bool debug;
 	enum verbosity verbosity;
@@ -111,9 +116,10 @@ struct test_env {
 	struct test_state *test_state; /* current running test state */
 	struct subtest_state *subtest_state; /* current running subtest state */
 
-	FILE *stdout;
-	FILE *stderr;
+	FILE *stdout_saved;
+	FILE *stderr_saved;
 	int nr_cpus;
+	FILE *json;
 
 	int succ_cnt; /* successful tests */
 	int sub_succ_cnt; /* successful sub-tests */
@@ -126,6 +132,12 @@ struct test_env {
 	pid_t *worker_pids; /* array of worker pids */
 	int *worker_socks; /* array of worker socks */
 	int *worker_current_test; /* array of current running test for each worker */
+
+	pthread_t main_thread;
+	int secs_till_notify;
+	int secs_till_kill;
+	timer_t watchdog; /* watch for stalled tests/subtests */
+	enum { WD_NOTIFY, WD_KILL } watchdog_state;
 };
 
 #define MAX_LOG_TRUNK_SIZE 8192
@@ -174,6 +186,7 @@ void test__end_subtest(void);
 void test__skip(void);
 void test__fail(void);
 int test__join_cgroup(const char *path);
+void hexdump(const char *prefix, const void *buf, size_t len);
 
 #define PRINT_FAIL(format...)                                                  \
 	({                                                                     \
@@ -333,6 +346,20 @@ int test__join_cgroup(const char *path);
 	___ok;								\
 })
 
+#define ASSERT_MEMEQ(actual, expected, len, name) ({			\
+	static int duration = 0;					\
+	const void *__act = actual;					\
+	const void *__exp = expected;					\
+	int __len = len;						\
+	bool ___ok = memcmp(__act, __exp, __len) == 0;			\
+	CHECK(!___ok, (name), "unexpected memory mismatch\n");		\
+	fprintf(stdout, "actual:\n");					\
+	hexdump("\t", __act, __len);					\
+	fprintf(stdout, "expected:\n");					\
+	hexdump("\t", __exp, __len);					\
+	___ok;								\
+})
+
 #define ASSERT_OK(res, name) ({						\
 	static int duration = 0;					\
 	long long ___res = (res);					\
@@ -376,6 +403,54 @@ int test__join_cgroup(const char *path);
 	___ok;								\
 })
 
+#define ASSERT_OK_FD(fd, name) ({					\
+	static int duration = 0;					\
+	int ___fd = (fd);						\
+	bool ___ok = ___fd >= 0;					\
+	CHECK(!___ok, (name), "unexpected fd: %d (errno %d)\n",		\
+	      ___fd, errno);						\
+	___ok;								\
+})
+
+#define ASSERT_ERR_FD(fd, name) ({					\
+	static int duration = 0;					\
+	int ___fd = (fd);						\
+	bool ___ok = ___fd < 0;						\
+	CHECK(!___ok, (name), "unexpected fd: %d\n", ___fd);		\
+	___ok;								\
+})
+
+#define SYS(goto_label, fmt, ...)					\
+	({								\
+		char cmd[1024];						\
+		snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__);		\
+		if (!ASSERT_OK(system(cmd), cmd))			\
+			goto goto_label;				\
+	})
+
+#define SYS_FAIL(goto_label, fmt, ...)					\
+	({								\
+		char cmd[1024];						\
+		snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__);		\
+		if (!ASSERT_NEQ(0, system(cmd), cmd))			\
+			goto goto_label;				\
+	})
+
+#define ALL_TO_DEV_NULL " >/dev/null 2>&1"
+
+#define SYS_NOFAIL(fmt, ...)						\
+	({								\
+		char cmd[1024];						\
+		int n;							\
+		n = snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__);	\
+		if (n < sizeof(cmd) && sizeof(cmd) - n >= sizeof(ALL_TO_DEV_NULL)) \
+			strcat(cmd, ALL_TO_DEV_NULL);			\
+		system(cmd);						\
+	})
+
+int start_libbpf_log_capture(void);
+char *stop_libbpf_log_capture(void);
+
 static inline __u64 ptr_to_u64(const void *ptr)
 {
 	return (__u64) (unsigned long) ptr;
@@ -386,14 +461,46 @@ static inline void *u64_to_ptr(__u64 ptr)
 	return (void *) (unsigned long) ptr;
 }
 
+static inline __u32 id_from_prog_fd(int fd)
+{
+	struct bpf_prog_info prog_info = {};
+	__u32 prog_info_len = sizeof(prog_info);
+	int err;
+
+	err = bpf_obj_get_info_by_fd(fd, &prog_info, &prog_info_len);
+	if (!ASSERT_OK(err, "id_from_prog_fd"))
+		return 0;
+
+	ASSERT_NEQ(prog_info.id, 0, "prog_info.id");
+	return prog_info.id;
+}
+
+static inline __u32 id_from_link_fd(int fd)
+{
+	struct bpf_link_info link_info = {};
+	__u32 link_info_len = sizeof(link_info);
+	int err;
+
+	err = bpf_link_get_info_by_fd(fd, &link_info, &link_info_len);
+	if (!ASSERT_OK(err, "id_from_link_fd"))
+		return 0;
+
+	ASSERT_NEQ(link_info.id, 0, "link_info.id");
+	return link_info.id;
+}
+
 int bpf_find_map(const char *test, struct bpf_object *obj, const char *name);
 int compare_map_keys(int map1_fd, int map2_fd);
 int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len);
-int extract_build_id(char *build_id, size_t size);
-int kern_sync_rcu(void);
 int trigger_module_test_read(int read_sz);
 int trigger_module_test_write(int write_sz);
 int write_sysctl(const char *sysctl, const char *value);
+int get_bpf_max_tramp_links_from(struct btf *btf);
+int get_bpf_max_tramp_links(void);
+
+struct netns_obj;
+struct netns_obj *netns_new(const char *name, bool open);
+void netns_free(struct netns_obj *netns);
 
 #ifdef __x86_64__
 #define SYS_NANOSLEEP_KPROBE_NAME "__x64_sys_nanosleep"
@@ -401,19 +508,30 @@ int write_sysctl(const char *sysctl, const char *value);
 #define SYS_NANOSLEEP_KPROBE_NAME "__s390x_sys_nanosleep"
 #elif defined(__aarch64__)
 #define SYS_NANOSLEEP_KPROBE_NAME "__arm64_sys_nanosleep"
+#elif defined(__riscv)
+#define SYS_NANOSLEEP_KPROBE_NAME "__riscv_sys_nanosleep"
 #else
 #define SYS_NANOSLEEP_KPROBE_NAME "sys_nanosleep"
 #endif
 
 #define BPF_TESTMOD_TEST_FILE "/sys/kernel/bpf_testmod"
 
+typedef int (*pre_execution_cb)(struct bpf_object *obj);
+
 struct test_loader {
 	char *log_buf;
 	size_t log_buf_sz;
+	pre_execution_cb pre_execution_cb;
 
 	struct bpf_object *obj;
 };
 
+static inline void test_loader__set_pre_execution_cb(struct test_loader *tester,
+						     pre_execution_cb cb)
+{
+	tester->pre_execution_cb = cb;
+}
+
 typedef const void *(*skel_elf_bytes_fn)(size_t *sz);
 
 extern void test_loader__run_subtests(struct test_loader *tester,
@@ -429,4 +547,20 @@ extern void test_loader_fini(struct test_loader *tester);
 	test_loader_fini(&tester);					       \
 })
 
+struct expect_msg {
+	const char *substr; /* substring match */
+	regex_t regex;
+	bool is_regex;
+	bool on_next_line;
+	bool negative;
+};
+
+struct expected_msgs {
+	struct expect_msg *patterns;
+	size_t cnt;
+};
+
+void validate_msgs(const char *log_buf, struct expected_msgs *msgs,
+		   void (*emit_fn)(const char *buf, bool force));
+
 #endif /* __TEST_PROGS_H */
diff --git a/tools/testing/selftests/bpf/test_skb_cgroup_id.sh b/tools/testing/selftests/bpf/test_skb_cgroup_id.sh
deleted file mode 100755
index 515c2eafc97f..000000000000
--- a/tools/testing/selftests/bpf/test_skb_cgroup_id.sh
+++ /dev/null
@@ -1,63 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-# Copyright (c) 2018 Facebook
-
-set -eu
-
-wait_for_ip()
-{
-	local _i
-	echo -n "Wait for testing link-local IP to become available "
-	for _i in $(seq ${MAX_PING_TRIES}); do
-		echo -n "."
-		if $PING6 -c 1 -W 1 ff02::1%${TEST_IF} >/dev/null 2>&1; then
-			echo " OK"
-			return
-		fi
-		sleep 1
-	done
-	echo 1>&2 "ERROR: Timeout waiting for test IP to become available."
-	exit 1
-}
-
-setup()
-{
-	# Create testing interfaces not to interfere with current environment.
-	ip link add dev ${TEST_IF} type veth peer name ${TEST_IF_PEER}
-	ip link set ${TEST_IF} up
-	ip link set ${TEST_IF_PEER} up
-
-	wait_for_ip
-
-	tc qdisc add dev ${TEST_IF} clsact
-	tc filter add dev ${TEST_IF} egress bpf obj ${BPF_PROG_OBJ} \
-		sec ${BPF_PROG_SECTION} da
-
-	BPF_PROG_ID=$(tc filter show dev ${TEST_IF} egress | \
-			awk '/ id / {sub(/.* id /, "", $0); print($1)}')
-}
-
-cleanup()
-{
-	ip link del ${TEST_IF} 2>/dev/null || :
-	ip link del ${TEST_IF_PEER} 2>/dev/null || :
-}
-
-main()
-{
-	trap cleanup EXIT 2 3 6 15
-	setup
-	${PROG} ${TEST_IF} ${BPF_PROG_ID}
-}
-
-DIR=$(dirname $0)
-TEST_IF="test_cgid_1"
-TEST_IF_PEER="test_cgid_2"
-MAX_PING_TRIES=5
-BPF_PROG_OBJ="${DIR}/test_skb_cgroup_id_kern.bpf.o"
-BPF_PROG_SECTION="cgroup_id_logger"
-BPF_PROG_ID=0
-PROG="${DIR}/test_skb_cgroup_id_user"
-type ping6 >/dev/null 2>&1 && PING6="ping6" || PING6="ping -6"
-
-main
diff --git a/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c b/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c
deleted file mode 100644
index 3256de30f563..000000000000
--- a/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c
+++ /dev/null
@@ -1,183 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright (c) 2018 Facebook
-
-#include <stdlib.h>
-#include <string.h>
-#include <unistd.h>
-
-#include <arpa/inet.h>
-#include <net/if.h>
-#include <netinet/in.h>
-#include <sys/socket.h>
-#include <sys/types.h>
-
-
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-#include "cgroup_helpers.h"
-
-#define CGROUP_PATH		"/skb_cgroup_test"
-#define NUM_CGROUP_LEVELS	4
-
-/* RFC 4291, Section 2.7.1 */
-#define LINKLOCAL_MULTICAST	"ff02::1"
-
-static int mk_dst_addr(const char *ip, const char *iface,
-		       struct sockaddr_in6 *dst)
-{
-	memset(dst, 0, sizeof(*dst));
-
-	dst->sin6_family = AF_INET6;
-	dst->sin6_port = htons(1025);
-
-	if (inet_pton(AF_INET6, ip, &dst->sin6_addr) != 1) {
-		log_err("Invalid IPv6: %s", ip);
-		return -1;
-	}
-
-	dst->sin6_scope_id = if_nametoindex(iface);
-	if (!dst->sin6_scope_id) {
-		log_err("Failed to get index of iface: %s", iface);
-		return -1;
-	}
-
-	return 0;
-}
-
-static int send_packet(const char *iface)
-{
-	struct sockaddr_in6 dst;
-	char msg[] = "msg";
-	int err = 0;
-	int fd = -1;
-
-	if (mk_dst_addr(LINKLOCAL_MULTICAST, iface, &dst))
-		goto err;
-
-	fd = socket(AF_INET6, SOCK_DGRAM, 0);
-	if (fd == -1) {
-		log_err("Failed to create UDP socket");
-		goto err;
-	}
-
-	if (sendto(fd, &msg, sizeof(msg), 0, (const struct sockaddr *)&dst,
-		   sizeof(dst)) == -1) {
-		log_err("Failed to send datagram");
-		goto err;
-	}
-
-	goto out;
-err:
-	err = -1;
-out:
-	if (fd >= 0)
-		close(fd);
-	return err;
-}
-
-int get_map_fd_by_prog_id(int prog_id)
-{
-	struct bpf_prog_info info = {};
-	__u32 info_len = sizeof(info);
-	__u32 map_ids[1];
-	int prog_fd = -1;
-	int map_fd = -1;
-
-	prog_fd = bpf_prog_get_fd_by_id(prog_id);
-	if (prog_fd < 0) {
-		log_err("Failed to get fd by prog id %d", prog_id);
-		goto err;
-	}
-
-	info.nr_map_ids = 1;
-	info.map_ids = (__u64) (unsigned long) map_ids;
-
-	if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len)) {
-		log_err("Failed to get info by prog fd %d", prog_fd);
-		goto err;
-	}
-
-	if (!info.nr_map_ids) {
-		log_err("No maps found for prog fd %d", prog_fd);
-		goto err;
-	}
-
-	map_fd = bpf_map_get_fd_by_id(map_ids[0]);
-	if (map_fd < 0)
-		log_err("Failed to get fd by map id %d", map_ids[0]);
-err:
-	if (prog_fd >= 0)
-		close(prog_fd);
-	return map_fd;
-}
-
-int check_ancestor_cgroup_ids(int prog_id)
-{
-	__u64 actual_ids[NUM_CGROUP_LEVELS], expected_ids[NUM_CGROUP_LEVELS];
-	__u32 level;
-	int err = 0;
-	int map_fd;
-
-	expected_ids[0] = get_cgroup_id("/..");	/* root cgroup */
-	expected_ids[1] = get_cgroup_id("");
-	expected_ids[2] = get_cgroup_id(CGROUP_PATH);
-	expected_ids[3] = 0; /* non-existent cgroup */
-
-	map_fd = get_map_fd_by_prog_id(prog_id);
-	if (map_fd < 0)
-		goto err;
-
-	for (level = 0; level < NUM_CGROUP_LEVELS; ++level) {
-		if (bpf_map_lookup_elem(map_fd, &level, &actual_ids[level])) {
-			log_err("Failed to lookup key %d", level);
-			goto err;
-		}
-		if (actual_ids[level] != expected_ids[level]) {
-			log_err("%llx (actual) != %llx (expected), level: %u\n",
-				actual_ids[level], expected_ids[level], level);
-			goto err;
-		}
-	}
-
-	goto out;
-err:
-	err = -1;
-out:
-	if (map_fd >= 0)
-		close(map_fd);
-	return err;
-}
-
-int main(int argc, char **argv)
-{
-	int cgfd = -1;
-	int err = 0;
-
-	if (argc < 3) {
-		fprintf(stderr, "Usage: %s iface prog_id\n", argv[0]);
-		exit(EXIT_FAILURE);
-	}
-
-	/* Use libbpf 1.0 API mode */
-	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
-
-	cgfd = cgroup_setup_and_join(CGROUP_PATH);
-	if (cgfd < 0)
-		goto err;
-
-	if (send_packet(argv[1]))
-		goto err;
-
-	if (check_ancestor_cgroup_ids(atoi(argv[2])))
-		goto err;
-
-	goto out;
-err:
-	err = -1;
-out:
-	close(cgfd);
-	cleanup_cgroup_environment();
-	printf("[%s]\n", err ? "FAIL" : "PASS");
-	return err;
-}
diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
deleted file mode 100644
index 2c89674fc62c..000000000000
--- a/tools/testing/selftests/bpf/test_sock_addr.c
+++ /dev/null
@@ -1,1433 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright (c) 2018 Facebook
-
-#define _GNU_SOURCE
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-
-#include <arpa/inet.h>
-#include <netinet/in.h>
-#include <sys/types.h>
-#include <sys/select.h>
-#include <sys/socket.h>
-
-#include <linux/filter.h>
-
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-#include "cgroup_helpers.h"
-#include "bpf_util.h"
-
-#ifndef ENOTSUPP
-# define ENOTSUPP 524
-#endif
-
-#define CG_PATH	"/foo"
-#define CONNECT4_PROG_PATH	"./connect4_prog.bpf.o"
-#define CONNECT6_PROG_PATH	"./connect6_prog.bpf.o"
-#define SENDMSG4_PROG_PATH	"./sendmsg4_prog.bpf.o"
-#define SENDMSG6_PROG_PATH	"./sendmsg6_prog.bpf.o"
-#define RECVMSG4_PROG_PATH	"./recvmsg4_prog.bpf.o"
-#define RECVMSG6_PROG_PATH	"./recvmsg6_prog.bpf.o"
-#define BIND4_PROG_PATH		"./bind4_prog.bpf.o"
-#define BIND6_PROG_PATH		"./bind6_prog.bpf.o"
-
-#define SERV4_IP		"192.168.1.254"
-#define SERV4_REWRITE_IP	"127.0.0.1"
-#define SRC4_IP			"172.16.0.1"
-#define SRC4_REWRITE_IP		"127.0.0.4"
-#define SERV4_PORT		4040
-#define SERV4_REWRITE_PORT	4444
-
-#define SERV6_IP		"face:b00c:1234:5678::abcd"
-#define SERV6_REWRITE_IP	"::1"
-#define SERV6_V4MAPPED_IP	"::ffff:192.168.0.4"
-#define SRC6_IP			"::1"
-#define SRC6_REWRITE_IP		"::6"
-#define WILDCARD6_IP		"::"
-#define SERV6_PORT		6060
-#define SERV6_REWRITE_PORT	6666
-
-#define INET_NTOP_BUF	40
-
-struct sock_addr_test;
-
-typedef int (*load_fn)(const struct sock_addr_test *test);
-typedef int (*info_fn)(int, struct sockaddr *, socklen_t *);
-
-char bpf_log_buf[BPF_LOG_BUF_SIZE];
-
-struct sock_addr_test {
-	const char *descr;
-	/* BPF prog properties */
-	load_fn loadfn;
-	enum bpf_attach_type expected_attach_type;
-	enum bpf_attach_type attach_type;
-	/* Socket properties */
-	int domain;
-	int type;
-	/* IP:port pairs for BPF prog to override */
-	const char *requested_ip;
-	unsigned short requested_port;
-	const char *expected_ip;
-	unsigned short expected_port;
-	const char *expected_src_ip;
-	/* Expected test result */
-	enum {
-		LOAD_REJECT,
-		ATTACH_REJECT,
-		ATTACH_OKAY,
-		SYSCALL_EPERM,
-		SYSCALL_ENOTSUPP,
-		SUCCESS,
-	} expected_result;
-};
-
-static int bind4_prog_load(const struct sock_addr_test *test);
-static int bind6_prog_load(const struct sock_addr_test *test);
-static int connect4_prog_load(const struct sock_addr_test *test);
-static int connect6_prog_load(const struct sock_addr_test *test);
-static int sendmsg_allow_prog_load(const struct sock_addr_test *test);
-static int sendmsg_deny_prog_load(const struct sock_addr_test *test);
-static int recvmsg_allow_prog_load(const struct sock_addr_test *test);
-static int recvmsg_deny_prog_load(const struct sock_addr_test *test);
-static int sendmsg4_rw_asm_prog_load(const struct sock_addr_test *test);
-static int recvmsg4_rw_c_prog_load(const struct sock_addr_test *test);
-static int sendmsg4_rw_c_prog_load(const struct sock_addr_test *test);
-static int sendmsg6_rw_asm_prog_load(const struct sock_addr_test *test);
-static int recvmsg6_rw_c_prog_load(const struct sock_addr_test *test);
-static int sendmsg6_rw_c_prog_load(const struct sock_addr_test *test);
-static int sendmsg6_rw_v4mapped_prog_load(const struct sock_addr_test *test);
-static int sendmsg6_rw_wildcard_prog_load(const struct sock_addr_test *test);
-
-static struct sock_addr_test tests[] = {
-	/* bind */
-	{
-		"bind4: load prog with wrong expected attach type",
-		bind4_prog_load,
-		BPF_CGROUP_INET6_BIND,
-		BPF_CGROUP_INET4_BIND,
-		AF_INET,
-		SOCK_STREAM,
-		NULL,
-		0,
-		NULL,
-		0,
-		NULL,
-		LOAD_REJECT,
-	},
-	{
-		"bind4: attach prog with wrong attach type",
-		bind4_prog_load,
-		BPF_CGROUP_INET4_BIND,
-		BPF_CGROUP_INET6_BIND,
-		AF_INET,
-		SOCK_STREAM,
-		NULL,
-		0,
-		NULL,
-		0,
-		NULL,
-		ATTACH_REJECT,
-	},
-	{
-		"bind4: rewrite IP & TCP port in",
-		bind4_prog_load,
-		BPF_CGROUP_INET4_BIND,
-		BPF_CGROUP_INET4_BIND,
-		AF_INET,
-		SOCK_STREAM,
-		SERV4_IP,
-		SERV4_PORT,
-		SERV4_REWRITE_IP,
-		SERV4_REWRITE_PORT,
-		NULL,
-		SUCCESS,
-	},
-	{
-		"bind4: rewrite IP & UDP port in",
-		bind4_prog_load,
-		BPF_CGROUP_INET4_BIND,
-		BPF_CGROUP_INET4_BIND,
-		AF_INET,
-		SOCK_DGRAM,
-		SERV4_IP,
-		SERV4_PORT,
-		SERV4_REWRITE_IP,
-		SERV4_REWRITE_PORT,
-		NULL,
-		SUCCESS,
-	},
-	{
-		"bind6: load prog with wrong expected attach type",
-		bind6_prog_load,
-		BPF_CGROUP_INET4_BIND,
-		BPF_CGROUP_INET6_BIND,
-		AF_INET6,
-		SOCK_STREAM,
-		NULL,
-		0,
-		NULL,
-		0,
-		NULL,
-		LOAD_REJECT,
-	},
-	{
-		"bind6: attach prog with wrong attach type",
-		bind6_prog_load,
-		BPF_CGROUP_INET6_BIND,
-		BPF_CGROUP_INET4_BIND,
-		AF_INET,
-		SOCK_STREAM,
-		NULL,
-		0,
-		NULL,
-		0,
-		NULL,
-		ATTACH_REJECT,
-	},
-	{
-		"bind6: rewrite IP & TCP port in",
-		bind6_prog_load,
-		BPF_CGROUP_INET6_BIND,
-		BPF_CGROUP_INET6_BIND,
-		AF_INET6,
-		SOCK_STREAM,
-		SERV6_IP,
-		SERV6_PORT,
-		SERV6_REWRITE_IP,
-		SERV6_REWRITE_PORT,
-		NULL,
-		SUCCESS,
-	},
-	{
-		"bind6: rewrite IP & UDP port in",
-		bind6_prog_load,
-		BPF_CGROUP_INET6_BIND,
-		BPF_CGROUP_INET6_BIND,
-		AF_INET6,
-		SOCK_DGRAM,
-		SERV6_IP,
-		SERV6_PORT,
-		SERV6_REWRITE_IP,
-		SERV6_REWRITE_PORT,
-		NULL,
-		SUCCESS,
-	},
-
-	/* connect */
-	{
-		"connect4: load prog with wrong expected attach type",
-		connect4_prog_load,
-		BPF_CGROUP_INET6_CONNECT,
-		BPF_CGROUP_INET4_CONNECT,
-		AF_INET,
-		SOCK_STREAM,
-		NULL,
-		0,
-		NULL,
-		0,
-		NULL,
-		LOAD_REJECT,
-	},
-	{
-		"connect4: attach prog with wrong attach type",
-		connect4_prog_load,
-		BPF_CGROUP_INET4_CONNECT,
-		BPF_CGROUP_INET6_CONNECT,
-		AF_INET,
-		SOCK_STREAM,
-		NULL,
-		0,
-		NULL,
-		0,
-		NULL,
-		ATTACH_REJECT,
-	},
-	{
-		"connect4: rewrite IP & TCP port",
-		connect4_prog_load,
-		BPF_CGROUP_INET4_CONNECT,
-		BPF_CGROUP_INET4_CONNECT,
-		AF_INET,
-		SOCK_STREAM,
-		SERV4_IP,
-		SERV4_PORT,
-		SERV4_REWRITE_IP,
-		SERV4_REWRITE_PORT,
-		SRC4_REWRITE_IP,
-		SUCCESS,
-	},
-	{
-		"connect4: rewrite IP & UDP port",
-		connect4_prog_load,
-		BPF_CGROUP_INET4_CONNECT,
-		BPF_CGROUP_INET4_CONNECT,
-		AF_INET,
-		SOCK_DGRAM,
-		SERV4_IP,
-		SERV4_PORT,
-		SERV4_REWRITE_IP,
-		SERV4_REWRITE_PORT,
-		SRC4_REWRITE_IP,
-		SUCCESS,
-	},
-	{
-		"connect6: load prog with wrong expected attach type",
-		connect6_prog_load,
-		BPF_CGROUP_INET4_CONNECT,
-		BPF_CGROUP_INET6_CONNECT,
-		AF_INET6,
-		SOCK_STREAM,
-		NULL,
-		0,
-		NULL,
-		0,
-		NULL,
-		LOAD_REJECT,
-	},
-	{
-		"connect6: attach prog with wrong attach type",
-		connect6_prog_load,
-		BPF_CGROUP_INET6_CONNECT,
-		BPF_CGROUP_INET4_CONNECT,
-		AF_INET,
-		SOCK_STREAM,
-		NULL,
-		0,
-		NULL,
-		0,
-		NULL,
-		ATTACH_REJECT,
-	},
-	{
-		"connect6: rewrite IP & TCP port",
-		connect6_prog_load,
-		BPF_CGROUP_INET6_CONNECT,
-		BPF_CGROUP_INET6_CONNECT,
-		AF_INET6,
-		SOCK_STREAM,
-		SERV6_IP,
-		SERV6_PORT,
-		SERV6_REWRITE_IP,
-		SERV6_REWRITE_PORT,
-		SRC6_REWRITE_IP,
-		SUCCESS,
-	},
-	{
-		"connect6: rewrite IP & UDP port",
-		connect6_prog_load,
-		BPF_CGROUP_INET6_CONNECT,
-		BPF_CGROUP_INET6_CONNECT,
-		AF_INET6,
-		SOCK_DGRAM,
-		SERV6_IP,
-		SERV6_PORT,
-		SERV6_REWRITE_IP,
-		SERV6_REWRITE_PORT,
-		SRC6_REWRITE_IP,
-		SUCCESS,
-	},
-
-	/* sendmsg */
-	{
-		"sendmsg4: load prog with wrong expected attach type",
-		sendmsg4_rw_asm_prog_load,
-		BPF_CGROUP_UDP6_SENDMSG,
-		BPF_CGROUP_UDP4_SENDMSG,
-		AF_INET,
-		SOCK_DGRAM,
-		NULL,
-		0,
-		NULL,
-		0,
-		NULL,
-		LOAD_REJECT,
-	},
-	{
-		"sendmsg4: attach prog with wrong attach type",
-		sendmsg4_rw_asm_prog_load,
-		BPF_CGROUP_UDP4_SENDMSG,
-		BPF_CGROUP_UDP6_SENDMSG,
-		AF_INET,
-		SOCK_DGRAM,
-		NULL,
-		0,
-		NULL,
-		0,
-		NULL,
-		ATTACH_REJECT,
-	},
-	{
-		"sendmsg4: rewrite IP & port (asm)",
-		sendmsg4_rw_asm_prog_load,
-		BPF_CGROUP_UDP4_SENDMSG,
-		BPF_CGROUP_UDP4_SENDMSG,
-		AF_INET,
-		SOCK_DGRAM,
-		SERV4_IP,
-		SERV4_PORT,
-		SERV4_REWRITE_IP,
-		SERV4_REWRITE_PORT,
-		SRC4_REWRITE_IP,
-		SUCCESS,
-	},
-	{
-		"sendmsg4: rewrite IP & port (C)",
-		sendmsg4_rw_c_prog_load,
-		BPF_CGROUP_UDP4_SENDMSG,
-		BPF_CGROUP_UDP4_SENDMSG,
-		AF_INET,
-		SOCK_DGRAM,
-		SERV4_IP,
-		SERV4_PORT,
-		SERV4_REWRITE_IP,
-		SERV4_REWRITE_PORT,
-		SRC4_REWRITE_IP,
-		SUCCESS,
-	},
-	{
-		"sendmsg4: deny call",
-		sendmsg_deny_prog_load,
-		BPF_CGROUP_UDP4_SENDMSG,
-		BPF_CGROUP_UDP4_SENDMSG,
-		AF_INET,
-		SOCK_DGRAM,
-		SERV4_IP,
-		SERV4_PORT,
-		SERV4_REWRITE_IP,
-		SERV4_REWRITE_PORT,
-		SRC4_REWRITE_IP,
-		SYSCALL_EPERM,
-	},
-	{
-		"sendmsg6: load prog with wrong expected attach type",
-		sendmsg6_rw_asm_prog_load,
-		BPF_CGROUP_UDP4_SENDMSG,
-		BPF_CGROUP_UDP6_SENDMSG,
-		AF_INET6,
-		SOCK_DGRAM,
-		NULL,
-		0,
-		NULL,
-		0,
-		NULL,
-		LOAD_REJECT,
-	},
-	{
-		"sendmsg6: attach prog with wrong attach type",
-		sendmsg6_rw_asm_prog_load,
-		BPF_CGROUP_UDP6_SENDMSG,
-		BPF_CGROUP_UDP4_SENDMSG,
-		AF_INET6,
-		SOCK_DGRAM,
-		NULL,
-		0,
-		NULL,
-		0,
-		NULL,
-		ATTACH_REJECT,
-	},
-	{
-		"sendmsg6: rewrite IP & port (asm)",
-		sendmsg6_rw_asm_prog_load,
-		BPF_CGROUP_UDP6_SENDMSG,
-		BPF_CGROUP_UDP6_SENDMSG,
-		AF_INET6,
-		SOCK_DGRAM,
-		SERV6_IP,
-		SERV6_PORT,
-		SERV6_REWRITE_IP,
-		SERV6_REWRITE_PORT,
-		SRC6_REWRITE_IP,
-		SUCCESS,
-	},
-	{
-		"sendmsg6: rewrite IP & port (C)",
-		sendmsg6_rw_c_prog_load,
-		BPF_CGROUP_UDP6_SENDMSG,
-		BPF_CGROUP_UDP6_SENDMSG,
-		AF_INET6,
-		SOCK_DGRAM,
-		SERV6_IP,
-		SERV6_PORT,
-		SERV6_REWRITE_IP,
-		SERV6_REWRITE_PORT,
-		SRC6_REWRITE_IP,
-		SUCCESS,
-	},
-	{
-		"sendmsg6: IPv4-mapped IPv6",
-		sendmsg6_rw_v4mapped_prog_load,
-		BPF_CGROUP_UDP6_SENDMSG,
-		BPF_CGROUP_UDP6_SENDMSG,
-		AF_INET6,
-		SOCK_DGRAM,
-		SERV6_IP,
-		SERV6_PORT,
-		SERV6_REWRITE_IP,
-		SERV6_REWRITE_PORT,
-		SRC6_REWRITE_IP,
-		SYSCALL_ENOTSUPP,
-	},
-	{
-		"sendmsg6: set dst IP = [::] (BSD'ism)",
-		sendmsg6_rw_wildcard_prog_load,
-		BPF_CGROUP_UDP6_SENDMSG,
-		BPF_CGROUP_UDP6_SENDMSG,
-		AF_INET6,
-		SOCK_DGRAM,
-		SERV6_IP,
-		SERV6_PORT,
-		SERV6_REWRITE_IP,
-		SERV6_REWRITE_PORT,
-		SRC6_REWRITE_IP,
-		SUCCESS,
-	},
-	{
-		"sendmsg6: preserve dst IP = [::] (BSD'ism)",
-		sendmsg_allow_prog_load,
-		BPF_CGROUP_UDP6_SENDMSG,
-		BPF_CGROUP_UDP6_SENDMSG,
-		AF_INET6,
-		SOCK_DGRAM,
-		WILDCARD6_IP,
-		SERV6_PORT,
-		SERV6_REWRITE_IP,
-		SERV6_PORT,
-		SRC6_IP,
-		SUCCESS,
-	},
-	{
-		"sendmsg6: deny call",
-		sendmsg_deny_prog_load,
-		BPF_CGROUP_UDP6_SENDMSG,
-		BPF_CGROUP_UDP6_SENDMSG,
-		AF_INET6,
-		SOCK_DGRAM,
-		SERV6_IP,
-		SERV6_PORT,
-		SERV6_REWRITE_IP,
-		SERV6_REWRITE_PORT,
-		SRC6_REWRITE_IP,
-		SYSCALL_EPERM,
-	},
-
-	/* recvmsg */
-	{
-		"recvmsg4: return code ok",
-		recvmsg_allow_prog_load,
-		BPF_CGROUP_UDP4_RECVMSG,
-		BPF_CGROUP_UDP4_RECVMSG,
-		AF_INET,
-		SOCK_DGRAM,
-		NULL,
-		0,
-		NULL,
-		0,
-		NULL,
-		ATTACH_OKAY,
-	},
-	{
-		"recvmsg4: return code !ok",
-		recvmsg_deny_prog_load,
-		BPF_CGROUP_UDP4_RECVMSG,
-		BPF_CGROUP_UDP4_RECVMSG,
-		AF_INET,
-		SOCK_DGRAM,
-		NULL,
-		0,
-		NULL,
-		0,
-		NULL,
-		LOAD_REJECT,
-	},
-	{
-		"recvmsg6: return code ok",
-		recvmsg_allow_prog_load,
-		BPF_CGROUP_UDP6_RECVMSG,
-		BPF_CGROUP_UDP6_RECVMSG,
-		AF_INET6,
-		SOCK_DGRAM,
-		NULL,
-		0,
-		NULL,
-		0,
-		NULL,
-		ATTACH_OKAY,
-	},
-	{
-		"recvmsg6: return code !ok",
-		recvmsg_deny_prog_load,
-		BPF_CGROUP_UDP6_RECVMSG,
-		BPF_CGROUP_UDP6_RECVMSG,
-		AF_INET6,
-		SOCK_DGRAM,
-		NULL,
-		0,
-		NULL,
-		0,
-		NULL,
-		LOAD_REJECT,
-	},
-	{
-		"recvmsg4: rewrite IP & port (C)",
-		recvmsg4_rw_c_prog_load,
-		BPF_CGROUP_UDP4_RECVMSG,
-		BPF_CGROUP_UDP4_RECVMSG,
-		AF_INET,
-		SOCK_DGRAM,
-		SERV4_REWRITE_IP,
-		SERV4_REWRITE_PORT,
-		SERV4_REWRITE_IP,
-		SERV4_REWRITE_PORT,
-		SERV4_IP,
-		SUCCESS,
-	},
-	{
-		"recvmsg6: rewrite IP & port (C)",
-		recvmsg6_rw_c_prog_load,
-		BPF_CGROUP_UDP6_RECVMSG,
-		BPF_CGROUP_UDP6_RECVMSG,
-		AF_INET6,
-		SOCK_DGRAM,
-		SERV6_REWRITE_IP,
-		SERV6_REWRITE_PORT,
-		SERV6_REWRITE_IP,
-		SERV6_REWRITE_PORT,
-		SERV6_IP,
-		SUCCESS,
-	},
-};
-
-static int mk_sockaddr(int domain, const char *ip, unsigned short port,
-		       struct sockaddr *addr, socklen_t addr_len)
-{
-	struct sockaddr_in6 *addr6;
-	struct sockaddr_in *addr4;
-
-	if (domain != AF_INET && domain != AF_INET6) {
-		log_err("Unsupported address family");
-		return -1;
-	}
-
-	memset(addr, 0, addr_len);
-
-	if (domain == AF_INET) {
-		if (addr_len < sizeof(struct sockaddr_in))
-			return -1;
-		addr4 = (struct sockaddr_in *)addr;
-		addr4->sin_family = domain;
-		addr4->sin_port = htons(port);
-		if (inet_pton(domain, ip, (void *)&addr4->sin_addr) != 1) {
-			log_err("Invalid IPv4: %s", ip);
-			return -1;
-		}
-	} else if (domain == AF_INET6) {
-		if (addr_len < sizeof(struct sockaddr_in6))
-			return -1;
-		addr6 = (struct sockaddr_in6 *)addr;
-		addr6->sin6_family = domain;
-		addr6->sin6_port = htons(port);
-		if (inet_pton(domain, ip, (void *)&addr6->sin6_addr) != 1) {
-			log_err("Invalid IPv6: %s", ip);
-			return -1;
-		}
-	}
-
-	return 0;
-}
-
-static int load_insns(const struct sock_addr_test *test,
-		      const struct bpf_insn *insns, size_t insns_cnt)
-{
-	LIBBPF_OPTS(bpf_prog_load_opts, opts);
-	int ret;
-
-	opts.expected_attach_type = test->expected_attach_type;
-	opts.log_buf = bpf_log_buf;
-	opts.log_size = BPF_LOG_BUF_SIZE;
-
-	ret = bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, NULL, "GPL", insns, insns_cnt, &opts);
-	if (ret < 0 && test->expected_result != LOAD_REJECT) {
-		log_err(">>> Loading program error.\n"
-			">>> Verifier output:\n%s\n-------\n", bpf_log_buf);
-	}
-
-	return ret;
-}
-
-static int load_path(const struct sock_addr_test *test, const char *path)
-{
-	struct bpf_object *obj;
-	struct bpf_program *prog;
-	int err;
-
-	obj = bpf_object__open_file(path, NULL);
-	err = libbpf_get_error(obj);
-	if (err) {
-		log_err(">>> Opening BPF object (%s) error.\n", path);
-		return -1;
-	}
-
-	prog = bpf_object__next_program(obj, NULL);
-	if (!prog)
-		goto err_out;
-
-	bpf_program__set_type(prog, BPF_PROG_TYPE_CGROUP_SOCK_ADDR);
-	bpf_program__set_expected_attach_type(prog, test->expected_attach_type);
-	bpf_program__set_flags(prog, BPF_F_TEST_RND_HI32);
-
-	err = bpf_object__load(obj);
-	if (err) {
-		if (test->expected_result != LOAD_REJECT)
-			log_err(">>> Loading program (%s) error.\n", path);
-		goto err_out;
-	}
-
-	return bpf_program__fd(prog);
-err_out:
-	bpf_object__close(obj);
-	return -1;
-}
-
-static int bind4_prog_load(const struct sock_addr_test *test)
-{
-	return load_path(test, BIND4_PROG_PATH);
-}
-
-static int bind6_prog_load(const struct sock_addr_test *test)
-{
-	return load_path(test, BIND6_PROG_PATH);
-}
-
-static int connect4_prog_load(const struct sock_addr_test *test)
-{
-	return load_path(test, CONNECT4_PROG_PATH);
-}
-
-static int connect6_prog_load(const struct sock_addr_test *test)
-{
-	return load_path(test, CONNECT6_PROG_PATH);
-}
-
-static int xmsg_ret_only_prog_load(const struct sock_addr_test *test,
-				   int32_t rc)
-{
-	struct bpf_insn insns[] = {
-		/* return rc */
-		BPF_MOV64_IMM(BPF_REG_0, rc),
-		BPF_EXIT_INSN(),
-	};
-	return load_insns(test, insns, ARRAY_SIZE(insns));
-}
-
-static int sendmsg_allow_prog_load(const struct sock_addr_test *test)
-{
-	return xmsg_ret_only_prog_load(test, /*rc*/ 1);
-}
-
-static int sendmsg_deny_prog_load(const struct sock_addr_test *test)
-{
-	return xmsg_ret_only_prog_load(test, /*rc*/ 0);
-}
-
-static int recvmsg_allow_prog_load(const struct sock_addr_test *test)
-{
-	return xmsg_ret_only_prog_load(test, /*rc*/ 1);
-}
-
-static int recvmsg_deny_prog_load(const struct sock_addr_test *test)
-{
-	return xmsg_ret_only_prog_load(test, /*rc*/ 0);
-}
-
-static int sendmsg4_rw_asm_prog_load(const struct sock_addr_test *test)
-{
-	struct sockaddr_in dst4_rw_addr;
-	struct in_addr src4_rw_ip;
-
-	if (inet_pton(AF_INET, SRC4_REWRITE_IP, (void *)&src4_rw_ip) != 1) {
-		log_err("Invalid IPv4: %s", SRC4_REWRITE_IP);
-		return -1;
-	}
-
-	if (mk_sockaddr(AF_INET, SERV4_REWRITE_IP, SERV4_REWRITE_PORT,
-			(struct sockaddr *)&dst4_rw_addr,
-			sizeof(dst4_rw_addr)) == -1)
-		return -1;
-
-	struct bpf_insn insns[] = {
-		BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-
-		/* if (sk.family == AF_INET && */
-		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
-			    offsetof(struct bpf_sock_addr, family)),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 8),
-
-		/*     sk.type == SOCK_DGRAM)  { */
-		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
-			    offsetof(struct bpf_sock_addr, type)),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_DGRAM, 6),
-
-		/*      msg_src_ip4 = src4_rw_ip */
-		BPF_MOV32_IMM(BPF_REG_7, src4_rw_ip.s_addr),
-		BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,
-			    offsetof(struct bpf_sock_addr, msg_src_ip4)),
-
-		/*      user_ip4 = dst4_rw_addr.sin_addr */
-		BPF_MOV32_IMM(BPF_REG_7, dst4_rw_addr.sin_addr.s_addr),
-		BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,
-			    offsetof(struct bpf_sock_addr, user_ip4)),
-
-		/*      user_port = dst4_rw_addr.sin_port */
-		BPF_MOV32_IMM(BPF_REG_7, dst4_rw_addr.sin_port),
-		BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,
-			    offsetof(struct bpf_sock_addr, user_port)),
-		/* } */
-
-		/* return 1 */
-		BPF_MOV64_IMM(BPF_REG_0, 1),
-		BPF_EXIT_INSN(),
-	};
-
-	return load_insns(test, insns, ARRAY_SIZE(insns));
-}
-
-static int recvmsg4_rw_c_prog_load(const struct sock_addr_test *test)
-{
-	return load_path(test, RECVMSG4_PROG_PATH);
-}
-
-static int sendmsg4_rw_c_prog_load(const struct sock_addr_test *test)
-{
-	return load_path(test, SENDMSG4_PROG_PATH);
-}
-
-static int sendmsg6_rw_dst_asm_prog_load(const struct sock_addr_test *test,
-					 const char *rw_dst_ip)
-{
-	struct sockaddr_in6 dst6_rw_addr;
-	struct in6_addr src6_rw_ip;
-
-	if (inet_pton(AF_INET6, SRC6_REWRITE_IP, (void *)&src6_rw_ip) != 1) {
-		log_err("Invalid IPv6: %s", SRC6_REWRITE_IP);
-		return -1;
-	}
-
-	if (mk_sockaddr(AF_INET6, rw_dst_ip, SERV6_REWRITE_PORT,
-			(struct sockaddr *)&dst6_rw_addr,
-			sizeof(dst6_rw_addr)) == -1)
-		return -1;
-
-	struct bpf_insn insns[] = {
-		BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-
-		/* if (sk.family == AF_INET6) { */
-		BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
-			    offsetof(struct bpf_sock_addr, family)),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET6, 18),
-
-#define STORE_IPV6_WORD_N(DST, SRC, N)					       \
-		BPF_MOV32_IMM(BPF_REG_7, SRC[N]),			       \
-		BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,		       \
-			    offsetof(struct bpf_sock_addr, DST[N]))
-
-#define STORE_IPV6(DST, SRC)						       \
-		STORE_IPV6_WORD_N(DST, SRC, 0),				       \
-		STORE_IPV6_WORD_N(DST, SRC, 1),				       \
-		STORE_IPV6_WORD_N(DST, SRC, 2),				       \
-		STORE_IPV6_WORD_N(DST, SRC, 3)
-
-		STORE_IPV6(msg_src_ip6, src6_rw_ip.s6_addr32),
-		STORE_IPV6(user_ip6, dst6_rw_addr.sin6_addr.s6_addr32),
-
-		/*      user_port = dst6_rw_addr.sin6_port */
-		BPF_MOV32_IMM(BPF_REG_7, dst6_rw_addr.sin6_port),
-		BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,
-			    offsetof(struct bpf_sock_addr, user_port)),
-
-		/* } */
-
-		/* return 1 */
-		BPF_MOV64_IMM(BPF_REG_0, 1),
-		BPF_EXIT_INSN(),
-	};
-
-	return load_insns(test, insns, ARRAY_SIZE(insns));
-}
-
-static int sendmsg6_rw_asm_prog_load(const struct sock_addr_test *test)
-{
-	return sendmsg6_rw_dst_asm_prog_load(test, SERV6_REWRITE_IP);
-}
-
-static int recvmsg6_rw_c_prog_load(const struct sock_addr_test *test)
-{
-	return load_path(test, RECVMSG6_PROG_PATH);
-}
-
-static int sendmsg6_rw_v4mapped_prog_load(const struct sock_addr_test *test)
-{
-	return sendmsg6_rw_dst_asm_prog_load(test, SERV6_V4MAPPED_IP);
-}
-
-static int sendmsg6_rw_wildcard_prog_load(const struct sock_addr_test *test)
-{
-	return sendmsg6_rw_dst_asm_prog_load(test, WILDCARD6_IP);
-}
-
-static int sendmsg6_rw_c_prog_load(const struct sock_addr_test *test)
-{
-	return load_path(test, SENDMSG6_PROG_PATH);
-}
-
-static int cmp_addr(const struct sockaddr_storage *addr1,
-		    const struct sockaddr_storage *addr2, int cmp_port)
-{
-	const struct sockaddr_in *four1, *four2;
-	const struct sockaddr_in6 *six1, *six2;
-
-	if (addr1->ss_family != addr2->ss_family)
-		return -1;
-
-	if (addr1->ss_family == AF_INET) {
-		four1 = (const struct sockaddr_in *)addr1;
-		four2 = (const struct sockaddr_in *)addr2;
-		return !((four1->sin_port == four2->sin_port || !cmp_port) &&
-			 four1->sin_addr.s_addr == four2->sin_addr.s_addr);
-	} else if (addr1->ss_family == AF_INET6) {
-		six1 = (const struct sockaddr_in6 *)addr1;
-		six2 = (const struct sockaddr_in6 *)addr2;
-		return !((six1->sin6_port == six2->sin6_port || !cmp_port) &&
-			 !memcmp(&six1->sin6_addr, &six2->sin6_addr,
-				 sizeof(struct in6_addr)));
-	}
-
-	return -1;
-}
-
-static int cmp_sock_addr(info_fn fn, int sock1,
-			 const struct sockaddr_storage *addr2, int cmp_port)
-{
-	struct sockaddr_storage addr1;
-	socklen_t len1 = sizeof(addr1);
-
-	memset(&addr1, 0, len1);
-	if (fn(sock1, (struct sockaddr *)&addr1, (socklen_t *)&len1) != 0)
-		return -1;
-
-	return cmp_addr(&addr1, addr2, cmp_port);
-}
-
-static int cmp_local_ip(int sock1, const struct sockaddr_storage *addr2)
-{
-	return cmp_sock_addr(getsockname, sock1, addr2, /*cmp_port*/ 0);
-}
-
-static int cmp_local_addr(int sock1, const struct sockaddr_storage *addr2)
-{
-	return cmp_sock_addr(getsockname, sock1, addr2, /*cmp_port*/ 1);
-}
-
-static int cmp_peer_addr(int sock1, const struct sockaddr_storage *addr2)
-{
-	return cmp_sock_addr(getpeername, sock1, addr2, /*cmp_port*/ 1);
-}
-
-static int start_server(int type, const struct sockaddr_storage *addr,
-			socklen_t addr_len)
-{
-	int fd;
-
-	fd = socket(addr->ss_family, type, 0);
-	if (fd == -1) {
-		log_err("Failed to create server socket");
-		goto out;
-	}
-
-	if (bind(fd, (const struct sockaddr *)addr, addr_len) == -1) {
-		log_err("Failed to bind server socket");
-		goto close_out;
-	}
-
-	if (type == SOCK_STREAM) {
-		if (listen(fd, 128) == -1) {
-			log_err("Failed to listen on server socket");
-			goto close_out;
-		}
-	}
-
-	goto out;
-close_out:
-	close(fd);
-	fd = -1;
-out:
-	return fd;
-}
-
-static int connect_to_server(int type, const struct sockaddr_storage *addr,
-			     socklen_t addr_len)
-{
-	int domain;
-	int fd = -1;
-
-	domain = addr->ss_family;
-
-	if (domain != AF_INET && domain != AF_INET6) {
-		log_err("Unsupported address family");
-		goto err;
-	}
-
-	fd = socket(domain, type, 0);
-	if (fd == -1) {
-		log_err("Failed to create client socket");
-		goto err;
-	}
-
-	if (connect(fd, (const struct sockaddr *)addr, addr_len) == -1) {
-		log_err("Fail to connect to server");
-		goto err;
-	}
-
-	goto out;
-err:
-	close(fd);
-	fd = -1;
-out:
-	return fd;
-}
-
-int init_pktinfo(int domain, struct cmsghdr *cmsg)
-{
-	struct in6_pktinfo *pktinfo6;
-	struct in_pktinfo *pktinfo4;
-
-	if (domain == AF_INET) {
-		cmsg->cmsg_level = SOL_IP;
-		cmsg->cmsg_type = IP_PKTINFO;
-		cmsg->cmsg_len = CMSG_LEN(sizeof(struct in_pktinfo));
-		pktinfo4 = (struct in_pktinfo *)CMSG_DATA(cmsg);
-		memset(pktinfo4, 0, sizeof(struct in_pktinfo));
-		if (inet_pton(domain, SRC4_IP,
-			      (void *)&pktinfo4->ipi_spec_dst) != 1)
-			return -1;
-	} else if (domain == AF_INET6) {
-		cmsg->cmsg_level = SOL_IPV6;
-		cmsg->cmsg_type = IPV6_PKTINFO;
-		cmsg->cmsg_len = CMSG_LEN(sizeof(struct in6_pktinfo));
-		pktinfo6 = (struct in6_pktinfo *)CMSG_DATA(cmsg);
-		memset(pktinfo6, 0, sizeof(struct in6_pktinfo));
-		if (inet_pton(domain, SRC6_IP,
-			      (void *)&pktinfo6->ipi6_addr) != 1)
-			return -1;
-	} else {
-		return -1;
-	}
-
-	return 0;
-}
-
-static int sendmsg_to_server(int type, const struct sockaddr_storage *addr,
-			     socklen_t addr_len, int set_cmsg, int flags,
-			     int *syscall_err)
-{
-	union {
-		char buf[CMSG_SPACE(sizeof(struct in6_pktinfo))];
-		struct cmsghdr align;
-	} control6;
-	union {
-		char buf[CMSG_SPACE(sizeof(struct in_pktinfo))];
-		struct cmsghdr align;
-	} control4;
-	struct msghdr hdr;
-	struct iovec iov;
-	char data = 'a';
-	int domain;
-	int fd = -1;
-
-	domain = addr->ss_family;
-
-	if (domain != AF_INET && domain != AF_INET6) {
-		log_err("Unsupported address family");
-		goto err;
-	}
-
-	fd = socket(domain, type, 0);
-	if (fd == -1) {
-		log_err("Failed to create client socket");
-		goto err;
-	}
-
-	memset(&iov, 0, sizeof(iov));
-	iov.iov_base = &data;
-	iov.iov_len = sizeof(data);
-
-	memset(&hdr, 0, sizeof(hdr));
-	hdr.msg_name = (void *)addr;
-	hdr.msg_namelen = addr_len;
-	hdr.msg_iov = &iov;
-	hdr.msg_iovlen = 1;
-
-	if (set_cmsg) {
-		if (domain == AF_INET) {
-			hdr.msg_control = &control4;
-			hdr.msg_controllen = sizeof(control4.buf);
-		} else if (domain == AF_INET6) {
-			hdr.msg_control = &control6;
-			hdr.msg_controllen = sizeof(control6.buf);
-		}
-		if (init_pktinfo(domain, CMSG_FIRSTHDR(&hdr))) {
-			log_err("Fail to init pktinfo");
-			goto err;
-		}
-	}
-
-	if (sendmsg(fd, &hdr, flags) != sizeof(data)) {
-		log_err("Fail to send message to server");
-		*syscall_err = errno;
-		goto err;
-	}
-
-	goto out;
-err:
-	close(fd);
-	fd = -1;
-out:
-	return fd;
-}
-
-static int fastconnect_to_server(const struct sockaddr_storage *addr,
-				 socklen_t addr_len)
-{
-	int sendmsg_err;
-
-	return sendmsg_to_server(SOCK_STREAM, addr, addr_len, /*set_cmsg*/0,
-				 MSG_FASTOPEN, &sendmsg_err);
-}
-
-static int recvmsg_from_client(int sockfd, struct sockaddr_storage *src_addr)
-{
-	struct timeval tv;
-	struct msghdr hdr;
-	struct iovec iov;
-	char data[64];
-	fd_set rfds;
-
-	FD_ZERO(&rfds);
-	FD_SET(sockfd, &rfds);
-
-	tv.tv_sec = 2;
-	tv.tv_usec = 0;
-
-	if (select(sockfd + 1, &rfds, NULL, NULL, &tv) <= 0 ||
-	    !FD_ISSET(sockfd, &rfds))
-		return -1;
-
-	memset(&iov, 0, sizeof(iov));
-	iov.iov_base = data;
-	iov.iov_len = sizeof(data);
-
-	memset(&hdr, 0, sizeof(hdr));
-	hdr.msg_name = src_addr;
-	hdr.msg_namelen = sizeof(struct sockaddr_storage);
-	hdr.msg_iov = &iov;
-	hdr.msg_iovlen = 1;
-
-	return recvmsg(sockfd, &hdr, 0);
-}
-
-static int init_addrs(const struct sock_addr_test *test,
-		      struct sockaddr_storage *requested_addr,
-		      struct sockaddr_storage *expected_addr,
-		      struct sockaddr_storage *expected_src_addr)
-{
-	socklen_t addr_len = sizeof(struct sockaddr_storage);
-
-	if (mk_sockaddr(test->domain, test->expected_ip, test->expected_port,
-			(struct sockaddr *)expected_addr, addr_len) == -1)
-		goto err;
-
-	if (mk_sockaddr(test->domain, test->requested_ip, test->requested_port,
-			(struct sockaddr *)requested_addr, addr_len) == -1)
-		goto err;
-
-	if (test->expected_src_ip &&
-	    mk_sockaddr(test->domain, test->expected_src_ip, 0,
-			(struct sockaddr *)expected_src_addr, addr_len) == -1)
-		goto err;
-
-	return 0;
-err:
-	return -1;
-}
-
-static int run_bind_test_case(const struct sock_addr_test *test)
-{
-	socklen_t addr_len = sizeof(struct sockaddr_storage);
-	struct sockaddr_storage requested_addr;
-	struct sockaddr_storage expected_addr;
-	int clientfd = -1;
-	int servfd = -1;
-	int err = 0;
-
-	if (init_addrs(test, &requested_addr, &expected_addr, NULL))
-		goto err;
-
-	servfd = start_server(test->type, &requested_addr, addr_len);
-	if (servfd == -1)
-		goto err;
-
-	if (cmp_local_addr(servfd, &expected_addr))
-		goto err;
-
-	/* Try to connect to server just in case */
-	clientfd = connect_to_server(test->type, &expected_addr, addr_len);
-	if (clientfd == -1)
-		goto err;
-
-	goto out;
-err:
-	err = -1;
-out:
-	close(clientfd);
-	close(servfd);
-	return err;
-}
-
-static int run_connect_test_case(const struct sock_addr_test *test)
-{
-	socklen_t addr_len = sizeof(struct sockaddr_storage);
-	struct sockaddr_storage expected_src_addr;
-	struct sockaddr_storage requested_addr;
-	struct sockaddr_storage expected_addr;
-	int clientfd = -1;
-	int servfd = -1;
-	int err = 0;
-
-	if (init_addrs(test, &requested_addr, &expected_addr,
-		       &expected_src_addr))
-		goto err;
-
-	/* Prepare server to connect to */
-	servfd = start_server(test->type, &expected_addr, addr_len);
-	if (servfd == -1)
-		goto err;
-
-	clientfd = connect_to_server(test->type, &requested_addr, addr_len);
-	if (clientfd == -1)
-		goto err;
-
-	/* Make sure src and dst addrs were overridden properly */
-	if (cmp_peer_addr(clientfd, &expected_addr))
-		goto err;
-
-	if (cmp_local_ip(clientfd, &expected_src_addr))
-		goto err;
-
-	if (test->type == SOCK_STREAM) {
-		/* Test TCP Fast Open scenario */
-		clientfd = fastconnect_to_server(&requested_addr, addr_len);
-		if (clientfd == -1)
-			goto err;
-
-		/* Make sure src and dst addrs were overridden properly */
-		if (cmp_peer_addr(clientfd, &expected_addr))
-			goto err;
-
-		if (cmp_local_ip(clientfd, &expected_src_addr))
-			goto err;
-	}
-
-	goto out;
-err:
-	err = -1;
-out:
-	close(clientfd);
-	close(servfd);
-	return err;
-}
-
-static int run_xmsg_test_case(const struct sock_addr_test *test, int max_cmsg)
-{
-	socklen_t addr_len = sizeof(struct sockaddr_storage);
-	struct sockaddr_storage expected_addr;
-	struct sockaddr_storage server_addr;
-	struct sockaddr_storage sendmsg_addr;
-	struct sockaddr_storage recvmsg_addr;
-	int clientfd = -1;
-	int servfd = -1;
-	int set_cmsg;
-	int err = 0;
-
-	if (test->type != SOCK_DGRAM)
-		goto err;
-
-	if (init_addrs(test, &sendmsg_addr, &server_addr, &expected_addr))
-		goto err;
-
-	/* Prepare server to sendmsg to */
-	servfd = start_server(test->type, &server_addr, addr_len);
-	if (servfd == -1)
-		goto err;
-
-	for (set_cmsg = 0; set_cmsg <= max_cmsg; ++set_cmsg) {
-		if (clientfd >= 0)
-			close(clientfd);
-
-		clientfd = sendmsg_to_server(test->type, &sendmsg_addr,
-					     addr_len, set_cmsg, /*flags*/0,
-					     &err);
-		if (err)
-			goto out;
-		else if (clientfd == -1)
-			goto err;
-
-		/* Try to receive message on server instead of using
-		 * getpeername(2) on client socket, to check that client's
-		 * destination address was rewritten properly, since
-		 * getpeername(2) doesn't work with unconnected datagram
-		 * sockets.
-		 *
-		 * Get source address from recvmsg(2) as well to make sure
-		 * source was rewritten properly: getsockname(2) can't be used
-		 * since socket is unconnected and source defined for one
-		 * specific packet may differ from the one used by default and
-		 * returned by getsockname(2).
-		 */
-		if (recvmsg_from_client(servfd, &recvmsg_addr) == -1)
-			goto err;
-
-		if (cmp_addr(&recvmsg_addr, &expected_addr, /*cmp_port*/0))
-			goto err;
-	}
-
-	goto out;
-err:
-	err = -1;
-out:
-	close(clientfd);
-	close(servfd);
-	return err;
-}
-
-static int run_test_case(int cgfd, const struct sock_addr_test *test)
-{
-	int progfd = -1;
-	int err = 0;
-
-	printf("Test case: %s .. ", test->descr);
-
-	progfd = test->loadfn(test);
-	if (test->expected_result == LOAD_REJECT && progfd < 0)
-		goto out;
-	else if (test->expected_result == LOAD_REJECT || progfd < 0)
-		goto err;
-
-	err = bpf_prog_attach(progfd, cgfd, test->attach_type,
-			      BPF_F_ALLOW_OVERRIDE);
-	if (test->expected_result == ATTACH_REJECT && err) {
-		err = 0; /* error was expected, reset it */
-		goto out;
-	} else if (test->expected_result == ATTACH_REJECT || err) {
-		goto err;
-	} else if (test->expected_result == ATTACH_OKAY) {
-		err = 0;
-		goto out;
-	}
-
-	switch (test->attach_type) {
-	case BPF_CGROUP_INET4_BIND:
-	case BPF_CGROUP_INET6_BIND:
-		err = run_bind_test_case(test);
-		break;
-	case BPF_CGROUP_INET4_CONNECT:
-	case BPF_CGROUP_INET6_CONNECT:
-		err = run_connect_test_case(test);
-		break;
-	case BPF_CGROUP_UDP4_SENDMSG:
-	case BPF_CGROUP_UDP6_SENDMSG:
-		err = run_xmsg_test_case(test, 1);
-		break;
-	case BPF_CGROUP_UDP4_RECVMSG:
-	case BPF_CGROUP_UDP6_RECVMSG:
-		err = run_xmsg_test_case(test, 0);
-		break;
-	default:
-		goto err;
-	}
-
-	if (test->expected_result == SYSCALL_EPERM && err == EPERM) {
-		err = 0; /* error was expected, reset it */
-		goto out;
-	}
-
-	if (test->expected_result == SYSCALL_ENOTSUPP && err == ENOTSUPP) {
-		err = 0; /* error was expected, reset it */
-		goto out;
-	}
-
-	if (err || test->expected_result != SUCCESS)
-		goto err;
-
-	goto out;
-err:
-	err = -1;
-out:
-	/* Detaching w/o checking return code: best effort attempt. */
-	if (progfd != -1)
-		bpf_prog_detach(cgfd, test->attach_type);
-	close(progfd);
-	printf("[%s]\n", err ? "FAIL" : "PASS");
-	return err;
-}
-
-static int run_tests(int cgfd)
-{
-	int passes = 0;
-	int fails = 0;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(tests); ++i) {
-		if (run_test_case(cgfd, &tests[i]))
-			++fails;
-		else
-			++passes;
-	}
-	printf("Summary: %d PASSED, %d FAILED\n", passes, fails);
-	return fails ? -1 : 0;
-}
-
-int main(int argc, char **argv)
-{
-	int cgfd = -1;
-	int err = 0;
-
-	if (argc < 2) {
-		fprintf(stderr,
-			"%s has to be run via %s.sh. Skip direct run.\n",
-			argv[0], argv[0]);
-		exit(err);
-	}
-
-	cgfd = cgroup_setup_and_join(CG_PATH);
-	if (cgfd < 0)
-		goto err;
-
-	/* Use libbpf 1.0 API mode */
-	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
-
-	if (run_tests(cgfd))
-		goto err;
-
-	goto out;
-err:
-	err = -1;
-out:
-	close(cgfd);
-	cleanup_cgroup_environment();
-	return err;
-}
diff --git a/tools/testing/selftests/bpf/test_sock_addr.sh b/tools/testing/selftests/bpf/test_sock_addr.sh
deleted file mode 100755
index 3b9fdb8094aa..000000000000
--- a/tools/testing/selftests/bpf/test_sock_addr.sh
+++ /dev/null
@@ -1,58 +0,0 @@
-#!/bin/sh
-
-set -eu
-
-ping_once()
-{
-	type ping${1} >/dev/null 2>&1 && PING="ping${1}" || PING="ping -${1}"
-	$PING -q -c 1 -W 1 ${2%%/*} >/dev/null 2>&1
-}
-
-wait_for_ip()
-{
-	local _i
-	echo -n "Wait for testing IPv4/IPv6 to become available "
-	for _i in $(seq ${MAX_PING_TRIES}); do
-		echo -n "."
-		if ping_once 4 ${TEST_IPv4} && ping_once 6 ${TEST_IPv6}; then
-			echo " OK"
-			return
-		fi
-	done
-	echo 1>&2 "ERROR: Timeout waiting for test IP to become available."
-	exit 1
-}
-
-setup()
-{
-	# Create testing interfaces not to interfere with current environment.
-	ip link add dev ${TEST_IF} type veth peer name ${TEST_IF_PEER}
-	ip link set ${TEST_IF} up
-	ip link set ${TEST_IF_PEER} up
-
-	ip -4 addr add ${TEST_IPv4} dev ${TEST_IF}
-	ip -6 addr add ${TEST_IPv6} dev ${TEST_IF}
-	wait_for_ip
-}
-
-cleanup()
-{
-	ip link del ${TEST_IF} 2>/dev/null || :
-	ip link del ${TEST_IF_PEER} 2>/dev/null || :
-}
-
-main()
-{
-	trap cleanup EXIT 2 3 6 15
-	setup
-	./test_sock_addr setup_done
-}
-
-BASENAME=$(basename $0 .sh)
-TEST_IF="${BASENAME}1"
-TEST_IF_PEER="${BASENAME}2"
-TEST_IPv4="127.0.0.4/8"
-TEST_IPv6="::6/128"
-MAX_PING_TRIES=5
-
-main
diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 024a0faafb3b..76568db7a664 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -56,6 +56,8 @@ static void running_handler(int a);
 #define BPF_SOCKHASH_FILENAME "test_sockhash_kern.bpf.o"
 #define CG_PATH "/sockmap"
 
+#define EDATAINTEGRITY 2001
+
 /* global sockets */
 int s1, s2, c1, c2, p1, p2;
 int test_cnt;
@@ -63,7 +65,8 @@ int passed;
 int failed;
 int map_fd[9];
 struct bpf_map *maps[9];
-int prog_fd[11];
+struct bpf_program *progs[9];
+struct bpf_link *links[9];
 
 int txmsg_pass;
 int txmsg_redir;
@@ -85,6 +88,10 @@ int ktls;
 int peek_flag;
 int skb_use_parser;
 int txmsg_omit_skb_parser;
+int verify_push_start;
+int verify_push_len;
+int verify_pop_start;
+int verify_pop_len;
 
 static const struct option long_options[] = {
 	{"help",	no_argument,		NULL, 'h' },
@@ -417,16 +424,18 @@ static int msg_loop_sendpage(int fd, int iov_length, int cnt,
 {
 	bool drop = opt->drop_expected;
 	unsigned char k = 0;
+	int i, j, fp;
 	FILE *file;
-	int i, fp;
 
 	file = tmpfile();
 	if (!file) {
 		perror("create file for sendpage");
 		return 1;
 	}
-	for (i = 0; i < iov_length * cnt; i++, k++)
-		fwrite(&k, sizeof(char), 1, file);
+	for (i = 0; i < cnt; i++, k = 0) {
+		for (j = 0; j < iov_length; j++, k++)
+			fwrite(&k, sizeof(char), 1, file);
+	}
 	fflush(file);
 	fseek(file, 0, SEEK_SET);
 
@@ -509,42 +518,111 @@ unwind_iov:
 	return -ENOMEM;
 }
 
-static int msg_verify_data(struct msghdr *msg, int size, int chunk_sz)
+/* In push or pop test, we need to do some calculations for msg_verify_data */
+static void msg_verify_date_prep(void)
 {
-	int i, j = 0, bytes_cnt = 0;
-	unsigned char k = 0;
+	int push_range_end = txmsg_start_push + txmsg_end_push - 1;
+	int pop_range_end = txmsg_start_pop + txmsg_pop - 1;
+
+	if (txmsg_end_push && txmsg_pop &&
+	    txmsg_start_push <= pop_range_end && txmsg_start_pop <= push_range_end) {
+		/* The push range and the pop range overlap */
+		int overlap_len;
+
+		verify_push_start = txmsg_start_push;
+		verify_pop_start = txmsg_start_pop;
+		if (txmsg_start_push < txmsg_start_pop)
+			overlap_len = min(push_range_end - txmsg_start_pop + 1, txmsg_pop);
+		else
+			overlap_len = min(pop_range_end - txmsg_start_push + 1, txmsg_end_push);
+		verify_push_len = max(txmsg_end_push - overlap_len, 0);
+		verify_pop_len = max(txmsg_pop - overlap_len, 0);
+	} else {
+		/* Otherwise */
+		verify_push_start = txmsg_start_push;
+		verify_pop_start = txmsg_start_pop;
+		verify_push_len = txmsg_end_push;
+		verify_pop_len = txmsg_pop;
+	}
+}
 
-	for (i = 0; i < msg->msg_iovlen; i++) {
+static int msg_verify_data(struct msghdr *msg, int size, int chunk_sz,
+			   unsigned char *k_p, int *bytes_cnt_p,
+			   int *check_cnt_p, int *push_p)
+{
+	int bytes_cnt = *bytes_cnt_p, check_cnt = *check_cnt_p, push = *push_p;
+	unsigned char k = *k_p;
+	int i, j;
+
+	for (i = 0, j = 0; i < msg->msg_iovlen && size; i++, j = 0) {
 		unsigned char *d = msg->msg_iov[i].iov_base;
 
 		/* Special case test for skb ingress + ktls */
 		if (i == 0 && txmsg_ktls_skb) {
 			if (msg->msg_iov[i].iov_len < 4)
-				return -EIO;
+				return -EDATAINTEGRITY;
 			if (memcmp(d, "PASS", 4) != 0) {
 				fprintf(stderr,
 					"detected skb data error with skb ingress update @iov[%i]:%i \"%02x %02x %02x %02x\" != \"PASS\"\n",
 					i, 0, d[0], d[1], d[2], d[3]);
-				return -EIO;
+				return -EDATAINTEGRITY;
 			}
 			j = 4; /* advance index past PASS header */
 		}
 
 		for (; j < msg->msg_iov[i].iov_len && size; j++) {
+			if (push > 0 &&
+			    check_cnt == verify_push_start + verify_push_len - push) {
+				int skipped;
+revisit_push:
+				skipped = push;
+				if (j + push >= msg->msg_iov[i].iov_len)
+					skipped = msg->msg_iov[i].iov_len - j;
+				push -= skipped;
+				size -= skipped;
+				j += skipped - 1;
+				check_cnt += skipped;
+				continue;
+			}
+
+			if (verify_pop_len > 0 && check_cnt == verify_pop_start) {
+				bytes_cnt += verify_pop_len;
+				check_cnt += verify_pop_len;
+				k += verify_pop_len;
+
+				if (bytes_cnt == chunk_sz) {
+					k = 0;
+					bytes_cnt = 0;
+					check_cnt = 0;
+					push = verify_push_len;
+				}
+
+				if (push > 0 &&
+				    check_cnt == verify_push_start + verify_push_len - push)
+					goto revisit_push;
+			}
+
 			if (d[j] != k++) {
 				fprintf(stderr,
 					"detected data corruption @iov[%i]:%i %02x != %02x, %02x ?= %02x\n",
 					i, j, d[j], k - 1, d[j+1], k);
-				return -EIO;
+				return -EDATAINTEGRITY;
 			}
 			bytes_cnt++;
+			check_cnt++;
 			if (bytes_cnt == chunk_sz) {
 				k = 0;
 				bytes_cnt = 0;
+				check_cnt = 0;
+				push = verify_push_len;
 			}
 			size--;
 		}
 	}
+	*k_p = k;
+	*bytes_cnt_p = bytes_cnt;
+	*check_cnt_p = check_cnt;
+	*push_p = push;
 	return 0;
 }
 
@@ -597,10 +675,14 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		}
 		clock_gettime(CLOCK_MONOTONIC, &s->end);
 	} else {
+		float total_bytes, txmsg_pop_total, txmsg_push_total;
 		int slct, recvp = 0, recv, max_fd = fd;
-		float total_bytes, txmsg_pop_total;
 		int fd_flags = O_NONBLOCK;
 		struct timeval timeout;
+		unsigned char k = 0;
+		int bytes_cnt = 0;
+		int check_cnt = 0;
+		int push = 0;
 		fd_set w;
 
 		fcntl(fd, fd_flags);
@@ -614,12 +696,22 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 		 * This is really only useful for testing edge cases in code
 		 * paths.
 		 */
-		total_bytes = (float)iov_count * (float)iov_length * (float)cnt;
-		if (txmsg_apply)
+		total_bytes = (float)iov_length * (float)cnt;
+		if (!opt->sendpage)
+			total_bytes *= (float)iov_count;
+		if (txmsg_apply) {
+			txmsg_push_total = txmsg_end_push * (total_bytes / txmsg_apply);
 			txmsg_pop_total = txmsg_pop * (total_bytes / txmsg_apply);
-		else
+		} else {
+			txmsg_push_total = txmsg_end_push * cnt;
 			txmsg_pop_total = txmsg_pop * cnt;
+		}
+		total_bytes += txmsg_push_total;
 		total_bytes -= txmsg_pop_total;
+		if (data) {
+			msg_verify_date_prep();
+			push = verify_push_len;
+		}
 		err = clock_gettime(CLOCK_MONOTONIC, &s->start);
 		if (err < 0)
 			perror("recv start time");
@@ -680,7 +772,8 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 				}
 			}
 
-			s->bytes_recvd += recv;
+			if (recv > 0)
+				s->bytes_recvd += recv;
 
 			if (opt->check_recved_len && s->bytes_recvd > total_bytes) {
 				errno = EMSGSIZE;
@@ -691,10 +784,11 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 
 			if (data) {
 				int chunk_sz = opt->sendpage ?
-						iov_length * cnt :
+						iov_length :
 						iov_length * iov_count;
 
-				errno = msg_verify_data(&msg, recv, chunk_sz);
+				errno = msg_verify_data(&msg, recv, chunk_sz, &k, &bytes_cnt,
+							&check_cnt, &push);
 				if (errno) {
 					perror("data verify msg failed");
 					goto out_errno;
@@ -702,7 +796,11 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 				if (recvp) {
 					errno = msg_verify_data(&msg_peek,
 								recvp,
-								chunk_sz);
+								chunk_sz,
+								&k,
+								&bytes_cnt,
+								&check_cnt,
+								&push);
 					if (errno) {
 						perror("data verify msg_peek failed");
 						goto out_errno;
@@ -784,8 +882,6 @@ static int sendmsg_test(struct sockmap_options *opt)
 
 	rxpid = fork();
 	if (rxpid == 0) {
-		if (txmsg_pop || txmsg_start_pop)
-			iov_buf -= (txmsg_pop - txmsg_start_pop + 1);
 		if (opt->drop_expected || txmsg_ktls_skb_drop)
 			_exit(0);
 
@@ -810,7 +906,7 @@ static int sendmsg_test(struct sockmap_options *opt)
 				s.bytes_sent, sent_Bps, sent_Bps/giga,
 				s.bytes_recvd, recvd_Bps, recvd_Bps/giga,
 				peek_flag ? "(peek_msg)" : "");
-		if (err && txmsg_cork)
+		if (err && err != -EDATAINTEGRITY && txmsg_cork)
 			err = 0;
 		exit(err ? 1 : 0);
 	} else if (rxpid == -1) {
@@ -952,7 +1048,8 @@ enum {
 
 static int run_options(struct sockmap_options *options, int cg_fd,  int test)
 {
-	int i, key, next_key, err, tx_prog_fd = -1, zero = 0;
+	int i, key, next_key, err, zero = 0;
+	struct bpf_program *tx_prog;
 
 	/* If base test skip BPF setup */
 	if (test == BASE || test == BASE_SENDPAGE)
@@ -960,48 +1057,44 @@ static int run_options(struct sockmap_options *options, int cg_fd,  int test)
 
 	/* Attach programs to sockmap */
 	if (!txmsg_omit_skb_parser) {
-		err = bpf_prog_attach(prog_fd[0], map_fd[0],
-				      BPF_SK_SKB_STREAM_PARSER, 0);
-		if (err) {
+		links[0] = bpf_program__attach_sockmap(progs[0], map_fd[0]);
+		if (!links[0]) {
 			fprintf(stderr,
-				"ERROR: bpf_prog_attach (sockmap %i->%i): %d (%s)\n",
-				prog_fd[0], map_fd[0], err, strerror(errno));
-			return err;
+				"ERROR: bpf_program__attach_sockmap (sockmap %i->%i): (%s)\n",
+				bpf_program__fd(progs[0]), map_fd[0], strerror(errno));
+			return -1;
 		}
 	}
 
-	err = bpf_prog_attach(prog_fd[1], map_fd[0],
-				BPF_SK_SKB_STREAM_VERDICT, 0);
-	if (err) {
-		fprintf(stderr, "ERROR: bpf_prog_attach (sockmap): %d (%s)\n",
-			err, strerror(errno));
-		return err;
+	links[1] = bpf_program__attach_sockmap(progs[1], map_fd[0]);
+	if (!links[1]) {
+		fprintf(stderr, "ERROR: bpf_program__attach_sockmap (sockmap): (%s)\n",
+			strerror(errno));
+		return -1;
 	}
 
 	/* Attach programs to TLS sockmap */
 	if (txmsg_ktls_skb) {
 		if (!txmsg_omit_skb_parser) {
-			err = bpf_prog_attach(prog_fd[0], map_fd[8],
-					      BPF_SK_SKB_STREAM_PARSER, 0);
-			if (err) {
+			links[2] = bpf_program__attach_sockmap(progs[0], map_fd[8]);
+			if (!links[2]) {
 				fprintf(stderr,
-					"ERROR: bpf_prog_attach (TLS sockmap %i->%i): %d (%s)\n",
-					prog_fd[0], map_fd[8], err, strerror(errno));
-				return err;
+					"ERROR: bpf_program__attach_sockmap (TLS sockmap %i->%i): (%s)\n",
+					bpf_program__fd(progs[0]), map_fd[8], strerror(errno));
+				return -1;
 			}
 		}
 
-		err = bpf_prog_attach(prog_fd[2], map_fd[8],
-				      BPF_SK_SKB_STREAM_VERDICT, 0);
-		if (err) {
-			fprintf(stderr, "ERROR: bpf_prog_attach (TLS sockmap): %d (%s)\n",
-				err, strerror(errno));
-			return err;
+		links[3] = bpf_program__attach_sockmap(progs[2], map_fd[8]);
+		if (!links[3]) {
+			fprintf(stderr, "ERROR: bpf_program__attach_sockmap (TLS sockmap): (%s)\n",
+				strerror(errno));
+			return -1;
 		}
 	}
 
 	/* Attach to cgroups */
-	err = bpf_prog_attach(prog_fd[3], cg_fd, BPF_CGROUP_SOCK_OPS, 0);
+	err = bpf_prog_attach(bpf_program__fd(progs[3]), cg_fd, BPF_CGROUP_SOCK_OPS, 0);
 	if (err) {
 		fprintf(stderr, "ERROR: bpf_prog_attach (groups): %d (%s)\n",
 			err, strerror(errno));
@@ -1017,30 +1110,31 @@ run:
 
 	/* Attach txmsg program to sockmap */
 	if (txmsg_pass)
-		tx_prog_fd = prog_fd[4];
+		tx_prog = progs[4];
 	else if (txmsg_redir)
-		tx_prog_fd = prog_fd[5];
+		tx_prog = progs[5];
 	else if (txmsg_apply)
-		tx_prog_fd = prog_fd[6];
+		tx_prog = progs[6];
 	else if (txmsg_cork)
-		tx_prog_fd = prog_fd[7];
+		tx_prog = progs[7];
 	else if (txmsg_drop)
-		tx_prog_fd = prog_fd[8];
+		tx_prog = progs[8];
 	else
-		tx_prog_fd = 0;
+		tx_prog = NULL;
 
-	if (tx_prog_fd) {
-		int redir_fd, i = 0;
+	if (tx_prog) {
+		int redir_fd;
 
-		err = bpf_prog_attach(tx_prog_fd,
-				      map_fd[1], BPF_SK_MSG_VERDICT, 0);
-		if (err) {
+		links[4] = bpf_program__attach_sockmap(tx_prog, map_fd[1]);
+		if (!links[4]) {
 			fprintf(stderr,
-				"ERROR: bpf_prog_attach (txmsg): %d (%s)\n",
-				err, strerror(errno));
+				"ERROR: bpf_program__attach_sockmap (txmsg): (%s)\n",
+				strerror(errno));
+			err = -1;
 			goto out;
 		}
 
+		i = 0;
 		err = bpf_map_update_elem(map_fd[1], &i, &c1, BPF_ANY);
 		if (err) {
 			fprintf(stderr,
@@ -1278,17 +1372,15 @@ run:
 	} else
 		fprintf(stderr, "unknown test\n");
 out:
-	/* Detatch and zero all the maps */
-	bpf_prog_detach2(prog_fd[3], cg_fd, BPF_CGROUP_SOCK_OPS);
-	bpf_prog_detach2(prog_fd[0], map_fd[0], BPF_SK_SKB_STREAM_PARSER);
-	bpf_prog_detach2(prog_fd[1], map_fd[0], BPF_SK_SKB_STREAM_VERDICT);
-	bpf_prog_detach2(prog_fd[0], map_fd[8], BPF_SK_SKB_STREAM_PARSER);
-	bpf_prog_detach2(prog_fd[2], map_fd[8], BPF_SK_SKB_STREAM_VERDICT);
+	/* Detach and zero all the maps */
+	bpf_prog_detach2(bpf_program__fd(progs[3]), cg_fd, BPF_CGROUP_SOCK_OPS);
 
-	if (tx_prog_fd >= 0)
-		bpf_prog_detach2(tx_prog_fd, map_fd[1], BPF_SK_MSG_VERDICT);
+	for (i = 0; i < ARRAY_SIZE(links); i++) {
+		if (links[i])
+			bpf_link__detach(links[i]);
+	}
 
-	for (i = 0; i < 8; i++) {
+	for (i = 0; i < ARRAY_SIZE(map_fd); i++) {
 		key = next_key = 0;
 		bpf_map_update_elem(map_fd[i], &key, &zero, BPF_ANY);
 		while (bpf_map_get_next_key(map_fd[i], &key, &next_key) == 0) {
@@ -1458,8 +1550,8 @@ static void test_send_many(struct sockmap_options *opt, int cgrp)
 
 static void test_send_large(struct sockmap_options *opt, int cgrp)
 {
-	opt->iov_length = 256;
-	opt->iov_count = 1024;
+	opt->iov_length = 8192;
+	opt->iov_count = 32;
 	opt->rate = 2;
 	test_exec(cgrp, opt);
 }
@@ -1487,8 +1579,12 @@ static void test_txmsg_redir(int cgrp, struct sockmap_options *opt)
 
 static void test_txmsg_redir_wait_sndmem(int cgrp, struct sockmap_options *opt)
 {
-	txmsg_redir = 1;
 	opt->tx_wait_mem = true;
+	txmsg_redir = 1;
+	test_send_large(opt, cgrp);
+
+	txmsg_redir = 1;
+	txmsg_apply = 4097;
 	test_send_large(opt, cgrp);
 	opt->tx_wait_mem = false;
 }
@@ -1588,17 +1684,19 @@ static void test_txmsg_cork_hangs(int cgrp, struct sockmap_options *opt)
 static void test_txmsg_pull(int cgrp, struct sockmap_options *opt)
 {
 	/* Test basic start/end */
+	txmsg_pass = 1;
 	txmsg_start = 1;
 	txmsg_end = 2;
 	test_send(opt, cgrp);
 
 	/* Test >4k pull */
+	txmsg_pass = 1;
 	txmsg_start = 4096;
 	txmsg_end = 9182;
 	test_send_large(opt, cgrp);
 
 	/* Test pull + redirect */
-	txmsg_redir = 0;
+	txmsg_redir = 1;
 	txmsg_start = 1;
 	txmsg_end = 2;
 	test_send(opt, cgrp);
@@ -1620,12 +1718,16 @@ static void test_txmsg_pull(int cgrp, struct sockmap_options *opt)
 
 static void test_txmsg_pop(int cgrp, struct sockmap_options *opt)
 {
+	bool data = opt->data_test;
+
 	/* Test basic pop */
+	txmsg_pass = 1;
 	txmsg_start_pop = 1;
 	txmsg_pop = 2;
 	test_send_many(opt, cgrp);
 
 	/* Test pop with >4k */
+	txmsg_pass = 1;
 	txmsg_start_pop = 4096;
 	txmsg_pop = 4096;
 	test_send_large(opt, cgrp);
@@ -1636,6 +1738,12 @@ static void test_txmsg_pop(int cgrp, struct sockmap_options *opt)
 	txmsg_pop = 2;
 	test_send_many(opt, cgrp);
 
+	/* TODO: Test for pop + cork should be different,
+	 * - It makes the layout of the received data difficult
+	 * - It makes it hard to calculate the total_bytes in the recvmsg
+	 * Temporarily skip the data integrity test for this case now.
+	 */
+	opt->data_test = false;
 	/* Test pop + cork */
 	txmsg_redir = 0;
 	txmsg_cork = 512;
@@ -1649,16 +1757,21 @@ static void test_txmsg_pop(int cgrp, struct sockmap_options *opt)
 	txmsg_start_pop = 1;
 	txmsg_pop = 2;
 	test_send_many(opt, cgrp);
+	opt->data_test = data;
 }
 
 static void test_txmsg_push(int cgrp, struct sockmap_options *opt)
 {
+	bool data = opt->data_test;
+
 	/* Test basic push */
+	txmsg_pass = 1;
 	txmsg_start_push = 1;
 	txmsg_end_push = 1;
 	test_send(opt, cgrp);
 
 	/* Test push 4kB >4k */
+	txmsg_pass = 1;
 	txmsg_start_push = 4096;
 	txmsg_end_push = 4096;
 	test_send_large(opt, cgrp);
@@ -1669,18 +1782,63 @@ static void test_txmsg_push(int cgrp, struct sockmap_options *opt)
 	txmsg_end_push = 2;
 	test_send_many(opt, cgrp);
 
+	/* TODO: Test for push + cork should be different,
+	 * - It makes the layout of the received data difficult
+	 * - It makes it hard to calculate the total_bytes in the recvmsg
+	 * Temporarily skip the data integrity test for this case now.
+	 */
+	opt->data_test = false;
 	/* Test push + cork */
 	txmsg_redir = 0;
 	txmsg_cork = 512;
 	txmsg_start_push = 1;
 	txmsg_end_push = 2;
 	test_send_many(opt, cgrp);
+	opt->data_test = data;
 }
 
 static void test_txmsg_push_pop(int cgrp, struct sockmap_options *opt)
 {
+	/* Test push/pop range overlapping */
+	txmsg_pass = 1;
+	txmsg_start_push = 1;
+	txmsg_end_push = 10;
+	txmsg_start_pop = 5;
+	txmsg_pop = 4;
+	test_send_large(opt, cgrp);
+
+	txmsg_pass = 1;
+	txmsg_start_push = 1;
+	txmsg_end_push = 10;
+	txmsg_start_pop = 5;
+	txmsg_pop = 16;
+	test_send_large(opt, cgrp);
+
+	txmsg_pass = 1;
+	txmsg_start_push = 5;
+	txmsg_end_push = 4;
+	txmsg_start_pop = 1;
+	txmsg_pop = 10;
+	test_send_large(opt, cgrp);
+
+	txmsg_pass = 1;
+	txmsg_start_push = 5;
+	txmsg_end_push = 16;
+	txmsg_start_pop = 1;
+	txmsg_pop = 10;
+	test_send_large(opt, cgrp);
+
+	/* Test push/pop range non-overlapping */
+	txmsg_pass = 1;
 	txmsg_start_push = 1;
 	txmsg_end_push = 10;
+	txmsg_start_pop = 16;
+	txmsg_pop = 4;
+	test_send_large(opt, cgrp);
+
+	txmsg_pass = 1;
+	txmsg_start_push = 16;
+	txmsg_end_push = 10;
 	txmsg_start_pop = 5;
 	txmsg_pop = 4;
 	test_send_large(opt, cgrp);
@@ -1783,34 +1941,6 @@ char *map_names[] = {
 	"tls_sock_map",
 };
 
-int prog_attach_type[] = {
-	BPF_SK_SKB_STREAM_PARSER,
-	BPF_SK_SKB_STREAM_VERDICT,
-	BPF_SK_SKB_STREAM_VERDICT,
-	BPF_CGROUP_SOCK_OPS,
-	BPF_SK_MSG_VERDICT,
-	BPF_SK_MSG_VERDICT,
-	BPF_SK_MSG_VERDICT,
-	BPF_SK_MSG_VERDICT,
-	BPF_SK_MSG_VERDICT,
-	BPF_SK_MSG_VERDICT,
-	BPF_SK_MSG_VERDICT,
-};
-
-int prog_type[] = {
-	BPF_PROG_TYPE_SK_SKB,
-	BPF_PROG_TYPE_SK_SKB,
-	BPF_PROG_TYPE_SK_SKB,
-	BPF_PROG_TYPE_SOCK_OPS,
-	BPF_PROG_TYPE_SK_MSG,
-	BPF_PROG_TYPE_SK_MSG,
-	BPF_PROG_TYPE_SK_MSG,
-	BPF_PROG_TYPE_SK_MSG,
-	BPF_PROG_TYPE_SK_MSG,
-	BPF_PROG_TYPE_SK_MSG,
-	BPF_PROG_TYPE_SK_MSG,
-};
-
 static int populate_progs(char *bpf_file)
 {
 	struct bpf_program *prog;
@@ -1829,17 +1959,10 @@ static int populate_progs(char *bpf_file)
 		return -1;
 	}
 
-	bpf_object__for_each_program(prog, obj) {
-		bpf_program__set_type(prog, prog_type[i]);
-		bpf_program__set_expected_attach_type(prog,
-						      prog_attach_type[i]);
-		i++;
-	}
-
 	i = bpf_object__load(obj);
 	i = 0;
 	bpf_object__for_each_program(prog, obj) {
-		prog_fd[i] = bpf_program__fd(prog);
+		progs[i] = prog;
 		i++;
 	}
 
@@ -1853,6 +1976,9 @@ static int populate_progs(char *bpf_file)
 		}
 	}
 
+	for (i = 0; i < ARRAY_SIZE(links); i++)
+		links[i] = NULL;
+
 	return 0;
 }
 
@@ -1887,10 +2013,13 @@ static int check_whitelist(struct _test *t, struct sockmap_options *opt)
 	while (entry) {
 		if ((opt->prepend && strstr(opt->prepend, entry) != 0) ||
 		    strstr(opt->map, entry) != 0 ||
-		    strstr(t->title, entry) != 0)
+		    strstr(t->title, entry) != 0) {
+			free(ptr);
 			return 0;
+		}
 		entry = strtok(NULL, ",");
 	}
+	free(ptr);
 	return -EINVAL;
 }
 
@@ -1907,10 +2036,13 @@ static int check_blacklist(struct _test *t, struct sockmap_options *opt)
 	while (entry) {
 		if ((opt->prepend && strstr(opt->prepend, entry) != 0) ||
 		    strstr(opt->map, entry) != 0 ||
-		    strstr(t->title, entry) != 0)
+		    strstr(t->title, entry) != 0) {
+			free(ptr);
 			return 0;
+		}
 		entry = strtok(NULL, ",");
 	}
+	free(ptr);
 	return -EINVAL;
 }
 
@@ -1964,7 +2096,6 @@ static void test_selftests_ktls(int cg_fd, struct sockmap_options *opt)
 
 static int test_selftest(int cg_fd, struct sockmap_options *opt)
 {
-
 	test_selftests_sockmap(cg_fd, opt);
 	test_selftests_sockhash(cg_fd, opt);
 	test_selftests_ktls(cg_fd, opt);
@@ -2104,9 +2235,9 @@ out:
 		free(options.whitelist);
 	if (options.blacklist)
 		free(options.blacklist);
+	close(cg_fd);
 	if (cg_created)
 		cleanup_cgroup_environment();
-	close(cg_fd);
 	return err;
 }
 
diff --git a/tools/testing/selftests/bpf/test_tag.c b/tools/testing/selftests/bpf/test_tag.c
index 5546b05a0486..f1300047c1e0 100644
--- a/tools/testing/selftests/bpf/test_tag.c
+++ b/tools/testing/selftests/bpf/test_tag.c
@@ -116,7 +116,7 @@ static void tag_from_alg(int insns, uint8_t *tag, uint32_t len)
 	static const struct sockaddr_alg alg = {
 		.salg_family	= AF_ALG,
 		.salg_type	= "hash",
-		.salg_name	= "sha1",
+		.salg_name	= "sha256",
 	};
 	int fd_base, fd_alg, ret;
 	ssize_t size;
diff --git a/tools/testing/selftests/bpf/test_tc_edt.sh b/tools/testing/selftests/bpf/test_tc_edt.sh
deleted file mode 100755
index 76f0bd17061f..000000000000
--- a/tools/testing/selftests/bpf/test_tc_edt.sh
+++ /dev/null
@@ -1,100 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-#
-# This test installs a TC bpf program that throttles a TCP flow
-# with dst port = 9000 down to 5MBps. Then it measures actual
-# throughput of the flow.
-
-BPF_FILE="test_tc_edt.bpf.o"
-if [[ $EUID -ne 0 ]]; then
-	echo "This script must be run as root"
-	echo "FAIL"
-	exit 1
-fi
-
-# check that nc, dd, and timeout are present
-command -v nc >/dev/null 2>&1 || \
-	{ echo >&2 "nc is not available"; exit 1; }
-command -v dd >/dev/null 2>&1 || \
-	{ echo >&2 "nc is not available"; exit 1; }
-command -v timeout >/dev/null 2>&1 || \
-	{ echo >&2 "timeout is not available"; exit 1; }
-
-readonly NS_SRC="ns-src-$(mktemp -u XXXXXX)"
-readonly NS_DST="ns-dst-$(mktemp -u XXXXXX)"
-
-readonly IP_SRC="172.16.1.100"
-readonly IP_DST="172.16.2.100"
-
-cleanup()
-{
-	ip netns del ${NS_SRC}
-	ip netns del ${NS_DST}
-}
-
-trap cleanup EXIT
-
-set -e  # exit on error
-
-ip netns add "${NS_SRC}"
-ip netns add "${NS_DST}"
-ip link add veth_src type veth peer name veth_dst
-ip link set veth_src netns ${NS_SRC}
-ip link set veth_dst netns ${NS_DST}
-
-ip -netns ${NS_SRC} addr add ${IP_SRC}/24  dev veth_src
-ip -netns ${NS_DST} addr add ${IP_DST}/24  dev veth_dst
-
-ip -netns ${NS_SRC} link set dev veth_src up
-ip -netns ${NS_DST} link set dev veth_dst up
-
-ip -netns ${NS_SRC} route add ${IP_DST}/32  dev veth_src
-ip -netns ${NS_DST} route add ${IP_SRC}/32  dev veth_dst
-
-# set up TC on TX
-ip netns exec ${NS_SRC} tc qdisc add dev veth_src root fq
-ip netns exec ${NS_SRC} tc qdisc add dev veth_src clsact
-ip netns exec ${NS_SRC} tc filter add dev veth_src egress \
-	bpf da obj ${BPF_FILE} sec cls_test
-
-
-# start the listener
-ip netns exec ${NS_DST} bash -c \
-	"nc -4 -l -p 9000 >/dev/null &"
-declare -i NC_PID=$!
-sleep 1
-
-declare -ir TIMEOUT=20
-declare -ir EXPECTED_BPS=5000000
-
-# run the load, capture RX bytes on DST
-declare -ir RX_BYTES_START=$( ip netns exec ${NS_DST} \
-	cat /sys/class/net/veth_dst/statistics/rx_bytes )
-
-set +e
-ip netns exec ${NS_SRC} bash -c "timeout ${TIMEOUT} dd if=/dev/zero \
-	bs=1000 count=1000000 > /dev/tcp/${IP_DST}/9000 2>/dev/null"
-set -e
-
-declare -ir RX_BYTES_END=$( ip netns exec ${NS_DST} \
-	cat /sys/class/net/veth_dst/statistics/rx_bytes )
-
-declare -ir ACTUAL_BPS=$(( ($RX_BYTES_END - $RX_BYTES_START) / $TIMEOUT ))
-
-echo $TIMEOUT $ACTUAL_BPS $EXPECTED_BPS | \
-	awk '{printf "elapsed: %d sec; bps difference: %.2f%%\n",
-		$1, ($2-$3)*100.0/$3}'
-
-# Pass the test if the actual bps is within 1% of the expected bps.
-# The difference is usually about 0.1% on a 20-sec test, and ==> zero
-# the longer the test runs.
-declare -ir RES=$( echo $ACTUAL_BPS $EXPECTED_BPS | \
-	 awk 'function abs(x){return ((x < 0.0) ? -x : x)}
-	      {if (abs(($1-$2)*100.0/$2) > 1.0) { print "1" }
-		else { print "0"} }' )
-if [ "${RES}" == "0" ] ; then
-	echo "PASS"
-else
-	echo "FAIL"
-	exit 1
-fi
diff --git a/tools/testing/selftests/bpf/test_tc_tunnel.sh b/tools/testing/selftests/bpf/test_tc_tunnel.sh
deleted file mode 100755
index 334bdfeab940..000000000000
--- a/tools/testing/selftests/bpf/test_tc_tunnel.sh
+++ /dev/null
@@ -1,305 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-#
-# In-place tunneling
-
-BPF_FILE="test_tc_tunnel.bpf.o"
-# must match the port that the bpf program filters on
-readonly port=8000
-
-readonly ns_prefix="ns-$$-"
-readonly ns1="${ns_prefix}1"
-readonly ns2="${ns_prefix}2"
-
-readonly ns1_v4=192.168.1.1
-readonly ns2_v4=192.168.1.2
-readonly ns1_v6=fd::1
-readonly ns2_v6=fd::2
-
-# Must match port used by bpf program
-readonly udpport=5555
-# MPLSoverUDP
-readonly mplsudpport=6635
-readonly mplsproto=137
-
-readonly infile="$(mktemp)"
-readonly outfile="$(mktemp)"
-
-setup() {
-	ip netns add "${ns1}"
-	ip netns add "${ns2}"
-
-	ip link add dev veth1 mtu 1500 netns "${ns1}" type veth \
-	      peer name veth2 mtu 1500 netns "${ns2}"
-
-	ip netns exec "${ns1}" ethtool -K veth1 tso off
-
-	ip -netns "${ns1}" link set veth1 up
-	ip -netns "${ns2}" link set veth2 up
-
-	ip -netns "${ns1}" -4 addr add "${ns1_v4}/24" dev veth1
-	ip -netns "${ns2}" -4 addr add "${ns2_v4}/24" dev veth2
-	ip -netns "${ns1}" -6 addr add "${ns1_v6}/64" dev veth1 nodad
-	ip -netns "${ns2}" -6 addr add "${ns2_v6}/64" dev veth2 nodad
-
-	# clamp route to reserve room for tunnel headers
-	ip -netns "${ns1}" -4 route flush table main
-	ip -netns "${ns1}" -6 route flush table main
-	ip -netns "${ns1}" -4 route add "${ns2_v4}" mtu 1450 dev veth1
-	ip -netns "${ns1}" -6 route add "${ns2_v6}" mtu 1430 dev veth1
-
-	sleep 1
-
-	dd if=/dev/urandom of="${infile}" bs="${datalen}" count=1 status=none
-}
-
-cleanup() {
-	ip netns del "${ns2}"
-	ip netns del "${ns1}"
-
-	if [[ -f "${outfile}" ]]; then
-		rm "${outfile}"
-	fi
-	if [[ -f "${infile}" ]]; then
-		rm "${infile}"
-	fi
-
-	if [[ -n $server_pid ]]; then
-		kill $server_pid 2> /dev/null
-	fi
-}
-
-server_listen() {
-	ip netns exec "${ns2}" nc "${netcat_opt}" -l "${port}" > "${outfile}" &
-	server_pid=$!
-	sleep 0.2
-}
-
-client_connect() {
-	ip netns exec "${ns1}" timeout 2 nc "${netcat_opt}" -w 1 "${addr2}" "${port}" < "${infile}"
-	echo $?
-}
-
-verify_data() {
-	wait "${server_pid}"
-	server_pid=
-	# sha1sum returns two fields [sha1] [filepath]
-	# convert to bash array and access first elem
-	insum=($(sha1sum ${infile}))
-	outsum=($(sha1sum ${outfile}))
-	if [[ "${insum[0]}" != "${outsum[0]}" ]]; then
-		echo "data mismatch"
-		exit 1
-	fi
-}
-
-set -e
-
-# no arguments: automated test, run all
-if [[ "$#" -eq "0" ]]; then
-	echo "ipip"
-	$0 ipv4 ipip none 100
-
-	echo "ip6ip6"
-	$0 ipv6 ip6tnl none 100
-
-	echo "sit"
-	$0 ipv6 sit none 100
-
-	echo "ip4 vxlan"
-	$0 ipv4 vxlan eth 2000
-
-	echo "ip6 vxlan"
-	$0 ipv6 ip6vxlan eth 2000
-
-	for mac in none mpls eth ; do
-		echo "ip gre $mac"
-		$0 ipv4 gre $mac 100
-
-		echo "ip6 gre $mac"
-		$0 ipv6 ip6gre $mac 100
-
-		echo "ip gre $mac gso"
-		$0 ipv4 gre $mac 2000
-
-		echo "ip6 gre $mac gso"
-		$0 ipv6 ip6gre $mac 2000
-
-		echo "ip udp $mac"
-		$0 ipv4 udp $mac 100
-
-		echo "ip6 udp $mac"
-		$0 ipv6 ip6udp $mac 100
-
-		echo "ip udp $mac gso"
-		$0 ipv4 udp $mac 2000
-
-		echo "ip6 udp $mac gso"
-		$0 ipv6 ip6udp $mac 2000
-	done
-
-	echo "OK. All tests passed"
-	exit 0
-fi
-
-if [[ "$#" -ne "4" ]]; then
-	echo "Usage: $0"
-	echo "   or: $0 <ipv4|ipv6> <tuntype> <none|mpls|eth> <data_len>"
-	exit 1
-fi
-
-case "$1" in
-"ipv4")
-	readonly addr1="${ns1_v4}"
-	readonly addr2="${ns2_v4}"
-	readonly ipproto=4
-	readonly netcat_opt=-${ipproto}
-	readonly foumod=fou
-	readonly foutype=ipip
-	readonly fouproto=4
-	readonly fouproto_mpls=${mplsproto}
-	readonly gretaptype=gretap
-	;;
-"ipv6")
-	readonly addr1="${ns1_v6}"
-	readonly addr2="${ns2_v6}"
-	readonly ipproto=6
-	readonly netcat_opt=-${ipproto}
-	readonly foumod=fou6
-	readonly foutype=ip6tnl
-	readonly fouproto="41 -6"
-	readonly fouproto_mpls="${mplsproto} -6"
-	readonly gretaptype=ip6gretap
-	;;
-*)
-	echo "unknown arg: $1"
-	exit 1
-	;;
-esac
-
-readonly tuntype=$2
-readonly mac=$3
-readonly datalen=$4
-
-echo "encap ${addr1} to ${addr2}, type ${tuntype}, mac ${mac} len ${datalen}"
-
-trap cleanup EXIT
-
-setup
-
-# basic communication works
-echo "test basic connectivity"
-server_listen
-client_connect
-verify_data
-
-# clientside, insert bpf program to encap all TCP to port ${port}
-# client can no longer connect
-ip netns exec "${ns1}" tc qdisc add dev veth1 clsact
-ip netns exec "${ns1}" tc filter add dev veth1 egress \
-	bpf direct-action object-file ${BPF_FILE} \
-	section "encap_${tuntype}_${mac}"
-echo "test bpf encap without decap (expect failure)"
-server_listen
-! client_connect
-
-if [[ "$tuntype" =~ "udp" ]]; then
-	# Set up fou tunnel.
-	ttype="${foutype}"
-	targs="encap fou encap-sport auto encap-dport $udpport"
-	# fou may be a module; allow this to fail.
-	modprobe "${foumod}" ||true
-	if [[ "$mac" == "mpls" ]]; then
-		dport=${mplsudpport}
-		dproto=${fouproto_mpls}
-		tmode="mode any ttl 255"
-	else
-		dport=${udpport}
-		dproto=${fouproto}
-	fi
-	ip netns exec "${ns2}" ip fou add port $dport ipproto ${dproto}
-	targs="encap fou encap-sport auto encap-dport $dport"
-elif [[ "$tuntype" =~ "gre" && "$mac" == "eth" ]]; then
-	ttype=$gretaptype
-elif [[ "$tuntype" =~ "vxlan" && "$mac" == "eth" ]]; then
-	ttype="vxlan"
-	targs="id 1 dstport 8472 udp6zerocsumrx"
-else
-	ttype=$tuntype
-	targs=""
-fi
-
-# tunnel address family differs from inner for SIT
-if [[ "${tuntype}" == "sit" ]]; then
-	link_addr1="${ns1_v4}"
-	link_addr2="${ns2_v4}"
-else
-	link_addr1="${addr1}"
-	link_addr2="${addr2}"
-fi
-
-# serverside, insert decap module
-# server is still running
-# client can connect again
-ip netns exec "${ns2}" ip link add name testtun0 type "${ttype}" \
-	${tmode} remote "${link_addr1}" local "${link_addr2}" $targs
-
-expect_tun_fail=0
-
-if [[ "$tuntype" == "ip6udp" && "$mac" == "mpls" ]]; then
-	# No support for MPLS IPv6 fou tunnel; expect failure.
-	expect_tun_fail=1
-elif [[ "$tuntype" =~ "udp" && "$mac" == "eth" ]]; then
-	# No support for TEB fou tunnel; expect failure.
-	expect_tun_fail=1
-elif [[ "$tuntype" =~ (gre|vxlan) && "$mac" == "eth" ]]; then
-	# Share ethernet address between tunnel/veth2 so L2 decap works.
-	ethaddr=$(ip netns exec "${ns2}" ip link show veth2 | \
-		  awk '/ether/ { print $2 }')
-	ip netns exec "${ns2}" ip link set testtun0 address $ethaddr
-elif [[ "$mac" == "mpls" ]]; then
-	modprobe mpls_iptunnel ||true
-	modprobe mpls_gso ||true
-	ip netns exec "${ns2}" sysctl -qw net.mpls.platform_labels=65536
-	ip netns exec "${ns2}" ip -f mpls route add 1000 dev lo
-	ip netns exec "${ns2}" ip link set lo up
-	ip netns exec "${ns2}" sysctl -qw net.mpls.conf.testtun0.input=1
-	ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.lo.rp_filter=0
-fi
-
-# Because packets are decapped by the tunnel they arrive on testtun0 from
-# the IP stack perspective.  Ensure reverse path filtering is disabled
-# otherwise we drop the TCP SYN as arriving on testtun0 instead of the
-# expected veth2 (veth2 is where 192.168.1.2 is configured).
-ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.rp_filter=0
-# rp needs to be disabled for both all and testtun0 as the rp value is
-# selected as the max of the "all" and device-specific values.
-ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.testtun0.rp_filter=0
-ip netns exec "${ns2}" ip link set dev testtun0 up
-if [[ "$expect_tun_fail" == 1 ]]; then
-	# This tunnel mode is not supported, so we expect failure.
-	echo "test bpf encap with tunnel device decap (expect failure)"
-	! client_connect
-else
-	echo "test bpf encap with tunnel device decap"
-	client_connect
-	verify_data
-	server_listen
-fi
-
-# bpf_skb_net_shrink does not take tunnel flags yet, cannot update L3.
-if [[ "${tuntype}" == "sit" ]]; then
-	echo OK
-	exit 0
-fi
-
-# serverside, use BPF for decap
-ip netns exec "${ns2}" ip link del dev testtun0
-ip netns exec "${ns2}" tc qdisc add dev veth2 clsact
-ip netns exec "${ns2}" tc filter add dev veth2 ingress \
-	bpf direct-action object-file ${BPF_FILE} section decap
-echo "test bpf encap with bpf decap"
-client_connect
-verify_data
-
-echo OK
diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh
deleted file mode 100755
index b42c24282c25..000000000000
--- a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh
+++ /dev/null
@@ -1,85 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-# Copyright (c) 2018 Facebook
-# Copyright (c) 2019 Cloudflare
-
-set -eu
-readonly NS1="ns1-$(mktemp -u XXXXXX)"
-
-wait_for_ip()
-{
-	local _i
-	printf "Wait for IP %s to become available " "$1"
-	for _i in $(seq ${MAX_PING_TRIES}); do
-		printf "."
-		if ns1_exec ping -c 1 -W 1 "$1" >/dev/null 2>&1; then
-			echo " OK"
-			return
-		fi
-		sleep 1
-	done
-	echo 1>&2 "ERROR: Timeout waiting for test IP to become available."
-	exit 1
-}
-
-get_prog_id()
-{
-	awk '/ id / {sub(/.* id /, "", $0); print($1)}'
-}
-
-ns1_exec()
-{
-	ip netns exec ${NS1} "$@"
-}
-
-setup()
-{
-	ip netns add ${NS1}
-	ns1_exec ip link set lo up
-
-	ns1_exec sysctl -w net.ipv4.tcp_syncookies=2
-	ns1_exec sysctl -w net.ipv4.tcp_window_scaling=0
-	ns1_exec sysctl -w net.ipv4.tcp_timestamps=0
-	ns1_exec sysctl -w net.ipv4.tcp_sack=0
-
-	wait_for_ip 127.0.0.1
-	wait_for_ip ::1
-}
-
-cleanup()
-{
-	ip netns del ns1 2>/dev/null || :
-}
-
-main()
-{
-	trap cleanup EXIT 2 3 6 15
-	setup
-
-	printf "Testing clsact..."
-	ns1_exec tc qdisc add dev "${TEST_IF}" clsact
-	ns1_exec tc filter add dev "${TEST_IF}" ingress \
-		bpf obj "${BPF_PROG_OBJ}" sec "${CLSACT_SECTION}" da
-
-	BPF_PROG_ID=$(ns1_exec tc filter show dev "${TEST_IF}" ingress | \
-		      get_prog_id)
-	ns1_exec "${PROG}" "${BPF_PROG_ID}"
-	ns1_exec tc qdisc del dev "${TEST_IF}" clsact
-
-	printf "Testing XDP..."
-	ns1_exec ip link set "${TEST_IF}" xdp \
-		object "${BPF_PROG_OBJ}" section "${XDP_SECTION}"
-	BPF_PROG_ID=$(ns1_exec ip link show "${TEST_IF}" | get_prog_id)
-	ns1_exec "${PROG}" "${BPF_PROG_ID}"
-}
-
-DIR=$(dirname $0)
-TEST_IF=lo
-MAX_PING_TRIES=5
-BPF_PROG_OBJ="${DIR}/test_tcp_check_syncookie_kern.bpf.o"
-CLSACT_SECTION="tc"
-XDP_SECTION="xdp"
-BPF_PROG_ID=0
-PROG="${DIR}/test_tcp_check_syncookie_user"
-
-main
diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c
deleted file mode 100644
index 5c8ef062f760..000000000000
--- a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c
+++ /dev/null
@@ -1,299 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright (c) 2018 Facebook
-// Copyright (c) 2019 Cloudflare
-
-#include <limits.h>
-#include <string.h>
-#include <stdlib.h>
-#include <unistd.h>
-
-#include <arpa/inet.h>
-#include <netinet/in.h>
-#include <sys/types.h>
-#include <sys/socket.h>
-
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-#include "cgroup_helpers.h"
-
-static int start_server(const struct sockaddr *addr, socklen_t len, bool dual)
-{
-	int mode = !dual;
-	int fd;
-
-	fd = socket(addr->sa_family, SOCK_STREAM, 0);
-	if (fd == -1) {
-		log_err("Failed to create server socket");
-		goto out;
-	}
-
-	if (addr->sa_family == AF_INET6) {
-		if (setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, (char *)&mode,
-			       sizeof(mode)) == -1) {
-			log_err("Failed to set the dual-stack mode");
-			goto close_out;
-		}
-	}
-
-	if (bind(fd, addr, len) == -1) {
-		log_err("Failed to bind server socket");
-		goto close_out;
-	}
-
-	if (listen(fd, 128) == -1) {
-		log_err("Failed to listen on server socket");
-		goto close_out;
-	}
-
-	goto out;
-
-close_out:
-	close(fd);
-	fd = -1;
-out:
-	return fd;
-}
-
-static int connect_to_server(const struct sockaddr *addr, socklen_t len)
-{
-	int fd = -1;
-
-	fd = socket(addr->sa_family, SOCK_STREAM, 0);
-	if (fd == -1) {
-		log_err("Failed to create client socket");
-		goto out;
-	}
-
-	if (connect(fd, (const struct sockaddr *)addr, len) == -1) {
-		log_err("Fail to connect to server");
-		goto close_out;
-	}
-
-	goto out;
-
-close_out:
-	close(fd);
-	fd = -1;
-out:
-	return fd;
-}
-
-static int get_map_fd_by_prog_id(int prog_id, bool *xdp)
-{
-	struct bpf_prog_info info = {};
-	__u32 info_len = sizeof(info);
-	__u32 map_ids[1];
-	int prog_fd = -1;
-	int map_fd = -1;
-
-	prog_fd = bpf_prog_get_fd_by_id(prog_id);
-	if (prog_fd < 0) {
-		log_err("Failed to get fd by prog id %d", prog_id);
-		goto err;
-	}
-
-	info.nr_map_ids = 1;
-	info.map_ids = (__u64)(unsigned long)map_ids;
-
-	if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len)) {
-		log_err("Failed to get info by prog fd %d", prog_fd);
-		goto err;
-	}
-
-	if (!info.nr_map_ids) {
-		log_err("No maps found for prog fd %d", prog_fd);
-		goto err;
-	}
-
-	*xdp = info.type == BPF_PROG_TYPE_XDP;
-
-	map_fd = bpf_map_get_fd_by_id(map_ids[0]);
-	if (map_fd < 0)
-		log_err("Failed to get fd by map id %d", map_ids[0]);
-err:
-	if (prog_fd >= 0)
-		close(prog_fd);
-	return map_fd;
-}
-
-static int run_test(int server_fd, int results_fd, bool xdp,
-		    const struct sockaddr *addr, socklen_t len)
-{
-	int client = -1, srv_client = -1;
-	int ret = 0;
-	__u32 key = 0;
-	__u32 key_gen = 1;
-	__u32 key_mss = 2;
-	__u32 value = 0;
-	__u32 value_gen = 0;
-	__u32 value_mss = 0;
-
-	if (bpf_map_update_elem(results_fd, &key, &value, 0) < 0) {
-		log_err("Can't clear results");
-		goto err;
-	}
-
-	if (bpf_map_update_elem(results_fd, &key_gen, &value_gen, 0) < 0) {
-		log_err("Can't clear results");
-		goto err;
-	}
-
-	if (bpf_map_update_elem(results_fd, &key_mss, &value_mss, 0) < 0) {
-		log_err("Can't clear results");
-		goto err;
-	}
-
-	client = connect_to_server(addr, len);
-	if (client == -1)
-		goto err;
-
-	srv_client = accept(server_fd, NULL, 0);
-	if (srv_client == -1) {
-		log_err("Can't accept connection");
-		goto err;
-	}
-
-	if (bpf_map_lookup_elem(results_fd, &key, &value) < 0) {
-		log_err("Can't lookup result");
-		goto err;
-	}
-
-	if (value == 0) {
-		log_err("Didn't match syncookie: %u", value);
-		goto err;
-	}
-
-	if (bpf_map_lookup_elem(results_fd, &key_gen, &value_gen) < 0) {
-		log_err("Can't lookup result");
-		goto err;
-	}
-
-	if (xdp && value_gen == 0) {
-		// SYN packets do not get passed through generic XDP, skip the
-		// rest of the test.
-		printf("Skipping XDP cookie check\n");
-		goto out;
-	}
-
-	if (bpf_map_lookup_elem(results_fd, &key_mss, &value_mss) < 0) {
-		log_err("Can't lookup result");
-		goto err;
-	}
-
-	if (value != value_gen) {
-		log_err("BPF generated cookie does not match kernel one");
-		goto err;
-	}
-
-	if (value_mss < 536 || value_mss > USHRT_MAX) {
-		log_err("Unexpected MSS retrieved");
-		goto err;
-	}
-
-	goto out;
-
-err:
-	ret = 1;
-out:
-	close(client);
-	close(srv_client);
-	return ret;
-}
-
-static bool get_port(int server_fd, in_port_t *port)
-{
-	struct sockaddr_in addr;
-	socklen_t len = sizeof(addr);
-
-	if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) {
-		log_err("Failed to get server addr");
-		return false;
-	}
-
-	/* sin_port and sin6_port are located at the same offset. */
-	*port = addr.sin_port;
-	return true;
-}
-
-int main(int argc, char **argv)
-{
-	struct sockaddr_in addr4;
-	struct sockaddr_in6 addr6;
-	struct sockaddr_in addr4dual;
-	struct sockaddr_in6 addr6dual;
-	int server = -1;
-	int server_v6 = -1;
-	int server_dual = -1;
-	int results = -1;
-	int err = 0;
-	bool xdp;
-
-	if (argc < 2) {
-		fprintf(stderr, "Usage: %s prog_id\n", argv[0]);
-		exit(1);
-	}
-
-	/* Use libbpf 1.0 API mode */
-	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
-
-	results = get_map_fd_by_prog_id(atoi(argv[1]), &xdp);
-	if (results < 0) {
-		log_err("Can't get map");
-		goto err;
-	}
-
-	memset(&addr4, 0, sizeof(addr4));
-	addr4.sin_family = AF_INET;
-	addr4.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
-	addr4.sin_port = 0;
-	memcpy(&addr4dual, &addr4, sizeof(addr4dual));
-
-	memset(&addr6, 0, sizeof(addr6));
-	addr6.sin6_family = AF_INET6;
-	addr6.sin6_addr = in6addr_loopback;
-	addr6.sin6_port = 0;
-
-	memset(&addr6dual, 0, sizeof(addr6dual));
-	addr6dual.sin6_family = AF_INET6;
-	addr6dual.sin6_addr = in6addr_any;
-	addr6dual.sin6_port = 0;
-
-	server = start_server((const struct sockaddr *)&addr4, sizeof(addr4),
-			      false);
-	if (server == -1 || !get_port(server, &addr4.sin_port))
-		goto err;
-
-	server_v6 = start_server((const struct sockaddr *)&addr6,
-				 sizeof(addr6), false);
-	if (server_v6 == -1 || !get_port(server_v6, &addr6.sin6_port))
-		goto err;
-
-	server_dual = start_server((const struct sockaddr *)&addr6dual,
-				   sizeof(addr6dual), true);
-	if (server_dual == -1 || !get_port(server_dual, &addr4dual.sin_port))
-		goto err;
-
-	if (run_test(server, results, xdp,
-		     (const struct sockaddr *)&addr4, sizeof(addr4)))
-		goto err;
-
-	if (run_test(server_v6, results, xdp,
-		     (const struct sockaddr *)&addr6, sizeof(addr6)))
-		goto err;
-
-	if (run_test(server_dual, results, xdp,
-		     (const struct sockaddr *)&addr4dual, sizeof(addr4dual)))
-		goto err;
-
-	printf("ok\n");
-	goto out;
-err:
-	err = 1;
-out:
-	close(server);
-	close(server_v6);
-	close(server_dual);
-	close(results);
-	return err;
-}
diff --git a/tools/testing/selftests/bpf/test_tcp_hdr_options.h b/tools/testing/selftests/bpf/test_tcp_hdr_options.h
index 6118e3ab61fc..56c9f8a3ad3d 100644
--- a/tools/testing/selftests/bpf/test_tcp_hdr_options.h
+++ b/tools/testing/selftests/bpf/test_tcp_hdr_options.h
@@ -50,6 +50,7 @@ struct linum_err {
 
 #define TCPOPT_EOL		0
 #define TCPOPT_NOP		1
+#define TCPOPT_MSS		2
 #define TCPOPT_WINDOW		3
 #define TCPOPT_EXP		254
 
diff --git a/tools/testing/selftests/bpf/test_tcpnotify_user.c b/tools/testing/selftests/bpf/test_tcpnotify_user.c
index 595194453ff8..35b4893ccdf8 100644
--- a/tools/testing/selftests/bpf/test_tcpnotify_user.c
+++ b/tools/testing/selftests/bpf/test_tcpnotify_user.c
@@ -15,20 +15,18 @@
 #include <bpf/libbpf.h>
 #include <sys/ioctl.h>
 #include <linux/rtnetlink.h>
-#include <signal.h>
 #include <linux/perf_event.h>
-#include <linux/err.h>
 
-#include "bpf_util.h"
 #include "cgroup_helpers.h"
 
 #include "test_tcpnotify.h"
-#include "trace_helpers.h"
 #include "testing_helpers.h"
 
 #define SOCKET_BUFFER_SIZE (getpagesize() < 8192L ? getpagesize() : 8192L)
 
 pthread_t tid;
+static bool exit_thread;
+
 int rx_callbacks;
 
 static void dummyfn(void *ctx, int cpu, void *data, __u32 size)
@@ -45,7 +43,7 @@ void tcp_notifier_poller(struct perf_buffer *pb)
 {
 	int err;
 
-	while (1) {
+	while (!exit_thread) {
 		err = perf_buffer__poll(pb, 100);
 		if (err < 0 && err != -EINTR) {
 			printf("failed perf_buffer__poll: %d\n", err);
@@ -78,15 +76,10 @@ int main(int argc, char **argv)
 	int error = EXIT_FAILURE;
 	struct bpf_object *obj;
 	char test_script[80];
-	cpu_set_t cpuset;
 	__u32 key = 0;
 
 	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
 
-	CPU_ZERO(&cpuset);
-	CPU_SET(0, &cpuset);
-	pthread_setaffinity_np(pthread_self(), sizeof(cpu_set_t), &cpuset);
-
 	cg_fd = cgroup_setup_and_join(cg_path);
 	if (cg_fd < 0)
 		goto err;
@@ -151,6 +144,13 @@ int main(int argc, char **argv)
 
 	sleep(10);
 
+	exit_thread = true;
+	int ret = pthread_join(tid, NULL);
+	if (ret) {
+		printf("FAILED: pthread_join\n");
+		goto err;
+	}
+
 	if (verify_result(&g)) {
 		printf("FAILED: Wrong stats Expected %d calls, got %d\n",
 			g.ncalls, rx_callbacks);
diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh
deleted file mode 100755
index 2eaedc1d9ed3..000000000000
--- a/tools/testing/selftests/bpf/test_tunnel.sh
+++ /dev/null
@@ -1,698 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-# End-to-end eBPF tunnel test suite
-#   The script tests BPF network tunnel implementation.
-#
-# Topology:
-# ---------
-#     root namespace   |     at_ns0 namespace
-#                      |
-#      -----------     |     -----------
-#      | tnl dev |     |     | tnl dev |  (overlay network)
-#      -----------     |     -----------
-#      metadata-mode   |     native-mode
-#       with bpf       |
-#                      |
-#      ----------      |     ----------
-#      |  veth1  | --------- |  veth0  |  (underlay network)
-#      ----------    peer    ----------
-#
-#
-# Device Configuration
-# --------------------
-# Root namespace with metadata-mode tunnel + BPF
-# Device names and addresses:
-# 	veth1 IP: 172.16.1.200, IPv6: 00::22 (underlay)
-# 	tunnel dev <type>11, ex: gre11, IPv4: 10.1.1.200, IPv6: 1::22 (overlay)
-#
-# Namespace at_ns0 with native tunnel
-# Device names and addresses:
-# 	veth0 IPv4: 172.16.1.100, IPv6: 00::11 (underlay)
-# 	tunnel dev <type>00, ex: gre00, IPv4: 10.1.1.100, IPv6: 1::11 (overlay)
-#
-#
-# End-to-end ping packet flow
-# ---------------------------
-# Most of the tests start by namespace creation, device configuration,
-# then ping the underlay and overlay network.  When doing 'ping 10.1.1.100'
-# from root namespace, the following operations happen:
-# 1) Route lookup shows 10.1.1.100/24 belongs to tnl dev, fwd to tnl dev.
-# 2) Tnl device's egress BPF program is triggered and set the tunnel metadata,
-#    with remote_ip=172.16.1.100 and others.
-# 3) Outer tunnel header is prepended and route the packet to veth1's egress
-# 4) veth0's ingress queue receive the tunneled packet at namespace at_ns0
-# 5) Tunnel protocol handler, ex: vxlan_rcv, decap the packet
-# 6) Forward the packet to the overlay tnl dev
-
-BPF_FILE="test_tunnel_kern.bpf.o"
-BPF_PIN_TUNNEL_DIR="/sys/fs/bpf/tc/tunnel"
-PING_ARG="-c 3 -w 10 -q"
-ret=0
-GREEN='\033[0;92m'
-RED='\033[0;31m'
-NC='\033[0m' # No Color
-
-config_device()
-{
-	ip netns add at_ns0
-	ip link add veth0 type veth peer name veth1
-	ip link set veth0 netns at_ns0
-	ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0
-	ip netns exec at_ns0 ip link set dev veth0 up
-	ip link set dev veth1 up mtu 1500
-	ip addr add dev veth1 172.16.1.200/24
-}
-
-add_gre_tunnel()
-{
-	# at_ns0 namespace
-	ip netns exec at_ns0 \
-        ip link add dev $DEV_NS type $TYPE seq key 2 \
-		local 172.16.1.100 remote 172.16.1.200
-	ip netns exec at_ns0 ip link set dev $DEV_NS up
-	ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
-
-	# root namespace
-	ip link add dev $DEV type $TYPE key 2 external
-	ip link set dev $DEV up
-	ip addr add dev $DEV 10.1.1.200/24
-}
-
-add_ip6gretap_tunnel()
-{
-
-	# assign ipv6 address
-	ip netns exec at_ns0 ip addr add ::11/96 dev veth0
-	ip netns exec at_ns0 ip link set dev veth0 up
-	ip addr add dev veth1 ::22/96
-	ip link set dev veth1 up
-
-	# at_ns0 namespace
-	ip netns exec at_ns0 \
-		ip link add dev $DEV_NS type $TYPE seq flowlabel 0xbcdef key 2 \
-		local ::11 remote ::22
-
-	ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
-	ip netns exec at_ns0 ip addr add dev $DEV_NS fc80::100/96
-	ip netns exec at_ns0 ip link set dev $DEV_NS up
-
-	# root namespace
-	ip link add dev $DEV type $TYPE external
-	ip addr add dev $DEV 10.1.1.200/24
-	ip addr add dev $DEV fc80::200/24
-	ip link set dev $DEV up
-}
-
-add_erspan_tunnel()
-{
-	# at_ns0 namespace
-	if [ "$1" == "v1" ]; then
-		ip netns exec at_ns0 \
-		ip link add dev $DEV_NS type $TYPE seq key 2 \
-		local 172.16.1.100 remote 172.16.1.200 \
-		erspan_ver 1 erspan 123
-	else
-		ip netns exec at_ns0 \
-		ip link add dev $DEV_NS type $TYPE seq key 2 \
-		local 172.16.1.100 remote 172.16.1.200 \
-		erspan_ver 2 erspan_dir egress erspan_hwid 3
-	fi
-	ip netns exec at_ns0 ip link set dev $DEV_NS up
-	ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
-
-	# root namespace
-	ip link add dev $DEV type $TYPE external
-	ip link set dev $DEV up
-	ip addr add dev $DEV 10.1.1.200/24
-}
-
-add_ip6erspan_tunnel()
-{
-
-	# assign ipv6 address
-	ip netns exec at_ns0 ip addr add ::11/96 dev veth0
-	ip netns exec at_ns0 ip link set dev veth0 up
-	ip addr add dev veth1 ::22/96
-	ip link set dev veth1 up
-
-	# at_ns0 namespace
-	if [ "$1" == "v1" ]; then
-		ip netns exec at_ns0 \
-		ip link add dev $DEV_NS type $TYPE seq key 2 \
-		local ::11 remote ::22 \
-		erspan_ver 1 erspan 123
-	else
-		ip netns exec at_ns0 \
-		ip link add dev $DEV_NS type $TYPE seq key 2 \
-		local ::11 remote ::22 \
-		erspan_ver 2 erspan_dir egress erspan_hwid 7
-	fi
-	ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
-	ip netns exec at_ns0 ip link set dev $DEV_NS up
-
-	# root namespace
-	ip link add dev $DEV type $TYPE external
-	ip addr add dev $DEV 10.1.1.200/24
-	ip link set dev $DEV up
-}
-
-add_geneve_tunnel()
-{
-	# at_ns0 namespace
-	ip netns exec at_ns0 \
-		ip link add dev $DEV_NS type $TYPE \
-		id 2 dstport 6081 remote 172.16.1.200
-	ip netns exec at_ns0 ip link set dev $DEV_NS up
-	ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
-
-	# root namespace
-	ip link add dev $DEV type $TYPE dstport 6081 external
-	ip link set dev $DEV up
-	ip addr add dev $DEV 10.1.1.200/24
-}
-
-add_ip6geneve_tunnel()
-{
-	ip netns exec at_ns0 ip addr add ::11/96 dev veth0
-	ip netns exec at_ns0 ip link set dev veth0 up
-	ip addr add dev veth1 ::22/96
-	ip link set dev veth1 up
-
-	# at_ns0 namespace
-	ip netns exec at_ns0 \
-		ip link add dev $DEV_NS type $TYPE id 22 \
-		remote ::22     # geneve has no local option
-	ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
-	ip netns exec at_ns0 ip link set dev $DEV_NS up
-
-	# root namespace
-	ip link add dev $DEV type $TYPE external
-	ip addr add dev $DEV 10.1.1.200/24
-	ip link set dev $DEV up
-}
-
-add_ipip_tunnel()
-{
-	# at_ns0 namespace
-	ip netns exec at_ns0 \
-		ip link add dev $DEV_NS type $TYPE \
-		local 172.16.1.100 remote 172.16.1.200
-	ip netns exec at_ns0 ip link set dev $DEV_NS up
-	ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
-
-	# root namespace
-	ip link add dev $DEV type $TYPE external
-	ip link set dev $DEV up
-	ip addr add dev $DEV 10.1.1.200/24
-}
-
-add_ip6tnl_tunnel()
-{
-	ip netns exec at_ns0 ip addr add ::11/96 dev veth0
-	ip netns exec at_ns0 ip link set dev veth0 up
-	ip addr add dev veth1 ::22/96
-	ip link set dev veth1 up
-
-	# at_ns0 namespace
-	ip netns exec at_ns0 \
-		ip link add dev $DEV_NS type $TYPE \
-		local ::11 remote ::22
-	ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
-	ip netns exec at_ns0 ip addr add dev $DEV_NS 1::11/96
-	ip netns exec at_ns0 ip link set dev $DEV_NS up
-
-	# root namespace
-	ip link add dev $DEV type $TYPE external
-	ip addr add dev $DEV 10.1.1.200/24
-	ip addr add dev $DEV 1::22/96
-	ip link set dev $DEV up
-}
-
-test_gre()
-{
-	TYPE=gretap
-	DEV_NS=gretap00
-	DEV=gretap11
-	ret=0
-
-	check $TYPE
-	config_device
-	add_gre_tunnel
-	attach_bpf $DEV gre_set_tunnel gre_get_tunnel
-	ping $PING_ARG 10.1.1.100
-	check_err $?
-	ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
-	check_err $?
-	cleanup
-
-        if [ $ret -ne 0 ]; then
-                echo -e ${RED}"FAIL: $TYPE"${NC}
-                return 1
-        fi
-        echo -e ${GREEN}"PASS: $TYPE"${NC}
-}
-
-test_ip6gre()
-{
-	TYPE=ip6gre
-	DEV_NS=ip6gre00
-	DEV=ip6gre11
-	ret=0
-
-	check $TYPE
-	config_device
-	# reuse the ip6gretap function
-	add_ip6gretap_tunnel
-	attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel
-	# underlay
-	ping6 $PING_ARG ::11
-	# overlay: ipv4 over ipv6
-	ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
-	ping $PING_ARG 10.1.1.100
-	check_err $?
-	# overlay: ipv6 over ipv6
-	ip netns exec at_ns0 ping6 $PING_ARG fc80::200
-	check_err $?
-	cleanup
-
-        if [ $ret -ne 0 ]; then
-                echo -e ${RED}"FAIL: $TYPE"${NC}
-                return 1
-        fi
-        echo -e ${GREEN}"PASS: $TYPE"${NC}
-}
-
-test_ip6gretap()
-{
-	TYPE=ip6gretap
-	DEV_NS=ip6gretap00
-	DEV=ip6gretap11
-	ret=0
-
-	check $TYPE
-	config_device
-	add_ip6gretap_tunnel
-	attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel
-	# underlay
-	ping6 $PING_ARG ::11
-	# overlay: ipv4 over ipv6
-	ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
-	ping $PING_ARG 10.1.1.100
-	check_err $?
-	# overlay: ipv6 over ipv6
-	ip netns exec at_ns0 ping6 $PING_ARG fc80::200
-	check_err $?
-	cleanup
-
-	if [ $ret -ne 0 ]; then
-                echo -e ${RED}"FAIL: $TYPE"${NC}
-                return 1
-        fi
-        echo -e ${GREEN}"PASS: $TYPE"${NC}
-}
-
-test_erspan()
-{
-	TYPE=erspan
-	DEV_NS=erspan00
-	DEV=erspan11
-	ret=0
-
-	check $TYPE
-	config_device
-	add_erspan_tunnel $1
-	attach_bpf $DEV erspan_set_tunnel erspan_get_tunnel
-	ping $PING_ARG 10.1.1.100
-	check_err $?
-	ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
-	check_err $?
-	cleanup
-
-	if [ $ret -ne 0 ]; then
-                echo -e ${RED}"FAIL: $TYPE"${NC}
-                return 1
-        fi
-        echo -e ${GREEN}"PASS: $TYPE"${NC}
-}
-
-test_ip6erspan()
-{
-	TYPE=ip6erspan
-	DEV_NS=ip6erspan00
-	DEV=ip6erspan11
-	ret=0
-
-	check $TYPE
-	config_device
-	add_ip6erspan_tunnel $1
-	attach_bpf $DEV ip4ip6erspan_set_tunnel ip4ip6erspan_get_tunnel
-	ping6 $PING_ARG ::11
-	ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
-	check_err $?
-	cleanup
-
-	if [ $ret -ne 0 ]; then
-                echo -e ${RED}"FAIL: $TYPE"${NC}
-                return 1
-        fi
-        echo -e ${GREEN}"PASS: $TYPE"${NC}
-}
-
-test_geneve()
-{
-	TYPE=geneve
-	DEV_NS=geneve00
-	DEV=geneve11
-	ret=0
-
-	check $TYPE
-	config_device
-	add_geneve_tunnel
-	attach_bpf $DEV geneve_set_tunnel geneve_get_tunnel
-	ping $PING_ARG 10.1.1.100
-	check_err $?
-	ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
-	check_err $?
-	cleanup
-
-	if [ $ret -ne 0 ]; then
-                echo -e ${RED}"FAIL: $TYPE"${NC}
-                return 1
-        fi
-        echo -e ${GREEN}"PASS: $TYPE"${NC}
-}
-
-test_ip6geneve()
-{
-	TYPE=geneve
-	DEV_NS=ip6geneve00
-	DEV=ip6geneve11
-	ret=0
-
-	check $TYPE
-	config_device
-	add_ip6geneve_tunnel
-	attach_bpf $DEV ip6geneve_set_tunnel ip6geneve_get_tunnel
-	ping $PING_ARG 10.1.1.100
-	check_err $?
-	ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
-	check_err $?
-	cleanup
-
-	if [ $ret -ne 0 ]; then
-                echo -e ${RED}"FAIL: ip6$TYPE"${NC}
-                return 1
-        fi
-        echo -e ${GREEN}"PASS: ip6$TYPE"${NC}
-}
-
-test_ipip()
-{
-	TYPE=ipip
-	DEV_NS=ipip00
-	DEV=ipip11
-	ret=0
-
-	check $TYPE
-	config_device
-	add_ipip_tunnel
-	ip link set dev veth1 mtu 1500
-	attach_bpf $DEV ipip_set_tunnel ipip_get_tunnel
-	ping $PING_ARG 10.1.1.100
-	check_err $?
-	ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
-	check_err $?
-	cleanup
-
-	if [ $ret -ne 0 ]; then
-                echo -e ${RED}"FAIL: $TYPE"${NC}
-                return 1
-        fi
-        echo -e ${GREEN}"PASS: $TYPE"${NC}
-}
-
-test_ipip6()
-{
-	TYPE=ip6tnl
-	DEV_NS=ipip6tnl00
-	DEV=ipip6tnl11
-	ret=0
-
-	check $TYPE
-	config_device
-	add_ip6tnl_tunnel
-	ip link set dev veth1 mtu 1500
-	attach_bpf $DEV ipip6_set_tunnel ipip6_get_tunnel
-	# underlay
-	ping6 $PING_ARG ::11
-	# ip4 over ip6
-	ping $PING_ARG 10.1.1.100
-	check_err $?
-	ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
-	check_err $?
-	cleanup
-
-	if [ $ret -ne 0 ]; then
-                echo -e ${RED}"FAIL: $TYPE"${NC}
-                return 1
-        fi
-        echo -e ${GREEN}"PASS: $TYPE"${NC}
-}
-
-test_ip6ip6()
-{
-	TYPE=ip6tnl
-	DEV_NS=ip6ip6tnl00
-	DEV=ip6ip6tnl11
-	ret=0
-
-	check $TYPE
-	config_device
-	add_ip6tnl_tunnel
-	ip link set dev veth1 mtu 1500
-	attach_bpf $DEV ip6ip6_set_tunnel ip6ip6_get_tunnel
-	# underlay
-	ping6 $PING_ARG ::11
-	# ip6 over ip6
-	ping6 $PING_ARG 1::11
-	check_err $?
-	ip netns exec at_ns0 ping6 $PING_ARG 1::22
-	check_err $?
-	cleanup
-
-	if [ $ret -ne 0 ]; then
-                echo -e ${RED}"FAIL: ip6$TYPE"${NC}
-                return 1
-        fi
-        echo -e ${GREEN}"PASS: ip6$TYPE"${NC}
-}
-
-setup_xfrm_tunnel()
-{
-	auth=0x$(printf '1%.0s' {1..40})
-	enc=0x$(printf '2%.0s' {1..32})
-	spi_in_to_out=0x1
-	spi_out_to_in=0x2
-	# at_ns0 namespace
-	# at_ns0 -> root
-	ip netns exec at_ns0 \
-		ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \
-			spi $spi_in_to_out reqid 1 mode tunnel \
-			auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
-	ip netns exec at_ns0 \
-		ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir out \
-		tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \
-		mode tunnel
-	# root -> at_ns0
-	ip netns exec at_ns0 \
-		ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \
-			spi $spi_out_to_in reqid 2 mode tunnel \
-			auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
-	ip netns exec at_ns0 \
-		ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir in \
-		tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \
-		mode tunnel
-	# address & route
-	ip netns exec at_ns0 \
-		ip addr add dev veth0 10.1.1.100/32
-	ip netns exec at_ns0 \
-		ip route add 10.1.1.200 dev veth0 via 172.16.1.200 \
-			src 10.1.1.100
-
-	# root namespace
-	# at_ns0 -> root
-	ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \
-		spi $spi_in_to_out reqid 1 mode tunnel \
-		auth-trunc 'hmac(sha1)' $auth 96  enc 'cbc(aes)' $enc
-	ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir in \
-		tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \
-		mode tunnel
-	# root -> at_ns0
-	ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \
-		spi $spi_out_to_in reqid 2 mode tunnel \
-		auth-trunc 'hmac(sha1)' $auth 96  enc 'cbc(aes)' $enc
-	ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir out \
-		tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \
-		mode tunnel
-	# address & route
-	ip addr add dev veth1 10.1.1.200/32
-	ip route add 10.1.1.100 dev veth1 via 172.16.1.100 src 10.1.1.200
-}
-
-test_xfrm_tunnel()
-{
-	config_device
-	> /sys/kernel/debug/tracing/trace
-	setup_xfrm_tunnel
-	mkdir -p ${BPF_PIN_TUNNEL_DIR}
-	bpftool prog loadall ${BPF_FILE} ${BPF_PIN_TUNNEL_DIR}
-	tc qdisc add dev veth1 clsact
-	tc filter add dev veth1 proto ip ingress bpf da object-pinned \
-		${BPF_PIN_TUNNEL_DIR}/xfrm_get_state
-	ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
-	sleep 1
-	grep "reqid 1" /sys/kernel/debug/tracing/trace
-	check_err $?
-	grep "spi 0x1" /sys/kernel/debug/tracing/trace
-	check_err $?
-	grep "remote ip 0xac100164" /sys/kernel/debug/tracing/trace
-	check_err $?
-	cleanup
-
-	if [ $ret -ne 0 ]; then
-		echo -e ${RED}"FAIL: xfrm tunnel"${NC}
-		return 1
-	fi
-	echo -e ${GREEN}"PASS: xfrm tunnel"${NC}
-}
-
-attach_bpf()
-{
-	DEV=$1
-	SET=$2
-	GET=$3
-	mkdir -p ${BPF_PIN_TUNNEL_DIR}
-	bpftool prog loadall ${BPF_FILE} ${BPF_PIN_TUNNEL_DIR}/
-	tc qdisc add dev $DEV clsact
-	tc filter add dev $DEV egress bpf da object-pinned ${BPF_PIN_TUNNEL_DIR}/$SET
-	tc filter add dev $DEV ingress bpf da object-pinned ${BPF_PIN_TUNNEL_DIR}/$GET
-}
-
-cleanup()
-{
-        rm -rf ${BPF_PIN_TUNNEL_DIR}
-
-	ip netns delete at_ns0 2> /dev/null
-	ip link del veth1 2> /dev/null
-	ip link del ipip11 2> /dev/null
-	ip link del ipip6tnl11 2> /dev/null
-	ip link del ip6ip6tnl11 2> /dev/null
-	ip link del gretap11 2> /dev/null
-	ip link del ip6gre11 2> /dev/null
-	ip link del ip6gretap11 2> /dev/null
-	ip link del geneve11 2> /dev/null
-	ip link del ip6geneve11 2> /dev/null
-	ip link del erspan11 2> /dev/null
-	ip link del ip6erspan11 2> /dev/null
-	ip xfrm policy delete dir out src 10.1.1.200/32 dst 10.1.1.100/32 2> /dev/null
-	ip xfrm policy delete dir in src 10.1.1.100/32 dst 10.1.1.200/32 2> /dev/null
-	ip xfrm state delete src 172.16.1.100 dst 172.16.1.200 proto esp spi 0x1 2> /dev/null
-	ip xfrm state delete src 172.16.1.200 dst 172.16.1.100 proto esp spi 0x2 2> /dev/null
-}
-
-cleanup_exit()
-{
-	echo "CATCH SIGKILL or SIGINT, cleanup and exit"
-	cleanup
-	exit 0
-}
-
-check()
-{
-	ip link help 2>&1 | grep -q "\s$1\s"
-	if [ $? -ne 0 ];then
-		echo "SKIP $1: iproute2 not support"
-	cleanup
-	return 1
-	fi
-}
-
-enable_debug()
-{
-	echo 'file ip_gre.c +p' > /sys/kernel/debug/dynamic_debug/control
-	echo 'file ip6_gre.c +p' > /sys/kernel/debug/dynamic_debug/control
-	echo 'file geneve.c +p' > /sys/kernel/debug/dynamic_debug/control
-	echo 'file ipip.c +p' > /sys/kernel/debug/dynamic_debug/control
-}
-
-check_err()
-{
-	if [ $ret -eq 0 ]; then
-		ret=$1
-	fi
-}
-
-bpf_tunnel_test()
-{
-	local errors=0
-
-	echo "Testing GRE tunnel..."
-	test_gre
-	errors=$(( $errors + $? ))
-
-	echo "Testing IP6GRE tunnel..."
-	test_ip6gre
-	errors=$(( $errors + $? ))
-
-	echo "Testing IP6GRETAP tunnel..."
-	test_ip6gretap
-	errors=$(( $errors + $? ))
-
-	echo "Testing ERSPAN tunnel..."
-	test_erspan v2
-	errors=$(( $errors + $? ))
-
-	echo "Testing IP6ERSPAN tunnel..."
-	test_ip6erspan v2
-	errors=$(( $errors + $? ))
-
-	echo "Testing GENEVE tunnel..."
-	test_geneve
-	errors=$(( $errors + $? ))
-
-	echo "Testing IP6GENEVE tunnel..."
-	test_ip6geneve
-	errors=$(( $errors + $? ))
-
-	echo "Testing IPIP tunnel..."
-	test_ipip
-	errors=$(( $errors + $? ))
-
-	echo "Testing IPIP6 tunnel..."
-	test_ipip6
-	errors=$(( $errors + $? ))
-
-	echo "Testing IP6IP6 tunnel..."
-	test_ip6ip6
-	errors=$(( $errors + $? ))
-
-	echo "Testing IPSec tunnel..."
-	test_xfrm_tunnel
-	errors=$(( $errors + $? ))
-
-	return $errors
-}
-
-trap cleanup 0 3 6
-trap cleanup_exit 2 9
-
-cleanup
-bpf_tunnel_test
-
-if [ $? -ne 0 ]; then
-	echo -e "$(basename $0): ${RED}FAIL${NC}"
-	exit 1
-fi
-echo -e "$(basename $0): ${GREEN}PASS${NC}"
-exit 0
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 8c808551dfd7..27db34ecf3f5 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -33,22 +33,14 @@
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
 
-#ifdef HAVE_GENHDR
-# include "autoconf.h"
-#else
-# if defined(__i386) || defined(__x86_64) || defined(__s390x__) || defined(__aarch64__)
-#  define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS 1
-# endif
-#endif
+#include "autoconf_helper.h"
+#include "unpriv_helpers.h"
 #include "cap_helpers.h"
 #include "bpf_rand.h"
 #include "bpf_util.h"
 #include "test_btf.h"
 #include "../../../include/linux/filter.h"
-
-#ifndef ENOTSUPP
-#define ENOTSUPP 524
-#endif
+#include "testing_helpers.h"
 
 #define MAX_INSNS	BPF_MAXINSNS
 #define MAX_EXPECTED_INSNS	32
@@ -71,6 +63,7 @@
 
 #define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS	(1 << 0)
 #define F_LOAD_WITH_STRICT_ALIGNMENT		(1 << 1)
+#define F_NEEDS_JIT_ENABLED			(1 << 2)
 
 /* need CAP_BPF, CAP_NET_ADMIN, CAP_PERFMON to load progs */
 #define ADMIN_CAPS (1ULL << CAP_NET_ADMIN |	\
@@ -78,6 +71,7 @@
 		    1ULL << CAP_BPF)
 #define UNPRIV_SYSCTL "kernel/unprivileged_bpf_disabled"
 static bool unpriv_disabled = false;
+static bool jit_disabled;
 static int skips;
 static bool verbose = false;
 static int verif_log_level = 0;
@@ -209,7 +203,7 @@ loop:
 		insn[i++] = BPF_MOV64_IMM(BPF_REG_2, 1);
 		insn[i++] = BPF_MOV64_IMM(BPF_REG_3, 2);
 		insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-					 BPF_FUNC_skb_vlan_push),
+					 BPF_FUNC_skb_vlan_push);
 		insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 3);
 		i++;
 	}
@@ -220,7 +214,7 @@ loop:
 		i++;
 		insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6);
 		insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-					 BPF_FUNC_skb_vlan_pop),
+					 BPF_FUNC_skb_vlan_pop);
 		insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 3);
 		i++;
 	}
@@ -699,13 +693,13 @@ static int create_cgroup_storage(bool percpu)
  *   struct bpf_timer t;
  * };
  * struct btf_ptr {
+ *   struct prog_test_ref_kfunc __kptr_untrusted *ptr;
  *   struct prog_test_ref_kfunc __kptr *ptr;
- *   struct prog_test_ref_kfunc __kptr_ref *ptr;
- *   struct prog_test_member __kptr_ref *ptr;
+ *   struct prog_test_member __kptr *ptr;
  * }
  */
 static const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l\0bpf_timer\0timer\0t"
-				  "\0btf_ptr\0prog_test_ref_kfunc\0ptr\0kptr\0kptr_ref"
+				  "\0btf_ptr\0prog_test_ref_kfunc\0ptr\0kptr\0kptr_untrusted"
 				  "\0prog_test_member";
 static __u32 btf_raw_types[] = {
 	/* int */
@@ -724,23 +718,23 @@ static __u32 btf_raw_types[] = {
 	BTF_MEMBER_ENC(41, 4, 0), /* struct bpf_timer t; */
 	/* struct prog_test_ref_kfunc */		/* [6] */
 	BTF_STRUCT_ENC(51, 0, 0),
-	BTF_STRUCT_ENC(89, 0, 0),			/* [7] */
+	BTF_STRUCT_ENC(95, 0, 0),			/* [7] */
+	/* type tag "kptr_untrusted" */
+	BTF_TYPE_TAG_ENC(80, 6),			/* [8] */
 	/* type tag "kptr" */
-	BTF_TYPE_TAG_ENC(75, 6),			/* [8] */
-	/* type tag "kptr_ref" */
-	BTF_TYPE_TAG_ENC(80, 6),			/* [9] */
-	BTF_TYPE_TAG_ENC(80, 7),			/* [10] */
+	BTF_TYPE_TAG_ENC(75, 6),			/* [9] */
+	BTF_TYPE_TAG_ENC(75, 7),			/* [10] */
 	BTF_PTR_ENC(8),					/* [11] */
 	BTF_PTR_ENC(9),					/* [12] */
 	BTF_PTR_ENC(10),				/* [13] */
 	/* struct btf_ptr */				/* [14] */
 	BTF_STRUCT_ENC(43, 3, 24),
-	BTF_MEMBER_ENC(71, 11, 0), /* struct prog_test_ref_kfunc __kptr *ptr; */
-	BTF_MEMBER_ENC(71, 12, 64), /* struct prog_test_ref_kfunc __kptr_ref *ptr; */
-	BTF_MEMBER_ENC(71, 13, 128), /* struct prog_test_member __kptr_ref *ptr; */
+	BTF_MEMBER_ENC(71, 11, 0), /* struct prog_test_ref_kfunc __kptr_untrusted *ptr; */
+	BTF_MEMBER_ENC(71, 12, 64), /* struct prog_test_ref_kfunc __kptr *ptr; */
+	BTF_MEMBER_ENC(71, 13, 128), /* struct prog_test_member __kptr *ptr; */
 };
 
-static char bpf_vlog[UINT_MAX >> 8];
+static char bpf_vlog[UINT_MAX >> 5];
 
 static int load_btf_spec(__u32 *types, int types_len,
 			 const char *strings, int strings_len)
@@ -878,8 +872,140 @@ static int create_map_kptr(void)
 	return fd;
 }
 
+static void set_root(bool set)
+{
+	__u64 caps;
+
+	if (set) {
+		if (cap_enable_effective(1ULL << CAP_SYS_ADMIN, &caps))
+			perror("cap_disable_effective(CAP_SYS_ADMIN)");
+	} else {
+		if (cap_disable_effective(1ULL << CAP_SYS_ADMIN, &caps))
+			perror("cap_disable_effective(CAP_SYS_ADMIN)");
+	}
+}
+
+static __u64 ptr_to_u64(const void *ptr)
+{
+	return (uintptr_t) ptr;
+}
+
+static struct btf *btf__load_testmod_btf(struct btf *vmlinux)
+{
+	struct bpf_btf_info info;
+	__u32 len = sizeof(info);
+	struct btf *btf = NULL;
+	char name[64];
+	__u32 id = 0;
+	int err, fd;
+
+	/* Iterate all loaded BTF objects and find bpf_testmod,
+	 * we need SYS_ADMIN cap for that.
+	 */
+	set_root(true);
+
+	while (true) {
+		err = bpf_btf_get_next_id(id, &id);
+		if (err) {
+			if (errno == ENOENT)
+				break;
+			perror("bpf_btf_get_next_id failed");
+			break;
+		}
+
+		fd = bpf_btf_get_fd_by_id(id);
+		if (fd < 0) {
+			if (errno == ENOENT)
+				continue;
+			perror("bpf_btf_get_fd_by_id failed");
+			break;
+		}
+
+		memset(&info, 0, sizeof(info));
+		info.name_len = sizeof(name);
+		info.name = ptr_to_u64(name);
+		len = sizeof(info);
+
+		err = bpf_obj_get_info_by_fd(fd, &info, &len);
+		if (err) {
+			close(fd);
+			perror("bpf_obj_get_info_by_fd failed");
+			break;
+		}
+
+		if (strcmp("bpf_testmod", name)) {
+			close(fd);
+			continue;
+		}
+
+		btf = btf__load_from_kernel_by_id_split(id, vmlinux);
+		if (!btf) {
+			close(fd);
+			break;
+		}
+
+		/* We need the fd to stay open so it can be used in fd_array.
+		 * The final cleanup call to btf__free will free btf object
+		 * and close the file descriptor.
+		 */
+		btf__set_fd(btf, fd);
+		break;
+	}
+
+	set_root(false);
+	return btf;
+}
+
+static struct btf *testmod_btf;
+static struct btf *vmlinux_btf;
+
+static void kfuncs_cleanup(void)
+{
+	btf__free(testmod_btf);
+	btf__free(vmlinux_btf);
+}
+
+static void fixup_prog_kfuncs(struct bpf_insn *prog, int *fd_array,
+			      struct kfunc_btf_id_pair *fixup_kfunc_btf_id)
+{
+	/* Patch in kfunc BTF IDs */
+	while (fixup_kfunc_btf_id->kfunc) {
+		int btf_id = 0;
+
+		/* try to find kfunc in kernel BTF */
+		vmlinux_btf = vmlinux_btf ?: btf__load_vmlinux_btf();
+		if (vmlinux_btf) {
+			btf_id = btf__find_by_name_kind(vmlinux_btf,
+							fixup_kfunc_btf_id->kfunc,
+							BTF_KIND_FUNC);
+			btf_id = btf_id < 0 ? 0 : btf_id;
+		}
+
+		/* kfunc not found in kernel BTF, try bpf_testmod BTF */
+		if (!btf_id) {
+			testmod_btf = testmod_btf ?: btf__load_testmod_btf(vmlinux_btf);
+			if (testmod_btf) {
+				btf_id = btf__find_by_name_kind(testmod_btf,
+								fixup_kfunc_btf_id->kfunc,
+								BTF_KIND_FUNC);
+				btf_id = btf_id < 0 ? 0 : btf_id;
+				if (btf_id) {
+					/* We put bpf_testmod module fd into fd_array
+					 * and its index 1 into instruction 'off'.
+					 */
+					*fd_array = btf__fd(testmod_btf);
+					prog[fixup_kfunc_btf_id->insn_idx].off = 1;
+				}
+			}
+		}
+
+		prog[fixup_kfunc_btf_id->insn_idx].imm = btf_id;
+		fixup_kfunc_btf_id++;
+	}
+}
+
 static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
-			  struct bpf_insn *prog, int *map_fds)
+			  struct bpf_insn *prog, int *map_fds, int *fd_array)
 {
 	int *fixup_map_hash_8b = test->fixup_map_hash_8b;
 	int *fixup_map_hash_48b = test->fixup_map_hash_48b;
@@ -904,7 +1030,6 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
 	int *fixup_map_ringbuf = test->fixup_map_ringbuf;
 	int *fixup_map_timer = test->fixup_map_timer;
 	int *fixup_map_kptr = test->fixup_map_kptr;
-	struct kfunc_btf_id_pair *fixup_kfunc_btf_id = test->fixup_kfunc_btf_id;
 
 	if (test->fill_helper) {
 		test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn));
@@ -1084,7 +1209,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
 	}
 	if (*fixup_map_ringbuf) {
 		map_fds[20] = create_map(BPF_MAP_TYPE_RINGBUF, 0,
-					   0, 4096);
+					 0, getpagesize());
 		do {
 			prog[*fixup_map_ringbuf].imm = map_fds[20];
 			fixup_map_ringbuf++;
@@ -1105,32 +1230,9 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
 		} while (*fixup_map_kptr);
 	}
 
-	/* Patch in kfunc BTF IDs */
-	if (fixup_kfunc_btf_id->kfunc) {
-		struct btf *btf;
-		int btf_id;
-
-		do {
-			btf_id = 0;
-			btf = btf__load_vmlinux_btf();
-			if (btf) {
-				btf_id = btf__find_by_name_kind(btf,
-								fixup_kfunc_btf_id->kfunc,
-								BTF_KIND_FUNC);
-				btf_id = btf_id < 0 ? 0 : btf_id;
-			}
-			btf__free(btf);
-			prog[fixup_kfunc_btf_id->insn_idx].imm = btf_id;
-			fixup_kfunc_btf_id++;
-		} while (fixup_kfunc_btf_id->kfunc);
-	}
+	fixup_prog_kfuncs(prog, fd_array, test->fixup_kfunc_btf_id);
 }
 
-struct libcap {
-	struct __user_cap_header_struct hdr;
-	struct __user_cap_data_struct data[2];
-};
-
 static int set_admin(bool admin)
 {
 	int err;
@@ -1232,47 +1334,6 @@ static bool cmp_str_seq(const char *log, const char *exp)
 	return true;
 }
 
-static int get_xlated_program(int fd_prog, struct bpf_insn **buf, int *cnt)
-{
-	struct bpf_prog_info info = {};
-	__u32 info_len = sizeof(info);
-	__u32 xlated_prog_len;
-	__u32 buf_element_size = sizeof(struct bpf_insn);
-
-	if (bpf_obj_get_info_by_fd(fd_prog, &info, &info_len)) {
-		perror("bpf_obj_get_info_by_fd failed");
-		return -1;
-	}
-
-	xlated_prog_len = info.xlated_prog_len;
-	if (xlated_prog_len % buf_element_size) {
-		printf("Program length %d is not multiple of %d\n",
-		       xlated_prog_len, buf_element_size);
-		return -1;
-	}
-
-	*cnt = xlated_prog_len / buf_element_size;
-	*buf = calloc(*cnt, buf_element_size);
-	if (!buf) {
-		perror("can't allocate xlated program buffer");
-		return -ENOMEM;
-	}
-
-	bzero(&info, sizeof(info));
-	info.xlated_prog_len = xlated_prog_len;
-	info.xlated_prog_insns = (__u64)(unsigned long)*buf;
-	if (bpf_obj_get_info_by_fd(fd_prog, &info, &info_len)) {
-		perror("second bpf_obj_get_info_by_fd failed");
-		goto out_free_buf;
-	}
-
-	return 0;
-
-out_free_buf:
-	free(*buf);
-	return -1;
-}
-
 static bool is_null_insn(struct bpf_insn *insn)
 {
 	struct bpf_insn null_insn = {};
@@ -1395,7 +1456,7 @@ static void print_insn(struct bpf_insn *buf, int cnt)
 static bool check_xlated_program(struct bpf_test *test, int fd_prog)
 {
 	struct bpf_insn *buf;
-	int cnt;
+	unsigned int cnt;
 	bool result = true;
 	bool check_expected = !is_null_insn(test->expected_insns);
 	bool check_unexpected = !is_null_insn(test->unexpected_insns);
@@ -1450,11 +1511,19 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	int run_errs, run_successes;
 	int map_fds[MAX_NR_MAPS];
 	const char *expected_err;
+	int fd_array[2] = { -1, -1 };
 	int saved_errno;
 	int fixup_skips;
 	__u32 pflags;
 	int i, err;
 
+	if ((test->flags & F_NEEDS_JIT_ENABLED) && jit_disabled) {
+		printf("SKIP (requires BPF JIT)\n");
+		skips++;
+		sched_yield();
+		return;
+	}
+
 	fd_prog = -1;
 	for (i = 0; i < MAX_NR_MAPS; i++)
 		map_fds[i] = -1;
@@ -1463,7 +1532,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	if (!prog_type)
 		prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
 	fixup_skips = skips;
-	do_test_fixup(test, prog_type, prog, map_fds);
+	do_test_fixup(test, prog_type, prog, map_fds, &fd_array[1]);
 	if (test->fill_insns) {
 		prog = test->fill_insns;
 		prog_len = test->prog_len;
@@ -1476,7 +1545,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	if (fixup_skips != skips)
 		return;
 
-	pflags = BPF_F_TEST_RND_HI32;
+	pflags = testing_prog_flags();
 	if (test->flags & F_LOAD_WITH_STRICT_ALIGNMENT)
 		pflags |= BPF_F_STRICT_ALIGNMENT;
 	if (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS)
@@ -1490,13 +1559,15 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		       test->errstr_unpriv : test->errstr;
 
 	opts.expected_attach_type = test->expected_attach_type;
-	if (verbose)
-		opts.log_level = verif_log_level | 4; /* force stats */
-	else if (expected_ret == VERBOSE_ACCEPT)
+	if (expected_ret == VERBOSE_ACCEPT)
 		opts.log_level = 2;
+	else if (verbose)
+		opts.log_level = verif_log_level | 4; /* force stats */
 	else
 		opts.log_level = DEFAULT_LIBBPF_LOG_LEVEL;
 	opts.prog_flags = pflags;
+	if (fd_array[1] != -1)
+		opts.fd_array = &fd_array[0];
 
 	if ((prog_type == BPF_PROG_TYPE_TRACING ||
 	     prog_type == BPF_PROG_TYPE_LSM) && test->kfunc) {
@@ -1665,22 +1736,6 @@ static bool is_admin(void)
 	return (caps & ADMIN_CAPS) == ADMIN_CAPS;
 }
 
-static void get_unpriv_disabled()
-{
-	char buf[2];
-	FILE *fd;
-
-	fd = fopen("/proc/sys/"UNPRIV_SYSCTL, "r");
-	if (!fd) {
-		perror("fopen /proc/sys/"UNPRIV_SYSCTL);
-		unpriv_disabled = true;
-		return;
-	}
-	if (fgets(buf, 2, fd) == buf && atoi(buf))
-		unpriv_disabled = true;
-	fclose(fd);
-}
-
 static bool test_as_unpriv(struct bpf_test *test)
 {
 #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
@@ -1705,6 +1760,12 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to)
 {
 	int i, passes = 0, errors = 0;
 
+	/* ensure previous instance of the module is unloaded */
+	unload_bpf_testmod(verbose);
+
+	if (load_bpf_testmod(verbose))
+		return EXIT_FAILURE;
+
 	for (i = from; i < to; i++) {
 		struct bpf_test *test = &tests[i];
 
@@ -1732,6 +1793,9 @@ static int do_test(bool unpriv, unsigned int from, unsigned int to)
 		}
 	}
 
+	unload_bpf_testmod(verbose);
+	kfuncs_cleanup();
+
 	printf("Summary: %d PASSED, %d SKIPPED, %d FAILED\n", passes,
 	       skips, errors);
 	return errors ? EXIT_FAILURE : EXIT_SUCCESS;
@@ -1773,13 +1837,15 @@ int main(int argc, char **argv)
 		}
 	}
 
-	get_unpriv_disabled();
+	unpriv_disabled = get_unpriv_disabled();
 	if (unpriv && unpriv_disabled) {
 		printf("Cannot run as unprivileged user with sysctl %s.\n",
 		       UNPRIV_SYSCTL);
 		return EXIT_FAILURE;
 	}
 
+	jit_disabled = !is_jit_enabled();
+
 	/* Use libbpf 1.0 API mode */
 	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
 
diff --git a/tools/testing/selftests/bpf/test_verifier_log.c b/tools/testing/selftests/bpf/test_verifier_log.c
deleted file mode 100644
index 70feda97cee5..000000000000
--- a/tools/testing/selftests/bpf/test_verifier_log.c
+++ /dev/null
@@ -1,175 +0,0 @@
-#include <errno.h>
-#include <stdlib.h>
-#include <stdio.h>
-#include <string.h>
-#include <unistd.h>
-#include <sys/time.h>
-
-#include <linux/bpf.h>
-#include <linux/filter.h>
-#include <linux/unistd.h>
-
-#include <bpf/bpf.h>
-
-#define LOG_SIZE (1 << 20)
-
-#define err(str...)	printf("ERROR: " str)
-
-static const struct bpf_insn code_sample[] = {
-	/* We need a few instructions to pass the min log length */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-		     BPF_FUNC_map_lookup_elem),
-	BPF_EXIT_INSN(),
-};
-
-static inline __u64 ptr_to_u64(const void *ptr)
-{
-	return (__u64) (unsigned long) ptr;
-}
-
-static int load(char *log, size_t log_len, int log_level)
-{
-	union bpf_attr attr;
-
-	bzero(&attr, sizeof(attr));
-	attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
-	attr.insn_cnt = (__u32)(sizeof(code_sample) / sizeof(struct bpf_insn));
-	attr.insns = ptr_to_u64(code_sample);
-	attr.license = ptr_to_u64("GPL");
-	attr.log_buf = ptr_to_u64(log);
-	attr.log_size = log_len;
-	attr.log_level = log_level;
-
-	return syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
-}
-
-static void check_ret(int ret, int exp_errno)
-{
-	if (ret > 0) {
-		close(ret);
-		err("broken sample loaded successfully!?\n");
-		exit(1);
-	}
-
-	if (!ret || errno != exp_errno) {
-		err("Program load returned: ret:%d/errno:%d, expected ret:%d/errno:%d\n",
-		    ret, errno, -1, exp_errno);
-		exit(1);
-	}
-}
-
-static void check_ones(const char *buf, size_t len, const char *msg)
-{
-	while (len--)
-		if (buf[len] != 1) {
-			err("%s", msg);
-			exit(1);
-		}
-}
-
-static void test_log_good(char *log, size_t buf_len, size_t log_len,
-			  size_t exp_len, int exp_errno, const char *full_log)
-{
-	size_t len;
-	int ret;
-
-	memset(log, 1, buf_len);
-
-	ret = load(log, log_len, 1);
-	check_ret(ret, exp_errno);
-
-	len = strnlen(log, buf_len);
-	if (len == buf_len) {
-		err("verifier did not NULL terminate the log\n");
-		exit(1);
-	}
-	if (exp_len && len != exp_len) {
-		err("incorrect log length expected:%zd have:%zd\n",
-		    exp_len, len);
-		exit(1);
-	}
-
-	if (strchr(log, 1)) {
-		err("verifier leaked a byte through\n");
-		exit(1);
-	}
-
-	check_ones(log + len + 1, buf_len - len - 1,
-		   "verifier wrote bytes past NULL termination\n");
-
-	if (memcmp(full_log, log, LOG_SIZE)) {
-		err("log did not match expected output\n");
-		exit(1);
-	}
-}
-
-static void test_log_bad(char *log, size_t log_len, int log_level)
-{
-	int ret;
-
-	ret = load(log, log_len, log_level);
-	check_ret(ret, EINVAL);
-	if (log)
-		check_ones(log, LOG_SIZE,
-			   "verifier touched log with bad parameters\n");
-}
-
-int main(int argc, char **argv)
-{
-	char full_log[LOG_SIZE];
-	char log[LOG_SIZE];
-	size_t want_len;
-	int i;
-
-	memset(log, 1, LOG_SIZE);
-
-	/* Use libbpf 1.0 API mode */
-	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
-
-	/* Test incorrect attr */
-	printf("Test log_level 0...\n");
-	test_log_bad(log, LOG_SIZE, 0);
-
-	printf("Test log_size < 128...\n");
-	test_log_bad(log, 15, 1);
-
-	printf("Test log_buff = NULL...\n");
-	test_log_bad(NULL, LOG_SIZE, 1);
-
-	/* Test with log big enough */
-	printf("Test oversized buffer...\n");
-	test_log_good(full_log, LOG_SIZE, LOG_SIZE, 0, EACCES, full_log);
-
-	want_len = strlen(full_log);
-
-	printf("Test exact buffer...\n");
-	test_log_good(log, LOG_SIZE, want_len + 2, want_len, EACCES, full_log);
-
-	printf("Test undersized buffers...\n");
-	for (i = 0; i < 64; i++) {
-		full_log[want_len - i + 1] = 1;
-		full_log[want_len - i] = 0;
-
-		test_log_good(log, LOG_SIZE, want_len + 1 - i, want_len - i,
-			      ENOSPC, full_log);
-	}
-
-	printf("test_verifier_log: OK\n");
-	return 0;
-}
diff --git a/tools/testing/selftests/bpf/test_xdp_features.sh b/tools/testing/selftests/bpf/test_xdp_features.sh
new file mode 100755
index 000000000000..0aa71c4455c0
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_features.sh
@@ -0,0 +1,107 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+readonly NS="ns1-$(mktemp -u XXXXXX)"
+readonly V0_IP4=10.10.0.11
+readonly V1_IP4=10.10.0.1
+readonly V0_IP6=2001:db8::11
+readonly V1_IP6=2001:db8::1
+
+ret=1
+
+setup() {
+	{
+		ip netns add ${NS}
+
+		ip link add v1 type veth peer name v0 netns ${NS}
+
+		ip link set v1 up
+		ip addr add $V1_IP4/24 dev v1
+		ip addr add $V1_IP6/64 nodad dev v1
+		ip -n ${NS} link set dev v0 up
+		ip -n ${NS} addr add $V0_IP4/24 dev v0
+		ip -n ${NS} addr add $V0_IP6/64 nodad dev v0
+
+		# Enable XDP mode and disable checksum offload
+		ethtool -K v1 gro on
+		ethtool -K v1 tx-checksumming off
+		ip netns exec ${NS} ethtool -K v0 gro on
+		ip netns exec ${NS} ethtool -K v0 tx-checksumming off
+	} > /dev/null 2>&1
+}
+
+cleanup() {
+	ip link del v1 2> /dev/null
+	ip netns del ${NS} 2> /dev/null
+	[ "$(pidof xdp_features)" = "" ] || kill $(pidof xdp_features) 2> /dev/null
+}
+
+wait_for_dut_server() {
+	while sleep 1; do
+		ss -tlp | grep -q xdp_features
+		[ $? -eq 0 ] && break
+	done
+}
+
+test_xdp_features() {
+	setup
+
+	## XDP_PASS
+	./xdp_features -f XDP_PASS -D $V1_IP6 -T $V0_IP6 v1 &
+	wait_for_dut_server
+	ip netns exec ${NS} ./xdp_features -t -f XDP_PASS \
+					   -D $V1_IP6 -C $V1_IP6 \
+					   -T $V0_IP6 v0
+	[ $? -ne 0 ] && exit
+
+	## XDP_DROP
+	./xdp_features -f XDP_DROP -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1 &
+	wait_for_dut_server
+	ip netns exec ${NS} ./xdp_features -t -f XDP_DROP \
+					   -D ::ffff:$V1_IP4 \
+					   -C ::ffff:$V1_IP4 \
+					   -T ::ffff:$V0_IP4 v0
+	[ $? -ne 0 ] && exit
+
+	## XDP_ABORTED
+	./xdp_features -f XDP_ABORTED -D $V1_IP6 -T $V0_IP6 v1 &
+	wait_for_dut_server
+	ip netns exec ${NS} ./xdp_features -t -f XDP_ABORTED \
+					   -D $V1_IP6 -C $V1_IP6 \
+					   -T $V0_IP6 v0
+	[ $? -ne 0 ] && exit
+
+	## XDP_TX
+	./xdp_features -f XDP_TX -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1 &
+	wait_for_dut_server
+	ip netns exec ${NS} ./xdp_features -t -f XDP_TX \
+					   -D ::ffff:$V1_IP4 \
+					   -C ::ffff:$V1_IP4 \
+					   -T ::ffff:$V0_IP4 v0
+	[ $? -ne 0 ] && exit
+
+	## XDP_REDIRECT
+	./xdp_features -f XDP_REDIRECT -D $V1_IP6 -T $V0_IP6 v1 &
+	wait_for_dut_server
+	ip netns exec ${NS} ./xdp_features -t -f XDP_REDIRECT \
+					   -D $V1_IP6 -C $V1_IP6 \
+					   -T $V0_IP6 v0
+	[ $? -ne 0 ] && exit
+
+	## XDP_NDO_XMIT
+	./xdp_features -f XDP_NDO_XMIT -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1 &
+	wait_for_dut_server
+	ip netns exec ${NS} ./xdp_features -t -f XDP_NDO_XMIT \
+					   -D ::ffff:$V1_IP4 \
+					   -C ::ffff:$V1_IP4 \
+					   -T ::ffff:$V0_IP4 v0
+	ret=$?
+	cleanup
+}
+
+set -e
+trap cleanup 2 3 6 9
+
+test_xdp_features
+
+exit $ret
diff --git a/tools/testing/selftests/bpf/test_xdp_meta.sh b/tools/testing/selftests/bpf/test_xdp_meta.sh
deleted file mode 100755
index 2740322c1878..000000000000
--- a/tools/testing/selftests/bpf/test_xdp_meta.sh
+++ /dev/null
@@ -1,58 +0,0 @@
-#!/bin/sh
-
-BPF_FILE="test_xdp_meta.bpf.o"
-# Kselftest framework requirement - SKIP code is 4.
-readonly KSFT_SKIP=4
-readonly NS1="ns1-$(mktemp -u XXXXXX)"
-readonly NS2="ns2-$(mktemp -u XXXXXX)"
-
-cleanup()
-{
-	if [ "$?" = "0" ]; then
-		echo "selftests: test_xdp_meta [PASS]";
-	else
-		echo "selftests: test_xdp_meta [FAILED]";
-	fi
-
-	set +e
-	ip link del veth1 2> /dev/null
-	ip netns del ${NS1} 2> /dev/null
-	ip netns del ${NS2} 2> /dev/null
-}
-
-ip link set dev lo xdp off 2>/dev/null > /dev/null
-if [ $? -ne 0 ];then
-	echo "selftests: [SKIP] Could not run test without the ip xdp support"
-	exit $KSFT_SKIP
-fi
-set -e
-
-ip netns add ${NS1}
-ip netns add ${NS2}
-
-trap cleanup 0 2 3 6 9
-
-ip link add veth1 type veth peer name veth2
-
-ip link set veth1 netns ${NS1}
-ip link set veth2 netns ${NS2}
-
-ip netns exec ${NS1} ip addr add 10.1.1.11/24 dev veth1
-ip netns exec ${NS2} ip addr add 10.1.1.22/24 dev veth2
-
-ip netns exec ${NS1} tc qdisc add dev veth1 clsact
-ip netns exec ${NS2} tc qdisc add dev veth2 clsact
-
-ip netns exec ${NS1} tc filter add dev veth1 ingress bpf da obj ${BPF_FILE} sec t
-ip netns exec ${NS2} tc filter add dev veth2 ingress bpf da obj ${BPF_FILE} sec t
-
-ip netns exec ${NS1} ip link set dev veth1 xdp obj ${BPF_FILE} sec x
-ip netns exec ${NS2} ip link set dev veth2 xdp obj ${BPF_FILE} sec x
-
-ip netns exec ${NS1} ip link set dev veth1 up
-ip netns exec ${NS2} ip link set dev veth2 up
-
-ip netns exec ${NS1} ping -c 1 10.1.1.22
-ip netns exec ${NS2} ping -c 1 10.1.1.11
-
-exit 0
diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.sh b/tools/testing/selftests/bpf/test_xdp_redirect.sh
deleted file mode 100755
index 0746a4fde9d3..000000000000
--- a/tools/testing/selftests/bpf/test_xdp_redirect.sh
+++ /dev/null
@@ -1,79 +0,0 @@
-#!/bin/bash
-# Create 2 namespaces with two veth peers, and
-# forward packets in-between using generic XDP
-#
-# NS1(veth11)     NS2(veth22)
-#     |               |
-#     |               |
-#   (veth1, ------ (veth2,
-#   id:111)         id:222)
-#     | xdp forwarding |
-#     ------------------
-
-readonly NS1="ns1-$(mktemp -u XXXXXX)"
-readonly NS2="ns2-$(mktemp -u XXXXXX)"
-ret=0
-
-setup()
-{
-
-	local xdpmode=$1
-
-	ip netns add ${NS1}
-	ip netns add ${NS2}
-
-	ip link add veth1 index 111 type veth peer name veth11 netns ${NS1}
-	ip link add veth2 index 222 type veth peer name veth22 netns ${NS2}
-
-	ip link set veth1 up
-	ip link set veth2 up
-	ip -n ${NS1} link set dev veth11 up
-	ip -n ${NS2} link set dev veth22 up
-
-	ip -n ${NS1} addr add 10.1.1.11/24 dev veth11
-	ip -n ${NS2} addr add 10.1.1.22/24 dev veth22
-}
-
-cleanup()
-{
-	ip link del veth1 2> /dev/null
-	ip link del veth2 2> /dev/null
-	ip netns del ${NS1} 2> /dev/null
-	ip netns del ${NS2} 2> /dev/null
-}
-
-test_xdp_redirect()
-{
-	local xdpmode=$1
-
-	setup
-
-	ip link set dev veth1 $xdpmode off &> /dev/null
-	if [ $? -ne 0 ];then
-		echo "selftests: test_xdp_redirect $xdpmode [SKIP]"
-		return 0
-	fi
-
-	ip -n ${NS1} link set veth11 $xdpmode obj xdp_dummy.bpf.o sec xdp &> /dev/null
-	ip -n ${NS2} link set veth22 $xdpmode obj xdp_dummy.bpf.o sec xdp &> /dev/null
-	ip link set dev veth1 $xdpmode obj test_xdp_redirect.bpf.o sec redirect_to_222 &> /dev/null
-	ip link set dev veth2 $xdpmode obj test_xdp_redirect.bpf.o sec redirect_to_111 &> /dev/null
-
-	if ip netns exec ${NS1} ping -c 1 10.1.1.22 &> /dev/null &&
-	   ip netns exec ${NS2} ping -c 1 10.1.1.11 &> /dev/null; then
-		echo "selftests: test_xdp_redirect $xdpmode [PASS]";
-	else
-		ret=1
-		echo "selftests: test_xdp_redirect $xdpmode [FAILED]";
-	fi
-
-	cleanup
-}
-
-set -e
-trap cleanup 2 3 6 9
-
-test_xdp_redirect xdpgeneric
-test_xdp_redirect xdpdrv
-
-exit $ret
diff --git a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh
deleted file mode 100755
index 4c3c3fdd2d73..000000000000
--- a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh
+++ /dev/null
@@ -1,214 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-#
-# Test topology:
-#    - - - - - - - - - - - - - - - - - - -
-#    | veth1         veth2         veth3 |  ns0
-#     - -| - - - - - - | - - - - - - | - -
-#    ---------     ---------     ---------
-#    | veth0 |     | veth0 |     | veth0 |
-#    ---------     ---------     ---------
-#       ns1           ns2           ns3
-#
-# Test modules:
-# XDP modes: generic, native, native + egress_prog
-#
-# Test cases:
-#   ARP: Testing BPF_F_BROADCAST, the ingress interface also should receive
-#   the redirects.
-#      ns1 -> gw: ns1, ns2, ns3, should receive the arp request
-#   IPv4: Testing BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, the ingress
-#   interface should not receive the redirects.
-#      ns1 -> gw: ns1 should not receive, ns2, ns3 should receive redirects.
-#   IPv6: Testing none flag, all the pkts should be redirected back
-#      ping test: ns1 -> ns2 (block), echo requests will be redirect back
-#   egress_prog:
-#      all src mac should be egress interface's mac
-
-# netns numbers
-NUM=3
-IFACES=""
-DRV_MODE="xdpgeneric xdpdrv xdpegress"
-PASS=0
-FAIL=0
-LOG_DIR=$(mktemp -d)
-declare -a NS
-NS[0]="ns0-$(mktemp -u XXXXXX)"
-NS[1]="ns1-$(mktemp -u XXXXXX)"
-NS[2]="ns2-$(mktemp -u XXXXXX)"
-NS[3]="ns3-$(mktemp -u XXXXXX)"
-
-test_pass()
-{
-	echo "Pass: $@"
-	PASS=$((PASS + 1))
-}
-
-test_fail()
-{
-	echo "fail: $@"
-	FAIL=$((FAIL + 1))
-}
-
-clean_up()
-{
-	for i in $(seq 0 $NUM); do
-		ip netns del ${NS[$i]} 2> /dev/null
-	done
-}
-
-# Kselftest framework requirement - SKIP code is 4.
-check_env()
-{
-	ip link set dev lo xdpgeneric off &>/dev/null
-	if [ $? -ne 0 ];then
-		echo "selftests: [SKIP] Could not run test without the ip xdpgeneric support"
-		exit 4
-	fi
-
-	which tcpdump &>/dev/null
-	if [ $? -ne 0 ];then
-		echo "selftests: [SKIP] Could not run test without tcpdump"
-		exit 4
-	fi
-}
-
-setup_ns()
-{
-	local mode=$1
-	IFACES=""
-
-	if [ "$mode" = "xdpegress" ]; then
-		mode="xdpdrv"
-	fi
-
-	ip netns add ${NS[0]}
-	for i in $(seq $NUM); do
-	        ip netns add ${NS[$i]}
-		ip -n ${NS[$i]} link add veth0 type veth peer name veth$i netns ${NS[0]}
-		ip -n ${NS[$i]} link set veth0 up
-		ip -n ${NS[0]} link set veth$i up
-
-		ip -n ${NS[$i]} addr add 192.0.2.$i/24 dev veth0
-		ip -n ${NS[$i]} addr add 2001:db8::$i/64 dev veth0
-		# Add a neigh entry for IPv4 ping test
-		ip -n ${NS[$i]} neigh add 192.0.2.253 lladdr 00:00:00:00:00:01 dev veth0
-		ip -n ${NS[$i]} link set veth0 $mode obj \
-			xdp_dummy.bpf.o sec xdp &> /dev/null || \
-			{ test_fail "Unable to load dummy xdp" && exit 1; }
-		IFACES="$IFACES veth$i"
-		veth_mac[$i]=$(ip -n ${NS[0]} link show veth$i | awk '/link\/ether/ {print $2}')
-	done
-}
-
-do_egress_tests()
-{
-	local mode=$1
-
-	# mac test
-	ip netns exec ${NS[2]} tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-2_${mode}.log &
-	ip netns exec ${NS[3]} tcpdump -e -i veth0 -nn -l -e &> ${LOG_DIR}/mac_ns1-3_${mode}.log &
-	sleep 0.5
-	ip netns exec ${NS[1]} ping 192.0.2.254 -i 0.1 -c 4 &> /dev/null
-	sleep 0.5
-	pkill tcpdump
-
-	# mac check
-	grep -q "${veth_mac[2]} > ff:ff:ff:ff:ff:ff" ${LOG_DIR}/mac_ns1-2_${mode}.log && \
-	       test_pass "$mode mac ns1-2" || test_fail "$mode mac ns1-2"
-	grep -q "${veth_mac[3]} > ff:ff:ff:ff:ff:ff" ${LOG_DIR}/mac_ns1-3_${mode}.log && \
-		test_pass "$mode mac ns1-3" || test_fail "$mode mac ns1-3"
-}
-
-do_ping_tests()
-{
-	local mode=$1
-
-	# ping6 test: echo request should be redirect back to itself, not others
-	ip netns exec ${NS[1]} ip neigh add 2001:db8::2 dev veth0 lladdr 00:00:00:00:00:02
-
-	ip netns exec ${NS[1]} tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-1_${mode}.log &
-	ip netns exec ${NS[2]} tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-2_${mode}.log &
-	ip netns exec ${NS[3]} tcpdump -i veth0 -nn -l -e &> ${LOG_DIR}/ns1-3_${mode}.log &
-	sleep 0.5
-	# ARP test
-	ip netns exec ${NS[1]} arping -q -c 2 -I veth0 192.0.2.254
-	# IPv4 test
-	ip netns exec ${NS[1]} ping 192.0.2.253 -i 0.1 -c 4 &> /dev/null
-	# IPv6 test
-	ip netns exec ${NS[1]} ping6 2001:db8::2 -i 0.1 -c 2 &> /dev/null
-	sleep 0.5
-	pkill tcpdump
-
-	# All netns should receive the redirect arp requests
-	[ $(grep -cF "who-has 192.0.2.254" ${LOG_DIR}/ns1-1_${mode}.log) -eq 4 ] && \
-		test_pass "$mode arp(F_BROADCAST) ns1-1" || \
-		test_fail "$mode arp(F_BROADCAST) ns1-1"
-	[ $(grep -cF "who-has 192.0.2.254" ${LOG_DIR}/ns1-2_${mode}.log) -eq 2 ] && \
-		test_pass "$mode arp(F_BROADCAST) ns1-2" || \
-		test_fail "$mode arp(F_BROADCAST) ns1-2"
-	[ $(grep -cF "who-has 192.0.2.254" ${LOG_DIR}/ns1-3_${mode}.log) -eq 2 ] && \
-		test_pass "$mode arp(F_BROADCAST) ns1-3" || \
-		test_fail "$mode arp(F_BROADCAST) ns1-3"
-
-	# ns1 should not receive the redirect echo request, others should
-	[ $(grep -c "ICMP echo request" ${LOG_DIR}/ns1-1_${mode}.log) -eq 4 ] && \
-		test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-1" || \
-		test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-1"
-	[ $(grep -c "ICMP echo request" ${LOG_DIR}/ns1-2_${mode}.log) -eq 4 ] && \
-		test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-2" || \
-		test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-2"
-	[ $(grep -c "ICMP echo request" ${LOG_DIR}/ns1-3_${mode}.log) -eq 4 ] && \
-		test_pass "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-3" || \
-		test_fail "$mode IPv4 (F_BROADCAST|F_EXCLUDE_INGRESS) ns1-3"
-
-	# ns1 should receive the echo request, ns2 should not
-	[ $(grep -c "ICMP6, echo request" ${LOG_DIR}/ns1-1_${mode}.log) -eq 4 ] && \
-		test_pass "$mode IPv6 (no flags) ns1-1" || \
-		test_fail "$mode IPv6 (no flags) ns1-1"
-	[ $(grep -c "ICMP6, echo request" ${LOG_DIR}/ns1-2_${mode}.log) -eq 0 ] && \
-		test_pass "$mode IPv6 (no flags) ns1-2" || \
-		test_fail "$mode IPv6 (no flags) ns1-2"
-}
-
-do_tests()
-{
-	local mode=$1
-	local drv_p
-
-	case ${mode} in
-		xdpdrv)  drv_p="-N";;
-		xdpegress) drv_p="-X";;
-		xdpgeneric) drv_p="-S";;
-	esac
-
-	ip netns exec ${NS[0]} ./xdp_redirect_multi $drv_p $IFACES &> ${LOG_DIR}/xdp_redirect_${mode}.log &
-	xdp_pid=$!
-	sleep 1
-	if ! ps -p $xdp_pid > /dev/null; then
-		test_fail "$mode xdp_redirect_multi start failed"
-		return 1
-	fi
-
-	if [ "$mode" = "xdpegress" ]; then
-		do_egress_tests $mode
-	else
-		do_ping_tests $mode
-	fi
-
-	kill $xdp_pid
-}
-
-check_env
-
-trap clean_up EXIT
-
-for mode in ${DRV_MODE}; do
-	setup_ns $mode
-	do_tests $mode
-	clean_up
-done
-rm -rf ${LOG_DIR}
-
-echo "Summary: PASS $PASS, FAIL $FAIL"
-[ $FAIL -eq 0 ] && exit 0 || exit 1
diff --git a/tools/testing/selftests/bpf/test_xdp_veth.sh b/tools/testing/selftests/bpf/test_xdp_veth.sh
deleted file mode 100755
index 5211ca9a0239..000000000000
--- a/tools/testing/selftests/bpf/test_xdp_veth.sh
+++ /dev/null
@@ -1,121 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-#
-# Create 3 namespaces with 3 veth peers, and
-# forward packets in-between using native XDP
-#
-#                      XDP_TX
-# NS1(veth11)        NS2(veth22)        NS3(veth33)
-#      |                  |                  |
-#      |                  |                  |
-#   (veth1,            (veth2,            (veth3,
-#   id:111)            id:122)            id:133)
-#     ^ |                ^ |                ^ |
-#     | |  XDP_REDIRECT  | |  XDP_REDIRECT  | |
-#     | ------------------ ------------------ |
-#     -----------------------------------------
-#                    XDP_REDIRECT
-
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
-TESTNAME=xdp_veth
-BPF_FS=$(awk '$3 == "bpf" {print $2; exit}' /proc/mounts)
-BPF_DIR=$BPF_FS/test_$TESTNAME
-readonly NS1="ns1-$(mktemp -u XXXXXX)"
-readonly NS2="ns2-$(mktemp -u XXXXXX)"
-readonly NS3="ns3-$(mktemp -u XXXXXX)"
-
-_cleanup()
-{
-	set +e
-	ip link del veth1 2> /dev/null
-	ip link del veth2 2> /dev/null
-	ip link del veth3 2> /dev/null
-	ip netns del ${NS1} 2> /dev/null
-	ip netns del ${NS2} 2> /dev/null
-	ip netns del ${NS3} 2> /dev/null
-	rm -rf $BPF_DIR 2> /dev/null
-}
-
-cleanup_skip()
-{
-	echo "selftests: $TESTNAME [SKIP]"
-	_cleanup
-
-	exit $ksft_skip
-}
-
-cleanup()
-{
-	if [ "$?" = 0 ]; then
-		echo "selftests: $TESTNAME [PASS]"
-	else
-		echo "selftests: $TESTNAME [FAILED]"
-	fi
-	_cleanup
-}
-
-if [ $(id -u) -ne 0 ]; then
-	echo "selftests: $TESTNAME [SKIP] Need root privileges"
-	exit $ksft_skip
-fi
-
-if ! ip link set dev lo xdp off > /dev/null 2>&1; then
-	echo "selftests: $TESTNAME [SKIP] Could not run test without the ip xdp support"
-	exit $ksft_skip
-fi
-
-if [ -z "$BPF_FS" ]; then
-	echo "selftests: $TESTNAME [SKIP] Could not run test without bpffs mounted"
-	exit $ksft_skip
-fi
-
-if ! bpftool version > /dev/null 2>&1; then
-	echo "selftests: $TESTNAME [SKIP] Could not run test without bpftool"
-	exit $ksft_skip
-fi
-
-set -e
-
-trap cleanup_skip EXIT
-
-ip netns add ${NS1}
-ip netns add ${NS2}
-ip netns add ${NS3}
-
-ip link add veth1 index 111 type veth peer name veth11 netns ${NS1}
-ip link add veth2 index 122 type veth peer name veth22 netns ${NS2}
-ip link add veth3 index 133 type veth peer name veth33 netns ${NS3}
-
-ip link set veth1 up
-ip link set veth2 up
-ip link set veth3 up
-
-ip -n ${NS1} addr add 10.1.1.11/24 dev veth11
-ip -n ${NS3} addr add 10.1.1.33/24 dev veth33
-
-ip -n ${NS1} link set dev veth11 up
-ip -n ${NS2} link set dev veth22 up
-ip -n ${NS3} link set dev veth33 up
-
-mkdir $BPF_DIR
-bpftool prog loadall \
-	xdp_redirect_map.bpf.o $BPF_DIR/progs type xdp \
-	pinmaps $BPF_DIR/maps
-bpftool map update pinned $BPF_DIR/maps/tx_port key 0 0 0 0 value 122 0 0 0
-bpftool map update pinned $BPF_DIR/maps/tx_port key 1 0 0 0 value 133 0 0 0
-bpftool map update pinned $BPF_DIR/maps/tx_port key 2 0 0 0 value 111 0 0 0
-ip link set dev veth1 xdp pinned $BPF_DIR/progs/xdp_redirect_map_0
-ip link set dev veth2 xdp pinned $BPF_DIR/progs/xdp_redirect_map_1
-ip link set dev veth3 xdp pinned $BPF_DIR/progs/xdp_redirect_map_2
-
-ip -n ${NS1} link set dev veth11 xdp obj xdp_dummy.bpf.o sec xdp
-ip -n ${NS2} link set dev veth22 xdp obj xdp_tx.bpf.o sec xdp
-ip -n ${NS3} link set dev veth33 xdp obj xdp_dummy.bpf.o sec xdp
-
-trap cleanup EXIT
-
-ip netns exec ${NS1} ping -c 1 -W 1 10.1.1.33
-
-exit 0
diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh
deleted file mode 100755
index fbcaa9f0120b..000000000000
--- a/tools/testing/selftests/bpf/test_xdp_vlan.sh
+++ /dev/null
@@ -1,233 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-# Author: Jesper Dangaard Brouer <hawk@kernel.org>
-
-# Kselftest framework requirement - SKIP code is 4.
-readonly KSFT_SKIP=4
-readonly NS1="ns1-$(mktemp -u XXXXXX)"
-readonly NS2="ns2-$(mktemp -u XXXXXX)"
-
-# Allow wrapper scripts to name test
-if [ -z "$TESTNAME" ]; then
-    TESTNAME=xdp_vlan
-fi
-
-# Default XDP mode
-XDP_MODE=xdpgeneric
-
-usage() {
-  echo "Testing XDP + TC eBPF VLAN manipulations: $TESTNAME"
-  echo ""
-  echo "Usage: $0 [-vfh]"
-  echo "  -v | --verbose : Verbose"
-  echo "  --flush        : Flush before starting (e.g. after --interactive)"
-  echo "  --interactive  : Keep netns setup running after test-run"
-  echo "  --mode=XXX     : Choose XDP mode (xdp | xdpgeneric | xdpdrv)"
-  echo ""
-}
-
-valid_xdp_mode()
-{
-	local mode=$1
-
-	case "$mode" in
-		xdpgeneric | xdpdrv | xdp)
-			return 0
-			;;
-		*)
-			return 1
-	esac
-}
-
-cleanup()
-{
-	local status=$?
-
-	if [ "$status" = "0" ]; then
-		echo "selftests: $TESTNAME [PASS]";
-	else
-		echo "selftests: $TESTNAME [FAILED]";
-	fi
-
-	if [ -n "$INTERACTIVE" ]; then
-		echo "Namespace setup still active explore with:"
-		echo " ip netns exec ${NS1} bash"
-		echo " ip netns exec ${NS2} bash"
-		exit $status
-	fi
-
-	set +e
-	ip link del veth1 2> /dev/null
-	ip netns del ${NS1} 2> /dev/null
-	ip netns del ${NS2} 2> /dev/null
-}
-
-# Using external program "getopt" to get --long-options
-OPTIONS=$(getopt -o hvfi: \
-    --long verbose,flush,help,interactive,debug,mode: -- "$@")
-if (( $? != 0 )); then
-    usage
-    echo "selftests: $TESTNAME [FAILED] Error calling getopt, unknown option?"
-    exit 2
-fi
-eval set -- "$OPTIONS"
-
-##  --- Parse command line arguments / parameters ---
-while true; do
-	case "$1" in
-	    -v | --verbose)
-		export VERBOSE=yes
-		shift
-		;;
-	    -i | --interactive | --debug )
-		INTERACTIVE=yes
-		shift
-		;;
-	    -f | --flush )
-		cleanup
-		shift
-		;;
-	    --mode )
-		shift
-		XDP_MODE=$1
-		shift
-		;;
-	    -- )
-		shift
-		break
-		;;
-	    -h | --help )
-		usage;
-		echo "selftests: $TESTNAME [SKIP] usage help info requested"
-		exit $KSFT_SKIP
-		;;
-	    * )
-		shift
-		break
-		;;
-	esac
-done
-
-if [ "$EUID" -ne 0 ]; then
-	echo "selftests: $TESTNAME [FAILED] need root privileges"
-	exit 1
-fi
-
-valid_xdp_mode $XDP_MODE
-if [ $? -ne 0 ]; then
-	echo "selftests: $TESTNAME [FAILED] unknown XDP mode ($XDP_MODE)"
-	exit 1
-fi
-
-ip link set dev lo xdpgeneric off 2>/dev/null > /dev/null
-if [ $? -ne 0 ]; then
-	echo "selftests: $TESTNAME [SKIP] need ip xdp support"
-	exit $KSFT_SKIP
-fi
-
-# Interactive mode likely require us to cleanup netns
-if [ -n "$INTERACTIVE" ]; then
-	ip link del veth1 2> /dev/null
-	ip netns del ${NS1} 2> /dev/null
-	ip netns del ${NS2} 2> /dev/null
-fi
-
-# Exit on failure
-set -e
-
-# Some shell-tools dependencies
-which ip > /dev/null
-which tc > /dev/null
-which ethtool > /dev/null
-
-# Make rest of shell verbose, showing comments as doc/info
-if [ -n "$VERBOSE" ]; then
-    set -v
-fi
-
-# Create two namespaces
-ip netns add ${NS1}
-ip netns add ${NS2}
-
-# Run cleanup if failing or on kill
-trap cleanup 0 2 3 6 9
-
-# Create veth pair
-ip link add veth1 type veth peer name veth2
-
-# Move veth1 and veth2 into the respective namespaces
-ip link set veth1 netns ${NS1}
-ip link set veth2 netns ${NS2}
-
-# NOTICE: XDP require VLAN header inside packet payload
-#  - Thus, disable VLAN offloading driver features
-#  - For veth REMEMBER TX side VLAN-offload
-#
-# Disable rx-vlan-offload (mostly needed on ns1)
-ip netns exec ${NS1} ethtool -K veth1 rxvlan off
-ip netns exec ${NS2} ethtool -K veth2 rxvlan off
-#
-# Disable tx-vlan-offload (mostly needed on ns2)
-ip netns exec ${NS2} ethtool -K veth2 txvlan off
-ip netns exec ${NS1} ethtool -K veth1 txvlan off
-
-export IPADDR1=100.64.41.1
-export IPADDR2=100.64.41.2
-
-# In ns1/veth1 add IP-addr on plain net_device
-ip netns exec ${NS1} ip addr add ${IPADDR1}/24 dev veth1
-ip netns exec ${NS1} ip link set veth1 up
-
-# In ns2/veth2 create VLAN device
-export VLAN=4011
-export DEVNS2=veth2
-ip netns exec ${NS2} ip link add link $DEVNS2 name $DEVNS2.$VLAN type vlan id $VLAN
-ip netns exec ${NS2} ip addr add ${IPADDR2}/24 dev $DEVNS2.$VLAN
-ip netns exec ${NS2} ip link set $DEVNS2 up
-ip netns exec ${NS2} ip link set $DEVNS2.$VLAN up
-
-# Bringup lo in netns (to avoids confusing people using --interactive)
-ip netns exec ${NS1} ip link set lo up
-ip netns exec ${NS2} ip link set lo up
-
-# At this point, the hosts cannot reach each-other,
-# because ns2 are using VLAN tags on the packets.
-
-ip netns exec ${NS2} sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Success: First ping must fail"'
-
-
-# Now we can use the test_xdp_vlan.c program to pop/push these VLAN tags
-# ----------------------------------------------------------------------
-# In ns1: ingress use XDP to remove VLAN tags
-export DEVNS1=veth1
-export BPF_FILE=test_xdp_vlan.bpf.o
-
-# First test: Remove VLAN by setting VLAN ID 0, using "xdp_vlan_change"
-export XDP_PROG=xdp_vlan_change
-ip netns exec ${NS1} ip link set $DEVNS1 $XDP_MODE object $BPF_FILE section $XDP_PROG
-
-# In ns1: egress use TC to add back VLAN tag 4011
-#  (del cmd)
-#  tc qdisc del dev $DEVNS1 clsact 2> /dev/null
-#
-ip netns exec ${NS1} tc qdisc add dev $DEVNS1 clsact
-ip netns exec ${NS1} tc filter add dev $DEVNS1 egress \
-  prio 1 handle 1 bpf da obj $BPF_FILE sec tc_vlan_push
-
-# Now the namespaces can reach each-other, test with ping:
-ip netns exec ${NS2} ping -i 0.2 -W 2 -c 2 $IPADDR1
-ip netns exec ${NS1} ping -i 0.2 -W 2 -c 2 $IPADDR2
-
-# Second test: Replace xdp prog, that fully remove vlan header
-#
-# Catch kernel bug for generic-XDP, that does didn't allow us to
-# remove a VLAN header, because skb->protocol still contain VLAN
-# ETH_P_8021Q indication, and this cause overwriting of our changes.
-#
-export XDP_PROG=xdp_vlan_remove_outer2
-ip netns exec ${NS1} ip link set $DEVNS1 $XDP_MODE off
-ip netns exec ${NS1} ip link set $DEVNS1 $XDP_MODE object $BPF_FILE section $XDP_PROG
-
-# Now the namespaces should still be able reach each-other, test with ping:
-ip netns exec ${NS2} ping -i 0.2 -W 2 -c 2 $IPADDR1
-ip netns exec ${NS1} ping -i 0.2 -W 2 -c 2 $IPADDR2
diff --git a/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh b/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh
deleted file mode 100755
index c515326d6d59..000000000000
--- a/tools/testing/selftests/bpf/test_xdp_vlan_mode_generic.sh
+++ /dev/null
@@ -1,9 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-# Exit on failure
-set -e
-
-# Wrapper script to test generic-XDP
-export TESTNAME=xdp_vlan_mode_generic
-./test_xdp_vlan.sh --mode=xdpgeneric
diff --git a/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh b/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh
deleted file mode 100755
index 5cf7ce1f16c1..000000000000
--- a/tools/testing/selftests/bpf/test_xdp_vlan_mode_native.sh
+++ /dev/null
@@ -1,9 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-# Exit on failure
-set -e
-
-# Wrapper script to test native-XDP
-export TESTNAME=xdp_vlan_mode_native
-./test_xdp_vlan.sh --mode=xdpdrv
diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh
index d821fd098504..62db060298a4 100755
--- a/tools/testing/selftests/bpf/test_xsk.sh
+++ b/tools/testing/selftests/bpf/test_xsk.sh
@@ -24,8 +24,6 @@
 #      -----------     |     ----------
 #      |  vethX  | --------- |  vethY |
 #      -----------   peer    ----------
-#           |          |          |
-#      namespaceX      |     namespaceY
 #
 # AF_XDP is an address family optimized for high performance packet processing,
 # it is XDP’s user-space interface.
@@ -39,10 +37,9 @@
 # Prerequisites setup by script:
 #
 #   Set up veth interfaces as per the topology shown ^^:
-#   * setup two veth interfaces and one namespace
-#   ** veth<xxxx> in root namespace
-#   ** veth<yyyy> in af_xdp<xxxx> namespace
-#   ** namespace af_xdp<xxxx>
+#   * setup two veth interfaces
+#   ** veth<xxxx>
+#   ** veth<yyyy>
 #   *** xxxx and yyyy are randomly generated 4 digit numbers used to avoid
 #       conflict with any existing interface
 #   * tests the veth and xsk layers of the topology
@@ -71,22 +68,38 @@
 # Run with verbose output:
 #   sudo ./test_xsk.sh -v
 #
-# Run and dump packet contents:
-#   sudo ./test_xsk.sh -D
+# Set up veth interfaces and leave them up so xskxceiver can be launched in a debugger:
+#   sudo ./test_xsk.sh -d
 #
 # Run test suite for physical device in loopback mode
 #   sudo ./test_xsk.sh -i IFACE
+#
+# Run test suite in a specific mode only [skb,drv,zc]
+#   sudo ./test_xsk.sh -m MODE
+#
+# List available tests
+#   ./test_xsk.sh -l
+#
+# Run a specific test from the test suite
+#   sudo ./test_xsk.sh -t TEST_NAME
+#
+# Display the available command line options
+#   ./test_xsk.sh -h
 
 . xsk_prereqs.sh
 
 ETH=""
 
-while getopts "vDi:" flag
+while getopts "vi:dm:lt:h" flag
 do
 	case "${flag}" in
 		v) verbose=1;;
-		D) dump_pkts=1;;
+		d) debug=1;;
 		i) ETH=${OPTARG};;
+		m) MODE=${OPTARG};;
+		l) list=1;;
+		t) TEST=${OPTARG};;
+		h) help=1;;
 	esac
 done
 
@@ -99,28 +112,26 @@ VETH0_POSTFIX=$(cat ${URANDOM} | tr -dc '0-9' | fold -w 256 | head -n 1 | head -
 VETH0=ve${VETH0_POSTFIX}
 VETH1_POSTFIX=$(cat ${URANDOM} | tr -dc '0-9' | fold -w 256 | head -n 1 | head --bytes 4)
 VETH1=ve${VETH1_POSTFIX}
-NS0=root
-NS1=af_xdp${VETH1_POSTFIX}
 MTU=1500
 
 trap ctrl_c INT
 
 function ctrl_c() {
-        cleanup_exit ${VETH0} ${VETH1} ${NS1}
+        cleanup_exit ${VETH0} ${VETH1}
 	exit 1
 }
 
 setup_vethPairs() {
 	if [[ $verbose -eq 1 ]]; then
-	        echo "setting up ${VETH0}: namespace: ${NS0}"
+	        echo "setting up ${VETH0}"
 	fi
-	ip netns add ${NS1}
 	ip link add ${VETH0} numtxqueues 4 numrxqueues 4 type veth peer name ${VETH1} numtxqueues 4 numrxqueues 4
 	if [ -f /proc/net/if_inet6 ]; then
 		echo 1 > /proc/sys/net/ipv6/conf/${VETH0}/disable_ipv6
+		echo 1 > /proc/sys/net/ipv6/conf/${VETH1}/disable_ipv6
 	fi
 	if [[ $verbose -eq 1 ]]; then
-	        echo "setting up ${VETH1}: namespace: ${NS1}"
+	        echo "setting up ${VETH1}"
 	fi
 
 	if [[ $busy_poll -eq 1 ]]; then
@@ -130,18 +141,25 @@ setup_vethPairs() {
 		echo 200000 > /sys/class/net/${VETH1}/gro_flush_timeout
 	fi
 
-	ip link set ${VETH1} netns ${NS1}
-	ip netns exec ${NS1} ip link set ${VETH1} mtu ${MTU}
+	ip link set ${VETH1} mtu ${MTU}
 	ip link set ${VETH0} mtu ${MTU}
-	ip netns exec ${NS1} ip link set ${VETH1} up
-	ip netns exec ${NS1} ip link set dev lo up
+	ip link set ${VETH1} up
 	ip link set ${VETH0} up
 }
 
+if [[ $list -eq 1 ]]; then
+        ./${XSKOBJ} -l
+        exit
+fi
+
+if [[ $help -eq 1 ]]; then
+	./${XSKOBJ}
+        exit
+fi
+
 if [ ! -z $ETH ]; then
 	VETH0=${ETH}
 	VETH1=${ETH}
-	NS1=""
 else
 	validate_root_exec
 	validate_veth_support ${VETH0}
@@ -151,7 +169,7 @@ else
 	retval=$?
 	if [ $retval -ne 0 ]; then
 		test_status $retval "${TEST_NAME}"
-		cleanup_exit ${VETH0} ${VETH1} ${NS1}
+		cleanup_exit ${VETH0} ${VETH1}
 		exit $retval
 	fi
 fi
@@ -161,8 +179,12 @@ if [[ $verbose -eq 1 ]]; then
 	ARGS+="-v "
 fi
 
-if [[ $dump_pkts -eq 1 ]]; then
-	ARGS="-D "
+if [ -n "$MODE" ]; then
+	ARGS+="-m ${MODE} "
+fi
+
+if [ -n "$TEST" ]; then
+	ARGS+="-t ${TEST} "
 fi
 
 retval=$?
@@ -174,11 +196,23 @@ statusList=()
 
 TEST_NAME="XSK_SELFTESTS_${VETH0}_SOFTIRQ"
 
+if [[ $debug -eq 1 ]]; then
+    echo "-i" ${VETH0} "-i" ${VETH1}
+    exit
+fi
+
 exec_xskxceiver
 
 if [ -z $ETH ]; then
-	cleanup_exit ${VETH0} ${VETH1} ${NS1}
+	cleanup_exit ${VETH0} ${VETH1}
+else
+	cleanup_iface ${ETH} ${MTU}
+fi
+
+if [[ $list -eq 1 ]]; then
+    exit
 fi
+
 TEST_NAME="XSK_SELFTESTS_${VETH0}_BUSY_POLL"
 busy_poll=1
 
@@ -190,7 +224,9 @@ exec_xskxceiver
 ## END TESTS
 
 if [ -z $ETH ]; then
-	cleanup_exit ${VETH0} ${VETH1} ${NS1}
+	cleanup_exit ${VETH0} ${VETH1}
+else
+	cleanup_iface ${ETH} ${MTU}
 fi
 
 failures=0
@@ -205,4 +241,6 @@ done
 
 if [ $failures -eq 0 ]; then
         echo "All tests successful!"
+else
+	exit 1
 fi
diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c
index 9695318e8132..16eb37e5bad6 100644
--- a/tools/testing/selftests/bpf/testing_helpers.c
+++ b/tools/testing/selftests/bpf/testing_helpers.c
@@ -1,13 +1,16 @@
 // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 /* Copyright (C) 2019 Netronome Systems, Inc. */
 /* Copyright (C) 2020 Facebook, Inc. */
+#include <ctype.h>
 #include <stdlib.h>
 #include <string.h>
 #include <errno.h>
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
+#include "disasm.h"
 #include "test_progs.h"
 #include "testing_helpers.h"
+#include <linux/membarrier.h>
 
 int parse_num_list(const char *s, bool **num_set, int *num_set_len)
 {
@@ -70,92 +73,168 @@ int parse_num_list(const char *s, bool **num_set, int *num_set_len)
 	return 0;
 }
 
-int parse_test_list(const char *s,
-		    struct test_filter_set *set,
-		    bool is_glob_pattern)
+static int do_insert_test(struct test_filter_set *set,
+			  char *test_str,
+			  char *subtest_str)
 {
-	char *input, *state = NULL, *next;
-	struct test_filter *tmp, *tests = NULL;
-	int i, j, cnt = 0;
+	struct test_filter *tmp, *test;
+	char **ctmp;
+	int i;
 
-	input = strdup(s);
-	if (!input)
+	for (i = 0; i < set->cnt; i++) {
+		test = &set->tests[i];
+
+		if (strcmp(test_str, test->name) == 0) {
+			free(test_str);
+			goto subtest;
+		}
+	}
+
+	tmp = realloc(set->tests, sizeof(*test) * (set->cnt + 1));
+	if (!tmp)
 		return -ENOMEM;
 
-	while ((next = strtok_r(state ? NULL : input, ",", &state))) {
-		char *subtest_str = strchr(next, '/');
-		char *pattern = NULL;
-		int glob_chars = 0;
+	set->tests = tmp;
+	test = &set->tests[set->cnt];
 
-		tmp = realloc(tests, sizeof(*tests) * (cnt + 1));
-		if (!tmp)
-			goto err;
-		tests = tmp;
+	test->name = test_str;
+	test->subtests = NULL;
+	test->subtest_cnt = 0;
 
-		tests[cnt].subtest_cnt = 0;
-		tests[cnt].subtests = NULL;
+	set->cnt++;
 
-		if (is_glob_pattern) {
-			pattern = "%s";
-		} else {
-			pattern = "*%s*";
-			glob_chars = 2;
-		}
+subtest:
+	if (!subtest_str)
+		return 0;
 
-		if (subtest_str) {
-			char **tmp_subtests = NULL;
-			int subtest_cnt = tests[cnt].subtest_cnt;
-
-			*subtest_str = '\0';
-			subtest_str += 1;
-			tmp_subtests = realloc(tests[cnt].subtests,
-					       sizeof(*tmp_subtests) *
-					       (subtest_cnt + 1));
-			if (!tmp_subtests)
-				goto err;
-			tests[cnt].subtests = tmp_subtests;
-
-			tests[cnt].subtests[subtest_cnt] =
-				malloc(strlen(subtest_str) + glob_chars + 1);
-			if (!tests[cnt].subtests[subtest_cnt])
-				goto err;
-			sprintf(tests[cnt].subtests[subtest_cnt],
-				pattern,
-				subtest_str);
-
-			tests[cnt].subtest_cnt++;
+	for (i = 0; i < test->subtest_cnt; i++) {
+		if (strcmp(subtest_str, test->subtests[i]) == 0) {
+			free(subtest_str);
+			return 0;
 		}
+	}
 
-		tests[cnt].name = malloc(strlen(next) + glob_chars + 1);
-		if (!tests[cnt].name)
-			goto err;
-		sprintf(tests[cnt].name, pattern, next);
+	ctmp = realloc(test->subtests,
+		       sizeof(*test->subtests) * (test->subtest_cnt + 1));
+	if (!ctmp)
+		return -ENOMEM;
 
-		cnt++;
+	test->subtests = ctmp;
+	test->subtests[test->subtest_cnt] = subtest_str;
+
+	test->subtest_cnt++;
+
+	return 0;
+}
+
+static int insert_test(struct test_filter_set *set,
+		       char *test_spec,
+		       bool is_glob_pattern)
+{
+	char *pattern, *subtest_str, *ext_test_str, *ext_subtest_str = NULL;
+	int glob_chars = 0;
+
+	if (is_glob_pattern) {
+		pattern = "%s";
+	} else {
+		pattern = "*%s*";
+		glob_chars = 2;
 	}
 
-	tmp = realloc(set->tests, sizeof(*tests) * (cnt + set->cnt));
-	if (!tmp)
+	subtest_str = strchr(test_spec, '/');
+	if (subtest_str) {
+		*subtest_str = '\0';
+		subtest_str += 1;
+	}
+
+	ext_test_str = malloc(strlen(test_spec) + glob_chars + 1);
+	if (!ext_test_str)
 		goto err;
 
-	memcpy(tmp +  set->cnt, tests, sizeof(*tests) * cnt);
-	set->tests = tmp;
-	set->cnt += cnt;
+	sprintf(ext_test_str, pattern, test_spec);
 
-	free(tests);
-	free(input);
-	return 0;
+	if (subtest_str) {
+		ext_subtest_str = malloc(strlen(subtest_str) + glob_chars + 1);
+		if (!ext_subtest_str)
+			goto err;
+
+		sprintf(ext_subtest_str, pattern, subtest_str);
+	}
+
+	return do_insert_test(set, ext_test_str, ext_subtest_str);
 
 err:
-	for (i = 0; i < cnt; i++) {
-		for (j = 0; j < tests[i].subtest_cnt; j++)
-			free(tests[i].subtests[j]);
+	free(ext_test_str);
+	free(ext_subtest_str);
+
+	return -ENOMEM;
+}
+
+int parse_test_list_file(const char *path,
+			 struct test_filter_set *set,
+			 bool is_glob_pattern)
+{
+	char *buf = NULL, *capture_start, *capture_end, *scan_end;
+	size_t buflen = 0;
+	int err = 0;
+	FILE *f;
+
+	f = fopen(path, "r");
+	if (!f) {
+		err = -errno;
+		fprintf(stderr, "Failed to open '%s': %d\n", path, err);
+		return err;
+	}
+
+	while (getline(&buf, &buflen, f) != -1) {
+		capture_start = buf;
+
+		while (isspace(*capture_start))
+			++capture_start;
+
+		capture_end = capture_start;
+		scan_end = capture_start;
+
+		while (*scan_end && *scan_end != '#') {
+			if (!isspace(*scan_end))
+				capture_end = scan_end;
 
-		free(tests[i].name);
+			++scan_end;
+		}
+
+		if (capture_end == capture_start)
+			continue;
+
+		*(++capture_end) = '\0';
+
+		err = insert_test(set, capture_start, is_glob_pattern);
+		if (err)
+			break;
 	}
-	free(tests);
+
+	fclose(f);
+	return err;
+}
+
+int parse_test_list(const char *s,
+		    struct test_filter_set *set,
+		    bool is_glob_pattern)
+{
+	char *input, *state = NULL, *test_spec;
+	int err = 0, cnt = 0;
+
+	input = strdup(s);
+	if (!input)
+		return -ENOMEM;
+
+	while ((test_spec = strtok_r(cnt++ ? NULL : input, ",", &state))) {
+		err = insert_test(set, test_spec, is_glob_pattern);
+		if (err)
+			break;
+	}
+
 	free(input);
-	return -ENOMEM;
+	return err;
 }
 
 __u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info)
@@ -164,7 +243,7 @@ __u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info)
 	int err;
 
 	memset(info, 0, sizeof(*info));
-	err = bpf_obj_get_info_by_fd(bpf_link__fd(link), info, &info_len);
+	err = bpf_link_get_info_by_fd(bpf_link__fd(link), info, &info_len);
 	if (err) {
 		printf("failed to get link info: %d\n", -errno);
 		return 0;
@@ -174,6 +253,34 @@ __u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info)
 
 int extra_prog_load_log_flags = 0;
 
+int testing_prog_flags(void)
+{
+	static int cached_flags = -1;
+	static int prog_flags[] = { BPF_F_TEST_RND_HI32, BPF_F_TEST_REG_INVARIANTS };
+	static struct bpf_insn insns[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	};
+	int insn_cnt = ARRAY_SIZE(insns), i, fd, flags = 0;
+	LIBBPF_OPTS(bpf_prog_load_opts, opts);
+
+	if (cached_flags >= 0)
+		return cached_flags;
+
+	for (i = 0; i < ARRAY_SIZE(prog_flags); i++) {
+		opts.prog_flags = prog_flags[i];
+		fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, "flag-test", "GPL",
+				   insns, insn_cnt, &opts);
+		if (fd >= 0) {
+			flags |= prog_flags[i];
+			close(fd);
+		}
+	}
+
+	cached_flags = flags;
+	return cached_flags;
+}
+
 int bpf_prog_test_load(const char *file, enum bpf_prog_type type,
 		       struct bpf_object **pobj, int *prog_fd)
 {
@@ -195,10 +302,10 @@ int bpf_prog_test_load(const char *file, enum bpf_prog_type type,
 		goto err_out;
 	}
 
-	if (type != BPF_PROG_TYPE_UNSPEC)
+	if (type != BPF_PROG_TYPE_UNSPEC && bpf_program__type(prog) != type)
 		bpf_program__set_type(prog, type);
 
-	flags = bpf_program__flags(prog) | BPF_F_TEST_RND_HI32;
+	flags = bpf_program__flags(prog) | testing_prog_flags();
 	bpf_program__set_flags(prog, flags);
 
 	err = bpf_object__load(obj);
@@ -221,7 +328,7 @@ int bpf_test_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 {
 	LIBBPF_OPTS(bpf_prog_load_opts, opts,
 		.kern_version = kern_version,
-		.prog_flags = BPF_F_TEST_RND_HI32,
+		.prog_flags = testing_prog_flags(),
 		.log_level = extra_prog_load_log_flags,
 		.log_buf = log_buf,
 		.log_size = log_buf_sz,
@@ -229,3 +336,177 @@ int bpf_test_load_program(enum bpf_prog_type type, const struct bpf_insn *insns,
 
 	return bpf_prog_load(type, NULL, license, insns, insns_cnt, &opts);
 }
+
+__u64 read_perf_max_sample_freq(void)
+{
+	__u64 sample_freq = 5000; /* fallback to 5000 on error */
+	FILE *f;
+
+	f = fopen("/proc/sys/kernel/perf_event_max_sample_rate", "r");
+	if (f == NULL) {
+		printf("Failed to open /proc/sys/kernel/perf_event_max_sample_rate: err %d\n"
+		       "return default value: 5000\n", -errno);
+		return sample_freq;
+	}
+	if (fscanf(f, "%llu", &sample_freq) != 1) {
+		printf("Failed to parse /proc/sys/kernel/perf_event_max_sample_rate: err %d\n"
+		       "return default value: 5000\n", -errno);
+	}
+
+	fclose(f);
+	return sample_freq;
+}
+
+int finit_module(int fd, const char *param_values, int flags)
+{
+	return syscall(__NR_finit_module, fd, param_values, flags);
+}
+
+int delete_module(const char *name, int flags)
+{
+	return syscall(__NR_delete_module, name, flags);
+}
+
+int unload_module(const char *name, bool verbose)
+{
+	int ret, cnt = 0;
+
+	if (kern_sync_rcu())
+		fprintf(stdout, "Failed to trigger kernel-side RCU sync!\n");
+
+	for (;;) {
+		ret = delete_module(name, 0);
+		if (!ret || errno != EAGAIN)
+			break;
+		if (++cnt > 10000) {
+			fprintf(stdout, "Unload of %s timed out\n", name);
+			break;
+		}
+		usleep(100);
+	}
+
+	if (ret) {
+		if (errno == ENOENT) {
+			if (verbose)
+				fprintf(stdout, "%s.ko is already unloaded.\n", name);
+			return -1;
+		}
+		fprintf(stdout, "Failed to unload %s.ko from kernel: %d\n", name, -errno);
+		return -1;
+	}
+	if (verbose)
+		fprintf(stdout, "Successfully unloaded %s.ko.\n", name);
+	return 0;
+}
+
+static int __load_module(const char *path, const char *param_values, bool verbose)
+{
+	int fd;
+
+	if (verbose)
+		fprintf(stdout, "Loading %s...\n", path);
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0) {
+		fprintf(stdout, "Can't find %s kernel module: %d\n", path, -errno);
+		return -ENOENT;
+	}
+	if (finit_module(fd, param_values, 0)) {
+		fprintf(stdout, "Failed to load %s into the kernel: %d\n", path, -errno);
+		close(fd);
+		return -EINVAL;
+	}
+	close(fd);
+
+	if (verbose)
+		fprintf(stdout, "Successfully loaded %s.\n", path);
+	return 0;
+}
+
+int load_module_params(const char *path, const char *param_values, bool verbose)
+{
+	return __load_module(path, param_values, verbose);
+}
+
+int load_module(const char *path, bool verbose)
+{
+	return __load_module(path, "", verbose);
+}
+
+int unload_bpf_testmod(bool verbose)
+{
+	return unload_module("bpf_testmod", verbose);
+}
+
+int load_bpf_testmod(bool verbose)
+{
+	return load_module("bpf_testmod.ko", verbose);
+}
+
+/*
+ * Trigger synchronize_rcu() in kernel.
+ */
+int kern_sync_rcu(void)
+{
+	return syscall(__NR_membarrier, MEMBARRIER_CMD_SHARED, 0, 0);
+}
+
+int get_xlated_program(int fd_prog, struct bpf_insn **buf, __u32 *cnt)
+{
+	__u32 buf_element_size = sizeof(struct bpf_insn);
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
+	__u32 xlated_prog_len;
+
+	if (bpf_prog_get_info_by_fd(fd_prog, &info, &info_len)) {
+		perror("bpf_prog_get_info_by_fd failed");
+		return -1;
+	}
+
+	xlated_prog_len = info.xlated_prog_len;
+	if (xlated_prog_len % buf_element_size) {
+		printf("Program length %u is not multiple of %u\n",
+		       xlated_prog_len, buf_element_size);
+		return -1;
+	}
+
+	*cnt = xlated_prog_len / buf_element_size;
+	*buf = calloc(*cnt, buf_element_size);
+	if (!*buf) {
+		perror("can't allocate xlated program buffer");
+		return -ENOMEM;
+	}
+
+	bzero(&info, sizeof(info));
+	info.xlated_prog_len = xlated_prog_len;
+	info.xlated_prog_insns = (__u64)(unsigned long)*buf;
+	if (bpf_prog_get_info_by_fd(fd_prog, &info, &info_len)) {
+		perror("second bpf_prog_get_info_by_fd failed");
+		goto out_free_buf;
+	}
+
+	return 0;
+
+out_free_buf:
+	free(*buf);
+	*buf = NULL;
+	return -1;
+}
+
+bool is_jit_enabled(void)
+{
+	const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable";
+	bool enabled = false;
+	int sysctl_fd;
+
+	sysctl_fd = open(jit_sysctl, O_RDONLY);
+	if (sysctl_fd != -1) {
+		char tmpc;
+
+		if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1)
+			enabled = (tmpc != '0');
+		close(sysctl_fd);
+	}
+
+	return enabled;
+}
diff --git a/tools/testing/selftests/bpf/testing_helpers.h b/tools/testing/selftests/bpf/testing_helpers.h
index 6ec00bf79cb5..eb20d3772218 100644
--- a/tools/testing/selftests/bpf/testing_helpers.h
+++ b/tools/testing/selftests/bpf/testing_helpers.h
@@ -1,8 +1,16 @@
 /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 /* Copyright (C) 2020 Facebook, Inc. */
+
+#ifndef __TESTING_HELPERS_H
+#define __TESTING_HELPERS_H
+
 #include <stdbool.h>
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
+#include <time.h>
+
+#define __TO_STR(x) #x
+#define TO_STR(x) __TO_STR(x)
 
 int parse_num_list(const char *s, bool **set, int *set_len);
 __u32 link_info_prog_id(const struct bpf_link *link, struct bpf_link_info *info);
@@ -20,3 +28,35 @@ struct test_filter_set;
 int parse_test_list(const char *s,
 		    struct test_filter_set *test_set,
 		    bool is_glob_pattern);
+int parse_test_list_file(const char *path,
+			 struct test_filter_set *test_set,
+			 bool is_glob_pattern);
+
+__u64 read_perf_max_sample_freq(void);
+int load_bpf_testmod(bool verbose);
+int unload_bpf_testmod(bool verbose);
+int kern_sync_rcu(void);
+int finit_module(int fd, const char *param_values, int flags);
+int delete_module(const char *name, int flags);
+int load_module(const char *path, bool verbose);
+int load_module_params(const char *path, const char *param_values, bool verbose);
+int unload_module(const char *name, bool verbose);
+
+static inline __u64 get_time_ns(void)
+{
+	struct timespec t;
+
+	clock_gettime(CLOCK_MONOTONIC, &t);
+
+	return (u64)t.tv_sec * 1000000000 + t.tv_nsec;
+}
+
+struct bpf_insn;
+/* Request BPF program instructions after all rewrites are applied,
+ * e.g. verifier.c:convert_ctx_access() is done.
+ */
+int get_xlated_program(int fd_prog, struct bpf_insn **buf, __u32 *cnt);
+int testing_prog_flags(void);
+bool is_jit_enabled(void);
+
+#endif /* __TESTING_HELPERS_H */
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index 09a16a77bae4..eeaab7013ca2 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -7,110 +7,215 @@
 #include <errno.h>
 #include <fcntl.h>
 #include <poll.h>
+#include <pthread.h>
 #include <unistd.h>
 #include <linux/perf_event.h>
+#include <linux/fs.h>
+#include <sys/ioctl.h>
 #include <sys/mman.h>
 #include "trace_helpers.h"
+#include <linux/limits.h>
+#include <libelf.h>
+#include <gelf.h>
+#include "bpf/hashmap.h"
+#include "bpf/libbpf_internal.h"
+#include "bpf_util.h"
+
+#define TRACEFS_PIPE	"/sys/kernel/tracing/trace_pipe"
+#define DEBUGFS_PIPE	"/sys/kernel/debug/tracing/trace_pipe"
+
+struct ksyms {
+	struct ksym *syms;
+	size_t sym_cap;
+	size_t sym_cnt;
+};
+
+static struct ksyms *ksyms;
+static pthread_mutex_t ksyms_mutex = PTHREAD_MUTEX_INITIALIZER;
+
+static int ksyms__add_symbol(struct ksyms *ksyms, const char *name,
+			     unsigned long addr)
+{
+	void *tmp;
+
+	tmp = strdup(name);
+	if (!tmp)
+		return -ENOMEM;
+	ksyms->syms[ksyms->sym_cnt].addr = addr;
+	ksyms->syms[ksyms->sym_cnt].name = tmp;
+	ksyms->sym_cnt++;
+	return 0;
+}
 
-#define DEBUGFS "/sys/kernel/debug/tracing/"
+void free_kallsyms_local(struct ksyms *ksyms)
+{
+	unsigned int i;
 
-#define MAX_SYMS 300000
-static struct ksym syms[MAX_SYMS];
-static int sym_cnt;
+	if (!ksyms)
+		return;
 
-static int ksym_cmp(const void *p1, const void *p2)
-{
-	return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr;
+	if (!ksyms->syms) {
+		free(ksyms);
+		return;
+	}
+
+	for (i = 0; i < ksyms->sym_cnt; i++)
+		free(ksyms->syms[i].name);
+	free(ksyms->syms);
+	free(ksyms);
 }
 
-int load_kallsyms_refresh(void)
+static struct ksyms *load_kallsyms_local_common(ksym_cmp_t cmp_cb)
 {
 	FILE *f;
 	char func[256], buf[256];
 	char symbol;
 	void *addr;
-	int i = 0;
-
-	sym_cnt = 0;
+	int ret;
+	struct ksyms *ksyms;
 
 	f = fopen("/proc/kallsyms", "r");
 	if (!f)
-		return -ENOENT;
+		return NULL;
+
+	ksyms = calloc(1, sizeof(struct ksyms));
+	if (!ksyms) {
+		fclose(f);
+		return NULL;
+	}
 
 	while (fgets(buf, sizeof(buf), f)) {
 		if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3)
 			break;
 		if (!addr)
 			continue;
-		syms[i].addr = (long) addr;
-		syms[i].name = strdup(func);
-		i++;
+
+		ret = libbpf_ensure_mem((void **) &ksyms->syms, &ksyms->sym_cap,
+					sizeof(struct ksym), ksyms->sym_cnt + 1);
+		if (ret)
+			goto error;
+		ret = ksyms__add_symbol(ksyms, func, (unsigned long)addr);
+		if (ret)
+			goto error;
 	}
 	fclose(f);
-	sym_cnt = i;
-	qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp);
-	return 0;
+	qsort(ksyms->syms, ksyms->sym_cnt, sizeof(struct ksym), cmp_cb);
+	return ksyms;
+
+error:
+	fclose(f);
+	free_kallsyms_local(ksyms);
+	return NULL;
+}
+
+static int ksym_cmp(const void *p1, const void *p2)
+{
+	return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr;
+}
+
+struct ksyms *load_kallsyms_local(void)
+{
+	return load_kallsyms_local_common(ksym_cmp);
+}
+
+struct ksyms *load_kallsyms_custom_local(ksym_cmp_t cmp_cb)
+{
+	return load_kallsyms_local_common(cmp_cb);
 }
 
 int load_kallsyms(void)
 {
-	/*
-	 * This is called/used from multiplace places,
-	 * load symbols just once.
-	 */
-	if (sym_cnt)
-		return 0;
-	return load_kallsyms_refresh();
+	pthread_mutex_lock(&ksyms_mutex);
+	if (!ksyms)
+		ksyms = load_kallsyms_local();
+	pthread_mutex_unlock(&ksyms_mutex);
+	return ksyms ? 0 : 1;
 }
 
-struct ksym *ksym_search(long key)
+struct ksym *ksym_search_local(struct ksyms *ksyms, long key)
 {
-	int start = 0, end = sym_cnt;
+	int start = 0, end = ksyms->sym_cnt;
 	int result;
 
 	/* kallsyms not loaded. return NULL */
-	if (sym_cnt <= 0)
+	if (ksyms->sym_cnt <= 0)
 		return NULL;
 
 	while (start < end) {
 		size_t mid = start + (end - start) / 2;
 
-		result = key - syms[mid].addr;
+		result = key - ksyms->syms[mid].addr;
 		if (result < 0)
 			end = mid;
 		else if (result > 0)
 			start = mid + 1;
 		else
-			return &syms[mid];
+			return &ksyms->syms[mid];
 	}
 
-	if (start >= 1 && syms[start - 1].addr < key &&
-	    key < syms[start].addr)
+	if (start >= 1 && ksyms->syms[start - 1].addr < key &&
+	    key < ksyms->syms[start].addr)
 		/* valid ksym */
-		return &syms[start - 1];
+		return &ksyms->syms[start - 1];
 
 	/* out of range. return _stext */
-	return &syms[0];
+	return &ksyms->syms[0];
 }
 
-long ksym_get_addr(const char *name)
+struct ksym *search_kallsyms_custom_local(struct ksyms *ksyms, const void *p,
+					  ksym_search_cmp_t cmp_cb)
+{
+	int start = 0, mid, end = ksyms->sym_cnt;
+	struct ksym *ks;
+	int result;
+
+	while (start < end) {
+		mid = start + (end - start) / 2;
+		ks = &ksyms->syms[mid];
+		result = cmp_cb(p, ks);
+		if (result < 0)
+			end = mid;
+		else if (result > 0)
+			start = mid + 1;
+		else
+			return ks;
+	}
+
+	return NULL;
+}
+
+struct ksym *ksym_search(long key)
+{
+	if (!ksyms)
+		return NULL;
+	return ksym_search_local(ksyms, key);
+}
+
+long ksym_get_addr_local(struct ksyms *ksyms, const char *name)
 {
 	int i;
 
-	for (i = 0; i < sym_cnt; i++) {
-		if (strcmp(syms[i].name, name) == 0)
-			return syms[i].addr;
+	for (i = 0; i < ksyms->sym_cnt; i++) {
+		if (strcmp(ksyms->syms[i].name, name) == 0)
+			return ksyms->syms[i].addr;
 	}
 
 	return 0;
 }
 
+long ksym_get_addr(const char *name)
+{
+	if (!ksyms)
+		return 0;
+	return ksym_get_addr_local(ksyms, name);
+}
+
 /* open kallsyms and read symbol addresses on the fly. Without caching all symbols,
  * this is faster than load + find.
  */
 int kallsyms_find(const char *sym, unsigned long long *addr)
 {
-	char type, name[500];
+	char type, name[500], *match;
 	unsigned long long value;
 	int err = 0;
 	FILE *f;
@@ -120,6 +225,17 @@ int kallsyms_find(const char *sym, unsigned long long *addr)
 		return -EINVAL;
 
 	while (fscanf(f, "%llx %c %499s%*[^\n]\n", &value, &type, name) > 0) {
+		/* If CONFIG_LTO_CLANG_THIN is enabled, static variable/function
+		 * symbols could be promoted to global due to cross-file inlining.
+		 * For such cases, clang compiler will add .llvm.<hash> suffix
+		 * to those symbols to avoid potential naming conflict.
+		 * Let us ignore .llvm.<hash> suffix during symbol comparison.
+		 */
+		if (type == 'd') {
+			match = strstr(name, ".llvm.");
+			if (match)
+				*match = '\0';
+		}
 		if (strcmp(name, sym) == 0) {
 			*addr = value;
 			goto out;
@@ -132,49 +248,95 @@ out:
 	return err;
 }
 
-void read_trace_pipe(void)
+#ifdef PROCMAP_QUERY
+int env_verbosity __weak = 0;
+
+static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags)
 {
-	int trace_fd;
+	char path_buf[PATH_MAX], build_id_buf[20];
+	struct procmap_query q;
+	int err;
+
+	memset(&q, 0, sizeof(q));
+	q.size = sizeof(q);
+	q.query_flags = query_flags;
+	q.query_addr = (__u64)addr;
+	q.vma_name_addr = (__u64)path_buf;
+	q.vma_name_size = sizeof(path_buf);
+	q.build_id_addr = (__u64)build_id_buf;
+	q.build_id_size = sizeof(build_id_buf);
+
+	err = ioctl(fd, PROCMAP_QUERY, &q);
+	if (err < 0) {
+		err = -errno;
+		if (err == -ENOTTY)
+			return -EOPNOTSUPP; /* ioctl() not implemented yet */
+		if (err == -ENOENT)
+			return -ESRCH; /* vma not found */
+		return err;
+	}
 
-	trace_fd = open(DEBUGFS "trace_pipe", O_RDONLY, 0);
-	if (trace_fd < 0)
-		return;
+	if (env_verbosity >= 1) {
+		printf("VMA FOUND (addr %08lx): %08lx-%08lx %c%c%c%c %08lx %02x:%02x %ld %s (build ID: %s, %d bytes)\n",
+		       (long)addr, (long)q.vma_start, (long)q.vma_end,
+		       (q.vma_flags & PROCMAP_QUERY_VMA_READABLE) ? 'r' : '-',
+		       (q.vma_flags & PROCMAP_QUERY_VMA_WRITABLE) ? 'w' : '-',
+		       (q.vma_flags & PROCMAP_QUERY_VMA_EXECUTABLE) ? 'x' : '-',
+		       (q.vma_flags & PROCMAP_QUERY_VMA_SHARED) ? 's' : 'p',
+		       (long)q.vma_offset, q.dev_major, q.dev_minor, (long)q.inode,
+		       q.vma_name_size ? path_buf : "",
+		       q.build_id_size ? "YES" : "NO",
+		       q.build_id_size);
+	}
 
-	while (1) {
-		static char buf[4096];
-		ssize_t sz;
+	*start = q.vma_start;
+	*offset = q.vma_offset;
+	*flags = q.vma_flags;
+	return 0;
+}
+#else
+# ifndef PROCMAP_QUERY_VMA_EXECUTABLE
+#  define PROCMAP_QUERY_VMA_EXECUTABLE 0x04
+# endif
 
-		sz = read(trace_fd, buf, sizeof(buf) - 1);
-		if (sz > 0) {
-			buf[sz] = 0;
-			puts(buf);
-		}
-	}
+static int procmap_query(int fd, const void *addr, __u32 query_flags, size_t *start, size_t *offset, int *flags)
+{
+	return -EOPNOTSUPP;
 }
+#endif
 
 ssize_t get_uprobe_offset(const void *addr)
 {
-	size_t start, end, base;
-	char buf[256];
-	bool found = false;
+	size_t start, base, end;
 	FILE *f;
+	char buf[256];
+	int err, flags;
 
 	f = fopen("/proc/self/maps", "r");
 	if (!f)
 		return -errno;
 
-	while (fscanf(f, "%zx-%zx %s %zx %*[^\n]\n", &start, &end, buf, &base) == 4) {
-		if (buf[2] == 'x' && (uintptr_t)addr >= start && (uintptr_t)addr < end) {
-			found = true;
-			break;
+	/* requested executable VMA only */
+	err = procmap_query(fileno(f), addr, PROCMAP_QUERY_VMA_EXECUTABLE, &start, &base, &flags);
+	if (err == -EOPNOTSUPP) {
+		bool found = false;
+
+		while (fscanf(f, "%zx-%zx %s %zx %*[^\n]\n", &start, &end, buf, &base) == 4) {
+			if (buf[2] == 'x' && (uintptr_t)addr >= start && (uintptr_t)addr < end) {
+				found = true;
+				break;
+			}
+		}
+		if (!found) {
+			fclose(f);
+			return -ESRCH;
 		}
+	} else if (err) {
+		fclose(f);
+		return err;
 	}
-
 	fclose(f);
 
-	if (!found)
-		return -ESRCH;
-
 #if defined(__powerpc64__) && defined(_CALL_ELF) && _CALL_ELF == 2
 
 #define OP_RT_RA_MASK   0xffff0000UL
@@ -199,7 +361,7 @@ ssize_t get_uprobe_offset(const void *addr)
 	 * addi  r2,r2,XXXX
 	 */
 	{
-		const u32 *insn = (const u32 *)(uintptr_t)addr;
+		const __u32 *insn = (const __u32 *)(uintptr_t)addr;
 
 		if ((((*insn & OP_RT_RA_MASK) == ADDIS_R2_R12) ||
 		     ((*insn & OP_RT_RA_MASK) == LIS_R2)) &&
@@ -215,18 +377,379 @@ ssize_t get_rel_offset(uintptr_t addr)
 	size_t start, end, offset;
 	char buf[256];
 	FILE *f;
+	int err, flags;
 
 	f = fopen("/proc/self/maps", "r");
 	if (!f)
 		return -errno;
 
-	while (fscanf(f, "%zx-%zx %s %zx %*[^\n]\n", &start, &end, buf, &offset) == 4) {
-		if (addr >= start && addr < end) {
-			fclose(f);
-			return (size_t)addr - start + offset;
+	err = procmap_query(fileno(f), (const void *)addr, 0, &start, &offset, &flags);
+	if (err == 0) {
+		fclose(f);
+		return (size_t)addr - start + offset;
+	} else if (err != -EOPNOTSUPP) {
+		fclose(f);
+		return err;
+	} else if (err) {
+		while (fscanf(f, "%zx-%zx %s %zx %*[^\n]\n", &start, &end, buf, &offset) == 4) {
+			if (addr >= start && addr < end) {
+				fclose(f);
+				return (size_t)addr - start + offset;
+			}
 		}
 	}
 
 	fclose(f);
 	return -EINVAL;
 }
+
+static int
+parse_build_id_buf(const void *note_start, Elf32_Word note_size, char *build_id)
+{
+	Elf32_Word note_offs = 0;
+
+	while (note_offs + sizeof(Elf32_Nhdr) < note_size) {
+		Elf32_Nhdr *nhdr = (Elf32_Nhdr *)(note_start + note_offs);
+
+		if (nhdr->n_type == 3 && nhdr->n_namesz == sizeof("GNU") &&
+		    !strcmp((char *)(nhdr + 1), "GNU") && nhdr->n_descsz > 0 &&
+		    nhdr->n_descsz <= BPF_BUILD_ID_SIZE) {
+			memcpy(build_id, note_start + note_offs +
+			       ALIGN(sizeof("GNU"), 4) + sizeof(Elf32_Nhdr), nhdr->n_descsz);
+			memset(build_id + nhdr->n_descsz, 0, BPF_BUILD_ID_SIZE - nhdr->n_descsz);
+			return (int) nhdr->n_descsz;
+		}
+
+		note_offs = note_offs + sizeof(Elf32_Nhdr) +
+			   ALIGN(nhdr->n_namesz, 4) + ALIGN(nhdr->n_descsz, 4);
+	}
+
+	return -ENOENT;
+}
+
+/* Reads binary from *path* file and returns it in the *build_id* buffer
+ * with *size* which is expected to be at least BPF_BUILD_ID_SIZE bytes.
+ * Returns size of build id on success. On error the error value is
+ * returned.
+ */
+int read_build_id(const char *path, char *build_id, size_t size)
+{
+	int fd, err = -EINVAL;
+	Elf *elf = NULL;
+	GElf_Ehdr ehdr;
+	size_t max, i;
+
+	if (size < BPF_BUILD_ID_SIZE)
+		return -EINVAL;
+
+	fd = open(path, O_RDONLY | O_CLOEXEC);
+	if (fd < 0)
+		return -errno;
+
+	(void)elf_version(EV_CURRENT);
+
+	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
+	if (!elf)
+		goto out;
+	if (elf_kind(elf) != ELF_K_ELF)
+		goto out;
+	if (!gelf_getehdr(elf, &ehdr))
+		goto out;
+
+	for (i = 0; i < ehdr.e_phnum; i++) {
+		GElf_Phdr mem, *phdr;
+		char *data;
+
+		phdr = gelf_getphdr(elf, i, &mem);
+		if (!phdr)
+			goto out;
+		if (phdr->p_type != PT_NOTE)
+			continue;
+		data = elf_rawfile(elf, &max);
+		if (!data)
+			goto out;
+		if (phdr->p_offset + phdr->p_memsz > max)
+			goto out;
+		err = parse_build_id_buf(data + phdr->p_offset, phdr->p_memsz, build_id);
+		if (err > 0)
+			break;
+	}
+
+out:
+	if (elf)
+		elf_end(elf);
+	close(fd);
+	return err;
+}
+
+int read_trace_pipe_iter(void (*cb)(const char *str, void *data), void *data, int iter)
+{
+	size_t buflen, n;
+	char *buf = NULL;
+	FILE *fp = NULL;
+
+	if (access(TRACEFS_PIPE, F_OK) == 0)
+		fp = fopen(TRACEFS_PIPE, "r");
+	else
+		fp = fopen(DEBUGFS_PIPE, "r");
+	if (!fp)
+		return -1;
+
+	 /* We do not want to wait forever when iter is specified. */
+	if (iter)
+		fcntl(fileno(fp), F_SETFL, O_NONBLOCK);
+
+	while ((n = getline(&buf, &buflen, fp) >= 0) || errno == EAGAIN) {
+		if (n > 0)
+			cb(buf, data);
+		if (iter && !(--iter))
+			break;
+	}
+
+	free(buf);
+	if (fp)
+		fclose(fp);
+	return 0;
+}
+
+static void trace_pipe_cb(const char *str, void *data)
+{
+	printf("%s", str);
+}
+
+void read_trace_pipe(void)
+{
+	read_trace_pipe_iter(trace_pipe_cb, NULL, 0);
+}
+
+static size_t symbol_hash(long key, void *ctx __maybe_unused)
+{
+	return str_hash((const char *) key);
+}
+
+static bool symbol_equal(long key1, long key2, void *ctx __maybe_unused)
+{
+	return strcmp((const char *) key1, (const char *) key2) == 0;
+}
+
+static bool is_invalid_entry(char *buf, bool kernel)
+{
+	if (kernel && strchr(buf, '['))
+		return true;
+	if (!kernel && !strchr(buf, '['))
+		return true;
+	return false;
+}
+
+static const char * const trace_blacklist[] = {
+	"migrate_disable",
+	"migrate_enable",
+	"rcu_read_unlock_strict",
+	"preempt_count_add",
+	"preempt_count_sub",
+	"__rcu_read_lock",
+	"__rcu_read_unlock",
+	"bpf_get_numa_node_id",
+};
+
+static bool skip_entry(char *name)
+{
+	int i;
+
+	/*
+	 * We attach to almost all kernel functions and some of them
+	 * will cause 'suspicious RCU usage' when fprobe is attached
+	 * to them. Filter out the current culprits - arch_cpu_idle
+	 * default_idle and rcu_* functions.
+	 */
+	if (!strcmp(name, "arch_cpu_idle"))
+		return true;
+	if (!strcmp(name, "default_idle"))
+		return true;
+	if (!strncmp(name, "rcu_", 4))
+		return true;
+	if (!strcmp(name, "bpf_dispatcher_xdp_func"))
+		return true;
+	if (!strncmp(name, "__ftrace_invalid_address__",
+		     sizeof("__ftrace_invalid_address__") - 1))
+		return true;
+
+	for (i = 0; i < ARRAY_SIZE(trace_blacklist); i++) {
+		if (!strcmp(name, trace_blacklist[i]))
+			return true;
+	}
+
+	return false;
+}
+
+/* Do comparison by ignoring '.llvm.<hash>' suffixes. */
+static int compare_name(const char *name1, const char *name2)
+{
+	const char *res1, *res2;
+	int len1, len2;
+
+	res1 = strstr(name1, ".llvm.");
+	res2 = strstr(name2, ".llvm.");
+	len1 = res1 ? res1 - name1 : strlen(name1);
+	len2 = res2 ? res2 - name2 : strlen(name2);
+
+	if (len1 == len2)
+		return strncmp(name1, name2, len1);
+	if (len1 < len2)
+		return strncmp(name1, name2, len1) <= 0 ? -1 : 1;
+	return strncmp(name1, name2, len2) >= 0 ? 1 : -1;
+}
+
+static int load_kallsyms_compare(const void *p1, const void *p2)
+{
+	return compare_name(((const struct ksym *)p1)->name, ((const struct ksym *)p2)->name);
+}
+
+static int search_kallsyms_compare(const void *p1, const struct ksym *p2)
+{
+	return compare_name(p1, p2->name);
+}
+
+int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel)
+{
+	size_t cap = 0, cnt = 0;
+	char *name = NULL, *ksym_name, **syms = NULL;
+	struct hashmap *map;
+	struct ksyms *ksyms;
+	struct ksym *ks;
+	char buf[256];
+	FILE *f;
+	int err = 0;
+
+	ksyms = load_kallsyms_custom_local(load_kallsyms_compare);
+	if (!ksyms)
+		return -EINVAL;
+
+	/*
+	 * The available_filter_functions contains many duplicates,
+	 * but other than that all symbols are usable to trace.
+	 * Filtering out duplicates by using hashmap__add, which won't
+	 * add existing entry.
+	 */
+
+	if (access("/sys/kernel/tracing/trace", F_OK) == 0)
+		f = fopen("/sys/kernel/tracing/available_filter_functions", "r");
+	else
+		f = fopen("/sys/kernel/debug/tracing/available_filter_functions", "r");
+
+	if (!f)
+		return -EINVAL;
+
+	map = hashmap__new(symbol_hash, symbol_equal, NULL);
+	if (IS_ERR(map)) {
+		err = libbpf_get_error(map);
+		goto error;
+	}
+
+	while (fgets(buf, sizeof(buf), f)) {
+		if (is_invalid_entry(buf, kernel))
+			continue;
+
+		free(name);
+		if (sscanf(buf, "%ms$*[^\n]\n", &name) != 1)
+			continue;
+		if (skip_entry(name))
+			continue;
+
+		ks = search_kallsyms_custom_local(ksyms, name, search_kallsyms_compare);
+		if (!ks) {
+			err = -EINVAL;
+			goto error;
+		}
+
+		ksym_name = ks->name;
+		err = hashmap__add(map, ksym_name, 0);
+		if (err == -EEXIST) {
+			err = 0;
+			continue;
+		}
+		if (err)
+			goto error;
+
+		err = libbpf_ensure_mem((void **) &syms, &cap,
+					sizeof(*syms), cnt + 1);
+		if (err)
+			goto error;
+
+		syms[cnt++] = ksym_name;
+	}
+
+	*symsp = syms;
+	*cntp = cnt;
+
+error:
+	free(name);
+	fclose(f);
+	hashmap__free(map);
+	if (err)
+		free(syms);
+	return err;
+}
+
+int bpf_get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel)
+{
+	unsigned long *addr, *addrs, *tmp_addrs;
+	int err = 0, max_cnt, inc_cnt;
+	char *name = NULL;
+	size_t cnt = 0;
+	char buf[256];
+	FILE *f;
+
+	if (access("/sys/kernel/tracing/trace", F_OK) == 0)
+		f = fopen("/sys/kernel/tracing/available_filter_functions_addrs", "r");
+	else
+		f = fopen("/sys/kernel/debug/tracing/available_filter_functions_addrs", "r");
+
+	if (!f)
+		return -ENOENT;
+
+	/* In my local setup, the number of entries is 50k+ so Let us initially
+	 * allocate space to hold 64k entries. If 64k is not enough, incrementally
+	 * increase 1k each time.
+	 */
+	max_cnt = 65536;
+	inc_cnt = 1024;
+	addrs = malloc(max_cnt * sizeof(long));
+	if (addrs == NULL) {
+		err = -ENOMEM;
+		goto error;
+	}
+
+	while (fgets(buf, sizeof(buf), f)) {
+		if (is_invalid_entry(buf, kernel))
+			continue;
+
+		free(name);
+		if (sscanf(buf, "%p %ms$*[^\n]\n", &addr, &name) != 2)
+			continue;
+		if (skip_entry(name))
+			continue;
+
+		if (cnt == max_cnt) {
+			max_cnt += inc_cnt;
+			tmp_addrs = realloc(addrs, max_cnt * sizeof(long));
+			if (!tmp_addrs) {
+				err = -ENOMEM;
+				goto error;
+			}
+			addrs = tmp_addrs;
+		}
+
+		addrs[cnt++] = (unsigned long)addr;
+	}
+
+	*addrsp = addrs;
+	*cntp = cnt;
+
+error:
+	free(name);
+	fclose(f);
+	if (err)
+		free(addrs);
+	return err;
+}
diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h
index 53efde0e2998..9437bdd4afa5 100644
--- a/tools/testing/selftests/bpf/trace_helpers.h
+++ b/tools/testing/selftests/bpf/trace_helpers.h
@@ -4,23 +4,44 @@
 
 #include <bpf/libbpf.h>
 
+#define __ALIGN_MASK(x, mask)	(((x)+(mask))&~(mask))
+#define ALIGN(x, a)		__ALIGN_MASK(x, (typeof(x))(a)-1)
+
 struct ksym {
 	long addr;
 	char *name;
 };
+struct ksyms;
 
-int load_kallsyms(void);
-int load_kallsyms_refresh(void);
+typedef int (*ksym_cmp_t)(const void *p1, const void *p2);
+typedef int (*ksym_search_cmp_t)(const void *p1, const struct ksym *p2);
 
+int load_kallsyms(void);
 struct ksym *ksym_search(long key);
 long ksym_get_addr(const char *name);
 
+struct ksyms *load_kallsyms_local(void);
+struct ksym *ksym_search_local(struct ksyms *ksyms, long key);
+long ksym_get_addr_local(struct ksyms *ksyms, const char *name);
+void free_kallsyms_local(struct ksyms *ksyms);
+
+struct ksyms *load_kallsyms_custom_local(ksym_cmp_t cmp_cb);
+struct ksym *search_kallsyms_custom_local(struct ksyms *ksyms, const void *p1,
+					  ksym_search_cmp_t cmp_cb);
+
 /* open kallsyms and find addresses on the fly, faster than load + search. */
 int kallsyms_find(const char *sym, unsigned long long *addr);
 
 void read_trace_pipe(void);
+int read_trace_pipe_iter(void (*cb)(const char *str, void *data),
+			 void *data, int iter);
 
 ssize_t get_uprobe_offset(const void *addr);
 ssize_t get_rel_offset(uintptr_t addr);
 
+int read_build_id(const char *path, char *build_id, size_t size);
+
+int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel);
+int bpf_get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel);
+
 #endif
diff --git a/tools/testing/selftests/bpf/unpriv_helpers.c b/tools/testing/selftests/bpf/unpriv_helpers.c
new file mode 100644
index 000000000000..f997d7ec8fd0
--- /dev/null
+++ b/tools/testing/selftests/bpf/unpriv_helpers.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <errno.h>
+#include <limits.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/utsname.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <zlib.h>
+
+#include "unpriv_helpers.h"
+
+static gzFile open_config(void)
+{
+	struct utsname uts;
+	char buf[PATH_MAX];
+	gzFile config;
+
+	if (uname(&uts)) {
+		perror("uname");
+		goto config_gz;
+	}
+
+	snprintf(buf, sizeof(buf), "/boot/config-%s", uts.release);
+	config = gzopen(buf, "rb");
+	if (config)
+		return config;
+	fprintf(stderr, "gzopen %s: %s\n", buf, strerror(errno));
+
+config_gz:
+	config = gzopen("/proc/config.gz", "rb");
+	if (!config)
+		perror("gzopen /proc/config.gz");
+	return config;
+}
+
+static int config_contains(const char *pat)
+{
+	const char *msg;
+	char buf[1024];
+	gzFile config;
+	int n, err;
+
+	config = open_config();
+	if (!config)
+		return -1;
+
+	for (;;) {
+		if (!gzgets(config, buf, sizeof(buf))) {
+			msg = gzerror(config, &err);
+			if (err == Z_ERRNO)
+				perror("gzgets /proc/config.gz");
+			else if (err != Z_OK)
+				fprintf(stderr, "gzgets /proc/config.gz: %s", msg);
+			gzclose(config);
+			return -1;
+		}
+		n = strlen(buf);
+		if (buf[n - 1] == '\n')
+			buf[n - 1] = 0;
+		if (strcmp(buf, pat) == 0) {
+			gzclose(config);
+			return 1;
+		}
+	}
+	gzclose(config);
+	return 0;
+}
+
+static bool cmdline_contains(const char *pat)
+{
+	char cmdline[4096], *c;
+	int fd, ret = false;
+
+	fd = open("/proc/cmdline", O_RDONLY);
+	if (fd < 0) {
+		perror("open /proc/cmdline");
+		return false;
+	}
+
+	if (read(fd, cmdline, sizeof(cmdline) - 1) < 0) {
+		perror("read /proc/cmdline");
+		goto out;
+	}
+
+	cmdline[sizeof(cmdline) - 1] = '\0';
+	for (c = strtok(cmdline, " \n"); c; c = strtok(NULL, " \n")) {
+		if (strncmp(c, pat, strlen(c)))
+			continue;
+		ret = true;
+		break;
+	}
+out:
+	close(fd);
+	return ret;
+}
+
+static int get_mitigations_off(void)
+{
+	int enabled_in_config;
+
+	if (cmdline_contains("mitigations=off"))
+		return 1;
+	enabled_in_config = config_contains("CONFIG_CPU_MITIGATIONS=y");
+	if (enabled_in_config < 0)
+		return -1;
+	return !enabled_in_config;
+}
+
+bool get_unpriv_disabled(void)
+{
+	int mitigations_off;
+	bool disabled;
+	char buf[2];
+	FILE *fd;
+
+	fd = fopen("/proc/sys/" UNPRIV_SYSCTL, "r");
+	if (fd) {
+		disabled = (fgets(buf, 2, fd) == buf && atoi(buf));
+		fclose(fd);
+	} else {
+		perror("fopen /proc/sys/" UNPRIV_SYSCTL);
+		disabled = true;
+	}
+
+	if (disabled)
+		return true;
+
+	/*
+	 * Some unpriv tests rely on spectre mitigations being on.
+	 * If mitigations are off or status can't be determined
+	 * assume that unpriv tests are disabled.
+	 */
+	mitigations_off = get_mitigations_off();
+	if (mitigations_off < 0) {
+		fprintf(stderr,
+			"Can't determine if mitigations are enabled, disabling unpriv tests.");
+		return true;
+	}
+	return mitigations_off;
+}
diff --git a/tools/testing/selftests/bpf/unpriv_helpers.h b/tools/testing/selftests/bpf/unpriv_helpers.h
new file mode 100644
index 000000000000..151f67329665
--- /dev/null
+++ b/tools/testing/selftests/bpf/unpriv_helpers.h
@@ -0,0 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <stdbool.h>
+
+#define UNPRIV_SYSCTL "kernel/unprivileged_bpf_disabled"
+
+bool get_unpriv_disabled(void);
diff --git a/tools/testing/selftests/bpf/uprobe_multi.c b/tools/testing/selftests/bpf/uprobe_multi.c
new file mode 100644
index 000000000000..dd38dc68f635
--- /dev/null
+++ b/tools/testing/selftests/bpf/uprobe_multi.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdio.h>
+#include <string.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <sys/mman.h>
+#include <unistd.h>
+#include <sdt.h>
+
+#ifndef MADV_POPULATE_READ
+#define MADV_POPULATE_READ 22
+#endif
+
+#ifndef MADV_PAGEOUT
+#define MADV_PAGEOUT 21
+#endif
+
+int __attribute__((weak)) uprobe(void)
+{
+	return 0;
+}
+
+#define __PASTE(a, b) a##b
+#define PASTE(a, b) __PASTE(a, b)
+
+#define NAME(name, idx) PASTE(name, idx)
+
+#define DEF(name, idx) int __attribute__((weak)) NAME(name, idx)(void) { return 0; }
+#define CALL(name, idx) NAME(name, idx)();
+
+#define F(body, name, idx) body(name, idx)
+
+#define F10(body, name, idx) \
+	F(body, PASTE(name, idx), 0) F(body, PASTE(name, idx), 1) F(body, PASTE(name, idx), 2) \
+	F(body, PASTE(name, idx), 3) F(body, PASTE(name, idx), 4) F(body, PASTE(name, idx), 5) \
+	F(body, PASTE(name, idx), 6) F(body, PASTE(name, idx), 7) F(body, PASTE(name, idx), 8) \
+	F(body, PASTE(name, idx), 9)
+
+#define F100(body, name, idx) \
+	F10(body, PASTE(name, idx), 0) F10(body, PASTE(name, idx), 1) F10(body, PASTE(name, idx), 2) \
+	F10(body, PASTE(name, idx), 3) F10(body, PASTE(name, idx), 4) F10(body, PASTE(name, idx), 5) \
+	F10(body, PASTE(name, idx), 6) F10(body, PASTE(name, idx), 7) F10(body, PASTE(name, idx), 8) \
+	F10(body, PASTE(name, idx), 9)
+
+#define F1000(body, name, idx) \
+	F100(body, PASTE(name, idx), 0) F100(body, PASTE(name, idx), 1) F100(body, PASTE(name, idx), 2) \
+	F100(body, PASTE(name, idx), 3) F100(body, PASTE(name, idx), 4) F100(body, PASTE(name, idx), 5) \
+	F100(body, PASTE(name, idx), 6) F100(body, PASTE(name, idx), 7) F100(body, PASTE(name, idx), 8) \
+	F100(body, PASTE(name, idx), 9)
+
+#define F10000(body, name, idx) \
+	F1000(body, PASTE(name, idx), 0) F1000(body, PASTE(name, idx), 1) F1000(body, PASTE(name, idx), 2) \
+	F1000(body, PASTE(name, idx), 3) F1000(body, PASTE(name, idx), 4) F1000(body, PASTE(name, idx), 5) \
+	F1000(body, PASTE(name, idx), 6) F1000(body, PASTE(name, idx), 7) F1000(body, PASTE(name, idx), 8) \
+	F1000(body, PASTE(name, idx), 9)
+
+F10000(DEF, uprobe_multi_func_, 0)
+F10000(DEF, uprobe_multi_func_, 1)
+F10000(DEF, uprobe_multi_func_, 2)
+F10000(DEF, uprobe_multi_func_, 3)
+F10000(DEF, uprobe_multi_func_, 4)
+
+static int bench(void)
+{
+	F10000(CALL, uprobe_multi_func_, 0)
+	F10000(CALL, uprobe_multi_func_, 1)
+	F10000(CALL, uprobe_multi_func_, 2)
+	F10000(CALL, uprobe_multi_func_, 3)
+	F10000(CALL, uprobe_multi_func_, 4)
+	return 0;
+}
+
+#define PROBE STAP_PROBE(test, usdt);
+
+#define PROBE10    PROBE PROBE PROBE PROBE PROBE \
+		   PROBE PROBE PROBE PROBE PROBE
+#define PROBE100   PROBE10 PROBE10 PROBE10 PROBE10 PROBE10 \
+		   PROBE10 PROBE10 PROBE10 PROBE10 PROBE10
+#define PROBE1000  PROBE100 PROBE100 PROBE100 PROBE100 PROBE100 \
+		   PROBE100 PROBE100 PROBE100 PROBE100 PROBE100
+#define PROBE10000 PROBE1000 PROBE1000 PROBE1000 PROBE1000 PROBE1000 \
+		   PROBE1000 PROBE1000 PROBE1000 PROBE1000 PROBE1000
+
+static int usdt(void)
+{
+	PROBE10000
+	PROBE10000
+	PROBE10000
+	PROBE10000
+	PROBE10000
+	return 0;
+}
+
+extern char build_id_start[];
+extern char build_id_end[];
+
+int __attribute__((weak)) trigger_uprobe(bool build_id_resident)
+{
+	int page_sz = sysconf(_SC_PAGESIZE);
+	void *addr;
+
+	/* page-align build ID start */
+	addr = (void *)((uintptr_t)&build_id_start & ~(page_sz - 1));
+
+	/* to guarantee MADV_PAGEOUT work reliably, we need to ensure that
+	 * memory range is mapped into current process, so we unconditionally
+	 * do MADV_POPULATE_READ, and then MADV_PAGEOUT, if necessary
+	 */
+	madvise(addr, page_sz, MADV_POPULATE_READ);
+	if (!build_id_resident)
+		madvise(addr, page_sz, MADV_PAGEOUT);
+
+	(void)uprobe();
+
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	if (argc != 2)
+		goto error;
+
+	if (!strcmp("bench", argv[1]))
+		return bench();
+	if (!strcmp("usdt", argv[1]))
+		return usdt();
+	if (!strcmp("uprobe-paged-out", argv[1]))
+		return trigger_uprobe(false /* page-out build ID */);
+	if (!strcmp("uprobe-paged-in", argv[1]))
+		return trigger_uprobe(true /* page-in build ID */);
+
+error:
+	fprintf(stderr, "usage: %s <bench|usdt>\n", argv[0]);
+	return -1;
+}
diff --git a/tools/testing/selftests/bpf/uprobe_multi.ld b/tools/testing/selftests/bpf/uprobe_multi.ld
new file mode 100644
index 000000000000..a2e94828bc8c
--- /dev/null
+++ b/tools/testing/selftests/bpf/uprobe_multi.ld
@@ -0,0 +1,11 @@
+SECTIONS
+{
+	. = ALIGN(4096);
+	.note.gnu.build-id : { *(.note.gnu.build-id) }
+	. = ALIGN(4096);
+}
+INSERT AFTER .text;
+
+build_id_start = ADDR(.note.gnu.build-id);
+build_id_end = ADDR(.note.gnu.build-id) + SIZEOF(.note.gnu.build-id);
+
diff --git a/tools/testing/selftests/bpf/uptr_test_common.h b/tools/testing/selftests/bpf/uptr_test_common.h
new file mode 100644
index 000000000000..f8a134ba12f9
--- /dev/null
+++ b/tools/testing/selftests/bpf/uptr_test_common.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#ifndef _UPTR_TEST_COMMON_H
+#define _UPTR_TEST_COMMON_H
+
+#define MAGIC_VALUE 0xabcd1234
+#define PAGE_SIZE 4096
+
+#ifdef __BPF__
+/* Avoid fwd btf type being generated for the following struct */
+struct large_data *dummy_large_data;
+struct empty_data *dummy_empty_data;
+struct user_data *dummy_data;
+struct cgroup *dummy_cgrp;
+#else
+#define __uptr
+#define __kptr
+#endif
+
+struct user_data {
+	int a;
+	int b;
+	int result;
+	int nested_result;
+};
+
+struct nested_udata {
+	struct user_data __uptr *udata;
+};
+
+struct value_type {
+	struct user_data __uptr *udata;
+	struct cgroup __kptr *cgrp;
+	struct nested_udata nested;
+};
+
+struct value_lock_type {
+	struct user_data __uptr *udata;
+	struct bpf_spin_lock lock;
+};
+
+struct large_data {
+	__u8 one_page[PAGE_SIZE];
+	int a;
+};
+
+struct large_uptr {
+	struct large_data __uptr *udata;
+};
+
+struct empty_data {
+};
+
+struct empty_uptr {
+	struct empty_data __uptr *udata;
+};
+
+struct kstruct_uptr {
+	struct cgroup __uptr *cgrp;
+};
+
+#endif
diff --git a/tools/testing/selftests/bpf/urandom_read.c b/tools/testing/selftests/bpf/urandom_read.c
index e92644d0fa75..4ed795655b9f 100644
--- a/tools/testing/selftests/bpf/urandom_read.c
+++ b/tools/testing/selftests/bpf/urandom_read.c
@@ -11,6 +11,9 @@
 #define _SDT_HAS_SEMAPHORES 1
 #include "sdt.h"
 
+#define SHARED 1
+#include "bpf/libbpf_internal.h"
+
 #define SEC(name) __attribute__((section(name), used))
 
 #define BUF_SIZE 256
@@ -21,10 +24,14 @@ void urand_read_without_sema(int iter_num, int iter_cnt, int read_sz);
 void urandlib_read_with_sema(int iter_num, int iter_cnt, int read_sz);
 void urandlib_read_without_sema(int iter_num, int iter_cnt, int read_sz);
 
+int urandlib_api(void);
+COMPAT_VERSION(urandlib_api_old, urandlib_api, LIBURANDOM_READ_1.0.0)
+int urandlib_api_old(void);
+int urandlib_api_sameoffset(void);
+
 unsigned short urand_read_with_sema_semaphore SEC(".probes");
 
-static __attribute__((noinline))
-void urandom_read(int fd, int count)
+static noinline void urandom_read(int fd, int count)
 {
 	char buf[BUF_SIZE];
 	int i;
@@ -83,6 +90,10 @@ int main(int argc, char *argv[])
 
 	urandom_read(fd, count);
 
+	urandlib_api();
+	urandlib_api_old();
+	urandlib_api_sameoffset();
+
 	close(fd);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/urandom_read_lib1.c b/tools/testing/selftests/bpf/urandom_read_lib1.c
index 86186e24b740..8c1356d8b4ee 100644
--- a/tools/testing/selftests/bpf/urandom_read_lib1.c
+++ b/tools/testing/selftests/bpf/urandom_read_lib1.c
@@ -3,6 +3,9 @@
 #define _SDT_HAS_SEMAPHORES 1
 #include "sdt.h"
 
+#define SHARED 1
+#include "bpf/libbpf_internal.h"
+
 #define SEC(name) __attribute__((section(name), used))
 
 unsigned short urandlib_read_with_sema_semaphore SEC(".probes");
@@ -11,3 +14,22 @@ void urandlib_read_with_sema(int iter_num, int iter_cnt, int read_sz)
 {
 	STAP_PROBE3(urandlib, read_with_sema, iter_num, iter_cnt, read_sz);
 }
+
+COMPAT_VERSION(urandlib_api_v1, urandlib_api, LIBURANDOM_READ_1.0.0)
+int urandlib_api_v1(void)
+{
+	return 1;
+}
+
+DEFAULT_VERSION(urandlib_api_v2, urandlib_api, LIBURANDOM_READ_2.0.0)
+int urandlib_api_v2(void)
+{
+	return 2;
+}
+
+COMPAT_VERSION(urandlib_api_sameoffset, urandlib_api_sameoffset, LIBURANDOM_READ_1.0.0)
+DEFAULT_VERSION(urandlib_api_sameoffset, urandlib_api_sameoffset, LIBURANDOM_READ_2.0.0)
+int urandlib_api_sameoffset(void)
+{
+	return 3;
+}
diff --git a/tools/testing/selftests/bpf/usdt.h b/tools/testing/selftests/bpf/usdt.h
new file mode 100644
index 000000000000..549d1f774810
--- /dev/null
+++ b/tools/testing/selftests/bpf/usdt.h
@@ -0,0 +1,545 @@
+// SPDX-License-Identifier: BSD-2-Clause
+/*
+ *  This single-header library defines a collection of variadic macros for
+ *  defining and triggering USDTs (User Statically-Defined Tracepoints):
+ *
+ *      - For USDTs without associated semaphore:
+ *          USDT(group, name, args...)
+ *
+ *      - For USDTs with implicit (transparent to the user) semaphore:
+ *          USDT_WITH_SEMA(group, name, args...)
+ *          USDT_IS_ACTIVE(group, name)
+ *
+ *      - For USDTs with explicit (user-defined and provided) semaphore:
+ *          USDT_WITH_EXPLICIT_SEMA(sema, group, name, args...)
+ *          USDT_SEMA_IS_ACTIVE(sema)
+ *
+ *  all of which emit a NOP instruction into the instruction stream, and so
+ *  have *zero* overhead for the surrounding code. USDTs are identified by
+ *  a combination of `group` and `name` identifiers, which is used by external
+ *  tracing tooling (tracers) for identifying exact USDTs of interest.
+ *
+ *  USDTs can have an associated (2-byte) activity counter (USDT semaphore),
+ *  automatically maintained by Linux kernel whenever any correctly written
+ *  BPF-based tracer is attached to the USDT. This USDT semaphore can be used
+ *  to check whether there is a need to do any extra data collection and
+ *  processing for a given USDT (if necessary), and otherwise avoid extra work
+ *  for a common case of USDT not being traced ("active").
+ *
+ *  See documentation for USDT_WITH_SEMA()/USDT_IS_ACTIVE() or
+ *  USDT_WITH_EXPLICIT_SEMA()/USDT_SEMA_IS_ACTIVE() APIs below for details on
+ *  working with USDTs with implicitly or explicitly associated
+ *  USDT semaphores, respectively.
+ *
+ *  There is also some additional data recorded into an auxiliary note
+ *  section. The data in the note section describes the operands, in terms of
+ *  size and location, used by tracing tooling to know where to find USDT
+ *  arguments. Each location is encoded as an assembler operand string.
+ *  Tracing tools (bpftrace and BPF-based tracers, systemtap, etc) insert
+ *  breakpoints on top of the nop, and decode the location operand-strings,
+ *  like an assembler, to find the values being passed.
+ *
+ *  The operand strings are selected by the compiler for each operand.
+ *  They are constrained by inline-assembler codes.The default is:
+ *
+ *  #define USDT_ARG_CONSTRAINT nor
+ *
+ *  This is a good default if the operands tend to be integral and
+ *  moderate in number (smaller than number of registers). In other
+ *  cases, the compiler may report "'asm' requires impossible reload" or
+ *  similar. In this case, consider simplifying the macro call (fewer
+ *  and simpler operands), reduce optimization, or override the default
+ *  constraints string via:
+ *
+ *  #define USDT_ARG_CONSTRAINT g
+ *  #include <usdt.h>
+ *
+ * For some historical description of USDT v3 format (the one used by this
+ * library and generally recognized and assumed by BPF-based tracing tools)
+ * see [0]. The more formal specification can be found at [1]. Additional
+ * argument constraints information can be found at [2].
+ *
+ * Original SystemTap's sys/sdt.h implementation ([3]) was used as a base for
+ * this USDT library implementation. Current implementation differs *a lot* in
+ * terms of exposed user API and general usability, which was the main goal
+ * and focus of the reimplementation work. Nevertheless, underlying recorded
+ * USDT definitions are fully binary compatible and any USDT-based tooling
+ * should work equally well with USDTs defined by either SystemTap's or this
+ * library's USDT implementation.
+ *
+ *   [0] https://ecos.sourceware.org/ml/systemtap/2010-q3/msg00145.html
+ *   [1] https://sourceware.org/systemtap/wiki/UserSpaceProbeImplementation
+ *   [2] https://gcc.gnu.org/onlinedocs/gcc/Constraints.html
+ *   [3] https://sourceware.org/git/?p=systemtap.git;a=blob;f=includes/sys/sdt.h
+ */
+#ifndef __USDT_H
+#define __USDT_H
+
+/*
+ * Changelog:
+ *
+ * 0.1.0
+ * -----
+ * - Initial release
+ */
+#define USDT_MAJOR_VERSION 0
+#define USDT_MINOR_VERSION 1
+#define USDT_PATCH_VERSION 0
+
+/* C++20 and C23 added __VA_OPT__ as a standard replacement for non-standard `##__VA_ARGS__` extension */
+#if (defined(__STDC_VERSION__) && __STDC_VERSION__ > 201710L) || (defined(__cplusplus) && __cplusplus > 201703L)
+#define __usdt_va_opt 1
+#define __usdt_va_args(...) __VA_OPT__(,) __VA_ARGS__
+#else
+#define __usdt_va_args(...) , ##__VA_ARGS__
+#endif
+
+/*
+ * Trigger USDT with `group`:`name` identifier and pass through `args` as its
+ * arguments. Zero arguments are acceptable as well. No USDT semaphore is
+ * associated with this USDT.
+ *
+ * Such "semaphoreless" USDTs are commonly used when there is no extra data
+ * collection or processing needed to collect and prepare USDT arguments and
+ * they are just available in the surrounding code. USDT() macro will just
+ * record their locations in CPU registers or in memory for tracing tooling to
+ * be able to access them, if necessary.
+ */
+#ifdef __usdt_va_opt
+#define USDT(group, name, ...)							\
+	__usdt_probe(group, name, __usdt_sema_none, 0 __VA_OPT__(,) __VA_ARGS__)
+#else
+#define USDT(group, name, ...)							\
+	__usdt_probe(group, name, __usdt_sema_none, 0, ##__VA_ARGS__)
+#endif
+
+/*
+ * Trigger USDT with `group`:`name` identifier and pass through `args` as its
+ * arguments. Zero arguments are acceptable as well. USDT also get an
+ * implicitly-defined associated USDT semaphore, which will be "activated" by
+ * tracing tooling and can be used to check whether USDT is being actively
+ * observed.
+ *
+ * USDTs with semaphore are commonly used when there is a need to perform
+ * additional data collection and processing to prepare USDT arguments, which
+ * otherwise might not be necessary for the rest of application logic. In such
+ * case, USDT semaphore can be used to avoid unnecessary extra work. If USDT
+ * is not traced (which is presumed to be a common situation), the associated
+ * USDT semaphore is "inactive", and so there is no need to waste resources to
+ * prepare USDT arguments. Use USDT_IS_ACTIVE(group, name) to check whether
+ * USDT is "active".
+ *
+ * N.B. There is an inherent (albeit short) gap between checking whether USDT
+ * is active and triggering corresponding USDT, in which external tracer can
+ * be attached to an USDT and activate USDT semaphore after the activity check.
+ * If such a race occurs, tracers might miss one USDT execution. Tracers are
+ * expected to accommodate such possibility and this is expected to not be
+ * a problem for applications and tracers.
+ *
+ * N.B. Implicit USDT semaphore defined by USDT_WITH_SEMA() is contained
+ * within a single executable or shared library and is not shared outside
+ * them. I.e., if you use USDT_WITH_SEMA() with the same USDT group and name
+ * identifier across executable and shared library, it will work and won't
+ * conflict, per se, but will define independent USDT semaphores, one for each
+ * shared library/executable in which USDT_WITH_SEMA(group, name) is used.
+ * That is, if you attach to this USDT in one shared library (or executable),
+ * then only USDT semaphore within that shared library (or executable) will be
+ * updated by the kernel, while other libraries (or executable) will not see
+ * activated USDT semaphore. In short, it's best to use unique USDT group:name
+ * identifiers across different shared libraries (and, equivalently, between
+ * executable and shared library). This is advanced consideration and is
+ * rarely (if ever) seen in practice, but just to avoid surprises this is
+ * called out here. (Static libraries become a part of final executable, once
+ * linked by linker, so the above considerations don't apply to them.)
+ */
+#ifdef __usdt_va_opt
+#define USDT_WITH_SEMA(group, name, ...)					\
+	__usdt_probe(group, name,						\
+		     __usdt_sema_implicit, __usdt_sema_name(group, name)	\
+		     __VA_OPT__(,) __VA_ARGS__)
+#else
+#define USDT_WITH_SEMA(group, name, ...)					\
+	__usdt_probe(group, name,						\
+		     __usdt_sema_implicit, __usdt_sema_name(group, name),	\
+		     ##__VA_ARGS__)
+#endif
+
+struct usdt_sema { volatile unsigned short active; };
+
+/*
+ * Check if USDT with `group`:`name` identifier is "active" (i.e., whether it
+ * is attached to by external tracing tooling and is actively observed).
+ *
+ * This macro can be used to decide whether any additional and potentially
+ * expensive data collection or processing should be done to pass extra
+ * information into the given USDT. It is assumed that USDT is triggered with
+ * USDT_WITH_SEMA() macro which will implicitly define associated USDT
+ * semaphore. (If one needs more control over USDT semaphore, see
+ * USDT_DEFINE_SEMA() and USDT_WITH_EXPLICIT_SEMA() macros below.)
+ *
+ * N.B. Such checks are necessarily racy and speculative. Between checking
+ * whether USDT is active and triggering the USDT itself, tracer can be
+ * detached with no notification. This race should be extremely rare and worst
+ * case should result in one-time wasted extra data collection and processing.
+ */
+#define USDT_IS_ACTIVE(group, name) ({						\
+	extern struct usdt_sema __usdt_sema_name(group, name)			\
+		__usdt_asm_name(__usdt_sema_name(group, name));			\
+	__usdt_sema_implicit(__usdt_sema_name(group, name));			\
+	__usdt_sema_name(group, name).active > 0;				\
+})
+
+/*
+ * APIs for working with user-defined explicit USDT semaphores.
+ *
+ * This is a less commonly used advanced API for use cases in which user needs
+ * an explicit control over (potentially shared across multiple USDTs) USDT
+ * semaphore instance. This can be used when there is a group of logically
+ * related USDTs that all need extra data collection and processing whenever
+ * any of a family of related USDTs are "activated" (i.e., traced). In such
+ * a case, all such related USDTs will be associated with the same shared USDT
+ * semaphore defined with USDT_DEFINE_SEMA() and the USDTs themselves will be
+ * triggered with USDT_WITH_EXPLICIT_SEMA() macros, taking an explicit extra
+ * USDT semaphore identifier as an extra parameter.
+ */
+
+/**
+ * Underlying C global variable name for user-defined USDT semaphore with
+ * `sema` identifier. Could be useful for debugging, but normally shouldn't be
+ * used explicitly.
+ */
+#define USDT_SEMA(sema) __usdt_sema_##sema
+
+/*
+ * Define storage for user-defined USDT semaphore `sema`.
+ *
+ * Should be used only once in non-header source file to let compiler allocate
+ * space for the semaphore variable. Just like with any other global variable.
+ *
+ * This macro can be used anywhere where global variable declaration is
+ * allowed. Just like with global variable definitions, there should be only
+ * one definition of user-defined USDT semaphore with given `sema` identifier,
+ * otherwise compiler or linker will complain about duplicate variable
+ * definition.
+ *
+ * For C++, it is allowed to use USDT_DEFINE_SEMA() both in global namespace
+ * and inside namespaces (including nested namespaces). Just make sure that
+ * USDT_DECLARE_SEMA() is placed within the namespace where this semaphore is
+ * referenced, or any of its parent namespaces, so the C++ language-level
+ * identifier is visible to the code that needs to reference the semaphore.
+ * At the lowest layer, USDT semaphores have global naming and visibility
+ * (they have a corresponding `__usdt_sema_<name>` symbol, which can be linked
+ * against from C or C++ code, if necessary). To keep it simple, putting
+ * USDT_DECLARE_SEMA() declarations into global namespaces is the simplest
+ * no-brainer solution. All these aspects are irrelevant for plain C, because
+ * C doesn't have namespaces and everything is always in the global namespace.
+ *
+ * N.B. Due to USDT metadata being recorded in non-allocatable ELF note
+ * section, it has limitations when it comes to relocations, which, in
+ * practice, means that it's not possible to correctly share USDT semaphores
+ * between main executable and shared libraries, or even between multiple
+ * shared libraries. USDT semaphore has to be contained to individual shared
+ * library or executable to avoid unpleasant surprises with half-working USDT
+ * semaphores. We enforce this by marking semaphore ELF symbols as having
+ * a hidden visibility. This is quite an advanced use case and consideration
+ * and for most users this should have no consequences whatsoever.
+ */
+#define USDT_DEFINE_SEMA(sema)							\
+	struct usdt_sema __usdt_sema_sec USDT_SEMA(sema)			\
+		__usdt_asm_name(USDT_SEMA(sema))				\
+		__attribute__((visibility("hidden"))) = { 0 }
+
+/*
+ * Declare extern reference to user-defined USDT semaphore `sema`.
+ *
+ * Refers to a variable defined in another compilation unit by
+ * USDT_DEFINE_SEMA() and allows to use the same USDT semaphore across
+ * multiple compilation units (i.e., .c and .cpp files).
+ *
+ * See USDT_DEFINE_SEMA() notes above for C++ language usage peculiarities.
+ */
+#define USDT_DECLARE_SEMA(sema)							\
+	extern struct usdt_sema USDT_SEMA(sema) __usdt_asm_name(USDT_SEMA(sema))
+
+/*
+ * Check if user-defined USDT semaphore `sema` is "active" (i.e., whether it
+ * is attached to by external tracing tooling and is actively observed).
+ *
+ * This macro can be used to decide whether any additional and potentially
+ * expensive data collection or processing should be done to pass extra
+ * information into USDT(s) associated with USDT semaphore `sema`.
+ *
+ * N.B. Such checks are necessarily racy. Between checking the state of USDT
+ * semaphore and triggering associated USDT(s), the active tracer might attach
+ * or detach. This race should be extremely rare and worst case should result
+ * in one-time missed USDT event or wasted extra data collection and
+ * processing. USDT-using tracers should be written with this in mind and is
+ * not a concern of the application defining USDTs with associated semaphore.
+ */
+#define USDT_SEMA_IS_ACTIVE(sema) (USDT_SEMA(sema).active > 0)
+
+/*
+ * Invoke USDT specified by `group` and `name` identifiers and associate
+ * explicitly user-defined semaphore `sema` with it. Pass through `args` as
+ * USDT arguments. `args` are optional and zero arguments are acceptable.
+ *
+ * Semaphore is defined with the help of USDT_DEFINE_SEMA() macro and can be
+ * checked whether active with USDT_SEMA_IS_ACTIVE().
+ */
+#ifdef __usdt_va_opt
+#define USDT_WITH_EXPLICIT_SEMA(sema, group, name, ...)				\
+	__usdt_probe(group, name, __usdt_sema_explicit, USDT_SEMA(sema), ##__VA_ARGS__)
+#else
+#define USDT_WITH_EXPLICIT_SEMA(sema, group, name, ...)				\
+	__usdt_probe(group, name, __usdt_sema_explicit, USDT_SEMA(sema) __VA_OPT__(,) __VA_ARGS__)
+#endif
+
+/*
+ * Adjustable implementation aspects
+ */
+#ifndef USDT_ARG_CONSTRAINT
+#if defined __powerpc__
+#define USDT_ARG_CONSTRAINT		nZr
+#elif defined __arm__
+#define USDT_ARG_CONSTRAINT		g
+#elif defined __loongarch__
+#define USDT_ARG_CONSTRAINT		nmr
+#else
+#define USDT_ARG_CONSTRAINT		nor
+#endif
+#endif /* USDT_ARG_CONSTRAINT */
+
+#ifndef USDT_NOP
+#if defined(__ia64__) || defined(__s390__) || defined(__s390x__)
+#define USDT_NOP			nop 0
+#else
+#define USDT_NOP			nop
+#endif
+#endif /* USDT_NOP */
+
+/*
+ * Implementation details
+ */
+/* USDT name for implicitly-defined USDT semaphore, derived from group:name */
+#define __usdt_sema_name(group, name)	__usdt_sema_##group##__##name
+/* ELF section into which USDT semaphores are put */
+#define __usdt_sema_sec			__attribute__((section(".probes")))
+
+#define __usdt_concat(a, b)		a ## b
+#define __usdt_apply(fn, n)		__usdt_concat(fn, n)
+
+#ifndef __usdt_nth
+#define __usdt_nth(_, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, N, ...) N
+#endif
+
+#ifndef __usdt_narg
+#ifdef __usdt_va_opt
+#define __usdt_narg(...) __usdt_nth(_ __VA_OPT__(,) __VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+#else
+#define __usdt_narg(...) __usdt_nth(_, ##__VA_ARGS__, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+#endif
+#endif /* __usdt_narg */
+
+#define __usdt_hash			#
+#define __usdt_str_(x)			#x
+#define __usdt_str(x)			__usdt_str_(x)
+
+#ifndef __usdt_asm_name
+#define __usdt_asm_name(name)		__asm__(__usdt_str(name))
+#endif
+
+#define __usdt_asm0()		"\n"
+#define __usdt_asm1(x)		__usdt_str(x) "\n"
+#define __usdt_asm2(x, ...)	__usdt_str(x) "," __usdt_asm1(__VA_ARGS__)
+#define __usdt_asm3(x, ...)	__usdt_str(x) "," __usdt_asm2(__VA_ARGS__)
+#define __usdt_asm4(x, ...)	__usdt_str(x) "," __usdt_asm3(__VA_ARGS__)
+#define __usdt_asm5(x, ...)	__usdt_str(x) "," __usdt_asm4(__VA_ARGS__)
+#define __usdt_asm6(x, ...)	__usdt_str(x) "," __usdt_asm5(__VA_ARGS__)
+#define __usdt_asm7(x, ...)	__usdt_str(x) "," __usdt_asm6(__VA_ARGS__)
+#define __usdt_asm8(x, ...)	__usdt_str(x) "," __usdt_asm7(__VA_ARGS__)
+#define __usdt_asm9(x, ...)	__usdt_str(x) "," __usdt_asm8(__VA_ARGS__)
+#define __usdt_asm10(x, ...)	__usdt_str(x) "," __usdt_asm9(__VA_ARGS__)
+#define __usdt_asm11(x, ...)	__usdt_str(x) "," __usdt_asm10(__VA_ARGS__)
+#define __usdt_asm12(x, ...)	__usdt_str(x) "," __usdt_asm11(__VA_ARGS__)
+#define __usdt_asm(...)		__usdt_apply(__usdt_asm, __usdt_narg(__VA_ARGS__))(__VA_ARGS__)
+
+#ifdef __LP64__
+#define __usdt_asm_addr		.8byte
+#else
+#define __usdt_asm_addr		.4byte
+#endif
+
+#define __usdt_asm_strz_(x)	__usdt_asm1(.asciz #x)
+#define __usdt_asm_strz(x)	__usdt_asm_strz_(x)
+#define __usdt_asm_str_(x)	__usdt_asm1(.ascii #x)
+#define __usdt_asm_str(x)	__usdt_asm_str_(x)
+
+/* "semaphoreless" USDT case */
+#ifndef __usdt_sema_none
+#define __usdt_sema_none(sema)
+#endif
+
+/* implicitly defined __usdt_sema__group__name semaphore (using weak symbols) */
+#ifndef __usdt_sema_implicit
+#define __usdt_sema_implicit(sema)								\
+	__asm__ __volatile__ (									\
+	__usdt_asm1(.ifndef sema)								\
+	__usdt_asm3(		.pushsection .probes, "aw", "progbits")				\
+	__usdt_asm1(		.weak sema)							\
+	__usdt_asm1(		.hidden sema)							\
+	__usdt_asm1(		.align 2)							\
+	__usdt_asm1(sema:)									\
+	__usdt_asm1(		.zero 2)							\
+	__usdt_asm2(		.type sema, @object)						\
+	__usdt_asm2(		.size sema, 2)							\
+	__usdt_asm1(		.popsection)							\
+	__usdt_asm1(.endif)									\
+	);
+#endif
+
+/* externally defined semaphore using USDT_DEFINE_SEMA() and passed explicitly by user */
+#ifndef __usdt_sema_explicit
+#define __usdt_sema_explicit(sema)								\
+	__asm__ __volatile__ ("" :: "m" (sema));
+#endif
+
+/* main USDT definition (nop and .note.stapsdt metadata) */
+#define __usdt_probe(group, name, sema_def, sema, ...) do {					\
+	sema_def(sema)										\
+	__asm__ __volatile__ (									\
+	__usdt_asm( 990:	USDT_NOP)							\
+	__usdt_asm3(		.pushsection .note.stapsdt, "", "note")				\
+	__usdt_asm1(		.balign 4)							\
+	__usdt_asm3(		.4byte 992f-991f,994f-993f,3)					\
+	__usdt_asm1(991:	.asciz "stapsdt")						\
+	__usdt_asm1(992:	.balign 4)							\
+	__usdt_asm1(993:	__usdt_asm_addr 990b)						\
+	__usdt_asm1(		__usdt_asm_addr _.stapsdt.base)					\
+	__usdt_asm1(		__usdt_asm_addr sema)						\
+	__usdt_asm_strz(group)									\
+	__usdt_asm_strz(name)									\
+	__usdt_asm_args(__VA_ARGS__)								\
+	__usdt_asm1(		.ascii "\0")							\
+	__usdt_asm1(994:	.balign 4)							\
+	__usdt_asm1(		.popsection)							\
+	__usdt_asm1(.ifndef _.stapsdt.base)							\
+	__usdt_asm5(		.pushsection .stapsdt.base,"aG","progbits",.stapsdt.base,comdat)\
+	__usdt_asm1(		.weak _.stapsdt.base)						\
+	__usdt_asm1(		.hidden _.stapsdt.base)						\
+	__usdt_asm1(_.stapsdt.base:)								\
+	__usdt_asm1(		.space 1)							\
+	__usdt_asm2(		.size _.stapsdt.base, 1)					\
+	__usdt_asm1(		.popsection)							\
+	__usdt_asm1(.endif)									\
+	:: __usdt_asm_ops(__VA_ARGS__)								\
+	);											\
+} while (0)
+
+/*
+ * NB: gdb PR24541 highlighted an unspecified corner of the sdt.h
+ * operand note format.
+ *
+ * The named register may be a longer or shorter (!) alias for the
+ * storage where the value in question is found. For example, on
+ * i386, 64-bit value may be put in register pairs, and a register
+ * name stored would identify just one of them. Previously, gcc was
+ * asked to emit the %w[id] (16-bit alias of some registers holding
+ * operands), even when a wider 32-bit value was used.
+ *
+ * Bottom line: the byte-width given before the @ sign governs. If
+ * there is a mismatch between that width and that of the named
+ * register, then a sys/sdt.h note consumer may need to employ
+ * architecture-specific heuristics to figure out where the compiler
+ * has actually put the complete value.
+ */
+#if defined(__powerpc__) || defined(__powerpc64__)
+#define __usdt_argref(id)	%I[id]%[id]
+#elif defined(__i386__)
+#define __usdt_argref(id)	%k[id]		/* gcc.gnu.org/PR80115 sourceware.org/PR24541 */
+#else
+#define __usdt_argref(id)	%[id]
+#endif
+
+#define __usdt_asm_arg(n)	__usdt_asm_str(%c[__usdt_asz##n])				\
+				__usdt_asm1(.ascii "@")						\
+				__usdt_asm_str(__usdt_argref(__usdt_aval##n))
+
+#define __usdt_asm_args0	/* no arguments */
+#define __usdt_asm_args1	__usdt_asm_arg(1)
+#define __usdt_asm_args2	__usdt_asm_args1 __usdt_asm1(.ascii " ") __usdt_asm_arg(2)
+#define __usdt_asm_args3	__usdt_asm_args2 __usdt_asm1(.ascii " ") __usdt_asm_arg(3)
+#define __usdt_asm_args4	__usdt_asm_args3 __usdt_asm1(.ascii " ") __usdt_asm_arg(4)
+#define __usdt_asm_args5	__usdt_asm_args4 __usdt_asm1(.ascii " ") __usdt_asm_arg(5)
+#define __usdt_asm_args6	__usdt_asm_args5 __usdt_asm1(.ascii " ") __usdt_asm_arg(6)
+#define __usdt_asm_args7	__usdt_asm_args6 __usdt_asm1(.ascii " ") __usdt_asm_arg(7)
+#define __usdt_asm_args8	__usdt_asm_args7 __usdt_asm1(.ascii " ") __usdt_asm_arg(8)
+#define __usdt_asm_args9	__usdt_asm_args8 __usdt_asm1(.ascii " ") __usdt_asm_arg(9)
+#define __usdt_asm_args10	__usdt_asm_args9 __usdt_asm1(.ascii " ") __usdt_asm_arg(10)
+#define __usdt_asm_args11	__usdt_asm_args10 __usdt_asm1(.ascii " ") __usdt_asm_arg(11)
+#define __usdt_asm_args12	__usdt_asm_args11 __usdt_asm1(.ascii " ") __usdt_asm_arg(12)
+#define __usdt_asm_args(...)	__usdt_apply(__usdt_asm_args, __usdt_narg(__VA_ARGS__))
+
+#define __usdt_is_arr(x)	(__builtin_classify_type(x) == 14 || __builtin_classify_type(x) == 5)
+#define __usdt_arg_size(x)	(__usdt_is_arr(x) ? sizeof(void *) : sizeof(x))
+
+/*
+ * We can't use __builtin_choose_expr() in C++, so fall back to table-based
+ * signedness determination for known types, utilizing templates magic.
+ */
+#ifdef __cplusplus
+
+#define __usdt_is_signed(x)	(!__usdt_is_arr(x) && __usdt_t<__typeof(x)>::is_signed)
+
+#include <cstddef>
+
+template<typename T> struct __usdt_t { static const bool is_signed = false; };
+template<typename A> struct __usdt_t<A[]> : public __usdt_t<A *> {};
+template<typename A, size_t N> struct __usdt_t<A[N]> : public __usdt_t<A *> {};
+
+#define __usdt_def_signed(T)									\
+template<> struct __usdt_t<T>		     { static const bool is_signed = true; };		\
+template<> struct __usdt_t<const T>	     { static const bool is_signed = true; };		\
+template<> struct __usdt_t<volatile T>	     { static const bool is_signed = true; };		\
+template<> struct __usdt_t<const volatile T> { static const bool is_signed = true; }
+#define __usdt_maybe_signed(T)									\
+template<> struct __usdt_t<T>		     { static const bool is_signed = (T)-1 < (T)1; };	\
+template<> struct __usdt_t<const T>	     { static const bool is_signed = (T)-1 < (T)1; };	\
+template<> struct __usdt_t<volatile T>	     { static const bool is_signed = (T)-1 < (T)1; };	\
+template<> struct __usdt_t<const volatile T> { static const bool is_signed = (T)-1 < (T)1; }
+
+__usdt_def_signed(signed char);
+__usdt_def_signed(short);
+__usdt_def_signed(int);
+__usdt_def_signed(long);
+__usdt_def_signed(long long);
+__usdt_maybe_signed(char);
+__usdt_maybe_signed(wchar_t);
+
+#else /* !__cplusplus */
+
+#define __usdt_is_inttype(x)	(__builtin_classify_type(x) >= 1 && __builtin_classify_type(x) <= 4)
+#define __usdt_inttype(x)	__typeof(__builtin_choose_expr(__usdt_is_inttype(x), (x), 0U))
+#define __usdt_is_signed(x)	((__usdt_inttype(x))-1 < (__usdt_inttype(x))1)
+
+#endif /* __cplusplus */
+
+#define __usdt_asm_op(n, x)									\
+	[__usdt_asz##n] "n" ((__usdt_is_signed(x) ? (int)-1 : 1) * (int)__usdt_arg_size(x)),	\
+	[__usdt_aval##n] __usdt_str(USDT_ARG_CONSTRAINT)(x)
+
+#define __usdt_asm_ops0()				[__usdt_dummy] "g" (0)
+#define __usdt_asm_ops1(x)				__usdt_asm_op(1, x)
+#define __usdt_asm_ops2(a,x)				__usdt_asm_ops1(a), __usdt_asm_op(2, x)
+#define __usdt_asm_ops3(a,b,x)				__usdt_asm_ops2(a,b), __usdt_asm_op(3, x)
+#define __usdt_asm_ops4(a,b,c,x)			__usdt_asm_ops3(a,b,c), __usdt_asm_op(4, x)
+#define __usdt_asm_ops5(a,b,c,d,x)			__usdt_asm_ops4(a,b,c,d), __usdt_asm_op(5, x)
+#define __usdt_asm_ops6(a,b,c,d,e,x)			__usdt_asm_ops5(a,b,c,d,e), __usdt_asm_op(6, x)
+#define __usdt_asm_ops7(a,b,c,d,e,f,x)			__usdt_asm_ops6(a,b,c,d,e,f), __usdt_asm_op(7, x)
+#define __usdt_asm_ops8(a,b,c,d,e,f,g,x)		__usdt_asm_ops7(a,b,c,d,e,f,g), __usdt_asm_op(8, x)
+#define __usdt_asm_ops9(a,b,c,d,e,f,g,h,x)		__usdt_asm_ops8(a,b,c,d,e,f,g,h), __usdt_asm_op(9, x)
+#define __usdt_asm_ops10(a,b,c,d,e,f,g,h,i,x)		__usdt_asm_ops9(a,b,c,d,e,f,g,h,i), __usdt_asm_op(10, x)
+#define __usdt_asm_ops11(a,b,c,d,e,f,g,h,i,j,x)		__usdt_asm_ops10(a,b,c,d,e,f,g,h,i,j), __usdt_asm_op(11, x)
+#define __usdt_asm_ops12(a,b,c,d,e,f,g,h,i,j,k,x)	__usdt_asm_ops11(a,b,c,d,e,f,g,h,i,j,k), __usdt_asm_op(12, x)
+#define __usdt_asm_ops(...)				__usdt_apply(__usdt_asm_ops, __usdt_narg(__VA_ARGS__))(__VA_ARGS__)
+
+#endif /* __USDT_H */
diff --git a/tools/testing/selftests/bpf/verifier/and.c b/tools/testing/selftests/bpf/verifier/and.c
deleted file mode 100644
index 7d7ebee5cc7a..000000000000
--- a/tools/testing/selftests/bpf/verifier/and.c
+++ /dev/null
@@ -1,68 +0,0 @@
-{
-	"invalid and of negative number",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, -4),
-	BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, offsetof(struct test_val, foo)),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "R0 max value is outside of the allowed memory range",
-	.result = REJECT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"invalid range check",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 12),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_9, 1),
-	BPF_ALU32_IMM(BPF_MOD, BPF_REG_1, 2),
-	BPF_ALU32_IMM(BPF_ADD, BPF_REG_1, 1),
-	BPF_ALU32_REG(BPF_AND, BPF_REG_9, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_ADD, BPF_REG_9, 1),
-	BPF_ALU32_IMM(BPF_RSH, BPF_REG_9, 1),
-	BPF_MOV32_IMM(BPF_REG_3, 1),
-	BPF_ALU32_REG(BPF_SUB, BPF_REG_3, BPF_REG_9),
-	BPF_ALU32_IMM(BPF_MUL, BPF_REG_3, 0x10000000),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_3),
-	BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_3, 0),
-	BPF_MOV64_REG(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "R0 max value is outside of the allowed memory range",
-	.result = REJECT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"check known subreg with unknown reg",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 32),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xFFFF1234),
-	/* Upper bits are unknown but AND above masks out 1 zero'ing lower bits */
-	BPF_JMP32_IMM(BPF_JLT, BPF_REG_0, 1, 1),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, 512),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R1 !read_ok",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-	.retval = 0
-},
diff --git a/tools/testing/selftests/bpf/verifier/array_access.c b/tools/testing/selftests/bpf/verifier/array_access.c
deleted file mode 100644
index 1b138cd2b187..000000000000
--- a/tools/testing/selftests/bpf/verifier/array_access.c
+++ /dev/null
@@ -1,379 +0,0 @@
-{
-	"valid map access into an array with a constant",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, offsetof(struct test_val, foo)),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr_unpriv = "R0 leaks addr",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-},
-{
-	"valid map access into an array with a register",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_IMM(BPF_REG_1, 4),
-	BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, offsetof(struct test_val, foo)),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr_unpriv = "R0 leaks addr",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"valid map access into an array with a variable",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JGE, BPF_REG_1, MAX_ENTRIES, 3),
-	BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, offsetof(struct test_val, foo)),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr_unpriv = "R0 leaks addr",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"valid map access into an array with a signed variable",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_JMP32_IMM(BPF_JSGT, BPF_REG_1, 0xffffffff, 1),
-	BPF_MOV32_IMM(BPF_REG_1, 0),
-	BPF_MOV32_IMM(BPF_REG_2, MAX_ENTRIES),
-	BPF_JMP_REG(BPF_JSGT, BPF_REG_2, BPF_REG_1, 1),
-	BPF_MOV32_IMM(BPF_REG_1, 0),
-	BPF_ALU32_IMM(BPF_LSH, BPF_REG_1, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, offsetof(struct test_val, foo)),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr_unpriv = "R0 leaks addr",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"invalid map access into an array with a constant",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, (MAX_ENTRIES + 1) << 2,
-		   offsetof(struct test_val, foo)),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "invalid access to map value, value_size=48 off=48 size=8",
-	.result = REJECT,
-},
-{
-	"invalid map access into an array with a register",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_IMM(BPF_REG_1, MAX_ENTRIES + 1),
-	BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, offsetof(struct test_val, foo)),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "R0 min value is outside of the allowed memory range",
-	.result = REJECT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"invalid map access into an array with a variable",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, offsetof(struct test_val, foo)),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "R0 unbounded memory access, make sure to bounds check any such access",
-	.result = REJECT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"invalid map access into an array with no floor check",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV32_IMM(BPF_REG_2, MAX_ENTRIES),
-	BPF_JMP_REG(BPF_JSGT, BPF_REG_2, BPF_REG_1, 1),
-	BPF_MOV32_IMM(BPF_REG_1, 0),
-	BPF_ALU32_IMM(BPF_LSH, BPF_REG_1, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, offsetof(struct test_val, foo)),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr_unpriv = "R0 leaks addr",
-	.errstr = "R0 unbounded memory access",
-	.result_unpriv = REJECT,
-	.result = REJECT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"invalid map access into an array with a invalid max check",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV32_IMM(BPF_REG_2, MAX_ENTRIES + 1),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 1),
-	BPF_MOV32_IMM(BPF_REG_1, 0),
-	BPF_ALU32_IMM(BPF_LSH, BPF_REG_1, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, offsetof(struct test_val, foo)),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr_unpriv = "R0 leaks addr",
-	.errstr = "invalid access to map value, value_size=48 off=44 size=8",
-	.result_unpriv = REJECT,
-	.result = REJECT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"invalid map access into an array with a invalid max check",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10),
-	BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_8),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0,
-		    offsetof(struct test_val, foo)),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3, 11 },
-	.errstr = "R0 pointer += pointer",
-	.result = REJECT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"valid read map access into a read-only array 1",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_ro = { 3 },
-	.result = ACCEPT,
-	.retval = 28,
-},
-{
-	"valid read map access into a read-only array 2",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-		     BPF_FUNC_csum_diff),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xffff),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.fixup_map_array_ro = { 3 },
-	.result = ACCEPT,
-	.retval = 65507,
-},
-{
-	"invalid write map access into a read-only array 1",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_ro = { 3 },
-	.result = REJECT,
-	.errstr = "write into map forbidden",
-},
-{
-	"invalid write map access into a read-only array 2",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_4, 8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-		     BPF_FUNC_skb_load_bytes),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.fixup_map_array_ro = { 4 },
-	.result = REJECT,
-	.errstr = "write into map forbidden",
-},
-{
-	"valid write map access into a write-only array 1",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_wo = { 3 },
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"valid write map access into a write-only array 2",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_4, 8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-		     BPF_FUNC_skb_load_bytes),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.fixup_map_array_wo = { 4 },
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"invalid read map access into a write-only array 1",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_wo = { 3 },
-	.result = REJECT,
-	.errstr = "read from map forbidden",
-},
-{
-	"invalid read map access into a write-only array 2",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-		     BPF_FUNC_csum_diff),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.fixup_map_array_wo = { 3 },
-	.result = REJECT,
-	.errstr = "read from map forbidden",
-},
diff --git a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c
index b39665f33524..9a7b1106fda8 100644
--- a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c
+++ b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c
@@ -84,17 +84,6 @@
 	.errstr = "!read_ok",
 },
 {
-	"Can't use cmpxchg on uninit memory",
-	.insns = {
-		BPF_MOV64_IMM(BPF_REG_0, 3),
-		BPF_MOV64_IMM(BPF_REG_2, 4),
-		BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, BPF_REG_10, BPF_REG_2, -8),
-		BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid read from stack",
-},
-{
 	"BPF_W cmpxchg should zero top 32 bits",
 	.insns = {
 		/* r0 = U64_MAX; */
@@ -242,4 +231,5 @@
 	.result = REJECT,
 	.errstr = "R0 invalid mem access",
 	.errstr_unpriv = "R10 partial copy of pointer",
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
diff --git a/tools/testing/selftests/bpf/verifier/basic_instr.c b/tools/testing/selftests/bpf/verifier/basic_instr.c
index 071dbc889e8c..bd928a72ad73 100644
--- a/tools/testing/selftests/bpf/verifier/basic_instr.c
+++ b/tools/testing/selftests/bpf/verifier/basic_instr.c
@@ -176,11 +176,11 @@
 	.retval = 1,
 },
 {
-	"invalid 64-bit BPF_END",
+	"invalid 64-bit BPF_END with BPF_TO_BE",
 	.insns = {
 	BPF_MOV32_IMM(BPF_REG_0, 0),
 	{
-		.code  = BPF_ALU64 | BPF_END | BPF_TO_LE,
+		.code  = BPF_ALU64 | BPF_END | BPF_TO_BE,
 		.dst_reg = BPF_REG_0,
 		.src_reg = 0,
 		.off   = 0,
@@ -188,7 +188,7 @@
 	},
 	BPF_EXIT_INSN(),
 	},
-	.errstr = "unknown opcode d7",
+	.errstr = "unknown opcode df",
 	.result = REJECT,
 },
 {
diff --git a/tools/testing/selftests/bpf/verifier/basic_stack.c b/tools/testing/selftests/bpf/verifier/basic_stack.c
deleted file mode 100644
index f995777dddb3..000000000000
--- a/tools/testing/selftests/bpf/verifier/basic_stack.c
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-	"stack out of bounds",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, 8, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "invalid write to stack",
-	.result = REJECT,
-},
-{
-	"uninitialized stack1",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 2 },
-	.errstr = "invalid indirect read from stack",
-	.result = REJECT,
-},
-{
-	"uninitialized stack2",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, -8),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "invalid read from stack",
-	.result = REJECT,
-},
-{
-	"invalid fp arithmetic",
-	/* If this gets ever changed, make sure JITs can deal with it. */
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 8),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 subtraction from stack pointer",
-	.result = REJECT,
-},
-{
-	"non-invalid fp arithmetic",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-},
-{
-	"misaligned read from stack",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, -4),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "misaligned stack access",
-	.result = REJECT,
-},
diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c
deleted file mode 100644
index 33125d5f6772..000000000000
--- a/tools/testing/selftests/bpf/verifier/bounds.c
+++ /dev/null
@@ -1,755 +0,0 @@
-{
-	"subtraction bounds (map value) variant 1",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 0xff, 7),
-	BPF_LDX_MEM(BPF_B, BPF_REG_3, BPF_REG_0, 1),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_3, 0xff, 5),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_3),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 56),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "R0 max value is outside of the allowed memory range",
-	.result = REJECT,
-},
-{
-	"subtraction bounds (map value) variant 2",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 0xff, 6),
-	BPF_LDX_MEM(BPF_B, BPF_REG_3, BPF_REG_0, 1),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_3, 0xff, 4),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_3),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
-	.errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
-	.result = REJECT,
-},
-{
-	"check subtraction on pointers for unpriv",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_LD_MAP_FD(BPF_REG_ARG1, 0),
-	BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_FP),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_ARG2, 0, 9),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_REG(BPF_REG_9, BPF_REG_FP),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_9, BPF_REG_0),
-	BPF_LD_MAP_FD(BPF_REG_ARG1, 0),
-	BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_FP),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_ARG2, 0, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_9, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 1, 9 },
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R9 pointer -= pointer prohibited",
-},
-{
-	"bounds check based on zero-extended MOV",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	/* r2 = 0x0000'0000'ffff'ffff */
-	BPF_MOV32_IMM(BPF_REG_2, 0xffffffff),
-	/* r2 = 0 */
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 32),
-	/* no-op */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2),
-	/* access at offset 0 */
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
-	/* exit */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.result = ACCEPT
-},
-{
-	"bounds check based on sign-extended MOV. test1",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	/* r2 = 0xffff'ffff'ffff'ffff */
-	BPF_MOV64_IMM(BPF_REG_2, 0xffffffff),
-	/* r2 = 0xffff'ffff */
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 32),
-	/* r0 = <oob pointer> */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2),
-	/* access to OOB pointer */
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
-	/* exit */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "map_value pointer and 4294967295",
-	.result = REJECT
-},
-{
-	"bounds check based on sign-extended MOV. test2",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	/* r2 = 0xffff'ffff'ffff'ffff */
-	BPF_MOV64_IMM(BPF_REG_2, 0xffffffff),
-	/* r2 = 0xfff'ffff */
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 36),
-	/* r0 = <oob pointer> */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2),
-	/* access to OOB pointer */
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
-	/* exit */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "R0 min value is outside of the allowed memory range",
-	.result = REJECT
-},
-{
-	"bounds check based on reg_off + var_off + insn_off. test1",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, mark)),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_6, 1),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, (1 << 29) - 1),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, (1 << 29) - 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 3),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 4 },
-	.errstr = "value_size=8 off=1073741825",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"bounds check based on reg_off + var_off + insn_off. test2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, mark)),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_6, 1),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, (1 << 30) - 1),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, (1 << 29) - 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 3),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 4 },
-	.errstr = "value 1073741823",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"bounds check after truncation of non-boundary-crossing range",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
-	/* r1 = [0x00, 0xff] */
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_2, 1),
-	/* r2 = 0x10'0000'0000 */
-	BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 36),
-	/* r1 = [0x10'0000'0000, 0x10'0000'00ff] */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2),
-	/* r1 = [0x10'7fff'ffff, 0x10'8000'00fe] */
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x7fffffff),
-	/* r1 = [0x00, 0xff] */
-	BPF_ALU32_IMM(BPF_SUB, BPF_REG_1, 0x7fffffff),
-	/* r1 = 0 */
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8),
-	/* no-op */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	/* access at offset 0 */
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
-	/* exit */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.result = ACCEPT
-},
-{
-	"bounds check after truncation of boundary-crossing range (1)",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
-	/* r1 = [0x00, 0xff] */
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1),
-	/* r1 = [0xffff'ff80, 0x1'0000'007f] */
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1),
-	/* r1 = [0xffff'ff80, 0xffff'ffff] or
-	 *      [0x0000'0000, 0x0000'007f]
-	 */
-	BPF_ALU32_IMM(BPF_ADD, BPF_REG_1, 0),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1),
-	/* r1 = [0x00, 0xff] or
-	 *      [0xffff'ffff'0000'0080, 0xffff'ffff'ffff'ffff]
-	 */
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1),
-	/* error on OOB pointer computation */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	/* exit */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	/* not actually fully unbounded, but the bound is very high */
-	.errstr = "value -4294967168 makes map_value pointer be out of bounds",
-	.result = REJECT,
-},
-{
-	"bounds check after truncation of boundary-crossing range (2)",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
-	/* r1 = [0x00, 0xff] */
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1),
-	/* r1 = [0xffff'ff80, 0x1'0000'007f] */
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1),
-	/* r1 = [0xffff'ff80, 0xffff'ffff] or
-	 *      [0x0000'0000, 0x0000'007f]
-	 * difference to previous test: truncation via MOV32
-	 * instead of ALU32.
-	 */
-	BPF_MOV32_REG(BPF_REG_1, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1),
-	/* r1 = [0x00, 0xff] or
-	 *      [0xffff'ffff'0000'0080, 0xffff'ffff'ffff'ffff]
-	 */
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1),
-	/* error on OOB pointer computation */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	/* exit */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "value -4294967168 makes map_value pointer be out of bounds",
-	.result = REJECT,
-},
-{
-	"bounds check after wrapping 32-bit addition",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
-	/* r1 = 0x7fff'ffff */
-	BPF_MOV64_IMM(BPF_REG_1, 0x7fffffff),
-	/* r1 = 0xffff'fffe */
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x7fffffff),
-	/* r1 = 0 */
-	BPF_ALU32_IMM(BPF_ADD, BPF_REG_1, 2),
-	/* no-op */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	/* access at offset 0 */
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
-	/* exit */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.result = ACCEPT
-},
-{
-	"bounds check after shift with oversized count operand",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_MOV64_IMM(BPF_REG_2, 32),
-	BPF_MOV64_IMM(BPF_REG_1, 1),
-	/* r1 = (u32)1 << (u32)32 = ? */
-	BPF_ALU32_REG(BPF_LSH, BPF_REG_1, BPF_REG_2),
-	/* r1 = [0x0000, 0xffff] */
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xffff),
-	/* computes unknown pointer, potentially OOB */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	/* potentially OOB access */
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
-	/* exit */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "R0 max value is outside of the allowed memory range",
-	.result = REJECT
-},
-{
-	"bounds check after right shift of maybe-negative number",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	/* r1 = [0x00, 0xff] */
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	/* r1 = [-0x01, 0xfe] */
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 1),
-	/* r1 = 0 or 0xff'ffff'ffff'ffff */
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8),
-	/* r1 = 0 or 0xffff'ffff'ffff */
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8),
-	/* computes unknown pointer, potentially OOB */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	/* potentially OOB access */
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
-	/* exit */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "R0 unbounded memory access",
-	.result = REJECT
-},
-{
-	"bounds check after 32-bit right shift with 64-bit input",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	/* r1 = 2 */
-	BPF_MOV64_IMM(BPF_REG_1, 2),
-	/* r1 = 1<<32 */
-	BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 31),
-	/* r1 = 0 (NOT 2!) */
-	BPF_ALU32_IMM(BPF_RSH, BPF_REG_1, 31),
-	/* r1 = 0xffff'fffe (NOT 0!) */
-	BPF_ALU32_IMM(BPF_SUB, BPF_REG_1, 2),
-	/* error on computing OOB pointer */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	/* exit */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "math between map_value pointer and 4294967294 is not allowed",
-	.result = REJECT,
-},
-{
-	"bounds check map access with off+size signed 32bit overflow. test1",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0x7ffffffe),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
-	BPF_JMP_A(0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "map_value pointer and 2147483646",
-	.result = REJECT
-},
-{
-	"bounds check map access with off+size signed 32bit overflow. test2",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0x1fffffff),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0x1fffffff),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0x1fffffff),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
-	BPF_JMP_A(0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "pointer offset 1073741822",
-	.errstr_unpriv = "R0 pointer arithmetic of map value goes out of range",
-	.result = REJECT
-},
-{
-	"bounds check map access with off+size signed 32bit overflow. test3",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 0x1fffffff),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 0x1fffffff),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 2),
-	BPF_JMP_A(0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "pointer offset -1073741822",
-	.errstr_unpriv = "R0 pointer arithmetic of map value goes out of range",
-	.result = REJECT
-},
-{
-	"bounds check map access with off+size signed 32bit overflow. test4",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_1, 1000000),
-	BPF_ALU64_IMM(BPF_MUL, BPF_REG_1, 1000000),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 2),
-	BPF_JMP_A(0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "map_value pointer and 1000000000000",
-	.result = REJECT
-},
-{
-	"bounds check mixed 32bit and 64bit arithmetic. test1",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_1, -1),
-	BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 32),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
-	/* r1 = 0xffffFFFF00000001 */
-	BPF_JMP32_IMM(BPF_JGT, BPF_REG_1, 1, 3),
-	/* check ALU64 op keeps 32bit bounds */
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
-	BPF_JMP32_IMM(BPF_JGT, BPF_REG_1, 2, 1),
-	BPF_JMP_A(1),
-	/* invalid ldx if bounds are lost above */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, -1),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R0 invalid mem access 'scalar'",
-	.result_unpriv = REJECT,
-	.result = ACCEPT
-},
-{
-	"bounds check mixed 32bit and 64bit arithmetic. test2",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_1, -1),
-	BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 32),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
-	/* r1 = 0xffffFFFF00000001 */
-	BPF_MOV64_IMM(BPF_REG_2, 3),
-	/* r1 = 0x2 */
-	BPF_ALU32_IMM(BPF_ADD, BPF_REG_1, 1),
-	/* check ALU32 op zero extends 64bit bounds */
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 1),
-	BPF_JMP_A(1),
-	/* invalid ldx if bounds are lost above */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, -1),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R0 invalid mem access 'scalar'",
-	.result_unpriv = REJECT,
-	.result = ACCEPT
-},
-{
-	"assigning 32bit bounds to 64bit for wA = 0, wB = wA",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_MOV32_IMM(BPF_REG_9, 0),
-	BPF_MOV32_REG(BPF_REG_2, BPF_REG_9),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_7),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_8, 1),
-	BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_6, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"bounds check for reg = 0, reg xor 1",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_1, 0),
-	BPF_ALU64_IMM(BPF_XOR, BPF_REG_1, 1),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R0 min value is outside of the allowed memory range",
-	.result_unpriv = REJECT,
-	.fixup_map_hash_8b = { 3 },
-	.result = ACCEPT,
-},
-{
-	"bounds check for reg32 = 0, reg32 xor 1",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV32_IMM(BPF_REG_1, 0),
-	BPF_ALU32_IMM(BPF_XOR, BPF_REG_1, 1),
-	BPF_JMP32_IMM(BPF_JNE, BPF_REG_1, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R0 min value is outside of the allowed memory range",
-	.result_unpriv = REJECT,
-	.fixup_map_hash_8b = { 3 },
-	.result = ACCEPT,
-},
-{
-	"bounds check for reg = 2, reg xor 3",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_1, 2),
-	BPF_ALU64_IMM(BPF_XOR, BPF_REG_1, 3),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R0 min value is outside of the allowed memory range",
-	.result_unpriv = REJECT,
-	.fixup_map_hash_8b = { 3 },
-	.result = ACCEPT,
-},
-{
-	"bounds check for reg = any, reg xor 3",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_XOR, BPF_REG_1, 3),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.result = REJECT,
-	.errstr = "invalid access to map value",
-	.errstr_unpriv = "invalid access to map value",
-},
-{
-	"bounds check for reg32 = any, reg32 xor 3",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
-	BPF_ALU32_IMM(BPF_XOR, BPF_REG_1, 3),
-	BPF_JMP32_IMM(BPF_JNE, BPF_REG_1, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.result = REJECT,
-	.errstr = "invalid access to map value",
-	.errstr_unpriv = "invalid access to map value",
-},
-{
-	"bounds check for reg > 0, reg xor 3",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JLE, BPF_REG_1, 0, 3),
-	BPF_ALU64_IMM(BPF_XOR, BPF_REG_1, 3),
-	BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R0 min value is outside of the allowed memory range",
-	.result_unpriv = REJECT,
-	.fixup_map_hash_8b = { 3 },
-	.result = ACCEPT,
-},
-{
-	"bounds check for reg32 > 0, reg32 xor 3",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
-	BPF_JMP32_IMM(BPF_JLE, BPF_REG_1, 0, 3),
-	BPF_ALU32_IMM(BPF_XOR, BPF_REG_1, 3),
-	BPF_JMP32_IMM(BPF_JGE, BPF_REG_1, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R0 min value is outside of the allowed memory range",
-	.result_unpriv = REJECT,
-	.fixup_map_hash_8b = { 3 },
-	.result = ACCEPT,
-},
-{
-	"bounds checks after 32-bit truncation. test 1",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	/* This used to reduce the max bound to 0x7fffffff */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 0x7fffffff, 1),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr_unpriv = "R0 leaks addr",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-},
-{
-	"bounds checks after 32-bit truncation. test 2",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JSLT, BPF_REG_1, 1, 1),
-	BPF_JMP32_IMM(BPF_JSLT, BPF_REG_1, 0, 1),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr_unpriv = "R0 leaks addr",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-},
diff --git a/tools/testing/selftests/bpf/verifier/bounds_deduction.c b/tools/testing/selftests/bpf/verifier/bounds_deduction.c
deleted file mode 100644
index 3931c481e30c..000000000000
--- a/tools/testing/selftests/bpf/verifier/bounds_deduction.c
+++ /dev/null
@@ -1,136 +0,0 @@
-{
-	"check deducing bounds from const, 1",
-	.insns = {
-		BPF_MOV64_IMM(BPF_REG_0, 1),
-		BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 1, 0),
-		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
-		BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
-	.errstr = "R0 tried to subtract pointer from scalar",
-	.result = REJECT,
-},
-{
-	"check deducing bounds from const, 2",
-	.insns = {
-		BPF_MOV64_IMM(BPF_REG_0, 1),
-		BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 1, 1),
-		BPF_EXIT_INSN(),
-		BPF_JMP_IMM(BPF_JSLE, BPF_REG_0, 1, 1),
-		BPF_EXIT_INSN(),
-		BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
-		BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"check deducing bounds from const, 3",
-	.insns = {
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_JMP_IMM(BPF_JSLE, BPF_REG_0, 0, 0),
-		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
-		BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
-	.errstr = "R0 tried to subtract pointer from scalar",
-	.result = REJECT,
-},
-{
-	"check deducing bounds from const, 4",
-	.insns = {
-		BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_JMP_IMM(BPF_JSLE, BPF_REG_0, 0, 1),
-		BPF_EXIT_INSN(),
-		BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 1),
-		BPF_EXIT_INSN(),
-		BPF_ALU64_REG(BPF_SUB, BPF_REG_6, BPF_REG_0),
-		BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R6 has pointer with unsupported alu operation",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-},
-{
-	"check deducing bounds from const, 5",
-	.insns = {
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 1, 1),
-		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
-		BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
-	.errstr = "R0 tried to subtract pointer from scalar",
-	.result = REJECT,
-},
-{
-	"check deducing bounds from const, 6",
-	.insns = {
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 1),
-		BPF_EXIT_INSN(),
-		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
-		BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
-	.errstr = "R0 tried to subtract pointer from scalar",
-	.result = REJECT,
-},
-{
-	"check deducing bounds from const, 7",
-	.insns = {
-		BPF_MOV64_IMM(BPF_REG_0, ~0),
-		BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 0),
-		BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
-		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-			    offsetof(struct __sk_buff, mark)),
-		BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
-	.errstr = "dereference of modified ctx ptr",
-	.result = REJECT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"check deducing bounds from const, 8",
-	.insns = {
-		BPF_MOV64_IMM(BPF_REG_0, ~0),
-		BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 1),
-		BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
-		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-			    offsetof(struct __sk_buff, mark)),
-		BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
-	.errstr = "negative offset ctx ptr R1 off=-1 disallowed",
-	.result = REJECT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"check deducing bounds from const, 9",
-	.insns = {
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 0),
-		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
-		BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
-	.errstr = "R0 tried to subtract pointer from scalar",
-	.result = REJECT,
-},
-{
-	"check deducing bounds from const, 10",
-	.insns = {
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_JMP_IMM(BPF_JSLE, BPF_REG_0, 0, 0),
-		/* Marks reg as unknown. */
-		BPF_ALU64_IMM(BPF_NEG, BPF_REG_0, 0),
-		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
-		BPF_EXIT_INSN(),
-	},
-	.errstr = "math between ctx pointer and register with unbounded min value is not allowed",
-	.result = REJECT,
-},
diff --git a/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c b/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c
deleted file mode 100644
index c2aa6f26738b..000000000000
--- a/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c
+++ /dev/null
@@ -1,393 +0,0 @@
-{
-	"bounds checks mixing signed and unsigned, positive bounds",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
-	BPF_MOV64_IMM(BPF_REG_2, 2),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 3),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 4, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "unbounded min value",
-	.result = REJECT,
-},
-{
-	"bounds checks mixing signed and unsigned",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
-	BPF_MOV64_IMM(BPF_REG_2, -1),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 3),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "unbounded min value",
-	.result = REJECT,
-},
-{
-	"bounds checks mixing signed and unsigned, variant 2",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
-	BPF_MOV64_IMM(BPF_REG_2, -1),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 5),
-	BPF_MOV64_IMM(BPF_REG_8, 0),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_1),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_8, 1, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_8),
-	BPF_ST_MEM(BPF_B, BPF_REG_8, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "unbounded min value",
-	.result = REJECT,
-},
-{
-	"bounds checks mixing signed and unsigned, variant 3",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
-	BPF_MOV64_IMM(BPF_REG_2, -1),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 4),
-	BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_8, 1, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_8),
-	BPF_ST_MEM(BPF_B, BPF_REG_8, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "unbounded min value",
-	.result = REJECT,
-},
-{
-	"bounds checks mixing signed and unsigned, variant 4",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
-	BPF_MOV64_IMM(BPF_REG_2, 1),
-	BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.result = ACCEPT,
-},
-{
-	"bounds checks mixing signed and unsigned, variant 5",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
-	BPF_MOV64_IMM(BPF_REG_2, -1),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 5),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 4),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 4),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
-	BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "unbounded min value",
-	.result = REJECT,
-},
-{
-	"bounds checks mixing signed and unsigned, variant 6",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -512),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -16),
-	BPF_MOV64_IMM(BPF_REG_6, -1),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_6, 5),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_4, 1, 4),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 1),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-	BPF_ST_MEM(BPF_H, BPF_REG_10, -512, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R4 min value is negative, either use unsigned",
-	.result = REJECT,
-},
-{
-	"bounds checks mixing signed and unsigned, variant 7",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
-	BPF_MOV64_IMM(BPF_REG_2, 1024 * 1024 * 1024),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, 3),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.result = ACCEPT,
-},
-{
-	"bounds checks mixing signed and unsigned, variant 8",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
-	BPF_MOV64_IMM(BPF_REG_2, -1),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "unbounded min value",
-	.result = REJECT,
-},
-{
-	"bounds checks mixing signed and unsigned, variant 9",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
-	BPF_LD_IMM64(BPF_REG_2, -9223372036854775808ULL),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.result = ACCEPT,
-},
-{
-	"bounds checks mixing signed and unsigned, variant 10",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "unbounded min value",
-	.result = REJECT,
-},
-{
-	"bounds checks mixing signed and unsigned, variant 11",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
-	BPF_MOV64_IMM(BPF_REG_2, -1),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2),
-	/* Dead branch. */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "unbounded min value",
-	.result = REJECT,
-},
-{
-	"bounds checks mixing signed and unsigned, variant 12",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
-	BPF_MOV64_IMM(BPF_REG_2, -6),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "unbounded min value",
-	.result = REJECT,
-},
-{
-	"bounds checks mixing signed and unsigned, variant 13",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
-	BPF_MOV64_IMM(BPF_REG_2, 2),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2),
-	BPF_MOV64_IMM(BPF_REG_7, 1),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_7, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_1),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_7, 4, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_7),
-	BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "unbounded min value",
-	.result = REJECT,
-},
-{
-	"bounds checks mixing signed and unsigned, variant 14",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
-		    offsetof(struct __sk_buff, mark)),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
-	BPF_MOV64_IMM(BPF_REG_2, -1),
-	BPF_MOV64_IMM(BPF_REG_8, 2),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_9, 42, 6),
-	BPF_JMP_REG(BPF_JSGT, BPF_REG_8, BPF_REG_1, 3),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 1, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_2, -3),
-	BPF_JMP_IMM(BPF_JA, 0, 0, -7),
-	},
-	.fixup_map_hash_8b = { 4 },
-	.errstr = "unbounded min value",
-	.result = REJECT,
-},
-{
-	"bounds checks mixing signed and unsigned, variant 15",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
-	BPF_MOV64_IMM(BPF_REG_2, -6),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_2, BPF_REG_1, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_0, 1, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "unbounded min value",
-	.result = REJECT,
-},
diff --git a/tools/testing/selftests/bpf/verifier/bpf_get_stack.c b/tools/testing/selftests/bpf/verifier/bpf_get_stack.c
deleted file mode 100644
index 3e024c891178..000000000000
--- a/tools/testing/selftests/bpf/verifier/bpf_get_stack.c
+++ /dev/null
@@ -1,87 +0,0 @@
-{
-	"bpf_get_stack return R0 within range",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 28),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_9, sizeof(struct test_val)/2),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
-	BPF_MOV64_IMM(BPF_REG_3, sizeof(struct test_val)/2),
-	BPF_MOV64_IMM(BPF_REG_4, 256),
-	BPF_EMIT_CALL(BPF_FUNC_get_stack),
-	BPF_MOV64_IMM(BPF_REG_1, 0),
-	BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_LSH, BPF_REG_8, 32),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_8, 32),
-	BPF_JMP_REG(BPF_JSGT, BPF_REG_1, BPF_REG_8, 16),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_9, BPF_REG_8),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_8),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_9),
-	BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 32),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_1, 32),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_1),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
-	BPF_MOV64_IMM(BPF_REG_5, sizeof(struct test_val)/2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_5),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_9),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_EMIT_CALL(BPF_FUNC_get_stack),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 4 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"bpf_get_task_stack return R0 range is refined",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_6, 0), // ctx->meta->seq
-	BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_1, 8), // ctx->task
-	BPF_LD_MAP_FD(BPF_REG_1, 0), // fixup_map_array_48b
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_9, BPF_REG_0), // keep buf for seq_write
-	BPF_MOV64_IMM(BPF_REG_3, 48),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_EMIT_CALL(BPF_FUNC_get_task_stack),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_0, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_9),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_seq_write),
-
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACING,
-	.expected_attach_type = BPF_TRACE_ITER,
-	.kfunc = "task",
-	.runs = -1, // Don't run, just load
-	.fixup_map_array_48b = { 3 },
-},
diff --git a/tools/testing/selftests/bpf/verifier/bpf_loop_inline.c b/tools/testing/selftests/bpf/verifier/bpf_loop_inline.c
index a535d41dc20d..59125b22ae39 100644
--- a/tools/testing/selftests/bpf/verifier/bpf_loop_inline.c
+++ b/tools/testing/selftests/bpf/verifier/bpf_loop_inline.c
@@ -57,6 +57,7 @@
 	.expected_insns = { PSEUDO_CALL_INSN() },
 	.unexpected_insns = { HELPER_CALL_INSN() },
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.flags = F_NEEDS_JIT_ENABLED,
 	.result = ACCEPT,
 	.runs = 0,
 	.func_info = { { 0, MAIN_TYPE }, { 12, CALLBACK_TYPE } },
@@ -90,6 +91,7 @@
 	.expected_insns = { HELPER_CALL_INSN() },
 	.unexpected_insns = { PSEUDO_CALL_INSN() },
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.flags = F_NEEDS_JIT_ENABLED,
 	.result = ACCEPT,
 	.runs = 0,
 	.func_info = { { 0, MAIN_TYPE }, { 16, CALLBACK_TYPE } },
@@ -127,6 +129,7 @@
 	.expected_insns = { HELPER_CALL_INSN() },
 	.unexpected_insns = { PSEUDO_CALL_INSN() },
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.flags = F_NEEDS_JIT_ENABLED,
 	.result = ACCEPT,
 	.runs = 0,
 	.func_info = {
@@ -165,6 +168,7 @@
 	.expected_insns = { PSEUDO_CALL_INSN() },
 	.unexpected_insns = { HELPER_CALL_INSN() },
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.flags = F_NEEDS_JIT_ENABLED,
 	.result = ACCEPT,
 	.runs = 0,
 	.func_info = {
@@ -235,6 +239,7 @@
 	},
 	.unexpected_insns = { HELPER_CALL_INSN() },
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.flags = F_NEEDS_JIT_ENABLED,
 	.result = ACCEPT,
 	.func_info = {
 		{ 0, MAIN_TYPE },
@@ -252,6 +257,7 @@
 	.unexpected_insns = { HELPER_CALL_INSN() },
 	.result = ACCEPT,
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.flags = F_NEEDS_JIT_ENABLED,
 	.func_info = { { 0, MAIN_TYPE }, { 16, CALLBACK_TYPE } },
 	.func_info_cnt = 2,
 	BTF_TYPES
diff --git a/tools/testing/selftests/bpf/verifier/bpf_st_mem.c b/tools/testing/selftests/bpf/verifier/bpf_st_mem.c
new file mode 100644
index 000000000000..ce13002c7a19
--- /dev/null
+++ b/tools/testing/selftests/bpf/verifier/bpf_st_mem.c
@@ -0,0 +1,99 @@
+{
+	"BPF_ST_MEM stack imm non-zero",
+	.insns = {
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 42),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, -42),
+	/* if value is tracked correctly R0 is zero */
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	/* Use prog type that requires return value in range [0, 1] */
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+	.runs = -1,
+},
+{
+	"BPF_ST_MEM stack imm zero",
+	.insns = {
+	/* mark stack 0000 0000 */
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	/* read and sum a few bytes */
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_10, -8),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_10, -4),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_10, -1),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+	/* if value is tracked correctly R0 is zero */
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	/* Use prog type that requires return value in range [0, 1] */
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+	.runs = -1,
+},
+{
+	"BPF_ST_MEM stack imm zero, variable offset",
+	.insns = {
+	/* set fp[-16], fp[-24] to zeros */
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0),
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -24, 0),
+	/* r0 = random value in range [-32, -15] */
+	BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
+	BPF_JMP_IMM(BPF_JLE, BPF_REG_0, 16, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 32),
+	/* fp[r0] = 0, make a variable offset write of zero,
+	 *             this should preserve zero marks on stack.
+	 */
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_10),
+	BPF_ST_MEM(BPF_B, BPF_REG_0, 0, 0),
+	/* r0 = fp[-20], if variable offset write was tracked correctly
+	 *               r0 would be a known zero.
+	 */
+	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_10, -20),
+	/* Would fail return code verification if r0 range is not tracked correctly. */
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	/* Use prog type that requires return value in range [0, 1] */
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+	.runs = -1,
+},
+{
+	"BPF_ST_MEM stack imm sign",
+	/* Check if verifier correctly reasons about sign of an
+	 * immediate spilled to stack by BPF_ST instruction.
+	 *
+	 *   fp[-8] = -44;
+	 *   r0 = fp[-8];
+	 *   if r0 s< 0 goto ret0;
+	 *   r0 = -1;
+	 *   exit;
+	 * ret0:
+	 *   r0 = 0;
+	 *   exit;
+	 */
+	.insns = {
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, -44),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+	BPF_JMP_IMM(BPF_JSLT, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, -1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	/* Use prog type that requires return value in range [0, 1] */
+	.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+	.expected_attach_type = BPF_SK_LOOKUP,
+	.result = VERBOSE_ACCEPT,
+	.runs = -1,
+	.errstr = "0: (7a) *(u64 *)(r10 -8) = -44        ; R10=fp0 fp-8=-44\
+	2: (c5) if r0 s< 0x0 goto pc+2\
+	R0=-44",
+},
diff --git a/tools/testing/selftests/bpf/verifier/btf_ctx_access.c b/tools/testing/selftests/bpf/verifier/btf_ctx_access.c
deleted file mode 100644
index 6340db6b46dc..000000000000
--- a/tools/testing/selftests/bpf/verifier/btf_ctx_access.c
+++ /dev/null
@@ -1,12 +0,0 @@
-{
-	"btf_ctx_access accept",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 8),	/* load 2nd argument value (int pointer) */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACING,
-	.expected_attach_type = BPF_TRACE_FENTRY,
-	.kfunc = "bpf_modify_return_test",
-},
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index 9d993926bf0e..c8d640802cce 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -76,7 +76,7 @@
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.result = REJECT,
-	.errstr = "R1 must have zero offset when passed to release func or trusted arg to kfunc",
+	.errstr = "arg#0 expected pointer to ctx, but got fp",
 	.fixup_kfunc_btf_id = {
 		{ "bpf_kfunc_call_test_pass_ctx", 2 },
 	},
@@ -109,7 +109,7 @@
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.result = REJECT,
-	.errstr = "arg#0 is ptr_or_null_ expected ptr_ or socket",
+	.errstr = "Possibly NULL pointer passed to trusted arg0",
 	.fixup_kfunc_btf_id = {
 		{ "bpf_kfunc_call_test_acquire", 3 },
 		{ "bpf_kfunc_call_test_release", 5 },
@@ -165,23 +165,27 @@
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
 	BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 0),
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
 	BPF_EXIT_INSN(),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 16),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -4),
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.fixup_kfunc_btf_id = {
 		{ "bpf_kfunc_call_test_acquire", 3 },
-		{ "bpf_kfunc_call_test_release", 9 },
+		{ "bpf_kfunc_call_test_offset", 9 },
+		{ "bpf_kfunc_call_test_release", 12 },
 	},
 	.result_unpriv = REJECT,
 	.result = REJECT,
-	.errstr = "negative offset ptr_ ptr R1 off=-4 disallowed",
+	.errstr = "ptr R1 off=-4 disallowed",
 },
 {
 	"calls: invalid kfunc call: PTR_TO_BTF_ID with variable offset",
@@ -243,7 +247,7 @@
 	},
 	.result_unpriv = REJECT,
 	.result = REJECT,
-	.errstr = "R1 must be referenced",
+	.errstr = "R1 must be",
 },
 {
 	"calls: valid kfunc call: referenced arg needs refcounted PTR_TO_BTF_ID",
@@ -272,6 +276,19 @@
 	.result = ACCEPT,
 },
 {
+	"calls: invalid kfunc call: must provide (attach_prog_fd, btf_id) pair when freplace",
+	.insns = {
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_EXT,
+	.result = REJECT,
+	.errstr = "Tracing programs must provide btf_id",
+	.fixup_kfunc_btf_id = {
+		{ "bpf_dynptr_from_skb", 0 },
+	},
+},
+{
 	"calls: basic sanity",
 	.insns = {
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
@@ -438,7 +455,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-	.errstr = "back-edge from insn 0 to 0",
+	.errstr = "the call stack of 9 frames is too deep",
 	.result = REJECT,
 },
 {
@@ -795,7 +812,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-	.errstr = "back-edge",
+	.errstr = "the call stack of 9 frames is too deep",
 	.result = REJECT,
 },
 {
@@ -807,7 +824,7 @@
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-	.errstr = "back-edge",
+	.errstr = "the call stack of 9 frames is too deep",
 	.result = REJECT,
 },
 {
@@ -1358,7 +1375,7 @@
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
 	/* write into map value */
 	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
-	/* fetch secound map_value_ptr from the stack */
+	/* fetch second map_value_ptr from the stack */
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -16),
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
 	/* write into map value */
@@ -1422,7 +1439,7 @@
 	/* second time with fp-16 */
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
-	/* fetch secound map_value_ptr from the stack */
+	/* fetch second map_value_ptr from the stack */
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
 	/* write into map value */
 	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
@@ -1476,7 +1493,7 @@
 	/* second time with fp-16 */
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
-	/* fetch secound map_value_ptr from the stack */
+	/* fetch second map_value_ptr from the stack */
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
 	/* write into map value */
 	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
@@ -1501,7 +1518,9 @@
 	.prog_type = BPF_PROG_TYPE_XDP,
 	.fixup_map_hash_8b = { 23 },
 	.result = REJECT,
-	.errstr = "invalid read from stack R7 off=-16 size=8",
+	.errstr = "R0 invalid mem access 'scalar'",
+	.result_unpriv = REJECT,
+	.errstr_unpriv = "invalid read from stack R7 off=-16 size=8",
 },
 {
 	"calls: two calls that receive map_value via arg=ptr_stack_of_caller. test1",
@@ -2221,19 +2240,22 @@
 	 * that fp-8 stack slot was unused in the fall-through
 	 * branch and will accept the program incorrectly
 	 */
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 2, 2),
+	BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
+	BPF_JMP_IMM(BPF_JGT, BPF_REG_0, 2, 2),
 	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
 	BPF_JMP_IMM(BPF_JA, 0, 0, 0),
 	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
 	BPF_LD_MAP_FD(BPF_REG_1, 0),
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
-	.fixup_map_hash_48b = { 6 },
-	.errstr = "invalid indirect read from stack R2 off -8+0 size 8",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
+	.fixup_map_hash_48b = { 7 },
+	.errstr_unpriv = "invalid read from stack R2 off -8+0 size 8",
+	.result_unpriv = REJECT,
+	/* in privileged mode reads from uninitialized stack locations are permitted */
+	.result = ACCEPT,
 },
 {
 	"calls: ctx read at start of subprog",
@@ -2358,7 +2380,7 @@
 	 */
 	BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_7, 1),
 	BPF_MOV64_REG(BPF_REG_9, BPF_REG_8),
-	/* r9 = *r9                ; verifier get's to this point via two paths:
+	/* r9 = *r9                ; verifier gets to this point via two paths:
 	 *                         ; (I) one including r9 = r8, verified first;
 	 *                         ; (II) one excluding r9 = r8, verified next.
 	 *                         ; After load of *r9 to r9 the frame[0].fp[-24].id == r9.id.
@@ -2387,3 +2409,27 @@
 	.errstr_unpriv = "",
 	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
 },
+{
+	"calls: several args with ref_obj_id",
+	.insns = {
+	/* Reserve at least sizeof(struct iphdr) bytes in the ring buffer.
+	 * With a smaller size, the verifier would reject the call to
+	 * bpf_tcp_raw_gen_syncookie_ipv4 before we can reach the
+	 * ref_obj_id error.
+	 */
+	BPF_MOV64_IMM(BPF_REG_2, 20),
+	BPF_MOV64_IMM(BPF_REG_3, 0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve),
+	/* if r0 == 0 goto <exit> */
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tcp_raw_gen_syncookie_ipv4),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_ringbuf = { 2 },
+	.result = REJECT,
+	.errstr = "more than one arg with ref_obj_id",
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+},
diff --git a/tools/testing/selftests/bpf/verifier/cfg.c b/tools/testing/selftests/bpf/verifier/cfg.c
deleted file mode 100644
index 4eb76ed739ce..000000000000
--- a/tools/testing/selftests/bpf/verifier/cfg.c
+++ /dev/null
@@ -1,73 +0,0 @@
-{
-	"unreachable",
-	.insns = {
-	BPF_EXIT_INSN(),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "unreachable",
-	.result = REJECT,
-},
-{
-	"unreachable2",
-	.insns = {
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "unreachable",
-	.result = REJECT,
-},
-{
-	"out of range jump",
-	.insns = {
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "jump out of range",
-	.result = REJECT,
-},
-{
-	"out of range jump2",
-	.insns = {
-	BPF_JMP_IMM(BPF_JA, 0, 0, -2),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "jump out of range",
-	.result = REJECT,
-},
-{
-	"loop (back-edge)",
-	.insns = {
-	BPF_JMP_IMM(BPF_JA, 0, 0, -1),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "unreachable insn 1",
-	.errstr_unpriv = "back-edge",
-	.result = REJECT,
-},
-{
-	"loop2 (back-edge)",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JA, 0, 0, -4),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "unreachable insn 4",
-	.errstr_unpriv = "back-edge",
-	.result = REJECT,
-},
-{
-	"conditional loop",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, -3),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "infinite loop detected",
-	.errstr_unpriv = "back-edge",
-	.result = REJECT,
-},
diff --git a/tools/testing/selftests/bpf/verifier/cgroup_inv_retcode.c b/tools/testing/selftests/bpf/verifier/cgroup_inv_retcode.c
deleted file mode 100644
index 6d65fe3e7321..000000000000
--- a/tools/testing/selftests/bpf/verifier/cgroup_inv_retcode.c
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-	"bpf_exit with invalid return code. test1",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R0 has value (0x0; 0xffffffff)",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
-},
-{
-	"bpf_exit with invalid return code. test2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
-},
-{
-	"bpf_exit with invalid return code. test3",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 3),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R0 has value (0x0; 0x3)",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
-},
-{
-	"bpf_exit with invalid return code. test4",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
-},
-{
-	"bpf_exit with invalid return code. test5",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 2),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R0 has value (0x2; 0x0)",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
-},
-{
-	"bpf_exit with invalid return code. test6",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R0 is not a known value (ctx)",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
-},
-{
-	"bpf_exit with invalid return code. test7",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 4),
-	BPF_ALU64_REG(BPF_MUL, BPF_REG_0, BPF_REG_2),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R0 has unknown scalar value",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
-},
diff --git a/tools/testing/selftests/bpf/verifier/cgroup_skb.c b/tools/testing/selftests/bpf/verifier/cgroup_skb.c
deleted file mode 100644
index 52e4c03b076b..000000000000
--- a/tools/testing/selftests/bpf/verifier/cgroup_skb.c
+++ /dev/null
@@ -1,197 +0,0 @@
-{
-	"direct packet read test#1 for CGROUP_SKB",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
-		    offsetof(struct __sk_buff, len)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
-		    offsetof(struct __sk_buff, pkt_type)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, mark)),
-	BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
-		    offsetof(struct __sk_buff, mark)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
-		    offsetof(struct __sk_buff, queue_mapping)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
-		    offsetof(struct __sk_buff, protocol)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
-		    offsetof(struct __sk_buff, vlan_present)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "invalid bpf_context access off=76 size=4",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"direct packet read test#2 for CGROUP_SKB",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
-		    offsetof(struct __sk_buff, vlan_tci)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
-		    offsetof(struct __sk_buff, vlan_proto)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, priority)),
-	BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
-		    offsetof(struct __sk_buff, priority)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
-		    offsetof(struct __sk_buff, ingress_ifindex)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
-		    offsetof(struct __sk_buff, tc_index)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
-		    offsetof(struct __sk_buff, hash)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"direct packet read test#3 for CGROUP_SKB",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
-		    offsetof(struct __sk_buff, cb[0])),
-	BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
-		    offsetof(struct __sk_buff, cb[1])),
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, cb[2])),
-	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
-		    offsetof(struct __sk_buff, cb[3])),
-	BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
-		    offsetof(struct __sk_buff, cb[4])),
-	BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
-		    offsetof(struct __sk_buff, napi_id)),
-	BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_4,
-		    offsetof(struct __sk_buff, cb[0])),
-	BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_5,
-		    offsetof(struct __sk_buff, cb[1])),
-	BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
-		    offsetof(struct __sk_buff, cb[2])),
-	BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_7,
-		    offsetof(struct __sk_buff, cb[3])),
-	BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_8,
-		    offsetof(struct __sk_buff, cb[4])),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"direct packet read test#4 for CGROUP_SKB",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, family)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, remote_ip4)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
-		    offsetof(struct __sk_buff, local_ip4)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
-		    offsetof(struct __sk_buff, remote_ip6[0])),
-	BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
-		    offsetof(struct __sk_buff, remote_ip6[1])),
-	BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
-		    offsetof(struct __sk_buff, remote_ip6[2])),
-	BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
-		    offsetof(struct __sk_buff, remote_ip6[3])),
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, local_ip6[0])),
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, local_ip6[1])),
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, local_ip6[2])),
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, local_ip6[3])),
-	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
-		    offsetof(struct __sk_buff, remote_port)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
-		    offsetof(struct __sk_buff, local_port)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"invalid access of tc_classid for CGROUP_SKB",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, tc_classid)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid bpf_context access",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"invalid access of data_meta for CGROUP_SKB",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_meta)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid bpf_context access",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"invalid access of flow_keys for CGROUP_SKB",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, flow_keys)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid bpf_context access",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"invalid write access to napi_id for CGROUP_SKB",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
-		    offsetof(struct __sk_buff, napi_id)),
-	BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_9,
-		    offsetof(struct __sk_buff, napi_id)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid bpf_context access",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"write tstamp from CGROUP_SKB",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
-		    offsetof(struct __sk_buff, tstamp)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "invalid bpf_context access off=152 size=8",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"read tstamp from CGROUP_SKB",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, tstamp)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
diff --git a/tools/testing/selftests/bpf/verifier/cgroup_storage.c b/tools/testing/selftests/bpf/verifier/cgroup_storage.c
deleted file mode 100644
index 97057c0a1b8a..000000000000
--- a/tools/testing/selftests/bpf/verifier/cgroup_storage.c
+++ /dev/null
@@ -1,220 +0,0 @@
-{
-	"valid cgroup storage access",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_cgroup_storage = { 1 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"invalid cgroup storage access 1",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 1 },
-	.result = REJECT,
-	.errstr = "cannot pass map_type 1 into func bpf_get_local_storage",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"invalid cgroup storage access 2",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 1),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "fd 1 is not pointing to valid bpf_map",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"invalid cgroup storage access 3",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 256),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_cgroup_storage = { 1 },
-	.result = REJECT,
-	.errstr = "invalid access to map value, value_size=64 off=256 size=4",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"invalid cgroup storage access 4",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, -2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_cgroup_storage = { 1 },
-	.result = REJECT,
-	.errstr = "invalid access to map value, value_size=64 off=-2 size=4",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"invalid cgroup storage access 5",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 7),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_cgroup_storage = { 1 },
-	.result = REJECT,
-	.errstr = "get_local_storage() doesn't support non-zero flags",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"invalid cgroup storage access 6",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_cgroup_storage = { 1 },
-	.result = REJECT,
-	.errstr = "get_local_storage() doesn't support non-zero flags",
-	.errstr_unpriv = "R2 leaks addr into helper function",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"valid per-cpu cgroup storage access",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_percpu_cgroup_storage = { 1 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"invalid per-cpu cgroup storage access 1",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 1 },
-	.result = REJECT,
-	.errstr = "cannot pass map_type 1 into func bpf_get_local_storage",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"invalid per-cpu cgroup storage access 2",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 1),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "fd 1 is not pointing to valid bpf_map",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"invalid per-cpu cgroup storage access 3",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 256),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_percpu_cgroup_storage = { 1 },
-	.result = REJECT,
-	.errstr = "invalid access to map value, value_size=64 off=256 size=4",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"invalid per-cpu cgroup storage access 4",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, -2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_cgroup_storage = { 1 },
-	.result = REJECT,
-	.errstr = "invalid access to map value, value_size=64 off=-2 size=4",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"invalid per-cpu cgroup storage access 5",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 7),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_percpu_cgroup_storage = { 1 },
-	.result = REJECT,
-	.errstr = "get_local_storage() doesn't support non-zero flags",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"invalid per-cpu cgroup storage access 6",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_percpu_cgroup_storage = { 1 },
-	.result = REJECT,
-	.errstr = "get_local_storage() doesn't support non-zero flags",
-	.errstr_unpriv = "R2 leaks addr into helper function",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
diff --git a/tools/testing/selftests/bpf/verifier/const_or.c b/tools/testing/selftests/bpf/verifier/const_or.c
deleted file mode 100644
index 0719b0ddec04..000000000000
--- a/tools/testing/selftests/bpf/verifier/const_or.c
+++ /dev/null
@@ -1,60 +0,0 @@
-{
-	"constant register |= constant should keep constant type",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -48),
-	BPF_MOV64_IMM(BPF_REG_2, 34),
-	BPF_ALU64_IMM(BPF_OR, BPF_REG_2, 13),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"constant register |= constant should not bypass stack boundary checks",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -48),
-	BPF_MOV64_IMM(BPF_REG_2, 34),
-	BPF_ALU64_IMM(BPF_OR, BPF_REG_2, 24),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "invalid indirect access to stack R1 off=-48 size=58",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"constant register |= constant register should keep constant type",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -48),
-	BPF_MOV64_IMM(BPF_REG_2, 34),
-	BPF_MOV64_IMM(BPF_REG_4, 13),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_4),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"constant register |= constant register should not bypass stack boundary checks",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -48),
-	BPF_MOV64_IMM(BPF_REG_2, 34),
-	BPF_MOV64_IMM(BPF_REG_4, 24),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_4),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "invalid indirect access to stack R1 off=-48 size=58",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
diff --git a/tools/testing/selftests/bpf/verifier/ctx.c b/tools/testing/selftests/bpf/verifier/ctx.c
deleted file mode 100644
index c8eaf0536c24..000000000000
--- a/tools/testing/selftests/bpf/verifier/ctx.c
+++ /dev/null
@@ -1,197 +0,0 @@
-{
-	"context stores via ST",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_ST_MEM(BPF_DW, BPF_REG_1, offsetof(struct __sk_buff, mark), 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "BPF_ST stores into R1 ctx is not allowed",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"context stores via BPF_ATOMIC",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_ATOMIC_OP(BPF_W, BPF_ADD, BPF_REG_1, BPF_REG_0, offsetof(struct __sk_buff, mark)),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "BPF_ATOMIC stores into R1 ctx is not allowed",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"arithmetic ops make PTR_TO_CTX unusable",
-	.insns = {
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_1,
-			      offsetof(struct __sk_buff, data) -
-			      offsetof(struct __sk_buff, mark)),
-		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-			    offsetof(struct __sk_buff, mark)),
-		BPF_EXIT_INSN(),
-	},
-	.errstr = "dereference of modified ctx ptr",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"pass unmodified ctx pointer to helper",
-	.insns = {
-		BPF_MOV64_IMM(BPF_REG_2, 0),
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-			     BPF_FUNC_csum_update),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-},
-{
-	"pass modified ctx pointer to helper, 1",
-	.insns = {
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -612),
-		BPF_MOV64_IMM(BPF_REG_2, 0),
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-			     BPF_FUNC_csum_update),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = REJECT,
-	.errstr = "negative offset ctx ptr R1 off=-612 disallowed",
-},
-{
-	"pass modified ctx pointer to helper, 2",
-	.insns = {
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -612),
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-			     BPF_FUNC_get_socket_cookie),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	},
-	.result_unpriv = REJECT,
-	.result = REJECT,
-	.errstr_unpriv = "negative offset ctx ptr R1 off=-612 disallowed",
-	.errstr = "negative offset ctx ptr R1 off=-612 disallowed",
-},
-{
-	"pass modified ctx pointer to helper, 3",
-	.insns = {
-		BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, 0),
-		BPF_ALU64_IMM(BPF_AND, BPF_REG_3, 4),
-		BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-		BPF_MOV64_IMM(BPF_REG_2, 0),
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-			     BPF_FUNC_csum_update),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = REJECT,
-	.errstr = "variable ctx access var_off=(0x0; 0x4)",
-},
-{
-	"pass ctx or null check, 1: ctx",
-	.insns = {
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-			     BPF_FUNC_get_netns_cookie),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-	.expected_attach_type = BPF_CGROUP_UDP6_SENDMSG,
-	.result = ACCEPT,
-},
-{
-	"pass ctx or null check, 2: null",
-	.insns = {
-		BPF_MOV64_IMM(BPF_REG_1, 0),
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-			     BPF_FUNC_get_netns_cookie),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-	.expected_attach_type = BPF_CGROUP_UDP6_SENDMSG,
-	.result = ACCEPT,
-},
-{
-	"pass ctx or null check, 3: 1",
-	.insns = {
-		BPF_MOV64_IMM(BPF_REG_1, 1),
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-			     BPF_FUNC_get_netns_cookie),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-	.expected_attach_type = BPF_CGROUP_UDP6_SENDMSG,
-	.result = REJECT,
-	.errstr = "R1 type=scalar expected=ctx",
-},
-{
-	"pass ctx or null check, 4: ctx - const",
-	.insns = {
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -612),
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-			     BPF_FUNC_get_netns_cookie),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-	.expected_attach_type = BPF_CGROUP_UDP6_SENDMSG,
-	.result = REJECT,
-	.errstr = "negative offset ctx ptr R1 off=-612 disallowed",
-},
-{
-	"pass ctx or null check, 5: null (connect)",
-	.insns = {
-		BPF_MOV64_IMM(BPF_REG_1, 0),
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-			     BPF_FUNC_get_netns_cookie),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-	.expected_attach_type = BPF_CGROUP_INET4_CONNECT,
-	.result = ACCEPT,
-},
-{
-	"pass ctx or null check, 6: null (bind)",
-	.insns = {
-		BPF_MOV64_IMM(BPF_REG_1, 0),
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-			     BPF_FUNC_get_netns_cookie),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
-	.expected_attach_type = BPF_CGROUP_INET4_POST_BIND,
-	.result = ACCEPT,
-},
-{
-	"pass ctx or null check, 7: ctx (bind)",
-	.insns = {
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-			     BPF_FUNC_get_socket_cookie),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
-	.expected_attach_type = BPF_CGROUP_INET4_POST_BIND,
-	.result = ACCEPT,
-},
-{
-	"pass ctx or null check, 8: null (bind)",
-	.insns = {
-		BPF_MOV64_IMM(BPF_REG_1, 0),
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-			     BPF_FUNC_get_socket_cookie),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
-	.expected_attach_type = BPF_CGROUP_INET4_POST_BIND,
-	.result = REJECT,
-	.errstr = "R1 type=scalar expected=ctx",
-},
diff --git a/tools/testing/selftests/bpf/verifier/ctx_sk_msg.c b/tools/testing/selftests/bpf/verifier/ctx_sk_msg.c
deleted file mode 100644
index c6c69220a569..000000000000
--- a/tools/testing/selftests/bpf/verifier/ctx_sk_msg.c
+++ /dev/null
@@ -1,181 +0,0 @@
-{
-	"valid access family in SK_MSG",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct sk_msg_md, family)),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SK_MSG,
-},
-{
-	"valid access remote_ip4 in SK_MSG",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct sk_msg_md, remote_ip4)),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SK_MSG,
-},
-{
-	"valid access local_ip4 in SK_MSG",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct sk_msg_md, local_ip4)),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SK_MSG,
-},
-{
-	"valid access remote_port in SK_MSG",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct sk_msg_md, remote_port)),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SK_MSG,
-},
-{
-	"valid access local_port in SK_MSG",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct sk_msg_md, local_port)),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SK_MSG,
-},
-{
-	"valid access remote_ip6 in SK_MSG",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct sk_msg_md, remote_ip6[0])),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct sk_msg_md, remote_ip6[1])),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct sk_msg_md, remote_ip6[2])),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct sk_msg_md, remote_ip6[3])),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SK_SKB,
-},
-{
-	"valid access local_ip6 in SK_MSG",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct sk_msg_md, local_ip6[0])),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct sk_msg_md, local_ip6[1])),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct sk_msg_md, local_ip6[2])),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct sk_msg_md, local_ip6[3])),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SK_SKB,
-},
-{
-	"valid access size in SK_MSG",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct sk_msg_md, size)),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SK_MSG,
-},
-{
-	"invalid 64B read of size in SK_MSG",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct sk_msg_md, size)),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "invalid bpf_context access",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_SK_MSG,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"invalid read past end of SK_MSG",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct sk_msg_md, size) + 4),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "invalid bpf_context access",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_SK_MSG,
-},
-{
-	"invalid read offset in SK_MSG",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct sk_msg_md, family) + 1),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "invalid bpf_context access",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_SK_MSG,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"direct packet read for SK_MSG",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct sk_msg_md, data)),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct sk_msg_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SK_MSG,
-},
-{
-	"direct packet write for SK_MSG",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct sk_msg_md, data)),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct sk_msg_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	BPF_STX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SK_MSG,
-},
-{
-	"overlapping checks for direct packet access SK_MSG",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct sk_msg_md, data)),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct sk_msg_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_2, 6),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SK_MSG,
-},
diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c
index 83cecfbd6739..0b394a7f7a2d 100644
--- a/tools/testing/selftests/bpf/verifier/ctx_skb.c
+++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c
@@ -1169,6 +1169,7 @@
        },
        .result = ACCEPT,
        .prog_type = BPF_PROG_TYPE_SK_SKB,
+       .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
        "pkt_end < pkt taken check",
@@ -1190,4 +1191,5 @@
        },
        .result = ACCEPT,
        .prog_type = BPF_PROG_TYPE_SK_SKB,
+       .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
diff --git a/tools/testing/selftests/bpf/verifier/d_path.c b/tools/testing/selftests/bpf/verifier/d_path.c
deleted file mode 100644
index b988396379a7..000000000000
--- a/tools/testing/selftests/bpf/verifier/d_path.c
+++ /dev/null
@@ -1,37 +0,0 @@
-{
-	"d_path accept",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_MOV64_IMM(BPF_REG_6, 0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_6, 0),
-	BPF_LD_IMM64(BPF_REG_3, 8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_d_path),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACING,
-	.expected_attach_type = BPF_TRACE_FENTRY,
-	.kfunc = "dentry_open",
-},
-{
-	"d_path reject",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_MOV64_IMM(BPF_REG_6, 0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_6, 0),
-	BPF_LD_IMM64(BPF_REG_3, 8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_d_path),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "helper call is not allowed in probe",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACING,
-	.expected_attach_type = BPF_TRACE_FENTRY,
-	.kfunc = "d_path",
-},
diff --git a/tools/testing/selftests/bpf/verifier/dead_code.c b/tools/testing/selftests/bpf/verifier/dead_code.c
index ee454327e5c6..77207b498c6f 100644
--- a/tools/testing/selftests/bpf/verifier/dead_code.c
+++ b/tools/testing/selftests/bpf/verifier/dead_code.c
@@ -2,14 +2,13 @@
 	"dead code: start",
 	.insns = {
 	BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+	/* unpriv: nospec (inserted to prevent "R9 !read_ok") */
 	BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
 	BPF_JMP_IMM(BPF_JA, 0, 0, 2),
 	BPF_MOV64_IMM(BPF_REG_0, 7),
 	BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 10, -4),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R9 !read_ok",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 7,
 },
diff --git a/tools/testing/selftests/bpf/verifier/direct_packet_access.c b/tools/testing/selftests/bpf/verifier/direct_packet_access.c
deleted file mode 100644
index dce2e28aeb43..000000000000
--- a/tools/testing/selftests/bpf/verifier/direct_packet_access.c
+++ /dev/null
@@ -1,710 +0,0 @@
-{
-	"pkt_end - pkt_start is allowed",
-	.insns = {
-		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-			    offsetof(struct __sk_buff, data_end)),
-		BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-			    offsetof(struct __sk_buff, data)),
-		BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_2),
-		BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = TEST_DATA_LEN,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"direct packet access: test1",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"direct packet access: test2",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_MOV64_REG(BPF_REG_5, BPF_REG_3),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_5, BPF_REG_4, 15),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_3, 7),
-	BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_3, 12),
-	BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 14),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_4),
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, len)),
-	BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 49),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 49),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_3),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 8),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_3, 4),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"direct packet access: test3",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "invalid bpf_context access off=76",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
-},
-{
-	"direct packet access: test4 (write)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	BPF_STX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"direct packet access: test5 (pkt_end >= reg, good access)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"direct packet access: test6 (pkt_end >= reg, bad access)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_0, 3),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "invalid access to packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"direct packet access: test7 (pkt_end >= reg, both accesses)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_0, 3),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "invalid access to packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"direct packet access: test8 (double test, variant 1)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_0, 4),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"direct packet access: test9 (double test, variant 2)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"direct packet access: test10 (write invalid)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_STX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "invalid access to packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"direct packet access: test11 (shift, good access)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 22),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 8),
-	BPF_MOV64_IMM(BPF_REG_3, 144),
-	BPF_MOV64_REG(BPF_REG_5, BPF_REG_3),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 23),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_5, 3),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_5),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.retval = 1,
-},
-{
-	"direct packet access: test12 (and, good access)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 22),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 8),
-	BPF_MOV64_IMM(BPF_REG_3, 144),
-	BPF_MOV64_REG(BPF_REG_5, BPF_REG_3),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 23),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_5, 15),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_5),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.retval = 1,
-},
-{
-	"direct packet access: test13 (branches, good access)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 22),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 13),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, mark)),
-	BPF_MOV64_IMM(BPF_REG_4, 1),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_4, 2),
-	BPF_MOV64_IMM(BPF_REG_3, 14),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_MOV64_IMM(BPF_REG_3, 24),
-	BPF_MOV64_REG(BPF_REG_5, BPF_REG_3),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 23),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_5, 15),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_5),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.retval = 1,
-},
-{
-	"direct packet access: test14 (pkt_ptr += 0, CONST_IMM, good access)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 22),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 7),
-	BPF_MOV64_IMM(BPF_REG_5, 12),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_5, 4),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_5),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.retval = 1,
-},
-{
-	"direct packet access: test15 (spill with xadd)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 8),
-	BPF_MOV64_IMM(BPF_REG_5, 4096),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
-	BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
-	BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_4, BPF_REG_5, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_4, 0),
-	BPF_STX_MEM(BPF_W, BPF_REG_2, BPF_REG_5, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R2 invalid mem access 'scalar'",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"direct packet access: test16 (arith on data_end)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 16),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	BPF_STX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R3 pointer arithmetic on pkt_end",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"direct packet access: test17 (pruning, alignment)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
-		    offsetof(struct __sk_buff, mark)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 14),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_7, 1, 4),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, -4),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
-	BPF_JMP_A(-6),
-	},
-	.errstr = "misaligned packet access off 2+(0x0; 0x0)+15+-4 size 4",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.flags = F_LOAD_WITH_STRICT_ALIGNMENT,
-},
-{
-	"direct packet access: test18 (imm += pkt_ptr, 1)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_IMM(BPF_REG_0, 8),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	BPF_STX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"direct packet access: test19 (imm += pkt_ptr, 2)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 3),
-	BPF_MOV64_IMM(BPF_REG_4, 4),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_2),
-	BPF_STX_MEM(BPF_B, BPF_REG_4, BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"direct packet access: test20 (x += pkt_ptr, 1)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_IMM(BPF_REG_0, 0xffffffff),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0x7fff),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_5, BPF_REG_4),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0x7fff - 1),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1),
-	BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"direct packet access: test21 (x += pkt_ptr, 2)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 9),
-	BPF_MOV64_IMM(BPF_REG_4, 0xffffffff),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_4, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_4, 0x7fff),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_5, BPF_REG_4),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0x7fff - 1),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1),
-	BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"direct packet access: test22 (x += pkt_ptr, 3)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -8),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_3, -16),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_10, -16),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 11),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -8),
-	BPF_MOV64_IMM(BPF_REG_4, 0xffffffff),
-	BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_10, BPF_REG_4, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 49),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_4),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 2),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 2),
-	BPF_MOV64_IMM(BPF_REG_2, 1),
-	BPF_STX_MEM(BPF_H, BPF_REG_4, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"direct packet access: test23 (x += pkt_ptr, 4)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, mark)),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xffff),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_0, 31),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_5, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0xffff - 1),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = REJECT,
-	.errstr = "invalid access to packet, off=0 size=8, R5(id=2,off=0,r=0)",
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"direct packet access: test24 (x += pkt_ptr, 5)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_IMM(BPF_REG_0, 0xffffffff),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xff),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_0, 64),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_5, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0x7fff - 1),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"direct packet access: test25 (marking on <, good access)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_0, BPF_REG_3, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_JMP_IMM(BPF_JA, 0, 0, -4),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"direct packet access: test26 (marking on <, bad access)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_0, BPF_REG_3, 3),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_JMP_IMM(BPF_JA, 0, 0, -3),
-	},
-	.result = REJECT,
-	.errstr = "invalid access to packet",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"direct packet access: test27 (marking on <=, good access)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_0, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.retval = 1,
-},
-{
-	"direct packet access: test28 (marking on <=, bad access)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_JMP_IMM(BPF_JA, 0, 0, -4),
-	},
-	.result = REJECT,
-	.errstr = "invalid access to packet",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"direct packet access: test29 (reg > pkt_end in subprog)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_2, 1),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"direct packet access: test30 (check_id() in regsafe(), bad access)",
-	.insns = {
-	/* r9 = ctx */
-	BPF_MOV64_REG(BPF_REG_9, BPF_REG_1),
-	/* r7 = ktime_get_ns() */
-	BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	/* r6 = ktime_get_ns() */
-	BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	/* r2 = ctx->data
-	 * r3 = ctx->data
-	 * r4 = ctx->data_end
-	 */
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_9, offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_9, offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_9, offsetof(struct __sk_buff, data_end)),
-	/* if r6 > 100 goto exit
-	 * if r7 > 100 goto exit
-	 */
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_6, 100, 9),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_7, 100, 8),
-	/* r2 += r6              ; this forces assignment of ID to r2
-	 * r2 += 1               ; get some fixed off for r2
-	 * r3 += r7              ; this forces assignment of ID to r3
-	 * r3 += 1               ; get some fixed off for r3
-	 */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_7),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 1),
-	/* if r6 > r7 goto +1    ; no new information about the state is derived from
-	 *                       ; this check, thus produced verifier states differ
-	 *                       ; only in 'insn_idx'
-	 * r2 = r3               ; optionally share ID between r2 and r3
-	 */
-	BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_7, 1),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_3),
-	/* if r3 > ctx->data_end goto exit */
-	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_4, 1),
-	/* r5 = *(u8 *) (r2 - 1) ; access packet memory using r2,
-	 *                       ; this is not always safe
-	 */
-	BPF_LDX_MEM(BPF_B, BPF_REG_5, BPF_REG_2, -1),
-	/* exit(0) */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.flags = BPF_F_TEST_STATE_FREQ,
-	.result = REJECT,
-	.errstr = "invalid access to packet, off=0 size=1, R2",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
diff --git a/tools/testing/selftests/bpf/verifier/direct_stack_access_wraparound.c b/tools/testing/selftests/bpf/verifier/direct_stack_access_wraparound.c
deleted file mode 100644
index 698e3779fdd2..000000000000
--- a/tools/testing/selftests/bpf/verifier/direct_stack_access_wraparound.c
+++ /dev/null
@@ -1,40 +0,0 @@
-{
-	"direct stack access with 32-bit wraparound. test1",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x7fffffff),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x7fffffff),
-	BPF_MOV32_IMM(BPF_REG_0, 0),
-	BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "fp pointer and 2147483647",
-	.result = REJECT
-},
-{
-	"direct stack access with 32-bit wraparound. test2",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x3fffffff),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x3fffffff),
-	BPF_MOV32_IMM(BPF_REG_0, 0),
-	BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "fp pointer and 1073741823",
-	.result = REJECT
-},
-{
-	"direct stack access with 32-bit wraparound. test3",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x1fffffff),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x1fffffff),
-	BPF_MOV32_IMM(BPF_REG_0, 0),
-	BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "fp pointer offset 1073741822",
-	.errstr_unpriv = "R1 stack pointer arithmetic goes out of range",
-	.result = REJECT
-},
diff --git a/tools/testing/selftests/bpf/verifier/div0.c b/tools/testing/selftests/bpf/verifier/div0.c
deleted file mode 100644
index 7685edfbcf71..000000000000
--- a/tools/testing/selftests/bpf/verifier/div0.c
+++ /dev/null
@@ -1,184 +0,0 @@
-{
-	"DIV32 by 0, zero check 1",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_0, 42),
-	BPF_MOV32_IMM(BPF_REG_1, 0),
-	BPF_MOV32_IMM(BPF_REG_2, 1),
-	BPF_ALU32_REG(BPF_DIV, BPF_REG_2, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 42,
-},
-{
-	"DIV32 by 0, zero check 2",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_0, 42),
-	BPF_LD_IMM64(BPF_REG_1, 0xffffffff00000000LL),
-	BPF_MOV32_IMM(BPF_REG_2, 1),
-	BPF_ALU32_REG(BPF_DIV, BPF_REG_2, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 42,
-},
-{
-	"DIV64 by 0, zero check",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_0, 42),
-	BPF_MOV32_IMM(BPF_REG_1, 0),
-	BPF_MOV32_IMM(BPF_REG_2, 1),
-	BPF_ALU64_REG(BPF_DIV, BPF_REG_2, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 42,
-},
-{
-	"MOD32 by 0, zero check 1",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_0, 42),
-	BPF_MOV32_IMM(BPF_REG_1, 0),
-	BPF_MOV32_IMM(BPF_REG_2, 1),
-	BPF_ALU32_REG(BPF_MOD, BPF_REG_2, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 42,
-},
-{
-	"MOD32 by 0, zero check 2",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_0, 42),
-	BPF_LD_IMM64(BPF_REG_1, 0xffffffff00000000LL),
-	BPF_MOV32_IMM(BPF_REG_2, 1),
-	BPF_ALU32_REG(BPF_MOD, BPF_REG_2, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 42,
-},
-{
-	"MOD64 by 0, zero check",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_0, 42),
-	BPF_MOV32_IMM(BPF_REG_1, 0),
-	BPF_MOV32_IMM(BPF_REG_2, 1),
-	BPF_ALU64_REG(BPF_MOD, BPF_REG_2, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 42,
-},
-{
-	"DIV32 by 0, zero check ok, cls",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_0, 42),
-	BPF_MOV32_IMM(BPF_REG_1, 2),
-	BPF_MOV32_IMM(BPF_REG_2, 16),
-	BPF_ALU32_REG(BPF_DIV, BPF_REG_2, BPF_REG_1),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.retval = 8,
-},
-{
-	"DIV32 by 0, zero check 1, cls",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_1, 0),
-	BPF_MOV32_IMM(BPF_REG_0, 1),
-	BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"DIV32 by 0, zero check 2, cls",
-	.insns = {
-	BPF_LD_IMM64(BPF_REG_1, 0xffffffff00000000LL),
-	BPF_MOV32_IMM(BPF_REG_0, 1),
-	BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"DIV64 by 0, zero check, cls",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_1, 0),
-	BPF_MOV32_IMM(BPF_REG_0, 1),
-	BPF_ALU64_REG(BPF_DIV, BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"MOD32 by 0, zero check ok, cls",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_0, 42),
-	BPF_MOV32_IMM(BPF_REG_1, 3),
-	BPF_MOV32_IMM(BPF_REG_2, 5),
-	BPF_ALU32_REG(BPF_MOD, BPF_REG_2, BPF_REG_1),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.retval = 2,
-},
-{
-	"MOD32 by 0, zero check 1, cls",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_1, 0),
-	BPF_MOV32_IMM(BPF_REG_0, 1),
-	BPF_ALU32_REG(BPF_MOD, BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"MOD32 by 0, zero check 2, cls",
-	.insns = {
-	BPF_LD_IMM64(BPF_REG_1, 0xffffffff00000000LL),
-	BPF_MOV32_IMM(BPF_REG_0, 1),
-	BPF_ALU32_REG(BPF_MOD, BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"MOD64 by 0, zero check 1, cls",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_1, 0),
-	BPF_MOV32_IMM(BPF_REG_0, 2),
-	BPF_ALU64_REG(BPF_MOD, BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.retval = 2,
-},
-{
-	"MOD64 by 0, zero check 2, cls",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_1, 0),
-	BPF_MOV32_IMM(BPF_REG_0, -1),
-	BPF_ALU64_REG(BPF_MOD, BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.retval = -1,
-},
diff --git a/tools/testing/selftests/bpf/verifier/div_overflow.c b/tools/testing/selftests/bpf/verifier/div_overflow.c
deleted file mode 100644
index acab4f00819f..000000000000
--- a/tools/testing/selftests/bpf/verifier/div_overflow.c
+++ /dev/null
@@ -1,110 +0,0 @@
-/* Just make sure that JITs used udiv/umod as otherwise we get
- * an exception from INT_MIN/-1 overflow similarly as with div
- * by zero.
- */
-{
-	"DIV32 overflow, check 1",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_1, -1),
-	BPF_MOV32_IMM(BPF_REG_0, INT_MIN),
-	BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"DIV32 overflow, check 2",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_0, INT_MIN),
-	BPF_ALU32_IMM(BPF_DIV, BPF_REG_0, -1),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"DIV64 overflow, check 1",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, -1),
-	BPF_LD_IMM64(BPF_REG_2, LLONG_MIN),
-	BPF_ALU64_REG(BPF_DIV, BPF_REG_2, BPF_REG_1),
-	BPF_MOV32_IMM(BPF_REG_0, 0),
-	BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_2, 1),
-	BPF_MOV32_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"DIV64 overflow, check 2",
-	.insns = {
-	BPF_LD_IMM64(BPF_REG_1, LLONG_MIN),
-	BPF_ALU64_IMM(BPF_DIV, BPF_REG_1, -1),
-	BPF_MOV32_IMM(BPF_REG_0, 0),
-	BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_1, 1),
-	BPF_MOV32_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"MOD32 overflow, check 1",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_1, -1),
-	BPF_MOV32_IMM(BPF_REG_0, INT_MIN),
-	BPF_ALU32_REG(BPF_MOD, BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.retval = INT_MIN,
-},
-{
-	"MOD32 overflow, check 2",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_0, INT_MIN),
-	BPF_ALU32_IMM(BPF_MOD, BPF_REG_0, -1),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.retval = INT_MIN,
-},
-{
-	"MOD64 overflow, check 1",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, -1),
-	BPF_LD_IMM64(BPF_REG_2, LLONG_MIN),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_2),
-	BPF_ALU64_REG(BPF_MOD, BPF_REG_2, BPF_REG_1),
-	BPF_MOV32_IMM(BPF_REG_0, 0),
-	BPF_JMP_REG(BPF_JNE, BPF_REG_3, BPF_REG_2, 1),
-	BPF_MOV32_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"MOD64 overflow, check 2",
-	.insns = {
-	BPF_LD_IMM64(BPF_REG_2, LLONG_MIN),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_MOD, BPF_REG_2, -1),
-	BPF_MOV32_IMM(BPF_REG_0, 0),
-	BPF_JMP_REG(BPF_JNE, BPF_REG_3, BPF_REG_2, 1),
-	BPF_MOV32_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.retval = 1,
-},
diff --git a/tools/testing/selftests/bpf/verifier/helper_access_var_len.c b/tools/testing/selftests/bpf/verifier/helper_access_var_len.c
deleted file mode 100644
index a6c869a7319c..000000000000
--- a/tools/testing/selftests/bpf/verifier/helper_access_var_len.c
+++ /dev/null
@@ -1,616 +0,0 @@
-{
-	"helper access to variable memory: stack, bitwise AND + JMP, correct bounds",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -64),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -56),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -48),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -40),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -32),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
-	BPF_MOV64_IMM(BPF_REG_2, 16),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 64),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to variable memory: stack, bitwise AND, zero included",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 64),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "invalid indirect read from stack R1 off -64+0 size 64",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to variable memory: stack, bitwise AND + JMP, wrong max",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 65),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "invalid indirect access to stack R1 off=-64 size=65",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to variable memory: stack, JMP, correct bounds",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -64),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -56),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -48),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -40),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -32),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
-	BPF_MOV64_IMM(BPF_REG_2, 16),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 64, 4),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to variable memory: stack, JMP (signed), correct bounds",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -64),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -56),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -48),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -40),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -32),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
-	BPF_MOV64_IMM(BPF_REG_2, 16),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, 64, 4),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to variable memory: stack, JMP, bounds + offset",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 64, 5),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 3),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "invalid indirect access to stack R1 off=-64 size=65",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to variable memory: stack, JMP, wrong max",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 65, 4),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "invalid indirect access to stack R1 off=-64 size=65",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to variable memory: stack, JMP, no max check",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_4, BPF_REG_2, 2),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	/* because max wasn't checked, signed min is negative */
-	.errstr = "R2 min value is negative, either use unsigned or 'var &= const'",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to variable memory: stack, JMP, no min check",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 64, 3),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "invalid indirect read from stack R1 off -64+0 size 64",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to variable memory: stack, JMP (signed), no min check",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, -128),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, -128),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, 64, 3),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R2 min value is negative",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to variable memory: map, JMP, correct bounds",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val)),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val), 4),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to variable memory: map, JMP, wrong max",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 8),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val) + 1, 4),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 4 },
-	.errstr = "invalid access to map value, value_size=48 off=0 size=49",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to variable memory: map adjusted, JMP, correct bounds",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 20),
-	BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val)),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val) - 20, 4),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to variable memory: map adjusted, JMP, wrong max",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 8),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 20),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_2, sizeof(struct test_val) - 19, 4),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_JMP_REG(BPF_JSGE, BPF_REG_4, BPF_REG_2, 2),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 4 },
-	.errstr = "R1 min value is outside of the allowed memory range",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to variable memory: size = 0 allowed on NULL (ARG_PTR_TO_MEM_OR_NULL)",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-	BPF_EMIT_CALL(BPF_FUNC_csum_diff),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"helper access to variable memory: size > 0 not allowed on NULL (ARG_PTR_TO_MEM_OR_NULL)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_1, 0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 64),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-	BPF_EMIT_CALL(BPF_FUNC_csum_diff),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 type=scalar expected=fp",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"helper access to variable memory: size = 0 allowed on != NULL stack pointer (ARG_PTR_TO_MEM_OR_NULL)",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 8),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-	BPF_EMIT_CALL(BPF_FUNC_csum_diff),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"helper access to variable memory: size = 0 allowed on != NULL map pointer (ARG_PTR_TO_MEM_OR_NULL)",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-	BPF_EMIT_CALL(BPF_FUNC_csum_diff),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"helper access to variable memory: size possible = 0 allowed on != NULL stack pointer (ARG_PTR_TO_MEM_OR_NULL)",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 8, 7),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-	BPF_EMIT_CALL(BPF_FUNC_csum_diff),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"helper access to variable memory: size possible = 0 allowed on != NULL map pointer (ARG_PTR_TO_MEM_OR_NULL)",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 8, 4),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-	BPF_EMIT_CALL(BPF_FUNC_csum_diff),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"helper access to variable memory: size possible = 0 allowed on != NULL packet pointer (ARG_PTR_TO_MEM_OR_NULL)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 7),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_6, 0),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 8, 4),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-	BPF_EMIT_CALL(BPF_FUNC_csum_diff),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.retval = 0 /* csum_diff of 64-byte packet */,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"helper access to variable memory: size = 0 not allowed on NULL (!ARG_PTR_TO_MEM_OR_NULL)",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 type=scalar expected=fp",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to variable memory: size > 0 not allowed on NULL (!ARG_PTR_TO_MEM_OR_NULL)",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_2, 1),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 type=scalar expected=fp",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to variable memory: size = 0 allowed on != NULL stack pointer (!ARG_PTR_TO_MEM_OR_NULL)",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to variable memory: size = 0 allowed on != NULL map pointer (!ARG_PTR_TO_MEM_OR_NULL)",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to variable memory: size possible = 0 allowed on != NULL stack pointer (!ARG_PTR_TO_MEM_OR_NULL)",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 8, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to variable memory: size possible = 0 allowed on != NULL map pointer (!ARG_PTR_TO_MEM_OR_NULL)",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_2, 8, 2),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to variable memory: 8 bytes leak",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -64),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -56),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -48),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -40),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 63),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "invalid indirect read from stack R1 off -64+32 size 64",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to variable memory: 8 bytes no leak (init memory)",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -64),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -56),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -48),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -40),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -32),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -64),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 32),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 32),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -16),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
diff --git a/tools/testing/selftests/bpf/verifier/helper_packet_access.c b/tools/testing/selftests/bpf/verifier/helper_packet_access.c
deleted file mode 100644
index ae54587e9829..000000000000
--- a/tools/testing/selftests/bpf/verifier/helper_packet_access.c
+++ /dev/null
@@ -1,460 +0,0 @@
-{
-	"helper access to packet: test1, valid packet_ptr range",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 5),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_2),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_update_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 5 },
-	.result_unpriv = ACCEPT,
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-},
-{
-	"helper access to packet: test2, unchecked packet_ptr",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 1 },
-	.result = REJECT,
-	.errstr = "invalid access to packet",
-	.prog_type = BPF_PROG_TYPE_XDP,
-},
-{
-	"helper access to packet: test3, variable add",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-			offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 10),
-	BPF_LDX_MEM(BPF_B, BPF_REG_5, BPF_REG_2, 0),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_5),
-	BPF_MOV64_REG(BPF_REG_5, BPF_REG_4),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_5, BPF_REG_3, 4),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 11 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-},
-{
-	"helper access to packet: test4, packet_ptr with bad range",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 7 },
-	.result = REJECT,
-	.errstr = "invalid access to packet",
-	.prog_type = BPF_PROG_TYPE_XDP,
-},
-{
-	"helper access to packet: test5, packet_ptr with too short range",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 7),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 3),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 6 },
-	.result = REJECT,
-	.errstr = "invalid access to packet",
-	.prog_type = BPF_PROG_TYPE_XDP,
-},
-{
-	"helper access to packet: test6, cls valid packet_ptr range",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 5),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_2),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_update_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 5 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"helper access to packet: test7, cls unchecked packet_ptr",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 1 },
-	.result = REJECT,
-	.errstr = "invalid access to packet",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"helper access to packet: test8, cls variable add",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-			offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-			offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 10),
-	BPF_LDX_MEM(BPF_B, BPF_REG_5, BPF_REG_2, 0),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_5),
-	BPF_MOV64_REG(BPF_REG_5, BPF_REG_4),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_5, BPF_REG_3, 4),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 11 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"helper access to packet: test9, cls packet_ptr with bad range",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 7 },
-	.result = REJECT,
-	.errstr = "invalid access to packet",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"helper access to packet: test10, cls packet_ptr with too short range",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 1),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 7),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 3),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 6 },
-	.result = REJECT,
-	.errstr = "invalid access to packet",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"helper access to packet: test11, cls unsuitable helper 1",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 7),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_7, 4),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 42),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_store_bytes),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "helper access to the packet",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"helper access to packet: test12, cls unsuitable helper 2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_7, 3),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "helper access to the packet",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"helper access to packet: test13, cls helper ok",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_7, 6),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_csum_diff),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"helper access to packet: test14, cls helper ok sub",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_7, 6),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 4),
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_csum_diff),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"helper access to packet: test15, cls helper fail sub",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_7, 6),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 12),
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_csum_diff),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid access to packet",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"helper access to packet: test16, cls helper fail range 1",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_7, 6),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_2, 8),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_csum_diff),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid access to packet",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"helper access to packet: test17, cls helper fail range 2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_7, 6),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_2, -9),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_csum_diff),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "R2 min value is negative",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"helper access to packet: test18, cls helper fail range 3",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_7, 6),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_2, ~0),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_csum_diff),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "R2 min value is negative",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"helper access to packet: test19, cls helper range zero",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_7, 6),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_csum_diff),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"helper access to packet: test20, pkt end as input",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_7, 6),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_csum_diff),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "R1 type=pkt_end expected=fp",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"helper access to packet: test21, wrong reg",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_7, 6),
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_csum_diff),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid access to packet",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
diff --git a/tools/testing/selftests/bpf/verifier/helper_restricted.c b/tools/testing/selftests/bpf/verifier/helper_restricted.c
deleted file mode 100644
index a067b7098b97..000000000000
--- a/tools/testing/selftests/bpf/verifier/helper_restricted.c
+++ /dev/null
@@ -1,196 +0,0 @@
-{
-	"bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_KPROBE",
-	.insns = {
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	},
-	.errstr = "unknown func bpf_ktime_get_coarse_ns",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_KPROBE,
-},
-{
-	"bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_TRACEPOINT",
-	.insns = {
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	},
-	.errstr = "unknown func bpf_ktime_get_coarse_ns",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_PERF_EVENT",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "unknown func bpf_ktime_get_coarse_ns",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_PERF_EVENT,
-},
-{
-	"bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "unknown func bpf_ktime_get_coarse_ns",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT,
-},
-{
-	"bpf_timer_init isn restricted in BPF_PROG_TYPE_KPROBE",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_3, 1),
-	BPF_EMIT_CALL(BPF_FUNC_timer_init),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_timer = { 3, 8 },
-	.errstr = "tracing progs cannot use bpf_timer yet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_KPROBE,
-},
-{
-	"bpf_timer_init is forbidden in BPF_PROG_TYPE_PERF_EVENT",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_3, 1),
-	BPF_EMIT_CALL(BPF_FUNC_timer_init),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_timer = { 3, 8 },
-	.errstr = "tracing progs cannot use bpf_timer yet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_PERF_EVENT,
-},
-{
-	"bpf_timer_init is forbidden in BPF_PROG_TYPE_TRACEPOINT",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_3, 1),
-	BPF_EMIT_CALL(BPF_FUNC_timer_init),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_timer = { 3, 8 },
-	.errstr = "tracing progs cannot use bpf_timer yet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"bpf_timer_init is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_3, 1),
-	BPF_EMIT_CALL(BPF_FUNC_timer_init),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_timer = { 3, 8 },
-	.errstr = "tracing progs cannot use bpf_timer yet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT,
-},
-{
-	"bpf_spin_lock is forbidden in BPF_PROG_TYPE_KPROBE",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_spin_lock),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_spin_lock = { 3 },
-	.errstr = "tracing progs cannot use bpf_spin_lock yet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_KPROBE,
-},
-{
-	"bpf_spin_lock is forbidden in BPF_PROG_TYPE_TRACEPOINT",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_spin_lock),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_spin_lock = { 3 },
-	.errstr = "tracing progs cannot use bpf_spin_lock yet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"bpf_spin_lock is forbidden in BPF_PROG_TYPE_PERF_EVENT",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_spin_lock),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_spin_lock = { 3 },
-	.errstr = "tracing progs cannot use bpf_spin_lock yet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_PERF_EVENT,
-},
-{
-	"bpf_spin_lock is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_spin_lock),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_spin_lock = { 3 },
-	.errstr = "tracing progs cannot use bpf_spin_lock yet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT,
-},
diff --git a/tools/testing/selftests/bpf/verifier/helper_value_access.c b/tools/testing/selftests/bpf/verifier/helper_value_access.c
deleted file mode 100644
index 1c7882ddfa63..000000000000
--- a/tools/testing/selftests/bpf/verifier/helper_value_access.c
+++ /dev/null
@@ -1,953 +0,0 @@
-{
-	"helper access to map: full range",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val)),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to map: partial range",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_2, 8),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to map: empty range",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_EMIT_CALL(BPF_FUNC_trace_printk),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "invalid access to map value, value_size=48 off=0 size=0",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to map: out-of-bound range",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_2, sizeof(struct test_val) + 8),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "invalid access to map value, value_size=48 off=0 size=56",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to map: negative range",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_2, -8),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "R2 min value is negative",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to adjusted map (via const imm): full range",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, offsetof(struct test_val, foo)),
-	BPF_MOV64_IMM(BPF_REG_2,
-		      sizeof(struct test_val) -	offsetof(struct test_val, foo)),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to adjusted map (via const imm): partial range",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, offsetof(struct test_val, foo)),
-	BPF_MOV64_IMM(BPF_REG_2, 8),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to adjusted map (via const imm): empty range",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, offsetof(struct test_val, foo)),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_EMIT_CALL(BPF_FUNC_trace_printk),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "invalid access to map value, value_size=48 off=4 size=0",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to adjusted map (via const imm): out-of-bound range",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, offsetof(struct test_val, foo)),
-	BPF_MOV64_IMM(BPF_REG_2,
-		      sizeof(struct test_val) - offsetof(struct test_val, foo) + 8),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "invalid access to map value, value_size=48 off=4 size=52",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to adjusted map (via const imm): negative range (> adjustment)",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, offsetof(struct test_val, foo)),
-	BPF_MOV64_IMM(BPF_REG_2, -8),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "R2 min value is negative",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to adjusted map (via const imm): negative range (< adjustment)",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, offsetof(struct test_val, foo)),
-	BPF_MOV64_IMM(BPF_REG_2, -1),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "R2 min value is negative",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to adjusted map (via const reg): full range",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_3, offsetof(struct test_val, foo)),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-	BPF_MOV64_IMM(BPF_REG_2,
-		      sizeof(struct test_val) - offsetof(struct test_val, foo)),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to adjusted map (via const reg): partial range",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_3, offsetof(struct test_val, foo)),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-	BPF_MOV64_IMM(BPF_REG_2, 8),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to adjusted map (via const reg): empty range",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_EMIT_CALL(BPF_FUNC_trace_printk),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "R1 min value is outside of the allowed memory range",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to adjusted map (via const reg): out-of-bound range",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_3, offsetof(struct test_val, foo)),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-	BPF_MOV64_IMM(BPF_REG_2,
-		      sizeof(struct test_val) -
-		      offsetof(struct test_val, foo) + 8),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "invalid access to map value, value_size=48 off=4 size=52",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to adjusted map (via const reg): negative range (> adjustment)",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_3, offsetof(struct test_val, foo)),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-	BPF_MOV64_IMM(BPF_REG_2, -8),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "R2 min value is negative",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to adjusted map (via const reg): negative range (< adjustment)",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_3, offsetof(struct test_val, foo)),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-	BPF_MOV64_IMM(BPF_REG_2, -1),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "R2 min value is negative",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to adjusted map (via variable): full range",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_3, offsetof(struct test_val, foo), 4),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-	BPF_MOV64_IMM(BPF_REG_2,
-		      sizeof(struct test_val) - offsetof(struct test_val, foo)),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to adjusted map (via variable): partial range",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_3, offsetof(struct test_val, foo), 4),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-	BPF_MOV64_IMM(BPF_REG_2, 8),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to adjusted map (via variable): empty range",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_3, offsetof(struct test_val, foo), 3),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_EMIT_CALL(BPF_FUNC_trace_printk),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "R1 min value is outside of the allowed memory range",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to adjusted map (via variable): no max check",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-	BPF_MOV64_IMM(BPF_REG_2, 1),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "R1 unbounded memory access",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to adjusted map (via variable): wrong max check",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_3, offsetof(struct test_val, foo), 4),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-	BPF_MOV64_IMM(BPF_REG_2,
-		      sizeof(struct test_val) -
-		      offsetof(struct test_val, foo) + 1),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "invalid access to map value, value_size=48 off=4 size=45",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to map: bounds check using <, good access",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JLT, BPF_REG_3, 32, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to map: bounds check using <, bad access",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JLT, BPF_REG_3, 32, 4),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.result = REJECT,
-	.errstr = "R1 unbounded memory access",
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to map: bounds check using <=, good access",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JLE, BPF_REG_3, 32, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to map: bounds check using <=, bad access",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JLE, BPF_REG_3, 32, 4),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.result = REJECT,
-	.errstr = "R1 unbounded memory access",
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to map: bounds check using s<, good access",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, 32, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, 0, -3),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to map: bounds check using s<, good access 2",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, 32, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, -3, -3),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to map: bounds check using s<, bad access",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, 32, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_JMP_IMM(BPF_JSLT, BPF_REG_3, -3, -3),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.result = REJECT,
-	.errstr = "R1 min value is negative",
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to map: bounds check using s<=, good access",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, 32, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, 0, -3),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to map: bounds check using s<=, good access 2",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, 32, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, -3, -3),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"helper access to map: bounds check using s<=, bad access",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, 32, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_JMP_IMM(BPF_JSLE, BPF_REG_3, -3, -3),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.result = REJECT,
-	.errstr = "R1 min value is negative",
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"map lookup helper access to map",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 3, 8 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"map update helper access to map",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_update_elem),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 3, 10 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"map update helper access to map: wrong size",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_update_elem),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.fixup_map_hash_16b = { 10 },
-	.result = REJECT,
-	.errstr = "invalid access to map value, value_size=8 off=0 size=16",
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"map helper access to adjusted map (via const imm)",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, offsetof(struct other_val, bar)),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 3, 9 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"map helper access to adjusted map (via const imm): out-of-bound 1",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, sizeof(struct other_val) - 4),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 3, 9 },
-	.result = REJECT,
-	.errstr = "invalid access to map value, value_size=16 off=12 size=8",
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"map helper access to adjusted map (via const imm): out-of-bound 2",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 3, 9 },
-	.result = REJECT,
-	.errstr = "invalid access to map value, value_size=16 off=-4 size=8",
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"map helper access to adjusted map (via const reg)",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_3, offsetof(struct other_val, bar)),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 3, 10 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"map helper access to adjusted map (via const reg): out-of-bound 1",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_3, sizeof(struct other_val) - 4),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 3, 10 },
-	.result = REJECT,
-	.errstr = "invalid access to map value, value_size=16 off=12 size=8",
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"map helper access to adjusted map (via const reg): out-of-bound 2",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_3, -4),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 3, 10 },
-	.result = REJECT,
-	.errstr = "invalid access to map value, value_size=16 off=-4 size=8",
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"map helper access to adjusted map (via variable)",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_3, offsetof(struct other_val, bar), 4),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 3, 11 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"map helper access to adjusted map (via variable): no max check",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 3, 10 },
-	.result = REJECT,
-	.errstr = "R2 unbounded memory access, make sure to bounds check any such access",
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"map helper access to adjusted map (via variable): wrong max check",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_3, offsetof(struct other_val, bar) + 1, 4),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 3, 11 },
-	.result = REJECT,
-	.errstr = "invalid access to map value, value_size=16 off=9 size=8",
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
diff --git a/tools/testing/selftests/bpf/verifier/int_ptr.c b/tools/testing/selftests/bpf/verifier/int_ptr.c
deleted file mode 100644
index 070893fb2900..000000000000
--- a/tools/testing/selftests/bpf/verifier/int_ptr.c
+++ /dev/null
@@ -1,160 +0,0 @@
-{
-	"ARG_PTR_TO_LONG uninitialized",
-	.insns = {
-		/* bpf_strtoul arg1 (buf) */
-		BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
-		BPF_MOV64_IMM(BPF_REG_0, 0x00303036),
-		BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
-
-		BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
-
-		/* bpf_strtoul arg2 (buf_len) */
-		BPF_MOV64_IMM(BPF_REG_2, 4),
-
-		/* bpf_strtoul arg3 (flags) */
-		BPF_MOV64_IMM(BPF_REG_3, 0),
-
-		/* bpf_strtoul arg4 (res) */
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
-		BPF_MOV64_REG(BPF_REG_4, BPF_REG_7),
-
-		/* bpf_strtoul() */
-		BPF_EMIT_CALL(BPF_FUNC_strtoul),
-
-		BPF_MOV64_IMM(BPF_REG_0, 1),
-		BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_CGROUP_SYSCTL,
-	.errstr = "invalid indirect read from stack R4 off -16+0 size 8",
-},
-{
-	"ARG_PTR_TO_LONG half-uninitialized",
-	.insns = {
-		/* bpf_strtoul arg1 (buf) */
-		BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
-		BPF_MOV64_IMM(BPF_REG_0, 0x00303036),
-		BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
-
-		BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
-
-		/* bpf_strtoul arg2 (buf_len) */
-		BPF_MOV64_IMM(BPF_REG_2, 4),
-
-		/* bpf_strtoul arg3 (flags) */
-		BPF_MOV64_IMM(BPF_REG_3, 0),
-
-		/* bpf_strtoul arg4 (res) */
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
-		BPF_STX_MEM(BPF_W, BPF_REG_7, BPF_REG_0, 0),
-		BPF_MOV64_REG(BPF_REG_4, BPF_REG_7),
-
-		/* bpf_strtoul() */
-		BPF_EMIT_CALL(BPF_FUNC_strtoul),
-
-		BPF_MOV64_IMM(BPF_REG_0, 1),
-		BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_CGROUP_SYSCTL,
-	.errstr = "invalid indirect read from stack R4 off -16+4 size 8",
-},
-{
-	"ARG_PTR_TO_LONG misaligned",
-	.insns = {
-		/* bpf_strtoul arg1 (buf) */
-		BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
-		BPF_MOV64_IMM(BPF_REG_0, 0x00303036),
-		BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
-
-		BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
-
-		/* bpf_strtoul arg2 (buf_len) */
-		BPF_MOV64_IMM(BPF_REG_2, 4),
-
-		/* bpf_strtoul arg3 (flags) */
-		BPF_MOV64_IMM(BPF_REG_3, 0),
-
-		/* bpf_strtoul arg4 (res) */
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -12),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_STX_MEM(BPF_W, BPF_REG_7, BPF_REG_0, 0),
-		BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 4),
-		BPF_MOV64_REG(BPF_REG_4, BPF_REG_7),
-
-		/* bpf_strtoul() */
-		BPF_EMIT_CALL(BPF_FUNC_strtoul),
-
-		BPF_MOV64_IMM(BPF_REG_0, 1),
-		BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_CGROUP_SYSCTL,
-	.errstr = "misaligned stack access off (0x0; 0x0)+-20+0 size 8",
-},
-{
-	"ARG_PTR_TO_LONG size < sizeof(long)",
-	.insns = {
-		/* bpf_strtoul arg1 (buf) */
-		BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -16),
-		BPF_MOV64_IMM(BPF_REG_0, 0x00303036),
-		BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
-
-		BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
-
-		/* bpf_strtoul arg2 (buf_len) */
-		BPF_MOV64_IMM(BPF_REG_2, 4),
-
-		/* bpf_strtoul arg3 (flags) */
-		BPF_MOV64_IMM(BPF_REG_3, 0),
-
-		/* bpf_strtoul arg4 (res) */
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 12),
-		BPF_STX_MEM(BPF_W, BPF_REG_7, BPF_REG_0, 0),
-		BPF_MOV64_REG(BPF_REG_4, BPF_REG_7),
-
-		/* bpf_strtoul() */
-		BPF_EMIT_CALL(BPF_FUNC_strtoul),
-
-		BPF_MOV64_IMM(BPF_REG_0, 1),
-		BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_CGROUP_SYSCTL,
-	.errstr = "invalid indirect access to stack R4 off=-4 size=8",
-},
-{
-	"ARG_PTR_TO_LONG initialized",
-	.insns = {
-		/* bpf_strtoul arg1 (buf) */
-		BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
-		BPF_MOV64_IMM(BPF_REG_0, 0x00303036),
-		BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
-
-		BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
-
-		/* bpf_strtoul arg2 (buf_len) */
-		BPF_MOV64_IMM(BPF_REG_2, 4),
-
-		/* bpf_strtoul arg3 (flags) */
-		BPF_MOV64_IMM(BPF_REG_3, 0),
-
-		/* bpf_strtoul arg4 (res) */
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -8),
-		BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
-		BPF_MOV64_REG(BPF_REG_4, BPF_REG_7),
-
-		/* bpf_strtoul() */
-		BPF_EMIT_CALL(BPF_FUNC_strtoul),
-
-		BPF_MOV64_IMM(BPF_REG_0, 1),
-		BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_CGROUP_SYSCTL,
-},
diff --git a/tools/testing/selftests/bpf/verifier/jeq_infer_not_null.c b/tools/testing/selftests/bpf/verifier/jeq_infer_not_null.c
deleted file mode 100644
index 67a1c07ead34..000000000000
--- a/tools/testing/selftests/bpf/verifier/jeq_infer_not_null.c
+++ /dev/null
@@ -1,174 +0,0 @@
-{
-	/* This is equivalent to the following program:
-	 *
-	 *   r6 = skb->sk;
-	 *   r7 = sk_fullsock(r6);
-	 *   r0 = sk_fullsock(r6);
-	 *   if (r0 == 0) return 0;    (a)
-	 *   if (r0 != r7) return 0;   (b)
-	 *   *r7->type;                (c)
-	 *   return 0;
-	 *
-	 * It is safe to dereference r7 at point (c), because of (a) and (b).
-	 * The test verifies that relation r0 == r7 is propagated from (b) to (c).
-	 */
-	"jne/jeq infer not null, PTR_TO_SOCKET_OR_NULL -> PTR_TO_SOCKET for JNE false branch",
-	.insns = {
-	/* r6 = skb->sk; */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	/* if (r6 == 0) return 0; */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 8),
-	/* r7 = sk_fullsock(skb); */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	/* r0 = sk_fullsock(skb); */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	/* if (r0 == null) return 0; */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	/* if (r0 == r7) r0 = *(r7->type); */
-	BPF_JMP_REG(BPF_JNE, BPF_REG_0, BPF_REG_7, 1), /* Use ! JNE ! */
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, offsetof(struct bpf_sock, type)),
-	/* return 0 */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R7 pointer comparison",
-},
-{
-	/* Same as above, but verify that another branch of JNE still
-	 * prohibits access to PTR_MAYBE_NULL.
-	 */
-	"jne/jeq infer not null, PTR_TO_SOCKET_OR_NULL unchanged for JNE true branch",
-	.insns = {
-	/* r6 = skb->sk */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	/* if (r6 == 0) return 0; */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 9),
-	/* r7 = sk_fullsock(skb); */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	/* r0 = sk_fullsock(skb); */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	/* if (r0 == null) return 0; */
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
-	/* if (r0 == r7) return 0; */
-	BPF_JMP_REG(BPF_JNE, BPF_REG_0, BPF_REG_7, 1), /* Use ! JNE ! */
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	/* r0 = *(r7->type); */
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, offsetof(struct bpf_sock, type)),
-	/* return 0 */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = REJECT,
-	.errstr = "R7 invalid mem access 'sock_or_null'",
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R7 pointer comparison",
-},
-{
-	/* Same as a first test, but not null should be inferred for JEQ branch */
-	"jne/jeq infer not null, PTR_TO_SOCKET_OR_NULL -> PTR_TO_SOCKET for JEQ true branch",
-	.insns = {
-	/* r6 = skb->sk; */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	/* if (r6 == null) return 0; */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 9),
-	/* r7 = sk_fullsock(skb); */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	/* r0 = sk_fullsock(skb); */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	/* if (r0 == null) return 0; */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
-	/* if (r0 != r7) return 0; */
-	BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_7, 1), /* Use ! JEQ ! */
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	/* r0 = *(r7->type); */
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, offsetof(struct bpf_sock, type)),
-	/* return 0; */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R7 pointer comparison",
-},
-{
-	/* Same as above, but verify that another branch of JNE still
-	 * prohibits access to PTR_MAYBE_NULL.
-	 */
-	"jne/jeq infer not null, PTR_TO_SOCKET_OR_NULL unchanged for JEQ false branch",
-	.insns = {
-	/* r6 = skb->sk; */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	/* if (r6 == null) return 0; */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 8),
-	/* r7 = sk_fullsock(skb); */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	/* r0 = sk_fullsock(skb); */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	/* if (r0 == null) return 0; */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	/* if (r0 != r7) r0 = *(r7->type); */
-	BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_7, 1), /* Use ! JEQ ! */
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, offsetof(struct bpf_sock, type)),
-	/* return 0; */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = REJECT,
-	.errstr = "R7 invalid mem access 'sock_or_null'",
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R7 pointer comparison",
-},
-{
-	/* Maps are treated in a different branch of `mark_ptr_not_null_reg`,
-	 * so separate test for maps case.
-	 */
-	"jne/jeq infer not null, PTR_TO_MAP_VALUE_OR_NULL -> PTR_TO_MAP_VALUE",
-	.insns = {
-	/* r9 = &some stack to use as key */
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_9, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_9, -8),
-	/* r8 = process local map */
-	BPF_LD_MAP_FD(BPF_REG_8, 0),
-	/* r6 = map_lookup_elem(r8, r9); */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_9),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	/* r7 = map_lookup_elem(r8, r9); */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_9),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	/* if (r6 == 0) return 0; */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 2),
-	/* if (r6 != r7) return 0; */
-	BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_7, 1),
-	/* read *r7; */
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, offsetof(struct bpf_xdp_sock, queue_id)),
-	/* return 0; */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_xskmap = { 3 },
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.result = ACCEPT,
-},
diff --git a/tools/testing/selftests/bpf/verifier/jmp32.c b/tools/testing/selftests/bpf/verifier/jmp32.c
index 1a27a6210554..91d83e9cb148 100644
--- a/tools/testing/selftests/bpf/verifier/jmp32.c
+++ b/tools/testing/selftests/bpf/verifier/jmp32.c
@@ -84,11 +84,10 @@
 	BPF_JMP32_IMM(BPF_JSET, BPF_REG_7, 0x10, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP32_IMM(BPF_JGE, BPF_REG_7, 0x10, 1),
+	/* unpriv: nospec (inserted to prevent "R9 !read_ok") */
 	BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R9 !read_ok",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
 {
@@ -149,11 +148,10 @@
 	BPF_JMP32_IMM(BPF_JEQ, BPF_REG_7, 0x10, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP32_IMM(BPF_JSGE, BPF_REG_7, 0xf, 1),
+	/* unpriv: nospec (inserted to prevent "R9 !read_ok") */
 	BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R9 !read_ok",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
 {
@@ -214,11 +212,10 @@
 	BPF_JMP32_IMM(BPF_JNE, BPF_REG_7, 0x10, 1),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x10, 1),
 	BPF_EXIT_INSN(),
+	/* unpriv: nospec (inserted to prevent "R9 !read_ok") */
 	BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R9 !read_ok",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
 {
@@ -283,13 +280,13 @@
 	BPF_JMP32_REG(BPF_JGE, BPF_REG_7, BPF_REG_8, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP32_IMM(BPF_JGE, BPF_REG_7, 0x7ffffff0, 1),
+	/* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R0 invalid mem access 'scalar'",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jgt32: BPF_K",
@@ -353,13 +350,13 @@
 	BPF_JMP32_REG(BPF_JGT, BPF_REG_7, BPF_REG_8, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP_IMM(BPF_JGT, BPF_REG_7, 0x7ffffff0, 1),
+	/* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R0 invalid mem access 'scalar'",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jle32: BPF_K",
@@ -423,13 +420,13 @@
 	BPF_JMP32_REG(BPF_JLE, BPF_REG_7, BPF_REG_8, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP32_IMM(BPF_JLE, BPF_REG_7, 0x7ffffff0, 1),
+	/* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R0 invalid mem access 'scalar'",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jlt32: BPF_K",
@@ -493,13 +490,13 @@
 	BPF_JMP32_REG(BPF_JLT, BPF_REG_7, BPF_REG_8, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0x7ffffff0, 1),
+	/* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R0 invalid mem access 'scalar'",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jsge32: BPF_K",
@@ -563,13 +560,13 @@
 	BPF_JMP32_REG(BPF_JSGE, BPF_REG_7, BPF_REG_8, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0x7ffffff0, 1),
+	/* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R0 invalid mem access 'scalar'",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jsgt32: BPF_K",
@@ -633,13 +630,13 @@
 	BPF_JMP32_REG(BPF_JSGT, BPF_REG_7, BPF_REG_8, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP_IMM(BPF_JSGT, BPF_REG_7, -2, 1),
+	/* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R0 invalid mem access 'scalar'",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jsle32: BPF_K",
@@ -703,13 +700,13 @@
 	BPF_JMP32_REG(BPF_JSLE, BPF_REG_7, BPF_REG_8, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP_IMM(BPF_JSLE, BPF_REG_7, 0x7ffffff0, 1),
+	/* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R0 invalid mem access 'scalar'",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jslt32: BPF_K",
@@ -773,13 +770,13 @@
 	BPF_JMP32_REG(BPF_JSLT, BPF_REG_7, BPF_REG_8, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP32_IMM(BPF_JSLT, BPF_REG_7, -1, 1),
+	/* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R0 invalid mem access 'scalar'",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jgt32: range bound deduction, reg op imm",
diff --git a/tools/testing/selftests/bpf/verifier/jset.c b/tools/testing/selftests/bpf/verifier/jset.c
index 11fc68da735e..e901eefd774a 100644
--- a/tools/testing/selftests/bpf/verifier/jset.c
+++ b/tools/testing/selftests/bpf/verifier/jset.c
@@ -78,12 +78,11 @@
 	.insns = {
 	BPF_MOV64_IMM(BPF_REG_0, 1),
 	BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 1, 1),
+	/* unpriv: nospec (inserted to prevent "R9 !read_ok") */
 	BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
-	.errstr_unpriv = "R9 !read_ok",
-	.result_unpriv = REJECT,
 	.retval = 1,
 	.result = ACCEPT,
 },
@@ -136,13 +135,12 @@
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
 	BPF_ALU64_IMM(BPF_OR, BPF_REG_0, 2),
 	BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 3, 1),
+	/* unpriv: nospec (inserted to prevent "R9 !read_ok") */
 	BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
-	.errstr_unpriv = "R9 !read_ok",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
 {
@@ -154,16 +152,16 @@
 	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xff),
 	BPF_JMP_IMM(BPF_JSET, BPF_REG_1, 0xf0, 3),
 	BPF_JMP_IMM(BPF_JLT, BPF_REG_1, 0x10, 1),
+	/* unpriv: nospec (inserted to prevent "R9 !read_ok") */
 	BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
 	BPF_EXIT_INSN(),
 	BPF_JMP_IMM(BPF_JSET, BPF_REG_1, 0x10, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0x10, 1),
+	/* unpriv: nospec (inserted to prevent "R9 !read_ok") */
 	BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
-	.errstr_unpriv = "R9 !read_ok",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
diff --git a/tools/testing/selftests/bpf/verifier/ld_imm64.c b/tools/testing/selftests/bpf/verifier/ld_imm64.c
index f9297900cea6..78f19c255f20 100644
--- a/tools/testing/selftests/bpf/verifier/ld_imm64.c
+++ b/tools/testing/selftests/bpf/verifier/ld_imm64.c
@@ -9,8 +9,8 @@
 	BPF_MOV64_IMM(BPF_REG_0, 2),
 	BPF_EXIT_INSN(),
 	},
-	.errstr = "invalid BPF_LD_IMM insn",
-	.errstr_unpriv = "R1 pointer comparison",
+	.errstr = "jump into the middle of ldimm64 insn 1",
+	.errstr_unpriv = "jump into the middle of ldimm64 insn 1",
 	.result = REJECT,
 },
 {
@@ -23,8 +23,8 @@
 	BPF_LD_IMM64(BPF_REG_0, 1),
 	BPF_EXIT_INSN(),
 	},
-	.errstr = "invalid BPF_LD_IMM insn",
-	.errstr_unpriv = "R1 pointer comparison",
+	.errstr = "jump into the middle of ldimm64 insn 1",
+	.errstr_unpriv = "jump into the middle of ldimm64 insn 1",
 	.result = REJECT,
 },
 {
diff --git a/tools/testing/selftests/bpf/verifier/ld_ind.c b/tools/testing/selftests/bpf/verifier/ld_ind.c
deleted file mode 100644
index 079734227538..000000000000
--- a/tools/testing/selftests/bpf/verifier/ld_ind.c
+++ /dev/null
@@ -1,72 +0,0 @@
-{
-	"ld_ind: check calling conv, r1",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_MOV64_IMM(BPF_REG_1, 1),
-	BPF_LD_IND(BPF_W, BPF_REG_1, -0x200000),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 !read_ok",
-	.result = REJECT,
-},
-{
-	"ld_ind: check calling conv, r2",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_MOV64_IMM(BPF_REG_2, 1),
-	BPF_LD_IND(BPF_W, BPF_REG_2, -0x200000),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R2 !read_ok",
-	.result = REJECT,
-},
-{
-	"ld_ind: check calling conv, r3",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_MOV64_IMM(BPF_REG_3, 1),
-	BPF_LD_IND(BPF_W, BPF_REG_3, -0x200000),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_3),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R3 !read_ok",
-	.result = REJECT,
-},
-{
-	"ld_ind: check calling conv, r4",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_MOV64_IMM(BPF_REG_4, 1),
-	BPF_LD_IND(BPF_W, BPF_REG_4, -0x200000),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_4),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R4 !read_ok",
-	.result = REJECT,
-},
-{
-	"ld_ind: check calling conv, r5",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_MOV64_IMM(BPF_REG_5, 1),
-	BPF_LD_IND(BPF_W, BPF_REG_5, -0x200000),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_5),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R5 !read_ok",
-	.result = REJECT,
-},
-{
-	"ld_ind: check calling conv, r7",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_MOV64_IMM(BPF_REG_7, 1),
-	BPF_LD_IND(BPF_W, BPF_REG_7, -0x200000),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 1,
-},
diff --git a/tools/testing/selftests/bpf/verifier/leak_ptr.c b/tools/testing/selftests/bpf/verifier/leak_ptr.c
deleted file mode 100644
index 73f0dea95546..000000000000
--- a/tools/testing/selftests/bpf/verifier/leak_ptr.c
+++ /dev/null
@@ -1,67 +0,0 @@
-{
-	"leak pointer into ctx 1",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
-		    offsetof(struct __sk_buff, cb[0])),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_1, BPF_REG_2,
-		      offsetof(struct __sk_buff, cb[0])),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 2 },
-	.errstr_unpriv = "R2 leaks addr into mem",
-	.result_unpriv = REJECT,
-	.result = REJECT,
-	.errstr = "BPF_ATOMIC stores into R1 ctx is not allowed",
-},
-{
-	"leak pointer into ctx 2",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
-		    offsetof(struct __sk_buff, cb[0])),
-	BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_1, BPF_REG_10,
-		      offsetof(struct __sk_buff, cb[0])),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R10 leaks addr into mem",
-	.result_unpriv = REJECT,
-	.result = REJECT,
-	.errstr = "BPF_ATOMIC stores into R1 ctx is not allowed",
-},
-{
-	"leak pointer into ctx 3",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2,
-		      offsetof(struct __sk_buff, cb[0])),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 1 },
-	.errstr_unpriv = "R2 leaks addr into ctx",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-},
-{
-	"leak pointer into map val",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0),
-	BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_0, BPF_REG_6, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 4 },
-	.errstr_unpriv = "R6 leaks addr into mem",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-},
diff --git a/tools/testing/selftests/bpf/verifier/loops1.c b/tools/testing/selftests/bpf/verifier/loops1.c
deleted file mode 100644
index 1af37187dc12..000000000000
--- a/tools/testing/selftests/bpf/verifier/loops1.c
+++ /dev/null
@@ -1,206 +0,0 @@
-{
-	"bounded loop, count to 4",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
-	BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -2),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-	.retval = 4,
-},
-{
-	"bounded loop, count to 20",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 3),
-	BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 20, -2),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"bounded loop, count from positive unknown to 4",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_JMP_IMM(BPF_JSLT, BPF_REG_0, 0, 2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
-	BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -2),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-	.retval = 4,
-},
-{
-	"bounded loop, count from totally unknown to 4",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
-	BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -2),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"bounded loop, count to 4 with equality",
-	.insns = {
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 4, -2),
-		BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"bounded loop, start in the middle",
-	.insns = {
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_JMP_A(1),
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
-		BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -2),
-		BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "back-edge",
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-	.retval = 4,
-},
-{
-	"bounded loop containing a forward jump",
-	.insns = {
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
-		BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_0, 0),
-		BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -3),
-		BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-	.retval = 4,
-},
-{
-	"bounded loop that jumps out rather than in",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_6, 0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_6, 10000, 2),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_JMP_A(-4),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"infinite loop after a conditional jump",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 5),
-	BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, 2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
-	BPF_JMP_A(-2),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "program is too large",
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"bounded recursion",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_JMP_IMM(BPF_JLT, BPF_REG_1, 4, 1),
-	BPF_EXIT_INSN(),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -5),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "back-edge",
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"infinite loop in two jumps",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_JMP_A(0),
-	BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 4, -2),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "loop detected",
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"infinite loop: three-jump trick",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
-	BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 2, 1),
-	BPF_EXIT_INSN(),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
-	BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 2, 1),
-	BPF_EXIT_INSN(),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
-	BPF_JMP_IMM(BPF_JLT, BPF_REG_0, 2, -11),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "loop detected",
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"not-taken loop with back jump to 1st insn",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 123),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 4, -2),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.retval = 123,
-},
-{
-	"taken loop with back jump to 1st insn",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 10),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 1),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, -3),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.retval = 55,
-},
-{
-	"taken loop with back jump to 1st insn, 2",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 10),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 1),
-	BPF_JMP32_IMM(BPF_JNE, BPF_REG_1, 0, -3),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.retval = 55,
-},
diff --git a/tools/testing/selftests/bpf/verifier/lwt.c b/tools/testing/selftests/bpf/verifier/lwt.c
deleted file mode 100644
index 5c8944d0b091..000000000000
--- a/tools/testing/selftests/bpf/verifier/lwt.c
+++ /dev/null
@@ -1,189 +0,0 @@
-{
-	"invalid direct packet write for LWT_IN",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	BPF_STX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "cannot write into packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_LWT_IN,
-},
-{
-	"invalid direct packet write for LWT_OUT",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	BPF_STX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "cannot write into packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_LWT_OUT,
-},
-{
-	"direct packet write for LWT_XMIT",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	BPF_STX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_LWT_XMIT,
-},
-{
-	"direct packet read for LWT_IN",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_LWT_IN,
-},
-{
-	"direct packet read for LWT_OUT",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_LWT_OUT,
-},
-{
-	"direct packet read for LWT_XMIT",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_LWT_XMIT,
-},
-{
-	"overlapping checks for direct packet access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_2, 6),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_LWT_XMIT,
-},
-{
-	"make headroom for LWT_XMIT",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_MOV64_IMM(BPF_REG_2, 34),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_skb_change_head),
-	/* split for s390 to succeed */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_2, 42),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_EMIT_CALL(BPF_FUNC_skb_change_head),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_LWT_XMIT,
-},
-{
-	"invalid access of tc_classid for LWT_IN",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, tc_classid)),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid bpf_context access",
-},
-{
-	"invalid access of tc_classid for LWT_OUT",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, tc_classid)),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid bpf_context access",
-},
-{
-	"invalid access of tc_classid for LWT_XMIT",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, tc_classid)),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid bpf_context access",
-},
-{
-	"check skb->tc_classid half load not permitted for lwt prog",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
-	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, tc_classid)),
-#else
-	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, tc_classid) + 2),
-#endif
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid bpf_context access",
-	.prog_type = BPF_PROG_TYPE_LWT_IN,
-},
diff --git a/tools/testing/selftests/bpf/verifier/map_in_map.c b/tools/testing/selftests/bpf/verifier/map_in_map.c
deleted file mode 100644
index 128a348b762d..000000000000
--- a/tools/testing/selftests/bpf/verifier/map_in_map.c
+++ /dev/null
@@ -1,96 +0,0 @@
-{
-	"map in map access",
-	.insns = {
-	BPF_ST_MEM(0, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
-	BPF_ST_MEM(0, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_in_map = { 3 },
-	.result = ACCEPT,
-},
-{
-	"map in map state pruning",
-	.insns = {
-	BPF_ST_MEM(0, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -4),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 11),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_6),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_in_map = { 4, 14 },
-	.flags = BPF_F_TEST_STATE_FREQ,
-	.result = VERBOSE_ACCEPT,
-	.errstr = "processed 25 insns",
-	.prog_type = BPF_PROG_TYPE_XDP,
-},
-{
-	"invalid inner map pointer",
-	.insns = {
-	BPF_ST_MEM(0, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_ST_MEM(0, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_in_map = { 3 },
-	.errstr = "R1 pointer arithmetic on map_ptr prohibited",
-	.result = REJECT,
-},
-{
-	"forgot null checking on the inner map pointer",
-	.insns = {
-	BPF_ST_MEM(0, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_ST_MEM(0, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_in_map = { 3 },
-	.errstr = "R1 type=map_value_or_null expected=map_ptr",
-	.result = REJECT,
-},
diff --git a/tools/testing/selftests/bpf/verifier/map_kptr.c b/tools/testing/selftests/bpf/verifier/map_kptr.c
index 6914904344c0..4b39f8472f9b 100644
--- a/tools/testing/selftests/bpf/verifier/map_kptr.c
+++ b/tools/testing/selftests/bpf/verifier/map_kptr.c
@@ -68,6 +68,7 @@
 	.fixup_map_kptr = { 1 },
 	.result = REJECT,
 	.errstr = "kptr access cannot have variable offset",
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"map_kptr: bpf_kptr_xchg non-const var_off",
@@ -121,6 +122,7 @@
 	.fixup_map_kptr = { 1 },
 	.result = REJECT,
 	.errstr = "kptr access misaligned expected=0 off=7",
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"map_kptr: reject var_off != 0",
@@ -151,7 +153,7 @@
 	.result = REJECT,
 	.errstr = "variable untrusted_ptr_ access var_off=(0x0; 0x7) disallowed",
 },
-/* Tests for unreferened PTR_TO_BTF_ID */
+/* Tests for unreferenced PTR_TO_BTF_ID */
 {
 	"map_kptr: unref: reject btf_struct_ids_match == false",
 	.insns = {
@@ -288,33 +290,6 @@
 	.result = REJECT,
 	.errstr = "off=0 kptr isn't referenced kptr",
 },
-{
-	"map_kptr: unref: bpf_kfunc_call_test_kptr_get rejected",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_LD_MAP_FD(BPF_REG_6, 0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.fixup_map_kptr = { 1 },
-	.result = REJECT,
-	.errstr = "arg#0 no referenced kptr at map value offset=0",
-	.fixup_kfunc_btf_id = {
-		{ "bpf_kfunc_call_test_kptr_get", 13 },
-	}
-},
 /* Tests for referenced PTR_TO_BTF_ID */
 {
 	"map_kptr: ref: loaded pointer marked as untrusted",
@@ -336,7 +311,7 @@
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.fixup_map_kptr = { 1 },
 	.result = REJECT,
-	.errstr = "R1 type=untrusted_ptr_or_null_ expected=percpu_ptr_",
+	.errstr = "R1 type=rcu_ptr_or_null_ expected=percpu_ptr_",
 },
 {
 	"map_kptr: ref: reject off != 0",
@@ -398,7 +373,7 @@
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.fixup_map_kptr = { 1 },
 	.result = REJECT,
-	.errstr = "Unreleased reference id=5 alloc_insn=20",
+	.errstr = "Unreleased reference id=4 alloc_insn=20",
 	.fixup_kfunc_btf_id = {
 		{ "bpf_kfunc_call_test_acquire", 15 },
 	}
diff --git a/tools/testing/selftests/bpf/verifier/map_ptr.c b/tools/testing/selftests/bpf/verifier/map_ptr.c
deleted file mode 100644
index 17ee84dc7766..000000000000
--- a/tools/testing/selftests/bpf/verifier/map_ptr.c
+++ /dev/null
@@ -1,99 +0,0 @@
-{
-	"bpf_map_ptr: read with negative offset rejected",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 1 },
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN",
-	.result = REJECT,
-	.errstr = "R1 is bpf_array invalid negative access: off=-8",
-},
-{
-	"bpf_map_ptr: write rejected",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN",
-	.result = REJECT,
-	.errstr = "only read from bpf_array is supported",
-},
-{
-	"bpf_map_ptr: read non-existent field rejected",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_6, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, 1),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 1 },
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN",
-	.result = REJECT,
-	.errstr = "cannot access ptr member ops with moff 0 in struct bpf_map with off 1 size 4",
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"bpf_map_ptr: read ops field accepted",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_6, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 1 },
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN",
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"bpf_map_ptr: r = 0, map_ptr = map_ptr + r",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 4 },
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R1 has pointer with unsupported alu operation",
-	.result = ACCEPT,
-},
-{
-	"bpf_map_ptr: r = 0, r = r + map_ptr",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_MOV64_IMM(BPF_REG_1, 0),
-	BPF_LD_MAP_FD(BPF_REG_0, 0),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 4 },
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R0 has pointer with unsupported alu operation",
-	.result = ACCEPT,
-},
diff --git a/tools/testing/selftests/bpf/verifier/map_ptr_mixing.c b/tools/testing/selftests/bpf/verifier/map_ptr_mixing.c
deleted file mode 100644
index 1f2b8c4cb26d..000000000000
--- a/tools/testing/selftests/bpf/verifier/map_ptr_mixing.c
+++ /dev/null
@@ -1,100 +0,0 @@
-{
-	"calls: two calls returning different map pointers for lookup (hash, array)",
-	.insns = {
-	/* main prog */
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_CALL_REL(11),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_CALL_REL(12),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, offsetof(struct test_val, foo)),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	/* subprog 1 */
-	BPF_LD_MAP_FD(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	/* subprog 2 */
-	BPF_LD_MAP_FD(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.fixup_map_hash_48b = { 13 },
-	.fixup_map_array_48b = { 16 },
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"calls: two calls returning different map pointers for lookup (hash, map in map)",
-	.insns = {
-	/* main prog */
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_CALL_REL(11),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_CALL_REL(12),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, offsetof(struct test_val, foo)),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	/* subprog 1 */
-	BPF_LD_MAP_FD(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	/* subprog 2 */
-	BPF_LD_MAP_FD(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.fixup_map_in_map = { 16 },
-	.fixup_map_array_48b = { 13 },
-	.result = REJECT,
-	.errstr = "only read from bpf_array is supported",
-},
-{
-	"cond: two branches returning different map pointers for lookup (tail, tail)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, mark)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 0, 3),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 2),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_3, 7),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_prog1 = { 5 },
-	.fixup_prog2 = { 2 },
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "tail_call abusing map_ptr",
-	.result = ACCEPT,
-	.retval = 42,
-},
-{
-	"cond: two branches returning same map pointers for lookup (tail, tail)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
-		    offsetof(struct __sk_buff, mark)),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 3),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 2),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_3, 7),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_prog2 = { 2, 5 },
-	.result_unpriv = ACCEPT,
-	.result = ACCEPT,
-	.retval = 42,
-},
diff --git a/tools/testing/selftests/bpf/verifier/map_ret_val.c b/tools/testing/selftests/bpf/verifier/map_ret_val.c
deleted file mode 100644
index bdd0e8d18333..000000000000
--- a/tools/testing/selftests/bpf/verifier/map_ret_val.c
+++ /dev/null
@@ -1,65 +0,0 @@
-{
-	"invalid map_fd for function call",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_delete_elem),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "fd 0 is not pointing to valid bpf_map",
-	.result = REJECT,
-},
-{
-	"don't check return value before access",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "R0 invalid mem access 'map_value_or_null'",
-	.result = REJECT,
-},
-{
-	"access memory with incorrect alignment",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 4, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "misaligned value access",
-	.result = REJECT,
-	.flags = F_LOAD_WITH_STRICT_ALIGNMENT,
-},
-{
-	"sometimes access memory with incorrect alignment",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
-	BPF_EXIT_INSN(),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "R0 invalid mem access",
-	.errstr_unpriv = "R0 leaks addr",
-	.result = REJECT,
-	.flags = F_LOAD_WITH_STRICT_ALIGNMENT,
-},
diff --git a/tools/testing/selftests/bpf/verifier/masking.c b/tools/testing/selftests/bpf/verifier/masking.c
deleted file mode 100644
index 6e1358c544fd..000000000000
--- a/tools/testing/selftests/bpf/verifier/masking.c
+++ /dev/null
@@ -1,322 +0,0 @@
-{
-	"masking, test out of bounds 1",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_1, 5),
-	BPF_MOV32_IMM(BPF_REG_2, 5 - 1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63),
-	BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"masking, test out of bounds 2",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_1, 1),
-	BPF_MOV32_IMM(BPF_REG_2, 1 - 1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63),
-	BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"masking, test out of bounds 3",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_1, 0xffffffff),
-	BPF_MOV32_IMM(BPF_REG_2, 0xffffffff - 1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63),
-	BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"masking, test out of bounds 4",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_1, 0xffffffff),
-	BPF_MOV32_IMM(BPF_REG_2, 1 - 1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63),
-	BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"masking, test out of bounds 5",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_1, -1),
-	BPF_MOV32_IMM(BPF_REG_2, 1 - 1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63),
-	BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"masking, test out of bounds 6",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_1, -1),
-	BPF_MOV32_IMM(BPF_REG_2, 0xffffffff - 1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63),
-	BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"masking, test out of bounds 7",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 5),
-	BPF_MOV32_IMM(BPF_REG_2, 5 - 1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63),
-	BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"masking, test out of bounds 8",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 1),
-	BPF_MOV32_IMM(BPF_REG_2, 1 - 1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63),
-	BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"masking, test out of bounds 9",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 0xffffffff),
-	BPF_MOV32_IMM(BPF_REG_2, 0xffffffff - 1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63),
-	BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"masking, test out of bounds 10",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 0xffffffff),
-	BPF_MOV32_IMM(BPF_REG_2, 1 - 1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63),
-	BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"masking, test out of bounds 11",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, -1),
-	BPF_MOV32_IMM(BPF_REG_2, 1 - 1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63),
-	BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"masking, test out of bounds 12",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, -1),
-	BPF_MOV32_IMM(BPF_REG_2, 0xffffffff - 1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63),
-	BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"masking, test in bounds 1",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_1, 4),
-	BPF_MOV32_IMM(BPF_REG_2, 5 - 1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63),
-	BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 4,
-},
-{
-	"masking, test in bounds 2",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_1, 0),
-	BPF_MOV32_IMM(BPF_REG_2, 0xffffffff - 1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63),
-	BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"masking, test in bounds 3",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_1, 0xfffffffe),
-	BPF_MOV32_IMM(BPF_REG_2, 0xffffffff - 1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63),
-	BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0xfffffffe,
-},
-{
-	"masking, test in bounds 4",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_1, 0xabcde),
-	BPF_MOV32_IMM(BPF_REG_2, 0xabcdef - 1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63),
-	BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0xabcde,
-},
-{
-	"masking, test in bounds 5",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_1, 0),
-	BPF_MOV32_IMM(BPF_REG_2, 1 - 1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63),
-	BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"masking, test in bounds 6",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_1, 46),
-	BPF_MOV32_IMM(BPF_REG_2, 47 - 1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63),
-	BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 46,
-},
-{
-	"masking, test in bounds 7",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_3, -46),
-	BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, -1),
-	BPF_MOV32_IMM(BPF_REG_2, 47 - 1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_3),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_3),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63),
-	BPF_ALU64_REG(BPF_AND, BPF_REG_3, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_3),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 46,
-},
-{
-	"masking, test in bounds 8",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_3, -47),
-	BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, -1),
-	BPF_MOV32_IMM(BPF_REG_2, 47 - 1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_3),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_3),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0),
-	BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63),
-	BPF_ALU64_REG(BPF_AND, BPF_REG_3, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_3),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
diff --git a/tools/testing/selftests/bpf/verifier/meta_access.c b/tools/testing/selftests/bpf/verifier/meta_access.c
deleted file mode 100644
index b45e8af41420..000000000000
--- a/tools/testing/selftests/bpf/verifier/meta_access.c
+++ /dev/null
@@ -1,235 +0,0 @@
-{
-	"meta access, test1",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-},
-{
-	"meta access, test2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 8),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid access to packet, off=-8",
-	.prog_type = BPF_PROG_TYPE_XDP,
-},
-{
-	"meta access, test3",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid access to packet",
-	.prog_type = BPF_PROG_TYPE_XDP,
-},
-{
-	"meta access, test4",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_4),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid access to packet",
-	.prog_type = BPF_PROG_TYPE_XDP,
-},
-{
-	"meta access, test5",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_3),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_4, 3),
-	BPF_MOV64_IMM(BPF_REG_2, -8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_xdp_adjust_meta),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_3, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "R3 !read_ok",
-	.prog_type = BPF_PROG_TYPE_XDP,
-},
-{
-	"meta access, test6",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_3),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_0, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid access to packet",
-	.prog_type = BPF_PROG_TYPE_XDP,
-},
-{
-	"meta access, test7",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_3),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-},
-{
-	"meta access, test8",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0xFFFF),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-},
-{
-	"meta access, test9",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 0xFFFF),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 1),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_4, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid access to packet",
-	.prog_type = BPF_PROG_TYPE_XDP,
-},
-{
-	"meta access, test10",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_IMM(BPF_REG_5, 42),
-	BPF_MOV64_IMM(BPF_REG_6, 24),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_5, -8),
-	BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_10, BPF_REG_6, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -8),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_5, 100, 6),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_5),
-	BPF_MOV64_REG(BPF_REG_5, BPF_REG_3),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_5, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid access to packet",
-	.prog_type = BPF_PROG_TYPE_XDP,
-},
-{
-	"meta access, test11",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_IMM(BPF_REG_5, 42),
-	BPF_MOV64_IMM(BPF_REG_6, 24),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_5, -8),
-	BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_10, BPF_REG_6, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -8),
-	BPF_JMP_IMM(BPF_JGT, BPF_REG_5, 100, 6),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_5),
-	BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_5, BPF_REG_5, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-},
-{
-	"meta access, test12",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_5, BPF_REG_3),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 16),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_5, BPF_REG_4, 5),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_3, 0),
-	BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 16),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_5, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-},
diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c
index 6c03a7d805f9..59a020c35647 100644
--- a/tools/testing/selftests/bpf/verifier/precise.c
+++ b/tools/testing/selftests/bpf/verifier/precise.c
@@ -38,25 +38,24 @@
 	.fixup_map_array_48b = { 1 },
 	.result = VERBOSE_ACCEPT,
 	.errstr =
-	"26: (85) call bpf_probe_read_kernel#113\
-	last_idx 26 first_idx 20\
-	regs=4 stack=0 before 25\
-	regs=4 stack=0 before 24\
-	regs=4 stack=0 before 23\
-	regs=4 stack=0 before 22\
-	regs=4 stack=0 before 20\
-	parent didn't have regs=4 stack=0 marks\
-	last_idx 19 first_idx 10\
-	regs=4 stack=0 before 19\
-	regs=200 stack=0 before 18\
-	regs=300 stack=0 before 17\
-	regs=201 stack=0 before 15\
-	regs=201 stack=0 before 14\
-	regs=200 stack=0 before 13\
-	regs=200 stack=0 before 12\
-	regs=200 stack=0 before 11\
-	regs=200 stack=0 before 10\
-	parent already had regs=0 stack=0 marks",
+	"mark_precise: frame0: last_idx 26 first_idx 20\
+	mark_precise: frame0: regs=r2 stack= before 25\
+	mark_precise: frame0: regs=r2 stack= before 24\
+	mark_precise: frame0: regs=r2 stack= before 23\
+	mark_precise: frame0: regs=r2 stack= before 22\
+	mark_precise: frame0: regs=r2 stack= before 20\
+	mark_precise: frame0: parent state regs=r2,r9 stack=:\
+	mark_precise: frame0: last_idx 19 first_idx 10\
+	mark_precise: frame0: regs=r2,r9 stack= before 19\
+	mark_precise: frame0: regs=r9 stack= before 18\
+	mark_precise: frame0: regs=r8,r9 stack= before 17\
+	mark_precise: frame0: regs=r0,r9 stack= before 15\
+	mark_precise: frame0: regs=r0,r9 stack= before 14\
+	mark_precise: frame0: regs=r9 stack= before 13\
+	mark_precise: frame0: regs=r9 stack= before 12\
+	mark_precise: frame0: regs=r9 stack= before 11\
+	mark_precise: frame0: regs=r9 stack= before 10\
+	mark_precise: frame0: parent state regs= stack=:",
 },
 {
 	"precise: test 2",
@@ -100,20 +99,20 @@
 	.flags = BPF_F_TEST_STATE_FREQ,
 	.errstr =
 	"26: (85) call bpf_probe_read_kernel#113\
-	last_idx 26 first_idx 22\
-	regs=4 stack=0 before 25\
-	regs=4 stack=0 before 24\
-	regs=4 stack=0 before 23\
-	regs=4 stack=0 before 22\
-	parent didn't have regs=4 stack=0 marks\
-	last_idx 20 first_idx 20\
-	regs=4 stack=0 before 20\
-	parent didn't have regs=4 stack=0 marks\
-	last_idx 19 first_idx 17\
-	regs=4 stack=0 before 19\
-	regs=200 stack=0 before 18\
-	regs=300 stack=0 before 17\
-	parent already had regs=0 stack=0 marks",
+	mark_precise: frame0: last_idx 26 first_idx 22\
+	mark_precise: frame0: regs=r2 stack= before 25\
+	mark_precise: frame0: regs=r2 stack= before 24\
+	mark_precise: frame0: regs=r2 stack= before 23\
+	mark_precise: frame0: regs=r2 stack= before 22\
+	mark_precise: frame0: parent state regs=r2 stack=:\
+	mark_precise: frame0: last_idx 20 first_idx 20\
+	mark_precise: frame0: regs=r2 stack= before 20\
+	mark_precise: frame0: parent state regs=r2,r9 stack=:\
+	mark_precise: frame0: last_idx 19 first_idx 17\
+	mark_precise: frame0: regs=r2,r9 stack= before 19\
+	mark_precise: frame0: regs=r9 stack= before 18\
+	mark_precise: frame0: regs=r8,r9 stack= before 17\
+	mark_precise: frame0: parent state regs= stack=:",
 },
 {
 	"precise: cross frame pruning",
@@ -141,10 +140,11 @@
 	.result = REJECT,
 },
 {
-	"precise: ST insn causing spi > allocated_stack",
+	"precise: ST zero to stack insn is supported",
 	.insns = {
 	BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_3, 123, 0),
+	/* not a register spill, so we stop precision propagation for R4 here */
 	BPF_ST_MEM(BPF_DW, BPF_REG_3, -8, 0),
 	BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
 	BPF_MOV64_IMM(BPF_REG_0, -1),
@@ -153,15 +153,16 @@
 	},
 	.prog_type = BPF_PROG_TYPE_XDP,
 	.flags = BPF_F_TEST_STATE_FREQ,
-	.errstr = "5: (2d) if r4 > r0 goto pc+0\
-	last_idx 5 first_idx 5\
-	parent didn't have regs=10 stack=0 marks\
-	last_idx 4 first_idx 2\
-	regs=10 stack=0 before 4\
-	regs=10 stack=0 before 3\
-	regs=0 stack=1 before 2\
-	last_idx 5 first_idx 5\
-	parent didn't have regs=1 stack=0 marks",
+	.errstr = "mark_precise: frame0: last_idx 5 first_idx 5\
+	mark_precise: frame0: parent state regs=r4 stack=:\
+	mark_precise: frame0: last_idx 4 first_idx 2\
+	mark_precise: frame0: regs=r4 stack= before 4\
+	mark_precise: frame0: regs=r4 stack= before 3\
+	mark_precise: frame0: last_idx 5 first_idx 5\
+	mark_precise: frame0: parent state regs=r0 stack=:\
+	mark_precise: frame0: last_idx 4 first_idx 2\
+	mark_precise: frame0: regs=r0 stack= before 4\
+	5: R0=-1 R4=0",
 	.result = VERBOSE_ACCEPT,
 	.retval = -1,
 },
@@ -169,6 +170,8 @@
 	"precise: STX insn causing spi > allocated_stack",
 	.insns = {
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
+	/* make later reg spill more interesting by having somewhat known scalar */
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xff),
 	BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_3, 123, 0),
 	BPF_STX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, -8),
@@ -179,16 +182,22 @@
 	},
 	.prog_type = BPF_PROG_TYPE_XDP,
 	.flags = BPF_F_TEST_STATE_FREQ,
-	.errstr = "last_idx 6 first_idx 6\
-	parent didn't have regs=10 stack=0 marks\
-	last_idx 5 first_idx 3\
-	regs=10 stack=0 before 5\
-	regs=10 stack=0 before 4\
-	regs=0 stack=1 before 3\
-	last_idx 6 first_idx 6\
-	parent didn't have regs=1 stack=0 marks\
-	last_idx 5 first_idx 3\
-	regs=1 stack=0 before 5",
+	.errstr = "mark_precise: frame0: last_idx 7 first_idx 7\
+	mark_precise: frame0: parent state regs=r4 stack=:\
+	mark_precise: frame0: last_idx 6 first_idx 4\
+	mark_precise: frame0: regs=r4 stack= before 6: (b7) r0 = -1\
+	mark_precise: frame0: regs=r4 stack= before 5: (79) r4 = *(u64 *)(r10 -8)\
+	mark_precise: frame0: regs= stack=-8 before 4: (7b) *(u64 *)(r3 -8) = r0\
+	mark_precise: frame0: parent state regs=r0 stack=:\
+	mark_precise: frame0: last_idx 3 first_idx 3\
+	mark_precise: frame0: regs=r0 stack= before 3: (55) if r3 != 0x7b goto pc+0\
+	mark_precise: frame0: regs=r0 stack= before 2: (bf) r3 = r10\
+	mark_precise: frame0: regs=r0 stack= before 1: (57) r0 &= 255\
+	mark_precise: frame0: parent state regs=r0 stack=:\
+	mark_precise: frame0: last_idx 0 first_idx 0\
+	mark_precise: frame0: regs=r0 stack= before 0: (85) call bpf_get_prandom_u32#7\
+	mark_precise: frame0: last_idx 7 first_idx 7\
+	mark_precise: frame0: parent state regs= stack=:",
 	.result = VERBOSE_ACCEPT,
 	.retval = -1,
 },
@@ -213,7 +222,43 @@
 	},
 	.fixup_map_ringbuf = { 1 },
 	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = BPF_F_TEST_STATE_FREQ,
+	.flags = BPF_F_TEST_STATE_FREQ | F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	.errstr = "invalid access to memory, mem_size=1 off=42 size=8",
 	.result = REJECT,
 },
+{
+	"precise: program doesn't prematurely prune branches",
+	.insns = {
+		BPF_ALU64_IMM(BPF_MOV, BPF_REG_6, 0x400),
+		BPF_ALU64_IMM(BPF_MOV, BPF_REG_7, 0),
+		BPF_ALU64_IMM(BPF_MOV, BPF_REG_8, 0),
+		BPF_ALU64_IMM(BPF_MOV, BPF_REG_9, 0x80000000),
+		BPF_ALU64_IMM(BPF_MOD, BPF_REG_6, 0x401),
+		BPF_JMP_IMM(BPF_JA, 0, 0, 0),
+		BPF_JMP_REG(BPF_JLE, BPF_REG_6, BPF_REG_9, 2),
+		BPF_ALU64_IMM(BPF_MOD, BPF_REG_6, 1),
+		BPF_ALU64_IMM(BPF_MOV, BPF_REG_9, 0),
+		BPF_JMP_REG(BPF_JLE, BPF_REG_6, BPF_REG_9, 1),
+		BPF_ALU64_IMM(BPF_MOV, BPF_REG_6, 0),
+		BPF_ALU64_IMM(BPF_MOV, BPF_REG_0, 0),
+		BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4),
+		BPF_LD_MAP_FD(BPF_REG_4, 0),
+		BPF_ALU64_REG(BPF_MOV, BPF_REG_1, BPF_REG_4),
+		BPF_ALU64_REG(BPF_MOV, BPF_REG_2, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+		BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+		BPF_EXIT_INSN(),
+		BPF_ALU64_IMM(BPF_RSH, BPF_REG_6, 10),
+		BPF_ALU64_IMM(BPF_MUL, BPF_REG_6, 8192),
+		BPF_ALU64_REG(BPF_MOV, BPF_REG_1, BPF_REG_0),
+		BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_6),
+		BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0),
+		BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_3, 0),
+		BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 13 },
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.result = REJECT,
+	.errstr = "register with unbounded min value is not allowed",
+},
diff --git a/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c b/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c
deleted file mode 100644
index fc4e301260f6..000000000000
--- a/tools/testing/selftests/bpf/verifier/prevent_map_lookup.c
+++ /dev/null
@@ -1,29 +0,0 @@
-{
-	"prevent map lookup in stack trace",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_stacktrace = { 3 },
-	.result = REJECT,
-	.errstr = "cannot pass map_type 7 into func bpf_map_lookup_elem",
-	.prog_type = BPF_PROG_TYPE_PERF_EVENT,
-},
-{
-	"prevent map lookup in prog array",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_prog2 = { 3 },
-	.result = REJECT,
-	.errstr = "cannot pass map_type 3 into func bpf_map_lookup_elem",
-},
diff --git a/tools/testing/selftests/bpf/verifier/raw_stack.c b/tools/testing/selftests/bpf/verifier/raw_stack.c
deleted file mode 100644
index eb5ed936580b..000000000000
--- a/tools/testing/selftests/bpf/verifier/raw_stack.c
+++ /dev/null
@@ -1,305 +0,0 @@
-{
-	"raw_stack: no skb_load_bytes",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_4, 8),
-	/* Call to skb_load_bytes() omitted. */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid read from stack R6 off=-8 size=8",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"raw_stack: skb_load_bytes, negative len",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_4, -8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "R4 min value is negative",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"raw_stack: skb_load_bytes, negative len 2",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_4, ~0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "R4 min value is negative",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"raw_stack: skb_load_bytes, zero len",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid zero-sized read",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"raw_stack: skb_load_bytes, no init",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_4, 8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"raw_stack: skb_load_bytes, init",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_6, 0, 0xcafe),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_4, 8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"raw_stack: skb_load_bytes, spilled regs around bounds",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -16),
-	BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, -8),
-	BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1,  8),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_4, 8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_6,  8),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0,
-		    offsetof(struct __sk_buff, mark)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_2,
-		    offsetof(struct __sk_buff, priority)),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"raw_stack: skb_load_bytes, spilled regs corruption",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
-	BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_4, 8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0,
-		    offsetof(struct __sk_buff, mark)),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "R0 invalid mem access 'scalar'",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"raw_stack: skb_load_bytes, spilled regs corruption 2",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -16),
-	BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, -8),
-	BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1,  0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1,  8),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_4, 8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_6,  8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_6,  0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0,
-		    offsetof(struct __sk_buff, mark)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_2,
-		    offsetof(struct __sk_buff, priority)),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_3,
-		    offsetof(struct __sk_buff, pkt_type)),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_3),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "R3 invalid mem access 'scalar'",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"raw_stack: skb_load_bytes, spilled regs + data",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -16),
-	BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, -8),
-	BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1,  0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1,  8),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_4, 8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_6,  8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_6,  0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0,
-		    offsetof(struct __sk_buff, mark)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_2,
-		    offsetof(struct __sk_buff, priority)),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_3),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"raw_stack: skb_load_bytes, invalid access 1",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -513),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_4, 8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid indirect access to stack R3 off=-513 size=8",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"raw_stack: skb_load_bytes, invalid access 2",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -1),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_4, 8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid indirect access to stack R3 off=-1 size=8",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"raw_stack: skb_load_bytes, invalid access 3",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 0xffffffff),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_4, 0xffffffff),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "R4 min value is negative",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"raw_stack: skb_load_bytes, invalid access 4",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -1),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_4, 0x7fffffff),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "R4 unbounded memory access, use 'var &= const' or 'if (var < const)'",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"raw_stack: skb_load_bytes, invalid access 5",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -512),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_4, 0x7fffffff),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "R4 unbounded memory access, use 'var &= const' or 'if (var < const)'",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"raw_stack: skb_load_bytes, invalid access 6",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -512),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid zero-sized read",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"raw_stack: skb_load_bytes, large access",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -512),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_4, 512),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_load_bytes),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
diff --git a/tools/testing/selftests/bpf/verifier/raw_tp_writable.c b/tools/testing/selftests/bpf/verifier/raw_tp_writable.c
deleted file mode 100644
index 2978fb5a769d..000000000000
--- a/tools/testing/selftests/bpf/verifier/raw_tp_writable.c
+++ /dev/null
@@ -1,35 +0,0 @@
-{
-	"raw_tracepoint_writable: reject variable offset",
-	.insns = {
-		/* r6 is our tp buffer */
-		BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
-
-		BPF_LD_MAP_FD(BPF_REG_1, 0),
-		/* move the key (== 0) to r10-8 */
-		BPF_MOV32_IMM(BPF_REG_0, 0),
-		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-		BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
-		/* lookup in the map */
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
-			     BPF_FUNC_map_lookup_elem),
-
-		/* exit clean if null */
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-		BPF_EXIT_INSN(),
-
-		/* shift the buffer pointer to a variable location */
-		BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0),
-		BPF_ALU64_REG(BPF_ADD, BPF_REG_6, BPF_REG_0),
-		/* clobber whatever's there */
-		BPF_MOV64_IMM(BPF_REG_7, 4242),
-		BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_7, 0),
-
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 1, },
-	.prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
-	.errstr = "R6 invalid variable buffer offset: off=0, var_off=(0x0; 0xffffffff)",
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c
deleted file mode 100644
index 9540164712b7..000000000000
--- a/tools/testing/selftests/bpf/verifier/ref_tracking.c
+++ /dev/null
@@ -1,1082 +0,0 @@
-{
-	"reference tracking: leak potential reference",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), /* leak reference */
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "Unreleased reference",
-	.result = REJECT,
-},
-{
-	"reference tracking: leak potential reference to sock_common",
-	.insns = {
-	BPF_SK_LOOKUP(skc_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), /* leak reference */
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "Unreleased reference",
-	.result = REJECT,
-},
-{
-	"reference tracking: leak potential reference on stack",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
-	BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "Unreleased reference",
-	.result = REJECT,
-},
-{
-	"reference tracking: leak potential reference on stack 2",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
-	BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "Unreleased reference",
-	.result = REJECT,
-},
-{
-	"reference tracking: zero potential reference",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_IMM(BPF_REG_0, 0), /* leak reference */
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "Unreleased reference",
-	.result = REJECT,
-},
-{
-	"reference tracking: zero potential reference to sock_common",
-	.insns = {
-	BPF_SK_LOOKUP(skc_lookup_tcp),
-	BPF_MOV64_IMM(BPF_REG_0, 0), /* leak reference */
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "Unreleased reference",
-	.result = REJECT,
-},
-{
-	"reference tracking: copy and zero potential references",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_7, 0), /* leak reference */
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "Unreleased reference",
-	.result = REJECT,
-},
-{
-	"reference tracking: acquire/release user key reference",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, -3),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_LSM,
-	.kfunc = "bpf",
-	.expected_attach_type = BPF_LSM_MAC,
-	.flags = BPF_F_SLEEPABLE,
-	.fixup_kfunc_btf_id = {
-		{ "bpf_lookup_user_key", 2 },
-		{ "bpf_key_put", 5 },
-	},
-	.result = ACCEPT,
-},
-{
-	"reference tracking: acquire/release system key reference",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 1),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_LSM,
-	.kfunc = "bpf",
-	.expected_attach_type = BPF_LSM_MAC,
-	.flags = BPF_F_SLEEPABLE,
-	.fixup_kfunc_btf_id = {
-		{ "bpf_lookup_system_key", 1 },
-		{ "bpf_key_put", 4 },
-	},
-	.result = ACCEPT,
-},
-{
-	"reference tracking: release user key reference without check",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, -3),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_LSM,
-	.kfunc = "bpf",
-	.expected_attach_type = BPF_LSM_MAC,
-	.flags = BPF_F_SLEEPABLE,
-	.errstr = "arg#0 is ptr_or_null_ expected ptr_ or socket",
-	.fixup_kfunc_btf_id = {
-		{ "bpf_lookup_user_key", 2 },
-		{ "bpf_key_put", 4 },
-	},
-	.result = REJECT,
-},
-{
-	"reference tracking: release system key reference without check",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 1),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_LSM,
-	.kfunc = "bpf",
-	.expected_attach_type = BPF_LSM_MAC,
-	.flags = BPF_F_SLEEPABLE,
-	.errstr = "arg#0 is ptr_or_null_ expected ptr_ or socket",
-	.fixup_kfunc_btf_id = {
-		{ "bpf_lookup_system_key", 1 },
-		{ "bpf_key_put", 3 },
-	},
-	.result = REJECT,
-},
-{
-	"reference tracking: release with NULL key pointer",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_LSM,
-	.kfunc = "bpf",
-	.expected_attach_type = BPF_LSM_MAC,
-	.flags = BPF_F_SLEEPABLE,
-	.errstr = "arg#0 pointer type STRUCT bpf_key must point to scalar, or struct with scalar",
-	.fixup_kfunc_btf_id = {
-		{ "bpf_key_put", 1 },
-	},
-	.result = REJECT,
-},
-{
-	"reference tracking: leak potential reference to user key",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, -3),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_LSM,
-	.kfunc = "bpf",
-	.expected_attach_type = BPF_LSM_MAC,
-	.flags = BPF_F_SLEEPABLE,
-	.errstr = "Unreleased reference",
-	.fixup_kfunc_btf_id = {
-		{ "bpf_lookup_user_key", 2 },
-	},
-	.result = REJECT,
-},
-{
-	"reference tracking: leak potential reference to system key",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 1),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_LSM,
-	.kfunc = "bpf",
-	.expected_attach_type = BPF_LSM_MAC,
-	.flags = BPF_F_SLEEPABLE,
-	.errstr = "Unreleased reference",
-	.fixup_kfunc_btf_id = {
-		{ "bpf_lookup_system_key", 1 },
-	},
-	.result = REJECT,
-},
-{
-	"reference tracking: release reference without check",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	/* reference in r0 may be NULL */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "type=sock_or_null expected=sock",
-	.result = REJECT,
-},
-{
-	"reference tracking: release reference to sock_common without check",
-	.insns = {
-	BPF_SK_LOOKUP(skc_lookup_tcp),
-	/* reference in r0 may be NULL */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "type=sock_common_or_null expected=sock",
-	.result = REJECT,
-},
-{
-	"reference tracking: release reference",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-},
-{
-	"reference tracking: release reference to sock_common",
-	.insns = {
-	BPF_SK_LOOKUP(skc_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-},
-{
-	"reference tracking: release reference 2",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-},
-{
-	"reference tracking: release reference twice",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "type=scalar expected=sock",
-	.result = REJECT,
-},
-{
-	"reference tracking: release reference twice inside branch",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), /* goto end */
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "type=scalar expected=sock",
-	.result = REJECT,
-},
-{
-	"reference tracking: alloc, check, free in one subbranch",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 16),
-	/* if (offsetof(skb, mark) > data_len) exit; */
-	BPF_JMP_REG(BPF_JLE, BPF_REG_0, BPF_REG_3, 1),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_2,
-		    offsetof(struct __sk_buff, mark)),
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 1), /* mark == 0? */
-	/* Leak reference in R0 */
-	BPF_EXIT_INSN(),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), /* sk NULL? */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "Unreleased reference",
-	.result = REJECT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"reference tracking: alloc, check, free in both subbranches",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 16),
-	/* if (offsetof(skb, mark) > data_len) exit; */
-	BPF_JMP_REG(BPF_JLE, BPF_REG_0, BPF_REG_3, 1),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_2,
-		    offsetof(struct __sk_buff, mark)),
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 4), /* mark == 0? */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), /* sk NULL? */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), /* sk NULL? */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"reference tracking in call: free reference in subprog",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), /* unchecked reference */
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-
-	/* subprog 1 */
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_2, 0, 1),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-},
-{
-	"reference tracking in call: free reference in subprog and outside",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), /* unchecked reference */
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-
-	/* subprog 1 */
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_2, 0, 1),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "type=scalar expected=sock",
-	.result = REJECT,
-},
-{
-	"reference tracking in call: alloc & leak reference in subprog",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-
-	/* subprog 1 */
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_4),
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	/* spill unchecked sk_ptr into stack of caller */
-	BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "Unreleased reference",
-	.result = REJECT,
-},
-{
-	"reference tracking in call: alloc in subprog, release outside",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-
-	/* subprog 1 */
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_EXIT_INSN(), /* return sk */
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.retval = POINTER_VALUE,
-	.result = ACCEPT,
-},
-{
-	"reference tracking in call: sk_ptr leak into caller stack",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-
-	/* subprog 1 */
-	BPF_MOV64_REG(BPF_REG_5, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, -8),
-	BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_4, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 5),
-	/* spill unchecked sk_ptr into stack of caller */
-	BPF_MOV64_REG(BPF_REG_5, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_5, 0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-
-	/* subprog 2 */
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "Unreleased reference",
-	.result = REJECT,
-},
-{
-	"reference tracking in call: sk_ptr spill into caller stack",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-
-	/* subprog 1 */
-	BPF_MOV64_REG(BPF_REG_5, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, -8),
-	BPF_STX_MEM(BPF_DW, BPF_REG_5, BPF_REG_4, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 8),
-	/* spill unchecked sk_ptr into stack of caller */
-	BPF_MOV64_REG(BPF_REG_5, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_5, 0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	/* now the sk_ptr is verified, free the reference */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_4, 0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-
-	/* subprog 2 */
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-},
-{
-	"reference tracking: allow LD_ABS",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_LD_ABS(BPF_B, 0),
-	BPF_LD_ABS(BPF_H, 0),
-	BPF_LD_ABS(BPF_W, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-},
-{
-	"reference tracking: forbid LD_ABS while holding reference",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_LD_ABS(BPF_B, 0),
-	BPF_LD_ABS(BPF_H, 0),
-	BPF_LD_ABS(BPF_W, 0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "BPF_LD_[ABS|IND] cannot be mixed with socket references",
-	.result = REJECT,
-},
-{
-	"reference tracking: allow LD_IND",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_MOV64_IMM(BPF_REG_7, 1),
-	BPF_LD_IND(BPF_W, BPF_REG_7, -0x200000),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"reference tracking: forbid LD_IND while holding reference",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_7, 1),
-	BPF_LD_IND(BPF_W, BPF_REG_7, -0x200000),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_4),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "BPF_LD_[ABS|IND] cannot be mixed with socket references",
-	.result = REJECT,
-},
-{
-	"reference tracking: check reference or tail call",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	/* if (sk) bpf_sk_release() */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 7),
-	/* bpf_tail_call() */
-	BPF_MOV64_IMM(BPF_REG_3, 3),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_prog1 = { 17 },
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-},
-{
-	"reference tracking: release reference then tail call",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	/* if (sk) bpf_sk_release() */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	/* bpf_tail_call() */
-	BPF_MOV64_IMM(BPF_REG_3, 3),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_prog1 = { 18 },
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-},
-{
-	"reference tracking: leak possible reference over tail call",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
-	/* Look up socket and store in REG_6 */
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	/* bpf_tail_call() */
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_3, 3),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	/* if (sk) bpf_sk_release() */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_prog1 = { 16 },
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "tail_call would lead to reference leak",
-	.result = REJECT,
-},
-{
-	"reference tracking: leak checked reference over tail call",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
-	/* Look up socket and store in REG_6 */
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	/* if (!sk) goto end */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-	/* bpf_tail_call() */
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_prog1 = { 17 },
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "tail_call would lead to reference leak",
-	.result = REJECT,
-},
-{
-	"reference tracking: mangle and release sock_or_null",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 5),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "R1 pointer arithmetic on sock_or_null prohibited",
-	.result = REJECT,
-},
-{
-	"reference tracking: mangle and release sock",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 5),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "R1 pointer arithmetic on sock prohibited",
-	.result = REJECT,
-},
-{
-	"reference tracking: access member",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-},
-{
-	"reference tracking: write to member",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_LD_IMM64(BPF_REG_2, 42),
-	BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_2,
-		    offsetof(struct bpf_sock, mark)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_LD_IMM64(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "cannot write into sock",
-	.result = REJECT,
-},
-{
-	"reference tracking: invalid 64-bit access of member",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "invalid sock access off=0 size=8",
-	.result = REJECT,
-},
-{
-	"reference tracking: access after release",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "!read_ok",
-	.result = REJECT,
-},
-{
-	"reference tracking: direct access for lookup",
-	.insns = {
-	/* Check that the packet is at least 64B long */
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 64),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 9),
-	/* sk = sk_lookup_tcp(ctx, skb->data, ...) */
-	BPF_MOV64_IMM(BPF_REG_3, sizeof(struct bpf_sock_tuple)),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_5, 0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_0, 4),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-},
-{
-	"reference tracking: use ptr from bpf_tcp_sock() after release",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, offsetof(struct bpf_tcp_sock, snd_cwnd)),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = REJECT,
-	.errstr = "invalid mem access",
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"reference tracking: use ptr from bpf_sk_fullsock() after release",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, offsetof(struct bpf_sock, type)),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = REJECT,
-	.errstr = "invalid mem access",
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"reference tracking: use ptr from bpf_sk_fullsock(tp) after release",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, type)),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = REJECT,
-	.errstr = "invalid mem access",
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"reference tracking: use sk after bpf_sk_release(tp)",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, type)),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = REJECT,
-	.errstr = "invalid mem access",
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"reference tracking: use ptr from bpf_get_listener_sock() after bpf_sk_release(sk)",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_get_listener_sock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, src_port)),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-},
-{
-	"reference tracking: bpf_sk_release(listen_sk)",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_get_listener_sock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, type)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = REJECT,
-	.errstr = "R1 must be referenced when passed to release function",
-},
-{
-	/* !bpf_sk_fullsock(sk) is checked but !bpf_tcp_sock(sk) is not checked */
-	"reference tracking: tp->snd_cwnd after bpf_sk_fullsock(sk) and bpf_tcp_sock(sk)",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
-	BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0, 3),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_8, offsetof(struct bpf_tcp_sock, snd_cwnd)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = REJECT,
-	.errstr = "invalid mem access",
-},
-{
-	"reference tracking: branch tracking valid pointer null comparison",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_3, 1),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 0, 1),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 2),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-},
-{
-	"reference tracking: branch tracking valid pointer value comparison",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_3, 1),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 4),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 1234, 2),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.errstr = "Unreleased reference",
-	.result = REJECT,
-},
-{
-	"reference tracking: bpf_sk_release(btf_tcp_sock)",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_skc_to_tcp_sock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "unknown func",
-},
-{
-	"reference tracking: use ptr from bpf_skc_to_tcp_sock() after release",
-	.insns = {
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_skc_to_tcp_sock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_7, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = REJECT,
-	.errstr = "invalid mem access",
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "unknown func",
-},
-{
-	"reference tracking: try to leak released ptr reg",
-	.insns = {
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4),
-		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-		BPF_LD_MAP_FD(BPF_REG_1, 0),
-		BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-		BPF_EXIT_INSN(),
-		BPF_MOV64_REG(BPF_REG_9, BPF_REG_0),
-
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_LD_MAP_FD(BPF_REG_1, 0),
-		BPF_MOV64_IMM(BPF_REG_2, 8),
-		BPF_MOV64_IMM(BPF_REG_3, 0),
-		BPF_EMIT_CALL(BPF_FUNC_ringbuf_reserve),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-		BPF_EXIT_INSN(),
-		BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
-
-		BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
-		BPF_MOV64_IMM(BPF_REG_2, 0),
-		BPF_EMIT_CALL(BPF_FUNC_ringbuf_discard),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-
-		BPF_STX_MEM(BPF_DW, BPF_REG_9, BPF_REG_8, 0),
-		BPF_EXIT_INSN()
-	},
-	.fixup_map_array_48b = { 4 },
-	.fixup_map_ringbuf = { 11 },
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R8 !read_ok"
-},
diff --git a/tools/testing/selftests/bpf/verifier/regalloc.c b/tools/testing/selftests/bpf/verifier/regalloc.c
deleted file mode 100644
index bb0dd89dd212..000000000000
--- a/tools/testing/selftests/bpf/verifier/regalloc.c
+++ /dev/null
@@ -1,277 +0,0 @@
-{
-	"regalloc basic",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_0, 20, 4),
-	BPF_JMP_IMM(BPF_JSLT, BPF_REG_2, 0, 3),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_2),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 4 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"regalloc negative",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_0, 24, 4),
-	BPF_JMP_IMM(BPF_JSLT, BPF_REG_2, 0, 3),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_2),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_7, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 4 },
-	.result = REJECT,
-	.errstr = "invalid access to map value, value_size=48 off=48 size=1",
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"regalloc src_reg mark",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_0, 20, 5),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_JMP_REG(BPF_JSGE, BPF_REG_3, BPF_REG_2, 3),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_2),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 4 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"regalloc src_reg negative",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_0, 22, 5),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_JMP_REG(BPF_JSGE, BPF_REG_3, BPF_REG_2, 3),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_2),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 4 },
-	.result = REJECT,
-	.errstr = "invalid access to map value, value_size=48 off=44 size=8",
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"regalloc and spill",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_0, 20, 7),
-	/* r0 has upper bound that should propagate into r2 */
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -8), /* spill r2 */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_2, 0), /* clear r0 and r2 */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_10, -8), /* fill r3 */
-	BPF_JMP_REG(BPF_JSGE, BPF_REG_0, BPF_REG_3, 2),
-	/* r3 has lower and upper bounds */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_3),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 4 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"regalloc and spill negative",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_0, 48, 7),
-	/* r0 has upper bound that should propagate into r2 */
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -8), /* spill r2 */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_2, 0), /* clear r0 and r2 */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_10, -8), /* fill r3 */
-	BPF_JMP_REG(BPF_JSGE, BPF_REG_0, BPF_REG_3, 2),
-	/* r3 has lower and upper bounds */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_3),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 4 },
-	.result = REJECT,
-	.errstr = "invalid access to map value, value_size=48 off=48 size=8",
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"regalloc three regs",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_0, 12, 5),
-	BPF_JMP_IMM(BPF_JSLT, BPF_REG_2, 0, 4),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_4),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 4 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"regalloc after call",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 10),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_9, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 6),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_8, 20, 4),
-	BPF_JMP_IMM(BPF_JSLT, BPF_REG_9, 0, 3),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_8),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_9),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 4 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"regalloc in callee",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_7),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 20, 5),
-	BPF_JMP_IMM(BPF_JSLT, BPF_REG_2, 0, 4),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_1),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_2),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 4 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"regalloc, spill, JEQ",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), /* spill r0 */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 0),
-	/* The verifier will walk the rest twice with r0 == 0 and r0 == map_value */
-	BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_2, 20, 0),
-	/* The verifier will walk the rest two more times with r0 == 20 and r0 == unknown */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_10, -8), /* fill r3 with map_value */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0, 1), /* skip ldx if map_value == NULL */
-	/* Buggy verifier will think that r3 == 20 here */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0), /* read from map_value */
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 4 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
diff --git a/tools/testing/selftests/bpf/verifier/ringbuf.c b/tools/testing/selftests/bpf/verifier/ringbuf.c
deleted file mode 100644
index 92e3f6a61a79..000000000000
--- a/tools/testing/selftests/bpf/verifier/ringbuf.c
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-	"ringbuf: invalid reservation offset 1",
-	.insns = {
-	/* reserve 8 byte ringbuf memory */
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_2, 8),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve),
-	/* store a pointer to the reserved memory in R6 */
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	/* check whether the reservation was successful */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-	/* spill R6(mem) into the stack */
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
-	/* fill it back in R7 */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, -8),
-	/* should be able to access *(R7) = 0 */
-	BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 0),
-	/* submit the reserved ringbuf memory */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
-	/* add invalid offset to reserved ringbuf memory */
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xcafe),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_ringbuf = { 1 },
-	.result = REJECT,
-	.errstr = "R1 must have zero offset when passed to release func",
-},
-{
-	"ringbuf: invalid reservation offset 2",
-	.insns = {
-	/* reserve 8 byte ringbuf memory */
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_2, 8),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve),
-	/* store a pointer to the reserved memory in R6 */
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	/* check whether the reservation was successful */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-	/* spill R6(mem) into the stack */
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
-	/* fill it back in R7 */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, -8),
-	/* add invalid offset to reserved ringbuf memory */
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 0xcafe),
-	/* should be able to access *(R7) = 0 */
-	BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 0),
-	/* submit the reserved ringbuf memory */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_ringbuf = { 1 },
-	.result = REJECT,
-	.errstr = "R7 min value is outside of the allowed memory range",
-},
-{
-	"ringbuf: check passing rb mem to helpers",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	/* reserve 8 byte ringbuf memory */
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_2, 8),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	/* check whether the reservation was successful */
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	/* pass allocated ring buffer memory to fib lookup */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_3, 8),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_fib_lookup),
-	/* submit the ringbuf memory */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_ringbuf = { 2 },
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.result = ACCEPT,
-},
diff --git a/tools/testing/selftests/bpf/verifier/runtime_jit.c b/tools/testing/selftests/bpf/verifier/runtime_jit.c
deleted file mode 100644
index 94c399d1faca..000000000000
--- a/tools/testing/selftests/bpf/verifier/runtime_jit.c
+++ /dev/null
@@ -1,231 +0,0 @@
-{
-	"runtime/jit: tail_call within bounds, prog once",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_prog1 = { 1 },
-	.result = ACCEPT,
-	.retval = 42,
-},
-{
-	"runtime/jit: tail_call within bounds, prog loop",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_3, 1),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_prog1 = { 1 },
-	.result = ACCEPT,
-	.retval = 41,
-},
-{
-	"runtime/jit: tail_call within bounds, no prog",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_3, 3),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_prog1 = { 1 },
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"runtime/jit: tail_call within bounds, key 2",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_3, 2),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_prog1 = { 1 },
-	.result = ACCEPT,
-	.retval = 24,
-},
-{
-	"runtime/jit: tail_call within bounds, key 2 / key 2, first branch",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 13),
-	BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
-		    offsetof(struct __sk_buff, cb[0])),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, cb[0])),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 13, 4),
-	BPF_MOV64_IMM(BPF_REG_3, 2),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 3),
-	BPF_MOV64_IMM(BPF_REG_3, 2),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_prog1 = { 5, 9 },
-	.result = ACCEPT,
-	.retval = 24,
-},
-{
-	"runtime/jit: tail_call within bounds, key 2 / key 2, second branch",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 14),
-	BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
-		    offsetof(struct __sk_buff, cb[0])),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, cb[0])),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 13, 4),
-	BPF_MOV64_IMM(BPF_REG_3, 2),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 3),
-	BPF_MOV64_IMM(BPF_REG_3, 2),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_prog1 = { 5, 9 },
-	.result = ACCEPT,
-	.retval = 24,
-},
-{
-	"runtime/jit: tail_call within bounds, key 0 / key 2, first branch",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 13),
-	BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
-		    offsetof(struct __sk_buff, cb[0])),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, cb[0])),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 13, 4),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 3),
-	BPF_MOV64_IMM(BPF_REG_3, 2),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_prog1 = { 5, 9 },
-	.result = ACCEPT,
-	.retval = 24,
-},
-{
-	"runtime/jit: tail_call within bounds, key 0 / key 2, second branch",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 14),
-	BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
-		    offsetof(struct __sk_buff, cb[0])),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, cb[0])),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 13, 4),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 3),
-	BPF_MOV64_IMM(BPF_REG_3, 2),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_prog1 = { 5, 9 },
-	.result = ACCEPT,
-	.retval = 42,
-},
-{
-	"runtime/jit: tail_call within bounds, different maps, first branch",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 13),
-	BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
-		    offsetof(struct __sk_buff, cb[0])),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, cb[0])),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 13, 4),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 3),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_prog1 = { 5 },
-	.fixup_prog2 = { 9 },
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "tail_call abusing map_ptr",
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"runtime/jit: tail_call within bounds, different maps, second branch",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 14),
-	BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0,
-		    offsetof(struct __sk_buff, cb[0])),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, cb[0])),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 13, 4),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 3),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_prog1 = { 5 },
-	.fixup_prog2 = { 9 },
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "tail_call abusing map_ptr",
-	.result = ACCEPT,
-	.retval = 42,
-},
-{
-	"runtime/jit: tail_call out of bounds",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_3, 256),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call),
-	BPF_MOV64_IMM(BPF_REG_0, 2),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_prog1 = { 1 },
-	.result = ACCEPT,
-	.retval = 2,
-},
-{
-	"runtime/jit: pass negative index to tail_call",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_3, -1),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call),
-	BPF_MOV64_IMM(BPF_REG_0, 2),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_prog1 = { 1 },
-	.result = ACCEPT,
-	.retval = 2,
-},
-{
-	"runtime/jit: pass > 32bit index to tail_call",
-	.insns = {
-	BPF_LD_IMM64(BPF_REG_3, 0x100000000ULL),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call),
-	BPF_MOV64_IMM(BPF_REG_0, 2),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_prog1 = { 2 },
-	.result = ACCEPT,
-	.retval = 42,
-	/* Verifier rewrite for unpriv skips tail call here. */
-	.retval_unpriv = 2,
-},
diff --git a/tools/testing/selftests/bpf/verifier/search_pruning.c b/tools/testing/selftests/bpf/verifier/search_pruning.c
deleted file mode 100644
index 68b14fdfebdb..000000000000
--- a/tools/testing/selftests/bpf/verifier/search_pruning.c
+++ /dev/null
@@ -1,227 +0,0 @@
-{
-	"pointer/scalar confusion in state equality check (way 1)",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
-	BPF_JMP_A(1),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_10),
-	BPF_JMP_A(0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.result = ACCEPT,
-	.retval = POINTER_VALUE,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R0 leaks addr as return value"
-},
-{
-	"pointer/scalar confusion in state equality check (way 2)",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_10),
-	BPF_JMP_A(1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.result = ACCEPT,
-	.retval = POINTER_VALUE,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R0 leaks addr as return value"
-},
-{
-	"liveness pruning and write screening",
-	.insns = {
-	/* Get an unknown value */
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
-	/* branch conditions teach us nothing about R2 */
-	BPF_JMP_IMM(BPF_JGE, BPF_REG_2, 0, 1),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JGE, BPF_REG_2, 0, 1),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R0 !read_ok",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_LWT_IN,
-},
-{
-	"varlen_map_value_access pruning",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV32_IMM(BPF_REG_2, MAX_ENTRIES),
-	BPF_JMP_REG(BPF_JSGT, BPF_REG_2, BPF_REG_1, 1),
-	BPF_MOV32_IMM(BPF_REG_1, 0),
-	BPF_ALU32_IMM(BPF_LSH, BPF_REG_1, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 0),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, offsetof(struct test_val, foo)),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr_unpriv = "R0 leaks addr",
-	.errstr = "R0 unbounded memory access",
-	.result_unpriv = REJECT,
-	.result = REJECT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"search pruning: all branches should be verified (nop operation)",
-	.insns = {
-		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-		BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-		BPF_LD_MAP_FD(BPF_REG_1, 0),
-		BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
-		BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0),
-		BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0xbeef, 2),
-		BPF_MOV64_IMM(BPF_REG_4, 0),
-		BPF_JMP_A(1),
-		BPF_MOV64_IMM(BPF_REG_4, 1),
-		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_4, -16),
-		BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
-		BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -16),
-		BPF_JMP_IMM(BPF_JEQ, BPF_REG_5, 0, 2),
-		BPF_MOV64_IMM(BPF_REG_6, 0),
-		BPF_ST_MEM(BPF_DW, BPF_REG_6, 0, 0xdead),
-		BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "R6 invalid mem access 'scalar'",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"search pruning: all branches should be verified (invalid stack access)",
-	.insns = {
-		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-		BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-		BPF_LD_MAP_FD(BPF_REG_1, 0),
-		BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
-		BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0),
-		BPF_MOV64_IMM(BPF_REG_4, 0),
-		BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0xbeef, 2),
-		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_4, -16),
-		BPF_JMP_A(1),
-		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_4, -24),
-		BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
-		BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -16),
-		BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr = "invalid read from stack off -16+0 size 8",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"precision tracking for u32 spill/fill",
-	.insns = {
-		BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
-		BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
-		BPF_MOV32_IMM(BPF_REG_6, 32),
-		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-		BPF_MOV32_IMM(BPF_REG_6, 4),
-		/* Additional insns to introduce a pruning point. */
-		BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
-		BPF_MOV64_IMM(BPF_REG_3, 0),
-		BPF_MOV64_IMM(BPF_REG_3, 0),
-		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-		BPF_MOV64_IMM(BPF_REG_3, 0),
-		/* u32 spill/fill */
-		BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_6, -8),
-		BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_10, -8),
-		/* out-of-bound map value access for r6=32 */
-		BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0),
-		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
-		BPF_LD_MAP_FD(BPF_REG_1, 0),
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-		BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_8),
-		BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 15 },
-	.result = REJECT,
-	.errstr = "R0 min value is outside of the allowed memory range",
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"precision tracking for u32 spills, u64 fill",
-	.insns = {
-		BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
-		BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-		BPF_MOV32_IMM(BPF_REG_7, 0xffffffff),
-		/* Additional insns to introduce a pruning point. */
-		BPF_MOV64_IMM(BPF_REG_3, 1),
-		BPF_MOV64_IMM(BPF_REG_3, 1),
-		BPF_MOV64_IMM(BPF_REG_3, 1),
-		BPF_MOV64_IMM(BPF_REG_3, 1),
-		BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
-		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-		BPF_MOV64_IMM(BPF_REG_3, 1),
-		BPF_ALU32_IMM(BPF_DIV, BPF_REG_3, 0),
-		/* u32 spills, u64 fill */
-		BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_6, -4),
-		BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, -8),
-		BPF_LDX_MEM(BPF_DW, BPF_REG_8, BPF_REG_10, -8),
-		/* if r8 != X goto pc+1  r8 known in fallthrough branch */
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_8, 0xffffffff, 1),
-		BPF_MOV64_IMM(BPF_REG_3, 1),
-		/* if r8 == X goto pc+1  condition always true on first
-		 * traversal, so starts backtracking to mark r8 as requiring
-		 * precision. r7 marked as needing precision. r6 not marked
-		 * since it's not tracked.
-		 */
-		BPF_JMP_IMM(BPF_JEQ, BPF_REG_8, 0xffffffff, 1),
-		/* fails if r8 correctly marked unknown after fill. */
-		BPF_ALU32_IMM(BPF_DIV, BPF_REG_3, 0),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "div by zero",
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"allocated_stack",
-	.insns = {
-		BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
-		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-		BPF_ALU64_REG(BPF_MOV, BPF_REG_7, BPF_REG_0),
-		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
-		BPF_MOV64_IMM(BPF_REG_0, 0),
-		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
-		BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_10, -8),
-		BPF_STX_MEM(BPF_B, BPF_REG_10, BPF_REG_7, -9),
-		BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_10, -9),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 0),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 0),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 0),
-		BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 0),
-		BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.result_unpriv = ACCEPT,
-	.insn_processed = 15,
-},
diff --git a/tools/testing/selftests/bpf/verifier/sleepable.c b/tools/testing/selftests/bpf/verifier/sleepable.c
new file mode 100644
index 000000000000..1f0d2bdc673f
--- /dev/null
+++ b/tools/testing/selftests/bpf/verifier/sleepable.c
@@ -0,0 +1,91 @@
+{
+	"sleepable fentry accept",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACING,
+	.expected_attach_type = BPF_TRACE_FENTRY,
+	.kfunc = "bpf_fentry_test1",
+	.result = ACCEPT,
+	.flags = BPF_F_SLEEPABLE,
+	.runs = -1,
+},
+{
+	"sleepable fexit accept",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACING,
+	.expected_attach_type = BPF_TRACE_FENTRY,
+	.kfunc = "bpf_fentry_test1",
+	.result = ACCEPT,
+	.flags = BPF_F_SLEEPABLE,
+	.runs = -1,
+},
+{
+	"sleepable fmod_ret accept",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACING,
+	.expected_attach_type = BPF_MODIFY_RETURN,
+	.kfunc = "bpf_fentry_test1",
+	.result = ACCEPT,
+	.flags = BPF_F_SLEEPABLE,
+	.runs = -1,
+},
+{
+	"sleepable iter accept",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACING,
+	.expected_attach_type = BPF_TRACE_ITER,
+	.kfunc = "task",
+	.result = ACCEPT,
+	.flags = BPF_F_SLEEPABLE,
+	.runs = -1,
+},
+{
+	"sleepable lsm accept",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_LSM,
+	.kfunc = "bpf",
+	.expected_attach_type = BPF_LSM_MAC,
+	.result = ACCEPT,
+	.flags = BPF_F_SLEEPABLE,
+	.runs = -1,
+},
+{
+	"sleepable uprobe accept",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_KPROBE,
+	.kfunc = "bpf_fentry_test1",
+	.result = ACCEPT,
+	.flags = BPF_F_SLEEPABLE,
+	.runs = -1,
+},
+{
+	"sleepable raw tracepoint reject",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACING,
+	.expected_attach_type = BPF_TRACE_RAW_TP,
+	.kfunc = "sched_switch",
+	.result = REJECT,
+	.errstr = "Only fentry/fexit/fmod_ret, lsm, iter, uprobe, and struct_ops programs can be sleepable",
+	.flags = BPF_F_SLEEPABLE,
+	.runs = -1,
+},
diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c
deleted file mode 100644
index d11d0b28be41..000000000000
--- a/tools/testing/selftests/bpf/verifier/sock.c
+++ /dev/null
@@ -1,733 +0,0 @@
-{
-	"skb->sk: no NULL check",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = REJECT,
-	.errstr = "invalid mem access 'sock_common_or_null'",
-},
-{
-	"skb->sk: sk->family [non fullsock field]",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, offsetof(struct bpf_sock, family)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = ACCEPT,
-},
-{
-	"skb->sk: sk->type [fullsock field]",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, offsetof(struct bpf_sock, type)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = REJECT,
-	.errstr = "invalid sock_common access",
-},
-{
-	"bpf_sk_fullsock(skb->sk): no !skb->sk check",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = REJECT,
-	.errstr = "type=sock_common_or_null expected=sock_common",
-},
-{
-	"sk_fullsock(skb->sk): no NULL check on ret",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, type)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = REJECT,
-	.errstr = "invalid mem access 'sock_or_null'",
-},
-{
-	"sk_fullsock(skb->sk): sk->type [fullsock field]",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, type)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = ACCEPT,
-},
-{
-	"sk_fullsock(skb->sk): sk->family [non fullsock field]",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, family)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = ACCEPT,
-},
-{
-	"sk_fullsock(skb->sk): sk->state [narrow load]",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, state)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = ACCEPT,
-},
-{
-	"sk_fullsock(skb->sk): sk->dst_port [word load] (backward compatibility)",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = ACCEPT,
-},
-{
-	"sk_fullsock(skb->sk): sk->dst_port [half load]",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = ACCEPT,
-},
-{
-	"sk_fullsock(skb->sk): sk->dst_port [half load] (invalid)",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = REJECT,
-	.errstr = "invalid sock access",
-},
-{
-	"sk_fullsock(skb->sk): sk->dst_port [byte load]",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_0, offsetof(struct bpf_sock, dst_port)),
-	BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 1),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = ACCEPT,
-},
-{
-	"sk_fullsock(skb->sk): sk->dst_port [byte load] (invalid)",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = REJECT,
-	.errstr = "invalid sock access",
-},
-{
-	"sk_fullsock(skb->sk): past sk->dst_port [half load] (invalid)",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_0, offsetofend(struct bpf_sock, dst_port)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = REJECT,
-	.errstr = "invalid sock access",
-},
-{
-	"sk_fullsock(skb->sk): sk->dst_ip6 [load 2nd byte]",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_ip6[0]) + 1),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = ACCEPT,
-},
-{
-	"sk_fullsock(skb->sk): sk->type [narrow load]",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, type)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = ACCEPT,
-},
-{
-	"sk_fullsock(skb->sk): sk->protocol [narrow load]",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, protocol)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = ACCEPT,
-},
-{
-	"sk_fullsock(skb->sk): beyond last field",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetofend(struct bpf_sock, rx_queue_mapping)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = REJECT,
-	.errstr = "invalid sock access",
-},
-{
-	"bpf_tcp_sock(skb->sk): no !skb->sk check",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = REJECT,
-	.errstr = "type=sock_common_or_null expected=sock_common",
-},
-{
-	"bpf_tcp_sock(skb->sk): no NULL check on ret",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_tcp_sock, snd_cwnd)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = REJECT,
-	.errstr = "invalid mem access 'tcp_sock_or_null'",
-},
-{
-	"bpf_tcp_sock(skb->sk): tp->snd_cwnd",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_tcp_sock, snd_cwnd)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = ACCEPT,
-},
-{
-	"bpf_tcp_sock(skb->sk): tp->bytes_acked",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_tcp_sock, bytes_acked)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = ACCEPT,
-},
-{
-	"bpf_tcp_sock(skb->sk): beyond last field",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, offsetofend(struct bpf_tcp_sock, bytes_acked)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = REJECT,
-	.errstr = "invalid tcp_sock access",
-},
-{
-	"bpf_tcp_sock(bpf_sk_fullsock(skb->sk)): tp->snd_cwnd",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_tcp_sock, snd_cwnd)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.result = ACCEPT,
-},
-{
-	"bpf_sk_release(skb->sk)",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = REJECT,
-	.errstr = "R1 must be referenced when passed to release function",
-},
-{
-	"bpf_sk_release(bpf_sk_fullsock(skb->sk))",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = REJECT,
-	.errstr = "R1 must be referenced when passed to release function",
-},
-{
-	"bpf_sk_release(bpf_tcp_sock(skb->sk))",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = REJECT,
-	.errstr = "R1 must be referenced when passed to release function",
-},
-{
-	"sk_storage_get(map, skb->sk, NULL, 0): value == NULL",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_storage_get),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_sk_storage_map = { 11 },
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-},
-{
-	"sk_storage_get(map, skb->sk, 1, 1): value == 1",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_4, 1),
-	BPF_MOV64_IMM(BPF_REG_3, 1),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_storage_get),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_sk_storage_map = { 11 },
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = REJECT,
-	.errstr = "R3 type=scalar expected=fp",
-},
-{
-	"sk_storage_get(map, skb->sk, &stack_value, 1): stack_value",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_4, 1),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -8),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_storage_get),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_sk_storage_map = { 14 },
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-},
-{
-	"sk_storage_get(map, skb->sk, &stack_value, 1): partially init stack_value",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_4, 1),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -8),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_storage_get),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_sk_storage_map = { 14 },
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = REJECT,
-	.errstr = "invalid indirect read from stack",
-},
-{
-	"bpf_map_lookup_elem(smap, &key)",
-	.insns = {
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_sk_storage_map = { 3 },
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = REJECT,
-	.errstr = "cannot pass map_type 24 into func bpf_map_lookup_elem",
-},
-{
-	"bpf_map_lookup_elem(xskmap, &key); xs->queue_id",
-	.insns = {
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_xdp_sock, queue_id)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_xskmap = { 3 },
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.result = ACCEPT,
-},
-{
-	"bpf_map_lookup_elem(sockmap, &key)",
-	.insns = {
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_sockmap = { 3 },
-	.prog_type = BPF_PROG_TYPE_SK_SKB,
-	.result = REJECT,
-	.errstr = "Unreleased reference id=2 alloc_insn=5",
-},
-{
-	"bpf_map_lookup_elem(sockhash, &key)",
-	.insns = {
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_sockhash = { 3 },
-	.prog_type = BPF_PROG_TYPE_SK_SKB,
-	.result = REJECT,
-	.errstr = "Unreleased reference id=2 alloc_insn=5",
-},
-{
-	"bpf_map_lookup_elem(sockmap, &key); sk->type [fullsock field]; bpf_sk_release(sk)",
-	.insns = {
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, type)),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_sockmap = { 3 },
-	.prog_type = BPF_PROG_TYPE_SK_SKB,
-	.result = ACCEPT,
-},
-{
-	"bpf_map_lookup_elem(sockhash, &key); sk->type [fullsock field]; bpf_sk_release(sk)",
-	.insns = {
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, type)),
-	BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_sockhash = { 3 },
-	.prog_type = BPF_PROG_TYPE_SK_SKB,
-	.result = ACCEPT,
-},
-{
-	"bpf_sk_select_reuseport(ctx, reuseport_array, &key, flags)",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -4),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_select_reuseport),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_reuseport_array = { 4 },
-	.prog_type = BPF_PROG_TYPE_SK_REUSEPORT,
-	.result = ACCEPT,
-},
-{
-	"bpf_sk_select_reuseport(ctx, sockmap, &key, flags)",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -4),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_select_reuseport),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_sockmap = { 4 },
-	.prog_type = BPF_PROG_TYPE_SK_REUSEPORT,
-	.result = ACCEPT,
-},
-{
-	"bpf_sk_select_reuseport(ctx, sockhash, &key, flags)",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_4, 0),
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -4),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_EMIT_CALL(BPF_FUNC_sk_select_reuseport),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_sockmap = { 4 },
-	.prog_type = BPF_PROG_TYPE_SK_REUSEPORT,
-	.result = ACCEPT,
-},
-{
-	"mark null check on return value of bpf_skc_to helpers",
-	.insns = {
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_EMIT_CALL(BPF_FUNC_skc_to_tcp_sock),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_EMIT_CALL(BPF_FUNC_skc_to_tcp_request_sock),
-	BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_8, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_7, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = REJECT,
-	.errstr = "invalid mem access",
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "unknown func",
-},
diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c
deleted file mode 100644
index 9bb302dade23..000000000000
--- a/tools/testing/selftests/bpf/verifier/spill_fill.c
+++ /dev/null
@@ -1,344 +0,0 @@
-{
-	"check valid spill/fill",
-	.insns = {
-	/* spill R1(ctx) into stack */
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
-	/* fill it back into R2 */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -8),
-	/* should be able to access R0 = *(R2 + 8) */
-	/* BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 8), */
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R0 leaks addr",
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.retval = POINTER_VALUE,
-},
-{
-	"check valid spill/fill, skb mark",
-	.insns = {
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0,
-		    offsetof(struct __sk_buff, mark)),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.result_unpriv = ACCEPT,
-},
-{
-	"check valid spill/fill, ptr to mem",
-	.insns = {
-	/* reserve 8 byte ringbuf memory */
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_2, 8),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve),
-	/* store a pointer to the reserved memory in R6 */
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	/* check whether the reservation was successful */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	/* spill R6(mem) into the stack */
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, -8),
-	/* fill it back in R7 */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_10, -8),
-	/* should be able to access *(R7) = 0 */
-	BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 0),
-	/* submit the reserved ringbuf memory */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_ringbuf = { 1 },
-	.result = ACCEPT,
-	.result_unpriv = ACCEPT,
-},
-{
-	"check with invalid reg offset 0",
-	.insns = {
-	/* reserve 8 byte ringbuf memory */
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_2, 8),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_reserve),
-	/* store a pointer to the reserved memory in R6 */
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	/* add invalid offset to memory or NULL */
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
-	/* check whether the reservation was successful */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	/* should not be able to access *(R7) = 0 */
-	BPF_ST_MEM(BPF_W, BPF_REG_6, 0, 0),
-	/* submit the reserved ringbuf memory */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ringbuf_submit),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_ringbuf = { 1 },
-	.result = REJECT,
-	.errstr = "R0 pointer arithmetic on ringbuf_mem_or_null prohibited",
-},
-{
-	"check corrupted spill/fill",
-	.insns = {
-	/* spill R1(ctx) into stack */
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
-	/* mess up with R1 pointer on stack */
-	BPF_ST_MEM(BPF_B, BPF_REG_10, -7, 0x23),
-	/* fill back into R0 is fine for priv.
-	 * R0 now becomes SCALAR_VALUE.
-	 */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
-	/* Load from R0 should fail. */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 8),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "attempt to corrupt spilled",
-	.errstr = "R0 invalid mem access 'scalar'",
-	.result = REJECT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"check corrupted spill/fill, LSB",
-	.insns = {
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
-	BPF_ST_MEM(BPF_H, BPF_REG_10, -8, 0xcafe),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "attempt to corrupt spilled",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-	.retval = POINTER_VALUE,
-},
-{
-	"check corrupted spill/fill, MSB",
-	.insns = {
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0x12345678),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "attempt to corrupt spilled",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-	.retval = POINTER_VALUE,
-},
-{
-	"Spill and refill a u32 const scalar.  Offset to skb->data",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	/* r4 = 20 */
-	BPF_MOV32_IMM(BPF_REG_4, 20),
-	/* *(u32 *)(r10 -8) = r4 */
-	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8),
-	/* r4 = *(u32 *)(r10 -8) */
-	BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -8),
-	/* r0 = r2 */
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	/* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=20 */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4),
-	/* if (r0 > r3) R0=pkt,off=20 R2=pkt R3=pkt_end R4=20 */
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	/* r0 = *(u32 *)r2 R0=pkt,off=20,r=20 R2=pkt,r=20 R3=pkt_end R4=20 */
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"Spill a u32 const, refill from another half of the uninit u32 from the stack",
-	.insns = {
-	/* r4 = 20 */
-	BPF_MOV32_IMM(BPF_REG_4, 20),
-	/* *(u32 *)(r10 -8) = r4 */
-	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8),
-	/* r4 = *(u32 *)(r10 -4) fp-8=????rrrr*/
-	BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -4),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid read from stack off -4+0 size 4",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"Spill a u32 const scalar.  Refill as u16.  Offset to skb->data",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	/* r4 = 20 */
-	BPF_MOV32_IMM(BPF_REG_4, 20),
-	/* *(u32 *)(r10 -8) = r4 */
-	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8),
-	/* r4 = *(u16 *)(r10 -8) */
-	BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -8),
-	/* r0 = r2 */
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	/* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=65535 */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4),
-	/* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=umax=65535 */
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	/* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=20 */
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid access to packet",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"Spill u32 const scalars.  Refill as u64.  Offset to skb->data",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	/* r6 = 0 */
-	BPF_MOV32_IMM(BPF_REG_6, 0),
-	/* r7 = 20 */
-	BPF_MOV32_IMM(BPF_REG_7, 20),
-	/* *(u32 *)(r10 -4) = r6 */
-	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_6, -4),
-	/* *(u32 *)(r10 -8) = r7 */
-	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, -8),
-	/* r4 = *(u64 *)(r10 -8) */
-	BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -8),
-	/* r0 = r2 */
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	/* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=65535 */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4),
-	/* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=umax=65535 */
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	/* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=20 */
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid access to packet",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"Spill a u32 const scalar.  Refill as u16 from fp-6.  Offset to skb->data",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	/* r4 = 20 */
-	BPF_MOV32_IMM(BPF_REG_4, 20),
-	/* *(u32 *)(r10 -8) = r4 */
-	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8),
-	/* r4 = *(u16 *)(r10 -6) */
-	BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -6),
-	/* r0 = r2 */
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	/* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=65535 */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4),
-	/* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=umax=65535 */
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	/* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=20 */
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid access to packet",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"Spill and refill a u32 const scalar at non 8byte aligned stack addr.  Offset to skb->data",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	/* r4 = 20 */
-	BPF_MOV32_IMM(BPF_REG_4, 20),
-	/* *(u32 *)(r10 -8) = r4 */
-	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8),
-	/* *(u32 *)(r10 -4) = r4 */
-	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -4),
-	/* r4 = *(u32 *)(r10 -4),  */
-	BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -4),
-	/* r0 = r2 */
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	/* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=umax=U32_MAX */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4),
-	/* if (r0 > r3) R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4= */
-	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
-	/* r0 = *(u32 *)r2 R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4= */
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid access to packet",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"Spill and refill a umax=40 bounded scalar.  Offset to skb->data",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_1,
-		    offsetof(struct __sk_buff, tstamp)),
-	BPF_JMP_IMM(BPF_JLE, BPF_REG_4, 40, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	/* *(u32 *)(r10 -8) = r4 R4=umax=40 */
-	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8),
-	/* r4 = (*u32 *)(r10 - 8) */
-	BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -8),
-	/* r2 += r4 R2=pkt R4=umax=40 */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_4),
-	/* r0 = r2 R2=pkt,umax=40 R4=umax=40 */
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	/* r2 += 20 R0=pkt,umax=40 R2=pkt,umax=40 */
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 20),
-	/* if (r2 > r3) R0=pkt,umax=40 R2=pkt,off=20,umax=40 */
-	BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_3, 1),
-	/* r0 = *(u32 *)r0 R0=pkt,r=20,umax=40 R2=pkt,off=20,r=20,umax=40 */
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"Spill a u32 scalar at fp-4 and then at fp-8",
-	.insns = {
-	/* r4 = 4321 */
-	BPF_MOV32_IMM(BPF_REG_4, 4321),
-	/* *(u32 *)(r10 -4) = r4 */
-	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -4),
-	/* *(u32 *)(r10 -8) = r4 */
-	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8),
-	/* r4 = *(u64 *)(r10 -8) */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
diff --git a/tools/testing/selftests/bpf/verifier/spin_lock.c b/tools/testing/selftests/bpf/verifier/spin_lock.c
deleted file mode 100644
index eaf114f07e2e..000000000000
--- a/tools/testing/selftests/bpf/verifier/spin_lock.c
+++ /dev/null
@@ -1,447 +0,0 @@
-{
-	"spin_lock: test1 success",
-	.insns = {
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1,
-		      0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_spin_lock = { 3 },
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"spin_lock: test2 direct ld/st",
-	.insns = {
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1,
-		      0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_spin_lock = { 3 },
-	.result = REJECT,
-	.errstr = "cannot be accessed directly",
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"spin_lock: test3 direct ld/st",
-	.insns = {
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1,
-		      0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 1),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_spin_lock = { 3 },
-	.result = REJECT,
-	.errstr = "cannot be accessed directly",
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"spin_lock: test4 direct ld/st",
-	.insns = {
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1,
-		      0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_6, 3),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_spin_lock = { 3 },
-	.result = REJECT,
-	.errstr = "cannot be accessed directly",
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"spin_lock: test5 call within a locked region",
-	.insns = {
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1,
-		      0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_spin_lock = { 3 },
-	.result = REJECT,
-	.errstr = "calls are not allowed",
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"spin_lock: test6 missing unlock",
-	.insns = {
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1,
-		      0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 0),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_spin_lock = { 3 },
-	.result = REJECT,
-	.errstr = "unlock is missing",
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"spin_lock: test7 unlock without lock",
-	.insns = {
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1,
-		      0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_spin_lock = { 3 },
-	.result = REJECT,
-	.errstr = "without taking a lock",
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"spin_lock: test8 double lock",
-	.insns = {
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1,
-		      0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_spin_lock = { 3 },
-	.result = REJECT,
-	.errstr = "calls are not allowed",
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"spin_lock: test9 different lock",
-	.insns = {
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1,
-		      0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1,
-		      0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_spin_lock = { 3, 11 },
-	.result = REJECT,
-	.errstr = "unlock of different lock",
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"spin_lock: test10 lock in subprog without unlock",
-	.insns = {
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1,
-		      0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 5),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_spin_lock = { 3 },
-	.result = REJECT,
-	.errstr = "unlock is missing",
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"spin_lock: test11 ld_abs under lock",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1,
-		      0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock),
-	BPF_LD_ABS(BPF_B, 0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_spin_lock = { 4 },
-	.result = REJECT,
-	.errstr = "inside bpf_spin_lock",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"spin_lock: regsafe compare reg->id for map value",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_6, offsetof(struct __sk_buff, mark)),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_MOV64_REG(BPF_REG_9, BPF_REG_1),
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_9),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_8),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_spin_lock = { 2 },
-	.result = REJECT,
-	.errstr = "bpf_spin_unlock of different lock",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.flags = BPF_F_TEST_STATE_FREQ,
-},
-/* Make sure that regsafe() compares ids for spin lock records using
- * check_ids():
- *  1: r9 = map_lookup_elem(...)  ; r9.id == 1
- *  2: r8 = map_lookup_elem(...)  ; r8.id == 2
- *  3: r7 = ktime_get_ns()
- *  4: r6 = ktime_get_ns()
- *  5: if r6 > r7 goto <9>
- *  6: spin_lock(r8)
- *  7: r9 = r8
- *  8: goto <10>
- *  9: spin_lock(r9)
- * 10: spin_unlock(r9)             ; r9.id == 1 || r9.id == 2 and lock is active,
- *                                 ; second visit to (10) should be considered safe
- *                                 ; if check_ids() is used.
- * 11: exit(0)
- */
-{
-	"spin_lock: regsafe() check_ids() similar id mappings",
-	.insns = {
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
-	/* r9 = map_lookup_elem(...) */
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1,
-		      0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 24),
-	BPF_MOV64_REG(BPF_REG_9, BPF_REG_0),
-	/* r8 = map_lookup_elem(...) */
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-	BPF_LD_MAP_FD(BPF_REG_1,
-		      0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 18),
-	BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
-	/* r7 = ktime_get_ns() */
-	BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	/* r6 = ktime_get_ns() */
-	BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	/* if r6 > r7 goto +5      ; no new information about the state is derived from
-	 *                         ; this check, thus produced verifier states differ
-	 *                         ; only in 'insn_idx'
-	 * spin_lock(r8)
-	 * r9 = r8
-	 * goto unlock
-	 */
-	BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_7, 5),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_EMIT_CALL(BPF_FUNC_spin_lock),
-	BPF_MOV64_REG(BPF_REG_9, BPF_REG_8),
-	BPF_JMP_A(3),
-	/* spin_lock(r9) */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_9),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_EMIT_CALL(BPF_FUNC_spin_lock),
-	/* spin_unlock(r9) */
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_9),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4),
-	BPF_EMIT_CALL(BPF_FUNC_spin_unlock),
-	/* exit(0) */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_spin_lock = { 3, 10 },
-	.result = VERBOSE_ACCEPT,
-	.errstr = "28: safe",
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-	.flags = BPF_F_TEST_STATE_FREQ,
-},
diff --git a/tools/testing/selftests/bpf/verifier/stack_ptr.c b/tools/testing/selftests/bpf/verifier/stack_ptr.c
deleted file mode 100644
index 8ab94d65f3d5..000000000000
--- a/tools/testing/selftests/bpf/verifier/stack_ptr.c
+++ /dev/null
@@ -1,359 +0,0 @@
-{
-	"PTR_TO_STACK store/load",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -10),
-	BPF_ST_MEM(BPF_DW, BPF_REG_1, 2, 0xfaceb00c),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 2),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0xfaceb00c,
-},
-{
-	"PTR_TO_STACK store/load - bad alignment on off",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_1, 2, 0xfaceb00c),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 2),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "misaligned stack access off (0x0; 0x0)+-8+2 size 8",
-},
-{
-	"PTR_TO_STACK store/load - bad alignment on reg",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -10),
-	BPF_ST_MEM(BPF_DW, BPF_REG_1, 8, 0xfaceb00c),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 8),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "misaligned stack access off (0x0; 0x0)+-10+8 size 8",
-},
-{
-	"PTR_TO_STACK store/load - out of bounds low",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -80000),
-	BPF_ST_MEM(BPF_DW, BPF_REG_1, 8, 0xfaceb00c),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 8),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid write to stack R1 off=-79992 size=8",
-	.errstr_unpriv = "R1 stack pointer arithmetic goes out of range",
-},
-{
-	"PTR_TO_STACK store/load - out of bounds high",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_1, 8, 0xfaceb00c),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 8),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid write to stack R1 off=0 size=8",
-},
-{
-	"PTR_TO_STACK check high 1",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -1),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 42,
-},
-{
-	"PTR_TO_STACK check high 2",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, -1, 42),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, -1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 42,
-},
-{
-	"PTR_TO_STACK check high 3",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, -1, 42),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, -1),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R1 stack pointer arithmetic goes out of range",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-	.retval = 42,
-},
-{
-	"PTR_TO_STACK check high 4",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R1 stack pointer arithmetic goes out of range",
-	.errstr = "invalid write to stack R1 off=0 size=1",
-	.result = REJECT,
-},
-{
-	"PTR_TO_STACK check high 5",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, (1 << 29) - 1),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr_unpriv = "R1 stack pointer arithmetic goes out of range",
-	.errstr = "invalid write to stack R1",
-},
-{
-	"PTR_TO_STACK check high 6",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, (1 << 29) - 1),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, SHRT_MAX, 42),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, SHRT_MAX),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr_unpriv = "R1 stack pointer arithmetic goes out of range",
-	.errstr = "invalid write to stack",
-},
-{
-	"PTR_TO_STACK check high 7",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, (1 << 29) - 1),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, (1 << 29) - 1),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, SHRT_MAX, 42),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, SHRT_MAX),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr_unpriv = "R1 stack pointer arithmetic goes out of range",
-	.errstr = "fp pointer offset",
-},
-{
-	"PTR_TO_STACK check low 1",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -512),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 42,
-},
-{
-	"PTR_TO_STACK check low 2",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -513),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 1, 42),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 1),
-	BPF_EXIT_INSN(),
-	},
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R1 stack pointer arithmetic goes out of range",
-	.result = ACCEPT,
-	.retval = 42,
-},
-{
-	"PTR_TO_STACK check low 3",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -513),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R1 stack pointer arithmetic goes out of range",
-	.errstr = "invalid write to stack R1 off=-513 size=1",
-	.result = REJECT,
-},
-{
-	"PTR_TO_STACK check low 4",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, INT_MIN),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "math between fp pointer",
-},
-{
-	"PTR_TO_STACK check low 5",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -((1 << 29) - 1)),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr_unpriv = "R1 stack pointer arithmetic goes out of range",
-	.errstr = "invalid write to stack",
-},
-{
-	"PTR_TO_STACK check low 6",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -((1 << 29) - 1)),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, SHRT_MIN, 42),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, SHRT_MIN),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid write to stack",
-	.errstr_unpriv = "R1 stack pointer arithmetic goes out of range",
-},
-{
-	"PTR_TO_STACK check low 7",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -((1 << 29) - 1)),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -((1 << 29) - 1)),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, SHRT_MIN, 42),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, SHRT_MIN),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr_unpriv = "R1 stack pointer arithmetic goes out of range",
-	.errstr = "fp pointer offset",
-},
-{
-	"PTR_TO_STACK mixed reg/k, 1",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -3),
-	BPF_MOV64_IMM(BPF_REG_2, -3),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 42,
-},
-{
-	"PTR_TO_STACK mixed reg/k, 2",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -3),
-	BPF_MOV64_IMM(BPF_REG_2, -3),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42),
-	BPF_MOV64_REG(BPF_REG_5, BPF_REG_10),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_5, -6),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 42,
-},
-{
-	"PTR_TO_STACK mixed reg/k, 3",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -3),
-	BPF_MOV64_IMM(BPF_REG_2, -3),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = -3,
-},
-{
-	"PTR_TO_STACK reg",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_MOV64_IMM(BPF_REG_2, -3),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2),
-	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 42,
-},
-{
-	"stack pointer arithmetic",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 4),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 0),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, -10),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1),
-	BPF_ST_MEM(0, BPF_REG_2, 4, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 8),
-	BPF_ST_MEM(0, BPF_REG_2, 4, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-},
-{
-	"store PTR_TO_STACK in R10 to array map using BPF_B",
-	.insns = {
-	/* Load pointer to map. */
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 2),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	/* Copy R10 to R9. */
-	BPF_MOV64_REG(BPF_REG_9, BPF_REG_10),
-	/* Pollute other registers with unaligned values. */
-	BPF_MOV64_IMM(BPF_REG_2, -1),
-	BPF_MOV64_IMM(BPF_REG_3, -1),
-	BPF_MOV64_IMM(BPF_REG_4, -1),
-	BPF_MOV64_IMM(BPF_REG_5, -1),
-	BPF_MOV64_IMM(BPF_REG_6, -1),
-	BPF_MOV64_IMM(BPF_REG_7, -1),
-	BPF_MOV64_IMM(BPF_REG_8, -1),
-	/* Store both R9 and R10 with BPF_B and read back. */
-	BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_10, 0),
-	BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_1, 0),
-	BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_9, 0),
-	BPF_LDX_MEM(BPF_B, BPF_REG_3, BPF_REG_1, 0),
-	/* Should read back as same value. */
-	BPF_JMP_REG(BPF_JEQ, BPF_REG_2, BPF_REG_3, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_0, 42),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = ACCEPT,
-	.retval = 42,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
diff --git a/tools/testing/selftests/bpf/verifier/subreg.c b/tools/testing/selftests/bpf/verifier/subreg.c
deleted file mode 100644
index 4c4133c80440..000000000000
--- a/tools/testing/selftests/bpf/verifier/subreg.c
+++ /dev/null
@@ -1,533 +0,0 @@
-/* This file contains sub-register zero extension checks for insns defining
- * sub-registers, meaning:
- *   - All insns under BPF_ALU class. Their BPF_ALU32 variants or narrow width
- *     forms (BPF_END) could define sub-registers.
- *   - Narrow direct loads, BPF_B/H/W | BPF_LDX.
- *   - BPF_LD is not exposed to JIT back-ends, so no need for testing.
- *
- * "get_prandom_u32" is used to initialize low 32-bit of some registers to
- * prevent potential optimizations done by verifier or JIT back-ends which could
- * optimize register back into constant when range info shows one register is a
- * constant.
- */
-{
-	"add32 reg zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LD_IMM64(BPF_REG_0, 0x100000000ULL),
-	BPF_ALU32_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"add32 imm zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	/* An insn could have no effect on the low 32-bit, for example:
-	 *   a = a + 0
-	 *   a = a | 0
-	 *   a = a & -1
-	 * But, they should still zero high 32-bit.
-	 */
-	BPF_ALU32_IMM(BPF_ADD, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_ADD, BPF_REG_0, -2),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_6),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"sub32 reg zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LD_IMM64(BPF_REG_0, 0x1ffffffffULL),
-	BPF_ALU32_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"sub32 imm zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_SUB, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_SUB, BPF_REG_0, 1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_6),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"mul32 reg zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LD_IMM64(BPF_REG_0, 0x100000001ULL),
-	BPF_ALU32_REG(BPF_MUL, BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"mul32 imm zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_MUL, BPF_REG_0, 1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_MUL, BPF_REG_0, -1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_6),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"div32 reg zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_0, -1),
-	BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"div32 imm zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_DIV, BPF_REG_0, 1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_DIV, BPF_REG_0, 2),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_6),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"or32 reg zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LD_IMM64(BPF_REG_0, 0x100000001ULL),
-	BPF_ALU32_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"or32 imm zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_OR, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_OR, BPF_REG_0, 1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_6),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"and32 reg zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x100000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_1, BPF_REG_0),
-	BPF_LD_IMM64(BPF_REG_0, 0x1ffffffffULL),
-	BPF_ALU32_REG(BPF_AND, BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"and32 imm zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_AND, BPF_REG_0, -1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_AND, BPF_REG_0, -2),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_6),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"lsh32 reg zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x100000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_MOV64_IMM(BPF_REG_1, 1),
-	BPF_ALU32_REG(BPF_LSH, BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"lsh32 imm zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_LSH, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_LSH, BPF_REG_0, 1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_6),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"rsh32 reg zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_MOV64_IMM(BPF_REG_1, 1),
-	BPF_ALU32_REG(BPF_RSH, BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"rsh32 imm zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_RSH, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_RSH, BPF_REG_0, 1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_6),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"neg32 reg zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_NEG, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"mod32 reg zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_0, -1),
-	BPF_ALU32_REG(BPF_MOD, BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"mod32 imm zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_MOD, BPF_REG_0, 1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_MOD, BPF_REG_0, 2),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_6),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"xor32 reg zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-	BPF_LD_IMM64(BPF_REG_0, 0x100000000ULL),
-	BPF_ALU32_REG(BPF_XOR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"xor32 imm zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_XOR, BPF_REG_0, 1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"mov32 reg zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x100000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_1, BPF_REG_0),
-	BPF_LD_IMM64(BPF_REG_0, 0x100000000ULL),
-	BPF_MOV32_REG(BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"mov32 imm zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_MOV32_IMM(BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_MOV32_IMM(BPF_REG_0, 1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_6),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"arsh32 reg zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_MOV64_IMM(BPF_REG_1, 1),
-	BPF_ALU32_REG(BPF_ARSH, BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"arsh32 imm zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_ARSH, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_ALU32_IMM(BPF_ARSH, BPF_REG_0, 1),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_6),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"end16 (to_le) reg zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 32),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_6),
-	BPF_ENDIAN(BPF_TO_LE, BPF_REG_0, 16),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"end32 (to_le) reg zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 32),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_6),
-	BPF_ENDIAN(BPF_TO_LE, BPF_REG_0, 32),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"end16 (to_be) reg zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 32),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_6),
-	BPF_ENDIAN(BPF_TO_BE, BPF_REG_0, 16),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"end32 (to_be) reg zero extend check",
-	.insns = {
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 32),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_6),
-	BPF_ENDIAN(BPF_TO_BE, BPF_REG_0, 32),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"ldx_b zero extend check",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -4),
-	BPF_ST_MEM(BPF_W, BPF_REG_6, 0, 0xfaceb00c),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, 0),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"ldx_h zero extend check",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -4),
-	BPF_ST_MEM(BPF_W, BPF_REG_6, 0, 0xfaceb00c),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_6, 0),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"ldx_w zero extend check",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -4),
-	BPF_ST_MEM(BPF_W, BPF_REG_6, 0, 0xfaceb00c),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
-	BPF_LD_IMM64(BPF_REG_1, 0x1000000000ULL),
-	BPF_ALU64_REG(BPF_OR, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 0),
-	BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, 32),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = 0,
-},
diff --git a/tools/testing/selftests/bpf/verifier/uninit.c b/tools/testing/selftests/bpf/verifier/uninit.c
deleted file mode 100644
index 987a5871ff1d..000000000000
--- a/tools/testing/selftests/bpf/verifier/uninit.c
+++ /dev/null
@@ -1,39 +0,0 @@
-{
-	"read uninitialized register",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R2 !read_ok",
-	.result = REJECT,
-},
-{
-	"read invalid register",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_0, -1),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R15 is invalid",
-	.result = REJECT,
-},
-{
-	"program doesn't init R0 before exit",
-	.insns = {
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_2, BPF_REG_1),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R0 !read_ok",
-	.result = REJECT,
-},
-{
-	"program doesn't init R0 before exit in all branches",
-	.insns = {
-	BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 2),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R0 !read_ok",
-	.errstr_unpriv = "R1 pointer comparison",
-	.result = REJECT,
-},
diff --git a/tools/testing/selftests/bpf/verifier/unpriv.c b/tools/testing/selftests/bpf/verifier/unpriv.c
deleted file mode 100644
index 878ca26c3f0a..000000000000
--- a/tools/testing/selftests/bpf/verifier/unpriv.c
+++ /dev/null
@@ -1,539 +0,0 @@
-{
-	"unpriv: return pointer",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_10),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R0 leaks addr",
-	.retval = POINTER_VALUE,
-},
-{
-	"unpriv: add const to pointer",
-	.insns = {
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-},
-{
-	"unpriv: add pointer to pointer",
-	.insns = {
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_10),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "R1 pointer += pointer",
-},
-{
-	"unpriv: neg pointer",
-	.insns = {
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R1 pointer arithmetic",
-},
-{
-	"unpriv: cmp pointer with const",
-	.insns = {
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R1 pointer comparison",
-},
-{
-	"unpriv: cmp pointer with pointer",
-	.insns = {
-	BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_10, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R10 pointer comparison",
-},
-{
-	"unpriv: check that printk is disallowed",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_2, 8),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_1),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_trace_printk),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "unknown func bpf_trace_printk#6",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
-},
-{
-	"unpriv: pass pointer to helper function",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_2),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_2),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_update_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr_unpriv = "R4 leaks addr",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-},
-{
-	"unpriv: indirectly pass pointer on stack to helper function",
-	.insns = {
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_10, -8),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr_unpriv = "invalid indirect read from stack R2 off -8+0 size 8",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-},
-{
-	"unpriv: mangle pointer on stack 1",
-	.insns = {
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_10, -8),
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -8, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "attempt to corrupt spilled",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-},
-{
-	"unpriv: mangle pointer on stack 2",
-	.insns = {
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_10, -8),
-	BPF_ST_MEM(BPF_B, BPF_REG_10, -1, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "attempt to corrupt spilled",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-},
-{
-	"unpriv: read pointer from stack in small chunks",
-	.insns = {
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_10, -8),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "invalid size",
-	.result = REJECT,
-},
-{
-	"unpriv: write pointer into ctx",
-	.insns = {
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R1 leaks addr",
-	.result_unpriv = REJECT,
-	.errstr = "invalid bpf_context access",
-	.result = REJECT,
-},
-{
-	"unpriv: spill/fill of ctx",
-	.insns = {
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
-	BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-},
-{
-	"unpriv: spill/fill of ctx 2",
-	.insns = {
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
-	BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_hash_recalc),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"unpriv: spill/fill of ctx 3",
-	.insns = {
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
-	BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_10, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_hash_recalc),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "R1 type=fp expected=ctx",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"unpriv: spill/fill of ctx 4",
-	.insns = {
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
-	BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_RAW_INSN(BPF_STX | BPF_ATOMIC | BPF_DW,
-		     BPF_REG_10, BPF_REG_0, -8, BPF_ADD),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_hash_recalc),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "R1 type=scalar expected=ctx",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"unpriv: spill/fill of different pointers stx",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_3, 42),
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 3),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
-	BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
-	BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
-	BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3,
-		    offsetof(struct __sk_buff, mark)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "same insn cannot be used with different pointers",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"unpriv: spill/fill of different pointers stx - ctx and sock",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
-	/* struct bpf_sock *sock = bpf_sock_lookup(...); */
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	/* u64 foo; */
-	/* void *target = &foo; */
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
-	/* if (skb == NULL) *target = sock; */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
-		BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0),
-	/* else *target = skb; */
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
-		BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
-	/* struct __sk_buff *skb = *target; */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
-	/* skb->mark = 42; */
-	BPF_MOV64_IMM(BPF_REG_3, 42),
-	BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3,
-		    offsetof(struct __sk_buff, mark)),
-	/* if (sk) bpf_sk_release(sk) */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
-		BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "type=ctx expected=sock",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"unpriv: spill/fill of different pointers stx - leak sock",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
-	/* struct bpf_sock *sock = bpf_sock_lookup(...); */
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	/* u64 foo; */
-	/* void *target = &foo; */
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
-	/* if (skb == NULL) *target = sock; */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
-		BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0),
-	/* else *target = skb; */
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
-		BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
-	/* struct __sk_buff *skb = *target; */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
-	/* skb->mark = 42; */
-	BPF_MOV64_IMM(BPF_REG_3, 42),
-	BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3,
-		    offsetof(struct __sk_buff, mark)),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	//.errstr = "same insn cannot be used with different pointers",
-	.errstr = "Unreleased reference",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"unpriv: spill/fill of different pointers stx - sock and ctx (read)",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
-	/* struct bpf_sock *sock = bpf_sock_lookup(...); */
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	/* u64 foo; */
-	/* void *target = &foo; */
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
-	/* if (skb) *target = skb */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
-		BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
-	/* else *target = sock */
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
-		BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0),
-	/* struct bpf_sock *sk = *target; */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
-	/* if (sk) u32 foo = sk->mark; bpf_sk_release(sk); */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 2),
-		BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-			    offsetof(struct bpf_sock, mark)),
-		BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "same insn cannot be used with different pointers",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"unpriv: spill/fill of different pointers stx - sock and ctx (write)",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
-	/* struct bpf_sock *sock = bpf_sock_lookup(...); */
-	BPF_SK_LOOKUP(sk_lookup_tcp),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	/* u64 foo; */
-	/* void *target = &foo; */
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
-	/* if (skb) *target = skb */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
-		BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
-	/* else *target = sock */
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
-		BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0),
-	/* struct bpf_sock *sk = *target; */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
-	/* if (sk) sk->mark = 42; bpf_sk_release(sk); */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 3),
-		BPF_MOV64_IMM(BPF_REG_3, 42),
-		BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3,
-			    offsetof(struct bpf_sock, mark)),
-		BPF_EMIT_CALL(BPF_FUNC_sk_release),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	//.errstr = "same insn cannot be used with different pointers",
-	.errstr = "cannot write into sock",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"unpriv: spill/fill of different pointers ldx",
-	.insns = {
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 3),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2,
-		      -(__s32)offsetof(struct bpf_perf_event_data,
-				       sample_period) - 8),
-	BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_2, 0),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
-	BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_6, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1,
-		    offsetof(struct bpf_perf_event_data, sample_period)),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "same insn cannot be used with different pointers",
-	.prog_type = BPF_PROG_TYPE_PERF_EVENT,
-},
-{
-	"unpriv: write pointer into map elem value",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.errstr_unpriv = "R0 leaks addr",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-},
-{
-	"alu32: mov u32 const",
-	.insns = {
-	BPF_MOV32_IMM(BPF_REG_7, 0),
-	BPF_ALU32_IMM(BPF_AND, BPF_REG_7, 1),
-	BPF_MOV32_REG(BPF_REG_0, BPF_REG_7),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R7 invalid mem access 'scalar'",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-	.retval = 0,
-},
-{
-	"unpriv: partial copy of pointer",
-	.insns = {
-	BPF_MOV32_REG(BPF_REG_1, BPF_REG_10),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R10 partial copy",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-},
-{
-	"unpriv: pass pointer to tail_call",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_3, BPF_REG_1),
-	BPF_LD_MAP_FD(BPF_REG_2, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_tail_call),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_prog1 = { 1 },
-	.errstr_unpriv = "R3 leaks addr into helper",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-},
-{
-	"unpriv: cmp map pointer with zero",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 1 },
-	.errstr_unpriv = "R1 pointer comparison",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-},
-{
-	"unpriv: write into frame pointer",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_10, BPF_REG_1),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "frame pointer is read only",
-	.result = REJECT,
-},
-{
-	"unpriv: spill/fill frame pointer",
-	.insns = {
-	BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -8),
-	BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_10, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_10, BPF_REG_6, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "frame pointer is read only",
-	.result = REJECT,
-},
-{
-	"unpriv: cmp of frame pointer",
-	.insns = {
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_10, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R10 pointer comparison",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-},
-{
-	"unpriv: adding of fp, reg",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_1, 0),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_10),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R1 stack pointer arithmetic goes out of range",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-},
-{
-	"unpriv: adding of fp, imm",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R1 stack pointer arithmetic goes out of range",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-},
-{
-	"unpriv: cmp of stack pointer",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_2, 0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr_unpriv = "R2 pointer comparison",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-},
diff --git a/tools/testing/selftests/bpf/verifier/value.c b/tools/testing/selftests/bpf/verifier/value.c
deleted file mode 100644
index 0e42592b1218..000000000000
--- a/tools/testing/selftests/bpf/verifier/value.c
+++ /dev/null
@@ -1,104 +0,0 @@
-{
-	"map element value store of cleared call register",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr_unpriv = "R1 !read_ok",
-	.errstr = "R1 !read_ok",
-	.result = REJECT,
-	.result_unpriv = REJECT,
-},
-{
-	"map element value with unaligned store",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 17),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 3),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 2, 43),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, -2, 44),
-	BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
-	BPF_ST_MEM(BPF_DW, BPF_REG_8, 0, 32),
-	BPF_ST_MEM(BPF_DW, BPF_REG_8, 2, 33),
-	BPF_ST_MEM(BPF_DW, BPF_REG_8, -2, 34),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_8, 5),
-	BPF_ST_MEM(BPF_DW, BPF_REG_8, 0, 22),
-	BPF_ST_MEM(BPF_DW, BPF_REG_8, 4, 23),
-	BPF_ST_MEM(BPF_DW, BPF_REG_8, -7, 24),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_8),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 3),
-	BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 22),
-	BPF_ST_MEM(BPF_DW, BPF_REG_7, 4, 23),
-	BPF_ST_MEM(BPF_DW, BPF_REG_7, -4, 24),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr_unpriv = "R0 leaks addr",
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"map element value with unaligned load",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JGE, BPF_REG_1, MAX_ENTRIES, 9),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 3),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 2),
-	BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_8, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_8, 2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 5),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 4),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr_unpriv = "R0 leaks addr",
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"map element value is preserved across register spilling",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, offsetof(struct test_val, foo)),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -184),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_1, 0),
-	BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 42),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr_unpriv = "R0 leaks addr",
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
diff --git a/tools/testing/selftests/bpf/verifier/value_adj_spill.c b/tools/testing/selftests/bpf/verifier/value_adj_spill.c
deleted file mode 100644
index 7135e8021b81..000000000000
--- a/tools/testing/selftests/bpf/verifier/value_adj_spill.c
+++ /dev/null
@@ -1,43 +0,0 @@
-{
-	"map element value is preserved across register spilling",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -184),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_1, 0),
-	BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 42),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr_unpriv = "R0 leaks addr",
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-},
-{
-	"map element value or null is marked on register spilling",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -152),
-	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_1, 0),
-	BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 42),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr_unpriv = "R0 leaks addr",
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-},
diff --git a/tools/testing/selftests/bpf/verifier/value_illegal_alu.c b/tools/testing/selftests/bpf/verifier/value_illegal_alu.c
deleted file mode 100644
index d6f29eb4bd57..000000000000
--- a/tools/testing/selftests/bpf/verifier/value_illegal_alu.c
+++ /dev/null
@@ -1,95 +0,0 @@
-{
-	"map element value illegal alu op, 1",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "R0 bitwise operator &= on pointer",
-	.result = REJECT,
-},
-{
-	"map element value illegal alu op, 2",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	BPF_ALU32_IMM(BPF_ADD, BPF_REG_0, 0),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "R0 32-bit pointer arithmetic prohibited",
-	.result = REJECT,
-},
-{
-	"map element value illegal alu op, 3",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	BPF_ALU64_IMM(BPF_DIV, BPF_REG_0, 42),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "R0 pointer arithmetic with /= operator",
-	.result = REJECT,
-},
-{
-	"map element value illegal alu op, 4",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	BPF_ENDIAN(BPF_FROM_BE, BPF_REG_0, 64),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr_unpriv = "R0 pointer arithmetic prohibited",
-	.errstr = "invalid mem access 'scalar'",
-	.result = REJECT,
-	.result_unpriv = REJECT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"map element value illegal alu op, 5",
-	.insns = {
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-	BPF_MOV64_IMM(BPF_REG_3, 4096),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
-	BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_2, BPF_REG_3, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr_unpriv = "leaking pointer from stack off -8",
-	.errstr = "R0 invalid mem access 'scalar'",
-	.result = REJECT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
diff --git a/tools/testing/selftests/bpf/verifier/value_or_null.c b/tools/testing/selftests/bpf/verifier/value_or_null.c
deleted file mode 100644
index 52a8bca14f03..000000000000
--- a/tools/testing/selftests/bpf/verifier/value_or_null.c
+++ /dev/null
@@ -1,220 +0,0 @@
-{
-	"multiple registers share map_lookup_elem result",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 10),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 4 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS
-},
-{
-	"alu ops on ptr_to_map_value_or_null, 1",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 10),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 2),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 4 },
-	.errstr = "R4 pointer arithmetic on map_value_or_null",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS
-},
-{
-	"alu ops on ptr_to_map_value_or_null, 2",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 10),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_4, -1),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 4 },
-	.errstr = "R4 pointer arithmetic on map_value_or_null",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS
-},
-{
-	"alu ops on ptr_to_map_value_or_null, 3",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 10),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
-	BPF_ALU64_IMM(BPF_LSH, BPF_REG_4, 1),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 4 },
-	.errstr = "R4 pointer arithmetic on map_value_or_null",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS
-},
-{
-	"invalid memory access with multiple map_lookup_elem calls",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 10),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 4 },
-	.result = REJECT,
-	.errstr = "R4 !read_ok",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS
-},
-{
-	"valid indirect map_lookup_elem access with 2nd lookup in branch",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 10),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_2, 10),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 0, 3),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 4 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS
-},
-{
-	"invalid map access from else condition",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JGE, BPF_REG_1, MAX_ENTRIES-1, 1),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
-	BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, offsetof(struct test_val, foo)),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 3 },
-	.errstr = "R0 unbounded memory access",
-	.result = REJECT,
-	.errstr_unpriv = "R0 leaks addr",
-	.result_unpriv = REJECT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"map lookup and null branch prediction",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_1, 10),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 2),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 0, 1),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_10, 10),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 4 },
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-},
-{
-	"MAP_VALUE_OR_NULL check_ids() in regsafe()",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	/* r9 = map_lookup_elem(...) */
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1,
-		      0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_REG(BPF_REG_9, BPF_REG_0),
-	/* r8 = map_lookup_elem(...) */
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1,
-		      0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
-	/* r7 = ktime_get_ns() */
-	BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	/* r6 = ktime_get_ns() */
-	BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	/* if r6 > r7 goto +1    ; no new information about the state is derived from
-	 *                       ; this check, thus produced verifier states differ
-	 *                       ; only in 'insn_idx'
-	 * r9 = r8               ; optionally share ID between r9 and r8
-	 */
-	BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_7, 1),
-	BPF_MOV64_REG(BPF_REG_9, BPF_REG_8),
-	/* if r9 == 0 goto <exit> */
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_9, 0, 1),
-	/* read map value via r8, this is not always
-	 * safe because r8 might be not equal to r9.
-	 */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_8, 0),
-	/* exit 0 */
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.flags = BPF_F_TEST_STATE_FREQ,
-	.fixup_map_hash_8b = { 3, 9 },
-	.result = REJECT,
-	.errstr = "R8 invalid mem access 'map_value_or_null'",
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
deleted file mode 100644
index 249187d3c530..000000000000
--- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
+++ /dev/null
@@ -1,1140 +0,0 @@
-{
-	"map access: known scalar += value_ptr unknown vs const",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, len)),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
-	BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
-	BPF_MOV64_IMM(BPF_REG_1, 6),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_MOV64_IMM(BPF_REG_1, 3),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 5 },
-	.fixup_map_array_48b = { 8 },
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"map access: known scalar += value_ptr const vs unknown",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, len)),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
-	BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2),
-	BPF_MOV64_IMM(BPF_REG_1, 3),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 3),
-	BPF_MOV64_IMM(BPF_REG_1, 6),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 5 },
-	.fixup_map_array_48b = { 8 },
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"map access: known scalar += value_ptr const vs const (ne)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, len)),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-	BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2),
-	BPF_MOV64_IMM(BPF_REG_1, 3),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_MOV64_IMM(BPF_REG_1, 5),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 5 },
-	.fixup_map_array_48b = { 8 },
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"map access: known scalar += value_ptr const vs const (eq)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, len)),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-	BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2),
-	BPF_MOV64_IMM(BPF_REG_1, 5),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_MOV64_IMM(BPF_REG_1, 5),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 5 },
-	.fixup_map_array_48b = { 8 },
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"map access: known scalar += value_ptr unknown vs unknown (eq)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, len)),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
-	BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
-	BPF_MOV64_IMM(BPF_REG_1, 6),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 3),
-	BPF_MOV64_IMM(BPF_REG_1, 6),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 5 },
-	.fixup_map_array_48b = { 8 },
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"map access: known scalar += value_ptr unknown vs unknown (lt)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, len)),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
-	BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
-	BPF_MOV64_IMM(BPF_REG_1, 6),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x3),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 3),
-	BPF_MOV64_IMM(BPF_REG_1, 6),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 5 },
-	.fixup_map_array_48b = { 8 },
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"map access: known scalar += value_ptr unknown vs unknown (gt)",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, len)),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
-	BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
-	BPF_MOV64_IMM(BPF_REG_1, 6),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 3),
-	BPF_MOV64_IMM(BPF_REG_1, 6),
-	BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x3),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 5 },
-	.fixup_map_array_48b = { 8 },
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"map access: known scalar += value_ptr from different maps",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, len)),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
-	BPF_MOV64_IMM(BPF_REG_1, 4),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 5 },
-	.fixup_map_array_48b = { 8 },
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"map access: value_ptr -= known scalar from different maps",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, len)),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_IMM(BPF_REG_1, 4),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_16b = { 5 },
-	.fixup_map_array_48b = { 8 },
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R0 min value is outside of the allowed memory range",
-	.retval = 1,
-},
-{
-	"map access: known scalar += value_ptr from different maps, but same value properties",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
-		    offsetof(struct __sk_buff, len)),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
-	BPF_MOV64_IMM(BPF_REG_1, 4),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_48b = { 5 },
-	.fixup_map_array_48b = { 8 },
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"map access: mixing value pointer and scalar, 1",
-	.insns = {
-	// load map value pointer into r0 and r2
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_LD_MAP_FD(BPF_REG_ARG1, 0),
-	BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_FP),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG2, -16),
-	BPF_ST_MEM(BPF_DW, BPF_REG_FP, -16, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	// load some number from the map into r1
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	// depending on r1, branch:
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 3),
-	// branch A
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	BPF_JMP_A(2),
-	// branch B
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_3, 0x100000),
-	// common instruction
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
-	// depending on r1, branch:
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
-	// branch A
-	BPF_JMP_A(4),
-	// branch B
-	BPF_MOV64_IMM(BPF_REG_0, 0x13371337),
-	// verifier follows fall-through
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 0x100000, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	// fake-dead code; targeted from branch A to
-	// prevent dead code sanitization
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 1 },
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R2 pointer comparison prohibited",
-	.retval = 0,
-},
-{
-	"map access: mixing value pointer and scalar, 2",
-	.insns = {
-	// load map value pointer into r0 and r2
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_LD_MAP_FD(BPF_REG_ARG1, 0),
-	BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_FP),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG2, -16),
-	BPF_ST_MEM(BPF_DW, BPF_REG_FP, -16, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	// load some number from the map into r1
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	// depending on r1, branch:
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 3),
-	// branch A
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_3, 0x100000),
-	BPF_JMP_A(2),
-	// branch B
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_3, 0),
-	// common instruction
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
-	// depending on r1, branch:
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1),
-	// branch A
-	BPF_JMP_A(4),
-	// branch B
-	BPF_MOV64_IMM(BPF_REG_0, 0x13371337),
-	// verifier follows fall-through
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 0x100000, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	// fake-dead code; targeted from branch A to
-	// prevent dead code sanitization, rejected
-	// via branch B however
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 1 },
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R0 invalid mem access 'scalar'",
-	.retval = 0,
-},
-{
-	"sanitation: alu with different scalars 1",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_LD_MAP_FD(BPF_REG_ARG1, 0),
-	BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_FP),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG2, -16),
-	BPF_ST_MEM(BPF_DW, BPF_REG_FP, -16, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 3),
-	BPF_MOV64_IMM(BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_3, 0x100000),
-	BPF_JMP_A(2),
-	BPF_MOV64_IMM(BPF_REG_2, 42),
-	BPF_MOV64_IMM(BPF_REG_3, 0x100001),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 1 },
-	.result = ACCEPT,
-	.retval = 0x100000,
-},
-{
-	"sanitation: alu with different scalars 2",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_FP),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
-	BPF_ST_MEM(BPF_DW, BPF_REG_FP, -16, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_delete_elem),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_FP),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
-	BPF_EMIT_CALL(BPF_FUNC_map_delete_elem),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_8, BPF_REG_6),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_7),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_8),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 1 },
-	.result = ACCEPT,
-	.retval = -EINVAL * 2,
-},
-{
-	"sanitation: alu with different scalars 3",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, EINVAL),
-	BPF_ALU64_IMM(BPF_MUL, BPF_REG_0, -1),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
-	BPF_MOV64_IMM(BPF_REG_0, EINVAL),
-	BPF_ALU64_IMM(BPF_MUL, BPF_REG_0, -1),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_8, BPF_REG_6),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_7),
-	BPF_MOV64_REG(BPF_REG_0, BPF_REG_8),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.retval = -EINVAL * 2,
-},
-{
-	"map access: value_ptr += known scalar, upper oob arith, test 1",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_IMM(BPF_REG_1, 48),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R0 pointer arithmetic of map value goes out of range",
-	.retval = 1,
-},
-{
-	"map access: value_ptr += known scalar, upper oob arith, test 2",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_IMM(BPF_REG_1, 49),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R0 pointer arithmetic of map value goes out of range",
-	.retval = 1,
-},
-{
-	"map access: value_ptr += known scalar, upper oob arith, test 3",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_MOV64_IMM(BPF_REG_1, 47),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"map access: value_ptr -= known scalar, lower oob arith, test 1",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
-	BPF_MOV64_IMM(BPF_REG_1, 47),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_MOV64_IMM(BPF_REG_1, 48),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = REJECT,
-	.errstr = "R0 min value is outside of the allowed memory range",
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R0 pointer arithmetic of map value goes out of range",
-},
-{
-	"map access: value_ptr -= known scalar, lower oob arith, test 2",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-	BPF_MOV64_IMM(BPF_REG_1, 47),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_MOV64_IMM(BPF_REG_1, 48),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
-	BPF_MOV64_IMM(BPF_REG_1, 1),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R0 pointer arithmetic of map value goes out of range",
-	.retval = 1,
-},
-{
-	"map access: value_ptr -= known scalar, lower oob arith, test 3",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
-	BPF_MOV64_IMM(BPF_REG_1, 47),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_MOV64_IMM(BPF_REG_1, 47),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"map access: known scalar += value_ptr",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
-	BPF_MOV64_IMM(BPF_REG_1, 4),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"map access: value_ptr += known scalar, 1",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
-	BPF_MOV64_IMM(BPF_REG_1, 4),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"map access: value_ptr += known scalar, 2",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
-	BPF_MOV64_IMM(BPF_REG_1, 49),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = REJECT,
-	.errstr = "invalid access to map value",
-},
-{
-	"map access: value_ptr += known scalar, 3",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
-	BPF_MOV64_IMM(BPF_REG_1, -1),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = REJECT,
-	.errstr = "invalid access to map value",
-},
-{
-	"map access: value_ptr += known scalar, 4",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
-	BPF_MOV64_IMM(BPF_REG_1, 5),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_MOV64_IMM(BPF_REG_1, -2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_MOV64_IMM(BPF_REG_1, -1),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"map access: value_ptr += known scalar, 5",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
-	BPF_MOV64_IMM(BPF_REG_1, (6 + 1) * sizeof(int)),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = ACCEPT,
-	.retval = 0xabcdef12,
-},
-{
-	"map access: value_ptr += known scalar, 6",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
-	BPF_MOV64_IMM(BPF_REG_1, (3 + 1) * sizeof(int)),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_MOV64_IMM(BPF_REG_1, 3 * sizeof(int)),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = ACCEPT,
-	.retval = 0xabcdef12,
-},
-{
-	"map access: value_ptr += N, value_ptr -= N known scalar",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_MOV32_IMM(BPF_REG_1, 0x12345678),
-	BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 2),
-	BPF_MOV64_IMM(BPF_REG_1, 2),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = ACCEPT,
-	.retval = 0x12345678,
-},
-{
-	"map access: unknown scalar += value_ptr, 1",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"map access: unknown scalar += value_ptr, 2",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 31),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = ACCEPT,
-	.retval = 0xabcdef12,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"map access: unknown scalar += value_ptr, 3",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
-	BPF_MOV64_IMM(BPF_REG_1, -1),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_MOV64_IMM(BPF_REG_1, 1),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 31),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R0 pointer arithmetic of map value goes out of range",
-	.retval = 0xabcdef12,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"map access: unknown scalar += value_ptr, 4",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
-	BPF_MOV64_IMM(BPF_REG_1, 19),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 31),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = REJECT,
-	.errstr = "R1 max value is outside of the allowed memory range",
-	.errstr_unpriv = "R1 pointer arithmetic of map value goes out of range",
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"map access: value_ptr += unknown scalar, 1",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"map access: value_ptr += unknown scalar, 2",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 31),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = ACCEPT,
-	.retval = 0xabcdef12,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"map access: value_ptr += unknown scalar, 3",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 8),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 16),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_3, 1),
-	BPF_ALU64_IMM(BPF_OR, BPF_REG_3, 1),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_3, 4),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_3),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_0, 2),
-	BPF_JMP_IMM(BPF_JA, 0, 0, -3),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"map access: value_ptr += value_ptr",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_0),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = REJECT,
-	.errstr = "R0 pointer += pointer prohibited",
-},
-{
-	"map access: known scalar -= value_ptr",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
-	BPF_MOV64_IMM(BPF_REG_1, 4),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = REJECT,
-	.errstr = "R1 tried to subtract pointer from scalar",
-},
-{
-	"map access: value_ptr -= known scalar",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
-	BPF_MOV64_IMM(BPF_REG_1, 4),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = REJECT,
-	.errstr = "R0 min value is outside of the allowed memory range",
-},
-{
-	"map access: value_ptr -= known scalar, 2",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
-	BPF_MOV64_IMM(BPF_REG_1, 6),
-	BPF_MOV64_IMM(BPF_REG_2, 4),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_2),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = ACCEPT,
-	.retval = 1,
-},
-{
-	"map access: unknown scalar -= value_ptr",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = REJECT,
-	.errstr = "R1 tried to subtract pointer from scalar",
-},
-{
-	"map access: value_ptr -= unknown scalar",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = REJECT,
-	.errstr = "R0 min value is negative",
-},
-{
-	"map access: value_ptr -= unknown scalar, 2",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf),
-	BPF_ALU64_IMM(BPF_OR, BPF_REG_1, 0x7),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R0 pointer arithmetic of map value goes out of range",
-	.retval = 1,
-},
-{
-	"map access: value_ptr -= value_ptr",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_0),
-	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 3 },
-	.result = REJECT,
-	.errstr = "R0 invalid mem access 'scalar'",
-	.errstr_unpriv = "R0 pointer -= pointer prohibited",
-},
-{
-	"map access: trying to leak tainted dst reg",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
-	BPF_MOV32_IMM(BPF_REG_1, 0xFFFFFFFF),
-	BPF_MOV32_REG(BPF_REG_1, BPF_REG_1),
-	BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1),
-	BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_array_48b = { 4 },
-	.result = REJECT,
-	.errstr = "math between map_value pointer and 4294967295 is not allowed",
-},
-{
-	"32bit pkt_ptr -= scalar",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_7),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 40),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_8, 2),
-	BPF_ALU32_REG(BPF_MOV, BPF_REG_4, BPF_REG_7),
-	BPF_ALU32_REG(BPF_SUB, BPF_REG_6, BPF_REG_4),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"32bit scalar -= pkt_ptr",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
-		    offsetof(struct __sk_buff, data_end)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
-		    offsetof(struct __sk_buff, data)),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_7),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 40),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_8, 2),
-	BPF_ALU32_REG(BPF_MOV, BPF_REG_4, BPF_REG_6),
-	BPF_ALU32_REG(BPF_SUB, BPF_REG_4, BPF_REG_7),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.result = ACCEPT,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
diff --git a/tools/testing/selftests/bpf/verifier/var_off.c b/tools/testing/selftests/bpf/verifier/var_off.c
deleted file mode 100644
index d37f512fad16..000000000000
--- a/tools/testing/selftests/bpf/verifier/var_off.c
+++ /dev/null
@@ -1,343 +0,0 @@
-{
-	"variable-offset ctx access",
-	.insns = {
-	/* Get an unknown value */
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
-	/* Make it small and 4-byte aligned */
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4),
-	/* add it to skb.  We now have either &skb->len or
-	 * &skb->pkt_type, but we don't know which
-	 */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2),
-	/* dereference it */
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "variable ctx access var_off=(0x0; 0x4)",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_LWT_IN,
-},
-{
-	"variable-offset stack read, priv vs unpriv",
-	.insns = {
-	/* Fill the top 8 bytes of the stack */
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	/* Get an unknown value */
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
-	/* Make it small and 4-byte aligned */
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 8),
-	/* add it to fp.  We now have either fp-4 or fp-8, but
-	 * we don't know which
-	 */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10),
-	/* dereference it for a stack read */
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.result_unpriv = REJECT,
-	.errstr_unpriv = "R2 variable stack access prohibited for !root",
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"variable-offset stack read, uninitialized",
-	.insns = {
-	/* Get an unknown value */
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
-	/* Make it small and 4-byte aligned */
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 8),
-	/* add it to fp.  We now have either fp-4 or fp-8, but
-	 * we don't know which
-	 */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10),
-	/* dereference it for a stack read */
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "invalid variable-offset read from stack R2",
-	.prog_type = BPF_PROG_TYPE_LWT_IN,
-},
-{
-	"variable-offset stack write, priv vs unpriv",
-	.insns = {
-	/* Get an unknown value */
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
-	/* Make it small and 8-byte aligned */
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 8),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 16),
-	/* Add it to fp.  We now have either fp-8 or fp-16, but
-	 * we don't know which
-	 */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10),
-	/* Dereference it for a stack write */
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	/* Now read from the address we just wrote. This shows
-	 * that, after a variable-offset write, a priviledged
-	 * program can read the slots that were in the range of
-	 * that write (even if the verifier doesn't actually know
-	 * if the slot being read was really written to or not.
-	 */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_2, 0),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	/* Variable stack access is rejected for unprivileged.
-	 */
-	.errstr_unpriv = "R2 variable stack access prohibited for !root",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-},
-{
-	"variable-offset stack write clobbers spilled regs",
-	.insns = {
-	/* Dummy instruction; needed because we need to patch the next one
-	 * and we can't patch the first instruction.
-	 */
-	BPF_MOV64_IMM(BPF_REG_6, 0),
-	/* Make R0 a map ptr */
-	BPF_LD_MAP_FD(BPF_REG_0, 0),
-	/* Get an unknown value */
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
-	/* Make it small and 8-byte aligned */
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 8),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 16),
-	/* Add it to fp. We now have either fp-8 or fp-16, but
-	 * we don't know which.
-	 */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10),
-	/* Spill R0(map ptr) into stack */
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
-	/* Dereference the unknown value for a stack write */
-	BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
-	/* Fill the register back into R2 */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -8),
-	/* Try to dereference R2 for a memory load */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 8),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 1 },
-	/* The unprivileged case is not too interesting; variable
-	 * stack access is rejected.
-	 */
-	.errstr_unpriv = "R2 variable stack access prohibited for !root",
-	.result_unpriv = REJECT,
-	/* In the priviledged case, dereferencing a spilled-and-then-filled
-	 * register is rejected because the previous variable offset stack
-	 * write might have overwritten the spilled pointer (i.e. we lose track
-	 * of the spilled register when we analyze the write).
-	 */
-	.errstr = "R2 invalid mem access 'scalar'",
-	.result = REJECT,
-},
-{
-	"indirect variable-offset stack access, unbounded",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 6),
-	BPF_MOV64_IMM(BPF_REG_3, 28),
-	/* Fill the top 16 bytes of the stack. */
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	/* Get an unknown value. */
-	BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_1, offsetof(struct bpf_sock_ops,
-							   bytes_received)),
-	/* Check the lower bound but don't check the upper one. */
-	BPF_JMP_IMM(BPF_JSLT, BPF_REG_4, 0, 4),
-	/* Point the lower bound to initialized stack. Offset is now in range
-	 * from fp-16 to fp+0x7fffffffffffffef, i.e. max value is unbounded.
-	 */
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_4, 16),
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_10),
-	BPF_MOV64_IMM(BPF_REG_5, 8),
-	/* Dereference it indirectly. */
-	BPF_EMIT_CALL(BPF_FUNC_getsockopt),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "invalid unbounded variable-offset indirect access to stack R4",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_SOCK_OPS,
-},
-{
-	"indirect variable-offset stack access, max out of bound",
-	.insns = {
-	/* Fill the top 8 bytes of the stack */
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	/* Get an unknown value */
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
-	/* Make it small and 4-byte aligned */
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 8),
-	/* add it to fp.  We now have either fp-4 or fp-8, but
-	 * we don't know which
-	 */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10),
-	/* dereference it indirectly */
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 5 },
-	.errstr = "invalid variable-offset indirect access to stack R2",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_LWT_IN,
-},
-{
-	"indirect variable-offset stack access, min out of bound",
-	.insns = {
-	/* Fill the top 8 bytes of the stack */
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	/* Get an unknown value */
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
-	/* Make it small and 4-byte aligned */
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 516),
-	/* add it to fp.  We now have either fp-516 or fp-512, but
-	 * we don't know which
-	 */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10),
-	/* dereference it indirectly */
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 5 },
-	.errstr = "invalid variable-offset indirect access to stack R2",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_LWT_IN,
-},
-{
-	"indirect variable-offset stack access, max_off+size > max_initialized",
-	.insns = {
-	/* Fill only the second from top 8 bytes of the stack. */
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0),
-	/* Get an unknown value. */
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
-	/* Make it small and 4-byte aligned. */
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 16),
-	/* Add it to fp.  We now have either fp-12 or fp-16, but we don't know
-	 * which. fp-12 size 8 is partially uninitialized stack.
-	 */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10),
-	/* Dereference it indirectly. */
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 5 },
-	.errstr = "invalid indirect read from stack R2 var_off",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_LWT_IN,
-},
-{
-	"indirect variable-offset stack access, min_off < min_initialized",
-	.insns = {
-	/* Fill only the top 8 bytes of the stack. */
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	/* Get an unknown value */
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
-	/* Make it small and 4-byte aligned. */
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 16),
-	/* Add it to fp.  We now have either fp-12 or fp-16, but we don't know
-	 * which. fp-16 size 8 is partially uninitialized stack.
-	 */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10),
-	/* Dereference it indirectly. */
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 5 },
-	.errstr = "invalid indirect read from stack R2 var_off",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_LWT_IN,
-},
-{
-	"indirect variable-offset stack access, priv vs unpriv",
-	.insns = {
-	/* Fill the top 16 bytes of the stack. */
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	/* Get an unknown value. */
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
-	/* Make it small and 4-byte aligned. */
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 16),
-	/* Add it to fp.  We now have either fp-12 or fp-16, we don't know
-	 * which, but either way it points to initialized stack.
-	 */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10),
-	/* Dereference it indirectly. */
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 6 },
-	.errstr_unpriv = "R2 variable stack access prohibited for !root",
-	.result_unpriv = REJECT,
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-},
-{
-	"indirect variable-offset stack access, uninitialized",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_2, 6),
-	BPF_MOV64_IMM(BPF_REG_3, 28),
-	/* Fill the top 16 bytes of the stack. */
-	BPF_ST_MEM(BPF_W, BPF_REG_10, -16, 0),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	/* Get an unknown value. */
-	BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, 0),
-	/* Make it small and 4-byte aligned. */
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_4, 4),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_4, 16),
-	/* Add it to fp.  We now have either fp-12 or fp-16, we don't know
-	 * which, but either way it points to initialized stack.
-	 */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_10),
-	BPF_MOV64_IMM(BPF_REG_5, 8),
-	/* Dereference it indirectly. */
-	BPF_EMIT_CALL(BPF_FUNC_getsockopt),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "invalid indirect read from stack R4 var_off",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_SOCK_OPS,
-},
-{
-	"indirect variable-offset stack access, ok",
-	.insns = {
-	/* Fill the top 16 bytes of the stack. */
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0),
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	/* Get an unknown value. */
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
-	/* Make it small and 4-byte aligned. */
-	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 16),
-	/* Add it to fp.  We now have either fp-12 or fp-16, we don't know
-	 * which, but either way it points to initialized stack.
-	 */
-	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10),
-	/* Dereference it indirectly. */
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 6 },
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_LWT_IN,
-},
diff --git a/tools/testing/selftests/bpf/verifier/xadd.c b/tools/testing/selftests/bpf/verifier/xadd.c
deleted file mode 100644
index b96ef3526815..000000000000
--- a/tools/testing/selftests/bpf/verifier/xadd.c
+++ /dev/null
@@ -1,97 +0,0 @@
-{
-	"xadd/w check unaligned stack",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
-	BPF_ATOMIC_OP(BPF_W, BPF_ADD, BPF_REG_10, BPF_REG_0, -7),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "misaligned stack access off",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"xadd/w check unaligned map",
-	.insns = {
-	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
-	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
-	BPF_LD_MAP_FD(BPF_REG_1, 0),
-	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
-	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_1, 1),
-	BPF_ATOMIC_OP(BPF_W, BPF_ADD, BPF_REG_0, BPF_REG_1, 3),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 3),
-	BPF_EXIT_INSN(),
-	},
-	.fixup_map_hash_8b = { 3 },
-	.result = REJECT,
-	.errstr = "misaligned value access off",
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-},
-{
-	"xadd/w check unaligned pkt",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 2),
-	BPF_MOV64_IMM(BPF_REG_0, 99),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 6),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
-	BPF_ST_MEM(BPF_W, BPF_REG_2, 3, 0),
-	BPF_ATOMIC_OP(BPF_W, BPF_ADD, BPF_REG_2, BPF_REG_0, 1),
-	BPF_ATOMIC_OP(BPF_W, BPF_ADD, BPF_REG_2, BPF_REG_0, 2),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 1),
-	BPF_EXIT_INSN(),
-	},
-	.result = REJECT,
-	.errstr = "BPF_ATOMIC stores into R2 pkt is not allowed",
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"xadd/w check whether src/dst got mangled, 1",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
-	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
-	BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_10, BPF_REG_0, -8),
-	BPF_ATOMIC_OP(BPF_DW, BPF_ADD, BPF_REG_10, BPF_REG_0, -8),
-	BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_0, 3),
-	BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_10, 2),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_0, 42),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.retval = 3,
-},
-{
-	"xadd/w check whether src/dst got mangled, 2",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
-	BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
-	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -8),
-	BPF_ATOMIC_OP(BPF_W, BPF_ADD, BPF_REG_10, BPF_REG_0, -8),
-	BPF_ATOMIC_OP(BPF_W, BPF_ADD, BPF_REG_10, BPF_REG_0, -8),
-	BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_0, 3),
-	BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_10, 2),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -8),
-	BPF_EXIT_INSN(),
-	BPF_MOV64_IMM(BPF_REG_0, 42),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
-	.retval = 3,
-},
diff --git a/tools/testing/selftests/bpf/verifier/xdp.c b/tools/testing/selftests/bpf/verifier/xdp.c
deleted file mode 100644
index 5ac390508139..000000000000
--- a/tools/testing/selftests/bpf/verifier/xdp.c
+++ /dev/null
@@ -1,14 +0,0 @@
-{
-	"XDP, using ifindex from netdev",
-	.insns = {
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, ingress_ifindex)),
-	BPF_JMP_IMM(BPF_JLT, BPF_REG_2, 1, 1),
-	BPF_MOV64_IMM(BPF_REG_0, 1),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.retval = 1,
-},
diff --git a/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c b/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c
deleted file mode 100644
index b4ec228eb95d..000000000000
--- a/tools/testing/selftests/bpf/verifier/xdp_direct_packet_access.c
+++ /dev/null
@@ -1,1468 +0,0 @@
-{
-	"XDP pkt read, pkt_end mangling, bad access 1",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R3 pointer arithmetic on pkt_end",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-},
-{
-	"XDP pkt read, pkt_end mangling, bad access 2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_ALU64_IMM(BPF_SUB, BPF_REG_3, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R3 pointer arithmetic on pkt_end",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-},
-{
-	"XDP pkt read, pkt_data' > pkt_end, corner case, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data' > pkt_end, bad access 1",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data' > pkt_end, bad access 2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data' > pkt_end, corner case +1, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data' > pkt_end, corner case -1, bad access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_end > pkt_data', good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_end > pkt_data', corner case -1, bad access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_end > pkt_data', bad access 2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_end > pkt_data', corner case, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_end > pkt_data', corner case +1, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data' < pkt_end, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data' < pkt_end, corner case -1, bad access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data' < pkt_end, bad access 2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data' < pkt_end, corner case, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data' < pkt_end, corner case +1, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_end < pkt_data', corner case, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_end < pkt_data', bad access 1",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_end < pkt_data', bad access 2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_end < pkt_data', corner case +1, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_end < pkt_data', corner case -1, bad access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data' >= pkt_end, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data' >= pkt_end, corner case -1, bad access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data' >= pkt_end, bad access 2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data' >= pkt_end, corner case, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data' >= pkt_end, corner case +1, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_end >= pkt_data', corner case, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_end >= pkt_data', bad access 1",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_end >= pkt_data', bad access 2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_end >= pkt_data', corner case +1, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_end >= pkt_data', corner case -1, bad access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data' <= pkt_end, corner case, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data' <= pkt_end, bad access 1",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data' <= pkt_end, bad access 2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data' <= pkt_end, corner case +1, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data' <= pkt_end, corner case -1, bad access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_end <= pkt_data', good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_end <= pkt_data', corner case -1, bad access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_end <= pkt_data', bad access 2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_end <= pkt_data', corner case, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_end <= pkt_data', corner case +1, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
-		    offsetof(struct xdp_md, data_end)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_meta' > pkt_data, corner case, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_meta' > pkt_data, bad access 1",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_meta' > pkt_data, bad access 2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_meta' > pkt_data, corner case +1, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_meta' > pkt_data, corner case -1, bad access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data > pkt_meta', good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data > pkt_meta', corner case -1, bad access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data > pkt_meta', bad access 2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data > pkt_meta', corner case, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data > pkt_meta', corner case +1, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_meta' < pkt_data, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_meta' < pkt_data, corner case -1, bad access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_meta' < pkt_data, bad access 2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_meta' < pkt_data, corner case, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_meta' < pkt_data, corner case +1, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data < pkt_meta', corner case, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data < pkt_meta', bad access 1",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data < pkt_meta', bad access 2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 0),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data < pkt_meta', corner case +1, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data < pkt_meta', corner case -1, bad access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_meta' >= pkt_data, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_meta' >= pkt_data, corner case -1, bad access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_meta' >= pkt_data, bad access 2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_meta' >= pkt_data, corner case, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_meta' >= pkt_data, corner case +1, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data >= pkt_meta', corner case, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data >= pkt_meta', bad access 1",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data >= pkt_meta', bad access 2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data >= pkt_meta', corner case +1, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data >= pkt_meta', corner case -1, bad access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_meta' <= pkt_data, corner case, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_meta' <= pkt_data, bad access 1",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_meta' <= pkt_data, bad access 2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_meta' <= pkt_data, corner case +1, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_meta' <= pkt_data, corner case -1, bad access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
-	BPF_JMP_IMM(BPF_JA, 0, 0, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data <= pkt_meta', good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data <= pkt_meta', corner case -1, bad access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data <= pkt_meta', bad access 2",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 0),
-	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.errstr = "R1 offset is outside of the packet",
-	.result = REJECT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data <= pkt_meta', corner case, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
-{
-	"XDP pkt read, pkt_data <= pkt_meta', corner case +1, good access",
-	.insns = {
-	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
-		    offsetof(struct xdp_md, data_meta)),
-	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
-	BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
-	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
-	BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
-	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
-	BPF_MOV64_IMM(BPF_REG_0, 0),
-	BPF_EXIT_INSN(),
-	},
-	.result = ACCEPT,
-	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-},
diff --git a/tools/testing/selftests/bpf/verify_sig_setup.sh b/tools/testing/selftests/bpf/verify_sig_setup.sh
index ba08922b4a27..09179fb551f0 100755
--- a/tools/testing/selftests/bpf/verify_sig_setup.sh
+++ b/tools/testing/selftests/bpf/verify_sig_setup.sh
@@ -32,7 +32,7 @@ usage()
 	exit 1
 }
 
-setup()
+genkey()
 {
 	local tmp_dir="$1"
 
@@ -45,9 +45,14 @@ setup()
 
 	openssl x509 -in ${tmp_dir}/signing_key.pem -out \
 		${tmp_dir}/signing_key.der -outform der
+}
 
-	key_id=$(cat ${tmp_dir}/signing_key.der | keyctl padd asymmetric ebpf_testing_key @s)
+setup()
+{
+	local tmp_dir="$1"
 
+	genkey "${tmp_dir}"
+	key_id=$(cat ${tmp_dir}/signing_key.der | keyctl padd asymmetric ebpf_testing_key @s)
 	keyring_id=$(keyctl newring ebpf_testing_keyring @s)
 	keyctl link $key_id $keyring_id
 }
@@ -60,6 +65,27 @@ cleanup() {
 	rm -rf ${tmp_dir}
 }
 
+fsverity_create_sign_file() {
+	local tmp_dir="$1"
+
+	data_file=${tmp_dir}/data-file
+	sig_file=${tmp_dir}/sig-file
+	dd if=/dev/urandom of=$data_file bs=1 count=12345 2> /dev/null
+	fsverity sign --key ${tmp_dir}/signing_key.pem $data_file $sig_file
+
+	# We do not want to enable fsverity on $data_file yet. Try whether
+	# the file system support fsverity on a different file.
+	touch ${tmp_dir}/tmp-file
+	fsverity enable ${tmp_dir}/tmp-file
+}
+
+fsverity_enable_file() {
+	local tmp_dir="$1"
+
+	data_file=${tmp_dir}/data-file
+	fsverity enable $data_file
+}
+
 catch()
 {
 	local exit_code="$1"
@@ -84,8 +110,14 @@ main()
 
 	if [[ "${action}" == "setup" ]]; then
 		setup "${tmp_dir}"
+	elif [[ "${action}" == "genkey" ]]; then
+		genkey "${tmp_dir}"
 	elif [[ "${action}" == "cleanup" ]]; then
 		cleanup "${tmp_dir}"
+	elif [[ "${action}" == "fsverity-create-sign" ]]; then
+		fsverity_create_sign_file "${tmp_dir}"
+	elif [[ "${action}" == "fsverity-enable" ]]; then
+		fsverity_enable_file "${tmp_dir}"
 	else
 		echo "Unknown action: ${action}"
 		exit 1
diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c
index f961b49b8ef4..e962f133250c 100644
--- a/tools/testing/selftests/bpf/veristat.c
+++ b/tools/testing/selftests/bpf/veristat.c
@@ -1,10 +1,11 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
 #define _GNU_SOURCE
 #include <argp.h>
+#include <libgen.h>
+#include <ctype.h>
 #include <string.h>
 #include <stdlib.h>
-#include <linux/compiler.h>
 #include <sched.h>
 #include <pthread.h>
 #include <dirent.h>
@@ -15,9 +16,26 @@
 #include <sys/sysinfo.h>
 #include <sys/stat.h>
 #include <bpf/libbpf.h>
+#include <bpf/btf.h>
+#include <bpf/bpf.h>
 #include <libelf.h>
 #include <gelf.h>
 #include <float.h>
+#include <math.h>
+#include <limits.h>
+#include <assert.h>
+
+#ifndef ARRAY_SIZE
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+#endif
+
+#ifndef max
+#define max(a, b) ((a) > (b) ? (a) : (b))
+#endif
+
+#ifndef min
+#define min(a, b) ((a) < (b) ? (a) : (b))
+#endif
 
 enum stat_id {
 	VERDICT,
@@ -27,6 +45,12 @@ enum stat_id {
 	PEAK_STATES,
 	MAX_STATES_PER_INSN,
 	MARK_READ_MAX_LEN,
+	SIZE,
+	JITED_SIZE,
+	STACK,
+	PROG_TYPE,
+	ATTACH_TYPE,
+	MEMORY_PEAK,
 
 	FILE_NAME,
 	PROG_NAME,
@@ -95,6 +119,7 @@ struct stat_specs {
 	enum stat_id ids[ALL_STATS_CNT];
 	enum stat_variant variants[ALL_STATS_CNT];
 	bool asc[ALL_STATS_CNT];
+	bool abs[ALL_STATS_CNT];
 	int lens[ALL_STATS_CNT * 3]; /* 3x for comparison mode */
 };
 
@@ -129,22 +154,61 @@ struct filter {
 	int stat_id;
 	enum stat_variant stat_var;
 	long value;
+	bool abs;
+};
+
+struct rvalue {
+	enum { INTEGRAL, ENUMERATOR } type;
+	union {
+		long long ivalue;
+		char *svalue;
+	};
+};
+
+struct field_access {
+	enum { FIELD_NAME, ARRAY_INDEX } type;
+	union {
+		char *name;
+		struct rvalue index;
+	};
+};
+
+struct var_preset {
+	struct field_access *atoms;
+	int atom_count;
+	char *full_name;
+	struct rvalue value;
+	bool applied;
+};
+
+enum dump_mode {
+	DUMP_NONE = 0,
+	DUMP_XLATED = 1,
+	DUMP_JITED = 2,
 };
 
 static struct env {
 	char **filenames;
 	int filename_cnt;
 	bool verbose;
+	bool debug;
 	bool quiet;
-	int log_level;
+	bool force_checkpoints;
+	bool force_reg_invariants;
 	enum resfmt out_fmt;
+	bool show_version;
 	bool comparison_mode;
 	bool replay_mode;
+	int top_n;
+
+	int log_level;
+	int log_size;
+	bool log_fixed;
 
 	struct verif_stats *prog_stats;
 	int prog_stat_cnt;
 
-	/* baseline_stats is allocated and used only in comparsion mode */
+	/* baseline_stats is allocated and used only in comparison mode */
 	struct verif_stats *baseline_stats;
 	int baseline_stat_cnt;
 
@@ -163,29 +227,69 @@ static struct env {
 	int files_skipped;
 	int progs_processed;
 	int progs_skipped;
+	int top_src_lines;
+	struct var_preset *presets;
+	int npresets;
+	char orig_cgroup[PATH_MAX];
+	char stat_cgroup[PATH_MAX];
+	int memory_peak_fd;
+	__u32 dump_mode;
 } env;
 
 static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args)
 {
 	if (!env.verbose)
 		return 0;
-	if (level == LIBBPF_DEBUG /* && !env.verbose */)
+	if (level == LIBBPF_DEBUG  && !env.debug)
 		return 0;
 	return vfprintf(stderr, format, args);
 }
 
-const char *argp_program_version = "veristat";
+#define log_errno(fmt, ...) log_errno_aux(__FILE__, __LINE__, fmt, ##__VA_ARGS__)
+
+__attribute__((format(printf, 3, 4)))
+static int log_errno_aux(const char *file, int line, const char *fmt, ...)
+{
+	int err = -errno;
+	va_list ap;
+
+	va_start(ap, fmt);
+	fprintf(stderr, "%s:%d: ", file, line);
+	vfprintf(stderr, fmt, ap);
+	fprintf(stderr, " failed with error '%s'.\n", strerror(errno));
+	va_end(ap);
+	return err;
+}
+
+#ifndef VERISTAT_VERSION
+#define VERISTAT_VERSION "<kernel>"
+#endif
+
+const char *argp_program_version = "veristat v" VERISTAT_VERSION;
 const char *argp_program_bug_address = "<bpf@vger.kernel.org>";
 const char argp_program_doc[] =
 "veristat    BPF verifier stats collection and comparison tool.\n"
 "\n"
 "USAGE: veristat <obj-file> [<obj-file>...]\n"
-"   OR: veristat -C <baseline.csv> <comparison.csv>\n";
+"   OR: veristat -C <baseline.csv> <comparison.csv>\n"
+"   OR: veristat -R <results.csv>\n"
+"   OR: veristat -vl2 <to_analyze.bpf.o>\n";
+
+enum {
+	OPT_LOG_FIXED = 1000,
+	OPT_LOG_SIZE = 1001,
+	OPT_DUMP = 1002,
+};
 
 static const struct argp_option opts[] = {
 	{ NULL, 'h', NULL, OPTION_HIDDEN, "Show the full help" },
+	{ "version", 'V', NULL, 0, "Print version" },
 	{ "verbose", 'v', NULL, 0, "Verbose mode" },
-	{ "log-level", 'l', "LEVEL", 0, "Verifier log level (default 0 for normal mode, 1 for verbose mode)" },
+	{ "debug", 'd', NULL, 0, "Debug mode (turns on libbpf debug logging)" },
+	{ "log-level", 'l', "LEVEL", 0, "Verifier log level (default 0 for normal mode, 1 for verbose mode, 2 for full verification log)" },
+	{ "log-fixed", OPT_LOG_FIXED, NULL, 0, "Disable verifier log rotation" },
+	{ "log-size", OPT_LOG_SIZE, "BYTES", 0, "Customize verifier log size (default to 16MB)" },
+	{ "top-n", 'n', "N", 0, "Emit only up to first N results." },
 	{ "quiet", 'q', NULL, 0, "Quiet mode" },
 	{ "emit", 'e', "SPEC", 0, "Specify stats to be emitted" },
 	{ "sort", 's', "SPEC", 0, "Specify sort order" },
@@ -193,25 +297,42 @@ static const struct argp_option opts[] = {
 	{ "compare", 'C', NULL, 0, "Comparison mode" },
 	{ "replay", 'R', NULL, 0, "Replay mode" },
 	{ "filter", 'f', "FILTER", 0, "Filter expressions (or @filename for file with expressions)." },
+	{ "test-states", 't', NULL, 0,
+	  "Force frequent BPF verifier state checkpointing (set BPF_F_TEST_STATE_FREQ program flag)" },
+	{ "test-reg-invariants", 'r', NULL, 0,
+	  "Force BPF verifier failure on register invariant violation (BPF_F_TEST_REG_INVARIANTS program flag)" },
+	{ "top-src-lines", 'S', "N", 0, "Emit N most frequent source code lines" },
+	{ "set-global-vars", 'G', "GLOBAL", 0, "Set global variables provided in the expression, for example \"var1 = 1\"" },
+	{ "dump", OPT_DUMP, "DUMP_MODE", OPTION_ARG_OPTIONAL, "Print BPF program dump (xlated, jited)" },
 	{},
 };
 
 static int parse_stats(const char *stats_str, struct stat_specs *specs);
 static int append_filter(struct filter **filters, int *cnt, const char *str);
 static int append_filter_file(const char *path);
+static int append_var_preset(struct var_preset **presets, int *cnt, const char *expr);
+static int append_var_preset_file(const char *filename);
+static int append_file(const char *path);
+static int append_file_from_file(const char *path);
 
 static error_t parse_arg(int key, char *arg, struct argp_state *state)
 {
-	void *tmp;
 	int err;
 
 	switch (key) {
 	case 'h':
 		argp_state_help(state, stderr, ARGP_HELP_STD_HELP);
 		break;
+	case 'V':
+		env.show_version = true;
+		break;
 	case 'v':
 		env.verbose = true;
 		break;
+	case 'd':
+		env.debug = true;
+		env.verbose = true;
+		break;
 	case 'q':
 		env.quiet = true;
 		break;
@@ -243,6 +364,31 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 			argp_usage(state);
 		}
 		break;
+	case OPT_LOG_FIXED:
+		env.log_fixed = true;
+		break;
+	case OPT_LOG_SIZE:
+		errno = 0;
+		env.log_size = strtol(arg, NULL, 10);
+		if (errno) {
+			fprintf(stderr, "invalid log size: %s\n", arg);
+			argp_usage(state);
+		}
+		break;
+	case 't':
+		env.force_checkpoints = true;
+		break;
+	case 'r':
+		env.force_reg_invariants = true;
+		break;
+	case 'n':
+		errno = 0;
+		env.top_n = strtol(arg, NULL, 10);
+		if (errno) {
+			fprintf(stderr, "invalid top N specifier: %s\n", arg);
+			argp_usage(state);
+		}
+		break;
 	case 'C':
 		env.comparison_mode = true;
 		break;
@@ -261,15 +407,44 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 			return err;
 		}
 		break;
+	case 'S':
+		errno = 0;
+		env.top_src_lines = strtol(arg, NULL, 10);
+		if (errno) {
+			fprintf(stderr, "invalid top lines N specifier: %s\n", arg);
+			argp_usage(state);
+		}
+		break;
+	case 'G': {
+		if (arg[0] == '@')
+			err = append_var_preset_file(arg + 1);
+		else
+			err = append_var_preset(&env.presets, &env.npresets, arg);
+		if (err) {
+			fprintf(stderr, "Failed to parse global variable presets: %s\n", arg);
+			return err;
+		}
+		break;
+	}
 	case ARGP_KEY_ARG:
-		tmp = realloc(env.filenames, (env.filename_cnt + 1) * sizeof(*env.filenames));
-		if (!tmp)
-			return -ENOMEM;
-		env.filenames = tmp;
-		env.filenames[env.filename_cnt] = strdup(arg);
-		if (!env.filenames[env.filename_cnt])
-			return -ENOMEM;
-		env.filename_cnt++;
+		if (arg[0] == '@')
+			err = append_file_from_file(arg + 1);
+		else
+			err = append_file(arg);
+		if (err) {
+			fprintf(stderr, "Failed to collect BPF object files: %d\n", err);
+			return err;
+		}
+		break;
+	case OPT_DUMP:
+		if (!arg || strcasecmp(arg, "xlated") == 0) {
+			env.dump_mode |= DUMP_XLATED;
+		} else if (strcasecmp(arg, "jited") == 0) {
+			env.dump_mode |= DUMP_JITED;
+		} else {
+			fprintf(stderr, "Unrecognized dump mode '%s'\n", arg);
+			return -EINVAL;
+		}
 		break;
 	default:
 		return ARGP_ERR_UNKNOWN;
@@ -408,7 +583,8 @@ static struct {
 	{ OP_EQ, "=" },
 };
 
-static bool parse_stat_id_var(const char *name, size_t len, int *id, enum stat_variant *var);
+static bool parse_stat_id_var(const char *name, size_t len, int *id,
+			      enum stat_variant *var, bool *is_abs);
 
 static int append_filter(struct filter **filters, int *cnt, const char *str)
 {
@@ -441,13 +617,14 @@ static int append_filter(struct filter **filters, int *cnt, const char *str)
 		long val;
 		const char *end = str;
 		const char *op_str;
+		bool is_abs;
 
 		op_str = operators[i].op_str;
 		p = strstr(str, op_str);
 		if (!p)
 			continue;
 
-		if (!parse_stat_id_var(str, p - str, &id, &var)) {
+		if (!parse_stat_id_var(str, p - str, &id, &var, &is_abs)) {
 			fprintf(stderr, "Unrecognized stat name in '%s'!\n", str);
 			return -EINVAL;
 		}
@@ -486,6 +663,7 @@ static int append_filter(struct filter **filters, int *cnt, const char *str)
 		f->stat_id = id;
 		f->stat_var = var;
 		f->op = operators[i].op_kind;
+		f->abs = true;
 		f->value = val;
 
 		*cnt += 1;
@@ -537,7 +715,7 @@ static int append_filter_file(const char *path)
 	f = fopen(path, "r");
 	if (!f) {
 		err = -errno;
-		fprintf(stderr, "Failed to open filters in '%s': %d\n", path, err);
+		fprintf(stderr, "Failed to open filters in '%s': %s\n", path, strerror(-err));
 		return err;
 	}
 
@@ -560,19 +738,64 @@ cleanup:
 }
 
 static const struct stat_specs default_output_spec = {
-	.spec_cnt = 7,
+	.spec_cnt = 8,
 	.ids = {
 		FILE_NAME, PROG_NAME, VERDICT, DURATION,
-		TOTAL_INSNS, TOTAL_STATES, PEAK_STATES,
+		TOTAL_INSNS, TOTAL_STATES, SIZE, JITED_SIZE
 	},
 };
 
+static int append_file(const char *path)
+{
+	void *tmp;
+
+	tmp = realloc(env.filenames, (env.filename_cnt + 1) * sizeof(*env.filenames));
+	if (!tmp)
+		return -ENOMEM;
+	env.filenames = tmp;
+	env.filenames[env.filename_cnt] = strdup(path);
+	if (!env.filenames[env.filename_cnt])
+		return -ENOMEM;
+	env.filename_cnt++;
+	return 0;
+}
+
+static int append_file_from_file(const char *path)
+{
+	char buf[1024];
+	int err = 0;
+	FILE *f;
+
+	f = fopen(path, "r");
+	if (!f) {
+		err = -errno;
+		fprintf(stderr, "Failed to open object files list in '%s': %s\n",
+			path, strerror(errno));
+		return err;
+	}
+
+	while (fscanf(f, " %1023[^\n]\n", buf) == 1) {
+		/* lines starting with # are comments, skip them */
+		if (buf[0] == '\0' || buf[0] == '#')
+			continue;
+		err = append_file(buf);
+		if (err)
+			goto cleanup;
+	}
+
+cleanup:
+	fclose(f);
+	return err;
+}
+
 static const struct stat_specs default_csv_output_spec = {
-	.spec_cnt = 9,
+	.spec_cnt = 15,
 	.ids = {
 		FILE_NAME, PROG_NAME, VERDICT, DURATION,
 		TOTAL_INSNS, TOTAL_STATES, PEAK_STATES,
 		MAX_STATES_PER_INSN, MARK_READ_MAX_LEN,
+		SIZE, JITED_SIZE, PROG_TYPE, ATTACH_TYPE,
+		STACK, MEMORY_PEAK,
 	},
 };
 
@@ -608,9 +831,16 @@ static struct stat_def {
 	[PEAK_STATES] = { "Peak states", {"peak_states"}, },
 	[MAX_STATES_PER_INSN] = { "Max states per insn", {"max_states_per_insn"}, },
 	[MARK_READ_MAX_LEN] = { "Max mark read length", {"max_mark_read_len", "mark_read"}, },
+	[SIZE] = { "Program size", {"prog_size"}, },
+	[JITED_SIZE] = { "Jited size", {"prog_size_jited"}, },
+	[STACK] = {"Stack depth", {"stack_depth", "stack"}, },
+	[PROG_TYPE] = { "Program type", {"prog_type"}, },
+	[ATTACH_TYPE] = { "Attach type", {"attach_type", }, },
+	[MEMORY_PEAK] = { "Peak memory (MiB)", {"mem_peak", }, },
 };
 
-static bool parse_stat_id_var(const char *name, size_t len, int *id, enum stat_variant *var)
+static bool parse_stat_id_var(const char *name, size_t len, int *id,
+			      enum stat_variant *var, bool *is_abs)
 {
 	static const char *var_sfxs[] = {
 		[VARIANT_A] = "_a",
@@ -620,6 +850,14 @@ static bool parse_stat_id_var(const char *name, size_t len, int *id, enum stat_v
 	};
 	int i, j, k;
 
+	/* |<stat>| means we take absolute value of given stat */
+	*is_abs = false;
+	if (len > 2 && name[0] == '|' && name[len - 1] == '|') {
+		*is_abs = true;
+		name += 1;
+		len -= 2;
+	}
+
 	for (i = 0; i < ARRAY_SIZE(stat_defs); i++) {
 		struct stat_def *def = &stat_defs[i];
 		size_t alias_len, sfx_len;
@@ -672,10 +910,22 @@ static bool is_desc_sym(char c)
 	return c == 'v' || c == 'V' || c == '.' || c == '!' || c == '_';
 }
 
+static char *rtrim(char *str)
+{
+	int i;
+
+	for (i = strlen(str) - 1; i > 0; --i) {
+		if (!isspace(str[i]))
+			break;
+		str[i] = '\0';
+	}
+	return str;
+}
+
 static int parse_stat(const char *stat_name, struct stat_specs *specs)
 {
 	int id;
-	bool has_order = false, is_asc = false;
+	bool has_order = false, is_asc = false, is_abs = false;
 	size_t len = strlen(stat_name);
 	enum stat_variant var;
 
@@ -690,7 +940,7 @@ static int parse_stat(const char *stat_name, struct stat_specs *specs)
 		len -= 1;
 	}
 
-	if (!parse_stat_id_var(stat_name, len, &id, &var)) {
+	if (!parse_stat_id_var(stat_name, len, &id, &var, &is_abs)) {
 		fprintf(stderr, "Unrecognized stat name '%s'\n", stat_name);
 		return -ESRCH;
 	}
@@ -698,6 +948,7 @@ static int parse_stat(const char *stat_name, struct stat_specs *specs)
 	specs->ids[specs->spec_cnt] = id;
 	specs->variants[specs->spec_cnt] = var;
 	specs->asc[specs->spec_cnt] = has_order ? is_asc : stat_defs[id].asc_by_default;
+	specs->abs[specs->spec_cnt] = is_abs;
 	specs->spec_cnt++;
 
 	return 0;
@@ -706,18 +957,21 @@ static int parse_stat(const char *stat_name, struct stat_specs *specs)
 static int parse_stats(const char *stats_str, struct stat_specs *specs)
 {
 	char *input, *state = NULL, *next;
-	int err;
+	int err, cnt = 0;
 
 	input = strdup(stats_str);
 	if (!input)
 		return -ENOMEM;
 
-	while ((next = strtok_r(state ? NULL : input, ",", &state))) {
+	while ((next = strtok_r(cnt++ ? NULL : input, ",", &state))) {
 		err = parse_stat(next, specs);
-		if (err)
+		if (err) {
+			free(input);
 			return err;
+		}
 	}
 
+	free(input);
 	return 0;
 }
 
@@ -742,7 +996,8 @@ static char verif_log_buf[64 * 1024];
 static int parse_verif_log(char * const buf, size_t buf_sz, struct verif_stats *s)
 {
 	const char *cur;
-	int pos, lines;
+	int pos, lines, sub_stack, cnt = 0;
+	char *state = NULL, *token, stack[512];
 
 	buf[buf_sz - 1] = '\0';
 
@@ -760,19 +1015,228 @@ static int parse_verif_log(char * const buf, size_t buf_sz, struct verif_stats *
 
 		if (1 == sscanf(cur, "verification time %ld usec\n", &s->stats[DURATION]))
 			continue;
-		if (6 == sscanf(cur, "processed %ld insns (limit %*d) max_states_per_insn %ld total_states %ld peak_states %ld mark_read %ld",
+		if (5 == sscanf(cur, "processed %ld insns (limit %*d) max_states_per_insn %ld total_states %ld peak_states %ld mark_read %ld",
 				&s->stats[TOTAL_INSNS],
 				&s->stats[MAX_STATES_PER_INSN],
 				&s->stats[TOTAL_STATES],
 				&s->stats[PEAK_STATES],
 				&s->stats[MARK_READ_MAX_LEN]))
 			continue;
-	}
 
+		if (1 == sscanf(cur, "stack depth %511s", stack))
+			continue;
+	}
+	while ((token = strtok_r(cnt++ ? NULL : stack, "+", &state))) {
+		if (sscanf(token, "%d", &sub_stack) == 0)
+			break;
+		s->stats[STACK] += sub_stack;
+	}
 	return 0;
 }
 
-static void fixup_obj(struct bpf_object *obj)
+struct line_cnt {
+	char *line;
+	int cnt;
+};
+
+static int str_cmp(const void *a, const void *b)
+{
+	const char **str1 = (const char **)a;
+	const char **str2 = (const char **)b;
+
+	return strcmp(*str1, *str2);
+}
+
+static int line_cnt_cmp(const void *a, const void *b)
+{
+	const struct line_cnt *a_cnt = (const struct line_cnt *)a;
+	const struct line_cnt *b_cnt = (const struct line_cnt *)b;
+
+	if (a_cnt->cnt != b_cnt->cnt)
+		return a_cnt->cnt > b_cnt->cnt ? -1 : 1;
+	return strcmp(a_cnt->line, b_cnt->line);
+}
+
+static int print_top_src_lines(char * const buf, size_t buf_sz, const char *prog_name)
+{
+	int lines_cap = 0;
+	int lines_size = 0;
+	char **lines = NULL;
+	char *line = NULL;
+	char *state;
+	struct line_cnt *freq = NULL;
+	struct line_cnt *cur;
+	int unique_lines;
+	int err = 0;
+	int i;
+
+	while ((line = strtok_r(line ? NULL : buf, "\n", &state))) {
+		if (strncmp(line, "; ", 2) != 0)
+			continue;
+		line += 2;
+
+		if (lines_size == lines_cap) {
+			char **tmp;
+
+			lines_cap = max(16, lines_cap * 2);
+			tmp = realloc(lines, lines_cap * sizeof(*tmp));
+			if (!tmp) {
+				err = -ENOMEM;
+				goto cleanup;
+			}
+			lines = tmp;
+		}
+		lines[lines_size] = line;
+		lines_size++;
+	}
+
+	if (lines_size == 0)
+		goto cleanup;
+
+	qsort(lines, lines_size, sizeof(*lines), str_cmp);
+
+	freq = calloc(lines_size, sizeof(*freq));
+	if (!freq) {
+		err = -ENOMEM;
+		goto cleanup;
+	}
+
+	cur = freq;
+	cur->line = lines[0];
+	cur->cnt = 1;
+	for (i = 1; i < lines_size; ++i) {
+		if (strcmp(lines[i], cur->line) != 0) {
+			cur++;
+			cur->line = lines[i];
+			cur->cnt = 0;
+		}
+		cur->cnt++;
+	}
+	unique_lines = cur - freq + 1;
+
+	qsort(freq, unique_lines, sizeof(struct line_cnt), line_cnt_cmp);
+
+	printf("Top source lines (%s):\n", prog_name);
+	for (i = 0; i < min(unique_lines, env.top_src_lines); ++i) {
+		const char *src_code = freq[i].line;
+		const char *src_line = NULL;
+		char *split = strrchr(freq[i].line, '@');
+
+		if (split) {
+			src_line = split + 1;
+
+			while (*src_line && isspace(*src_line))
+				src_line++;
+
+			while (split > src_code && isspace(*split))
+				split--;
+			*split = '\0';
+		}
+
+		if (src_line)
+			printf("%5d: (%s)\t%s\n", freq[i].cnt, src_line, src_code);
+		else
+			printf("%5d: %s\n", freq[i].cnt, src_code);
+	}
+	printf("\n");
+
+cleanup:
+	free(freq);
+	free(lines);
+	return err;
+}
+
+static int guess_prog_type_by_ctx_name(const char *ctx_name,
+				       enum bpf_prog_type *prog_type,
+				       enum bpf_attach_type *attach_type)
+{
+	/* We need to guess program type based on its declared context type.
+	 * This guess can't be perfect as many different program types might
+	 * share the same context type.  So we can only hope to reasonably
+	 * well guess this and get lucky.
+	 *
+	 * Just in case, we support both UAPI-side type names and
+	 * kernel-internal names.
+	 */
+	static struct {
+		const char *uapi_name;
+		const char *kern_name;
+		enum bpf_prog_type prog_type;
+		enum bpf_attach_type attach_type;
+	} ctx_map[] = {
+		/* __sk_buff is most ambiguous, we assume TC program */
+		{ "__sk_buff", "sk_buff", BPF_PROG_TYPE_SCHED_CLS },
+		{ "bpf_sock", "sock", BPF_PROG_TYPE_CGROUP_SOCK, BPF_CGROUP_INET4_POST_BIND },
+		{ "bpf_sock_addr", "bpf_sock_addr_kern",  BPF_PROG_TYPE_CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_BIND },
+		{ "bpf_sock_ops", "bpf_sock_ops_kern", BPF_PROG_TYPE_SOCK_OPS, BPF_CGROUP_SOCK_OPS },
+		{ "sk_msg_md", "sk_msg", BPF_PROG_TYPE_SK_MSG, BPF_SK_MSG_VERDICT },
+		{ "bpf_cgroup_dev_ctx", "bpf_cgroup_dev_ctx", BPF_PROG_TYPE_CGROUP_DEVICE, BPF_CGROUP_DEVICE },
+		{ "bpf_sysctl", "bpf_sysctl_kern", BPF_PROG_TYPE_CGROUP_SYSCTL, BPF_CGROUP_SYSCTL },
+		{ "bpf_sockopt", "bpf_sockopt_kern", BPF_PROG_TYPE_CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT },
+		{ "sk_reuseport_md", "sk_reuseport_kern", BPF_PROG_TYPE_SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE },
+		{ "bpf_sk_lookup", "bpf_sk_lookup_kern", BPF_PROG_TYPE_SK_LOOKUP, BPF_SK_LOOKUP },
+		{ "xdp_md", "xdp_buff", BPF_PROG_TYPE_XDP, BPF_XDP },
+		/* tracing types with no expected attach type */
+		{ "bpf_user_pt_regs_t", "pt_regs", BPF_PROG_TYPE_KPROBE },
+		{ "bpf_perf_event_data", "bpf_perf_event_data_kern", BPF_PROG_TYPE_PERF_EVENT },
+		/* raw_tp programs use u64[] from kernel side, we don't want
+		 * to match on that, probably; so NULL for kern-side type
+		 */
+		{ "bpf_raw_tracepoint_args", NULL, BPF_PROG_TYPE_RAW_TRACEPOINT },
+	};
+	int i;
+
+	if (!ctx_name)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(ctx_map); i++) {
+		if (strcmp(ctx_map[i].uapi_name, ctx_name) == 0 ||
+		    (ctx_map[i].kern_name && strcmp(ctx_map[i].kern_name, ctx_name) == 0)) {
+			*prog_type = ctx_map[i].prog_type;
+			*attach_type = ctx_map[i].attach_type;
+			return 0;
+		}
+	}
+
+	return -ESRCH;
+}
+
+/* Make sure only target program is referenced from struct_ops map,
+ * otherwise libbpf would automatically set autocreate for all
+ * referenced programs.
+ * See libbpf.c:bpf_object_adjust_struct_ops_autoload.
+ */
+static void mask_unrelated_struct_ops_progs(struct bpf_object *obj,
+					    struct bpf_map *map,
+					    struct bpf_program *prog)
+{
+	struct btf *btf = bpf_object__btf(obj);
+	const struct btf_type *t, *mt;
+	struct btf_member *m;
+	int i, moff;
+	size_t data_sz, ptr_sz = sizeof(void *);
+	void *data;
+
+	t = btf__type_by_id(btf, bpf_map__btf_value_type_id(map));
+	if (!btf_is_struct(t))
+		return;
+
+	data = bpf_map__initial_value(map, &data_sz);
+	for (i = 0; i < btf_vlen(t); i++) {
+		m = &btf_members(t)[i];
+		mt = btf__type_by_id(btf, m->type);
+		if (!btf_is_ptr(mt))
+			continue;
+		moff = m->offset / 8;
+		if (moff + ptr_sz > data_sz)
+			continue;
+		if (memcmp(data + moff, &prog, ptr_sz) == 0)
+			continue;
+		memset(data + moff, 0, ptr_sz);
+	}
+}
+
+static void fixup_obj(struct bpf_object *obj, struct bpf_program *prog, const char *filename)
 {
 	struct bpf_map *map;
 
@@ -786,24 +1250,374 @@ static void fixup_obj(struct bpf_object *obj)
 		case BPF_MAP_TYPE_TASK_STORAGE:
 		case BPF_MAP_TYPE_INODE_STORAGE:
 		case BPF_MAP_TYPE_CGROUP_STORAGE:
+		case BPF_MAP_TYPE_CGRP_STORAGE:
+			break;
+		case BPF_MAP_TYPE_STRUCT_OPS:
+			mask_unrelated_struct_ops_progs(obj, map, prog);
 			break;
 		default:
 			if (bpf_map__max_entries(map) == 0)
 				bpf_map__set_max_entries(map, 1);
 		}
 	}
+
+	/* SEC(freplace) programs can't be loaded with veristat as is,
+	 * but we can try guessing their target program's expected type by
+	 * looking at the type of program's first argument and substituting
+	 * corresponding program type
+	 */
+	if (bpf_program__type(prog) == BPF_PROG_TYPE_EXT) {
+		const struct btf *btf = bpf_object__btf(obj);
+		const char *prog_name = bpf_program__name(prog);
+		enum bpf_prog_type prog_type;
+		enum bpf_attach_type attach_type;
+		const struct btf_type *t;
+		const char *ctx_name;
+		int id;
+
+		if (!btf)
+			goto skip_freplace_fixup;
+
+		id = btf__find_by_name_kind(btf, prog_name, BTF_KIND_FUNC);
+		t = btf__type_by_id(btf, id);
+		t = btf__type_by_id(btf, t->type);
+		if (!btf_is_func_proto(t) || btf_vlen(t) != 1)
+			goto skip_freplace_fixup;
+
+		/* context argument is a pointer to a struct/typedef */
+		t = btf__type_by_id(btf, btf_params(t)[0].type);
+		while (t && btf_is_mod(t))
+			t = btf__type_by_id(btf, t->type);
+		if (!t || !btf_is_ptr(t))
+			goto skip_freplace_fixup;
+		t = btf__type_by_id(btf, t->type);
+		while (t && btf_is_mod(t))
+			t = btf__type_by_id(btf, t->type);
+		if (!t)
+			goto skip_freplace_fixup;
+
+		ctx_name = btf__name_by_offset(btf, t->name_off);
+
+		if (guess_prog_type_by_ctx_name(ctx_name, &prog_type, &attach_type) == 0) {
+			bpf_program__set_type(prog, prog_type);
+			bpf_program__set_expected_attach_type(prog, attach_type);
+
+			if (!env.quiet) {
+				fprintf(stderr, "Using guessed program type '%s' for %s/%s...\n",
+					libbpf_bpf_prog_type_str(prog_type),
+					filename, prog_name);
+			}
+		} else {
+			if (!env.quiet) {
+				fprintf(stderr, "Failed to guess program type for freplace program with context type name '%s' for %s/%s. Consider using canonical type names to help veristat...\n",
+					ctx_name, filename, prog_name);
+			}
+		}
+	}
+skip_freplace_fixup:
+	return;
+}
+
+static int max_verifier_log_size(void)
+{
+	const int SMALL_LOG_SIZE = UINT_MAX >> 8;
+	const int BIG_LOG_SIZE = UINT_MAX >> 2;
+	struct bpf_insn insns[] = {
+		{ .code = BPF_ALU | BPF_MOV | BPF_X, .dst_reg = BPF_REG_0, },
+		{ .code  = BPF_JMP | BPF_EXIT, },
+	};
+	LIBBPF_OPTS(bpf_prog_load_opts, opts,
+		    .log_size = BIG_LOG_SIZE,
+		    .log_buf = (void *)-1,
+		    .log_level = 4
+	);
+	int ret, insn_cnt = ARRAY_SIZE(insns);
+	static int log_size;
+
+	if (log_size != 0)
+		return log_size;
+
+	ret = bpf_prog_load(BPF_PROG_TYPE_TRACEPOINT, NULL, "GPL", insns, insn_cnt, &opts);
+
+	if (ret == -EFAULT)
+		log_size = BIG_LOG_SIZE;
+	else /* ret == -EINVAL, big log size is not supported by the verifier */
+		log_size = SMALL_LOG_SIZE;
+
+	return log_size;
+}
+
+static bool output_stat_enabled(int id)
+{
+	int i;
+
+	for (i = 0; i < env.output_spec.spec_cnt; i++)
+		if (env.output_spec.ids[i] == id)
+			return true;
+	return false;
+}
+
+__attribute__((format(printf, 2, 3)))
+static int write_one_line(const char *file, const char *fmt, ...)
+{
+	int err, saved_errno;
+	va_list ap;
+	FILE *f;
+
+	f = fopen(file, "w");
+	if (!f)
+		return -1;
+
+	va_start(ap, fmt);
+	errno = 0;
+	err = vfprintf(f, fmt, ap);
+	saved_errno = errno;
+	va_end(ap);
+	fclose(f);
+	errno = saved_errno;
+	return err < 0 ? -1 : 0;
+}
+
+__attribute__((format(scanf, 3, 4)))
+static int scanf_one_line(const char *file, int fields_expected, const char *fmt, ...)
+{
+	int res = 0, saved_errno = 0;
+	char *line = NULL;
+	size_t line_len;
+	va_list ap;
+	FILE *f;
+
+	f = fopen(file, "r");
+	if (!f)
+		return -1;
+
+	va_start(ap, fmt);
+	while (getline(&line, &line_len, f) > 0) {
+		res = vsscanf(line, fmt, ap);
+		if (res == fields_expected)
+			goto out;
+	}
+	if (ferror(f)) {
+		saved_errno = errno;
+		res = -1;
+	}
+
+out:
+	va_end(ap);
+	free(line);
+	fclose(f);
+	errno = saved_errno;
+	return res;
+}
+
+static void destroy_stat_cgroup(void)
+{
+	char buf[PATH_MAX];
+	int err;
+
+	close(env.memory_peak_fd);
+
+	if (env.orig_cgroup[0]) {
+		snprintf(buf, sizeof(buf), "%s/cgroup.procs", env.orig_cgroup);
+		err = write_one_line(buf, "%d\n", getpid());
+		if (err < 0)
+			log_errno("moving self to original cgroup %s\n", env.orig_cgroup);
+	}
+
+	if (env.stat_cgroup[0]) {
+		err = rmdir(env.stat_cgroup);
+		if (err < 0)
+			log_errno("deletion of cgroup %s", env.stat_cgroup);
+	}
+
+	env.memory_peak_fd = -1;
+	env.orig_cgroup[0] = 0;
+	env.stat_cgroup[0] = 0;
+}
+
+/*
+ * Creates a cgroup at /sys/fs/cgroup/veristat-accounting-<pid>,
+ * moves current process to this cgroup.
+ */
+static void create_stat_cgroup(void)
+{
+	char cgroup_fs_mount[4096];
+	char buf[4096];
+	int err;
+
+	env.memory_peak_fd = -1;
+
+	if (!output_stat_enabled(MEMORY_PEAK))
+		return;
+
+	err = scanf_one_line("/proc/self/mounts", 2, "%*s %4095s cgroup2 %s",
+			     cgroup_fs_mount, buf);
+	if (err != 2) {
+		if (err < 0)
+			log_errno("reading /proc/self/mounts");
+		else if (!env.quiet)
+			fprintf(stderr, "Can't find cgroupfs v2 mount point.\n");
+		goto err_out;
+	}
+
+	/* cgroup-v2.rst promises the line "0::<group>" for cgroups v2 */
+	err = scanf_one_line("/proc/self/cgroup", 1, "0::%4095s", buf);
+	if (err != 1) {
+		if (err < 0)
+			log_errno("reading /proc/self/cgroup");
+		else if (!env.quiet)
+			fprintf(stderr, "Can't infer veristat process cgroup.");
+		goto err_out;
+	}
+
+	snprintf(env.orig_cgroup, sizeof(env.orig_cgroup), "%s/%s", cgroup_fs_mount, buf);
+
+	snprintf(buf, sizeof(buf), "%s/veristat-accounting-%d", cgroup_fs_mount, getpid());
+	err = mkdir(buf, 0777);
+	if (err < 0) {
+		log_errno("creation of cgroup %s", buf);
+		goto err_out;
+	}
+	strcpy(env.stat_cgroup, buf);
+
+	snprintf(buf, sizeof(buf), "%s/cgroup.procs", env.stat_cgroup);
+	err = write_one_line(buf, "%d\n", getpid());
+	if (err < 0) {
+		log_errno("entering cgroup %s", buf);
+		goto err_out;
+	}
+
+	snprintf(buf, sizeof(buf), "%s/memory.peak", env.stat_cgroup);
+	env.memory_peak_fd = open(buf, O_RDWR | O_APPEND);
+	if (env.memory_peak_fd < 0) {
+		log_errno("opening %s", buf);
+		goto err_out;
+	}
+
+	return;
+
+err_out:
+	if (!env.quiet)
+		fprintf(stderr, "Memory usage metric unavailable.\n");
+	destroy_stat_cgroup();
+}
+
+/* Current value of /sys/fs/cgroup/veristat-accounting-<pid>/memory.peak */
+static long cgroup_memory_peak(void)
+{
+	long err, memory_peak;
+	char buf[32];
+
+	if (env.memory_peak_fd < 0)
+		return -1;
+
+	err = pread(env.memory_peak_fd, buf, sizeof(buf) - 1, 0);
+	if (err <= 0) {
+		log_errno("pread(%s/memory.peak)", env.stat_cgroup);
+		return -1;
+	}
+
+	buf[err] = 0;
+	errno = 0;
+	memory_peak = strtoll(buf, NULL, 10);
+	if (errno) {
+		log_errno("%s/memory.peak:strtoll(%s)", env.stat_cgroup, buf);
+		return -1;
+	}
+
+	return memory_peak;
+}
+
+static int reset_stat_cgroup(void)
+{
+	char buf[] = "r\n";
+	int err;
+
+	if (env.memory_peak_fd < 0)
+		return -1;
+
+	err = pwrite(env.memory_peak_fd, buf, sizeof(buf), 0);
+	if (err <= 0) {
+		log_errno("pwrite(%s/memory.peak)", env.stat_cgroup);
+		return -1;
+	}
+	return 0;
+}
+
+static int parse_rvalue(const char *val, struct rvalue *rvalue)
+{
+	long long value;
+	char *val_end;
+
+	if (val[0] == '-' || isdigit(val[0])) {
+		/* must be a number */
+		errno = 0;
+		value = strtoll(val, &val_end, 0);
+		if (errno == ERANGE) {
+			errno = 0;
+			value = strtoull(val, &val_end, 0);
+		}
+		if (errno || *val_end != '\0') {
+			fprintf(stderr, "Failed to parse value '%s'\n", val);
+			return -EINVAL;
+		}
+		rvalue->ivalue = value;
+		rvalue->type = INTEGRAL;
+	} else {
+		/* if not a number, consider it enum value */
+		rvalue->svalue = strdup(val);
+		if (!rvalue->svalue)
+			return -ENOMEM;
+		rvalue->type = ENUMERATOR;
+	}
+	return 0;
+}
+
+static void dump(__u32 prog_id, enum dump_mode mode, const char *file_name, const char *prog_name)
+{
+	char command[64], buf[4096];
+	FILE *fp;
+	int status;
+
+	status = system("command -v bpftool > /dev/null 2>&1");
+	if (status != 0) {
+		fprintf(stderr, "bpftool is not available, can't print program dump\n");
+		return;
+	}
+	snprintf(command, sizeof(command), "bpftool prog dump %s id %u",
+		 mode == DUMP_JITED ? "jited" : "xlated", prog_id);
+	fp = popen(command, "r");
+	if (!fp) {
+		fprintf(stderr, "bpftool failed with error: %d\n", errno);
+		return;
+	}
+
+	printf("DUMP (%s) %s/%s:\n", mode == DUMP_JITED ? "JITED" : "XLATED", file_name, prog_name);
+	while (fgets(buf, sizeof(buf), fp))
+		fputs(buf, stdout);
+	fprintf(stdout, "\n");
+
+	if (ferror(fp))
+		fprintf(stderr, "Failed to dump BPF prog with error: %d\n", errno);
+
+	pclose(fp);
 }
 
 static int process_prog(const char *filename, struct bpf_object *obj, struct bpf_program *prog)
 {
+	const char *base_filename = basename(strdupa(filename));
 	const char *prog_name = bpf_program__name(prog);
-	size_t buf_sz = sizeof(verif_log_buf);
-	char *buf = verif_log_buf;
+	long mem_peak_a, mem_peak_b, mem_peak = -1;
+	char *buf;
+	int buf_sz, log_level;
 	struct verif_stats *stats;
-	int err = 0;
+	struct bpf_prog_info info;
+	__u32 info_len = sizeof(info);
+	int err = 0, cgroup_err;
 	void *tmp;
+	int fd;
 
-	if (!should_process_file_prog(basename(filename), bpf_program__name(prog))) {
+	if (!should_process_file_prog(base_filename, bpf_program__name(prog))) {
 		env.progs_skipped++;
 		return 0;
 	}
@@ -815,28 +1629,64 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf
 	stats = &env.prog_stats[env.prog_stat_cnt++];
 	memset(stats, 0, sizeof(*stats));
 
-	if (env.verbose) {
-		buf_sz = 16 * 1024 * 1024;
+	if (env.verbose || env.top_src_lines > 0) {
+		buf_sz = env.log_size ? env.log_size : max_verifier_log_size();
 		buf = malloc(buf_sz);
 		if (!buf)
 			return -ENOMEM;
-		bpf_program__set_log_buf(prog, buf, buf_sz);
-		bpf_program__set_log_level(prog, env.log_level | 4); /* stats + log */
+		/* ensure we always request stats */
+		log_level = env.log_level | 4 | (env.log_fixed ? 8 : 0);
+		/* --top-src-lines needs verifier log */
+		if (env.top_src_lines > 0 && env.log_level == 0)
+			log_level |= 2;
 	} else {
-		bpf_program__set_log_buf(prog, buf, buf_sz);
-		bpf_program__set_log_level(prog, 4); /* only verifier stats */
+		buf = verif_log_buf;
+		buf_sz = sizeof(verif_log_buf);
+		/* request only verifier stats */
+		log_level = 4 | (env.log_fixed ? 8 : 0);
 	}
 	verif_log_buf[0] = '\0';
 
-	/* increase chances of successful BPF object loading */
-	fixup_obj(obj);
+	bpf_program__set_log_buf(prog, buf, buf_sz);
+	bpf_program__set_log_level(prog, log_level);
 
-	err = bpf_object__load(obj);
+	/* increase chances of successful BPF object loading */
+	fixup_obj(obj, prog, base_filename);
+
+	if (env.force_checkpoints)
+		bpf_program__set_flags(prog, bpf_program__flags(prog) | BPF_F_TEST_STATE_FREQ);
+	if (env.force_reg_invariants)
+		bpf_program__set_flags(prog, bpf_program__flags(prog) | BPF_F_TEST_REG_INVARIANTS);
+
+	err = bpf_object__prepare(obj);
+	if (!err) {
+		cgroup_err = reset_stat_cgroup();
+		mem_peak_a = cgroup_memory_peak();
+		err = bpf_object__load(obj);
+		mem_peak_b = cgroup_memory_peak();
+		if (!cgroup_err && mem_peak_a >= 0 && mem_peak_b >= 0)
+			mem_peak = mem_peak_b - mem_peak_a;
+	}
 	env.progs_processed++;
 
-	stats->file_name = strdup(basename(filename));
+	stats->file_name = strdup(base_filename);
 	stats->prog_name = strdup(bpf_program__name(prog));
 	stats->stats[VERDICT] = err == 0; /* 1 - success, 0 - failure */
+	stats->stats[SIZE] = bpf_program__insn_cnt(prog);
+	stats->stats[PROG_TYPE] = bpf_program__type(prog);
+	stats->stats[ATTACH_TYPE] = bpf_program__expected_attach_type(prog);
+	stats->stats[MEMORY_PEAK] = mem_peak < 0 ? -1 : mem_peak / (1024 * 1024);
+
+	memset(&info, 0, info_len);
+	fd = bpf_program__fd(prog);
+	if (fd > 0 && bpf_prog_get_info_by_fd(fd, &info, &info_len) == 0) {
+		stats->stats[JITED_SIZE] = info.jited_prog_len;
+		if (env.dump_mode & DUMP_JITED)
+			dump(info.id, DUMP_JITED, base_filename, prog_name);
+		if (env.dump_mode & DUMP_XLATED)
+			dump(info.id, DUMP_XLATED, base_filename, prog_name);
+	}
+
 	parse_verif_log(buf, buf_sz, stats);
 
 	if (env.verbose) {
@@ -844,22 +1694,501 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf
 		       filename, prog_name, stats->stats[DURATION],
 		       err ? "failure" : "success", buf);
 	}
+	if (env.top_src_lines > 0)
+		print_top_src_lines(buf, buf_sz, stats->prog_name);
 
 	if (verif_log_buf != buf)
 		free(buf);
 
 	return 0;
-};
+}
+
+static int append_preset_atom(struct var_preset *preset, char *value, bool is_index)
+{
+	struct field_access *tmp;
+	int i = preset->atom_count;
+	int err;
+
+	tmp = reallocarray(preset->atoms, i + 1, sizeof(*preset->atoms));
+	if (!tmp)
+		return -ENOMEM;
+
+	preset->atoms = tmp;
+	preset->atom_count++;
+
+	if (is_index) {
+		preset->atoms[i].type = ARRAY_INDEX;
+		err = parse_rvalue(value, &preset->atoms[i].index);
+		if (err)
+			return err;
+	} else {
+		preset->atoms[i].type = FIELD_NAME;
+		preset->atoms[i].name = strdup(value);
+		if (!preset->atoms[i].name)
+			return -ENOMEM;
+	}
+	return 0;
+}
+
+static int parse_var_atoms(const char *full_var, struct var_preset *preset)
+{
+	char expr[256], var[256], *name, *saveptr;
+	int n, len, off, err;
+
+	snprintf(expr, sizeof(expr), "%s", full_var);
+	preset->atom_count = 0;
+	while ((name = strtok_r(preset->atom_count ? NULL : expr, ".", &saveptr))) {
+		len = strlen(name);
+		/* parse variable name */
+		if (sscanf(name, "%[a-zA-Z0-9_] %n", var, &off) != 1) {
+			fprintf(stderr, "Can't parse %s\n", name);
+			return -EINVAL;
+		}
+		err = append_preset_atom(preset, var, false);
+		if (err)
+			return err;
+
+		/* parse optional array indexes */
+		while (off < len) {
+			if (sscanf(name + off, " [ %[a-zA-Z0-9_] ] %n", var, &n) != 1) {
+				fprintf(stderr, "Can't parse %s as index\n", name + off);
+				return -EINVAL;
+			}
+			err = append_preset_atom(preset, var, true);
+			if (err)
+				return err;
+			off += n;
+		}
+	}
+	return 0;
+}
+
+static int append_var_preset(struct var_preset **presets, int *cnt, const char *expr)
+{
+	void *tmp;
+	struct var_preset *cur;
+	char var[256], val[256];
+	int n, err;
+
+	tmp = realloc(*presets, (*cnt + 1) * sizeof(**presets));
+	if (!tmp)
+		return -ENOMEM;
+	*presets = tmp;
+	cur = &(*presets)[*cnt];
+	memset(cur, 0, sizeof(*cur));
+	(*cnt)++;
+
+	if (sscanf(expr, " %[][a-zA-Z0-9_. ] = %s %n", var, val, &n) != 2 || n != strlen(expr)) {
+		fprintf(stderr, "Failed to parse expression '%s'\n", expr);
+		return -EINVAL;
+	}
+	/* Remove trailing spaces from var, as scanf may add those */
+	rtrim(var);
+
+	err = parse_rvalue(val, &cur->value);
+	if (err)
+		return err;
+
+	cur->full_name = strdup(var);
+	if (!cur->full_name)
+		return -ENOMEM;
+
+	err = parse_var_atoms(var, cur);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int append_var_preset_file(const char *filename)
+{
+	char buf[1024];
+	FILE *f;
+	int err = 0;
+
+	f = fopen(filename, "rt");
+	if (!f) {
+		err = -errno;
+		fprintf(stderr, "Failed to open presets in '%s': %s\n", filename, strerror(-err));
+		return -EINVAL;
+	}
+
+	while (fscanf(f, " %1023[^\n]\n", buf) == 1) {
+		if (buf[0] == '\0' || buf[0] == '#')
+			continue;
+
+		err = append_var_preset(&env.presets, &env.npresets, buf);
+		if (err)
+			goto cleanup;
+	}
+
+cleanup:
+	fclose(f);
+	return err;
+}
+
+static bool is_signed_type(const struct btf_type *t)
+{
+	if (btf_is_int(t))
+		return btf_int_encoding(t) & BTF_INT_SIGNED;
+	if (btf_is_any_enum(t))
+		return btf_kflag(t);
+	return true;
+}
+
+static int enum_value_from_name(const struct btf *btf, const struct btf_type *t,
+				const char *evalue, long long *retval)
+{
+	if (btf_is_enum(t)) {
+		struct btf_enum *e = btf_enum(t);
+		int i, n = btf_vlen(t);
+
+		for (i = 0; i < n; ++i, ++e) {
+			const char *cur_name = btf__name_by_offset(btf, e->name_off);
+
+			if (strcmp(cur_name, evalue) == 0) {
+				*retval = e->val;
+				return 0;
+			}
+		}
+	} else if (btf_is_enum64(t)) {
+		struct btf_enum64 *e = btf_enum64(t);
+		int i, n = btf_vlen(t);
+
+		for (i = 0; i < n; ++i, ++e) {
+			const char *cur_name = btf__name_by_offset(btf, e->name_off);
+			__u64 value =  btf_enum64_value(e);
+
+			if (strcmp(cur_name, evalue) == 0) {
+				*retval = value;
+				return 0;
+			}
+		}
+	}
+	return -EINVAL;
+}
+
+static bool is_preset_supported(const struct btf_type *t)
+{
+	return btf_is_int(t) || btf_is_enum(t) || btf_is_enum64(t);
+}
+
+static int find_enum_value(const struct btf *btf, const char *name, long long *value)
+{
+	const struct btf_type *t;
+	int cnt, i;
+	long long lvalue;
+
+	cnt = btf__type_cnt(btf);
+	for (i = 1; i != cnt; ++i) {
+		t = btf__type_by_id(btf, i);
+
+		if (!btf_is_any_enum(t))
+			continue;
+
+		if (enum_value_from_name(btf, t, name, &lvalue) == 0) {
+			*value = lvalue;
+			return 0;
+		}
+	}
+	return -ESRCH;
+}
+
+static int resolve_rvalue(struct btf *btf, const struct rvalue *rvalue, long long *result)
+{
+	int err = 0;
+
+	switch (rvalue->type) {
+	case INTEGRAL:
+		*result = rvalue->ivalue;
+		return 0;
+	case ENUMERATOR:
+		err = find_enum_value(btf, rvalue->svalue, result);
+		if (err) {
+			fprintf(stderr, "Can't resolve enum value %s\n", rvalue->svalue);
+			return err;
+		}
+		return 0;
+	default:
+		fprintf(stderr, "Unknown rvalue type\n");
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
+static int adjust_var_secinfo_array(struct btf *btf, int tid, struct field_access *atom,
+				    const char *array_name, struct btf_var_secinfo *sinfo)
+{
+	const struct btf_type *t;
+	struct btf_array *barr;
+	long long idx;
+	int err;
+
+	tid = btf__resolve_type(btf, tid);
+	t = btf__type_by_id(btf, tid);
+	if (!btf_is_array(t)) {
+		fprintf(stderr, "Array index is not expected for %s\n",
+			array_name);
+		return -EINVAL;
+	}
+	barr = btf_array(t);
+	err = resolve_rvalue(btf, &atom->index, &idx);
+	if (err)
+		return err;
+	if (idx < 0 || idx >= barr->nelems) {
+		fprintf(stderr, "Array index %lld is out of bounds [0, %u): %s\n",
+			idx, barr->nelems, array_name);
+		return -EINVAL;
+	}
+	sinfo->size = btf__resolve_size(btf, barr->type);
+	sinfo->offset += sinfo->size * idx;
+	sinfo->type = btf__resolve_type(btf, barr->type);
+	return 0;
+}
+
+static int adjust_var_secinfo_member(const struct btf *btf,
+				     const struct btf_type *parent_type,
+				     __u32 parent_offset,
+				     const char *member_name,
+				     struct btf_var_secinfo *sinfo)
+{
+	int i;
+
+	if (!btf_is_composite(parent_type)) {
+		fprintf(stderr, "Can't resolve field %s for non-composite type\n", member_name);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < btf_vlen(parent_type); ++i) {
+		const struct btf_member *member;
+		const struct btf_type *member_type;
+		int tid, off;
+
+		member = btf_members(parent_type) + i;
+		tid =  btf__resolve_type(btf, member->type);
+		if (tid < 0)
+			return -EINVAL;
+
+		member_type = btf__type_by_id(btf, tid);
+		off = parent_offset + member->offset;
+		if (member->name_off) {
+			const char *name = btf__name_by_offset(btf, member->name_off);
+
+			if (strcmp(member_name, name) == 0) {
+				if (btf_member_bitfield_size(parent_type, i) != 0) {
+					fprintf(stderr, "Bitfield presets are not supported %s\n",
+						name);
+					return -EINVAL;
+				}
+				sinfo->offset += off / 8;
+				sinfo->type = tid;
+				sinfo->size = member_type->size;
+				return 0;
+			}
+		} else if (btf_is_composite(member_type)) {
+			int err;
+
+			err = adjust_var_secinfo_member(btf, member_type, off,
+							member_name, sinfo);
+			if (!err)
+				return 0;
+		}
+	}
+
+	return -ESRCH;
+}
+
+static int adjust_var_secinfo(struct btf *btf, const struct btf_type *t,
+			      struct btf_var_secinfo *sinfo, struct var_preset *preset)
+{
+	const struct btf_type *base_type;
+	const char *prev_name;
+	int err, i;
+	int tid;
+
+	assert(preset->atom_count > 0);
+	assert(preset->atoms[0].type == FIELD_NAME);
+
+	tid = btf__resolve_type(btf, t->type);
+	base_type = btf__type_by_id(btf, tid);
+	prev_name = preset->atoms[0].name;
+
+	for (i = 1; i < preset->atom_count; ++i) {
+		struct field_access *atom = preset->atoms + i;
+
+		switch (atom->type) {
+		case ARRAY_INDEX:
+			err = adjust_var_secinfo_array(btf, tid, atom, prev_name, sinfo);
+			break;
+		case FIELD_NAME:
+			err = adjust_var_secinfo_member(btf, base_type, 0, atom->name, sinfo);
+			if (err == -ESRCH)
+				fprintf(stderr, "Can't find '%s'\n", atom->name);
+			prev_name = atom->name;
+			break;
+		default:
+			fprintf(stderr, "Unknown field_access type\n");
+			return -EOPNOTSUPP;
+		}
+		if (err)
+			return err;
+		base_type = btf__type_by_id(btf, sinfo->type);
+		tid = sinfo->type;
+	}
+
+	return 0;
+}
+
+static int set_global_var(struct bpf_object *obj, struct btf *btf,
+			  struct bpf_map *map, struct btf_var_secinfo *sinfo,
+			  struct var_preset *preset)
+{
+	const struct btf_type *base_type;
+	void *ptr;
+	long long value = preset->value.ivalue;
+	size_t size;
+
+	base_type = btf__type_by_id(btf, btf__resolve_type(btf, sinfo->type));
+	if (!base_type) {
+		fprintf(stderr, "Failed to resolve type %d\n", sinfo->type);
+		return -EINVAL;
+	}
+	if (!is_preset_supported(base_type)) {
+		fprintf(stderr, "Can't set %s. Only ints and enums are supported\n",
+			preset->full_name);
+		return -EINVAL;
+	}
+
+	if (preset->value.type == ENUMERATOR) {
+		if (btf_is_any_enum(base_type)) {
+			if (enum_value_from_name(btf, base_type, preset->value.svalue, &value)) {
+				fprintf(stderr,
+					"Failed to find integer value for enum element %s\n",
+					preset->value.svalue);
+				return -EINVAL;
+			}
+		} else {
+			fprintf(stderr, "Value %s is not supported for type %s\n",
+				preset->value.svalue,
+				btf__name_by_offset(btf, base_type->name_off));
+			return -EINVAL;
+		}
+	}
+
+	/* Check if value fits into the target variable size */
+	if  (sinfo->size < sizeof(value)) {
+		bool is_signed = is_signed_type(base_type);
+		__u32 unsigned_bits = sinfo->size * 8 - (is_signed ? 1 : 0);
+		long long max_val = 1ll << unsigned_bits;
+
+		if (value >= max_val || value < -max_val) {
+			fprintf(stderr,
+				"Variable %s value %lld is out of range [%lld; %lld]\n",
+				btf__name_by_offset(btf, base_type->name_off), value,
+				is_signed ? -max_val : 0, max_val - 1);
+			return -EINVAL;
+		}
+	}
+
+	ptr = bpf_map__initial_value(map, &size);
+	if (!ptr || sinfo->offset + sinfo->size > size)
+		return -EINVAL;
+
+	if (__BYTE_ORDER == __LITTLE_ENDIAN) {
+		memcpy(ptr + sinfo->offset, &value, sinfo->size);
+	} else { /* __BYTE_ORDER == __BIG_ENDIAN */
+		__u8 src_offset = sizeof(value) - sinfo->size;
+
+		memcpy(ptr + sinfo->offset, (void *)&value + src_offset, sinfo->size);
+	}
+	return 0;
+}
+
+static int set_global_vars(struct bpf_object *obj, struct var_preset *presets, int npresets)
+{
+	struct btf_var_secinfo *sinfo;
+	const char *sec_name;
+	const struct btf_type *t;
+	struct bpf_map *map;
+	struct btf *btf;
+	int i, j, k, n, cnt, err = 0;
+
+	if (npresets == 0)
+		return 0;
+
+	btf = bpf_object__btf(obj);
+	if (!btf)
+		return -EINVAL;
+
+	cnt = btf__type_cnt(btf);
+	for (i = 1; i != cnt; ++i) {
+		t = btf__type_by_id(btf, i);
+
+		if (!btf_is_datasec(t))
+			continue;
+
+		sinfo = btf_var_secinfos(t);
+		sec_name = btf__name_by_offset(btf, t->name_off);
+		map = bpf_object__find_map_by_name(obj, sec_name);
+		if (!map)
+			continue;
+
+		n = btf_vlen(t);
+		for (j = 0; j < n; ++j, ++sinfo) {
+			const struct btf_type *var_type = btf__type_by_id(btf, sinfo->type);
+			const char *var_name;
+
+			if (!btf_is_var(var_type))
+				continue;
+
+			var_name = btf__name_by_offset(btf, var_type->name_off);
+
+			for (k = 0; k < npresets; ++k) {
+				struct btf_var_secinfo tmp_sinfo;
+
+				if (strcmp(var_name, presets[k].atoms[0].name) != 0)
+					continue;
+
+				if (presets[k].applied) {
+					fprintf(stderr, "Variable %s is set more than once",
+						var_name);
+					return -EINVAL;
+				}
+				tmp_sinfo = *sinfo;
+				err = adjust_var_secinfo(btf, var_type,
+							 &tmp_sinfo, presets + k);
+				if (err)
+					return err;
+
+				err = set_global_var(obj, btf, map, &tmp_sinfo, presets + k);
+				if (err)
+					return err;
+
+				presets[k].applied = true;
+			}
+		}
+	}
+	for (i = 0; i < npresets; ++i) {
+		if (!presets[i].applied) {
+			fprintf(stderr, "Global variable preset %s has not been applied\n",
+				presets[i].full_name);
+			err = -EINVAL;
+		}
+		presets[i].applied = false;
+	}
+	return err;
+}
 
 static int process_obj(const char *filename)
 {
+	const char *base_filename = basename(strdupa(filename));
 	struct bpf_object *obj = NULL, *tobj;
 	struct bpf_program *prog, *tprog, *lprog;
 	libbpf_print_fn_t old_libbpf_print_fn;
 	LIBBPF_OPTS(bpf_object_open_opts, opts);
 	int err = 0, prog_cnt = 0;
 
-	if (!should_process_file_prog(basename(filename), NULL)) {
+	if (!should_process_file_prog(base_filename, NULL)) {
 		if (env.verbose)
 			printf("Skipping '%s' due to filters...\n", filename);
 		env.files_skipped++;
@@ -873,7 +2202,7 @@ static int process_obj(const char *filename)
 	}
 
 	if (!env.quiet && env.out_fmt == RESFMT_TABLE)
-		printf("Processing '%s'...\n", basename(filename));
+		printf("Processing '%s'...\n", base_filename);
 
 	old_libbpf_print_fn = libbpf_set_print(libbpf_print_fn);
 	obj = bpf_object__open_file(filename, &opts);
@@ -882,7 +2211,7 @@ static int process_obj(const char *filename)
 		 * that BPF object file is incomplete and has to be statically
 		 * linked into a final BPF object file; instead of bailing
 		 * out, report it into stderr, mark it as skipped, and
-		 * proceeed
+		 * proceed
 		 */
 		fprintf(stderr, "Failed to open '%s': %d\n", filename, -errno);
 		env.files_skipped++;
@@ -899,6 +2228,11 @@ static int process_obj(const char *filename)
 	if (prog_cnt == 1) {
 		prog = bpf_object__next_program(obj, NULL);
 		bpf_program__set_autoload(prog, true);
+		err = set_global_vars(obj, env.presets, env.npresets);
+		if (err) {
+			fprintf(stderr, "Failed to set global variables %d\n", err);
+			goto cleanup;
+		}
 		process_prog(filename, obj, prog);
 		goto cleanup;
 	}
@@ -913,6 +2247,13 @@ static int process_obj(const char *filename)
 			goto cleanup;
 		}
 
+		err = set_global_vars(tobj, env.presets, env.npresets);
+		if (err) {
+			fprintf(stderr, "Failed to set global variables %d\n", err);
+			goto cleanup;
+		}
+
+		lprog = NULL;
 		bpf_object__for_each_program(tprog, tobj) {
 			const char *tprog_name = bpf_program__name(tprog);
 
@@ -935,7 +2276,7 @@ cleanup:
 }
 
 static int cmp_stat(const struct verif_stats *s1, const struct verif_stats *s2,
-		    enum stat_id id, bool asc)
+		    enum stat_id id, bool asc, bool abs)
 {
 	int cmp = 0;
 
@@ -946,16 +2287,27 @@ static int cmp_stat(const struct verif_stats *s1, const struct verif_stats *s2,
 	case PROG_NAME:
 		cmp = strcmp(s1->prog_name, s2->prog_name);
 		break;
+	case ATTACH_TYPE:
+	case PROG_TYPE:
+	case SIZE:
+	case JITED_SIZE:
+	case STACK:
 	case VERDICT:
 	case DURATION:
 	case TOTAL_INSNS:
 	case TOTAL_STATES:
 	case PEAK_STATES:
 	case MAX_STATES_PER_INSN:
+	case MEMORY_PEAK:
 	case MARK_READ_MAX_LEN: {
 		long v1 = s1->stats[id];
 		long v2 = s2->stats[id];
 
+		if (abs) {
+			v1 = v1 < 0 ? -v1 : v1;
+			v2 = v2 < 0 ? -v2 : v2;
+		}
+
 		if (v1 != v2)
 			cmp = v1 < v2 ? -1 : 1;
 		break;
@@ -974,7 +2326,8 @@ static int cmp_prog_stats(const void *v1, const void *v2)
 	int i, cmp;
 
 	for (i = 0; i < env.sort_spec.spec_cnt; i++) {
-		cmp = cmp_stat(s1, s2, env.sort_spec.ids[i], env.sort_spec.asc[i]);
+		cmp = cmp_stat(s1, s2, env.sort_spec.ids[i],
+			       env.sort_spec.asc[i], env.sort_spec.abs[i]);
 		if (cmp != 0)
 			return cmp;
 	}
@@ -1043,15 +2396,21 @@ static void fetch_join_stat_value(const struct verif_stats_join *s,
 
 static int cmp_join_stat(const struct verif_stats_join *s1,
 			 const struct verif_stats_join *s2,
-			 enum stat_id id, enum stat_variant var, bool asc)
+			 enum stat_id id, enum stat_variant var,
+			 bool asc, bool abs)
 {
 	const char *str1 = NULL, *str2 = NULL;
-	double v1, v2;
+	double v1 = 0.0, v2 = 0.0;
 	int cmp = 0;
 
 	fetch_join_stat_value(s1, id, var, &str1, &v1);
 	fetch_join_stat_value(s2, id, var, &str2, &v2);
 
+	if (abs) {
+		v1 = fabs(v1);
+		v2 = fabs(v2);
+	}
+
 	if (str1)
 		cmp = strcmp(str1, str2);
 	else if (v1 != v2)
@@ -1069,7 +2428,8 @@ static int cmp_join_stats(const void *v1, const void *v2)
 		cmp = cmp_join_stat(s1, s2,
 				    env.sort_spec.ids[i],
 				    env.sort_spec.variants[i],
-				    env.sort_spec.asc[i]);
+				    env.sort_spec.asc[i],
+				    env.sort_spec.abs[i]);
 		if (cmp != 0)
 			return cmp;
 	}
@@ -1147,12 +2507,28 @@ static void prepare_value(const struct verif_stats *s, enum stat_id id,
 		else
 			*str = s->stats[VERDICT] ? "success" : "failure";
 		break;
+	case ATTACH_TYPE:
+		if (!s)
+			*str = "N/A";
+		else
+			*str = libbpf_bpf_attach_type_str(s->stats[ATTACH_TYPE]) ?: "N/A";
+		break;
+	case PROG_TYPE:
+		if (!s)
+			*str = "N/A";
+		else
+			*str = libbpf_bpf_prog_type_str(s->stats[PROG_TYPE]) ?: "N/A";
+		break;
 	case DURATION:
 	case TOTAL_INSNS:
 	case TOTAL_STATES:
 	case PEAK_STATES:
 	case MAX_STATES_PER_INSN:
 	case MARK_READ_MAX_LEN:
+	case STACK:
+	case SIZE:
+	case JITED_SIZE:
+	case MEMORY_PEAK:
 		*val = s ? s->stats[id] : 0;
 		break;
 	default:
@@ -1236,7 +2612,11 @@ static int parse_stat_value(const char *str, enum stat_id id, struct verif_stats
 	case TOTAL_STATES:
 	case PEAK_STATES:
 	case MAX_STATES_PER_INSN:
-	case MARK_READ_MAX_LEN: {
+	case MARK_READ_MAX_LEN:
+	case SIZE:
+	case JITED_SIZE:
+	case MEMORY_PEAK:
+	case STACK: {
 		long val;
 		int err, n;
 
@@ -1249,6 +2629,42 @@ static int parse_stat_value(const char *str, enum stat_id id, struct verif_stats
 		st->stats[id] = val;
 		break;
 	}
+	case PROG_TYPE: {
+		enum bpf_prog_type prog_type = 0;
+		const char *type;
+
+		while ((type = libbpf_bpf_prog_type_str(prog_type)))  {
+			if (strcmp(type, str) == 0) {
+				st->stats[id] = prog_type;
+				break;
+			}
+			prog_type++;
+		}
+
+		if (!type) {
+			fprintf(stderr, "Unrecognized prog type %s\n", str);
+			return -EINVAL;
+		}
+		break;
+	}
+	case ATTACH_TYPE: {
+		enum bpf_attach_type attach_type = 0;
+		const char *type;
+
+		while ((type = libbpf_bpf_attach_type_str(attach_type)))  {
+			if (strcmp(type, str) == 0) {
+				st->stats[id] = attach_type;
+				break;
+			}
+			attach_type++;
+		}
+
+		if (!type) {
+			fprintf(stderr, "Unrecognized attach type %s\n", str);
+			return -EINVAL;
+		}
+		break;
+	}
 	default:
 		fprintf(stderr, "Unrecognized stat #%d\n", id);
 		return -EINVAL;
@@ -1276,7 +2692,7 @@ static int parse_stats_csv(const char *filename, struct stat_specs *specs,
 	while (fgets(line, sizeof(line), f)) {
 		char *input = line, *state = NULL, *next;
 		struct verif_stats *st = NULL;
-		int col = 0;
+		int col = 0, cnt = 0;
 
 		if (!header) {
 			void *tmp;
@@ -1294,7 +2710,7 @@ static int parse_stats_csv(const char *filename, struct stat_specs *specs,
 			*stat_cntp += 1;
 		}
 
-		while ((next = strtok_r(state ? NULL : input, ",\n", &state))) {
+		while ((next = strtok_r(cnt++ ? NULL : input, ",\n", &state))) {
 			if (header) {
 				/* for the first line, set up spec stats */
 				err = parse_stat(next, specs);
@@ -1552,6 +2968,9 @@ static bool is_join_stat_filter_matched(struct filter *f, const struct verif_sta
 
 	fetch_join_stat_value(stats, f->stat_id, f->stat_var, &str, &value);
 
+	if (f->abs)
+		value = fabs(value);
+
 	switch (f->op) {
 	case OP_EQ: return value > f->value - eps && value < f->value + eps;
 	case OP_NEQ: return value < f->value - eps || value > f->value + eps;
@@ -1598,7 +3017,7 @@ static int handle_comparison_mode(void)
 	struct stat_specs base_specs = {}, comp_specs = {};
 	struct stat_specs tmp_sort_spec;
 	enum resfmt cur_fmt;
-	int err, i, j, last_idx;
+	int err, i, j, last_idx, cnt;
 
 	if (env.filename_cnt != 2) {
 		fprintf(stderr, "Comparison mode expects exactly two input CSV files!\n\n");
@@ -1691,23 +3110,27 @@ static int handle_comparison_mode(void)
 			join->stats_b = comp;
 			i++;
 			j++;
-		} else if (comp == &fallback_stats || r < 0) {
+		} else if (base != &fallback_stats && (comp == &fallback_stats || r < 0)) {
 			join->file_name = base->file_name;
 			join->prog_name = base->prog_name;
 			join->stats_a = base;
 			join->stats_b = NULL;
 			i++;
-		} else {
+		} else if (comp != &fallback_stats && (base == &fallback_stats || r > 0)) {
 			join->file_name = comp->file_name;
 			join->prog_name = comp->prog_name;
 			join->stats_a = NULL;
 			join->stats_b = comp;
 			j++;
+		} else {
+			fprintf(stderr, "%s:%d: should never reach here i=%i, j=%i",
+				__FILE__, __LINE__, i, j);
+			return -EINVAL;
 		}
 		env.join_stat_cnt += 1;
 	}
 
-	/* now sort joined results accorsing to sort spec */
+	/* now sort joined results according to sort spec */
 	qsort(env.join_stats, env.join_stat_cnt, sizeof(*env.join_stats), cmp_join_stats);
 
 	/* for human-readable table output we need to do extra pass to
@@ -1723,16 +3146,23 @@ static int handle_comparison_mode(void)
 one_more_time:
 	output_comp_headers(cur_fmt);
 
+	last_idx = -1;
+	cnt = 0;
 	for (i = 0; i < env.join_stat_cnt; i++) {
 		const struct verif_stats_join *join = &env.join_stats[i];
 
 		if (!should_output_join_stats(join))
 			continue;
 
+		if (env.top_n && cnt >= env.top_n)
+			break;
+
 		if (cur_fmt == RESFMT_TABLE_CALCLEN)
 			last_idx = i;
 
 		output_comp_stats(join, cur_fmt, i == last_idx);
+
+		cnt++;
 	}
 
 	if (cur_fmt == RESFMT_TABLE_CALCLEN) {
@@ -1747,6 +3177,9 @@ static bool is_stat_filter_matched(struct filter *f, const struct verif_stats *s
 {
 	long value = stats->stats[f->stat_id];
 
+	if (f->abs)
+		value = value < 0 ? -value : value;
+
 	switch (f->op) {
 	case OP_EQ: return value == f->value;
 	case OP_NEQ: return value != f->value;
@@ -1791,7 +3224,7 @@ static bool should_output_stats(const struct verif_stats *stats)
 static void output_prog_stats(void)
 {
 	const struct verif_stats *stats;
-	int i, last_stat_idx = 0;
+	int i, last_stat_idx = 0, cnt = 0;
 
 	if (env.out_fmt == RESFMT_TABLE) {
 		/* calculate column widths */
@@ -1811,13 +3244,16 @@ static void output_prog_stats(void)
 		stats = &env.prog_stats[i];
 		if (!should_output_stats(stats))
 			continue;
+		if (env.top_n && cnt >= env.top_n)
+			break;
 		output_stats(stats, env.out_fmt, i == last_stat_idx);
+		cnt++;
 	}
 }
 
 static int handle_verif_mode(void)
 {
-	int i, err;
+	int i, err = 0;
 
 	if (env.filename_cnt == 0) {
 		fprintf(stderr, "Please provide path to BPF object file!\n\n");
@@ -1825,11 +3261,12 @@ static int handle_verif_mode(void)
 		return -EINVAL;
 	}
 
+	create_stat_cgroup();
 	for (i = 0; i < env.filename_cnt; i++) {
 		err = process_obj(env.filenames[i]);
 		if (err) {
 			fprintf(stderr, "Failed to process '%s': %d\n", env.filenames[i], err);
-			return err;
+			goto out;
 		}
 	}
 
@@ -1837,7 +3274,9 @@ static int handle_verif_mode(void)
 
 	output_prog_stats();
 
-	return 0;
+out:
+	destroy_stat_cgroup();
+	return err;
 }
 
 static int handle_replay_mode(void)
@@ -1867,11 +3306,16 @@ static int handle_replay_mode(void)
 
 int main(int argc, char **argv)
 {
-	int err = 0, i;
+	int err = 0, i, j;
 
 	if (argp_parse(&argp, argc, argv, 0, NULL, NULL))
 		return 1;
 
+	if (env.show_version) {
+		printf("%s\n", argp_program_version);
+		return 0;
+	}
+
 	if (env.verbose && env.quiet) {
 		fprintf(stderr, "Verbose and quiet modes are incompatible, please specify just one or neither!\n\n");
 		argp_help(&argp, stderr, ARGP_HELP_USAGE, "veristat");
@@ -1920,5 +3364,21 @@ int main(int argc, char **argv)
 		free(env.deny_filters[i].prog_glob);
 	}
 	free(env.deny_filters);
+	for (i = 0; i < env.npresets; ++i) {
+		free(env.presets[i].full_name);
+		for (j = 0; j < env.presets[i].atom_count; ++j) {
+			switch (env.presets[i].atoms[j].type) {
+			case FIELD_NAME:
+				free(env.presets[i].atoms[j].name);
+				break;
+			case ARRAY_INDEX:
+				if (env.presets[i].atoms[j].index.type == ENUMERATOR)
+					free(env.presets[i].atoms[j].index.svalue);
+				break;
+			}
+		}
+		free(env.presets[i].atoms);
+	}
+	free(env.presets);
 	return -err;
 }
diff --git a/tools/testing/selftests/bpf/veristat.cfg b/tools/testing/selftests/bpf/veristat.cfg
index 1a385061618d..e661ffdcaadf 100644
--- a/tools/testing/selftests/bpf/veristat.cfg
+++ b/tools/testing/selftests/bpf/veristat.cfg
@@ -15,3 +15,4 @@ test_usdt*
 test_verif_scale*
 test_xdp_noinline*
 xdp_synproxy*
+verifier_search_pruning*
diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh
index 316a56d680f2..2f869daf8a06 100755
--- a/tools/testing/selftests/bpf/vmtest.sh
+++ b/tools/testing/selftests/bpf/vmtest.sh
@@ -1,31 +1,56 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-set -u
 set -e
 
-# This script currently only works for x86_64 and s390x, as
-# it is based on the VM image used by the BPF CI, which is
-# available only for these architectures.
-ARCH="$(uname -m)"
-case "${ARCH}" in
+# This script currently only works for the following platforms,
+# as it is based on the VM image used by the BPF CI, which is
+# available only for these architectures. We can also specify
+# the local rootfs image generated by the following script:
+# https://github.com/libbpf/ci/blob/main/rootfs/mkrootfs_debian.sh
+PLATFORM="${PLATFORM:-$(uname -m)}"
+case "${PLATFORM}" in
 s390x)
 	QEMU_BINARY=qemu-system-s390x
 	QEMU_CONSOLE="ttyS1"
-	QEMU_FLAGS=(-smp 2)
-	BZIMAGE="arch/s390/boot/compressed/vmlinux"
+	HOST_FLAGS=(-smp 2 -enable-kvm)
+	CROSS_FLAGS=(-smp 2)
+	BZIMAGE="arch/s390/boot/vmlinux"
+	ARCH="s390"
 	;;
 x86_64)
 	QEMU_BINARY=qemu-system-x86_64
 	QEMU_CONSOLE="ttyS0,115200"
-	QEMU_FLAGS=(-cpu host -smp 8)
+	HOST_FLAGS=(-cpu host -enable-kvm -smp 8)
+	CROSS_FLAGS=(-smp 8)
 	BZIMAGE="arch/x86/boot/bzImage"
+	ARCH="x86"
 	;;
 aarch64)
 	QEMU_BINARY=qemu-system-aarch64
 	QEMU_CONSOLE="ttyAMA0,115200"
-	QEMU_FLAGS=(-M virt,gic-version=3 -cpu host -smp 8)
+	HOST_FLAGS=(-M virt,gic-version=3 -cpu host -enable-kvm -smp 8)
+	CROSS_FLAGS=(-M virt,gic-version=3 -cpu cortex-a76 -smp 8)
 	BZIMAGE="arch/arm64/boot/Image"
+	ARCH="arm64"
+	;;
+riscv64)
+	# required qemu version v7.2.0+
+	QEMU_BINARY=qemu-system-riscv64
+	QEMU_CONSOLE="ttyS0,115200"
+	HOST_FLAGS=(-M virt -cpu host -enable-kvm -smp 8)
+	CROSS_FLAGS=(-M virt -cpu rv64,sscofpmf=true -smp 8)
+	BZIMAGE="arch/riscv/boot/Image"
+	ARCH="riscv"
+	;;
+ppc64el)
+	QEMU_BINARY=qemu-system-ppc64
+	QEMU_CONSOLE="hvc0"
+	# KVM could not be tested for powerpc, therefore not enabled for now.
+	HOST_FLAGS=(-machine pseries -cpu POWER9)
+	CROSS_FLAGS=(-machine pseries -cpu POWER9)
+	BZIMAGE="vmlinux"
+	ARCH="powerpc"
 	;;
 *)
 	echo "Unsupported architecture"
@@ -34,9 +59,12 @@ aarch64)
 esac
 DEFAULT_COMMAND="./test_progs"
 MOUNT_DIR="mnt"
+LOCAL_ROOTFS_IMAGE=""
 ROOTFS_IMAGE="root.img"
 OUTPUT_DIR="$HOME/.bpf_selftests"
-KCONFIG_REL_PATHS=("tools/testing/selftests/bpf/config" "tools/testing/selftests/bpf/config.${ARCH}")
+KCONFIG_REL_PATHS=("tools/testing/selftests/bpf/config"
+	"tools/testing/selftests/bpf/config.vm"
+	"tools/testing/selftests/bpf/config.${PLATFORM}")
 INDEX_URL="https://raw.githubusercontent.com/libbpf/ci/master/INDEX"
 NUM_COMPILE_JOBS="$(nproc)"
 LOG_FILE_BASE="$(date +"bpf_selftests.%Y-%m-%d_%H-%M-%S")"
@@ -56,6 +84,10 @@ tools/testing/selftests/bpf. e.g:
 If no command is specified and a debug shell (-s) is not requested,
 "${DEFAULT_COMMAND}" will be run by default.
 
+Using PLATFORM= and CROSS_COMPILE= options will enable cross platform testing:
+
+  PLATFORM=<platform> CROSS_COMPILE=<toolchain> $0 -- ./test_progs -t test_lsm
+
 If you build your kernel using KBUILD_OUTPUT= or O= options, these
 can be passed as environment variables to the script:
 
@@ -67,6 +99,7 @@ or
 
 Options:
 
+	-l)             Specify the path to the local rootfs image.
 	-i)		Update the rootfs image with a newer version.
 	-d)		Update the output directory (default: ${OUTPUT_DIR})
 	-j)		Number of jobs for compilation, similar to -j in make
@@ -90,24 +123,11 @@ populate_url_map()
 	fi
 }
 
-download()
-{
-	local file="$1"
-
-	if [[ ! -v URLS[$file] ]]; then
-		echo "$file not found" >&2
-		return 1
-	fi
-
-	echo "Downloading $file..." >&2
-	curl -Lsf "${URLS[$file]}" "${@:2}"
-}
-
 newest_rootfs_version()
 {
 	{
 	for file in "${!URLS[@]}"; do
-		if [[ $file =~ ^"${ARCH}"/libbpf-vmtest-rootfs-(.*)\.tar\.zst$ ]]; then
+		if [[ $file =~ ^"${PLATFORM}"/libbpf-vmtest-rootfs-(.*)\.tar\.zst$ ]]; then
 			echo "${BASH_REMATCH[1]}"
 		fi
 	done
@@ -116,16 +136,34 @@ newest_rootfs_version()
 
 download_rootfs()
 {
-	local rootfsversion="$1"
-	local dir="$2"
+	populate_url_map
+
+	local rootfsversion="$(newest_rootfs_version)"
+	local file="${PLATFORM}/libbpf-vmtest-rootfs-$rootfsversion.tar.zst"
+
+	if [[ ! -v URLS[$file] ]]; then
+		echo "$file not found" >&2
+		return 1
+	fi
+
+	echo "Downloading $file..." >&2
+	curl -Lsf "${URLS[$file]}" "${@:2}"
+}
+
+load_rootfs()
+{
+	local dir="$1"
 
 	if ! which zstd &> /dev/null; then
 		echo 'Could not find "zstd" on the system, please install zstd'
 		exit 1
 	fi
 
-	download "${ARCH}/libbpf-vmtest-rootfs-$rootfsversion.tar.zst" |
-		zstd -d | sudo tar -C "$dir" -x
+	if [[ -n "${LOCAL_ROOTFS_IMAGE}" ]]; then
+		cat "${LOCAL_ROOTFS_IMAGE}" | zstd -d | sudo tar -C "$dir" -x
+	else
+		download_rootfs | zstd -d | sudo tar -C "$dir" -x
+	fi
 }
 
 recompile_kernel()
@@ -225,7 +263,7 @@ create_vm_image()
 	mkfs.ext4 -q "${rootfs_img}"
 
 	mount_image
-	download_rootfs "$(newest_rootfs_version)" "${mount_dir}"
+	load_rootfs "${mount_dir}"
 	unmount_image
 }
 
@@ -242,12 +280,17 @@ EOF
 		exit 1
 	fi
 
+	if [[ "${PLATFORM}" != "$(uname -m)" ]]; then
+		QEMU_FLAGS=("${CROSS_FLAGS[@]}")
+	else
+		QEMU_FLAGS=("${HOST_FLAGS[@]}")
+	fi
+
 	${QEMU_BINARY} \
 		-nodefaults \
 		-display none \
 		-serial mon:stdio \
 		"${QEMU_FLAGS[@]}" \
-		-enable-kvm \
 		-m 4G \
 		-drive file="${rootfs_img}",format=raw,index=1,media=disk,if=virtio,cache=none \
 		-kernel "${kernel_bzimage}" \
@@ -339,8 +382,11 @@ main()
 	local exit_command="poweroff -f"
 	local debug_shell="no"
 
-	while getopts ':hskid:j:' opt; do
+	while getopts ':hskl:id:j:' opt; do
 		case ${opt} in
+		l)
+			LOCAL_ROOTFS_IMAGE="$OPTARG"
+			;;
 		i)
 			update_image="yes"
 			;;
@@ -375,6 +421,11 @@ main()
 
 	trap 'catch "$?"' EXIT
 
+	if [[ "${PLATFORM}" != "$(uname -m)" ]] && [[ -z "${CROSS_COMPILE}" ]]; then
+		echo "Cross-platform testing needs to specify CROSS_COMPILE"
+		exit 1
+	fi
+
 	if [[ $# -eq 0  && "${debug_shell}" == "no" ]]; then
 		echo "No command specified, will run ${DEFAULT_COMMAND} in the vm"
 	else
@@ -382,7 +433,8 @@ main()
 	fi
 
 	local kconfig_file="${OUTPUT_DIR}/latest.config"
-	local make_command="make -j ${NUM_COMPILE_JOBS} KCONFIG_CONFIG=${kconfig_file}"
+	local make_command="make ARCH=${ARCH} CROSS_COMPILE=${CROSS_COMPILE} \
+			    -j ${NUM_COMPILE_JOBS} KCONFIG_CONFIG=${kconfig_file}"
 
 	# Figure out where the kernel is being built.
 	# O takes precedence over KBUILD_OUTPUT.
@@ -400,8 +452,6 @@ main()
 		make_command="${make_command} KBUILD_OUTPUT=${KBUILD_OUTPUT}"
 	fi
 
-	populate_url_map
-
 	local rootfs_img="${OUTPUT_DIR}/${ROOTFS_IMAGE}"
 	local mount_dir="${OUTPUT_DIR}/${MOUNT_DIR}"
 
diff --git a/tools/testing/selftests/bpf/with_addr.sh b/tools/testing/selftests/bpf/with_addr.sh
deleted file mode 100755
index ffcd3953f94c..000000000000
--- a/tools/testing/selftests/bpf/with_addr.sh
+++ /dev/null
@@ -1,54 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-#
-# add private ipv4 and ipv6 addresses to loopback
-
-readonly V6_INNER='100::a/128'
-readonly V4_INNER='192.168.0.1/32'
-
-if getopts ":s" opt; then
-  readonly SIT_DEV_NAME='sixtofourtest0'
-  readonly V6_SIT='2::/64'
-  readonly V4_SIT='172.17.0.1/32'
-  shift
-fi
-
-fail() {
-  echo "error: $*" 1>&2
-  exit 1
-}
-
-setup() {
-  ip -6 addr add "${V6_INNER}" dev lo || fail 'failed to setup v6 address'
-  ip -4 addr add "${V4_INNER}" dev lo || fail 'failed to setup v4 address'
-
-  if [[ -n "${V6_SIT}" ]]; then
-    ip link add "${SIT_DEV_NAME}" type sit remote any local any \
-	    || fail 'failed to add sit'
-    ip link set dev "${SIT_DEV_NAME}" up \
-	    || fail 'failed to bring sit device up'
-    ip -6 addr add "${V6_SIT}" dev "${SIT_DEV_NAME}" \
-	    || fail 'failed to setup v6 SIT address'
-    ip -4 addr add "${V4_SIT}" dev "${SIT_DEV_NAME}" \
-	    || fail 'failed to setup v4 SIT address'
-  fi
-
-  sleep 2	# avoid race causing bind to fail
-}
-
-cleanup() {
-  if [[ -n "${V6_SIT}" ]]; then
-    ip -4 addr del "${V4_SIT}" dev "${SIT_DEV_NAME}"
-    ip -6 addr del "${V6_SIT}" dev "${SIT_DEV_NAME}"
-    ip link del "${SIT_DEV_NAME}"
-  fi
-
-  ip -4 addr del "${V4_INNER}" dev lo
-  ip -6 addr del "${V6_INNER}" dev lo
-}
-
-trap cleanup EXIT
-
-setup
-"$@"
-exit "$?"
diff --git a/tools/testing/selftests/bpf/with_tunnels.sh b/tools/testing/selftests/bpf/with_tunnels.sh
deleted file mode 100755
index e24949ed3a20..000000000000
--- a/tools/testing/selftests/bpf/with_tunnels.sh
+++ /dev/null
@@ -1,36 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-#
-# setup tunnels for flow dissection test
-
-readonly SUFFIX="test_$(mktemp -u XXXX)"
-CONFIG="remote 127.0.0.2 local 127.0.0.1 dev lo"
-
-setup() {
-  ip link add "ipip_${SUFFIX}" type ipip ${CONFIG}
-  ip link add "gre_${SUFFIX}" type gre ${CONFIG}
-  ip link add "sit_${SUFFIX}" type sit ${CONFIG}
-
-  echo "tunnels before test:"
-  ip tunnel show
-
-  ip link set "ipip_${SUFFIX}" up
-  ip link set "gre_${SUFFIX}" up
-  ip link set "sit_${SUFFIX}" up
-}
-
-
-cleanup() {
-  ip tunnel del "ipip_${SUFFIX}"
-  ip tunnel del "gre_${SUFFIX}"
-  ip tunnel del "sit_${SUFFIX}"
-
-  echo "tunnels after test:"
-  ip tunnel show
-}
-
-trap cleanup EXIT
-
-setup
-"$@"
-exit "$?"
diff --git a/tools/testing/selftests/bpf/xdp_features.c b/tools/testing/selftests/bpf/xdp_features.c
new file mode 100644
index 000000000000..595c79141cf3
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdp_features.c
@@ -0,0 +1,718 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/netdev.h>
+#include <linux/if_link.h>
+#include <signal.h>
+#include <argp.h>
+#include <net/if.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <netinet/tcp.h>
+#include <unistd.h>
+#include <arpa/inet.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <pthread.h>
+
+#include <network_helpers.h>
+
+#include "xdp_features.skel.h"
+#include "xdp_features.h"
+
+#define RED(str)	"\033[0;31m" str "\033[0m"
+#define GREEN(str)	"\033[0;32m" str "\033[0m"
+#define YELLOW(str)	"\033[0;33m" str "\033[0m"
+
+static struct env {
+	bool verbosity;
+	char ifname[IF_NAMESIZE];
+	int ifindex;
+	bool is_tester;
+	struct {
+		enum netdev_xdp_act drv_feature;
+		enum xdp_action action;
+	} feature;
+	struct sockaddr_storage dut_ctrl_addr;
+	struct sockaddr_storage dut_addr;
+	struct sockaddr_storage tester_addr;
+} env;
+
+#define BUFSIZE		128
+
+void test__fail(void) { /* for network_helpers.c */ }
+
+static int libbpf_print_fn(enum libbpf_print_level level,
+			   const char *format, va_list args)
+{
+	if (level == LIBBPF_DEBUG && !env.verbosity)
+		return 0;
+	return vfprintf(stderr, format, args);
+}
+
+static volatile bool exiting;
+
+static void sig_handler(int sig)
+{
+	exiting = true;
+}
+
+const char *argp_program_version = "xdp-features 0.0";
+const char argp_program_doc[] =
+"XDP features detection application.\n"
+"\n"
+"XDP features application checks the XDP advertised features match detected ones.\n"
+"\n"
+"USAGE: ./xdp-features [-vt] [-f <xdp-feature>] [-D <dut-data-ip>] [-T <tester-data-ip>] [-C <dut-ctrl-ip>] <iface-name>\n"
+"\n"
+"dut-data-ip, tester-data-ip, dut-ctrl-ip: IPv6 or IPv4-mapped-IPv6 addresses;\n"
+"\n"
+"XDP features\n:"
+"- XDP_PASS\n"
+"- XDP_DROP\n"
+"- XDP_ABORTED\n"
+"- XDP_REDIRECT\n"
+"- XDP_NDO_XMIT\n"
+"- XDP_TX\n";
+
+static const struct argp_option opts[] = {
+	{ "verbose", 'v', NULL, 0, "Verbose debug output" },
+	{ "tester", 't', NULL, 0, "Tester mode" },
+	{ "feature", 'f', "XDP-FEATURE", 0, "XDP feature to test" },
+	{ "dut_data_ip", 'D', "DUT-DATA-IP", 0, "DUT IP data channel" },
+	{ "dut_ctrl_ip", 'C', "DUT-CTRL-IP", 0, "DUT IP control channel" },
+	{ "tester_data_ip", 'T', "TESTER-DATA-IP", 0, "Tester IP data channel" },
+	{},
+};
+
+static int get_xdp_feature(const char *arg)
+{
+	if (!strcmp(arg, "XDP_PASS")) {
+		env.feature.action = XDP_PASS;
+		env.feature.drv_feature = NETDEV_XDP_ACT_BASIC;
+	} else if (!strcmp(arg, "XDP_DROP")) {
+		env.feature.drv_feature = NETDEV_XDP_ACT_BASIC;
+		env.feature.action = XDP_DROP;
+	} else if (!strcmp(arg, "XDP_ABORTED")) {
+		env.feature.drv_feature = NETDEV_XDP_ACT_BASIC;
+		env.feature.action = XDP_ABORTED;
+	} else if (!strcmp(arg, "XDP_TX")) {
+		env.feature.drv_feature = NETDEV_XDP_ACT_BASIC;
+		env.feature.action = XDP_TX;
+	} else if (!strcmp(arg, "XDP_REDIRECT")) {
+		env.feature.drv_feature = NETDEV_XDP_ACT_REDIRECT;
+		env.feature.action = XDP_REDIRECT;
+	} else if (!strcmp(arg, "XDP_NDO_XMIT")) {
+		env.feature.drv_feature = NETDEV_XDP_ACT_NDO_XMIT;
+	} else {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static char *get_xdp_feature_str(void)
+{
+	switch (env.feature.action) {
+	case XDP_PASS:
+		return YELLOW("XDP_PASS");
+	case XDP_DROP:
+		return YELLOW("XDP_DROP");
+	case XDP_ABORTED:
+		return YELLOW("XDP_ABORTED");
+	case XDP_TX:
+		return YELLOW("XDP_TX");
+	case XDP_REDIRECT:
+		return YELLOW("XDP_REDIRECT");
+	default:
+		break;
+	}
+
+	if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT)
+		return YELLOW("XDP_NDO_XMIT");
+
+	return "";
+}
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+	switch (key) {
+	case 'v':
+		env.verbosity = true;
+		break;
+	case 't':
+		env.is_tester = true;
+		break;
+	case 'f':
+		if (get_xdp_feature(arg) < 0) {
+			fprintf(stderr, "Invalid xdp feature: %s\n", arg);
+			argp_usage(state);
+			return ARGP_ERR_UNKNOWN;
+		}
+		break;
+	case 'D':
+		if (make_sockaddr(AF_INET6, arg, DUT_ECHO_PORT,
+				  &env.dut_addr, NULL)) {
+			fprintf(stderr,
+				"Invalid address assigned to the Device Under Test: %s\n",
+				arg);
+			return ARGP_ERR_UNKNOWN;
+		}
+		break;
+	case 'C':
+		if (make_sockaddr(AF_INET6, arg, DUT_CTRL_PORT,
+				  &env.dut_ctrl_addr, NULL)) {
+			fprintf(stderr,
+				"Invalid address assigned to the Device Under Test: %s\n",
+				arg);
+			return ARGP_ERR_UNKNOWN;
+		}
+		break;
+	case 'T':
+		if (make_sockaddr(AF_INET6, arg, 0, &env.tester_addr, NULL)) {
+			fprintf(stderr,
+				"Invalid address assigned to the Tester device: %s\n",
+				arg);
+			return ARGP_ERR_UNKNOWN;
+		}
+		break;
+	case ARGP_KEY_ARG:
+		errno = 0;
+		if (strlen(arg) >= IF_NAMESIZE) {
+			fprintf(stderr, "Invalid device name: %s\n", arg);
+			argp_usage(state);
+			return ARGP_ERR_UNKNOWN;
+		}
+
+		env.ifindex = if_nametoindex(arg);
+		if (!env.ifindex)
+			env.ifindex = strtoul(arg, NULL, 0);
+		if (!env.ifindex || !if_indextoname(env.ifindex, env.ifname)) {
+			fprintf(stderr,
+				"Bad interface index or name (%d): %s\n",
+				errno, strerror(errno));
+			argp_usage(state);
+			return ARGP_ERR_UNKNOWN;
+		}
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+
+	return 0;
+}
+
+static const struct argp argp = {
+	.options = opts,
+	.parser = parse_arg,
+	.doc = argp_program_doc,
+};
+
+static void set_env_default(void)
+{
+	env.feature.drv_feature = NETDEV_XDP_ACT_NDO_XMIT;
+	env.feature.action = -EINVAL;
+	env.ifindex = -ENODEV;
+	strcpy(env.ifname, "unknown");
+	make_sockaddr(AF_INET6, "::ffff:127.0.0.1", DUT_CTRL_PORT,
+		      &env.dut_ctrl_addr, NULL);
+	make_sockaddr(AF_INET6, "::ffff:127.0.0.1", DUT_ECHO_PORT,
+		      &env.dut_addr, NULL);
+	make_sockaddr(AF_INET6, "::ffff:127.0.0.1", 0, &env.tester_addr, NULL);
+}
+
+static void *dut_echo_thread(void *arg)
+{
+	unsigned char buf[sizeof(struct tlv_hdr)];
+	int sockfd = *(int *)arg;
+
+	while (!exiting) {
+		struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
+		struct sockaddr_storage addr;
+		socklen_t addrlen;
+		size_t n;
+
+		n = recvfrom(sockfd, buf, sizeof(buf), MSG_WAITALL,
+			     (struct sockaddr *)&addr, &addrlen);
+		if (n != ntohs(tlv->len))
+			continue;
+
+		if (ntohs(tlv->type) != CMD_ECHO)
+			continue;
+
+		sendto(sockfd, buf, sizeof(buf), MSG_NOSIGNAL | MSG_CONFIRM,
+		       (struct sockaddr *)&addr, addrlen);
+	}
+
+	pthread_exit((void *)0);
+	close(sockfd);
+
+	return NULL;
+}
+
+static int dut_run_echo_thread(pthread_t *t, int *sockfd)
+{
+	int err;
+
+	sockfd = start_reuseport_server(AF_INET6, SOCK_DGRAM, NULL,
+					DUT_ECHO_PORT, 0, 1);
+	if (!sockfd) {
+		fprintf(stderr,
+			"Failed creating data UDP socket on device %s\n",
+			env.ifname);
+		return -errno;
+	}
+
+	/* start echo channel */
+	err = pthread_create(t, NULL, dut_echo_thread, sockfd);
+	if (err) {
+		fprintf(stderr,
+			"Failed creating data UDP thread on device %s: %s\n",
+			env.ifname, strerror(-err));
+		free_fds(sockfd, 1);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int dut_attach_xdp_prog(struct xdp_features *skel, int flags)
+{
+	enum xdp_action action = env.feature.action;
+	struct bpf_program *prog;
+	unsigned int key = 0;
+	int err, fd = 0;
+
+	if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT) {
+		struct bpf_devmap_val entry = {
+			.ifindex = env.ifindex,
+		};
+
+		err = bpf_map__update_elem(skel->maps.dev_map,
+					   &key, sizeof(key),
+					   &entry, sizeof(entry), 0);
+		if (err < 0)
+			return err;
+
+		fd = bpf_program__fd(skel->progs.xdp_do_redirect_cpumap);
+		action = XDP_REDIRECT;
+	}
+
+	switch (action) {
+	case XDP_TX:
+		prog = skel->progs.xdp_do_tx;
+		break;
+	case XDP_DROP:
+		prog = skel->progs.xdp_do_drop;
+		break;
+	case XDP_ABORTED:
+		prog = skel->progs.xdp_do_aborted;
+		break;
+	case XDP_PASS:
+		prog = skel->progs.xdp_do_pass;
+		break;
+	case XDP_REDIRECT: {
+		struct bpf_cpumap_val entry = {
+			.qsize = 2048,
+			.bpf_prog.fd = fd,
+		};
+
+		err = bpf_map__update_elem(skel->maps.cpu_map,
+					   &key, sizeof(key),
+					   &entry, sizeof(entry), 0);
+		if (err < 0)
+			return err;
+
+		prog = skel->progs.xdp_do_redirect;
+		break;
+	}
+	default:
+		return -EINVAL;
+	}
+
+	err = bpf_xdp_attach(env.ifindex, bpf_program__fd(prog), flags, NULL);
+	if (err)
+		fprintf(stderr, "Failed attaching XDP program to device %s\n",
+			env.ifname);
+	return err;
+}
+
+static int recv_msg(int sockfd, void *buf, size_t bufsize, void *val,
+		    size_t val_size)
+{
+	struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
+	size_t len;
+
+	len = recv(sockfd, buf, bufsize, 0);
+	if (len != ntohs(tlv->len) || len < sizeof(*tlv))
+		return -EINVAL;
+
+	if (val) {
+		len -= sizeof(*tlv);
+		if (len > val_size)
+			return -ENOMEM;
+
+		memcpy(val, tlv->data, len);
+	}
+
+	return 0;
+}
+
+static int dut_run(struct xdp_features *skel)
+{
+	int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE;
+	int state, err = 0, *sockfd, ctrl_sockfd, echo_sockfd;
+	struct sockaddr_storage ctrl_addr;
+	pthread_t dut_thread = 0;
+	socklen_t addrlen;
+
+	sockfd = start_reuseport_server(AF_INET6, SOCK_STREAM, NULL,
+					DUT_CTRL_PORT, 0, 1);
+	if (!sockfd) {
+		fprintf(stderr,
+			"Failed creating control socket on device %s\n", env.ifname);
+		return -errno;
+	}
+
+	ctrl_sockfd = accept(*sockfd, (struct sockaddr *)&ctrl_addr, &addrlen);
+	if (ctrl_sockfd < 0) {
+		fprintf(stderr,
+			"Failed accepting connections on device %s control socket\n",
+			env.ifname);
+		free_fds(sockfd, 1);
+		return -errno;
+	}
+
+	/* CTRL loop */
+	while (!exiting) {
+		unsigned char buf[BUFSIZE] = {};
+		struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
+
+		err = recv_msg(ctrl_sockfd, buf, BUFSIZE, NULL, 0);
+		if (err)
+			continue;
+
+		switch (ntohs(tlv->type)) {
+		case CMD_START: {
+			if (state == CMD_START)
+				continue;
+
+			state = CMD_START;
+			/* Load the XDP program on the DUT */
+			err = dut_attach_xdp_prog(skel, flags);
+			if (err)
+				goto out;
+
+			err = dut_run_echo_thread(&dut_thread, &echo_sockfd);
+			if (err < 0)
+				goto out;
+
+			tlv->type = htons(CMD_ACK);
+			tlv->len = htons(sizeof(*tlv));
+			err = send(ctrl_sockfd, buf, sizeof(*tlv), 0);
+			if (err < 0)
+				goto end_thread;
+			break;
+		}
+		case CMD_STOP:
+			if (state != CMD_START)
+				break;
+
+			state = CMD_STOP;
+
+			exiting = true;
+			bpf_xdp_detach(env.ifindex, flags, NULL);
+
+			tlv->type = htons(CMD_ACK);
+			tlv->len = htons(sizeof(*tlv));
+			err = send(ctrl_sockfd, buf, sizeof(*tlv), 0);
+			goto end_thread;
+		case CMD_GET_XDP_CAP: {
+			LIBBPF_OPTS(bpf_xdp_query_opts, opts);
+			unsigned long long val;
+			size_t n;
+
+			err = bpf_xdp_query(env.ifindex, XDP_FLAGS_DRV_MODE,
+					    &opts);
+			if (err) {
+				fprintf(stderr,
+					"Failed querying XDP cap for device %s\n",
+					env.ifname);
+				goto end_thread;
+			}
+
+			tlv->type = htons(CMD_ACK);
+			n = sizeof(*tlv) + sizeof(opts.feature_flags);
+			tlv->len = htons(n);
+
+			val = htobe64(opts.feature_flags);
+			memcpy(tlv->data, &val, sizeof(val));
+
+			err = send(ctrl_sockfd, buf, n, 0);
+			if (err < 0)
+				goto end_thread;
+			break;
+		}
+		case CMD_GET_STATS: {
+			unsigned int key = 0, val;
+			size_t n;
+
+			err = bpf_map__lookup_elem(skel->maps.dut_stats,
+						   &key, sizeof(key),
+						   &val, sizeof(val), 0);
+			if (err) {
+				fprintf(stderr,
+					"bpf_map_lookup_elem failed (%d)\n", err);
+				goto end_thread;
+			}
+
+			tlv->type = htons(CMD_ACK);
+			n = sizeof(*tlv) + sizeof(val);
+			tlv->len = htons(n);
+
+			val = htonl(val);
+			memcpy(tlv->data, &val, sizeof(val));
+
+			err = send(ctrl_sockfd, buf, n, 0);
+			if (err < 0)
+				goto end_thread;
+			break;
+		}
+		default:
+			break;
+		}
+	}
+
+end_thread:
+	pthread_join(dut_thread, NULL);
+out:
+	bpf_xdp_detach(env.ifindex, flags, NULL);
+	close(ctrl_sockfd);
+	free_fds(sockfd, 1);
+
+	return err;
+}
+
+static bool tester_collect_detected_cap(struct xdp_features *skel,
+					unsigned int dut_stats)
+{
+	unsigned int err, key = 0, val;
+
+	if (!dut_stats)
+		return false;
+
+	err = bpf_map__lookup_elem(skel->maps.stats, &key, sizeof(key),
+				   &val, sizeof(val), 0);
+	if (err) {
+		fprintf(stderr, "bpf_map_lookup_elem failed (%d)\n", err);
+		return false;
+	}
+
+	switch (env.feature.action) {
+	case XDP_PASS:
+	case XDP_TX:
+	case XDP_REDIRECT:
+		return val > 0;
+	case XDP_DROP:
+	case XDP_ABORTED:
+		return val == 0;
+	default:
+		break;
+	}
+
+	if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT)
+		return val > 0;
+
+	return false;
+}
+
+static int send_and_recv_msg(int sockfd, enum test_commands cmd, void *val,
+			     size_t val_size)
+{
+	unsigned char buf[BUFSIZE] = {};
+	struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
+	int err;
+
+	tlv->type = htons(cmd);
+	tlv->len = htons(sizeof(*tlv));
+
+	err = send(sockfd, buf, sizeof(*tlv), 0);
+	if (err < 0)
+		return err;
+
+	err = recv_msg(sockfd, buf, BUFSIZE, val, val_size);
+	if (err < 0)
+		return err;
+
+	return ntohs(tlv->type) == CMD_ACK ? 0 : -EINVAL;
+}
+
+static int send_echo_msg(void)
+{
+	unsigned char buf[sizeof(struct tlv_hdr)];
+	struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
+	int sockfd, n;
+
+	sockfd = socket(AF_INET6, SOCK_DGRAM, 0);
+	if (sockfd < 0) {
+		fprintf(stderr,
+			"Failed creating data UDP socket on device %s\n",
+			env.ifname);
+		return -errno;
+	}
+
+	tlv->type = htons(CMD_ECHO);
+	tlv->len = htons(sizeof(*tlv));
+
+	n = sendto(sockfd, buf, sizeof(*tlv), MSG_NOSIGNAL | MSG_CONFIRM,
+		   (struct sockaddr *)&env.dut_addr, sizeof(env.dut_addr));
+	close(sockfd);
+
+	return n == ntohs(tlv->len) ? 0 : -EINVAL;
+}
+
+static int tester_run(struct xdp_features *skel)
+{
+	int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE;
+	unsigned long long advertised_feature;
+	struct bpf_program *prog;
+	unsigned int stats;
+	int i, err, sockfd;
+	bool detected_cap;
+
+	sockfd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (sockfd < 0) {
+		fprintf(stderr,
+			"Failed creating tester service control socket\n");
+		return -errno;
+	}
+
+	if (settimeo(sockfd, 1000) < 0)
+		return -EINVAL;
+
+	err = connect(sockfd, (struct sockaddr *)&env.dut_ctrl_addr,
+		      sizeof(env.dut_ctrl_addr));
+	if (err) {
+		fprintf(stderr,
+			"Failed connecting to the Device Under Test control socket\n");
+		return -errno;
+	}
+
+	err = send_and_recv_msg(sockfd, CMD_GET_XDP_CAP, &advertised_feature,
+				sizeof(advertised_feature));
+	if (err < 0) {
+		close(sockfd);
+		return err;
+	}
+
+	advertised_feature = be64toh(advertised_feature);
+
+	if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT ||
+	    env.feature.action == XDP_TX)
+		prog = skel->progs.xdp_tester_check_tx;
+	else
+		prog = skel->progs.xdp_tester_check_rx;
+
+	err = bpf_xdp_attach(env.ifindex, bpf_program__fd(prog), flags, NULL);
+	if (err) {
+		fprintf(stderr, "Failed attaching XDP program to device %s\n",
+			env.ifname);
+		goto out;
+	}
+
+	err = send_and_recv_msg(sockfd, CMD_START, NULL, 0);
+	if (err)
+		goto out;
+
+	for (i = 0; i < 10 && !exiting; i++) {
+		err = send_echo_msg();
+		if (err < 0)
+			goto out;
+
+		sleep(1);
+	}
+
+	err = send_and_recv_msg(sockfd, CMD_GET_STATS, &stats, sizeof(stats));
+	if (err)
+		goto out;
+
+	/* stop the test */
+	err = send_and_recv_msg(sockfd, CMD_STOP, NULL, 0);
+	/* send a new echo message to wake echo thread of the dut */
+	send_echo_msg();
+
+	detected_cap = tester_collect_detected_cap(skel, ntohl(stats));
+
+	fprintf(stdout, "Feature %s: [%s][%s]\n", get_xdp_feature_str(),
+		detected_cap ? GREEN("DETECTED") : RED("NOT DETECTED"),
+		env.feature.drv_feature & advertised_feature ? GREEN("ADVERTISED")
+							     : RED("NOT ADVERTISED"));
+out:
+	bpf_xdp_detach(env.ifindex, flags, NULL);
+	close(sockfd);
+	return err < 0 ? err : 0;
+}
+
+int main(int argc, char **argv)
+{
+	struct xdp_features *skel;
+	int err;
+
+	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+	libbpf_set_print(libbpf_print_fn);
+
+	signal(SIGINT, sig_handler);
+	signal(SIGTERM, sig_handler);
+
+	set_env_default();
+
+	/* Parse command line arguments */
+	err = argp_parse(&argp, argc, argv, 0, NULL, NULL);
+	if (err)
+		return err;
+
+	if (env.ifindex < 0) {
+		fprintf(stderr, "Invalid device name %s\n", env.ifname);
+		return -ENODEV;
+	}
+
+	/* Load and verify BPF application */
+	skel = xdp_features__open();
+	if (!skel) {
+		fprintf(stderr, "Failed to open and load BPF skeleton\n");
+		return -EINVAL;
+	}
+
+	skel->rodata->tester_addr =
+		((struct sockaddr_in6 *)&env.tester_addr)->sin6_addr;
+	skel->rodata->dut_addr =
+		((struct sockaddr_in6 *)&env.dut_addr)->sin6_addr;
+
+	/* Load & verify BPF programs */
+	err = xdp_features__load(skel);
+	if (err) {
+		fprintf(stderr, "Failed to load and verify BPF skeleton\n");
+		goto cleanup;
+	}
+
+	err = xdp_features__attach(skel);
+	if (err) {
+		fprintf(stderr, "Failed to attach BPF skeleton\n");
+		goto cleanup;
+	}
+
+	if (env.is_tester) {
+		/* Tester */
+		fprintf(stdout, "Starting tester service on device %s\n",
+			env.ifname);
+		err = tester_run(skel);
+	} else {
+		/* DUT */
+		fprintf(stdout, "Starting test on device %s\n", env.ifname);
+		err = dut_run(skel);
+	}
+
+cleanup:
+	xdp_features__destroy(skel);
+
+	return err < 0 ? -err : 0;
+}
diff --git a/tools/testing/selftests/bpf/xdp_features.h b/tools/testing/selftests/bpf/xdp_features.h
new file mode 100644
index 000000000000..2670c541713b
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdp_features.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/* test commands */
+enum test_commands {
+	CMD_STOP,		/* CMD */
+	CMD_START,		/* CMD */
+	CMD_ECHO,		/* CMD */
+	CMD_ACK,		/* CMD + data */
+	CMD_GET_XDP_CAP,	/* CMD */
+	CMD_GET_STATS,		/* CMD */
+};
+
+#define DUT_CTRL_PORT	12345
+#define DUT_ECHO_PORT	12346
+
+struct tlv_hdr {
+	__be16 type;
+	__be16 len;
+	__u8 data[];
+};
diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c
new file mode 100644
index 000000000000..3d8de0d4c96a
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c
@@ -0,0 +1,894 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Reference program for verifying XDP metadata on real HW. Functional test
+ * only, doesn't test the performance.
+ *
+ * RX:
+ * - UDP 9091 packets are diverted into AF_XDP
+ * - Metadata verified:
+ *   - rx_timestamp
+ *   - rx_hash
+ *
+ * TX:
+ * - UDP 9091 packets trigger TX reply
+ * - TX HW timestamp is requested and reported back upon completion
+ * - TX checksum is requested
+ * - TX launch time HW offload is requested for transmission
+ */
+
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "xdp_hw_metadata.skel.h"
+#include "xsk.h"
+
+#include <error.h>
+#include <linux/kernel.h>
+#include <linux/bits.h>
+#include <linux/bitfield.h>
+#include <linux/errqueue.h>
+#include <linux/if_link.h>
+#include <linux/net_tstamp.h>
+#include <netinet/udp.h>
+#include <linux/sockios.h>
+#include <linux/if_xdp.h>
+#include <sys/mman.h>
+#include <net/if.h>
+#include <ctype.h>
+#include <poll.h>
+#include <time.h>
+#include <unistd.h>
+#include <libgen.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <linux/pkt_sched.h>
+#include <linux/pkt_cls.h>
+#include <linux/ethtool.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+
+#include "xdp_metadata.h"
+
+#define UMEM_NUM 256
+#define UMEM_FRAME_SIZE XSK_UMEM__DEFAULT_FRAME_SIZE
+#define UMEM_SIZE (UMEM_FRAME_SIZE * UMEM_NUM)
+#define XDP_FLAGS (XDP_FLAGS_DRV_MODE | XDP_FLAGS_REPLACE)
+
+struct xsk {
+	void *umem_area;
+	struct xsk_umem *umem;
+	struct xsk_ring_prod fill;
+	struct xsk_ring_cons comp;
+	struct xsk_ring_prod tx;
+	struct xsk_ring_cons rx;
+	struct xsk_socket *socket;
+};
+
+struct xdp_hw_metadata *bpf_obj;
+__u16 bind_flags = XDP_USE_NEED_WAKEUP | XDP_ZEROCOPY;
+struct xsk *rx_xsk;
+const char *ifname;
+int ifindex;
+int rxq;
+bool skip_tx;
+__u64 last_hw_rx_timestamp;
+__u64 last_xdp_rx_timestamp;
+__u64 last_launch_time;
+__u64 launch_time_delta_to_hw_rx_timestamp;
+int launch_time_queue;
+
+#define run_command(cmd, ...)					\
+({								\
+	char command[1024];					\
+	memset(command, 0, sizeof(command));			\
+	snprintf(command, sizeof(command), cmd, ##__VA_ARGS__);	\
+	fprintf(stderr, "Running: %s\n", command);		\
+	system(command);					\
+})
+
+void test__fail(void) { /* for network_helpers.c */ }
+
+static int open_xsk(int ifindex, struct xsk *xsk, __u32 queue_id)
+{
+	int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
+	const struct xsk_socket_config socket_config = {
+		.rx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
+		.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
+		.bind_flags = bind_flags,
+	};
+	const struct xsk_umem_config umem_config = {
+		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
+		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
+		.frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE,
+		.flags = XDP_UMEM_TX_METADATA_LEN,
+		.tx_metadata_len = sizeof(struct xsk_tx_metadata),
+	};
+	__u32 idx = 0;
+	u64 addr;
+	int ret;
+	int i;
+
+	xsk->umem_area = mmap(NULL, UMEM_SIZE, PROT_READ | PROT_WRITE, mmap_flags, -1, 0);
+	if (xsk->umem_area == MAP_FAILED)
+		return -ENOMEM;
+
+	ret = xsk_umem__create(&xsk->umem,
+			       xsk->umem_area, UMEM_SIZE,
+			       &xsk->fill,
+			       &xsk->comp,
+			       &umem_config);
+	if (ret)
+		return ret;
+
+	ret = xsk_socket__create(&xsk->socket, ifindex, queue_id,
+				 xsk->umem,
+				 &xsk->rx,
+				 &xsk->tx,
+				 &socket_config);
+	if (ret)
+		return ret;
+
+	/* First half of umem is for TX. This way address matches 1-to-1
+	 * to the completion queue index.
+	 */
+
+	for (i = 0; i < UMEM_NUM / 2; i++) {
+		addr = i * UMEM_FRAME_SIZE;
+		printf("%p: tx_desc[%d] -> %lx\n", xsk, i, addr);
+	}
+
+	/* Second half of umem is for RX. */
+
+	ret = xsk_ring_prod__reserve(&xsk->fill, UMEM_NUM / 2, &idx);
+	for (i = 0; i < UMEM_NUM / 2; i++) {
+		addr = (UMEM_NUM / 2 + i) * UMEM_FRAME_SIZE;
+		printf("%p: rx_desc[%d] -> %lx\n", xsk, i, addr);
+		*xsk_ring_prod__fill_addr(&xsk->fill, idx + i) = addr;
+	}
+	xsk_ring_prod__submit(&xsk->fill, ret);
+
+	return 0;
+}
+
+static void close_xsk(struct xsk *xsk)
+{
+	if (xsk->umem)
+		xsk_umem__delete(xsk->umem);
+	if (xsk->socket)
+		xsk_socket__delete(xsk->socket);
+	munmap(xsk->umem_area, UMEM_SIZE);
+}
+
+static void refill_rx(struct xsk *xsk, __u64 addr)
+{
+	__u32 idx;
+
+	if (xsk_ring_prod__reserve(&xsk->fill, 1, &idx) == 1) {
+		printf("%p: complete rx idx=%u addr=%llx\n", xsk, idx, addr);
+		*xsk_ring_prod__fill_addr(&xsk->fill, idx) = addr;
+		xsk_ring_prod__submit(&xsk->fill, 1);
+	}
+}
+
+static int kick_tx(struct xsk *xsk)
+{
+	return sendto(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, 0);
+}
+
+static int kick_rx(struct xsk *xsk)
+{
+	return recvfrom(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, NULL);
+}
+
+#define NANOSEC_PER_SEC 1000000000 /* 10^9 */
+static __u64 gettime(clockid_t clock_id)
+{
+	struct timespec t;
+	int res;
+
+	/* See man clock_gettime(2) for type of clock_id's */
+	res = clock_gettime(clock_id, &t);
+
+	if (res < 0)
+		error(res, errno, "Error with clock_gettime()");
+
+	return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec;
+}
+
+static void print_tstamp_delta(const char *name, const char *refname,
+			       __u64 tstamp, __u64 reference)
+{
+	__s64 delta = (__s64)reference - (__s64)tstamp;
+
+	printf("%s:   %llu (sec:%0.4f) delta to %s sec:%0.4f (%0.3f usec)\n",
+	       name, tstamp, (double)tstamp / NANOSEC_PER_SEC, refname,
+	       (double)delta / NANOSEC_PER_SEC,
+	       (double)delta / 1000);
+}
+
+#define VLAN_PRIO_MASK		GENMASK(15, 13) /* Priority Code Point */
+#define VLAN_DEI_MASK		GENMASK(12, 12) /* Drop Eligible Indicator */
+#define VLAN_VID_MASK		GENMASK(11, 0)	/* VLAN Identifier */
+static void print_vlan_tci(__u16 tag)
+{
+	__u16 vlan_id = FIELD_GET(VLAN_VID_MASK, tag);
+	__u8 pcp = FIELD_GET(VLAN_PRIO_MASK, tag);
+	bool dei = FIELD_GET(VLAN_DEI_MASK, tag);
+
+	printf("PCP=%u, DEI=%d, VID=0x%X\n", pcp, dei, vlan_id);
+}
+
+static void verify_xdp_metadata(void *data, clockid_t clock_id)
+{
+	struct xdp_meta *meta;
+
+	meta = data - sizeof(*meta);
+
+	if (meta->hint_valid & XDP_META_FIELD_RSS)
+		printf("rx_hash: 0x%X with RSS type:0x%X\n",
+		       meta->rx_hash, meta->rx_hash_type);
+	else
+		printf("No rx_hash, err=%d\n", meta->rx_hash_err);
+
+	if (meta->hint_valid & XDP_META_FIELD_TS) {
+		__u64 ref_tstamp = gettime(clock_id);
+
+		/* store received timestamps to calculate a delta at tx */
+		last_hw_rx_timestamp = meta->rx_timestamp;
+		last_xdp_rx_timestamp = meta->xdp_timestamp;
+
+		print_tstamp_delta("HW RX-time", "User RX-time",
+				   meta->rx_timestamp, ref_tstamp);
+		print_tstamp_delta("XDP RX-time", "User RX-time",
+				   meta->xdp_timestamp, ref_tstamp);
+	} else {
+		printf("No rx_timestamp, err=%d\n", meta->rx_timestamp_err);
+	}
+
+	if (meta->hint_valid & XDP_META_FIELD_VLAN_TAG) {
+		printf("rx_vlan_proto: 0x%X\n", ntohs(meta->rx_vlan_proto));
+		printf("rx_vlan_tci: ");
+		print_vlan_tci(meta->rx_vlan_tci);
+	} else {
+		printf("No rx_vlan_tci or rx_vlan_proto, err=%d\n",
+		       meta->rx_vlan_tag_err);
+	}
+}
+
+static void verify_skb_metadata(int fd)
+{
+	char cmsg_buf[1024];
+	char packet_buf[128];
+
+	struct scm_timestamping *ts;
+	struct iovec packet_iov;
+	struct cmsghdr *cmsg;
+	struct msghdr hdr;
+
+	memset(&hdr, 0, sizeof(hdr));
+	hdr.msg_iov = &packet_iov;
+	hdr.msg_iovlen = 1;
+	packet_iov.iov_base = packet_buf;
+	packet_iov.iov_len = sizeof(packet_buf);
+
+	hdr.msg_control = cmsg_buf;
+	hdr.msg_controllen = sizeof(cmsg_buf);
+
+	if (recvmsg(fd, &hdr, 0) < 0)
+		error(1, errno, "recvmsg");
+
+	for (cmsg = CMSG_FIRSTHDR(&hdr); cmsg != NULL;
+	     cmsg = CMSG_NXTHDR(&hdr, cmsg)) {
+
+		if (cmsg->cmsg_level != SOL_SOCKET)
+			continue;
+
+		switch (cmsg->cmsg_type) {
+		case SCM_TIMESTAMPING:
+			ts = (struct scm_timestamping *)CMSG_DATA(cmsg);
+			if (ts->ts[2].tv_sec || ts->ts[2].tv_nsec) {
+				printf("found skb hwtstamp = %lu.%lu\n",
+				       ts->ts[2].tv_sec, ts->ts[2].tv_nsec);
+				return;
+			}
+			break;
+		default:
+			break;
+		}
+	}
+
+	printf("skb hwtstamp is not found!\n");
+}
+
+static bool complete_tx(struct xsk *xsk, clockid_t clock_id)
+{
+	struct xsk_tx_metadata *meta;
+	__u64 addr;
+	void *data;
+	__u32 idx;
+
+	if (!xsk_ring_cons__peek(&xsk->comp, 1, &idx))
+		return false;
+
+	addr = *xsk_ring_cons__comp_addr(&xsk->comp, idx);
+	data = xsk_umem__get_data(xsk->umem_area, addr);
+	meta = data - sizeof(struct xsk_tx_metadata);
+
+	printf("%p: complete tx idx=%u addr=%llx\n", xsk, idx, addr);
+
+	if (meta->completion.tx_timestamp) {
+		__u64 ref_tstamp = gettime(clock_id);
+
+		if (launch_time_delta_to_hw_rx_timestamp) {
+			print_tstamp_delta("HW Launch-time",
+					   "HW TX-complete-time",
+					   last_launch_time,
+					   meta->completion.tx_timestamp);
+		}
+		print_tstamp_delta("HW TX-complete-time", "User TX-complete-time",
+				   meta->completion.tx_timestamp, ref_tstamp);
+		print_tstamp_delta("XDP RX-time", "User TX-complete-time",
+				   last_xdp_rx_timestamp, ref_tstamp);
+		print_tstamp_delta("HW RX-time", "HW TX-complete-time",
+				   last_hw_rx_timestamp, meta->completion.tx_timestamp);
+	} else {
+		printf("No tx_timestamp\n");
+	}
+
+	xsk_ring_cons__release(&xsk->comp, 1);
+
+	return true;
+}
+
+#define swap(a, b, len) do { \
+	for (int i = 0; i < len; i++) { \
+		__u8 tmp = ((__u8 *)a)[i]; \
+		((__u8 *)a)[i] = ((__u8 *)b)[i]; \
+		((__u8 *)b)[i] = tmp; \
+	} \
+} while (0)
+
+static void ping_pong(struct xsk *xsk, void *rx_packet, clockid_t clock_id)
+{
+	struct xsk_tx_metadata *meta;
+	struct ipv6hdr *ip6h = NULL;
+	struct iphdr *iph = NULL;
+	struct xdp_desc *tx_desc;
+	struct udphdr *udph;
+	struct ethhdr *eth;
+	__sum16 want_csum;
+	void *data;
+	__u32 idx;
+	int ret;
+	int len;
+
+	ret = xsk_ring_prod__reserve(&xsk->tx, 1, &idx);
+	if (ret != 1) {
+		printf("%p: failed to reserve tx slot\n", xsk);
+		return;
+	}
+
+	tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx);
+	tx_desc->addr = idx % (UMEM_NUM / 2) * UMEM_FRAME_SIZE + sizeof(struct xsk_tx_metadata);
+	data = xsk_umem__get_data(xsk->umem_area, tx_desc->addr);
+
+	meta = data - sizeof(struct xsk_tx_metadata);
+	memset(meta, 0, sizeof(*meta));
+	meta->flags = XDP_TXMD_FLAGS_TIMESTAMP;
+
+	eth = rx_packet;
+
+	if (eth->h_proto == htons(ETH_P_IP)) {
+		iph = (void *)(eth + 1);
+		udph = (void *)(iph + 1);
+	} else if (eth->h_proto == htons(ETH_P_IPV6)) {
+		ip6h = (void *)(eth + 1);
+		udph = (void *)(ip6h + 1);
+	} else {
+		printf("%p: failed to detect IP version for ping pong %04x\n", xsk, eth->h_proto);
+		xsk_ring_prod__cancel(&xsk->tx, 1);
+		return;
+	}
+
+	len = ETH_HLEN;
+	if (ip6h)
+		len += sizeof(*ip6h) + ntohs(ip6h->payload_len);
+	if (iph)
+		len += ntohs(iph->tot_len);
+
+	swap(eth->h_dest, eth->h_source, ETH_ALEN);
+	if (iph)
+		swap(&iph->saddr, &iph->daddr, 4);
+	else
+		swap(&ip6h->saddr, &ip6h->daddr, 16);
+	swap(&udph->source, &udph->dest, 2);
+
+	want_csum = udph->check;
+	if (ip6h)
+		udph->check = ~csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
+					       ntohs(udph->len), IPPROTO_UDP, 0);
+	else
+		udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
+						 ntohs(udph->len), IPPROTO_UDP, 0);
+
+	meta->flags |= XDP_TXMD_FLAGS_CHECKSUM;
+	if (iph)
+		meta->request.csum_start = sizeof(*eth) + sizeof(*iph);
+	else
+		meta->request.csum_start = sizeof(*eth) + sizeof(*ip6h);
+	meta->request.csum_offset = offsetof(struct udphdr, check);
+
+	printf("%p: ping-pong with csum=%04x (want %04x) csum_start=%d csum_offset=%d\n",
+	       xsk, ntohs(udph->check), ntohs(want_csum),
+	       meta->request.csum_start, meta->request.csum_offset);
+
+	/* Set the value of launch time */
+	if (launch_time_delta_to_hw_rx_timestamp) {
+		meta->flags |= XDP_TXMD_FLAGS_LAUNCH_TIME;
+		meta->request.launch_time = last_hw_rx_timestamp +
+					    launch_time_delta_to_hw_rx_timestamp;
+		last_launch_time = meta->request.launch_time;
+		print_tstamp_delta("HW RX-time", "HW Launch-time",
+				   last_hw_rx_timestamp,
+				   meta->request.launch_time);
+	}
+
+	memcpy(data, rx_packet, len); /* don't share umem chunk for simplicity */
+	tx_desc->options |= XDP_TX_METADATA;
+	tx_desc->len = len;
+
+	xsk_ring_prod__submit(&xsk->tx, 1);
+}
+
+static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t clock_id)
+{
+	const struct xdp_desc *rx_desc;
+	struct pollfd fds[rxq + 1];
+	__u64 comp_addr;
+	__u64 deadline;
+	__u64 addr;
+	__u32 idx = 0;
+	int ret;
+	int i;
+
+	for (i = 0; i < rxq; i++) {
+		fds[i].fd = xsk_socket__fd(rx_xsk[i].socket);
+		fds[i].events = POLLIN;
+		fds[i].revents = 0;
+	}
+
+	fds[rxq].fd = server_fd;
+	fds[rxq].events = POLLIN;
+	fds[rxq].revents = 0;
+
+	while (true) {
+		errno = 0;
+
+		for (i = 0; i < rxq; i++) {
+			ret = kick_rx(&rx_xsk[i]);
+			if (ret)
+				printf("kick_rx ret=%d\n", ret);
+		}
+
+		ret = poll(fds, rxq + 1, 1000);
+		printf("poll: %d (%d) skip=%llu fail=%llu redir=%llu\n",
+		       ret, errno, bpf_obj->bss->pkts_skip,
+		       bpf_obj->bss->pkts_fail, bpf_obj->bss->pkts_redir);
+		if (ret < 0)
+			break;
+		if (ret == 0)
+			continue;
+
+		if (fds[rxq].revents)
+			verify_skb_metadata(server_fd);
+
+		for (i = 0; i < rxq; i++) {
+			bool first_seg = true;
+			bool is_eop = true;
+
+			if (fds[i].revents == 0)
+				continue;
+
+			struct xsk *xsk = &rx_xsk[i];
+peek:
+			ret = xsk_ring_cons__peek(&xsk->rx, 1, &idx);
+			printf("xsk_ring_cons__peek: %d\n", ret);
+			if (ret != 1)
+				continue;
+
+			rx_desc = xsk_ring_cons__rx_desc(&xsk->rx, idx);
+			comp_addr = xsk_umem__extract_addr(rx_desc->addr);
+			addr = xsk_umem__add_offset_to_addr(rx_desc->addr);
+			is_eop = !(rx_desc->options & XDP_PKT_CONTD);
+			printf("%p: rx_desc[%u]->addr=%llx addr=%llx comp_addr=%llx%s\n",
+			       xsk, idx, rx_desc->addr, addr, comp_addr, is_eop ? " EoP" : "");
+			if (first_seg) {
+				verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr),
+						    clock_id);
+				first_seg = false;
+
+				if (!skip_tx) {
+					/* mirror first chunk back */
+					ping_pong(xsk, xsk_umem__get_data(xsk->umem_area, addr),
+						  clock_id);
+
+					ret = kick_tx(xsk);
+					if (ret)
+						printf("kick_tx ret=%d\n", ret);
+
+					/* wait 1 second + cover launch time */
+					deadline = gettime(clock_id) +
+						   NANOSEC_PER_SEC +
+						   launch_time_delta_to_hw_rx_timestamp;
+					while (true) {
+						if (complete_tx(xsk, clock_id))
+							break;
+						if (gettime(clock_id) >= deadline)
+							break;
+						usleep(10);
+					}
+				}
+			}
+
+			xsk_ring_cons__release(&xsk->rx, 1);
+			refill_rx(xsk, comp_addr);
+			if (!is_eop)
+				goto peek;
+		}
+	}
+
+	return 0;
+}
+
+static int rxq_num(const char *ifname)
+{
+	struct ethtool_channels ch = {
+		.cmd = ETHTOOL_GCHANNELS,
+	};
+
+	struct ifreq ifr = {
+		.ifr_data = (void *)&ch,
+	};
+	strncpy(ifr.ifr_name, ifname, IF_NAMESIZE - 1);
+	int fd, ret;
+
+	fd = socket(AF_UNIX, SOCK_DGRAM, 0);
+	if (fd < 0)
+		error(1, errno, "socket");
+
+	ret = ioctl(fd, SIOCETHTOOL, &ifr);
+	if (ret < 0)
+		error(1, errno, "ioctl(SIOCETHTOOL)");
+
+	close(fd);
+
+	return ch.rx_count + ch.combined_count;
+}
+
+static void hwtstamp_ioctl(int op, const char *ifname, struct hwtstamp_config *cfg)
+{
+	struct ifreq ifr = {
+		.ifr_data = (void *)cfg,
+	};
+	strncpy(ifr.ifr_name, ifname, IF_NAMESIZE - 1);
+	int fd, ret;
+
+	fd = socket(AF_UNIX, SOCK_DGRAM, 0);
+	if (fd < 0)
+		error(1, errno, "socket");
+
+	ret = ioctl(fd, op, &ifr);
+	if (ret < 0)
+		error(1, errno, "ioctl(%d)", op);
+
+	close(fd);
+}
+
+static struct hwtstamp_config saved_hwtstamp_cfg;
+static const char *saved_hwtstamp_ifname;
+
+static void hwtstamp_restore(void)
+{
+	hwtstamp_ioctl(SIOCSHWTSTAMP, saved_hwtstamp_ifname, &saved_hwtstamp_cfg);
+}
+
+static void hwtstamp_enable(const char *ifname)
+{
+	struct hwtstamp_config cfg = {
+		.rx_filter = HWTSTAMP_FILTER_ALL,
+		.tx_type = HWTSTAMP_TX_ON,
+	};
+
+	hwtstamp_ioctl(SIOCGHWTSTAMP, ifname, &saved_hwtstamp_cfg);
+	saved_hwtstamp_ifname = strdup(ifname);
+	atexit(hwtstamp_restore);
+
+	hwtstamp_ioctl(SIOCSHWTSTAMP, ifname, &cfg);
+}
+
+static void cleanup(void)
+{
+	LIBBPF_OPTS(bpf_xdp_attach_opts, opts);
+	int ret;
+	int i;
+
+	if (bpf_obj) {
+		opts.old_prog_fd = bpf_program__fd(bpf_obj->progs.rx);
+		if (opts.old_prog_fd >= 0) {
+			printf("detaching bpf program....\n");
+			ret = bpf_xdp_detach(ifindex, XDP_FLAGS, &opts);
+			if (ret)
+				printf("failed to detach XDP program: %d\n", ret);
+		}
+	}
+
+	for (i = 0; i < rxq; i++)
+		close_xsk(&rx_xsk[i]);
+
+	if (bpf_obj)
+		xdp_hw_metadata__destroy(bpf_obj);
+
+	free((void *)saved_hwtstamp_ifname);
+}
+
+static void handle_signal(int sig)
+{
+	/* interrupting poll() is all we need */
+}
+
+static void timestamping_enable(int fd, int val)
+{
+	int ret;
+
+	ret = setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, &val, sizeof(val));
+	if (ret < 0)
+		error(1, errno, "setsockopt(SO_TIMESTAMPING)");
+}
+
+static void print_usage(void)
+{
+	const char *usage =
+		"Usage: xdp_hw_metadata [OPTIONS] [IFNAME]\n"
+		"  -c    Run in copy mode (zerocopy is default)\n"
+		"  -h    Display this help and exit\n\n"
+		"  -m    Enable multi-buffer XDP for larger MTU\n"
+		"  -r    Don't generate AF_XDP reply (rx metadata only)\n"
+		"  -l    Delta of launch time relative to HW RX-time in ns\n"
+		"        default: 0 ns (launch time request is disabled)\n"
+		"  -L    Tx Queue to be enabled with launch time offload\n"
+		"        default: 0 (Tx Queue 0)\n"
+		"Generate test packets on the other machine with:\n"
+		"  echo -n xdp | nc -u -q1 <dst_ip> 9091\n";
+
+	printf("%s", usage);
+}
+
+static void read_args(int argc, char *argv[])
+{
+	int opt;
+
+	while ((opt = getopt(argc, argv, "chmrl:L:")) != -1) {
+		switch (opt) {
+		case 'c':
+			bind_flags &= ~XDP_USE_NEED_WAKEUP;
+			bind_flags &= ~XDP_ZEROCOPY;
+			bind_flags |= XDP_COPY;
+			break;
+		case 'h':
+			print_usage();
+			exit(0);
+		case 'm':
+			bind_flags |= XDP_USE_SG;
+			break;
+		case 'r':
+			skip_tx = true;
+			break;
+		case 'l':
+			launch_time_delta_to_hw_rx_timestamp = atoll(optarg);
+			break;
+		case 'L':
+			launch_time_queue = atoll(optarg);
+			break;
+		case '?':
+			if (isprint(optopt))
+				fprintf(stderr, "Unknown option: -%c\n", optopt);
+			fallthrough;
+		default:
+			print_usage();
+			error(-1, opterr, "Command line options error");
+		}
+	}
+
+	if (optind >= argc) {
+		fprintf(stderr, "No device name provided\n");
+		print_usage();
+		exit(-1);
+	}
+
+	ifname = argv[optind];
+	ifindex = if_nametoindex(ifname);
+
+	if (!ifname)
+		error(-1, errno, "Invalid interface name");
+}
+
+void clean_existing_configurations(void)
+{
+	/* Check and delete root qdisc if exists */
+	if (run_command("sudo tc qdisc show dev %s | grep -q 'qdisc mqprio 8001:'", ifname) == 0)
+		run_command("sudo tc qdisc del dev %s root", ifname);
+
+	/* Check and delete ingress qdisc if exists */
+	if (run_command("sudo tc qdisc show dev %s | grep -q 'qdisc ingress ffff:'", ifname) == 0)
+		run_command("sudo tc qdisc del dev %s ingress", ifname);
+
+	/* Check and delete ethtool filters if any exist */
+	if (run_command("sudo ethtool -n %s | grep -q 'Filter:'", ifname) == 0) {
+		run_command("sudo ethtool -n %s | grep 'Filter:' | awk '{print $2}' | xargs -n1 sudo ethtool -N %s delete >&2",
+			    ifname, ifname);
+	}
+}
+
+#define MAX_TC 16
+
+int main(int argc, char *argv[])
+{
+	clockid_t clock_id = CLOCK_TAI;
+	struct bpf_program *prog;
+	int server_fd = -1;
+	size_t map_len = 0;
+	size_t que_len = 0;
+	char *buf = NULL;
+	char *map = NULL;
+	char *que = NULL;
+	char *tmp = NULL;
+	int tc = 0;
+	int ret;
+	int i;
+
+	read_args(argc, argv);
+
+	rxq = rxq_num(ifname);
+	printf("rxq: %d\n", rxq);
+
+	if (launch_time_queue >= rxq || launch_time_queue < 0)
+		error(1, 0, "Invalid launch_time_queue.");
+
+	clean_existing_configurations();
+	sleep(1);
+
+	/* Enable tx and rx hardware timestamping */
+	hwtstamp_enable(ifname);
+
+	/* Prepare priority to traffic class map for tc-mqprio */
+	for (i = 0; i < MAX_TC; i++) {
+		if (i < rxq)
+			tc = i;
+
+		if (asprintf(&buf, "%d ", tc) == -1) {
+			printf("Failed to malloc buf for tc map.\n");
+			goto free_mem;
+		}
+
+		map_len += strlen(buf);
+		tmp = realloc(map, map_len + 1);
+		if (!tmp) {
+			printf("Failed to realloc tc map.\n");
+			goto free_mem;
+		}
+		map = tmp;
+		strcat(map, buf);
+		free(buf);
+		buf = NULL;
+	}
+
+	/* Prepare traffic class to hardware queue map for tc-mqprio */
+	for (i = 0; i <= tc; i++) {
+		if (asprintf(&buf, "1@%d ", i) == -1) {
+			printf("Failed to malloc buf for tc queues.\n");
+			goto free_mem;
+		}
+
+		que_len += strlen(buf);
+		tmp = realloc(que, que_len + 1);
+		if (!tmp) {
+			printf("Failed to realloc tc queues.\n");
+			goto free_mem;
+		}
+		que = tmp;
+		strcat(que, buf);
+		free(buf);
+		buf = NULL;
+	}
+
+	/* Add mqprio qdisc */
+	run_command("sudo tc qdisc add dev %s handle 8001: parent root mqprio num_tc %d map %squeues %shw 0",
+		    ifname, tc + 1, map, que);
+
+	/* To test launch time, send UDP packet with VLAN priority 1 to port 9091 */
+	if (launch_time_delta_to_hw_rx_timestamp) {
+		/* Enable launch time hardware offload on launch_time_queue */
+		run_command("sudo tc qdisc replace dev %s parent 8001:%d etf offload clockid CLOCK_TAI delta 500000",
+			    ifname, launch_time_queue + 1);
+		sleep(1);
+
+		/* Route incoming packet with VLAN priority 1 into launch_time_queue */
+		if (run_command("sudo ethtool -N %s flow-type ether vlan 0x2000 vlan-mask 0x1FFF action %d",
+				ifname, launch_time_queue)) {
+			run_command("sudo tc qdisc add dev %s ingress", ifname);
+			run_command("sudo tc filter add dev %s parent ffff: protocol 802.1Q flower vlan_prio 1 hw_tc %d",
+				    ifname, launch_time_queue);
+		}
+
+		/* Enable VLAN tag stripping offload */
+		run_command("sudo ethtool -K %s rxvlan on", ifname);
+	}
+
+	rx_xsk = malloc(sizeof(struct xsk) * rxq);
+	if (!rx_xsk)
+		error(1, ENOMEM, "malloc");
+
+	for (i = 0; i < rxq; i++) {
+		printf("open_xsk(%s, %p, %d)\n", ifname, &rx_xsk[i], i);
+		ret = open_xsk(ifindex, &rx_xsk[i], i);
+		if (ret)
+			error(1, -ret, "open_xsk");
+
+		printf("xsk_socket__fd() -> %d\n", xsk_socket__fd(rx_xsk[i].socket));
+	}
+
+	printf("open bpf program...\n");
+	bpf_obj = xdp_hw_metadata__open();
+	if (libbpf_get_error(bpf_obj))
+		error(1, libbpf_get_error(bpf_obj), "xdp_hw_metadata__open");
+
+	prog = bpf_object__find_program_by_name(bpf_obj->obj, "rx");
+	bpf_program__set_ifindex(prog, ifindex);
+	bpf_program__set_flags(prog, BPF_F_XDP_DEV_BOUND_ONLY);
+
+	printf("load bpf program...\n");
+	ret = xdp_hw_metadata__load(bpf_obj);
+	if (ret)
+		error(1, -ret, "xdp_hw_metadata__load");
+
+	printf("prepare skb endpoint...\n");
+	server_fd = start_server(AF_INET6, SOCK_DGRAM, NULL, 9092, 1000);
+	if (server_fd < 0)
+		error(1, errno, "start_server");
+	timestamping_enable(server_fd,
+			    SOF_TIMESTAMPING_SOFTWARE |
+			    SOF_TIMESTAMPING_RAW_HARDWARE);
+
+	printf("prepare xsk map...\n");
+	for (i = 0; i < rxq; i++) {
+		int sock_fd = xsk_socket__fd(rx_xsk[i].socket);
+		__u32 queue_id = i;
+
+		printf("map[%d] = %d\n", queue_id, sock_fd);
+		ret = bpf_map_update_elem(bpf_map__fd(bpf_obj->maps.xsk), &queue_id, &sock_fd, 0);
+		if (ret)
+			error(1, -ret, "bpf_map_update_elem");
+	}
+
+	printf("attach bpf program...\n");
+	ret = bpf_xdp_attach(ifindex,
+			     bpf_program__fd(bpf_obj->progs.rx),
+			     XDP_FLAGS, NULL);
+	if (ret)
+		error(1, -ret, "bpf_xdp_attach");
+
+	signal(SIGINT, handle_signal);
+	ret = verify_metadata(rx_xsk, rxq, server_fd, clock_id);
+	close(server_fd);
+	cleanup();
+	if (ret)
+		error(1, -ret, "verify_metadata");
+
+	clean_existing_configurations();
+
+free_mem:
+	free(buf);
+	free(map);
+	free(que);
+}
diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h
new file mode 100644
index 000000000000..87318ad1117a
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdp_metadata.h
@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#pragma once
+
+#ifndef ETH_P_IP
+#define ETH_P_IP 0x0800
+#endif
+
+#ifndef ETH_P_IPV6
+#define ETH_P_IPV6 0x86DD
+#endif
+
+#ifndef ETH_P_8021Q
+#define ETH_P_8021Q 0x8100
+#endif
+
+#ifndef ETH_P_8021AD
+#define ETH_P_8021AD 0x88A8
+#endif
+
+#ifndef BIT
+#define BIT(nr)			(1 << (nr))
+#endif
+
+/* Non-existent checksum status */
+#define XDP_CHECKSUM_MAGIC	BIT(2)
+
+enum xdp_meta_field {
+	XDP_META_FIELD_TS	= BIT(0),
+	XDP_META_FIELD_RSS	= BIT(1),
+	XDP_META_FIELD_VLAN_TAG	= BIT(2),
+};
+
+struct xdp_meta {
+	union {
+		__u64 rx_timestamp;
+		__s32 rx_timestamp_err;
+	};
+	__u64 xdp_timestamp;
+	__u32 rx_hash;
+	union {
+		__u32 rx_hash_type;
+		__s32 rx_hash_err;
+	};
+	union {
+		struct {
+			__be16 rx_vlan_proto;
+			__u16 rx_vlan_tci;
+		};
+		__s32 rx_vlan_tag_err;
+	};
+	enum xdp_meta_field hint_valid;
+};
diff --git a/tools/testing/selftests/bpf/xdp_redirect_multi.c b/tools/testing/selftests/bpf/xdp_redirect_multi.c
deleted file mode 100644
index c1fc44c87c30..000000000000
--- a/tools/testing/selftests/bpf/xdp_redirect_multi.c
+++ /dev/null
@@ -1,226 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/bpf.h>
-#include <linux/if_link.h>
-#include <assert.h>
-#include <errno.h>
-#include <signal.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <net/if.h>
-#include <unistd.h>
-#include <libgen.h>
-#include <sys/ioctl.h>
-#include <sys/types.h>
-#include <sys/socket.h>
-#include <netinet/in.h>
-
-#include "bpf_util.h"
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-#define MAX_IFACE_NUM 32
-#define MAX_INDEX_NUM 1024
-
-static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
-static int ifaces[MAX_IFACE_NUM] = {};
-
-static void int_exit(int sig)
-{
-	__u32 prog_id = 0;
-	int i;
-
-	for (i = 0; ifaces[i] > 0; i++) {
-		if (bpf_xdp_query_id(ifaces[i], xdp_flags, &prog_id)) {
-			printf("bpf_xdp_query_id failed\n");
-			exit(1);
-		}
-		if (prog_id)
-			bpf_xdp_detach(ifaces[i], xdp_flags, NULL);
-	}
-
-	exit(0);
-}
-
-static int get_mac_addr(unsigned int ifindex, void *mac_addr)
-{
-	char ifname[IF_NAMESIZE];
-	struct ifreq ifr;
-	int fd, ret = -1;
-
-	fd = socket(AF_INET, SOCK_DGRAM, 0);
-	if (fd < 0)
-		return ret;
-
-	if (!if_indextoname(ifindex, ifname))
-		goto err_out;
-
-	strcpy(ifr.ifr_name, ifname);
-
-	if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0)
-		goto err_out;
-
-	memcpy(mac_addr, ifr.ifr_hwaddr.sa_data, 6 * sizeof(char));
-	ret = 0;
-
-err_out:
-	close(fd);
-	return ret;
-}
-
-static void usage(const char *prog)
-{
-	fprintf(stderr,
-		"usage: %s [OPTS] <IFNAME|IFINDEX> <IFNAME|IFINDEX> ...\n"
-		"OPTS:\n"
-		"    -S    use skb-mode\n"
-		"    -N    enforce native mode\n"
-		"    -F    force loading prog\n"
-		"    -X    load xdp program on egress\n",
-		prog);
-}
-
-int main(int argc, char **argv)
-{
-	int prog_fd, group_all, mac_map;
-	struct bpf_program *ingress_prog, *egress_prog;
-	int i, err, ret, opt, egress_prog_fd = 0;
-	struct bpf_devmap_val devmap_val;
-	bool attach_egress_prog = false;
-	unsigned char mac_addr[6];
-	char ifname[IF_NAMESIZE];
-	struct bpf_object *obj;
-	unsigned int ifindex;
-	char filename[256];
-
-	while ((opt = getopt(argc, argv, "SNFX")) != -1) {
-		switch (opt) {
-		case 'S':
-			xdp_flags |= XDP_FLAGS_SKB_MODE;
-			break;
-		case 'N':
-			/* default, set below */
-			break;
-		case 'F':
-			xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
-			break;
-		case 'X':
-			attach_egress_prog = true;
-			break;
-		default:
-			usage(basename(argv[0]));
-			return 1;
-		}
-	}
-
-	if (!(xdp_flags & XDP_FLAGS_SKB_MODE)) {
-		xdp_flags |= XDP_FLAGS_DRV_MODE;
-	} else if (attach_egress_prog) {
-		printf("Load xdp program on egress with SKB mode not supported yet\n");
-		goto err_out;
-	}
-
-	if (optind == argc) {
-		printf("usage: %s <IFNAME|IFINDEX> <IFNAME|IFINDEX> ...\n", argv[0]);
-		goto err_out;
-	}
-
-	printf("Get interfaces:");
-	for (i = 0; i < MAX_IFACE_NUM && argv[optind + i]; i++) {
-		ifaces[i] = if_nametoindex(argv[optind + i]);
-		if (!ifaces[i])
-			ifaces[i] = strtoul(argv[optind + i], NULL, 0);
-		if (!if_indextoname(ifaces[i], ifname)) {
-			perror("Invalid interface name or i");
-			goto err_out;
-		}
-		if (ifaces[i] > MAX_INDEX_NUM) {
-			printf(" interface index too large\n");
-			goto err_out;
-		}
-		printf(" %d", ifaces[i]);
-	}
-	printf("\n");
-
-	snprintf(filename, sizeof(filename), "%s_kern.bpf.o", argv[0]);
-	obj = bpf_object__open_file(filename, NULL);
-	err = libbpf_get_error(obj);
-	if (err)
-		goto err_out;
-	err = bpf_object__load(obj);
-	if (err)
-		goto err_out;
-	prog_fd = bpf_program__fd(bpf_object__next_program(obj, NULL));
-
-	if (attach_egress_prog)
-		group_all = bpf_object__find_map_fd_by_name(obj, "map_egress");
-	else
-		group_all = bpf_object__find_map_fd_by_name(obj, "map_all");
-	mac_map = bpf_object__find_map_fd_by_name(obj, "mac_map");
-
-	if (group_all < 0 || mac_map < 0) {
-		printf("bpf_object__find_map_fd_by_name failed\n");
-		goto err_out;
-	}
-
-	if (attach_egress_prog) {
-		/* Find ingress/egress prog for 2nd xdp prog */
-		ingress_prog = bpf_object__find_program_by_name(obj, "xdp_redirect_map_all_prog");
-		egress_prog = bpf_object__find_program_by_name(obj, "xdp_devmap_prog");
-		if (!ingress_prog || !egress_prog) {
-			printf("finding ingress/egress_prog in obj file failed\n");
-			goto err_out;
-		}
-		prog_fd = bpf_program__fd(ingress_prog);
-		egress_prog_fd = bpf_program__fd(egress_prog);
-		if (prog_fd < 0 || egress_prog_fd < 0) {
-			printf("find egress_prog fd failed\n");
-			goto err_out;
-		}
-	}
-
-	signal(SIGINT, int_exit);
-	signal(SIGTERM, int_exit);
-
-	/* Init forward multicast groups and exclude group */
-	for (i = 0; ifaces[i] > 0; i++) {
-		ifindex = ifaces[i];
-
-		if (attach_egress_prog) {
-			ret = get_mac_addr(ifindex, mac_addr);
-			if (ret < 0) {
-				printf("get interface %d mac failed\n", ifindex);
-				goto err_out;
-			}
-			ret = bpf_map_update_elem(mac_map, &ifindex, mac_addr, 0);
-			if (ret) {
-				perror("bpf_update_elem mac_map failed\n");
-				goto err_out;
-			}
-		}
-
-		/* Add all the interfaces to group all */
-		devmap_val.ifindex = ifindex;
-		devmap_val.bpf_prog.fd = egress_prog_fd;
-		ret = bpf_map_update_elem(group_all, &ifindex, &devmap_val, 0);
-		if (ret) {
-			perror("bpf_map_update_elem");
-			goto err_out;
-		}
-
-		/* bind prog_fd to each interface */
-		ret = bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL);
-		if (ret) {
-			printf("Set xdp fd failed on %d\n", ifindex);
-			goto err_out;
-		}
-	}
-
-	/* sleep some time for testing */
-	sleep(999);
-
-	return 0;
-
-err_out:
-	return 1;
-}
diff --git a/tools/testing/selftests/bpf/xdp_synproxy.c b/tools/testing/selftests/bpf/xdp_synproxy.c
index 410a1385a01d..ce68c342b56f 100644
--- a/tools/testing/selftests/bpf/xdp_synproxy.c
+++ b/tools/testing/selftests/bpf/xdp_synproxy.c
@@ -116,6 +116,7 @@ static void parse_options(int argc, char *argv[], unsigned int *ifindex, __u32 *
 	*tcpipopts = 0;
 	*ports = NULL;
 	*single = false;
+	*tc = false;
 
 	while (true) {
 		int opt;
@@ -216,9 +217,10 @@ static int syncookie_attach(const char *argv0, unsigned int ifindex, bool tc)
 
 	prog_fd = bpf_program__fd(prog);
 
-	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	err = bpf_prog_get_info_by_fd(prog_fd, &info, &info_len);
 	if (err < 0) {
-		fprintf(stderr, "Error: bpf_obj_get_info_by_fd: %s\n", strerror(-err));
+		fprintf(stderr, "Error: bpf_prog_get_info_by_fd: %s\n",
+			strerror(-err));
 		goto out;
 	}
 	attached_tc = tc;
@@ -291,9 +293,10 @@ static int syncookie_open_bpf_maps(__u32 prog_id, int *values_map_fd, int *ports
 	};
 	info_len = sizeof(prog_info);
 
-	err = bpf_obj_get_info_by_fd(prog_fd, &prog_info, &info_len);
+	err = bpf_prog_get_info_by_fd(prog_fd, &prog_info, &info_len);
 	if (err != 0) {
-		fprintf(stderr, "Error: bpf_obj_get_info_by_fd: %s\n", strerror(-err));
+		fprintf(stderr, "Error: bpf_prog_get_info_by_fd: %s\n",
+			strerror(-err));
 		goto out;
 	}
 
@@ -316,9 +319,10 @@ static int syncookie_open_bpf_maps(__u32 prog_id, int *values_map_fd, int *ports
 		map_fd = err;
 
 		info_len = sizeof(map_info);
-		err = bpf_obj_get_info_by_fd(map_fd, &map_info, &info_len);
+		err = bpf_map_get_info_by_fd(map_fd, &map_info, &info_len);
 		if (err != 0) {
-			fprintf(stderr, "Error: bpf_obj_get_info_by_fd: %s\n", strerror(-err));
+			fprintf(stderr, "Error: bpf_map_get_info_by_fd: %s\n",
+				strerror(-err));
 			close(map_fd);
 			goto err_close_map_fds;
 		}
diff --git a/tools/testing/selftests/bpf/xdping.c b/tools/testing/selftests/bpf/xdping.c
index 1503a1d2faa0..9ed8c796645d 100644
--- a/tools/testing/selftests/bpf/xdping.c
+++ b/tools/testing/selftests/bpf/xdping.c
@@ -155,7 +155,7 @@ int main(int argc, char **argv)
 	}
 
 	if (!server) {
-		/* Only supports IPv4; see hints initiailization above. */
+		/* Only supports IPv4; see hints initialization above. */
 		if (getaddrinfo(argv[optind], NULL, &hints, &a) || !a) {
 			fprintf(stderr, "Could not resolve %s\n", argv[optind]);
 			return 1;
diff --git a/tools/testing/selftests/bpf/xsk.c b/tools/testing/selftests/bpf/xsk.c
index 39d349509ba4..25d568abf0f2 100644
--- a/tools/testing/selftests/bpf/xsk.c
+++ b/tools/testing/selftests/bpf/xsk.c
@@ -18,17 +18,19 @@
 #include <linux/ethtool.h>
 #include <linux/filter.h>
 #include <linux/if_ether.h>
+#include <linux/if_link.h>
 #include <linux/if_packet.h>
 #include <linux/if_xdp.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
 #include <linux/sockios.h>
 #include <net/if.h>
 #include <sys/ioctl.h>
 #include <sys/mman.h>
 #include <sys/socket.h>
 #include <sys/types.h>
-#include <linux/if_link.h>
 
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
@@ -49,10 +51,7 @@
 
 #define pr_warn(fmt, ...) fprintf(stderr, fmt, ##__VA_ARGS__)
 
-enum xsk_prog {
-	XSK_PROG_FALLBACK,
-	XSK_PROG_REDIRECT_FLAGS,
-};
+#define XSKMAP_SIZE 1
 
 struct xsk_umem {
 	struct xsk_ring_prod *fill_save;
@@ -74,41 +73,20 @@ struct xsk_ctx {
 	int refcount;
 	int ifindex;
 	struct list_head list;
-	int prog_fd;
-	int link_fd;
-	int xsks_map_fd;
-	char ifname[IFNAMSIZ];
-	bool has_bpf_link;
 };
 
 struct xsk_socket {
 	struct xsk_ring_cons *rx;
 	struct xsk_ring_prod *tx;
-	__u64 outstanding_tx;
 	struct xsk_ctx *ctx;
 	struct xsk_socket_config config;
 	int fd;
 };
 
-struct xsk_nl_info {
-	bool xdp_prog_attached;
-	int ifindex;
-	int fd;
-};
-
-/* Up until and including Linux 5.3 */
-struct xdp_ring_offset_v1 {
-	__u64 producer;
-	__u64 consumer;
-	__u64 desc;
-};
-
-/* Up until and including Linux 5.3 */
-struct xdp_mmap_offsets_v1 {
-	struct xdp_ring_offset_v1 rx;
-	struct xdp_ring_offset_v1 tx;
-	struct xdp_ring_offset_v1 fr;
-	struct xdp_ring_offset_v1 cr;
+struct nl_mtu_req {
+	struct nlmsghdr nh;
+	struct ifinfomsg msg;
+	char             buf[512];
 };
 
 int xsk_umem__fd(const struct xsk_umem *umem)
@@ -137,6 +115,7 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg,
 		cfg->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
 		cfg->frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM;
 		cfg->flags = XSK_UMEM__DEFAULT_FLAGS;
+		cfg->tx_metadata_len = 0;
 		return;
 	}
 
@@ -145,6 +124,7 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg,
 	cfg->frame_size = usr_cfg->frame_size;
 	cfg->frame_headroom = usr_cfg->frame_headroom;
 	cfg->flags = usr_cfg->flags;
+	cfg->tx_metadata_len = usr_cfg->tx_metadata_len;
 }
 
 static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
@@ -153,55 +133,17 @@ static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
 	if (!usr_cfg) {
 		cfg->rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS;
 		cfg->tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
-		cfg->libbpf_flags = 0;
-		cfg->xdp_flags = 0;
 		cfg->bind_flags = 0;
 		return 0;
 	}
 
-	if (usr_cfg->libbpf_flags & ~XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)
-		return -EINVAL;
-
 	cfg->rx_size = usr_cfg->rx_size;
 	cfg->tx_size = usr_cfg->tx_size;
-	cfg->libbpf_flags = usr_cfg->libbpf_flags;
-	cfg->xdp_flags = usr_cfg->xdp_flags;
 	cfg->bind_flags = usr_cfg->bind_flags;
 
 	return 0;
 }
 
-static void xsk_mmap_offsets_v1(struct xdp_mmap_offsets *off)
-{
-	struct xdp_mmap_offsets_v1 off_v1;
-
-	/* getsockopt on a kernel <= 5.3 has no flags fields.
-	 * Copy over the offsets to the correct places in the >=5.4 format
-	 * and put the flags where they would have been on that kernel.
-	 */
-	memcpy(&off_v1, off, sizeof(off_v1));
-
-	off->rx.producer = off_v1.rx.producer;
-	off->rx.consumer = off_v1.rx.consumer;
-	off->rx.desc = off_v1.rx.desc;
-	off->rx.flags = off_v1.rx.consumer + sizeof(__u32);
-
-	off->tx.producer = off_v1.tx.producer;
-	off->tx.consumer = off_v1.tx.consumer;
-	off->tx.desc = off_v1.tx.desc;
-	off->tx.flags = off_v1.tx.consumer + sizeof(__u32);
-
-	off->fr.producer = off_v1.fr.producer;
-	off->fr.consumer = off_v1.fr.consumer;
-	off->fr.desc = off_v1.fr.desc;
-	off->fr.flags = off_v1.fr.consumer + sizeof(__u32);
-
-	off->cr.producer = off_v1.cr.producer;
-	off->cr.consumer = off_v1.cr.consumer;
-	off->cr.desc = off_v1.cr.desc;
-	off->cr.flags = off_v1.cr.consumer + sizeof(__u32);
-}
-
 static int xsk_get_mmap_offsets(int fd, struct xdp_mmap_offsets *off)
 {
 	socklen_t optlen;
@@ -215,11 +157,6 @@ static int xsk_get_mmap_offsets(int fd, struct xdp_mmap_offsets *off)
 	if (optlen == sizeof(*off))
 		return 0;
 
-	if (optlen == sizeof(struct xdp_mmap_offsets_v1)) {
-		xsk_mmap_offsets_v1(off);
-		return 0;
-	}
-
 	return -EINVAL;
 }
 
@@ -317,6 +254,7 @@ int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area,
 	mr.chunk_size = umem->config.frame_size;
 	mr.headroom = umem->config.frame_headroom;
 	mr.flags = umem->config.flags;
+	mr.tx_metadata_len = umem->config.tx_metadata_len;
 
 	err = setsockopt(umem->fd, SOL_XDP, XDP_UMEM_REG, &mr, sizeof(mr));
 	if (err) {
@@ -340,531 +278,181 @@ out_umem_alloc:
 	return err;
 }
 
-struct xsk_umem_config_v1 {
-	__u32 fill_size;
-	__u32 comp_size;
-	__u32 frame_size;
-	__u32 frame_headroom;
-};
-
-static enum xsk_prog get_xsk_prog(void)
+bool xsk_is_in_mode(u32 ifindex, int mode)
 {
-	enum xsk_prog detected = XSK_PROG_FALLBACK;
-	char data_in = 0, data_out;
-	struct bpf_insn insns[] = {
-		BPF_LD_MAP_FD(BPF_REG_1, 0),
-		BPF_MOV64_IMM(BPF_REG_2, 0),
-		BPF_MOV64_IMM(BPF_REG_3, XDP_PASS),
-		BPF_EMIT_CALL(BPF_FUNC_redirect_map),
-		BPF_EXIT_INSN(),
-	};
-	LIBBPF_OPTS(bpf_test_run_opts, opts,
-		.data_in = &data_in,
-		.data_size_in = 1,
-		.data_out = &data_out,
-	);
-
-	int prog_fd, map_fd, ret, insn_cnt = ARRAY_SIZE(insns);
+	LIBBPF_OPTS(bpf_xdp_query_opts, opts);
+	int ret;
 
-	map_fd = bpf_map_create(BPF_MAP_TYPE_XSKMAP, NULL, sizeof(int), sizeof(int), 1, NULL);
-	if (map_fd < 0)
-		return detected;
-
-	insns[0].imm = map_fd;
-
-	prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "GPL", insns, insn_cnt, NULL);
-	if (prog_fd < 0) {
-		close(map_fd);
-		return detected;
+	ret = bpf_xdp_query(ifindex, mode, &opts);
+	if (ret) {
+		printf("XDP mode query returned error %s\n", strerror(errno));
+		return false;
 	}
 
-	ret = bpf_prog_test_run_opts(prog_fd, &opts);
-	if (!ret && opts.retval == XDP_PASS)
-		detected = XSK_PROG_REDIRECT_FLAGS;
-	close(prog_fd);
-	close(map_fd);
-	return detected;
-}
+	if (mode == XDP_FLAGS_DRV_MODE)
+		return opts.attach_mode == XDP_ATTACHED_DRV;
+	else if (mode == XDP_FLAGS_SKB_MODE)
+		return opts.attach_mode == XDP_ATTACHED_SKB;
 
-static int xsk_load_xdp_prog(struct xsk_socket *xsk)
-{
-	static const int log_buf_size = 16 * 1024;
-	struct xsk_ctx *ctx = xsk->ctx;
-	char log_buf[log_buf_size];
-	int prog_fd;
-
-	/* This is the fallback C-program:
-	 * SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx)
-	 * {
-	 *     int ret, index = ctx->rx_queue_index;
-	 *
-	 *     // A set entry here means that the correspnding queue_id
-	 *     // has an active AF_XDP socket bound to it.
-	 *     ret = bpf_redirect_map(&xsks_map, index, XDP_PASS);
-	 *     if (ret > 0)
-	 *         return ret;
-	 *
-	 *     // Fallback for pre-5.3 kernels, not supporting default
-	 *     // action in the flags parameter.
-	 *     if (bpf_map_lookup_elem(&xsks_map, &index))
-	 *         return bpf_redirect_map(&xsks_map, index, 0);
-	 *     return XDP_PASS;
-	 * }
-	 */
-	struct bpf_insn prog[] = {
-		/* r2 = *(u32 *)(r1 + 16) */
-		BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 16),
-		/* *(u32 *)(r10 - 4) = r2 */
-		BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -4),
-		/* r1 = xskmap[] */
-		BPF_LD_MAP_FD(BPF_REG_1, ctx->xsks_map_fd),
-		/* r3 = XDP_PASS */
-		BPF_MOV64_IMM(BPF_REG_3, 2),
-		/* call bpf_redirect_map */
-		BPF_EMIT_CALL(BPF_FUNC_redirect_map),
-		/* if w0 != 0 goto pc+13 */
-		BPF_JMP32_IMM(BPF_JSGT, BPF_REG_0, 0, 13),
-		/* r2 = r10 */
-		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
-		/* r2 += -4 */
-		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
-		/* r1 = xskmap[] */
-		BPF_LD_MAP_FD(BPF_REG_1, ctx->xsks_map_fd),
-		/* call bpf_map_lookup_elem */
-		BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
-		/* r1 = r0 */
-		BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
-		/* r0 = XDP_PASS */
-		BPF_MOV64_IMM(BPF_REG_0, 2),
-		/* if r1 == 0 goto pc+5 */
-		BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 5),
-		/* r2 = *(u32 *)(r10 - 4) */
-		BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_10, -4),
-		/* r1 = xskmap[] */
-		BPF_LD_MAP_FD(BPF_REG_1, ctx->xsks_map_fd),
-		/* r3 = 0 */
-		BPF_MOV64_IMM(BPF_REG_3, 0),
-		/* call bpf_redirect_map */
-		BPF_EMIT_CALL(BPF_FUNC_redirect_map),
-		/* The jumps are to this instruction */
-		BPF_EXIT_INSN(),
-	};
-
-	/* This is the post-5.3 kernel C-program:
-	 * SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx)
-	 * {
-	 *     return bpf_redirect_map(&xsks_map, ctx->rx_queue_index, XDP_PASS);
-	 * }
-	 */
-	struct bpf_insn prog_redirect_flags[] = {
-		/* r2 = *(u32 *)(r1 + 16) */
-		BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 16),
-		/* r1 = xskmap[] */
-		BPF_LD_MAP_FD(BPF_REG_1, ctx->xsks_map_fd),
-		/* r3 = XDP_PASS */
-		BPF_MOV64_IMM(BPF_REG_3, 2),
-		/* call bpf_redirect_map */
-		BPF_EMIT_CALL(BPF_FUNC_redirect_map),
-		BPF_EXIT_INSN(),
-	};
-	size_t insns_cnt[] = {ARRAY_SIZE(prog),
-			      ARRAY_SIZE(prog_redirect_flags),
-	};
-	struct bpf_insn *progs[] = {prog, prog_redirect_flags};
-	enum xsk_prog option = get_xsk_prog();
-	LIBBPF_OPTS(bpf_prog_load_opts, opts,
-		.log_buf = log_buf,
-		.log_size = log_buf_size,
-	);
-
-	prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "LGPL-2.1 or BSD-2-Clause",
-				progs[option], insns_cnt[option], &opts);
-	if (prog_fd < 0) {
-		pr_warn("BPF log buffer:\n%s", log_buf);
-		return prog_fd;
-	}
-
-	ctx->prog_fd = prog_fd;
-	return 0;
+	return false;
 }
 
-static int xsk_create_bpf_link(struct xsk_socket *xsk)
+/* Lifted from netlink.c in tools/lib/bpf */
+static int netlink_recvmsg(int sock, struct msghdr *mhdr, int flags)
 {
-	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts);
-	struct xsk_ctx *ctx = xsk->ctx;
-	__u32 prog_id = 0;
-	int link_fd;
-	int err;
-
-	err = bpf_xdp_query_id(ctx->ifindex, xsk->config.xdp_flags, &prog_id);
-	if (err) {
-		pr_warn("getting XDP prog id failed\n");
-		return err;
-	}
-
-	/* if there's a netlink-based XDP prog loaded on interface, bail out
-	 * and ask user to do the removal by himself
-	 */
-	if (prog_id) {
-		pr_warn("Netlink-based XDP prog detected, please unload it in order to launch AF_XDP prog\n");
-		return -EINVAL;
-	}
-
-	opts.flags = xsk->config.xdp_flags & ~(XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_REPLACE);
-
-	link_fd = bpf_link_create(ctx->prog_fd, ctx->ifindex, BPF_XDP, &opts);
-	if (link_fd < 0) {
-		pr_warn("bpf_link_create failed: %s\n", strerror(errno));
-		return link_fd;
-	}
-
-	ctx->link_fd = link_fd;
-	return 0;
-}
+	int len;
 
-static int xsk_get_max_queues(struct xsk_socket *xsk)
-{
-	struct ethtool_channels channels = { .cmd = ETHTOOL_GCHANNELS };
-	struct xsk_ctx *ctx = xsk->ctx;
-	struct ifreq ifr = {};
-	int fd, err, ret;
+	do {
+		len = recvmsg(sock, mhdr, flags);
+	} while (len < 0 && (errno == EINTR || errno == EAGAIN));
 
-	fd = socket(AF_LOCAL, SOCK_DGRAM | SOCK_CLOEXEC, 0);
-	if (fd < 0)
+	if (len < 0)
 		return -errno;
-
-	ifr.ifr_data = (void *)&channels;
-	bpf_strlcpy(ifr.ifr_name, ctx->ifname, IFNAMSIZ);
-	err = ioctl(fd, SIOCETHTOOL, &ifr);
-	if (err && errno != EOPNOTSUPP) {
-		ret = -errno;
-		goto out;
-	}
-
-	if (err) {
-		/* If the device says it has no channels, then all traffic
-		 * is sent to a single stream, so max queues = 1.
-		 */
-		ret = 1;
-	} else {
-		/* Take the max of rx, tx, combined. Drivers return
-		 * the number of channels in different ways.
-		 */
-		ret = max(channels.max_rx, channels.max_tx);
-		ret = max(ret, (int)channels.max_combined);
-	}
-
-out:
-	close(fd);
-	return ret;
+	return len;
 }
 
-static int xsk_create_bpf_maps(struct xsk_socket *xsk)
+/* Lifted from netlink.c in tools/lib/bpf */
+static int alloc_iov(struct iovec *iov, int len)
 {
-	struct xsk_ctx *ctx = xsk->ctx;
-	int max_queues;
-	int fd;
-
-	max_queues = xsk_get_max_queues(xsk);
-	if (max_queues < 0)
-		return max_queues;
+	void *nbuf;
 
-	fd = bpf_map_create(BPF_MAP_TYPE_XSKMAP, "xsks_map",
-			    sizeof(int), sizeof(int), max_queues, NULL);
-	if (fd < 0)
-		return fd;
-
-	ctx->xsks_map_fd = fd;
+	nbuf = realloc(iov->iov_base, len);
+	if (!nbuf)
+		return -ENOMEM;
 
+	iov->iov_base = nbuf;
+	iov->iov_len = len;
 	return 0;
 }
 
-static void xsk_delete_bpf_maps(struct xsk_socket *xsk)
+/* Original version lifted from netlink.c in tools/lib/bpf */
+static int netlink_recv(int sock)
 {
-	struct xsk_ctx *ctx = xsk->ctx;
-
-	bpf_map_delete_elem(ctx->xsks_map_fd, &ctx->queue_id);
-	close(ctx->xsks_map_fd);
-}
-
-static int xsk_lookup_bpf_maps(struct xsk_socket *xsk)
-{
-	__u32 i, *map_ids, num_maps, prog_len = sizeof(struct bpf_prog_info);
-	__u32 map_len = sizeof(struct bpf_map_info);
-	struct bpf_prog_info prog_info = {};
-	struct xsk_ctx *ctx = xsk->ctx;
-	struct bpf_map_info map_info;
-	int fd, err;
-
-	err = bpf_obj_get_info_by_fd(ctx->prog_fd, &prog_info, &prog_len);
-	if (err)
-		return err;
-
-	num_maps = prog_info.nr_map_ids;
-
-	map_ids = calloc(prog_info.nr_map_ids, sizeof(*map_ids));
-	if (!map_ids)
-		return -ENOMEM;
-
-	memset(&prog_info, 0, prog_len);
-	prog_info.nr_map_ids = num_maps;
-	prog_info.map_ids = (__u64)(unsigned long)map_ids;
-
-	err = bpf_obj_get_info_by_fd(ctx->prog_fd, &prog_info, &prog_len);
-	if (err)
-		goto out_map_ids;
-
-	ctx->xsks_map_fd = -1;
-
-	for (i = 0; i < prog_info.nr_map_ids; i++) {
-		fd = bpf_map_get_fd_by_id(map_ids[i]);
-		if (fd < 0)
-			continue;
-
-		memset(&map_info, 0, map_len);
-		err = bpf_obj_get_info_by_fd(fd, &map_info, &map_len);
-		if (err) {
-			close(fd);
-			continue;
+	struct iovec iov = {};
+	struct msghdr mhdr = {
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+	};
+	bool multipart = true;
+	struct nlmsgerr *err;
+	struct nlmsghdr *nh;
+	int len, ret;
+
+	ret = alloc_iov(&iov, 4096);
+	if (ret)
+		goto done;
+
+	while (multipart) {
+		multipart = false;
+		len = netlink_recvmsg(sock, &mhdr, MSG_PEEK | MSG_TRUNC);
+		if (len < 0) {
+			ret = len;
+			goto done;
 		}
 
-		if (!strncmp(map_info.name, "xsks_map", sizeof(map_info.name))) {
-			ctx->xsks_map_fd = fd;
-			break;
+		if (len > iov.iov_len) {
+			ret = alloc_iov(&iov, len);
+			if (ret)
+				goto done;
 		}
 
-		close(fd);
-	}
-
-	if (ctx->xsks_map_fd == -1)
-		err = -ENOENT;
-
-out_map_ids:
-	free(map_ids);
-	return err;
-}
-
-static int xsk_set_bpf_maps(struct xsk_socket *xsk)
-{
-	struct xsk_ctx *ctx = xsk->ctx;
-
-	return bpf_map_update_elem(ctx->xsks_map_fd, &ctx->queue_id,
-				   &xsk->fd, 0);
-}
-
-static int xsk_link_lookup(int ifindex, __u32 *prog_id, int *link_fd)
-{
-	struct bpf_link_info link_info;
-	__u32 link_len;
-	__u32 id = 0;
-	int err;
-	int fd;
-
-	while (true) {
-		err = bpf_link_get_next_id(id, &id);
-		if (err) {
-			if (errno == ENOENT) {
-				err = 0;
-				break;
-			}
-			pr_warn("can't get next link: %s\n", strerror(errno));
-			break;
+		len = netlink_recvmsg(sock, &mhdr, 0);
+		if (len < 0) {
+			ret = len;
+			goto done;
 		}
 
-		fd = bpf_link_get_fd_by_id(id);
-		if (fd < 0) {
-			if (errno == ENOENT)
-				continue;
-			pr_warn("can't get link by id (%u): %s\n", id, strerror(errno));
-			err = -errno;
+		if (len == 0)
 			break;
-		}
 
-		link_len = sizeof(struct bpf_link_info);
-		memset(&link_info, 0, link_len);
-		err = bpf_obj_get_info_by_fd(fd, &link_info, &link_len);
-		if (err) {
-			pr_warn("can't get link info: %s\n", strerror(errno));
-			close(fd);
-			break;
-		}
-		if (link_info.type == BPF_LINK_TYPE_XDP) {
-			if (link_info.xdp.ifindex == ifindex) {
-				*link_fd = fd;
-				if (prog_id)
-					*prog_id = link_info.prog_id;
+		for (nh = (struct nlmsghdr *)iov.iov_base; NLMSG_OK(nh, len);
+		     nh = NLMSG_NEXT(nh, len)) {
+			if (nh->nlmsg_flags & NLM_F_MULTI)
+				multipart = true;
+			switch (nh->nlmsg_type) {
+			case NLMSG_ERROR:
+				err = (struct nlmsgerr *)NLMSG_DATA(nh);
+				if (!err->error)
+					continue;
+				ret = err->error;
+				goto done;
+			case NLMSG_DONE:
+				ret = 0;
+				goto done;
+			default:
 				break;
 			}
 		}
-		close(fd);
 	}
-
-	return err;
+	ret = 0;
+done:
+	free(iov.iov_base);
+	return ret;
 }
 
-static bool xsk_probe_bpf_link(void)
+int xsk_set_mtu(int ifindex, int mtu)
 {
-	LIBBPF_OPTS(bpf_link_create_opts, opts, .flags = XDP_FLAGS_SKB_MODE);
-	struct bpf_insn insns[2] = {
-		BPF_MOV64_IMM(BPF_REG_0, XDP_PASS),
-		BPF_EXIT_INSN()
-	};
-	int prog_fd, link_fd = -1, insn_cnt = ARRAY_SIZE(insns);
-	int ifindex_lo = 1;
-	bool ret = false;
-	int err;
-
-	err = xsk_link_lookup(ifindex_lo, NULL, &link_fd);
-	if (err)
-		return ret;
-
-	if (link_fd >= 0)
-		return true;
+	struct nl_mtu_req req;
+	struct rtattr *rta;
+	int fd, ret;
 
-	prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "GPL", insns, insn_cnt, NULL);
-	if (prog_fd < 0)
-		return ret;
-
-	link_fd = bpf_link_create(prog_fd, ifindex_lo, BPF_XDP, &opts);
-	close(prog_fd);
+	fd = socket(AF_NETLINK, SOCK_DGRAM, NETLINK_ROUTE);
+	if (fd < 0)
+		return fd;
 
-	if (link_fd >= 0) {
-		ret = true;
-		close(link_fd);
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_type = RTM_NEWLINK;
+	req.msg.ifi_family = AF_UNSPEC;
+	req.msg.ifi_index = ifindex;
+	rta = (struct rtattr *)(((char *)&req) + NLMSG_ALIGN(req.nh.nlmsg_len));
+	rta->rta_type = IFLA_MTU;
+	rta->rta_len = RTA_LENGTH(sizeof(unsigned int));
+	req.nh.nlmsg_len = NLMSG_ALIGN(req.nh.nlmsg_len) + RTA_LENGTH(sizeof(mtu));
+	memcpy(RTA_DATA(rta), &mtu, sizeof(mtu));
+
+	ret = send(fd, &req, req.nh.nlmsg_len, 0);
+	if (ret < 0) {
+		close(fd);
+		return errno;
 	}
 
+	ret = netlink_recv(fd);
+	close(fd);
 	return ret;
 }
 
-static int xsk_create_xsk_struct(int ifindex, struct xsk_socket *xsk)
+int xsk_attach_xdp_program(struct bpf_program *prog, int ifindex, u32 xdp_flags)
 {
-	char ifname[IFNAMSIZ];
-	struct xsk_ctx *ctx;
-	char *interface;
-
-	ctx = calloc(1, sizeof(*ctx));
-	if (!ctx)
-		return -ENOMEM;
-
-	interface = if_indextoname(ifindex, &ifname[0]);
-	if (!interface) {
-		free(ctx);
-		return -errno;
-	}
-
-	ctx->ifindex = ifindex;
-	bpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ);
-
-	xsk->ctx = ctx;
-	xsk->ctx->has_bpf_link = xsk_probe_bpf_link();
+	int prog_fd;
 
-	return 0;
+	prog_fd = bpf_program__fd(prog);
+	return bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL);
 }
 
-static int xsk_init_xdp_res(struct xsk_socket *xsk,
-			    int *xsks_map_fd)
+void xsk_detach_xdp_program(int ifindex, u32 xdp_flags)
 {
-	struct xsk_ctx *ctx = xsk->ctx;
-	int err;
-
-	err = xsk_create_bpf_maps(xsk);
-	if (err)
-		return err;
-
-	err = xsk_load_xdp_prog(xsk);
-	if (err)
-		goto err_load_xdp_prog;
-
-	if (ctx->has_bpf_link)
-		err = xsk_create_bpf_link(xsk);
-	else
-		err = bpf_xdp_attach(xsk->ctx->ifindex, ctx->prog_fd,
-				     xsk->config.xdp_flags, NULL);
-
-	if (err)
-		goto err_attach_xdp_prog;
-
-	if (!xsk->rx)
-		return err;
-
-	err = xsk_set_bpf_maps(xsk);
-	if (err)
-		goto err_set_bpf_maps;
-
-	return err;
-
-err_set_bpf_maps:
-	if (ctx->has_bpf_link)
-		close(ctx->link_fd);
-	else
-		bpf_xdp_detach(ctx->ifindex, 0, NULL);
-err_attach_xdp_prog:
-	close(ctx->prog_fd);
-err_load_xdp_prog:
-	xsk_delete_bpf_maps(xsk);
-	return err;
+	bpf_xdp_detach(ifindex, xdp_flags, NULL);
 }
 
-static int xsk_lookup_xdp_res(struct xsk_socket *xsk, int *xsks_map_fd, int prog_id)
+void xsk_clear_xskmap(struct bpf_map *map)
 {
-	struct xsk_ctx *ctx = xsk->ctx;
-	int err;
-
-	ctx->prog_fd = bpf_prog_get_fd_by_id(prog_id);
-	if (ctx->prog_fd < 0) {
-		err = -errno;
-		goto err_prog_fd;
-	}
-	err = xsk_lookup_bpf_maps(xsk);
-	if (err)
-		goto err_lookup_maps;
-
-	if (!xsk->rx)
-		return err;
-
-	err = xsk_set_bpf_maps(xsk);
-	if (err)
-		goto err_set_maps;
+	u32 index = 0;
+	int map_fd;
 
-	return err;
-
-err_set_maps:
-	close(ctx->xsks_map_fd);
-err_lookup_maps:
-	close(ctx->prog_fd);
-err_prog_fd:
-	if (ctx->has_bpf_link)
-		close(ctx->link_fd);
-	return err;
+	map_fd = bpf_map__fd(map);
+	bpf_map_delete_elem(map_fd, &index);
 }
 
-static int __xsk_setup_xdp_prog(struct xsk_socket *_xdp, int *xsks_map_fd)
+int xsk_update_xskmap(struct bpf_map *map, struct xsk_socket *xsk, u32 index)
 {
-	struct xsk_socket *xsk = _xdp;
-	struct xsk_ctx *ctx = xsk->ctx;
-	__u32 prog_id = 0;
-	int err;
+	int map_fd, sock_fd;
 
-	if (ctx->has_bpf_link)
-		err = xsk_link_lookup(ctx->ifindex, &prog_id, &ctx->link_fd);
-	else
-		err = bpf_xdp_query_id(ctx->ifindex, xsk->config.xdp_flags, &prog_id);
+	map_fd = bpf_map__fd(map);
+	sock_fd = xsk_socket__fd(xsk);
 
-	if (err)
-		return err;
-
-	err = !prog_id ? xsk_init_xdp_res(xsk, xsks_map_fd) :
-			 xsk_lookup_xdp_res(xsk, xsks_map_fd, prog_id);
-
-	if (!err && xsks_map_fd)
-		*xsks_map_fd = ctx->xsks_map_fd;
-
-	return err;
-}
-
-int xsk_setup_xdp_prog_xsk(struct xsk_socket *xsk, int *xsks_map_fd)
-{
-	return __xsk_setup_xdp_prog(xsk, xsks_map_fd);
+	return bpf_map_update_elem(map_fd, &index, &sock_fd, 0);
 }
 
 static struct xsk_ctx *xsk_get_ctx(struct xsk_umem *umem, int ifindex,
@@ -913,7 +501,7 @@ out_free:
 
 static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk,
 				      struct xsk_umem *umem, int ifindex,
-				      const char *ifname, __u32 queue_id,
+				      __u32 queue_id,
 				      struct xsk_ring_prod *fill,
 				      struct xsk_ring_cons *comp)
 {
@@ -940,51 +528,15 @@ static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk,
 	ctx->refcount = 1;
 	ctx->umem = umem;
 	ctx->queue_id = queue_id;
-	bpf_strlcpy(ctx->ifname, ifname, IFNAMSIZ);
 
 	ctx->fill = fill;
 	ctx->comp = comp;
 	list_add(&ctx->list, &umem->ctx_list);
-	ctx->has_bpf_link = xsk_probe_bpf_link();
 	return ctx;
 }
 
-static void xsk_destroy_xsk_struct(struct xsk_socket *xsk)
-{
-	free(xsk->ctx);
-	free(xsk);
-}
-
-int xsk_socket__update_xskmap(struct xsk_socket *xsk, int fd)
-{
-	xsk->ctx->xsks_map_fd = fd;
-	return xsk_set_bpf_maps(xsk);
-}
-
-int xsk_setup_xdp_prog(int ifindex, int *xsks_map_fd)
-{
-	struct xsk_socket *xsk;
-	int res;
-
-	xsk = calloc(1, sizeof(*xsk));
-	if (!xsk)
-		return -ENOMEM;
-
-	res = xsk_create_xsk_struct(ifindex, xsk);
-	if (res) {
-		free(xsk);
-		return -EINVAL;
-	}
-
-	res = __xsk_setup_xdp_prog(xsk, xsks_map_fd);
-
-	xsk_destroy_xsk_struct(xsk);
-
-	return res;
-}
-
 int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
-			      const char *ifname,
+			      int ifindex,
 			      __u32 queue_id, struct xsk_umem *umem,
 			      struct xsk_ring_cons *rx,
 			      struct xsk_ring_prod *tx,
@@ -998,7 +550,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 	struct xdp_mmap_offsets off;
 	struct xsk_socket *xsk;
 	struct xsk_ctx *ctx;
-	int err, ifindex;
+	int err;
 
 	if (!umem || !xsk_ptr || !(rx || tx))
 		return -EFAULT;
@@ -1013,13 +565,6 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 	if (err)
 		goto out_xsk_alloc;
 
-	xsk->outstanding_tx = 0;
-	ifindex = if_nametoindex(ifname);
-	if (!ifindex) {
-		err = -errno;
-		goto out_xsk_alloc;
-	}
-
 	if (umem->refcount++ > 0) {
 		xsk->fd = socket(AF_XDP, SOCK_RAW | SOCK_CLOEXEC, 0);
 		if (xsk->fd < 0) {
@@ -1039,8 +584,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 			goto out_socket;
 		}
 
-		ctx = xsk_create_ctx(xsk, umem, ifindex, ifname, queue_id,
-				     fill, comp);
+		ctx = xsk_create_ctx(xsk, umem, ifindex, queue_id, fill, comp);
 		if (!ctx) {
 			err = -ENOMEM;
 			goto out_socket;
@@ -1138,12 +682,6 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 		goto out_mmap_tx;
 	}
 
-	if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) {
-		err = __xsk_setup_xdp_prog(xsk, NULL);
-		if (err)
-			goto out_mmap_tx;
-	}
-
 	*xsk_ptr = xsk;
 	umem->fill_save = NULL;
 	umem->comp_save = NULL;
@@ -1167,7 +705,7 @@ out_xsk_alloc:
 	return err;
 }
 
-int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
+int xsk_socket__create(struct xsk_socket **xsk_ptr, int ifindex,
 		       __u32 queue_id, struct xsk_umem *umem,
 		       struct xsk_ring_cons *rx, struct xsk_ring_prod *tx,
 		       const struct xsk_socket_config *usr_config)
@@ -1175,7 +713,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 	if (!umem)
 		return -EFAULT;
 
-	return xsk_socket__create_shared(xsk_ptr, ifname, queue_id, umem,
+	return xsk_socket__create_shared(xsk_ptr, ifindex, queue_id, umem,
 					 rx, tx, umem->fill_save,
 					 umem->comp_save, usr_config);
 }
@@ -1219,13 +757,6 @@ void xsk_socket__delete(struct xsk_socket *xsk)
 	ctx = xsk->ctx;
 	umem = ctx->umem;
 
-	if (ctx->refcount == 1) {
-		xsk_delete_bpf_maps(xsk);
-		close(ctx->prog_fd);
-		if (ctx->has_bpf_link)
-			close(ctx->link_fd);
-	}
-
 	xsk_put_ctx(ctx, true);
 
 	err = xsk_get_mmap_offsets(xsk->fd, &off);
diff --git a/tools/testing/selftests/bpf/xsk.h b/tools/testing/selftests/bpf/xsk.h
index 997723b0bfb2..48729da142c2 100644
--- a/tools/testing/selftests/bpf/xsk.h
+++ b/tools/testing/selftests/bpf/xsk.h
@@ -23,77 +23,6 @@
 extern "C" {
 #endif
 
-/* This whole API has been deprecated and moved to libxdp that can be found at
- * https://github.com/xdp-project/xdp-tools. The APIs are exactly the same so
- * it should just be linking with libxdp instead of libbpf for this set of
- * functionality. If not, please submit a bug report on the aforementioned page.
- */
-
-/* Load-Acquire Store-Release barriers used by the XDP socket
- * library. The following macros should *NOT* be considered part of
- * the xsk.h API, and is subject to change anytime.
- *
- * LIBRARY INTERNAL
- */
-
-#define __XSK_READ_ONCE(x) (*(volatile typeof(x) *)&x)
-#define __XSK_WRITE_ONCE(x, v) (*(volatile typeof(x) *)&x) = (v)
-
-#if defined(__i386__) || defined(__x86_64__)
-# define libbpf_smp_store_release(p, v)					\
-	do {								\
-		asm volatile("" : : : "memory");			\
-		__XSK_WRITE_ONCE(*p, v);				\
-	} while (0)
-# define libbpf_smp_load_acquire(p)					\
-	({								\
-		typeof(*p) ___p1 = __XSK_READ_ONCE(*p);			\
-		asm volatile("" : : : "memory");			\
-		___p1;							\
-	})
-#elif defined(__aarch64__)
-# define libbpf_smp_store_release(p, v)					\
-		asm volatile ("stlr %w1, %0" : "=Q" (*p) : "r" (v) : "memory")
-# define libbpf_smp_load_acquire(p)					\
-	({								\
-		typeof(*p) ___p1;					\
-		asm volatile ("ldar %w0, %1"				\
-			      : "=r" (___p1) : "Q" (*p) : "memory");	\
-		___p1;							\
-	})
-#elif defined(__riscv)
-# define libbpf_smp_store_release(p, v)					\
-	do {								\
-		asm volatile ("fence rw,w" : : : "memory");		\
-		__XSK_WRITE_ONCE(*p, v);				\
-	} while (0)
-# define libbpf_smp_load_acquire(p)					\
-	({								\
-		typeof(*p) ___p1 = __XSK_READ_ONCE(*p);			\
-		asm volatile ("fence r,rw" : : : "memory");		\
-		___p1;							\
-	})
-#endif
-
-#ifndef libbpf_smp_store_release
-#define libbpf_smp_store_release(p, v)					\
-	do {								\
-		__sync_synchronize();					\
-		__XSK_WRITE_ONCE(*p, v);				\
-	} while (0)
-#endif
-
-#ifndef libbpf_smp_load_acquire
-#define libbpf_smp_load_acquire(p)					\
-	({								\
-		typeof(*p) ___p1 = __XSK_READ_ONCE(*p);			\
-		__sync_synchronize();					\
-		___p1;							\
-	})
-#endif
-
-/* LIBRARY INTERNAL -- END */
-
 /* Do not access these members directly. Use the functions below. */
 #define DEFINE_XSK_RING(name) \
 struct name { \
@@ -164,11 +93,11 @@ static inline __u32 xsk_prod_nb_free(struct xsk_ring_prod *r, __u32 nb)
 	/* Refresh the local tail pointer.
 	 * cached_cons is r->size bigger than the real consumer pointer so
 	 * that this addition can be avoided in the more frequently
-	 * executed code that computs free_entries in the beginning of
-	 * this function. Without this optimization it whould have been
+	 * executed code that computes free_entries in the beginning of
+	 * this function. Without this optimization it would have been
 	 * free_entries = r->cached_prod - r->cached_cons + r->size.
 	 */
-	r->cached_cons = libbpf_smp_load_acquire(r->consumer);
+	r->cached_cons = __atomic_load_n(r->consumer, __ATOMIC_ACQUIRE);
 	r->cached_cons += r->size;
 
 	return r->cached_cons - r->cached_prod;
@@ -179,7 +108,7 @@ static inline __u32 xsk_cons_nb_avail(struct xsk_ring_cons *r, __u32 nb)
 	__u32 entries = r->cached_prod - r->cached_cons;
 
 	if (entries == 0) {
-		r->cached_prod = libbpf_smp_load_acquire(r->producer);
+		r->cached_prod = __atomic_load_n(r->producer, __ATOMIC_ACQUIRE);
 		entries = r->cached_prod - r->cached_cons;
 	}
 
@@ -202,7 +131,12 @@ static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, __u32 nb)
 	/* Make sure everything has been written to the ring before indicating
 	 * this to the kernel by writing the producer pointer.
 	 */
-	libbpf_smp_store_release(prod->producer, *prod->producer + nb);
+	__atomic_store_n(prod->producer, *prod->producer + nb, __ATOMIC_RELEASE);
+}
+
+static inline void xsk_ring_prod__cancel(struct xsk_ring_prod *prod, __u32 nb)
+{
+	prod->cached_prod -= nb;
 }
 
 static inline __u32 xsk_ring_cons__peek(struct xsk_ring_cons *cons, __u32 nb, __u32 *idx)
@@ -227,8 +161,7 @@ static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, __u32 nb)
 	/* Make sure data has been read before indicating we are done
 	 * with the entries by updating the consumer pointer.
 	 */
-	libbpf_smp_store_release(cons->consumer, *cons->consumer + nb);
-
+	__atomic_store_n(cons->consumer, *cons->consumer + nb, __ATOMIC_RELEASE);
 }
 
 static inline void *xsk_umem__get_data(void *umem_area, __u64 addr)
@@ -267,20 +200,18 @@ struct xsk_umem_config {
 	__u32 frame_size;
 	__u32 frame_headroom;
 	__u32 flags;
+	__u32 tx_metadata_len;
 };
 
-int xsk_setup_xdp_prog_xsk(struct xsk_socket *xsk, int *xsks_map_fd);
-int xsk_setup_xdp_prog(int ifindex, int *xsks_map_fd);
-int xsk_socket__update_xskmap(struct xsk_socket *xsk, int xsks_map_fd);
-
-/* Flags for the libbpf_flags field. */
-#define XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD (1 << 0)
+int xsk_attach_xdp_program(struct bpf_program *prog, int ifindex, u32 xdp_flags);
+void xsk_detach_xdp_program(int ifindex, u32 xdp_flags);
+int xsk_update_xskmap(struct bpf_map *map, struct xsk_socket *xsk, u32 index);
+void xsk_clear_xskmap(struct bpf_map *map);
+bool xsk_is_in_mode(u32 ifindex, int mode);
 
 struct xsk_socket_config {
 	__u32 rx_size;
 	__u32 tx_size;
-	__u32 libbpf_flags;
-	__u32 xdp_flags;
 	__u16 bind_flags;
 };
 
@@ -291,13 +222,13 @@ int xsk_umem__create(struct xsk_umem **umem,
 		     struct xsk_ring_cons *comp,
 		     const struct xsk_umem_config *config);
 int xsk_socket__create(struct xsk_socket **xsk,
-		       const char *ifname, __u32 queue_id,
+		       int ifindex, __u32 queue_id,
 		       struct xsk_umem *umem,
 		       struct xsk_ring_cons *rx,
 		       struct xsk_ring_prod *tx,
 		       const struct xsk_socket_config *config);
 int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
-			      const char *ifname,
+			      int ifindex,
 			      __u32 queue_id, struct xsk_umem *umem,
 			      struct xsk_ring_cons *rx,
 			      struct xsk_ring_prod *tx,
@@ -309,6 +240,8 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 int xsk_umem__delete(struct xsk_umem *umem);
 void xsk_socket__delete(struct xsk_socket *xsk);
 
+int xsk_set_mtu(int ifindex, int mtu);
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif
diff --git a/tools/testing/selftests/bpf/xsk_prereqs.sh b/tools/testing/selftests/bpf/xsk_prereqs.sh
index a0b71723a818..47c7b8064f38 100755
--- a/tools/testing/selftests/bpf/xsk_prereqs.sh
+++ b/tools/testing/selftests/bpf/xsk_prereqs.sh
@@ -53,23 +53,22 @@ test_exit()
 	exit 1
 }
 
+cleanup_iface()
+{
+	ip link set $1 mtu $2
+	ip link set $1 xdp off
+	ip link set $1 xdpgeneric off
+}
+
 clear_configs()
 {
-	if [ $(ip netns show | grep $3 &>/dev/null; echo $?;) == 0 ]; then
-		[ $(ip netns exec $3 ip link show $2 &>/dev/null; echo $?;) == 0 ] &&
-			{ ip netns exec $3 ip link del $2; }
-		ip netns del $3
-	fi
-	#Once we delete a veth pair node, the entire veth pair is removed,
-	#this is just to be cautious just incase the NS does not exist then
-	#veth node inside NS won't get removed so we explicitly remove it
 	[ $(ip link show $1 &>/dev/null; echo $?;) == 0 ] &&
 		{ ip link del $1; }
 }
 
 cleanup_exit()
 {
-	clear_configs $1 $2 $3
+	clear_configs $1 $2
 }
 
 validate_ip_utility()
@@ -83,10 +82,12 @@ exec_xskxceiver()
 	        ARGS+="-b "
 	fi
 
-	./${XSKOBJ} -i ${VETH0} -i ${VETH1},${NS1} ${ARGS}
-
+	./${XSKOBJ} -i ${VETH0} -i ${VETH1} ${ARGS}
 	retval=$?
-	test_status $retval "${TEST_NAME}"
-	statusList+=($retval)
-	nameList+=(${TEST_NAME})
+
+	if [[ $list -ne 1 ]]; then
+	    test_status $retval "${TEST_NAME}"
+	    statusList+=($retval)
+	    nameList+=(${TEST_NAME})
+	fi
 }
diff --git a/tools/testing/selftests/bpf/xsk_xdp_common.h b/tools/testing/selftests/bpf/xsk_xdp_common.h
new file mode 100644
index 000000000000..45810ff552da
--- /dev/null
+++ b/tools/testing/selftests/bpf/xsk_xdp_common.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef XSK_XDP_COMMON_H_
+#define XSK_XDP_COMMON_H_
+
+#define MAX_SOCKETS 2
+#define PKT_HDR_ALIGN (sizeof(struct ethhdr) + 2) /* Just to align the data in the packet */
+
+struct xdp_info {
+	__u64 count;
+} __attribute__((aligned(32)));
+
+#endif /* XSK_XDP_COMMON_H_ */
diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c
index 162d3a516f2c..05b3cebc5ca9 100644
--- a/tools/testing/selftests/bpf/xskxceiver.c
+++ b/tools/testing/selftests/bpf/xskxceiver.c
@@ -49,18 +49,20 @@
  *    h. tests for invalid and corner case Tx descriptors so that the correct ones
  *       are discarded and let through, respectively.
  *    i. 2K frame size tests
- *
- * Total tests: 12
+ *    j. If multi-buffer is supported, send 9k packets divided into 3 frames
+ *    k. If multi-buffer and huge pages are supported, send 9k packets in a single frame
+ *       using unaligned mode
+ *    l. If multi-buffer is supported, try various nasty combinations of descriptors to
+ *       check if they pass the validation or not
  *
  * Flow:
  * -----
  * - Single process spawns two threads: Tx and Rx
- * - Each of these two threads attach to a veth interface within their assigned
- *   namespaces
- * - Each thread Creates one AF_XDP socket connected to a unique umem for each
+ * - Each of these two threads attach to a veth interface
+ * - Each thread creates one AF_XDP socket connected to a unique umem for each
  *   veth interface
- * - Tx thread Transmits 10k packets from veth<xxxx> to veth<yyyy>
- * - Rx thread verifies if all 10k packets were received and delivered in-order,
+ * - Tx thread Transmits a number of packets from veth<xxxx> to veth<yyyy>
+ * - Rx thread verifies if all packets were received and delivered in-order,
  *   and have the right content
  *
  * Enable/disable packet dump mode:
@@ -70,268 +72,49 @@
  */
 
 #define _GNU_SOURCE
+#include <assert.h>
 #include <fcntl.h>
-#include <errno.h>
 #include <getopt.h>
-#include <asm/barrier.h>
 #include <linux/if_link.h>
 #include <linux/if_ether.h>
-#include <linux/ip.h>
-#include <linux/udp.h>
+#include <linux/mman.h>
+#include <linux/netdev.h>
+#include <linux/ethtool.h>
 #include <arpa/inet.h>
 #include <net/if.h>
 #include <locale.h>
-#include <poll.h>
-#include <pthread.h>
-#include <signal.h>
-#include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
-#include <string.h>
+#include <libgen.h>
 #include <stddef.h>
 #include <sys/mman.h>
-#include <sys/socket.h>
-#include <sys/time.h>
 #include <sys/types.h>
-#include <sys/queue.h>
-#include <time.h>
-#include <unistd.h>
-#include <stdatomic.h>
+
+#include "prog_tests/test_xsk.h"
+#include "xsk_xdp_progs.skel.h"
 #include "xsk.h"
 #include "xskxceiver.h"
 #include <bpf/bpf.h>
 #include <linux/filter.h>
-#include "../kselftest.h"
+#include "kselftest.h"
+#include "xsk_xdp_common.h"
 
-/* AF_XDP APIs were moved into libxdp and marked as deprecated in libbpf.
- * Until xskxceiver is either moved or re-writed into libxdp, suppress
- * deprecation warnings in this file
- */
-#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
+#include <network_helpers.h>
 
-static const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62";
-static const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61";
-static const char *IP1 = "192.168.100.162";
-static const char *IP2 = "192.168.100.161";
-static const u16 UDP_PORT1 = 2020;
-static const u16 UDP_PORT2 = 2121;
+static bool opt_print_tests;
+static enum test_mode opt_mode = TEST_MODE_ALL;
+static u32 opt_run_test = RUN_ALL_TESTS;
+
+void test__fail(void) { /* for network_helpers.c */ }
 
 static void __exit_with_error(int error, const char *file, const char *func, int line)
 {
-	ksft_test_result_fail("[%s:%s:%i]: ERROR: %d/\"%s\"\n", file, func, line, error,
-			      strerror(error));
+	ksft_test_result_fail("[%s:%s:%i]: ERROR: %d/\"%s\"\n", file, func, line,
+			      error, strerror(error));
 	ksft_exit_xfail();
 }
 
 #define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, __LINE__)
-#define busy_poll_string(test) (test)->ifobj_tx->busy_poll ? "BUSY-POLL " : ""
-static char *mode_string(struct test_spec *test)
-{
-	switch (test->mode) {
-	case TEST_MODE_SKB:
-		return "SKB";
-	case TEST_MODE_DRV:
-		return "DRV";
-	case TEST_MODE_ZC:
-		return "ZC";
-	default:
-		return "BOGUS";
-	}
-}
-
-static void report_failure(struct test_spec *test)
-{
-	if (test->fail)
-		return;
-
-	ksft_test_result_fail("FAIL: %s %s%s\n", mode_string(test), busy_poll_string(test),
-			      test->name);
-	test->fail = true;
-}
-
-static void memset32_htonl(void *dest, u32 val, u32 size)
-{
-	u32 *ptr = (u32 *)dest;
-	int i;
-
-	val = htonl(val);
-
-	for (i = 0; i < (size & (~0x3)); i += 4)
-		ptr[i >> 2] = val;
-}
-
-/*
- * Fold a partial checksum
- * This function code has been taken from
- * Linux kernel include/asm-generic/checksum.h
- */
-static __u16 csum_fold(__u32 csum)
-{
-	u32 sum = (__force u32)csum;
-
-	sum = (sum & 0xffff) + (sum >> 16);
-	sum = (sum & 0xffff) + (sum >> 16);
-	return (__force __u16)~sum;
-}
-
-/*
- * This function code has been taken from
- * Linux kernel lib/checksum.c
- */
-static u32 from64to32(u64 x)
-{
-	/* add up 32-bit and 32-bit for 32+c bit */
-	x = (x & 0xffffffff) + (x >> 32);
-	/* add up carry.. */
-	x = (x & 0xffffffff) + (x >> 32);
-	return (u32)x;
-}
-
-/*
- * This function code has been taken from
- * Linux kernel lib/checksum.c
- */
-static __u32 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum)
-{
-	unsigned long long s = (__force u32)sum;
-
-	s += (__force u32)saddr;
-	s += (__force u32)daddr;
-#ifdef __BIG_ENDIAN__
-	s += proto + len;
-#else
-	s += (proto + len) << 8;
-#endif
-	return (__force __u32)from64to32(s);
-}
-
-/*
- * This function has been taken from
- * Linux kernel include/asm-generic/checksum.h
- */
-static __u16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum)
-{
-	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
-}
-
-static u16 udp_csum(u32 saddr, u32 daddr, u32 len, u8 proto, u16 *udp_pkt)
-{
-	u32 csum = 0;
-	u32 cnt = 0;
-
-	/* udp hdr and data */
-	for (; cnt < len; cnt += 2)
-		csum += udp_pkt[cnt >> 1];
-
-	return csum_tcpudp_magic(saddr, daddr, len, proto, csum);
-}
-
-static void gen_eth_hdr(struct ifobject *ifobject, struct ethhdr *eth_hdr)
-{
-	memcpy(eth_hdr->h_dest, ifobject->dst_mac, ETH_ALEN);
-	memcpy(eth_hdr->h_source, ifobject->src_mac, ETH_ALEN);
-	eth_hdr->h_proto = htons(ETH_P_IP);
-}
-
-static void gen_ip_hdr(struct ifobject *ifobject, struct iphdr *ip_hdr)
-{
-	ip_hdr->version = IP_PKT_VER;
-	ip_hdr->ihl = 0x5;
-	ip_hdr->tos = IP_PKT_TOS;
-	ip_hdr->tot_len = htons(IP_PKT_SIZE);
-	ip_hdr->id = 0;
-	ip_hdr->frag_off = 0;
-	ip_hdr->ttl = IPDEFTTL;
-	ip_hdr->protocol = IPPROTO_UDP;
-	ip_hdr->saddr = ifobject->src_ip;
-	ip_hdr->daddr = ifobject->dst_ip;
-	ip_hdr->check = 0;
-}
-
-static void gen_udp_hdr(u32 payload, void *pkt, struct ifobject *ifobject,
-			struct udphdr *udp_hdr)
-{
-	udp_hdr->source = htons(ifobject->src_port);
-	udp_hdr->dest = htons(ifobject->dst_port);
-	udp_hdr->len = htons(UDP_PKT_SIZE);
-	memset32_htonl(pkt + PKT_HDR_SIZE, payload, UDP_PKT_DATA_SIZE);
-}
-
-static bool is_umem_valid(struct ifobject *ifobj)
-{
-	return !!ifobj->umem->umem;
-}
-
-static void gen_udp_csum(struct udphdr *udp_hdr, struct iphdr *ip_hdr)
-{
-	udp_hdr->check = 0;
-	udp_hdr->check =
-	    udp_csum(ip_hdr->saddr, ip_hdr->daddr, UDP_PKT_SIZE, IPPROTO_UDP, (u16 *)udp_hdr);
-}
-
-static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size)
-{
-	struct xsk_umem_config cfg = {
-		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
-		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
-		.frame_size = umem->frame_size,
-		.frame_headroom = umem->frame_headroom,
-		.flags = XSK_UMEM__DEFAULT_FLAGS
-	};
-	int ret;
-
-	if (umem->unaligned_mode)
-		cfg.flags |= XDP_UMEM_UNALIGNED_CHUNK_FLAG;
-
-	ret = xsk_umem__create(&umem->umem, buffer, size,
-			       &umem->fq, &umem->cq, &cfg);
-	if (ret)
-		return ret;
-
-	umem->buffer = buffer;
-	return 0;
-}
-
-static void enable_busy_poll(struct xsk_socket_info *xsk)
-{
-	int sock_opt;
-
-	sock_opt = 1;
-	if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_PREFER_BUSY_POLL,
-		       (void *)&sock_opt, sizeof(sock_opt)) < 0)
-		exit_with_error(errno);
-
-	sock_opt = 20;
-	if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_BUSY_POLL,
-		       (void *)&sock_opt, sizeof(sock_opt)) < 0)
-		exit_with_error(errno);
-
-	sock_opt = BATCH_SIZE;
-	if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_BUSY_POLL_BUDGET,
-		       (void *)&sock_opt, sizeof(sock_opt)) < 0)
-		exit_with_error(errno);
-}
-
-static int __xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem,
-				  struct ifobject *ifobject, bool shared)
-{
-	struct xsk_socket_config cfg = {};
-	struct xsk_ring_cons *rxr;
-	struct xsk_ring_prod *txr;
-
-	xsk->umem = umem;
-	cfg.rx_size = xsk->rxqsize;
-	cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
-	cfg.libbpf_flags = XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD;
-	cfg.xdp_flags = ifobject->xdp_flags;
-	cfg.bind_flags = ifobject->bind_flags;
-	if (shared)
-		cfg.bind_flags |= XDP_SHARED_UMEM;
-
-	txr = ifobject->tx_on ? &xsk->tx : NULL;
-	rxr = ifobject->rx_on ? &xsk->rx : NULL;
-	return xsk_socket__create(&xsk->xsk, ifobject->ifname, 0, umem->umem, rxr, txr, &cfg);
-}
 
 static bool ifobj_zc_avail(struct ifobject *ifobject)
 {
@@ -350,22 +133,20 @@ static bool ifobj_zc_avail(struct ifobject *ifobject)
 	umem = calloc(1, sizeof(struct xsk_umem_info));
 	if (!umem) {
 		munmap(bufs, umem_sz);
-		exit_with_error(-ENOMEM);
+		exit_with_error(ENOMEM);
 	}
 	umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
-	ret = xsk_configure_umem(umem, bufs, umem_sz);
+	ret = xsk_configure_umem(ifobject, umem, bufs, umem_sz);
 	if (ret)
 		exit_with_error(-ret);
 
 	xsk = calloc(1, sizeof(struct xsk_socket_info));
 	if (!xsk)
 		goto out;
-	ifobject->xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
-	ifobject->xdp_flags |= XDP_FLAGS_DRV_MODE;
 	ifobject->bind_flags = XDP_USE_NEED_WAKEUP | XDP_ZEROCOPY;
 	ifobject->rx_on = true;
 	xsk->rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
-	ret = __xsk_configure_socket(xsk, umem, ifobject, false);
+	ret = xsk_configure_socket(xsk, umem, ifobject, false);
 	if (!ret)
 		zc_avail = true;
 
@@ -381,44 +162,29 @@ out:
 static struct option long_options[] = {
 	{"interface", required_argument, 0, 'i'},
 	{"busy-poll", no_argument, 0, 'b'},
-	{"dump-pkts", no_argument, 0, 'D'},
 	{"verbose", no_argument, 0, 'v'},
+	{"mode", required_argument, 0, 'm'},
+	{"list", no_argument, 0, 'l'},
+	{"test", required_argument, 0, 't'},
+	{"help", no_argument, 0, 'h'},
 	{0, 0, 0, 0}
 };
 
-static void usage(const char *prog)
+static void print_usage(char **argv)
 {
 	const char *str =
-		"  Usage: %s [OPTIONS]\n"
+		"  Usage: xskxceiver [OPTIONS]\n"
 		"  Options:\n"
 		"  -i, --interface      Use interface\n"
-		"  -D, --dump-pkts      Dump packets L2 - L5\n"
 		"  -v, --verbose        Verbose output\n"
-		"  -b, --busy-poll      Enable busy poll\n";
-
-	ksft_print_msg(str, prog);
-}
-
-static int switch_namespace(const char *nsname)
-{
-	char fqns[26] = "/var/run/netns/";
-	int nsfd;
-
-	if (!nsname || strlen(nsname) == 0)
-		return -1;
-
-	strncat(fqns, nsname, sizeof(fqns) - strlen(fqns) - 1);
-	nsfd = open(fqns, O_RDONLY);
-
-	if (nsfd == -1)
-		exit_with_error(errno);
-
-	if (setns(nsfd, 0) == -1)
-		exit_with_error(errno);
+		"  -b, --busy-poll      Enable busy poll\n"
+		"  -m, --mode           Run only mode skb, drv, or zc\n"
+		"  -l, --list           List all available tests\n"
+		"  -t, --test           Run a specific test. Enter number from -l option.\n"
+		"  -h, --help           Display this help and exit\n";
 
-	print_verbose("NS switched: %s\n", nsname);
-
-	return nsfd;
+	ksft_print_msg(str, basename(argv[0]));
+	ksft_exit_xfail();
 }
 
 static bool validate_interface(struct ifobject *ifobj)
@@ -438,9 +204,7 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj
 	opterr = 0;
 
 	for (;;) {
-		char *sptr, *token;
-
-		c = getopt_long(argc, argv, "i:Dvb", long_options, &option_index);
+		c = getopt_long(argc, argv, "i:vbm:lt:", long_options, &option_index);
 		if (c == -1)
 			break;
 
@@ -453,16 +217,15 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj
 			else
 				break;
 
-			sptr = strndupa(optarg, strlen(optarg));
-			memcpy(ifobj->ifname, strsep(&sptr, ","), MAX_INTERFACE_NAME_CHARS);
-			token = strsep(&sptr, ",");
-			if (token)
-				memcpy(ifobj->nsname, token, MAX_INTERFACES_NAMESPACE_CHARS);
+			memcpy(ifobj->ifname, optarg,
+			       min_t(size_t, MAX_INTERFACE_NAME_CHARS, strlen(optarg)));
+
+			ifobj->ifindex = if_nametoindex(ifobj->ifname);
+			if (!ifobj->ifindex)
+				exit_with_error(errno);
+
 			interface_nb++;
 			break;
-		case 'D':
-			opt_pkt_dump = true;
-			break;
 		case 'v':
 			opt_verbose = true;
 			break;
@@ -470,1400 +233,65 @@ static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj
 			ifobj_tx->busy_poll = true;
 			ifobj_rx->busy_poll = true;
 			break;
-		default:
-			usage(basename(argv[0]));
-			ksft_exit_xfail();
-		}
-	}
-}
-
-static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
-			     struct ifobject *ifobj_rx)
-{
-	u32 i, j;
-
-	for (i = 0; i < MAX_INTERFACES; i++) {
-		struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx;
-
-		ifobj->xsk = &ifobj->xsk_arr[0];
-		ifobj->use_poll = false;
-		ifobj->use_fill_ring = true;
-		ifobj->release_rx = true;
-		ifobj->validation_func = NULL;
-
-		if (i == 0) {
-			ifobj->rx_on = false;
-			ifobj->tx_on = true;
-			ifobj->pkt_stream = test->tx_pkt_stream_default;
-		} else {
-			ifobj->rx_on = true;
-			ifobj->tx_on = false;
-			ifobj->pkt_stream = test->rx_pkt_stream_default;
-		}
-
-		memset(ifobj->umem, 0, sizeof(*ifobj->umem));
-		ifobj->umem->num_frames = DEFAULT_UMEM_BUFFERS;
-		ifobj->umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
-		if (ifobj->shared_umem && ifobj->rx_on)
-			ifobj->umem->base_addr = DEFAULT_UMEM_BUFFERS *
-				XSK_UMEM__DEFAULT_FRAME_SIZE;
-
-		for (j = 0; j < MAX_SOCKETS; j++) {
-			memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j]));
-			ifobj->xsk_arr[j].rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
-		}
-	}
-
-	test->ifobj_tx = ifobj_tx;
-	test->ifobj_rx = ifobj_rx;
-	test->current_step = 0;
-	test->total_steps = 1;
-	test->nb_sockets = 1;
-	test->fail = false;
-}
-
-static void test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
-			   struct ifobject *ifobj_rx, enum test_mode mode)
-{
-	struct pkt_stream *tx_pkt_stream;
-	struct pkt_stream *rx_pkt_stream;
-	u32 i;
-
-	tx_pkt_stream = test->tx_pkt_stream_default;
-	rx_pkt_stream = test->rx_pkt_stream_default;
-	memset(test, 0, sizeof(*test));
-	test->tx_pkt_stream_default = tx_pkt_stream;
-	test->rx_pkt_stream_default = rx_pkt_stream;
-
-	for (i = 0; i < MAX_INTERFACES; i++) {
-		struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx;
-
-		ifobj->xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
-		if (mode == TEST_MODE_SKB)
-			ifobj->xdp_flags |= XDP_FLAGS_SKB_MODE;
-		else
-			ifobj->xdp_flags |= XDP_FLAGS_DRV_MODE;
-
-		ifobj->bind_flags = XDP_USE_NEED_WAKEUP;
-		if (mode == TEST_MODE_ZC)
-			ifobj->bind_flags |= XDP_ZEROCOPY;
-		else
-			ifobj->bind_flags |= XDP_COPY;
-	}
-
-	test->mode = mode;
-	__test_spec_init(test, ifobj_tx, ifobj_rx);
-}
-
-static void test_spec_reset(struct test_spec *test)
-{
-	__test_spec_init(test, test->ifobj_tx, test->ifobj_rx);
-}
-
-static void test_spec_set_name(struct test_spec *test, const char *name)
-{
-	strncpy(test->name, name, MAX_TEST_NAME_SIZE);
-}
-
-static void pkt_stream_reset(struct pkt_stream *pkt_stream)
-{
-	if (pkt_stream)
-		pkt_stream->rx_pkt_nb = 0;
-}
-
-static struct pkt *pkt_stream_get_pkt(struct pkt_stream *pkt_stream, u32 pkt_nb)
-{
-	if (pkt_nb >= pkt_stream->nb_pkts)
-		return NULL;
-
-	return &pkt_stream->pkts[pkt_nb];
-}
-
-static struct pkt *pkt_stream_get_next_rx_pkt(struct pkt_stream *pkt_stream, u32 *pkts_sent)
-{
-	while (pkt_stream->rx_pkt_nb < pkt_stream->nb_pkts) {
-		(*pkts_sent)++;
-		if (pkt_stream->pkts[pkt_stream->rx_pkt_nb].valid)
-			return &pkt_stream->pkts[pkt_stream->rx_pkt_nb++];
-		pkt_stream->rx_pkt_nb++;
-	}
-	return NULL;
-}
-
-static void pkt_stream_delete(struct pkt_stream *pkt_stream)
-{
-	free(pkt_stream->pkts);
-	free(pkt_stream);
-}
-
-static void pkt_stream_restore_default(struct test_spec *test)
-{
-	struct pkt_stream *tx_pkt_stream = test->ifobj_tx->pkt_stream;
-	struct pkt_stream *rx_pkt_stream = test->ifobj_rx->pkt_stream;
-
-	if (tx_pkt_stream != test->tx_pkt_stream_default) {
-		pkt_stream_delete(test->ifobj_tx->pkt_stream);
-		test->ifobj_tx->pkt_stream = test->tx_pkt_stream_default;
-	}
-
-	if (rx_pkt_stream != test->rx_pkt_stream_default) {
-		pkt_stream_delete(test->ifobj_rx->pkt_stream);
-		test->ifobj_rx->pkt_stream = test->rx_pkt_stream_default;
-	}
-}
-
-static struct pkt_stream *__pkt_stream_alloc(u32 nb_pkts)
-{
-	struct pkt_stream *pkt_stream;
-
-	pkt_stream = calloc(1, sizeof(*pkt_stream));
-	if (!pkt_stream)
-		return NULL;
-
-	pkt_stream->pkts = calloc(nb_pkts, sizeof(*pkt_stream->pkts));
-	if (!pkt_stream->pkts) {
-		free(pkt_stream);
-		return NULL;
-	}
-
-	pkt_stream->nb_pkts = nb_pkts;
-	return pkt_stream;
-}
-
-static void pkt_set(struct xsk_umem_info *umem, struct pkt *pkt, u64 addr, u32 len)
-{
-	pkt->addr = addr + umem->base_addr;
-	pkt->len = len;
-	if (len > umem->frame_size - XDP_PACKET_HEADROOM - MIN_PKT_SIZE * 2 - umem->frame_headroom)
-		pkt->valid = false;
-	else
-		pkt->valid = true;
-}
-
-static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb_pkts, u32 pkt_len)
-{
-	struct pkt_stream *pkt_stream;
-	u32 i;
-
-	pkt_stream = __pkt_stream_alloc(nb_pkts);
-	if (!pkt_stream)
-		exit_with_error(ENOMEM);
-
-	pkt_stream->nb_pkts = nb_pkts;
-	for (i = 0; i < nb_pkts; i++) {
-		pkt_set(umem, &pkt_stream->pkts[i], (i % umem->num_frames) * umem->frame_size,
-			pkt_len);
-		pkt_stream->pkts[i].payload = i;
-	}
-
-	return pkt_stream;
-}
-
-static struct pkt_stream *pkt_stream_clone(struct xsk_umem_info *umem,
-					   struct pkt_stream *pkt_stream)
-{
-	return pkt_stream_generate(umem, pkt_stream->nb_pkts, pkt_stream->pkts[0].len);
-}
-
-static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len)
-{
-	struct pkt_stream *pkt_stream;
-
-	pkt_stream = pkt_stream_generate(test->ifobj_tx->umem, nb_pkts, pkt_len);
-	test->ifobj_tx->pkt_stream = pkt_stream;
-	pkt_stream = pkt_stream_generate(test->ifobj_rx->umem, nb_pkts, pkt_len);
-	test->ifobj_rx->pkt_stream = pkt_stream;
-}
-
-static void __pkt_stream_replace_half(struct ifobject *ifobj, u32 pkt_len,
-				      int offset)
-{
-	struct xsk_umem_info *umem = ifobj->umem;
-	struct pkt_stream *pkt_stream;
-	u32 i;
-
-	pkt_stream = pkt_stream_clone(umem, ifobj->pkt_stream);
-	for (i = 1; i < ifobj->pkt_stream->nb_pkts; i += 2)
-		pkt_set(umem, &pkt_stream->pkts[i],
-			(i % umem->num_frames) * umem->frame_size + offset, pkt_len);
-
-	ifobj->pkt_stream = pkt_stream;
-}
-
-static void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, int offset)
-{
-	__pkt_stream_replace_half(test->ifobj_tx, pkt_len, offset);
-	__pkt_stream_replace_half(test->ifobj_rx, pkt_len, offset);
-}
-
-static void pkt_stream_receive_half(struct test_spec *test)
-{
-	struct xsk_umem_info *umem = test->ifobj_rx->umem;
-	struct pkt_stream *pkt_stream = test->ifobj_tx->pkt_stream;
-	u32 i;
-
-	test->ifobj_rx->pkt_stream = pkt_stream_generate(umem, pkt_stream->nb_pkts,
-							 pkt_stream->pkts[0].len);
-	pkt_stream = test->ifobj_rx->pkt_stream;
-	for (i = 1; i < pkt_stream->nb_pkts; i += 2)
-		pkt_stream->pkts[i].valid = false;
-}
-
-static struct pkt *pkt_generate(struct ifobject *ifobject, u32 pkt_nb)
-{
-	struct pkt *pkt = pkt_stream_get_pkt(ifobject->pkt_stream, pkt_nb);
-	struct udphdr *udp_hdr;
-	struct ethhdr *eth_hdr;
-	struct iphdr *ip_hdr;
-	void *data;
-
-	if (!pkt)
-		return NULL;
-	if (!pkt->valid || pkt->len < MIN_PKT_SIZE)
-		return pkt;
-
-	data = xsk_umem__get_data(ifobject->umem->buffer, pkt->addr);
-	udp_hdr = (struct udphdr *)(data + sizeof(struct ethhdr) + sizeof(struct iphdr));
-	ip_hdr = (struct iphdr *)(data + sizeof(struct ethhdr));
-	eth_hdr = (struct ethhdr *)data;
-
-	gen_udp_hdr(pkt_nb, data, ifobject, udp_hdr);
-	gen_ip_hdr(ifobject, ip_hdr);
-	gen_udp_csum(udp_hdr, ip_hdr);
-	gen_eth_hdr(ifobject, eth_hdr);
-
-	return pkt;
-}
-
-static void __pkt_stream_generate_custom(struct ifobject *ifobj,
-					 struct pkt *pkts, u32 nb_pkts)
-{
-	struct pkt_stream *pkt_stream;
-	u32 i;
-
-	pkt_stream = __pkt_stream_alloc(nb_pkts);
-	if (!pkt_stream)
-		exit_with_error(ENOMEM);
-
-	for (i = 0; i < nb_pkts; i++) {
-		pkt_stream->pkts[i].addr = pkts[i].addr + ifobj->umem->base_addr;
-		pkt_stream->pkts[i].len = pkts[i].len;
-		pkt_stream->pkts[i].payload = i;
-		pkt_stream->pkts[i].valid = pkts[i].valid;
-	}
-
-	ifobj->pkt_stream = pkt_stream;
-}
-
-static void pkt_stream_generate_custom(struct test_spec *test, struct pkt *pkts, u32 nb_pkts)
-{
-	__pkt_stream_generate_custom(test->ifobj_tx, pkts, nb_pkts);
-	__pkt_stream_generate_custom(test->ifobj_rx, pkts, nb_pkts);
-}
-
-static void pkt_dump(void *pkt, u32 len)
-{
-	char s[INET_ADDRSTRLEN];
-	struct ethhdr *ethhdr;
-	struct udphdr *udphdr;
-	struct iphdr *iphdr;
-	int payload, i;
-
-	ethhdr = pkt;
-	iphdr = pkt + sizeof(*ethhdr);
-	udphdr = pkt + sizeof(*ethhdr) + sizeof(*iphdr);
-
-	/*extract L2 frame */
-	fprintf(stdout, "DEBUG>> L2: dst mac: ");
-	for (i = 0; i < ETH_ALEN; i++)
-		fprintf(stdout, "%02X", ethhdr->h_dest[i]);
-
-	fprintf(stdout, "\nDEBUG>> L2: src mac: ");
-	for (i = 0; i < ETH_ALEN; i++)
-		fprintf(stdout, "%02X", ethhdr->h_source[i]);
-
-	/*extract L3 frame */
-	fprintf(stdout, "\nDEBUG>> L3: ip_hdr->ihl: %02X\n", iphdr->ihl);
-	fprintf(stdout, "DEBUG>> L3: ip_hdr->saddr: %s\n",
-		inet_ntop(AF_INET, &iphdr->saddr, s, sizeof(s)));
-	fprintf(stdout, "DEBUG>> L3: ip_hdr->daddr: %s\n",
-		inet_ntop(AF_INET, &iphdr->daddr, s, sizeof(s)));
-	/*extract L4 frame */
-	fprintf(stdout, "DEBUG>> L4: udp_hdr->src: %d\n", ntohs(udphdr->source));
-	fprintf(stdout, "DEBUG>> L4: udp_hdr->dst: %d\n", ntohs(udphdr->dest));
-	/*extract L5 frame */
-	payload = *((uint32_t *)(pkt + PKT_HDR_SIZE));
-
-	fprintf(stdout, "DEBUG>> L5: payload: %d\n", payload);
-	fprintf(stdout, "---------------------------------------\n");
-}
-
-static bool is_offset_correct(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream, u64 addr,
-			      u64 pkt_stream_addr)
-{
-	u32 headroom = umem->unaligned_mode ? 0 : umem->frame_headroom;
-	u32 offset = addr % umem->frame_size, expected_offset = 0;
-
-	if (!pkt_stream->use_addr_for_fill)
-		pkt_stream_addr = 0;
-
-	expected_offset += (pkt_stream_addr + headroom + XDP_PACKET_HEADROOM) % umem->frame_size;
-
-	if (offset == expected_offset)
-		return true;
-
-	ksft_print_msg("[%s] expected [%u], got [%u]\n", __func__, expected_offset, offset);
-	return false;
-}
-
-static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len)
-{
-	void *data = xsk_umem__get_data(buffer, addr);
-	struct iphdr *iphdr = (struct iphdr *)(data + sizeof(struct ethhdr));
-
-	if (!pkt) {
-		ksft_print_msg("[%s] too many packets received\n", __func__);
-		return false;
-	}
-
-	if (len < MIN_PKT_SIZE || pkt->len < MIN_PKT_SIZE) {
-		/* Do not try to verify packets that are smaller than minimum size. */
-		return true;
-	}
-
-	if (pkt->len != len) {
-		ksft_print_msg("[%s] expected length [%d], got length [%d]\n",
-			       __func__, pkt->len, len);
-		return false;
-	}
-
-	if (iphdr->version == IP_PKT_VER && iphdr->tos == IP_PKT_TOS) {
-		u32 seqnum = ntohl(*((u32 *)(data + PKT_HDR_SIZE)));
-
-		if (opt_pkt_dump)
-			pkt_dump(data, PKT_SIZE);
-
-		if (pkt->payload != seqnum) {
-			ksft_print_msg("[%s] expected seqnum [%d], got seqnum [%d]\n",
-				       __func__, pkt->payload, seqnum);
-			return false;
-		}
-	} else {
-		ksft_print_msg("Invalid frame received: ");
-		ksft_print_msg("[IP_PKT_VER: %02X], [IP_PKT_TOS: %02X]\n", iphdr->version,
-			       iphdr->tos);
-		return false;
-	}
-
-	return true;
-}
-
-static void kick_tx(struct xsk_socket_info *xsk)
-{
-	int ret;
-
-	ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0);
-	if (ret >= 0)
-		return;
-	if (errno == ENOBUFS || errno == EAGAIN || errno == EBUSY || errno == ENETDOWN) {
-		usleep(100);
-		return;
-	}
-	exit_with_error(errno);
-}
-
-static void kick_rx(struct xsk_socket_info *xsk)
-{
-	int ret;
-
-	ret = recvfrom(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, NULL);
-	if (ret < 0)
-		exit_with_error(errno);
-}
-
-static int complete_pkts(struct xsk_socket_info *xsk, int batch_size)
-{
-	unsigned int rcvd;
-	u32 idx;
-
-	if (xsk_ring_prod__needs_wakeup(&xsk->tx))
-		kick_tx(xsk);
-
-	rcvd = xsk_ring_cons__peek(&xsk->umem->cq, batch_size, &idx);
-	if (rcvd) {
-		if (rcvd > xsk->outstanding_tx) {
-			u64 addr = *xsk_ring_cons__comp_addr(&xsk->umem->cq, idx + rcvd - 1);
-
-			ksft_print_msg("[%s] Too many packets completed\n", __func__);
-			ksft_print_msg("Last completion address: %llx\n", addr);
-			return TEST_FAILURE;
-		}
-
-		xsk_ring_cons__release(&xsk->umem->cq, rcvd);
-		xsk->outstanding_tx -= rcvd;
-	}
-
-	return TEST_PASS;
-}
-
-static int receive_pkts(struct test_spec *test, struct pollfd *fds)
-{
-	struct timeval tv_end, tv_now, tv_timeout = {THREAD_TMOUT, 0};
-	struct pkt_stream *pkt_stream = test->ifobj_rx->pkt_stream;
-	u32 idx_rx = 0, idx_fq = 0, rcvd, i, pkts_sent = 0;
-	struct xsk_socket_info *xsk = test->ifobj_rx->xsk;
-	struct ifobject *ifobj = test->ifobj_rx;
-	struct xsk_umem_info *umem = xsk->umem;
-	struct pkt *pkt;
-	int ret;
-
-	ret = gettimeofday(&tv_now, NULL);
-	if (ret)
-		exit_with_error(errno);
-	timeradd(&tv_now, &tv_timeout, &tv_end);
-
-	pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &pkts_sent);
-	while (pkt) {
-		ret = gettimeofday(&tv_now, NULL);
-		if (ret)
-			exit_with_error(errno);
-		if (timercmp(&tv_now, &tv_end, >)) {
-			ksft_print_msg("ERROR: [%s] Receive loop timed out\n", __func__);
-			return TEST_FAILURE;
-		}
-
-		kick_rx(xsk);
-		if (ifobj->use_poll) {
-			ret = poll(fds, 1, POLL_TMOUT);
-			if (ret < 0)
-				exit_with_error(-ret);
-
-			if (!ret) {
-				if (!is_umem_valid(test->ifobj_tx))
-					return TEST_PASS;
-
-				ksft_print_msg("ERROR: [%s] Poll timed out\n", __func__);
-				return TEST_FAILURE;
-
-			}
-
-			if (!(fds->revents & POLLIN))
-				continue;
-		}
-
-		rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx);
-		if (!rcvd)
-			continue;
-
-		if (ifobj->use_fill_ring) {
-			ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
-			while (ret != rcvd) {
-				if (ret < 0)
-					exit_with_error(-ret);
-				if (xsk_ring_prod__needs_wakeup(&umem->fq)) {
-					ret = poll(fds, 1, POLL_TMOUT);
-					if (ret < 0)
-						exit_with_error(-ret);
-				}
-				ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
-			}
-		}
-
-		for (i = 0; i < rcvd; i++) {
-			const struct xdp_desc *desc = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++);
-			u64 addr = desc->addr, orig;
-
-			orig = xsk_umem__extract_addr(addr);
-			addr = xsk_umem__add_offset_to_addr(addr);
-
-			if (!is_pkt_valid(pkt, umem->buffer, addr, desc->len) ||
-			    !is_offset_correct(umem, pkt_stream, addr, pkt->addr))
-				return TEST_FAILURE;
-
-			if (ifobj->use_fill_ring)
-				*xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) = orig;
-			pkt = pkt_stream_get_next_rx_pkt(pkt_stream, &pkts_sent);
-		}
-
-		if (ifobj->use_fill_ring)
-			xsk_ring_prod__submit(&umem->fq, rcvd);
-		if (ifobj->release_rx)
-			xsk_ring_cons__release(&xsk->rx, rcvd);
-
-		pthread_mutex_lock(&pacing_mutex);
-		pkts_in_flight -= pkts_sent;
-		if (pkts_in_flight < umem->num_frames)
-			pthread_cond_signal(&pacing_cond);
-		pthread_mutex_unlock(&pacing_mutex);
-		pkts_sent = 0;
-	}
-
-	return TEST_PASS;
-}
-
-static int __send_pkts(struct ifobject *ifobject, u32 *pkt_nb, struct pollfd *fds,
-		       bool timeout)
-{
-	struct xsk_socket_info *xsk = ifobject->xsk;
-	bool use_poll = ifobject->use_poll;
-	u32 i, idx = 0, valid_pkts = 0;
-	int ret;
-
-	while (xsk_ring_prod__reserve(&xsk->tx, BATCH_SIZE, &idx) < BATCH_SIZE) {
-		if (use_poll) {
-			ret = poll(fds, 1, POLL_TMOUT);
-			if (timeout) {
-				if (ret < 0) {
-					ksft_print_msg("ERROR: [%s] Poll error %d\n",
-						       __func__, ret);
-					return TEST_FAILURE;
-				}
-				if (ret == 0)
-					return TEST_PASS;
-				break;
-			}
-			if (ret <= 0) {
-				ksft_print_msg("ERROR: [%s] Poll error %d\n",
-					       __func__, ret);
-				return TEST_FAILURE;
-			}
-		}
-
-		complete_pkts(xsk, BATCH_SIZE);
-	}
-
-	for (i = 0; i < BATCH_SIZE; i++) {
-		struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i);
-		struct pkt *pkt = pkt_generate(ifobject, *pkt_nb);
-
-		if (!pkt)
+		case 'm':
+			if (!strncmp("skb", optarg, strlen(optarg)))
+				opt_mode = TEST_MODE_SKB;
+			else if (!strncmp("drv", optarg, strlen(optarg)))
+				opt_mode = TEST_MODE_DRV;
+			else if (!strncmp("zc", optarg, strlen(optarg)))
+				opt_mode = TEST_MODE_ZC;
+			else
+				print_usage(argv);
 			break;
-
-		tx_desc->addr = pkt->addr;
-		tx_desc->len = pkt->len;
-		(*pkt_nb)++;
-		if (pkt->valid)
-			valid_pkts++;
-	}
-
-	pthread_mutex_lock(&pacing_mutex);
-	pkts_in_flight += valid_pkts;
-	/* pkts_in_flight might be negative if many invalid packets are sent */
-	if (pkts_in_flight >= (int)(ifobject->umem->num_frames - BATCH_SIZE)) {
-		kick_tx(xsk);
-		pthread_cond_wait(&pacing_cond, &pacing_mutex);
-	}
-	pthread_mutex_unlock(&pacing_mutex);
-
-	xsk_ring_prod__submit(&xsk->tx, i);
-	xsk->outstanding_tx += valid_pkts;
-
-	if (use_poll) {
-		ret = poll(fds, 1, POLL_TMOUT);
-		if (ret <= 0) {
-			if (ret == 0 && timeout)
-				return TEST_PASS;
-
-			ksft_print_msg("ERROR: [%s] Poll error %d\n", __func__, ret);
-			return TEST_FAILURE;
-		}
-	}
-
-	if (!timeout) {
-		if (complete_pkts(xsk, i))
-			return TEST_FAILURE;
-
-		usleep(10);
-		return TEST_PASS;
-	}
-
-	return TEST_CONTINUE;
-}
-
-static void wait_for_tx_completion(struct xsk_socket_info *xsk)
-{
-	while (xsk->outstanding_tx)
-		complete_pkts(xsk, BATCH_SIZE);
-}
-
-static int send_pkts(struct test_spec *test, struct ifobject *ifobject)
-{
-	bool timeout = !is_umem_valid(test->ifobj_rx);
-	struct pollfd fds = { };
-	u32 pkt_cnt = 0, ret;
-
-	fds.fd = xsk_socket__fd(ifobject->xsk->xsk);
-	fds.events = POLLOUT;
-
-	while (pkt_cnt < ifobject->pkt_stream->nb_pkts) {
-		ret = __send_pkts(ifobject, &pkt_cnt, &fds, timeout);
-		if ((ret || test->fail) && !timeout)
-			return TEST_FAILURE;
-		else if (ret == TEST_PASS && timeout)
-			return ret;
-	}
-
-	wait_for_tx_completion(ifobject->xsk);
-	return TEST_PASS;
-}
-
-static int get_xsk_stats(struct xsk_socket *xsk, struct xdp_statistics *stats)
-{
-	int fd = xsk_socket__fd(xsk), err;
-	socklen_t optlen, expected_len;
-
-	optlen = sizeof(*stats);
-	err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, stats, &optlen);
-	if (err) {
-		ksft_print_msg("[%s] getsockopt(XDP_STATISTICS) error %u %s\n",
-			       __func__, -err, strerror(-err));
-		return TEST_FAILURE;
-	}
-
-	expected_len = sizeof(struct xdp_statistics);
-	if (optlen != expected_len) {
-		ksft_print_msg("[%s] getsockopt optlen error. Expected: %u got: %u\n",
-			       __func__, expected_len, optlen);
-		return TEST_FAILURE;
-	}
-
-	return TEST_PASS;
-}
-
-static int validate_rx_dropped(struct ifobject *ifobject)
-{
-	struct xsk_socket *xsk = ifobject->xsk->xsk;
-	struct xdp_statistics stats;
-	int err;
-
-	kick_rx(ifobject->xsk);
-
-	err = get_xsk_stats(xsk, &stats);
-	if (err)
-		return TEST_FAILURE;
-
-	if (stats.rx_dropped == ifobject->pkt_stream->nb_pkts / 2)
-		return TEST_PASS;
-
-	return TEST_FAILURE;
-}
-
-static int validate_rx_full(struct ifobject *ifobject)
-{
-	struct xsk_socket *xsk = ifobject->xsk->xsk;
-	struct xdp_statistics stats;
-	int err;
-
-	usleep(1000);
-	kick_rx(ifobject->xsk);
-
-	err = get_xsk_stats(xsk, &stats);
-	if (err)
-		return TEST_FAILURE;
-
-	if (stats.rx_ring_full)
-		return TEST_PASS;
-
-	return TEST_FAILURE;
-}
-
-static int validate_fill_empty(struct ifobject *ifobject)
-{
-	struct xsk_socket *xsk = ifobject->xsk->xsk;
-	struct xdp_statistics stats;
-	int err;
-
-	usleep(1000);
-	kick_rx(ifobject->xsk);
-
-	err = get_xsk_stats(xsk, &stats);
-	if (err)
-		return TEST_FAILURE;
-
-	if (stats.rx_fill_ring_empty_descs)
-		return TEST_PASS;
-
-	return TEST_FAILURE;
-}
-
-static int validate_tx_invalid_descs(struct ifobject *ifobject)
-{
-	struct xsk_socket *xsk = ifobject->xsk->xsk;
-	int fd = xsk_socket__fd(xsk);
-	struct xdp_statistics stats;
-	socklen_t optlen;
-	int err;
-
-	optlen = sizeof(stats);
-	err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, &stats, &optlen);
-	if (err) {
-		ksft_print_msg("[%s] getsockopt(XDP_STATISTICS) error %u %s\n",
-			       __func__, -err, strerror(-err));
-		return TEST_FAILURE;
-	}
-
-	if (stats.tx_invalid_descs != ifobject->pkt_stream->nb_pkts / 2) {
-		ksft_print_msg("[%s] tx_invalid_descs incorrect. Got [%u] expected [%u]\n",
-			       __func__, stats.tx_invalid_descs, ifobject->pkt_stream->nb_pkts);
-		return TEST_FAILURE;
-	}
-
-	return TEST_PASS;
-}
-
-static void xsk_configure_socket(struct test_spec *test, struct ifobject *ifobject,
-				 struct xsk_umem_info *umem, bool tx)
-{
-	int i, ret;
-
-	for (i = 0; i < test->nb_sockets; i++) {
-		bool shared = (ifobject->shared_umem && tx) ? true : !!i;
-		u32 ctr = 0;
-
-		while (ctr++ < SOCK_RECONF_CTR) {
-			ret = __xsk_configure_socket(&ifobject->xsk_arr[i], umem,
-						     ifobject, shared);
-			if (!ret)
-				break;
-
-			/* Retry if it fails as xsk_socket__create() is asynchronous */
-			if (ctr >= SOCK_RECONF_CTR)
-				exit_with_error(-ret);
-			usleep(USLEEP_MAX);
+		case 'l':
+			opt_print_tests = true;
+			break;
+		case 't':
+			errno = 0;
+			opt_run_test = strtol(optarg, NULL, 0);
+			if (errno)
+				print_usage(argv);
+			break;
+		case 'h':
+		default:
+			print_usage(argv);
 		}
-		if (ifobject->busy_poll)
-			enable_busy_poll(&ifobject->xsk_arr[i]);
 	}
 }
 
-static void thread_common_ops_tx(struct test_spec *test, struct ifobject *ifobject)
+static void xsk_unload_xdp_programs(struct ifobject *ifobj)
 {
-	xsk_configure_socket(test, ifobject, test->ifobj_rx->umem, true);
-	ifobject->xsk = &ifobject->xsk_arr[0];
-	ifobject->xsk_map_fd = test->ifobj_rx->xsk_map_fd;
-	memcpy(ifobject->umem, test->ifobj_rx->umem, sizeof(struct xsk_umem_info));
+	xsk_xdp_progs__destroy(ifobj->xdp_progs);
 }
 
-static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream)
+static void run_pkt_test(struct test_spec *test)
 {
-	u32 idx = 0, i, buffers_to_fill;
 	int ret;
 
-	if (umem->num_frames < XSK_RING_PROD__DEFAULT_NUM_DESCS)
-		buffers_to_fill = umem->num_frames;
-	else
-		buffers_to_fill = XSK_RING_PROD__DEFAULT_NUM_DESCS;
-
-	ret = xsk_ring_prod__reserve(&umem->fq, buffers_to_fill, &idx);
-	if (ret != buffers_to_fill)
-		exit_with_error(ENOSPC);
-	for (i = 0; i < buffers_to_fill; i++) {
-		u64 addr;
-
-		if (pkt_stream->use_addr_for_fill) {
-			struct pkt *pkt = pkt_stream_get_pkt(pkt_stream, i);
-
-			if (!pkt)
-				break;
-			addr = pkt->addr;
-		} else {
-			addr = i * umem->frame_size;
-		}
-
-		*xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr;
-	}
-	xsk_ring_prod__submit(&umem->fq, buffers_to_fill);
-}
-
-static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
-{
-	u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size;
-	int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
-	LIBBPF_OPTS(bpf_xdp_query_opts, opts);
-	int ret, ifindex;
-	void *bufs;
-
-	ifobject->ns_fd = switch_namespace(ifobject->nsname);
-
-	if (ifobject->umem->unaligned_mode)
-		mmap_flags |= MAP_HUGETLB;
-
-	if (ifobject->shared_umem)
-		umem_sz *= 2;
-
-	bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0);
-	if (bufs == MAP_FAILED)
-		exit_with_error(errno);
-
-	ret = xsk_configure_umem(ifobject->umem, bufs, umem_sz);
-	if (ret)
-		exit_with_error(-ret);
-
-	xsk_populate_fill_ring(ifobject->umem, ifobject->pkt_stream);
-
-	xsk_configure_socket(test, ifobject, ifobject->umem, false);
-
-	ifobject->xsk = &ifobject->xsk_arr[0];
-
-	if (!ifobject->rx_on)
-		return;
-
-	ifindex = if_nametoindex(ifobject->ifname);
-	if (!ifindex)
-		exit_with_error(errno);
-
-	ret = xsk_setup_xdp_prog_xsk(ifobject->xsk->xsk, &ifobject->xsk_map_fd);
-	if (ret)
-		exit_with_error(-ret);
-
-	ret = bpf_xdp_query(ifindex, ifobject->xdp_flags, &opts);
-	if (ret)
-		exit_with_error(-ret);
-
-	if (ifobject->xdp_flags & XDP_FLAGS_SKB_MODE) {
-		if (opts.attach_mode != XDP_ATTACHED_SKB) {
-			ksft_print_msg("ERROR: [%s] XDP prog not in SKB mode\n");
-			exit_with_error(-EINVAL);
-		}
-	} else if (ifobject->xdp_flags & XDP_FLAGS_DRV_MODE) {
-		if (opts.attach_mode != XDP_ATTACHED_DRV) {
-			ksft_print_msg("ERROR: [%s] XDP prog not in DRV mode\n");
-			exit_with_error(-EINVAL);
-		}
-	}
-
-	ret = xsk_socket__update_xskmap(ifobject->xsk->xsk, ifobject->xsk_map_fd);
-	if (ret)
-		exit_with_error(-ret);
-}
-
-static void *worker_testapp_validate_tx(void *arg)
-{
-	struct test_spec *test = (struct test_spec *)arg;
-	struct ifobject *ifobject = test->ifobj_tx;
-	int err;
-
-	if (test->current_step == 1) {
-		if (!ifobject->shared_umem)
-			thread_common_ops(test, ifobject);
-		else
-			thread_common_ops_tx(test, ifobject);
-	}
-
-	print_verbose("Sending %d packets on interface %s\n", ifobject->pkt_stream->nb_pkts,
-		      ifobject->ifname);
-	err = send_pkts(test, ifobject);
-
-	if (!err && ifobject->validation_func)
-		err = ifobject->validation_func(ifobject);
-	if (err)
-		report_failure(test);
-
-	pthread_exit(NULL);
-}
-
-static void *worker_testapp_validate_rx(void *arg)
-{
-	struct test_spec *test = (struct test_spec *)arg;
-	struct ifobject *ifobject = test->ifobj_rx;
-	struct pollfd fds = { };
-	int id = 0;
-	int err;
-
-	if (test->current_step == 1) {
-		thread_common_ops(test, ifobject);
-	} else {
-		bpf_map_delete_elem(ifobject->xsk_map_fd, &id);
-		xsk_socket__update_xskmap(ifobject->xsk->xsk, ifobject->xsk_map_fd);
-	}
-
-	fds.fd = xsk_socket__fd(ifobject->xsk->xsk);
-	fds.events = POLLIN;
-
-	pthread_barrier_wait(&barr);
-
-	err = receive_pkts(test, &fds);
-
-	if (!err && ifobject->validation_func)
-		err = ifobject->validation_func(ifobject);
-	if (err) {
-		report_failure(test);
-		pthread_mutex_lock(&pacing_mutex);
-		pthread_cond_signal(&pacing_cond);
-		pthread_mutex_unlock(&pacing_mutex);
-	}
-
-	pthread_exit(NULL);
-}
-
-static void testapp_clean_xsk_umem(struct ifobject *ifobj)
-{
-	u64 umem_sz = ifobj->umem->num_frames * ifobj->umem->frame_size;
-
-	if (ifobj->shared_umem)
-		umem_sz *= 2;
-
-	xsk_umem__delete(ifobj->umem->umem);
-	munmap(ifobj->umem->buffer, umem_sz);
-}
-
-static void handler(int signum)
-{
-	pthread_exit(NULL);
-}
-
-static int testapp_validate_traffic_single_thread(struct test_spec *test, struct ifobject *ifobj,
-						  enum test_type type)
-{
-	bool old_shared_umem = ifobj->shared_umem;
-	pthread_t t0;
-
-	if (pthread_barrier_init(&barr, NULL, 2))
-		exit_with_error(errno);
-
-	test->current_step++;
-	if (type == TEST_TYPE_POLL_RXQ_TMOUT)
-		pkt_stream_reset(ifobj->pkt_stream);
-	pkts_in_flight = 0;
-
-	test->ifobj_rx->shared_umem = false;
-	test->ifobj_tx->shared_umem = false;
-
-	signal(SIGUSR1, handler);
-	/* Spawn thread */
-	pthread_create(&t0, NULL, ifobj->func_ptr, test);
-
-	if (type != TEST_TYPE_POLL_TXQ_TMOUT)
-		pthread_barrier_wait(&barr);
-
-	if (pthread_barrier_destroy(&barr))
-		exit_with_error(errno);
-
-	pthread_kill(t0, SIGUSR1);
-	pthread_join(t0, NULL);
-
-	if (test->total_steps == test->current_step || test->fail) {
-		xsk_socket__delete(ifobj->xsk->xsk);
-		testapp_clean_xsk_umem(ifobj);
-	}
-
-	test->ifobj_rx->shared_umem = old_shared_umem;
-	test->ifobj_tx->shared_umem = old_shared_umem;
-
-	return !!test->fail;
-}
-
-static int testapp_validate_traffic(struct test_spec *test)
-{
-	struct ifobject *ifobj_tx = test->ifobj_tx;
-	struct ifobject *ifobj_rx = test->ifobj_rx;
-	pthread_t t0, t1;
-
-	if (pthread_barrier_init(&barr, NULL, 2))
-		exit_with_error(errno);
-
-	test->current_step++;
-	pkt_stream_reset(ifobj_rx->pkt_stream);
-	pkts_in_flight = 0;
-
-	/*Spawn RX thread */
-	pthread_create(&t0, NULL, ifobj_rx->func_ptr, test);
-
-	pthread_barrier_wait(&barr);
-	if (pthread_barrier_destroy(&barr))
-		exit_with_error(errno);
-
-	/*Spawn TX thread */
-	pthread_create(&t1, NULL, ifobj_tx->func_ptr, test);
-
-	pthread_join(t1, NULL);
-	pthread_join(t0, NULL);
-
-	if (test->total_steps == test->current_step || test->fail) {
-		xsk_socket__delete(ifobj_tx->xsk->xsk);
-		xsk_socket__delete(ifobj_rx->xsk->xsk);
-		testapp_clean_xsk_umem(ifobj_rx);
-		if (!ifobj_tx->shared_umem)
-			testapp_clean_xsk_umem(ifobj_tx);
-	}
-
-	return !!test->fail;
-}
+	ret = test->test_func(test);
 
-static void testapp_teardown(struct test_spec *test)
-{
-	int i;
-
-	test_spec_set_name(test, "TEARDOWN");
-	for (i = 0; i < MAX_TEARDOWN_ITER; i++) {
-		if (testapp_validate_traffic(test))
-			return;
-		test_spec_reset(test);
-	}
-}
-
-static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2)
-{
-	thread_func_t tmp_func_ptr = (*ifobj1)->func_ptr;
-	struct ifobject *tmp_ifobj = (*ifobj1);
-
-	(*ifobj1)->func_ptr = (*ifobj2)->func_ptr;
-	(*ifobj2)->func_ptr = tmp_func_ptr;
-
-	*ifobj1 = *ifobj2;
-	*ifobj2 = tmp_ifobj;
-}
-
-static void testapp_bidi(struct test_spec *test)
-{
-	test_spec_set_name(test, "BIDIRECTIONAL");
-	test->ifobj_tx->rx_on = true;
-	test->ifobj_rx->tx_on = true;
-	test->total_steps = 2;
-	if (testapp_validate_traffic(test))
-		return;
-
-	print_verbose("Switching Tx/Rx vectors\n");
-	swap_directions(&test->ifobj_rx, &test->ifobj_tx);
-	testapp_validate_traffic(test);
-
-	swap_directions(&test->ifobj_rx, &test->ifobj_tx);
-}
-
-static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx)
-{
-	int ret;
-
-	xsk_socket__delete(ifobj_tx->xsk->xsk);
-	xsk_socket__delete(ifobj_rx->xsk->xsk);
-	ifobj_tx->xsk = &ifobj_tx->xsk_arr[1];
-	ifobj_rx->xsk = &ifobj_rx->xsk_arr[1];
-
-	ret = xsk_socket__update_xskmap(ifobj_rx->xsk->xsk, ifobj_rx->xsk_map_fd);
-	if (ret)
-		exit_with_error(-ret);
-}
-
-static void testapp_bpf_res(struct test_spec *test)
-{
-	test_spec_set_name(test, "BPF_RES");
-	test->total_steps = 2;
-	test->nb_sockets = 2;
-	if (testapp_validate_traffic(test))
-		return;
-
-	swap_xsk_resources(test->ifobj_tx, test->ifobj_rx);
-	testapp_validate_traffic(test);
-}
-
-static void testapp_headroom(struct test_spec *test)
-{
-	test_spec_set_name(test, "UMEM_HEADROOM");
-	test->ifobj_rx->umem->frame_headroom = UMEM_HEADROOM_TEST_SIZE;
-	testapp_validate_traffic(test);
-}
-
-static void testapp_stats_rx_dropped(struct test_spec *test)
-{
-	test_spec_set_name(test, "STAT_RX_DROPPED");
-	pkt_stream_replace_half(test, MIN_PKT_SIZE * 4, 0);
-	test->ifobj_rx->umem->frame_headroom = test->ifobj_rx->umem->frame_size -
-		XDP_PACKET_HEADROOM - MIN_PKT_SIZE * 3;
-	pkt_stream_receive_half(test);
-	test->ifobj_rx->validation_func = validate_rx_dropped;
-	testapp_validate_traffic(test);
-}
-
-static void testapp_stats_tx_invalid_descs(struct test_spec *test)
-{
-	test_spec_set_name(test, "STAT_TX_INVALID");
-	pkt_stream_replace_half(test, XSK_UMEM__INVALID_FRAME_SIZE, 0);
-	test->ifobj_tx->validation_func = validate_tx_invalid_descs;
-	testapp_validate_traffic(test);
-
-	pkt_stream_restore_default(test);
-}
-
-static void testapp_stats_rx_full(struct test_spec *test)
-{
-	test_spec_set_name(test, "STAT_RX_FULL");
-	pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, PKT_SIZE);
-	test->ifobj_rx->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem,
-							 DEFAULT_UMEM_BUFFERS, PKT_SIZE);
-	if (!test->ifobj_rx->pkt_stream)
-		exit_with_error(ENOMEM);
-
-	test->ifobj_rx->xsk->rxqsize = DEFAULT_UMEM_BUFFERS;
-	test->ifobj_rx->release_rx = false;
-	test->ifobj_rx->validation_func = validate_rx_full;
-	testapp_validate_traffic(test);
-
-	pkt_stream_restore_default(test);
-}
-
-static void testapp_stats_fill_empty(struct test_spec *test)
-{
-	test_spec_set_name(test, "STAT_RX_FILL_EMPTY");
-	pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, PKT_SIZE);
-	test->ifobj_rx->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem,
-							 DEFAULT_UMEM_BUFFERS, PKT_SIZE);
-	if (!test->ifobj_rx->pkt_stream)
-		exit_with_error(ENOMEM);
-
-	test->ifobj_rx->use_fill_ring = false;
-	test->ifobj_rx->validation_func = validate_fill_empty;
-	testapp_validate_traffic(test);
-
-	pkt_stream_restore_default(test);
-}
-
-/* Simple test */
-static bool hugepages_present(struct ifobject *ifobject)
-{
-	const size_t mmap_sz = 2 * ifobject->umem->num_frames * ifobject->umem->frame_size;
-	void *bufs;
-
-	bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE,
-		    MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0);
-	if (bufs == MAP_FAILED)
-		return false;
-
-	munmap(bufs, mmap_sz);
-	return true;
-}
-
-static bool testapp_unaligned(struct test_spec *test)
-{
-	if (!hugepages_present(test->ifobj_tx)) {
-		ksft_test_result_skip("No 2M huge pages present.\n");
-		return false;
-	}
-
-	test_spec_set_name(test, "UNALIGNED_MODE");
-	test->ifobj_tx->umem->unaligned_mode = true;
-	test->ifobj_rx->umem->unaligned_mode = true;
-	/* Let half of the packets straddle a buffer boundrary */
-	pkt_stream_replace_half(test, PKT_SIZE, -PKT_SIZE / 2);
-	test->ifobj_rx->pkt_stream->use_addr_for_fill = true;
-	testapp_validate_traffic(test);
-
-	pkt_stream_restore_default(test);
-	return true;
-}
-
-static void testapp_single_pkt(struct test_spec *test)
-{
-	struct pkt pkts[] = {{0x1000, PKT_SIZE, 0, true}};
-
-	pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts));
-	testapp_validate_traffic(test);
-	pkt_stream_restore_default(test);
-}
-
-static void testapp_invalid_desc(struct test_spec *test)
-{
-	struct pkt pkts[] = {
-		/* Zero packet address allowed */
-		{0, PKT_SIZE, 0, true},
-		/* Allowed packet */
-		{0x1000, PKT_SIZE, 0, true},
-		/* Straddling the start of umem */
-		{-2, PKT_SIZE, 0, false},
-		/* Packet too large */
-		{0x2000, XSK_UMEM__INVALID_FRAME_SIZE, 0, false},
-		/* After umem ends */
-		{UMEM_SIZE, PKT_SIZE, 0, false},
-		/* Straddle the end of umem */
-		{UMEM_SIZE - PKT_SIZE / 2, PKT_SIZE, 0, false},
-		/* Straddle a page boundrary */
-		{0x3000 - PKT_SIZE / 2, PKT_SIZE, 0, false},
-		/* Straddle a 2K boundrary */
-		{0x3800 - PKT_SIZE / 2, PKT_SIZE, 0, true},
-		/* Valid packet for synch so that something is received */
-		{0x4000, PKT_SIZE, 0, true}};
-
-	if (test->ifobj_tx->umem->unaligned_mode) {
-		/* Crossing a page boundrary allowed */
-		pkts[6].valid = true;
-	}
-	if (test->ifobj_tx->umem->frame_size == XSK_UMEM__DEFAULT_FRAME_SIZE / 2) {
-		/* Crossing a 2K frame size boundrary not allowed */
-		pkts[7].valid = false;
-	}
-
-	if (test->ifobj_tx->shared_umem) {
-		pkts[4].addr += UMEM_SIZE;
-		pkts[5].addr += UMEM_SIZE;
-	}
-
-	pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts));
-	testapp_validate_traffic(test);
-	pkt_stream_restore_default(test);
-}
-
-static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *src_mac,
-		       const char *dst_ip, const char *src_ip, const u16 dst_port,
-		       const u16 src_port, thread_func_t func_ptr)
-{
-	struct in_addr ip;
-
-	memcpy(ifobj->dst_mac, dst_mac, ETH_ALEN);
-	memcpy(ifobj->src_mac, src_mac, ETH_ALEN);
-
-	inet_aton(dst_ip, &ip);
-	ifobj->dst_ip = ip.s_addr;
-
-	inet_aton(src_ip, &ip);
-	ifobj->src_ip = ip.s_addr;
-
-	ifobj->dst_port = dst_port;
-	ifobj->src_port = src_port;
-
-	ifobj->func_ptr = func_ptr;
-}
-
-static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_type type)
-{
-	switch (type) {
-	case TEST_TYPE_STATS_RX_DROPPED:
-		if (mode == TEST_MODE_ZC) {
-			ksft_test_result_skip("Can not run RX_DROPPED test for ZC mode\n");
-			return;
-		}
-		testapp_stats_rx_dropped(test);
-		break;
-	case TEST_TYPE_STATS_TX_INVALID_DESCS:
-		testapp_stats_tx_invalid_descs(test);
-		break;
-	case TEST_TYPE_STATS_RX_FULL:
-		testapp_stats_rx_full(test);
-		break;
-	case TEST_TYPE_STATS_FILL_EMPTY:
-		testapp_stats_fill_empty(test);
-		break;
-	case TEST_TYPE_TEARDOWN:
-		testapp_teardown(test);
-		break;
-	case TEST_TYPE_BIDI:
-		testapp_bidi(test);
-		break;
-	case TEST_TYPE_BPF_RES:
-		testapp_bpf_res(test);
-		break;
-	case TEST_TYPE_RUN_TO_COMPLETION:
-		test_spec_set_name(test, "RUN_TO_COMPLETION");
-		testapp_validate_traffic(test);
-		break;
-	case TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT:
-		test_spec_set_name(test, "RUN_TO_COMPLETION_SINGLE_PKT");
-		testapp_single_pkt(test);
-		break;
-	case TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME:
-		test_spec_set_name(test, "RUN_TO_COMPLETION_2K_FRAME_SIZE");
-		test->ifobj_tx->umem->frame_size = 2048;
-		test->ifobj_rx->umem->frame_size = 2048;
-		pkt_stream_replace(test, DEFAULT_PKT_CNT, PKT_SIZE);
-		testapp_validate_traffic(test);
-
-		pkt_stream_restore_default(test);
-		break;
-	case TEST_TYPE_RX_POLL:
-		test->ifobj_rx->use_poll = true;
-		test_spec_set_name(test, "POLL_RX");
-		testapp_validate_traffic(test);
-		break;
-	case TEST_TYPE_TX_POLL:
-		test->ifobj_tx->use_poll = true;
-		test_spec_set_name(test, "POLL_TX");
-		testapp_validate_traffic(test);
-		break;
-	case TEST_TYPE_POLL_TXQ_TMOUT:
-		test_spec_set_name(test, "POLL_TXQ_FULL");
-		test->ifobj_tx->use_poll = true;
-		/* create invalid frame by set umem frame_size and pkt length equal to 2048 */
-		test->ifobj_tx->umem->frame_size = 2048;
-		pkt_stream_replace(test, 2 * DEFAULT_PKT_CNT, 2048);
-		testapp_validate_traffic_single_thread(test, test->ifobj_tx, type);
-		pkt_stream_restore_default(test);
-		break;
-	case TEST_TYPE_POLL_RXQ_TMOUT:
-		test_spec_set_name(test, "POLL_RXQ_EMPTY");
-		test->ifobj_rx->use_poll = true;
-		testapp_validate_traffic_single_thread(test, test->ifobj_rx, type);
-		break;
-	case TEST_TYPE_ALIGNED_INV_DESC:
-		test_spec_set_name(test, "ALIGNED_INV_DESC");
-		testapp_invalid_desc(test);
-		break;
-	case TEST_TYPE_ALIGNED_INV_DESC_2K_FRAME:
-		test_spec_set_name(test, "ALIGNED_INV_DESC_2K_FRAME_SIZE");
-		test->ifobj_tx->umem->frame_size = 2048;
-		test->ifobj_rx->umem->frame_size = 2048;
-		testapp_invalid_desc(test);
-		break;
-	case TEST_TYPE_UNALIGNED_INV_DESC:
-		if (!hugepages_present(test->ifobj_tx)) {
-			ksft_test_result_skip("No 2M huge pages present.\n");
-			return;
-		}
-		test_spec_set_name(test, "UNALIGNED_INV_DESC");
-		test->ifobj_tx->umem->unaligned_mode = true;
-		test->ifobj_rx->umem->unaligned_mode = true;
-		testapp_invalid_desc(test);
+	switch (ret) {
+	case TEST_PASS:
+		ksft_test_result_pass("PASS: %s %s%s\n", mode_string(test), busy_poll_string(test),
+				      test->name);
 		break;
-	case TEST_TYPE_UNALIGNED:
-		if (!testapp_unaligned(test))
-			return;
+	case TEST_SKIP:
+		ksft_test_result_skip("SKIP: %s %s%s\n", mode_string(test), busy_poll_string(test),
+				      test->name);
 		break;
-	case TEST_TYPE_HEADROOM:
-		testapp_headroom(test);
+	case TEST_FAILURE:
+		ksft_test_result_fail("FAIL: %s %s%s\n", mode_string(test), busy_poll_string(test),
+				      test->name);
 		break;
 	default:
-		break;
+		ksft_test_result_fail("FAIL: %s %s%s -- Unexpected returned value (%d)\n",
+				      mode_string(test), busy_poll_string(test), test->name, ret);
 	}
 
-	if (!test->fail)
-		ksft_test_result_pass("PASS: %s %s%s\n", mode_string(test), busy_poll_string(test),
-				      test->name);
-}
-
-static struct ifobject *ifobject_create(void)
-{
-	struct ifobject *ifobj;
-
-	ifobj = calloc(1, sizeof(struct ifobject));
-	if (!ifobj)
-		return NULL;
-
-	ifobj->xsk_arr = calloc(MAX_SOCKETS, sizeof(*ifobj->xsk_arr));
-	if (!ifobj->xsk_arr)
-		goto out_xsk_arr;
-
-	ifobj->umem = calloc(1, sizeof(*ifobj->umem));
-	if (!ifobj->umem)
-		goto out_umem;
-
-	ifobj->ns_fd = -1;
-
-	return ifobj;
-
-out_umem:
-	free(ifobj->xsk_arr);
-out_xsk_arr:
-	free(ifobj);
-	return NULL;
-}
-
-static void ifobject_delete(struct ifobject *ifobj)
-{
-	if (ifobj->ns_fd != -1)
-		close(ifobj->ns_fd);
-	free(ifobj->umem);
-	free(ifobj->xsk_arr);
-	free(ifobj);
+	pkt_stream_restore_default(test);
 }
 
-static bool is_xdp_supported(struct ifobject *ifobject)
+static bool is_xdp_supported(int ifindex)
 {
 	int flags = XDP_FLAGS_DRV_MODE;
 
@@ -1872,7 +300,6 @@ static bool is_xdp_supported(struct ifobject *ifobject)
 		BPF_MOV64_IMM(BPF_REG_0, XDP_PASS),
 		BPF_EXIT_INSN()
 	};
-	int ifindex = if_nametoindex(ifobject->ifname);
 	int prog_fd, insn_cnt = ARRAY_SIZE(insns);
 	int err;
 
@@ -1892,15 +319,28 @@ static bool is_xdp_supported(struct ifobject *ifobject)
 	return true;
 }
 
+static void print_tests(void)
+{
+	u32 i;
+
+	printf("Tests:\n");
+	for (i = 0; i < ARRAY_SIZE(tests); i++)
+		printf("%u: %s\n", i, tests[i].name);
+	for (i = ARRAY_SIZE(tests); i < ARRAY_SIZE(tests) + ARRAY_SIZE(ci_skip_tests); i++)
+		printf("%u: %s\n", i, ci_skip_tests[i - ARRAY_SIZE(tests)].name);
+}
+
 int main(int argc, char **argv)
 {
+	const size_t total_tests = ARRAY_SIZE(tests) + ARRAY_SIZE(ci_skip_tests);
 	struct pkt_stream *rx_pkt_stream_default;
 	struct pkt_stream *tx_pkt_stream_default;
 	struct ifobject *ifobj_tx, *ifobj_rx;
+	u32 i, j, failed_tests = 0, nb_tests;
 	int modes = TEST_MODE_SKB + 1;
-	u32 i, j, failed_tests = 0;
 	struct test_spec test;
-	bool shared_umem;
+	bool shared_netdev;
+	int ret;
 
 	/* Use libbpf 1.0 API mode */
 	libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
@@ -1915,49 +355,97 @@ int main(int argc, char **argv)
 	setlocale(LC_ALL, "");
 
 	parse_command_line(ifobj_tx, ifobj_rx, argc, argv);
-	shared_umem = !strcmp(ifobj_tx->ifname, ifobj_rx->ifname);
-
-	ifobj_tx->shared_umem = shared_umem;
-	ifobj_rx->shared_umem = shared_umem;
 
-	if (!validate_interface(ifobj_tx) || !validate_interface(ifobj_rx)) {
-		usage(basename(argv[0]));
+	if (opt_print_tests) {
+		print_tests();
+		ksft_exit_xpass();
+	}
+	if (opt_run_test != RUN_ALL_TESTS && opt_run_test >= total_tests) {
+		ksft_print_msg("Error: test %u does not exist.\n", opt_run_test);
 		ksft_exit_xfail();
 	}
 
-	init_iface(ifobj_tx, MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2,
-		   worker_testapp_validate_tx);
-	init_iface(ifobj_rx, MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1,
-		   worker_testapp_validate_rx);
+	shared_netdev = (ifobj_tx->ifindex == ifobj_rx->ifindex);
+	ifobj_tx->shared_umem = shared_netdev;
+	ifobj_rx->shared_umem = shared_netdev;
+
+	if (!validate_interface(ifobj_tx) || !validate_interface(ifobj_rx))
+		print_usage(argv);
 
-	if (is_xdp_supported(ifobj_tx)) {
+	if (is_xdp_supported(ifobj_tx->ifindex)) {
 		modes++;
 		if (ifobj_zc_avail(ifobj_tx))
 			modes++;
 	}
 
-	test_spec_init(&test, ifobj_tx, ifobj_rx, 0);
-	tx_pkt_stream_default = pkt_stream_generate(ifobj_tx->umem, DEFAULT_PKT_CNT, PKT_SIZE);
-	rx_pkt_stream_default = pkt_stream_generate(ifobj_rx->umem, DEFAULT_PKT_CNT, PKT_SIZE);
+	ret = get_hw_ring_size(ifobj_tx->ifname, &ifobj_tx->ring);
+	if (!ret) {
+		ifobj_tx->hw_ring_size_supp = true;
+		ifobj_tx->set_ring.default_tx = ifobj_tx->ring.tx_pending;
+		ifobj_tx->set_ring.default_rx = ifobj_tx->ring.rx_pending;
+	}
+
+	if (init_iface(ifobj_rx, worker_testapp_validate_rx) ||
+	    init_iface(ifobj_tx, worker_testapp_validate_tx)) {
+		ksft_print_msg("Error : can't initialize interfaces\n");
+		ksft_exit_xfail();
+	}
+
+	test_init(&test, ifobj_tx, ifobj_rx, 0, &tests[0]);
+	tx_pkt_stream_default = pkt_stream_generate(DEFAULT_PKT_CNT, MIN_PKT_SIZE);
+	rx_pkt_stream_default = pkt_stream_generate(DEFAULT_PKT_CNT, MIN_PKT_SIZE);
 	if (!tx_pkt_stream_default || !rx_pkt_stream_default)
 		exit_with_error(ENOMEM);
 	test.tx_pkt_stream_default = tx_pkt_stream_default;
 	test.rx_pkt_stream_default = rx_pkt_stream_default;
 
-	ksft_set_plan(modes * TEST_TYPE_MAX);
+	if (opt_run_test == RUN_ALL_TESTS)
+		nb_tests = total_tests;
+	else
+		nb_tests = 1;
+	if (opt_mode == TEST_MODE_ALL) {
+		ksft_set_plan(modes * nb_tests);
+	} else {
+		if (opt_mode == TEST_MODE_DRV && modes <= TEST_MODE_DRV) {
+			ksft_print_msg("Error: XDP_DRV mode not supported.\n");
+			ksft_exit_xfail();
+		}
+		if (opt_mode == TEST_MODE_ZC && modes <= TEST_MODE_ZC) {
+			ksft_print_msg("Error: zero-copy mode not supported.\n");
+			ksft_exit_xfail();
+		}
+
+		ksft_set_plan(nb_tests);
+	}
+
+	for (i = 0; i < modes; i++) {
+		if (opt_mode != TEST_MODE_ALL && i != opt_mode)
+			continue;
+
+		for (j = 0; j < total_tests; j++) {
+			if (opt_run_test != RUN_ALL_TESTS && j != opt_run_test)
+				continue;
 
-	for (i = 0; i < modes; i++)
-		for (j = 0; j < TEST_TYPE_MAX; j++) {
-			test_spec_init(&test, ifobj_tx, ifobj_rx, i);
-			run_pkt_test(&test, i, j);
+			if (j < ARRAY_SIZE(tests))
+				test_init(&test, ifobj_tx, ifobj_rx, i, &tests[j]);
+			else
+				test_init(&test, ifobj_tx, ifobj_rx, i,
+					  &ci_skip_tests[j - ARRAY_SIZE(tests)]);
+			run_pkt_test(&test);
 			usleep(USLEEP_MAX);
 
 			if (test.fail)
 				failed_tests++;
 		}
+	}
+
+	if (ifobj_tx->hw_ring_size_supp)
+		hw_ring_size_reset(ifobj_tx);
 
 	pkt_stream_delete(tx_pkt_stream_default);
 	pkt_stream_delete(rx_pkt_stream_default);
+	xsk_unload_xdp_programs(ifobj_tx);
+	xsk_unload_xdp_programs(ifobj_rx);
 	ifobject_delete(ifobj_tx);
 	ifobject_delete(ifobj_rx);
 
diff --git a/tools/testing/selftests/bpf/xskxceiver.h b/tools/testing/selftests/bpf/xskxceiver.h
index edb76d2def9f..3ca518df23ad 100644
--- a/tools/testing/selftests/bpf/xskxceiver.h
+++ b/tools/testing/selftests/bpf/xskxceiver.h
@@ -5,6 +5,11 @@
 #ifndef XSKXCEIVER_H_
 #define XSKXCEIVER_H_
 
+#include <limits.h>
+
+#include "xsk_xdp_progs.skel.h"
+#include "xsk_xdp_common.h"
+
 #ifndef SOL_XDP
 #define SOL_XDP 283
 #endif
@@ -17,165 +22,13 @@
 #define PF_XDP AF_XDP
 #endif
 
-#ifndef SO_BUSY_POLL_BUDGET
-#define SO_BUSY_POLL_BUDGET 70
-#endif
-
-#ifndef SO_PREFER_BUSY_POLL
-#define SO_PREFER_BUSY_POLL 69
-#endif
-
-#define TEST_PASS 0
-#define TEST_FAILURE -1
-#define TEST_CONTINUE 1
-#define MAX_INTERFACES 2
-#define MAX_INTERFACE_NAME_CHARS 16
-#define MAX_INTERFACES_NAMESPACE_CHARS 16
-#define MAX_SOCKETS 2
-#define MAX_TEST_NAME_SIZE 32
 #define MAX_TEARDOWN_ITER 10
-#define PKT_HDR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \
-			sizeof(struct udphdr))
-#define MIN_ETH_PKT_SIZE 64
-#define ETH_FCS_SIZE 4
-#define MIN_PKT_SIZE (MIN_ETH_PKT_SIZE - ETH_FCS_SIZE)
-#define PKT_SIZE (MIN_PKT_SIZE)
-#define IP_PKT_SIZE (PKT_SIZE - sizeof(struct ethhdr))
-#define IP_PKT_VER 0x4
-#define IP_PKT_TOS 0x9
-#define UDP_PKT_SIZE (IP_PKT_SIZE - sizeof(struct iphdr))
-#define UDP_PKT_DATA_SIZE (UDP_PKT_SIZE - sizeof(struct udphdr))
-#define USLEEP_MAX 10000
+#define MAX_ETH_JUMBO_SIZE 9000
 #define SOCK_RECONF_CTR 10
-#define BATCH_SIZE 64
-#define POLL_TMOUT 1000
-#define THREAD_TMOUT 3
-#define DEFAULT_PKT_CNT (4 * 1024)
-#define DEFAULT_UMEM_BUFFERS (DEFAULT_PKT_CNT / 4)
-#define UMEM_SIZE (DEFAULT_UMEM_BUFFERS * XSK_UMEM__DEFAULT_FRAME_SIZE)
 #define RX_FULL_RXQSIZE 32
 #define UMEM_HEADROOM_TEST_SIZE 128
-#define XSK_UMEM__INVALID_FRAME_SIZE (XSK_UMEM__DEFAULT_FRAME_SIZE + 1)
-
-#define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0)
-
-enum test_mode {
-	TEST_MODE_SKB,
-	TEST_MODE_DRV,
-	TEST_MODE_ZC,
-	TEST_MODE_MAX
-};
-
-enum test_type {
-	TEST_TYPE_RUN_TO_COMPLETION,
-	TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME,
-	TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT,
-	TEST_TYPE_RX_POLL,
-	TEST_TYPE_TX_POLL,
-	TEST_TYPE_POLL_RXQ_TMOUT,
-	TEST_TYPE_POLL_TXQ_TMOUT,
-	TEST_TYPE_UNALIGNED,
-	TEST_TYPE_ALIGNED_INV_DESC,
-	TEST_TYPE_ALIGNED_INV_DESC_2K_FRAME,
-	TEST_TYPE_UNALIGNED_INV_DESC,
-	TEST_TYPE_HEADROOM,
-	TEST_TYPE_TEARDOWN,
-	TEST_TYPE_BIDI,
-	TEST_TYPE_STATS_RX_DROPPED,
-	TEST_TYPE_STATS_TX_INVALID_DESCS,
-	TEST_TYPE_STATS_RX_FULL,
-	TEST_TYPE_STATS_FILL_EMPTY,
-	TEST_TYPE_BPF_RES,
-	TEST_TYPE_MAX
-};
-
-static bool opt_pkt_dump;
-static bool opt_verbose;
-
-struct xsk_umem_info {
-	struct xsk_ring_prod fq;
-	struct xsk_ring_cons cq;
-	struct xsk_umem *umem;
-	u32 num_frames;
-	u32 frame_headroom;
-	void *buffer;
-	u32 frame_size;
-	u32 base_addr;
-	bool unaligned_mode;
-};
-
-struct xsk_socket_info {
-	struct xsk_ring_cons rx;
-	struct xsk_ring_prod tx;
-	struct xsk_umem_info *umem;
-	struct xsk_socket *xsk;
-	u32 outstanding_tx;
-	u32 rxqsize;
-};
-
-struct pkt {
-	u64 addr;
-	u32 len;
-	u32 payload;
-	bool valid;
-};
-
-struct pkt_stream {
-	u32 nb_pkts;
-	u32 rx_pkt_nb;
-	struct pkt *pkts;
-	bool use_addr_for_fill;
-};
-
-struct ifobject;
-typedef int (*validation_func_t)(struct ifobject *ifobj);
-typedef void *(*thread_func_t)(void *arg);
-
-struct ifobject {
-	char ifname[MAX_INTERFACE_NAME_CHARS];
-	char nsname[MAX_INTERFACES_NAMESPACE_CHARS];
-	struct xsk_socket_info *xsk;
-	struct xsk_socket_info *xsk_arr;
-	struct xsk_umem_info *umem;
-	thread_func_t func_ptr;
-	validation_func_t validation_func;
-	struct pkt_stream *pkt_stream;
-	int ns_fd;
-	int xsk_map_fd;
-	u32 dst_ip;
-	u32 src_ip;
-	u32 xdp_flags;
-	u32 bind_flags;
-	u16 src_port;
-	u16 dst_port;
-	bool tx_on;
-	bool rx_on;
-	bool use_poll;
-	bool busy_poll;
-	bool use_fill_ring;
-	bool release_rx;
-	bool shared_umem;
-	u8 dst_mac[ETH_ALEN];
-	u8 src_mac[ETH_ALEN];
-};
-
-struct test_spec {
-	struct ifobject *ifobj_tx;
-	struct ifobject *ifobj_rx;
-	struct pkt_stream *tx_pkt_stream_default;
-	struct pkt_stream *rx_pkt_stream_default;
-	u16 total_steps;
-	u16 current_step;
-	u16 nb_sockets;
-	bool fail;
-	enum test_mode mode;
-	char name[MAX_TEST_NAME_SIZE];
-};
-
-pthread_barrier_t barr;
-pthread_mutex_t pacing_mutex = PTHREAD_MUTEX_INITIALIZER;
-pthread_cond_t pacing_cond = PTHREAD_COND_INITIALIZER;
-
-int pkts_in_flight;
+#define XSK_UMEM__INVALID_FRAME_SIZE (MAX_ETH_JUMBO_SIZE + 1)
+#define RUN_ALL_TESTS UINT_MAX
+#define NUM_MAC_ADDRESSES 4
 
 #endif				/* XSKXCEIVER_H_ */
diff --git a/tools/testing/selftests/breakpoints/breakpoint_test.c b/tools/testing/selftests/breakpoints/breakpoint_test.c
index 3266cc9293fe..1159d81890c2 100644
--- a/tools/testing/selftests/breakpoints/breakpoint_test.c
+++ b/tools/testing/selftests/breakpoints/breakpoint_test.c
@@ -18,7 +18,7 @@
 #include <errno.h>
 #include <string.h>
 
-#include "../kselftest.h"
+#include "kselftest.h"
 
 #define COUNT_ISN_BPS	4
 #define COUNT_WPS	4
@@ -284,9 +284,9 @@ static void check_success(const char *msg)
 	nr_tests++;
 
 	if (ret)
-		ksft_test_result_pass(msg);
+		ksft_test_result_pass("%s", msg);
 	else
-		ksft_test_result_fail(msg);
+		ksft_test_result_fail("%s", msg);
 }
 
 static void launch_instruction_breakpoints(char *buf, int local, int global)
diff --git a/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c b/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c
index e7041816085a..5fc0f37f3fd4 100644
--- a/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c
+++ b/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c
@@ -26,7 +26,7 @@
 #include <errno.h>
 #include <signal.h>
 
-#include "../kselftest.h"
+#include "kselftest.h"
 
 static volatile uint8_t var[96] __attribute__((__aligned__(32)));
 
diff --git a/tools/testing/selftests/breakpoints/step_after_suspend_test.c b/tools/testing/selftests/breakpoints/step_after_suspend_test.c
index 2cf6f10ab7c4..ca2aaab9e4ca 100644
--- a/tools/testing/selftests/breakpoints/step_after_suspend_test.c
+++ b/tools/testing/selftests/breakpoints/step_after_suspend_test.c
@@ -19,7 +19,7 @@
 #include <sys/types.h>
 #include <sys/wait.h>
 
-#include "../kselftest.h"
+#include "kselftest.h"
 
 void child(int cpu)
 {
@@ -89,7 +89,7 @@ int run_test(int cpu)
 
 	wpid = waitpid(pid, &status, __WALL);
 	if (wpid != pid) {
-		ksft_print_msg("waitpid() failed: $s\n", strerror(errno));
+		ksft_print_msg("waitpid() failed: %s\n", strerror(errno));
 		return KSFT_FAIL;
 	}
 	if (WIFEXITED(status)) {
@@ -127,23 +127,42 @@ int run_test(int cpu)
 	return KSFT_PASS;
 }
 
+/*
+ * Reads the suspend success count from sysfs.
+ * Returns the count on success or exits on failure.
+ */
+static int get_suspend_success_count_or_fail(void)
+{
+	FILE *fp;
+	int val;
+
+	fp = fopen("/sys/power/suspend_stats/success", "r");
+	if (!fp)
+		ksft_exit_fail_msg(
+			"Failed to open suspend_stats/success: %s\n",
+			strerror(errno));
+
+	if (fscanf(fp, "%d", &val) != 1) {
+		fclose(fp);
+		ksft_exit_fail_msg(
+			"Failed to read suspend success count\n");
+	}
+
+	fclose(fp);
+	return val;
+}
+
 void suspend(void)
 {
-	int power_state_fd;
-	struct sigevent event = {};
 	int timerfd;
 	int err;
+	int count_before;
+	int count_after;
 	struct itimerspec spec = {};
 
 	if (getuid() != 0)
 		ksft_exit_skip("Please run the test as root - Exiting.\n");
 
-	power_state_fd = open("/sys/power/state", O_RDWR);
-	if (power_state_fd < 0)
-		ksft_exit_fail_msg(
-			"open(\"/sys/power/state\") failed %s)\n",
-			strerror(errno));
-
 	timerfd = timerfd_create(CLOCK_BOOTTIME_ALARM, 0);
 	if (timerfd < 0)
 		ksft_exit_fail_msg("timerfd_create() failed\n");
@@ -153,11 +172,15 @@ void suspend(void)
 	if (err < 0)
 		ksft_exit_fail_msg("timerfd_settime() failed\n");
 
-	if (write(power_state_fd, "mem", strlen("mem")) != strlen("mem"))
+	count_before = get_suspend_success_count_or_fail();
+
+	system("(echo mem > /sys/power/state) 2> /dev/null");
+
+	count_after = get_suspend_success_count_or_fail();
+	if (count_after <= count_before)
 		ksft_exit_fail_msg("Failed to enter Suspend state\n");
 
 	close(timerfd);
-	close(power_state_fd);
 }
 
 int main(int argc, char **argv)
diff --git a/tools/testing/selftests/cachestat/.gitignore b/tools/testing/selftests/cachestat/.gitignore
new file mode 100644
index 000000000000..abbb13b6e96b
--- /dev/null
+++ b/tools/testing/selftests/cachestat/.gitignore
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+test_cachestat
+tmpshmcstat
diff --git a/tools/testing/selftests/cachestat/Makefile b/tools/testing/selftests/cachestat/Makefile
new file mode 100644
index 000000000000..778b54ebb036
--- /dev/null
+++ b/tools/testing/selftests/cachestat/Makefile
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+TEST_GEN_PROGS := test_cachestat
+
+CFLAGS += $(KHDR_INCLUDES)
+CFLAGS += -Wall
+LDLIBS += -lrt
+
+include ../lib.mk
diff --git a/tools/testing/selftests/cachestat/test_cachestat.c b/tools/testing/selftests/cachestat/test_cachestat.c
new file mode 100644
index 000000000000..542cd09cb443
--- /dev/null
+++ b/tools/testing/selftests/cachestat/test_cachestat.c
@@ -0,0 +1,365 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#define __SANE_USERSPACE_TYPES__ // Use ll64
+
+#include <stdio.h>
+#include <stdbool.h>
+#include <linux/kernel.h>
+#include <linux/magic.h>
+#include <linux/mman.h>
+#include <sys/mman.h>
+#include <sys/shm.h>
+#include <sys/syscall.h>
+#include <sys/vfs.h>
+#include <unistd.h>
+#include <string.h>
+#include <fcntl.h>
+#include <errno.h>
+
+#include "kselftest.h"
+
+#define NR_TESTS	9
+
+static const char * const dev_files[] = {
+	"/dev/zero", "/dev/null", "/dev/urandom",
+	"/proc/version", "/proc"
+};
+
+void print_cachestat(struct cachestat *cs)
+{
+	ksft_print_msg(
+	"Using cachestat: Cached: %llu, Dirty: %llu, Writeback: %llu, Evicted: %llu, Recently Evicted: %llu\n",
+	cs->nr_cache, cs->nr_dirty, cs->nr_writeback,
+	cs->nr_evicted, cs->nr_recently_evicted);
+}
+
+enum file_type {
+	FILE_MMAP,
+	FILE_SHMEM
+};
+
+bool write_exactly(int fd, size_t filesize)
+{
+	int random_fd = open("/dev/urandom", O_RDONLY);
+	char *cursor, *data;
+	int remained;
+	bool ret;
+
+	if (random_fd < 0) {
+		ksft_print_msg("Unable to access urandom.\n");
+		ret = false;
+		goto out;
+	}
+
+	data = malloc(filesize);
+	if (!data) {
+		ksft_print_msg("Unable to allocate data.\n");
+		ret = false;
+		goto close_random_fd;
+	}
+
+	remained = filesize;
+	cursor = data;
+
+	while (remained) {
+		ssize_t read_len = read(random_fd, cursor, remained);
+
+		if (read_len <= 0) {
+			ksft_print_msg("Unable to read from urandom.\n");
+			ret = false;
+			goto out_free_data;
+		}
+
+		remained -= read_len;
+		cursor += read_len;
+	}
+
+	/* write random data to fd */
+	remained = filesize;
+	cursor = data;
+	while (remained) {
+		ssize_t write_len = write(fd, cursor, remained);
+
+		if (write_len <= 0) {
+			ksft_print_msg("Unable write random data to file.\n");
+			ret = false;
+			goto out_free_data;
+		}
+
+		remained -= write_len;
+		cursor += write_len;
+	}
+
+	ret = true;
+out_free_data:
+	free(data);
+close_random_fd:
+	close(random_fd);
+out:
+	return ret;
+}
+
+/*
+ * fsync() is implemented via noop_fsync() on tmpfs. This makes the fsync()
+ * test fail below, so we need to check for test file living on a tmpfs.
+ */
+static bool is_on_tmpfs(int fd)
+{
+	struct statfs statfs_buf;
+
+	if (fstatfs(fd, &statfs_buf))
+		return false;
+
+	return statfs_buf.f_type == TMPFS_MAGIC;
+}
+
+/*
+ * Open/create the file at filename, (optionally) write random data to it
+ * (exactly num_pages), then test the cachestat syscall on this file.
+ *
+ * If test_fsync == true, fsync the file, then check the number of dirty
+ * pages.
+ */
+static int test_cachestat(const char *filename, bool write_random, bool create,
+			  bool test_fsync, unsigned long num_pages,
+			  int open_flags, mode_t open_mode)
+{
+	size_t PS = sysconf(_SC_PAGESIZE);
+	int filesize = num_pages * PS;
+	int ret = KSFT_PASS;
+	long syscall_ret;
+	struct cachestat cs;
+	struct cachestat_range cs_range = { 0, filesize };
+
+	int fd = open(filename, open_flags, open_mode);
+
+	if (fd == -1) {
+		ksft_print_msg("Unable to create/open file.\n");
+		ret = KSFT_FAIL;
+		goto out;
+	} else {
+		ksft_print_msg("Create/open %s\n", filename);
+	}
+
+	if (write_random) {
+		if (!write_exactly(fd, filesize)) {
+			ksft_print_msg("Unable to access urandom.\n");
+			ret = KSFT_FAIL;
+			goto out1;
+		}
+	}
+
+	syscall_ret = syscall(__NR_cachestat, fd, &cs_range, &cs, 0);
+
+	ksft_print_msg("Cachestat call returned %ld\n", syscall_ret);
+
+	if (syscall_ret) {
+		ksft_print_msg("Cachestat returned non-zero.\n");
+		ret = KSFT_FAIL;
+		goto out1;
+
+	} else {
+		print_cachestat(&cs);
+
+		if (write_random) {
+			if (cs.nr_cache + cs.nr_evicted != num_pages) {
+				ksft_print_msg(
+					"Total number of cached and evicted pages is off.\n");
+				ret = KSFT_FAIL;
+			}
+		}
+	}
+
+	if (test_fsync) {
+		if (is_on_tmpfs(fd)) {
+			ret = KSFT_SKIP;
+		} else if (fsync(fd)) {
+			ksft_print_msg("fsync fails.\n");
+			ret = KSFT_FAIL;
+		} else {
+			syscall_ret = syscall(__NR_cachestat, fd, &cs_range, &cs, 0);
+
+			ksft_print_msg("Cachestat call (after fsync) returned %ld\n",
+				syscall_ret);
+
+			if (!syscall_ret) {
+				print_cachestat(&cs);
+
+				if (cs.nr_dirty) {
+					ret = KSFT_FAIL;
+					ksft_print_msg(
+						"Number of dirty should be zero after fsync.\n");
+				}
+			} else {
+				ksft_print_msg("Cachestat (after fsync) returned non-zero.\n");
+				ret = KSFT_FAIL;
+				goto out1;
+			}
+		}
+	}
+
+out1:
+	close(fd);
+
+	if (create)
+		remove(filename);
+out:
+	return ret;
+}
+const char *file_type_str(enum file_type type)
+{
+	switch (type) {
+	case FILE_SHMEM:
+		return "shmem";
+	case FILE_MMAP:
+		return "mmap";
+	default:
+		return "unknown";
+	}
+}
+
+
+bool run_cachestat_test(enum file_type type)
+{
+	size_t PS = sysconf(_SC_PAGESIZE);
+	size_t filesize = PS * 512 * 2; /* 2 2MB huge pages */
+	int syscall_ret;
+	size_t compute_len = PS * 512;
+	struct cachestat_range cs_range = { PS, compute_len };
+	char *filename = "tmpshmcstat", *map;
+	struct cachestat cs;
+	bool ret = true;
+	int fd;
+	unsigned long num_pages = compute_len / PS;
+	if (type == FILE_SHMEM)
+		fd = shm_open(filename, O_CREAT | O_RDWR, 0600);
+	else
+		fd = open(filename, O_RDWR | O_CREAT | O_TRUNC, 0666);
+
+	if (fd < 0) {
+		ksft_print_msg("Unable to create %s file.\n",
+				file_type_str(type));
+		ret = false;
+		goto out;
+	}
+
+	if (ftruncate(fd, filesize)) {
+		ksft_print_msg("Unable to truncate %s file.\n",file_type_str(type));
+		ret = false;
+		goto close_fd;
+	}
+	switch (type) {
+	case FILE_SHMEM:
+		if (!write_exactly(fd, filesize)) {
+			ksft_print_msg("Unable to write to file.\n");
+			ret = false;
+			goto close_fd;
+		}
+		break;
+	case FILE_MMAP:
+		map = mmap(NULL, filesize, PROT_READ | PROT_WRITE,
+				 MAP_SHARED, fd, 0);
+
+		if (map == MAP_FAILED) {
+			ksft_print_msg("mmap failed.\n");
+			ret = false;
+			goto close_fd;
+		}
+		for (int i = 0; i < filesize; i++)
+			map[i] = 'A';
+		break;
+	default:
+		ksft_print_msg("Unsupported file type.\n");
+		ret = false;
+		goto close_fd;
+	}
+	syscall_ret = syscall(__NR_cachestat, fd, &cs_range, &cs, 0);
+
+	if (syscall_ret) {
+		ksft_print_msg("Cachestat returned non-zero.\n");
+		ret = false;
+		goto close_fd;
+	} else {
+		print_cachestat(&cs);
+		if (cs.nr_cache + cs.nr_evicted != num_pages) {
+			ksft_print_msg(
+				"Total number of cached and evicted pages is off.\n");
+			ret = false;
+		}
+	}
+
+close_fd:
+	shm_unlink(filename);
+out:
+	return ret;
+}
+
+int main(void)
+{
+	int ret;
+
+	ksft_print_header();
+
+	ret = syscall(__NR_cachestat, -1, NULL, NULL, 0);
+	if (ret == -1 && errno == ENOSYS)
+		ksft_exit_skip("cachestat syscall not available\n");
+
+	ksft_set_plan(NR_TESTS);
+
+	if (ret == -1 && errno == EBADF) {
+		ksft_test_result_pass("bad file descriptor recognized\n");
+		ret = 0;
+	} else {
+		ksft_test_result_fail("bad file descriptor ignored\n");
+		ret = 1;
+	}
+
+	for (int i = 0; i < 5; i++) {
+		const char *dev_filename = dev_files[i];
+
+		if (test_cachestat(dev_filename, false, false, false,
+			4, O_RDONLY, 0400) == KSFT_PASS)
+			ksft_test_result_pass("cachestat works with %s\n", dev_filename);
+		else {
+			ksft_test_result_fail("cachestat fails with %s\n", dev_filename);
+			ret = 1;
+		}
+	}
+
+	if (test_cachestat("tmpfilecachestat", true, true,
+		false, 4, O_CREAT | O_RDWR, 0600) == KSFT_PASS)
+		ksft_test_result_pass("cachestat works with a normal file\n");
+	else {
+		ksft_test_result_fail("cachestat fails with normal file\n");
+		ret = 1;
+	}
+
+	switch (test_cachestat("tmpfilecachestat", true, true,
+		true, 4, O_CREAT | O_RDWR, 0600)) {
+	case KSFT_FAIL:
+		ksft_test_result_fail("cachestat fsync fails with normal file\n");
+		ret = KSFT_FAIL;
+		break;
+	case KSFT_PASS:
+		ksft_test_result_pass("cachestat fsync works with a normal file\n");
+		break;
+	case KSFT_SKIP:
+		ksft_test_result_skip("tmpfilecachestat is on tmpfs\n");
+		break;
+	}
+
+	if (run_cachestat_test(FILE_SHMEM))
+		ksft_test_result_pass("cachestat works with a shmem file\n");
+	else {
+		ksft_test_result_fail("cachestat fails with a shmem file\n");
+		ret = 1;
+	}
+
+	if (run_cachestat_test(FILE_MMAP))
+		ksft_test_result_pass("cachestat works with a mmap file\n");
+	else {
+		ksft_test_result_fail("cachestat fails with a mmap file\n");
+		ret = 1;
+	}
+	return ret;
+}
diff --git a/tools/testing/selftests/capabilities/Makefile b/tools/testing/selftests/capabilities/Makefile
index 6e9d98d457d5..411ac098308f 100644
--- a/tools/testing/selftests/capabilities/Makefile
+++ b/tools/testing/selftests/capabilities/Makefile
@@ -2,7 +2,7 @@
 TEST_GEN_FILES := validate_cap
 TEST_GEN_PROGS := test_execve
 
-CFLAGS += -O2 -g -std=gnu99 -Wall
+CFLAGS += -O2 -g -std=gnu99 -Wall $(KHDR_INCLUDES)
 LDLIBS += -lcap-ng -lrt -ldl
 
 include ../lib.mk
diff --git a/tools/testing/selftests/capabilities/test_execve.c b/tools/testing/selftests/capabilities/test_execve.c
index df0ef02b4036..46fc8d46b6e6 100644
--- a/tools/testing/selftests/capabilities/test_execve.c
+++ b/tools/testing/selftests/capabilities/test_execve.c
@@ -18,15 +18,7 @@
 #include <sys/prctl.h>
 #include <sys/stat.h>
 
-#include "../kselftest.h"
-
-#ifndef PR_CAP_AMBIENT
-#define PR_CAP_AMBIENT			47
-# define PR_CAP_AMBIENT_IS_SET		1
-# define PR_CAP_AMBIENT_RAISE		2
-# define PR_CAP_AMBIENT_LOWER		3
-# define PR_CAP_AMBIENT_CLEAR_ALL	4
-#endif
+#include "kselftest.h"
 
 static int nerrs;
 static pid_t mpid;	/*  main() pid is used to avoid duplicate test counts */
@@ -90,17 +82,13 @@ static bool create_and_enter_ns(uid_t inner_uid)
 {
 	uid_t outer_uid;
 	gid_t outer_gid;
-	int i;
+	int i, ret;
 	bool have_outer_privilege;
 
 	outer_uid = getuid();
 	outer_gid = getgid();
 
-	/*
-	 * TODO: If we're already root, we could skip creating the userns.
-	 */
-
-	if (unshare(CLONE_NEWNS) == 0) {
+	if (outer_uid == 0 && unshare(CLONE_NEWNS) == 0) {
 		ksft_print_msg("[NOTE]\tUsing global UIDs for tests\n");
 		if (prctl(PR_SET_KEEPCAPS, 1, 0, 0, 0) != 0)
 			ksft_exit_fail_msg("PR_SET_KEEPCAPS - %s\n",
@@ -109,7 +97,10 @@ static bool create_and_enter_ns(uid_t inner_uid)
 			ksft_exit_fail_msg("setresuid - %s\n", strerror(errno));
 
 		// Re-enable effective caps
-		capng_get_caps_process();
+		ret = capng_get_caps_process();
+		if (ret == -1)
+			ksft_exit_fail_msg("capng_get_caps_process failed\n");
+
 		for (i = 0; i < CAP_LAST_CAP; i++)
 			if (capng_have_capability(CAPNG_PERMITTED, i))
 				capng_update(CAPNG_ADD, CAPNG_EFFECTIVE, i);
@@ -219,6 +210,7 @@ static void exec_validate_cap(bool eff, bool perm, bool inh, bool ambient)
 
 static int do_tests(int uid, const char *our_path)
 {
+	int ret;
 	bool have_outer_privilege = create_and_enter_ns(uid);
 
 	int ourpath_fd = open(our_path, O_RDONLY | O_DIRECTORY);
@@ -262,7 +254,9 @@ static int do_tests(int uid, const char *our_path)
 			ksft_exit_fail_msg("chmod - %s\n", strerror(errno));
 	}
 
-	capng_get_caps_process();
+	ret = capng_get_caps_process();
+	if (ret == -1)
+		ksft_exit_fail_msg("capng_get_caps_process failed\n");
 
 	/* Make sure that i starts out clear */
 	capng_update(CAPNG_DROP, CAPNG_INHERITABLE, CAP_NET_BIND_SERVICE);
diff --git a/tools/testing/selftests/capabilities/validate_cap.c b/tools/testing/selftests/capabilities/validate_cap.c
index cdfc94268fe6..cef1d9937b9f 100644
--- a/tools/testing/selftests/capabilities/validate_cap.c
+++ b/tools/testing/selftests/capabilities/validate_cap.c
@@ -7,15 +7,7 @@
 #include <sys/prctl.h>
 #include <sys/auxv.h>
 
-#include "../kselftest.h"
-
-#ifndef PR_CAP_AMBIENT
-#define PR_CAP_AMBIENT			47
-# define PR_CAP_AMBIENT_IS_SET		1
-# define PR_CAP_AMBIENT_RAISE		2
-# define PR_CAP_AMBIENT_LOWER		3
-# define PR_CAP_AMBIENT_CLEAR_ALL	4
-#endif
+#include "kselftest.h"
 
 #if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ >= 19)
 # define HAVE_GETAUXVAL
@@ -36,6 +28,7 @@ static bool bool_arg(char **argv, int i)
 int main(int argc, char **argv)
 {
 	const char *atsec = "";
+	int ret;
 
 	/*
 	 * Be careful just in case a setgid or setcapped copy of this
@@ -52,7 +45,11 @@ int main(int argc, char **argv)
 		atsec = " (AT_SECURE is not set)";
 #endif
 
-	capng_get_caps_process();
+	ret = capng_get_caps_process();
+	if (ret == -1) {
+		ksft_print_msg("capng_get_caps_process failed\n");
+		return 1;
+	}
 
 	if (capng_have_capability(CAPNG_EFFECTIVE, CAP_NET_BIND_SERVICE) != bool_arg(argv, 1)) {
 		ksft_print_msg("Wrong effective state%s\n", atsec);
diff --git a/tools/testing/selftests/cgroup/.gitignore b/tools/testing/selftests/cgroup/.gitignore
index c4a57e69f749..952e4448bf07 100644
--- a/tools/testing/selftests/cgroup/.gitignore
+++ b/tools/testing/selftests/cgroup/.gitignore
@@ -1,8 +1,12 @@
 # SPDX-License-Identifier: GPL-2.0-only
-test_memcontrol
 test_core
+test_cpu
+test_cpuset
 test_freezer
-test_kmem
+test_hugetlb_memcg
 test_kill
-test_cpu
+test_kmem
+test_memcontrol
+test_pids
+test_zswap
 wait_inotify
diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile
index 3d263747d2ad..e01584c2189a 100644
--- a/tools/testing/selftests/cgroup/Makefile
+++ b/tools/testing/selftests/cgroup/Makefile
@@ -4,22 +4,32 @@ CFLAGS += -Wall -pthread
 all: ${HELPER_PROGS}
 
 TEST_FILES     := with_stress.sh
-TEST_PROGS     := test_stress.sh test_cpuset_prs.sh
+TEST_PROGS     := test_stress.sh test_cpuset_prs.sh test_cpuset_v1_hp.sh
 TEST_GEN_FILES := wait_inotify
-TEST_GEN_PROGS = test_memcontrol
-TEST_GEN_PROGS += test_kmem
-TEST_GEN_PROGS += test_core
+# Keep the lists lexicographically sorted
+TEST_GEN_PROGS  = test_core
+TEST_GEN_PROGS += test_cpu
+TEST_GEN_PROGS += test_cpuset
 TEST_GEN_PROGS += test_freezer
+TEST_GEN_PROGS += test_hugetlb_memcg
 TEST_GEN_PROGS += test_kill
-TEST_GEN_PROGS += test_cpu
+TEST_GEN_PROGS += test_kmem
+TEST_GEN_PROGS += test_memcontrol
+TEST_GEN_PROGS += test_pids
+TEST_GEN_PROGS += test_zswap
 
 LOCAL_HDRS += $(selfdir)/clone3/clone3_selftests.h $(selfdir)/pidfd/pidfd.h
 
 include ../lib.mk
+include lib/libcgroup.mk
 
-$(OUTPUT)/test_memcontrol: cgroup_util.c
-$(OUTPUT)/test_kmem: cgroup_util.c
-$(OUTPUT)/test_core: cgroup_util.c
-$(OUTPUT)/test_freezer: cgroup_util.c
-$(OUTPUT)/test_kill: cgroup_util.c
-$(OUTPUT)/test_cpu: cgroup_util.c
+$(OUTPUT)/test_core: $(LIBCGROUP_O)
+$(OUTPUT)/test_cpu: $(LIBCGROUP_O)
+$(OUTPUT)/test_cpuset: $(LIBCGROUP_O)
+$(OUTPUT)/test_freezer: $(LIBCGROUP_O)
+$(OUTPUT)/test_hugetlb_memcg: $(LIBCGROUP_O)
+$(OUTPUT)/test_kill: $(LIBCGROUP_O)
+$(OUTPUT)/test_kmem: $(LIBCGROUP_O)
+$(OUTPUT)/test_memcontrol: $(LIBCGROUP_O)
+$(OUTPUT)/test_pids: $(LIBCGROUP_O)
+$(OUTPUT)/test_zswap: $(LIBCGROUP_O)
diff --git a/tools/testing/selftests/cgroup/config b/tools/testing/selftests/cgroup/config
index 97d549ee894f..39f979690dd3 100644
--- a/tools/testing/selftests/cgroup/config
+++ b/tools/testing/selftests/cgroup/config
@@ -3,5 +3,4 @@ CONFIG_CGROUP_CPUACCT=y
 CONFIG_CGROUP_FREEZER=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_MEMCG=y
-CONFIG_MEMCG_KMEM=y
 CONFIG_PAGE_COUNTER=y
diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/lib/cgroup_util.c
index e8bbbdb77e0d..44c52f620fda 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/lib/cgroup_util.c
@@ -17,10 +17,12 @@
 #include <unistd.h>
 
 #include "cgroup_util.h"
-#include "../clone3/clone3_selftests.h"
+#include "../../clone3/clone3_selftests.h"
+
+bool cg_test_v1_named;
 
 /* Returns read len on success, or -errno on failure. */
-static ssize_t read_text(const char *path, char *buf, size_t max_len)
+ssize_t read_text(const char *path, char *buf, size_t max_len)
 {
 	ssize_t len;
 	int fd;
@@ -39,7 +41,7 @@ static ssize_t read_text(const char *path, char *buf, size_t max_len)
 }
 
 /* Returns written len on success, or -errno on failure. */
-static ssize_t write_text(const char *path, char *buf, ssize_t len)
+ssize_t write_text(const char *path, char *buf, ssize_t len)
 {
 	int fd;
 
@@ -141,6 +143,16 @@ long cg_read_long(const char *cgroup, const char *control)
 	return atol(buf);
 }
 
+long cg_read_long_fd(int fd)
+{
+	char buf[128];
+
+	if (pread(fd, buf, sizeof(buf), 0) <= 0)
+		return -1;
+
+	return atol(buf);
+}
+
 long cg_read_key_long(const char *cgroup, const char *control, const char *key)
 {
 	char buf[PAGE_SIZE];
@@ -183,6 +195,18 @@ int cg_write(const char *cgroup, const char *control, char *buf)
 	return ret == len ? 0 : ret;
 }
 
+/*
+ * Returns fd on success, or -1 on failure.
+ * (fd should be closed with close() as usual)
+ */
+int cg_open(const char *cgroup, const char *control, int flags)
+{
+	char path[PATH_MAX];
+
+	snprintf(path, sizeof(path), "%s/%s", cgroup, control);
+	return open(path, flags);
+}
+
 int cg_write_numeric(const char *cgroup, const char *control, long value)
 {
 	char buf[64];
@@ -195,10 +219,11 @@ int cg_write_numeric(const char *cgroup, const char *control, long value)
 	return cg_write(cgroup, control, buf);
 }
 
-int cg_find_unified_root(char *root, size_t len)
+static int cg_find_root(char *root, size_t len, const char *controller,
+			bool *nsdelegate)
 {
 	char buf[10 * PAGE_SIZE];
-	char *fs, *mount, *type;
+	char *fs, *mount, *type, *options;
 	const char delim[] = "\n\t ";
 
 	if (read_text("/proc/self/mounts", buf, sizeof(buf)) <= 0)
@@ -211,19 +236,40 @@ int cg_find_unified_root(char *root, size_t len)
 	for (fs = strtok(buf, delim); fs; fs = strtok(NULL, delim)) {
 		mount = strtok(NULL, delim);
 		type = strtok(NULL, delim);
+		options = strtok(NULL, delim);
 		strtok(NULL, delim);
 		strtok(NULL, delim);
-		strtok(NULL, delim);
-
-		if (strcmp(type, "cgroup2") == 0) {
-			strncpy(root, mount, len);
-			return 0;
+		if (strcmp(type, "cgroup") == 0) {
+			if (!controller || !strstr(options, controller))
+				continue;
+		} else if (strcmp(type, "cgroup2") == 0) {
+			if (controller &&
+					cg_read_strstr(mount, "cgroup.controllers", controller))
+				continue;
+		} else {
+			continue;
 		}
+		strncpy(root, mount, len);
+
+		if (nsdelegate)
+			*nsdelegate = !!strstr(options, "nsdelegate");
+		return 0;
+
 	}
 
 	return -1;
 }
 
+int cg_find_controller_root(char *root, size_t len, const char *controller)
+{
+	return cg_find_root(root, len, controller, NULL);
+}
+
+int cg_find_unified_root(char *root, size_t len, bool *nsdelegate)
+{
+	return cg_find_root(root, len, NULL, nsdelegate);
+}
+
 int cg_create(const char *cgroup)
 {
 	return mkdir(cgroup, 0755);
@@ -286,6 +332,8 @@ int cg_destroy(const char *cgroup)
 {
 	int ret;
 
+	if (!cgroup)
+		return 0;
 retry:
 	ret = rmdir(cgroup);
 	if (ret && errno == EBUSY) {
@@ -315,7 +363,7 @@ int cg_enter_current(const char *cgroup)
 
 int cg_enter_current_thread(const char *cgroup)
 {
-	return cg_write(cgroup, "cgroup.threads", "0");
+	return cg_write(cgroup, CG_THREADS_FILE, "0");
 }
 
 int cg_run(const char *cgroup,
@@ -462,94 +510,28 @@ int cg_run_nowait(const char *cgroup,
 	return pid;
 }
 
-int get_temp_fd(void)
-{
-	return open(".", O_TMPFILE | O_RDWR | O_EXCL);
-}
-
-int alloc_pagecache(int fd, size_t size)
-{
-	char buf[PAGE_SIZE];
-	struct stat st;
-	int i;
-
-	if (fstat(fd, &st))
-		goto cleanup;
-
-	size += st.st_size;
-
-	if (ftruncate(fd, size))
-		goto cleanup;
-
-	for (i = 0; i < size; i += sizeof(buf))
-		read(fd, buf, sizeof(buf));
-
-	return 0;
-
-cleanup:
-	return -1;
-}
-
-int alloc_anon(const char *cgroup, void *arg)
+int proc_mount_contains(const char *option)
 {
-	size_t size = (unsigned long)arg;
-	char *buf, *ptr;
+	char buf[4 * PAGE_SIZE];
+	ssize_t read;
 
-	buf = malloc(size);
-	for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
-		*ptr = 0;
+	read = read_text("/proc/mounts", buf, sizeof(buf));
+	if (read < 0)
+		return read;
 
-	free(buf);
-	return 0;
+	return strstr(buf, option) != NULL;
 }
 
-int is_swap_enabled(void)
+int cgroup_feature(const char *feature)
 {
 	char buf[PAGE_SIZE];
-	const char delim[] = "\n";
-	int cnt = 0;
-	char *line;
-
-	if (read_text("/proc/swaps", buf, sizeof(buf)) <= 0)
-		return -1;
-
-	for (line = strtok(buf, delim); line; line = strtok(NULL, delim))
-		cnt++;
-
-	return cnt > 1;
-}
-
-int set_oom_adj_score(int pid, int score)
-{
-	char path[PATH_MAX];
-	int fd, len;
-
-	sprintf(path, "/proc/%d/oom_score_adj", pid);
-
-	fd = open(path, O_WRONLY | O_APPEND);
-	if (fd < 0)
-		return fd;
-
-	len = dprintf(fd, "%d", score);
-	if (len < 0) {
-		close(fd);
-		return len;
-	}
-
-	close(fd);
-	return 0;
-}
-
-int proc_mount_contains(const char *option)
-{
-	char buf[4 * PAGE_SIZE];
 	ssize_t read;
 
-	read = read_text("/proc/mounts", buf, sizeof(buf));
+	read = read_text("/sys/kernel/cgroup/features", buf, sizeof(buf));
 	if (read < 0)
 		return read;
 
-	return strstr(buf, option) != NULL;
+	return strstr(buf, feature) != NULL;
 }
 
 ssize_t proc_read_text(int pid, bool thread, const char *item, char *buf, size_t size)
diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
index c92df4e5d395..7ab2824ed7b5 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.h
+++ b/tools/testing/selftests/cgroup/lib/include/cgroup_util.h
@@ -2,24 +2,54 @@
 #include <stdbool.h>
 #include <stdlib.h>
 
-#include "../kselftest.h"
-
+#ifndef PAGE_SIZE
 #define PAGE_SIZE 4096
+#endif
 
 #define MB(x) (x << 20)
 
 #define USEC_PER_SEC	1000000L
 #define NSEC_PER_SEC	1000000000L
 
+#define TEST_UID	65534 /* usually nobody, any !root is fine */
+
+#define CG_THREADS_FILE (!cg_test_v1_named ? "cgroup.threads" : "tasks")
+#define CG_NAMED_NAME "selftest"
+#define CG_PATH_FORMAT (!cg_test_v1_named ? "0::%s" : (":name=" CG_NAMED_NAME ":%s"))
+
 /*
  * Checks if two given values differ by less than err% of their sum.
  */
 static inline int values_close(long a, long b, int err)
 {
-	return abs(a - b) <= (a + b) / 100 * err;
+	return labs(a - b) <= (a + b) / 100 * err;
 }
 
-extern int cg_find_unified_root(char *root, size_t len);
+/*
+ * Checks if two given values differ by less than err% of their sum and assert
+ * with detailed debug info if not.
+ */
+static inline int values_close_report(long a, long b, int err)
+{
+	long diff  = labs(a - b);
+	long limit = (a + b) / 100 * err;
+	double actual_err = (a + b) ? (100.0 * diff / (a + b)) : 0.0;
+	int close = diff <= limit;
+
+	if (!close)
+		fprintf(stderr,
+			"[FAIL] actual=%ld expected=%ld | diff=%ld | limit=%ld | "
+			"tolerance=%d%% | actual_error=%.2f%%\n",
+			a, b, diff, limit, err, actual_err);
+
+	return close;
+}
+
+extern ssize_t read_text(const char *path, char *buf, size_t max_len);
+extern ssize_t write_text(const char *path, char *buf, ssize_t len);
+
+extern int cg_find_controller_root(char *root, size_t len, const char *controller);
+extern int cg_find_unified_root(char *root, size_t len, bool *nsdelegate);
 extern char *cg_name(const char *root, const char *name);
 extern char *cg_name_indexed(const char *root, const char *name, int index);
 extern char *cg_control(const char *cgroup, const char *control);
@@ -32,9 +62,11 @@ extern int cg_read_strcmp(const char *cgroup, const char *control,
 extern int cg_read_strstr(const char *cgroup, const char *control,
 			  const char *needle);
 extern long cg_read_long(const char *cgroup, const char *control);
+extern long cg_read_long_fd(int fd);
 long cg_read_key_long(const char *cgroup, const char *control, const char *key);
 extern long cg_read_lc(const char *cgroup, const char *control);
 extern int cg_write(const char *cgroup, const char *control, char *buf);
+extern int cg_open(const char *cgroup, const char *control, int flags);
 int cg_write_numeric(const char *cgroup, const char *control, long value);
 extern int cg_run(const char *cgroup,
 		  int (*fn)(const char *cgroup, void *arg),
@@ -45,14 +77,10 @@ extern int cg_enter_current_thread(const char *cgroup);
 extern int cg_run_nowait(const char *cgroup,
 			 int (*fn)(const char *cgroup, void *arg),
 			 void *arg);
-extern int get_temp_fd(void);
-extern int alloc_pagecache(int fd, size_t size);
-extern int alloc_anon(const char *cgroup, void *arg);
-extern int is_swap_enabled(void);
-extern int set_oom_adj_score(int pid, int score);
 extern int cg_wait_for_proc_count(const char *cgroup, int count);
 extern int cg_killall(const char *cgroup);
 int proc_mount_contains(const char *option);
+int cgroup_feature(const char *feature);
 extern ssize_t proc_read_text(int pid, bool thread, const char *item, char *buf, size_t size);
 extern int proc_read_strstr(int pid, bool thread, const char *item, const char *needle);
 extern pid_t clone_into_cgroup(int cgroup_fd);
@@ -62,3 +90,4 @@ extern int dirfd_open_opath(const char *dir);
 extern int cg_prepare_for_wait(const char *cgroup);
 extern int memcg_prepare_for_wait(const char *cgroup);
 extern int cg_wait_for(int fd);
+extern bool cg_test_v1_named;
diff --git a/tools/testing/selftests/cgroup/lib/libcgroup.mk b/tools/testing/selftests/cgroup/lib/libcgroup.mk
new file mode 100644
index 000000000000..7a73007204c3
--- /dev/null
+++ b/tools/testing/selftests/cgroup/lib/libcgroup.mk
@@ -0,0 +1,19 @@
+CGROUP_DIR := $(selfdir)/cgroup
+
+LIBCGROUP_C := lib/cgroup_util.c
+
+LIBCGROUP_O := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBCGROUP_C))
+
+LIBCGROUP_O_DIRS := $(shell dirname $(LIBCGROUP_O) | uniq)
+
+CFLAGS += -I$(CGROUP_DIR)/lib/include
+
+EXTRA_HDRS := $(selfdir)/clone3/clone3_selftests.h
+
+$(LIBCGROUP_O_DIRS):
+	mkdir -p $@
+
+$(LIBCGROUP_O): $(OUTPUT)/%.o : $(CGROUP_DIR)/%.c $(EXTRA_HDRS) $(LIBCGROUP_O_DIRS)
+	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
+
+EXTRA_CLEAN += $(LIBCGROUP_O)
diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c
index 600123503063..102262555a59 100644
--- a/tools/testing/selftests/cgroup/test_core.c
+++ b/tools/testing/selftests/cgroup/test_core.c
@@ -5,6 +5,8 @@
 #include <linux/sched.h>
 #include <sys/types.h>
 #include <sys/mman.h>
+#include <sys/mount.h>
+#include <sys/stat.h>
 #include <sys/wait.h>
 #include <unistd.h>
 #include <fcntl.h>
@@ -15,9 +17,14 @@
 #include <string.h>
 #include <pthread.h>
 
-#include "../kselftest.h"
+#include "kselftest.h"
 #include "cgroup_util.h"
 
+static bool nsdelegate;
+#ifndef CLONE_NEWCGROUP
+#define CLONE_NEWCGROUP 0
+#endif
+
 static int touch_anon(char *buf, size_t size)
 {
 	int fd;
@@ -146,6 +153,9 @@ static int test_cgcore_populated(const char *root)
 	int cgroup_fd = -EBADF;
 	pid_t pid;
 
+	if (cg_test_v1_named)
+		return KSFT_SKIP;
+
 	cg_test_a = cg_name(root, "cg_test_a");
 	cg_test_b = cg_name(root, "cg_test_a/cg_test_b");
 	cg_test_c = cg_name(root, "cg_test_a/cg_test_b/cg_test_c");
@@ -275,6 +285,9 @@ static int test_cgcore_invalid_domain(const char *root)
 	int ret = KSFT_FAIL;
 	char *grandparent = NULL, *parent = NULL, *child = NULL;
 
+	if (cg_test_v1_named)
+		return KSFT_SKIP;
+
 	grandparent = cg_name(root, "cg_test_grandparent");
 	parent = cg_name(root, "cg_test_grandparent/cg_test_parent");
 	child = cg_name(root, "cg_test_grandparent/cg_test_parent/cg_test_child");
@@ -337,6 +350,9 @@ static int test_cgcore_parent_becomes_threaded(const char *root)
 	int ret = KSFT_FAIL;
 	char *parent = NULL, *child = NULL;
 
+	if (cg_test_v1_named)
+		return KSFT_SKIP;
+
 	parent = cg_name(root, "cg_test_parent");
 	child = cg_name(root, "cg_test_parent/cg_test_child");
 	if (!parent || !child)
@@ -376,7 +392,8 @@ static int test_cgcore_no_internal_process_constraint_on_threads(const char *roo
 	int ret = KSFT_FAIL;
 	char *parent = NULL, *child = NULL;
 
-	if (cg_read_strstr(root, "cgroup.controllers", "cpu") ||
+	if (cg_test_v1_named ||
+	    cg_read_strstr(root, "cgroup.controllers", "cpu") ||
 	    cg_write(root, "cgroup.subtree_control", "+cpu")) {
 		ret = KSFT_SKIP;
 		goto cleanup;
@@ -428,6 +445,9 @@ static int test_cgcore_top_down_constraint_enable(const char *root)
 	int ret = KSFT_FAIL;
 	char *parent = NULL, *child = NULL;
 
+	if (cg_test_v1_named)
+		return KSFT_SKIP;
+
 	parent = cg_name(root, "cg_test_parent");
 	child = cg_name(root, "cg_test_parent/cg_test_child");
 	if (!parent || !child)
@@ -463,6 +483,9 @@ static int test_cgcore_top_down_constraint_disable(const char *root)
 	int ret = KSFT_FAIL;
 	char *parent = NULL, *child = NULL;
 
+	if (cg_test_v1_named)
+		return KSFT_SKIP;
+
 	parent = cg_name(root, "cg_test_parent");
 	child = cg_name(root, "cg_test_parent/cg_test_child");
 	if (!parent || !child)
@@ -504,6 +527,9 @@ static int test_cgcore_internal_process_constraint(const char *root)
 	int ret = KSFT_FAIL;
 	char *parent = NULL, *child = NULL;
 
+	if (cg_test_v1_named)
+		return KSFT_SKIP;
+
 	parent = cg_name(root, "cg_test_parent");
 	child = cg_name(root, "cg_test_parent/cg_test_child");
 	if (!parent || !child)
@@ -571,7 +597,7 @@ static int test_cgcore_proc_migration(const char *root)
 	}
 
 	cg_enter_current(dst);
-	if (cg_read_lc(dst, "cgroup.threads") != n_threads + 1)
+	if (cg_read_lc(dst, CG_THREADS_FILE) != n_threads + 1)
 		goto cleanup;
 
 	ret = KSFT_PASS;
@@ -603,7 +629,7 @@ static void *migrating_thread_fn(void *arg)
 	char lines[3][PATH_MAX];
 
 	for (g = 1; g < 3; ++g)
-		snprintf(lines[g], sizeof(lines[g]), "0::%s", grps[g] + strlen(grps[0]));
+		snprintf(lines[g], sizeof(lines[g]), CG_PATH_FORMAT, grps[g] + strlen(grps[0]));
 
 	for (i = 0; i < n_iterations; ++i) {
 		cg_enter_current_thread(grps[(i % 2) + 1]);
@@ -640,10 +666,12 @@ static int test_cgcore_thread_migration(const char *root)
 	if (cg_create(grps[2]))
 		goto cleanup;
 
-	if (cg_write(grps[1], "cgroup.type", "threaded"))
-		goto cleanup;
-	if (cg_write(grps[2], "cgroup.type", "threaded"))
-		goto cleanup;
+	if (!cg_test_v1_named) {
+		if (cg_write(grps[1], "cgroup.type", "threaded"))
+			goto cleanup;
+		if (cg_write(grps[2], "cgroup.type", "threaded"))
+			goto cleanup;
+	}
 
 	if (cg_enter_current(grps[1]))
 		goto cleanup;
@@ -657,7 +685,7 @@ static int test_cgcore_thread_migration(const char *root)
 	if (retval)
 		goto cleanup;
 
-	snprintf(line, sizeof(line), "0::%s", grps[1] + strlen(grps[0]));
+	snprintf(line, sizeof(line), CG_PATH_FORMAT, grps[1] + strlen(grps[0]));
 	if (proc_read_strstr(0, 1, "cgroup", line))
 		goto cleanup;
 
@@ -683,7 +711,7 @@ cleanup:
  */
 static int test_cgcore_lesser_euid_open(const char *root)
 {
-	const uid_t test_euid = 65534;	/* usually nobody, any !root is fine */
+	const uid_t test_euid = TEST_UID;
 	int ret = KSFT_FAIL;
 	char *cg_test_a = NULL, *cg_test_b = NULL;
 	char *cg_test_a_procs = NULL, *cg_test_b_procs = NULL;
@@ -775,6 +803,9 @@ static int test_cgcore_lesser_ns_open(const char *root)
 	pid_t pid;
 	int status;
 
+	if (!nsdelegate)
+		return KSFT_SKIP;
+
 	cg_test_a = cg_name(root, "cg_test_a");
 	cg_test_b = cg_name(root, "cg_test_b");
 
@@ -837,6 +868,38 @@ cleanup:
 	return ret;
 }
 
+static int setup_named_v1_root(char *root, size_t len, const char *name)
+{
+	char options[PATH_MAX];
+	int r;
+
+	r = snprintf(root, len, "/mnt/cg_selftest");
+	if (r < 0)
+		return r;
+
+	r = snprintf(options, sizeof(options), "none,name=%s", name);
+	if (r < 0)
+		return r;
+
+	r = mkdir(root, 0755);
+	if (r < 0 && errno != EEXIST)
+		return r;
+
+	r = mount("none", root, "cgroup", 0, options);
+	if (r < 0)
+		return r;
+
+	return 0;
+}
+
+static void cleanup_named_v1_root(char *root)
+{
+	if (!cg_test_v1_named)
+		return;
+	umount(root);
+	rmdir(root);
+}
+
 #define T(x) { x, #x }
 struct corecg_test {
 	int (*fn)(const char *root);
@@ -860,15 +923,22 @@ struct corecg_test {
 int main(int argc, char *argv[])
 {
 	char root[PATH_MAX];
-	int i, ret = EXIT_SUCCESS;
-
-	if (cg_find_unified_root(root, sizeof(root)))
-		ksft_exit_skip("cgroup v2 isn't mounted\n");
+	int i;
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
+	if (cg_find_unified_root(root, sizeof(root), &nsdelegate)) {
+		if (setup_named_v1_root(root, sizeof(root), CG_NAMED_NAME))
+			ksft_exit_skip("cgroup v2 isn't mounted and could not setup named v1 hierarchy\n");
+		cg_test_v1_named = true;
+		goto post_v2_setup;
+	}
 
 	if (cg_read_strstr(root, "cgroup.subtree_control", "memory"))
 		if (cg_write(root, "cgroup.subtree_control", "+memory"))
 			ksft_exit_skip("Failed to set memory controller\n");
 
+post_v2_setup:
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		switch (tests[i].fn(root)) {
 		case KSFT_PASS:
@@ -878,11 +948,11 @@ int main(int argc, char *argv[])
 			ksft_test_result_skip("%s\n", tests[i].name);
 			break;
 		default:
-			ret = EXIT_FAILURE;
 			ksft_test_result_fail("%s\n", tests[i].name);
 			break;
 		}
 	}
 
-	return ret;
+	cleanup_named_v1_root(root);
+	ksft_finished();
 }
diff --git a/tools/testing/selftests/cgroup/test_cpu.c b/tools/testing/selftests/cgroup/test_cpu.c
index 24020a2c68dc..c83f05438d7c 100644
--- a/tools/testing/selftests/cgroup/test_cpu.c
+++ b/tools/testing/selftests/cgroup/test_cpu.c
@@ -2,14 +2,16 @@
 
 #define _GNU_SOURCE
 #include <linux/limits.h>
+#include <sys/param.h>
 #include <sys/sysinfo.h>
 #include <sys/wait.h>
 #include <errno.h>
 #include <pthread.h>
 #include <stdio.h>
 #include <time.h>
+#include <unistd.h>
 
-#include "../kselftest.h"
+#include "kselftest.h"
 #include "cgroup_util.h"
 
 enum hog_clock_type {
@@ -217,7 +219,7 @@ static int test_cpucg_stats(const char *root)
 	if (user_usec <= 0)
 		goto cleanup;
 
-	if (!values_close(usage_usec, expected_usage_usec, 1))
+	if (!values_close_report(usage_usec, expected_usage_usec, 1))
 		goto cleanup;
 
 	ret = KSFT_PASS;
@@ -229,6 +231,79 @@ cleanup:
 	return ret;
 }
 
+/*
+ * Creates a nice process that consumes CPU and checks that the elapsed
+ * usertime in the cgroup is close to the expected time.
+ */
+static int test_cpucg_nice(const char *root)
+{
+	int ret = KSFT_FAIL;
+	int status;
+	long user_usec, nice_usec;
+	long usage_seconds = 2;
+	long expected_nice_usec = usage_seconds * USEC_PER_SEC;
+	char *cpucg;
+	pid_t pid;
+
+	cpucg = cg_name(root, "cpucg_test");
+	if (!cpucg)
+		goto cleanup;
+
+	if (cg_create(cpucg))
+		goto cleanup;
+
+	user_usec = cg_read_key_long(cpucg, "cpu.stat", "user_usec");
+	nice_usec = cg_read_key_long(cpucg, "cpu.stat", "nice_usec");
+	if (nice_usec == -1)
+		ret = KSFT_SKIP;
+	if (user_usec != 0 || nice_usec != 0)
+		goto cleanup;
+
+	/*
+	 * We fork here to create a new process that can be niced without
+	 * polluting the nice value of other selftests
+	 */
+	pid = fork();
+	if (pid < 0) {
+		goto cleanup;
+	} else if (pid == 0) {
+		struct cpu_hog_func_param param = {
+			.nprocs = 1,
+			.ts = {
+				.tv_sec = usage_seconds,
+				.tv_nsec = 0,
+			},
+			.clock_type = CPU_HOG_CLOCK_PROCESS,
+		};
+		char buf[64];
+		snprintf(buf, sizeof(buf), "%d", getpid());
+		if (cg_write(cpucg, "cgroup.procs", buf))
+			goto cleanup;
+
+		/* Try to keep niced CPU usage as constrained to hog_cpu as possible */
+		nice(1);
+		hog_cpus_timed(cpucg, &param);
+		exit(0);
+	} else {
+		waitpid(pid, &status, 0);
+		if (!WIFEXITED(status))
+			goto cleanup;
+
+		user_usec = cg_read_key_long(cpucg, "cpu.stat", "user_usec");
+		nice_usec = cg_read_key_long(cpucg, "cpu.stat", "nice_usec");
+		if (!values_close_report(nice_usec, expected_nice_usec, 1))
+			goto cleanup;
+
+		ret = KSFT_PASS;
+	}
+
+cleanup:
+	cg_destroy(cpucg);
+	free(cpucg);
+
+	return ret;
+}
+
 static int
 run_cpucg_weight_test(
 		const char *root,
@@ -237,7 +312,7 @@ run_cpucg_weight_test(
 {
 	int ret = KSFT_FAIL, i;
 	char *parent = NULL;
-	struct cpu_hogger children[3] = {NULL};
+	struct cpu_hogger children[3] = {};
 
 	parent = cg_name(root, "cpucg_test_0");
 	if (!parent)
@@ -329,7 +404,7 @@ overprovision_validate(const struct cpu_hogger *children, int num_children)
 			goto cleanup;
 
 		delta = children[i + 1].usage - children[i].usage;
-		if (!values_close(delta, children[0].usage, 35))
+		if (!values_close_report(delta, children[0].usage, 35))
 			goto cleanup;
 	}
 
@@ -369,7 +444,7 @@ underprovision_validate(const struct cpu_hogger *children, int num_children)
 	int ret = KSFT_FAIL, i;
 
 	for (i = 0; i < num_children - 1; i++) {
-		if (!values_close(children[i + 1].usage, children[0].usage, 15))
+		if (!values_close_report(children[i + 1].usage, children[0].usage, 15))
 			goto cleanup;
 	}
 
@@ -408,7 +483,7 @@ run_cpucg_nested_weight_test(const char *root, bool overprovisioned)
 {
 	int ret = KSFT_FAIL, i;
 	char *parent = NULL, *child = NULL;
-	struct cpu_hogger leaf[3] = {NULL};
+	struct cpu_hogger leaf[3] = {};
 	long nested_leaf_usage, child_usage;
 	int nprocs = get_nprocs();
 
@@ -498,16 +573,16 @@ run_cpucg_nested_weight_test(const char *root, bool overprovisioned)
 
 	nested_leaf_usage = leaf[1].usage + leaf[2].usage;
 	if (overprovisioned) {
-		if (!values_close(leaf[0].usage, nested_leaf_usage, 15))
+		if (!values_close_report(leaf[0].usage, nested_leaf_usage, 15))
 			goto cleanup;
-	} else if (!values_close(leaf[0].usage * 2, nested_leaf_usage, 15))
+	} else if (!values_close_report(leaf[0].usage * 2, nested_leaf_usage, 15))
 		goto cleanup;
 
 
 	child_usage = cg_read_key_long(child, "cpu.stat", "usage_usec");
 	if (child_usage <= 0)
 		goto cleanup;
-	if (!values_close(child_usage, nested_leaf_usage, 1))
+	if (!values_close_report(child_usage, nested_leaf_usage, 1))
 		goto cleanup;
 
 	ret = KSFT_PASS;
@@ -571,10 +646,16 @@ test_cpucg_nested_weight_underprovisioned(const char *root)
 static int test_cpucg_max(const char *root)
 {
 	int ret = KSFT_FAIL;
-	long usage_usec, user_usec;
-	long usage_seconds = 1;
-	long expected_usage_usec = usage_seconds * USEC_PER_SEC;
+	long quota_usec = 1000;
+	long default_period_usec = 100000; /* cpu.max's default period */
+	long duration_seconds = 1;
+
+	long duration_usec = duration_seconds * USEC_PER_SEC;
+	long usage_usec, n_periods, remainder_usec, expected_usage_usec;
 	char *cpucg;
+	char quota_buf[32];
+
+	snprintf(quota_buf, sizeof(quota_buf), "%ld", quota_usec);
 
 	cpucg = cg_name(root, "cpucg_test");
 	if (!cpucg)
@@ -583,13 +664,13 @@ static int test_cpucg_max(const char *root)
 	if (cg_create(cpucg))
 		goto cleanup;
 
-	if (cg_write(cpucg, "cpu.max", "1000"))
+	if (cg_write(cpucg, "cpu.max", quota_buf))
 		goto cleanup;
 
 	struct cpu_hog_func_param param = {
 		.nprocs = 1,
 		.ts = {
-			.tv_sec = usage_seconds,
+			.tv_sec = duration_seconds,
 			.tv_nsec = 0,
 		},
 		.clock_type = CPU_HOG_CLOCK_WALL,
@@ -598,14 +679,19 @@ static int test_cpucg_max(const char *root)
 		goto cleanup;
 
 	usage_usec = cg_read_key_long(cpucg, "cpu.stat", "usage_usec");
-	user_usec = cg_read_key_long(cpucg, "cpu.stat", "user_usec");
-	if (user_usec <= 0)
+	if (usage_usec <= 0)
 		goto cleanup;
 
-	if (user_usec >= expected_usage_usec)
-		goto cleanup;
+	/*
+	 * The following calculation applies only since
+	 * the cpu hog is set to run as per wall-clock time
+	 */
+	n_periods = duration_usec / default_period_usec;
+	remainder_usec = duration_usec - n_periods * default_period_usec;
+	expected_usage_usec
+		= n_periods * quota_usec + MIN(remainder_usec, quota_usec);
 
-	if (values_close(usage_usec, expected_usage_usec, 95))
+	if (!values_close_report(usage_usec, expected_usage_usec, 10))
 		goto cleanup;
 
 	ret = KSFT_PASS;
@@ -624,10 +710,16 @@ cleanup:
 static int test_cpucg_max_nested(const char *root)
 {
 	int ret = KSFT_FAIL;
-	long usage_usec, user_usec;
-	long usage_seconds = 1;
-	long expected_usage_usec = usage_seconds * USEC_PER_SEC;
+	long quota_usec = 1000;
+	long default_period_usec = 100000; /* cpu.max's default period */
+	long duration_seconds = 1;
+
+	long duration_usec = duration_seconds * USEC_PER_SEC;
+	long usage_usec, n_periods, remainder_usec, expected_usage_usec;
 	char *parent, *child;
+	char quota_buf[32];
+
+	snprintf(quota_buf, sizeof(quota_buf), "%ld", quota_usec);
 
 	parent = cg_name(root, "cpucg_parent");
 	child = cg_name(parent, "cpucg_child");
@@ -643,13 +735,13 @@ static int test_cpucg_max_nested(const char *root)
 	if (cg_create(child))
 		goto cleanup;
 
-	if (cg_write(parent, "cpu.max", "1000"))
+	if (cg_write(parent, "cpu.max", quota_buf))
 		goto cleanup;
 
 	struct cpu_hog_func_param param = {
 		.nprocs = 1,
 		.ts = {
-			.tv_sec = usage_seconds,
+			.tv_sec = duration_seconds,
 			.tv_nsec = 0,
 		},
 		.clock_type = CPU_HOG_CLOCK_WALL,
@@ -658,14 +750,19 @@ static int test_cpucg_max_nested(const char *root)
 		goto cleanup;
 
 	usage_usec = cg_read_key_long(child, "cpu.stat", "usage_usec");
-	user_usec = cg_read_key_long(child, "cpu.stat", "user_usec");
-	if (user_usec <= 0)
+	if (usage_usec <= 0)
 		goto cleanup;
 
-	if (user_usec >= expected_usage_usec)
-		goto cleanup;
+	/*
+	 * The following calculation applies only since
+	 * the cpu hog is set to run as per wall-clock time
+	 */
+	n_periods = duration_usec / default_period_usec;
+	remainder_usec = duration_usec - n_periods * default_period_usec;
+	expected_usage_usec
+		= n_periods * quota_usec + MIN(remainder_usec, quota_usec);
 
-	if (values_close(usage_usec, expected_usage_usec, 95))
+	if (!values_close_report(usage_usec, expected_usage_usec, 10))
 		goto cleanup;
 
 	ret = KSFT_PASS;
@@ -686,6 +783,7 @@ struct cpucg_test {
 } tests[] = {
 	T(test_cpucg_subtree_control),
 	T(test_cpucg_stats),
+	T(test_cpucg_nice),
 	T(test_cpucg_weight_overprovisioned),
 	T(test_cpucg_weight_underprovisioned),
 	T(test_cpucg_nested_weight_overprovisioned),
@@ -698,9 +796,11 @@ struct cpucg_test {
 int main(int argc, char *argv[])
 {
 	char root[PATH_MAX];
-	int i, ret = EXIT_SUCCESS;
+	int i;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
 	if (cg_read_strstr(root, "cgroup.subtree_control", "cpu"))
@@ -716,11 +816,10 @@ int main(int argc, char *argv[])
 			ksft_test_result_skip("%s\n", tests[i].name);
 			break;
 		default:
-			ret = EXIT_FAILURE;
 			ksft_test_result_fail("%s\n", tests[i].name);
 			break;
 		}
 	}
 
-	return ret;
+	ksft_finished();
 }
diff --git a/tools/testing/selftests/cgroup/test_cpuset.c b/tools/testing/selftests/cgroup/test_cpuset.c
new file mode 100644
index 000000000000..c5cf8b56ceb8
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_cpuset.c
@@ -0,0 +1,276 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/limits.h>
+#include <signal.h>
+
+#include "kselftest.h"
+#include "cgroup_util.h"
+
+static int idle_process_fn(const char *cgroup, void *arg)
+{
+	(void)pause();
+	return 0;
+}
+
+static int do_migration_fn(const char *cgroup, void *arg)
+{
+	int object_pid = (int)(size_t)arg;
+
+	if (setuid(TEST_UID))
+		return EXIT_FAILURE;
+
+	// XXX checking /proc/$pid/cgroup would be quicker than wait
+	if (cg_enter(cgroup, object_pid) ||
+	    cg_wait_for_proc_count(cgroup, 1))
+		return EXIT_FAILURE;
+
+	return EXIT_SUCCESS;
+}
+
+static int do_controller_fn(const char *cgroup, void *arg)
+{
+	const char *child = cgroup;
+	const char *parent = arg;
+
+	if (setuid(TEST_UID))
+		return EXIT_FAILURE;
+
+	if (!cg_read_strstr(child, "cgroup.controllers", "cpuset"))
+		return EXIT_FAILURE;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+cpuset"))
+		return EXIT_FAILURE;
+
+	if (cg_read_strstr(child, "cgroup.controllers", "cpuset"))
+		return EXIT_FAILURE;
+
+	if (cg_write(parent, "cgroup.subtree_control", "-cpuset"))
+		return EXIT_FAILURE;
+
+	if (!cg_read_strstr(child, "cgroup.controllers", "cpuset"))
+		return EXIT_FAILURE;
+
+	return EXIT_SUCCESS;
+}
+
+/*
+ * Migrate a process between two sibling cgroups.
+ * The success should only depend on the parent cgroup permissions and not the
+ * migrated process itself (cpuset controller is in place because it uses
+ * security_task_setscheduler() in cgroup v1).
+ *
+ * Deliberately don't set cpuset.cpus in children to avoid definining migration
+ * permissions between two different cpusets.
+ */
+static int test_cpuset_perms_object(const char *root, bool allow)
+{
+	char *parent = NULL, *child_src = NULL, *child_dst = NULL;
+	char *parent_procs = NULL, *child_src_procs = NULL, *child_dst_procs = NULL;
+	const uid_t test_euid = TEST_UID;
+	int object_pid = 0;
+	int ret = KSFT_FAIL;
+
+	parent = cg_name(root, "cpuset_test_0");
+	if (!parent)
+		goto cleanup;
+	parent_procs = cg_name(parent, "cgroup.procs");
+	if (!parent_procs)
+		goto cleanup;
+	if (cg_create(parent))
+		goto cleanup;
+
+	child_src = cg_name(parent, "cpuset_test_1");
+	if (!child_src)
+		goto cleanup;
+	child_src_procs = cg_name(child_src, "cgroup.procs");
+	if (!child_src_procs)
+		goto cleanup;
+	if (cg_create(child_src))
+		goto cleanup;
+
+	child_dst = cg_name(parent, "cpuset_test_2");
+	if (!child_dst)
+		goto cleanup;
+	child_dst_procs = cg_name(child_dst, "cgroup.procs");
+	if (!child_dst_procs)
+		goto cleanup;
+	if (cg_create(child_dst))
+		goto cleanup;
+
+	if (cg_write(parent, "cgroup.subtree_control", "+cpuset"))
+		goto cleanup;
+
+	if (cg_read_strstr(child_src, "cgroup.controllers", "cpuset") ||
+	    cg_read_strstr(child_dst, "cgroup.controllers", "cpuset"))
+		goto cleanup;
+
+	/* Enable permissions along src->dst tree path */
+	if (chown(child_src_procs, test_euid, -1) ||
+	    chown(child_dst_procs, test_euid, -1))
+		goto cleanup;
+
+	if (allow && chown(parent_procs, test_euid, -1))
+		goto cleanup;
+
+	/* Fork a privileged child as a test object */
+	object_pid = cg_run_nowait(child_src, idle_process_fn, NULL);
+	if (object_pid < 0)
+		goto cleanup;
+
+	/* Carry out migration in a child process that can drop all privileges
+	 * (including capabilities), the main process must remain privileged for
+	 * cleanup.
+	 * Child process's cgroup is irrelevant but we place it into child_dst
+	 * as hacky way to pass information about migration target to the child.
+	 */
+	if (allow ^ (cg_run(child_dst, do_migration_fn, (void *)(size_t)object_pid) == EXIT_SUCCESS))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (object_pid > 0) {
+		(void)kill(object_pid, SIGTERM);
+		(void)clone_reap(object_pid, WEXITED);
+	}
+
+	cg_destroy(child_dst);
+	free(child_dst_procs);
+	free(child_dst);
+
+	cg_destroy(child_src);
+	free(child_src_procs);
+	free(child_src);
+
+	cg_destroy(parent);
+	free(parent_procs);
+	free(parent);
+
+	return ret;
+}
+
+static int test_cpuset_perms_object_allow(const char *root)
+{
+	return test_cpuset_perms_object(root, true);
+}
+
+static int test_cpuset_perms_object_deny(const char *root)
+{
+	return test_cpuset_perms_object(root, false);
+}
+
+/*
+ * Migrate a process between parent and child implicitely
+ * Implicit migration happens when a controller is enabled/disabled.
+ *
+ */
+static int test_cpuset_perms_subtree(const char *root)
+{
+	char *parent = NULL, *child = NULL;
+	char *parent_procs = NULL, *parent_subctl = NULL, *child_procs = NULL;
+	const uid_t test_euid = TEST_UID;
+	int object_pid = 0;
+	int ret = KSFT_FAIL;
+
+	parent = cg_name(root, "cpuset_test_0");
+	if (!parent)
+		goto cleanup;
+	parent_procs = cg_name(parent, "cgroup.procs");
+	if (!parent_procs)
+		goto cleanup;
+	parent_subctl = cg_name(parent, "cgroup.subtree_control");
+	if (!parent_subctl)
+		goto cleanup;
+	if (cg_create(parent))
+		goto cleanup;
+
+	child = cg_name(parent, "cpuset_test_1");
+	if (!child)
+		goto cleanup;
+	child_procs = cg_name(child, "cgroup.procs");
+	if (!child_procs)
+		goto cleanup;
+	if (cg_create(child))
+		goto cleanup;
+
+	/* Enable permissions as in a delegated subtree */
+	if (chown(parent_procs, test_euid, -1) ||
+	    chown(parent_subctl, test_euid, -1) ||
+	    chown(child_procs, test_euid, -1))
+		goto cleanup;
+
+	/* Put a privileged child in the subtree and modify controller state
+	 * from an unprivileged process, the main process remains privileged
+	 * for cleanup.
+	 * The unprivileged child runs in subtree too to avoid parent and
+	 * internal-node constraing violation.
+	 */
+	object_pid = cg_run_nowait(child, idle_process_fn, NULL);
+	if (object_pid < 0)
+		goto cleanup;
+
+	if (cg_run(child, do_controller_fn, parent) != EXIT_SUCCESS)
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (object_pid > 0) {
+		(void)kill(object_pid, SIGTERM);
+		(void)clone_reap(object_pid, WEXITED);
+	}
+
+	cg_destroy(child);
+	free(child_procs);
+	free(child);
+
+	cg_destroy(parent);
+	free(parent_subctl);
+	free(parent_procs);
+	free(parent);
+
+	return ret;
+}
+
+
+#define T(x) { x, #x }
+struct cpuset_test {
+	int (*fn)(const char *root);
+	const char *name;
+} tests[] = {
+	T(test_cpuset_perms_object_allow),
+	T(test_cpuset_perms_object_deny),
+	T(test_cpuset_perms_subtree),
+};
+#undef T
+
+int main(int argc, char *argv[])
+{
+	char root[PATH_MAX];
+	int i;
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
+	if (cg_find_unified_root(root, sizeof(root), NULL))
+		ksft_exit_skip("cgroup v2 isn't mounted\n");
+
+	if (cg_read_strstr(root, "cgroup.subtree_control", "cpuset"))
+		if (cg_write(root, "cgroup.subtree_control", "+cpuset"))
+			ksft_exit_skip("Failed to set cpuset controller\n");
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		switch (tests[i].fn(root)) {
+		case KSFT_PASS:
+			ksft_test_result_pass("%s\n", tests[i].name);
+			break;
+		case KSFT_SKIP:
+			ksft_test_result_skip("%s\n", tests[i].name);
+			break;
+		default:
+			ksft_test_result_fail("%s\n", tests[i].name);
+			break;
+		}
+	}
+
+	ksft_finished();
+}
diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index 186e1c26867e..a17256d9f88a 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -3,25 +3,18 @@
 #
 # Test for cpuset v2 partition root state (PRS)
 #
-# The sched verbose flag is set, if available, so that the console log
+# The sched verbose flag can be optionally set so that the console log
 # can be examined for the correct setting of scheduling domain.
 #
 
 skip_test() {
 	echo "$1"
 	echo "Test SKIPPED"
-	exit 0
+	exit 4 # ksft_skip
 }
 
 [[ $(id -u) -eq 0 ]] || skip_test "Test must be run as root!"
 
-# Set sched verbose flag, if available
-if [[ -d /sys/kernel/debug/sched ]]
-then
-	# Used to restore the original setting during cleanup
-	SCHED_DEBUG=$(cat /sys/kernel/debug/sched/verbose)
-	echo Y > /sys/kernel/debug/sched/verbose
-fi
 
 # Get wait_inotify location
 WAIT_INOTIFY=$(cd $(dirname $0); pwd)/wait_inotify
@@ -29,23 +22,35 @@ WAIT_INOTIFY=$(cd $(dirname $0); pwd)/wait_inotify
 # Find cgroup v2 mount point
 CGROUP2=$(mount -t cgroup2 | head -1 | awk -e '{print $3}')
 [[ -n "$CGROUP2" ]] || skip_test "Cgroup v2 mount point not found!"
+SUBPARTS_CPUS=$CGROUP2/.__DEBUG__.cpuset.cpus.subpartitions
+CPULIST=$(cat $CGROUP2/cpuset.cpus.effective)
 
-CPUS=$(lscpu | grep "^CPU(s):" | sed -e "s/.*:[[:space:]]*//")
-[[ $CPUS -lt 8 ]] && skip_test "Test needs at least 8 cpus available!"
+NR_CPUS=$(lscpu | grep "^CPU(s):" | sed -e "s/.*:[[:space:]]*//")
+[[ $NR_CPUS -lt 8 ]] && skip_test "Test needs at least 8 cpus available!"
+
+# Check to see if /dev/console exists and is writable
+if [[ -c /dev/console && -w /dev/console ]]
+then
+	CONSOLE=/dev/console
+else
+	CONSOLE=/dev/null
+fi
 
 # Set verbose flag and delay factor
 PROG=$1
-VERBOSE=
+VERBOSE=0
 DELAY_FACTOR=1
+SCHED_DEBUG=
 while [[ "$1" = -* ]]
 do
 	case "$1" in
-		-v) VERBOSE=1
-		    break
+		-v) ((VERBOSE++))
+		    # Enable sched/verbose can slow thing down
+		    [[ $DELAY_FACTOR -eq 1 ]] &&
+			DELAY_FACTOR=2
 		    ;;
 		-d) DELAY_FACTOR=$2
 		    shift
-		    break
 		    ;;
 		*)  echo "Usage: $PROG [-v] [-d <delay-factor>"
 		    exit
@@ -54,18 +59,63 @@ do
 	shift
 done
 
+# Set sched verbose flag if available when "-v" option is specified
+if [[ $VERBOSE -gt 0 && -d /sys/kernel/debug/sched ]]
+then
+	# Used to restore the original setting during cleanup
+	SCHED_DEBUG=$(cat /sys/kernel/debug/sched/verbose)
+	echo Y > /sys/kernel/debug/sched/verbose
+fi
+
 cd $CGROUP2
 echo +cpuset > cgroup.subtree_control
+
+#
+# If cpuset has been set up and used in child cgroups, we may not be able to
+# create partition under root cgroup because of the CPU exclusivity rule.
+# So we are going to skip the test if this is the case.
+#
 [[ -d test ]] || mkdir test
-cd test
+echo 0-6 > test/cpuset.cpus
+echo root > test/cpuset.cpus.partition
+cat test/cpuset.cpus.partition | grep -q invalid
+RESULT=$?
+echo member > test/cpuset.cpus.partition
+echo "" > test/cpuset.cpus
+[[ $RESULT -eq 0 ]] && skip_test "Child cgroups are using cpuset!"
+
+#
+# If isolated CPUs have been reserved at boot time (as shown in
+# cpuset.cpus.isolated), these isolated CPUs should be outside of CPUs 0-8
+# that will be used by this script for testing purpose. If not, some of
+# the tests may fail incorrectly. Wait a bit and retry again just in case
+# these isolated CPUs are leftover from previous run and have just been
+# cleaned up earlier in this script.
+#
+# These pre-isolated CPUs should stay in an isolated state throughout the
+# testing process for now.
+#
+BOOT_ISOLCPUS=$(cat $CGROUP2/cpuset.cpus.isolated)
+[[ -n "$BOOT_ISOLCPUS" ]] && {
+	sleep 0.5
+	BOOT_ISOLCPUS=$(cat $CGROUP2/cpuset.cpus.isolated)
+}
+if [[ -n "$BOOT_ISOLCPUS" ]]
+then
+	[[ $(echo $BOOT_ISOLCPUS | sed -e "s/[,-].*//") -le 8 ]] &&
+		skip_test "Pre-isolated CPUs ($BOOT_ISOLCPUS) overlap CPUs to be tested"
+	echo "Pre-isolated CPUs: $BOOT_ISOLCPUS"
+fi
 
 cleanup()
 {
 	online_cpus
-	rmdir A1/A2/A3 A1/A2 A1 B1 > /dev/null 2>&1
-	cd ..
-	rmdir test > /dev/null 2>&1
-	echo "$SCHED_DEBUG" > /sys/kernel/debug/sched/verbose
+	cd $CGROUP2
+	rmdir A1/A2/A3 A1/A2 A1 B1 test/A1 test/B1 test > /dev/null 2>&1
+	rmdir rtest/p1/c11 rtest/p1/c12 rtest/p2/c21 \
+	      rtest/p2/c22 rtest/p1 rtest/p2 rtest > /dev/null 2>&1
+	[[ -n "$SCHED_DEBUG" ]] &&
+		echo "$SCHED_DEBUG" > /sys/kernel/debug/sched/verbose
 }
 
 # Pause in ms
@@ -85,8 +135,8 @@ console_msg()
 {
 	MSG=$1
 	echo "$MSG"
-	echo "" > /dev/console
-	echo "$MSG" > /dev/console
+	echo "" > $CONSOLE
+	echo "$MSG" > $CONSOLE
 	pause 0.01
 }
 
@@ -97,7 +147,7 @@ test_partition()
 	[[ $? -eq 0 ]] || exit 1
 	ACTUAL_VAL=$(cat cpuset.cpus.partition)
 	[[ $ACTUAL_VAL != $EXPECTED_VAL ]] && {
-		echo "cpuset.cpus.partition: expect $EXPECTED_VAL, found $EXPECTED_VAL"
+		echo "cpuset.cpus.partition: expect $EXPECTED_VAL, found $ACTUAL_VAL"
 		echo "Test FAILED"
 		exit 1
 	}
@@ -108,7 +158,7 @@ test_effective_cpus()
 	EXPECTED_VAL=$1
 	ACTUAL_VAL=$(cat cpuset.cpus.effective)
 	[[ "$ACTUAL_VAL" != "$EXPECTED_VAL" ]] && {
-		echo "cpuset.cpus.effective: expect '$EXPECTED_VAL', found '$EXPECTED_VAL'"
+		echo "cpuset.cpus.effective: expect '$EXPECTED_VAL', found '$ACTUAL_VAL'"
 		echo "Test FAILED"
 		exit 1
 	}
@@ -129,192 +179,314 @@ test_add_proc()
 }
 
 #
-# Testing the new "isolated" partition root type
-#
-test_isolated()
-{
-	echo 2-3 > cpuset.cpus
-	TYPE=$(cat cpuset.cpus.partition)
-	[[ $TYPE = member ]] || echo member > cpuset.cpus.partition
-
-	console_msg "Change from member to root"
-	test_partition root
-
-	console_msg "Change from root to isolated"
-	test_partition isolated
-
-	console_msg "Change from isolated to member"
-	test_partition member
-
-	console_msg "Change from member to isolated"
-	test_partition isolated
-
-	console_msg "Change from isolated to root"
-	test_partition root
-
-	console_msg "Change from root to member"
-	test_partition member
-
-	#
-	# Testing partition root with no cpu
-	#
-	console_msg "Distribute all cpus to child partition"
-	echo +cpuset > cgroup.subtree_control
-	test_partition root
-
-	mkdir A1
-	cd A1
-	echo 2-3 > cpuset.cpus
-	test_partition root
-	test_effective_cpus 2-3
-	cd ..
-	test_effective_cpus ""
-
-	console_msg "Moving task to partition test"
-	test_add_proc "No space left"
-	cd A1
-	test_add_proc ""
-	cd ..
-
-	console_msg "Shrink and expand child partition"
-	cd A1
-	echo 2 > cpuset.cpus
-	cd ..
-	test_effective_cpus 3
-	cd A1
-	echo 2-3 > cpuset.cpus
-	cd ..
-	test_effective_cpus ""
-
-	# Cleaning up
-	console_msg "Cleaning up"
-	echo $$ > $CGROUP2/cgroup.procs
-	[[ -d A1 ]] && rmdir A1
-}
-
-#
 # Cpuset controller state transition test matrix.
 #
 # Cgroup test hierarchy
 #
-# test -- A1 -- A2 -- A3
-#      \- B1
+#	      root
+#	        |
+#	 +------+------+
+#	 |             |
+#	 A1            B1
+#	 |
+#	 A2
+#	 |
+#	 A3
 #
-#  P<v> = set cpus.partition (0:member, 1:root, 2:isolated, -1:root invalid)
-#  C<l> = add cpu-list
+#  P<v> = set cpus.partition (0:member, 1:root, 2:isolated)
+#  C<l> = add cpu-list to cpuset.cpus
+#  X<l> = add cpu-list to cpuset.cpus.exclusive
 #  S<p> = use prefix in subtree_control
 #  T    = put a task into cgroup
-#  O<c>-<v> = Write <v> to CPU online file of <c>
+#  CX<l> = add cpu-list to both cpuset.cpus and cpuset.cpus.exclusive
+#  O<c>=<v> = Write <v> to CPU online file of <c>
+#
+# ECPUs    - effective CPUs of cpusets
+# Pstate   - partition root state
+# ISOLCPUS - isolated CPUs (<icpus>[,<icpus2>])
+#
+# Note that if there are 2 fields in ISOLCPUS, the first one is for
+# sched-debug matching which includes offline CPUs and single-CPU partitions
+# while the second one is for matching cpuset.cpus.isolated.
 #
 SETUP_A123_PARTITIONS="C1-3:P1:S+ C2-3:P1:S+ C3:P1"
 TEST_MATRIX=(
-	# test  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate
-	# ----  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------
-	"  S+    C0-1     .      .    C2-3    S+    C4-5     .      .     0 A2:0-1"
-	"  S+    C0-1     .      .    C2-3    P1      .      .      .     0 "
-	"  S+    C0-1     .      .    C2-3   P1:S+ C0-1:P1   .      .     0 "
-	"  S+    C0-1     .      .    C2-3   P1:S+  C1:P1    .      .     0 "
-	"  S+   C0-1:S+   .      .    C2-3     .      .      .     P1     0 "
-	"  S+   C0-1:P1   .      .    C2-3    S+     C1      .      .     0 "
-	"  S+   C0-1:P1   .      .    C2-3    S+    C1:P1    .      .     0 "
-	"  S+   C0-1:P1   .      .    C2-3    S+    C1:P1    .     P1     0 "
-	"  S+   C0-1:P1   .      .    C2-3   C4-5     .      .      .     0 A1:4-5"
-	"  S+   C0-1:P1   .      .    C2-3  S+:C4-5   .      .      .     0 A1:4-5"
-	"  S+    C0-1     .      .   C2-3:P1   .      .      .     C2     0 "
-	"  S+    C0-1     .      .   C2-3:P1   .      .      .    C4-5    0 B1:4-5"
-	"  S+ C0-3:P1:S+ C2-3:P1 .      .      .      .      .      .     0 A1:0-1,A2:2-3"
-	"  S+ C0-3:P1:S+ C2-3:P1 .      .     C1-3    .      .      .     0 A1:1,A2:2-3"
-	"  S+ C2-3:P1:S+  C3:P1  .      .     C3      .      .      .     0 A1:,A2:3 A1:P1,A2:P1"
-	"  S+ C2-3:P1:S+  C3:P1  .      .     C3      P0     .      .     0 A1:3,A2:3 A1:P1,A2:P0"
-	"  S+ C2-3:P1:S+  C2:P1  .      .     C2-4    .      .      .     0 A1:3-4,A2:2"
-	"  S+ C2-3:P1:S+  C3:P1  .      .     C3      .      .     C0-2   0 A1:,B1:0-2 A1:P1,A2:P1"
-	"  S+ $SETUP_A123_PARTITIONS    .     C2-3    .      .      .     0 A1:,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
+	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
+	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
+	"   C0-1     .      .    C2-3    S+    C4-5     .      .     0 A2:0-1"
+	"   C0-1     .      .    C2-3    P1      .      .      .     0 "
+	"   C0-1     .      .    C2-3   P1:S+ C0-1:P1   .      .     0 "
+	"   C0-1     .      .    C2-3   P1:S+  C1:P1    .      .     0 "
+	"  C0-1:S+   .      .    C2-3     .      .      .     P1     0 "
+	"  C0-1:P1   .      .    C2-3    S+     C1      .      .     0 "
+	"  C0-1:P1   .      .    C2-3    S+    C1:P1    .      .     0 "
+	"  C0-1:P1   .      .    C2-3    S+    C1:P1    .     P1     0 "
+	"  C0-1:P1   .      .    C2-3   C4-5     .      .      .     0 A1:4-5"
+	"  C0-1:P1   .      .    C2-3  S+:C4-5   .      .      .     0 A1:4-5"
+	"   C0-1     .      .   C2-3:P1   .      .      .     C2     0 "
+	"   C0-1     .      .   C2-3:P1   .      .      .    C4-5    0 B1:4-5"
+	"C0-3:P1:S+ C2-3:P1 .      .      .      .      .      .     0 A1:0-1|A2:2-3|XA2:2-3"
+	"C0-3:P1:S+ C2-3:P1 .      .     C1-3    .      .      .     0 A1:1|A2:2-3|XA2:2-3"
+	"C2-3:P1:S+  C3:P1  .      .     C3      .      .      .     0 A1:|A2:3|XA2:3 A1:P1|A2:P1"
+	"C2-3:P1:S+  C3:P1  .      .     C3      P0     .      .     0 A1:3|A2:3 A1:P1|A2:P0"
+	"C2-3:P1:S+  C2:P1  .      .     C2-4    .      .      .     0 A1:3-4|A2:2"
+	"C2-3:P1:S+  C3:P1  .      .     C3      .      .     C0-2   0 A1:|B1:0-2 A1:P1|A2:P1"
+	"$SETUP_A123_PARTITIONS    .     C2-3    .      .      .     0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
 
 	# CPU offlining cases:
-	"  S+    C0-1     .      .    C2-3    S+    C4-5     .     O2-0   0 A1:0-1,B1:3"
-	"  S+ C0-3:P1:S+ C2-3:P1 .      .     O2-0    .      .      .     0 A1:0-1,A2:3"
-	"  S+ C0-3:P1:S+ C2-3:P1 .      .     O2-0   O2-1    .      .     0 A1:0-1,A2:2-3"
-	"  S+ C0-3:P1:S+ C2-3:P1 .      .     O1-0    .      .      .     0 A1:0,A2:2-3"
-	"  S+ C0-3:P1:S+ C2-3:P1 .      .     O1-0   O1-1    .      .     0 A1:0-1,A2:2-3"
-	"  S+ C2-3:P1:S+  C3:P1  .      .     O3-0   O3-1    .      .     0 A1:2,A2:3 A1:P1,A2:P1"
-	"  S+ C2-3:P1:S+  C3:P2  .      .     O3-0   O3-1    .      .     0 A1:2,A2:3 A1:P1,A2:P2"
-	"  S+ C2-3:P1:S+  C3:P1  .      .     O2-0   O2-1    .      .     0 A1:2,A2:3 A1:P1,A2:P1"
-	"  S+ C2-3:P1:S+  C3:P2  .      .     O2-0   O2-1    .      .     0 A1:2,A2:3 A1:P1,A2:P2"
-	"  S+ C2-3:P1:S+  C3:P1  .      .     O2-0    .      .      .     0 A1:,A2:3 A1:P1,A2:P1"
-	"  S+ C2-3:P1:S+  C3:P1  .      .     O3-0    .      .      .     0 A1:2,A2: A1:P1,A2:P1"
-	"  S+ C2-3:P1:S+  C3:P1  .      .    T:O2-0   .      .      .     0 A1:3,A2:3 A1:P1,A2:P-1"
-	"  S+ C2-3:P1:S+  C3:P1  .      .      .    T:O3-0   .      .     0 A1:2,A2:2 A1:P1,A2:P-1"
-	"  S+ $SETUP_A123_PARTITIONS    .     O1-0    .      .      .     0 A1:,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
-	"  S+ $SETUP_A123_PARTITIONS    .     O2-0    .      .      .     0 A1:1,A2:,A3:3 A1:P1,A2:P1,A3:P1"
-	"  S+ $SETUP_A123_PARTITIONS    .     O3-0    .      .      .     0 A1:1,A2:2,A3: A1:P1,A2:P1,A3:P1"
-	"  S+ $SETUP_A123_PARTITIONS    .    T:O1-0   .      .      .     0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1"
-	"  S+ $SETUP_A123_PARTITIONS    .      .    T:O2-0   .      .     0 A1:1,A2:3,A3:3 A1:P1,A2:P1,A3:P-1"
-	"  S+ $SETUP_A123_PARTITIONS    .      .      .    T:O3-0   .     0 A1:1,A2:2,A3:2 A1:P1,A2:P1,A3:P-1"
-	"  S+ $SETUP_A123_PARTITIONS    .    T:O1-0  O1-1    .      .     0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
-	"  S+ $SETUP_A123_PARTITIONS    .      .    T:O2-0  O2-1    .     0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
-	"  S+ $SETUP_A123_PARTITIONS    .      .      .    T:O3-0  O3-1   0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
-	"  S+ $SETUP_A123_PARTITIONS    .    T:O1-0  O2-0   O1-1    .     0 A1:1,A2:,A3:3 A1:P1,A2:P1,A3:P1"
-	"  S+ $SETUP_A123_PARTITIONS    .    T:O1-0  O2-0   O2-1    .     0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1"
-
-	# test  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate
-	# ----  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------
+	"   C0-1     .      .    C2-3    S+    C4-5     .     O2=0   0 A1:0-1|B1:3"
+	"C0-3:P1:S+ C2-3:P1 .      .     O2=0    .      .      .     0 A1:0-1|A2:3"
+	"C0-3:P1:S+ C2-3:P1 .      .     O2=0   O2=1    .      .     0 A1:0-1|A2:2-3"
+	"C0-3:P1:S+ C2-3:P1 .      .     O1=0    .      .      .     0 A1:0|A2:2-3"
+	"C0-3:P1:S+ C2-3:P1 .      .     O1=0   O1=1    .      .     0 A1:0-1|A2:2-3"
+	"C2-3:P1:S+  C3:P1  .      .     O3=0   O3=1    .      .     0 A1:2|A2:3 A1:P1|A2:P1"
+	"C2-3:P1:S+  C3:P2  .      .     O3=0   O3=1    .      .     0 A1:2|A2:3 A1:P1|A2:P2"
+	"C2-3:P1:S+  C3:P1  .      .     O2=0   O2=1    .      .     0 A1:2|A2:3 A1:P1|A2:P1"
+	"C2-3:P1:S+  C3:P2  .      .     O2=0   O2=1    .      .     0 A1:2|A2:3 A1:P1|A2:P2"
+	"C2-3:P1:S+  C3:P1  .      .     O2=0    .      .      .     0 A1:|A2:3 A1:P1|A2:P1"
+	"C2-3:P1:S+  C3:P1  .      .     O3=0    .      .      .     0 A1:2|A2: A1:P1|A2:P1"
+	"C2-3:P1:S+  C3:P1  .      .    T:O2=0   .      .      .     0 A1:3|A2:3 A1:P1|A2:P-1"
+	"C2-3:P1:S+  C3:P1  .      .      .    T:O3=0   .      .     0 A1:2|A2:2 A1:P1|A2:P-1"
+	"$SETUP_A123_PARTITIONS    .     O1=0    .      .      .     0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
+	"$SETUP_A123_PARTITIONS    .     O2=0    .      .      .     0 A1:1|A2:|A3:3 A1:P1|A2:P1|A3:P1"
+	"$SETUP_A123_PARTITIONS    .     O3=0    .      .      .     0 A1:1|A2:2|A3: A1:P1|A2:P1|A3:P1"
+	"$SETUP_A123_PARTITIONS    .    T:O1=0   .      .      .     0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P-1|A3:P-1"
+	"$SETUP_A123_PARTITIONS    .      .    T:O2=0   .      .     0 A1:1|A2:3|A3:3 A1:P1|A2:P1|A3:P-1"
+	"$SETUP_A123_PARTITIONS    .      .      .    T:O3=0   .     0 A1:1|A2:2|A3:2 A1:P1|A2:P1|A3:P-1"
+	"$SETUP_A123_PARTITIONS    .    T:O1=0  O1=1    .      .     0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
+	"$SETUP_A123_PARTITIONS    .      .    T:O2=0  O2=1    .     0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
+	"$SETUP_A123_PARTITIONS    .      .      .    T:O3=0  O3=1   0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
+	"$SETUP_A123_PARTITIONS    .    T:O1=0  O2=0   O1=1    .     0 A1:1|A2:|A3:3 A1:P1|A2:P1|A3:P1"
+	"$SETUP_A123_PARTITIONS    .    T:O1=0  O2=0   O2=1    .     0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P-1|A3:P-1"
+
+	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
+	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
+	#
+	# Remote partition and cpuset.cpus.exclusive tests
+	#
+	" C0-3:S+ C1-3:S+ C2-3     .    X2-3     .      .      .     0 A1:0-3|A2:1-3|A3:2-3|XA1:2-3"
+	" C0-3:S+ C1-3:S+ C2-3     .    X2-3  X2-3:P2   .      .     0 A1:0-1|A2:2-3|A3:2-3 A1:P0|A2:P2 2-3"
+	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X3:P2    .      .     0 A1:0-2|A2:3|A3:3 A1:P0|A2:P2 3"
+	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3  X2-3:P2   .     0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3 X2-3:P2:C3 .     0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+	" C0-3:S+ C1-3:S+ C2-3   C2-3     .      .      .      P2    0 A1:0-3|A2:1-3|A3:2-3|B1:2-3 A1:P0|A3:P0|B1:P-2"
+	" C0-3:S+ C1-3:S+ C2-3   C4-5     .      .      .      P2    0 B1:4-5 B1:P2 4-5"
+	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3   X2-3  X2-3:P2   P2    0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
+	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3   X2-3 X2-3:P2:C1-3 P2  0 A3:2-3|B1:4 A3:P2|B1:P2 2-4"
+	" C0-3:S+ C1-3:S+ C2-3    C4    X1-3  X1-3:P2   P2     .     0 A2:1|A3:2-3 A2:P2|A3:P2 1-3"
+	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3   X2-3  X2-3:P2 P2:C4-5 0 A3:2-3|B1:4-5 A3:P2|B1:P2 2-5"
+	" C4:X0-3:S+ X1-3:S+ X2-3  .      .      P2     .      .     0 A1:4|A2:1-3|A3:1-3 A2:P2 1-3"
+	" C4:X0-3:S+ X1-3:S+ X2-3  .      .      .      P2     .     0 A1:4|A2:4|A3:2-3 A3:P2 2-3"
+
+	# Nested remote/local partition tests
+	" C0-3:S+ C1-3:S+ C2-3   C4-5   X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:|A3:2-3|B1:4-5 \
+								       A1:P0|A2:P1|A3:P2|B1:P1 2-3"
+	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:|A3:2-3|B1:4 \
+								       A1:P0|A2:P1|A3:P2|B1:P1 2-4|2-3"
+	" C0-3:S+ C1-3:S+ C2-3    C4    X2-3  X2-3:P1    .     P1    0 A1:0-1|A2:2-3|A3:2-3|B1:4 \
+								       A1:P0|A2:P1|A3:P0|B1:P1"
+	" C0-3:S+ C1-3:S+  C3     C4    X2-3  X2-3:P1   P2     P1    0 A1:0-1|A2:2|A3:3|B1:4 \
+								       A1:P0|A2:P1|A3:P2|B1:P1 2-4|3"
+	" C0-4:S+ C1-4:S+ C2-4     .    X2-4  X2-4:P2  X4:P1    .    0 A1:0-1|A2:2-3|A3:4 \
+								       A1:P0|A2:P2|A3:P1 2-4|2-3"
+	" C0-4:S+ C1-4:S+ C2-4     .    X2-4  X2-4:P2 X3-4:P1   .    0 A1:0-1|A2:2|A3:3-4 \
+								       A1:P0|A2:P2|A3:P1 2"
+	" C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \
+				   .      .      X5      .      .    0 A1:0-4|A2:1-4|A3:2-4 \
+								       A1:P0|A2:P-2|A3:P-1 ."
+	" C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \
+				   .      .      .      X1      .    0 A1:0-1|A2:2-4|A3:2-4 \
+								       A1:P0|A2:P2|A3:P-1 2-4"
+
+	# Remote partition offline tests
+	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3 X2-3:P2:O2=0 .   0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3"
+	" C0-3:S+ C1-3:S+ C2-3     .    X2-3   X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3"
+	" C0-3:S+ C1-3:S+  C3      .    X2-3   X2-3    P2:O3=0   .   0 A1:0-2|A2:1-2|A3: A1:P0|A3:P2 3"
+	" C0-3:S+ C1-3:S+  C3      .    X2-3   X2-3   T:P2:O3=0  .   0 A1:0-2|A2:1-2|A3:1-2 A1:P0|A3:P-2 3|"
+
+	# An invalidated remote partition cannot self-recover from hotplug
+	" C0-3:S+ C1-3:S+  C2      .    X2-3   X2-3   T:P2:O2=0 O2=1 0 A1:0-3|A2:1-3|A3:2 A1:P0|A3:P-2 ."
+
+	# cpus.exclusive.effective clearing test
+	" C0-3:S+ C1-3:S+  C2      .   X2-3:X    .      .      .     0 A1:0-3|A2:1-3|A3:2|XA1:"
+
+	# Invalid to valid remote partition transition test
+	" C0-3:S+   C1-3    .      .      .    X3:P2    .      .     0 A1:0-3|A2:1-3|XA2: A2:P-2 ."
+	" C0-3:S+ C1-3:X3:P2
+			    .      .    X2-3    P2      .      .     0 A1:0-2|A2:3|XA2:3 A2:P2 3"
+
+	# Invalid to valid local partition direct transition tests
+	" C1-3:S+:P2 X4:P2  .      .      .      .      .      .     0 A1:1-3|XA1:1-3|A2:1-3:XA2: A1:P2|A2:P-2 1-3"
+	" C1-3:S+:P2 X4:P2  .      .      .    X3:P2    .      .     0 A1:1-2|XA1:1-3|A2:3:XA2:3 A1:P2|A2:P2 1-3"
+	"  C0-3:P2   .      .    C4-6   C0-4     .      .      .     0 A1:0-4|B1:4-6 A1:P-2|B1:P0"
+	"  C0-3:P2   .      .    C4-6 C0-4:C0-3  .      .      .     0 A1:0-3|B1:4-6 A1:P2|B1:P0 0-3"
+
+	# Local partition invalidation tests
+	" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
+				   .      .      .      .      .     0 A1:1|A2:2|A3:3 A1:P2|A2:P2|A3:P2 1-3"
+	" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
+				   .      .     X4      .      .     0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3"
+	" C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \
+				   .      .    C4:X     .      .     0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3"
+	# Local partition CPU change tests
+	" C0-5:S+:P2 C4-5:S+:P1 .  .      .    C3-5     .      .     0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2"
+	" C0-5:S+:P2 C4-5:S+:P1 .  .    C1-5     .      .      .     0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3"
+
+	# cpus_allowed/exclusive_cpus update tests
+	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
+				   .    X:C4     .      P2     .     0 A1:4|A2:4|XA2:|XA3:|A3:4 \
+								       A1:P0|A3:P-2 ."
+	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
+				   .     X1      .      P2     .     0 A1:0-3|A2:1-3|XA1:1|XA2:|XA3:|A3:2-3 \
+								       A1:P0|A3:P-2 ."
+	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \
+				   .      .     X3      P2     .     0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3 \
+								       A1:P0|A3:P2 3"
+	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \
+				   .      .     X3      .      .     0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3|XA3:3 \
+								       A1:P0|A3:P2 3"
+	" C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \
+				   .     X4      .      .      .     0 A1:0-3|A2:1-3|A3:2-3|XA1:4|XA2:|XA3 \
+								       A1:P0|A3:P-2"
+
+	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
+	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
 	#
-	# Incorrect change to cpuset.cpus invalidates partition root
+	# Incorrect change to cpuset.cpus[.exclusive] invalidates partition root
 	#
 	# Adding CPUs to partition root that are not in parent's
 	# cpuset.cpus is allowed, but those extra CPUs are ignored.
-	"  S+ C2-3:P1:S+ C3:P1   .      .      .     C2-4    .      .     0 A1:,A2:2-3 A1:P1,A2:P1"
+	"C2-3:P1:S+ C3:P1   .      .      .     C2-4    .      .     0 A1:|A2:2-3 A1:P1|A2:P1"
 
 	# Taking away all CPUs from parent or itself if there are tasks
 	# will make the partition invalid.
-	"  S+ C2-3:P1:S+  C3:P1  .      .      T     C2-3    .      .     0 A1:2-3,A2:2-3 A1:P1,A2:P-1"
-	"  S+ $SETUP_A123_PARTITIONS    .    T:C2-3   .      .      .     0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1"
-	"  S+ $SETUP_A123_PARTITIONS    . T:C2-3:C1-3 .      .      .     0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
+	"C2-3:P1:S+  C3:P1  .      .      T     C2-3    .      .     0 A1:2-3|A2:2-3 A1:P1|A2:P-1"
+	" C3:P1:S+    C3    .      .      T      P1     .      .     0 A1:3|A2:3 A1:P1|A2:P-1"
+	"$SETUP_A123_PARTITIONS    .    T:C2-3   .      .      .     0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P-1|A3:P-1"
+	"$SETUP_A123_PARTITIONS    . T:C2-3:C1-3 .      .      .     0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1"
 
 	# Changing a partition root to member makes child partitions invalid
-	"  S+ C2-3:P1:S+  C3:P1  .      .      P0     .      .      .     0 A1:2-3,A2:3 A1:P0,A2:P-1"
-	"  S+ $SETUP_A123_PARTITIONS    .     C2-3    P0     .      .     0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P0,A3:P-1"
+	"C2-3:P1:S+  C3:P1  .      .      P0     .      .      .     0 A1:2-3|A2:3 A1:P0|A2:P-1"
+	"$SETUP_A123_PARTITIONS    .     C2-3    P0     .      .     0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P0|A3:P-1"
 
 	# cpuset.cpus can contains cpus not in parent's cpuset.cpus as long
 	# as they overlap.
-	"  S+ C2-3:P1:S+  .      .      .      .   C3-4:P1   .      .     0 A1:2,A2:3 A1:P1,A2:P1"
+	"C2-3:P1:S+  .      .      .      .   C3-4:P1   .      .     0 A1:2|A2:3 A1:P1|A2:P1"
 
 	# Deletion of CPUs distributed to child cgroup is allowed.
-	"  S+ C0-1:P1:S+ C1      .    C2-3   C4-5     .      .      .     0 A1:4-5,A2:4-5"
+	"C0-1:P1:S+ C1      .    C2-3   C4-5     .      .      .     0 A1:4-5|A2:4-5"
 
 	# To become a valid partition root, cpuset.cpus must overlap parent's
 	# cpuset.cpus.
-	"  S+   C0-1:P1   .      .    C2-3    S+   C4-5:P1   .      .     0 A1:0-1,A2:0-1 A1:P1,A2:P-1"
+	"  C0-1:P1   .      .    C2-3    S+   C4-5:P1   .      .     0 A1:0-1|A2:0-1 A1:P1|A2:P-1"
 
 	# Enabling partition with child cpusets is allowed
-	"  S+   C0-1:S+  C1      .    C2-3    P1      .      .      .     0 A1:0-1,A2:1 A1:P1"
+	"  C0-1:S+  C1      .    C2-3    P1      .      .      .     0 A1:0-1|A2:1 A1:P1"
 
-	# A partition root with non-partition root parent is invalid, but it
+	# A partition root with non-partition root parent is invalid| but it
 	# can be made valid if its parent becomes a partition root too.
-	"  S+   C0-1:S+  C1      .    C2-3     .      P2     .      .     0 A1:0-1,A2:1 A1:P0,A2:P-2"
-	"  S+   C0-1:S+ C1:P2    .    C2-3     P1     .      .      .     0 A1:0,A2:1 A1:P1,A2:P2"
+	"  C0-1:S+  C1      .    C2-3     .      P2     .      .     0 A1:0-1|A2:1 A1:P0|A2:P-2"
+	"  C0-1:S+ C1:P2    .    C2-3     P1     .      .      .     0 A1:0|A2:1 A1:P1|A2:P2 0-1|1"
 
 	# A non-exclusive cpuset.cpus change will invalidate partition and its siblings
-	"  S+   C0-1:P1   .      .    C2-3   C0-2     .      .      .     0 A1:0-2,B1:2-3 A1:P-1,B1:P0"
-	"  S+   C0-1:P1   .      .  P1:C2-3  C0-2   .      .      .     0 A1:0-2,B1:2-3 A1:P-1,B1:P-1"
-	"  S+    C0-1     .      .  P1:C2-3  C0-2   .      .      .     0 A1:0-2,B1:2-3 A1:P0,B1:P-1"
-
-	# test  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate
-	# ----  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------
+	"  C0-1:P1   .      .    C2-3   C0-2     .      .      .     0 A1:0-2|B1:2-3 A1:P-1|B1:P0"
+	"  C0-1:P1   .      .  P1:C2-3  C0-2     .      .      .     0 A1:0-2|B1:2-3 A1:P-1|B1:P-1"
+	"   C0-1     .      .  P1:C2-3  C0-2     .      .      .     0 A1:0-2|B1:2-3 A1:P0|B1:P-1"
+
+	# cpuset.cpus can overlap with sibling cpuset.cpus.exclusive but not subsumed by it
+	"   C0-3     .      .    C4-5     X5     .      .      .     0 A1:0-3|B1:4-5"
+
+	# Child partition root that try to take all CPUs from parent partition
+	# with tasks will remain invalid.
+	" C1-4:P1:S+ P1     .      .       .     .      .      .     0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
+	" C1-4:P1:S+ P1     .      .       .   C1-4     .      .     0 A1|A2:1-4 A1:P1|A2:P1"
+	" C1-4:P1:S+ P1     .      .       T   C1-4     .      .     0 A1:1-4|A2:1-4 A1:P1|A2:P-1"
+
+	# Clearing of cpuset.cpus with a preset cpuset.cpus.exclusive shouldn't
+	# affect cpuset.cpus.exclusive.effective.
+	" C1-4:X3:S+ C1:X3  .      .       .     C      .      .     0 A2:1-4|XA2:3"
+
+	# cpuset.cpus can contain CPUs that overlap a sibling cpuset with cpus.exclusive
+	# but creating a local partition out of it is not allowed. Similarly and change
+	# in cpuset.cpus of a local partition that overlaps sibling exclusive CPUs will
+	# invalidate it.
+	" CX1-4:S+ CX2-4:P2 .    C5-6      .     .      .      P1    0 A1:1|A2:2-4|B1:5-6|XB1:5-6 \
+								       A1:P0|A2:P2:B1:P1 2-4"
+	" CX1-4:S+ CX2-4:P2 .    C3-6      .     .      .      P1    0 A1:1|A2:2-4|B1:5-6 \
+								       A1:P0|A2:P2:B1:P-1 2-4"
+	" CX1-4:S+ CX2-4:P2 .    C5-6      .     .      .   P1:C3-6  0 A1:1|A2:2-4|B1:5-6 \
+								       A1:P0|A2:P2:B1:P-1 2-4"
+
+	#  old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS
+	#  ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ --------
 	# Failure cases:
 
 	# A task cannot be added to a partition with no cpu
-	"  S+ C2-3:P1:S+  C3:P1  .      .    O2-0:T   .      .      .     1 A1:,A2:3 A1:P1,A2:P1"
+	"C2-3:P1:S+  C3:P1  .      .    O2=0:T   .      .      .     1 A1:|A2:3 A1:P1|A2:P1"
+
+	# Changes to cpuset.cpus.exclusive that violate exclusivity rule is rejected
+	"   C0-3     .      .    C4-5   X0-3     .      .     X3-5   1 A1:0-3|B1:4-5"
+
+	# cpuset.cpus cannot be a subset of sibling cpuset.cpus.exclusive
+	"   C0-3     .      .    C4-5   X3-5     .      .      .     1 A1:0-3|B1:4-5"
+)
+
+#
+# Cpuset controller remote partition test matrix.
+#
+# Cgroup test hierarchy
+#
+#	      root
+#	        |
+#	      rtest (cpuset.cpus.exclusive=1-7)
+#	        |
+#	 +------+------+
+#	 |             |
+#	 p1            p2
+#     +--+--+       +--+--+
+#     |     |       |     |
+#    c11   c12     c21   c22
+#
+# REMOTE_TEST_MATRIX uses the same notational convention as TEST_MATRIX.
+# Only CPUs 1-7 should be used.
+#
+REMOTE_TEST_MATRIX=(
+	#  old-p1 old-p2 old-c11 old-c12 old-c21 old-c22
+	#  new-p1 new-p2 new-c11 new-c12 new-c21 new-c22 ECPUs Pstate ISOLCPUS
+	#  ------ ------ ------- ------- ------- ------- ----- ------ --------
+	" X1-3:S+ X4-6:S+ X1-2     X3     X4-5     X6 \
+	      .      .     P2      P2      P2      P2    c11:1-2|c12:3|c21:4-5|c22:6 \
+							 c11:P2|c12:P2|c21:P2|c22:P2 1-6"
+	" CX1-4:S+   .   X1-2:P2   C3      .       .  \
+	      .      .     .      C3-4     .       .     p1:3-4|c11:1-2|c12:3-4 \
+							 p1:P0|c11:P2|c12:P0 1-2"
+	" CX1-4:S+   .   X1-2:P2   .       .       .  \
+	    X2-4     .     .       .       .       .     p1:1,3-4|c11:2 \
+							 p1:P0|c11:P2 2"
+	" CX1-5:S+   .   X1-2:P2 X3-5:P1   .       .  \
+	    X2-4     .     .       .       .       .     p1:1,5|c11:2|c12:3-4 \
+							 p1:P0|c11:P2|c12:P1 2"
+	" CX1-4:S+   .   X1-2:P2 X3-4:P1   .       .  \
+	      .      .     X2      .       .       .     p1:1|c11:2|c12:3-4 \
+							 p1:P0|c11:P2|c12:P1 2"
+	# p1 as member, will get its effective CPUs from its parent rtest
+	" CX1-4:S+   .   X1-2:P2 X3-4:P1   .       .  \
+	      .      .     X1     CX2-4    .       .     p1:5-7|c11:1|c12:2-4 \
+							 p1:P0|c11:P2|c12:P1 1"
+	" CX1-4:S+ X5-6:P1:S+ .    .       .       .  \
+	      .      .   X1-2:P2  X4-5:P1  .     X1-7:P2 p1:3|c11:1-2|c12:4:c22:5-6 \
+							 p1:P0|p2:P1|c11:P2|c12:P1|c22:P2 \
+							 1-2,4-6|1-2,5-6"
 )
 
 #
 # Write to the cpu online file
-#  $1 - <c>-<v> where <c> = cpu number, <v> value to be written
+#  $1 - <c>=<v> where <c> = cpu number, <v> value to be written
 #
 write_cpu_online()
 {
-	CPU=${1%-*}
-	VAL=${1#*-}
+	CPU=${1%=*}
+	VAL=${1#*=}
 	CPUFILE=//sys/devices/system/cpu/cpu${CPU}/online
 	if [[ $VAL -eq 0 ]]
 	then
@@ -326,7 +498,7 @@ write_cpu_online()
 		}
 	fi
 	echo $VAL > $CPUFILE
-	pause 0.01
+	pause 0.05
 }
 
 #
@@ -342,11 +514,12 @@ set_ctrl_state()
 	TMPMSG=/tmp/.msg_$$
 	CGRP=$1
 	STATE=$2
-	SHOWERR=${3}${VERBOSE}
+	SHOWERR=${3}
 	CTRL=${CTRL:=$CONTROLLER}
 	HASERR=0
 	REDIRECT="2> $TMPMSG"
 	[[ -z "$STATE" || "$STATE" = '.' ]] && return 0
+	[[ $VERBOSE -gt 0 ]] && SHOWERR=1
 
 	rm -f $TMPMSG
 	for CMD in $(echo $STATE | sed -e "s/:/ /g")
@@ -355,20 +528,27 @@ set_ctrl_state()
 		SFILE=$CGRP/cgroup.subtree_control
 		PFILE=$CGRP/cpuset.cpus.partition
 		CFILE=$CGRP/cpuset.cpus
-		S=$(expr substr $CMD 1 1)
-		if [[ $S = S ]]
-		then
-			PREFIX=${CMD#?}
+		XFILE=$CGRP/cpuset.cpus.exclusive
+		case $CMD in
+		    S*) PREFIX=${CMD#?}
 			COMM="echo ${PREFIX}${CTRL} > $SFILE"
 			eval $COMM $REDIRECT
-		elif [[ $S = C ]]
-		then
+			;;
+		    X*)
 			CPUS=${CMD#?}
+			COMM="echo $CPUS > $XFILE"
+			eval $COMM $REDIRECT
+			;;
+		    CX*)
+			CPUS=${CMD#??}
+			COMM="echo $CPUS > $CFILE; echo $CPUS > $XFILE"
+			eval $COMM $REDIRECT
+			;;
+		    C*) CPUS=${CMD#?}
 			COMM="echo $CPUS > $CFILE"
 			eval $COMM $REDIRECT
-		elif [[ $S = P ]]
-		then
-			VAL=${CMD#?}
+			;;
+		    P*) VAL=${CMD#?}
 			case $VAL in
 			0)  VAL=member
 			    ;;
@@ -383,15 +563,17 @@ set_ctrl_state()
 			esac
 			COMM="echo $VAL > $PFILE"
 			eval $COMM $REDIRECT
-		elif [[ $S = O ]]
-		then
-			VAL=${CMD#?}
+			;;
+		    O*) VAL=${CMD#?}
 			write_cpu_online $VAL
-		elif [[ $S = T ]]
-		then
-			COMM="echo 0 > $TFILE"
+			;;
+		    T*) COMM="echo 0 > $TFILE"
 			eval $COMM $REDIRECT
-		fi
+			;;
+		    *)  echo "Unknown command: $CMD"
+		        exit 1
+			;;
+		esac
 		RET=$?
 		[[ $RET -ne 0 ]] && {
 			[[ -n "$SHOWERR" ]] && {
@@ -423,81 +605,110 @@ online_cpus()
 	[[ -n "OFFLINE_CPUS" ]] && {
 		for C in $OFFLINE_CPUS
 		do
-			write_cpu_online ${C}-1
+			write_cpu_online ${C}=1
 		done
 	}
 }
 
 #
-# Return 1 if the list of effective cpus isn't the same as the initial list.
+# Remove all the test cgroup directories
 #
 reset_cgroup_states()
 {
 	echo 0 > $CGROUP2/cgroup.procs
 	online_cpus
-	rmdir A1/A2/A3 A1/A2 A1 B1 > /dev/null 2>&1
-	set_ctrl_state . S-
-	pause 0.01
+	rmdir $RESET_LIST > /dev/null 2>&1
 }
 
 dump_states()
 {
-	for DIR in A1 A1/A2 A1/A2/A3 B1
+	for DIR in $CGROUP_LIST
 	do
+		CPUS=$DIR/cpuset.cpus
 		ECPUS=$DIR/cpuset.cpus.effective
+		XCPUS=$DIR/cpuset.cpus.exclusive
+		XECPUS=$DIR/cpuset.cpus.exclusive.effective
 		PRS=$DIR/cpuset.cpus.partition
-		[[ -e $ECPUS ]] && echo "$ECPUS: $(cat $ECPUS)"
-		[[ -e $PRS   ]] && echo "$PRS: $(cat $PRS)"
+		PCPUS=$DIR/.__DEBUG__.cpuset.cpus.subpartitions
+		ISCPUS=$DIR/cpuset.cpus.isolated
+		[[ -e $CPUS   ]] && echo "$CPUS: $(cat $CPUS)"
+		[[ -e $XCPUS  ]] && echo "$XCPUS: $(cat $XCPUS)"
+		[[ -e $ECPUS  ]] && echo "$ECPUS: $(cat $ECPUS)"
+		[[ -e $XECPUS ]] && echo "$XECPUS: $(cat $XECPUS)"
+		[[ -e $PRS    ]] && echo "$PRS: $(cat $PRS)"
+		[[ -e $PCPUS  ]] && echo "$PCPUS: $(cat $PCPUS)"
+		[[ -e $ISCPUS ]] && echo "$ISCPUS: $(cat $ISCPUS)"
 	done
 }
 
 #
+# Set the actual cgroup directory into $CGRP_DIR
+# $1 - cgroup name
+#
+set_cgroup_dir()
+{
+	CGRP_DIR=$1
+	[[ $CGRP_DIR = A2  ]] && CGRP_DIR=A1/A2
+	[[ $CGRP_DIR = A3  ]] && CGRP_DIR=A1/A2/A3
+	[[ $CGRP_DIR = c11 ]] && CGRP_DIR=p1/c11
+	[[ $CGRP_DIR = c12 ]] && CGRP_DIR=p1/c12
+	[[ $CGRP_DIR = c21 ]] && CGRP_DIR=p2/c21
+	[[ $CGRP_DIR = c22 ]] && CGRP_DIR=p2/c22
+}
+
+#
 # Check effective cpus
-# $1 - check string, format: <cgroup>:<cpu-list>[,<cgroup>:<cpu-list>]*
+# $1 - check string, format: <cgroup>:<cpu-list>[|<cgroup>:<cpu-list>]*
 #
 check_effective_cpus()
 {
 	CHK_STR=$1
-	for CHK in $(echo $CHK_STR | sed -e "s/,/ /g")
+	for CHK in $(echo $CHK_STR | sed -e "s/|/ /g")
 	do
 		set -- $(echo $CHK | sed -e "s/:/ /g")
 		CGRP=$1
-		CPUS=$2
-		[[ $CGRP = A2 ]] && CGRP=A1/A2
-		[[ $CGRP = A3 ]] && CGRP=A1/A2/A3
-		FILE=$CGRP/cpuset.cpus.effective
-		[[ -e $FILE ]] || return 1
-		[[ $CPUS = $(cat $FILE) ]] || return 1
+		EXPECTED_CPUS=$2
+		ACTUAL_CPUS=
+		if [[ $CGRP = X* ]]
+		then
+			CGRP=${CGRP#X}
+			FILE=cpuset.cpus.exclusive.effective
+		else
+			FILE=cpuset.cpus.effective
+		fi
+		set_cgroup_dir $CGRP
+		[[ -e $CGRP_DIR/$FILE ]] || return 1
+		ACTUAL_CPUS=$(cat $CGRP_DIR/$FILE)
+		[[ $EXPECTED_CPUS = $ACTUAL_CPUS ]] || return 1
 	done
 }
 
 #
 # Check cgroup states
-#  $1 - check string, format: <cgroup>:<state>[,<cgroup>:<state>]*
+#  $1 - check string, format: <cgroup>:<state>[|<cgroup>:<state>]*
 #
 check_cgroup_states()
 {
 	CHK_STR=$1
-	for CHK in $(echo $CHK_STR | sed -e "s/,/ /g")
+	for CHK in $(echo $CHK_STR | sed -e "s/|/ /g")
 	do
 		set -- $(echo $CHK | sed -e "s/:/ /g")
 		CGRP=$1
-		STATE=$2
+		EXPECTED_STATE=$2
 		FILE=
-		EVAL=$(expr substr $STATE 2 2)
-		[[ $CGRP = A2 ]] && CGRP=A1/A2
-		[[ $CGRP = A3 ]] && CGRP=A1/A2/A3
+		EVAL=$(expr substr $EXPECTED_STATE 2 2)
 
-		case $STATE in
-			P*) FILE=$CGRP/cpuset.cpus.partition
+		set_cgroup_dir $CGRP
+		case $EXPECTED_STATE in
+			P*) FILE=$CGRP_DIR/cpuset.cpus.partition
 			    ;;
-			*)  echo "Unknown state: $STATE!"
+			*)  echo "Unknown state: $EXPECTED_STATE!"
 			    exit 1
 			    ;;
 		esac
-		VAL=$(cat $FILE)
+		ACTUAL_STATE=$(cat $FILE)
 
-		case "$VAL" in
+		case "$ACTUAL_STATE" in
 			member) VAL=0
 				;;
 			root)	VAL=1
@@ -513,11 +724,204 @@ check_cgroup_states()
 				;;
 		esac
 		[[ $EVAL != $VAL ]] && return 1
+
+		#
+		# For root partition, dump sched-domains info to console if
+		# verbose mode set for manual comparison with sched debug info.
+		#
+		[[ $VAL -eq 1 && $VERBOSE -gt 0 ]] && {
+			DOMS=$(cat $CGRP_DIR/cpuset.cpus.effective)
+			[[ -n "$DOMS" ]] &&
+				echo " [$CGRP_DIR] sched-domain: $DOMS" > $CONSOLE
+		}
 	done
 	return 0
 }
 
 #
+# Get isolated (including offline) CPUs by looking at
+# /sys/kernel/debug/sched/domains and cpuset.cpus.isolated control file,
+# if available, and compare that with the expected value.
+#
+# Note that isolated CPUs from the sched/domains context include offline
+# CPUs as well as CPUs in non-isolated 1-CPU partition. Those CPUs may
+# not be included in the cpuset.cpus.isolated control file which contains
+# only CPUs in isolated partitions as well as those that are isolated at
+# boot time.
+#
+# $1 - expected isolated cpu list(s) <isolcpus1>{,<isolcpus2>}
+# <isolcpus1> - expected sched/domains value
+# <isolcpus2> - cpuset.cpus.isolated value = <isolcpus1> if not defined
+#
+check_isolcpus()
+{
+	EXPECTED_ISOLCPUS=$1
+	ISCPUS=${CGROUP2}/cpuset.cpus.isolated
+	ISOLCPUS=$(cat $ISCPUS)
+	LASTISOLCPU=
+	SCHED_DOMAINS=/sys/kernel/debug/sched/domains
+	if [[ $EXPECTED_ISOLCPUS = . ]]
+	then
+		EXPECTED_ISOLCPUS=
+		EXPECTED_SDOMAIN=
+	elif [[ $(expr $EXPECTED_ISOLCPUS : ".*|.*") > 0 ]]
+	then
+		set -- $(echo $EXPECTED_ISOLCPUS | sed -e "s/|/ /g")
+		EXPECTED_ISOLCPUS=$2
+		EXPECTED_SDOMAIN=$1
+	else
+		EXPECTED_SDOMAIN=$EXPECTED_ISOLCPUS
+	fi
+
+	#
+	# Appending pre-isolated CPUs
+	# Even though CPU #8 isn't used for testing, it can't be pre-isolated
+	# to make appending those CPUs easier.
+	#
+	[[ -n "$BOOT_ISOLCPUS" ]] && {
+		EXPECTED_ISOLCPUS=${EXPECTED_ISOLCPUS:+${EXPECTED_ISOLCPUS},}${BOOT_ISOLCPUS}
+		EXPECTED_SDOMAIN=${EXPECTED_SDOMAIN:+${EXPECTED_SDOMAIN},}${BOOT_ISOLCPUS}
+	}
+
+	#
+	# Check cpuset.cpus.isolated cpumask
+	#
+	[[ "$EXPECTED_ISOLCPUS" != "$ISOLCPUS" ]] && {
+		# Take a 50ms pause and try again
+		pause 0.05
+		ISOLCPUS=$(cat $ISCPUS)
+	}
+	[[ "$EXPECTED_ISOLCPUS" != "$ISOLCPUS" ]] && return 1
+	ISOLCPUS=
+	EXPECTED_ISOLCPUS=$EXPECTED_SDOMAIN
+
+	#
+	# Use the sched domain in debugfs to check isolated CPUs, if available
+	#
+	[[ -d $SCHED_DOMAINS ]] || return 0
+
+	for ((CPU=0; CPU < $NR_CPUS; CPU++))
+	do
+		[[ -n "$(ls ${SCHED_DOMAINS}/cpu$CPU)" ]] && continue
+
+		if [[ -z "$LASTISOLCPU" ]]
+		then
+			ISOLCPUS=$CPU
+			LASTISOLCPU=$CPU
+		elif [[ "$LASTISOLCPU" -eq $((CPU - 1)) ]]
+		then
+			echo $ISOLCPUS | grep -q "\<$LASTISOLCPU\$"
+			if [[ $? -eq 0 ]]
+			then
+				ISOLCPUS=${ISOLCPUS}-
+			fi
+			LASTISOLCPU=$CPU
+		else
+			if [[ $ISOLCPUS = *- ]]
+			then
+				ISOLCPUS=${ISOLCPUS}$LASTISOLCPU
+			fi
+			ISOLCPUS=${ISOLCPUS},$CPU
+			LASTISOLCPU=$CPU
+		fi
+	done
+	[[ "$ISOLCPUS" = *- ]] && ISOLCPUS=${ISOLCPUS}$LASTISOLCPU
+
+	[[ "$EXPECTED_SDOMAIN" = "$ISOLCPUS" ]]
+}
+
+test_fail()
+{
+	TESTNUM=$1
+	TESTTYPE=$2
+	ADDINFO=$3
+	echo "Test $TEST[$TESTNUM] failed $TESTTYPE check!"
+	[[ -n "$ADDINFO" ]] && echo "*** $ADDINFO ***"
+	eval echo \${$TEST[$I]}
+	echo
+	dump_states
+	exit 1
+}
+
+#
+# Check to see if there are unexpected isolated CPUs left beyond the boot
+# time isolated ones.
+#
+null_isolcpus_check()
+{
+	[[ $VERBOSE -gt 0 ]] || return 0
+	# Retry a few times before printing error
+	RETRY=0
+	while [[ $RETRY -lt 8 ]]
+	do
+		pause 0.02
+		check_isolcpus "."
+		[[ $? -eq 0 ]] && return 0
+		((RETRY++))
+	done
+	echo "Unexpected isolated CPUs: $ISOLCPUS"
+	dump_states
+	exit 1
+}
+
+#
+# Check state transition test result
+#  $1 - Test number
+#  $2 - Expected effective CPU values
+#  $3 - Expected partition states
+#  $4 - Expected isolated CPUs
+#
+check_test_results()
+{
+	_NR=$1
+	_ECPUS="$2"
+	_PSTATES="$3"
+	_ISOLCPUS="$4"
+
+	[[ -n "$_ECPUS" && "$_ECPUS" != . ]] && {
+		check_effective_cpus $_ECPUS
+		[[ $? -ne 0 ]] && test_fail $_NR "effective CPU" \
+			 "Cgroup $CGRP: expected $EXPECTED_CPUS, got $ACTUAL_CPUS"
+	}
+
+	[[ -n "$_PSTATES" && "$_PSTATES" != . ]] && {
+		check_cgroup_states $_PSTATES
+		[[ $? -ne 0 ]] && test_fail $_NR states \
+			"Cgroup $CGRP: expected $EXPECTED_STATE, got $ACTUAL_STATE"
+	}
+
+	# Compare the expected isolated CPUs with the actual ones,
+	# if available
+	[[ -n "$_ISOLCPUS" ]] && {
+		check_isolcpus $_ISOLCPUS
+		[[ $? -ne 0 ]] && {
+			[[ -n "$BOOT_ISOLCPUS" ]] && _ISOLCPUS=${_ISOLCPUS},${BOOT_ISOLCPUS}
+			test_fail $_NR "isolated CPU" \
+				"Expect $_ISOLCPUS, get $ISOLCPUS instead"
+		}
+	}
+	reset_cgroup_states
+	#
+	# Check to see if effective cpu list changes
+	#
+	_NEWLIST=$(cat $CGROUP2/cpuset.cpus.effective)
+	RETRY=0
+	while [[ $_NEWLIST != $CPULIST && $RETRY -lt 8 ]]
+	do
+		# Wait a bit longer & recheck a few times
+		pause 0.02
+		((RETRY++))
+		_NEWLIST=$(cat $CGROUP2/cpuset.cpus.effective)
+	done
+	[[ $_NEWLIST != $CPULIST ]] && {
+		echo "Effective cpus changed to $_NEWLIST after test $_NR!"
+		exit 1
+	}
+	null_isolcpus_check
+	[[ $VERBOSE -gt 0 ]] && echo "Test $I done."
+}
+
+#
 # Run cpuset state transition test
 #  $1 - test matrix name
 #
@@ -529,91 +933,189 @@ run_state_test()
 {
 	TEST=$1
 	CONTROLLER=cpuset
-	CPULIST=0-6
+	CGROUP_LIST=". A1 A1/A2 A1/A2/A3 B1"
+	RESET_LIST="A1/A2/A3 A1/A2 A1 B1"
 	I=0
 	eval CNT="\${#$TEST[@]}"
 
 	reset_cgroup_states
-	echo $CPULIST > cpuset.cpus
-	echo root > cpuset.cpus.partition
 	console_msg "Running state transition test ..."
 
 	while [[ $I -lt $CNT ]]
 	do
-		echo "Running test $I ..." > /dev/console
+		echo "Running test $I ..." > $CONSOLE
+		[[ $VERBOSE -gt 1 ]] && {
+			echo ""
+			eval echo \${$TEST[$I]}
+		}
 		eval set -- "\${$TEST[$I]}"
-		ROOT=$1
-		OLD_A1=$2
-		OLD_A2=$3
-		OLD_A3=$4
-		OLD_B1=$5
-		NEW_A1=$6
-		NEW_A2=$7
-		NEW_A3=$8
-		NEW_B1=$9
-		RESULT=${10}
-		ECPUS=${11}
-		STATES=${12}
-
-		set_ctrl_state_noerr .        $ROOT
+		OLD_A1=$1
+		OLD_A2=$2
+		OLD_A3=$3
+		OLD_B1=$4
+		NEW_A1=$5
+		NEW_A2=$6
+		NEW_A3=$7
+		NEW_B1=$8
+		RESULT=$9
+		ECPUS=${10}
+		STATES=${11}
+		ICPUS=${12}
+
 		set_ctrl_state_noerr A1       $OLD_A1
 		set_ctrl_state_noerr A1/A2    $OLD_A2
 		set_ctrl_state_noerr A1/A2/A3 $OLD_A3
 		set_ctrl_state_noerr B1       $OLD_B1
+
 		RETVAL=0
 		set_ctrl_state A1       $NEW_A1; ((RETVAL += $?))
 		set_ctrl_state A1/A2    $NEW_A2; ((RETVAL += $?))
 		set_ctrl_state A1/A2/A3 $NEW_A3; ((RETVAL += $?))
 		set_ctrl_state B1       $NEW_B1; ((RETVAL += $?))
 
-		[[ $RETVAL -ne $RESULT ]] && {
-			echo "Test $TEST[$I] failed result check!"
-			eval echo \"\${$TEST[$I]}\"
-			dump_states
-			online_cpus
-			exit 1
-		}
+		[[ $RETVAL -ne $RESULT ]] && test_fail $I result
 
-		[[ -n "$ECPUS" && "$ECPUS" != . ]] && {
-			check_effective_cpus $ECPUS
-			[[ $? -ne 0 ]] && {
-				echo "Test $TEST[$I] failed effective CPU check!"
-				eval echo \"\${$TEST[$I]}\"
-				echo
-				dump_states
-				online_cpus
-				exit 1
-			}
-		}
+		check_test_results $I "$ECPUS" "$STATES" "$ICPUS"
+		((I++))
+	done
+	echo "All $I tests of $TEST PASSED."
+}
 
-		[[ -n "$STATES" ]] && {
-			check_cgroup_states $STATES
-			[[ $? -ne 0 ]] && {
-				echo "FAILED: Test $TEST[$I] failed states check!"
-				eval echo \"\${$TEST[$I]}\"
-				echo
-				dump_states
-				online_cpus
-				exit 1
-			}
-		}
+#
+# Run cpuset remote partition state transition test
+#  $1 - test matrix name
+#
+run_remote_state_test()
+{
+	TEST=$1
+	CONTROLLER=cpuset
+	[[ -d rtest ]] || mkdir rtest
+	cd rtest
+	echo +cpuset > cgroup.subtree_control
+	echo "1-7" > cpuset.cpus
+	echo "1-7" > cpuset.cpus.exclusive
+	CGROUP_LIST=".. . p1 p2 p1/c11 p1/c12 p2/c21 p2/c22"
+	RESET_LIST="p1/c11 p1/c12 p2/c21 p2/c22 p1 p2"
+	I=0
+	eval CNT="\${#$TEST[@]}"
 
-		reset_cgroup_states
-		#
-		# Check to see if effective cpu list changes
-		#
-		pause 0.05
-		NEWLIST=$(cat cpuset.cpus.effective)
-		[[ $NEWLIST != $CPULIST ]] && {
-			echo "Effective cpus changed to $NEWLIST after test $I!"
-			exit 1
+	reset_cgroup_states
+	console_msg "Running remote partition state transition test ..."
+
+	while [[ $I -lt $CNT ]]
+	do
+		echo "Running test $I ..." > $CONSOLE
+		[[ $VERBOSE -gt 1 ]] && {
+			echo ""
+			eval echo \${$TEST[$I]}
 		}
-		[[ -n "$VERBOSE" ]] && echo "Test $I done."
+		eval set -- "\${$TEST[$I]}"
+		OLD_p1=$1
+		OLD_p2=$2
+		OLD_c11=$3
+		OLD_c12=$4
+		OLD_c21=$5
+		OLD_c22=$6
+		NEW_p1=$7
+		NEW_p2=$8
+		NEW_c11=$9
+		NEW_c12=${10}
+		NEW_c21=${11}
+		NEW_c22=${12}
+		ECPUS=${13}
+		STATES=${14}
+		ICPUS=${15}
+
+		set_ctrl_state_noerr p1     $OLD_p1
+		set_ctrl_state_noerr p2     $OLD_p2
+		set_ctrl_state_noerr p1/c11 $OLD_c11
+		set_ctrl_state_noerr p1/c12 $OLD_c12
+		set_ctrl_state_noerr p2/c21 $OLD_c21
+		set_ctrl_state_noerr p2/c22 $OLD_c22
+
+		RETVAL=0
+		set_ctrl_state p1     $NEW_p1 ; ((RETVAL += $?))
+		set_ctrl_state p2     $NEW_p2 ; ((RETVAL += $?))
+		set_ctrl_state p1/c11 $NEW_c11; ((RETVAL += $?))
+		set_ctrl_state p1/c12 $NEW_c12; ((RETVAL += $?))
+		set_ctrl_state p2/c21 $NEW_c21; ((RETVAL += $?))
+		set_ctrl_state p2/c22 $NEW_c22; ((RETVAL += $?))
+
+		[[ $RETVAL -ne 0 ]] && test_fail $I result
+
+		check_test_results $I "$ECPUS" "$STATES" "$ICPUS"
 		((I++))
 	done
+	cd ..
+	rmdir rtest
 	echo "All $I tests of $TEST PASSED."
+}
 
-	echo member > cpuset.cpus.partition
+#
+# Testing the new "isolated" partition root type
+#
+test_isolated()
+{
+	cd $CGROUP2/test
+	echo 2-3 > cpuset.cpus
+	TYPE=$(cat cpuset.cpus.partition)
+	[[ $TYPE = member ]] || echo member > cpuset.cpus.partition
+
+	console_msg "Change from member to root"
+	test_partition root
+
+	console_msg "Change from root to isolated"
+	test_partition isolated
+
+	console_msg "Change from isolated to member"
+	test_partition member
+
+	console_msg "Change from member to isolated"
+	test_partition isolated
+
+	console_msg "Change from isolated to root"
+	test_partition root
+
+	console_msg "Change from root to member"
+	test_partition member
+
+	#
+	# Testing partition root with no cpu
+	#
+	console_msg "Distribute all cpus to child partition"
+	echo +cpuset > cgroup.subtree_control
+	test_partition root
+
+	mkdir A1
+	cd A1
+	echo 2-3 > cpuset.cpus
+	test_partition root
+	test_effective_cpus 2-3
+	cd ..
+	test_effective_cpus ""
+
+	console_msg "Moving task to partition test"
+	test_add_proc "No space left"
+	cd A1
+	test_add_proc ""
+	cd ..
+
+	console_msg "Shrink and expand child partition"
+	cd A1
+	echo 2 > cpuset.cpus
+	cd ..
+	test_effective_cpus 3
+	cd A1
+	echo 2-3 > cpuset.cpus
+	cd ..
+	test_effective_cpus ""
+
+	# Cleaning up
+	console_msg "Cleaning up"
+	echo $$ > $CGROUP2/cgroup.procs
+	[[ -d A1 ]] && rmdir A1
+	null_isolcpus_check
+	pause 0.05
 }
 
 #
@@ -638,6 +1140,7 @@ test_inotify()
 {
 	ERR=0
 	PRS=/tmp/.prs_$$
+	cd $CGROUP2/test
 	[[ -f $WAIT_INOTIFY ]] || {
 		echo "wait_inotify not found, inotify test SKIPPED."
 		return
@@ -651,7 +1154,7 @@ test_inotify()
 	rm -f $PRS
 	wait_inotify $PWD/cpuset.cpus.partition $PRS &
 	pause 0.01
-	set_ctrl_state . "O1-0"
+	set_ctrl_state . "O1=0"
 	pause 0.01
 	check_cgroup_states ".:P-1"
 	if [[ $? -ne 0 ]]
@@ -678,12 +1181,13 @@ test_inotify()
 	else
 		echo "Inotify test PASSED"
 	fi
+	echo member > cpuset.cpus.partition
+	echo "" > cpuset.cpus
 }
 
 trap cleanup 0 2 3 6
 run_state_test TEST_MATRIX
+run_remote_state_test REMOTE_TEST_MATRIX
 test_isolated
 test_inotify
 echo "All tests PASSED."
-cd ..
-rmdir test
diff --git a/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh b/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh
new file mode 100755
index 000000000000..42a6628fb8bc
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_cpuset_v1_base.sh
@@ -0,0 +1,77 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Basc test for cpuset v1 interfaces write/read
+#
+
+skip_test() {
+	echo "$1"
+	echo "Test SKIPPED"
+	exit 4 # ksft_skip
+}
+
+write_test() {
+	dir=$1
+	interface=$2
+	value=$3
+	original=$(cat $dir/$interface)
+	echo "testing $interface $value"
+	echo $value > $dir/$interface
+	new=$(cat $dir/$interface)
+	[[ $value -ne $(cat $dir/$interface) ]] && {
+		echo "$interface write $value failed: new:$new"
+		exit 1
+	}
+}
+
+[[ $(id -u) -eq 0 ]] || skip_test "Test must be run as root!"
+
+# Find cpuset v1 mount point
+CPUSET=$(mount -t cgroup | grep cpuset | head -1 | awk '{print $3}')
+[[ -n "$CPUSET" ]] || skip_test "cpuset v1 mount point not found!"
+
+#
+# Create a test cpuset, read write test
+#
+TDIR=test$$
+[[ -d $CPUSET/$TDIR ]] || mkdir $CPUSET/$TDIR
+
+ITF_MATRIX=(
+	#interface			value		expect 	root_only
+	'cpuset.cpus			0-1		0-1	0'
+	'cpuset.mem_exclusive		1		1	0'
+	'cpuset.mem_exclusive		0		0	0'
+	'cpuset.mem_hardwall		1		1	0'
+	'cpuset.mem_hardwall		0		0	0'
+	'cpuset.memory_migrate		1		1	0'
+	'cpuset.memory_migrate		0		0	0'
+	'cpuset.memory_spread_page	1		1	0'
+	'cpuset.memory_spread_page	0		0	0'
+	'cpuset.memory_spread_slab	1		1	0'
+	'cpuset.memory_spread_slab	0		0	0'
+	'cpuset.mems			0		0	0'
+	'cpuset.sched_load_balance	1		1	0'
+	'cpuset.sched_load_balance	0		0	0'
+	'cpuset.sched_relax_domain_level	2	2	0'
+	'cpuset.memory_pressure_enabled	1		1	1'
+	'cpuset.memory_pressure_enabled	0		0	1'
+)
+
+run_test()
+{
+	cnt="${ITF_MATRIX[@]}"
+	for i in "${ITF_MATRIX[@]}" ; do
+		args=($i)
+		root_only=${args[3]}
+		[[ $root_only -eq 1 ]] && {
+			write_test "$CPUSET" "${args[0]}" "${args[1]}" "${args[2]}"
+			continue
+		}
+		write_test "$CPUSET/$TDIR" "${args[0]}" "${args[1]}" "${args[2]}"
+	done
+}
+
+run_test
+rmdir $CPUSET/$TDIR
+echo "Test PASSED"
+exit 0
diff --git a/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh b/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh
new file mode 100755
index 000000000000..7406c24be1ac
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh
@@ -0,0 +1,46 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test the special cpuset v1 hotplug case where a cpuset become empty of
+# CPUs will force migration of tasks out to an ancestor.
+#
+
+skip_test() {
+	echo "$1"
+	echo "Test SKIPPED"
+	exit 4 # ksft_skip
+}
+
+[[ $(id -u) -eq 0 ]] || skip_test "Test must be run as root!"
+
+# Find cpuset v1 mount point
+CPUSET=$(mount -t cgroup | grep cpuset | head -1 | awk -e '{print $3}')
+[[ -n "$CPUSET" ]] || skip_test "cpuset v1 mount point not found!"
+
+#
+# Create a test cpuset, put a CPU and a task there and offline that CPU
+#
+TDIR=test$$
+[[ -d $CPUSET/$TDIR ]] || mkdir $CPUSET/$TDIR
+echo 1 > $CPUSET/$TDIR/cpuset.cpus
+echo 0 > $CPUSET/$TDIR/cpuset.mems
+sleep 10&
+TASK=$!
+echo $TASK > $CPUSET/$TDIR/tasks
+NEWCS=$(cat /proc/$TASK/cpuset)
+[[ $NEWCS != "/$TDIR" ]] && {
+	echo "Unexpected cpuset $NEWCS, test FAILED!"
+	exit 1
+}
+
+echo 0 > /sys/devices/system/cpu/cpu1/online
+sleep 0.5
+echo 1 > /sys/devices/system/cpu/cpu1/online
+NEWCS=$(cat /proc/$TASK/cpuset)
+rmdir $CPUSET/$TDIR
+[[ $NEWCS != "/" ]] && {
+	echo "cpuset $NEWCS, test FAILED!"
+	exit 1
+}
+echo "Test PASSED"
+exit 0
diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c
index ff519029f6f4..97fae92c8387 100644
--- a/tools/testing/selftests/cgroup/test_freezer.c
+++ b/tools/testing/selftests/cgroup/test_freezer.c
@@ -11,7 +11,7 @@
 #include <string.h>
 #include <sys/wait.h>
 
-#include "../kselftest.h"
+#include "kselftest.h"
 #include "cgroup_util.h"
 
 #define DEBUG
@@ -740,7 +740,7 @@ static int test_cgfreezer_ptraced(const char *root)
 
 	/*
 	 * cg_check_frozen(cgroup, true) will fail here,
-	 * because the task in in the TRACEd state.
+	 * because the task is in the TRACEd state.
 	 */
 	if (cg_freeze_wait(cgroup, false))
 		goto cleanup;
@@ -804,6 +804,662 @@ cleanup:
 	return ret;
 }
 
+/*
+ * Get the current frozen_usec for the cgroup.
+ */
+static long cg_check_freezetime(const char *cgroup)
+{
+	return cg_read_key_long(cgroup, "cgroup.stat.local",
+				"frozen_usec ");
+}
+
+/*
+ * Test that the freeze time will behave as expected for an empty cgroup.
+ */
+static int test_cgfreezer_time_empty(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cgroup = NULL;
+	long prev, curr;
+
+	cgroup = cg_name(root, "cg_time_test_empty");
+	if (!cgroup)
+		goto cleanup;
+
+	/*
+	 * 1) Create an empty cgroup and check that its freeze time
+	 *    is 0.
+	 */
+	if (cg_create(cgroup))
+		goto cleanup;
+
+	curr = cg_check_freezetime(cgroup);
+	if (curr < 0) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+	if (curr > 0) {
+		debug("Expect time (%ld) to be 0\n", curr);
+		goto cleanup;
+	}
+
+	if (cg_freeze_nowait(cgroup, true))
+		goto cleanup;
+
+	/*
+	 * 2) Sleep for 1000 us. Check that the freeze time is at
+	 *    least 1000 us.
+	 */
+	usleep(1000);
+	curr = cg_check_freezetime(cgroup);
+	if (curr < 1000) {
+		debug("Expect time (%ld) to be at least 1000 us\n",
+		      curr);
+		goto cleanup;
+	}
+
+	/*
+	 * 3) Unfreeze the cgroup. Check that the freeze time is
+	 *    larger than at 2).
+	 */
+	if (cg_freeze_nowait(cgroup, false))
+		goto cleanup;
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr <= prev) {
+		debug("Expect time (%ld) to be more than previous check (%ld)\n",
+		      curr, prev);
+		goto cleanup;
+	}
+
+	/*
+	 * 4) Check the freeze time again to ensure that it has not
+	 *    changed.
+	 */
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr != prev) {
+		debug("Expect time (%ld) to be unchanged from previous check (%ld)\n",
+		      curr, prev);
+		goto cleanup;
+	}
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (cgroup)
+		cg_destroy(cgroup);
+	free(cgroup);
+	return ret;
+}
+
+/*
+ * A simple test for cgroup freezer time accounting. This test follows
+ * the same flow as test_cgfreezer_time_empty, but with a single process
+ * in the cgroup.
+ */
+static int test_cgfreezer_time_simple(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cgroup = NULL;
+	long prev, curr;
+
+	cgroup = cg_name(root, "cg_time_test_simple");
+	if (!cgroup)
+		goto cleanup;
+
+	/*
+	 * 1) Create a cgroup and check that its freeze time is 0.
+	 */
+	if (cg_create(cgroup))
+		goto cleanup;
+
+	curr = cg_check_freezetime(cgroup);
+	if (curr < 0) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+	if (curr > 0) {
+		debug("Expect time (%ld) to be 0\n", curr);
+		goto cleanup;
+	}
+
+	/*
+	 * 2) Populate the cgroup with one child and check that the
+	 *    freeze time is still 0.
+	 */
+	cg_run_nowait(cgroup, child_fn, NULL);
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr > prev) {
+		debug("Expect time (%ld) to be 0\n", curr);
+		goto cleanup;
+	}
+
+	if (cg_freeze_nowait(cgroup, true))
+		goto cleanup;
+
+	/*
+	 * 3) Sleep for 1000 us. Check that the freeze time is at
+	 *    least 1000 us.
+	 */
+	usleep(1000);
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr < 1000) {
+		debug("Expect time (%ld) to be at least 1000 us\n",
+		      curr);
+		goto cleanup;
+	}
+
+	/*
+	 * 4) Unfreeze the cgroup. Check that the freeze time is
+	 *    larger than at 3).
+	 */
+	if (cg_freeze_nowait(cgroup, false))
+		goto cleanup;
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr <= prev) {
+		debug("Expect time (%ld) to be more than previous check (%ld)\n",
+		      curr, prev);
+		goto cleanup;
+	}
+
+	/*
+	 * 5) Sleep for 1000 us. Check that the freeze time is the
+	 *    same as at 4).
+	 */
+	usleep(1000);
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr != prev) {
+		debug("Expect time (%ld) to be unchanged from previous check (%ld)\n",
+		      curr, prev);
+		goto cleanup;
+	}
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (cgroup)
+		cg_destroy(cgroup);
+	free(cgroup);
+	return ret;
+}
+
+/*
+ * Test that freezer time accounting works as expected, even while we're
+ * populating a cgroup with processes.
+ */
+static int test_cgfreezer_time_populate(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cgroup = NULL;
+	long prev, curr;
+	int i;
+
+	cgroup = cg_name(root, "cg_time_test_populate");
+	if (!cgroup)
+		goto cleanup;
+
+	if (cg_create(cgroup))
+		goto cleanup;
+
+	curr = cg_check_freezetime(cgroup);
+	if (curr < 0) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+	if (curr > 0) {
+		debug("Expect time (%ld) to be 0\n", curr);
+		goto cleanup;
+	}
+
+	/*
+	 * 1) Populate the cgroup with 100 processes. Check that
+	 *    the freeze time is 0.
+	 */
+	for (i = 0; i < 100; i++)
+		cg_run_nowait(cgroup, child_fn, NULL);
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr != prev) {
+		debug("Expect time (%ld) to be 0\n", curr);
+		goto cleanup;
+	}
+
+	/*
+	 * 2) Wait for the group to become fully populated. Check
+	 *    that the freeze time is 0.
+	 */
+	if (cg_wait_for_proc_count(cgroup, 100))
+		goto cleanup;
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr != prev) {
+		debug("Expect time (%ld) to be 0\n", curr);
+		goto cleanup;
+	}
+
+	/*
+	 * 3) Freeze the cgroup and then populate it with 100 more
+	 *    processes. Check that the freeze time continues to grow.
+	 */
+	if (cg_freeze_nowait(cgroup, true))
+		goto cleanup;
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr <= prev) {
+		debug("Expect time (%ld) to be more than previous check (%ld)\n",
+		      curr, prev);
+		goto cleanup;
+	}
+
+	for (i = 0; i < 100; i++)
+		cg_run_nowait(cgroup, child_fn, NULL);
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr <= prev) {
+		debug("Expect time (%ld) to be more than previous check (%ld)\n",
+		      curr, prev);
+		goto cleanup;
+	}
+
+	/*
+	 * 4) Wait for the group to become fully populated. Check
+	 *    that the freeze time is larger than at 3).
+	 */
+	if (cg_wait_for_proc_count(cgroup, 200))
+		goto cleanup;
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr <= prev) {
+		debug("Expect time (%ld) to be more than previous check (%ld)\n",
+		      curr, prev);
+		goto cleanup;
+	}
+
+	/*
+	 * 5) Unfreeze the cgroup. Check that the freeze time is
+	 *    larger than at 4).
+	 */
+	if (cg_freeze_nowait(cgroup, false))
+		goto cleanup;
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr <= prev) {
+		debug("Expect time (%ld) to be more than previous check (%ld)\n",
+		      curr, prev);
+		goto cleanup;
+	}
+
+	/*
+	 * 6) Kill the processes. Check that the freeze time is the
+	 *    same as it was at 5).
+	 */
+	if (cg_killall(cgroup))
+		goto cleanup;
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr != prev) {
+		debug("Expect time (%ld) to be unchanged from previous check (%ld)\n",
+		      curr, prev);
+		goto cleanup;
+	}
+
+	/*
+	 * 7) Freeze and unfreeze the cgroup. Check that the freeze
+	 *    time is larger than it was at 6).
+	 */
+	if (cg_freeze_nowait(cgroup, true))
+		goto cleanup;
+	if (cg_freeze_nowait(cgroup, false))
+		goto cleanup;
+	prev = curr;
+	curr = cg_check_freezetime(cgroup);
+	if (curr <= prev) {
+		debug("Expect time (%ld) to be more than previous check (%ld)\n",
+		      curr, prev);
+		goto cleanup;
+	}
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (cgroup)
+		cg_destroy(cgroup);
+	free(cgroup);
+	return ret;
+}
+
+/*
+ * Test that frozen time for a cgroup continues to work as expected,
+ * even as processes are migrated. Frozen cgroup A's freeze time should
+ * continue to increase and running cgroup B's should stay 0.
+ */
+static int test_cgfreezer_time_migrate(const char *root)
+{
+	long prev_A, curr_A, curr_B;
+	char *cgroup[2] = {0};
+	int ret = KSFT_FAIL;
+	int pid;
+
+	cgroup[0] = cg_name(root, "cg_time_test_migrate_A");
+	if (!cgroup[0])
+		goto cleanup;
+
+	cgroup[1] = cg_name(root, "cg_time_test_migrate_B");
+	if (!cgroup[1])
+		goto cleanup;
+
+	if (cg_create(cgroup[0]))
+		goto cleanup;
+
+	if (cg_check_freezetime(cgroup[0]) < 0) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	if (cg_create(cgroup[1]))
+		goto cleanup;
+
+	pid = cg_run_nowait(cgroup[0], child_fn, NULL);
+	if (pid < 0)
+		goto cleanup;
+
+	if (cg_wait_for_proc_count(cgroup[0], 1))
+		goto cleanup;
+
+	curr_A = cg_check_freezetime(cgroup[0]);
+	if (curr_A) {
+		debug("Expect time (%ld) to be 0\n", curr_A);
+		goto cleanup;
+	}
+	curr_B = cg_check_freezetime(cgroup[1]);
+	if (curr_B) {
+		debug("Expect time (%ld) to be 0\n", curr_B);
+		goto cleanup;
+	}
+
+	/*
+	 * Freeze cgroup A.
+	 */
+	if (cg_freeze_wait(cgroup[0], true))
+		goto cleanup;
+	prev_A = curr_A;
+	curr_A = cg_check_freezetime(cgroup[0]);
+	if (curr_A <= prev_A) {
+		debug("Expect time (%ld) to be > 0\n", curr_A);
+		goto cleanup;
+	}
+
+	/*
+	 * Migrate from A (frozen) to B (running).
+	 */
+	if (cg_enter(cgroup[1], pid))
+		goto cleanup;
+
+	usleep(1000);
+	curr_B = cg_check_freezetime(cgroup[1]);
+	if (curr_B) {
+		debug("Expect time (%ld) to be 0\n", curr_B);
+		goto cleanup;
+	}
+
+	prev_A = curr_A;
+	curr_A = cg_check_freezetime(cgroup[0]);
+	if (curr_A <= prev_A) {
+		debug("Expect time (%ld) to be more than previous check (%ld)\n",
+		      curr_A, prev_A);
+		goto cleanup;
+	}
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (cgroup[0])
+		cg_destroy(cgroup[0]);
+	free(cgroup[0]);
+	if (cgroup[1])
+		cg_destroy(cgroup[1]);
+	free(cgroup[1]);
+	return ret;
+}
+
+/*
+ * The test creates a cgroup and freezes it. Then it creates a child cgroup.
+ * After that it checks that the child cgroup has a non-zero freeze time
+ * that is less than the parent's. Next, it freezes the child, unfreezes
+ * the parent, and sleeps. Finally, it checks that the child's freeze
+ * time has grown larger than the parent's.
+ */
+static int test_cgfreezer_time_parent(const char *root)
+{
+	char *parent, *child = NULL;
+	int ret = KSFT_FAIL;
+	long ptime, ctime;
+
+	parent = cg_name(root, "cg_test_parent_A");
+	if (!parent)
+		goto cleanup;
+
+	child = cg_name(parent, "cg_test_parent_B");
+	if (!child)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_check_freezetime(parent) < 0) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	if (cg_freeze_wait(parent, true))
+		goto cleanup;
+
+	usleep(1000);
+	if (cg_create(child))
+		goto cleanup;
+
+	if (cg_check_frozen(child, true))
+		goto cleanup;
+
+	/*
+	 * Since the parent was frozen the entire time the child cgroup
+	 * was being created, we expect the parent's freeze time to be
+	 * larger than the child's.
+	 *
+	 * Ideally, we would be able to check both times simultaneously,
+	 * but here we get the child's after we get the parent's.
+	 */
+	ptime = cg_check_freezetime(parent);
+	ctime = cg_check_freezetime(child);
+	if (ptime <= ctime) {
+		debug("Expect ptime (%ld) > ctime (%ld)\n", ptime, ctime);
+		goto cleanup;
+	}
+
+	if (cg_freeze_nowait(child, true))
+		goto cleanup;
+
+	if (cg_freeze_wait(parent, false))
+		goto cleanup;
+
+	if (cg_check_frozen(child, true))
+		goto cleanup;
+
+	usleep(100000);
+
+	ctime = cg_check_freezetime(child);
+	ptime = cg_check_freezetime(parent);
+
+	if (ctime <= ptime) {
+		debug("Expect ctime (%ld) > ptime (%ld)\n", ctime, ptime);
+		goto cleanup;
+	}
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (child)
+		cg_destroy(child);
+	free(child);
+	if (parent)
+		cg_destroy(parent);
+	free(parent);
+	return ret;
+}
+
+/*
+ * The test creates a parent cgroup and a child cgroup. Then, it freezes
+ * the child and checks that the child's freeze time is greater than the
+ * parent's, which should be zero.
+ */
+static int test_cgfreezer_time_child(const char *root)
+{
+	char *parent, *child = NULL;
+	int ret = KSFT_FAIL;
+	long ptime, ctime;
+
+	parent = cg_name(root, "cg_test_child_A");
+	if (!parent)
+		goto cleanup;
+
+	child = cg_name(parent, "cg_test_child_B");
+	if (!child)
+		goto cleanup;
+
+	if (cg_create(parent))
+		goto cleanup;
+
+	if (cg_check_freezetime(parent) < 0) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	if (cg_create(child))
+		goto cleanup;
+
+	if (cg_freeze_wait(child, true))
+		goto cleanup;
+
+	ctime = cg_check_freezetime(child);
+	ptime = cg_check_freezetime(parent);
+	if (ptime != 0) {
+		debug("Expect ptime (%ld) to be 0\n", ptime);
+		goto cleanup;
+	}
+
+	if (ctime <= ptime) {
+		debug("Expect ctime (%ld) <= ptime (%ld)\n", ctime, ptime);
+		goto cleanup;
+	}
+
+	ret = KSFT_PASS;
+
+cleanup:
+	if (child)
+		cg_destroy(child);
+	free(child);
+	if (parent)
+		cg_destroy(parent);
+	free(parent);
+	return ret;
+}
+
+/*
+ * The test creates the following hierarchy:
+ *    A
+ *    |
+ *    B
+ *    |
+ *    C
+ *
+ * Then it freezes the cgroups in the order C, B, A.
+ * Then it unfreezes the cgroups in the order A, B, C.
+ * Then it checks that C's freeze time is larger than B's and
+ * that B's is larger than A's.
+ */
+static int test_cgfreezer_time_nested(const char *root)
+{
+	char *cgroup[3] = {0};
+	int ret = KSFT_FAIL;
+	long time[3] = {0};
+	int i;
+
+	cgroup[0] = cg_name(root, "cg_test_time_A");
+	if (!cgroup[0])
+		goto cleanup;
+
+	cgroup[1] = cg_name(cgroup[0], "B");
+	if (!cgroup[1])
+		goto cleanup;
+
+	cgroup[2] = cg_name(cgroup[1], "C");
+	if (!cgroup[2])
+		goto cleanup;
+
+	if (cg_create(cgroup[0]))
+		goto cleanup;
+
+	if (cg_check_freezetime(cgroup[0]) < 0) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	if (cg_create(cgroup[1]))
+		goto cleanup;
+
+	if (cg_create(cgroup[2]))
+		goto cleanup;
+
+	if (cg_freeze_nowait(cgroup[2], true))
+		goto cleanup;
+
+	if (cg_freeze_nowait(cgroup[1], true))
+		goto cleanup;
+
+	if (cg_freeze_nowait(cgroup[0], true))
+		goto cleanup;
+
+	usleep(1000);
+
+	if (cg_freeze_nowait(cgroup[0], false))
+		goto cleanup;
+
+	if (cg_freeze_nowait(cgroup[1], false))
+		goto cleanup;
+
+	if (cg_freeze_nowait(cgroup[2], false))
+		goto cleanup;
+
+	time[2] = cg_check_freezetime(cgroup[2]);
+	time[1] = cg_check_freezetime(cgroup[1]);
+	time[0] = cg_check_freezetime(cgroup[0]);
+
+	if (time[2] <= time[1]) {
+		debug("Expect C's time (%ld) > B's time (%ld)", time[2], time[1]);
+		goto cleanup;
+	}
+
+	if (time[1] <= time[0]) {
+		debug("Expect B's time (%ld) > A's time (%ld)", time[1], time[0]);
+		goto cleanup;
+	}
+
+	ret = KSFT_PASS;
+
+cleanup:
+	for (i = 2; i >= 0 && cgroup[i]; i--) {
+		cg_destroy(cgroup[i]);
+		free(cgroup[i]);
+	}
+
+	return ret;
+}
+
 #define T(x) { x, #x }
 struct cgfreezer_test {
 	int (*fn)(const char *root);
@@ -819,15 +1475,24 @@ struct cgfreezer_test {
 	T(test_cgfreezer_stopped),
 	T(test_cgfreezer_ptraced),
 	T(test_cgfreezer_vfork),
+	T(test_cgfreezer_time_empty),
+	T(test_cgfreezer_time_simple),
+	T(test_cgfreezer_time_populate),
+	T(test_cgfreezer_time_migrate),
+	T(test_cgfreezer_time_parent),
+	T(test_cgfreezer_time_child),
+	T(test_cgfreezer_time_nested),
 };
 #undef T
 
 int main(int argc, char *argv[])
 {
 	char root[PATH_MAX];
-	int i, ret = EXIT_SUCCESS;
+	int i;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		switch (tests[i].fn(root)) {
@@ -838,11 +1503,10 @@ int main(int argc, char *argv[])
 			ksft_test_result_skip("%s\n", tests[i].name);
 			break;
 		default:
-			ret = EXIT_FAILURE;
 			ksft_test_result_fail("%s\n", tests[i].name);
 			break;
 		}
 	}
 
-	return ret;
+	ksft_finished();
 }
diff --git a/tools/testing/selftests/cgroup/test_hugetlb_memcg.c b/tools/testing/selftests/cgroup/test_hugetlb_memcg.c
new file mode 100644
index 000000000000..f451aa449be6
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_hugetlb_memcg.c
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <linux/limits.h>
+#include <sys/mman.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <fcntl.h>
+#include "kselftest.h"
+#include "cgroup_util.h"
+
+#define ADDR ((void *)(0x0UL))
+#define FLAGS (MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB)
+/* mapping 8 MBs == 4 hugepages */
+#define LENGTH (8UL*1024*1024)
+#define PROTECTION (PROT_READ | PROT_WRITE)
+
+/* borrowed from mm/hmm-tests.c */
+static long get_hugepage_size(void)
+{
+	int fd;
+	char buf[2048];
+	int len;
+	char *p, *q, *path = "/proc/meminfo", *tag = "Hugepagesize:";
+	long val;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0) {
+		/* Error opening the file */
+		return -1;
+	}
+
+	len = read(fd, buf, sizeof(buf));
+	close(fd);
+	if (len < 0) {
+		/* Error in reading the file */
+		return -1;
+	}
+	if (len == sizeof(buf)) {
+		/* Error file is too large */
+		return -1;
+	}
+	buf[len] = '\0';
+
+	/* Search for a tag if provided */
+	if (tag) {
+		p = strstr(buf, tag);
+		if (!p)
+			return -1; /* looks like the line we want isn't there */
+		p += strlen(tag);
+	} else
+		p = buf;
+
+	val = strtol(p, &q, 0);
+	if (*q != ' ') {
+		/* Error parsing the file */
+		return -1;
+	}
+
+	return val;
+}
+
+static int set_file(const char *path, long value)
+{
+	FILE *file;
+	int ret;
+
+	file = fopen(path, "w");
+	if (!file)
+		return -1;
+	ret = fprintf(file, "%ld\n", value);
+	fclose(file);
+	return ret;
+}
+
+static int set_nr_hugepages(long value)
+{
+	return set_file("/proc/sys/vm/nr_hugepages", value);
+}
+
+static unsigned int check_first(char *addr)
+{
+	return *(unsigned int *)addr;
+}
+
+static void write_data(char *addr)
+{
+	unsigned long i;
+
+	for (i = 0; i < LENGTH; i++)
+		*(addr + i) = (char)i;
+}
+
+static int hugetlb_test_program(const char *cgroup, void *arg)
+{
+	char *test_group = (char *)arg;
+	void *addr;
+	long old_current, expected_current, current;
+	int ret = EXIT_FAILURE;
+
+	old_current = cg_read_long(test_group, "memory.current");
+	set_nr_hugepages(20);
+	current = cg_read_long(test_group, "memory.current");
+	if (current - old_current >= MB(2)) {
+		ksft_print_msg(
+			"setting nr_hugepages should not increase hugepage usage.\n");
+		ksft_print_msg("before: %ld, after: %ld\n", old_current, current);
+		return EXIT_FAILURE;
+	}
+
+	addr = mmap(ADDR, LENGTH, PROTECTION, FLAGS, 0, 0);
+	if (addr == MAP_FAILED) {
+		ksft_print_msg("fail to mmap.\n");
+		return EXIT_FAILURE;
+	}
+	current = cg_read_long(test_group, "memory.current");
+	if (current - old_current >= MB(2)) {
+		ksft_print_msg("mmap should not increase hugepage usage.\n");
+		ksft_print_msg("before: %ld, after: %ld\n", old_current, current);
+		goto out_failed_munmap;
+	}
+	old_current = current;
+
+	/* read the first page */
+	check_first(addr);
+	expected_current = old_current + MB(2);
+	current = cg_read_long(test_group, "memory.current");
+	if (!values_close(expected_current, current, 5)) {
+		ksft_print_msg("memory usage should increase by around 2MB.\n");
+		ksft_print_msg(
+			"expected memory: %ld, actual memory: %ld\n",
+			expected_current, current);
+		goto out_failed_munmap;
+	}
+
+	/* write to the whole range */
+	write_data(addr);
+	current = cg_read_long(test_group, "memory.current");
+	expected_current = old_current + MB(8);
+	if (!values_close(expected_current, current, 5)) {
+		ksft_print_msg("memory usage should increase by around 8MB.\n");
+		ksft_print_msg(
+			"expected memory: %ld, actual memory: %ld\n",
+			expected_current, current);
+		goto out_failed_munmap;
+	}
+
+	/* unmap the whole range */
+	munmap(addr, LENGTH);
+	current = cg_read_long(test_group, "memory.current");
+	expected_current = old_current;
+	if (!values_close(expected_current, current, 5)) {
+		ksft_print_msg("memory usage should go back down.\n");
+		ksft_print_msg(
+			"expected memory: %ld, actual memory: %ld\n",
+			expected_current, current);
+		return ret;
+	}
+
+	ret = EXIT_SUCCESS;
+	return ret;
+
+out_failed_munmap:
+	munmap(addr, LENGTH);
+	return ret;
+}
+
+static int test_hugetlb_memcg(char *root)
+{
+	int ret = KSFT_FAIL;
+	char *test_group;
+
+	test_group = cg_name(root, "hugetlb_memcg_test");
+	if (!test_group || cg_create(test_group)) {
+		ksft_print_msg("fail to create cgroup.\n");
+		goto out;
+	}
+
+	if (cg_write(test_group, "memory.max", "100M")) {
+		ksft_print_msg("fail to set cgroup memory limit.\n");
+		goto out;
+	}
+
+	/* disable swap */
+	if (cg_write(test_group, "memory.swap.max", "0")) {
+		ksft_print_msg("fail to disable swap.\n");
+		goto out;
+	}
+
+	if (!cg_run(test_group, hugetlb_test_program, (void *)test_group))
+		ret = KSFT_PASS;
+out:
+	cg_destroy(test_group);
+	free(test_group);
+	return ret;
+}
+
+int main(int argc, char **argv)
+{
+	char root[PATH_MAX];
+	int ret = EXIT_SUCCESS, has_memory_hugetlb_acc;
+
+	has_memory_hugetlb_acc = proc_mount_contains("memory_hugetlb_accounting");
+	if (has_memory_hugetlb_acc < 0)
+		ksft_exit_skip("Failed to query cgroup mount option\n");
+	else if (!has_memory_hugetlb_acc)
+		ksft_exit_skip("memory hugetlb accounting is disabled\n");
+
+	/* Unit is kB! */
+	if (get_hugepage_size() != 2048) {
+		ksft_print_msg("test_hugetlb_memcg requires 2MB hugepages\n");
+		ksft_test_result_skip("test_hugetlb_memcg\n");
+		return ret;
+	}
+
+	if (cg_find_unified_root(root, sizeof(root), NULL))
+		ksft_exit_skip("cgroup v2 isn't mounted\n");
+
+	switch (test_hugetlb_memcg(root)) {
+	case KSFT_PASS:
+		ksft_test_result_pass("test_hugetlb_memcg\n");
+		break;
+	case KSFT_SKIP:
+		ksft_test_result_skip("test_hugetlb_memcg\n");
+		break;
+	default:
+		ret = EXIT_FAILURE;
+		ksft_test_result_fail("test_hugetlb_memcg\n");
+		break;
+	}
+
+	return ret;
+}
diff --git a/tools/testing/selftests/cgroup/test_kill.c b/tools/testing/selftests/cgroup/test_kill.c
index 6153690319c9..c8c9d306925b 100644
--- a/tools/testing/selftests/cgroup/test_kill.c
+++ b/tools/testing/selftests/cgroup/test_kill.c
@@ -9,7 +9,7 @@
 #include <sys/types.h>
 #include <unistd.h>
 
-#include "../kselftest.h"
+#include "kselftest.h"
 #include "../pidfd/pidfd.h"
 #include "cgroup_util.h"
 
@@ -274,9 +274,11 @@ struct cgkill_test {
 int main(int argc, char *argv[])
 {
 	char root[PATH_MAX];
-	int i, ret = EXIT_SUCCESS;
+	int i;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
 		switch (tests[i].fn(root)) {
@@ -287,11 +289,10 @@ int main(int argc, char *argv[])
 			ksft_test_result_skip("%s\n", tests[i].name);
 			break;
 		default:
-			ret = EXIT_FAILURE;
 			ksft_test_result_fail("%s\n", tests[i].name);
 			break;
 		}
 	}
 
-	return ret;
+	ksft_finished();
 }
diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c
index 258ddc565deb..ca38525484e3 100644
--- a/tools/testing/selftests/cgroup/test_kmem.c
+++ b/tools/testing/selftests/cgroup/test_kmem.c
@@ -14,7 +14,7 @@
 #include <sys/sysinfo.h>
 #include <pthread.h>
 
-#include "../kselftest.h"
+#include "kselftest.h"
 #include "cgroup_util.h"
 
 
@@ -70,12 +70,16 @@ static int test_kmem_basic(const char *root)
 		goto cleanup;
 
 	cg_write(cg, "memory.high", "1M");
+
+	/* wait for RCU freeing */
+	sleep(1);
+
 	slab1 = cg_read_key_long(cg, "memory.stat", "slab ");
-	if (slab1 <= 0)
+	if (slab1 < 0)
 		goto cleanup;
 
 	current = cg_read_long(cg, "memory.current");
-	if (current <= 0)
+	if (current < 0)
 		goto cleanup;
 
 	if (slab1 < slab0 / 2 && current < slab0 / 2)
@@ -158,11 +162,11 @@ static int cg_run_in_subcgroups(const char *parent,
  * allocates some slab memory (mostly negative dentries) using 2 * NR_CPUS
  * threads. Then it checks the sanity of numbers on the parent level:
  * the total size of the cgroups should be roughly equal to
- * anon + file + slab + kernel_stack.
+ * anon + file + kernel + sock.
  */
 static int test_kmem_memcg_deletion(const char *root)
 {
-	long current, slab, anon, file, kernel_stack, pagetables, percpu, sock, sum;
+	long current, anon, file, kernel, sock, sum;
 	int ret = KSFT_FAIL;
 	char *parent;
 
@@ -180,29 +184,22 @@ static int test_kmem_memcg_deletion(const char *root)
 		goto cleanup;
 
 	current = cg_read_long(parent, "memory.current");
-	slab = cg_read_key_long(parent, "memory.stat", "slab ");
 	anon = cg_read_key_long(parent, "memory.stat", "anon ");
 	file = cg_read_key_long(parent, "memory.stat", "file ");
-	kernel_stack = cg_read_key_long(parent, "memory.stat", "kernel_stack ");
-	pagetables = cg_read_key_long(parent, "memory.stat", "pagetables ");
-	percpu = cg_read_key_long(parent, "memory.stat", "percpu ");
+	kernel = cg_read_key_long(parent, "memory.stat", "kernel ");
 	sock = cg_read_key_long(parent, "memory.stat", "sock ");
-	if (current < 0 || slab < 0 || anon < 0 || file < 0 ||
-	    kernel_stack < 0 || pagetables < 0 || percpu < 0 || sock < 0)
+	if (current < 0 || anon < 0 || file < 0 || kernel < 0 || sock < 0)
 		goto cleanup;
 
-	sum = slab + anon + file + kernel_stack + pagetables + percpu + sock;
-	if (abs(sum - current) < MAX_VMSTAT_ERROR) {
+	sum = anon + file + kernel + sock;
+	if (labs(sum - current) < MAX_VMSTAT_ERROR) {
 		ret = KSFT_PASS;
 	} else {
 		printf("memory.current = %ld\n", current);
-		printf("slab + anon + file + kernel_stack = %ld\n", sum);
-		printf("slab = %ld\n", slab);
+		printf("anon + file + kernel + sock = %ld\n", sum);
 		printf("anon = %ld\n", anon);
 		printf("file = %ld\n", file);
-		printf("kernel_stack = %ld\n", kernel_stack);
-		printf("pagetables = %ld\n", pagetables);
-		printf("percpu = %ld\n", percpu);
+		printf("kernel = %ld\n", kernel);
 		printf("sock = %ld\n", sock);
 	}
 
@@ -311,6 +308,7 @@ static int test_kmem_dead_cgroups(const char *root)
 	char *parent;
 	long dead;
 	int i;
+	int max_time = 20;
 
 	parent = cg_name(root, "kmem_dead_cgroups_test");
 	if (!parent)
@@ -325,7 +323,7 @@ static int test_kmem_dead_cgroups(const char *root)
 	if (cg_run_in_subcgroups(parent, alloc_dcache, (void *)100, 30))
 		goto cleanup;
 
-	for (i = 0; i < 5; i++) {
+	for (i = 0; i < max_time; i++) {
 		dead = cg_read_key_long(parent, "cgroup.stat",
 					"nr_dying_descendants ");
 		if (dead == 0) {
@@ -337,6 +335,8 @@ static int test_kmem_dead_cgroups(const char *root)
 		 * let's wait a bit and repeat.
 		 */
 		sleep(1);
+		if (i > 5)
+			printf("Waiting time longer than 5s; wait: %ds (dead: %ld)\n", i, dead);
 	}
 
 cleanup:
@@ -383,7 +383,7 @@ static int test_percpu_basic(const char *root)
 	current = cg_read_long(parent, "memory.current");
 	percpu = cg_read_key_long(parent, "memory.stat", "percpu ");
 
-	if (current > 0 && percpu > 0 && abs(current - percpu) <
+	if (current > 0 && percpu > 0 && labs(current - percpu) <
 	    MAX_VMSTAT_ERROR)
 		ret = KSFT_PASS;
 	else
@@ -421,9 +421,11 @@ struct kmem_test {
 int main(int argc, char **argv)
 {
 	char root[PATH_MAX];
-	int i, ret = EXIT_SUCCESS;
+	int i;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
 	/*
@@ -446,11 +448,10 @@ int main(int argc, char **argv)
 			ksft_test_result_skip("%s\n", tests[i].name);
 			break;
 		default:
-			ret = EXIT_FAILURE;
 			ksft_test_result_fail("%s\n", tests[i].name);
 			break;
 		}
 	}
 
-	return ret;
+	ksft_finished();
 }
diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
index 1e616a8c6a9c..4e1647568c5b 100644
--- a/tools/testing/selftests/cgroup/test_memcontrol.c
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -18,12 +18,90 @@
 #include <errno.h>
 #include <sys/mman.h>
 
-#include "../kselftest.h"
+#include "kselftest.h"
 #include "cgroup_util.h"
 
 static bool has_localevents;
 static bool has_recursiveprot;
 
+int get_temp_fd(void)
+{
+	return open(".", O_TMPFILE | O_RDWR | O_EXCL);
+}
+
+int alloc_pagecache(int fd, size_t size)
+{
+	char buf[PAGE_SIZE];
+	struct stat st;
+	int i;
+
+	if (fstat(fd, &st))
+		goto cleanup;
+
+	size += st.st_size;
+
+	if (ftruncate(fd, size))
+		goto cleanup;
+
+	for (i = 0; i < size; i += sizeof(buf))
+		read(fd, buf, sizeof(buf));
+
+	return 0;
+
+cleanup:
+	return -1;
+}
+
+int alloc_anon(const char *cgroup, void *arg)
+{
+	size_t size = (unsigned long)arg;
+	char *buf, *ptr;
+
+	buf = malloc(size);
+	for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
+		*ptr = 0;
+
+	free(buf);
+	return 0;
+}
+
+int is_swap_enabled(void)
+{
+	char buf[PAGE_SIZE];
+	const char delim[] = "\n";
+	int cnt = 0;
+	char *line;
+
+	if (read_text("/proc/swaps", buf, sizeof(buf)) <= 0)
+		return -1;
+
+	for (line = strtok(buf, delim); line; line = strtok(NULL, delim))
+		cnt++;
+
+	return cnt > 1;
+}
+
+int set_oom_adj_score(int pid, int score)
+{
+	char path[PATH_MAX];
+	int fd, len;
+
+	sprintf(path, "/proc/%d/oom_score_adj", pid);
+
+	fd = open(path, O_WRONLY | O_APPEND);
+	if (fd < 0)
+		return fd;
+
+	len = dprintf(fd, "%d", score);
+	if (len < 0) {
+		close(fd);
+		return len;
+	}
+
+	close(fd);
+	return 0;
+}
+
 /*
  * This test creates two nested cgroups with and without enabling
  * the memory controller.
@@ -98,6 +176,11 @@ static int alloc_anon_50M_check(const char *cgroup, void *arg)
 	int ret = -1;
 
 	buf = malloc(size);
+	if (buf == NULL) {
+		fprintf(stderr, "malloc() failed\n");
+		return -1;
+	}
+
 	for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
 		*ptr = 0;
 
@@ -156,13 +239,16 @@ cleanup:
 /*
  * This test create a memory cgroup, allocates
  * some anonymous memory and some pagecache
- * and check memory.current and some memory.stat values.
+ * and checks memory.current, memory.peak, and some memory.stat values.
  */
-static int test_memcg_current(const char *root)
+static int test_memcg_current_peak(const char *root)
 {
 	int ret = KSFT_FAIL;
-	long current;
+	long current, peak, peak_reset;
 	char *memcg;
+	bool fd2_closed = false, fd3_closed = false, fd4_closed = false;
+	int peak_fd = -1, peak_fd2 = -1, peak_fd3 = -1, peak_fd4 = -1;
+	struct stat ss;
 
 	memcg = cg_name(root, "memcg_test");
 	if (!memcg)
@@ -175,15 +261,124 @@ static int test_memcg_current(const char *root)
 	if (current != 0)
 		goto cleanup;
 
+	peak = cg_read_long(memcg, "memory.peak");
+	if (peak != 0)
+		goto cleanup;
+
 	if (cg_run(memcg, alloc_anon_50M_check, NULL))
 		goto cleanup;
 
+	peak = cg_read_long(memcg, "memory.peak");
+	if (peak < MB(50))
+		goto cleanup;
+
+	/*
+	 * We'll open a few FDs for the same memory.peak file to exercise the free-path
+	 * We need at least three to be closed in a different order than writes occurred to test
+	 * the linked-list handling.
+	 */
+	peak_fd = cg_open(memcg, "memory.peak", O_RDWR | O_APPEND | O_CLOEXEC);
+
+	if (peak_fd == -1) {
+		if (errno == ENOENT)
+			ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	/*
+	 * Before we try to use memory.peak's fd, try to figure out whether
+	 * this kernel supports writing to that file in the first place. (by
+	 * checking the writable bit on the file's st_mode)
+	 */
+	if (fstat(peak_fd, &ss))
+		goto cleanup;
+
+	if ((ss.st_mode & S_IWUSR) == 0) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	peak_fd2 = cg_open(memcg, "memory.peak", O_RDWR | O_APPEND | O_CLOEXEC);
+
+	if (peak_fd2 == -1)
+		goto cleanup;
+
+	peak_fd3 = cg_open(memcg, "memory.peak", O_RDWR | O_APPEND | O_CLOEXEC);
+
+	if (peak_fd3 == -1)
+		goto cleanup;
+
+	/* any non-empty string resets, but make it clear */
+	static const char reset_string[] = "reset\n";
+
+	peak_reset = write(peak_fd, reset_string, sizeof(reset_string));
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	peak_reset = write(peak_fd2, reset_string, sizeof(reset_string));
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	peak_reset = write(peak_fd3, reset_string, sizeof(reset_string));
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	/* Make sure a completely independent read isn't affected by our  FD-local reset above*/
+	peak = cg_read_long(memcg, "memory.peak");
+	if (peak < MB(50))
+		goto cleanup;
+
+	fd2_closed = true;
+	if (close(peak_fd2))
+		goto cleanup;
+
+	peak_fd4 = cg_open(memcg, "memory.peak", O_RDWR | O_APPEND | O_CLOEXEC);
+
+	if (peak_fd4 == -1)
+		goto cleanup;
+
+	peak_reset = write(peak_fd4, reset_string, sizeof(reset_string));
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	peak = cg_read_long_fd(peak_fd);
+	if (peak > MB(30) || peak < 0)
+		goto cleanup;
+
 	if (cg_run(memcg, alloc_pagecache_50M_check, NULL))
 		goto cleanup;
 
+	peak = cg_read_long(memcg, "memory.peak");
+	if (peak < MB(50))
+		goto cleanup;
+
+	/* Make sure everything is back to normal */
+	peak = cg_read_long_fd(peak_fd);
+	if (peak < MB(50))
+		goto cleanup;
+
+	peak = cg_read_long_fd(peak_fd4);
+	if (peak < MB(50))
+		goto cleanup;
+
+	fd3_closed = true;
+	if (close(peak_fd3))
+		goto cleanup;
+
+	fd4_closed = true;
+	if (close(peak_fd4))
+		goto cleanup;
+
 	ret = KSFT_PASS;
 
 cleanup:
+	close(peak_fd);
+	if (!fd2_closed)
+		close(peak_fd2);
+	if (!fd3_closed)
+		close(peak_fd3);
+	if (!fd4_closed)
+		close(peak_fd4);
 	cg_destroy(memcg);
 	free(memcg);
 
@@ -211,6 +406,11 @@ static int alloc_anon_noexit(const char *cgroup, void *arg)
 	char *buf, *ptr;
 
 	buf = malloc(size);
+	if (buf == NULL) {
+		fprintf(stderr, "malloc() failed\n");
+		return -1;
+	}
+
 	for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
 		*ptr = 0;
 
@@ -258,10 +458,11 @@ static bool reclaim_until(const char *memcg, long goal);
  *
  * Then it checks actual memory usages and expects that:
  * A/B    memory.current ~= 50M
- * A/B/C  memory.current ~= 29M
- * A/B/D  memory.current ~= 21M
- * A/B/E  memory.current ~= 0
- * A/B/F  memory.current  = 0
+ * A/B/C  memory.current ~= 29M [memory.events:low > 0]
+ * A/B/D  memory.current ~= 21M [memory.events:low > 0]
+ * A/B/E  memory.current ~= 0   [memory.events:low == 0 if !memory_recursiveprot,
+ *				 undefined otherwise]
+ * A/B/F  memory.current  = 0   [memory.events:low == 0]
  * (for origin of the numbers, see model in memcg_protection.m.)
  *
  * After that it tries to allocate more than there is
@@ -282,6 +483,7 @@ static int test_memcg_protection(const char *root, bool min)
 	char *children[4] = {NULL};
 	const char *attribute = min ? "memory.min" : "memory.low";
 	long c[4];
+	long current;
 	int i, attempts;
 	int fd;
 
@@ -372,10 +574,10 @@ static int test_memcg_protection(const char *root, bool min)
 	for (i = 0; i < ARRAY_SIZE(children); i++)
 		c[i] = cg_read_long(children[i], "memory.current");
 
-	if (!values_close(c[0], MB(29), 10))
+	if (!values_close(c[0], MB(29), 15))
 		goto cleanup;
 
-	if (!values_close(c[1], MB(21), 10))
+	if (!values_close(c[1], MB(21), 20))
 		goto cleanup;
 
 	if (c[3] != 0)
@@ -390,7 +592,8 @@ static int test_memcg_protection(const char *root, bool min)
 		goto cleanup;
 	}
 
-	if (!values_close(cg_read_long(parent[1], "memory.current"), MB(50), 3))
+	current = min ? MB(50) : MB(30);
+	if (!values_close(cg_read_long(parent[1], "memory.current"), current, 3))
 		goto cleanup;
 
 	if (!reclaim_until(children[0], MB(10)))
@@ -401,7 +604,14 @@ static int test_memcg_protection(const char *root, bool min)
 		goto cleanup;
 	}
 
+	/*
+	 * Child 2 has memory.low=0, but some low protection may still be
+	 * distributed down from its parent with memory.low=50M if cgroup2
+	 * memory_recursiveprot mount option is enabled. Ignore the low
+	 * event count in this case.
+	 */
 	for (i = 0; i < ARRAY_SIZE(children); i++) {
+		int ignore_low_events_index = has_recursiveprot ? 2 : -1;
 		int no_low_events_index = 1;
 		long low, oom;
 
@@ -410,6 +620,8 @@ static int test_memcg_protection(const char *root, bool min)
 
 		if (oom)
 			goto cleanup;
+		if (i == ignore_low_events_index)
+			continue;
 		if (i <= no_low_events_index && low <= 0)
 			goto cleanup;
 		if (i > no_low_events_index && low)
@@ -704,7 +916,9 @@ static bool reclaim_until(const char *memcg, long goal)
  */
 static int test_memcg_reclaim(const char *root)
 {
-	int ret = KSFT_FAIL, fd, retries;
+	int ret = KSFT_FAIL;
+	int fd = -1;
+	int retries;
 	char *memcg;
 	long current, expected_usage;
 
@@ -778,6 +992,11 @@ static int alloc_anon_50M_check_swap(const char *cgroup, void *arg)
 	int ret = -1;
 
 	buf = malloc(size);
+	if (buf == NULL) {
+		fprintf(stderr, "malloc() failed\n");
+		return -1;
+	}
+
 	for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
 		*ptr = 0;
 
@@ -798,13 +1017,19 @@ cleanup:
 
 /*
  * This test checks that memory.swap.max limits the amount of
- * anonymous memory which can be swapped out.
+ * anonymous memory which can be swapped out. Additionally, it verifies that
+ * memory.swap.peak reflects the high watermark and can be reset.
  */
-static int test_memcg_swap_max(const char *root)
+static int test_memcg_swap_max_peak(const char *root)
 {
 	int ret = KSFT_FAIL;
 	char *memcg;
-	long max;
+	long max, peak;
+	struct stat ss;
+	int swap_peak_fd = -1, mem_peak_fd = -1;
+
+	/* any non-empty string resets */
+	static const char reset_string[] = "foobarbaz";
 
 	if (!is_swap_enabled())
 		return KSFT_SKIP;
@@ -821,6 +1046,61 @@ static int test_memcg_swap_max(const char *root)
 		goto cleanup;
 	}
 
+	swap_peak_fd = cg_open(memcg, "memory.swap.peak",
+			       O_RDWR | O_APPEND | O_CLOEXEC);
+
+	if (swap_peak_fd == -1) {
+		if (errno == ENOENT)
+			ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	/*
+	 * Before we try to use memory.swap.peak's fd, try to figure out
+	 * whether this kernel supports writing to that file in the first
+	 * place. (by checking the writable bit on the file's st_mode)
+	 */
+	if (fstat(swap_peak_fd, &ss))
+		goto cleanup;
+
+	if ((ss.st_mode & S_IWUSR) == 0) {
+		ret = KSFT_SKIP;
+		goto cleanup;
+	}
+
+	mem_peak_fd = cg_open(memcg, "memory.peak", O_RDWR | O_APPEND | O_CLOEXEC);
+
+	if (mem_peak_fd == -1)
+		goto cleanup;
+
+	if (cg_read_long(memcg, "memory.swap.peak"))
+		goto cleanup;
+
+	if (cg_read_long_fd(swap_peak_fd))
+		goto cleanup;
+
+	/* switch the swap and mem fds into local-peak tracking mode*/
+	int peak_reset = write(swap_peak_fd, reset_string, sizeof(reset_string));
+
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	if (cg_read_long_fd(swap_peak_fd))
+		goto cleanup;
+
+	if (cg_read_long(memcg, "memory.peak"))
+		goto cleanup;
+
+	if (cg_read_long_fd(mem_peak_fd))
+		goto cleanup;
+
+	peak_reset = write(mem_peak_fd, reset_string, sizeof(reset_string));
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	if (cg_read_long_fd(mem_peak_fd))
+		goto cleanup;
+
 	if (cg_read_strcmp(memcg, "memory.max", "max\n"))
 		goto cleanup;
 
@@ -843,6 +1123,61 @@ static int test_memcg_swap_max(const char *root)
 	if (cg_read_key_long(memcg, "memory.events", "oom_kill ") != 1)
 		goto cleanup;
 
+	peak = cg_read_long(memcg, "memory.peak");
+	if (peak < MB(29))
+		goto cleanup;
+
+	peak = cg_read_long(memcg, "memory.swap.peak");
+	if (peak < MB(29))
+		goto cleanup;
+
+	peak = cg_read_long_fd(mem_peak_fd);
+	if (peak < MB(29))
+		goto cleanup;
+
+	peak = cg_read_long_fd(swap_peak_fd);
+	if (peak < MB(29))
+		goto cleanup;
+
+	/*
+	 * open, reset and close the peak swap on another FD to make sure
+	 * multiple extant fds don't corrupt the linked-list
+	 */
+	peak_reset = cg_write(memcg, "memory.swap.peak", (char *)reset_string);
+	if (peak_reset)
+		goto cleanup;
+
+	peak_reset = cg_write(memcg, "memory.peak", (char *)reset_string);
+	if (peak_reset)
+		goto cleanup;
+
+	/* actually reset on the fds */
+	peak_reset = write(swap_peak_fd, reset_string, sizeof(reset_string));
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	peak_reset = write(mem_peak_fd, reset_string, sizeof(reset_string));
+	if (peak_reset != sizeof(reset_string))
+		goto cleanup;
+
+	peak = cg_read_long_fd(swap_peak_fd);
+	if (peak > MB(10))
+		goto cleanup;
+
+	/*
+	 * The cgroup is now empty, but there may be a page or two associated
+	 * with the open FD accounted to it.
+	 */
+	peak = cg_read_long_fd(mem_peak_fd);
+	if (peak > MB(1))
+		goto cleanup;
+
+	if (cg_read_long(memcg, "memory.peak") < MB(29))
+		goto cleanup;
+
+	if (cg_read_long(memcg, "memory.swap.peak") < MB(29))
+		goto cleanup;
+
 	if (cg_run(memcg, alloc_anon_50M_check_swap, (void *)MB(30)))
 		goto cleanup;
 
@@ -850,9 +1185,29 @@ static int test_memcg_swap_max(const char *root)
 	if (max <= 0)
 		goto cleanup;
 
+	peak = cg_read_long(memcg, "memory.peak");
+	if (peak < MB(29))
+		goto cleanup;
+
+	peak = cg_read_long(memcg, "memory.swap.peak");
+	if (peak < MB(29))
+		goto cleanup;
+
+	peak = cg_read_long_fd(mem_peak_fd);
+	if (peak < MB(29))
+		goto cleanup;
+
+	peak = cg_read_long_fd(swap_peak_fd);
+	if (peak < MB(19))
+		goto cleanup;
+
 	ret = KSFT_PASS;
 
 cleanup:
+	if (mem_peak_fd != -1 && close(mem_peak_fd))
+		ret = KSFT_FAIL;
+	if (swap_peak_fd != -1 && close(swap_peak_fd))
+		ret = KSFT_FAIL;
 	cg_destroy(memcg);
 	free(memcg);
 
@@ -972,7 +1327,9 @@ static int tcp_client(const char *cgroup, unsigned short port)
 	char servport[6];
 	int retries = 0x10; /* nice round number */
 	int sk, ret;
+	long allocated;
 
+	allocated = cg_read_long(cgroup, "memory.current");
 	snprintf(servport, sizeof(servport), "%hd", port);
 	ret = getaddrinfo(server, servport, NULL, &ai);
 	if (ret)
@@ -1000,7 +1357,8 @@ static int tcp_client(const char *cgroup, unsigned short port)
 		if (current < 0 || sock < 0)
 			goto close_sk;
 
-		if (values_close(current, sock, 10)) {
+		/* exclude the memory not related to socket connection */
+		if (values_close(current - allocated, sock, 10)) {
 			ret = KSFT_PASS;
 			break;
 		}
@@ -1273,7 +1631,7 @@ struct memcg_test {
 	const char *name;
 } tests[] = {
 	T(test_memcg_subtree_control),
-	T(test_memcg_current),
+	T(test_memcg_current_peak),
 	T(test_memcg_min),
 	T(test_memcg_low),
 	T(test_memcg_high),
@@ -1281,7 +1639,7 @@ struct memcg_test {
 	T(test_memcg_max),
 	T(test_memcg_reclaim),
 	T(test_memcg_oom_events),
-	T(test_memcg_swap_max),
+	T(test_memcg_swap_max_peak),
 	T(test_memcg_sock),
 	T(test_memcg_oom_group_leaf_events),
 	T(test_memcg_oom_group_parent_events),
@@ -1292,9 +1650,11 @@ struct memcg_test {
 int main(int argc, char **argv)
 {
 	char root[PATH_MAX];
-	int i, proc_status, ret = EXIT_SUCCESS;
+	int i, proc_status;
 
-	if (cg_find_unified_root(root, sizeof(root)))
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
+	if (cg_find_unified_root(root, sizeof(root), NULL))
 		ksft_exit_skip("cgroup v2 isn't mounted\n");
 
 	/*
@@ -1327,11 +1687,10 @@ int main(int argc, char **argv)
 			ksft_test_result_skip("%s\n", tests[i].name);
 			break;
 		default:
-			ret = EXIT_FAILURE;
 			ksft_test_result_fail("%s\n", tests[i].name);
 			break;
 		}
 	}
 
-	return ret;
+	ksft_finished();
 }
diff --git a/tools/testing/selftests/cgroup/test_pids.c b/tools/testing/selftests/cgroup/test_pids.c
new file mode 100644
index 000000000000..9a387c815d2c
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_pids.c
@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <linux/limits.h>
+#include <signal.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#include "kselftest.h"
+#include "cgroup_util.h"
+
+static int run_success(const char *cgroup, void *arg)
+{
+	return 0;
+}
+
+static int run_pause(const char *cgroup, void *arg)
+{
+	return pause();
+}
+
+/*
+ * This test checks that pids.max prevents forking new children above the
+ * specified limit in the cgroup.
+ */
+static int test_pids_max(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cg_pids;
+	int pid;
+
+	cg_pids = cg_name(root, "pids_test");
+	if (!cg_pids)
+		goto cleanup;
+
+	if (cg_create(cg_pids))
+		goto cleanup;
+
+	if (cg_read_strcmp(cg_pids, "pids.max", "max\n"))
+		goto cleanup;
+
+	if (cg_write(cg_pids, "pids.max", "2"))
+		goto cleanup;
+
+	if (cg_enter_current(cg_pids))
+		goto cleanup;
+
+	pid = cg_run_nowait(cg_pids, run_pause, NULL);
+	if (pid < 0)
+		goto cleanup;
+
+	if (cg_run_nowait(cg_pids, run_success, NULL) != -1 || errno != EAGAIN)
+		goto cleanup;
+
+	if (kill(pid, SIGINT))
+		goto cleanup;
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_enter_current(root);
+	cg_destroy(cg_pids);
+	free(cg_pids);
+
+	return ret;
+}
+
+/*
+ * This test checks that pids.events are counted in cgroup associated with pids.max
+ */
+static int test_pids_events(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *cg_parent = NULL, *cg_child = NULL;
+	int pid;
+
+	if (cgroup_feature("pids_localevents") <= 0)
+		return KSFT_SKIP;
+
+	cg_parent = cg_name(root, "pids_parent");
+	cg_child = cg_name(cg_parent, "pids_child");
+	if (!cg_parent || !cg_child)
+		goto cleanup;
+
+	if (cg_create(cg_parent))
+		goto cleanup;
+	if (cg_write(cg_parent, "cgroup.subtree_control", "+pids"))
+		goto cleanup;
+	if (cg_create(cg_child))
+		goto cleanup;
+
+	if (cg_write(cg_parent, "pids.max", "2"))
+		goto cleanup;
+
+	if (cg_read_strcmp(cg_child, "pids.max", "max\n"))
+		goto cleanup;
+
+	if (cg_enter_current(cg_child))
+		goto cleanup;
+
+	pid = cg_run_nowait(cg_child, run_pause, NULL);
+	if (pid < 0)
+		goto cleanup;
+
+	if (cg_run_nowait(cg_child, run_success, NULL) != -1 || errno != EAGAIN)
+		goto cleanup;
+
+	if (kill(pid, SIGINT))
+		goto cleanup;
+
+	if (cg_read_key_long(cg_child, "pids.events", "max ") != 0)
+		goto cleanup;
+	if (cg_read_key_long(cg_parent, "pids.events", "max ") != 1)
+		goto cleanup;
+
+
+	ret = KSFT_PASS;
+
+cleanup:
+	cg_enter_current(root);
+	if (cg_child)
+		cg_destroy(cg_child);
+	if (cg_parent)
+		cg_destroy(cg_parent);
+	free(cg_child);
+	free(cg_parent);
+
+	return ret;
+}
+
+
+
+#define T(x) { x, #x }
+struct pids_test {
+	int (*fn)(const char *root);
+	const char *name;
+} tests[] = {
+	T(test_pids_max),
+	T(test_pids_events),
+};
+#undef T
+
+int main(int argc, char **argv)
+{
+	char root[PATH_MAX];
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
+	if (cg_find_unified_root(root, sizeof(root), NULL))
+		ksft_exit_skip("cgroup v2 isn't mounted\n");
+
+	/*
+	 * Check that pids controller is available:
+	 * pids is listed in cgroup.controllers
+	 */
+	if (cg_read_strstr(root, "cgroup.controllers", "pids"))
+		ksft_exit_skip("pids controller isn't available\n");
+
+	if (cg_read_strstr(root, "cgroup.subtree_control", "pids"))
+		if (cg_write(root, "cgroup.subtree_control", "+pids"))
+			ksft_exit_skip("Failed to set pids controller\n");
+
+	for (int i = 0; i < ARRAY_SIZE(tests); i++) {
+		switch (tests[i].fn(root)) {
+		case KSFT_PASS:
+			ksft_test_result_pass("%s\n", tests[i].name);
+			break;
+		case KSFT_SKIP:
+			ksft_test_result_skip("%s\n", tests[i].name);
+			break;
+		default:
+			ksft_test_result_fail("%s\n", tests[i].name);
+			break;
+		}
+	}
+
+	ksft_finished();
+}
diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c
new file mode 100644
index 000000000000..64ebc3f3f203
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_zswap.c
@@ -0,0 +1,636 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <linux/limits.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <signal.h>
+#include <sys/sysinfo.h>
+#include <string.h>
+#include <sys/wait.h>
+#include <sys/mman.h>
+
+#include "kselftest.h"
+#include "cgroup_util.h"
+
+static int read_int(const char *path, size_t *value)
+{
+	FILE *file;
+	int ret = 0;
+
+	file = fopen(path, "r");
+	if (!file)
+		return -1;
+	if (fscanf(file, "%ld", value) != 1)
+		ret = -1;
+	fclose(file);
+	return ret;
+}
+
+static int set_min_free_kb(size_t value)
+{
+	FILE *file;
+	int ret;
+
+	file = fopen("/proc/sys/vm/min_free_kbytes", "w");
+	if (!file)
+		return -1;
+	ret = fprintf(file, "%ld\n", value);
+	fclose(file);
+	return ret;
+}
+
+static int read_min_free_kb(size_t *value)
+{
+	return read_int("/proc/sys/vm/min_free_kbytes", value);
+}
+
+static int get_zswap_stored_pages(size_t *value)
+{
+	return read_int("/sys/kernel/debug/zswap/stored_pages", value);
+}
+
+static long get_cg_wb_count(const char *cg)
+{
+	return cg_read_key_long(cg, "memory.stat", "zswpwb");
+}
+
+static long get_zswpout(const char *cgroup)
+{
+	return cg_read_key_long(cgroup, "memory.stat", "zswpout ");
+}
+
+static int allocate_and_read_bytes(const char *cgroup, void *arg)
+{
+	size_t size = (size_t)arg;
+	char *mem = (char *)malloc(size);
+	int ret = 0;
+
+	if (!mem)
+		return -1;
+	for (int i = 0; i < size; i += 4095)
+		mem[i] = 'a';
+
+	/* Go through the allocated memory to (z)swap in and out pages */
+	for (int i = 0; i < size; i += 4095) {
+		if (mem[i] != 'a')
+			ret = -1;
+	}
+
+	free(mem);
+	return ret;
+}
+
+static int allocate_bytes(const char *cgroup, void *arg)
+{
+	size_t size = (size_t)arg;
+	char *mem = (char *)malloc(size);
+
+	if (!mem)
+		return -1;
+	for (int i = 0; i < size; i += 4095)
+		mem[i] = 'a';
+	free(mem);
+	return 0;
+}
+
+static char *setup_test_group_1M(const char *root, const char *name)
+{
+	char *group_name = cg_name(root, name);
+
+	if (!group_name)
+		return NULL;
+	if (cg_create(group_name))
+		goto fail;
+	if (cg_write(group_name, "memory.max", "1M")) {
+		cg_destroy(group_name);
+		goto fail;
+	}
+	return group_name;
+fail:
+	free(group_name);
+	return NULL;
+}
+
+/*
+ * Sanity test to check that pages are written into zswap.
+ */
+static int test_zswap_usage(const char *root)
+{
+	long zswpout_before, zswpout_after;
+	int ret = KSFT_FAIL;
+	char *test_group;
+
+	test_group = cg_name(root, "no_shrink_test");
+	if (!test_group)
+		goto out;
+	if (cg_create(test_group))
+		goto out;
+	if (cg_write(test_group, "memory.max", "1M"))
+		goto out;
+
+	zswpout_before = get_zswpout(test_group);
+	if (zswpout_before < 0) {
+		ksft_print_msg("Failed to get zswpout\n");
+		goto out;
+	}
+
+	/* Allocate more than memory.max to push memory into zswap */
+	if (cg_run(test_group, allocate_bytes, (void *)MB(4)))
+		goto out;
+
+	/* Verify that pages come into zswap */
+	zswpout_after = get_zswpout(test_group);
+	if (zswpout_after <= zswpout_before) {
+		ksft_print_msg("zswpout does not increase after test program\n");
+		goto out;
+	}
+	ret = KSFT_PASS;
+
+out:
+	cg_destroy(test_group);
+	free(test_group);
+	return ret;
+}
+
+/*
+ * Check that when memory.zswap.max = 0, no pages can go to the zswap pool for
+ * the cgroup.
+ */
+static int test_swapin_nozswap(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *test_group;
+	long swap_peak, zswpout;
+
+	test_group = cg_name(root, "no_zswap_test");
+	if (!test_group)
+		goto out;
+	if (cg_create(test_group))
+		goto out;
+	if (cg_write(test_group, "memory.max", "8M"))
+		goto out;
+	if (cg_write(test_group, "memory.zswap.max", "0"))
+		goto out;
+
+	/* Allocate and read more than memory.max to trigger swapin */
+	if (cg_run(test_group, allocate_and_read_bytes, (void *)MB(32)))
+		goto out;
+
+	/* Verify that pages are swapped out, but no zswap happened */
+	swap_peak = cg_read_long(test_group, "memory.swap.peak");
+	if (swap_peak < 0) {
+		ksft_print_msg("failed to get cgroup's swap_peak\n");
+		goto out;
+	}
+
+	if (swap_peak < MB(24)) {
+		ksft_print_msg("at least 24MB of memory should be swapped out\n");
+		goto out;
+	}
+
+	zswpout = get_zswpout(test_group);
+	if (zswpout < 0) {
+		ksft_print_msg("failed to get zswpout\n");
+		goto out;
+	}
+
+	if (zswpout > 0) {
+		ksft_print_msg("zswapout > 0 when memory.zswap.max = 0\n");
+		goto out;
+	}
+
+	ret = KSFT_PASS;
+
+out:
+	cg_destroy(test_group);
+	free(test_group);
+	return ret;
+}
+
+/* Simple test to verify the (z)swapin code paths */
+static int test_zswapin(const char *root)
+{
+	int ret = KSFT_FAIL;
+	char *test_group;
+	long zswpin;
+
+	test_group = cg_name(root, "zswapin_test");
+	if (!test_group)
+		goto out;
+	if (cg_create(test_group))
+		goto out;
+	if (cg_write(test_group, "memory.max", "8M"))
+		goto out;
+	if (cg_write(test_group, "memory.zswap.max", "max"))
+		goto out;
+
+	/* Allocate and read more than memory.max to trigger (z)swap in */
+	if (cg_run(test_group, allocate_and_read_bytes, (void *)MB(32)))
+		goto out;
+
+	zswpin = cg_read_key_long(test_group, "memory.stat", "zswpin ");
+	if (zswpin < 0) {
+		ksft_print_msg("failed to get zswpin\n");
+		goto out;
+	}
+
+	if (zswpin < MB(24) / PAGE_SIZE) {
+		ksft_print_msg("at least 24MB should be brought back from zswap\n");
+		goto out;
+	}
+
+	ret = KSFT_PASS;
+
+out:
+	cg_destroy(test_group);
+	free(test_group);
+	return ret;
+}
+
+/*
+ * Attempt writeback with the following steps:
+ * 1. Allocate memory.
+ * 2. Reclaim memory equal to the amount that was allocated in step 1.
+      This will move it into zswap.
+ * 3. Save current zswap usage.
+ * 4. Move the memory allocated in step 1 back in from zswap.
+ * 5. Set zswap.max to half the amount that was recorded in step 3.
+ * 6. Attempt to reclaim memory equal to the amount that was allocated,
+      this will either trigger writeback if it's enabled, or reclamation
+      will fail if writeback is disabled as there isn't enough zswap space.
+ */
+static int attempt_writeback(const char *cgroup, void *arg)
+{
+	long pagesize = sysconf(_SC_PAGESIZE);
+	size_t memsize = MB(4);
+	char buf[pagesize];
+	long zswap_usage;
+	bool wb_enabled = *(bool *) arg;
+	int ret = -1;
+	char *mem;
+
+	mem = (char *)malloc(memsize);
+	if (!mem)
+		return ret;
+
+	/*
+	 * Fill half of each page with increasing data, and keep other
+	 * half empty, this will result in data that is still compressible
+	 * and ends up in zswap, with material zswap usage.
+	 */
+	for (int i = 0; i < pagesize; i++)
+		buf[i] = i < pagesize/2 ? (char) i : 0;
+
+	for (int i = 0; i < memsize; i += pagesize)
+		memcpy(&mem[i], buf, pagesize);
+
+	/* Try and reclaim allocated memory */
+	if (cg_write_numeric(cgroup, "memory.reclaim", memsize)) {
+		ksft_print_msg("Failed to reclaim all of the requested memory\n");
+		goto out;
+	}
+
+	zswap_usage = cg_read_long(cgroup, "memory.zswap.current");
+
+	/* zswpin */
+	for (int i = 0; i < memsize; i += pagesize) {
+		if (memcmp(&mem[i], buf, pagesize)) {
+			ksft_print_msg("invalid memory\n");
+			goto out;
+		}
+	}
+
+	if (cg_write_numeric(cgroup, "memory.zswap.max", zswap_usage/2))
+		goto out;
+
+	/*
+	 * If writeback is enabled, trying to reclaim memory now will trigger a
+	 * writeback as zswap.max is half of what was needed when reclaim ran the first time.
+	 * If writeback is disabled, memory reclaim will fail as zswap is limited and
+	 * it can't writeback to swap.
+	 */
+	ret = cg_write_numeric(cgroup, "memory.reclaim", memsize);
+	if (!wb_enabled)
+		ret = (ret == -EAGAIN) ? 0 : -1;
+
+out:
+	free(mem);
+	return ret;
+}
+
+static int test_zswap_writeback_one(const char *cgroup, bool wb)
+{
+	long zswpwb_before, zswpwb_after;
+
+	zswpwb_before = get_cg_wb_count(cgroup);
+	if (zswpwb_before != 0) {
+		ksft_print_msg("zswpwb_before = %ld instead of 0\n", zswpwb_before);
+		return -1;
+	}
+
+	if (cg_run(cgroup, attempt_writeback, (void *) &wb))
+		return -1;
+
+	/* Verify that zswap writeback occurred only if writeback was enabled */
+	zswpwb_after = get_cg_wb_count(cgroup);
+	if (zswpwb_after < 0)
+		return -1;
+
+	if (wb != !!zswpwb_after) {
+		ksft_print_msg("zswpwb_after is %ld while wb is %s\n",
+				zswpwb_after, wb ? "enabled" : "disabled");
+		return -1;
+	}
+
+	return 0;
+}
+
+/* Test to verify the zswap writeback path */
+static int test_zswap_writeback(const char *root, bool wb)
+{
+	int ret = KSFT_FAIL;
+	char *test_group, *test_group_child = NULL;
+
+	if (cg_read_strcmp(root, "memory.zswap.writeback", "1"))
+		return KSFT_SKIP;
+
+	test_group = cg_name(root, "zswap_writeback_test");
+	if (!test_group)
+		goto out;
+	if (cg_create(test_group))
+		goto out;
+	if (cg_write(test_group, "memory.zswap.writeback", wb ? "1" : "0"))
+		goto out;
+
+	if (test_zswap_writeback_one(test_group, wb))
+		goto out;
+
+	/* Reset memory.zswap.max to max (modified by attempt_writeback), and
+	 * set up child cgroup, whose memory.zswap.writeback is hardcoded to 1.
+	 * Thus, the parent's setting shall be what's in effect. */
+	if (cg_write(test_group, "memory.zswap.max", "max"))
+		goto out;
+	if (cg_write(test_group, "cgroup.subtree_control", "+memory"))
+		goto out;
+
+	test_group_child = cg_name(test_group, "zswap_writeback_test_child");
+	if (!test_group_child)
+		goto out;
+	if (cg_create(test_group_child))
+		goto out;
+	if (cg_write(test_group_child, "memory.zswap.writeback", "1"))
+		goto out;
+
+	if (test_zswap_writeback_one(test_group_child, wb))
+		goto out;
+
+	ret = KSFT_PASS;
+
+out:
+	if (test_group_child) {
+		cg_destroy(test_group_child);
+		free(test_group_child);
+	}
+	cg_destroy(test_group);
+	free(test_group);
+	return ret;
+}
+
+static int test_zswap_writeback_enabled(const char *root)
+{
+	return test_zswap_writeback(root, true);
+}
+
+static int test_zswap_writeback_disabled(const char *root)
+{
+	return test_zswap_writeback(root, false);
+}
+
+/*
+ * When trying to store a memcg page in zswap, if the memcg hits its memory
+ * limit in zswap, writeback should affect only the zswapped pages of that
+ * memcg.
+ */
+static int test_no_invasive_cgroup_shrink(const char *root)
+{
+	int ret = KSFT_FAIL;
+	size_t control_allocation_size = MB(10);
+	char *control_allocation = NULL, *wb_group = NULL, *control_group = NULL;
+
+	wb_group = setup_test_group_1M(root, "per_memcg_wb_test1");
+	if (!wb_group)
+		return KSFT_FAIL;
+	if (cg_write(wb_group, "memory.zswap.max", "10K"))
+		goto out;
+	control_group = setup_test_group_1M(root, "per_memcg_wb_test2");
+	if (!control_group)
+		goto out;
+
+	/* Push some test_group2 memory into zswap */
+	if (cg_enter_current(control_group))
+		goto out;
+	control_allocation = malloc(control_allocation_size);
+	for (int i = 0; i < control_allocation_size; i += 4095)
+		control_allocation[i] = 'a';
+	if (cg_read_key_long(control_group, "memory.stat", "zswapped") < 1)
+		goto out;
+
+	/* Allocate 10x memory.max to push wb_group memory into zswap and trigger wb */
+	if (cg_run(wb_group, allocate_bytes, (void *)MB(10)))
+		goto out;
+
+	/* Verify that only zswapped memory from gwb_group has been written back */
+	if (get_cg_wb_count(wb_group) > 0 && get_cg_wb_count(control_group) == 0)
+		ret = KSFT_PASS;
+out:
+	cg_enter_current(root);
+	if (control_group) {
+		cg_destroy(control_group);
+		free(control_group);
+	}
+	cg_destroy(wb_group);
+	free(wb_group);
+	if (control_allocation)
+		free(control_allocation);
+	return ret;
+}
+
+struct no_kmem_bypass_child_args {
+	size_t target_alloc_bytes;
+	size_t child_allocated;
+};
+
+static int no_kmem_bypass_child(const char *cgroup, void *arg)
+{
+	struct no_kmem_bypass_child_args *values = arg;
+	void *allocation;
+
+	allocation = malloc(values->target_alloc_bytes);
+	if (!allocation) {
+		values->child_allocated = true;
+		return -1;
+	}
+	for (long i = 0; i < values->target_alloc_bytes; i += 4095)
+		((char *)allocation)[i] = 'a';
+	values->child_allocated = true;
+	pause();
+	free(allocation);
+	return 0;
+}
+
+/*
+ * When pages owned by a memcg are pushed to zswap by kswapd, they should be
+ * charged to that cgroup. This wasn't the case before commit
+ * cd08d80ecdac("mm: correctly charge compressed memory to its memcg").
+ *
+ * The test first allocates memory in a memcg, then raises min_free_kbytes to
+ * a very high value so that the allocation falls below low wm, then makes
+ * another allocation to trigger kswapd that should push the memcg-owned pages
+ * to zswap and verifies that the zswap pages are correctly charged.
+ *
+ * To be run on a VM with at most 4G of memory.
+ */
+static int test_no_kmem_bypass(const char *root)
+{
+	size_t min_free_kb_high, min_free_kb_low, min_free_kb_original;
+	struct no_kmem_bypass_child_args *values;
+	size_t trigger_allocation_size;
+	int wait_child_iteration = 0;
+	long stored_pages_threshold;
+	struct sysinfo sys_info;
+	int ret = KSFT_FAIL;
+	int child_status;
+	char *test_group = NULL;
+	pid_t child_pid;
+
+	/* Read sys info and compute test values accordingly */
+	if (sysinfo(&sys_info) != 0)
+		return KSFT_FAIL;
+	if (sys_info.totalram > 5000000000)
+		return KSFT_SKIP;
+	values = mmap(0, sizeof(struct no_kmem_bypass_child_args), PROT_READ |
+			PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+	if (values == MAP_FAILED)
+		return KSFT_FAIL;
+	if (read_min_free_kb(&min_free_kb_original))
+		return KSFT_FAIL;
+	min_free_kb_high = sys_info.totalram / 2000;
+	min_free_kb_low = sys_info.totalram / 500000;
+	values->target_alloc_bytes = (sys_info.totalram - min_free_kb_high * 1000) +
+		sys_info.totalram * 5 / 100;
+	stored_pages_threshold = sys_info.totalram / 5 / 4096;
+	trigger_allocation_size = sys_info.totalram / 20;
+
+	/* Set up test memcg */
+	test_group = cg_name(root, "kmem_bypass_test");
+	if (!test_group)
+		goto out;
+
+	/* Spawn memcg child and wait for it to allocate */
+	set_min_free_kb(min_free_kb_low);
+	if (cg_create(test_group))
+		goto out;
+	values->child_allocated = false;
+	child_pid = cg_run_nowait(test_group, no_kmem_bypass_child, values);
+	if (child_pid < 0)
+		goto out;
+	while (!values->child_allocated && wait_child_iteration++ < 10000)
+		usleep(1000);
+
+	/* Try to wakeup kswapd and let it push child memory to zswap */
+	set_min_free_kb(min_free_kb_high);
+	for (int i = 0; i < 20; i++) {
+		size_t stored_pages;
+		char *trigger_allocation = malloc(trigger_allocation_size);
+
+		if (!trigger_allocation)
+			break;
+		for (int i = 0; i < trigger_allocation_size; i += 4095)
+			trigger_allocation[i] = 'b';
+		usleep(100000);
+		free(trigger_allocation);
+		if (get_zswap_stored_pages(&stored_pages))
+			break;
+		if (stored_pages < 0)
+			break;
+		/* If memory was pushed to zswap, verify it belongs to memcg */
+		if (stored_pages > stored_pages_threshold) {
+			int zswapped = cg_read_key_long(test_group, "memory.stat", "zswapped ");
+			int delta = stored_pages * 4096 - zswapped;
+			int result_ok = delta < stored_pages * 4096 / 4;
+
+			ret = result_ok ? KSFT_PASS : KSFT_FAIL;
+			break;
+		}
+	}
+
+	kill(child_pid, SIGTERM);
+	waitpid(child_pid, &child_status, 0);
+out:
+	set_min_free_kb(min_free_kb_original);
+	cg_destroy(test_group);
+	free(test_group);
+	return ret;
+}
+
+#define T(x) { x, #x }
+struct zswap_test {
+	int (*fn)(const char *root);
+	const char *name;
+} tests[] = {
+	T(test_zswap_usage),
+	T(test_swapin_nozswap),
+	T(test_zswapin),
+	T(test_zswap_writeback_enabled),
+	T(test_zswap_writeback_disabled),
+	T(test_no_kmem_bypass),
+	T(test_no_invasive_cgroup_shrink),
+};
+#undef T
+
+static bool zswap_configured(void)
+{
+	return access("/sys/module/zswap", F_OK) == 0;
+}
+
+int main(int argc, char **argv)
+{
+	char root[PATH_MAX];
+	int i;
+
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
+	if (cg_find_unified_root(root, sizeof(root), NULL))
+		ksft_exit_skip("cgroup v2 isn't mounted\n");
+
+	if (!zswap_configured())
+		ksft_exit_skip("zswap isn't configured\n");
+
+	/*
+	 * Check that memory controller is available:
+	 * memory is listed in cgroup.controllers
+	 */
+	if (cg_read_strstr(root, "cgroup.controllers", "memory"))
+		ksft_exit_skip("memory controller isn't available\n");
+
+	if (cg_read_strstr(root, "cgroup.subtree_control", "memory"))
+		if (cg_write(root, "cgroup.subtree_control", "+memory"))
+			ksft_exit_skip("Failed to set memory controller\n");
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		switch (tests[i].fn(root)) {
+		case KSFT_PASS:
+			ksft_test_result_pass("%s\n", tests[i].name);
+			break;
+		case KSFT_SKIP:
+			ksft_test_result_skip("%s\n", tests[i].name);
+			break;
+		default:
+			ksft_test_result_fail("%s\n", tests[i].name);
+			break;
+		}
+	}
+
+	ksft_finished();
+}
diff --git a/tools/testing/selftests/clone3/Makefile b/tools/testing/selftests/clone3/Makefile
index 79b19a2863a0..84832c369a2e 100644
--- a/tools/testing/selftests/clone3/Makefile
+++ b/tools/testing/selftests/clone3/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-CFLAGS += -g -std=gnu99 -I../../../../usr/include/
+CFLAGS += -g -std=gnu99 $(KHDR_INCLUDES)
 LDLIBS += -lcap
 
 TEST_GEN_PROGS := clone3 clone3_clear_sighand clone3_set_tid \
diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c
index cd4582129c7d..289e0c7c1f09 100644
--- a/tools/testing/selftests/clone3/clone3.c
+++ b/tools/testing/selftests/clone3/clone3.c
@@ -7,6 +7,7 @@
 #include <inttypes.h>
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <stdbool.h>
 #include <stdint.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -17,7 +18,7 @@
 #include <unistd.h>
 #include <sched.h>
 
-#include "../kselftest.h"
+#include "kselftest.h"
 #include "clone3_selftests.h"
 
 enum test_mode {
@@ -94,17 +95,22 @@ static int call_clone3(uint64_t flags, size_t size, enum test_mode test_mode)
 			getpid(), pid);
 
 	if (waitpid(-1, &status, __WALL) < 0) {
-		ksft_print_msg("Child returned %s\n", strerror(errno));
+		ksft_print_msg("waitpid() returned %s\n", strerror(errno));
 		return -errno;
 	}
+	if (!WIFEXITED(status)) {
+		ksft_print_msg("Child did not exit normally, status 0x%x\n",
+			       status);
+		return EXIT_FAILURE;
+	}
 	if (WEXITSTATUS(status))
 		return WEXITSTATUS(status);
 
 	return 0;
 }
 
-static void test_clone3(uint64_t flags, size_t size, int expected,
-		       enum test_mode test_mode)
+static bool test_clone3(uint64_t flags, size_t size, int expected,
+			enum test_mode test_mode)
 {
 	int ret;
 
@@ -114,86 +120,223 @@ static void test_clone3(uint64_t flags, size_t size, int expected,
 	ret = call_clone3(flags, size, test_mode);
 	ksft_print_msg("[%d] clone3() with flags says: %d expected %d\n",
 			getpid(), ret, expected);
-	if (ret != expected)
-		ksft_test_result_fail(
+	if (ret != expected) {
+		ksft_print_msg(
 			"[%d] Result (%d) is different than expected (%d)\n",
 			getpid(), ret, expected);
-	else
-		ksft_test_result_pass(
-			"[%d] Result (%d) matches expectation (%d)\n",
-			getpid(), ret, expected);
-}
-
-int main(int argc, char *argv[])
-{
-	uid_t uid = getuid();
-
-	ksft_print_header();
-	ksft_set_plan(17);
-	test_clone3_supported();
-
-	/* Just a simple clone3() should return 0.*/
-	test_clone3(0, 0, 0, CLONE3_ARGS_NO_TEST);
+		return false;
+	}
 
-	/* Do a clone3() in a new PID NS.*/
-	if (uid == 0)
-		test_clone3(CLONE_NEWPID, 0, 0, CLONE3_ARGS_NO_TEST);
-	else
-		ksft_test_result_skip("Skipping clone3() with CLONE_NEWPID\n");
+	return true;
+}
 
-	/* Do a clone3() with CLONE_ARGS_SIZE_VER0. */
-	test_clone3(0, CLONE_ARGS_SIZE_VER0, 0, CLONE3_ARGS_NO_TEST);
+typedef bool (*filter_function)(void);
+typedef size_t (*size_function)(void);
 
-	/* Do a clone3() with CLONE_ARGS_SIZE_VER0 - 8 */
-	test_clone3(0, CLONE_ARGS_SIZE_VER0 - 8, -EINVAL, CLONE3_ARGS_NO_TEST);
+static bool not_root(void)
+{
+	if (getuid() != 0) {
+		ksft_print_msg("Not running as root\n");
+		return true;
+	}
 
-	/* Do a clone3() with sizeof(struct clone_args) + 8 */
-	test_clone3(0, sizeof(struct __clone_args) + 8, 0, CLONE3_ARGS_NO_TEST);
+	return false;
+}
 
-	/* Do a clone3() with exit_signal having highest 32 bits non-zero */
-	test_clone3(0, 0, -EINVAL, CLONE3_ARGS_INVAL_EXIT_SIGNAL_BIG);
+static bool no_timenamespace(void)
+{
+	if (not_root())
+		return true;
 
-	/* Do a clone3() with negative 32-bit exit_signal */
-	test_clone3(0, 0, -EINVAL, CLONE3_ARGS_INVAL_EXIT_SIGNAL_NEG);
+	if (!access("/proc/self/ns/time", F_OK))
+		return false;
 
-	/* Do a clone3() with exit_signal not fitting into CSIGNAL mask */
-	test_clone3(0, 0, -EINVAL, CLONE3_ARGS_INVAL_EXIT_SIGNAL_CSIG);
+	ksft_print_msg("Time namespaces are not supported\n");
+	return true;
+}
 
-	/* Do a clone3() with NSIG < exit_signal < CSIG */
-	test_clone3(0, 0, -EINVAL, CLONE3_ARGS_INVAL_EXIT_SIGNAL_NSIG);
+static size_t page_size_plus_8(void)
+{
+	return getpagesize() + 8;
+}
 
-	test_clone3(0, sizeof(struct __clone_args) + 8, 0, CLONE3_ARGS_ALL_0);
+struct test {
+	const char *name;
+	uint64_t flags;
+	size_t size;
+	size_function size_function;
+	int expected;
+	enum test_mode test_mode;
+	filter_function filter;
+};
 
-	test_clone3(0, sizeof(struct __clone_args) + 16, -E2BIG,
-			CLONE3_ARGS_ALL_0);
+static const struct test tests[] = {
+	{
+		.name = "simple clone3()",
+		.flags = 0,
+		.size = 0,
+		.expected = 0,
+		.test_mode = CLONE3_ARGS_NO_TEST,
+	},
+	{
+		.name = "clone3() in a new PID_NS",
+		.flags = CLONE_NEWPID,
+		.size = 0,
+		.expected = 0,
+		.test_mode = CLONE3_ARGS_NO_TEST,
+		.filter = not_root,
+	},
+	{
+		.name = "CLONE_ARGS_SIZE_VER0",
+		.flags = 0,
+		.size = CLONE_ARGS_SIZE_VER0,
+		.expected = 0,
+		.test_mode = CLONE3_ARGS_NO_TEST,
+	},
+	{
+		.name = "CLONE_ARGS_SIZE_VER0 - 8",
+		.flags = 0,
+		.size = CLONE_ARGS_SIZE_VER0 - 8,
+		.expected = -EINVAL,
+		.test_mode = CLONE3_ARGS_NO_TEST,
+	},
+	{
+		.name = "sizeof(struct clone_args) + 8",
+		.flags = 0,
+		.size = sizeof(struct __clone_args) + 8,
+		.expected = 0,
+		.test_mode = CLONE3_ARGS_NO_TEST,
+	},
+	{
+		.name = "exit_signal with highest 32 bits non-zero",
+		.flags = 0,
+		.size = 0,
+		.expected = -EINVAL,
+		.test_mode = CLONE3_ARGS_INVAL_EXIT_SIGNAL_BIG,
+	},
+	{
+		.name = "negative 32-bit exit_signal",
+		.flags = 0,
+		.size = 0,
+		.expected = -EINVAL,
+		.test_mode = CLONE3_ARGS_INVAL_EXIT_SIGNAL_NEG,
+	},
+	{
+		.name = "exit_signal not fitting into CSIGNAL mask",
+		.flags = 0,
+		.size = 0,
+		.expected = -EINVAL,
+		.test_mode = CLONE3_ARGS_INVAL_EXIT_SIGNAL_CSIG,
+	},
+	{
+		.name = "NSIG < exit_signal < CSIG",
+		.flags = 0,
+		.size = 0,
+		.expected = -EINVAL,
+		.test_mode = CLONE3_ARGS_INVAL_EXIT_SIGNAL_NSIG,
+	},
+	{
+		.name = "Arguments sizeof(struct clone_args) + 8",
+		.flags = 0,
+		.size = sizeof(struct __clone_args) + 8,
+		.expected = 0,
+		.test_mode = CLONE3_ARGS_ALL_0,
+	},
+	{
+		.name = "Arguments sizeof(struct clone_args) + 16",
+		.flags = 0,
+		.size = sizeof(struct __clone_args) + 16,
+		.expected = -E2BIG,
+		.test_mode = CLONE3_ARGS_ALL_0,
+	},
+	{
+		.name = "Arguments sizeof(struct clone_arg) * 2",
+		.flags = 0,
+		.size = sizeof(struct __clone_args) + 16,
+		.expected = -E2BIG,
+		.test_mode = CLONE3_ARGS_ALL_0,
+	},
+	{
+		.name = "Arguments > page size",
+		.flags = 0,
+		.size_function = page_size_plus_8,
+		.expected = -E2BIG,
+		.test_mode = CLONE3_ARGS_NO_TEST,
+	},
+	{
+		.name = "CLONE_ARGS_SIZE_VER0 in a new PID NS",
+		.flags = CLONE_NEWPID,
+		.size = CLONE_ARGS_SIZE_VER0,
+		.expected = 0,
+		.test_mode = CLONE3_ARGS_NO_TEST,
+		.filter = not_root,
+	},
+	{
+		.name = "CLONE_ARGS_SIZE_VER0 - 8 in a new PID NS",
+		.flags = CLONE_NEWPID,
+		.size = CLONE_ARGS_SIZE_VER0 - 8,
+		.expected = -EINVAL,
+		.test_mode = CLONE3_ARGS_NO_TEST,
+	},
+	{
+		.name = "sizeof(struct clone_args) + 8 in a new PID NS",
+		.flags = CLONE_NEWPID,
+		.size = sizeof(struct __clone_args) + 8,
+		.expected = 0,
+		.test_mode = CLONE3_ARGS_NO_TEST,
+		.filter = not_root,
+	},
+	{
+		.name = "Arguments > page size in a new PID NS",
+		.flags = CLONE_NEWPID,
+		.size_function = page_size_plus_8,
+		.expected = -E2BIG,
+		.test_mode = CLONE3_ARGS_NO_TEST,
+	},
+	{
+		.name = "New time NS",
+		.flags = CLONE_NEWTIME,
+		.size = 0,
+		.expected = 0,
+		.test_mode = CLONE3_ARGS_NO_TEST,
+		.filter = no_timenamespace,
+	},
+	{
+		.name = "exit signal (SIGCHLD) in flags",
+		.flags = SIGCHLD,
+		.size = 0,
+		.expected = -EINVAL,
+		.test_mode = CLONE3_ARGS_NO_TEST,
+	},
+};
 
-	test_clone3(0, sizeof(struct __clone_args) * 2, -E2BIG,
-			CLONE3_ARGS_ALL_0);
+int main(int argc, char *argv[])
+{
+	size_t size;
+	int i;
 
-	/* Do a clone3() with > page size */
-	test_clone3(0, getpagesize() + 8, -E2BIG, CLONE3_ARGS_NO_TEST);
+	ksft_print_header();
+	ksft_set_plan(ARRAY_SIZE(tests));
+	test_clone3_supported();
 
-	/* Do a clone3() with CLONE_ARGS_SIZE_VER0 in a new PID NS. */
-	if (uid == 0)
-		test_clone3(CLONE_NEWPID, CLONE_ARGS_SIZE_VER0, 0,
-				CLONE3_ARGS_NO_TEST);
-	else
-		ksft_test_result_skip("Skipping clone3() with CLONE_NEWPID\n");
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		if (tests[i].filter && tests[i].filter()) {
+			ksft_test_result_skip("%s\n", tests[i].name);
+			continue;
+		}
 
-	/* Do a clone3() with CLONE_ARGS_SIZE_VER0 - 8 in a new PID NS */
-	test_clone3(CLONE_NEWPID, CLONE_ARGS_SIZE_VER0 - 8, -EINVAL,
-			CLONE3_ARGS_NO_TEST);
+		if (tests[i].size_function)
+			size = tests[i].size_function();
+		else
+			size = tests[i].size;
 
-	/* Do a clone3() with sizeof(struct clone_args) + 8 in a new PID NS */
-	if (uid == 0)
-		test_clone3(CLONE_NEWPID, sizeof(struct __clone_args) + 8, 0,
-				CLONE3_ARGS_NO_TEST);
-	else
-		ksft_test_result_skip("Skipping clone3() with CLONE_NEWPID\n");
+		ksft_print_msg("Running test '%s'\n", tests[i].name);
 
-	/* Do a clone3() with > page size in a new PID NS */
-	test_clone3(CLONE_NEWPID, getpagesize() + 8, -E2BIG,
-			CLONE3_ARGS_NO_TEST);
+		ksft_test_result(test_clone3(tests[i].flags, size,
+					     tests[i].expected,
+					     tests[i].test_mode),
+				 "%s\n", tests[i].name);
+	}
 
-	return !ksft_get_fail_cnt() ? ksft_exit_pass() : ksft_exit_fail();
+	ksft_finished();
 }
diff --git a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c
index 52d3f0364bda..e82281efa273 100644
--- a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c
+++ b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c
@@ -24,13 +24,9 @@
 #include <unistd.h>
 #include <sched.h>
 
-#include "../kselftest_harness.h"
+#include "kselftest_harness.h"
 #include "clone3_selftests.h"
 
-#ifndef MAX_PID_NS_LEVEL
-#define MAX_PID_NS_LEVEL 32
-#endif
-
 static void child_exit(int ret)
 {
 	fflush(stdout);
diff --git a/tools/testing/selftests/clone3/clone3_clear_sighand.c b/tools/testing/selftests/clone3/clone3_clear_sighand.c
index 47a8c0fc3676..de0c9d62015d 100644
--- a/tools/testing/selftests/clone3/clone3_clear_sighand.c
+++ b/tools/testing/selftests/clone3/clone3_clear_sighand.c
@@ -13,13 +13,9 @@
 #include <sys/syscall.h>
 #include <sys/wait.h>
 
-#include "../kselftest.h"
+#include "kselftest.h"
 #include "clone3_selftests.h"
 
-#ifndef CLONE_CLEAR_SIGHAND
-#define CLONE_CLEAR_SIGHAND 0x100000000ULL
-#endif
-
 static void nop_handler(int signo)
 {
 }
@@ -124,5 +120,5 @@ int main(int argc, char **argv)
 
 	test_clone3_clear_sighand();
 
-	return ksft_exit_pass();
+	ksft_exit_pass();
 }
diff --git a/tools/testing/selftests/clone3/clone3_selftests.h b/tools/testing/selftests/clone3/clone3_selftests.h
index e81ffaaee02b..a0593e8950f0 100644
--- a/tools/testing/selftests/clone3/clone3_selftests.h
+++ b/tools/testing/selftests/clone3/clone3_selftests.h
@@ -11,16 +11,12 @@
 #include <syscall.h>
 #include <sys/wait.h>
 
-#include "../kselftest.h"
+#include "kselftest.h"
 
 #define ptr_to_u64(ptr) ((__u64)((uintptr_t)(ptr)))
 
-#ifndef CLONE_INTO_CGROUP
-#define CLONE_INTO_CGROUP 0x200000000ULL /* Clone into a specific cgroup given the right permissions. */
-#endif
-
 #ifndef __NR_clone3
-#define __NR_clone3 -1
+#define __NR_clone3 435
 #endif
 
 struct __clone_args {
@@ -32,18 +28,9 @@ struct __clone_args {
 	__aligned_u64 stack;
 	__aligned_u64 stack_size;
 	__aligned_u64 tls;
-#ifndef CLONE_ARGS_SIZE_VER0
-#define CLONE_ARGS_SIZE_VER0 64	/* sizeof first published struct */
-#endif
 	__aligned_u64 set_tid;
 	__aligned_u64 set_tid_size;
-#ifndef CLONE_ARGS_SIZE_VER1
-#define CLONE_ARGS_SIZE_VER1 80	/* sizeof second published struct */
-#endif
 	__aligned_u64 cgroup;
-#ifndef CLONE_ARGS_SIZE_VER2
-#define CLONE_ARGS_SIZE_VER2 88	/* sizeof third published struct */
-#endif
 };
 
 static pid_t sys_clone3(struct __clone_args *args, size_t size)
diff --git a/tools/testing/selftests/clone3/clone3_set_tid.c b/tools/testing/selftests/clone3/clone3_set_tid.c
index 0229e9ebb995..5c944aee6b41 100644
--- a/tools/testing/selftests/clone3/clone3_set_tid.c
+++ b/tools/testing/selftests/clone3/clone3_set_tid.c
@@ -20,12 +20,10 @@
 #include <unistd.h>
 #include <sched.h>
 
-#include "../kselftest.h"
+#include "kselftest.h"
 #include "clone3_selftests.h"
 
-#ifndef MAX_PID_NS_LEVEL
 #define MAX_PID_NS_LEVEL 32
-#endif
 
 static int pipe_1[2];
 static int pipe_2[2];
@@ -116,7 +114,8 @@ static int call_clone3_set_tid(pid_t *set_tid,
 	return WEXITSTATUS(status);
 }
 
-static void test_clone3_set_tid(pid_t *set_tid,
+static void test_clone3_set_tid(const char *desc,
+				pid_t *set_tid,
 				size_t set_tid_size,
 				int flags,
 				int expected,
@@ -131,17 +130,13 @@ static void test_clone3_set_tid(pid_t *set_tid,
 	ret = call_clone3_set_tid(set_tid, set_tid_size, flags, expected_pid,
 				  wait_for_it);
 	ksft_print_msg(
-		"[%d] clone3() with CLONE_SET_TID %d says :%d - expected %d\n",
+		"[%d] clone3() with CLONE_SET_TID %d says: %d - expected %d\n",
 		getpid(), set_tid[0], ret, expected);
-	if (ret != expected)
-		ksft_test_result_fail(
-			"[%d] Result (%d) is different than expected (%d)\n",
-			getpid(), ret, expected);
-	else
-		ksft_test_result_pass(
-			"[%d] Result (%d) matches expectation (%d)\n",
-			getpid(), ret, expected);
+
+	ksft_test_result(ret == expected, "%s with %zu TIDs and flags 0x%x\n",
+			 desc, set_tid_size, flags);
 }
+
 int main(int argc, char *argv[])
 {
 	FILE *f;
@@ -174,73 +169,91 @@ int main(int argc, char *argv[])
 
 	/* Try invalid settings */
 	memset(&set_tid, 0, sizeof(set_tid));
-	test_clone3_set_tid(set_tid, MAX_PID_NS_LEVEL + 1, 0, -EINVAL, 0, 0);
+	test_clone3_set_tid("invalid size, 0 TID",
+			    set_tid, MAX_PID_NS_LEVEL + 1, 0, -EINVAL, 0, 0);
 
-	test_clone3_set_tid(set_tid, MAX_PID_NS_LEVEL * 2, 0, -EINVAL, 0, 0);
+	test_clone3_set_tid("invalid size, 0 TID",
+			    set_tid, MAX_PID_NS_LEVEL * 2, 0, -EINVAL, 0, 0);
 
-	test_clone3_set_tid(set_tid, MAX_PID_NS_LEVEL * 2 + 1, 0,
-			-EINVAL, 0, 0);
+	test_clone3_set_tid("invalid size, 0 TID",
+			    set_tid, MAX_PID_NS_LEVEL * 2 + 1, 0,
+			    -EINVAL, 0, 0);
 
-	test_clone3_set_tid(set_tid, MAX_PID_NS_LEVEL * 42, 0, -EINVAL, 0, 0);
+	test_clone3_set_tid("invalid size, 0 TID",
+			    set_tid, MAX_PID_NS_LEVEL * 42, 0, -EINVAL, 0, 0);
 
 	/*
 	 * This can actually work if this test running in a MAX_PID_NS_LEVEL - 1
 	 * nested PID namespace.
 	 */
-	test_clone3_set_tid(set_tid, MAX_PID_NS_LEVEL - 1, 0, -EINVAL, 0, 0);
+	test_clone3_set_tid("invalid size, 0 TID",
+			    set_tid, MAX_PID_NS_LEVEL - 1, 0, -EINVAL, 0, 0);
 
 	memset(&set_tid, 0xff, sizeof(set_tid));
-	test_clone3_set_tid(set_tid, MAX_PID_NS_LEVEL + 1, 0, -EINVAL, 0, 0);
+	test_clone3_set_tid("invalid size, TID all 1s",
+			    set_tid, MAX_PID_NS_LEVEL + 1, 0, -EINVAL, 0, 0);
 
-	test_clone3_set_tid(set_tid, MAX_PID_NS_LEVEL * 2, 0, -EINVAL, 0, 0);
+	test_clone3_set_tid("invalid size, TID all 1s",
+			    set_tid, MAX_PID_NS_LEVEL * 2, 0, -EINVAL, 0, 0);
 
-	test_clone3_set_tid(set_tid, MAX_PID_NS_LEVEL * 2 + 1, 0,
-			-EINVAL, 0, 0);
+	test_clone3_set_tid("invalid size, TID all 1s",
+			    set_tid, MAX_PID_NS_LEVEL * 2 + 1, 0,
+			    -EINVAL, 0, 0);
 
-	test_clone3_set_tid(set_tid, MAX_PID_NS_LEVEL * 42, 0, -EINVAL, 0, 0);
+	test_clone3_set_tid("invalid size, TID all 1s",
+			    set_tid, MAX_PID_NS_LEVEL * 42, 0, -EINVAL, 0, 0);
 
 	/*
 	 * This can actually work if this test running in a MAX_PID_NS_LEVEL - 1
 	 * nested PID namespace.
 	 */
-	test_clone3_set_tid(set_tid, MAX_PID_NS_LEVEL - 1, 0, -EINVAL, 0, 0);
+	test_clone3_set_tid("invalid size, TID all 1s",
+			    set_tid, MAX_PID_NS_LEVEL - 1, 0, -EINVAL, 0, 0);
 
 	memset(&set_tid, 0, sizeof(set_tid));
 	/* Try with an invalid PID */
 	set_tid[0] = 0;
-	test_clone3_set_tid(set_tid, 1, 0, -EINVAL, 0, 0);
+	test_clone3_set_tid("valid size, 0 TID",
+			    set_tid, 1, 0, -EINVAL, 0, 0);
 
 	set_tid[0] = -1;
-	test_clone3_set_tid(set_tid, 1, 0, -EINVAL, 0, 0);
+	test_clone3_set_tid("valid size, -1 TID",
+			    set_tid, 1, 0, -EINVAL, 0, 0);
 
 	/* Claim that the set_tid array actually contains 2 elements. */
-	test_clone3_set_tid(set_tid, 2, 0, -EINVAL, 0, 0);
+	test_clone3_set_tid("2 TIDs, -1 and 0",
+			    set_tid, 2, 0, -EINVAL, 0, 0);
 
 	/* Try it in a new PID namespace */
 	if (uid == 0)
-		test_clone3_set_tid(set_tid, 1, CLONE_NEWPID, -EINVAL, 0, 0);
+		test_clone3_set_tid("valid size, -1 TID",
+				    set_tid, 1, CLONE_NEWPID, -EINVAL, 0, 0);
 	else
 		ksft_test_result_skip("Clone3() with set_tid requires root\n");
 
 	/* Try with a valid PID (1) this should return -EEXIST. */
 	set_tid[0] = 1;
 	if (uid == 0)
-		test_clone3_set_tid(set_tid, 1, 0, -EEXIST, 0, 0);
+		test_clone3_set_tid("duplicate PID 1",
+				    set_tid, 1, 0, -EEXIST, 0, 0);
 	else
 		ksft_test_result_skip("Clone3() with set_tid requires root\n");
 
 	/* Try it in a new PID namespace */
 	if (uid == 0)
-		test_clone3_set_tid(set_tid, 1, CLONE_NEWPID, 0, 0, 0);
+		test_clone3_set_tid("duplicate PID 1",
+				    set_tid, 1, CLONE_NEWPID, 0, 0, 0);
 	else
 		ksft_test_result_skip("Clone3() with set_tid requires root\n");
 
 	/* pid_max should fail everywhere */
 	set_tid[0] = pid_max;
-	test_clone3_set_tid(set_tid, 1, 0, -EINVAL, 0, 0);
+	test_clone3_set_tid("set TID to maximum",
+			    set_tid, 1, 0, -EINVAL, 0, 0);
 
 	if (uid == 0)
-		test_clone3_set_tid(set_tid, 1, CLONE_NEWPID, -EINVAL, 0, 0);
+		test_clone3_set_tid("set TID to maximum",
+				    set_tid, 1, CLONE_NEWPID, -EINVAL, 0, 0);
 	else
 		ksft_test_result_skip("Clone3() with set_tid requires root\n");
 
@@ -264,10 +277,12 @@ int main(int argc, char *argv[])
 
 	/* After the child has finished, its PID should be free. */
 	set_tid[0] = pid;
-	test_clone3_set_tid(set_tid, 1, 0, 0, 0, 0);
+	test_clone3_set_tid("reallocate child TID",
+			    set_tid, 1, 0, 0, 0, 0);
 
 	/* This should fail as there is no PID 1 in that namespace */
-	test_clone3_set_tid(set_tid, 1, CLONE_NEWPID, -EINVAL, 0, 0);
+	test_clone3_set_tid("duplicate child TID",
+			    set_tid, 1, CLONE_NEWPID, -EINVAL, 0, 0);
 
 	/*
 	 * Creating a process with PID 1 in the newly created most nested
@@ -276,7 +291,8 @@ int main(int argc, char *argv[])
 	 */
 	set_tid[0] = 1;
 	set_tid[1] = pid;
-	test_clone3_set_tid(set_tid, 2, CLONE_NEWPID, 0, pid, 0);
+	test_clone3_set_tid("create PID 1 in new NS",
+			    set_tid, 2, CLONE_NEWPID, 0, pid, 0);
 
 	ksft_print_msg("unshare PID namespace\n");
 	if (unshare(CLONE_NEWPID) == -1)
@@ -286,7 +302,8 @@ int main(int argc, char *argv[])
 	set_tid[0] = pid;
 
 	/* This should fail as there is no PID 1 in that namespace */
-	test_clone3_set_tid(set_tid, 1, 0, -EINVAL, 0, 0);
+	test_clone3_set_tid("duplicate PID 1",
+			    set_tid, 1, 0, -EINVAL, 0, 0);
 
 	/* Let's create a PID 1 */
 	ns_pid = fork();
@@ -297,21 +314,25 @@ int main(int argc, char *argv[])
 		 */
 		set_tid[0] = 43;
 		set_tid[1] = -1;
-		test_clone3_set_tid(set_tid, 2, 0, -EINVAL, 0, 0);
+		test_clone3_set_tid("check leak on invalid TID -1",
+				    set_tid, 2, 0, -EINVAL, 0, 0);
 
 		set_tid[0] = 43;
 		set_tid[1] = pid;
-		test_clone3_set_tid(set_tid, 2, 0, 0, 43, 0);
+		test_clone3_set_tid("check leak on invalid specific TID",
+				    set_tid, 2, 0, 0, 43, 0);
 
 		ksft_print_msg("Child in PID namespace has PID %d\n", getpid());
 		set_tid[0] = 2;
-		test_clone3_set_tid(set_tid, 1, 0, 0, 2, 0);
+		test_clone3_set_tid("create PID 2 in child NS",
+				    set_tid, 1, 0, 0, 2, 0);
 
 		set_tid[0] = 1;
 		set_tid[1] = -1;
 		set_tid[2] = pid;
 		/* This should fail as there is invalid PID at level '1'. */
-		test_clone3_set_tid(set_tid, 3, CLONE_NEWPID, -EINVAL, 0, 0);
+		test_clone3_set_tid("fail due to invalid TID at level 1",
+				    set_tid, 3, CLONE_NEWPID, -EINVAL, 0, 0);
 
 		set_tid[0] = 1;
 		set_tid[1] = 42;
@@ -321,13 +342,15 @@ int main(int argc, char *argv[])
 		 * namespaces. Again assuming this is running in the host's
 		 * PID namespace. Not yet nested.
 		 */
-		test_clone3_set_tid(set_tid, 4, CLONE_NEWPID, -EINVAL, 0, 0);
+		test_clone3_set_tid("fail due to too few active PID NSs",
+				    set_tid, 4, CLONE_NEWPID, -EINVAL, 0, 0);
 
 		/*
 		 * This should work and from the parent we should see
 		 * something like 'NSpid:	pid	42	1'.
 		 */
-		test_clone3_set_tid(set_tid, 3, CLONE_NEWPID, 0, 42, true);
+		test_clone3_set_tid("verify that we have 3 PID NSs",
+				    set_tid, 3, CLONE_NEWPID, 0, 42, true);
 
 		child_exit(ksft_cnt.ksft_fail);
 	}
@@ -382,16 +405,14 @@ int main(int argc, char *argv[])
 	ksft_cnt.ksft_pass += 6 - (ksft_cnt.ksft_fail - WEXITSTATUS(status));
 	ksft_cnt.ksft_fail = WEXITSTATUS(status);
 
-	if (ns3 == pid && ns2 == 42 && ns1 == 1)
-		ksft_test_result_pass(
-			"PIDs in all namespaces as expected (%d,%d,%d)\n",
-			ns3, ns2, ns1);
-	else
-		ksft_test_result_fail(
-			"PIDs in all namespaces not as expected (%d,%d,%d)\n",
-			ns3, ns2, ns1);
+	ksft_print_msg("Expecting PIDs %d, 42, 1\n", pid);
+	ksft_print_msg("Have PIDs in namespaces: %d, %d, %d\n", ns3, ns2, ns1);
+	ksft_test_result(ns3 == pid && ns2 == 42 && ns1 == 1,
+			 "PIDs in all namespaces as expected\n");
 out:
 	ret = 0;
 
-	return !ret ? ksft_exit_pass() : ksft_exit_fail();
+	if (ret)
+		ksft_exit_fail();
+	ksft_exit_pass();
 }
diff --git a/tools/testing/selftests/connector/.gitignore b/tools/testing/selftests/connector/.gitignore
new file mode 100644
index 000000000000..c90098199a44
--- /dev/null
+++ b/tools/testing/selftests/connector/.gitignore
@@ -0,0 +1 @@
+proc_filter
diff --git a/tools/testing/selftests/connector/Makefile b/tools/testing/selftests/connector/Makefile
new file mode 100644
index 000000000000..92188b9bac5c
--- /dev/null
+++ b/tools/testing/selftests/connector/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -Wall $(KHDR_INCLUDES)
+
+TEST_GEN_PROGS = proc_filter
+
+include ../lib.mk
diff --git a/tools/testing/selftests/connector/proc_filter.c b/tools/testing/selftests/connector/proc_filter.c
new file mode 100644
index 000000000000..36c11467a8f1
--- /dev/null
+++ b/tools/testing/selftests/connector/proc_filter.c
@@ -0,0 +1,310 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <sys/types.h>
+#include <sys/epoll.h>
+#include <sys/socket.h>
+#include <linux/netlink.h>
+#include <linux/connector.h>
+#include <linux/cn_proc.h>
+
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <strings.h>
+#include <errno.h>
+#include <signal.h>
+#include <string.h>
+
+#include "kselftest.h"
+
+#define NL_MESSAGE_SIZE (sizeof(struct nlmsghdr) + sizeof(struct cn_msg) + \
+			 sizeof(struct proc_input))
+#define NL_MESSAGE_SIZE_NF (sizeof(struct nlmsghdr) + sizeof(struct cn_msg) + \
+			 sizeof(int))
+
+#define MAX_EVENTS 1
+
+volatile static int interrupted;
+static int nl_sock, ret_errno, tcount;
+static struct epoll_event evn;
+
+static int filter;
+
+#ifdef ENABLE_PRINTS
+#define Printf printf
+#else
+#define Printf ksft_print_msg
+#endif
+
+int send_message(void *pinp)
+{
+	char buff[NL_MESSAGE_SIZE];
+	struct nlmsghdr *hdr;
+	struct cn_msg *msg;
+
+	hdr = (struct nlmsghdr *)buff;
+	if (filter)
+		hdr->nlmsg_len = NL_MESSAGE_SIZE;
+	else
+		hdr->nlmsg_len = NL_MESSAGE_SIZE_NF;
+	hdr->nlmsg_type = NLMSG_DONE;
+	hdr->nlmsg_flags = 0;
+	hdr->nlmsg_seq = 0;
+	hdr->nlmsg_pid = getpid();
+
+	msg = (struct cn_msg *)NLMSG_DATA(hdr);
+	msg->id.idx = CN_IDX_PROC;
+	msg->id.val = CN_VAL_PROC;
+	msg->seq = 0;
+	msg->ack = 0;
+	msg->flags = 0;
+
+	if (filter) {
+		msg->len = sizeof(struct proc_input);
+		((struct proc_input *)msg->data)->mcast_op =
+			((struct proc_input *)pinp)->mcast_op;
+		((struct proc_input *)msg->data)->event_type =
+			((struct proc_input *)pinp)->event_type;
+	} else {
+		msg->len = sizeof(int);
+		*(int *)msg->data = *(enum proc_cn_mcast_op *)pinp;
+	}
+
+	if (send(nl_sock, hdr, hdr->nlmsg_len, 0) == -1) {
+		ret_errno = errno;
+		perror("send failed");
+		return -3;
+	}
+	return 0;
+}
+
+int register_proc_netlink(int *efd, void *input)
+{
+	struct sockaddr_nl sa_nl;
+	int err = 0, epoll_fd;
+
+	nl_sock = socket(PF_NETLINK, SOCK_DGRAM, NETLINK_CONNECTOR);
+
+	if (nl_sock == -1) {
+		ret_errno = errno;
+		perror("socket failed");
+		return -1;
+	}
+
+	bzero(&sa_nl, sizeof(sa_nl));
+	sa_nl.nl_family = AF_NETLINK;
+	sa_nl.nl_groups = CN_IDX_PROC;
+	sa_nl.nl_pid    = getpid();
+
+	if (bind(nl_sock, (struct sockaddr *)&sa_nl, sizeof(sa_nl)) == -1) {
+		ret_errno = errno;
+		perror("bind failed");
+		return -2;
+	}
+
+	epoll_fd = epoll_create1(EPOLL_CLOEXEC);
+	if (epoll_fd < 0) {
+		ret_errno = errno;
+		perror("epoll_create1 failed");
+		return -2;
+	}
+
+	err = send_message(input);
+
+	if (err < 0)
+		return err;
+
+	evn.events = EPOLLIN;
+	evn.data.fd = nl_sock;
+	if (epoll_ctl(epoll_fd, EPOLL_CTL_ADD, nl_sock, &evn) < 0) {
+		ret_errno = errno;
+		perror("epoll_ctl failed");
+		return -3;
+	}
+	*efd = epoll_fd;
+	return 0;
+}
+
+static void sigint(int sig)
+{
+	interrupted = 1;
+}
+
+int handle_packet(char *buff, int fd, struct proc_event *event)
+{
+	struct nlmsghdr *hdr;
+
+	hdr = (struct nlmsghdr *)buff;
+
+	if (hdr->nlmsg_type == NLMSG_ERROR) {
+		perror("NLMSG_ERROR error\n");
+		return -3;
+	} else if (hdr->nlmsg_type == NLMSG_DONE) {
+		event = (struct proc_event *)
+			((struct cn_msg *)NLMSG_DATA(hdr))->data;
+		tcount++;
+		switch (event->what) {
+		case PROC_EVENT_EXIT:
+			Printf("Exit process %d (tgid %d) with code %d, signal %d\n",
+			       event->event_data.exit.process_pid,
+			       event->event_data.exit.process_tgid,
+			       event->event_data.exit.exit_code,
+			       event->event_data.exit.exit_signal);
+			break;
+		case PROC_EVENT_FORK:
+			Printf("Fork process %d (tgid %d), parent %d (tgid %d)\n",
+			       event->event_data.fork.child_pid,
+			       event->event_data.fork.child_tgid,
+			       event->event_data.fork.parent_pid,
+			       event->event_data.fork.parent_tgid);
+			break;
+		case PROC_EVENT_EXEC:
+			Printf("Exec process %d (tgid %d)\n",
+			       event->event_data.exec.process_pid,
+			       event->event_data.exec.process_tgid);
+			break;
+		case PROC_EVENT_UID:
+			Printf("UID process %d (tgid %d) uid %d euid %d\n",
+			       event->event_data.id.process_pid,
+			       event->event_data.id.process_tgid,
+			       event->event_data.id.r.ruid,
+			       event->event_data.id.e.euid);
+			break;
+		case PROC_EVENT_GID:
+			Printf("GID process %d (tgid %d) gid %d egid %d\n",
+			       event->event_data.id.process_pid,
+			       event->event_data.id.process_tgid,
+			       event->event_data.id.r.rgid,
+			       event->event_data.id.e.egid);
+			break;
+		case PROC_EVENT_SID:
+			Printf("SID process %d (tgid %d)\n",
+			       event->event_data.sid.process_pid,
+			       event->event_data.sid.process_tgid);
+			break;
+		case PROC_EVENT_PTRACE:
+			Printf("Ptrace process %d (tgid %d), Tracer %d (tgid %d)\n",
+			       event->event_data.ptrace.process_pid,
+			       event->event_data.ptrace.process_tgid,
+			       event->event_data.ptrace.tracer_pid,
+			       event->event_data.ptrace.tracer_tgid);
+			break;
+		case PROC_EVENT_COMM:
+			Printf("Comm process %d (tgid %d) comm %s\n",
+			       event->event_data.comm.process_pid,
+			       event->event_data.comm.process_tgid,
+			       event->event_data.comm.comm);
+			break;
+		case PROC_EVENT_COREDUMP:
+			Printf("Coredump process %d (tgid %d) parent %d, (tgid %d)\n",
+			       event->event_data.coredump.process_pid,
+			       event->event_data.coredump.process_tgid,
+			       event->event_data.coredump.parent_pid,
+			       event->event_data.coredump.parent_tgid);
+			break;
+		default:
+			break;
+		}
+	}
+	return 0;
+}
+
+int handle_events(int epoll_fd, struct proc_event *pev)
+{
+	char buff[CONNECTOR_MAX_MSG_SIZE];
+	struct epoll_event ev[MAX_EVENTS];
+	int i, event_count = 0, err = 0;
+
+	event_count = epoll_wait(epoll_fd, ev, MAX_EVENTS, -1);
+	if (event_count < 0) {
+		ret_errno = errno;
+		if (ret_errno != EINTR)
+			perror("epoll_wait failed");
+		return -3;
+	}
+	for (i = 0; i < event_count; i++) {
+		if (!(ev[i].events & EPOLLIN))
+			continue;
+		if (recv(ev[i].data.fd, buff, sizeof(buff), 0) == -1) {
+			ret_errno = errno;
+			perror("recv failed");
+			return -3;
+		}
+		err = handle_packet(buff, ev[i].data.fd, pev);
+		if (err < 0)
+			return err;
+	}
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	int epoll_fd, err;
+	struct proc_event proc_ev;
+	struct proc_input input;
+
+	signal(SIGINT, sigint);
+
+	if (argc > 2) {
+		printf("Expected 0(assume no-filter) or 1 argument(-f)\n");
+		exit(KSFT_SKIP);
+	}
+
+	if (argc == 2) {
+		if (strcmp(argv[1], "-f") == 0) {
+			filter = 1;
+		} else {
+			printf("Valid option : -f (for filter feature)\n");
+			exit(KSFT_SKIP);
+		}
+	}
+
+	if (filter) {
+		input.event_type = PROC_EVENT_NONZERO_EXIT;
+		input.mcast_op = PROC_CN_MCAST_LISTEN;
+		err = register_proc_netlink(&epoll_fd, (void*)&input);
+	} else {
+		enum proc_cn_mcast_op op = PROC_CN_MCAST_LISTEN;
+		err = register_proc_netlink(&epoll_fd, (void*)&op);
+	}
+
+	if (err < 0) {
+		if (err == -2)
+			close(nl_sock);
+		if (err == -3) {
+			close(nl_sock);
+			close(epoll_fd);
+		}
+		exit(1);
+	}
+
+	while (!interrupted) {
+		err = handle_events(epoll_fd, &proc_ev);
+		if (err < 0) {
+			if (ret_errno == EINTR)
+				continue;
+			if (err == -2)
+				close(nl_sock);
+			if (err == -3) {
+				close(nl_sock);
+				close(epoll_fd);
+			}
+			exit(1);
+		}
+	}
+
+	if (filter) {
+		input.mcast_op = PROC_CN_MCAST_IGNORE;
+		send_message((void*)&input);
+	} else {
+		enum proc_cn_mcast_op op = PROC_CN_MCAST_IGNORE;
+		send_message((void*)&op);
+	}
+
+	close(epoll_fd);
+	close(nl_sock);
+
+	printf("Done total count: %d\n", tcount);
+	exit(0);
+}
diff --git a/tools/testing/selftests/core/.gitignore b/tools/testing/selftests/core/.gitignore
index 6e6712ce5817..7999361992aa 100644
--- a/tools/testing/selftests/core/.gitignore
+++ b/tools/testing/selftests/core/.gitignore
@@ -1 +1,2 @@
 close_range_test
+unshare_test
diff --git a/tools/testing/selftests/core/Makefile b/tools/testing/selftests/core/Makefile
index f6f2d6f473c6..8e99f87f5d7c 100644
--- a/tools/testing/selftests/core/Makefile
+++ b/tools/testing/selftests/core/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
-CFLAGS += -g -I../../../../usr/include/
+CFLAGS += -g $(KHDR_INCLUDES)
 
-TEST_GEN_PROGS := close_range_test
+TEST_GEN_PROGS := close_range_test unshare_test
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c
index 749239930ca8..f14eca63f20c 100644
--- a/tools/testing/selftests/core/close_range_test.c
+++ b/tools/testing/selftests/core/close_range_test.c
@@ -12,36 +12,22 @@
 #include <syscall.h>
 #include <unistd.h>
 #include <sys/resource.h>
+#include <linux/close_range.h>
 
-#include "../kselftest_harness.h"
+#include "kselftest_harness.h"
 #include "../clone3/clone3_selftests.h"
 
-#ifndef __NR_close_range
-	#if defined __alpha__
-		#define __NR_close_range 546
-	#elif defined _MIPS_SIM
-		#if _MIPS_SIM == _MIPS_SIM_ABI32	/* o32 */
-			#define __NR_close_range (436 + 4000)
-		#endif
-		#if _MIPS_SIM == _MIPS_SIM_NABI32	/* n32 */
-			#define __NR_close_range (436 + 6000)
-		#endif
-		#if _MIPS_SIM == _MIPS_SIM_ABI64	/* n64 */
-			#define __NR_close_range (436 + 5000)
-		#endif
-	#elif defined __ia64__
-		#define __NR_close_range (436 + 1024)
-	#else
-		#define __NR_close_range 436
-	#endif
+
+#ifndef F_LINUX_SPECIFIC_BASE
+#define F_LINUX_SPECIFIC_BASE 1024
 #endif
 
-#ifndef CLOSE_RANGE_UNSHARE
-#define CLOSE_RANGE_UNSHARE	(1U << 1)
+#ifndef F_DUPFD_QUERY
+#define F_DUPFD_QUERY (F_LINUX_SPECIFIC_BASE + 3)
 #endif
 
-#ifndef CLOSE_RANGE_CLOEXEC
-#define CLOSE_RANGE_CLOEXEC	(1U << 2)
+#ifndef F_CREATED_QUERY
+#define F_CREATED_QUERY (F_LINUX_SPECIFIC_BASE + 4)
 #endif
 
 static inline int sys_close_range(unsigned int fd, unsigned int max_fd,
@@ -72,6 +58,15 @@ TEST(core_close_range)
 			SKIP(return, "close_range() syscall not supported");
 	}
 
+	for (i = 0; i < 100; i++) {
+		ret = fcntl(open_fds[i], F_DUPFD_QUERY, open_fds[i + 1]);
+		if (ret < 0) {
+			EXPECT_EQ(errno, EINVAL);
+		} else {
+			EXPECT_EQ(ret, 0);
+		}
+	}
+
 	EXPECT_EQ(0, sys_close_range(open_fds[0], open_fds[50], 0));
 
 	for (i = 0; i <= 50; i++)
@@ -385,7 +380,7 @@ TEST(close_range_cloexec_unshare)
  */
 TEST(close_range_cloexec_syzbot)
 {
-	int fd1, fd2, fd3, flags, ret, status;
+	int fd1, fd2, fd3, fd4, flags, ret, status;
 	pid_t pid;
 	struct __clone_args args = {
 		.flags = CLONE_FILES,
@@ -399,6 +394,13 @@ TEST(close_range_cloexec_syzbot)
 	fd2 = dup2(fd1, 1000);
 	EXPECT_GT(fd2, 0);
 
+	flags = fcntl(fd1, F_DUPFD_QUERY, fd2);
+	if (flags < 0) {
+		EXPECT_EQ(errno, EINVAL);
+	} else {
+		EXPECT_EQ(flags, 1);
+	}
+
 	pid = sys_clone3(&args, sizeof(args));
 	ASSERT_GE(pid, 0);
 
@@ -423,6 +425,15 @@ TEST(close_range_cloexec_syzbot)
 		fd3 = dup2(fd1, 42);
 		EXPECT_GT(fd3, 0);
 
+		flags = fcntl(fd1, F_DUPFD_QUERY, fd3);
+		if (flags < 0) {
+			EXPECT_EQ(errno, EINVAL);
+		} else {
+			EXPECT_EQ(flags, 1);
+		}
+
+
+
 		/*
 			 * Duplicating the file descriptor must remove the
 			 * FD_CLOEXEC flag.
@@ -453,6 +464,24 @@ TEST(close_range_cloexec_syzbot)
 	fd3 = dup2(fd1, 42);
 	EXPECT_GT(fd3, 0);
 
+	flags = fcntl(fd1, F_DUPFD_QUERY, fd3);
+	if (flags < 0) {
+		EXPECT_EQ(errno, EINVAL);
+	} else {
+		EXPECT_EQ(flags, 1);
+	}
+
+	fd4 = open("/dev/null", O_RDWR);
+	EXPECT_GT(fd4, 0);
+
+	/* Same inode, different file pointers. */
+	flags = fcntl(fd1, F_DUPFD_QUERY, fd4);
+	if (flags < 0) {
+		EXPECT_EQ(errno, EINVAL);
+	} else {
+		EXPECT_EQ(flags, 0);
+	}
+
 	flags = fcntl(fd3, F_GETFD);
 	EXPECT_GT(flags, -1);
 	EXPECT_EQ(flags & FD_CLOEXEC, 0);
@@ -460,6 +489,7 @@ TEST(close_range_cloexec_syzbot)
 	EXPECT_EQ(close(fd1), 0);
 	EXPECT_EQ(close(fd2), 0);
 	EXPECT_EQ(close(fd3), 0);
+	EXPECT_EQ(close(fd4), 0);
 }
 
 /*
@@ -563,4 +593,74 @@ TEST(close_range_cloexec_unshare_syzbot)
 	EXPECT_EQ(close(fd3), 0);
 }
 
+TEST(close_range_bitmap_corruption)
+{
+	pid_t pid;
+	int status;
+	struct __clone_args args = {
+		.flags = CLONE_FILES,
+		.exit_signal = SIGCHLD,
+	};
+
+	/* get the first 128 descriptors open */
+	for (int i = 2; i < 128; i++)
+		EXPECT_GE(dup2(0, i), 0);
+
+	/* get descriptor table shared */
+	pid = sys_clone3(&args, sizeof(args));
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		/* unshare and truncate descriptor table down to 64 */
+		if (sys_close_range(64, ~0U, CLOSE_RANGE_UNSHARE))
+			exit(EXIT_FAILURE);
+
+		ASSERT_EQ(fcntl(64, F_GETFD), -1);
+		/* ... and verify that the range 64..127 is not
+		   stuck "fully used" according to secondary bitmap */
+		EXPECT_EQ(dup(0), 64)
+			exit(EXIT_FAILURE);
+		exit(EXIT_SUCCESS);
+	}
+
+	EXPECT_EQ(waitpid(pid, &status, 0), pid);
+	EXPECT_EQ(true, WIFEXITED(status));
+	EXPECT_EQ(0, WEXITSTATUS(status));
+}
+
+TEST(fcntl_created)
+{
+	for (int i = 0; i < 101; i++) {
+		int fd;
+		char path[PATH_MAX];
+
+		fd = open("/dev/null", O_RDONLY | O_CLOEXEC);
+		ASSERT_GE(fd, 0) {
+			if (errno == ENOENT)
+				SKIP(return,
+					   "Skipping test since /dev/null does not exist");
+		}
+
+		/* We didn't create "/dev/null". */
+		EXPECT_EQ(fcntl(fd, F_CREATED_QUERY, 0), 0);
+		close(fd);
+
+		sprintf(path, "aaaa_%d", i);
+		fd = open(path, O_CREAT | O_RDONLY | O_CLOEXEC, 0600);
+		ASSERT_GE(fd, 0);
+
+		/* We created "aaaa_%d". */
+		EXPECT_EQ(fcntl(fd, F_CREATED_QUERY, 0), 1);
+		close(fd);
+
+		fd = open(path, O_RDONLY | O_CLOEXEC);
+		ASSERT_GE(fd, 0);
+
+		/* We're opening it again, so no positive creation check. */
+		EXPECT_EQ(fcntl(fd, F_CREATED_QUERY, 0), 0);
+		close(fd);
+		unlink(path);
+	}
+}
+
 TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/core/unshare_test.c b/tools/testing/selftests/core/unshare_test.c
new file mode 100644
index 000000000000..ffce75a6c228
--- /dev/null
+++ b/tools/testing/selftests/core/unshare_test.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/kernel.h>
+#include <limits.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <syscall.h>
+#include <unistd.h>
+#include <sys/resource.h>
+#include <linux/close_range.h>
+
+#include "kselftest_harness.h"
+#include "../clone3/clone3_selftests.h"
+
+TEST(unshare_EMFILE)
+{
+	pid_t pid;
+	int status;
+	struct __clone_args args = {
+		.flags = CLONE_FILES,
+		.exit_signal = SIGCHLD,
+	};
+	int fd;
+	ssize_t n, n2;
+	static char buf[512], buf2[512];
+	struct rlimit rlimit;
+	int nr_open;
+
+	fd = open("/proc/sys/fs/nr_open", O_RDWR);
+	ASSERT_GE(fd, 0);
+
+	n = read(fd, buf, sizeof(buf));
+	ASSERT_GT(n, 0);
+	ASSERT_EQ(buf[n - 1], '\n');
+
+	ASSERT_EQ(sscanf(buf, "%d", &nr_open), 1);
+
+	ASSERT_EQ(0, getrlimit(RLIMIT_NOFILE, &rlimit));
+
+	/* bump fs.nr_open */
+	n2 = sprintf(buf2, "%d\n", nr_open + 1024);
+	lseek(fd, 0, SEEK_SET);
+	write(fd, buf2, n2);
+
+	/* bump ulimit -n */
+	rlimit.rlim_cur = nr_open + 1024;
+	rlimit.rlim_max = nr_open + 1024;
+	EXPECT_EQ(0, setrlimit(RLIMIT_NOFILE, &rlimit)) {
+		lseek(fd, 0, SEEK_SET);
+		write(fd, buf, n);
+		exit(EXIT_FAILURE);
+	}
+
+	/* get a descriptor past the old fs.nr_open */
+	EXPECT_GE(dup2(2, nr_open + 64), 0) {
+		lseek(fd, 0, SEEK_SET);
+		write(fd, buf, n);
+		exit(EXIT_FAILURE);
+	}
+
+	/* get descriptor table shared */
+	pid = sys_clone3(&args, sizeof(args));
+	EXPECT_GE(pid, 0) {
+		lseek(fd, 0, SEEK_SET);
+		write(fd, buf, n);
+		exit(EXIT_FAILURE);
+	}
+
+	if (pid == 0) {
+		int err;
+
+		/* restore fs.nr_open */
+		lseek(fd, 0, SEEK_SET);
+		write(fd, buf, n);
+		/* ... and now unshare(CLONE_FILES) must fail with EMFILE */
+		err = unshare(CLONE_FILES);
+		EXPECT_EQ(err, -1)
+			exit(EXIT_FAILURE);
+		EXPECT_EQ(errno, EMFILE)
+			exit(EXIT_FAILURE);
+		exit(EXIT_SUCCESS);
+	}
+
+	EXPECT_EQ(waitpid(pid, &status, 0), pid);
+	EXPECT_EQ(true, WIFEXITED(status));
+	EXPECT_EQ(0, WEXITSTATUS(status));
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/coredump/.gitignore b/tools/testing/selftests/coredump/.gitignore
new file mode 100644
index 000000000000..097f52db0be9
--- /dev/null
+++ b/tools/testing/selftests/coredump/.gitignore
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+stackdump_test
+coredump_socket_test
+coredump_socket_protocol_test
diff --git a/tools/testing/selftests/coredump/Makefile b/tools/testing/selftests/coredump/Makefile
new file mode 100644
index 000000000000..dece1a31d561
--- /dev/null
+++ b/tools/testing/selftests/coredump/Makefile
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0-only
+CFLAGS += -Wall -O0 -g $(KHDR_INCLUDES) $(TOOLS_INCLUDES)
+
+TEST_GEN_PROGS := stackdump_test \
+		  coredump_socket_test \
+		  coredump_socket_protocol_test
+TEST_FILES := stackdump
+
+include ../lib.mk
+
+$(OUTPUT)/stackdump_test: coredump_test_helpers.c
+$(OUTPUT)/coredump_socket_test: coredump_test_helpers.c
+$(OUTPUT)/coredump_socket_protocol_test: coredump_test_helpers.c
diff --git a/tools/testing/selftests/coredump/README.rst b/tools/testing/selftests/coredump/README.rst
new file mode 100644
index 000000000000..164a7aa181c8
--- /dev/null
+++ b/tools/testing/selftests/coredump/README.rst
@@ -0,0 +1,50 @@
+coredump selftest
+=================
+
+Background context
+------------------
+
+`coredump` is a feature which dumps a process's memory space when the process terminates
+unexpectedly (e.g. due to segmentation fault), which can be useful for debugging. By default,
+`coredump` dumps the memory to the file named `core`, but this behavior can be changed by writing a
+different file name to `/proc/sys/kernel/core_pattern`. Furthermore, `coredump` can be piped to a
+user-space program by writing the pipe symbol (`|`) followed by the command to be executed to
+`/proc/sys/kernel/core_pattern`. For the full description, see `man 5 core`.
+
+The piped user program may be interested in reading the stack pointers of the crashed process. The
+crashed process's stack pointers can be read from `procfs`: it is the `kstkesp` field in
+`/proc/$PID/stat`. See `man 5 proc` for all the details.
+
+The problem
+-----------
+While a thread is active, the stack pointer is unsafe to read and therefore the `kstkesp` field
+reads zero. But when the thread is dead (e.g. during a coredump), this field should have valid
+value.
+
+However, this was broken in the past and `kstkesp` was zero even during coredump:
+
+* commit 0a1eb2d474ed ("fs/proc: Stop reporting eip and esp in /proc/PID/stat") changed kstkesp to
+  always be zero
+
+* commit fd7d56270b52 ("fs/proc: Report eip/esp in /prod/PID/stat for coredumping") fixed it for the
+  coredumping thread. However, other threads in a coredumping process still had the problem.
+
+* commit cb8f381f1613 ("fs/proc/array.c: allow reporting eip/esp for all coredumping threads") fixed
+  for all threads in a coredumping process.
+
+* commit 92307383082d ("coredump:  Don't perform any cleanups before dumping core") broke it again
+  for the other threads in a coredumping process.
+
+The problem has been fixed now, but considering the history, it may appear again in the future.
+
+The goal of this test
+---------------------
+This test detects problem with reading `kstkesp` during coredump by doing the following:
+
+#. Tell the kernel to execute the "stackdump" script when a coredump happens. This script
+   reads the stack pointers of all threads of crashed processes.
+
+#. Spawn a child process who creates some threads and then crashes.
+
+#. Read the output from the "stackdump" script, and make sure all stack pointer values are
+   non-zero.
diff --git a/tools/testing/selftests/coredump/config b/tools/testing/selftests/coredump/config
new file mode 100644
index 000000000000..a05ef112b4f9
--- /dev/null
+++ b/tools/testing/selftests/coredump/config
@@ -0,0 +1,3 @@
+CONFIG_COREDUMP=y
+CONFIG_NET=y
+CONFIG_UNIX=y
diff --git a/tools/testing/selftests/coredump/coredump_socket_protocol_test.c b/tools/testing/selftests/coredump/coredump_socket_protocol_test.c
new file mode 100644
index 000000000000..d19b6717c53e
--- /dev/null
+++ b/tools/testing/selftests/coredump/coredump_socket_protocol_test.c
@@ -0,0 +1,1568 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <sys/stat.h>
+#include <sys/epoll.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+
+#include "coredump_test.h"
+
+#define NUM_CRASHING_COREDUMPS 5
+
+FIXTURE_SETUP(coredump)
+{
+	FILE *file;
+	int ret;
+
+	self->pid_coredump_server = -ESRCH;
+	self->fd_tmpfs_detached = -1;
+	file = fopen("/proc/sys/kernel/core_pattern", "r");
+	ASSERT_NE(NULL, file);
+
+	ret = fread(self->original_core_pattern, 1, sizeof(self->original_core_pattern), file);
+	ASSERT_TRUE(ret || feof(file));
+	ASSERT_LT(ret, sizeof(self->original_core_pattern));
+
+	self->original_core_pattern[ret] = '\0';
+	self->fd_tmpfs_detached = create_detached_tmpfs();
+	ASSERT_GE(self->fd_tmpfs_detached, 0);
+
+	ret = fclose(file);
+	ASSERT_EQ(0, ret);
+}
+
+FIXTURE_TEARDOWN(coredump)
+{
+	const char *reason;
+	FILE *file;
+	int ret, status;
+
+	if (self->pid_coredump_server > 0) {
+		kill(self->pid_coredump_server, SIGTERM);
+		waitpid(self->pid_coredump_server, &status, 0);
+	}
+	unlink("/tmp/coredump.file");
+	unlink("/tmp/coredump.socket");
+
+	file = fopen("/proc/sys/kernel/core_pattern", "w");
+	if (!file) {
+		reason = "Unable to open core_pattern";
+		goto fail;
+	}
+
+	ret = fprintf(file, "%s", self->original_core_pattern);
+	if (ret < 0) {
+		reason = "Unable to write to core_pattern";
+		goto fail;
+	}
+
+	ret = fclose(file);
+	if (ret) {
+		reason = "Unable to close core_pattern";
+		goto fail;
+	}
+
+	if (self->fd_tmpfs_detached >= 0) {
+		ret = close(self->fd_tmpfs_detached);
+		if (ret < 0) {
+			reason = "Unable to close detached tmpfs";
+			goto fail;
+		}
+		self->fd_tmpfs_detached = -1;
+	}
+
+	return;
+fail:
+	/* This should never happen */
+	fprintf(stderr, "Failed to cleanup coredump test: %s\n", reason);
+}
+
+TEST_F(coredump, socket_request_kernel)
+{
+	int pidfd, ret, status;
+	pid_t pid, pid_coredump_server;
+	struct stat st;
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	ASSERT_EQ(ret, 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		struct coredump_req req = {};
+		int fd_server = -1, fd_coredump = -1, fd_core_file = -1, fd_peer_pidfd = -1;
+		int exit_code = EXIT_FAILURE;
+
+		close(ipc_sockets[0]);
+
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0) {
+			fprintf(stderr, "socket_request_kernel: create_and_listen_unix_socket failed: %m\n");
+			goto out;
+		}
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+			fprintf(stderr, "socket_request_kernel: write_nointr to ipc socket failed: %m\n");
+			goto out;
+		}
+
+		close(ipc_sockets[1]);
+
+		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+		if (fd_coredump < 0) {
+			fprintf(stderr, "socket_request_kernel: accept4 failed: %m\n");
+			goto out;
+		}
+
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0) {
+			fprintf(stderr, "socket_request_kernel: get_peer_pidfd failed\n");
+			goto out;
+		}
+
+		if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+			fprintf(stderr, "socket_request_kernel: get_pidfd_info failed\n");
+			goto out;
+		}
+
+		if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+			fprintf(stderr, "socket_request_kernel: PIDFD_INFO_COREDUMP not set in mask\n");
+			goto out;
+		}
+
+		if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+			fprintf(stderr, "socket_request_kernel: PIDFD_COREDUMPED not set in coredump_mask\n");
+			goto out;
+		}
+
+		fd_core_file = creat("/tmp/coredump.file", 0644);
+		if (fd_core_file < 0) {
+			fprintf(stderr, "socket_request_kernel: creat coredump file failed: %m\n");
+			goto out;
+		}
+
+		if (!read_coredump_req(fd_coredump, &req)) {
+			fprintf(stderr, "socket_request_kernel: read_coredump_req failed\n");
+			goto out;
+		}
+
+		if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+					COREDUMP_KERNEL | COREDUMP_USERSPACE |
+					COREDUMP_REJECT | COREDUMP_WAIT)) {
+			fprintf(stderr, "socket_request_kernel: check_coredump_req failed\n");
+			goto out;
+		}
+
+		if (!send_coredump_ack(fd_coredump, &req,
+				       COREDUMP_KERNEL | COREDUMP_WAIT, 0)) {
+			fprintf(stderr, "socket_request_kernel: send_coredump_ack failed\n");
+			goto out;
+		}
+
+		if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK)) {
+			fprintf(stderr, "socket_request_kernel: read_marker COREDUMP_MARK_REQACK failed\n");
+			goto out;
+		}
+
+		for (;;) {
+			char buffer[4096];
+			ssize_t bytes_read, bytes_write;
+
+			bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+			if (bytes_read < 0) {
+				fprintf(stderr, "socket_request_kernel: read from coredump socket failed: %m\n");
+				goto out;
+			}
+
+			if (bytes_read == 0)
+				break;
+
+			bytes_write = write(fd_core_file, buffer, bytes_read);
+			if (bytes_read != bytes_write) {
+				if (bytes_write < 0 && errno == ENOSPC)
+					continue;
+				fprintf(stderr, "socket_request_kernel: write to core file failed (read=%zd, write=%zd): %m\n",
+					bytes_read, bytes_write);
+				goto out;
+			}
+		}
+
+		exit_code = EXIT_SUCCESS;
+		fprintf(stderr, "socket_request_kernel: completed successfully\n");
+out:
+		if (fd_core_file >= 0)
+			close(fd_core_file);
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		crashing_child();
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_TRUE(WCOREDUMP(status));
+
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+	ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+	ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+
+	ASSERT_EQ(stat("/tmp/coredump.file", &st), 0);
+	ASSERT_GT(st.st_size, 0);
+	system("file /tmp/coredump.file");
+}
+
+TEST_F(coredump, socket_request_userspace)
+{
+	int pidfd, ret, status;
+	pid_t pid, pid_coredump_server;
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	ASSERT_EQ(ret, 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		struct coredump_req req = {};
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+		int exit_code = EXIT_FAILURE;
+
+		close(ipc_sockets[0]);
+
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0) {
+			fprintf(stderr, "socket_request_userspace: create_and_listen_unix_socket failed: %m\n");
+			goto out;
+		}
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+			fprintf(stderr, "socket_request_userspace: write_nointr to ipc socket failed: %m\n");
+			goto out;
+		}
+
+		close(ipc_sockets[1]);
+
+		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+		if (fd_coredump < 0) {
+			fprintf(stderr, "socket_request_userspace: accept4 failed: %m\n");
+			goto out;
+		}
+
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0) {
+			fprintf(stderr, "socket_request_userspace: get_peer_pidfd failed\n");
+			goto out;
+		}
+
+		if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+			fprintf(stderr, "socket_request_userspace: get_pidfd_info failed\n");
+			goto out;
+		}
+
+		if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+			fprintf(stderr, "socket_request_userspace: PIDFD_INFO_COREDUMP not set in mask\n");
+			goto out;
+		}
+
+		if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+			fprintf(stderr, "socket_request_userspace: PIDFD_COREDUMPED not set in coredump_mask\n");
+			goto out;
+		}
+
+		if (!read_coredump_req(fd_coredump, &req)) {
+			fprintf(stderr, "socket_request_userspace: read_coredump_req failed\n");
+			goto out;
+		}
+
+		if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+					COREDUMP_KERNEL | COREDUMP_USERSPACE |
+					COREDUMP_REJECT | COREDUMP_WAIT)) {
+			fprintf(stderr, "socket_request_userspace: check_coredump_req failed\n");
+			goto out;
+		}
+
+		if (!send_coredump_ack(fd_coredump, &req,
+				       COREDUMP_USERSPACE | COREDUMP_WAIT, 0)) {
+			fprintf(stderr, "socket_request_userspace: send_coredump_ack failed\n");
+			goto out;
+		}
+
+		if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK)) {
+			fprintf(stderr, "socket_request_userspace: read_marker COREDUMP_MARK_REQACK failed\n");
+			goto out;
+		}
+
+		for (;;) {
+			char buffer[4096];
+			ssize_t bytes_read;
+
+			bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+			if (bytes_read > 0) {
+				fprintf(stderr, "socket_request_userspace: unexpected data received (expected no coredump data)\n");
+				goto out;
+			}
+
+			if (bytes_read < 0) {
+				fprintf(stderr, "socket_request_userspace: read from coredump socket failed: %m\n");
+				goto out;
+			}
+
+			if (bytes_read == 0)
+				break;
+		}
+
+		exit_code = EXIT_SUCCESS;
+		fprintf(stderr, "socket_request_userspace: completed successfully\n");
+out:
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		crashing_child();
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_TRUE(WCOREDUMP(status));
+
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+	ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+	ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_F(coredump, socket_request_reject)
+{
+	int pidfd, ret, status;
+	pid_t pid, pid_coredump_server;
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	ASSERT_EQ(ret, 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		struct coredump_req req = {};
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+		int exit_code = EXIT_FAILURE;
+
+		close(ipc_sockets[0]);
+
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0) {
+			fprintf(stderr, "socket_request_reject: create_and_listen_unix_socket failed: %m\n");
+			goto out;
+		}
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+			fprintf(stderr, "socket_request_reject: write_nointr to ipc socket failed: %m\n");
+			goto out;
+		}
+
+		close(ipc_sockets[1]);
+
+		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+		if (fd_coredump < 0) {
+			fprintf(stderr, "socket_request_reject: accept4 failed: %m\n");
+			goto out;
+		}
+
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0) {
+			fprintf(stderr, "socket_request_reject: get_peer_pidfd failed\n");
+			goto out;
+		}
+
+		if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+			fprintf(stderr, "socket_request_reject: get_pidfd_info failed\n");
+			goto out;
+		}
+
+		if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+			fprintf(stderr, "socket_request_reject: PIDFD_INFO_COREDUMP not set in mask\n");
+			goto out;
+		}
+
+		if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+			fprintf(stderr, "socket_request_reject: PIDFD_COREDUMPED not set in coredump_mask\n");
+			goto out;
+		}
+
+		if (!read_coredump_req(fd_coredump, &req)) {
+			fprintf(stderr, "socket_request_reject: read_coredump_req failed\n");
+			goto out;
+		}
+
+		if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+					COREDUMP_KERNEL | COREDUMP_USERSPACE |
+					COREDUMP_REJECT | COREDUMP_WAIT)) {
+			fprintf(stderr, "socket_request_reject: check_coredump_req failed\n");
+			goto out;
+		}
+
+		if (!send_coredump_ack(fd_coredump, &req,
+				       COREDUMP_REJECT | COREDUMP_WAIT, 0)) {
+			fprintf(stderr, "socket_request_reject: send_coredump_ack failed\n");
+			goto out;
+		}
+
+		if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK)) {
+			fprintf(stderr, "socket_request_reject: read_marker COREDUMP_MARK_REQACK failed\n");
+			goto out;
+		}
+
+		for (;;) {
+			char buffer[4096];
+			ssize_t bytes_read;
+
+			bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+			if (bytes_read > 0) {
+				fprintf(stderr, "socket_request_reject: unexpected data received (expected no coredump data for REJECT)\n");
+				goto out;
+			}
+
+			if (bytes_read < 0) {
+				fprintf(stderr, "socket_request_reject: read from coredump socket failed: %m\n");
+				goto out;
+			}
+
+			if (bytes_read == 0)
+				break;
+		}
+
+		exit_code = EXIT_SUCCESS;
+		fprintf(stderr, "socket_request_reject: completed successfully\n");
+out:
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		crashing_child();
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_FALSE(WCOREDUMP(status));
+
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+	ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+	ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_F(coredump, socket_request_invalid_flag_combination)
+{
+	int pidfd, ret, status;
+	pid_t pid, pid_coredump_server;
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	ASSERT_EQ(ret, 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		struct coredump_req req = {};
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+		int exit_code = EXIT_FAILURE;
+
+		close(ipc_sockets[0]);
+
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0) {
+			fprintf(stderr, "socket_request_invalid_flag_combination: create_and_listen_unix_socket failed: %m\n");
+			goto out;
+		}
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+			fprintf(stderr, "socket_request_invalid_flag_combination: write_nointr to ipc socket failed: %m\n");
+			goto out;
+		}
+
+		close(ipc_sockets[1]);
+
+		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+		if (fd_coredump < 0) {
+			fprintf(stderr, "socket_request_invalid_flag_combination: accept4 failed: %m\n");
+			goto out;
+		}
+
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0) {
+			fprintf(stderr, "socket_request_invalid_flag_combination: get_peer_pidfd failed\n");
+			goto out;
+		}
+
+		if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+			fprintf(stderr, "socket_request_invalid_flag_combination: get_pidfd_info failed\n");
+			goto out;
+		}
+
+		if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+			fprintf(stderr, "socket_request_invalid_flag_combination: PIDFD_INFO_COREDUMP not set in mask\n");
+			goto out;
+		}
+
+		if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+			fprintf(stderr, "socket_request_invalid_flag_combination: PIDFD_COREDUMPED not set in coredump_mask\n");
+			goto out;
+		}
+
+		if (!read_coredump_req(fd_coredump, &req)) {
+			fprintf(stderr, "socket_request_invalid_flag_combination: read_coredump_req failed\n");
+			goto out;
+		}
+
+		if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+					COREDUMP_KERNEL | COREDUMP_USERSPACE |
+					COREDUMP_REJECT | COREDUMP_WAIT)) {
+			fprintf(stderr, "socket_request_invalid_flag_combination: check_coredump_req failed\n");
+			goto out;
+		}
+
+		if (!send_coredump_ack(fd_coredump, &req,
+				       COREDUMP_KERNEL | COREDUMP_REJECT | COREDUMP_WAIT, 0)) {
+			fprintf(stderr, "socket_request_invalid_flag_combination: send_coredump_ack failed\n");
+			goto out;
+		}
+
+		if (!read_marker(fd_coredump, COREDUMP_MARK_CONFLICTING)) {
+			fprintf(stderr, "socket_request_invalid_flag_combination: read_marker COREDUMP_MARK_CONFLICTING failed\n");
+			goto out;
+		}
+
+		exit_code = EXIT_SUCCESS;
+		fprintf(stderr, "socket_request_invalid_flag_combination: completed successfully\n");
+out:
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		crashing_child();
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_FALSE(WCOREDUMP(status));
+
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+	ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+	ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_F(coredump, socket_request_unknown_flag)
+{
+	int pidfd, ret, status;
+	pid_t pid, pid_coredump_server;
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	ASSERT_EQ(ret, 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		struct coredump_req req = {};
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+		int exit_code = EXIT_FAILURE;
+
+		close(ipc_sockets[0]);
+
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0) {
+			fprintf(stderr, "socket_request_unknown_flag: create_and_listen_unix_socket failed: %m\n");
+			goto out;
+		}
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+			fprintf(stderr, "socket_request_unknown_flag: write_nointr to ipc socket failed: %m\n");
+			goto out;
+		}
+
+		close(ipc_sockets[1]);
+
+		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+		if (fd_coredump < 0) {
+			fprintf(stderr, "socket_request_unknown_flag: accept4 failed: %m\n");
+			goto out;
+		}
+
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0) {
+			fprintf(stderr, "socket_request_unknown_flag: get_peer_pidfd failed\n");
+			goto out;
+		}
+
+		if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+			fprintf(stderr, "socket_request_unknown_flag: get_pidfd_info failed\n");
+			goto out;
+		}
+
+		if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+			fprintf(stderr, "socket_request_unknown_flag: PIDFD_INFO_COREDUMP not set in mask\n");
+			goto out;
+		}
+
+		if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+			fprintf(stderr, "socket_request_unknown_flag: PIDFD_COREDUMPED not set in coredump_mask\n");
+			goto out;
+		}
+
+		if (!read_coredump_req(fd_coredump, &req)) {
+			fprintf(stderr, "socket_request_unknown_flag: read_coredump_req failed\n");
+			goto out;
+		}
+
+		if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+					COREDUMP_KERNEL | COREDUMP_USERSPACE |
+					COREDUMP_REJECT | COREDUMP_WAIT)) {
+			fprintf(stderr, "socket_request_unknown_flag: check_coredump_req failed\n");
+			goto out;
+		}
+
+		if (!send_coredump_ack(fd_coredump, &req, (1ULL << 63), 0)) {
+			fprintf(stderr, "socket_request_unknown_flag: send_coredump_ack failed\n");
+			goto out;
+		}
+
+		if (!read_marker(fd_coredump, COREDUMP_MARK_UNSUPPORTED)) {
+			fprintf(stderr, "socket_request_unknown_flag: read_marker COREDUMP_MARK_UNSUPPORTED failed\n");
+			goto out;
+		}
+
+		exit_code = EXIT_SUCCESS;
+		fprintf(stderr, "socket_request_unknown_flag: completed successfully\n");
+out:
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		crashing_child();
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_FALSE(WCOREDUMP(status));
+
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+	ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+	ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_F(coredump, socket_request_invalid_size_small)
+{
+	int pidfd, ret, status;
+	pid_t pid, pid_coredump_server;
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	ASSERT_EQ(ret, 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		struct coredump_req req = {};
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+		int exit_code = EXIT_FAILURE;
+
+		close(ipc_sockets[0]);
+
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0) {
+			fprintf(stderr, "socket_request_invalid_size_small: create_and_listen_unix_socket failed: %m\n");
+			goto out;
+		}
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+			fprintf(stderr, "socket_request_invalid_size_small: write_nointr to ipc socket failed: %m\n");
+			goto out;
+		}
+
+		close(ipc_sockets[1]);
+
+		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+		if (fd_coredump < 0) {
+			fprintf(stderr, "socket_request_invalid_size_small: accept4 failed: %m\n");
+			goto out;
+		}
+
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0) {
+			fprintf(stderr, "socket_request_invalid_size_small: get_peer_pidfd failed\n");
+			goto out;
+		}
+
+		if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+			fprintf(stderr, "socket_request_invalid_size_small: get_pidfd_info failed\n");
+			goto out;
+		}
+
+		if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+			fprintf(stderr, "socket_request_invalid_size_small: PIDFD_INFO_COREDUMP not set in mask\n");
+			goto out;
+		}
+
+		if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+			fprintf(stderr, "socket_request_invalid_size_small: PIDFD_COREDUMPED not set in coredump_mask\n");
+			goto out;
+		}
+
+		if (!read_coredump_req(fd_coredump, &req)) {
+			fprintf(stderr, "socket_request_invalid_size_small: read_coredump_req failed\n");
+			goto out;
+		}
+
+		if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+					COREDUMP_KERNEL | COREDUMP_USERSPACE |
+					COREDUMP_REJECT | COREDUMP_WAIT)) {
+			fprintf(stderr, "socket_request_invalid_size_small: check_coredump_req failed\n");
+			goto out;
+		}
+
+		if (!send_coredump_ack(fd_coredump, &req,
+				       COREDUMP_REJECT | COREDUMP_WAIT,
+				       COREDUMP_ACK_SIZE_VER0 / 2)) {
+			fprintf(stderr, "socket_request_invalid_size_small: send_coredump_ack failed\n");
+			goto out;
+		}
+
+		if (!read_marker(fd_coredump, COREDUMP_MARK_MINSIZE)) {
+			fprintf(stderr, "socket_request_invalid_size_small: read_marker COREDUMP_MARK_MINSIZE failed\n");
+			goto out;
+		}
+
+		exit_code = EXIT_SUCCESS;
+		fprintf(stderr, "socket_request_invalid_size_small: completed successfully\n");
+out:
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		crashing_child();
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_FALSE(WCOREDUMP(status));
+
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+	ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+	ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_F(coredump, socket_request_invalid_size_large)
+{
+	int pidfd, ret, status;
+	pid_t pid, pid_coredump_server;
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	ASSERT_EQ(ret, 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		struct coredump_req req = {};
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+		int exit_code = EXIT_FAILURE;
+
+		close(ipc_sockets[0]);
+
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0) {
+			fprintf(stderr, "socket_request_invalid_size_large: create_and_listen_unix_socket failed: %m\n");
+			goto out;
+		}
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+			fprintf(stderr, "socket_request_invalid_size_large: write_nointr to ipc socket failed: %m\n");
+			goto out;
+		}
+
+		close(ipc_sockets[1]);
+
+		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+		if (fd_coredump < 0) {
+			fprintf(stderr, "socket_request_invalid_size_large: accept4 failed: %m\n");
+			goto out;
+		}
+
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0) {
+			fprintf(stderr, "socket_request_invalid_size_large: get_peer_pidfd failed\n");
+			goto out;
+		}
+
+		if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+			fprintf(stderr, "socket_request_invalid_size_large: get_pidfd_info failed\n");
+			goto out;
+		}
+
+		if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+			fprintf(stderr, "socket_request_invalid_size_large: PIDFD_INFO_COREDUMP not set in mask\n");
+			goto out;
+		}
+
+		if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+			fprintf(stderr, "socket_request_invalid_size_large: PIDFD_COREDUMPED not set in coredump_mask\n");
+			goto out;
+		}
+
+		if (!read_coredump_req(fd_coredump, &req)) {
+			fprintf(stderr, "socket_request_invalid_size_large: read_coredump_req failed\n");
+			goto out;
+		}
+
+		if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+					COREDUMP_KERNEL | COREDUMP_USERSPACE |
+					COREDUMP_REJECT | COREDUMP_WAIT)) {
+			fprintf(stderr, "socket_request_invalid_size_large: check_coredump_req failed\n");
+			goto out;
+		}
+
+		if (!send_coredump_ack(fd_coredump, &req,
+				       COREDUMP_REJECT | COREDUMP_WAIT,
+				       COREDUMP_ACK_SIZE_VER0 + PAGE_SIZE)) {
+			fprintf(stderr, "socket_request_invalid_size_large: send_coredump_ack failed\n");
+			goto out;
+		}
+
+		if (!read_marker(fd_coredump, COREDUMP_MARK_MAXSIZE)) {
+			fprintf(stderr, "socket_request_invalid_size_large: read_marker COREDUMP_MARK_MAXSIZE failed\n");
+			goto out;
+		}
+
+		exit_code = EXIT_SUCCESS;
+		fprintf(stderr, "socket_request_invalid_size_large: completed successfully\n");
+out:
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		crashing_child();
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_FALSE(WCOREDUMP(status));
+
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+	ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+	ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+/*
+ * Test: PIDFD_INFO_COREDUMP_SIGNAL via socket coredump with SIGSEGV
+ *
+ * Verify that when using socket-based coredump protocol,
+ * the coredump_signal field is correctly exposed as SIGSEGV.
+ */
+TEST_F(coredump, socket_coredump_signal_sigsegv)
+{
+	int pidfd, ret, status;
+	pid_t pid, pid_coredump_server;
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	ASSERT_EQ(ret, 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		struct coredump_req req = {};
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+		int exit_code = EXIT_FAILURE;
+
+		close(ipc_sockets[0]);
+
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: create_and_listen_unix_socket failed: %m\n");
+			goto out;
+		}
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: write_nointr to ipc socket failed: %m\n");
+			goto out;
+		}
+
+		close(ipc_sockets[1]);
+
+		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+		if (fd_coredump < 0) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: accept4 failed: %m\n");
+			goto out;
+		}
+
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: get_peer_pidfd failed\n");
+			goto out;
+		}
+
+		if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: get_pidfd_info failed\n");
+			goto out;
+		}
+
+		if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: PIDFD_INFO_COREDUMP not set in mask\n");
+			goto out;
+		}
+
+		if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: PIDFD_COREDUMPED not set in coredump_mask\n");
+			goto out;
+		}
+
+		/* Verify coredump_signal is available and correct */
+		if (!(info.mask & PIDFD_INFO_COREDUMP_SIGNAL)) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: PIDFD_INFO_COREDUMP_SIGNAL not set in mask\n");
+			goto out;
+		}
+
+		if (info.coredump_signal != SIGSEGV) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: coredump_signal=%d, expected SIGSEGV=%d\n",
+				info.coredump_signal, SIGSEGV);
+			goto out;
+		}
+
+		if (!read_coredump_req(fd_coredump, &req)) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: read_coredump_req failed\n");
+			goto out;
+		}
+
+		if (!send_coredump_ack(fd_coredump, &req,
+				       COREDUMP_REJECT | COREDUMP_WAIT, 0)) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: send_coredump_ack failed\n");
+			goto out;
+		}
+
+		if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK)) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: read_marker COREDUMP_MARK_REQACK failed\n");
+			goto out;
+		}
+
+		exit_code = EXIT_SUCCESS;
+		fprintf(stderr, "socket_coredump_signal_sigsegv: completed successfully\n");
+out:
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		crashing_child();
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_EQ(WTERMSIG(status), SIGSEGV);
+
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+	ASSERT_TRUE(!!(info.mask & PIDFD_INFO_COREDUMP));
+	ASSERT_TRUE(!!(info.mask & PIDFD_INFO_COREDUMP_SIGNAL));
+	ASSERT_EQ(info.coredump_signal, SIGSEGV);
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+/*
+ * Test: PIDFD_INFO_COREDUMP_SIGNAL via socket coredump with SIGABRT
+ *
+ * Verify that when using socket-based coredump protocol,
+ * the coredump_signal field is correctly exposed as SIGABRT.
+ */
+TEST_F(coredump, socket_coredump_signal_sigabrt)
+{
+	int pidfd, ret, status;
+	pid_t pid, pid_coredump_server;
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	ASSERT_EQ(ret, 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		struct coredump_req req = {};
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+		int exit_code = EXIT_FAILURE;
+
+		close(ipc_sockets[0]);
+
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: create_and_listen_unix_socket failed: %m\n");
+			goto out;
+		}
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: write_nointr to ipc socket failed: %m\n");
+			goto out;
+		}
+
+		close(ipc_sockets[1]);
+
+		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+		if (fd_coredump < 0) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: accept4 failed: %m\n");
+			goto out;
+		}
+
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: get_peer_pidfd failed\n");
+			goto out;
+		}
+
+		if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: get_pidfd_info failed\n");
+			goto out;
+		}
+
+		if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: PIDFD_INFO_COREDUMP not set in mask\n");
+			goto out;
+		}
+
+		if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: PIDFD_COREDUMPED not set in coredump_mask\n");
+			goto out;
+		}
+
+		/* Verify coredump_signal is available and correct */
+		if (!(info.mask & PIDFD_INFO_COREDUMP_SIGNAL)) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: PIDFD_INFO_COREDUMP_SIGNAL not set in mask\n");
+			goto out;
+		}
+
+		if (info.coredump_signal != SIGABRT) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: coredump_signal=%d, expected SIGABRT=%d\n",
+				info.coredump_signal, SIGABRT);
+			goto out;
+		}
+
+		if (!read_coredump_req(fd_coredump, &req)) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: read_coredump_req failed\n");
+			goto out;
+		}
+
+		if (!send_coredump_ack(fd_coredump, &req,
+				       COREDUMP_REJECT | COREDUMP_WAIT, 0)) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: send_coredump_ack failed\n");
+			goto out;
+		}
+
+		if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK)) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: read_marker COREDUMP_MARK_REQACK failed\n");
+			goto out;
+		}
+
+		exit_code = EXIT_SUCCESS;
+		fprintf(stderr, "socket_coredump_signal_sigabrt: completed successfully\n");
+out:
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		abort();
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_EQ(WTERMSIG(status), SIGABRT);
+
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+	ASSERT_TRUE(!!(info.mask & PIDFD_INFO_COREDUMP));
+	ASSERT_TRUE(!!(info.mask & PIDFD_INFO_COREDUMP_SIGNAL));
+	ASSERT_EQ(info.coredump_signal, SIGABRT);
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_F_TIMEOUT(coredump, socket_multiple_crashing_coredumps, 500)
+{
+	int pidfd[NUM_CRASHING_COREDUMPS], status[NUM_CRASHING_COREDUMPS];
+	pid_t pid[NUM_CRASHING_COREDUMPS], pid_coredump_server;
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+
+	ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets), 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1, fd_core_file = -1;
+		int exit_code = EXIT_FAILURE;
+		struct coredump_req req = {};
+
+		close(ipc_sockets[0]);
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0) {
+			fprintf(stderr, "Failed to create and listen on unix socket\n");
+			goto out;
+		}
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+			fprintf(stderr, "Failed to notify parent via ipc socket\n");
+			goto out;
+		}
+		close(ipc_sockets[1]);
+
+		for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
+			fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+			if (fd_coredump < 0) {
+				fprintf(stderr, "accept4 failed: %m\n");
+				goto out;
+			}
+
+			fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+			if (fd_peer_pidfd < 0) {
+				fprintf(stderr, "get_peer_pidfd failed for fd %d: %m\n", fd_coredump);
+				goto out;
+			}
+
+			if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+				fprintf(stderr, "get_pidfd_info failed for fd %d\n", fd_peer_pidfd);
+				goto out;
+			}
+
+			if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+				fprintf(stderr, "pidfd info missing PIDFD_INFO_COREDUMP for fd %d\n", fd_peer_pidfd);
+				goto out;
+			}
+			if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+				fprintf(stderr, "pidfd info missing PIDFD_COREDUMPED for fd %d\n", fd_peer_pidfd);
+				goto out;
+			}
+
+			if (!read_coredump_req(fd_coredump, &req)) {
+				fprintf(stderr, "read_coredump_req failed for fd %d\n", fd_coredump);
+				goto out;
+			}
+
+			if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+						COREDUMP_KERNEL | COREDUMP_USERSPACE |
+						COREDUMP_REJECT | COREDUMP_WAIT)) {
+				fprintf(stderr, "check_coredump_req failed for fd %d\n", fd_coredump);
+				goto out;
+			}
+
+			if (!send_coredump_ack(fd_coredump, &req,
+					       COREDUMP_KERNEL | COREDUMP_WAIT, 0)) {
+				fprintf(stderr, "send_coredump_ack failed for fd %d\n", fd_coredump);
+				goto out;
+			}
+
+			if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK)) {
+				fprintf(stderr, "read_marker failed for fd %d\n", fd_coredump);
+				goto out;
+			}
+
+			fd_core_file = open_coredump_tmpfile(self->fd_tmpfs_detached);
+			if (fd_core_file < 0) {
+				fprintf(stderr, "%m - open_coredump_tmpfile failed for fd %d\n", fd_coredump);
+				goto out;
+			}
+
+			for (;;) {
+				char buffer[4096];
+				ssize_t bytes_read, bytes_write;
+
+				bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+				if (bytes_read < 0) {
+					fprintf(stderr, "read failed for fd %d: %m\n", fd_coredump);
+					goto out;
+				}
+
+				if (bytes_read == 0)
+					break;
+
+				bytes_write = write(fd_core_file, buffer, bytes_read);
+				if (bytes_read != bytes_write) {
+					if (bytes_write < 0 && errno == ENOSPC)
+						continue;
+					fprintf(stderr, "write failed for fd %d: %m\n", fd_core_file);
+					goto out;
+				}
+			}
+
+			close(fd_core_file);
+			close(fd_peer_pidfd);
+			close(fd_coredump);
+			fd_peer_pidfd = -1;
+			fd_coredump = -1;
+		}
+
+		exit_code = EXIT_SUCCESS;
+out:
+		if (fd_core_file >= 0)
+			close(fd_core_file);
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
+		pid[i] = fork();
+		ASSERT_GE(pid[i], 0);
+		if (pid[i] == 0)
+			crashing_child();
+		pidfd[i] = sys_pidfd_open(pid[i], 0);
+		ASSERT_GE(pidfd[i], 0);
+	}
+
+	for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
+		waitpid(pid[i], &status[i], 0);
+		ASSERT_TRUE(WIFSIGNALED(status[i]));
+		ASSERT_TRUE(WCOREDUMP(status[i]));
+	}
+
+	for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
+		info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP;
+		ASSERT_EQ(ioctl(pidfd[i], PIDFD_GET_INFO, &info), 0);
+		ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+		ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+	}
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_F_TIMEOUT(coredump, socket_multiple_crashing_coredumps_epoll_workers, 500)
+{
+	int pidfd[NUM_CRASHING_COREDUMPS], status[NUM_CRASHING_COREDUMPS];
+	pid_t pid[NUM_CRASHING_COREDUMPS], pid_coredump_server, worker_pids[NUM_CRASHING_COREDUMPS];
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@@/tmp/coredump.socket"));
+	ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets), 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		int fd_server = -1, exit_code = EXIT_FAILURE, n_conns = 0;
+		fd_server = -1;
+		exit_code = EXIT_FAILURE;
+		n_conns = 0;
+		close(ipc_sockets[0]);
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0) {
+			fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: create_and_listen_unix_socket failed: %m\n");
+			goto out;
+		}
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+			fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: write_nointr to ipc socket failed: %m\n");
+			goto out;
+		}
+		close(ipc_sockets[1]);
+
+		while (n_conns < NUM_CRASHING_COREDUMPS) {
+			int fd_coredump = -1, fd_peer_pidfd = -1, fd_core_file = -1;
+			struct coredump_req req = {};
+			fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+			if (fd_coredump < 0) {
+				if (errno == EAGAIN || errno == EWOULDBLOCK)
+					continue;
+				fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: accept4 failed: %m\n");
+				goto out;
+			}
+			fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+			if (fd_peer_pidfd < 0) {
+				fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: get_peer_pidfd failed\n");
+				goto out;
+			}
+			if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+				fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: get_pidfd_info failed\n");
+				goto out;
+			}
+			if (!(info.mask & PIDFD_INFO_COREDUMP) || !(info.coredump_mask & PIDFD_COREDUMPED)) {
+				fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: missing PIDFD_INFO_COREDUMP or PIDFD_COREDUMPED\n");
+				goto out;
+			}
+			if (!read_coredump_req(fd_coredump, &req)) {
+				fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: read_coredump_req failed\n");
+				goto out;
+			}
+			if (!check_coredump_req(&req, COREDUMP_ACK_SIZE_VER0,
+						COREDUMP_KERNEL | COREDUMP_USERSPACE |
+						COREDUMP_REJECT | COREDUMP_WAIT)) {
+				fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: check_coredump_req failed\n");
+				goto out;
+			}
+			if (!send_coredump_ack(fd_coredump, &req, COREDUMP_KERNEL | COREDUMP_WAIT, 0)) {
+				fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: send_coredump_ack failed\n");
+				goto out;
+			}
+			if (!read_marker(fd_coredump, COREDUMP_MARK_REQACK)) {
+				fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: read_marker failed\n");
+				goto out;
+			}
+			fd_core_file = open_coredump_tmpfile(self->fd_tmpfs_detached);
+			if (fd_core_file < 0) {
+				fprintf(stderr, "socket_multiple_crashing_coredumps_epoll_workers: open_coredump_tmpfile failed: %m\n");
+				goto out;
+			}
+			pid_t worker = fork();
+			if (worker == 0) {
+				close(fd_server);
+				process_coredump_worker(fd_coredump, fd_peer_pidfd, fd_core_file);
+			}
+			worker_pids[n_conns] = worker;
+			if (fd_coredump >= 0)
+				close(fd_coredump);
+			if (fd_peer_pidfd >= 0)
+				close(fd_peer_pidfd);
+			if (fd_core_file >= 0)
+				close(fd_core_file);
+			n_conns++;
+		}
+		exit_code = EXIT_SUCCESS;
+out:
+		if (fd_server >= 0)
+			close(fd_server);
+
+		// Reap all worker processes
+		for (int i = 0; i < n_conns; i++) {
+			int wstatus;
+			if (waitpid(worker_pids[i], &wstatus, 0) < 0) {
+				fprintf(stderr, "Failed to wait for worker %d: %m\n", worker_pids[i]);
+			} else if (WIFEXITED(wstatus) && WEXITSTATUS(wstatus) != EXIT_SUCCESS) {
+				fprintf(stderr, "Worker %d exited with error code %d\n", worker_pids[i], WEXITSTATUS(wstatus));
+				exit_code = EXIT_FAILURE;
+			}
+		}
+
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
+		pid[i] = fork();
+		ASSERT_GE(pid[i], 0);
+		if (pid[i] == 0)
+			crashing_child();
+		pidfd[i] = sys_pidfd_open(pid[i], 0);
+		ASSERT_GE(pidfd[i], 0);
+	}
+
+	for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
+		ASSERT_GE(waitpid(pid[i], &status[i], 0), 0);
+		ASSERT_TRUE(WIFSIGNALED(status[i]));
+		ASSERT_TRUE(WCOREDUMP(status[i]));
+	}
+
+	for (int i = 0; i < NUM_CRASHING_COREDUMPS; i++) {
+		info.mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP;
+		ASSERT_EQ(ioctl(pidfd[i], PIDFD_GET_INFO, &info), 0);
+		ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+		ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+	}
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/coredump/coredump_socket_test.c b/tools/testing/selftests/coredump/coredump_socket_test.c
new file mode 100644
index 000000000000..7e26d4a6a15d
--- /dev/null
+++ b/tools/testing/selftests/coredump/coredump_socket_test.c
@@ -0,0 +1,742 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <sys/stat.h>
+#include <sys/epoll.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+
+#include "coredump_test.h"
+
+FIXTURE_SETUP(coredump)
+{
+	FILE *file;
+	int ret;
+
+	self->pid_coredump_server = -ESRCH;
+	self->fd_tmpfs_detached = -1;
+	file = fopen("/proc/sys/kernel/core_pattern", "r");
+	ASSERT_NE(NULL, file);
+
+	ret = fread(self->original_core_pattern, 1, sizeof(self->original_core_pattern), file);
+	ASSERT_TRUE(ret || feof(file));
+	ASSERT_LT(ret, sizeof(self->original_core_pattern));
+
+	self->original_core_pattern[ret] = '\0';
+	self->fd_tmpfs_detached = create_detached_tmpfs();
+	ASSERT_GE(self->fd_tmpfs_detached, 0);
+
+	ret = fclose(file);
+	ASSERT_EQ(0, ret);
+}
+
+FIXTURE_TEARDOWN(coredump)
+{
+	const char *reason;
+	FILE *file;
+	int ret, status;
+
+	if (self->pid_coredump_server > 0) {
+		kill(self->pid_coredump_server, SIGTERM);
+		waitpid(self->pid_coredump_server, &status, 0);
+	}
+	unlink("/tmp/coredump.file");
+	unlink("/tmp/coredump.socket");
+
+	file = fopen("/proc/sys/kernel/core_pattern", "w");
+	if (!file) {
+		reason = "Unable to open core_pattern";
+		goto fail;
+	}
+
+	ret = fprintf(file, "%s", self->original_core_pattern);
+	if (ret < 0) {
+		reason = "Unable to write to core_pattern";
+		goto fail;
+	}
+
+	ret = fclose(file);
+	if (ret) {
+		reason = "Unable to close core_pattern";
+		goto fail;
+	}
+
+	if (self->fd_tmpfs_detached >= 0) {
+		ret = close(self->fd_tmpfs_detached);
+		if (ret < 0) {
+			reason = "Unable to close detached tmpfs";
+			goto fail;
+		}
+		self->fd_tmpfs_detached = -1;
+	}
+
+	return;
+fail:
+	/* This should never happen */
+	fprintf(stderr, "Failed to cleanup coredump test: %s\n", reason);
+}
+
+TEST_F(coredump, socket)
+{
+	int pidfd, ret, status;
+	pid_t pid, pid_coredump_server;
+	struct stat st;
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket"));
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	ASSERT_EQ(ret, 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1, fd_core_file = -1;
+		int exit_code = EXIT_FAILURE;
+
+		close(ipc_sockets[0]);
+
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0) {
+			fprintf(stderr, "socket test: create_and_listen_unix_socket failed: %m\n");
+			goto out;
+		}
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+			fprintf(stderr, "socket test: write_nointr to ipc socket failed: %m\n");
+			goto out;
+		}
+
+		close(ipc_sockets[1]);
+
+		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+		if (fd_coredump < 0) {
+			fprintf(stderr, "socket test: accept4 failed: %m\n");
+			goto out;
+		}
+
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0) {
+			fprintf(stderr, "socket test: get_peer_pidfd failed\n");
+			goto out;
+		}
+
+		if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+			fprintf(stderr, "socket test: get_pidfd_info failed\n");
+			goto out;
+		}
+
+		if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+			fprintf(stderr, "socket test: PIDFD_INFO_COREDUMP not set in mask\n");
+			goto out;
+		}
+
+		if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+			fprintf(stderr, "socket test: PIDFD_COREDUMPED not set in coredump_mask\n");
+			goto out;
+		}
+
+		fd_core_file = creat("/tmp/coredump.file", 0644);
+		if (fd_core_file < 0) {
+			fprintf(stderr, "socket test: creat coredump file failed: %m\n");
+			goto out;
+		}
+
+		for (;;) {
+			char buffer[4096];
+			ssize_t bytes_read, bytes_write;
+
+			bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+			if (bytes_read < 0) {
+				fprintf(stderr, "socket test: read from coredump socket failed: %m\n");
+				goto out;
+			}
+
+			if (bytes_read == 0)
+				break;
+
+			bytes_write = write(fd_core_file, buffer, bytes_read);
+			if (bytes_read != bytes_write) {
+				if (bytes_write < 0 && errno == ENOSPC)
+					continue;
+				fprintf(stderr, "socket test: write to core file failed (read=%zd, write=%zd): %m\n", bytes_read, bytes_write);
+				goto out;
+			}
+		}
+
+		exit_code = EXIT_SUCCESS;
+		fprintf(stderr, "socket test: completed successfully\n");
+out:
+		if (fd_core_file >= 0)
+			close(fd_core_file);
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		crashing_child();
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_TRUE(WCOREDUMP(status));
+
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+	ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+	ASSERT_GT((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+
+	ASSERT_EQ(stat("/tmp/coredump.file", &st), 0);
+	ASSERT_GT(st.st_size, 0);
+}
+
+TEST_F(coredump, socket_detect_userspace_client)
+{
+	int pidfd, ret, status;
+	pid_t pid, pid_coredump_server;
+	struct stat st;
+	struct pidfd_info info = {
+		.mask = PIDFD_INFO_COREDUMP,
+	};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket"));
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	ASSERT_EQ(ret, 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1;
+		int exit_code = EXIT_FAILURE;
+
+		close(ipc_sockets[0]);
+
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0) {
+			fprintf(stderr, "socket_detect_userspace_client: create_and_listen_unix_socket failed: %m\n");
+			goto out;
+		}
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+			fprintf(stderr, "socket_detect_userspace_client: write_nointr to ipc socket failed: %m\n");
+			goto out;
+		}
+
+		close(ipc_sockets[1]);
+
+		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+		if (fd_coredump < 0) {
+			fprintf(stderr, "socket_detect_userspace_client: accept4 failed: %m\n");
+			goto out;
+		}
+
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0) {
+			fprintf(stderr, "socket_detect_userspace_client: get_peer_pidfd failed\n");
+			goto out;
+		}
+
+		if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+			fprintf(stderr, "socket_detect_userspace_client: get_pidfd_info failed\n");
+			goto out;
+		}
+
+		if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+			fprintf(stderr, "socket_detect_userspace_client: PIDFD_INFO_COREDUMP not set in mask\n");
+			goto out;
+		}
+
+		if (info.coredump_mask & PIDFD_COREDUMPED) {
+			fprintf(stderr, "socket_detect_userspace_client: PIDFD_COREDUMPED incorrectly set (should be userspace client)\n");
+			goto out;
+		}
+
+		exit_code = EXIT_SUCCESS;
+		fprintf(stderr, "socket_detect_userspace_client: completed successfully\n");
+out:
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0) {
+		int fd_socket;
+		ssize_t ret;
+		const struct sockaddr_un coredump_sk = {
+			.sun_family = AF_UNIX,
+			.sun_path = "/tmp/coredump.socket",
+		};
+		size_t coredump_sk_len =
+			offsetof(struct sockaddr_un, sun_path) +
+			sizeof("/tmp/coredump.socket");
+
+		fd_socket = socket(AF_UNIX, SOCK_STREAM, 0);
+		if (fd_socket < 0) {
+			fprintf(stderr, "socket_detect_userspace_client (client): socket failed: %m\n");
+			_exit(EXIT_FAILURE);
+		}
+
+		ret = connect(fd_socket, (const struct sockaddr *)&coredump_sk, coredump_sk_len);
+		if (ret < 0) {
+			fprintf(stderr, "socket_detect_userspace_client (client): connect failed: %m\n");
+			_exit(EXIT_FAILURE);
+		}
+
+		close(fd_socket);
+		pause();
+		fprintf(stderr, "socket_detect_userspace_client (client): completed successfully\n");
+		_exit(EXIT_SUCCESS);
+	}
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+	ASSERT_GT((info.mask & PIDFD_INFO_COREDUMP), 0);
+	ASSERT_EQ((info.coredump_mask & PIDFD_COREDUMPED), 0);
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+
+	ASSERT_EQ(sys_pidfd_send_signal(pidfd, SIGKILL, NULL, 0), 0);
+	ASSERT_EQ(close(pidfd), 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_EQ(WTERMSIG(status), SIGKILL);
+
+	ASSERT_NE(stat("/tmp/coredump.file", &st), 0);
+	ASSERT_EQ(errno, ENOENT);
+}
+
+TEST_F(coredump, socket_enoent)
+{
+	int pidfd, status;
+	pid_t pid;
+
+	ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket"));
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		crashing_child();
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_FALSE(WCOREDUMP(status));
+}
+
+TEST_F(coredump, socket_no_listener)
+{
+	int pidfd, ret, status;
+	pid_t pid, pid_coredump_server;
+	int ipc_sockets[2];
+	char c;
+	const struct sockaddr_un coredump_sk = {
+		.sun_family = AF_UNIX,
+		.sun_path = "/tmp/coredump.socket",
+	};
+	size_t coredump_sk_len = offsetof(struct sockaddr_un, sun_path) +
+				 sizeof("/tmp/coredump.socket");
+
+	ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket"));
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	ASSERT_EQ(ret, 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		int fd_server = -1;
+		int exit_code = EXIT_FAILURE;
+
+		close(ipc_sockets[0]);
+
+		fd_server = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0);
+		if (fd_server < 0) {
+			fprintf(stderr, "socket_no_listener: socket failed: %m\n");
+			goto out;
+		}
+
+		ret = bind(fd_server, (const struct sockaddr *)&coredump_sk, coredump_sk_len);
+		if (ret < 0) {
+			fprintf(stderr, "socket_no_listener: bind failed: %m\n");
+			goto out;
+		}
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+			fprintf(stderr, "socket_no_listener: write_nointr to ipc socket failed: %m\n");
+			goto out;
+		}
+
+		exit_code = EXIT_SUCCESS;
+		fprintf(stderr, "socket_no_listener: completed successfully\n");
+out:
+		if (fd_server >= 0)
+			close(fd_server);
+		close(ipc_sockets[1]);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		crashing_child();
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_FALSE(WCOREDUMP(status));
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+/*
+ * Test: PIDFD_INFO_COREDUMP_SIGNAL via simple socket coredump
+ *
+ * Verify that when using simple socket-based coredump (@ pattern),
+ * the coredump_signal field is correctly exposed as SIGSEGV.
+ */
+TEST_F(coredump, socket_coredump_signal_sigsegv)
+{
+	int pidfd, ret, status;
+	pid_t pid, pid_coredump_server;
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket"));
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	ASSERT_EQ(ret, 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1, fd_core_file = -1;
+		int exit_code = EXIT_FAILURE;
+
+		close(ipc_sockets[0]);
+
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: create_and_listen_unix_socket failed: %m\n");
+			goto out;
+		}
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: write_nointr to ipc socket failed: %m\n");
+			goto out;
+		}
+
+		close(ipc_sockets[1]);
+
+		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+		if (fd_coredump < 0) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: accept4 failed: %m\n");
+			goto out;
+		}
+
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: get_peer_pidfd failed\n");
+			goto out;
+		}
+
+		if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: get_pidfd_info failed\n");
+			goto out;
+		}
+
+		if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: PIDFD_INFO_COREDUMP not set in mask\n");
+			goto out;
+		}
+
+		if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: PIDFD_COREDUMPED not set in coredump_mask\n");
+			goto out;
+		}
+
+		/* Verify coredump_signal is available and correct */
+		if (!(info.mask & PIDFD_INFO_COREDUMP_SIGNAL)) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: PIDFD_INFO_COREDUMP_SIGNAL not set in mask\n");
+			goto out;
+		}
+
+		if (info.coredump_signal != SIGSEGV) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: coredump_signal=%d, expected SIGSEGV=%d\n",
+				info.coredump_signal, SIGSEGV);
+			goto out;
+		}
+
+		fd_core_file = open_coredump_tmpfile(self->fd_tmpfs_detached);
+		if (fd_core_file < 0) {
+			fprintf(stderr, "socket_coredump_signal_sigsegv: open_coredump_tmpfile failed: %m\n");
+			goto out;
+		}
+
+		for (;;) {
+			char buffer[4096];
+			ssize_t bytes_read, bytes_write;
+
+			bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+			if (bytes_read < 0) {
+				fprintf(stderr, "socket_coredump_signal_sigsegv: read from coredump socket failed: %m\n");
+				goto out;
+			}
+
+			if (bytes_read == 0)
+				break;
+
+			bytes_write = write(fd_core_file, buffer, bytes_read);
+			if (bytes_read != bytes_write) {
+				fprintf(stderr, "socket_coredump_signal_sigsegv: write to core file failed (read=%zd, write=%zd): %m\n",
+					bytes_read, bytes_write);
+				goto out;
+			}
+		}
+
+		exit_code = EXIT_SUCCESS;
+		fprintf(stderr, "socket_coredump_signal_sigsegv: completed successfully\n");
+out:
+		if (fd_core_file >= 0)
+			close(fd_core_file);
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		crashing_child();
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_EQ(WTERMSIG(status), SIGSEGV);
+	ASSERT_TRUE(WCOREDUMP(status));
+
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+	ASSERT_TRUE(!!(info.mask & PIDFD_INFO_COREDUMP));
+	ASSERT_TRUE(!!(info.mask & PIDFD_INFO_COREDUMP_SIGNAL));
+	ASSERT_EQ(info.coredump_signal, SIGSEGV);
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+/*
+ * Test: PIDFD_INFO_COREDUMP_SIGNAL via simple socket coredump with SIGABRT
+ *
+ * Verify that when using simple socket-based coredump (@ pattern),
+ * the coredump_signal field is correctly exposed as SIGABRT.
+ */
+TEST_F(coredump, socket_coredump_signal_sigabrt)
+{
+	int pidfd, ret, status;
+	pid_t pid, pid_coredump_server;
+	struct pidfd_info info = {};
+	int ipc_sockets[2];
+	char c;
+
+	ASSERT_TRUE(set_core_pattern("@/tmp/coredump.socket"));
+
+	ret = socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, ipc_sockets);
+	ASSERT_EQ(ret, 0);
+
+	pid_coredump_server = fork();
+	ASSERT_GE(pid_coredump_server, 0);
+	if (pid_coredump_server == 0) {
+		int fd_server = -1, fd_coredump = -1, fd_peer_pidfd = -1, fd_core_file = -1;
+		int exit_code = EXIT_FAILURE;
+
+		close(ipc_sockets[0]);
+
+		fd_server = create_and_listen_unix_socket("/tmp/coredump.socket");
+		if (fd_server < 0) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: create_and_listen_unix_socket failed: %m\n");
+			goto out;
+		}
+
+		if (write_nointr(ipc_sockets[1], "1", 1) < 0) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: write_nointr to ipc socket failed: %m\n");
+			goto out;
+		}
+
+		close(ipc_sockets[1]);
+
+		fd_coredump = accept4(fd_server, NULL, NULL, SOCK_CLOEXEC);
+		if (fd_coredump < 0) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: accept4 failed: %m\n");
+			goto out;
+		}
+
+		fd_peer_pidfd = get_peer_pidfd(fd_coredump);
+		if (fd_peer_pidfd < 0) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: get_peer_pidfd failed\n");
+			goto out;
+		}
+
+		if (!get_pidfd_info(fd_peer_pidfd, &info)) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: get_pidfd_info failed\n");
+			goto out;
+		}
+
+		if (!(info.mask & PIDFD_INFO_COREDUMP)) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: PIDFD_INFO_COREDUMP not set in mask\n");
+			goto out;
+		}
+
+		if (!(info.coredump_mask & PIDFD_COREDUMPED)) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: PIDFD_COREDUMPED not set in coredump_mask\n");
+			goto out;
+		}
+
+		/* Verify coredump_signal is available and correct */
+		if (!(info.mask & PIDFD_INFO_COREDUMP_SIGNAL)) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: PIDFD_INFO_COREDUMP_SIGNAL not set in mask\n");
+			goto out;
+		}
+
+		if (info.coredump_signal != SIGABRT) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: coredump_signal=%d, expected SIGABRT=%d\n",
+				info.coredump_signal, SIGABRT);
+			goto out;
+		}
+
+		fd_core_file = open_coredump_tmpfile(self->fd_tmpfs_detached);
+		if (fd_core_file < 0) {
+			fprintf(stderr, "socket_coredump_signal_sigabrt: open_coredump_tmpfile failed: %m\n");
+			goto out;
+		}
+
+		for (;;) {
+			char buffer[4096];
+			ssize_t bytes_read, bytes_write;
+
+			bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+			if (bytes_read < 0) {
+				fprintf(stderr, "socket_coredump_signal_sigabrt: read from coredump socket failed: %m\n");
+				goto out;
+			}
+
+			if (bytes_read == 0)
+				break;
+
+			bytes_write = write(fd_core_file, buffer, bytes_read);
+			if (bytes_read != bytes_write) {
+				fprintf(stderr, "socket_coredump_signal_sigabrt: write to core file failed (read=%zd, write=%zd): %m\n",
+					bytes_read, bytes_write);
+				goto out;
+			}
+		}
+
+		exit_code = EXIT_SUCCESS;
+		fprintf(stderr, "socket_coredump_signal_sigabrt: completed successfully\n");
+out:
+		if (fd_core_file >= 0)
+			close(fd_core_file);
+		if (fd_peer_pidfd >= 0)
+			close(fd_peer_pidfd);
+		if (fd_coredump >= 0)
+			close(fd_coredump);
+		if (fd_server >= 0)
+			close(fd_server);
+		_exit(exit_code);
+	}
+	self->pid_coredump_server = pid_coredump_server;
+
+	EXPECT_EQ(close(ipc_sockets[1]), 0);
+	ASSERT_EQ(read_nointr(ipc_sockets[0], &c, 1), 1);
+	EXPECT_EQ(close(ipc_sockets[0]), 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+	if (pid == 0)
+		abort();
+
+	pidfd = sys_pidfd_open(pid, 0);
+	ASSERT_GE(pidfd, 0);
+
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_EQ(WTERMSIG(status), SIGABRT);
+	ASSERT_TRUE(WCOREDUMP(status));
+
+	ASSERT_TRUE(get_pidfd_info(pidfd, &info));
+	ASSERT_TRUE(!!(info.mask & PIDFD_INFO_COREDUMP));
+	ASSERT_TRUE(!!(info.mask & PIDFD_INFO_COREDUMP_SIGNAL));
+	ASSERT_EQ(info.coredump_signal, SIGABRT);
+
+	wait_and_check_coredump_server(pid_coredump_server, _metadata, self);
+}
+
+TEST_F(coredump, socket_invalid_paths)
+{
+	ASSERT_FALSE(set_core_pattern("@ /tmp/coredump.socket"));
+	ASSERT_FALSE(set_core_pattern("@/tmp/../coredump.socket"));
+	ASSERT_FALSE(set_core_pattern("@../coredump.socket"));
+	ASSERT_FALSE(set_core_pattern("@/tmp/coredump.socket/.."));
+	ASSERT_FALSE(set_core_pattern("@.."));
+
+	ASSERT_FALSE(set_core_pattern("@@ /tmp/coredump.socket"));
+	ASSERT_FALSE(set_core_pattern("@@/tmp/../coredump.socket"));
+	ASSERT_FALSE(set_core_pattern("@@../coredump.socket"));
+	ASSERT_FALSE(set_core_pattern("@@/tmp/coredump.socket/.."));
+	ASSERT_FALSE(set_core_pattern("@@.."));
+
+	ASSERT_FALSE(set_core_pattern("@@@/tmp/coredump.socket"));
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/coredump/coredump_test.h b/tools/testing/selftests/coredump/coredump_test.h
new file mode 100644
index 000000000000..ed47f01fa53c
--- /dev/null
+++ b/tools/testing/selftests/coredump/coredump_test.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __COREDUMP_TEST_H
+#define __COREDUMP_TEST_H
+
+#include <stdbool.h>
+#include <sys/types.h>
+#include <linux/coredump.h>
+
+#include "../kselftest_harness.h"
+#include "../pidfd/pidfd.h"
+
+#ifndef PAGE_SIZE
+#define PAGE_SIZE 4096
+#endif
+
+#define NUM_THREAD_SPAWN 128
+
+/* Coredump fixture */
+FIXTURE(coredump)
+{
+	char original_core_pattern[256];
+	pid_t pid_coredump_server;
+	int fd_tmpfs_detached;
+};
+
+/* Shared helper function declarations */
+void *do_nothing(void *arg);
+void crashing_child(void);
+int create_detached_tmpfs(void);
+int create_and_listen_unix_socket(const char *path);
+bool set_core_pattern(const char *pattern);
+int get_peer_pidfd(int fd);
+bool get_pidfd_info(int fd_peer_pidfd, struct pidfd_info *info);
+
+/* Inline helper that uses harness types */
+static inline void wait_and_check_coredump_server(pid_t pid_coredump_server,
+						   struct __test_metadata *const _metadata,
+						   FIXTURE_DATA(coredump) *self)
+{
+	int status;
+	waitpid(pid_coredump_server, &status, 0);
+	self->pid_coredump_server = -ESRCH;
+	ASSERT_TRUE(WIFEXITED(status));
+	ASSERT_EQ(WEXITSTATUS(status), 0);
+}
+
+/* Protocol helper function declarations */
+ssize_t recv_marker(int fd);
+bool read_marker(int fd, enum coredump_mark mark);
+bool read_coredump_req(int fd, struct coredump_req *req);
+bool send_coredump_ack(int fd, const struct coredump_req *req,
+		       __u64 mask, size_t size_ack);
+bool check_coredump_req(const struct coredump_req *req, size_t min_size,
+			__u64 required_mask);
+int open_coredump_tmpfile(int fd_tmpfs_detached);
+void process_coredump_worker(int fd_coredump, int fd_peer_pidfd, int fd_core_file);
+
+#endif /* __COREDUMP_TEST_H */
diff --git a/tools/testing/selftests/coredump/coredump_test_helpers.c b/tools/testing/selftests/coredump/coredump_test_helpers.c
new file mode 100644
index 000000000000..a6f6d5f2ae07
--- /dev/null
+++ b/tools/testing/selftests/coredump/coredump_test_helpers.c
@@ -0,0 +1,383 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <assert.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <linux/coredump.h>
+#include <linux/fs.h>
+#include <pthread.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/epoll.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <sys/un.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "../filesystems/wrappers.h"
+#include "../pidfd/pidfd.h"
+
+/* Forward declarations to avoid including harness header */
+struct __test_metadata;
+
+/* Match the fixture definition from coredump_test.h */
+struct _fixture_coredump_data {
+	char original_core_pattern[256];
+	pid_t pid_coredump_server;
+	int fd_tmpfs_detached;
+};
+
+#ifndef PAGE_SIZE
+#define PAGE_SIZE 4096
+#endif
+
+#define NUM_THREAD_SPAWN 128
+
+void *do_nothing(void *arg)
+{
+	(void)arg;
+	while (1)
+		pause();
+
+	return NULL;
+}
+
+void crashing_child(void)
+{
+	pthread_t thread;
+	int i;
+
+	for (i = 0; i < NUM_THREAD_SPAWN; ++i)
+		pthread_create(&thread, NULL, do_nothing, NULL);
+
+	/* crash on purpose */
+	i = *(int *)NULL;
+}
+
+int create_detached_tmpfs(void)
+{
+	int fd_context, fd_tmpfs;
+
+	fd_context = sys_fsopen("tmpfs", 0);
+	if (fd_context < 0)
+		return -1;
+
+	if (sys_fsconfig(fd_context, FSCONFIG_CMD_CREATE, NULL, NULL, 0) < 0)
+		return -1;
+
+	fd_tmpfs = sys_fsmount(fd_context, 0, 0);
+	close(fd_context);
+	return fd_tmpfs;
+}
+
+int create_and_listen_unix_socket(const char *path)
+{
+	struct sockaddr_un addr = {
+		.sun_family = AF_UNIX,
+	};
+	assert(strlen(path) < sizeof(addr.sun_path) - 1);
+	strncpy(addr.sun_path, path, sizeof(addr.sun_path) - 1);
+	size_t addr_len =
+		offsetof(struct sockaddr_un, sun_path) + strlen(path) + 1;
+	int fd, ret;
+
+	fd = socket(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0);
+	if (fd < 0)
+		goto out;
+
+	ret = bind(fd, (const struct sockaddr *)&addr, addr_len);
+	if (ret < 0)
+		goto out;
+
+	ret = listen(fd, 128);
+	if (ret < 0)
+		goto out;
+
+	return fd;
+
+out:
+	if (fd >= 0)
+		close(fd);
+	return -1;
+}
+
+bool set_core_pattern(const char *pattern)
+{
+	int fd;
+	ssize_t ret;
+
+	fd = open("/proc/sys/kernel/core_pattern", O_WRONLY | O_CLOEXEC);
+	if (fd < 0)
+		return false;
+
+	ret = write(fd, pattern, strlen(pattern));
+	close(fd);
+	if (ret < 0)
+		return false;
+
+	fprintf(stderr, "Set core_pattern to '%s' | %zu == %zu\n", pattern, ret, strlen(pattern));
+	return ret == strlen(pattern);
+}
+
+int get_peer_pidfd(int fd)
+{
+	int fd_peer_pidfd;
+	socklen_t fd_peer_pidfd_len = sizeof(fd_peer_pidfd);
+	int ret = getsockopt(fd, SOL_SOCKET, SO_PEERPIDFD, &fd_peer_pidfd,
+			     &fd_peer_pidfd_len);
+	if (ret < 0) {
+		fprintf(stderr, "get_peer_pidfd: getsockopt(SO_PEERPIDFD) failed: %m\n");
+		return -1;
+	}
+	fprintf(stderr, "get_peer_pidfd: successfully retrieved pidfd %d\n", fd_peer_pidfd);
+	return fd_peer_pidfd;
+}
+
+bool get_pidfd_info(int fd_peer_pidfd, struct pidfd_info *info)
+{
+	int ret;
+	memset(info, 0, sizeof(*info));
+	info->mask = PIDFD_INFO_EXIT | PIDFD_INFO_COREDUMP | PIDFD_INFO_COREDUMP_SIGNAL;
+	ret = ioctl(fd_peer_pidfd, PIDFD_GET_INFO, info);
+	if (ret < 0) {
+		fprintf(stderr, "get_pidfd_info: ioctl(PIDFD_GET_INFO) failed: %m\n");
+		return false;
+	}
+	fprintf(stderr, "get_pidfd_info: mask=0x%llx, coredump_mask=0x%x, coredump_signal=%d\n",
+		(unsigned long long)info->mask, info->coredump_mask, info->coredump_signal);
+	return true;
+}
+
+/* Protocol helper functions */
+
+ssize_t recv_marker(int fd)
+{
+	enum coredump_mark mark = COREDUMP_MARK_REQACK;
+	ssize_t ret;
+
+	ret = recv(fd, &mark, sizeof(mark), MSG_WAITALL);
+	if (ret != sizeof(mark))
+		return -1;
+
+	switch (mark) {
+	case COREDUMP_MARK_REQACK:
+		fprintf(stderr, "Received marker: ReqAck\n");
+		return COREDUMP_MARK_REQACK;
+	case COREDUMP_MARK_MINSIZE:
+		fprintf(stderr, "Received marker: MinSize\n");
+		return COREDUMP_MARK_MINSIZE;
+	case COREDUMP_MARK_MAXSIZE:
+		fprintf(stderr, "Received marker: MaxSize\n");
+		return COREDUMP_MARK_MAXSIZE;
+	case COREDUMP_MARK_UNSUPPORTED:
+		fprintf(stderr, "Received marker: Unsupported\n");
+		return COREDUMP_MARK_UNSUPPORTED;
+	case COREDUMP_MARK_CONFLICTING:
+		fprintf(stderr, "Received marker: Conflicting\n");
+		return COREDUMP_MARK_CONFLICTING;
+	default:
+		fprintf(stderr, "Received unknown marker: %u\n", mark);
+		break;
+	}
+	return -1;
+}
+
+bool read_marker(int fd, enum coredump_mark mark)
+{
+	ssize_t ret;
+
+	ret = recv_marker(fd);
+	if (ret < 0)
+		return false;
+	return ret == mark;
+}
+
+bool read_coredump_req(int fd, struct coredump_req *req)
+{
+	ssize_t ret;
+	size_t field_size, user_size, ack_size, kernel_size, remaining_size;
+
+	memset(req, 0, sizeof(*req));
+	field_size = sizeof(req->size);
+
+	/* Peek the size of the coredump request. */
+	ret = recv(fd, req, field_size, MSG_PEEK | MSG_WAITALL);
+	if (ret != field_size) {
+		fprintf(stderr, "read_coredump_req: peek failed (got %zd, expected %zu): %m\n",
+			ret, field_size);
+		return false;
+	}
+	kernel_size = req->size;
+
+	if (kernel_size < COREDUMP_ACK_SIZE_VER0) {
+		fprintf(stderr, "read_coredump_req: kernel_size %zu < min %d\n",
+			kernel_size, COREDUMP_ACK_SIZE_VER0);
+		return false;
+	}
+	if (kernel_size >= PAGE_SIZE) {
+		fprintf(stderr, "read_coredump_req: kernel_size %zu >= PAGE_SIZE %d\n",
+			kernel_size, PAGE_SIZE);
+		return false;
+	}
+
+	/* Use the minimum of user and kernel size to read the full request. */
+	user_size = sizeof(struct coredump_req);
+	ack_size = user_size < kernel_size ? user_size : kernel_size;
+	ret = recv(fd, req, ack_size, MSG_WAITALL);
+	if (ret != ack_size)
+		return false;
+
+	fprintf(stderr, "Read coredump request with size %u and mask 0x%llx\n",
+		req->size, (unsigned long long)req->mask);
+
+	if (user_size > kernel_size)
+		remaining_size = user_size - kernel_size;
+	else
+		remaining_size = kernel_size - user_size;
+
+	if (PAGE_SIZE <= remaining_size)
+		return false;
+
+	/*
+	 * Discard any additional data if the kernel's request was larger than
+	 * what we knew about or cared about.
+	 */
+	if (remaining_size) {
+		char buffer[PAGE_SIZE];
+
+		ret = recv(fd, buffer, sizeof(buffer), MSG_WAITALL);
+		if (ret != remaining_size)
+			return false;
+		fprintf(stderr, "Discarded %zu bytes of data after coredump request\n", remaining_size);
+	}
+
+	return true;
+}
+
+bool send_coredump_ack(int fd, const struct coredump_req *req,
+		       __u64 mask, size_t size_ack)
+{
+	ssize_t ret;
+	/*
+	 * Wrap struct coredump_ack in a larger struct so we can
+	 * simulate sending to much data to the kernel.
+	 */
+	struct large_ack_for_size_testing {
+		struct coredump_ack ack;
+		char buffer[PAGE_SIZE];
+	} large_ack = {};
+
+	if (!size_ack)
+		size_ack = sizeof(struct coredump_ack) < req->size_ack ?
+				   sizeof(struct coredump_ack) :
+				   req->size_ack;
+	large_ack.ack.mask = mask;
+	large_ack.ack.size = size_ack;
+	ret = send(fd, &large_ack, size_ack, MSG_NOSIGNAL);
+	if (ret != size_ack)
+		return false;
+
+	fprintf(stderr, "Sent coredump ack with size %zu and mask 0x%llx\n",
+		size_ack, (unsigned long long)mask);
+	return true;
+}
+
+bool check_coredump_req(const struct coredump_req *req, size_t min_size,
+			__u64 required_mask)
+{
+	if (req->size < min_size)
+		return false;
+	if ((req->mask & required_mask) != required_mask)
+		return false;
+	if (req->mask & ~required_mask)
+		return false;
+	return true;
+}
+
+int open_coredump_tmpfile(int fd_tmpfs_detached)
+{
+	return openat(fd_tmpfs_detached, ".", O_TMPFILE | O_RDWR | O_EXCL, 0600);
+}
+
+void process_coredump_worker(int fd_coredump, int fd_peer_pidfd, int fd_core_file)
+{
+	int epfd = -1;
+	int exit_code = EXIT_FAILURE;
+	struct epoll_event ev;
+	int flags;
+
+	/* Set socket to non-blocking mode for edge-triggered epoll */
+	flags = fcntl(fd_coredump, F_GETFL, 0);
+	if (flags < 0) {
+		fprintf(stderr, "Worker: fcntl(F_GETFL) failed: %m\n");
+		goto out;
+	}
+	if (fcntl(fd_coredump, F_SETFL, flags | O_NONBLOCK) < 0) {
+		fprintf(stderr, "Worker: fcntl(F_SETFL, O_NONBLOCK) failed: %m\n");
+		goto out;
+	}
+
+	epfd = epoll_create1(0);
+	if (epfd < 0) {
+		fprintf(stderr, "Worker: epoll_create1() failed: %m\n");
+		goto out;
+	}
+
+	ev.events = EPOLLIN | EPOLLRDHUP | EPOLLET;
+	ev.data.fd = fd_coredump;
+	if (epoll_ctl(epfd, EPOLL_CTL_ADD, fd_coredump, &ev) < 0) {
+		fprintf(stderr, "Worker: epoll_ctl(EPOLL_CTL_ADD) failed: %m\n");
+		goto out;
+	}
+
+	for (;;) {
+		struct epoll_event events[1];
+		int n = epoll_wait(epfd, events, 1, -1);
+		if (n < 0) {
+			fprintf(stderr, "Worker: epoll_wait() failed: %m\n");
+			break;
+		}
+
+		if (events[0].events & (EPOLLIN | EPOLLRDHUP)) {
+			for (;;) {
+				char buffer[4096];
+				ssize_t bytes_read = read(fd_coredump, buffer, sizeof(buffer));
+				if (bytes_read < 0) {
+					if (errno == EAGAIN || errno == EWOULDBLOCK)
+						break;
+					fprintf(stderr, "Worker: read() failed: %m\n");
+					goto out;
+				}
+				if (bytes_read == 0)
+					goto done;
+				ssize_t bytes_write = write(fd_core_file, buffer, bytes_read);
+				if (bytes_write != bytes_read) {
+					if (bytes_write < 0 && errno == ENOSPC)
+						continue;
+					fprintf(stderr, "Worker: write() failed (read=%zd, write=%zd): %m\n",
+						bytes_read, bytes_write);
+					goto out;
+				}
+			}
+		}
+	}
+
+done:
+	exit_code = EXIT_SUCCESS;
+	fprintf(stderr, "Worker: completed successfully\n");
+out:
+	if (epfd >= 0)
+		close(epfd);
+	if (fd_core_file >= 0)
+		close(fd_core_file);
+	if (fd_peer_pidfd >= 0)
+		close(fd_peer_pidfd);
+	if (fd_coredump >= 0)
+		close(fd_coredump);
+	_exit(exit_code);
+}
diff --git a/tools/testing/selftests/coredump/stackdump b/tools/testing/selftests/coredump/stackdump
new file mode 100755
index 000000000000..96714ce42d12
--- /dev/null
+++ b/tools/testing/selftests/coredump/stackdump
@@ -0,0 +1,14 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+CRASH_PROGRAM_ID=$1
+STACKDUMP_FILE=$2
+
+TMP=$(mktemp)
+
+for t in /proc/$CRASH_PROGRAM_ID/task/*; do
+	tid=$(basename $t)
+	cat /proc/$tid/stat | awk '{print $29}' >> $TMP
+done
+
+mv $TMP $STACKDUMP_FILE
diff --git a/tools/testing/selftests/coredump/stackdump_test.c b/tools/testing/selftests/coredump/stackdump_test.c
new file mode 100644
index 000000000000..1ec88937a1c2
--- /dev/null
+++ b/tools/testing/selftests/coredump/stackdump_test.c
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <assert.h>
+#include <fcntl.h>
+#include <inttypes.h>
+#include <libgen.h>
+#include <limits.h>
+#include <linux/coredump.h>
+#include <linux/fs.h>
+#include <linux/limits.h>
+#include <pthread.h>
+#include <string.h>
+#include <sys/mount.h>
+#include <poll.h>
+#include <sys/epoll.h>
+#include <sys/resource.h>
+#include <sys/stat.h>
+#include <sys/socket.h>
+#include <sys/un.h>
+#include <unistd.h>
+
+#include "kselftest_harness.h"
+#include "../filesystems/wrappers.h"
+#include "../pidfd/pidfd.h"
+
+#include "coredump_test.h"
+
+#define STACKDUMP_FILE "stack_values"
+#define STACKDUMP_SCRIPT "stackdump"
+
+#ifndef PAGE_SIZE
+#define PAGE_SIZE 4096
+#endif
+
+FIXTURE_SETUP(coredump)
+{
+	FILE *file;
+	int ret;
+
+	self->pid_coredump_server = -ESRCH;
+	self->fd_tmpfs_detached = -1;
+	file = fopen("/proc/sys/kernel/core_pattern", "r");
+	ASSERT_NE(NULL, file);
+
+	ret = fread(self->original_core_pattern, 1, sizeof(self->original_core_pattern), file);
+	ASSERT_TRUE(ret || feof(file));
+	ASSERT_LT(ret, sizeof(self->original_core_pattern));
+
+	self->original_core_pattern[ret] = '\0';
+	self->fd_tmpfs_detached = create_detached_tmpfs();
+	ASSERT_GE(self->fd_tmpfs_detached, 0);
+
+	ret = fclose(file);
+	ASSERT_EQ(0, ret);
+}
+
+FIXTURE_TEARDOWN(coredump)
+{
+	const char *reason;
+	FILE *file;
+	int ret, status;
+
+	unlink(STACKDUMP_FILE);
+
+	if (self->pid_coredump_server > 0) {
+		kill(self->pid_coredump_server, SIGTERM);
+		waitpid(self->pid_coredump_server, &status, 0);
+	}
+	unlink("/tmp/coredump.file");
+	unlink("/tmp/coredump.socket");
+
+	file = fopen("/proc/sys/kernel/core_pattern", "w");
+	if (!file) {
+		reason = "Unable to open core_pattern";
+		goto fail;
+	}
+
+	ret = fprintf(file, "%s", self->original_core_pattern);
+	if (ret < 0) {
+		reason = "Unable to write to core_pattern";
+		goto fail;
+	}
+
+	ret = fclose(file);
+	if (ret) {
+		reason = "Unable to close core_pattern";
+		goto fail;
+	}
+
+	if (self->fd_tmpfs_detached >= 0) {
+		ret = close(self->fd_tmpfs_detached);
+		if (ret < 0) {
+			reason = "Unable to close detached tmpfs";
+			goto fail;
+		}
+		self->fd_tmpfs_detached = -1;
+	}
+
+	return;
+fail:
+	/* This should never happen */
+	fprintf(stderr, "Failed to cleanup stackdump test: %s\n", reason);
+}
+
+TEST_F_TIMEOUT(coredump, stackdump, 120)
+{
+	unsigned long long stack;
+	char *test_dir, *line;
+	size_t line_length;
+	char buf[PAGE_SIZE];
+	int ret, i, status;
+	FILE *file;
+	pid_t pid;
+
+	/*
+	 * Step 1: Setup core_pattern so that the stackdump script is executed when the child
+	 * process crashes
+	 */
+	ret = readlink("/proc/self/exe", buf, sizeof(buf));
+	ASSERT_NE(-1, ret);
+	ASSERT_LT(ret, sizeof(buf));
+	buf[ret] = '\0';
+
+	test_dir = dirname(buf);
+
+	file = fopen("/proc/sys/kernel/core_pattern", "w");
+	ASSERT_NE(NULL, file);
+
+	ret = fprintf(file, "|%1$s/%2$s %%P %1$s/%3$s", test_dir, STACKDUMP_SCRIPT, STACKDUMP_FILE);
+	ASSERT_LT(0, ret);
+
+	ret = fclose(file);
+	ASSERT_EQ(0, ret);
+
+	/* Step 2: Create a process who spawns some threads then crashes */
+	pid = fork();
+	ASSERT_TRUE(pid >= 0);
+	if (pid == 0)
+		crashing_child();
+
+	/*
+	 * Step 3: Wait for the stackdump script to write the stack pointers to the stackdump file
+	 */
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFSIGNALED(status));
+	ASSERT_TRUE(WCOREDUMP(status));
+
+	for (i = 0; i < 10; ++i) {
+		file = fopen(STACKDUMP_FILE, "r");
+		if (file)
+			break;
+		sleep(1);
+	}
+	ASSERT_NE(file, NULL);
+
+	/* Step 4: Make sure all stack pointer values are non-zero */
+	line = NULL;
+	for (i = 0; -1 != getline(&line, &line_length, file); ++i) {
+		stack = strtoull(line, NULL, 10);
+		ASSERT_NE(stack, 0);
+	}
+	free(line);
+
+	ASSERT_EQ(i, 1 + NUM_THREAD_SPAWN);
+
+	fclose(file);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh
index d5dc7e0dc726..6232a46ca6e1 100755
--- a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh
+++ b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh
@@ -67,7 +67,7 @@ hotpluggable_cpus()
 	done
 }
 
-hotplaggable_offline_cpus()
+hotpluggable_offline_cpus()
 {
 	hotpluggable_cpus 0
 }
@@ -151,7 +151,7 @@ offline_cpu_expect_fail()
 
 online_all_hot_pluggable_cpus()
 {
-	for cpu in `hotplaggable_offline_cpus`; do
+	for cpu in `hotpluggable_offline_cpus`; do
 		online_cpu_expect_success $cpu
 	done
 }
diff --git a/tools/testing/selftests/cpufreq/.gitignore b/tools/testing/selftests/cpufreq/.gitignore
new file mode 100644
index 000000000000..67604e91e068
--- /dev/null
+++ b/tools/testing/selftests/cpufreq/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+cpufreq_selftest.*
diff --git a/tools/testing/selftests/cpufreq/Makefile b/tools/testing/selftests/cpufreq/Makefile
index c86ca8342222..9b2ccb10b0cf 100644
--- a/tools/testing/selftests/cpufreq/Makefile
+++ b/tools/testing/selftests/cpufreq/Makefile
@@ -3,6 +3,7 @@ all:
 
 TEST_PROGS := main.sh
 TEST_FILES := cpu.sh cpufreq.sh governor.sh module.sh special-tests.sh
+EXTRA_CLEAN := cpufreq_selftest.dmesg_cpufreq.txt cpufreq_selftest.dmesg_full.txt cpufreq_selftest.txt
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/cpufreq/config b/tools/testing/selftests/cpufreq/config
index 75e900793e8a..ce5068f5a6a2 100644
--- a/tools/testing/selftests/cpufreq/config
+++ b/tools/testing/selftests/cpufreq/config
@@ -5,11 +5,3 @@ CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_ONDEMAND=y
 CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
 CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y
-CONFIG_DEBUG_RT_MUTEXES=y
-CONFIG_DEBUG_PLIST=y
-CONFIG_DEBUG_SPINLOCK=y
-CONFIG_DEBUG_MUTEXES=y
-CONFIG_DEBUG_LOCK_ALLOC=y
-CONFIG_PROVE_LOCKING=y
-CONFIG_LOCKDEP=y
-CONFIG_DEBUG_ATOMIC_SLEEP=y
diff --git a/tools/testing/selftests/cpufreq/cpufreq.sh b/tools/testing/selftests/cpufreq/cpufreq.sh
index b583a2fb4504..9927b654fb8f 100755
--- a/tools/testing/selftests/cpufreq/cpufreq.sh
+++ b/tools/testing/selftests/cpufreq/cpufreq.sh
@@ -52,7 +52,14 @@ read_cpufreq_files_in_dir()
 	for file in $files; do
 		if [ -f $1/$file ]; then
 			printf "$file:"
-			cat $1/$file
+			#file is readable ?
+			local rfile=$(ls -l $1/$file | awk '$1 ~ /^.*r.*/ { print $NF; }')
+
+			if [ ! -z $rfile ]; then
+				cat $1/$file
+			else
+				printf "$file is not readable\n"
+			fi
 		else
 			printf "\n"
 			read_cpufreq_files_in_dir "$1/$file"
@@ -83,10 +90,10 @@ update_cpufreq_files_in_dir()
 
 	for file in $files; do
 		if [ -f $1/$file ]; then
-			# file is writable ?
-			local wfile=$(ls -l $1/$file | awk '$1 ~ /^.*w.*/ { print $NF; }')
+			# file is readable and writable ?
+			local rwfile=$(ls -l $1/$file | awk '$1 ~ /^.*rw.*/ { print $NF; }')
 
-			if [ ! -z $wfile ]; then
+			if [ ! -z $rwfile ]; then
 				# scaling_setspeed is a special file and we
 				# should skip updating it
 				if [ $file != "scaling_setspeed" ]; then
@@ -178,8 +185,7 @@ cpufreq_basic_tests()
 
 	count=$(count_cpufreq_managed_cpus)
 	if [ $count = 0 ]; then
-		printf "No cpu is managed by cpufreq core, exiting\n"
-		exit;
+		ktap_exit_fail_msg "No cpu is managed by cpufreq core, exiting\n"
 	else
 		printf "CPUFreq manages: $count CPUs\n\n"
 	fi
@@ -232,7 +238,23 @@ do_suspend()
 
 		for i in `seq 1 $2`; do
 			printf "Starting $1\n"
-			echo $filename > $SYSFS/power/state
+
+			if [ "$3" = "rtc" ]; then
+				if ! command -v rtcwake &> /dev/null; then
+					printf "rtcwake could not be found, please install it.\n"
+					return 1
+				fi
+
+				rtcwake -m $filename -s 15
+
+				if [ $? -ne 0 ]; then
+					printf "Failed to suspend using RTC wake alarm\n"
+					return 1
+				fi
+			else
+				echo $filename > $SYSFS/power/state
+			fi
+
 			printf "Came out of $1\n"
 
 			printf "Do basic tests after finishing $1 to verify cpufreq state\n\n"
diff --git a/tools/testing/selftests/cpufreq/main.sh b/tools/testing/selftests/cpufreq/main.sh
index 60ce18ed0666..f12ff7416e41 100755
--- a/tools/testing/selftests/cpufreq/main.sh
+++ b/tools/testing/selftests/cpufreq/main.sh
@@ -7,15 +7,15 @@ source governor.sh
 source module.sh
 source special-tests.sh
 
+DIR="$(dirname $(readlink -f "$0"))"
+source "${DIR}"/../kselftest/ktap_helpers.sh
+
 FUNC=basic	# do basic tests by default
 OUTFILE=cpufreq_selftest
 SYSFS=
 CPUROOT=
 CPUFREQROOT=
 
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
 helpme()
 {
 	printf "Usage: $0 [-h] [-todg args]
@@ -24,6 +24,8 @@ helpme()
 	[-t <basic: Basic cpufreq testing
 	     suspend: suspend/resume,
 	     hibernate: hibernate/resume,
+	     suspend_rtc: suspend/resume back using the RTC wakeup alarm,
+	     hibernate_rtc: hibernate/resume back using the RTC wakeup alarm,
 	     modtest: test driver or governor modules. Only to be used with -d or -g options,
 	     sptest1: Simple governor switch to produce lockdep.
 	     sptest2: Concurrent governor switch to produce lockdep.
@@ -32,7 +34,7 @@ helpme()
 	[-d <driver's module name: only with \"-t modtest>\"]
 	[-g <governor's module name: only with \"-t modtest>\"]
 	\n"
-	exit 2
+	exit "${KSFT_FAIL}"
 }
 
 prerequisite()
@@ -40,8 +42,8 @@ prerequisite()
 	msg="skip all tests:"
 
 	if [ $UID != 0 ]; then
-		echo $msg must be run as root >&2
-		exit $ksft_skip
+		ktap_skip_all "$msg must be run as root"
+		exit "${KSFT_SKIP}"
 	fi
 
 	taskset -p 01 $$
@@ -49,21 +51,21 @@ prerequisite()
 	SYSFS=`mount -t sysfs | head -1 | awk '{ print $3 }'`
 
 	if [ ! -d "$SYSFS" ]; then
-		echo $msg sysfs is not mounted >&2
-		exit 2
+		ktap_skip_all "$msg sysfs is not mounted"
+		exit "${KSFT_SKIP}"
 	fi
 
 	CPUROOT=$SYSFS/devices/system/cpu
 	CPUFREQROOT="$CPUROOT/cpufreq"
 
 	if ! ls $CPUROOT/cpu* > /dev/null 2>&1; then
-		echo $msg cpus not available in sysfs >&2
-		exit 2
+		ktap_skip_all "$msg cpus not available in sysfs"
+		exit "${KSFT_SKIP}"
 	fi
 
 	if ! ls $CPUROOT/cpufreq > /dev/null 2>&1; then
-		echo $msg cpufreq directory not available in sysfs >&2
-		exit 2
+		ktap_skip_all "$msg cpufreq directory not available in sysfs"
+		exit "${KSFT_SKIP}"
 	fi
 }
 
@@ -76,7 +78,8 @@ parse_arguments()
 				helpme
 				;;
 
-			t) # --func_type (Function to perform: basic, suspend, hibernate, modtest, sptest1/2/3/4 (default: basic))
+			t) # --func_type (Function to perform: basic, suspend, hibernate,
+			   # suspend_rtc, hibernate_rtc, modtest, sptest1/2/3/4 (default: basic))
 				FUNC=$OPTARG
 				;;
 
@@ -105,8 +108,7 @@ do_test()
 	count=$(count_cpufreq_managed_cpus)
 
 	if [ $count = 0 -a $FUNC != "modtest" ]; then
-		echo "No cpu is managed by cpufreq core, exiting"
-		exit 2;
+		ktap_exit_fail_msg "No cpu is managed by cpufreq core, exiting"
 	fi
 
 	case "$FUNC" in
@@ -122,11 +124,18 @@ do_test()
 		do_suspend "hibernate" 1
 		;;
 
+		"suspend_rtc")
+                do_suspend "suspend" 1 rtc
+                ;;
+
+                "hibernate_rtc")
+                do_suspend "hibernate" 1 rtc
+                ;;
+
 		"modtest")
 		# Do we have modules in place?
 		if [ -z $DRIVER_MOD ] && [ -z $GOVERNOR_MOD ]; then
-			echo "No driver or governor module passed with -d or -g"
-			exit 2;
+			ktap_exit_fail_msg "No driver or governor module passed with -d or -g"
 		fi
 
 		if [ $DRIVER_MOD ]; then
@@ -137,8 +146,7 @@ do_test()
 			fi
 		else
 			if [ $count = 0 ]; then
-				echo "No cpu is managed by cpufreq core, exiting"
-				exit 2;
+				ktap_exit_fail_msg "No cpu is managed by cpufreq core, exiting"
 			fi
 
 			module_governor_test $GOVERNOR_MOD
@@ -162,7 +170,7 @@ do_test()
 		;;
 
 		*)
-		echo "Invalid [-f] function type"
+		ktap_print_msg "Invalid [-f] function type"
 		helpme
 		;;
 	esac
@@ -186,13 +194,25 @@ dmesg_dumps()
 	dmesg >> $1.dmesg_full.txt
 }
 
+ktap_print_header
+
 # Parse arguments
 parse_arguments $@
 
+ktap_set_plan 1
+
 # Make sure all requirements are met
 prerequisite
 
 # Run requested functions
 clear_dumps $OUTFILE
 do_test | tee -a $OUTFILE.txt
+if [ "${PIPESTATUS[0]}" -ne 0 ]; then
+    exit ${PIPESTATUS[0]};
+fi
 dmesg_dumps $OUTFILE
+
+ktap_test_pass "Completed successfully"
+
+ktap_print_totals
+exit "${KSFT_PASS}"
diff --git a/tools/testing/selftests/cpufreq/module.sh b/tools/testing/selftests/cpufreq/module.sh
index 22563cd122e7..7f2667e0ae2d 100755
--- a/tools/testing/selftests/cpufreq/module.sh
+++ b/tools/testing/selftests/cpufreq/module.sh
@@ -24,16 +24,14 @@ test_basic_insmod_rmmod()
 	# insert module
 	insmod $1
 	if [ $? != 0 ]; then
-		printf "Insmod $1 failed\n"
-		exit;
+		ktap_exit_fail_msg "Insmod $1 failed\n"
 	fi
 
 	printf "Removing $1 module\n"
 	# remove module
 	rmmod $1
 	if [ $? != 0 ]; then
-		printf "rmmod $1 failed\n"
-		exit;
+		ktap_exit_fail_msg "rmmod $1 failed\n"
 	fi
 
 	printf "\n"
diff --git a/tools/testing/selftests/damon/.gitignore b/tools/testing/selftests/damon/.gitignore
index c6c2965a6607..2f0297657c81 100644
--- a/tools/testing/selftests/damon/.gitignore
+++ b/tools/testing/selftests/damon/.gitignore
@@ -1,2 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0-only
-huge_count_read_write
+access_memory
+access_memory_even
diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile
index b71247ba7196..2180c328a825 100644
--- a/tools/testing/selftests/damon/Makefile
+++ b/tools/testing/selftests/damon/Makefile
@@ -1,14 +1,26 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for damon selftests
 
-TEST_GEN_FILES += huge_count_read_write
-
-TEST_FILES = _chk_dependency.sh _debugfs_common.sh
-TEST_PROGS = debugfs_attrs.sh debugfs_schemes.sh debugfs_target_ids.sh
-TEST_PROGS += debugfs_empty_targets.sh debugfs_huge_count_read_write.sh
-TEST_PROGS += debugfs_duplicate_context_creation.sh
-TEST_PROGS += debugfs_rm_non_contexts.sh
-TEST_PROGS += sysfs.sh sysfs_update_removed_scheme_dir.sh
+TEST_GEN_FILES += access_memory access_memory_even
+
+TEST_FILES = _damon_sysfs.py
+TEST_FILES += drgn_dump_damon_status.py
+TEST_FILES += _common.sh
+
+# functionality tests
+TEST_PROGS += sysfs.sh
+TEST_PROGS += sysfs.py
+TEST_PROGS += sysfs_update_schemes_tried_regions_wss_estimation.py
+TEST_PROGS += damos_quota.py damos_quota_goal.py damos_apply_interval.py
+TEST_PROGS += damos_tried_regions.py damon_nr_regions.py
 TEST_PROGS += reclaim.sh lru_sort.sh
 
+# regression tests (reproducers of previously found bugs)
+TEST_PROGS += sysfs_update_removed_scheme_dir.sh
+TEST_PROGS += sysfs_update_schemes_tried_regions_hang.py
+TEST_PROGS += sysfs_memcg_path_leak.sh
+TEST_PROGS += sysfs_no_op_commit_break.py
+
+EXTRA_CLEAN = __pycache__
+
 include ../lib.mk
diff --git a/tools/testing/selftests/damon/_chk_dependency.sh b/tools/testing/selftests/damon/_chk_dependency.sh
deleted file mode 100644
index 0328ac0b5a5e..000000000000
--- a/tools/testing/selftests/damon/_chk_dependency.sh
+++ /dev/null
@@ -1,38 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
-DBGFS=/sys/kernel/debug/damon
-
-if [ $EUID -ne 0 ];
-then
-	echo "Run as root"
-	exit $ksft_skip
-fi
-
-if [ ! -d "$DBGFS" ]
-then
-	echo "$DBGFS not found"
-	exit $ksft_skip
-fi
-
-for f in attrs target_ids monitor_on
-do
-	if [ ! -f "$DBGFS/$f" ]
-	then
-		echo "$f not found"
-		exit 1
-	fi
-done
-
-permission_error="Operation not permitted"
-for f in attrs target_ids monitor_on
-do
-	status=$( cat "$DBGFS/$f" 2>&1 )
-	if [ "${status#*$permission_error}" != "$status" ]; then
-		echo "Permission for reading $DBGFS/$f denied; maybe secureboot enabled?"
-		exit $ksft_skip
-	fi
-done
diff --git a/tools/testing/selftests/damon/_common.sh b/tools/testing/selftests/damon/_common.sh
new file mode 100644
index 000000000000..0279698f733e
--- /dev/null
+++ b/tools/testing/selftests/damon/_common.sh
@@ -0,0 +1,11 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+check_dependencies()
+{
+	if [ $EUID -ne 0 ]
+	then
+		echo "Run as root"
+		exit $ksft_skip
+	fi
+}
diff --git a/tools/testing/selftests/damon/_damon_sysfs.py b/tools/testing/selftests/damon/_damon_sysfs.py
new file mode 100644
index 000000000000..748778b563cd
--- /dev/null
+++ b/tools/testing/selftests/damon/_damon_sysfs.py
@@ -0,0 +1,837 @@
+# SPDX-License-Identifier: GPL-2.0
+
+import os
+
+ksft_skip=4
+
+sysfs_root = None
+with open('/proc/mounts', 'r') as f:
+    for line in f:
+        dev_name, mount_point, dev_fs = line.split()[:3]
+        if dev_fs == 'sysfs':
+            sysfs_root = '%s/kernel/mm/damon/admin' % mount_point
+            break
+if sysfs_root is None:
+    print('Seems sysfs not mounted?')
+    exit(ksft_skip)
+
+if not os.path.exists(sysfs_root):
+    print('Seems DAMON disabled?')
+    exit(ksft_skip)
+
+def write_file(path, string):
+    "Returns error string if failed, or None otherwise"
+    string = '%s' % string
+    try:
+        with open(path, 'w') as f:
+            f.write(string)
+    except Exception as e:
+        return '%s' % e
+    return None
+
+def read_file(path):
+    '''Returns the read content and error string.  The read content is None if
+    the reading failed'''
+    try:
+        with open(path, 'r') as f:
+            return f.read(), None
+    except Exception as e:
+        return None, '%s' % e
+
+class DamosAccessPattern:
+    size = None
+    nr_accesses = None
+    age = None
+    scheme = None
+
+    def __init__(self, size=None, nr_accesses=None, age=None):
+        self.size = size
+        self.nr_accesses = nr_accesses
+        self.age = age
+
+        if self.size is None:
+            self.size = [0, 2**64 - 1]
+        if self.nr_accesses is None:
+            self.nr_accesses = [0, 2**32 - 1]
+        if self.age is None:
+            self.age = [0, 2**32 - 1]
+
+    def sysfs_dir(self):
+        return os.path.join(self.scheme.sysfs_dir(), 'access_pattern')
+
+    def stage(self):
+        err = write_file(
+                os.path.join(self.sysfs_dir(), 'sz', 'min'), self.size[0])
+        if err is not None:
+            return err
+        err = write_file(
+                os.path.join(self.sysfs_dir(), 'sz', 'max'), self.size[1])
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'nr_accesses', 'min'),
+                self.nr_accesses[0])
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'nr_accesses', 'max'),
+                self.nr_accesses[1])
+        if err is not None:
+            return err
+        err = write_file(
+                os.path.join(self.sysfs_dir(), 'age', 'min'), self.age[0])
+        if err is not None:
+            return err
+        err = write_file(
+                os.path.join(self.sysfs_dir(), 'age', 'max'), self.age[1])
+        if err is not None:
+            return err
+
+qgoal_metric_user_input = 'user_input'
+qgoal_metric_some_mem_psi_us = 'some_mem_psi_us'
+qgoal_metrics = [qgoal_metric_user_input, qgoal_metric_some_mem_psi_us]
+
+class DamosQuotaGoal:
+    metric = None
+    target_value = None
+    current_value = None
+    nid = None
+    effective_bytes = None
+    quota = None            # owner quota
+    idx = None
+
+    def __init__(self, metric, target_value=10000, current_value=0, nid=0):
+        self.metric = metric
+        self.target_value = target_value
+        self.current_value = current_value
+        self.nid = nid
+
+    def sysfs_dir(self):
+        return os.path.join(self.quota.sysfs_dir(), 'goals', '%d' % self.idx)
+
+    def stage(self):
+        err = write_file(os.path.join(self.sysfs_dir(), 'target_metric'),
+                         self.metric)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'target_value'),
+                         self.target_value)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'current_value'),
+                         self.current_value)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'nid'), self.nid)
+        if err is not None:
+            return err
+
+        return None
+
+class DamosQuota:
+    sz = None                   # size quota, in bytes
+    ms = None                   # time quota
+    goals = None                # quota goals
+    reset_interval_ms = None    # quota reset interval
+    weight_sz_permil = None
+    weight_nr_accesses_permil = None
+    weight_age_permil = None
+    scheme = None               # owner scheme
+
+    def __init__(self, sz=0, ms=0, goals=None, reset_interval_ms=0,
+                 weight_sz_permil=0, weight_nr_accesses_permil=0,
+                 weight_age_permil=0):
+        self.sz = sz
+        self.ms = ms
+        self.reset_interval_ms = reset_interval_ms
+        self.weight_sz_permil = weight_sz_permil
+        self.weight_nr_accesses_permil = weight_nr_accesses_permil
+        self.weight_age_permil = weight_age_permil
+        self.goals = goals if goals is not None else []
+        for idx, goal in enumerate(self.goals):
+            goal.idx = idx
+            goal.quota = self
+
+    def sysfs_dir(self):
+        return os.path.join(self.scheme.sysfs_dir(), 'quotas')
+
+    def stage(self):
+        err = write_file(os.path.join(self.sysfs_dir(), 'bytes'), self.sz)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'ms'), self.ms)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'reset_interval_ms'),
+                         self.reset_interval_ms)
+        if err is not None:
+            return err
+
+        err = write_file(os.path.join(
+            self.sysfs_dir(), 'weights', 'sz_permil'), self.weight_sz_permil)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(
+            self.sysfs_dir(), 'weights', 'nr_accesses_permil'),
+                         self.weight_nr_accesses_permil)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(
+            self.sysfs_dir(), 'weights', 'age_permil'), self.weight_age_permil)
+        if err is not None:
+            return err
+
+        nr_goals_file = os.path.join(self.sysfs_dir(), 'goals', 'nr_goals')
+        content, err = read_file(nr_goals_file)
+        if err is not None:
+            return err
+        if int(content) != len(self.goals):
+            err = write_file(nr_goals_file, len(self.goals))
+            if err is not None:
+                return err
+        for goal in self.goals:
+            err = goal.stage()
+            if err is not None:
+                return err
+        return None
+
+class DamosWatermarks:
+    metric = None
+    interval = None
+    high = None
+    mid = None
+    low = None
+    scheme = None   # owner scheme
+
+    def __init__(self, metric='none', interval=0, high=0, mid=0, low=0):
+        self.metric = metric
+        self.interval = interval
+        self.high = high
+        self.mid = mid
+        self.low = low
+
+    def sysfs_dir(self):
+        return os.path.join(self.scheme.sysfs_dir(), 'watermarks')
+
+    def stage(self):
+        err = write_file(os.path.join(self.sysfs_dir(), 'metric'), self.metric)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'interval_us'),
+                         self.interval)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'high'), self.high)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'mid'), self.mid)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'low'), self.low)
+        if err is not None:
+            return err
+
+class DamosFilter:
+    type_ = None
+    matching = None
+    allow = None
+    memcg_path = None
+    addr_start = None
+    addr_end = None
+    target_idx = None
+    min_ = None
+    max_ = None
+    idx = None
+    filters = None  # owner filters
+
+    def __init__(self, type_='anon', matching=False, allow=False,
+                 memcg_path='', addr_start=0, addr_end=0, target_idx=0, min_=0,
+                 max_=0):
+        self.type_ = type_
+        self.matching = matching
+        self.allow = allow
+        self.memcg_path = memcg_path,
+        self.addr_start = addr_start
+        self.addr_end = addr_end
+        self.target_idx = target_idx
+        self.min_ = min_
+        self.max_ = max_
+
+    def sysfs_dir(self):
+        return os.path.join(self.filters.sysfs_dir(), '%d' % self.idx)
+
+    def stage(self):
+        err = write_file(os.path.join(self.sysfs_dir(), 'type'), self.type_)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'matching'),
+                         self.matching)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'allow'), self.allow)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'memcg_path'),
+                         self.memcg_path)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'addr_start'),
+                         self.addr_start)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'addr_end'),
+                         self.addr_end)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'damon_target_idx'),
+                         self.target_idx)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'min'), self.min_)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'max'), self.max_)
+        if err is not None:
+            return err
+        return None
+
+class DamosFilters:
+    name = None
+    filters = None
+    scheme = None   # owner scheme
+
+    def __init__(self, name, filters=[]):
+        self.name = name
+        self.filters = filters
+        for idx, filter_ in enumerate(self.filters):
+            filter_.idx = idx
+            filter_.filters = self
+
+    def sysfs_dir(self):
+        return os.path.join(self.scheme.sysfs_dir(), self.name)
+
+    def stage(self):
+        err = write_file(os.path.join(self.sysfs_dir(), 'nr_filters'),
+                         len(self.filters))
+        if err is not None:
+            return err
+        for filter_ in self.filters:
+            err = filter_.stage()
+            if err is not None:
+                return err
+        return None
+
+class DamosDest:
+    id = None
+    weight = None
+    idx = None
+    dests = None    # owner dests
+
+    def __init__(self, id=0, weight=0):
+        self.id = id
+        self.weight = weight
+
+    def sysfs_dir(self):
+        return os.path.join(self.dests.sysfs_dir(), '%d' % self.idx)
+
+    def stage(self):
+        err = write_file(os.path.join(self.sysfs_dir(), 'id'), self.id)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'weight'), self.weight)
+        if err is not None:
+            return err
+        return None
+
+class DamosDests:
+    dests = None
+    scheme = None   # owner scheme
+
+    def __init__(self, dests=[]):
+        self.dests = dests
+        for idx, dest in enumerate(self.dests):
+            dest.idx = idx
+            dest.dests = self
+
+    def sysfs_dir(self):
+        return os.path.join(self.scheme.sysfs_dir(), 'dests')
+
+    def stage(self):
+        err = write_file(os.path.join(self.sysfs_dir(), 'nr_dests'),
+                         len(self.dests))
+        if err is not None:
+            return err
+        for dest in self.dests:
+            err = dest.stage()
+            if err is not None:
+                return err
+        return None
+
+class DamosStats:
+    nr_tried = None
+    sz_tried = None
+    nr_applied = None
+    sz_applied = None
+    qt_exceeds = None
+
+    def __init__(self, nr_tried, sz_tried, nr_applied, sz_applied, qt_exceeds):
+        self.nr_tried = nr_tried
+        self.sz_tried = sz_tried
+        self.nr_applied = nr_applied
+        self.sz_applied = sz_applied
+        self.qt_exceeds = qt_exceeds
+
+class DamosTriedRegion:
+    def __init__(self, start, end, nr_accesses, age):
+        self.start = start
+        self.end = end
+        self.nr_accesses = nr_accesses
+        self.age = age
+
+class Damos:
+    action = None
+    access_pattern = None
+    quota = None
+    watermarks = None
+    core_filters = None
+    ops_filters = None
+    filters = None
+    apply_interval_us = None
+    target_nid = None
+    dests = None
+    idx = None
+    context = None
+    tried_bytes = None
+    stats = None
+    tried_regions = None
+
+    def __init__(self, action='stat', access_pattern=DamosAccessPattern(),
+                 quota=DamosQuota(), watermarks=DamosWatermarks(),
+                 core_filters=[], ops_filters=[], filters=[], target_nid=0,
+                 dests=DamosDests(), apply_interval_us=0):
+        self.action = action
+        self.access_pattern = access_pattern
+        self.access_pattern.scheme = self
+        self.quota = quota
+        self.quota.scheme = self
+        self.watermarks = watermarks
+        self.watermarks.scheme = self
+
+        self.core_filters = DamosFilters(name='core_filters',
+                                         filters=core_filters)
+        self.core_filters.scheme = self
+        self.ops_filters = DamosFilters(name='ops_filters',
+                                         filters=ops_filters)
+        self.ops_filters.scheme = self
+        self.filters = DamosFilters(name='filters', filters=filters)
+        self.filters.scheme = self
+
+        self.target_nid = target_nid
+        self.dests = dests
+        self.dests.scheme = self
+
+        self.apply_interval_us = apply_interval_us
+
+    def sysfs_dir(self):
+        return os.path.join(
+                self.context.sysfs_dir(), 'schemes', '%d' % self.idx)
+
+    def stage(self):
+        err = write_file(os.path.join(self.sysfs_dir(), 'action'), self.action)
+        if err is not None:
+            return err
+        err = self.access_pattern.stage()
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'apply_interval_us'),
+                         '%d' % self.apply_interval_us)
+        if err is not None:
+            return err
+
+        err = self.quota.stage()
+        if err is not None:
+            return err
+
+        err = self.watermarks.stage()
+        if err is not None:
+            return err
+
+        err = self.core_filters.stage()
+        if err is not None:
+            return err
+        err = self.ops_filters.stage()
+        if err is not None:
+            return err
+        err = self.filters.stage()
+        if err is not None:
+            return err
+
+        err = write_file(os.path.join(self.sysfs_dir(), 'target_nid'), '%d' %
+                         self.target_nid)
+        if err is not None:
+            return err
+
+        err = self.dests.stage()
+        if err is not None:
+            return err
+
+class DamonTarget:
+    pid = None
+    obsolete = None
+    # todo: Support target regions if test is made
+    idx = None
+    context = None
+
+    def __init__(self, pid, obsolete=False):
+        self.pid = pid
+        self.obsolete = obsolete
+
+    def sysfs_dir(self):
+        return os.path.join(
+                self.context.sysfs_dir(), 'targets', '%d' % self.idx)
+
+    def stage(self):
+        err = write_file(
+                os.path.join(self.sysfs_dir(), 'regions', 'nr_regions'), '0')
+        if err is not None:
+            return err
+        err = write_file(
+                os.path.join(self.sysfs_dir(), 'pid_target'), self.pid)
+        if err is not None:
+            return err
+        return write_file(
+                os.path.join(self.sysfs_dir(), 'obsolete_target'),
+                'Y' if self.obsolete else 'N')
+
+class IntervalsGoal:
+    access_bp = None
+    aggrs = None
+    min_sample_us = None
+    max_sample_us = None
+    attrs = None    # owner DamonAttrs
+
+    def __init__(self, access_bp=0, aggrs=0, min_sample_us=0, max_sample_us=0):
+        self.access_bp = access_bp
+        self.aggrs = aggrs
+        self.min_sample_us = min_sample_us
+        self.max_sample_us = max_sample_us
+
+    def sysfs_dir(self):
+        return os.path.join(self.attrs.interval_sysfs_dir(), 'intervals_goal')
+
+    def stage(self):
+        err = write_file(
+                os.path.join(self.sysfs_dir(), 'access_bp'), self.access_bp)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'aggrs'), self.aggrs)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'min_sample_us'),
+                         self.min_sample_us)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'max_sample_us'),
+                         self.max_sample_us)
+        if err is not None:
+            return err
+        return None
+
+class DamonAttrs:
+    sample_us = None
+    aggr_us = None
+    intervals_goal = None
+    update_us = None
+    min_nr_regions = None
+    max_nr_regions = None
+    context = None
+
+    def __init__(self, sample_us=5000, aggr_us=100000,
+                 intervals_goal=IntervalsGoal(), update_us=1000000,
+            min_nr_regions=10, max_nr_regions=1000):
+        self.sample_us = sample_us
+        self.aggr_us = aggr_us
+        self.intervals_goal = intervals_goal
+        self.intervals_goal.attrs = self
+        self.update_us = update_us
+        self.min_nr_regions = min_nr_regions
+        self.max_nr_regions = max_nr_regions
+
+    def interval_sysfs_dir(self):
+        return os.path.join(self.context.sysfs_dir(), 'monitoring_attrs',
+                'intervals')
+
+    def nr_regions_range_sysfs_dir(self):
+        return os.path.join(self.context.sysfs_dir(), 'monitoring_attrs',
+                'nr_regions')
+
+    def stage(self):
+        err = write_file(os.path.join(self.interval_sysfs_dir(), 'sample_us'),
+                self.sample_us)
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.interval_sysfs_dir(), 'aggr_us'),
+                self.aggr_us)
+        if err is not None:
+            return err
+        err = self.intervals_goal.stage()
+        if err is not None:
+            return err
+        err = write_file(os.path.join(self.interval_sysfs_dir(), 'update_us'),
+                self.update_us)
+        if err is not None:
+            return err
+
+        err = write_file(
+                os.path.join(self.nr_regions_range_sysfs_dir(), 'min'),
+                self.min_nr_regions)
+        if err is not None:
+            return err
+
+        err = write_file(
+                os.path.join(self.nr_regions_range_sysfs_dir(), 'max'),
+                self.max_nr_regions)
+        if err is not None:
+            return err
+
+class DamonCtx:
+    ops = None
+    monitoring_attrs = None
+    targets = None
+    schemes = None
+    kdamond = None
+    idx = None
+
+    def __init__(self, ops='paddr', monitoring_attrs=DamonAttrs(), targets=[],
+            schemes=[]):
+        self.ops = ops
+        self.monitoring_attrs = monitoring_attrs
+        self.monitoring_attrs.context = self
+
+        self.targets = targets
+        for idx, target in enumerate(self.targets):
+            target.idx = idx
+            target.context = self
+
+        self.schemes = schemes
+        for idx, scheme in enumerate(self.schemes):
+            scheme.idx = idx
+            scheme.context = self
+
+    def sysfs_dir(self):
+        return os.path.join(self.kdamond.sysfs_dir(), 'contexts',
+                '%d' % self.idx)
+
+    def stage(self):
+        err = write_file(
+                os.path.join(self.sysfs_dir(), 'operations'), self.ops)
+        if err is not None:
+            return err
+        err = self.monitoring_attrs.stage()
+        if err is not None:
+            return err
+
+        nr_targets_file = os.path.join(
+                self.sysfs_dir(), 'targets', 'nr_targets')
+        content, err = read_file(nr_targets_file)
+        if err is not None:
+            return err
+        if int(content) != len(self.targets):
+            err = write_file(nr_targets_file, '%d' % len(self.targets))
+            if err is not None:
+                return err
+        for target in self.targets:
+            err = target.stage()
+            if err is not None:
+                return err
+
+        nr_schemes_file = os.path.join(
+                self.sysfs_dir(), 'schemes', 'nr_schemes')
+        content, err = read_file(nr_schemes_file)
+        if err is not None:
+            return err
+        if int(content) != len(self.schemes):
+            err = write_file(nr_schemes_file, '%d' % len(self.schemes))
+            if err is not None:
+                return err
+        for scheme in self.schemes:
+            err = scheme.stage()
+            if err is not None:
+                return err
+        return None
+
+class Kdamond:
+    state = None
+    pid = None
+    contexts = None
+    idx = None      # index of this kdamond between siblings
+    kdamonds = None # parent
+
+    def __init__(self, contexts=[]):
+        self.contexts = contexts
+        for idx, context in enumerate(self.contexts):
+            context.idx = idx
+            context.kdamond = self
+
+    def sysfs_dir(self):
+        return os.path.join(self.kdamonds.sysfs_dir(), '%d' % self.idx)
+
+    def start(self):
+        nr_contexts_file = os.path.join(self.sysfs_dir(),
+                'contexts', 'nr_contexts')
+        content, err = read_file(nr_contexts_file)
+        if err is not None:
+            return err
+        if int(content) != len(self.contexts):
+            err = write_file(nr_contexts_file, '%d' % len(self.contexts))
+            if err is not None:
+                return err
+
+        for context in self.contexts:
+            err = context.stage()
+            if err is not None:
+                return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'state'), 'on')
+        if err is not None:
+            return err
+        self.pid, err = read_file(os.path.join(self.sysfs_dir(), 'pid'))
+        return err
+
+    def stop(self):
+        err = write_file(os.path.join(self.sysfs_dir(), 'state'), 'off')
+        return err
+
+    def update_schemes_tried_regions(self):
+        err = write_file(os.path.join(self.sysfs_dir(), 'state'),
+                         'update_schemes_tried_regions')
+        if err is not None:
+            return err
+        for context in self.contexts:
+            for scheme in context.schemes:
+                tried_regions = []
+                tried_regions_dir = os.path.join(
+                        scheme.sysfs_dir(), 'tried_regions')
+                region_indices = []
+                for filename in os.listdir(
+                        os.path.join(scheme.sysfs_dir(), 'tried_regions')):
+                    tried_region_dir = os.path.join(tried_regions_dir, filename)
+                    if not os.path.isdir(tried_region_dir):
+                        continue
+                    region_indices.append(int(filename))
+                for region_idx in sorted(region_indices):
+                    tried_region_dir = os.path.join(tried_regions_dir,
+                                                    '%d' % region_idx)
+                    region_values = []
+                    for f in ['start', 'end', 'nr_accesses', 'age']:
+                        content, err = read_file(
+                                os.path.join(tried_region_dir, f))
+                        if err is not None:
+                            return err
+                        region_values.append(int(content))
+                    tried_regions.append(DamosTriedRegion(*region_values))
+                scheme.tried_regions = tried_regions
+
+    def update_schemes_tried_bytes(self):
+        err = write_file(os.path.join(self.sysfs_dir(), 'state'),
+                'update_schemes_tried_bytes')
+        if err is not None:
+            return err
+        for context in self.contexts:
+            for scheme in context.schemes:
+                content, err = read_file(os.path.join(scheme.sysfs_dir(),
+                    'tried_regions', 'total_bytes'))
+                if err is not None:
+                    return err
+                scheme.tried_bytes = int(content)
+
+    def update_schemes_stats(self):
+        err = write_file(os.path.join(self.sysfs_dir(), 'state'),
+                'update_schemes_stats')
+        if err is not None:
+            return err
+        for context in self.contexts:
+            for scheme in context.schemes:
+                stat_values = []
+                for stat in ['nr_tried', 'sz_tried', 'nr_applied',
+                             'sz_applied', 'qt_exceeds']:
+                    content, err = read_file(
+                            os.path.join(scheme.sysfs_dir(), 'stats', stat))
+                    if err is not None:
+                        return err
+                    stat_values.append(int(content))
+                scheme.stats = DamosStats(*stat_values)
+
+    def update_schemes_effective_quotas(self):
+        err = write_file(os.path.join(self.sysfs_dir(), 'state'),
+                         'update_schemes_effective_quotas')
+        if err is not None:
+            return err
+        for context in self.contexts:
+            for scheme in context.schemes:
+                for goal in scheme.quota.goals:
+                    content, err = read_file(
+                            os.path.join(scheme.quota.sysfs_dir(),
+                                         'effective_bytes'))
+                    if err is not None:
+                        return err
+                    goal.effective_bytes = int(content)
+        return None
+
+    def commit(self):
+        nr_contexts_file = os.path.join(self.sysfs_dir(),
+                'contexts', 'nr_contexts')
+        content, err = read_file(nr_contexts_file)
+        if err is not None:
+            return err
+        if int(content) != len(self.contexts):
+            err = write_file(nr_contexts_file, '%d' % len(self.contexts))
+            if err is not None:
+                return err
+
+        for context in self.contexts:
+            err = context.stage()
+            if err is not None:
+                return err
+        err = write_file(os.path.join(self.sysfs_dir(), 'state'), 'commit')
+        return err
+
+
+    def commit_schemes_quota_goals(self):
+        for context in self.contexts:
+            for scheme in context.schemes:
+                for goal in scheme.quota.goals:
+                    err = goal.stage()
+                    if err is not None:
+                        print('commit_schemes_quota_goals failed stagign: %s'%
+                              err)
+                        exit(1)
+        return write_file(os.path.join(self.sysfs_dir(), 'state'),
+                         'commit_schemes_quota_goals')
+
+class Kdamonds:
+    kdamonds = []
+
+    def __init__(self, kdamonds=[]):
+        self.kdamonds = kdamonds
+        for idx, kdamond in enumerate(self.kdamonds):
+            kdamond.idx = idx
+            kdamond.kdamonds = self
+
+    def sysfs_dir(self):
+        return os.path.join(sysfs_root, 'kdamonds')
+
+    def start(self):
+        err = write_file(os.path.join(self.sysfs_dir(),  'nr_kdamonds'),
+                '%s' % len(self.kdamonds))
+        if err is not None:
+            return err
+        for kdamond in self.kdamonds:
+            err = kdamond.start()
+            if err is not None:
+                return err
+        return None
+
+    def stop(self):
+        for kdamond in self.kdamonds:
+            err = kdamond.stop()
+            if err is not None:
+                return err
+        return None
diff --git a/tools/testing/selftests/damon/_debugfs_common.sh b/tools/testing/selftests/damon/_debugfs_common.sh
deleted file mode 100644
index 48989d4813ae..000000000000
--- a/tools/testing/selftests/damon/_debugfs_common.sh
+++ /dev/null
@@ -1,52 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-test_write_result() {
-	file=$1
-	content=$2
-	orig_content=$3
-	expect_reason=$4
-	expected=$5
-
-	echo "$content" > "$file"
-	if [ $? -ne "$expected" ]
-	then
-		echo "writing $content to $file doesn't return $expected"
-		echo "expected because: $expect_reason"
-		echo "$orig_content" > "$file"
-		exit 1
-	fi
-}
-
-test_write_succ() {
-	test_write_result "$1" "$2" "$3" "$4" 0
-}
-
-test_write_fail() {
-	test_write_result "$1" "$2" "$3" "$4" 1
-}
-
-test_content() {
-	file=$1
-	orig_content=$2
-	expected=$3
-	expect_reason=$4
-
-	content=$(cat "$file")
-	if [ "$content" != "$expected" ]
-	then
-		echo "reading $file expected $expected but $content"
-		echo "expected because: $expect_reason"
-		echo "$orig_content" > "$file"
-		exit 1
-	fi
-}
-
-source ./_chk_dependency.sh
-
-damon_onoff="$DBGFS/monitor_on"
-if [ $(cat "$damon_onoff") = "on" ]
-then
-	echo "monitoring is on"
-	exit $ksft_skip
-fi
diff --git a/tools/testing/selftests/damon/access_memory.c b/tools/testing/selftests/damon/access_memory.c
new file mode 100644
index 000000000000..56b17e8fe1be
--- /dev/null
+++ b/tools/testing/selftests/damon/access_memory.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Artificial memory access program for testing DAMON.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+
+int main(int argc, char *argv[])
+{
+	char **regions;
+	clock_t start_clock;
+	int nr_regions;
+	int sz_region;
+	int access_time_ms;
+	int i;
+
+	if (argc != 4) {
+		printf("Usage: %s <number> <size (bytes)> <time (ms)>\n",
+				argv[0]);
+		return -1;
+	}
+
+	nr_regions = atoi(argv[1]);
+	sz_region = atoi(argv[2]);
+	access_time_ms = atoi(argv[3]);
+
+	regions = malloc(sizeof(*regions) * nr_regions);
+	for (i = 0; i < nr_regions; i++)
+		regions[i] = malloc(sz_region);
+
+	for (i = 0; i < nr_regions; i++) {
+		start_clock = clock();
+		while ((clock() - start_clock) * 1000 / CLOCKS_PER_SEC <
+				access_time_ms)
+			memset(regions[i], i, sz_region);
+	}
+	return 0;
+}
diff --git a/tools/testing/selftests/damon/access_memory_even.c b/tools/testing/selftests/damon/access_memory_even.c
new file mode 100644
index 000000000000..93f3a71bcfd4
--- /dev/null
+++ b/tools/testing/selftests/damon/access_memory_even.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Artificial memory access program for testing DAMON.
+ *
+ * Receives number of regions and size of each region from user.  Allocate the
+ * regions and repeatedly access even numbered (starting from zero) regions.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+int main(int argc, char *argv[])
+{
+	char **regions;
+	int nr_regions;
+	int sz_region;
+	int i;
+
+	if (argc != 3) {
+		printf("Usage: %s <number> <size (bytes)>\n", argv[0]);
+		return -1;
+	}
+
+	nr_regions = atoi(argv[1]);
+	sz_region = atoi(argv[2]);
+
+	regions = malloc(sizeof(*regions) * nr_regions);
+	for (i = 0; i < nr_regions; i++)
+		regions[i] = malloc(sz_region);
+
+	while (1) {
+		for (i = 0; i < nr_regions; i++) {
+			if (i % 2 == 0)
+				memset(regions[i], i, sz_region);
+		}
+	}
+	return 0;
+}
diff --git a/tools/testing/selftests/damon/config b/tools/testing/selftests/damon/config
new file mode 100644
index 000000000000..a68a9fead5dc
--- /dev/null
+++ b/tools/testing/selftests/damon/config
@@ -0,0 +1,6 @@
+CONFIG_DAMON=y
+CONFIG_DAMON_SYSFS=y
+CONFIG_DAMON_PADDR=y
+CONFIG_DAMON_VADDR=y
+CONFIG_DAMON_RECLAIM=y
+CONFIG_DAMON_LRU_SORT=y
diff --git a/tools/testing/selftests/damon/damon_nr_regions.py b/tools/testing/selftests/damon/damon_nr_regions.py
new file mode 100755
index 000000000000..58f3291fed12
--- /dev/null
+++ b/tools/testing/selftests/damon/damon_nr_regions.py
@@ -0,0 +1,147 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import subprocess
+import time
+
+import _damon_sysfs
+
+def test_nr_regions(real_nr_regions, min_nr_regions, max_nr_regions):
+    '''
+    Create process of the given 'real_nr_regions' regions, monitor it using
+    DAMON with given '{min,max}_nr_regions' monitoring parameter.
+
+    Exit with non-zero return code if the given {min,max}_nr_regions is not
+    kept.
+    '''
+    sz_region = 10 * 1024 * 1024
+    proc = subprocess.Popen(['./access_memory_even', '%d' % real_nr_regions,
+                             '%d' % sz_region])
+
+    # stat every monitored regions
+    kdamonds = _damon_sysfs.Kdamonds([_damon_sysfs.Kdamond(
+            contexts=[_damon_sysfs.DamonCtx(
+                monitoring_attrs=_damon_sysfs.DamonAttrs(
+                    min_nr_regions=min_nr_regions,
+                    max_nr_regions=max_nr_regions),
+                ops='vaddr',
+                targets=[_damon_sysfs.DamonTarget(pid=proc.pid)],
+                schemes=[_damon_sysfs.Damos(action='stat',
+                    )] # schemes
+                )] # contexts
+            )]) # kdamonds
+
+    err = kdamonds.start()
+    if err is not None:
+        proc.terminate()
+        print('kdamond start failed: %s' % err)
+        exit(1)
+
+    collected_nr_regions = []
+    while proc.poll() is None:
+        time.sleep(0.1)
+        err = kdamonds.kdamonds[0].update_schemes_tried_regions()
+        if err is not None:
+            proc.terminate()
+            print('tried regions update failed: %s' % err)
+            exit(1)
+
+        scheme = kdamonds.kdamonds[0].contexts[0].schemes[0]
+        if scheme.tried_regions is None:
+            proc.terminate()
+            print('tried regions is not collected')
+            exit(1)
+
+        nr_tried_regions = len(scheme.tried_regions)
+        if nr_tried_regions <= 0:
+            proc.terminate()
+            print('tried regions is not created')
+            exit(1)
+        collected_nr_regions.append(nr_tried_regions)
+        if len(collected_nr_regions) > 10:
+            break
+    proc.terminate()
+    kdamonds.stop()
+
+    test_name = 'nr_regions test with %d/%d/%d real/min/max nr_regions' % (
+            real_nr_regions, min_nr_regions, max_nr_regions)
+    collected_nr_regions.sort()
+    if (collected_nr_regions[0] < min_nr_regions or
+        collected_nr_regions[-1] > max_nr_regions):
+        print('fail %s' % test_name)
+        print('number of regions that collected are:')
+        for nr in collected_nr_regions:
+            print(nr)
+        exit(1)
+    print('pass %s ' % test_name)
+
+def main():
+    # test min_nr_regions larger than real nr regions
+    test_nr_regions(10, 20, 100)
+
+    # test max_nr_regions smaller than real nr regions
+    test_nr_regions(15, 3, 10)
+
+    # test online-tuned max_nr_regions that smaller than real nr regions
+    sz_region = 10 * 1024 * 1024
+    proc = subprocess.Popen(['./access_memory_even', '14', '%d' % sz_region])
+
+    # stat every monitored regions
+    kdamonds = _damon_sysfs.Kdamonds([_damon_sysfs.Kdamond(
+            contexts=[_damon_sysfs.DamonCtx(
+                monitoring_attrs=_damon_sysfs.DamonAttrs(
+                    min_nr_regions=10, max_nr_regions=1000),
+                ops='vaddr',
+                targets=[_damon_sysfs.DamonTarget(pid=proc.pid)],
+                schemes=[_damon_sysfs.Damos(action='stat',
+                    )] # schemes
+                )] # contexts
+            )]) # kdamonds
+
+    err = kdamonds.start()
+    if err is not None:
+        proc.terminate()
+        print('kdamond start failed: %s' % err)
+        exit(1)
+
+    # wait until the real regions are found
+    time.sleep(3)
+
+    attrs = kdamonds.kdamonds[0].contexts[0].monitoring_attrs
+    attrs.min_nr_regions = 3
+    attrs.max_nr_regions = 7
+    attrs.update_us = 100000
+    err = kdamonds.kdamonds[0].commit()
+    if err is not None:
+        proc.terminate()
+        print('commit failed: %s' % err)
+        exit(1)
+    # wait for next merge operation is executed
+    time.sleep(0.3)
+
+    err = kdamonds.kdamonds[0].update_schemes_tried_regions()
+    if err is not None:
+        proc.terminate()
+        print('tried regions update failed: %s' % err)
+        exit(1)
+
+    scheme = kdamonds.kdamonds[0].contexts[0].schemes[0]
+    if scheme.tried_regions is None:
+        proc.terminate()
+        print('tried regions is not collected')
+        exit(1)
+
+    nr_tried_regions = len(scheme.tried_regions)
+    if nr_tried_regions <= 0:
+        proc.terminate()
+        print('tried regions is not created')
+        exit(1)
+    proc.terminate()
+
+    if nr_tried_regions > 7:
+        print('fail online-tuned max_nr_regions: %d > 7' % nr_tried_regions)
+        exit(1)
+    print('pass online-tuned max_nr_regions')
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/testing/selftests/damon/damos_apply_interval.py b/tools/testing/selftests/damon/damos_apply_interval.py
new file mode 100755
index 000000000000..f04d43702481
--- /dev/null
+++ b/tools/testing/selftests/damon/damos_apply_interval.py
@@ -0,0 +1,67 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import subprocess
+import time
+
+import _damon_sysfs
+
+def main():
+    # access two 10 MiB memory regions, 2 second per each
+    sz_region = 10 * 1024 * 1024
+    proc = subprocess.Popen(['./access_memory', '2', '%d' % sz_region, '2000'])
+
+    # Set quota up to 1 MiB per 100 ms
+    kdamonds = _damon_sysfs.Kdamonds([_damon_sysfs.Kdamond(
+            contexts=[_damon_sysfs.DamonCtx(
+                ops='vaddr',
+                targets=[_damon_sysfs.DamonTarget(pid=proc.pid)],
+                schemes=[
+                    _damon_sysfs.Damos(
+                        access_pattern=_damon_sysfs.DamosAccessPattern(
+                            # >= 25% access rate, >= 200ms age
+                            nr_accesses=[5, 20], age=[2, 2**64 - 1]),
+                        # aggregation interval (100 ms) is used
+                        apply_interval_us=0),
+                    # use 10ms apply interval
+                    _damon_sysfs.Damos(
+                        access_pattern=_damon_sysfs.DamosAccessPattern(
+                            # >= 25% access rate, >= 200ms age
+                            nr_accesses=[5, 20], age=[2, 2**64 - 1]),
+                        # explicitly set 10 ms apply interval
+                        apply_interval_us=10 * 1000)
+                    ] # schemes
+                )] # contexts
+            )]) # kdamonds
+
+    err = kdamonds.start()
+    if err != None:
+        print('kdamond start failed: %s' % err)
+        exit(1)
+
+    wss_collected = []
+    nr_quota_exceeds = 0
+    while proc.poll() == None:
+        time.sleep(0.1)
+        err = kdamonds.kdamonds[0].update_schemes_stats()
+        if err != None:
+            print('stats update failed: %s' % err)
+            exit(1)
+    schemes = kdamonds.kdamonds[0].contexts[0].schemes
+    nr_tried_stats = [s.stats.nr_tried for s in schemes]
+    if nr_tried_stats[0] == 0 or nr_tried_stats[1] == 0:
+        print('scheme(s) are not tried')
+        exit(1)
+
+    # Because the second scheme was having the apply interval that is ten times
+    # lower than that of the first scheme, the second scheme should be tried
+    # about ten times more frequently than the first scheme.  For possible
+    # timing errors, check if it was at least nine times more freuqnetly tried.
+    ratio = nr_tried_stats[1] / nr_tried_stats[0]
+    if ratio < 9:
+        print('%d / %d = %f (< 9)' %
+              (nr_tried_stats[1], nr_tried_stats[0], ratio))
+        exit(1)
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/testing/selftests/damon/damos_quota.py b/tools/testing/selftests/damon/damos_quota.py
new file mode 100755
index 000000000000..57c4937aaed2
--- /dev/null
+++ b/tools/testing/selftests/damon/damos_quota.py
@@ -0,0 +1,70 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import subprocess
+import time
+
+import _damon_sysfs
+
+def main():
+    # access two 10 MiB memory regions, 2 second per each
+    sz_region = 10 * 1024 * 1024
+    proc = subprocess.Popen(['./access_memory', '2', '%d' % sz_region, '2000'])
+
+    # Set quota up to 1 MiB per 100 ms
+    sz_quota = 1024 * 1024 # 1 MiB
+    quota_reset_interval = 100 # 100 ms
+    kdamonds = _damon_sysfs.Kdamonds([_damon_sysfs.Kdamond(
+            contexts=[_damon_sysfs.DamonCtx(
+                ops='vaddr',
+                targets=[_damon_sysfs.DamonTarget(pid=proc.pid)],
+                schemes=[_damon_sysfs.Damos(
+                    access_pattern=_damon_sysfs.DamosAccessPattern(
+                        # >= 25% access rate, >= 200ms age
+                        nr_accesses=[5, 20], age=[2, 2**64 - 1]),
+                    quota=_damon_sysfs.DamosQuota(
+                        sz=sz_quota, reset_interval_ms=quota_reset_interval)
+                    )] # schemes
+                )] # contexts
+            )]) # kdamonds
+
+    err = kdamonds.start()
+    if err != None:
+        print('kdamond start failed: %s' % err)
+        exit(1)
+
+    wss_collected = []
+    nr_quota_exceeds = 0
+    while proc.poll() == None:
+        time.sleep(0.1)
+        err = kdamonds.kdamonds[0].update_schemes_tried_bytes()
+        if err != None:
+            print('tried bytes update failed: %s' % err)
+            exit(1)
+        err = kdamonds.kdamonds[0].update_schemes_stats()
+        if err != None:
+            print('stats update failed: %s' % err)
+            exit(1)
+
+        scheme = kdamonds.kdamonds[0].contexts[0].schemes[0]
+        wss_collected.append(scheme.tried_bytes)
+        nr_quota_exceeds = scheme.stats.qt_exceeds
+
+    wss_collected.sort()
+    nr_expected_quota_exceeds = 0
+    for wss in wss_collected:
+        if wss > sz_quota:
+            print('quota is not kept: %s > %s' % (wss, sz_quota))
+            print('collected samples are as below')
+            print('\n'.join(['%d' % wss for wss in wss_collected]))
+            exit(1)
+        if wss == sz_quota:
+            nr_expected_quota_exceeds += 1
+
+    if nr_quota_exceeds < nr_expected_quota_exceeds:
+        print('quota is exceeded less than expected: %d < %d' %
+              (nr_quota_exceeds, nr_expected_quota_exceeds))
+        exit(1)
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/testing/selftests/damon/damos_quota_goal.py b/tools/testing/selftests/damon/damos_quota_goal.py
new file mode 100755
index 000000000000..f76e0412b564
--- /dev/null
+++ b/tools/testing/selftests/damon/damos_quota_goal.py
@@ -0,0 +1,80 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import subprocess
+import time
+
+import _damon_sysfs
+
+def main():
+    # access two 10 MiB memory regions, 2 second per each
+    sz_region = 10 * 1024 * 1024
+    proc = subprocess.Popen(['./access_memory', '2', '%d' % sz_region, '2000'])
+
+    goal = _damon_sysfs.DamosQuotaGoal(
+            metric=_damon_sysfs.qgoal_metric_user_input, target_value=10000)
+    kdamonds = _damon_sysfs.Kdamonds([_damon_sysfs.Kdamond(
+            contexts=[_damon_sysfs.DamonCtx(
+                ops='vaddr',
+                targets=[_damon_sysfs.DamonTarget(pid=proc.pid)],
+                schemes=[_damon_sysfs.Damos(
+                    action='stat',
+                    quota=_damon_sysfs.DamosQuota(
+                        goals=[goal], reset_interval_ms=100),
+                    )] # schemes
+                )] # contexts
+            )]) # kdamonds
+
+    err = kdamonds.start()
+    if err != None:
+        print('kdamond start failed: %s' % err)
+        exit(1)
+
+    score_values_to_test = [0, 15000, 5000, 18000]
+    while proc.poll() == None:
+        if len(score_values_to_test) == 0:
+            time.sleep(0.1)
+            continue
+
+        goal.current_value = score_values_to_test.pop(0)
+        expect_increase = goal.current_value < goal.target_value
+
+        err = kdamonds.kdamonds[0].commit_schemes_quota_goals()
+        if err is not None:
+            print('commit_schemes_quota_goals failed: %s' % err)
+            exit(1)
+
+        err = kdamonds.kdamonds[0].update_schemes_effective_quotas()
+        if err is not None:
+            print('before-update_schemes_effective_quotas failed: %s' % err)
+            exit(1)
+        last_effective_bytes = goal.effective_bytes
+
+        time.sleep(0.5)
+
+        err = kdamonds.kdamonds[0].update_schemes_effective_quotas()
+        if err is not None:
+            print('after-update_schemes_effective_quotas failed: %s' % err)
+            exit(1)
+
+        print('score: %s, effective quota: %d -> %d (%.3fx)' % (
+            goal.current_value, last_effective_bytes, goal.effective_bytes,
+            goal.effective_bytes / last_effective_bytes
+            if last_effective_bytes != 0 else -1.0))
+
+        if last_effective_bytes == goal.effective_bytes:
+            # effective quota was already minimum that cannot be more reduced
+            if expect_increase is False and last_effective_bytes == 1:
+                continue
+            print('efective bytes not changed: %d' % goal.effective_bytes)
+            exit(1)
+
+        increased = last_effective_bytes < goal.effective_bytes
+        if expect_increase != increased:
+            print('expectation of increase (%s) != increased (%s)' %
+                  (expect_increase, increased))
+            exit(1)
+        last_effective_bytes = goal.effective_bytes
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/testing/selftests/damon/damos_tried_regions.py b/tools/testing/selftests/damon/damos_tried_regions.py
new file mode 100755
index 000000000000..3b347eb28bd2
--- /dev/null
+++ b/tools/testing/selftests/damon/damos_tried_regions.py
@@ -0,0 +1,65 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import subprocess
+import time
+
+import _damon_sysfs
+
+def main():
+    # repeatedly access even-numbered ones in 14 regions of 10 MiB size
+    sz_region = 10 * 1024 * 1024
+    proc = subprocess.Popen(['./access_memory_even', '14', '%d' % sz_region])
+
+    # stat every monitored regions
+    kdamonds = _damon_sysfs.Kdamonds([_damon_sysfs.Kdamond(
+            contexts=[_damon_sysfs.DamonCtx(
+                ops='vaddr',
+                targets=[_damon_sysfs.DamonTarget(pid=proc.pid)],
+                schemes=[_damon_sysfs.Damos(action='stat',
+                    )] # schemes
+                )] # contexts
+            )]) # kdamonds
+
+    err = kdamonds.start()
+    if err is not None:
+        proc.terminate()
+        print('kdamond start failed: %s' % err)
+        exit(1)
+
+    collected_nr_regions = []
+    while proc.poll() is None:
+        time.sleep(0.1)
+        err = kdamonds.kdamonds[0].update_schemes_tried_regions()
+        if err is not None:
+            proc.terminate()
+            print('tried regions update failed: %s' % err)
+            exit(1)
+
+        scheme = kdamonds.kdamonds[0].contexts[0].schemes[0]
+        if scheme.tried_regions is None:
+            proc.terminate()
+            print('tried regions is not collected')
+            exit(1)
+
+        nr_tried_regions = len(scheme.tried_regions)
+        if nr_tried_regions <= 0:
+            proc.terminate()
+            print('tried regions is not created')
+            exit(1)
+        collected_nr_regions.append(nr_tried_regions)
+        if len(collected_nr_regions) > 10:
+            break
+    proc.terminate()
+
+    collected_nr_regions.sort()
+    sample = collected_nr_regions[4]
+    print('50-th percentile nr_regions: %d' % sample)
+    print('expectation (>= 14) is %s' % 'met' if sample >= 14 else 'not met')
+    if collected_nr_regions[4] < 14:
+        print('full nr_regions:')
+        print('\n'.join(collected_nr_regions))
+        exit(1)
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/testing/selftests/damon/debugfs_attrs.sh b/tools/testing/selftests/damon/debugfs_attrs.sh
deleted file mode 100644
index 902e312bca89..000000000000
--- a/tools/testing/selftests/damon/debugfs_attrs.sh
+++ /dev/null
@@ -1,17 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-source _debugfs_common.sh
-
-# Test attrs file
-# ===============
-
-file="$DBGFS/attrs"
-orig_content=$(cat "$file")
-
-test_write_succ "$file" "1 2 3 4 5" "$orig_content" "valid input"
-test_write_fail "$file" "1 2 3 4" "$orig_content" "no enough fields"
-test_write_fail "$file" "1 2 3 5 4" "$orig_content" \
-	"min_nr_regions > max_nr_regions"
-test_content "$file" "$orig_content" "1 2 3 4 5" "successfully written"
-echo "$orig_content" > "$file"
diff --git a/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh b/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh
deleted file mode 100644
index 4a76e37ef16b..000000000000
--- a/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh
+++ /dev/null
@@ -1,27 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-source _debugfs_common.sh
-
-# Test duplicated context creation
-# ================================
-
-if ! echo foo > "$DBGFS/mk_contexts"
-then
-	echo "context creation failed"
-	exit 1
-fi
-
-if echo foo > "$DBGFS/mk_contexts"
-then
-	echo "duplicate context creation success"
-	exit 1
-fi
-
-if ! echo foo > "$DBGFS/rm_contexts"
-then
-	echo "context deletion failed"
-	exit 1
-fi
-
-exit 0
diff --git a/tools/testing/selftests/damon/debugfs_empty_targets.sh b/tools/testing/selftests/damon/debugfs_empty_targets.sh
deleted file mode 100644
index 87aff8083822..000000000000
--- a/tools/testing/selftests/damon/debugfs_empty_targets.sh
+++ /dev/null
@@ -1,13 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-source _debugfs_common.sh
-
-# Test empty targets case
-# =======================
-
-orig_target_ids=$(cat "$DBGFS/target_ids")
-echo "" > "$DBGFS/target_ids"
-orig_monitor_on=$(cat "$DBGFS/monitor_on")
-test_write_fail "$DBGFS/monitor_on" "on" "orig_monitor_on" "empty target ids"
-echo "$orig_target_ids" > "$DBGFS/target_ids"
diff --git a/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh b/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh
deleted file mode 100644
index 922cadac2950..000000000000
--- a/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh
+++ /dev/null
@@ -1,22 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-source _debugfs_common.sh
-
-# Test huge count read write
-# ==========================
-
-dmesg -C
-
-for file in "$DBGFS/"*
-do
-	./huge_count_read_write "$file"
-done
-
-if dmesg | grep -q WARNING
-then
-	dmesg
-	exit 1
-else
-	exit 0
-fi
diff --git a/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh b/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh
deleted file mode 100644
index 48b7af6b022c..000000000000
--- a/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh
+++ /dev/null
@@ -1,19 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-source _debugfs_common.sh
-
-# Test putting non-ctx files/dirs to rm_contexts file
-# ===================================================
-
-dmesg -C
-
-for file in "$DBGFS/"*
-do
-	echo "$(basename "$f")" > "$DBGFS/rm_contexts"
-	if dmesg | grep -q BUG
-	then
-		dmesg
-		exit 1
-	fi
-done
diff --git a/tools/testing/selftests/damon/debugfs_schemes.sh b/tools/testing/selftests/damon/debugfs_schemes.sh
deleted file mode 100644
index 5b39ab44731c..000000000000
--- a/tools/testing/selftests/damon/debugfs_schemes.sh
+++ /dev/null
@@ -1,19 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-source _debugfs_common.sh
-
-# Test schemes file
-# =================
-
-file="$DBGFS/schemes"
-orig_content=$(cat "$file")
-
-test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3 1 100 3 2 1" \
-	"$orig_content" "valid input"
-test_write_fail "$file" "1 2
-3 4 5 6 3 0 0 0 1 2 3 1 100 3 2 1" "$orig_content" "multi lines"
-test_write_succ "$file" "" "$orig_content" "disabling"
-test_write_fail "$file" "2 1 2 1 10 1 3 10 1 1 1 1 1 1 1 1 2 3" \
-	"$orig_content" "wrong condition ranges"
-echo "$orig_content" > "$file"
diff --git a/tools/testing/selftests/damon/debugfs_target_ids.sh b/tools/testing/selftests/damon/debugfs_target_ids.sh
deleted file mode 100644
index 49aeabdb0aae..000000000000
--- a/tools/testing/selftests/damon/debugfs_target_ids.sh
+++ /dev/null
@@ -1,19 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-source _debugfs_common.sh
-
-# Test target_ids file
-# ====================
-
-file="$DBGFS/target_ids"
-orig_content=$(cat "$file")
-
-test_write_succ "$file" "1 2 3 4" "$orig_content" "valid input"
-test_write_succ "$file" "1 2 abc 4" "$orig_content" "still valid input"
-test_content "$file" "$orig_content" "1 2" "non-integer was there"
-test_write_succ "$file" "abc 2 3" "$orig_content" "the file allows wrong input"
-test_content "$file" "$orig_content" "" "wrong input written"
-test_write_succ "$file" "" "$orig_content" "empty input"
-test_content "$file" "$orig_content" "" "empty input written"
-echo "$orig_content" > "$file"
diff --git a/tools/testing/selftests/damon/drgn_dump_damon_status.py b/tools/testing/selftests/damon/drgn_dump_damon_status.py
new file mode 100755
index 000000000000..5374d18d1fa8
--- /dev/null
+++ b/tools/testing/selftests/damon/drgn_dump_damon_status.py
@@ -0,0 +1,223 @@
+#!/usr/bin/env drgn
+# SPDX-License-Identifier: GPL-2.0
+
+'''
+Read DAMON context data and dump as a json string.
+'''
+import drgn
+from drgn import FaultError, NULL, Object, cast, container_of, execscript, offsetof, reinterpret, sizeof
+from drgn.helpers.common import *
+from drgn.helpers.linux import *
+
+import json
+import sys
+
+if "prog" not in globals():
+    try:
+        prog = drgn.get_default_prog()
+    except drgn.NoDefaultProgramError:
+        prog = drgn.program_from_kernel()
+        drgn.set_default_prog(prog)
+
+def to_dict(object, attr_name_converter):
+    d = {}
+    for attr_name, converter in attr_name_converter:
+        d[attr_name] = converter(getattr(object, attr_name))
+    return d
+
+def ops_to_dict(ops):
+    return to_dict(ops, [
+        ['id', int],
+        ])
+
+def intervals_goal_to_dict(goal):
+    return to_dict(goal, [
+        ['access_bp', int],
+        ['aggrs', int],
+        ['min_sample_us', int],
+        ['max_sample_us', int],
+        ])
+
+def attrs_to_dict(attrs):
+    return to_dict(attrs, [
+        ['sample_interval', int],
+        ['aggr_interval', int],
+        ['ops_update_interval', int],
+        ['intervals_goal', intervals_goal_to_dict],
+        ['min_nr_regions', int],
+        ['max_nr_regions', int],
+        ])
+
+def addr_range_to_dict(addr_range):
+    return to_dict(addr_range, [
+        ['start', int],
+        ['end', int],
+        ])
+
+def region_to_dict(region):
+    return to_dict(region, [
+        ['ar', addr_range_to_dict],
+        ['sampling_addr', int],
+        ['nr_accesses', int],
+        ['nr_accesses_bp', int],
+        ['age', int],
+        ])
+
+def regions_to_list(regions):
+    return [region_to_dict(r)
+            for r in list_for_each_entry(
+                'struct damon_region', regions.address_of_(), 'list')]
+
+def target_to_dict(target):
+    return to_dict(target, [
+        ['pid', int],
+        ['nr_regions', int],
+        ['regions_list', regions_to_list],
+        ['obsolete', bool],
+        ])
+
+def targets_to_list(targets):
+    return [target_to_dict(t)
+            for t in list_for_each_entry(
+                'struct damon_target', targets.address_of_(), 'list')]
+
+def damos_access_pattern_to_dict(pattern):
+    return to_dict(pattern, [
+        ['min_sz_region', int],
+        ['max_sz_region', int],
+        ['min_nr_accesses', int],
+        ['max_nr_accesses', int],
+        ['min_age_region', int],
+        ['max_age_region', int],
+        ])
+
+def damos_quota_goal_to_dict(goal):
+    return to_dict(goal, [
+        ['metric', int],
+        ['target_value', int],
+        ['current_value', int],
+        ['last_psi_total', int],
+        ['nid', int],
+        ])
+
+def damos_quota_goals_to_list(goals):
+    return [damos_quota_goal_to_dict(g)
+            for g in list_for_each_entry(
+                'struct damos_quota_goal', goals.address_of_(), 'list')]
+
+def damos_quota_to_dict(quota):
+    return to_dict(quota, [
+        ['reset_interval', int],
+        ['ms', int], ['sz', int],
+        ['goals', damos_quota_goals_to_list],
+        ['esz', int],
+        ['weight_sz', int],
+        ['weight_nr_accesses', int],
+        ['weight_age', int],
+        ])
+
+def damos_watermarks_to_dict(watermarks):
+    return to_dict(watermarks, [
+        ['metric', int],
+        ['interval', int],
+        ['high', int], ['mid', int], ['low', int],
+        ])
+
+def damos_migrate_dests_to_dict(dests):
+    nr_dests = int(dests.nr_dests)
+    node_id_arr = []
+    weight_arr = []
+    for i in range(nr_dests):
+        node_id_arr.append(int(dests.node_id_arr[i]))
+        weight_arr.append(int(dests.weight_arr[i]))
+    return {
+            'node_id_arr': node_id_arr,
+            'weight_arr': weight_arr,
+            'nr_dests': nr_dests,
+            }
+
+def damos_filter_to_dict(damos_filter):
+    filter_type_keyword = {
+            0: 'anon',
+            1: 'active',
+            2: 'memcg',
+            3: 'young',
+            4: 'hugepage_size',
+            5: 'unmapped',
+            6: 'addr',
+            7: 'target'
+            }
+    dict_ = {
+            'type': filter_type_keyword[int(damos_filter.type)],
+            'matching': bool(damos_filter.matching),
+            'allow': bool(damos_filter.allow),
+            }
+    type_ = dict_['type']
+    if type_ == 'memcg':
+        dict_['memcg_id'] = int(damos_filter.memcg_id)
+    elif type_ == 'addr':
+        dict_['addr_range'] = [int(damos_filter.addr_range.start),
+                               int(damos_filter.addr_range.end)]
+    elif type_ == 'target':
+        dict_['target_idx'] = int(damos_filter.target_idx)
+    elif type_ == 'hugeapge_size':
+        dict_['sz_range'] = [int(damos_filter.sz_range.min),
+                             int(damos_filter.sz_range.max)]
+    return dict_
+
+def scheme_to_dict(scheme):
+    dict_ = to_dict(scheme, [
+        ['pattern', damos_access_pattern_to_dict],
+        ['action', int],
+        ['apply_interval_us', int],
+        ['quota', damos_quota_to_dict],
+        ['wmarks', damos_watermarks_to_dict],
+        ['target_nid', int],
+        ['migrate_dests', damos_migrate_dests_to_dict],
+        ])
+    core_filters = []
+    for f in list_for_each_entry(
+            'struct damos_filter', scheme.core_filters.address_of_(), 'list'):
+        core_filters.append(damos_filter_to_dict(f))
+    dict_['core_filters'] = core_filters
+    ops_filters = []
+    for f in list_for_each_entry(
+            'struct damos_filter', scheme.ops_filters.address_of_(), 'list'):
+        ops_filters.append(damos_filter_to_dict(f))
+    dict_['ops_filters'] = ops_filters
+
+    return dict_
+
+def schemes_to_list(schemes):
+    return [scheme_to_dict(s)
+            for s in list_for_each_entry(
+                'struct damos', schemes.address_of_(), 'list')]
+
+def damon_ctx_to_dict(ctx):
+    return to_dict(ctx, [
+        ['ops', ops_to_dict],
+        ['attrs', attrs_to_dict],
+        ['adaptive_targets', targets_to_list],
+        ['schemes', schemes_to_list],
+        ])
+
+def main():
+    if len(sys.argv) < 3:
+        print('Usage: %s <kdamond pid> <file>' % sys.argv[0])
+        exit(1)
+
+    pid = int(sys.argv[1])
+    file_to_store = sys.argv[2]
+
+    kthread_data = cast('struct kthread *',
+                        find_task(prog, pid).worker_private).data
+    ctx = cast('struct damon_ctx *', kthread_data)
+    status = {'contexts': [damon_ctx_to_dict(ctx)]}
+    if file_to_store == 'stdout':
+        print(json.dumps(status, indent=4))
+    else:
+        with open(file_to_store, 'w') as f:
+            json.dump(status, f, indent=4)
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/testing/selftests/damon/huge_count_read_write.c b/tools/testing/selftests/damon/huge_count_read_write.c
deleted file mode 100644
index a6fe0689f88d..000000000000
--- a/tools/testing/selftests/damon/huge_count_read_write.c
+++ /dev/null
@@ -1,48 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Author: SeongJae Park <sj@kernel.org>
- */
-
-#include <fcntl.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <stdio.h>
-
-#pragma GCC diagnostic push
-#if __GNUC__ >= 11 && __GNUC_MINOR__ >= 1
-/* Ignore read(2) overflow and write(2) overread compile warnings */
-#pragma GCC diagnostic ignored "-Wstringop-overread"
-#pragma GCC diagnostic ignored "-Wstringop-overflow"
-#endif
-
-void write_read_with_huge_count(char *file)
-{
-	int filedesc = open(file, O_RDWR);
-	char buf[25];
-	int ret;
-
-	printf("%s %s\n", __func__, file);
-	if (filedesc < 0) {
-		fprintf(stderr, "failed opening %s\n", file);
-		exit(1);
-	}
-
-	write(filedesc, "", 0xfffffffful);
-	perror("after write: ");
-	ret = read(filedesc, buf, 0xfffffffful);
-	perror("after read: ");
-	close(filedesc);
-}
-
-#pragma GCC diagnostic pop
-
-int main(int argc, char *argv[])
-{
-	if (argc != 2) {
-		fprintf(stderr, "Usage: %s <file>\n", argv[0]);
-		exit(1);
-	}
-	write_read_with_huge_count(argv[1]);
-
-	return 0;
-}
diff --git a/tools/testing/selftests/damon/lru_sort.sh b/tools/testing/selftests/damon/lru_sort.sh
index 61b80197c896..1e4849db78a9 100644..100755
--- a/tools/testing/selftests/damon/lru_sort.sh
+++ b/tools/testing/selftests/damon/lru_sort.sh
@@ -1,14 +1,12 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+source _common.sh
+
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
 
-if [ $EUID -ne 0 ]
-then
-	echo "Run as root"
-	exit $ksft_skip
-fi
+check_dependencies
 
 damon_lru_sort_enabled="/sys/module/damon_lru_sort/parameters/enabled"
 if [ ! -f "$damon_lru_sort_enabled" ]
diff --git a/tools/testing/selftests/damon/reclaim.sh b/tools/testing/selftests/damon/reclaim.sh
index 78dbc2334cbe..e56ceb035129 100644..100755
--- a/tools/testing/selftests/damon/reclaim.sh
+++ b/tools/testing/selftests/damon/reclaim.sh
@@ -1,14 +1,12 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+source _common.sh
+
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
 
-if [ $EUID -ne 0 ]
-then
-	echo "Run as root"
-	exit $ksft_skip
-fi
+check_dependencies
 
 damon_reclaim_enabled="/sys/module/damon_reclaim/parameters/enabled"
 if [ ! -f "$damon_reclaim_enabled" ]
diff --git a/tools/testing/selftests/damon/sysfs.py b/tools/testing/selftests/damon/sysfs.py
new file mode 100755
index 000000000000..9cca71eb0325
--- /dev/null
+++ b/tools/testing/selftests/damon/sysfs.py
@@ -0,0 +1,303 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import json
+import os
+import subprocess
+
+import _damon_sysfs
+
+def dump_damon_status_dict(pid):
+    try:
+        subprocess.check_output(['which', 'drgn'], stderr=subprocess.DEVNULL)
+    except:
+        return None, 'drgn not found'
+    file_dir = os.path.dirname(os.path.abspath(__file__))
+    dump_script = os.path.join(file_dir, 'drgn_dump_damon_status.py')
+    rc = subprocess.call(['drgn', dump_script, pid, 'damon_dump_output'],
+                         stderr=subprocess.DEVNULL)
+    if rc != 0:
+        return None, 'drgn fail'
+    try:
+        with open('damon_dump_output', 'r') as f:
+            return json.load(f), None
+    except Exception as e:
+        return None, 'json.load fail (%s)' % e
+
+def fail(expectation, status):
+    print('unexpected %s' % expectation)
+    print(json.dumps(status, indent=4))
+    exit(1)
+
+def assert_true(condition, expectation, status):
+    if condition is not True:
+        fail(expectation, status)
+
+def assert_watermarks_committed(watermarks, dump):
+    wmark_metric_val = {
+            'none': 0,
+            'free_mem_rate': 1,
+            }
+    assert_true(dump['metric'] == wmark_metric_val[watermarks.metric],
+                'metric', dump)
+    assert_true(dump['interval'] == watermarks.interval, 'interval', dump)
+    assert_true(dump['high'] == watermarks.high, 'high', dump)
+    assert_true(dump['mid'] == watermarks.mid, 'mid', dump)
+    assert_true(dump['low'] == watermarks.low, 'low', dump)
+
+def assert_quota_goal_committed(qgoal, dump):
+    metric_val = {
+            'user_input': 0,
+            'some_mem_psi_us': 1,
+            'node_mem_used_bp': 2,
+            'node_mem_free_bp': 3,
+            }
+    assert_true(dump['metric'] == metric_val[qgoal.metric], 'metric', dump)
+    assert_true(dump['target_value'] == qgoal.target_value, 'target_value',
+                dump)
+    if qgoal.metric == 'user_input':
+        assert_true(dump['current_value'] == qgoal.current_value,
+                    'current_value', dump)
+    assert_true(dump['nid'] == qgoal.nid, 'nid', dump)
+
+def assert_quota_committed(quota, dump):
+    assert_true(dump['reset_interval'] == quota.reset_interval_ms,
+                'reset_interval', dump)
+    assert_true(dump['ms'] == quota.ms, 'ms', dump)
+    assert_true(dump['sz'] == quota.sz, 'sz', dump)
+    for idx, qgoal in enumerate(quota.goals):
+        assert_quota_goal_committed(qgoal, dump['goals'][idx])
+    assert_true(dump['weight_sz'] == quota.weight_sz_permil, 'weight_sz', dump)
+    assert_true(dump['weight_nr_accesses'] == quota.weight_nr_accesses_permil,
+                'weight_nr_accesses', dump)
+    assert_true(
+            dump['weight_age'] == quota.weight_age_permil, 'weight_age', dump)
+
+
+def assert_migrate_dests_committed(dests, dump):
+    assert_true(dump['nr_dests'] == len(dests.dests), 'nr_dests', dump)
+    for idx, dest in enumerate(dests.dests):
+        assert_true(dump['node_id_arr'][idx] == dest.id, 'node_id', dump)
+        assert_true(dump['weight_arr'][idx] == dest.weight, 'weight', dump)
+
+def assert_filter_committed(filter_, dump):
+    assert_true(filter_.type_ == dump['type'], 'type', dump)
+    assert_true(filter_.matching == dump['matching'], 'matching', dump)
+    assert_true(filter_.allow == dump['allow'], 'allow', dump)
+    # TODO: check memcg_path and memcg_id if type is memcg
+    if filter_.type_ == 'addr':
+        assert_true([filter_.addr_start, filter_.addr_end] ==
+                    dump['addr_range'], 'addr_range', dump)
+    elif filter_.type_ == 'target':
+        assert_true(filter_.target_idx == dump['target_idx'], 'target_idx',
+                    dump)
+    elif filter_.type_ == 'hugepage_size':
+        assert_true([filter_.min_, filter_.max_] == dump['sz_range'],
+                    'sz_range', dump)
+
+def assert_access_pattern_committed(pattern, dump):
+    assert_true(dump['min_sz_region'] == pattern.size[0], 'min_sz_region',
+                dump)
+    assert_true(dump['max_sz_region'] == pattern.size[1], 'max_sz_region',
+                dump)
+    assert_true(dump['min_nr_accesses'] == pattern.nr_accesses[0],
+                'min_nr_accesses', dump)
+    assert_true(dump['max_nr_accesses'] == pattern.nr_accesses[1],
+                'max_nr_accesses', dump)
+    assert_true(dump['min_age_region'] == pattern.age[0], 'min_age_region',
+                dump)
+    assert_true(dump['max_age_region'] == pattern.age[1], 'miaxage_region',
+                dump)
+
+def assert_scheme_committed(scheme, dump):
+    assert_access_pattern_committed(scheme.access_pattern, dump['pattern'])
+    action_val = {
+            'willneed': 0,
+            'cold': 1,
+            'pageout': 2,
+            'hugepage': 3,
+            'nohugeapge': 4,
+            'lru_prio': 5,
+            'lru_deprio': 6,
+            'migrate_hot': 7,
+            'migrate_cold': 8,
+            'stat': 9,
+            }
+    assert_true(dump['action'] == action_val[scheme.action], 'action', dump)
+    assert_true(dump['apply_interval_us'] == scheme. apply_interval_us,
+                'apply_interval_us', dump)
+    assert_true(dump['target_nid'] == scheme.target_nid, 'target_nid', dump)
+    assert_migrate_dests_committed(scheme.dests, dump['migrate_dests'])
+    assert_quota_committed(scheme.quota, dump['quota'])
+    assert_watermarks_committed(scheme.watermarks, dump['wmarks'])
+    # TODO: test filters directory
+    for idx, f in enumerate(scheme.core_filters.filters):
+        assert_filter_committed(f, dump['core_filters'][idx])
+    for idx, f in enumerate(scheme.ops_filters.filters):
+        assert_filter_committed(f, dump['ops_filters'][idx])
+
+def assert_schemes_committed(schemes, dump):
+    assert_true(len(schemes) == len(dump), 'len_schemes', dump)
+    for idx, scheme in enumerate(schemes):
+        assert_scheme_committed(scheme, dump[idx])
+
+def assert_monitoring_attrs_committed(attrs, dump):
+    assert_true(dump['sample_interval'] == attrs.sample_us, 'sample_interval',
+                dump)
+    assert_true(dump['aggr_interval'] == attrs.aggr_us, 'aggr_interval', dump)
+    assert_true(dump['intervals_goal']['access_bp'] ==
+                attrs.intervals_goal.access_bp, 'access_bp',
+                dump['intervals_goal'])
+    assert_true(dump['intervals_goal']['aggrs'] == attrs.intervals_goal.aggrs,
+                'aggrs', dump['intervals_goal'])
+    assert_true(dump['intervals_goal']['min_sample_us'] ==
+                attrs.intervals_goal.min_sample_us, 'min_sample_us',
+                dump['intervals_goal'])
+    assert_true(dump['intervals_goal']['max_sample_us'] ==
+                attrs.intervals_goal.max_sample_us, 'max_sample_us',
+                dump['intervals_goal'])
+
+    assert_true(dump['ops_update_interval'] == attrs.update_us,
+                'ops_update_interval', dump)
+    assert_true(dump['min_nr_regions'] == attrs.min_nr_regions,
+                'min_nr_regions', dump)
+    assert_true(dump['max_nr_regions'] == attrs.max_nr_regions,
+                'max_nr_regions', dump)
+
+def assert_monitoring_target_committed(target, dump):
+    # target.pid is the pid "number", while dump['pid'] is 'struct pid'
+    # pointer, and hence cannot be compared.
+    assert_true(dump['obsolete'] == target.obsolete, 'target obsolete', dump)
+
+def assert_monitoring_targets_committed(targets, dump):
+    assert_true(len(targets) == len(dump), 'len_targets', dump)
+    for idx, target in enumerate(targets):
+        assert_monitoring_target_committed(target, dump[idx])
+
+def assert_ctx_committed(ctx, dump):
+    ops_val = {
+            'vaddr': 0,
+            'fvaddr': 1,
+            'paddr': 2,
+            }
+    assert_true(dump['ops']['id'] == ops_val[ctx.ops], 'ops_id', dump)
+    assert_monitoring_attrs_committed(ctx.monitoring_attrs, dump['attrs'])
+    assert_monitoring_targets_committed(ctx.targets, dump['adaptive_targets'])
+    assert_schemes_committed(ctx.schemes, dump['schemes'])
+
+def assert_ctxs_committed(kdamonds):
+    status, err = dump_damon_status_dict(kdamonds.kdamonds[0].pid)
+    if err is not None:
+        print(err)
+        kdamonds.stop()
+        exit(1)
+
+    ctxs = kdamonds.kdamonds[0].contexts
+    dump = status['contexts']
+    assert_true(len(ctxs) == len(dump), 'ctxs length', dump)
+    for idx, ctx in enumerate(ctxs):
+        assert_ctx_committed(ctx, dump[idx])
+
+def main():
+    kdamonds = _damon_sysfs.Kdamonds(
+            [_damon_sysfs.Kdamond(
+                contexts=[_damon_sysfs.DamonCtx(
+                    targets=[_damon_sysfs.DamonTarget(pid=-1)],
+                    schemes=[_damon_sysfs.Damos()],
+                    )])])
+    err = kdamonds.start()
+    if err is not None:
+        print('kdamond start failed: %s' % err)
+        exit(1)
+
+    assert_ctxs_committed(kdamonds)
+
+    context = _damon_sysfs.DamonCtx(
+            monitoring_attrs=_damon_sysfs.DamonAttrs(
+                sample_us=100000, aggr_us=2000000,
+                intervals_goal=_damon_sysfs.IntervalsGoal(
+                    access_bp=400, aggrs=3, min_sample_us=5000,
+                    max_sample_us=10000000),
+                update_us=2000000),
+            schemes=[_damon_sysfs.Damos(
+                action='pageout',
+                access_pattern=_damon_sysfs.DamosAccessPattern(
+                    size=[4096, 2**10],
+                    nr_accesses=[3, 317],
+                    age=[5,71]),
+                quota=_damon_sysfs.DamosQuota(
+                    sz=100*1024*1024, ms=100,
+                    goals=[_damon_sysfs.DamosQuotaGoal(
+                        metric='node_mem_used_bp',
+                        target_value=9950,
+                        nid=1)],
+                    reset_interval_ms=1500,
+                    weight_sz_permil=20,
+                    weight_nr_accesses_permil=200,
+                    weight_age_permil=1000),
+                watermarks=_damon_sysfs.DamosWatermarks(
+                    metric = 'free_mem_rate', interval = 500000, # 500 ms
+                    high = 500, mid = 400, low = 50),
+                target_nid=1,
+                apply_interval_us=1000000,
+                dests=_damon_sysfs.DamosDests(
+                    dests=[_damon_sysfs.DamosDest(id=1, weight=30),
+                           _damon_sysfs.DamosDest(id=0, weight=70)]),
+                core_filters=[
+                    _damon_sysfs.DamosFilter(type_='addr', matching=True,
+                                             allow=False, addr_start=42,
+                                             addr_end=4242),
+                    ],
+                ops_filters=[
+                    _damon_sysfs.DamosFilter(type_='anon', matching=True,
+                                             allow=True),
+                    ],
+                )])
+    context.idx = 0
+    context.kdamond = kdamonds.kdamonds[0]
+    kdamonds.kdamonds[0].contexts = [context]
+    kdamonds.kdamonds[0].commit()
+
+    assert_ctxs_committed(kdamonds)
+
+    # test online commitment of minimum context.
+    context = _damon_sysfs.DamonCtx()
+    context.idx = 0
+    context.kdamond = kdamonds.kdamonds[0]
+    kdamonds.kdamonds[0].contexts = [context]
+    kdamonds.kdamonds[0].commit()
+
+    assert_ctxs_committed(kdamonds)
+
+    kdamonds.stop()
+
+    # test obsolete_target.
+    proc1 = subprocess.Popen(['sh'], stdout=subprocess.PIPE,
+                             stderr=subprocess.PIPE)
+    proc2 = subprocess.Popen(['sh'], stdout=subprocess.PIPE,
+                             stderr=subprocess.PIPE)
+    proc3 = subprocess.Popen(['sh'], stdout=subprocess.PIPE,
+                             stderr=subprocess.PIPE)
+    kdamonds = _damon_sysfs.Kdamonds(
+            [_damon_sysfs.Kdamond(
+                contexts=[_damon_sysfs.DamonCtx(
+                    ops='vaddr',
+                    targets=[
+                        _damon_sysfs.DamonTarget(pid=proc1.pid),
+                        _damon_sysfs.DamonTarget(pid=proc2.pid),
+                        _damon_sysfs.DamonTarget(pid=proc3.pid),
+                        ],
+                    schemes=[_damon_sysfs.Damos()],
+                    )])])
+    err = kdamonds.start()
+    if err is not None:
+        print('kdamond start failed: %s' % err)
+        exit(1)
+    kdamonds.kdamonds[0].contexts[0].targets[1].obsolete = True
+    kdamonds.kdamonds[0].commit()
+    del kdamonds.kdamonds[0].contexts[0].targets[1]
+    assert_ctxs_committed(kdamonds)
+    kdamonds.stop()
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/testing/selftests/damon/sysfs.sh b/tools/testing/selftests/damon/sysfs.sh
index db4942383a50..83e3b7f63d81 100644..100755
--- a/tools/testing/selftests/damon/sysfs.sh
+++ b/tools/testing/selftests/damon/sysfs.sh
@@ -1,6 +1,8 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+source _common.sh
+
 # Kselftest frmework requirement - SKIP code is 4.
 ksft_skip=4
 
@@ -24,7 +26,7 @@ ensure_write_fail()
 	content=$2
 	reason=$3
 
-	if echo "$content" > "$file"
+	if (echo "$content" > "$file") 2> /dev/null
 	then
 		echo "writing $content to $file succeed ($fail_reason)"
 		echo "expected failure because $reason"
@@ -84,6 +86,7 @@ test_tried_regions()
 {
 	tried_regions_dir=$1
 	ensure_dir "$tried_regions_dir" "exist"
+	ensure_file "$tried_regions_dir/total_bytes" "exist" "400"
 }
 
 test_stats()
@@ -96,6 +99,39 @@ test_stats()
 	done
 }
 
+test_filter()
+{
+	filter_dir=$1
+	ensure_file "$filter_dir/type" "exist" "600"
+	ensure_write_succ "$filter_dir/type" "anon" "valid input"
+	ensure_write_succ "$filter_dir/type" "memcg" "valid input"
+	ensure_write_succ "$filter_dir/type" "addr" "valid input"
+	ensure_write_succ "$filter_dir/type" "target" "valid input"
+	ensure_write_fail "$filter_dir/type" "foo" "invalid input"
+	ensure_file "$filter_dir/matching" "exist" "600"
+	ensure_file "$filter_dir/memcg_path" "exist" "600"
+	ensure_file "$filter_dir/addr_start" "exist" "600"
+	ensure_file "$filter_dir/addr_end" "exist" "600"
+	ensure_file "$filter_dir/damon_target_idx" "exist" "600"
+}
+
+test_filters()
+{
+	filters_dir=$1
+	ensure_dir "$filters_dir" "exist"
+	ensure_file "$filters_dir/nr_filters" "exist" "600"
+	ensure_write_succ  "$filters_dir/nr_filters" "1" "valid input"
+	test_filter "$filters_dir/0"
+
+	ensure_write_succ  "$filters_dir/nr_filters" "2" "valid input"
+	test_filter "$filters_dir/0"
+	test_filter "$filters_dir/1"
+
+	ensure_write_succ "$filters_dir/nr_filters" "0" "valid input"
+	ensure_dir "$filters_dir/0" "not_exist"
+	ensure_dir "$filters_dir/1" "not_exist"
+}
+
 test_watermarks()
 {
 	watermarks_dir=$1
@@ -116,6 +152,32 @@ test_weights()
 	ensure_file "$weights_dir/age_permil" "exist" "600"
 }
 
+test_goal()
+{
+	goal_dir=$1
+	ensure_dir "$goal_dir" "exist"
+	ensure_file "$goal_dir/target_value" "exist" "600"
+	ensure_file "$goal_dir/current_value" "exist" "600"
+}
+
+test_goals()
+{
+	goals_dir=$1
+	ensure_dir "$goals_dir" "exist"
+	ensure_file "$goals_dir/nr_goals" "exist" "600"
+
+	ensure_write_succ  "$goals_dir/nr_goals" "1" "valid input"
+	test_goal "$goals_dir/0"
+
+	ensure_write_succ  "$goals_dir/nr_goals" "2" "valid input"
+	test_goal "$goals_dir/0"
+	test_goal "$goals_dir/1"
+
+	ensure_write_succ  "$goals_dir/nr_goals" "0" "valid input"
+	ensure_dir "$goals_dir/0" "not_exist"
+	ensure_dir "$goals_dir/1" "not_exist"
+}
+
 test_quotas()
 {
 	quotas_dir=$1
@@ -124,6 +186,7 @@ test_quotas()
 	ensure_file "$quotas_dir/bytes" "exist" 600
 	ensure_file "$quotas_dir/reset_interval_ms" "exist" 600
 	test_weights "$quotas_dir/weights"
+	test_goals "$quotas_dir/goals"
 }
 
 test_access_pattern()
@@ -141,8 +204,10 @@ test_scheme()
 	ensure_dir "$scheme_dir" "exist"
 	ensure_file "$scheme_dir/action" "exist" "600"
 	test_access_pattern "$scheme_dir/access_pattern"
+	ensure_file "$scheme_dir/apply_interval_us" "exist" "600"
 	test_quotas "$scheme_dir/quotas"
 	test_watermarks "$scheme_dir/watermarks"
+	test_filters "$scheme_dir/filters"
 	test_stats "$scheme_dir/stats"
 	test_tried_regions "$scheme_dir/tried_regions"
 }
@@ -301,14 +366,5 @@ test_damon_sysfs()
 	test_kdamonds "$damon_sysfs/kdamonds"
 }
 
-check_dependencies()
-{
-	if [ $EUID -ne 0 ]
-	then
-		echo "Run as root"
-		exit $ksft_skip
-	fi
-}
-
 check_dependencies
 test_damon_sysfs "/sys/kernel/mm/damon/admin"
diff --git a/tools/testing/selftests/damon/sysfs_memcg_path_leak.sh b/tools/testing/selftests/damon/sysfs_memcg_path_leak.sh
new file mode 100755
index 000000000000..64c5d8c518a4
--- /dev/null
+++ b/tools/testing/selftests/damon/sysfs_memcg_path_leak.sh
@@ -0,0 +1,43 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+if [ $EUID -ne 0 ]
+then
+	echo "Run as root"
+	exit $ksft_skip
+fi
+
+damon_sysfs="/sys/kernel/mm/damon/admin"
+if [ ! -d "$damon_sysfs" ]
+then
+	echo "damon sysfs not found"
+	exit $ksft_skip
+fi
+
+# ensure filter directory
+echo 1 > "$damon_sysfs/kdamonds/nr_kdamonds"
+echo 1 > "$damon_sysfs/kdamonds/0/contexts/nr_contexts"
+echo 1 > "$damon_sysfs/kdamonds/0/contexts/0/schemes/nr_schemes"
+echo 1 > "$damon_sysfs/kdamonds/0/contexts/0/schemes/0/filters/nr_filters"
+
+filter_dir="$damon_sysfs/kdamonds/0/contexts/0/schemes/0/filters/0"
+
+before_kb=$(grep Slab /proc/meminfo | awk '{print $2}')
+
+# try to leak 3000 KiB
+for i in {1..102400};
+do
+	echo "012345678901234567890123456789" > "$filter_dir/memcg_path"
+done
+
+after_kb=$(grep Slab /proc/meminfo | awk '{print $2}')
+# expect up to 1500 KiB free from other tasks memory
+expected_after_kb_max=$((before_kb + 1500))
+
+if [ "$after_kb" -gt "$expected_after_kb_max" ]
+then
+	echo "maybe memcg_path are leaking: $before_kb -> $after_kb"
+	exit 1
+else
+	exit 0
+fi
diff --git a/tools/testing/selftests/damon/sysfs_no_op_commit_break.py b/tools/testing/selftests/damon/sysfs_no_op_commit_break.py
new file mode 100755
index 000000000000..2c65cffe6b54
--- /dev/null
+++ b/tools/testing/selftests/damon/sysfs_no_op_commit_break.py
@@ -0,0 +1,72 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import json
+import os
+import subprocess
+import sys
+
+import _damon_sysfs
+
+def dump_damon_status_dict(pid):
+    try:
+        subprocess.check_output(['which', 'drgn'], stderr=subprocess.DEVNULL)
+    except:
+        return None, 'drgn not found'
+    file_dir = os.path.dirname(os.path.abspath(__file__))
+    dump_script = os.path.join(file_dir, 'drgn_dump_damon_status.py')
+    rc = subprocess.call(['drgn', dump_script, pid, 'damon_dump_output'],
+        stderr=subprocess.DEVNULL)
+
+    if rc != 0:
+        return None, f'drgn fail: return code({rc})'
+    try:
+        with open('damon_dump_output', 'r') as f:
+            return json.load(f), None
+    except Exception as e:
+        return None, 'json.load fail (%s)' % e
+
+def main():
+    kdamonds = _damon_sysfs.Kdamonds(
+        [_damon_sysfs.Kdamond(
+            contexts=[_damon_sysfs.DamonCtx(
+                schemes=[_damon_sysfs.Damos(
+                    ops_filters=[
+                        _damon_sysfs.DamosFilter(
+                            type_='anon',
+                            matching=True,
+                            allow=True,
+                        )
+                    ]
+                )],
+            )])]
+    )
+
+    err = kdamonds.start()
+    if err is not None:
+        print('kdamond start failed: %s' % err)
+        exit(1)
+
+    before_commit_status, err = \
+        dump_damon_status_dict(kdamonds.kdamonds[0].pid)
+    if err is not None:
+        print('before-commit status dump failed: %s' % err)
+        exit(1)
+
+    kdamonds.kdamonds[0].commit()
+
+    after_commit_status, err = \
+        dump_damon_status_dict(kdamonds.kdamonds[0].pid)
+    if err is not None:
+        print('after-commit status dump failed: %s' % err)
+        exit(1)
+
+    if before_commit_status != after_commit_status:
+        print(f'before: {json.dumps(before_commit_status, indent=2)}')
+        print(f'after: {json.dumps(after_commit_status, indent=2)}')
+        exit(1)
+
+    kdamonds.stop()
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/testing/selftests/damon/sysfs_update_removed_scheme_dir.sh b/tools/testing/selftests/damon/sysfs_update_removed_scheme_dir.sh
index ade35576e748..35fc32beeaf7 100644..100755
--- a/tools/testing/selftests/damon/sysfs_update_removed_scheme_dir.sh
+++ b/tools/testing/selftests/damon/sysfs_update_removed_scheme_dir.sh
@@ -1,14 +1,12 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+source _common.sh
+
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
 
-if [ $EUID -ne 0 ]
-then
-	echo "Run as root"
-	exit $ksft_skip
-fi
+check_dependencies
 
 damon_sysfs="/sys/kernel/mm/damon/admin"
 if [ ! -d "$damon_sysfs" ]
diff --git a/tools/testing/selftests/damon/sysfs_update_schemes_tried_regions_hang.py b/tools/testing/selftests/damon/sysfs_update_schemes_tried_regions_hang.py
new file mode 100755
index 000000000000..28c887a0108f
--- /dev/null
+++ b/tools/testing/selftests/damon/sysfs_update_schemes_tried_regions_hang.py
@@ -0,0 +1,33 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import subprocess
+import time
+
+import _damon_sysfs
+
+def main():
+    proc = subprocess.Popen(['sleep', '2'])
+    kdamonds = _damon_sysfs.Kdamonds([_damon_sysfs.Kdamond(
+            contexts=[_damon_sysfs.DamonCtx(
+                ops='vaddr',
+                targets=[_damon_sysfs.DamonTarget(pid=proc.pid)],
+                schemes=[_damon_sysfs.Damos(
+                    access_pattern=_damon_sysfs.DamosAccessPattern(
+                        nr_accesses=[200, 200]))] # schemes
+                )] # contexts
+            )]) # kdamonds
+
+    err = kdamonds.start()
+    if err != None:
+        print('kdamond start failed: %s' % err)
+        exit(1)
+
+    while proc.poll() == None:
+        err = kdamonds.kdamonds[0].update_schemes_tried_bytes()
+        if err != None:
+            print('tried bytes update failed: %s' % err)
+            exit(1)
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/testing/selftests/damon/sysfs_update_schemes_tried_regions_wss_estimation.py b/tools/testing/selftests/damon/sysfs_update_schemes_tried_regions_wss_estimation.py
new file mode 100755
index 000000000000..90ad7409a7a6
--- /dev/null
+++ b/tools/testing/selftests/damon/sysfs_update_schemes_tried_regions_wss_estimation.py
@@ -0,0 +1,55 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import subprocess
+import time
+
+import _damon_sysfs
+
+def main():
+    # access two 10 MiB memory regions, 2 second per each
+    sz_region = 10 * 1024 * 1024
+    proc = subprocess.Popen(['./access_memory', '2', '%d' % sz_region, '2000'])
+    kdamonds = _damon_sysfs.Kdamonds([_damon_sysfs.Kdamond(
+            contexts=[_damon_sysfs.DamonCtx(
+                ops='vaddr',
+                targets=[_damon_sysfs.DamonTarget(pid=proc.pid)],
+                schemes=[_damon_sysfs.Damos(
+                    access_pattern=_damon_sysfs.DamosAccessPattern(
+                        # >= 25% access rate, >= 200ms age
+                        nr_accesses=[5, 20], age=[2, 2**64 - 1]))] # schemes
+                )] # contexts
+            )]) # kdamonds
+
+    err = kdamonds.start()
+    if err != None:
+        print('kdamond start failed: %s' % err)
+        exit(1)
+
+    wss_collected = []
+    while proc.poll() == None:
+        time.sleep(0.1)
+        err = kdamonds.kdamonds[0].update_schemes_tried_bytes()
+        if err != None:
+            print('tried bytes update failed: %s' % err)
+            exit(1)
+
+        wss_collected.append(
+                kdamonds.kdamonds[0].contexts[0].schemes[0].tried_bytes)
+
+    wss_collected.sort()
+    acceptable_error_rate = 0.2
+    for percentile in [50, 75]:
+        sample = wss_collected[int(len(wss_collected) * percentile / 100)]
+        error_rate = abs(sample - sz_region) / sz_region
+        print('%d-th percentile (%d) error %f' %
+                (percentile, sample, error_rate))
+        if error_rate > acceptable_error_rate:
+            print('the error rate is not acceptable (> %f)' %
+                    acceptable_error_rate)
+            print('samples are as below')
+            print('\n'.join(['%d' % wss for wss in wss_collected]))
+            exit(1)
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/testing/selftests/devices/error_logs/Makefile b/tools/testing/selftests/devices/error_logs/Makefile
new file mode 100644
index 000000000000..d546c3fb0a7f
--- /dev/null
+++ b/tools/testing/selftests/devices/error_logs/Makefile
@@ -0,0 +1,3 @@
+TEST_PROGS := test_device_error_logs.py
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/devices/error_logs/test_device_error_logs.py b/tools/testing/selftests/devices/error_logs/test_device_error_logs.py
new file mode 100755
index 000000000000..3dd56c8ec92c
--- /dev/null
+++ b/tools/testing/selftests/devices/error_logs/test_device_error_logs.py
@@ -0,0 +1,85 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2024 Collabora Ltd
+#
+# This test checks for the presence of error (or more critical) log messages
+# coming from devices in the kernel log.
+#
+# One failed test case is reported for each device that has outputted error
+# logs. Devices with no errors do not produce a passing test case to avoid
+# polluting the results, therefore a successful run will list 0 tests run.
+#
+
+import glob
+import os
+import re
+import sys
+
+# Allow ksft module to be imported from different directory
+this_dir = os.path.dirname(os.path.realpath(__file__))
+sys.path.append(os.path.join(this_dir, "../../kselftest/"))
+
+import ksft
+
+kmsg = "/dev/kmsg"
+
+RE_log = re.compile(
+    r"(?P<prefix>[0-9]+),(?P<sequence>[0-9]+),(?P<timestamp>[0-9]+),(?P<flag>[^;]*)(,[^;]*)*;(?P<message>.*)"
+)
+RE_tag = re.compile(r" (?P<key>[^=]+)=(?P<value>.*)")
+
+PREFIX_ERROR = 3
+
+logs = []
+error_log_per_device = {}
+
+
+def parse_kmsg():
+    current_log = {}
+
+    with open(kmsg) as f:
+        os.set_blocking(f.fileno(), False)
+
+        for line in f:
+            tag_line = RE_tag.match(line)
+            log_line = RE_log.match(line)
+
+            if log_line:
+                if current_log:
+                    logs.append(current_log)  # Save last log
+
+                current_log = {
+                    "prefix": int(log_line.group("prefix")),
+                    "sequence": int(log_line.group("sequence")),
+                    "timestamp": int(log_line.group("timestamp")),
+                    "flag": log_line.group("flag"),
+                    "message": log_line.group("message"),
+                }
+            elif tag_line:
+                current_log[tag_line.group("key")] = tag_line.group("value")
+
+
+def generate_per_device_error_log():
+    for log in logs:
+        if log.get("DEVICE") and log["prefix"] <= PREFIX_ERROR:
+            if not error_log_per_device.get(log["DEVICE"]):
+                error_log_per_device[log["DEVICE"]] = []
+            error_log_per_device[log["DEVICE"]].append(log)
+
+
+parse_kmsg()
+
+generate_per_device_error_log()
+num_tests = len(error_log_per_device)
+
+ksft.print_header()
+ksft.set_plan(num_tests)
+
+for device in error_log_per_device:
+    for log in error_log_per_device[device]:
+        ksft.print_msg(log["message"])
+    ksft.test_result_fail(device)
+if num_tests == 0:
+    ksft.print_msg("No device error logs found")
+ksft.finished()
diff --git a/tools/testing/selftests/devices/probe/Makefile b/tools/testing/selftests/devices/probe/Makefile
new file mode 100644
index 000000000000..f630108c3fdf
--- /dev/null
+++ b/tools/testing/selftests/devices/probe/Makefile
@@ -0,0 +1,4 @@
+TEST_PROGS := test_discoverable_devices.py
+TEST_FILES := boards
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/devices/probe/boards/Dell Inc.,XPS 13 9300.yaml b/tools/testing/selftests/devices/probe/boards/Dell Inc.,XPS 13 9300.yaml
new file mode 100644
index 000000000000..ff932eb19f0b
--- /dev/null
+++ b/tools/testing/selftests/devices/probe/boards/Dell Inc.,XPS 13 9300.yaml
@@ -0,0 +1,40 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# This is the device definition for the XPS 13 9300.
+# The filename "Dell Inc.,XPS 13 9300" was chosen following the format
+# "Vendor,Product", where Vendor comes from
+# /sys/devices/virtual/dmi/id/sys_vendor, and Product comes from
+# /sys/devices/virtual/dmi/id/product_name.
+#
+# See google,spherion.yaml for more information.
+#
+- type: pci-controller
+  # This machine has a single PCI host controller so it's valid to not have any
+  # key to identify the controller. If it had more than one controller, the UID
+  # of the controller from ACPI could be used to distinguish as follows:
+  #acpi-uid: 0
+  devices:
+    - path: 14.0
+      type: usb-controller
+      usb-version: 2
+      devices:
+        - path: 9
+          name: camera
+          interfaces: [0, 1, 2, 3]
+        - path: 10
+          name: bluetooth
+          interfaces: [0, 1]
+    - path: 2.0
+      name: gpu
+    - path: 4.0
+      name: thermal
+    - path: 12.0
+      name: sensors
+    - path: 14.3
+      name: wifi
+    - path: 1d.0/0.0
+      name: ssd
+    - path: 1d.7/0.0
+      name: sdcard-reader
+    - path: 1f.3
+      name: audio
diff --git a/tools/testing/selftests/devices/probe/boards/google,spherion.yaml b/tools/testing/selftests/devices/probe/boards/google,spherion.yaml
new file mode 100644
index 000000000000..3ea843324797
--- /dev/null
+++ b/tools/testing/selftests/devices/probe/boards/google,spherion.yaml
@@ -0,0 +1,54 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# This is the device definition for the Google Spherion Chromebook.
+# The filename "google,spherion" comes from the Devicetree compatible, so this
+# file will be automatically used when the test is run on that machine.
+#
+# The top-level is a list of controllers, either for USB or PCI(e).
+# Every controller needs to have a 'type' key set to either 'usb-controller' or
+# 'pci-controller'.
+# Every controller needs to be uniquely identified on the platform. To achieve
+# this, several optional keys can be used:
+# - dt-mmio: identify the MMIO address of the controller as defined in the
+#   Devicetree.
+# - of-fullname-regex: regular expression to match against the OF_FULLNAME
+#   property. Useful when the controller's address is not unique across other
+#   sibling controllers. In this case, dt-mmio can't be used, and this property
+#   allows the matching to include parent nodes as well to make it unique.
+# - usb-version: for USB controllers to differentiate between USB3 and USB2
+#   buses sharing the same controller.
+# - acpi-uid: _UID property of the controller as supplied by the ACPI. Useful to
+#   distinguish between multiple PCI host controllers.
+#
+# The 'devices' key defines a list of devices that are accessible under that
+# controller. A device might be a leaf device or another controller (see
+# 'Dell Inc.,XPS 13 9300.yaml').
+#
+# The 'path' key is needed for every child device (that is, not top-level) to
+# define how to reach this device from the parent controller. For USB devices it
+# follows the format \d(.\d)* and denotes the port in the hub at each level in
+# the USB topology. For PCI devices it follows the format \d.\d(/\d.\d)*
+# denoting the device (identified by device-function pair) at each level in the
+# PCI topology.
+#
+# The 'name' key is used in the leaf devices to name the device for clarity in
+# the test output.
+#
+# For USB leaf devices, the 'interfaces' key should contain a list of the
+# interfaces in that device that should be bound to a driver.
+#
+- type: usb-controller
+  dt-mmio: 11200000
+  usb-version: 2
+  devices:
+    - path: 1.4.1
+      interfaces: [0, 1]
+      name: camera
+    - path: 1.4.2
+      interfaces: [0, 1]
+      name: bluetooth
+- type: pci-controller
+  dt-mmio: 11230000
+  devices:
+    - path: 0.0/0.0
+      name: wifi
diff --git a/tools/testing/selftests/devices/probe/test_discoverable_devices.py b/tools/testing/selftests/devices/probe/test_discoverable_devices.py
new file mode 100755
index 000000000000..d7a2bb91c807
--- /dev/null
+++ b/tools/testing/selftests/devices/probe/test_discoverable_devices.py
@@ -0,0 +1,358 @@
+#!/usr/bin/python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (c) 2023 Collabora Ltd
+#
+# This script tests for presence and driver binding of devices from discoverable
+# buses (ie USB, PCI).
+#
+# The per-platform YAML file defining the devices to be tested is stored inside
+# the boards/ directory and chosen based on DT compatible or DMI IDs (sys_vendor
+# and product_name).
+#
+# See boards/google,spherion.yaml and boards/'Dell Inc.,XPS 13 9300.yaml' for
+# the description and examples of the file structure and vocabulary.
+#
+
+import argparse
+import glob
+import os
+import re
+import sys
+import yaml
+
+# Allow ksft module to be imported from different directory
+this_dir = os.path.dirname(os.path.realpath(__file__))
+sys.path.append(os.path.join(this_dir, "../../kselftest/"))
+
+import ksft
+
+pci_controllers = []
+usb_controllers = []
+
+sysfs_usb_devices = "/sys/bus/usb/devices/"
+
+
+def find_pci_controller_dirs():
+    sysfs_devices = "/sys/devices"
+    pci_controller_sysfs_dir = "pci[0-9a-f]{4}:[0-9a-f]{2}"
+
+    dir_regex = re.compile(pci_controller_sysfs_dir)
+    for path, dirs, _ in os.walk(sysfs_devices):
+        for d in dirs:
+            if dir_regex.match(d):
+                pci_controllers.append(os.path.join(path, d))
+
+
+def find_usb_controller_dirs():
+    usb_controller_sysfs_dir = r"usb[\d]+"
+
+    dir_regex = re.compile(usb_controller_sysfs_dir)
+    for d in os.scandir(sysfs_usb_devices):
+        if dir_regex.match(d.name):
+            usb_controllers.append(os.path.realpath(d.path))
+
+
+def get_dt_mmio(sysfs_dev_dir):
+    re_dt_mmio = re.compile("OF_FULLNAME=.*@([0-9a-f]+)")
+    dt_mmio = None
+
+    # PCI controllers' sysfs don't have an of_node, so have to read it from the
+    # parent
+    while not dt_mmio:
+        try:
+            with open(os.path.join(sysfs_dev_dir, "uevent")) as f:
+                dt_mmio = re_dt_mmio.search(f.read()).group(1)
+                return dt_mmio
+        except:
+            pass
+        sysfs_dev_dir = os.path.dirname(sysfs_dev_dir)
+
+
+def get_of_fullname(sysfs_dev_dir):
+    re_of_fullname = re.compile("OF_FULLNAME=(.*)")
+    of_full_name = None
+
+    # PCI controllers' sysfs don't have an of_node, so have to read it from the
+    # parent
+    while not of_full_name:
+        try:
+            with open(os.path.join(sysfs_dev_dir, "uevent")) as f:
+                of_fullname = re_of_fullname.search(f.read()).group(1)
+                return of_fullname
+        except:
+            pass
+        sysfs_dev_dir = os.path.dirname(sysfs_dev_dir)
+
+
+def get_acpi_uid(sysfs_dev_dir):
+    with open(os.path.join(sysfs_dev_dir, "firmware_node", "uid")) as f:
+        return f.read()
+
+
+def get_usb_version(sysfs_dev_dir):
+    re_usb_version = re.compile(r"PRODUCT=.*/(\d)/.*")
+    with open(os.path.join(sysfs_dev_dir, "uevent")) as f:
+        return int(re_usb_version.search(f.read()).group(1))
+
+
+def get_usb_busnum(sysfs_dev_dir):
+    re_busnum = re.compile("BUSNUM=(.*)")
+    with open(os.path.join(sysfs_dev_dir, "uevent")) as f:
+        return int(re_busnum.search(f.read()).group(1))
+
+
+def find_controller_in_sysfs(controller, parent_sysfs=None):
+    if controller["type"] == "pci-controller":
+        controllers = pci_controllers
+    elif controller["type"] == "usb-controller":
+        controllers = usb_controllers
+
+    result_controllers = []
+
+    for c in controllers:
+        if parent_sysfs and parent_sysfs not in c:
+            continue
+
+        if controller.get("dt-mmio"):
+            if str(controller["dt-mmio"]) != get_dt_mmio(c):
+                continue
+
+        if controller.get("of-fullname-regex"):
+            re_of_fullname = re.compile(str(controller["of-fullname-regex"]))
+            if not re_of_fullname.match(get_of_fullname(c)):
+                continue
+
+        if controller.get("usb-version"):
+            if controller["usb-version"] != get_usb_version(c):
+                continue
+
+        if controller.get("acpi-uid"):
+            if controller["acpi-uid"] != get_acpi_uid(c):
+                continue
+
+        result_controllers.append(c)
+
+    return result_controllers
+
+
+def is_controller(device):
+    return device.get("type") and "controller" in device.get("type")
+
+
+def path_to_dir(parent_sysfs, dev_type, path):
+    if dev_type == "usb-device":
+        usb_dev_sysfs_fmt = "{}-{}"
+        busnum = get_usb_busnum(parent_sysfs)
+        dirname = os.path.join(
+            sysfs_usb_devices, usb_dev_sysfs_fmt.format(busnum, path)
+        )
+        return [os.path.realpath(dirname)]
+    else:
+        pci_dev_sysfs_fmt = "????:??:{}"
+        path_glob = ""
+        for dev_func in path.split("/"):
+            dev_func = dev_func.zfill(4)
+            path_glob = os.path.join(path_glob, pci_dev_sysfs_fmt.format(dev_func))
+
+        dir_list = glob.glob(os.path.join(parent_sysfs, path_glob))
+
+        return dir_list
+
+
+def find_in_sysfs(device, parent_sysfs=None):
+    if parent_sysfs and device.get("path"):
+        pathdirs = path_to_dir(
+            parent_sysfs, device["meta"]["type"], str(device["path"])
+        )
+        if len(pathdirs) != 1:
+            # Early return to report error
+            return pathdirs
+        pathdir = pathdirs[0]
+        sysfs_path = os.path.join(parent_sysfs, pathdir)
+    else:
+        sysfs_path = parent_sysfs
+
+    if is_controller(device):
+        return find_controller_in_sysfs(device, sysfs_path)
+    else:
+        return [sysfs_path]
+
+
+def check_driver_presence(sysfs_dir, current_node):
+    if current_node["meta"]["type"] == "usb-device":
+        usb_intf_fmt = "*-*:*.{}"
+
+        interfaces = []
+        for i in current_node["interfaces"]:
+            interfaces.append((i, usb_intf_fmt.format(i)))
+
+        for intf_num, intf_dir_fmt in interfaces:
+            test_name = f"{current_node['meta']['pathname']}.{intf_num}.driver"
+
+            intf_dirs = glob.glob(os.path.join(sysfs_dir, intf_dir_fmt))
+            if len(intf_dirs) != 1:
+                ksft.test_result_fail(test_name)
+                continue
+            intf_dir = intf_dirs[0]
+
+            driver_link = os.path.join(sysfs_dir, intf_dir, "driver")
+            ksft.test_result(os.path.isdir(driver_link), test_name)
+    else:
+        driver_link = os.path.join(sysfs_dir, "driver")
+        test_name = current_node["meta"]["pathname"] + ".driver"
+        ksft.test_result(os.path.isdir(driver_link), test_name)
+
+
+def generate_pathname(device):
+    pathname = ""
+
+    if device.get("path"):
+        pathname = str(device["path"])
+
+    if device.get("type"):
+        dev_type = device["type"]
+        if device.get("usb-version"):
+            dev_type = dev_type.replace("usb", "usb" + str(device["usb-version"]))
+        if device.get("acpi-uid") is not None:
+            dev_type = dev_type.replace("pci", "pci" + str(device["acpi-uid"]))
+        pathname = pathname + "/" + dev_type
+
+    if device.get("dt-mmio"):
+        pathname += "@" + str(device["dt-mmio"])
+
+    if device.get("of-fullname-regex"):
+        pathname += "-" + str(device["of-fullname-regex"])
+
+    if device.get("name"):
+        pathname = pathname + "/" + device["name"]
+
+    return pathname
+
+
+def fill_meta_keys(child, parent=None):
+    child["meta"] = {}
+
+    if parent:
+        child["meta"]["type"] = parent["type"].replace("controller", "device")
+
+    pathname = generate_pathname(child)
+    if parent:
+        pathname = parent["meta"]["pathname"] + "/" + pathname
+    child["meta"]["pathname"] = pathname
+
+
+def parse_device_tree_node(current_node, parent_sysfs=None):
+    if not parent_sysfs:
+        fill_meta_keys(current_node)
+
+    sysfs_dirs = find_in_sysfs(current_node, parent_sysfs)
+    if len(sysfs_dirs) != 1:
+        if len(sysfs_dirs) == 0:
+            ksft.test_result_fail(
+                f"Couldn't find in sysfs: {current_node['meta']['pathname']}"
+            )
+        else:
+            ksft.test_result_fail(
+                f"Found multiple sysfs entries for {current_node['meta']['pathname']}: {sysfs_dirs}"
+            )
+        return
+    sysfs_dir = sysfs_dirs[0]
+
+    if not is_controller(current_node):
+        ksft.test_result(
+            os.path.exists(sysfs_dir), current_node["meta"]["pathname"] + ".device"
+        )
+        check_driver_presence(sysfs_dir, current_node)
+    else:
+        for child_device in current_node["devices"]:
+            fill_meta_keys(child_device, current_node)
+            parse_device_tree_node(child_device, sysfs_dir)
+
+
+def count_tests(device_trees):
+    test_count = 0
+
+    def parse_node(device):
+        nonlocal test_count
+        if device.get("devices"):
+            for child in device["devices"]:
+                parse_node(child)
+        else:
+            if device.get("interfaces"):
+                test_count += len(device["interfaces"])
+            else:
+                test_count += 1
+            test_count += 1
+
+    for device_tree in device_trees:
+        parse_node(device_tree)
+
+    return test_count
+
+
+def get_board_filenames():
+    filenames = []
+
+    platform_compatible_file = "/proc/device-tree/compatible"
+    if os.path.exists(platform_compatible_file):
+        with open(platform_compatible_file) as f:
+            for line in f:
+                filenames.extend(line.split("\0"))
+    else:
+        dmi_id_dir = "/sys/devices/virtual/dmi/id"
+        vendor_dmi_file = os.path.join(dmi_id_dir, "sys_vendor")
+        product_dmi_file = os.path.join(dmi_id_dir, "product_name")
+
+        with open(vendor_dmi_file) as f:
+            vendor = f.read().replace("\n", "")
+        with open(product_dmi_file) as f:
+            product = f.read().replace("\n", "")
+
+        filenames = [vendor + "," + product]
+
+    return filenames
+
+
+def run_test(yaml_file):
+    ksft.print_msg(f"Using board file: {yaml_file}")
+
+    with open(yaml_file) as f:
+        device_trees = yaml.safe_load(f)
+
+    ksft.set_plan(count_tests(device_trees))
+
+    for device_tree in device_trees:
+        parse_device_tree_node(device_tree)
+
+
+parser = argparse.ArgumentParser()
+parser.add_argument(
+    "--boards-dir", default="boards", help="Directory containing the board YAML files"
+)
+args = parser.parse_args()
+
+find_pci_controller_dirs()
+find_usb_controller_dirs()
+
+ksft.print_header()
+
+if not os.path.exists(args.boards_dir):
+    ksft.print_msg(f"Boards directory '{args.boards_dir}' doesn't exist")
+    ksft.exit_fail()
+
+board_file = ""
+for board_filename in get_board_filenames():
+    full_board_filename = os.path.join(args.boards_dir, board_filename + ".yaml")
+
+    if os.path.exists(full_board_filename):
+        board_file = full_board_filename
+        break
+
+if not board_file:
+    ksft.print_msg("No matching board file found")
+    ksft.exit_fail()
+
+run_test(board_file)
+
+ksft.finished()
diff --git a/tools/testing/selftests/dma/Makefile b/tools/testing/selftests/dma/Makefile
deleted file mode 100644
index cd8c5ece1cba..000000000000
--- a/tools/testing/selftests/dma/Makefile
+++ /dev/null
@@ -1,7 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-CFLAGS += -I../../../../usr/include/
-CFLAGS += -I../../../../include/
-
-TEST_GEN_PROGS := dma_map_benchmark
-
-include ../lib.mk
diff --git a/tools/testing/selftests/dma/config b/tools/testing/selftests/dma/config
deleted file mode 100644
index 6102ee3c43cd..000000000000
--- a/tools/testing/selftests/dma/config
+++ /dev/null
@@ -1 +0,0 @@
-CONFIG_DMA_MAP_BENCHMARK=y
diff --git a/tools/testing/selftests/dma/dma_map_benchmark.c b/tools/testing/selftests/dma/dma_map_benchmark.c
deleted file mode 100644
index 5c997f17fcbd..000000000000
--- a/tools/testing/selftests/dma/dma_map_benchmark.c
+++ /dev/null
@@ -1,129 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2020 HiSilicon Limited.
- */
-
-#include <fcntl.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <unistd.h>
-#include <sys/ioctl.h>
-#include <sys/mman.h>
-#include <linux/types.h>
-#include <linux/map_benchmark.h>
-
-#define NSEC_PER_MSEC	1000000L
-
-static char *directions[] = {
-	"BIDIRECTIONAL",
-	"TO_DEVICE",
-	"FROM_DEVICE",
-};
-
-int main(int argc, char **argv)
-{
-	struct map_benchmark map;
-	int fd, opt;
-	/* default single thread, run 20 seconds on NUMA_NO_NODE */
-	int threads = 1, seconds = 20, node = -1;
-	/* default dma mask 32bit, bidirectional DMA */
-	int bits = 32, xdelay = 0, dir = DMA_MAP_BIDIRECTIONAL;
-	/* default granule 1 PAGESIZE */
-	int granule = 1;
-
-	int cmd = DMA_MAP_BENCHMARK;
-	char *p;
-
-	while ((opt = getopt(argc, argv, "t:s:n:b:d:x:g:")) != -1) {
-		switch (opt) {
-		case 't':
-			threads = atoi(optarg);
-			break;
-		case 's':
-			seconds = atoi(optarg);
-			break;
-		case 'n':
-			node = atoi(optarg);
-			break;
-		case 'b':
-			bits = atoi(optarg);
-			break;
-		case 'd':
-			dir = atoi(optarg);
-			break;
-		case 'x':
-			xdelay = atoi(optarg);
-			break;
-		case 'g':
-			granule = atoi(optarg);
-			break;
-		default:
-			return -1;
-		}
-	}
-
-	if (threads <= 0 || threads > DMA_MAP_MAX_THREADS) {
-		fprintf(stderr, "invalid number of threads, must be in 1-%d\n",
-			DMA_MAP_MAX_THREADS);
-		exit(1);
-	}
-
-	if (seconds <= 0 || seconds > DMA_MAP_MAX_SECONDS) {
-		fprintf(stderr, "invalid number of seconds, must be in 1-%d\n",
-			DMA_MAP_MAX_SECONDS);
-		exit(1);
-	}
-
-	if (xdelay < 0 || xdelay > DMA_MAP_MAX_TRANS_DELAY) {
-		fprintf(stderr, "invalid transmit delay, must be in 0-%ld\n",
-			DMA_MAP_MAX_TRANS_DELAY);
-		exit(1);
-	}
-
-	/* suppose the mininum DMA zone is 1MB in the world */
-	if (bits < 20 || bits > 64) {
-		fprintf(stderr, "invalid dma mask bit, must be in 20-64\n");
-		exit(1);
-	}
-
-	if (dir != DMA_MAP_BIDIRECTIONAL && dir != DMA_MAP_TO_DEVICE &&
-			dir != DMA_MAP_FROM_DEVICE) {
-		fprintf(stderr, "invalid dma direction\n");
-		exit(1);
-	}
-
-	if (granule < 1 || granule > 1024) {
-		fprintf(stderr, "invalid granule size\n");
-		exit(1);
-	}
-
-	fd = open("/sys/kernel/debug/dma_map_benchmark", O_RDWR);
-	if (fd == -1) {
-		perror("open");
-		exit(1);
-	}
-
-	memset(&map, 0, sizeof(map));
-	map.seconds = seconds;
-	map.threads = threads;
-	map.node = node;
-	map.dma_bits = bits;
-	map.dma_dir = dir;
-	map.dma_trans_ns = xdelay;
-	map.granule = granule;
-
-	if (ioctl(fd, cmd, &map)) {
-		perror("ioctl");
-		exit(1);
-	}
-
-	printf("dma mapping benchmark: threads:%d seconds:%d node:%d dir:%s granule: %d\n",
-			threads, seconds, node, dir[directions], granule);
-	printf("average map latency(us):%.1f standard deviation:%.1f\n",
-			map.avg_map_100ns/10.0, map.map_stddev/10.0);
-	printf("average unmap latency(us):%.1f standard deviation:%.1f\n",
-			map.avg_unmap_100ns/10.0, map.unmap_stddev/10.0);
-
-	return 0;
-}
diff --git a/tools/testing/selftests/dmabuf-heaps/.gitignore b/tools/testing/selftests/dmabuf-heaps/.gitignore
new file mode 100644
index 000000000000..b500e76b9045
--- /dev/null
+++ b/tools/testing/selftests/dmabuf-heaps/.gitignore
@@ -0,0 +1 @@
+dmabuf-heap
diff --git a/tools/testing/selftests/dmabuf-heaps/Makefile b/tools/testing/selftests/dmabuf-heaps/Makefile
index 604b43ece15f..9e7e158d5fa3 100644
--- a/tools/testing/selftests/dmabuf-heaps/Makefile
+++ b/tools/testing/selftests/dmabuf-heaps/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-CFLAGS += -static -O3 -Wl,-no-as-needed -Wall
+CFLAGS += -static -O3 -Wl,-no-as-needed -Wall $(KHDR_INCLUDES)
 
 TEST_GEN_PROGS = dmabuf-heap
 
diff --git a/tools/testing/selftests/dmabuf-heaps/config b/tools/testing/selftests/dmabuf-heaps/config
new file mode 100644
index 000000000000..be091f1cdfa0
--- /dev/null
+++ b/tools/testing/selftests/dmabuf-heaps/config
@@ -0,0 +1,3 @@
+CONFIG_DMABUF_HEAPS=y
+CONFIG_DMABUF_HEAPS_SYSTEM=y
+CONFIG_DRM_VGEM=y
diff --git a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c
index 29af27acd40e..fc9694fc4e89 100644
--- a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c
+++ b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c
@@ -13,9 +13,9 @@
 #include <sys/types.h>
 
 #include <linux/dma-buf.h>
+#include <linux/dma-heap.h>
 #include <drm/drm.h>
-
-#include "../../../../include/uapi/linux/dma-heap.h"
+#include "kselftest.h"
 
 #define DEVPATH "/dev/dma_heap"
 
@@ -29,9 +29,11 @@ static int check_vgem(int fd)
 	version.name = name;
 
 	ret = ioctl(fd, DRM_IOCTL_VERSION, &version);
-	if (ret)
+	if (ret || version.name_len != 4)
 		return 0;
 
+	name[4] = '\0';
+
 	return !strcmp(name, "vgem");
 }
 
@@ -91,14 +93,13 @@ static int dmabuf_heap_open(char *name)
 	char buf[256];
 
 	ret = snprintf(buf, 256, "%s/%s", DEVPATH, name);
-	if (ret < 0) {
-		printf("snprintf failed!\n");
-		return ret;
-	}
+	if (ret < 0)
+		ksft_exit_fail_msg("snprintf failed! %d\n", ret);
 
 	fd = open(buf, O_RDWR);
 	if (fd < 0)
-		printf("open %s failed!\n", buf);
+		ksft_exit_fail_msg("open %s failed: %s\n", buf, strerror(errno));
+
 	return fd;
 }
 
@@ -141,7 +142,7 @@ static int dmabuf_sync(int fd, int start_stop)
 
 #define ONE_MEG (1024 * 1024)
 
-static int test_alloc_and_import(char *heap_name)
+static void test_alloc_and_import(char *heap_name)
 {
 	int heap_fd = -1, dmabuf_fd = -1, importer_fd = -1;
 	uint32_t handle = 0;
@@ -149,27 +150,19 @@ static int test_alloc_and_import(char *heap_name)
 	int ret;
 
 	heap_fd = dmabuf_heap_open(heap_name);
-	if (heap_fd < 0)
-		return -1;
 
-	printf("  Testing allocation and importing:  ");
+	ksft_print_msg("Testing allocation and importing:\n");
 	ret = dmabuf_heap_alloc(heap_fd, ONE_MEG, 0, &dmabuf_fd);
 	if (ret) {
-		printf("FAIL (Allocation Failed!)\n");
-		ret = -1;
-		goto out;
+		ksft_test_result_fail("FAIL (Allocation Failed!) %d\n", ret);
+		return;
 	}
+
 	/* mmap and write a simple pattern */
-	p = mmap(NULL,
-		 ONE_MEG,
-		 PROT_READ | PROT_WRITE,
-		 MAP_SHARED,
-		 dmabuf_fd,
-		 0);
+	p = mmap(NULL, ONE_MEG, PROT_READ | PROT_WRITE, MAP_SHARED, dmabuf_fd, 0);
 	if (p == MAP_FAILED) {
-		printf("FAIL (mmap() failed)\n");
-		ret = -1;
-		goto out;
+		ksft_test_result_fail("FAIL (mmap() failed): %s\n", strerror(errno));
+		goto close_and_return;
 	}
 
 	dmabuf_sync(dmabuf_fd, DMA_BUF_SYNC_START);
@@ -179,71 +172,64 @@ static int test_alloc_and_import(char *heap_name)
 
 	importer_fd = open_vgem();
 	if (importer_fd < 0) {
-		ret = importer_fd;
-		printf("(Could not open vgem - skipping):  ");
+		ksft_test_result_skip("Could not open vgem %d\n", importer_fd);
 	} else {
 		ret = import_vgem_fd(importer_fd, dmabuf_fd, &handle);
-		if (ret < 0) {
-			printf("FAIL (Failed to import buffer)\n");
-			goto out;
-		}
+		ksft_test_result(ret >= 0, "Import buffer %d\n", ret);
 	}
 
 	ret = dmabuf_sync(dmabuf_fd, DMA_BUF_SYNC_START);
 	if (ret < 0) {
-		printf("FAIL (DMA_BUF_SYNC_START failed!)\n");
+		ksft_print_msg("FAIL (DMA_BUF_SYNC_START failed!) %d\n", ret);
 		goto out;
 	}
 
 	memset(p, 0xff, ONE_MEG);
 	ret = dmabuf_sync(dmabuf_fd, DMA_BUF_SYNC_END);
 	if (ret < 0) {
-		printf("FAIL (DMA_BUF_SYNC_END failed!)\n");
+		ksft_print_msg("FAIL (DMA_BUF_SYNC_END failed!) %d\n", ret);
 		goto out;
 	}
 
 	close_handle(importer_fd, handle);
-	ret = 0;
-	printf(" OK\n");
+	ksft_test_result_pass("%s dmabuf sync succeeded\n", __func__);
+	return;
+
 out:
-	if (p)
-		munmap(p, ONE_MEG);
-	if (importer_fd >= 0)
-		close(importer_fd);
-	if (dmabuf_fd >= 0)
-		close(dmabuf_fd);
-	if (heap_fd >= 0)
-		close(heap_fd);
+	ksft_test_result_fail("%s dmabuf sync failed\n", __func__);
+	munmap(p, ONE_MEG);
+	close(importer_fd);
 
-	return ret;
+close_and_return:
+	close(dmabuf_fd);
+	close(heap_fd);
 }
 
-static int test_alloc_zeroed(char *heap_name, size_t size)
+static void test_alloc_zeroed(char *heap_name, size_t size)
 {
 	int heap_fd = -1, dmabuf_fd[32];
-	int i, j, ret;
+	int i, j, k, ret;
 	void *p = NULL;
 	char *c;
 
-	printf("  Testing alloced %ldk buffers are zeroed:  ", size / 1024);
+	ksft_print_msg("Testing alloced %ldk buffers are zeroed:\n", size / 1024);
 	heap_fd = dmabuf_heap_open(heap_name);
-	if (heap_fd < 0)
-		return -1;
 
 	/* Allocate and fill a bunch of buffers */
 	for (i = 0; i < 32; i++) {
 		ret = dmabuf_heap_alloc(heap_fd, size, 0, &dmabuf_fd[i]);
-		if (ret < 0) {
-			printf("FAIL (Allocation (%i) failed)\n", i);
-			goto out;
+		if (ret) {
+			ksft_test_result_fail("FAIL (Allocation (%i) failed) %d\n", i, ret);
+			goto close_and_return;
 		}
+
 		/* mmap and fill with simple pattern */
 		p = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, dmabuf_fd[i], 0);
 		if (p == MAP_FAILED) {
-			printf("FAIL (mmap() failed!)\n");
-			ret = -1;
-			goto out;
+			ksft_test_result_fail("FAIL (mmap() failed!): %s\n", strerror(errno));
+			goto close_and_return;
 		}
+
 		dmabuf_sync(dmabuf_fd[i], DMA_BUF_SYNC_START);
 		memset(p, 0xff, size);
 		dmabuf_sync(dmabuf_fd[i], DMA_BUF_SYNC_END);
@@ -252,48 +238,47 @@ static int test_alloc_zeroed(char *heap_name, size_t size)
 	/* close them all */
 	for (i = 0; i < 32; i++)
 		close(dmabuf_fd[i]);
+	ksft_test_result_pass("Allocate and fill a bunch of buffers\n");
 
 	/* Allocate and validate all buffers are zeroed */
 	for (i = 0; i < 32; i++) {
 		ret = dmabuf_heap_alloc(heap_fd, size, 0, &dmabuf_fd[i]);
 		if (ret < 0) {
-			printf("FAIL (Allocation (%i) failed)\n", i);
-			goto out;
+			ksft_test_result_fail("FAIL (Allocation (%i) failed) %d\n", i, ret);
+			goto close_and_return;
 		}
 
 		/* mmap and validate everything is zero */
 		p = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED, dmabuf_fd[i], 0);
 		if (p == MAP_FAILED) {
-			printf("FAIL (mmap() failed!)\n");
-			ret = -1;
-			goto out;
+			ksft_test_result_fail("FAIL (mmap() failed!): %s\n", strerror(errno));
+			goto close_and_return;
 		}
+
 		dmabuf_sync(dmabuf_fd[i], DMA_BUF_SYNC_START);
 		c = (char *)p;
 		for (j = 0; j < size; j++) {
 			if (c[j] != 0) {
-				printf("FAIL (Allocated buffer not zeroed @ %i)\n", j);
-				break;
+				ksft_print_msg("FAIL (Allocated buffer not zeroed @ %i)\n", j);
+				dmabuf_sync(dmabuf_fd[i], DMA_BUF_SYNC_END);
+				munmap(p, size);
+				goto out;
 			}
 		}
 		dmabuf_sync(dmabuf_fd[i], DMA_BUF_SYNC_END);
 		munmap(p, size);
 	}
-	/* close them all */
-	for (i = 0; i < 32; i++)
-		close(dmabuf_fd[i]);
-
-	close(heap_fd);
-	printf("OK\n");
-	return 0;
 
 out:
-	while (i > 0) {
-		close(dmabuf_fd[i]);
-		i--;
-	}
+	ksft_test_result(i == 32, "Allocate and validate all buffers are zeroed\n");
+
+close_and_return:
+	/* close them all */
+	for (k = 0; k < i; k++)
+		close(dmabuf_fd[k]);
+
 	close(heap_fd);
-	return ret;
+	return;
 }
 
 /* Test the ioctl version compatibility w/ a smaller structure then expected */
@@ -361,126 +346,97 @@ static int dmabuf_heap_alloc_newer(int fd, size_t len, unsigned int flags,
 	return ret;
 }
 
-static int test_alloc_compat(char *heap_name)
+static void test_alloc_compat(char *heap_name)
 {
-	int heap_fd = -1, dmabuf_fd = -1;
-	int ret;
+	int ret, heap_fd = -1, dmabuf_fd = -1;
 
 	heap_fd = dmabuf_heap_open(heap_name);
-	if (heap_fd < 0)
-		return -1;
 
-	printf("  Testing (theoretical)older alloc compat:  ");
+	ksft_print_msg("Testing (theoretical) older alloc compat:\n");
 	ret = dmabuf_heap_alloc_older(heap_fd, ONE_MEG, 0, &dmabuf_fd);
-	if (ret) {
-		printf("FAIL (Older compat allocation failed!)\n");
-		ret = -1;
-		goto out;
-	}
-	close(dmabuf_fd);
-	printf("OK\n");
+	if (dmabuf_fd >= 0)
+		close(dmabuf_fd);
+	ksft_test_result(!ret, "dmabuf_heap_alloc_older\n");
 
-	printf("  Testing (theoretical)newer alloc compat:  ");
+	ksft_print_msg("Testing (theoretical) newer alloc compat:\n");
 	ret = dmabuf_heap_alloc_newer(heap_fd, ONE_MEG, 0, &dmabuf_fd);
-	if (ret) {
-		printf("FAIL (Newer compat allocation failed!)\n");
-		ret = -1;
-		goto out;
-	}
-	printf("OK\n");
-out:
 	if (dmabuf_fd >= 0)
 		close(dmabuf_fd);
-	if (heap_fd >= 0)
-		close(heap_fd);
+	ksft_test_result(!ret, "dmabuf_heap_alloc_newer\n");
 
-	return ret;
+	close(heap_fd);
 }
 
-static int test_alloc_errors(char *heap_name)
+static void test_alloc_errors(char *heap_name)
 {
 	int heap_fd = -1, dmabuf_fd = -1;
 	int ret;
 
 	heap_fd = dmabuf_heap_open(heap_name);
-	if (heap_fd < 0)
-		return -1;
 
-	printf("  Testing expected error cases:  ");
+	ksft_print_msg("Testing expected error cases:\n");
 	ret = dmabuf_heap_alloc(0, ONE_MEG, 0x111111, &dmabuf_fd);
-	if (!ret) {
-		printf("FAIL (Did not see expected error (invalid fd)!)\n");
-		ret = -1;
-		goto out;
-	}
+	ksft_test_result(ret, "Error expected on invalid fd %d\n", ret);
 
 	ret = dmabuf_heap_alloc(heap_fd, ONE_MEG, 0x111111, &dmabuf_fd);
-	if (!ret) {
-		printf("FAIL (Did not see expected error (invalid heap flags)!)\n");
-		ret = -1;
-		goto out;
-	}
+	ksft_test_result(ret, "Error expected on invalid heap flags %d\n", ret);
 
 	ret = dmabuf_heap_alloc_fdflags(heap_fd, ONE_MEG,
 					~(O_RDWR | O_CLOEXEC), 0, &dmabuf_fd);
-	if (!ret) {
-		printf("FAIL (Did not see expected error (invalid fd flags)!)\n");
-		ret = -1;
-		goto out;
-	}
+	ksft_test_result(ret, "Error expected on invalid heap flags %d\n", ret);
 
-	printf("OK\n");
-	ret = 0;
-out:
 	if (dmabuf_fd >= 0)
 		close(dmabuf_fd);
-	if (heap_fd >= 0)
-		close(heap_fd);
+	close(heap_fd);
+}
 
-	return ret;
+static int numer_of_heaps(void)
+{
+	DIR *d = opendir(DEVPATH);
+	struct dirent *dir;
+	int heaps = 0;
+
+	while ((dir = readdir(d))) {
+		if (!strncmp(dir->d_name, ".", 2))
+			continue;
+		if (!strncmp(dir->d_name, "..", 3))
+			continue;
+		heaps++;
+	}
+
+	return heaps;
 }
 
 int main(void)
 {
-	DIR *d;
 	struct dirent *dir;
-	int ret = -1;
+	DIR *d;
+
+	ksft_print_header();
 
 	d = opendir(DEVPATH);
 	if (!d) {
-		printf("No %s directory?\n", DEVPATH);
-		return -1;
+		ksft_print_msg("No %s directory?\n", DEVPATH);
+		return KSFT_SKIP;
 	}
 
-	while ((dir = readdir(d)) != NULL) {
+	ksft_set_plan(11 * numer_of_heaps());
+
+	while ((dir = readdir(d))) {
 		if (!strncmp(dir->d_name, ".", 2))
 			continue;
 		if (!strncmp(dir->d_name, "..", 3))
 			continue;
 
-		printf("Testing heap: %s\n", dir->d_name);
-		printf("=======================================\n");
-		ret = test_alloc_and_import(dir->d_name);
-		if (ret)
-			break;
-
-		ret = test_alloc_zeroed(dir->d_name, 4 * 1024);
-		if (ret)
-			break;
-
-		ret = test_alloc_zeroed(dir->d_name, ONE_MEG);
-		if (ret)
-			break;
-
-		ret = test_alloc_compat(dir->d_name);
-		if (ret)
-			break;
-
-		ret = test_alloc_errors(dir->d_name);
-		if (ret)
-			break;
+		ksft_print_msg("Testing heap: %s\n", dir->d_name);
+		ksft_print_msg("=======================================\n");
+		test_alloc_and_import(dir->d_name);
+		test_alloc_zeroed(dir->d_name, 4 * 1024);
+		test_alloc_zeroed(dir->d_name, ONE_MEG);
+		test_alloc_compat(dir->d_name);
+		test_alloc_errors(dir->d_name);
 	}
 	closedir(d);
 
-	return ret;
+	ksft_finished();
 }
diff --git a/tools/testing/selftests/drivers/dma-buf/Makefile b/tools/testing/selftests/drivers/dma-buf/Makefile
index 79cb16b4e01a..441407bb0e80 100644
--- a/tools/testing/selftests/drivers/dma-buf/Makefile
+++ b/tools/testing/selftests/drivers/dma-buf/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
-CFLAGS += -I../../../../../usr/include/
+CFLAGS += $(KHDR_INCLUDES)
 
 TEST_GEN_PROGS := udmabuf
 
diff --git a/tools/testing/selftests/drivers/dma-buf/udmabuf.c b/tools/testing/selftests/drivers/dma-buf/udmabuf.c
index c812080e304e..d78aec662586 100644
--- a/tools/testing/selftests/drivers/dma-buf/udmabuf.c
+++ b/tools/testing/selftests/drivers/dma-buf/udmabuf.c
@@ -9,52 +9,162 @@
 #include <errno.h>
 #include <fcntl.h>
 #include <malloc.h>
+#include <stdbool.h>
 
 #include <sys/ioctl.h>
 #include <sys/syscall.h>
+#include <sys/mman.h>
 #include <linux/memfd.h>
 #include <linux/udmabuf.h>
+#include "kselftest.h"
 
 #define TEST_PREFIX	"drivers/dma-buf/udmabuf"
 #define NUM_PAGES       4
+#define NUM_ENTRIES     4
+#define MEMFD_SIZE      1024 /* in pages */
 
-static int memfd_create(const char *name, unsigned int flags)
+static unsigned int page_size;
+
+static int create_memfd_with_seals(off64_t size, bool hpage)
+{
+	int memfd, ret;
+	unsigned int flags = MFD_ALLOW_SEALING;
+
+	if (hpage)
+		flags |= MFD_HUGETLB;
+
+	memfd = memfd_create("udmabuf-test", flags);
+	if (memfd < 0) {
+		ksft_print_msg("%s: [skip,no-memfd]\n", TEST_PREFIX);
+		exit(KSFT_SKIP);
+	}
+
+	ret = fcntl(memfd, F_ADD_SEALS, F_SEAL_SHRINK);
+	if (ret < 0) {
+		ksft_print_msg("%s: [skip,fcntl-add-seals]\n", TEST_PREFIX);
+		exit(KSFT_SKIP);
+	}
+
+	ret = ftruncate(memfd, size);
+	if (ret == -1) {
+		ksft_print_msg("%s: [FAIL,memfd-truncate]\n", TEST_PREFIX);
+		exit(KSFT_FAIL);
+	}
+
+	return memfd;
+}
+
+static int create_udmabuf_list(int devfd, int memfd, off64_t memfd_size)
+{
+	struct udmabuf_create_list *list;
+	int ubuf_fd, i;
+
+	list = malloc(sizeof(struct udmabuf_create_list) +
+		      sizeof(struct udmabuf_create_item) * NUM_ENTRIES);
+	if (!list) {
+		ksft_print_msg("%s: [FAIL, udmabuf-malloc]\n", TEST_PREFIX);
+		exit(KSFT_FAIL);
+	}
+
+	for (i = 0; i < NUM_ENTRIES; i++) {
+		list->list[i].memfd  = memfd;
+		list->list[i].offset = i * (memfd_size / NUM_ENTRIES);
+		list->list[i].size   = getpagesize() * NUM_PAGES;
+	}
+
+	list->count = NUM_ENTRIES;
+	list->flags = UDMABUF_FLAGS_CLOEXEC;
+	ubuf_fd = ioctl(devfd, UDMABUF_CREATE_LIST, list);
+	free(list);
+	if (ubuf_fd < 0) {
+		ksft_print_msg("%s: [FAIL, udmabuf-create]\n", TEST_PREFIX);
+		exit(KSFT_FAIL);
+	}
+
+	return ubuf_fd;
+}
+
+static void write_to_memfd(void *addr, off64_t size, char chr)
+{
+	int i;
+
+	for (i = 0; i < size / page_size; i++) {
+		*((char *)addr + (i * page_size)) = chr;
+	}
+}
+
+static void *mmap_fd(int fd, off64_t size)
 {
-	return syscall(__NR_memfd_create, name, flags);
+	void *addr;
+
+	addr = mmap(NULL, size, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);
+	if (addr == MAP_FAILED) {
+		ksft_print_msg("%s: ubuf_fd mmap fail\n", TEST_PREFIX);
+		exit(KSFT_FAIL);
+	}
+
+	return addr;
+}
+
+static int compare_chunks(void *addr1, void *addr2, off64_t memfd_size)
+{
+	off64_t off;
+	int i = 0, j, k = 0, ret = 0;
+	char char1, char2;
+
+	while (i < NUM_ENTRIES) {
+		off = i * (memfd_size / NUM_ENTRIES);
+		for (j = 0; j < NUM_PAGES; j++, k++) {
+			char1 = *((char *)addr1 + off + (j * getpagesize()));
+			char2 = *((char *)addr2 + (k * getpagesize()));
+			if (char1 != char2) {
+				ret = -1;
+				goto err;
+			}
+		}
+		i++;
+	}
+err:
+	munmap(addr1, memfd_size);
+	munmap(addr2, NUM_ENTRIES * NUM_PAGES * getpagesize());
+	return ret;
 }
 
 int main(int argc, char *argv[])
 {
 	struct udmabuf_create create;
 	int devfd, memfd, buf, ret;
-	off_t size;
-	void *mem;
+	off64_t size;
+	void *addr1, *addr2;
+
+	ksft_print_header();
+	ksft_set_plan(7);
 
 	devfd = open("/dev/udmabuf", O_RDWR);
 	if (devfd < 0) {
-		printf("%s: [skip,no-udmabuf: Unable to access DMA buffer device file]\n",
-		       TEST_PREFIX);
-		exit(77);
+		ksft_print_msg(
+			"%s: [skip,no-udmabuf: Unable to access DMA buffer device file]\n",
+			TEST_PREFIX);
+		exit(KSFT_SKIP);
 	}
 
 	memfd = memfd_create("udmabuf-test", MFD_ALLOW_SEALING);
 	if (memfd < 0) {
-		printf("%s: [skip,no-memfd]\n", TEST_PREFIX);
-		exit(77);
+		ksft_print_msg("%s: [skip,no-memfd]\n", TEST_PREFIX);
+		exit(KSFT_SKIP);
 	}
 
 	ret = fcntl(memfd, F_ADD_SEALS, F_SEAL_SHRINK);
 	if (ret < 0) {
-		printf("%s: [skip,fcntl-add-seals]\n", TEST_PREFIX);
-		exit(77);
+		ksft_print_msg("%s: [skip,fcntl-add-seals]\n", TEST_PREFIX);
+		exit(KSFT_SKIP);
 	}
 
-
 	size = getpagesize() * NUM_PAGES;
 	ret = ftruncate(memfd, size);
 	if (ret == -1) {
-		printf("%s: [FAIL,memfd-truncate]\n", TEST_PREFIX);
-		exit(1);
+		ksft_print_msg("%s: [FAIL,memfd-truncate]\n", TEST_PREFIX);
+		exit(KSFT_FAIL);
 	}
 
 	memset(&create, 0, sizeof(create));
@@ -64,44 +174,104 @@ int main(int argc, char *argv[])
 	create.offset = getpagesize()/2;
 	create.size   = getpagesize();
 	buf = ioctl(devfd, UDMABUF_CREATE, &create);
-	if (buf >= 0) {
-		printf("%s: [FAIL,test-1]\n", TEST_PREFIX);
-		exit(1);
-	}
+	if (buf >= 0)
+		ksft_test_result_fail("%s: [FAIL,test-1]\n", TEST_PREFIX);
+	else
+		ksft_test_result_pass("%s: [PASS,test-1]\n", TEST_PREFIX);
 
 	/* should fail (size not multiple of page) */
 	create.memfd  = memfd;
 	create.offset = 0;
 	create.size   = getpagesize()/2;
 	buf = ioctl(devfd, UDMABUF_CREATE, &create);
-	if (buf >= 0) {
-		printf("%s: [FAIL,test-2]\n", TEST_PREFIX);
-		exit(1);
-	}
+	if (buf >= 0)
+		ksft_test_result_fail("%s: [FAIL,test-2]\n", TEST_PREFIX);
+	else
+		ksft_test_result_pass("%s: [PASS,test-2]\n", TEST_PREFIX);
 
 	/* should fail (not memfd) */
 	create.memfd  = 0; /* stdin */
 	create.offset = 0;
 	create.size   = size;
 	buf = ioctl(devfd, UDMABUF_CREATE, &create);
-	if (buf >= 0) {
-		printf("%s: [FAIL,test-3]\n", TEST_PREFIX);
-		exit(1);
-	}
+	if (buf >= 0)
+		ksft_test_result_fail("%s: [FAIL,test-3]\n", TEST_PREFIX);
+	else
+		ksft_test_result_pass("%s: [PASS,test-3]\n", TEST_PREFIX);
 
 	/* should work */
+	page_size = getpagesize();
+	addr1 = mmap_fd(memfd, size);
+	write_to_memfd(addr1, size, 'a');
 	create.memfd  = memfd;
 	create.offset = 0;
 	create.size   = size;
 	buf = ioctl(devfd, UDMABUF_CREATE, &create);
-	if (buf < 0) {
-		printf("%s: [FAIL,test-4]\n", TEST_PREFIX);
-		exit(1);
-	}
+	if (buf < 0)
+		ksft_test_result_fail("%s: [FAIL,test-4]\n", TEST_PREFIX);
+	else
+		ksft_test_result_pass("%s: [PASS,test-4]\n", TEST_PREFIX);
+
+	munmap(addr1, size);
+	close(buf);
+	close(memfd);
+
+	/* should work (migration of 4k size pages)*/
+	size = MEMFD_SIZE * page_size;
+	memfd = create_memfd_with_seals(size, false);
+	addr1 = mmap_fd(memfd, size);
+	write_to_memfd(addr1, size, 'a');
+	buf = create_udmabuf_list(devfd, memfd, size);
+	addr2 = mmap_fd(buf, NUM_PAGES * NUM_ENTRIES * getpagesize());
+	write_to_memfd(addr1, size, 'b');
+	ret = compare_chunks(addr1, addr2, size);
+	if (ret < 0)
+		ksft_test_result_fail("%s: [FAIL,test-5]\n", TEST_PREFIX);
+	else
+		ksft_test_result_pass("%s: [PASS,test-5]\n", TEST_PREFIX);
+
+	close(buf);
+	close(memfd);
+
+	/* should work (migration of 2MB size huge pages)*/
+	page_size = getpagesize() * 512; /* 2 MB */
+	size = MEMFD_SIZE * page_size;
+	memfd = create_memfd_with_seals(size, true);
+	addr1 = mmap_fd(memfd, size);
+	write_to_memfd(addr1, size, 'a');
+	buf = create_udmabuf_list(devfd, memfd, size);
+	addr2 = mmap_fd(buf, NUM_PAGES * NUM_ENTRIES * getpagesize());
+	write_to_memfd(addr1, size, 'b');
+	ret = compare_chunks(addr1, addr2, size);
+	if (ret < 0)
+		ksft_test_result_fail("%s: [FAIL,test-6]\n", TEST_PREFIX);
+	else
+		ksft_test_result_pass("%s: [PASS,test-6]\n", TEST_PREFIX);
+
+	close(buf);
+	close(memfd);
+
+	/* same test as above but we pin first before writing to memfd */
+	page_size = getpagesize() * 512; /* 2 MB */
+	size = MEMFD_SIZE * page_size;
+	memfd = create_memfd_with_seals(size, true);
+	buf = create_udmabuf_list(devfd, memfd, size);
+	addr2 = mmap_fd(buf, NUM_PAGES * NUM_ENTRIES * getpagesize());
+	addr1 = mmap_fd(memfd, size);
+	write_to_memfd(addr1, size, 'a');
+	write_to_memfd(addr1, size, 'b');
+	ret = compare_chunks(addr1, addr2, size);
+	if (ret < 0)
+		ksft_test_result_fail("%s: [FAIL,test-7]\n", TEST_PREFIX);
+	else
+		ksft_test_result_pass("%s: [PASS,test-7]\n", TEST_PREFIX);
 
-	fprintf(stderr, "%s: ok\n", TEST_PREFIX);
 	close(buf);
 	close(memfd);
 	close(devfd);
+
+	ksft_print_msg("%s: ok\n", TEST_PREFIX);
+	ksft_print_cnts();
+
 	return 0;
 }
diff --git a/tools/testing/selftests/drivers/net/.gitignore b/tools/testing/selftests/drivers/net/.gitignore
new file mode 100644
index 000000000000..3633c7a3ed65
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/.gitignore
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+gro
+napi_id_helper
+psp_responder
diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile
new file mode 100644
index 000000000000..f5c71d993750
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/Makefile
@@ -0,0 +1,43 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += $(KHDR_INCLUDES)
+
+TEST_INCLUDES := $(wildcard lib/py/*.py) \
+		 $(wildcard lib/sh/*.sh) \
+		 ../../net/lib.sh \
+
+TEST_GEN_FILES := \
+	gro \
+	napi_id_helper \
+# end of TEST_GEN_FILES
+
+TEST_PROGS := \
+	gro.py \
+	hds.py \
+	napi_id.py \
+	napi_threaded.py \
+	netcons_basic.sh \
+	netcons_cmdline.sh \
+	netcons_fragmented_msg.sh \
+	netcons_overflow.sh \
+	netcons_sysdata.sh \
+	netcons_torture.sh \
+	netpoll_basic.py \
+	ping.py \
+	psp.py \
+	queues.py \
+	ring_reconfig.py \
+	shaper.py \
+	stats.py \
+	xdp.py \
+# end of TEST_PROGS
+
+# YNL files, must be before "include ..lib.mk"
+YNL_GEN_FILES := psp_responder
+TEST_GEN_FILES += $(YNL_GEN_FILES)
+
+include ../../lib.mk
+
+# YNL build
+YNL_GENS := psp
+
+include ../../net/ynl.mk
diff --git a/tools/testing/selftests/drivers/net/README.rst b/tools/testing/selftests/drivers/net/README.rst
new file mode 100644
index 000000000000..eb838ae94844
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/README.rst
@@ -0,0 +1,136 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Running driver tests
+====================
+
+Networking driver tests are executed within kselftest framework like any
+other tests. They support testing both real device drivers and emulated /
+software drivers (latter mostly to test the core parts of the stack).
+
+SW mode
+~~~~~~~
+
+By default, when no extra parameters are set or exported, tests execute
+against software drivers such as netdevsim. No extra preparation is required
+the software devices are created and destroyed as part of the test.
+In this mode the tests are indistinguishable from other selftests and
+(for example) can be run under ``virtme-ng`` like the core networking selftests.
+
+HW mode
+~~~~~~~
+
+Executing tests against a real device requires external preparation.
+The netdevice against which tests will be run must exist, be running
+(in UP state) and be configured with an IP address.
+
+Refer to list of :ref:`Variables` later in this file to set up running
+the tests against a real device.
+
+Both modes required
+~~~~~~~~~~~~~~~~~~~
+
+All tests in drivers/net must support running both against a software device
+and a real device. SW-only tests should instead be placed in net/ or
+drivers/net/netdevsim, HW-only tests in drivers/net/hw.
+
+Variables
+=========
+
+The variables can be set in the environment or by creating a net.config
+file in the same directory as this README file. Example::
+
+  $ NETIF=eth0 ./some_test.sh
+
+or::
+
+  $ cat tools/testing/selftests/drivers/net/net.config
+  # Variable set in a file
+  NETIF=eth0
+
+Local test (which don't require endpoint for sending / receiving traffic)
+need only the ``NETIF`` variable. Remaining variables define the endpoint
+and communication method.
+
+NETIF
+~~~~~
+
+Name of the netdevice against which the test should be executed.
+When empty or not set software devices will be used.
+
+LOCAL_V4, LOCAL_V6, REMOTE_V4, REMOTE_V6
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Local and remote endpoint IP addresses.
+
+REMOTE_TYPE
+~~~~~~~~~~~
+
+Communication method used to run commands on the remote endpoint.
+Test framework has built-in support for ``netns`` and ``ssh`` channels.
+``netns`` assumes the "remote" interface is part of the same
+host, just moved to the specified netns.
+``ssh`` communicates with remote endpoint over ``ssh`` and ``scp``.
+Using persistent SSH connections is strongly encouraged to avoid
+the latency of SSH connection setup on every command.
+
+Communication methods are defined by classes in ``lib/py/remote_{name}.py``.
+It should be possible to add a new method without modifying any of
+the framework, by simply adding an appropriately named file to ``lib/py``.
+
+REMOTE_ARGS
+~~~~~~~~~~~
+
+Arguments used to construct the communication channel.
+Communication channel dependent::
+
+  for netns - name of the "remote" namespace
+  for ssh - name/address of the remote host
+
+Example
+=======
+
+Build the selftests::
+
+  # make -C tools/testing/selftests/ TARGETS="drivers/net drivers/net/hw"
+
+"Install" the tests and copy them over to the target machine::
+
+  # make -C tools/testing/selftests/ TARGETS="drivers/net drivers/net/hw" \
+     install INSTALL_PATH=/tmp/ksft-net-drv
+
+  # rsync -ra --delete /tmp/ksft-net-drv root@192.168.1.1:/root/
+
+On the target machine, running the tests will use netdevsim by default::
+
+  [/root] # ./ksft-net-drv/run_kselftest.sh -t drivers/net:ping.py
+  TAP version 13
+  1..1
+  # timeout set to 45
+  # selftests: drivers/net: ping.py
+  # TAP version 13
+  # 1..3
+  # ok 1 ping.test_v4
+  # ok 2 ping.test_v6
+  # ok 3 ping.test_tcp
+  # # Totals: pass:3 fail:0 xfail:0 xpass:0 skip:0 error:0
+  ok 1 selftests: drivers/net: ping.py
+
+Create a config with remote info::
+
+  [/root] # cat > ./ksft-net-drv/drivers/net/net.config <<EOF
+  NETIF=eth0
+  LOCAL_V4=192.168.1.1
+  REMOTE_V4=192.168.1.2
+  REMOTE_TYPE=ssh
+  REMOTE_ARGS=root@192.168.1.2
+  EOF
+
+Run the test::
+
+  [/root] # ./ksft-net-drv/drivers/net/ping.py
+  TAP version 13
+  1..3
+  ok 1 ping.test_v4
+  ok 2 ping.test_v6 # SKIP Test requires IPv6 connectivity
+  ok 3 ping.test_tcp
+  # Totals: pass:2 fail:0 xfail:0 xpass:0 skip:1 error:0
diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile
index 8e3b786a748f..6c5c60adb5e8 100644
--- a/tools/testing/selftests/drivers/net/bonding/Makefile
+++ b/tools/testing/selftests/drivers/net/bonding/Makefile
@@ -4,14 +4,29 @@
 TEST_PROGS := \
 	bond-arp-interval-causes-panic.sh \
 	bond-break-lacpdu-tx.sh \
+	bond-eth-type-change.sh \
 	bond-lladdr-target.sh \
+	bond_ipsec_offload.sh \
+	bond_lacp_prio.sh \
+	bond_macvlan_ipvlan.sh \
+	bond_options.sh \
+	bond_passive_lacp.sh \
 	dev_addr_lists.sh \
 	mode-1-recovery-updelay.sh \
 	mode-2-recovery-updelay.sh \
-	option_prio.sh
+	netcons_over_bonding.sh \
+# end of TEST_PROGS
 
 TEST_FILES := \
+	bond_topo_2d1c.sh \
+	bond_topo_3d1c.sh \
 	lag_lib.sh \
-	net_forwarding_lib.sh
+# end of TEST_FILES
+
+TEST_INCLUDES := \
+	../../../net/lib.sh \
+	../lib/sh/lib_netcons.sh \
+	../../../net/forwarding/lib.sh \
+# end of TEST_INCLUDES
 
 include ../../../lib.mk
diff --git a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh
index 71c00bfafbc9..5667febee328 100755
--- a/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh
+++ b/tools/testing/selftests/drivers/net/bonding/bond-arp-interval-causes-panic.sh
@@ -11,7 +11,6 @@ finish()
 {
 	ip netns delete server || true
 	ip netns delete client || true
-	ip link del link1_1 || true
 }
 
 trap finish EXIT
@@ -23,26 +22,24 @@ server_ip4=192.168.1.254
 echo 180 >/proc/sys/kernel/panic
 
 # build namespaces
-ip link add dev link1_1 type veth peer name link1_2
-
 ip netns add "server"
-ip link set dev link1_2 netns server up name eth0
+ip netns add "client"
+ip -n client link add eth0 type veth peer name eth0 netns server
+ip netns exec server ip link set dev eth0 up
 ip netns exec server ip addr add ${server_ip4}/24 dev eth0
 
-ip netns add "client"
-ip link set dev link1_1 netns client down name eth0
 ip netns exec client ip link add dev bond0 down type bond mode 1 \
 	miimon 100 all_slaves_active 1
-ip netns exec client ip link set dev eth0 down master bond0
+ip netns exec client ip link set dev eth0 master bond0
 ip netns exec client ip link set dev bond0 up
 ip netns exec client ip addr add ${client_ip4}/24 dev bond0
 ip netns exec client ping -c 5 $server_ip4 >/dev/null
 
-ip netns exec client ip link set dev eth0 down nomaster
+ip netns exec client ip link set dev eth0 nomaster
 ip netns exec client ip link set dev bond0 down
 ip netns exec client ip link set dev bond0 type bond mode 0 \
 	arp_interval 1000 arp_ip_target "+${server_ip4}"
-ip netns exec client ip link set dev eth0 down master bond0
+ip netns exec client ip link set dev eth0 master bond0
 ip netns exec client ip link set dev bond0 up
 ip netns exec client ping -c 5 $server_ip4 >/dev/null
 
diff --git a/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh b/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh
index 47ab90596acb..1ec7f59db7f4 100755
--- a/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh
+++ b/tools/testing/selftests/drivers/net/bonding/bond-break-lacpdu-tx.sh
@@ -20,21 +20,21 @@
 #    +------+ +------+
 #
 # We use veths instead of physical interfaces
+REQUIRE_MZ=no
+NUM_NETIFS=0
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/forwarding/lib.sh
 
 set -e
-tmp=$(mktemp -q dump.XXXXXX)
 cleanup() {
 	ip link del fab-br0 >/dev/null 2>&1 || :
 	ip link del fbond  >/dev/null 2>&1 || :
 	ip link del veth1-bond  >/dev/null 2>&1 || :
 	ip link del veth2-bond  >/dev/null 2>&1 || :
-	modprobe -r bonding  >/dev/null 2>&1 || :
-	rm -f -- ${tmp}
 }
 
 trap cleanup 0 1 2
 cleanup
-sleep 1
 
 # create the bridge
 ip link add fab-br0 address 52:54:00:3B:7C:A6 mtu 1500 type bridge \
@@ -57,8 +57,8 @@ ip link add name veth2-bond type veth peer name veth2-end
 
 # add ports
 ip link set fbond master fab-br0
-ip link set veth1-bond down master fbond
-ip link set veth2-bond down master fbond
+ip link set veth1-bond master fbond
+ip link set veth2-bond master fbond
 
 # bring up
 ip link set veth1-end up
@@ -67,13 +67,12 @@ ip link set fab-br0 up
 ip link set fbond up
 ip addr add dev fab-br0 10.0.0.3
 
-tcpdump -n -i veth1-end -e ether proto 0x8809 >${tmp} 2>&1 &
-sleep 15
-pkill tcpdump >/dev/null 2>&1
 rc=0
-num=$(grep "packets captured" ${tmp} | awk '{print $1}')
-if test "$num" -gt 0; then
-	echo "PASS, captured ${num}"
+tc qdisc add dev veth1-end clsact
+tc filter add dev veth1-end ingress protocol 0x8809 pref 1 handle 101 flower skip_hw action pass
+if slowwait_for_counter 15 2 \
+	tc_rule_handle_stats_get "dev veth1-end ingress" 101 ".packets" "" &> /dev/null; then
+	echo "PASS, captured 2"
 else
 	echo "FAIL"
 	rc=1
diff --git a/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh b/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh
new file mode 100755
index 000000000000..8293dbc7c18f
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/bond-eth-type-change.sh
@@ -0,0 +1,84 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test bond device ether type changing
+#
+
+ALL_TESTS="
+	bond_test_unsuccessful_enslave_type_change
+	bond_test_successful_enslave_type_change
+"
+REQUIRE_MZ=no
+NUM_NETIFS=0
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/forwarding/lib.sh
+
+bond_check_flags()
+{
+	local bonddev=$1
+
+	ip -d l sh dev "$bonddev" | grep -q "MASTER"
+	check_err $? "MASTER flag is missing from the bond device"
+
+	ip -d l sh dev "$bonddev" | grep -q "SLAVE"
+	check_err $? "SLAVE flag is missing from the bond device"
+}
+
+# test enslaved bond dev type change from ARPHRD_ETHER and back
+# this allows us to test both MASTER and SLAVE flags at once
+bond_test_enslave_type_change()
+{
+	local test_success=$1
+	local devbond0="test-bond0"
+	local devbond1="test-bond1"
+	local devbond2="test-bond2"
+	local nonethdev="test-noneth0"
+
+	# create a non-ARPHRD_ETHER device for testing (e.g. nlmon type)
+	ip link add name "$nonethdev" type nlmon
+	check_err $? "could not create a non-ARPHRD_ETHER device (nlmon)"
+	ip link add name "$devbond0" type bond
+	if [ $test_success -eq 1 ]; then
+		# we need devbond0 in active-backup mode to successfully enslave nonethdev
+		ip link set dev "$devbond0" type bond mode active-backup
+		check_err $? "could not change bond mode to active-backup"
+	fi
+	ip link add name "$devbond1" type bond
+	ip link add name "$devbond2" type bond
+	ip link set dev "$devbond0" master "$devbond1"
+	check_err $? "could not enslave $devbond0 to $devbond1"
+	# change bond type to non-ARPHRD_ETHER
+	ip link set dev "$nonethdev" master "$devbond0" 1>/dev/null 2>/dev/null
+	ip link set dev "$nonethdev" nomaster 1>/dev/null 2>/dev/null
+	# restore ARPHRD_ETHER type by enslaving such device
+	ip link set dev "$devbond2" master "$devbond0"
+	check_err $? "could not enslave $devbond2 to $devbond0"
+
+	bond_check_flags "$devbond0"
+
+	# clean up
+	ip link del dev "$devbond0"
+	ip link del dev "$devbond1"
+	ip link del dev "$devbond2"
+	ip link del dev "$nonethdev"
+}
+
+bond_test_unsuccessful_enslave_type_change()
+{
+	RET=0
+
+	bond_test_enslave_type_change 0
+	log_test "Change ether type of an enslaved bond device with unsuccessful enslave"
+}
+
+bond_test_successful_enslave_type_change()
+{
+	RET=0
+
+	bond_test_enslave_type_change 1
+	log_test "Change ether type of an enslaved bond device with successful enslave"
+}
+
+tests_run
+
+exit "$EXIT_STATUS"
diff --git a/tools/testing/selftests/drivers/net/bonding/bond-lladdr-target.sh b/tools/testing/selftests/drivers/net/bonding/bond-lladdr-target.sh
index 89af402fabbe..78d3e0fe6604 100755
--- a/tools/testing/selftests/drivers/net/bonding/bond-lladdr-target.sh
+++ b/tools/testing/selftests/drivers/net/bonding/bond-lladdr-target.sh
@@ -17,6 +17,11 @@
 #  +----------------+
 #
 # We use veths instead of physical interfaces
+REQUIRE_MZ=no
+NUM_NETIFS=0
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/forwarding/lib.sh
+
 sw="sw-$(mktemp -u XXXXXX)"
 host="ns-$(mktemp -u XXXXXX)"
 
@@ -26,6 +31,16 @@ cleanup()
 	ip netns del $host
 }
 
+wait_lladdr_dad()
+{
+	$@ | grep fe80 | grep -qv tentative
+}
+
+wait_bond_up()
+{
+	$@ | grep -q 'state UP'
+}
+
 trap cleanup 0 1 2
 
 ip netns add $sw
@@ -37,8 +52,8 @@ ip -n $host link add veth1 type veth peer name veth1 netns $sw
 ip -n $sw link add br0 type bridge
 ip -n $sw link set br0 up
 sw_lladdr=$(ip -n $sw addr show br0 | awk '/fe80/{print $2}' | cut -d'/' -f1)
-# sleep some time to make sure bridge lladdr pass DAD
-sleep 2
+# wait some time to make sure bridge lladdr pass DAD
+slowwait 2 wait_lladdr_dad ip -n $sw addr show br0
 
 ip -n $host link add bond0 type bond mode 1 ns_ip6_target ${sw_lladdr} \
 	arp_validate 3 arp_interval 1000
@@ -53,7 +68,7 @@ ip -n $sw link set veth1 master br0
 ip -n $sw link set veth0 up
 ip -n $sw link set veth1 up
 
-sleep 5
+slowwait 5 wait_bond_up ip -n $host link show bond0
 
 rc=0
 if ip -n $host link show bond0 | grep -q LOWER_UP; then
diff --git a/tools/testing/selftests/drivers/net/bonding/bond_ipsec_offload.sh b/tools/testing/selftests/drivers/net/bonding/bond_ipsec_offload.sh
new file mode 100755
index 000000000000..f09e100232c7
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/bond_ipsec_offload.sh
@@ -0,0 +1,156 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# IPsec over bonding offload test:
+#
+#  +----------------+
+#  |     bond0      |
+#  |       |        |
+#  |  eth0    eth1  |
+#  +---+-------+----+
+#
+# We use netdevsim instead of physical interfaces
+#-------------------------------------------------------------------
+# Example commands
+#   ip x s add proto esp src 192.0.2.1 dst 192.0.2.2 \
+#            spi 0x07 mode transport reqid 0x07 replay-window 32 \
+#            aead 'rfc4106(gcm(aes))' 1234567890123456dcba 128 \
+#            sel src 192.0.2.1/24 dst 192.0.2.2/24
+#            offload dev bond0 dir out
+#   ip x p add dir out src 192.0.2.1/24 dst 192.0.2.2/24 \
+#            tmpl proto esp src 192.0.2.1 dst 192.0.2.2 \
+#            spi 0x07 mode transport reqid 0x07
+#
+#-------------------------------------------------------------------
+
+lib_dir=$(dirname "$0")
+# shellcheck disable=SC1091
+source "$lib_dir"/../../../net/lib.sh
+srcip=192.0.2.1
+dstip=192.0.2.2
+ipsec0=/sys/kernel/debug/netdevsim/netdevsim0/ports/0/ipsec
+ipsec1=/sys/kernel/debug/netdevsim/netdevsim0/ports/1/ipsec
+active_slave=""
+
+# shellcheck disable=SC2317
+active_slave_changed()
+{
+	local old_active_slave=$1
+	local new_active_slave
+
+	# shellcheck disable=SC2154
+	new_active_slave=$(ip -n "${ns}" -d -j link show bond0 | \
+		jq -r ".[].linkinfo.info_data.active_slave")
+	[ "$new_active_slave" != "$old_active_slave" ] && [ "$new_active_slave" != "null" ]
+}
+
+test_offload()
+{
+	# use ping to exercise the Tx path
+	ip netns exec "$ns" ping -I bond0 -c 3 -W 1 -i 0 "$dstip" >/dev/null
+
+	active_slave=$(ip -n "${ns}" -d -j link show bond0 | \
+		       jq -r ".[].linkinfo.info_data.active_slave")
+
+	if [ "$active_slave" = "$nic0" ]; then
+		sysfs=$ipsec0
+	elif [ "$active_slave" = "$nic1" ]; then
+		sysfs=$ipsec1
+	else
+		check_err 1 "bond_ipsec_offload invalid active_slave $active_slave"
+	fi
+
+	# The tx/rx order in sysfs may changed after failover
+	grep -q "SA count=2 tx=3" "$sysfs" && grep -q "tx ipaddr=$dstip" "$sysfs"
+	check_err $? "incorrect tx count with link ${active_slave}"
+
+	log_test bond_ipsec_offload "active_slave ${active_slave}"
+}
+
+setup_env()
+{
+	if ! mount | grep -q debugfs; then
+		mount -t debugfs none /sys/kernel/debug/ &> /dev/null
+		defer umount /sys/kernel/debug/
+
+	fi
+
+	# setup netdevsim since dummy/veth dev doesn't have offload support
+	if [ ! -w /sys/bus/netdevsim/new_device ] ; then
+		if ! modprobe -q netdevsim; then
+			echo "SKIP: can't load netdevsim for ipsec offload"
+			# shellcheck disable=SC2154
+			exit "$ksft_skip"
+		fi
+		defer modprobe -r netdevsim
+	fi
+
+	setup_ns ns
+	defer cleanup_ns "$ns"
+}
+
+setup_bond()
+{
+	ip -n "$ns" link add bond0 type bond mode active-backup miimon 100
+	ip -n "$ns" addr add "$srcip/24" dev bond0
+	ip -n "$ns" link set bond0 up
+
+	echo "0 2" | ip netns exec "$ns" tee /sys/bus/netdevsim/new_device >/dev/null
+	nic0=$(ip netns exec "$ns" ls /sys/bus/netdevsim/devices/netdevsim0/net | head -n 1)
+	nic1=$(ip netns exec "$ns" ls /sys/bus/netdevsim/devices/netdevsim0/net | tail -n 1)
+	ip -n "$ns" link set "$nic0" master bond0
+	ip -n "$ns" link set "$nic1" master bond0
+
+	# we didn't create a peer, make sure we can Tx by adding a permanent
+	# neighbour this need to be added after enslave
+	ip -n "$ns" neigh add "$dstip" dev bond0 lladdr 00:11:22:33:44:55
+
+	# create offloaded SAs, both in and out
+	ip -n "$ns" x p add dir out src "$srcip/24" dst "$dstip/24" \
+	    tmpl proto esp src "$srcip" dst "$dstip" spi 9 \
+	    mode transport reqid 42
+
+	ip -n "$ns" x p add dir in src "$dstip/24" dst "$srcip/24" \
+	    tmpl proto esp src "$dstip" dst "$srcip" spi 9 \
+	    mode transport reqid 42
+
+	ip -n "$ns" x s add proto esp src "$srcip" dst "$dstip" spi 9 \
+	    mode transport reqid 42 aead "rfc4106(gcm(aes))" \
+	    0x3132333435363738393031323334353664636261 128 \
+	    sel src "$srcip/24" dst "$dstip/24" \
+	    offload dev bond0 dir out
+
+	ip -n "$ns" x s add proto esp src "$dstip" dst "$srcip" spi 9 \
+	    mode transport reqid 42 aead "rfc4106(gcm(aes))" \
+	    0x3132333435363738393031323334353664636261 128 \
+	    sel src "$dstip/24" dst "$srcip/24" \
+	    offload dev bond0 dir in
+
+	# does offload show up in ip output
+	lines=$(ip -n "$ns" x s list | grep -c "crypto offload parameters: dev bond0 dir")
+	if [ "$lines" -ne 2 ] ; then
+		check_err 1 "bond_ipsec_offload SA offload missing from list output"
+	fi
+}
+
+trap defer_scopes_cleanup EXIT
+setup_env
+setup_bond
+
+# start Offload testing
+test_offload
+
+# do failover and re-test
+ip -n "$ns" link set "$active_slave" down
+slowwait 5 active_slave_changed "$active_slave"
+test_offload
+
+# make sure offload get removed from driver
+ip -n "$ns" x s flush
+ip -n "$ns" x p flush
+line0=$(grep -c "SA count=0" "$ipsec0")
+line1=$(grep -c "SA count=0" "$ipsec1")
+[ "$line0" -ne 1 ] || [ "$line1" -ne 1 ]
+check_fail $? "bond_ipsec_offload SA not removed from driver"
+
+exit "$EXIT_STATUS"
diff --git a/tools/testing/selftests/drivers/net/bonding/bond_lacp_prio.sh b/tools/testing/selftests/drivers/net/bonding/bond_lacp_prio.sh
new file mode 100755
index 000000000000..a483d505c6a8
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/bond_lacp_prio.sh
@@ -0,0 +1,108 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Testing if bond lacp per port priority works
+#
+#          Switch (s_ns)          Backup Switch (b_ns)
+#  +-------------------------+ +-------------------------+
+#  |          bond0          | |          bond0          |
+#  |            +            | |            +            |
+#  |      eth0  |  eth1      | |      eth0  |  eth1      |
+#  |        +---+---+        | |        +---+---+        |
+#  |        |       |        | |        |       |        |
+#  +-------------------------+ +-------------------------+
+#           |       |                   |       |
+#  +-----------------------------------------------------+
+#  |        |       |                   |       |        |
+#  |        +-------+---------+---------+-------+        |
+#  |      eth0     eth1       |       eth2     eth3      |
+#  |                          +                          |
+#  |                        bond0                        |
+#  +-----------------------------------------------------+
+#                        Client (c_ns)
+
+lib_dir=$(dirname "$0")
+# shellcheck disable=SC1091
+source "$lib_dir"/../../../net/lib.sh
+
+setup_links()
+{
+	# shellcheck disable=SC2154
+	ip -n "${c_ns}" link add eth0 type veth peer name eth0 netns "${s_ns}"
+	ip -n "${c_ns}" link add eth1 type veth peer name eth1 netns "${s_ns}"
+	# shellcheck disable=SC2154
+	ip -n "${c_ns}" link add eth2 type veth peer name eth0 netns "${b_ns}"
+	ip -n "${c_ns}" link add eth3 type veth peer name eth1 netns "${b_ns}"
+
+	ip -n "${c_ns}" link add bond0 type bond mode 802.3ad miimon 100 \
+		lacp_rate fast ad_select actor_port_prio
+	ip -n "${s_ns}" link add bond0 type bond mode 802.3ad miimon 100 \
+		lacp_rate fast
+	ip -n "${b_ns}" link add bond0 type bond mode 802.3ad miimon 100 \
+		lacp_rate fast
+
+	ip -n "${c_ns}" link set eth0 master bond0
+	ip -n "${c_ns}" link set eth1 master bond0
+	ip -n "${c_ns}" link set eth2 master bond0
+	ip -n "${c_ns}" link set eth3 master bond0
+	ip -n "${s_ns}" link set eth0 master bond0
+	ip -n "${s_ns}" link set eth1 master bond0
+	ip -n "${b_ns}" link set eth0 master bond0
+	ip -n "${b_ns}" link set eth1 master bond0
+
+	ip -n "${c_ns}" link set bond0 up
+	ip -n "${s_ns}" link set bond0 up
+	ip -n "${b_ns}" link set bond0 up
+}
+
+test_port_prio_setting()
+{
+	RET=0
+	ip -n "${c_ns}" link set eth0 type bond_slave actor_port_prio 1000
+	prio=$(cmd_jq "ip -n ${c_ns} -d -j link show eth0" \
+		".[].linkinfo.info_slave_data.actor_port_prio")
+	[ "$prio" -ne 1000 ] && RET=1
+	ip -n "${c_ns}" link set eth2 type bond_slave actor_port_prio 10
+	prio=$(cmd_jq "ip -n ${c_ns} -d -j link show eth2" \
+		".[].linkinfo.info_slave_data.actor_port_prio")
+	[ "$prio" -ne 10 ] && RET=1
+}
+
+test_agg_reselect()
+{
+	local bond_agg_id slave_agg_id
+	local expect_slave="$1"
+	RET=0
+
+	# Trigger link state change to reselect the aggregator
+	ip -n "${c_ns}" link set eth1 down
+	sleep 0.5
+	ip -n "${c_ns}" link set eth1 up
+	sleep 0.5
+
+	bond_agg_id=$(cmd_jq "ip -n ${c_ns} -d -j link show bond0" \
+		".[].linkinfo.info_data.ad_info.aggregator")
+	slave_agg_id=$(cmd_jq "ip -n ${c_ns} -d -j link show $expect_slave" \
+		".[].linkinfo.info_slave_data.ad_aggregator_id")
+	# shellcheck disable=SC2034
+	[ "${bond_agg_id}" -ne "${slave_agg_id}" ] && \
+		RET=1
+}
+
+trap cleanup_all_ns EXIT
+setup_ns c_ns s_ns b_ns
+setup_links
+
+test_port_prio_setting
+log_test "bond 802.3ad" "actor_port_prio setting"
+
+test_agg_reselect eth0
+log_test "bond 802.3ad" "actor_port_prio select"
+
+# Change the actor port prio and re-test
+ip -n "${c_ns}" link set eth0 type bond_slave actor_port_prio 10
+ip -n "${c_ns}" link set eth2 type bond_slave actor_port_prio 1000
+test_agg_reselect eth2
+log_test "bond 802.3ad" "actor_port_prio switch"
+
+exit "${EXIT_STATUS}"
diff --git a/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh b/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh
new file mode 100755
index 000000000000..559f300f965a
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh
@@ -0,0 +1,97 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test macvlan/ipvlan over bond
+
+lib_dir=$(dirname "$0")
+source ${lib_dir}/bond_topo_2d1c.sh
+
+xvlan1_ns="xvlan1-$(mktemp -u XXXXXX)"
+xvlan2_ns="xvlan2-$(mktemp -u XXXXXX)"
+xvlan1_ip4="192.0.2.11"
+xvlan1_ip6="2001:db8::11"
+xvlan2_ip4="192.0.2.12"
+xvlan2_ip6="2001:db8::12"
+
+cleanup()
+{
+	client_destroy
+	server_destroy
+	gateway_destroy
+
+	ip netns del ${xvlan1_ns}
+	ip netns del ${xvlan2_ns}
+}
+
+check_connection()
+{
+	local ns=${1}
+	local target=${2}
+	local message=${3}
+	RET=0
+
+	sleep 0.25
+	ip netns exec ${ns} ping ${target} -c 4 -i 0.1 &>/dev/null
+	check_err $? "ping failed"
+	log_test "${bond_mode}/${xvlan_type}_${xvlan_mode}: ${message}"
+}
+
+xvlan_over_bond()
+{
+	local param="$1"
+	local xvlan_type="$2"
+	local xvlan_mode="$3"
+	RET=0
+
+	# setup new bond mode
+	bond_reset "${param}"
+
+	ip -n ${s_ns} link add link bond0 name ${xvlan_type}0 type ${xvlan_type} mode ${xvlan_mode}
+	ip -n ${s_ns} link set ${xvlan_type}0 netns ${xvlan1_ns}
+	ip -n ${xvlan1_ns} link set dev ${xvlan_type}0 up
+	ip -n ${xvlan1_ns} addr add ${xvlan1_ip4}/24 dev ${xvlan_type}0
+	ip -n ${xvlan1_ns} addr add ${xvlan1_ip6}/24 dev ${xvlan_type}0
+
+	ip -n ${s_ns} link add link bond0 name ${xvlan_type}0 type ${xvlan_type} mode ${xvlan_mode}
+	ip -n ${s_ns} link set ${xvlan_type}0 netns ${xvlan2_ns}
+	ip -n ${xvlan2_ns} link set dev ${xvlan_type}0 up
+	ip -n ${xvlan2_ns} addr add ${xvlan2_ip4}/24 dev ${xvlan_type}0
+	ip -n ${xvlan2_ns} addr add ${xvlan2_ip6}/24 dev ${xvlan_type}0
+
+	sleep 2
+
+	check_connection "${c_ns}" "${s_ip4}" "IPv4: client->server"
+	check_connection "${c_ns}" "${s_ip6}" "IPv6: client->server"
+	check_connection "${c_ns}" "${xvlan1_ip4}" "IPv4: client->${xvlan_type}_1"
+	check_connection "${c_ns}" "${xvlan1_ip6}" "IPv6: client->${xvlan_type}_1"
+	check_connection "${c_ns}" "${xvlan2_ip4}" "IPv4: client->${xvlan_type}_2"
+	check_connection "${c_ns}" "${xvlan2_ip6}" "IPv6: client->${xvlan_type}_2"
+	check_connection "${xvlan1_ns}" "${xvlan2_ip4}" "IPv4: ${xvlan_type}_1->${xvlan_type}_2"
+	check_connection "${xvlan1_ns}" "${xvlan2_ip6}" "IPv6: ${xvlan_type}_1->${xvlan_type}_2"
+
+	check_connection "${s_ns}" "${c_ip4}" "IPv4: server->client"
+	check_connection "${s_ns}" "${c_ip6}" "IPv6: server->client"
+	check_connection "${xvlan1_ns}" "${c_ip4}" "IPv4: ${xvlan_type}_1->client"
+	check_connection "${xvlan1_ns}" "${c_ip6}" "IPv6: ${xvlan_type}_1->client"
+	check_connection "${xvlan2_ns}" "${c_ip4}" "IPv4: ${xvlan_type}_2->client"
+	check_connection "${xvlan2_ns}" "${c_ip6}" "IPv6: ${xvlan_type}_2->client"
+	check_connection "${xvlan2_ns}" "${xvlan1_ip4}" "IPv4: ${xvlan_type}_2->${xvlan_type}_1"
+	check_connection "${xvlan2_ns}" "${xvlan1_ip6}" "IPv6: ${xvlan_type}_2->${xvlan_type}_1"
+
+	ip -n ${c_ns} neigh flush dev eth0
+}
+
+trap cleanup EXIT
+
+setup_prepare
+ip netns add ${xvlan1_ns}
+ip netns add ${xvlan2_ns}
+
+bond_modes="active-backup balance-tlb balance-alb"
+
+for bond_mode in ${bond_modes}; do
+	xvlan_over_bond "mode ${bond_mode}" macvlan bridge
+	xvlan_over_bond "mode ${bond_mode}" ipvlan  l2
+done
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh
new file mode 100755
index 000000000000..187b478d0ddf
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh
@@ -0,0 +1,578 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test bonding options with mode 1,5,6
+
+ALL_TESTS="
+	prio
+	arp_validate
+	num_grat_arp
+	fail_over_mac
+	vlan_over_bond
+"
+
+lib_dir=$(dirname "$0")
+source ${lib_dir}/bond_topo_3d1c.sh
+c_maddr="33:33:ff:00:00:10"
+g_maddr="33:33:ff:00:02:54"
+
+skip_prio()
+{
+	local skip=1
+
+	# check if iproute support prio option
+	ip -n ${s_ns} link set eth0 type bond_slave prio 10
+	[[ $? -ne 0 ]] && skip=0
+
+	# check if kernel support prio option
+	ip -n ${s_ns} -d link show eth0 | grep -q "prio 10"
+	[[ $? -ne 0 ]] && skip=0
+
+	return $skip
+}
+
+skip_ns()
+{
+	local skip=1
+
+	# check if iproute support ns_ip6_target option
+	ip -n ${s_ns} link add bond1 type bond ns_ip6_target ${g_ip6}
+	[[ $? -ne 0 ]] && skip=0
+
+	# check if kernel support ns_ip6_target option
+	ip -n ${s_ns} -d link show bond1 | grep -q "ns_ip6_target ${g_ip6}"
+	[[ $? -ne 0 ]] && skip=0
+
+	ip -n ${s_ns} link del bond1
+
+	return $skip
+}
+
+active_slave=""
+active_slave_changed()
+{
+	local old_active_slave=$1
+	local new_active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" \
+				".[].linkinfo.info_data.active_slave")
+	[ "$new_active_slave" != "$old_active_slave" -a "$new_active_slave" != "null" ]
+}
+
+check_active_slave()
+{
+	local target_active_slave=$1
+	slowwait 5 active_slave_changed $active_slave
+	active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave")
+	test "$active_slave" = "$target_active_slave"
+	check_err $? "Current active slave is $active_slave but not $target_active_slave"
+}
+
+# Test bonding prio option
+prio_test()
+{
+	local param="$1"
+	RET=0
+
+	# create bond
+	bond_reset "${param}"
+	# set active_slave to primary eth1 specifically
+	ip -n ${s_ns} link set bond0 type bond active_slave eth1
+
+	# check bonding member prio value
+	ip -n ${s_ns} link set eth0 type bond_slave prio 0
+	ip -n ${s_ns} link set eth1 type bond_slave prio 10
+	ip -n ${s_ns} link set eth2 type bond_slave prio 11
+	cmd_jq "ip -n ${s_ns} -d -j link show eth0" \
+		".[].linkinfo.info_slave_data | select (.prio == 0)" "-e" &> /dev/null
+	check_err $? "eth0 prio is not 0"
+	cmd_jq "ip -n ${s_ns} -d -j link show eth1" \
+		".[].linkinfo.info_slave_data | select (.prio == 10)" "-e" &> /dev/null
+	check_err $? "eth1 prio is not 10"
+	cmd_jq "ip -n ${s_ns} -d -j link show eth2" \
+		".[].linkinfo.info_slave_data | select (.prio == 11)" "-e" &> /dev/null
+	check_err $? "eth2 prio is not 11"
+
+	bond_check_connection "setup"
+
+	# active slave should be the primary slave
+	check_active_slave eth1
+
+	# active slave should be the higher prio slave
+	ip -n ${s_ns} link set $active_slave down
+	check_active_slave eth2
+	bond_check_connection "fail over"
+
+	# when only 1 slave is up
+	ip -n ${s_ns} link set $active_slave down
+	check_active_slave eth0
+	bond_check_connection "only 1 slave up"
+
+	# when a higher prio slave change to up
+	ip -n ${s_ns} link set eth2 up
+	bond_check_connection "higher prio slave up"
+	case $primary_reselect in
+		"0")
+			check_active_slave "eth2"
+			;;
+		"1")
+			check_active_slave "eth0"
+			;;
+		"2")
+			check_active_slave "eth0"
+			;;
+	esac
+	local pre_active_slave=$active_slave
+
+	# when the primary slave change to up
+	ip -n ${s_ns} link set eth1 up
+	bond_check_connection "primary slave up"
+	case $primary_reselect in
+		"0")
+			check_active_slave "eth1"
+			;;
+		"1")
+			check_active_slave "$pre_active_slave"
+			;;
+		"2")
+			check_active_slave "$pre_active_slave"
+			ip -n ${s_ns} link set $active_slave down
+			bond_check_connection "pre_active slave down"
+			check_active_slave "eth1"
+			;;
+	esac
+
+	# Test changing bond slave prio
+	if [[ "$primary_reselect" == "0" ]];then
+		ip -n ${s_ns} link set eth0 type bond_slave prio 1000000
+		ip -n ${s_ns} link set eth1 type bond_slave prio 0
+		ip -n ${s_ns} link set eth2 type bond_slave prio -50
+		ip -n ${s_ns} -d link show eth0 | grep -q 'prio 1000000'
+		check_err $? "eth0 prio is not 1000000"
+		ip -n ${s_ns} -d link show eth1 | grep -q 'prio 0'
+		check_err $? "eth1 prio is not 0"
+		ip -n ${s_ns} -d link show eth2 | grep -q 'prio -50'
+		check_err $? "eth3 prio is not -50"
+		check_active_slave "eth1"
+
+		ip -n ${s_ns} link set $active_slave down
+		check_active_slave "eth0"
+		bond_check_connection "change slave prio"
+	fi
+}
+
+prio_miimon()
+{
+	local primary_reselect
+	local mode=$1
+
+	for primary_reselect in 0 1 2; do
+		prio_test "mode $mode miimon 100 primary eth1 primary_reselect $primary_reselect"
+		log_test "prio" "$mode miimon primary_reselect $primary_reselect"
+	done
+}
+
+prio_arp()
+{
+	local primary_reselect
+	local mode=$1
+
+	for primary_reselect in 0 1 2; do
+		prio_test "mode $mode arp_interval 100 arp_ip_target ${g_ip4} primary eth1 primary_reselect $primary_reselect"
+		log_test "prio" "$mode arp_ip_target primary_reselect $primary_reselect"
+	done
+}
+
+prio_ns()
+{
+	local primary_reselect
+	local mode=$1
+
+	if skip_ns; then
+		log_test_skip "prio ns" "Current iproute or kernel doesn't support bond option 'ns_ip6_target'."
+		return 0
+	fi
+
+	for primary_reselect in 0 1 2; do
+		prio_test "mode $mode arp_interval 100 ns_ip6_target ${g_ip6} primary eth1 primary_reselect $primary_reselect"
+		log_test "prio" "$mode ns_ip6_target primary_reselect $primary_reselect"
+	done
+}
+
+prio()
+{
+	local mode modes="active-backup balance-tlb balance-alb"
+
+	if skip_prio; then
+		log_test_skip "prio" "Current iproute or kernel doesn't support bond option 'prio'."
+		return 0
+	fi
+
+	for mode in $modes; do
+		prio_miimon $mode
+	done
+	prio_arp "active-backup"
+	prio_ns "active-backup"
+}
+
+wait_mii_up()
+{
+	for i in $(seq 0 2); do
+		mii_status=$(cmd_jq "ip -n ${s_ns} -j -d link show eth$i" ".[].linkinfo.info_slave_data.mii_status")
+		[ ${mii_status} != "UP" ] && return 1
+	done
+	return 0
+}
+
+arp_validate_test()
+{
+	local param="$1"
+	RET=0
+
+	# create bond
+	bond_reset "${param}"
+
+	bond_check_connection
+	[ $RET -ne 0 ] && log_test "arp_validate" "$retmsg"
+
+	# wait for a while to make sure the mii status stable
+	slowwait 5 wait_mii_up
+	for i in $(seq 0 2); do
+		mii_status=$(cmd_jq "ip -n ${s_ns} -j -d link show eth$i" ".[].linkinfo.info_slave_data.mii_status")
+		if [ ${mii_status} != "UP" ]; then
+			RET=1
+			log_test "arp_validate" "interface eth$i mii_status $mii_status"
+		fi
+	done
+}
+
+# Testing correct multicast groups are added to slaves for ns targets
+arp_validate_mcast()
+{
+	RET=0
+	local arp_valid=$(cmd_jq "ip -n ${s_ns} -j -d link show bond0" ".[].linkinfo.info_data.arp_validate")
+	local active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave")
+
+	for i in $(seq 0 2); do
+		maddr_list=$(ip -n ${s_ns} maddr show dev eth${i})
+
+		# arp_valid == 0 or active_slave should not join any maddrs
+		if { [ "$arp_valid" == "null" ] || [ "eth${i}" == ${active_slave} ]; } && \
+			echo "$maddr_list" | grep -qE "${c_maddr}|${g_maddr}"; then
+			RET=1
+			check_err 1 "arp_valid $arp_valid active_slave $active_slave, eth$i has mcast group"
+		# arp_valid != 0 and backup_slave should join both maddrs
+		elif [ "$arp_valid" != "null" ] && [ "eth${i}" != ${active_slave} ] && \
+		     ( ! echo "$maddr_list" | grep -q "${c_maddr}" || \
+		       ! echo "$maddr_list" | grep -q "${m_maddr}"); then
+			RET=1
+			check_err 1 "arp_valid $arp_valid active_slave $active_slave, eth$i has mcast group"
+		fi
+	done
+
+	# Do failover
+	ip -n ${s_ns} link set ${active_slave} down
+	# wait for active link change
+	slowwait 2 active_slave_changed $active_slave
+	active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave")
+
+	for i in $(seq 0 2); do
+		maddr_list=$(ip -n ${s_ns} maddr show dev eth${i})
+
+		# arp_valid == 0 or active_slave should not join any maddrs
+		if { [ "$arp_valid" == "null" ] || [ "eth${i}" == ${active_slave} ]; } && \
+			echo "$maddr_list" | grep -qE "${c_maddr}|${g_maddr}"; then
+			RET=1
+			check_err 1 "arp_valid $arp_valid active_slave $active_slave, eth$i has mcast group"
+		# arp_valid != 0 and backup_slave should join both maddrs
+		elif [ "$arp_valid" != "null" ] && [ "eth${i}" != ${active_slave} ] && \
+		     ( ! echo "$maddr_list" | grep -q "${c_maddr}" || \
+		       ! echo "$maddr_list" | grep -q "${m_maddr}"); then
+			RET=1
+			check_err 1 "arp_valid $arp_valid active_slave $active_slave, eth$i has mcast group"
+		fi
+	done
+}
+
+arp_validate_arp()
+{
+	local mode=$1
+	local val
+	for val in $(seq 0 6); do
+		arp_validate_test "mode $mode arp_interval 100 arp_ip_target ${g_ip4} arp_validate $val"
+		log_test "arp_validate" "$mode arp_ip_target arp_validate $val"
+	done
+}
+
+arp_validate_ns()
+{
+	local mode=$1
+	local val
+
+	if skip_ns; then
+		log_test_skip "arp_validate ns" "Current iproute or kernel doesn't support bond option 'ns_ip6_target'."
+		return 0
+	fi
+
+	for val in $(seq 0 6); do
+		arp_validate_test "mode $mode arp_interval 100 ns_ip6_target ${g_ip6},${c_ip6} arp_validate $val"
+		log_test "arp_validate" "$mode ns_ip6_target arp_validate $val"
+		arp_validate_mcast
+		log_test "arp_validate" "join mcast group"
+	done
+}
+
+arp_validate()
+{
+	arp_validate_arp "active-backup"
+	arp_validate_ns "active-backup"
+}
+
+garp_test()
+{
+	local param="$1"
+	local active_slave exp_num real_num i
+	RET=0
+
+	# create bond
+	bond_reset "${param}"
+
+	bond_check_connection
+	[ $RET -ne 0 ] && log_test "num_grat_arp" "$retmsg"
+
+
+	# Add tc rules to count GARP number
+	for i in $(seq 0 2); do
+		tc -n ${g_ns} filter add dev s$i ingress protocol arp pref 1 handle 101 \
+			flower skip_hw arp_op request arp_sip ${s_ip4} arp_tip ${s_ip4} action pass
+	done
+
+	# Do failover
+	active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave")
+	ip -n ${s_ns} link set ${active_slave} down
+
+	# wait for active link change
+	slowwait 2 active_slave_changed $active_slave
+
+	exp_num=$(echo "${param}" | cut -f6 -d ' ')
+	active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave")
+	slowwait_for_counter $((exp_num + 5)) $exp_num tc_rule_handle_stats_get \
+		"dev s${active_slave#eth} ingress" 101 ".packets" "-n ${g_ns}" &> /dev/null
+
+	# check result
+	real_num=$(tc_rule_handle_stats_get "dev s${active_slave#eth} ingress" 101 ".packets" "-n ${g_ns}")
+	if [ "${real_num}" -ne "${exp_num}" ]; then
+		echo "$real_num garp packets sent on active slave ${active_slave}"
+		RET=1
+	fi
+
+	for i in $(seq 0 2); do
+		tc -n ${g_ns} filter del dev s$i ingress
+	done
+}
+
+num_grat_arp()
+{
+	local val
+	for val in 10 20 30; do
+		garp_test "mode active-backup miimon 10 num_grat_arp $val peer_notify_delay 100"
+		log_test "num_grat_arp" "active-backup miimon num_grat_arp $val"
+	done
+}
+
+check_all_mac_same()
+{
+	RET=0
+	# all slaves should have same mac address (with the first port's mac)
+	local bond_mac=$(ip -n "$s_ns" -j link show bond0 | jq -r '.[]["address"]')
+	local eth0_mac=$(ip -n "$s_ns" -j link show eth0 | jq -r '.[]["address"]')
+	local eth1_mac=$(ip -n "$s_ns" -j link show eth1 | jq -r '.[]["address"]')
+	local eth2_mac=$(ip -n "$s_ns" -j link show eth2 | jq -r '.[]["address"]')
+	if [ "$bond_mac" != "${mac[0]}" ] || [ "$eth0_mac" != "$bond_mac" ] || \
+		[ "$eth1_mac" != "$bond_mac" ] || [ "$eth2_mac" != "$bond_mac" ]; then
+		RET=1
+	fi
+}
+
+check_bond_mac_same_with_first()
+{
+	RET=0
+	# bond mac address should be same with the first added slave
+	local bond_mac=$(ip -n "$s_ns" -j link show bond0 | jq -r '.[]["address"]')
+	if [ "$bond_mac" != "${mac[0]}" ]; then
+		RET=1
+	fi
+}
+
+check_bond_mac_same_with_active()
+{
+	RET=0
+	# bond mac address should be same with active slave
+	local bond_mac=$(ip -n "$s_ns" -j link show bond0 | jq -r '.[]["address"]')
+	local active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave")
+	local active_slave_mac=$(ip -n "$s_ns" -j link show "$active_slave" | jq -r '.[]["address"]')
+	if [ "$bond_mac" != "$active_slave_mac" ]; then
+		RET=1
+	fi
+}
+
+check_backup_slave_mac_not_change()
+{
+	RET=0
+	# backup slave's mac address is not changed
+	if ip -n "$s_ns" -d -j link show type bond_slave | jq -e '.[]
+		| select(.linkinfo.info_slave_data.state=="BACKUP")
+		| select(.address != .linkinfo.info_slave_data.perm_hwaddr)' &> /dev/null; then
+		RET=1
+	fi
+}
+
+check_backup_slave_mac_inherit()
+{
+	local backup_mac
+	RET=0
+
+	# backup slaves should use mac[1] or mac[2]
+	local backup_macs=$(ip -n "$s_ns" -d -j link show type bond_slave | \
+		jq -r '.[] | select(.linkinfo.info_slave_data.state=="BACKUP") | .address')
+	for backup_mac in $backup_macs; do
+		if [ "$backup_mac" != "${mac[1]}" ] && [ "$backup_mac" != "${mac[2]}" ]; then
+			RET=1
+		fi
+	done
+}
+
+check_first_slave_random_mac()
+{
+	RET=0
+	# remove the first added slave and added it back
+	ip -n "$s_ns" link set eth0 nomaster
+	ip -n "$s_ns" link set eth0 master bond0
+
+	# the first slave should use random mac address
+	eth0_mac=$(ip -n "$s_ns" -j link show eth0 | jq -r '.[]["address"]')
+	[ "$eth0_mac" = "${mac[0]}" ] && RET=1
+	log_test "bond fail_over_mac follow" "random first slave mac"
+
+	# remove the first slave, the permanent MAC address should be restored back
+	ip -n "$s_ns" link set eth0 nomaster
+	eth0_mac=$(ip -n "$s_ns" -j link show eth0 | jq -r '.[]["address"]')
+	[ "$eth0_mac" != "${mac[0]}" ] && RET=1
+}
+
+do_active_backup_failover()
+{
+	local active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave")
+	ip -n ${s_ns} link set ${active_slave} down
+	slowwait 2 active_slave_changed $active_slave
+	ip -n ${s_ns} link set ${active_slave} up
+}
+
+fail_over_mac()
+{
+	# Bring down the first interface on the switch to force the bond to
+	# select another active interface instead of the first one that joined.
+	ip -n "$g_ns" link set s0 down
+
+	# fail_over_mac none
+	bond_reset "mode active-backup miimon 100 fail_over_mac 0"
+	check_all_mac_same
+	log_test "fail_over_mac 0" "all slaves have same mac"
+	do_active_backup_failover
+	check_all_mac_same
+	log_test "fail_over_mac 0" "failover: all slaves have same mac"
+
+	# fail_over_mac active
+	bond_reset "mode active-backup miimon 100 fail_over_mac 1"
+	check_bond_mac_same_with_active
+	log_test "fail_over_mac 1" "bond mac is same with active slave mac"
+	check_backup_slave_mac_not_change
+	log_test "fail_over_mac 1" "backup slave mac is not changed"
+	do_active_backup_failover
+	check_bond_mac_same_with_active
+	log_test "fail_over_mac 1" "failover: bond mac is same with active slave mac"
+	check_backup_slave_mac_not_change
+	log_test "fail_over_mac 1" "failover: backup slave mac is not changed"
+
+	# fail_over_mac follow
+	bond_reset "mode active-backup miimon 100 fail_over_mac 2"
+	check_bond_mac_same_with_first
+	log_test "fail_over_mac 2" "bond mac is same with first slave mac"
+	check_bond_mac_same_with_active
+	log_test "fail_over_mac 2" "bond mac is same with active slave mac"
+	check_backup_slave_mac_inherit
+	log_test "fail_over_mac 2" "backup slave mac inherit"
+	do_active_backup_failover
+	check_bond_mac_same_with_first
+	log_test "fail_over_mac 2" "failover: bond mac is same with first slave mac"
+	check_bond_mac_same_with_active
+	log_test "fail_over_mac 2" "failover: bond mac is same with active slave mac"
+	check_backup_slave_mac_inherit
+	log_test "fail_over_mac 2" "failover: backup slave mac inherit"
+	check_first_slave_random_mac
+	log_test "fail_over_mac 2" "first slave mac random"
+}
+
+vlan_over_bond_arp()
+{
+	local mode="$1"
+	RET=0
+
+	bond_reset "mode $mode arp_interval 100 arp_ip_target 192.0.3.10"
+	ip -n "${s_ns}" link add bond0.3 link bond0 type vlan id 3
+	ip -n "${s_ns}" link set bond0.3 up
+	ip -n "${s_ns}" addr add 192.0.3.1/24 dev bond0.3
+	ip -n "${s_ns}" addr add 2001:db8::3:1/64 dev bond0.3
+
+	slowwait_for_counter 5 5 tc_rule_handle_stats_get \
+		"dev eth0.3 ingress" 101 ".packets" "-n ${c_ns}" &> /dev/null || RET=1
+	log_test "vlan over bond arp" "$mode"
+}
+
+vlan_over_bond_ns()
+{
+	local mode="$1"
+	RET=0
+
+	if skip_ns; then
+		log_test_skip "vlan_over_bond ns" "$mode"
+		return 0
+	fi
+
+	bond_reset "mode $mode arp_interval 100 ns_ip6_target 2001:db8::3:10"
+	ip -n "${s_ns}" link add bond0.3 link bond0 type vlan id 3
+	ip -n "${s_ns}" link set bond0.3 up
+	ip -n "${s_ns}" addr add 192.0.3.1/24 dev bond0.3
+	ip -n "${s_ns}" addr add 2001:db8::3:1/64 dev bond0.3
+
+	slowwait_for_counter 5 5 tc_rule_handle_stats_get \
+		"dev eth0.3 ingress" 102 ".packets" "-n ${c_ns}" &> /dev/null || RET=1
+	log_test "vlan over bond ns" "$mode"
+}
+
+vlan_over_bond()
+{
+	# add vlan 3 for client
+	ip -n "${c_ns}" link add eth0.3 link eth0 type vlan id 3
+	ip -n "${c_ns}" link set eth0.3 up
+	ip -n "${c_ns}" addr add 192.0.3.10/24 dev eth0.3
+	ip -n "${c_ns}" addr add 2001:db8::3:10/64 dev eth0.3
+
+	# Add tc rule to check the vlan pkts
+	tc -n "${c_ns}" qdisc add dev eth0.3 clsact
+	tc -n "${c_ns}" filter add dev eth0.3 ingress protocol arp \
+		handle 101 flower skip_hw arp_op request \
+		arp_sip 192.0.3.1 arp_tip 192.0.3.10 action pass
+	tc -n "${c_ns}" filter add dev eth0.3 ingress protocol ipv6 \
+		handle 102 flower skip_hw ip_proto icmpv6 \
+		type 135 src_ip 2001:db8::3:1 action pass
+
+	vlan_over_bond_arp "active-backup"
+	vlan_over_bond_ns "active-backup"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/bonding/bond_passive_lacp.sh b/tools/testing/selftests/drivers/net/bonding/bond_passive_lacp.sh
new file mode 100755
index 000000000000..9c3b089813df
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/bond_passive_lacp.sh
@@ -0,0 +1,105 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test if a bond interface works with lacp_active=off.
+
+# shellcheck disable=SC2034
+REQUIRE_MZ=no
+NUM_NETIFS=0
+lib_dir=$(dirname "$0")
+# shellcheck disable=SC1091
+source "$lib_dir"/../../../net/forwarding/lib.sh
+
+# shellcheck disable=SC2317
+check_port_state()
+{
+	local netns=$1
+	local port=$2
+	local state=$3
+
+	ip -n "${netns}" -d -j link show "$port" | \
+		jq -e ".[].linkinfo.info_slave_data.ad_actor_oper_port_state_str | index(\"${state}\") != null" > /dev/null
+}
+
+check_pkt_count()
+{
+	RET=0
+	local ns="$1"
+	local iface="$2"
+
+	# wait 65s, one per 30s
+	slowwait_for_counter 65 2 tc_rule_handle_stats_get \
+		"dev ${iface} egress" 101 ".packets" "-n ${ns}" &> /dev/null
+}
+
+setup() {
+	setup_ns c_ns s_ns
+
+	# shellcheck disable=SC2154
+	ip -n "${c_ns}" link add eth0 type veth peer name eth0 netns "${s_ns}"
+	ip -n "${c_ns}" link add eth1 type veth peer name eth1 netns "${s_ns}"
+
+	# Add tc filter to count the pkts
+	tc -n "${c_ns}" qdisc add dev eth0 clsact
+	tc -n "${c_ns}" filter add dev eth0 egress handle 101 protocol 0x8809 matchall action pass
+	tc -n "${s_ns}" qdisc add dev eth1 clsact
+	tc -n "${s_ns}" filter add dev eth1 egress handle 101 protocol 0x8809 matchall action pass
+
+	ip -n "${s_ns}" link add bond0 type bond mode 802.3ad lacp_active on lacp_rate fast
+	ip -n "${s_ns}" link set eth0 master bond0
+	ip -n "${s_ns}" link set eth1 master bond0
+
+	ip -n "${c_ns}" link add bond0 type bond mode 802.3ad lacp_active off lacp_rate fast
+	ip -n "${c_ns}" link set eth0 master bond0
+	ip -n "${c_ns}" link set eth1 master bond0
+
+}
+
+trap cleanup_all_ns EXIT
+setup
+
+# The bond will send 2 lacpdu pkts during init time, let's wait at least 2s
+# after interface up
+ip -n "${c_ns}" link set bond0 up
+sleep 2
+
+# 1. The passive side shouldn't send LACPDU.
+check_pkt_count "${c_ns}" "eth0" && RET=1
+log_test "802.3ad lacp_active off" "init port"
+
+ip -n "${s_ns}" link set bond0 up
+# 2. The passive side should not have the 'active' flag.
+RET=0
+slowwait 2 check_port_state "${c_ns}" "eth0" "active" && RET=1
+log_test "802.3ad lacp_active off" "port state active"
+
+# 3. The active side should have the 'active' flag.
+RET=0
+slowwait 2 check_port_state "${s_ns}" "eth0" "active" || RET=1
+log_test "802.3ad lacp_active on" "port state active"
+
+# 4. Make sure the connection is not expired.
+RET=0
+slowwait 5 check_port_state "${s_ns}" "eth0" "distributing"
+slowwait 10 check_port_state "${s_ns}" "eth0" "expired" && RET=1
+log_test "bond 802.3ad lacp_active off" "port connection"
+
+# After testing, disconnect one port on each side to check the state.
+ip -n "${s_ns}" link set eth0 nomaster
+ip -n "${s_ns}" link set eth0 up
+ip -n "${c_ns}" link set eth1 nomaster
+ip -n "${c_ns}" link set eth1 up
+# Due to Periodic Machine and Rx Machine state change, the bond will still
+# send lacpdu pkts in a few seconds. sleep at lease 5s to make sure
+# negotiation finished
+sleep 5
+
+# 5. The active side should keep sending LACPDU.
+check_pkt_count "${s_ns}" "eth1" || RET=1
+log_test "bond 802.3ad lacp_active on" "port pkt after disconnect"
+
+# 6. The passive side shouldn't send LACPDU anymore.
+check_pkt_count "${c_ns}" "eth0" && RET=1
+log_test "bond 802.3ad lacp_active off" "port pkt after disconnect"
+
+exit "$EXIT_STATUS"
diff --git a/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh b/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh
new file mode 100644
index 000000000000..167aa4a4a12a
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/bond_topo_2d1c.sh
@@ -0,0 +1,161 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Topology for Bond mode 1,5,6 testing
+#
+#  +-------------------------+
+#  |          bond0          |  Server
+#  |            +            |  192.0.2.1/24
+#  |      eth0  |  eth1      |  2001:db8::1/24
+#  |        +---+---+        |
+#  |        |       |        |
+#  +-------------------------+
+#           |       |
+#  +-------------------------+
+#  |        |       |        |
+#  |    +---+-------+---+    |  Gateway
+#  |    |      br0      |    |  192.0.2.254/24
+#  |    +-------+-------+    |  2001:db8::254/24
+#  |            |            |
+#  +-------------------------+
+#               |
+#  +-------------------------+
+#  |            |            |  Client
+#  |            +            |  192.0.2.10/24
+#  |          eth0           |  2001:db8::10/24
+#  +-------------------------+
+
+REQUIRE_MZ=no
+NUM_NETIFS=0
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/forwarding/lib.sh
+
+s_ns="s-$(mktemp -u XXXXXX)"
+c_ns="c-$(mktemp -u XXXXXX)"
+g_ns="g-$(mktemp -u XXXXXX)"
+s_ip4="192.0.2.1"
+c_ip4="192.0.2.10"
+g_ip4="192.0.2.254"
+s_ip6="2001:db8::1"
+c_ip6="2001:db8::10"
+g_ip6="2001:db8::254"
+mac[0]="00:0a:0b:0c:0d:01"
+mac[1]="00:0a:0b:0c:0d:02"
+
+gateway_create()
+{
+	ip netns add ${g_ns}
+	ip -n ${g_ns} link add br0 type bridge
+	ip -n ${g_ns} link set br0 up
+	ip -n ${g_ns} addr add ${g_ip4}/24 dev br0
+	ip -n ${g_ns} addr add ${g_ip6}/24 dev br0
+}
+
+gateway_destroy()
+{
+	ip -n ${g_ns} link del br0
+	ip netns del ${g_ns}
+}
+
+server_create()
+{
+	ip netns add ${s_ns}
+	ip -n ${s_ns} link add bond0 type bond mode active-backup miimon 100
+
+	for i in $(seq 0 1); do
+		ip -n ${s_ns} link add eth${i} type veth peer name s${i} netns ${g_ns}
+		ip -n "${s_ns}" link set "eth${i}" addr "${mac[$i]}"
+
+		ip -n ${g_ns} link set s${i} up
+		ip -n ${g_ns} link set s${i} master br0
+		ip -n ${s_ns} link set eth${i} master bond0
+
+		tc -n ${g_ns} qdisc add dev s${i} clsact
+	done
+
+	ip -n ${s_ns} link set bond0 up
+	ip -n ${s_ns} addr add ${s_ip4}/24 dev bond0
+	ip -n ${s_ns} addr add ${s_ip6}/24 dev bond0
+}
+
+# Reset bond with new mode and options
+bond_reset()
+{
+	# Count the eth link number in real-time as this function
+	# maybe called from other topologies.
+	local link_num=$(ip -n ${s_ns} -br link show | grep -c "^eth")
+	local param="$1"
+	link_num=$((link_num -1))
+
+	ip -n ${s_ns} link set bond0 down
+	ip -n ${s_ns} link del bond0
+
+	ip -n ${s_ns} link add bond0 type bond $param
+	for i in $(seq 0 ${link_num}); do
+		ip -n ${s_ns} link set eth$i master bond0
+	done
+
+	ip -n ${s_ns} link set bond0 up
+	ip -n ${s_ns} addr add ${s_ip4}/24 dev bond0
+	ip -n ${s_ns} addr add ${s_ip6}/24 dev bond0
+	# Wait for IPv6 address ready as it needs DAD
+	slowwait 2 ip netns exec ${s_ns} ping6 ${c_ip6} -c 1 -W 0.1 &> /dev/null
+}
+
+server_destroy()
+{
+	# Count the eth link number in real-time as this function
+	# maybe called from other topologies.
+	local link_num=$(ip -n ${s_ns} -br link show | grep -c "^eth")
+	link_num=$((link_num -1))
+	for i in $(seq 0 ${link_num}); do
+		ip -n ${s_ns} link del eth${i}
+	done
+	ip netns del ${s_ns}
+}
+
+client_create()
+{
+	ip netns add ${c_ns}
+	ip -n ${c_ns} link add eth0 type veth peer name c0 netns ${g_ns}
+
+	ip -n ${g_ns} link set c0 up
+	ip -n ${g_ns} link set c0 master br0
+
+	ip -n ${c_ns} link set eth0 up
+	ip -n ${c_ns} addr add ${c_ip4}/24 dev eth0
+	ip -n ${c_ns} addr add ${c_ip6}/24 dev eth0
+}
+
+client_destroy()
+{
+	ip -n ${c_ns} link del eth0
+	ip netns del ${c_ns}
+}
+
+setup_prepare()
+{
+	gateway_create
+	server_create
+	client_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	client_destroy
+	server_destroy
+	gateway_destroy
+}
+
+bond_check_connection()
+{
+	local msg=${1:-"check connection"}
+
+	slowwait 2 ip netns exec ${s_ns} ping ${c_ip4} -c 1 -W 0.1 &> /dev/null
+	ip netns exec ${s_ns} ping ${c_ip4} -c5 -i 0.1 &>/dev/null
+	check_err $? "${msg}: ping failed"
+	ip netns exec ${s_ns} ping6 ${c_ip6} -c5 -i 0.1 &>/dev/null
+	check_err $? "${msg}: ping6 failed"
+}
diff --git a/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh
new file mode 100644
index 000000000000..23a2932301cc
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh
@@ -0,0 +1,45 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Topology for Bond mode 1,5,6 testing
+#
+#  +-------------------------------------+
+#  |                bond0                |
+#  |                  +                  |  Server
+#  |      eth0        | eth1   eth2      |  192.0.2.1/24
+#  |        +-------------------+        |  2001:db8::1/24
+#  |        |         |         |        |
+#  +-------------------------------------+
+#           |         |         |
+#  +-------------------------------------+
+#  |        |         |         |        |
+#  |    +---+---------+---------+---+    |  Gateway
+#  |    |            br0            |    |  192.0.2.254/24
+#  |    +-------------+-------------+    |  2001:db8::254/24
+#  |                  |                  |
+#  +-------------------------------------+
+#                     |
+#  +-------------------------------------+
+#  |                  |                  |  Client
+#  |                  +                  |  192.0.2.10/24
+#  |                eth0                 |  2001:db8::10/24
+#  +-------------------------------------+
+
+source bond_topo_2d1c.sh
+mac[2]="00:0a:0b:0c:0d:03"
+
+setup_prepare()
+{
+	gateway_create
+	server_create
+	client_create
+
+	# Add the extra device as we use 3 down links for bond0
+	local i=2
+	ip -n ${s_ns} link add eth${i} type veth peer name s${i} netns ${g_ns}
+	ip -n "${s_ns}" link set "eth${i}" addr "${mac[$i]}"
+	ip -n ${g_ns} link set s${i} up
+	ip -n ${g_ns} link set s${i} master br0
+	ip -n ${s_ns} link set eth${i} master bond0
+	tc -n ${g_ns} qdisc add dev s${i} clsact
+}
diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config
index 70638fa50b2c..991494376223 100644
--- a/tools/testing/selftests/drivers/net/bonding/config
+++ b/tools/testing/selftests/drivers/net/bonding/config
@@ -1,2 +1,21 @@
 CONFIG_BONDING=y
+CONFIG_BRIDGE=y
+CONFIG_CONFIGFS_FS=y
+CONFIG_DUMMY=y
+CONFIG_INET_ESP=y
+CONFIG_INET_ESP_OFFLOAD=y
+CONFIG_IPV6=y
+CONFIG_IPVLAN=y
 CONFIG_MACVLAN=y
+CONFIG_NET_ACT_GACT=y
+CONFIG_NET_CLS_FLOWER=y
+CONFIG_NET_CLS_MATCHALL=m
+CONFIG_NETCONSOLE=m
+CONFIG_NETCONSOLE_DYNAMIC=y
+CONFIG_NETCONSOLE_EXTENDED_LOG=y
+CONFIG_NETDEVSIM=m
+CONFIG_NET_SCH_INGRESS=y
+CONFIG_NLMON=y
+CONFIG_VETH=y
+CONFIG_VLAN_8021Q=m
+CONFIG_XFRM_USER=m
diff --git a/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh b/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh
index 5cfe7d8ebc25..e6fa24eded5b 100755
--- a/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh
+++ b/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh
@@ -14,7 +14,7 @@ ALL_TESTS="
 REQUIRE_MZ=no
 NUM_NETIFS=0
 lib_dir=$(dirname "$0")
-source "$lib_dir"/net_forwarding_lib.sh
+source "$lib_dir"/../../../net/forwarding/lib.sh
 
 source "$lib_dir"/lag_lib.sh
 
diff --git a/tools/testing/selftests/drivers/net/bonding/lag_lib.sh b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh
index 2a268b17b61f..bf9bcd1b5ec0 100644
--- a/tools/testing/selftests/drivers/net/bonding/lag_lib.sh
+++ b/tools/testing/selftests/drivers/net/bonding/lag_lib.sh
@@ -48,6 +48,17 @@ test_LAG_cleanup()
 	ip link add mv0 link "$name" up address "$ucaddr" type macvlan
 	# Used to test dev->mc handling
 	ip address add "$addr6" dev "$name"
+
+	# Check that addresses were added as expected
+	(grep_bridge_fdb "$ucaddr" bridge fdb show dev dummy1 ||
+		grep_bridge_fdb "$ucaddr" bridge fdb show dev dummy2) >/dev/null
+	check_err $? "macvlan unicast address not found on a slave"
+
+	# mcaddr is added asynchronously by addrconf_dad_work(), use busywait
+	(busywait 10000 grep_bridge_fdb "$mcaddr" bridge fdb show dev dummy1 ||
+		grep_bridge_fdb "$mcaddr" bridge fdb show dev dummy2) >/dev/null
+	check_err $? "IPv6 solicited-node multicast mac address not found on a slave"
+
 	ip link set dev "$name" down
 	ip link del "$name"
 
@@ -96,13 +107,12 @@ lag_setup2x2()
 	NAMESPACES="${namespaces}"
 }
 
-# cleanup all lag related namespaces and remove the bonding module
+# cleanup all lag related namespaces
 lag_cleanup()
 {
 	for n in ${NAMESPACES}; do
 		ip netns delete ${n} >/dev/null 2>&1 || true
 	done
-	modprobe -r bonding
 }
 
 SWITCH="lag_node1"
@@ -148,7 +158,7 @@ test_bond_recovery()
 	create_bond $@
 
 	# verify connectivity
-	ip netns exec ${CLIENT} ping ${SWITCHIP} -c 2 >/dev/null 2>&1
+	slowwait 2 ip netns exec ${CLIENT} ping ${SWITCHIP} -c 2 -W 0.1 &> /dev/null
 	check_err $? "No connectivity"
 
 	# force the links of the bond down
@@ -158,7 +168,7 @@ test_bond_recovery()
 	ip netns exec ${SWITCH} ip link set eth1 down
 
 	# re-verify connectivity
-	ip netns exec ${CLIENT} ping ${SWITCHIP} -c 2 >/dev/null 2>&1
+	slowwait 2 ip netns exec ${CLIENT} ping ${SWITCHIP} -c 2 -W 0.1 &> /dev/null
 
 	local rc=$?
 	check_err $rc "Bond failed to recover"
diff --git a/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh b/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh
index ad4c845a4ac7..9d26ab4cad0b 100755
--- a/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh
+++ b/tools/testing/selftests/drivers/net/bonding/mode-1-recovery-updelay.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 # Regression Test:
@@ -23,7 +23,7 @@ REQUIRE_MZ=no
 REQUIRE_JQ=no
 NUM_NETIFS=0
 lib_dir=$(dirname "$0")
-source "$lib_dir"/net_forwarding_lib.sh
+source "$lib_dir"/../../../net/forwarding/lib.sh
 source "$lib_dir"/lag_lib.sh
 
 cleanup()
diff --git a/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh b/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh
index 2330d37453f9..2d275b3e47dd 100755
--- a/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh
+++ b/tools/testing/selftests/drivers/net/bonding/mode-2-recovery-updelay.sh
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 # Regression Test:
@@ -23,7 +23,7 @@ REQUIRE_MZ=no
 REQUIRE_JQ=no
 NUM_NETIFS=0
 lib_dir=$(dirname "$0")
-source "$lib_dir"/net_forwarding_lib.sh
+source "$lib_dir"/../../../net/forwarding/lib.sh
 source "$lib_dir"/lag_lib.sh
 
 cleanup()
diff --git a/tools/testing/selftests/drivers/net/bonding/net_forwarding_lib.sh b/tools/testing/selftests/drivers/net/bonding/net_forwarding_lib.sh
deleted file mode 120000
index 39c96828c5ef..000000000000
--- a/tools/testing/selftests/drivers/net/bonding/net_forwarding_lib.sh
+++ /dev/null
@@ -1 +0,0 @@
-../../../net/forwarding/lib.sh
-\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/bonding/netcons_over_bonding.sh b/tools/testing/selftests/drivers/net/bonding/netcons_over_bonding.sh
new file mode 100755
index 000000000000..477cc9379500
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/netcons_over_bonding.sh
@@ -0,0 +1,361 @@
+#!/usr/bin/env bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# This selftest exercises trying to have multiple netpoll users at the same
+# time.
+#
+# This selftest has multiple smalls test inside, and the goal is to
+# get interfaces with bonding and netconsole in different orders in order
+# to catch any possible issue.
+#
+# The main test composes of four interfaces being created using netdevsim; two
+# of them are bonded to serve as the netconsole's transmit interface. The
+# remaining two interfaces are similarly bonded and assigned to a separate
+# network namespace, which acts as the receive interface, where socat monitors
+# for incoming messages.
+#
+# A netconsole message is then sent to ensure it is properly received across
+# this configuration.
+#
+# Later, run a few other tests, to make sure that bonding and netconsole
+# cannot coexist.
+#
+# The test's objective is to exercise netpoll usage when managed simultaneously
+# by multiple subsystems (netconsole and bonding).
+#
+# Author: Breno Leitao <leitao@debian.org>
+
+set -euo pipefail
+
+SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")")
+
+source "${SCRIPTDIR}"/../lib/sh/lib_netcons.sh
+
+modprobe netdevsim 2> /dev/null || true
+modprobe netconsole 2> /dev/null || true
+modprobe bonding 2> /dev/null || true
+modprobe veth 2> /dev/null || true
+
+# The content of kmsg will be save to the following file
+OUTPUT_FILE="/tmp/${TARGET}"
+
+# Check for basic system dependency and exit if not found
+check_for_dependencies
+# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5)
+echo "6 5" > /proc/sys/kernel/printk
+# Remove the namespace, interfaces and netconsole target on exit
+trap cleanup_bond EXIT
+
+FORMAT="extended"
+IP_VERSION="ipv4"
+VETH0="veth"$(( RANDOM % 256))
+VETH1="veth"$((256 +  RANDOM % 256))
+TXNS=""
+RXNS=""
+
+# Create "bond_tx_XX" and "bond_rx_XX" interfaces, and set DSTIF and SRCIF with
+# the bonding interfaces
+function setup_bonding_ifaces() {
+	local RAND=$(( RANDOM % 100 ))
+	BOND_TX_MAIN_IF="bond_tx_$RAND"
+	BOND_RX_MAIN_IF="bond_rx_$RAND"
+
+	# Setup TX
+	if ! ip -n "${TXNS}" link add "${BOND_TX_MAIN_IF}" type bond mode balance-rr
+	then
+		echo "Failed to create bond TX interface. Is CONFIG_BONDING set?" >&2
+		# only clean nsim ifaces and namespace. Nothing else has been
+		# initialized
+		cleanup_bond_nsim
+		trap - EXIT
+		exit "${ksft_skip}"
+	fi
+
+	# create_netdevsim() got the interface up, but it needs to be down
+	# before being enslaved.
+	ip -n "${TXNS}" \
+		link set "${BOND_TX1_SLAVE_IF}" down
+	ip -n "${TXNS}" \
+		link set "${BOND_TX2_SLAVE_IF}" down
+	ip -n "${TXNS}" \
+		link set "${BOND_TX1_SLAVE_IF}" master "${BOND_TX_MAIN_IF}"
+	ip -n "${TXNS}" \
+		link set "${BOND_TX2_SLAVE_IF}" master "${BOND_TX_MAIN_IF}"
+	ip -n "${TXNS}" \
+		link set "${BOND_TX_MAIN_IF}" up
+
+	# Setup RX
+	ip -n "${RXNS}" \
+		link add "${BOND_RX_MAIN_IF}" type bond mode balance-rr
+	ip -n "${RXNS}" \
+		link set "${BOND_RX1_SLAVE_IF}" down
+	ip -n "${RXNS}" \
+		link set "${BOND_RX2_SLAVE_IF}" down
+	ip -n "${RXNS}" \
+		link set "${BOND_RX1_SLAVE_IF}" master "${BOND_RX_MAIN_IF}"
+	ip -n "${RXNS}" \
+		link set "${BOND_RX2_SLAVE_IF}" master "${BOND_RX_MAIN_IF}"
+	ip -n "${RXNS}" \
+		link set "${BOND_RX_MAIN_IF}" up
+
+	export DSTIF="${BOND_RX_MAIN_IF}"
+	export SRCIF="${BOND_TX_MAIN_IF}"
+}
+
+# Create 4 netdevsim interfaces. Two of them will be bound to TX bonding iface
+# and the other two will be bond to the RX interface (on the other namespace)
+function create_ifaces_bond() {
+	BOND_TX1_SLAVE_IF=$(create_netdevsim "${NSIM_BOND_TX_1}" "${TXNS}")
+	BOND_TX2_SLAVE_IF=$(create_netdevsim "${NSIM_BOND_TX_2}" "${TXNS}")
+	BOND_RX1_SLAVE_IF=$(create_netdevsim "${NSIM_BOND_RX_1}" "${RXNS}")
+	BOND_RX2_SLAVE_IF=$(create_netdevsim "${NSIM_BOND_RX_2}" "${RXNS}")
+}
+
+# netdevsim link BOND_TX to BOND_RX interfaces
+function link_ifaces_bond() {
+	local BOND_TX1_SLAVE_IFIDX
+	local BOND_TX2_SLAVE_IFIDX
+	local BOND_RX1_SLAVE_IFIDX
+	local BOND_RX2_SLAVE_IFIDX
+	local TXNS_FD
+	local RXNS_FD
+
+	BOND_TX1_SLAVE_IFIDX=$(ip netns exec "${TXNS}" \
+				cat /sys/class/net/"$BOND_TX1_SLAVE_IF"/ifindex)
+	BOND_TX2_SLAVE_IFIDX=$(ip netns exec "${TXNS}" \
+				cat /sys/class/net/"$BOND_TX2_SLAVE_IF"/ifindex)
+	BOND_RX1_SLAVE_IFIDX=$(ip netns exec "${RXNS}" \
+				cat /sys/class/net/"$BOND_RX1_SLAVE_IF"/ifindex)
+	BOND_RX2_SLAVE_IFIDX=$(ip netns exec "${RXNS}" \
+				cat /sys/class/net/"$BOND_RX2_SLAVE_IF"/ifindex)
+
+	exec {TXNS_FD}</var/run/netns/"${TXNS}"
+	exec {RXNS_FD}</var/run/netns/"${RXNS}"
+
+	# Linking TX ifaces to the RX ones (on the other namespace)
+	echo "${TXNS_FD}:$BOND_TX1_SLAVE_IFIDX $RXNS_FD:$BOND_RX1_SLAVE_IFIDX"  \
+		> "$NSIM_DEV_SYS_LINK"
+	echo "${TXNS_FD}:$BOND_TX2_SLAVE_IFIDX $RXNS_FD:$BOND_RX2_SLAVE_IFIDX"  \
+		> "$NSIM_DEV_SYS_LINK"
+
+	exec {TXNS_FD}<&-
+	exec {RXNS_FD}<&-
+}
+
+function create_all_ifaces() {
+	# setup_ns function is coming from lib.sh
+	setup_ns TXNS RXNS
+	export NAMESPACE="${RXNS}"
+
+	# Create two interfaces for RX and two for TX
+	create_ifaces_bond
+	# Link netlink ifaces
+	link_ifaces_bond
+}
+
+# configure DSTIF and SRCIF IPs
+function configure_ifaces_ips() {
+	local IP_VERSION=${1:-"ipv4"}
+	select_ipv4_or_ipv6 "${IP_VERSION}"
+
+	ip -n "${RXNS}" addr add "${DSTIP}"/24 dev "${DSTIF}"
+	ip -n "${RXNS}" link set "${DSTIF}" up
+
+	ip -n "${TXNS}" addr add "${SRCIP}"/24 dev "${SRCIF}"
+	ip -n "${TXNS}" link set "${SRCIF}" up
+}
+
+function test_enable_netpoll_on_enslaved_iface() {
+	echo 0 > "${NETCONS_PATH}"/enabled
+
+	# At this stage, BOND_TX1_SLAVE_IF is enslaved to BOND_TX_MAIN_IF, and
+	# linked to BOND_RX1_SLAVE_IF inside the namespace.
+	echo "${BOND_TX1_SLAVE_IF}" > "${NETCONS_PATH}"/dev_name
+
+	# This should fail with the following message in dmesg:
+	# netpoll: netconsole: ethX is a slave device, aborting
+	set +e
+	enable_netcons_ns 2> /dev/null
+	set -e
+
+	if [[ $(cat "${NETCONS_PATH}"/enabled) -eq 1 ]]
+	then
+		echo "test failed: Bonding and netpoll cannot co-exists." >&2
+		exit "${ksft_fail}"
+	fi
+}
+
+function test_delete_bond_and_reenable_target() {
+	ip -n "${TXNS}" \
+		link delete "${BOND_TX_MAIN_IF}" type bond
+
+	# BOND_TX1_SLAVE_IF is not attached to a bond interface anymore
+	# netpoll can be plugged in there
+	echo "${BOND_TX1_SLAVE_IF}" > "${NETCONS_PATH}"/dev_name
+
+	# this should work, since the interface is not enslaved
+	enable_netcons_ns
+
+	if [[ $(cat "${NETCONS_PATH}"/enabled) -eq 0 ]]
+	then
+		echo "test failed: Unable to start netpoll on an unbond iface." >&2
+		exit "${ksft_fail}"
+	fi
+}
+
+# Send a netconsole message to the netconsole target
+function test_send_netcons_msg_through_bond_iface() {
+	# Listen for netconsole port inside the namespace and
+	# destination interface
+	listen_port_and_save_to "${OUTPUT_FILE}" "${IP_VERSION}" &
+	# Wait for socat to start and listen to the port.
+	wait_for_port "${RXNS}" "${PORT}" "${IP_VERSION}"
+	# Send the message
+	echo "${MSG}: ${TARGET}" > /dev/kmsg
+	# Wait until socat saves the file to disk
+	busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}"
+	# Make sure the message was received in the dst part
+	# and exit
+	validate_result "${OUTPUT_FILE}" "${FORMAT}"
+	# kill socat in case it is still running
+	pkill_socat
+}
+
+# BOND_TX1_SLAVE_IF has netconsole enabled on it, bind it to BOND_TX_MAIN_IF.
+# Given BOND_TX_MAIN_IF was deleted, recreate it first
+function test_enslave_netcons_enabled_iface {
+	# netconsole got disabled while the interface was down
+	if [[ $(cat "${NETCONS_PATH}"/enabled) -eq 0 ]]
+	then
+		echo "test failed: netconsole expected to be enabled against BOND_TX1_SLAVE_IF" >&2
+		exit "${ksft_fail}"
+	fi
+
+	# recreate the bonding iface. it got deleted by previous
+	# test (test_delete_bond_and_reenable_target)
+	ip -n "${TXNS}" \
+		link add "${BOND_TX_MAIN_IF}" type bond mode balance-rr
+
+	# sub-interface need to be down before attaching to bonding
+	# This will also disable netconsole.
+	ip -n "${TXNS}" \
+		link set "${BOND_TX1_SLAVE_IF}" down
+	ip -n "${TXNS}" \
+		link set "${BOND_TX1_SLAVE_IF}" master "${BOND_TX_MAIN_IF}"
+	ip -n "${TXNS}" \
+		link set "${BOND_TX_MAIN_IF}" up
+
+	# netconsole got disabled while the interface was down
+	if [[ $(cat "${NETCONS_PATH}"/enabled) -eq 1 ]]
+	then
+		echo "test failed: Device is part of a bond iface, cannot have netcons enabled" >&2
+		exit "${ksft_fail}"
+	fi
+}
+
+# Get netconsole enabled on a bonding interface and attach a second
+# sub-interface.
+function test_enslave_iface_to_bond {
+	# BOND_TX_MAIN_IF has only BOND_TX1_SLAVE_IF right now
+	echo "${BOND_TX_MAIN_IF}" > "${NETCONS_PATH}"/dev_name
+	enable_netcons_ns
+
+	# netcons is attached to bond0 and BOND_TX1_SLAVE_IF is
+	# part of BOND_TX_MAIN_IF. Attach BOND_TX2_SLAVE_IF to BOND_TX_MAIN_IF.
+	ip -n "${TXNS}" \
+		link set "${BOND_TX2_SLAVE_IF}" master "${BOND_TX_MAIN_IF}"
+	if [[ $(cat "${NETCONS_PATH}"/enabled) -eq 0 ]]
+	then
+		echo "test failed: Netconsole should be enabled on bonding interface. Failed" >&2
+		exit "${ksft_fail}"
+	fi
+}
+
+function test_enslave_iff_disabled_netpoll_iface {
+	local ret
+
+	# Create two interfaces. veth interfaces it known to have
+	# IFF_DISABLE_NETPOLL set
+	if ! ip link add "${VETH0}" type veth peer name "${VETH1}"
+	then
+		echo "Failed to create veth TX interface. Is CONFIG_VETH set?" >&2
+		exit "${ksft_skip}"
+	fi
+	set +e
+	# This will print RTNETLINK answers: Device or resource busy
+	ip link set "${VETH0}" master "${BOND_TX_MAIN_IF}" 2> /dev/null
+	ret=$?
+	set -e
+	if [[ $ret -eq 0 ]]
+	then
+		echo "test failed: veth interface could not be enslaved"
+		exit "${ksft_fail}"
+	fi
+}
+
+# Given that netconsole picks the current net namespace, we need to enable it
+# from inside the TXNS namespace
+function enable_netcons_ns() {
+	ip netns exec "${TXNS}" sh -c \
+		"mount -t configfs configfs /sys/kernel/config && echo 1 > $NETCONS_PATH/enabled"
+}
+
+####################
+# Tests start here #
+####################
+
+# Create regular interfaces using netdevsim and link them
+create_all_ifaces
+
+# Setup the bonding interfaces
+# BOND_RX_MAIN_IF has BOND_RX{1,2}_SLAVE_IF
+# BOND_TX_MAIN_IF has BOND_TX{1,2}_SLAVE_IF
+setup_bonding_ifaces
+
+# Configure the ips as BOND_RX1_SLAVE_IF and BOND_TX1_SLAVE_IF
+configure_ifaces_ips "${IP_VERSION}"
+
+_create_dynamic_target "${FORMAT}" "${NETCONS_PATH}"
+enable_netcons_ns
+set_user_data
+
+# Test #1 : Create an bonding interface and attach netpoll into
+# the bonding interface. Netconsole/netpoll should work on
+# the bonding interface.
+test_send_netcons_msg_through_bond_iface
+echo "test #1: netpoll on bonding interface worked. Test passed" >&2
+
+# Test #2: Attach netpoll to an enslaved interface
+# Try to attach netpoll to an enslaved sub-interface (while still being part of
+# a bonding interface), which shouldn't be allowed
+test_enable_netpoll_on_enslaved_iface
+echo "test #2: netpoll correctly rejected enslaved interface (expected behavior). Test passed." >&2
+
+# Test #3: Unplug the sub-interface from bond and enable netconsole
+# Detach the interface from a bonding interface and attach netpoll again
+test_delete_bond_and_reenable_target
+echo "test #3: Able to attach to an unbound interface. Test passed." >&2
+
+# Test #4: Enslave a sub-interface that had netconsole enabled
+# Try to enslave an interface that has netconsole/netpoll enabled.
+# Previous test has netconsole enabled in BOND_TX1_SLAVE_IF, try to enslave it
+test_enslave_netcons_enabled_iface
+echo "test #4: Enslaving an interface with netpoll attached. Test passed." >&2
+
+# Test #5: Enslave a sub-interface to a bonding interface
+# Enslave an interface to a bond interface that has netpoll attached
+# At this stage, BOND_TX_MAIN_IF is created and BOND_TX1_SLAVE_IF is part of
+# it. Netconsole is currently disabled
+test_enslave_iface_to_bond
+echo "test #5: Enslaving an interface to bond+netpoll. Test passed." >&2
+
+# Test #6: Enslave a IFF_DISABLE_NETPOLL sub-interface to a bonding interface
+# At this stage, BOND_TX_MAIN_IF has both sub interface and netconsole is
+# enabled. This test will try to enslave an a veth (IFF_DISABLE_NETPOLL) interface
+# and it should fail, with netpoll: veth0 doesn't support polling
+test_enslave_iff_disabled_netpoll_iface
+echo "test #6: Enslaving IFF_DISABLE_NETPOLL ifaces to bond iface is not supported. Test passed." >&2
+
+cleanup_bond
+trap - EXIT
+exit "${EXIT_STATUS}"
diff --git a/tools/testing/selftests/drivers/net/bonding/option_prio.sh b/tools/testing/selftests/drivers/net/bonding/option_prio.sh
deleted file mode 100755
index c32eebff5005..000000000000
--- a/tools/testing/selftests/drivers/net/bonding/option_prio.sh
+++ /dev/null
@@ -1,245 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-#
-# Test bonding option prio
-#
-
-ALL_TESTS="
-	prio_arp_ip_target_test
-	prio_miimon_test
-"
-
-REQUIRE_MZ=no
-REQUIRE_JQ=no
-NUM_NETIFS=0
-lib_dir=$(dirname "$0")
-source "$lib_dir"/net_forwarding_lib.sh
-
-destroy()
-{
-	ip link del bond0 &>/dev/null
-	ip link del br0 &>/dev/null
-	ip link del veth0 &>/dev/null
-	ip link del veth1 &>/dev/null
-	ip link del veth2 &>/dev/null
-	ip netns del ns1 &>/dev/null
-	ip link del veth3 &>/dev/null
-}
-
-cleanup()
-{
-	pre_cleanup
-
-	destroy
-}
-
-skip()
-{
-        local skip=1
-	ip link add name bond0 type bond mode 1 miimon 100 &>/dev/null
-	ip link add name veth0 type veth peer name veth0_p
-	ip link set veth0 master bond0
-
-	# check if iproute support prio option
-	ip link set dev veth0 type bond_slave prio 10
-	[[ $? -ne 0 ]] && skip=0
-
-	# check if bonding support prio option
-	ip -d link show veth0 | grep -q "prio 10"
-	[[ $? -ne 0 ]] && skip=0
-
-	ip link del bond0 &>/dev/null
-	ip link del veth0
-
-	return $skip
-}
-
-active_slave=""
-check_active_slave()
-{
-	local target_active_slave=$1
-	active_slave="$(cat /sys/class/net/bond0/bonding/active_slave)"
-	test "$active_slave" = "$target_active_slave"
-	check_err $? "Current active slave is $active_slave but not $target_active_slave"
-}
-
-
-# Test bonding prio option with mode=$mode monitor=$monitor
-# and primary_reselect=$primary_reselect
-prio_test()
-{
-	RET=0
-
-	local monitor=$1
-	local mode=$2
-	local primary_reselect=$3
-
-	local bond_ip4="192.169.1.2"
-	local peer_ip4="192.169.1.1"
-	local bond_ip6="2009:0a:0b::02"
-	local peer_ip6="2009:0a:0b::01"
-
-
-	# create veths
-	ip link add name veth0 type veth peer name veth0_p
-	ip link add name veth1 type veth peer name veth1_p
-	ip link add name veth2 type veth peer name veth2_p
-
-	# create bond
-	if [[ "$monitor" == "miimon" ]];then
-		ip link add name bond0 type bond mode $mode miimon 100 primary veth1 primary_reselect $primary_reselect
-	elif [[ "$monitor" == "arp_ip_target" ]];then
-		ip link add name bond0 type bond mode $mode arp_interval 1000 arp_ip_target $peer_ip4 primary veth1 primary_reselect $primary_reselect
-	elif [[ "$monitor" == "ns_ip6_target" ]];then
-		ip link add name bond0 type bond mode $mode arp_interval 1000 ns_ip6_target $peer_ip6 primary veth1 primary_reselect $primary_reselect
-	fi
-	ip link set bond0 up
-	ip link set veth0 master bond0
-	ip link set veth1 master bond0
-	ip link set veth2 master bond0
-	# check bonding member prio value
-	ip link set dev veth0 type bond_slave prio 0
-	ip link set dev veth1 type bond_slave prio 10
-	ip link set dev veth2 type bond_slave prio 11
-	ip -d link show veth0 | grep -q 'prio 0'
-	check_err $? "veth0 prio is not 0"
-	ip -d link show veth1 | grep -q 'prio 10'
-	check_err $? "veth0 prio is not 10"
-	ip -d link show veth2 | grep -q 'prio 11'
-	check_err $? "veth0 prio is not 11"
-
-	ip link set veth0 up
-	ip link set veth1 up
-	ip link set veth2 up
-	ip link set veth0_p up
-	ip link set veth1_p up
-	ip link set veth2_p up
-
-	# prepare ping target
-	ip link add name br0 type bridge
-	ip link set br0 up
-	ip link set veth0_p master br0
-	ip link set veth1_p master br0
-	ip link set veth2_p master br0
-	ip link add name veth3 type veth peer name veth3_p
-	ip netns add ns1
-	ip link set veth3_p master br0 up
-	ip link set veth3 netns ns1 up
-	ip netns exec ns1 ip addr add $peer_ip4/24 dev veth3
-	ip netns exec ns1 ip addr add $peer_ip6/64 dev veth3
-	ip addr add $bond_ip4/24 dev bond0
-	ip addr add $bond_ip6/64 dev bond0
-	sleep 5
-
-	ping $peer_ip4 -c5 -I bond0 &>/dev/null
-	check_err $? "ping failed 1."
-	ping6 $peer_ip6 -c5 -I bond0 &>/dev/null
-	check_err $? "ping6 failed 1."
-
-	# active salve should be the primary slave
-	check_active_slave veth1
-
-	# active slave should be the higher prio slave
-	ip link set $active_slave down
-	ping $peer_ip4 -c5 -I bond0 &>/dev/null
-	check_err $? "ping failed 2."
-	check_active_slave veth2
-
-	# when only 1 slave is up
-	ip link set $active_slave down
-	ping $peer_ip4 -c5 -I bond0 &>/dev/null
-	check_err $? "ping failed 3."
-	check_active_slave veth0
-
-	# when a higher prio slave change to up
-	ip link set veth2 up
-	ping $peer_ip4 -c5 -I bond0 &>/dev/null
-	check_err $? "ping failed 4."
-	case $primary_reselect in
-		"0")
-			check_active_slave "veth2"
-			;;
-		"1")
-			check_active_slave "veth0"
-			;;
-		"2")
-			check_active_slave "veth0"
-			;;
-	esac
-	local pre_active_slave=$active_slave
-
-	# when the primary slave change to up
-	ip link set veth1 up
-	ping $peer_ip4 -c5 -I bond0 &>/dev/null
-	check_err $? "ping failed 5."
-	case $primary_reselect in
-		"0")
-			check_active_slave "veth1"
-			;;
-		"1")
-			check_active_slave "$pre_active_slave"
-			;;
-		"2")
-			check_active_slave "$pre_active_slave"
-			ip link set $active_slave down
-			ping $peer_ip4 -c5 -I bond0 &>/dev/null
-			check_err $? "ping failed 6."
-			check_active_slave "veth1"
-			;;
-	esac
-
-	# Test changing bond salve prio
-	if [[ "$primary_reselect" == "0" ]];then
-		ip link set dev veth0 type bond_slave prio 1000000
-		ip link set dev veth1 type bond_slave prio 0
-		ip link set dev veth2 type bond_slave prio -50
-		ip -d link show veth0 | grep -q 'prio 1000000'
-		check_err $? "veth0 prio is not 1000000"
-		ip -d link show veth1 | grep -q 'prio 0'
-		check_err $? "veth1 prio is not 0"
-		ip -d link show veth2 | grep -q 'prio -50'
-		check_err $? "veth3 prio is not -50"
-		check_active_slave "veth1"
-
-		ip link set $active_slave down
-		ping $peer_ip4 -c5 -I bond0 &>/dev/null
-		check_err $? "ping failed 7."
-		check_active_slave "veth0"
-	fi
-
-	cleanup
-
-	log_test "prio_test" "Test bonding option 'prio' with mode=$mode monitor=$monitor and primary_reselect=$primary_reselect"
-}
-
-prio_miimon_test()
-{
-	local mode
-	local primary_reselect
-
-	for mode in 1 5 6; do
-		for primary_reselect in 0 1 2; do
-			prio_test "miimon" $mode $primary_reselect
-		done
-	done
-}
-
-prio_arp_ip_target_test()
-{
-	local primary_reselect
-
-	for primary_reselect in 0 1 2; do
-		prio_test "arp_ip_target" 1 $primary_reselect
-	done
-}
-
-if skip;then
-	log_test_skip "option_prio.sh" "Current iproute doesn't support 'prio'."
-	exit 0
-fi
-
-trap cleanup EXIT
-
-tests_run
-
-exit "$EXIT_STATUS"
diff --git a/tools/testing/selftests/drivers/net/bonding/settings b/tools/testing/selftests/drivers/net/bonding/settings
index 6091b45d226b..79b65bdf05db 100644
--- a/tools/testing/selftests/drivers/net/bonding/settings
+++ b/tools/testing/selftests/drivers/net/bonding/settings
@@ -1 +1 @@
-timeout=120
+timeout=1200
diff --git a/tools/testing/selftests/drivers/net/config b/tools/testing/selftests/drivers/net/config
new file mode 100644
index 000000000000..77ccf83d87e0
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/config
@@ -0,0 +1,10 @@
+CONFIG_CONFIGFS_FS=y
+CONFIG_DEBUG_INFO_BTF=y
+CONFIG_DEBUG_INFO_BTF_MODULES=n
+CONFIG_INET_PSP=y
+CONFIG_IPV6=y
+CONFIG_NETCONSOLE=m
+CONFIG_NETCONSOLE_DYNAMIC=y
+CONFIG_NETCONSOLE_EXTENDED_LOG=y
+CONFIG_NETDEVSIM=m
+CONFIG_XDP_SOCKETS=y
diff --git a/tools/testing/selftests/drivers/net/dsa/Makefile b/tools/testing/selftests/drivers/net/dsa/Makefile
index c393e7b73805..7994bd0e5c44 100644
--- a/tools/testing/selftests/drivers/net/dsa/Makefile
+++ b/tools/testing/selftests/drivers/net/dsa/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0+ OR MIT
 
-TEST_PROGS = bridge_locked_port.sh \
+TEST_PROGS := \
+	bridge_locked_port.sh \
 	bridge_mdb.sh \
 	bridge_mld.sh \
 	bridge_vlan_aware.sh \
@@ -9,10 +10,27 @@ TEST_PROGS = bridge_locked_port.sh \
 	local_termination.sh \
 	no_forwarding.sh \
 	tc_actions.sh \
-	test_bridge_fdb_stress.sh
+	test_bridge_fdb_stress.sh \
+# end of TEST_PROGS
 
-TEST_PROGS_EXTENDED := lib.sh tc_common.sh
+TEST_FILES := \
+	forwarding.config \
+	run_net_forwarding_test.sh \
+# end of TEST_FILES
 
-TEST_FILES := forwarding.config
+TEST_INCLUDES := \
+	../../../net/forwarding/bridge_locked_port.sh \
+	../../../net/forwarding/bridge_mdb.sh \
+	../../../net/forwarding/bridge_mld.sh \
+	../../../net/forwarding/bridge_vlan_aware.sh \
+	../../../net/forwarding/bridge_vlan_mcast.sh \
+	../../../net/forwarding/bridge_vlan_unaware.sh \
+	../../../net/forwarding/lib.sh \
+	../../../net/forwarding/local_termination.sh \
+	../../../net/forwarding/no_forwarding.sh \
+	../../../net/forwarding/tc_actions.sh \
+	../../../net/forwarding/tc_common.sh \
+	../../../net/lib.sh \
+# end of TEST_INCLUDES
 
 include ../../../lib.mk
diff --git a/tools/testing/selftests/drivers/net/dsa/bridge_locked_port.sh b/tools/testing/selftests/drivers/net/dsa/bridge_locked_port.sh
index f5eb940c4c7c..d16a65e7595d 120000
--- a/tools/testing/selftests/drivers/net/dsa/bridge_locked_port.sh
+++ b/tools/testing/selftests/drivers/net/dsa/bridge_locked_port.sh
@@ -1 +1 @@
-../../../net/forwarding/bridge_locked_port.sh
-\ No newline at end of file
+run_net_forwarding_test.sh
+\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/dsa/bridge_mdb.sh b/tools/testing/selftests/drivers/net/dsa/bridge_mdb.sh
index 76492da525f7..d16a65e7595d 120000
--- a/tools/testing/selftests/drivers/net/dsa/bridge_mdb.sh
+++ b/tools/testing/selftests/drivers/net/dsa/bridge_mdb.sh
@@ -1 +1 @@
-../../../net/forwarding/bridge_mdb.sh
-\ No newline at end of file
+run_net_forwarding_test.sh
+\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/dsa/bridge_mld.sh b/tools/testing/selftests/drivers/net/dsa/bridge_mld.sh
index 81a7e0df0474..d16a65e7595d 120000
--- a/tools/testing/selftests/drivers/net/dsa/bridge_mld.sh
+++ b/tools/testing/selftests/drivers/net/dsa/bridge_mld.sh
@@ -1 +1 @@
-../../../net/forwarding/bridge_mld.sh
-\ No newline at end of file
+run_net_forwarding_test.sh
+\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/dsa/bridge_vlan_aware.sh b/tools/testing/selftests/drivers/net/dsa/bridge_vlan_aware.sh
index 9831ed74376a..d16a65e7595d 120000
--- a/tools/testing/selftests/drivers/net/dsa/bridge_vlan_aware.sh
+++ b/tools/testing/selftests/drivers/net/dsa/bridge_vlan_aware.sh
@@ -1 +1 @@
-../../../net/forwarding/bridge_vlan_aware.sh
-\ No newline at end of file
+run_net_forwarding_test.sh
+\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/dsa/bridge_vlan_mcast.sh b/tools/testing/selftests/drivers/net/dsa/bridge_vlan_mcast.sh
index 7f3c3f0bf719..d16a65e7595d 120000
--- a/tools/testing/selftests/drivers/net/dsa/bridge_vlan_mcast.sh
+++ b/tools/testing/selftests/drivers/net/dsa/bridge_vlan_mcast.sh
@@ -1 +1 @@
-../../../net/forwarding/bridge_vlan_mcast.sh
-\ No newline at end of file
+run_net_forwarding_test.sh
+\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/dsa/bridge_vlan_unaware.sh b/tools/testing/selftests/drivers/net/dsa/bridge_vlan_unaware.sh
index bf1a57e6bde1..d16a65e7595d 120000
--- a/tools/testing/selftests/drivers/net/dsa/bridge_vlan_unaware.sh
+++ b/tools/testing/selftests/drivers/net/dsa/bridge_vlan_unaware.sh
@@ -1 +1 @@
-../../../net/forwarding/bridge_vlan_unaware.sh
-\ No newline at end of file
+run_net_forwarding_test.sh
+\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/dsa/lib.sh b/tools/testing/selftests/drivers/net/dsa/lib.sh
deleted file mode 120000
index 39c96828c5ef..000000000000
--- a/tools/testing/selftests/drivers/net/dsa/lib.sh
+++ /dev/null
@@ -1 +0,0 @@
-../../../net/forwarding/lib.sh
-\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/dsa/local_termination.sh b/tools/testing/selftests/drivers/net/dsa/local_termination.sh
index c08166f84501..d16a65e7595d 120000
--- a/tools/testing/selftests/drivers/net/dsa/local_termination.sh
+++ b/tools/testing/selftests/drivers/net/dsa/local_termination.sh
@@ -1 +1 @@
-../../../net/forwarding/local_termination.sh
-\ No newline at end of file
+run_net_forwarding_test.sh
+\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/dsa/no_forwarding.sh b/tools/testing/selftests/drivers/net/dsa/no_forwarding.sh
index b9757466bc97..d16a65e7595d 120000
--- a/tools/testing/selftests/drivers/net/dsa/no_forwarding.sh
+++ b/tools/testing/selftests/drivers/net/dsa/no_forwarding.sh
@@ -1 +1 @@
-../../../net/forwarding/no_forwarding.sh
-\ No newline at end of file
+run_net_forwarding_test.sh
+\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/dsa/run_net_forwarding_test.sh b/tools/testing/selftests/drivers/net/dsa/run_net_forwarding_test.sh
new file mode 100755
index 000000000000..4106c0a102ea
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/dsa/run_net_forwarding_test.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+libdir=$(dirname "$(readlink -f "${BASH_SOURCE[0]}")")
+testname=$(basename "${BASH_SOURCE[0]}")
+
+source "$libdir"/forwarding.config
+cd "$libdir"/../../../net/forwarding/ || exit 1
+source "./$testname" "$@"
diff --git a/tools/testing/selftests/drivers/net/dsa/tc_actions.sh b/tools/testing/selftests/drivers/net/dsa/tc_actions.sh
index 306213d9430e..d16a65e7595d 120000
--- a/tools/testing/selftests/drivers/net/dsa/tc_actions.sh
+++ b/tools/testing/selftests/drivers/net/dsa/tc_actions.sh
@@ -1 +1 @@
-../../../net/forwarding/tc_actions.sh
-\ No newline at end of file
+run_net_forwarding_test.sh
+\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/dsa/tc_common.sh b/tools/testing/selftests/drivers/net/dsa/tc_common.sh
deleted file mode 120000
index bc3465bdc36b..000000000000
--- a/tools/testing/selftests/drivers/net/dsa/tc_common.sh
+++ /dev/null
@@ -1 +0,0 @@
-../../../net/forwarding/tc_common.sh
-\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/dsa/tc_taprio.sh b/tools/testing/selftests/drivers/net/dsa/tc_taprio.sh
new file mode 120000
index 000000000000..d16a65e7595d
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/dsa/tc_taprio.sh
@@ -0,0 +1 @@
+run_net_forwarding_test.sh
+\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh b/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh
index a1f269ee84da..74682151d04d 100755
--- a/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh
+++ b/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh
@@ -19,7 +19,7 @@ REQUIRE_JQ="no"
 REQUIRE_MZ="no"
 NETIF_CREATE="no"
 lib_dir=$(dirname "$0")
-source "$lib_dir"/lib.sh
+source "$lib_dir"/../../../net/forwarding/lib.sh
 
 cleanup() {
 	echo "Cleaning up"
@@ -31,7 +31,7 @@ trap 'cleanup' EXIT
 
 eth=${NETIFS[p1]}
 
-ip link del br0 2&>1 >/dev/null || :
+ip link del br0 2>&1 >/dev/null || :
 ip link add br0 type bridge && ip link set $eth master br0
 
 (while :; do
diff --git a/tools/testing/selftests/net/gro.c b/tools/testing/selftests/drivers/net/gro.c
index 30024d0ed373..e894037d2e3e 100644
--- a/tools/testing/selftests/net/gro.c
+++ b/tools/testing/selftests/drivers/net/gro.c
@@ -57,7 +57,8 @@
 #include <string.h>
 #include <unistd.h>
 
-#include "../kselftest.h"
+#include "kselftest.h"
+#include "../../net/lib/ksft.h"
 
 #define DPORT 8000
 #define SPORT 1500
@@ -71,6 +72,12 @@
 #define MAX_PAYLOAD (IP_MAXPACKET - sizeof(struct tcphdr) - sizeof(struct ipv6hdr))
 #define NUM_LARGE_PKT (MAX_PAYLOAD / MSS)
 #define MAX_HDR_LEN (ETH_HLEN + sizeof(struct ipv6hdr) + sizeof(struct tcphdr))
+#define MIN_EXTHDR_SIZE 8
+#define EXT_PAYLOAD_1 "\x00\x00\x00\x00\x00\x00"
+#define EXT_PAYLOAD_2 "\x11\x11\x11\x11\x11\x11"
+
+#define ipv6_optlen(p)  (((p)->hdrlen+1) << 3) /* calculate IPv6 extension header len */
+#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
 
 static const char *addr6_src = "fdaa::2";
 static const char *addr6_dst = "fdaa::1";
@@ -87,6 +94,8 @@ static bool tx_socket = true;
 static int tcp_offset = -1;
 static int total_hdr_len = -1;
 static int ethhdr_proto = -1;
+static bool ipip;
+static const int num_flush_id_cases = 6;
 
 static void vlog(const char *fmt, ...)
 {
@@ -104,26 +113,47 @@ static void setup_sock_filter(int fd)
 	const int dport_off = tcp_offset + offsetof(struct tcphdr, dest);
 	const int ethproto_off = offsetof(struct ethhdr, h_proto);
 	int optlen = 0;
-	int ipproto_off;
+	int ipproto_off, opt_ipproto_off;
 	int next_off;
 
-	if (proto == PF_INET)
+	if (ipip)
+		next_off = sizeof(struct iphdr) + offsetof(struct iphdr, protocol);
+	else if (proto == PF_INET)
 		next_off = offsetof(struct iphdr, protocol);
 	else
 		next_off = offsetof(struct ipv6hdr, nexthdr);
 	ipproto_off = ETH_HLEN + next_off;
 
+	/* Overridden later if exthdrs are used: */
+	opt_ipproto_off = ipproto_off;
+
 	if (strcmp(testname, "ip") == 0) {
 		if (proto == PF_INET)
 			optlen = sizeof(struct ip_timestamp);
-		else
-			optlen = sizeof(struct ip6_frag);
+		else {
+			BUILD_BUG_ON(sizeof(struct ip6_hbh) > MIN_EXTHDR_SIZE);
+			BUILD_BUG_ON(sizeof(struct ip6_dest) > MIN_EXTHDR_SIZE);
+			BUILD_BUG_ON(sizeof(struct ip6_frag) > MIN_EXTHDR_SIZE);
+
+			/* same size for HBH and Fragment extension header types */
+			optlen = MIN_EXTHDR_SIZE;
+			opt_ipproto_off = ETH_HLEN + sizeof(struct ipv6hdr)
+				+ offsetof(struct ip6_ext, ip6e_nxt);
+		}
 	}
 
+	/* this filter validates the following:
+	 *	- packet is IPv4/IPv6 according to the running test.
+	 *	- packet is TCP. Also handles the case of one extension header and then TCP.
+	 *	- checks the packet tcp dport equals to DPORT. Also handles the case of one
+	 *	  extension header and then TCP.
+	 */
 	struct sock_filter filter[] = {
 			BPF_STMT(BPF_LD  + BPF_H   + BPF_ABS, ethproto_off),
-			BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, ntohs(ethhdr_proto), 0, 7),
+			BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, ntohs(ethhdr_proto), 0, 9),
 			BPF_STMT(BPF_LD  + BPF_B   + BPF_ABS, ipproto_off),
+			BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, IPPROTO_TCP, 2, 0),
+			BPF_STMT(BPF_LD  + BPF_B   + BPF_ABS, opt_ipproto_off),
 			BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, IPPROTO_TCP, 0, 5),
 			BPF_STMT(BPF_LD  + BPF_H   + BPF_ABS, dport_off),
 			BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, DPORT, 2, 0),
@@ -218,7 +248,7 @@ static void fill_datalinklayer(void *buf)
 	eth->h_proto = ethhdr_proto;
 }
 
-static void fill_networklayer(void *buf, int payload_len)
+static void fill_networklayer(void *buf, int payload_len, int protocol)
 {
 	struct ipv6hdr *ip6h = buf;
 	struct iphdr *iph = buf;
@@ -228,7 +258,7 @@ static void fill_networklayer(void *buf, int payload_len)
 
 		ip6h->version = 6;
 		ip6h->payload_len = htons(sizeof(struct tcphdr) + payload_len);
-		ip6h->nexthdr = IPPROTO_TCP;
+		ip6h->nexthdr = protocol;
 		ip6h->hop_limit = 8;
 		if (inet_pton(AF_INET6, addr6_src, &ip6h->saddr) != 1)
 			error(1, errno, "inet_pton source ip6");
@@ -240,7 +270,7 @@ static void fill_networklayer(void *buf, int payload_len)
 		iph->version = 4;
 		iph->ihl = 5;
 		iph->ttl = 8;
-		iph->protocol	= IPPROTO_TCP;
+		iph->protocol	= protocol;
 		iph->tot_len = htons(sizeof(struct tcphdr) +
 				payload_len + sizeof(struct iphdr));
 		iph->frag_off = htons(0x4000); /* DF = 1, MF = 0 */
@@ -287,9 +317,19 @@ static void create_packet(void *buf, int seq_offset, int ack_offset,
 {
 	memset(buf, 0, total_hdr_len);
 	memset(buf + total_hdr_len, 'a', payload_len);
+
 	fill_transportlayer(buf + tcp_offset, seq_offset, ack_offset,
 			    payload_len, fin);
-	fill_networklayer(buf + ETH_HLEN, payload_len);
+
+	if (ipip) {
+		fill_networklayer(buf + ETH_HLEN, payload_len + sizeof(struct iphdr),
+				  IPPROTO_IPIP);
+		fill_networklayer(buf + ETH_HLEN + sizeof(struct iphdr),
+				  payload_len, IPPROTO_TCP);
+	} else {
+		fill_networklayer(buf + ETH_HLEN, payload_len, IPPROTO_TCP);
+	}
+
 	fill_datalinklayer(buf);
 }
 
@@ -390,6 +430,13 @@ static void recompute_packet(char *buf, char *no_ext, int extlen)
 		iph->tot_len = htons(ntohs(iph->tot_len) + extlen);
 		iph->check = 0;
 		iph->check = checksum_fold(iph, sizeof(struct iphdr), 0);
+
+		if (ipip) {
+			iph += 1;
+			iph->tot_len = htons(ntohs(iph->tot_len) + extlen);
+			iph->check = 0;
+			iph->check = checksum_fold(iph, sizeof(struct iphdr), 0);
+		}
 	} else {
 		ip6h->payload_len = htons(ntohs(ip6h->payload_len) + extlen);
 	}
@@ -576,6 +623,146 @@ static void add_ipv4_ts_option(void *buf, void *optpkt)
 	iph->check = checksum_fold(iph, sizeof(struct iphdr) + optlen, 0);
 }
 
+static void add_ipv6_exthdr(void *buf, void *optpkt, __u8 exthdr_type, char *ext_payload)
+{
+	struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr *)(optpkt + tcp_offset);
+	struct ipv6hdr *iph = (struct ipv6hdr *)(optpkt + ETH_HLEN);
+	char *exthdr_payload_start = (char *)(exthdr + 1);
+
+	exthdr->hdrlen = 0;
+	exthdr->nexthdr = IPPROTO_TCP;
+
+	memcpy(exthdr_payload_start, ext_payload, MIN_EXTHDR_SIZE - sizeof(*exthdr));
+
+	memcpy(optpkt, buf, tcp_offset);
+	memcpy(optpkt + tcp_offset + MIN_EXTHDR_SIZE, buf + tcp_offset,
+		sizeof(struct tcphdr) + PAYLOAD_LEN);
+
+	iph->nexthdr = exthdr_type;
+	iph->payload_len = htons(ntohs(iph->payload_len) + MIN_EXTHDR_SIZE);
+}
+
+static void fix_ip4_checksum(struct iphdr *iph)
+{
+	iph->check = 0;
+	iph->check = checksum_fold(iph, sizeof(struct iphdr), 0);
+}
+
+static void send_flush_id_case(int fd, struct sockaddr_ll *daddr, int tcase)
+{
+	static char buf1[MAX_HDR_LEN + PAYLOAD_LEN];
+	static char buf2[MAX_HDR_LEN + PAYLOAD_LEN];
+	static char buf3[MAX_HDR_LEN + PAYLOAD_LEN];
+	bool send_three = false;
+	struct iphdr *iph1;
+	struct iphdr *iph2;
+	struct iphdr *iph3;
+
+	iph1 = (struct iphdr *)(buf1 + ETH_HLEN);
+	iph2 = (struct iphdr *)(buf2 + ETH_HLEN);
+	iph3 = (struct iphdr *)(buf3 + ETH_HLEN);
+
+	create_packet(buf1, 0, 0, PAYLOAD_LEN, 0);
+	create_packet(buf2, PAYLOAD_LEN, 0, PAYLOAD_LEN, 0);
+	create_packet(buf3, PAYLOAD_LEN * 2, 0, PAYLOAD_LEN, 0);
+
+	switch (tcase) {
+	case 0: /* DF=1, Incrementing - should coalesce */
+		iph1->frag_off |= htons(IP_DF);
+		iph1->id = htons(8);
+
+		iph2->frag_off |= htons(IP_DF);
+		iph2->id = htons(9);
+		break;
+
+	case 1: /* DF=1, Fixed - should coalesce */
+		iph1->frag_off |= htons(IP_DF);
+		iph1->id = htons(8);
+
+		iph2->frag_off |= htons(IP_DF);
+		iph2->id = htons(8);
+		break;
+
+	case 2: /* DF=0, Incrementing - should coalesce */
+		iph1->frag_off &= ~htons(IP_DF);
+		iph1->id = htons(8);
+
+		iph2->frag_off &= ~htons(IP_DF);
+		iph2->id = htons(9);
+		break;
+
+	case 3: /* DF=0, Fixed - should coalesce */
+		iph1->frag_off &= ~htons(IP_DF);
+		iph1->id = htons(8);
+
+		iph2->frag_off &= ~htons(IP_DF);
+		iph2->id = htons(8);
+		break;
+
+	case 4: /* DF=1, two packets incrementing, and one fixed - should
+		 * coalesce only the first two packets
+		 */
+		iph1->frag_off |= htons(IP_DF);
+		iph1->id = htons(8);
+
+		iph2->frag_off |= htons(IP_DF);
+		iph2->id = htons(9);
+
+		iph3->frag_off |= htons(IP_DF);
+		iph3->id = htons(9);
+		send_three = true;
+		break;
+
+	case 5: /* DF=1, two packets fixed, and one incrementing - should
+		 * coalesce only the first two packets
+		 */
+		iph1->frag_off |= htons(IP_DF);
+		iph1->id = htons(8);
+
+		iph2->frag_off |= htons(IP_DF);
+		iph2->id = htons(8);
+
+		iph3->frag_off |= htons(IP_DF);
+		iph3->id = htons(9);
+		send_three = true;
+		break;
+	}
+
+	fix_ip4_checksum(iph1);
+	fix_ip4_checksum(iph2);
+	write_packet(fd, buf1, total_hdr_len + PAYLOAD_LEN, daddr);
+	write_packet(fd, buf2, total_hdr_len + PAYLOAD_LEN, daddr);
+
+	if (send_three) {
+		fix_ip4_checksum(iph3);
+		write_packet(fd, buf3, total_hdr_len + PAYLOAD_LEN, daddr);
+	}
+}
+
+static void test_flush_id(int fd, struct sockaddr_ll *daddr, char *fin_pkt)
+{
+	for (int i = 0; i < num_flush_id_cases; i++) {
+		sleep(1);
+		send_flush_id_case(fd, daddr, i);
+		sleep(1);
+		write_packet(fd, fin_pkt, total_hdr_len, daddr);
+	}
+}
+
+static void send_ipv6_exthdr(int fd, struct sockaddr_ll *daddr, char *ext_data1, char *ext_data2)
+{
+	static char buf[MAX_HDR_LEN + PAYLOAD_LEN];
+	static char exthdr_pck[sizeof(buf) + MIN_EXTHDR_SIZE];
+
+	create_packet(buf, 0, 0, PAYLOAD_LEN, 0);
+	add_ipv6_exthdr(buf, exthdr_pck, IPPROTO_DSTOPTS, ext_data1);
+	write_packet(fd, exthdr_pck, total_hdr_len + PAYLOAD_LEN + MIN_EXTHDR_SIZE, daddr);
+
+	create_packet(buf, PAYLOAD_LEN * 1, 0, PAYLOAD_LEN, 0);
+	add_ipv6_exthdr(buf, exthdr_pck, IPPROTO_DSTOPTS, ext_data2);
+	write_packet(fd, exthdr_pck, total_hdr_len + PAYLOAD_LEN + MIN_EXTHDR_SIZE, daddr);
+}
+
 /* IPv4 options shouldn't coalesce */
 static void send_ip_options(int fd, struct sockaddr_ll *daddr)
 {
@@ -611,7 +798,7 @@ static void send_fragment4(int fd, struct sockaddr_ll *daddr)
 	 */
 	memset(buf + total_hdr_len, 'a', PAYLOAD_LEN * 2);
 	fill_transportlayer(buf + tcp_offset, PAYLOAD_LEN, 0, PAYLOAD_LEN * 2, 0);
-	fill_networklayer(buf + ETH_HLEN, PAYLOAD_LEN);
+	fill_networklayer(buf + ETH_HLEN, PAYLOAD_LEN, IPPROTO_TCP);
 	fill_datalinklayer(buf);
 
 	iph->frag_off = htons(0x6000); // DF = 1, MF = 1
@@ -697,7 +884,7 @@ static void send_fragment6(int fd, struct sockaddr_ll *daddr)
 		create_packet(buf, PAYLOAD_LEN * i, 0, PAYLOAD_LEN, 0);
 		write_packet(fd, buf, bufpkt_len, daddr);
 	}
-
+	sleep(1);
 	create_packet(buf, PAYLOAD_LEN * 2, 0, PAYLOAD_LEN, 0);
 	memset(extpkt, 0, extpkt_len);
 
@@ -760,6 +947,7 @@ static void check_recv_pkts(int fd, int *correct_payload,
 	vlog("}, Total %d packets\nReceived {", correct_num_pkts);
 
 	while (1) {
+		ip_ext_len = 0;
 		pkt_size = recv(fd, buffer, IP_MAXPACKET + ETH_HLEN + 1, 0);
 		if (pkt_size < 0)
 			error(1, errno, "could not receive");
@@ -767,7 +955,7 @@ static void check_recv_pkts(int fd, int *correct_payload,
 		if (iph->version == 4)
 			ip_ext_len = (iph->ihl - 5) * 4;
 		else if (ip6h->version == 6 && ip6h->nexthdr != IPPROTO_TCP)
-			ip_ext_len = sizeof(struct ip6_frag);
+			ip_ext_len = MIN_EXTHDR_SIZE;
 
 		tcph = (struct tcphdr *)(buffer + tcp_offset + ip_ext_len);
 
@@ -802,6 +990,7 @@ static void check_recv_pkts(int fd, int *correct_payload,
 
 static void gro_sender(void)
 {
+	const int fin_delay_us = 100 * 1000;
 	static char fin_pkt[MAX_HDR_LEN];
 	struct sockaddr_ll daddr = {};
 	int txfd = -1;
@@ -845,15 +1034,22 @@ static void gro_sender(void)
 		write_packet(txfd, fin_pkt, total_hdr_len, &daddr);
 	} else if (strcmp(testname, "tcp") == 0) {
 		send_changed_checksum(txfd, &daddr);
+		/* Adding sleep before sending FIN so that it is not
+		 * received prior to other packets.
+		 */
+		usleep(fin_delay_us);
 		write_packet(txfd, fin_pkt, total_hdr_len, &daddr);
 
 		send_changed_seq(txfd, &daddr);
+		usleep(fin_delay_us);
 		write_packet(txfd, fin_pkt, total_hdr_len, &daddr);
 
 		send_changed_ts(txfd, &daddr);
+		usleep(fin_delay_us);
 		write_packet(txfd, fin_pkt, total_hdr_len, &daddr);
 
 		send_diff_opt(txfd, &daddr);
+		usleep(fin_delay_us);
 		write_packet(txfd, fin_pkt, total_hdr_len, &daddr);
 	} else if (strcmp(testname, "ip") == 0) {
 		send_changed_ECN(txfd, &daddr);
@@ -879,8 +1075,24 @@ static void gro_sender(void)
 			send_fragment4(txfd, &daddr);
 			sleep(1);
 			write_packet(txfd, fin_pkt, total_hdr_len, &daddr);
+
+			test_flush_id(txfd, &daddr, fin_pkt);
 		} else if (proto == PF_INET6) {
+			sleep(1);
 			send_fragment6(txfd, &daddr);
+			sleep(1);
+			write_packet(txfd, fin_pkt, total_hdr_len, &daddr);
+
+			sleep(1);
+			/* send IPv6 packets with ext header with same payload */
+			send_ipv6_exthdr(txfd, &daddr, EXT_PAYLOAD_1, EXT_PAYLOAD_1);
+			sleep(1);
+			write_packet(txfd, fin_pkt, total_hdr_len, &daddr);
+
+			sleep(1);
+			/* send IPv6 packets with ext header with different payload */
+			send_ipv6_exthdr(txfd, &daddr, EXT_PAYLOAD_1, EXT_PAYLOAD_2);
+			sleep(1);
 			write_packet(txfd, fin_pkt, total_hdr_len, &daddr);
 		}
 	} else if (strcmp(testname, "large") == 0) {
@@ -888,7 +1100,7 @@ static void gro_sender(void)
 		 * and min ipv6hdr size. Like MAX_HDR_SIZE,
 		 * MAX_PAYLOAD is defined with the larger header of the two.
 		 */
-		int offset = proto == PF_INET ? 20 : 0;
+		int offset = (proto == PF_INET && !ipip) ? 20 : 0;
 		int remainder = (MAX_PAYLOAD + offset) % MSS;
 
 		send_large(txfd, &daddr, remainder);
@@ -916,6 +1128,8 @@ static void gro_receiver(void)
 	set_timeout(rxfd);
 	bind_packetsocket(rxfd);
 
+	ksft_ready();
+
 	memset(correct_payload, 0, sizeof(correct_payload));
 
 	if (strcmp(testname, "data") == 0) {
@@ -991,16 +1205,54 @@ static void gro_receiver(void)
 
 			printf("fragmented ip4 doesn't coalesce: ");
 			check_recv_pkts(rxfd, correct_payload, 2);
+
+			/* is_atomic checks */
+			printf("DF=1, Incrementing - should coalesce: ");
+			correct_payload[0] = PAYLOAD_LEN * 2;
+			check_recv_pkts(rxfd, correct_payload, 1);
+
+			printf("DF=1, Fixed - should coalesce: ");
+			correct_payload[0] = PAYLOAD_LEN * 2;
+			check_recv_pkts(rxfd, correct_payload, 1);
+
+			printf("DF=0, Incrementing - should coalesce: ");
+			correct_payload[0] = PAYLOAD_LEN * 2;
+			check_recv_pkts(rxfd, correct_payload, 1);
+
+			printf("DF=0, Fixed - should coalesce: ");
+			correct_payload[0] = PAYLOAD_LEN * 2;
+			check_recv_pkts(rxfd, correct_payload, 1);
+
+			printf("DF=1, 2 Incrementing and one fixed - should coalesce only first 2 packets: ");
+			correct_payload[0] = PAYLOAD_LEN * 2;
+			correct_payload[1] = PAYLOAD_LEN;
+			check_recv_pkts(rxfd, correct_payload, 2);
+
+			printf("DF=1, 2 Fixed and one incrementing - should coalesce only first 2 packets: ");
+			correct_payload[0] = PAYLOAD_LEN * 2;
+			correct_payload[1] = PAYLOAD_LEN;
+			check_recv_pkts(rxfd, correct_payload, 2);
 		} else if (proto == PF_INET6) {
 			/* GRO doesn't check for ipv6 hop limit when flushing.
 			 * Hence no corresponding test to the ipv4 case.
 			 */
 			printf("fragmented ip6 doesn't coalesce: ");
 			correct_payload[0] = PAYLOAD_LEN * 2;
+			correct_payload[1] = PAYLOAD_LEN;
+			correct_payload[2] = PAYLOAD_LEN;
+			check_recv_pkts(rxfd, correct_payload, 3);
+
+			printf("ipv6 with ext header does coalesce: ");
+			correct_payload[0] = PAYLOAD_LEN * 2;
+			check_recv_pkts(rxfd, correct_payload, 1);
+
+			printf("ipv6 with ext header with different payloads doesn't coalesce: ");
+			correct_payload[0] = PAYLOAD_LEN;
+			correct_payload[1] = PAYLOAD_LEN;
 			check_recv_pkts(rxfd, correct_payload, 2);
 		}
 	} else if (strcmp(testname, "large") == 0) {
-		int offset = proto == PF_INET ? 20 : 0;
+		int offset = (proto == PF_INET && !ipip) ? 20 : 0;
 		int remainder = (MAX_PAYLOAD + offset) % MSS;
 
 		correct_payload[0] = (MAX_PAYLOAD + offset);
@@ -1029,6 +1281,7 @@ static void parse_args(int argc, char **argv)
 		{ "iface", required_argument, NULL, 'i' },
 		{ "ipv4", no_argument, NULL, '4' },
 		{ "ipv6", no_argument, NULL, '6' },
+		{ "ipip", no_argument, NULL, 'e' },
 		{ "rx", no_argument, NULL, 'r' },
 		{ "saddr", required_argument, NULL, 's' },
 		{ "smac", required_argument, NULL, 'S' },
@@ -1038,7 +1291,7 @@ static void parse_args(int argc, char **argv)
 	};
 	int c;
 
-	while ((c = getopt_long(argc, argv, "46d:D:i:rs:S:t:v", opts, NULL)) != -1) {
+	while ((c = getopt_long(argc, argv, "46d:D:ei:rs:S:t:v", opts, NULL)) != -1) {
 		switch (c) {
 		case '4':
 			proto = PF_INET;
@@ -1048,6 +1301,11 @@ static void parse_args(int argc, char **argv)
 			proto = PF_INET6;
 			ethhdr_proto = htons(ETH_P_IPV6);
 			break;
+		case 'e':
+			ipip = true;
+			proto = PF_INET;
+			ethhdr_proto = htons(ETH_P_IP);
+			break;
 		case 'd':
 			addr4_dst = addr6_dst = optarg;
 			break;
@@ -1083,7 +1341,10 @@ int main(int argc, char **argv)
 {
 	parse_args(argc, argv);
 
-	if (proto == PF_INET) {
+	if (ipip) {
+		tcp_offset = ETH_HLEN + sizeof(struct iphdr) * 2;
+		total_hdr_len = tcp_offset + sizeof(struct tcphdr);
+	} else if (proto == PF_INET) {
 		tcp_offset = ETH_HLEN + sizeof(struct iphdr);
 		total_hdr_len = tcp_offset + sizeof(struct tcphdr);
 	} else if (proto == PF_INET6) {
@@ -1096,11 +1357,13 @@ int main(int argc, char **argv)
 	read_MAC(src_mac, smac);
 	read_MAC(dst_mac, dmac);
 
-	if (tx_socket)
+	if (tx_socket) {
 		gro_sender();
-	else
+	} else {
+		/* Only the receiver exit status determines test success. */
 		gro_receiver();
+		fprintf(stderr, "Gro::%s test passed.\n", testname);
+	}
 
-	fprintf(stderr, "Gro::%s test passed.\n", testname);
 	return 0;
 }
diff --git a/tools/testing/selftests/drivers/net/gro.py b/tools/testing/selftests/drivers/net/gro.py
new file mode 100755
index 000000000000..ba83713bf7b5
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/gro.py
@@ -0,0 +1,164 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+GRO (Generic Receive Offload) conformance tests.
+
+Validates that GRO coalescing works correctly by running the gro
+binary in different configurations and checking for correct packet
+coalescing behavior.
+
+Test cases:
+  - data: Data packets with same size/headers and correct seq numbers coalesce
+  - ack: Pure ACK packets do not coalesce
+  - flags: Packets with PSH, SYN, URG, RST flags do not coalesce
+  - tcp: Packets with incorrect checksum, non-consecutive seqno don't coalesce
+  - ip: Packets with different ECN, TTL, TOS, or IP options don't coalesce
+  - large: Packets larger than GRO_MAX_SIZE don't coalesce
+"""
+
+import os
+from lib.py import ksft_run, ksft_exit, ksft_pr
+from lib.py import NetDrvEpEnv, KsftXfailEx
+from lib.py import cmd, defer, bkg, ip
+from lib.py import ksft_variants
+
+
+def _resolve_dmac(cfg, ipver):
+    """
+    Find the destination MAC address remote host should use to send packets
+    towards the local host. It may be a router / gateway address.
+    """
+
+    attr = "dmac" + ipver
+    # Cache the response across test cases
+    if hasattr(cfg, attr):
+        return getattr(cfg, attr)
+
+    route = ip(f"-{ipver} route get {cfg.addr_v[ipver]}",
+               json=True, host=cfg.remote)[0]
+    gw = route.get("gateway")
+    # Local L2 segment, address directly
+    if not gw:
+        setattr(cfg, attr, cfg.dev['address'])
+        return getattr(cfg, attr)
+
+    # ping to make sure neighbor is resolved,
+    # bind to an interface, for v6 the GW is likely link local
+    cmd(f"ping -c1 -W0 -I{cfg.remote_ifname} {gw}", host=cfg.remote)
+
+    neigh = ip(f"neigh get {gw} dev {cfg.remote_ifname}",
+               json=True, host=cfg.remote)[0]
+    setattr(cfg, attr, neigh['lladdr'])
+    return getattr(cfg, attr)
+
+
+def _write_defer_restore(cfg, path, val, defer_undo=False):
+    with open(path, "r", encoding="utf-8") as fp:
+        orig_val = fp.read().strip()
+        if str(val) == orig_val:
+            return
+    with open(path, "w", encoding="utf-8") as fp:
+        fp.write(val)
+    if defer_undo:
+        defer(_write_defer_restore, cfg, path, orig_val)
+
+
+def _set_mtu_restore(dev, mtu, host):
+    if dev['mtu'] < mtu:
+        ip(f"link set dev {dev['ifname']} mtu {mtu}", host=host)
+        defer(ip, f"link set dev {dev['ifname']} mtu {dev['mtu']}", host=host)
+
+
+def _setup(cfg, test_name):
+    """ Setup hardware loopback mode for GRO testing. """
+
+    if not hasattr(cfg, "bin_remote"):
+        cfg.bin_local = cfg.test_dir / "gro"
+        cfg.bin_remote = cfg.remote.deploy(cfg.bin_local)
+
+    # "large" test needs at least 4k MTU
+    if test_name == "large":
+        _set_mtu_restore(cfg.dev, 4096, None)
+        _set_mtu_restore(cfg.remote_dev, 4096, cfg.remote)
+
+    flush_path = f"/sys/class/net/{cfg.ifname}/gro_flush_timeout"
+    irq_path = f"/sys/class/net/{cfg.ifname}/napi_defer_hard_irqs"
+
+    _write_defer_restore(cfg, flush_path, "200000", defer_undo=True)
+    _write_defer_restore(cfg, irq_path, "10", defer_undo=True)
+
+    try:
+        # Disable TSO for local tests
+        cfg.require_nsim()  # will raise KsftXfailEx if not running on nsim
+
+        cmd(f"ethtool -K {cfg.ifname} gro on tso off")
+        cmd(f"ethtool -K {cfg.remote_ifname} gro on tso off", host=cfg.remote)
+    except KsftXfailEx:
+        pass
+
+def _gro_variants():
+    """Generator that yields all combinations of protocol and test types."""
+
+    for protocol in ["ipv4", "ipv6", "ipip"]:
+        for test_name in ["data", "ack", "flags", "tcp", "ip", "large"]:
+            yield protocol, test_name
+
+
+@ksft_variants(_gro_variants())
+def test(cfg, protocol, test_name):
+    """Run a single GRO test with retries."""
+
+    ipver = "6" if protocol[-1] == "6" else "4"
+    cfg.require_ipver(ipver)
+
+    _setup(cfg, test_name)
+
+    base_cmd_args = [
+        f"--{protocol}",
+        f"--dmac {_resolve_dmac(cfg, ipver)}",
+        f"--smac {cfg.remote_dev['address']}",
+        f"--daddr {cfg.addr_v[ipver]}",
+        f"--saddr {cfg.remote_addr_v[ipver]}",
+        f"--test {test_name}",
+        "--verbose"
+    ]
+    base_args = " ".join(base_cmd_args)
+
+    # Each test is run 6 times to deflake, because given the receive timing,
+    # not all packets that should coalesce will be considered in the same flow
+    # on every try.
+    max_retries = 6
+    for attempt in range(max_retries):
+        rx_cmd = f"{cfg.bin_local} {base_args} --rx --iface {cfg.ifname}"
+        tx_cmd = f"{cfg.bin_remote} {base_args} --iface {cfg.remote_ifname}"
+
+        fail_now = attempt >= max_retries - 1
+
+        with bkg(rx_cmd, ksft_ready=True, exit_wait=True,
+                 fail=fail_now) as rx_proc:
+            cmd(tx_cmd, host=cfg.remote)
+
+        if rx_proc.ret == 0:
+            return
+
+        ksft_pr(rx_proc.stdout.strip().replace('\n', '\n# '))
+        ksft_pr(rx_proc.stderr.strip().replace('\n', '\n# '))
+
+        if test_name == "large" and os.environ.get("KSFT_MACHINE_SLOW"):
+            ksft_pr(f"Ignoring {protocol}/{test_name} failure due to slow environment")
+            return
+
+        ksft_pr(f"Attempt {attempt + 1}/{max_retries} failed, retrying...")
+
+
+def main() -> None:
+    """ Ksft boiler plate main """
+
+    with NetDrvEpEnv(__file__) as cfg:
+        ksft_run(cases=[test], args=(cfg,))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/hds.py b/tools/testing/selftests/drivers/net/hds.py
new file mode 100755
index 000000000000..c4fe049e9baa
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hds.py
@@ -0,0 +1,329 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import errno
+import os
+import random
+from typing import Union
+from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_raises, KsftSkipEx
+from lib.py import CmdExitFailure, EthtoolFamily, NlError
+from lib.py import NetDrvEnv
+from lib.py import defer, ethtool, ip
+
+
+def _get_hds_mode(cfg, netnl) -> str:
+    try:
+        rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+    except NlError as e:
+        raise KsftSkipEx('ring-get not supported by device')
+    if 'tcp-data-split' not in rings:
+        raise KsftSkipEx('tcp-data-split not supported by device')
+    return rings['tcp-data-split']
+
+
+def _xdp_onoff(cfg):
+    prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
+    ip("link set dev %s xdp obj %s sec xdp" %
+       (cfg.ifname, prog))
+    ip("link set dev %s xdp off" % cfg.ifname)
+
+
+def _ioctl_ringparam_modify(cfg, netnl) -> None:
+    """
+    Helper for performing a hopefully unimportant IOCTL SET.
+    IOCTL does not support HDS, so it should not affect the HDS config.
+    """
+    try:
+        rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+    except NlError as e:
+        raise KsftSkipEx('ring-get not supported by device')
+
+    if 'tx' not in rings:
+        raise KsftSkipEx('setting Tx ring size not supported')
+
+    try:
+        ethtool(f"--disable-netlink -G {cfg.ifname} tx {rings['tx'] // 2}")
+    except CmdExitFailure as e:
+        ethtool(f"--disable-netlink -G {cfg.ifname} tx {rings['tx'] * 2}")
+    defer(ethtool, f"-G {cfg.ifname} tx {rings['tx']}")
+
+
+def get_hds(cfg, netnl) -> None:
+    _get_hds_mode(cfg, netnl)
+
+
+def get_hds_thresh(cfg, netnl) -> None:
+    try:
+        rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+    except NlError as e:
+        raise KsftSkipEx('ring-get not supported by device')
+    if 'hds-thresh' not in rings:
+        raise KsftSkipEx('hds-thresh not supported by device')
+
+
+def _hds_reset(cfg, netnl, rings) -> None:
+    cur = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+
+    arg = {'header': {'dev-index': cfg.ifindex}}
+    if cur.get('tcp-data-split') != rings.get('tcp-data-split'):
+        # Try to reset to "unknown" first, we don't know if the setting
+        # was the default or user chose it. Default seems more likely.
+        arg['tcp-data-split'] = "unknown"
+        netnl.rings_set(arg)
+        cur = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+        if cur['tcp-data-split'] == rings['tcp-data-split']:
+            del arg['tcp-data-split']
+        else:
+            # Try the explicit setting
+            arg['tcp-data-split'] = rings['tcp-data-split']
+    if cur.get('hds-thresh') != rings.get('hds-thresh'):
+        arg['hds-thresh'] = rings['hds-thresh']
+    if len(arg) > 1:
+        netnl.rings_set(arg)
+
+
+def _defer_reset_hds(cfg, netnl) -> Union[dict, None]:
+    try:
+        rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+        if 'hds-thresh' in rings or 'tcp-data-split' in rings:
+            defer(_hds_reset, cfg, netnl, rings)
+    except NlError as e:
+        pass
+
+
+def set_hds_enable(cfg, netnl) -> None:
+    _defer_reset_hds(cfg, netnl)
+    try:
+        netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'tcp-data-split': 'enabled'})
+    except NlError as e:
+        if e.error == errno.EINVAL:
+            raise KsftSkipEx("disabling of HDS not supported by the device")
+        elif e.error == errno.EOPNOTSUPP:
+            raise KsftSkipEx("ring-set not supported by the device")
+    try:
+        rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+    except NlError as e:
+        raise KsftSkipEx('ring-get not supported by device')
+    if 'tcp-data-split' not in rings:
+        raise KsftSkipEx('tcp-data-split not supported by device')
+
+    ksft_eq('enabled', rings['tcp-data-split'])
+
+def set_hds_disable(cfg, netnl) -> None:
+    _defer_reset_hds(cfg, netnl)
+    try:
+        netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'tcp-data-split': 'disabled'})
+    except NlError as e:
+        if e.error == errno.EINVAL:
+            raise KsftSkipEx("disabling of HDS not supported by the device")
+        elif e.error == errno.EOPNOTSUPP:
+            raise KsftSkipEx("ring-set not supported by the device")
+    try:
+        rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+    except NlError as e:
+        raise KsftSkipEx('ring-get not supported by device')
+    if 'tcp-data-split' not in rings:
+        raise KsftSkipEx('tcp-data-split not supported by device')
+
+    ksft_eq('disabled', rings['tcp-data-split'])
+
+def set_hds_thresh_zero(cfg, netnl) -> None:
+    _defer_reset_hds(cfg, netnl)
+    try:
+        netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'hds-thresh': 0})
+    except NlError as e:
+        if e.error == errno.EINVAL:
+            raise KsftSkipEx("hds-thresh-set not supported by the device")
+        elif e.error == errno.EOPNOTSUPP:
+            raise KsftSkipEx("ring-set not supported by the device")
+    try:
+        rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+    except NlError as e:
+        raise KsftSkipEx('ring-get not supported by device')
+    if 'hds-thresh' not in rings:
+        raise KsftSkipEx('hds-thresh not supported by device')
+
+    ksft_eq(0, rings['hds-thresh'])
+
+def set_hds_thresh_random(cfg, netnl) -> None:
+    _defer_reset_hds(cfg, netnl)
+    try:
+        rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+    except NlError as e:
+        raise KsftSkipEx('ring-get not supported by device')
+    if 'hds-thresh' not in rings:
+        raise KsftSkipEx('hds-thresh not supported by device')
+    if 'hds-thresh-max' not in rings:
+        raise KsftSkipEx('hds-thresh-max not defined by device')
+
+    if rings['hds-thresh-max'] < 2:
+        raise KsftSkipEx('hds-thresh-max is too small')
+    elif rings['hds-thresh-max'] == 2:
+        hds_thresh = 1
+    else:
+        while True:
+            hds_thresh = random.randint(1, rings['hds-thresh-max'] - 1)
+            if hds_thresh != rings['hds-thresh']:
+                break
+
+    try:
+        netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'hds-thresh': hds_thresh})
+    except NlError as e:
+        if e.error == errno.EINVAL:
+            raise KsftSkipEx("hds-thresh-set not supported by the device")
+        elif e.error == errno.EOPNOTSUPP:
+            raise KsftSkipEx("ring-set not supported by the device")
+    rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+    ksft_eq(hds_thresh, rings['hds-thresh'])
+
+def set_hds_thresh_max(cfg, netnl) -> None:
+    _defer_reset_hds(cfg, netnl)
+    try:
+        rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+    except NlError as e:
+        raise KsftSkipEx('ring-get not supported by device')
+    if 'hds-thresh' not in rings:
+        raise KsftSkipEx('hds-thresh not supported by device')
+    try:
+        netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'hds-thresh': rings['hds-thresh-max']})
+    except NlError as e:
+        if e.error == errno.EINVAL:
+            raise KsftSkipEx("hds-thresh-set not supported by the device")
+        elif e.error == errno.EOPNOTSUPP:
+            raise KsftSkipEx("ring-set not supported by the device")
+    rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+    ksft_eq(rings['hds-thresh'], rings['hds-thresh-max'])
+
+def set_hds_thresh_gt(cfg, netnl) -> None:
+    _defer_reset_hds(cfg, netnl)
+    try:
+        rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+    except NlError as e:
+        raise KsftSkipEx('ring-get not supported by device')
+    if 'hds-thresh' not in rings:
+        raise KsftSkipEx('hds-thresh not supported by device')
+    if 'hds-thresh-max' not in rings:
+        raise KsftSkipEx('hds-thresh-max not defined by device')
+    hds_gt = rings['hds-thresh-max'] + 1
+    with ksft_raises(NlError) as e:
+        netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'hds-thresh': hds_gt})
+    ksft_eq(e.exception.nl_msg.error, -errno.EINVAL)
+
+
+def set_xdp(cfg, netnl) -> None:
+    """
+    Enable single-buffer XDP on the device.
+    When HDS is in "auto" / UNKNOWN mode, XDP installation should work.
+    """
+    mode = _get_hds_mode(cfg, netnl)
+    if mode == 'enabled':
+        _defer_reset_hds(cfg, netnl)
+        netnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                         'tcp-data-split': 'unknown'})
+
+    _xdp_onoff(cfg)
+
+
+def enabled_set_xdp(cfg, netnl) -> None:
+    """
+    Enable single-buffer XDP on the device.
+    When HDS is in "enabled" mode, XDP installation should not work.
+    """
+    _get_hds_mode(cfg, netnl)
+    netnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                     'tcp-data-split': 'enabled'})
+
+    defer(netnl.rings_set, {'header': {'dev-index': cfg.ifindex},
+                            'tcp-data-split': 'unknown'})
+
+    with ksft_raises(CmdExitFailure) as e:
+        _xdp_onoff(cfg)
+
+
+def set_xdp(cfg, netnl) -> None:
+    """
+    Enable single-buffer XDP on the device.
+    When HDS is in "auto" / UNKNOWN mode, XDP installation should work.
+    """
+    mode = _get_hds_mode(cfg, netnl)
+    if mode == 'enabled':
+        netnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                         'tcp-data-split': 'unknown'})
+
+    _xdp_onoff(cfg)
+
+
+def enabled_set_xdp(cfg, netnl) -> None:
+    """
+    Enable single-buffer XDP on the device.
+    When HDS is in "enabled" mode, XDP installation should not work.
+    """
+    _get_hds_mode(cfg, netnl)  # Trigger skip if not supported
+
+    netnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                     'tcp-data-split': 'enabled'})
+    defer(netnl.rings_set, {'header': {'dev-index': cfg.ifindex},
+                            'tcp-data-split': 'unknown'})
+
+    with ksft_raises(CmdExitFailure) as e:
+        _xdp_onoff(cfg)
+
+
+def ioctl(cfg, netnl) -> None:
+    mode1 = _get_hds_mode(cfg, netnl)
+    _ioctl_ringparam_modify(cfg, netnl)
+    mode2 = _get_hds_mode(cfg, netnl)
+
+    ksft_eq(mode1, mode2)
+
+
+def ioctl_set_xdp(cfg, netnl) -> None:
+    """
+    Like set_xdp(), but we perturb the settings via the legacy ioctl.
+    """
+    mode = _get_hds_mode(cfg, netnl)
+    if mode == 'enabled':
+        netnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                         'tcp-data-split': 'unknown'})
+
+    _ioctl_ringparam_modify(cfg, netnl)
+
+    _xdp_onoff(cfg)
+
+
+def ioctl_enabled_set_xdp(cfg, netnl) -> None:
+    """
+    Enable single-buffer XDP on the device.
+    When HDS is in "enabled" mode, XDP installation should not work.
+    """
+    _get_hds_mode(cfg, netnl)  # Trigger skip if not supported
+
+    netnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                     'tcp-data-split': 'enabled'})
+    defer(netnl.rings_set, {'header': {'dev-index': cfg.ifindex},
+                            'tcp-data-split': 'unknown'})
+
+    with ksft_raises(CmdExitFailure) as e:
+        _xdp_onoff(cfg)
+
+
+def main() -> None:
+    with NetDrvEnv(__file__, queue_count=3) as cfg:
+        ksft_run([get_hds,
+                  get_hds_thresh,
+                  set_hds_disable,
+                  set_hds_enable,
+                  set_hds_thresh_random,
+                  set_hds_thresh_zero,
+                  set_hds_thresh_max,
+                  set_hds_thresh_gt,
+                  set_xdp,
+                  enabled_set_xdp,
+                  ioctl,
+                  ioctl_set_xdp,
+                  ioctl_enabled_set_xdp],
+                 args=(cfg, EthtoolFamily()))
+    ksft_exit()
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/hw/.gitignore b/tools/testing/selftests/drivers/net/hw/.gitignore
new file mode 100644
index 000000000000..46540468a775
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/.gitignore
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+iou-zcrx
+ncdevmem
+toeplitz
diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile
new file mode 100644
index 000000000000..9c163ba6feee
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/Makefile
@@ -0,0 +1,79 @@
+# SPDX-License-Identifier: GPL-2.0+ OR MIT
+
+# Check if io_uring supports zero-copy receive
+HAS_IOURING_ZCRX := $(shell \
+	echo -e '#include <liburing.h>\n' \
+	     'void *func = (void *)io_uring_register_ifq;\n' \
+	     'int main() {return 0;}' | \
+	$(CC) -luring -x c - -o /dev/null 2>&1 && echo y)
+
+ifeq ($(HAS_IOURING_ZCRX),y)
+COND_GEN_FILES += iou-zcrx
+else
+$(warning excluding iouring tests, liburing not installed or too old)
+endif
+
+TEST_GEN_FILES := \
+	$(COND_GEN_FILES) \
+# end of TEST_GEN_FILES
+
+TEST_PROGS = \
+	csum.py \
+	devlink_port_split.py \
+	devlink_rate_tc_bw.py \
+	devmem.py \
+	ethtool.sh \
+	ethtool_extended_state.sh \
+	ethtool_mm.sh \
+	ethtool_rmon.sh \
+	hw_stats_l3.sh \
+	hw_stats_l3_gre.sh \
+	iou-zcrx.py \
+	irq.py \
+	loopback.sh \
+	nic_timestamp.py \
+	pp_alloc_fail.py \
+	rss_api.py \
+	rss_ctx.py \
+	rss_flow_label.py \
+	rss_input_xfrm.py \
+	toeplitz.py \
+	tso.py \
+	xsk_reconfig.py \
+	#
+
+TEST_FILES := \
+	ethtool_lib.sh \
+	#
+
+TEST_INCLUDES := \
+	$(wildcard lib/py/*.py ../lib/py/*.py) \
+	../../../net/lib.sh \
+	../../../net/forwarding/ipip_lib.sh \
+	../../../net/forwarding/lib.sh \
+	../../../net/forwarding/tc_common.sh \
+	#
+
+# YNL files, must be before "include ..lib.mk"
+YNL_GEN_FILES := \
+	ncdevmem \
+	toeplitz \
+# end of YNL_GEN_FILES
+TEST_GEN_FILES += $(YNL_GEN_FILES)
+TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c))
+
+include ../../../lib.mk
+
+# YNL build
+YNL_GENS := \
+	ethtool \
+	netdev \
+# end of YNL_GENS
+
+include ../../../net/ynl.mk
+
+include ../../../net/bpf.mk
+
+ifeq ($(HAS_IOURING_ZCRX),y)
+$(OUTPUT)/iou-zcrx: LDLIBS += -luring
+endif
diff --git a/tools/testing/selftests/drivers/net/hw/config b/tools/testing/selftests/drivers/net/hw/config
new file mode 100644
index 000000000000..2307aa001be1
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/config
@@ -0,0 +1,11 @@
+CONFIG_FAIL_FUNCTION=y
+CONFIG_FAULT_INJECTION=y
+CONFIG_FAULT_INJECTION_DEBUG_FS=y
+CONFIG_FUNCTION_ERROR_INJECTION=y
+CONFIG_IO_URING=y
+CONFIG_IPV6=y
+CONFIG_IPV6_GRE=y
+CONFIG_NET_IPGRE=y
+CONFIG_NET_IPGRE_DEMUX=y
+CONFIG_UDMABUF=y
+CONFIG_VXLAN=y
diff --git a/tools/testing/selftests/drivers/net/hw/csum.py b/tools/testing/selftests/drivers/net/hw/csum.py
new file mode 100755
index 000000000000..3e3a89a34afe
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/csum.py
@@ -0,0 +1,110 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""Run the tools/testing/selftests/net/csum testsuite."""
+
+from os import path
+
+from lib.py import ksft_run, ksft_exit, KsftSkipEx
+from lib.py import EthtoolFamily, NetDrvEpEnv
+from lib.py import bkg, cmd, wait_port_listen
+
+def test_receive(cfg, ipver="6", extra_args=None):
+    """Test local nic checksum receive. Remote host sends crafted packets."""
+    if not cfg.have_rx_csum:
+        raise KsftSkipEx(f"Test requires rx checksum offload on {cfg.ifname}")
+
+    ip_args = f"-{ipver} -S {cfg.remote_addr_v[ipver]} -D {cfg.addr_v[ipver]}"
+
+    rx_cmd = f"{cfg.bin_local} -i {cfg.ifname} -n 100 {ip_args} -r 1 -R {extra_args}"
+    tx_cmd = f"{cfg.bin_remote} -i {cfg.remote_ifname} -n 100 {ip_args} -r 1 -T {extra_args}"
+
+    with bkg(rx_cmd, exit_wait=True):
+        wait_port_listen(34000, proto="udp")
+        cmd(tx_cmd, host=cfg.remote)
+
+
+def test_transmit(cfg, ipver="6", extra_args=None):
+    """Test local nic checksum transmit. Remote host verifies packets."""
+    if (not cfg.have_tx_csum_generic and
+        not (cfg.have_tx_csum_ipv4 and ipver == "4") and
+        not (cfg.have_tx_csum_ipv6 and ipver == "6")):
+        raise KsftSkipEx(f"Test requires tx checksum offload on {cfg.ifname}")
+
+    ip_args = f"-{ipver} -S {cfg.addr_v[ipver]} -D {cfg.remote_addr_v[ipver]}"
+
+    # Cannot randomize input when calculating zero checksum
+    if extra_args != "-U -Z":
+        extra_args += " -r 1"
+
+    rx_cmd = f"{cfg.bin_remote} -i {cfg.remote_ifname} -L 1 -n 100 {ip_args} -R {extra_args}"
+    tx_cmd = f"{cfg.bin_local} -i {cfg.ifname} -L 1 -n 100 {ip_args} -T {extra_args}"
+
+    with bkg(rx_cmd, host=cfg.remote, exit_wait=True):
+        wait_port_listen(34000, proto="udp", host=cfg.remote)
+        cmd(tx_cmd)
+
+
+def test_builder(name, cfg, ipver="6", tx=False, extra_args=""):
+    """Construct specific tests from the common template.
+
+       Most tests follow the same basic pattern, differing only in
+       Direction of the test and optional flags passed to csum."""
+    def f(cfg):
+        cfg.require_ipver(ipver)
+
+        if tx:
+            test_transmit(cfg, ipver, extra_args)
+        else:
+            test_receive(cfg, ipver, extra_args)
+
+    f.__name__ = f"ipv{ipver}_" + name
+    return f
+
+
+def check_nic_features(cfg) -> None:
+    """Test whether Tx and Rx checksum offload are enabled.
+
+       If the device under test has either off, then skip the relevant tests."""
+    cfg.have_tx_csum_generic = False
+    cfg.have_tx_csum_ipv4 = False
+    cfg.have_tx_csum_ipv6 = False
+    cfg.have_rx_csum = False
+
+    ethnl = EthtoolFamily()
+    features = ethnl.features_get({"header": {"dev-index": cfg.ifindex}})
+    for f in features["active"]["bits"]["bit"]:
+        if f["name"] == "tx-checksum-ip-generic":
+            cfg.have_tx_csum_generic = True
+        elif f["name"] == "tx-checksum-ipv4":
+            cfg.have_tx_csum_ipv4 = True
+        elif f["name"] == "tx-checksum-ipv6":
+            cfg.have_tx_csum_ipv6 = True
+        elif f["name"] == "rx-checksum":
+            cfg.have_rx_csum = True
+
+
+def main() -> None:
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+        check_nic_features(cfg)
+
+        cfg.bin_local = cfg.net_lib_dir / "csum"
+        cfg.bin_remote = cfg.remote.deploy(cfg.bin_local)
+
+        cases = []
+        for ipver in ["4", "6"]:
+            cases.append(test_builder("rx_tcp", cfg, ipver, False, "-t"))
+            cases.append(test_builder("rx_tcp_invalid", cfg, ipver, False, "-t -E"))
+
+            cases.append(test_builder("rx_udp", cfg, ipver, False, ""))
+            cases.append(test_builder("rx_udp_invalid", cfg, ipver, False, "-E"))
+
+            cases.append(test_builder("tx_udp_csum_offload", cfg, ipver, True, "-U"))
+            cases.append(test_builder("tx_udp_zero_checksum", cfg, ipver, True, "-U -Z"))
+
+        ksft_run(cases=cases, args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/net/devlink_port_split.py b/tools/testing/selftests/drivers/net/hw/devlink_port_split.py
index 2b5d6ff87373..2d84c7a0be6b 100755
--- a/tools/testing/selftests/net/devlink_port_split.py
+++ b/tools/testing/selftests/drivers/net/hw/devlink_port_split.py
@@ -59,6 +59,8 @@ class devlink_ports(object):
         assert stderr == ""
         ports = json.loads(stdout)['port']
 
+        validate_devlink_output(ports, 'flavour')
+
         for port in ports:
             if dev in port:
                 if ports[port]['flavour'] == 'physical':
@@ -220,6 +222,27 @@ def split_splittable_port(port, k, lanes, dev):
     unsplit(port.bus_info)
 
 
+def validate_devlink_output(devlink_data, target_property=None):
+    """
+    Determine if test should be skipped by checking:
+      1. devlink_data contains values
+      2. The target_property exist in devlink_data
+    """
+    skip_reason = None
+    if any(devlink_data.values()):
+        if target_property:
+            skip_reason = "{} not found in devlink output, test skipped".format(target_property)
+            for key in devlink_data:
+                if target_property in devlink_data[key]:
+                    skip_reason = None
+    else:
+        skip_reason = 'devlink output is empty, test skipped'
+
+    if skip_reason:
+        print(skip_reason)
+        sys.exit(KSFT_SKIP)
+
+
 def make_parser():
     parser = argparse.ArgumentParser(description='A test for port splitting.')
     parser.add_argument('--dev',
@@ -240,12 +263,9 @@ def main(cmdline=None):
         stdout, stderr = run_command(cmd)
         assert stderr == ""
 
+        validate_devlink_output(json.loads(stdout))
         devs = json.loads(stdout)['dev']
-        if devs:
-            dev = list(devs.keys())[0]
-        else:
-            print("no devlink device was found, test skipped")
-            sys.exit(KSFT_SKIP)
+        dev = list(devs.keys())[0]
 
     cmd = "devlink dev show %s" % dev
     stdout, stderr = run_command(cmd)
@@ -255,6 +275,7 @@ def main(cmdline=None):
 
     ports = devlink_ports(dev)
 
+    found_max_lanes = False
     for port in ports.if_names:
         max_lanes = get_max_lanes(port.name)
 
@@ -277,6 +298,11 @@ def main(cmdline=None):
                 split_splittable_port(port, lane, max_lanes, dev)
 
                 lane //= 2
+        found_max_lanes = True
+
+    if not found_max_lanes:
+        print(f"Test not started, no port of device {dev} reports max_lanes")
+        sys.exit(KSFT_SKIP)
 
 
 if __name__ == "__main__":
diff --git a/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py b/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py
new file mode 100755
index 000000000000..4e4faa9275bb
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py
@@ -0,0 +1,439 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+Devlink Rate TC Bandwidth Test Suite
+===================================
+
+This test suite verifies the functionality of devlink-rate traffic class (TC)
+bandwidth distribution in a virtualized environment. The tests validate that
+bandwidth can be properly allocated between different traffic classes and
+that TC mapping works as expected.
+
+Test Environment:
+----------------
+- Creates 1 VF
+- Establishes a bridge connecting the VF representor and the uplink representor
+- Sets up 2 VLAN interfaces on the VF with different VLAN IDs (101, 102)
+- Configures different traffic classes (TC3 and TC4) for each VLAN
+
+Test Cases:
+----------
+1. test_no_tc_mapping_bandwidth:
+   - Verifies that without TC mapping, bandwidth is NOT distributed according to
+     the configured 20/80 split between TC3 and TC4
+   - This test should fail if bandwidth matches the 20/80 split without TC
+     mapping
+   - Expected: Bandwidth should NOT be distributed as 20/80
+
+2. test_tc_mapping_bandwidth:
+   - Configures TC mapping using mqprio qdisc
+   - Verifies that with TC mapping, bandwidth IS distributed according to the
+     configured 20/80 split between TC3 and TC4
+   - Expected: Bandwidth should be distributed as 20/80
+
+Bandwidth Distribution:
+----------------------
+- TC3 (VLAN 101): Configured for 20% of total bandwidth
+- TC4 (VLAN 102): Configured for 80% of total bandwidth
+- Total bandwidth: 1Gbps
+- Tolerance: +-12%
+
+Hardware-Specific Behavior (mlx5):
+--------------------------
+mlx5 hardware enforces traffic class separation by ensuring that each transmit
+queue (SQ) is associated with a single TC. If a packet is sent on a queue that
+doesn't match the expected TC (based on DSCP or VLAN priority and hypervisor-set
+mapping), the hardware moves the queue to the correct TC scheduler to preserve
+traffic isolation.
+
+This behavior means that even without explicit TC-to-queue mapping, bandwidth
+enforcement may still appear to work—because the hardware dynamically adjusts
+the scheduling context. However, this can lead to performance issues in high
+rates and HOL blocking if traffic from different TCs is mixed on the same queue.
+"""
+
+import json
+import os
+import subprocess
+import threading
+import time
+
+from lib.py import ksft_pr, ksft_run, ksft_exit
+from lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx
+from lib.py import NetDrvEpEnv, DevlinkFamily
+from lib.py import NlError
+from lib.py import cmd, defer, ethtool, ip
+from lib.py import Iperf3Runner
+
+
+class BandwidthValidator:
+    """
+    Validates total bandwidth and individual shares with tolerance
+    relative to the overall total.
+    """
+
+    def __init__(self, shares):
+        self.tolerance_percent = 12
+        self.expected_total = sum(shares.values())
+        self.bounds = {}
+
+        for name, exp in shares.items():
+            self.bounds[name] = (self.min_expected(exp), self.max_expected(exp))
+
+    def min_expected(self, value):
+        """Calculates the minimum acceptable value based on tolerance."""
+        return value - (self.expected_total * self.tolerance_percent / 100)
+
+    def max_expected(self, value):
+        """Calculates the maximum acceptable value based on tolerance."""
+        return value + (self.expected_total * self.tolerance_percent / 100)
+
+    def bound(self, values):
+        """
+        Return True if all given values fall within tolerance.
+        """
+        for name, value in values.items():
+            low, high = self.bounds[name]
+            if not low <= value <= high:
+                return False
+        return True
+
+
+def setup_vf(cfg, set_tc_mapping=True):
+    """
+    Sets up a VF on the given network interface.
+
+    Enables SR-IOV and switchdev mode, brings the VF interface up,
+    and optionally configures TC mapping using mqprio.
+    """
+    try:
+        cmd(f"devlink dev eswitch set pci/{cfg.pci} mode switchdev")
+        defer(cmd, f"devlink dev eswitch set pci/{cfg.pci} mode legacy")
+    except Exception as exc:
+        raise KsftSkipEx(f"Failed to enable switchdev mode on {cfg.pci}") from exc
+    try:
+        cmd(f"echo 1 > /sys/class/net/{cfg.ifname}/device/sriov_numvfs", shell=True)
+        defer(cmd, f"echo 0 > /sys/class/net/{cfg.ifname}/device/sriov_numvfs", shell=True)
+    except Exception as exc:
+        raise KsftSkipEx(f"Failed to enable SR-IOV on {cfg.ifname}") from exc
+
+    time.sleep(2)
+    vf_ifc = (os.listdir(
+        f"/sys/class/net/{cfg.ifname}/device/virtfn0/net") or [None])[0]
+    if vf_ifc:
+        ip(f"link set dev {vf_ifc} up")
+    else:
+        raise KsftSkipEx("VF interface not found")
+    if set_tc_mapping:
+        cmd(f"tc qdisc add dev {vf_ifc} root handle 5 mqprio mode dcb hw 1 num_tc 8")
+
+    return vf_ifc
+
+
+def setup_vlans_on_vf(vf_ifc):
+    """
+    Sets up two VLAN interfaces on the given VF, each mapped to a different TC.
+    """
+    vlan_configs = [
+        {"vlan_id": 101, "tc": 3, "ip": "198.51.100.1"},
+        {"vlan_id": 102, "tc": 4, "ip": "198.51.100.9"},
+    ]
+
+    for config in vlan_configs:
+        vlan_dev = f"{vf_ifc}.{config['vlan_id']}"
+        ip(f"link add link {vf_ifc} name {vlan_dev} type vlan id {config['vlan_id']}")
+        ip(f"addr add {config['ip']}/29 dev {vlan_dev}")
+        ip(f"link set dev {vlan_dev} up")
+        ip(f"link set dev {vlan_dev} type vlan egress-qos-map 0:{config['tc']}")
+        ksft_pr(f"Created VLAN {vlan_dev} on {vf_ifc} with tc {config['tc']} and IP {config['ip']}")
+
+
+def get_vf_info(cfg):
+    """
+    Finds the VF representor interface and devlink port index
+    for the given PCI device used in the test environment.
+    """
+    cfg.vf_representor = None
+    cfg.vf_port_index = None
+    out = subprocess.check_output(["devlink", "-j", "port", "show"], encoding="utf-8")
+    ports = json.loads(out)["port"]
+
+    for port_name, props in ports.items():
+        netdev = props.get("netdev")
+
+        if (port_name.startswith(f"pci/{cfg.pci}/") and
+            props.get("vfnum") == 0):
+            cfg.vf_representor = netdev
+            cfg.vf_port_index = int(port_name.split("/")[-1])
+            break
+
+
+def setup_bridge(cfg):
+    """
+    Creates and configures a Linux bridge, with both the uplink
+    and VF representor interfaces attached to it.
+    """
+    bridge_name = f"br_{os.getpid()}"
+    ip(f"link add name {bridge_name} type bridge")
+    defer(cmd, f"ip link del name {bridge_name} type bridge")
+
+    ip(f"link set dev {cfg.ifname} master {bridge_name}")
+
+    rep_name = cfg.vf_representor
+    if rep_name:
+        ip(f"link set dev {rep_name} master {bridge_name}")
+        ip(f"link set dev {rep_name} up")
+        ksft_pr(f"Set representor {rep_name} up and added to bridge")
+    else:
+        raise KsftSkipEx("Could not find representor for the VF")
+
+    ip(f"link set dev {bridge_name} up")
+
+
+def setup_devlink_rate(cfg):
+    """
+    Configures devlink rate tx_max and traffic class bandwidth for the VF.
+    """
+    port_index = cfg.vf_port_index
+    if port_index is None:
+        raise KsftSkipEx("Could not find VF port index")
+    try:
+        cfg.devnl.rate_set({
+            "bus-name": "pci",
+            "dev-name": cfg.pci,
+            "port-index": port_index,
+            "rate-tx-max": 125000000,
+            "rate-tc-bws": [
+                {"index": 0, "bw": 0},
+                {"index": 1, "bw": 0},
+                {"index": 2, "bw": 0},
+                {"index": 3, "bw": 20},
+                {"index": 4, "bw": 80},
+                {"index": 5, "bw": 0},
+                {"index": 6, "bw": 0},
+                {"index": 7, "bw": 0},
+            ]
+        })
+    except NlError as exc:
+        if exc.error == 95:  # EOPNOTSUPP
+            raise KsftSkipEx("devlink rate configuration is not supported on the VF") from exc
+        raise KsftFailEx(f"rate_set failed on VF port {port_index}") from exc
+
+
+def setup_remote_vlans(cfg):
+    """
+    Sets up VLAN interfaces on the remote side.
+    """
+    remote_dev = cfg.remote_ifname
+    vlan_ids = [101, 102]
+    remote_ips = ["198.51.100.2", "198.51.100.10"]
+
+    for vlan_id, ip_addr in zip(vlan_ids, remote_ips):
+        vlan_dev = f"{remote_dev}.{vlan_id}"
+        cmd(f"ip link add link {remote_dev} name {vlan_dev} "
+            f"type vlan id {vlan_id}", host=cfg.remote)
+        cmd(f"ip addr add {ip_addr}/29 dev {vlan_dev}", host=cfg.remote)
+        cmd(f"ip link set dev {vlan_dev} up", host=cfg.remote)
+        defer(cmd, f"ip link del {vlan_dev}", host=cfg.remote)
+
+
+def setup_test_environment(cfg, set_tc_mapping=True):
+    """
+    Sets up the complete test environment including VF creation, VLANs,
+    bridge configuration and devlink rate setup.
+    """
+    vf_ifc = setup_vf(cfg, set_tc_mapping)
+    ksft_pr(f"Created VF interface: {vf_ifc}")
+
+    setup_vlans_on_vf(vf_ifc)
+
+    get_vf_info(cfg)
+    setup_bridge(cfg)
+
+    setup_devlink_rate(cfg)
+    setup_remote_vlans(cfg)
+
+
+def measure_bandwidth(cfg, server_ip, client_ip, barrier):
+    """
+    Synchronizes with peers and runs an iperf3-based bandwidth measurement
+    between the given endpoints. Returns average Gbps.
+    """
+    runner = Iperf3Runner(cfg, server_ip=server_ip, client_ip=client_ip)
+    try:
+        barrier.wait(timeout=10)
+    except Exception as exc:
+        raise KsftFailEx("iperf3 barrier wait timed") from exc
+
+    try:
+        bw_gbps = runner.measure_bandwidth(reverse=True)
+    except Exception as exc:
+        raise KsftFailEx("iperf3 bandwidth measurement failed") from exc
+
+    return bw_gbps
+
+
+def run_bandwidth_test(cfg):
+    """
+    Runs parallel bandwidth measurements for each VLAN/TC pair and collects results.
+    """
+    def _run_measure_bandwidth_thread(local_ip, remote_ip, results, barrier, tc_ix):
+        results[tc_ix] = measure_bandwidth(cfg, local_ip, remote_ip, barrier)
+
+    vf_vlan_data = [
+        # (local_ip, remote_ip, TC)
+        ("198.51.100.1",  "198.51.100.2", 3),
+        ("198.51.100.9", "198.51.100.10", 4),
+    ]
+
+    results = {}
+    threads = []
+    start_barrier = threading.Barrier(len(vf_vlan_data))
+
+    for local_ip, remote_ip, tc_ix in vf_vlan_data:
+        thread = threading.Thread(
+            target=_run_measure_bandwidth_thread,
+            args=(local_ip, remote_ip, results, start_barrier, tc_ix)
+        )
+        thread.start()
+        threads.append(thread)
+
+    for thread in threads:
+        thread.join()
+
+    for tc_ix, tc_bw in results.items():
+        if tc_bw is None:
+            raise KsftFailEx("iperf3 failed; cannot evaluate bandwidth")
+
+    return results
+
+
+def calculate_bandwidth_percentages(results):
+    """
+    Calculates the percentage of total bandwidth received by TC3 and TC4.
+    """
+    if 3 not in results or 4 not in results:
+        raise KsftFailEx(f"Missing expected TC results in {results}")
+
+    tc3_bw = results[3]
+    tc4_bw = results[4]
+    total_bw = tc3_bw + tc4_bw
+    tc3_percentage = (tc3_bw / total_bw) * 100
+    tc4_percentage = (tc4_bw / total_bw) * 100
+
+    return {
+        'tc3_bw': tc3_bw,
+        'tc4_bw': tc4_bw,
+        'tc3_percentage': tc3_percentage,
+        'tc4_percentage': tc4_percentage,
+        'total_bw': total_bw
+    }
+
+
+def print_bandwidth_results(bw_data, test_name):
+    """
+    Prints bandwidth measurements and TC usage summary for a given test.
+    """
+    ksft_pr(f"Bandwidth check results {test_name}:")
+    ksft_pr(f"TC 3: {bw_data['tc3_bw']:.2f} Gbits/sec")
+    ksft_pr(f"TC 4: {bw_data['tc4_bw']:.2f} Gbits/sec")
+    ksft_pr(f"Total bandwidth: {bw_data['total_bw']:.2f} Gbits/sec")
+    ksft_pr(f"TC 3 percentage: {bw_data['tc3_percentage']:.1f}%")
+    ksft_pr(f"TC 4 percentage: {bw_data['tc4_percentage']:.1f}%")
+
+
+def verify_total_bandwidth(bw_data, validator):
+    """
+    Ensures the total measured bandwidth falls within the acceptable tolerance.
+    """
+    total = bw_data['total_bw']
+
+    if validator.bound({"total": total}):
+        return
+
+    low, high = validator.bounds["total"]
+
+    if total < low:
+        raise KsftSkipEx(
+            f"Total bandwidth {total:.2f} Gbps < minimum "
+            f"{low:.2f} Gbps; "
+            f"parent tx_max ({validator.expected_total:.1f} G) "
+            f"not reached, cannot validate share"
+        )
+
+    raise KsftFailEx(
+        f"Total bandwidth {total:.2f} Gbps exceeds allowed ceiling "
+        f"{high:.2f} Gbps "
+        f"(VF tx_max set to {validator.expected_total:.1f} G)"
+    )
+
+
+def run_bandwidth_distribution_test(cfg, set_tc_mapping):
+    """
+    Runs parallel bandwidth measurements for both TCs and collects results.
+    """
+    setup_test_environment(cfg, set_tc_mapping)
+    bandwidths = run_bandwidth_test(cfg)
+    bw_data = calculate_bandwidth_percentages(bandwidths)
+    test_name = "with TC mapping" if set_tc_mapping else "without TC mapping"
+    print_bandwidth_results(bw_data, test_name)
+
+    verify_total_bandwidth(bw_data, cfg.traffic_bw_validator)
+
+    return cfg.tc_bw_validator.bound({"tc3": bw_data['tc3_percentage'],
+                                     "tc4": bw_data['tc4_percentage']})
+
+
+def test_no_tc_mapping_bandwidth(cfg):
+    """
+    Verifies that bandwidth is not split 20/80 without traffic class mapping.
+    """
+    pass_bw_msg = "Bandwidth is NOT distributed as 20/80 without TC mapping"
+    fail_bw_msg = "Bandwidth matched 20/80 split without TC mapping"
+    is_mlx5 = "driver: mlx5" in ethtool(f"-i {cfg.ifname}").stdout
+
+    if run_bandwidth_distribution_test(cfg, set_tc_mapping=False):
+        if is_mlx5:
+            raise KsftXfailEx(fail_bw_msg)
+        raise KsftFailEx(fail_bw_msg)
+    if is_mlx5:
+        raise KsftFailEx("mlx5 behavior changed:" + pass_bw_msg)
+    ksft_pr(pass_bw_msg)
+
+
+def test_tc_mapping_bandwidth(cfg):
+    """
+    Verifies that bandwidth is correctly split 20/80 between TC3 and TC4
+    when traffic class mapping is set.
+    """
+    if run_bandwidth_distribution_test(cfg, set_tc_mapping=True):
+        ksft_pr("Bandwidth is distributed as 20/80 with TC mapping")
+    else:
+        raise KsftFailEx("Bandwidth did not match 20/80 split with TC mapping")
+
+
+def main() -> None:
+    """
+    Main entry point for running the test cases.
+    """
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+        cfg.devnl = DevlinkFamily()
+
+        cfg.pci = os.path.basename(
+            os.path.realpath(f"/sys/class/net/{cfg.ifname}/device")
+        )
+        if not cfg.pci:
+            raise KsftSkipEx("Could not get PCI address of the interface")
+
+        cfg.traffic_bw_validator = BandwidthValidator({"total": 1})
+        cfg.tc_bw_validator = BandwidthValidator({"tc3": 20, "tc4": 80})
+
+        cases = [test_no_tc_mapping_bandwidth, test_tc_mapping_bandwidth]
+
+        ksft_run(cases=cases, args=(cfg,))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/hw/devmem.py b/tools/testing/selftests/drivers/net/hw/devmem.py
new file mode 100755
index 000000000000..45c2d49d55b6
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/devmem.py
@@ -0,0 +1,77 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+from os import path
+from lib.py import ksft_run, ksft_exit
+from lib.py import ksft_eq, KsftSkipEx
+from lib.py import NetDrvEpEnv
+from lib.py import bkg, cmd, rand_port, wait_port_listen
+from lib.py import ksft_disruptive
+
+
+def require_devmem(cfg):
+    if not hasattr(cfg, "_devmem_probed"):
+        probe_command = f"{cfg.bin_local} -f {cfg.ifname}"
+        cfg._devmem_supported = cmd(probe_command, fail=False, shell=True).ret == 0
+        cfg._devmem_probed = True
+
+    if not cfg._devmem_supported:
+        raise KsftSkipEx("Test requires devmem support")
+
+
+@ksft_disruptive
+def check_rx(cfg) -> None:
+    require_devmem(cfg)
+
+    port = rand_port()
+    socat = f"socat -u - TCP{cfg.addr_ipver}:{cfg.baddr}:{port},bind={cfg.remote_baddr}:{port}"
+    listen_cmd = f"{cfg.bin_local} -l -f {cfg.ifname} -s {cfg.addr} -p {port} -c {cfg.remote_addr} -v 7"
+
+    with bkg(listen_cmd, exit_wait=True) as ncdevmem:
+        wait_port_listen(port)
+        cmd(f"yes $(echo -e \x01\x02\x03\x04\x05\x06) | \
+            head -c 1K | {socat}", host=cfg.remote, shell=True)
+
+    ksft_eq(ncdevmem.ret, 0)
+
+
+@ksft_disruptive
+def check_tx(cfg) -> None:
+    require_devmem(cfg)
+
+    port = rand_port()
+    listen_cmd = f"socat -U - TCP{cfg.addr_ipver}-LISTEN:{port}"
+
+    with bkg(listen_cmd, host=cfg.remote, exit_wait=True) as socat:
+        wait_port_listen(port, host=cfg.remote)
+        cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_local} -f {cfg.ifname} -s {cfg.remote_addr} -p {port}", shell=True)
+
+    ksft_eq(socat.stdout.strip(), "hello\nworld")
+
+
+@ksft_disruptive
+def check_tx_chunks(cfg) -> None:
+    require_devmem(cfg)
+
+    port = rand_port()
+    listen_cmd = f"socat -U - TCP{cfg.addr_ipver}-LISTEN:{port}"
+
+    with bkg(listen_cmd, host=cfg.remote, exit_wait=True) as socat:
+        wait_port_listen(port, host=cfg.remote)
+        cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_local} -f {cfg.ifname} -s {cfg.remote_addr} -p {port} -z 3", shell=True)
+
+    ksft_eq(socat.stdout.strip(), "hello\nworld")
+
+
+def main() -> None:
+    with NetDrvEpEnv(__file__) as cfg:
+        cfg.bin_local = path.abspath(path.dirname(__file__) + "/ncdevmem")
+        cfg.bin_remote = cfg.remote.deploy(cfg.bin_local)
+
+        ksft_run([check_rx, check_tx, check_tx_chunks],
+                 args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/net/forwarding/ethtool.sh b/tools/testing/selftests/drivers/net/hw/ethtool.sh
index dbb9fcf759e0..fa6953de6b6d 100755
--- a/tools/testing/selftests/net/forwarding/ethtool.sh
+++ b/tools/testing/selftests/drivers/net/hw/ethtool.sh
@@ -10,7 +10,8 @@ ALL_TESTS="
 	different_speeds_autoneg_on
 "
 NUM_NETIFS=2
-source lib.sh
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/forwarding/lib.sh
 source ethtool_lib.sh
 
 h1_create()
@@ -64,9 +65,8 @@ same_speeds_autoneg_off()
 		setup_wait_dev_with_timeout $h1
 		setup_wait_dev_with_timeout $h2
 		ping_do $h1 192.0.2.2
-		check_err $? "speed $speed autoneg off"
-		log_test "force of same speed autoneg off"
-		log_info "speed = $speed"
+		check_err $? "ping with speed $speed autoneg off"
+		log_test "force speed $speed on both ends"
 	done
 
 	ethtool -s $h2 autoneg on
@@ -111,9 +111,8 @@ combination_of_neg_on_and_off()
 		setup_wait_dev_with_timeout $h1
 		setup_wait_dev_with_timeout $h2
 		ping_do $h1 192.0.2.2
-		check_err $? "h1-speed=$speed autoneg off, h2 autoneg on"
-		log_test "one side with autoneg off and another with autoneg on"
-		log_info "force speed = $speed"
+		check_err $? "ping with h1-speed=$speed autoneg off, h2 autoneg on"
+		log_test "force speed $speed vs. autoneg"
 	done
 
 	ethtool -s $h1 autoneg on
@@ -206,10 +205,9 @@ advertise_subset_of_speeds()
 		setup_wait_dev_with_timeout $h1
 		setup_wait_dev_with_timeout $h2
 		ping_do $h1 192.0.2.2
-		check_err $? "h1=$speed_1_to_advertise, h2=$speed_2_to_advertise ($speed_value)"
+		check_err $? "ping with h1=$speed_1_to_advertise, h2=$speed_2_to_advertise ($speed_value)"
 
-		log_test "advertise subset of speeds"
-		log_info "h1=$speed_1_to_advertise, h2=$speed_2_to_advertise"
+		log_test "advertise $speed_1_to_advertise vs. $speed_2_to_advertise"
 	done
 
 	ethtool -s $h2 autoneg on
diff --git a/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh b/tools/testing/selftests/drivers/net/hw/ethtool_extended_state.sh
index 072faa77f53b..a7584448416e 100755
--- a/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh
+++ b/tools/testing/selftests/drivers/net/hw/ethtool_extended_state.sh
@@ -8,7 +8,8 @@ ALL_TESTS="
 "
 
 NUM_NETIFS=2
-source lib.sh
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/forwarding/lib.sh
 source ethtool_lib.sh
 
 TIMEOUT=$((WAIT_TIMEOUT * 1000)) # ms
diff --git a/tools/testing/selftests/net/forwarding/ethtool_lib.sh b/tools/testing/selftests/drivers/net/hw/ethtool_lib.sh
index b9bfb45085af..b9bfb45085af 100644
--- a/tools/testing/selftests/net/forwarding/ethtool_lib.sh
+++ b/tools/testing/selftests/drivers/net/hw/ethtool_lib.sh
diff --git a/tools/testing/selftests/drivers/net/hw/ethtool_mm.sh b/tools/testing/selftests/drivers/net/hw/ethtool_mm.sh
new file mode 100755
index 000000000000..c301e735c8ab
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/ethtool_mm.sh
@@ -0,0 +1,341 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+	manual_with_verification_h1_to_h2
+	manual_with_verification_h2_to_h1
+	manual_without_verification_h1_to_h2
+	manual_without_verification_h2_to_h1
+	manual_failed_verification_h1_to_h2
+	manual_failed_verification_h2_to_h1
+	lldp
+"
+
+NUM_NETIFS=2
+REQUIRE_MZ=no
+PREEMPTIBLE_PRIO=0
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/forwarding/lib.sh
+
+traffic_test()
+{
+	local if=$1; shift
+	local src=$1; shift
+	local num_pkts=10000
+	local before=
+	local after=
+	local delta=
+
+	if [ ${has_pmac_stats[$if]} = false ]; then
+		src="aggregate"
+	fi
+
+	before=$(ethtool_std_stats_get $if "eth-mac" "FramesTransmittedOK" $src)
+
+	$MZ $if -q -c $num_pkts -p 64 -b bcast -t ip -R $PREEMPTIBLE_PRIO
+
+	after=$(ethtool_std_stats_get $if "eth-mac" "FramesTransmittedOK" $src)
+
+	delta=$((after - before))
+
+	# Allow an extra 1% tolerance for random packets sent by the stack
+	[ $delta -ge $num_pkts ] && [ $delta -le $((num_pkts + 100)) ]
+}
+
+manual_with_verification()
+{
+	local tx=$1; shift
+	local rx=$1; shift
+
+	RET=0
+
+	# It isn't completely clear from IEEE 802.3-2018 Figure 99-5: Transmit
+	# Processing state diagram whether the "send_r" variable (send response
+	# to verification frame) should be taken into consideration while the
+	# MAC Merge TX direction is disabled. That being said, at least the
+	# NXP ENETC does not, and requires tx-enabled on in order to respond to
+	# the link partner's verification frames.
+	ethtool --set-mm $rx tx-enabled on
+	ethtool --set-mm $tx verify-enabled on tx-enabled on
+
+	# Wait for verification to finish
+	sleep 1
+
+	ethtool --json --show-mm $tx | jq -r '.[]."verify-status"' | \
+		grep -q 'SUCCEEDED'
+	check_err "$?" "Verification did not succeed"
+
+	ethtool --json --show-mm $tx | jq -r '.[]."tx-active"' | grep -q 'true'
+	check_err "$?" "pMAC TX is not active"
+
+	traffic_test $tx "pmac"
+	check_err "$?" "Traffic did not get sent through $tx's pMAC"
+
+	ethtool --set-mm $tx verify-enabled off tx-enabled off
+	ethtool --set-mm $rx tx-enabled off
+
+	log_test "Manual configuration with verification: $tx to $rx"
+}
+
+manual_with_verification_h1_to_h2()
+{
+	manual_with_verification $h1 $h2
+}
+
+manual_with_verification_h2_to_h1()
+{
+	manual_with_verification $h2 $h1
+}
+
+manual_without_verification()
+{
+	local tx=$1; shift
+	local rx=$1; shift
+
+	RET=0
+
+	ethtool --set-mm $tx verify-enabled off tx-enabled on
+
+	ethtool --json --show-mm $tx | jq -r '.[]."verify-status"' | \
+		grep -q 'DISABLED'
+	check_err "$?" "Verification is not disabled"
+
+	ethtool --json --show-mm $tx | jq -r '.[]."tx-active"' | grep -q 'true'
+	check_err "$?" "pMAC TX is not active"
+
+	traffic_test $tx "pmac"
+	check_err "$?" "Traffic did not get sent through $tx's pMAC"
+
+	ethtool --set-mm $tx verify-enabled off tx-enabled off
+
+	log_test "Manual configuration without verification: $tx to $rx"
+}
+
+manual_without_verification_h1_to_h2()
+{
+	manual_without_verification $h1 $h2
+}
+
+manual_without_verification_h2_to_h1()
+{
+	manual_without_verification $h2 $h1
+}
+
+manual_failed_verification()
+{
+	local tx=$1; shift
+	local rx=$1; shift
+
+	RET=0
+
+	ethtool --set-mm $rx pmac-enabled off
+	ethtool --set-mm $tx verify-enabled on tx-enabled on
+
+	# Wait for verification to time out
+	sleep 1
+
+	ethtool --json --show-mm $tx | jq -r '.[]."verify-status"' | \
+		grep -q 'SUCCEEDED'
+	check_fail "$?" "Verification succeeded when it shouldn't have"
+
+	ethtool --json --show-mm $tx | jq -r '.[]."tx-active"' | grep -q 'true'
+	check_fail "$?" "pMAC TX is active when it shouldn't have"
+
+	traffic_test $tx "emac"
+	check_err "$?" "Traffic did not get sent through $tx's eMAC"
+
+	ethtool --set-mm $tx verify-enabled off tx-enabled off
+	ethtool --set-mm $rx pmac-enabled on
+
+	log_test "Manual configuration with failed verification: $tx to $rx"
+}
+
+manual_failed_verification_h1_to_h2()
+{
+	manual_failed_verification $h1 $h2
+}
+
+manual_failed_verification_h2_to_h1()
+{
+	manual_failed_verification $h2 $h1
+}
+
+smallest_supported_add_frag_size()
+{
+	local iface=$1
+	local rx_min_frag_size=
+
+	rx_min_frag_size=$(ethtool --json --show-mm $iface | \
+		jq '.[]."rx-min-frag-size"')
+
+	if [ $rx_min_frag_size -le 60 ]; then
+		echo 0
+	elif [ $rx_min_frag_size -le 124 ]; then
+		echo 1
+	elif [ $rx_min_frag_size -le 188 ]; then
+		echo 2
+	elif [ $rx_min_frag_size -le 252 ]; then
+		echo 3
+	else
+		echo "$iface: RX min frag size $rx_min_frag_size cannot be advertised over LLDP"
+		exit 1
+	fi
+}
+
+expected_add_frag_size()
+{
+	local iface=$1
+	local requested=$2
+	local min=$(smallest_supported_add_frag_size $iface)
+
+	[ $requested -le $min ] && echo $min || echo $requested
+}
+
+lldp_change_add_frag_size()
+{
+	local add_frag_size=$1
+	local pattern=
+
+	lldptool -T -i $h1 -V addEthCaps addFragSize=$add_frag_size >/dev/null
+	# Wait for TLVs to be received
+	sleep 2
+	pattern=$(printf "Additional fragment size: %d" \
+			 $(expected_add_frag_size $h1 $add_frag_size))
+	lldptool -i $h2 -t -n -V addEthCaps | grep -q "$pattern"
+}
+
+lldp()
+{
+	RET=0
+
+	systemctl start lldpad
+
+	# Configure the interfaces to receive and transmit LLDPDUs
+	lldptool -L -i $h1 adminStatus=rxtx >/dev/null
+	lldptool -L -i $h2 adminStatus=rxtx >/dev/null
+
+	# Enable the transmission of Additional Ethernet Capabilities TLV
+	lldptool -T -i $h1 -V addEthCaps enableTx=yes >/dev/null
+	lldptool -T -i $h2 -V addEthCaps enableTx=yes >/dev/null
+
+	# Wait for TLVs to be received
+	sleep 2
+
+	lldptool -i $h1 -t -n -V addEthCaps | \
+		grep -q "Preemption capability active"
+	check_err "$?" "$h1 pMAC TX is not active"
+
+	lldptool -i $h2 -t -n -V addEthCaps | \
+		grep -q "Preemption capability active"
+	check_err "$?" "$h2 pMAC TX is not active"
+
+	lldp_change_add_frag_size 3
+	check_err "$?" "addFragSize 3"
+
+	lldp_change_add_frag_size 2
+	check_err "$?" "addFragSize 2"
+
+	lldp_change_add_frag_size 1
+	check_err "$?" "addFragSize 1"
+
+	lldp_change_add_frag_size 0
+	check_err "$?" "addFragSize 0"
+
+	traffic_test $h1 "pmac"
+	check_err "$?" "Traffic did not get sent through $h1's pMAC"
+
+	traffic_test $h2 "pmac"
+	check_err "$?" "Traffic did not get sent through $h2's pMAC"
+
+	systemctl stop lldpad
+
+	log_test "LLDP"
+}
+
+h1_create()
+{
+	ip link set dev $h1 up
+
+	tc qdisc add dev $h1 root mqprio num_tc 4 map 0 1 2 3 \
+		queues 1@0 1@1 1@2 1@3 \
+		fp P E E E \
+		hw 1
+
+	ethtool --set-mm $h1 pmac-enabled on tx-enabled off verify-enabled off
+}
+
+h2_create()
+{
+	ip link set dev $h2 up
+
+	ethtool --set-mm $h2 pmac-enabled on tx-enabled off verify-enabled off
+
+	tc qdisc add dev $h2 root mqprio num_tc 4 map 0 1 2 3 \
+		queues 1@0 1@1 1@2 1@3 \
+		fp P E E E \
+		hw 1
+}
+
+h1_destroy()
+{
+	ethtool --set-mm $h1 pmac-enabled off tx-enabled off verify-enabled off
+
+	tc qdisc del dev $h1 root
+
+	ip link set dev $h1 down
+}
+
+h2_destroy()
+{
+	tc qdisc del dev $h2 root
+
+	ethtool --set-mm $h2 pmac-enabled off tx-enabled off verify-enabled off
+
+	ip link set dev $h2 down
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	h2=${NETIFS[p2]}
+
+	h1_create
+	h2_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	h2_destroy
+	h1_destroy
+}
+
+check_ethtool_mm_support
+check_tc_fp_support
+require_command lldptool
+bail_on_lldpad "autoconfigure the MAC Merge layer" "configure it manually"
+
+for netif in ${NETIFS[@]}; do
+	ethtool --show-mm $netif 2>&1 &> /dev/null
+	if [[ $? -ne 0 ]]; then
+		echo "SKIP: $netif does not support MAC Merge"
+		exit $ksft_skip
+	fi
+
+	if check_ethtool_pmac_std_stats_support $netif eth-mac; then
+		has_pmac_stats[$netif]=true
+	else
+		has_pmac_stats[$netif]=false
+		echo "$netif does not report pMAC statistics, falling back to aggregate"
+	fi
+done
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/hw/ethtool_rmon.sh b/tools/testing/selftests/drivers/net/hw/ethtool_rmon.sh
new file mode 100755
index 000000000000..8f60c1685ad4
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/ethtool_rmon.sh
@@ -0,0 +1,145 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+	rmon_rx_histogram
+	rmon_tx_histogram
+"
+
+NUM_NETIFS=2
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/forwarding/lib.sh
+
+ETH_FCS_LEN=4
+ETH_HLEN=$((6+6+2))
+
+declare -A netif_mtu
+
+ensure_mtu()
+{
+	local iface=$1; shift
+	local len=$1; shift
+	local current=$(ip -j link show dev $iface | jq -r '.[0].mtu')
+	local required=$((len - ETH_HLEN - ETH_FCS_LEN))
+
+	if [ $current -lt $required ]; then
+		ip link set dev $iface mtu $required || return 1
+	fi
+}
+
+bucket_test()
+{
+	local iface=$1; shift
+	local neigh=$1; shift
+	local set=$1; shift
+	local bucket=$1; shift
+	local len=$1; shift
+	local num_rx=10000
+	local num_tx=20000
+	local expected=
+	local before=
+	local after=
+	local delta=
+
+	# Mausezahn does not include FCS bytes in its length - but the
+	# histogram counters do
+	len=$((len - ETH_FCS_LEN))
+	len=$((len > 0 ? len : 0))
+
+	before=$(ethtool --json -S $iface --groups rmon | \
+		jq -r ".[0].rmon[\"${set}-pktsNtoM\"][$bucket].val")
+
+	# Send 10k one way and 20k in the other, to detect counters
+	# mapped to the wrong direction
+	$MZ $neigh -q -c $num_rx -p $len -a own -b bcast -d 10us
+	$MZ $iface -q -c $num_tx -p $len -a own -b bcast -d 10us
+
+	after=$(ethtool --json -S $iface --groups rmon | \
+		jq -r ".[0].rmon[\"${set}-pktsNtoM\"][$bucket].val")
+
+	delta=$((after - before))
+
+	expected=$([ $set = rx ] && echo $num_rx || echo $num_tx)
+
+	# Allow some extra tolerance for other packets sent by the stack
+	[ $delta -ge $expected ] && [ $delta -le $((expected + 100)) ]
+}
+
+rmon_histogram()
+{
+	local iface=$1; shift
+	local neigh=$1; shift
+	local set=$1; shift
+	local nbuckets=0
+	local step=
+
+	RET=0
+
+	while read -r -a bucket; do
+		step="$set-pkts${bucket[0]}to${bucket[1]} on $iface"
+
+		for if in $iface $neigh; do
+			if ! ensure_mtu $if ${bucket[0]}; then
+				log_test_xfail "$if does not support the required MTU for $step"
+				return
+			fi
+		done
+
+		if ! bucket_test $iface $neigh $set $nbuckets ${bucket[0]}; then
+			check_err 1 "$step failed"
+			return 1
+		fi
+		log_test "$step"
+		nbuckets=$((nbuckets + 1))
+	done < <(ethtool --json -S $iface --groups rmon | \
+		jq -r ".[0].rmon[\"${set}-pktsNtoM\"][]|[.low, .high]|@tsv" 2>/dev/null)
+
+	if [ $nbuckets -eq 0 ]; then
+		log_test_xfail "$iface does not support $set histogram counters"
+		return
+	fi
+}
+
+rmon_rx_histogram()
+{
+	rmon_histogram $h1 $h2 rx
+	rmon_histogram $h2 $h1 rx
+}
+
+rmon_tx_histogram()
+{
+	rmon_histogram $h1 $h2 tx
+	rmon_histogram $h2 $h1 tx
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	h2=${NETIFS[p2]}
+
+	for iface in $h1 $h2; do
+		netif_mtu[$iface]=$(ip -j link show dev $iface | jq -r '.[0].mtu')
+		ip link set dev $iface up
+	done
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	for iface in $h2 $h1; do
+		ip link set dev $iface \
+			mtu ${netif_mtu[$iface]} \
+			down
+	done
+}
+
+check_ethtool_counter_group_support
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/hw_stats_l3.sh b/tools/testing/selftests/drivers/net/hw/hw_stats_l3.sh
index 9c1f76e108af..67fafefc80be 100755
--- a/tools/testing/selftests/net/forwarding/hw_stats_l3.sh
+++ b/tools/testing/selftests/drivers/net/hw/hw_stats_l3.sh
@@ -48,7 +48,9 @@ ALL_TESTS="
 	test_double_enable
 "
 NUM_NETIFS=4
-source lib.sh
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/forwarding/lib.sh
+source "$lib_dir"/../../../net/forwarding/tc_common.sh
 
 h1_create()
 {
@@ -84,8 +86,9 @@ h2_destroy()
 
 router_rp1_200_create()
 {
-	ip link add name $rp1.200 up \
-		link $rp1 addrgenmode eui64 type vlan id 200
+	ip link add name $rp1.200 link $rp1 type vlan id 200
+	ip link set dev $rp1.200 addrgenmode eui64
+	ip link set dev $rp1.200 up
 	ip address add dev $rp1.200 192.0.2.2/28
 	ip address add dev $rp1.200 2001:db8:1::2/64
 	ip stats set dev $rp1.200 l3_stats on
@@ -256,9 +259,11 @@ reapply_config()
 
 	router_rp1_200_destroy
 
-	ip link add name $rp1.200 link $rp1 addrgenmode none type vlan id 200
+	ip link add name $rp1.200 link $rp1 type vlan id 200
+	ip link set dev $rp1.200 addrgenmode none
 	ip stats set dev $rp1.200 l3_stats on
-	ip link set dev $rp1.200 up addrgenmode eui64
+	ip link set dev $rp1.200 addrgenmode eui64
+	ip link set dev $rp1.200 up
 	ip address add dev $rp1.200 192.0.2.2/28
 	ip address add dev $rp1.200 2001:db8:1::2/64
 }
@@ -319,6 +324,11 @@ trap cleanup EXIT
 setup_prepare
 setup_wait
 
+used=$(ip -j stats show dev $rp1.200 group offload subgroup hw_stats_info |
+	   jq '.[].info.l3_stats.used')
+[[ $used = true ]]
+check_err $? "hw_stats_info.used=$used"
+log_test "l3_stats offloaded"
 tests_run
 
 exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh b/tools/testing/selftests/drivers/net/hw/hw_stats_l3_gre.sh
index eb9ec4a68f84..a94d92e1abce 100755
--- a/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh
+++ b/tools/testing/selftests/drivers/net/hw/hw_stats_l3_gre.sh
@@ -12,8 +12,10 @@ ALL_TESTS="
 	test_stats_tx
 "
 NUM_NETIFS=6
-source lib.sh
-source ipip_lib.sh
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/forwarding/lib.sh
+source "$lib_dir"/../../../net/forwarding/ipip_lib.sh
+source "$lib_dir"/../../../net/forwarding/tc_common.sh
 
 setup_prepare()
 {
diff --git a/tools/testing/selftests/drivers/net/hw/iou-zcrx.c b/tools/testing/selftests/drivers/net/hw/iou-zcrx.c
new file mode 100644
index 000000000000..62456df947bc
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/iou-zcrx.c
@@ -0,0 +1,464 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <assert.h>
+#include <errno.h>
+#include <error.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <arpa/inet.h>
+#include <linux/errqueue.h>
+#include <linux/if_packet.h>
+#include <linux/ipv6.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <net/ethernet.h>
+#include <net/if.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/tcp.h>
+#include <netinet/udp.h>
+#include <sys/epoll.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/resource.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/un.h>
+#include <sys/wait.h>
+
+#include <liburing.h>
+
+static long page_size;
+#define AREA_SIZE (8192 * page_size)
+#define SEND_SIZE (512 * 4096)
+#define min(a, b) \
+	({ \
+		typeof(a) _a = (a); \
+		typeof(b) _b = (b); \
+		_a < _b ? _a : _b; \
+	})
+#define min_t(t, a, b) \
+	({ \
+		t _ta = (a); \
+		t _tb = (b); \
+		min(_ta, _tb); \
+	})
+
+#define ALIGN_UP(v, align) (((v) + (align) - 1) & ~((align) - 1))
+
+static int cfg_server;
+static int cfg_client;
+static int cfg_port = 8000;
+static int cfg_payload_len;
+static const char *cfg_ifname;
+static int cfg_queue_id = -1;
+static bool cfg_oneshot;
+static int cfg_oneshot_recvs;
+static int cfg_send_size = SEND_SIZE;
+static struct sockaddr_in6 cfg_addr;
+
+static char *payload;
+static void *area_ptr;
+static void *ring_ptr;
+static size_t ring_size;
+static struct io_uring_zcrx_rq rq_ring;
+static unsigned long area_token;
+static int connfd;
+static bool stop;
+static size_t received;
+
+static unsigned long gettimeofday_ms(void)
+{
+	struct timeval tv;
+
+	gettimeofday(&tv, NULL);
+	return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
+}
+
+static int parse_address(const char *str, int port, struct sockaddr_in6 *sin6)
+{
+	int ret;
+
+	sin6->sin6_family = AF_INET6;
+	sin6->sin6_port = htons(port);
+
+	ret = inet_pton(sin6->sin6_family, str, &sin6->sin6_addr);
+	if (ret != 1) {
+		/* fallback to plain IPv4 */
+		ret = inet_pton(AF_INET, str, &sin6->sin6_addr.s6_addr32[3]);
+		if (ret != 1)
+			return -1;
+
+		/* add ::ffff prefix */
+		sin6->sin6_addr.s6_addr32[0] = 0;
+		sin6->sin6_addr.s6_addr32[1] = 0;
+		sin6->sin6_addr.s6_addr16[4] = 0;
+		sin6->sin6_addr.s6_addr16[5] = 0xffff;
+	}
+
+	return 0;
+}
+
+static inline size_t get_refill_ring_size(unsigned int rq_entries)
+{
+	size_t size;
+
+	ring_size = rq_entries * sizeof(struct io_uring_zcrx_rqe);
+	/* add space for the header (head/tail/etc.) */
+	ring_size += page_size;
+	return ALIGN_UP(ring_size, page_size);
+}
+
+static void setup_zcrx(struct io_uring *ring)
+{
+	unsigned int ifindex;
+	unsigned int rq_entries = 4096;
+	int ret;
+
+	ifindex = if_nametoindex(cfg_ifname);
+	if (!ifindex)
+		error(1, 0, "bad interface name: %s", cfg_ifname);
+
+	area_ptr = mmap(NULL,
+			AREA_SIZE,
+			PROT_READ | PROT_WRITE,
+			MAP_ANONYMOUS | MAP_PRIVATE,
+			0,
+			0);
+	if (area_ptr == MAP_FAILED)
+		error(1, 0, "mmap(): zero copy area");
+
+	ring_size = get_refill_ring_size(rq_entries);
+	ring_ptr = mmap(NULL,
+			ring_size,
+			PROT_READ | PROT_WRITE,
+			MAP_ANONYMOUS | MAP_PRIVATE,
+			0,
+			0);
+
+	struct io_uring_region_desc region_reg = {
+		.size = ring_size,
+		.user_addr = (__u64)(unsigned long)ring_ptr,
+		.flags = IORING_MEM_REGION_TYPE_USER,
+	};
+
+	struct io_uring_zcrx_area_reg area_reg = {
+		.addr = (__u64)(unsigned long)area_ptr,
+		.len = AREA_SIZE,
+		.flags = 0,
+	};
+
+	struct io_uring_zcrx_ifq_reg reg = {
+		.if_idx = ifindex,
+		.if_rxq = cfg_queue_id,
+		.rq_entries = rq_entries,
+		.area_ptr = (__u64)(unsigned long)&area_reg,
+		.region_ptr = (__u64)(unsigned long)&region_reg,
+	};
+
+	ret = io_uring_register_ifq(ring, &reg);
+	if (ret)
+		error(1, 0, "io_uring_register_ifq(): %d", ret);
+
+	rq_ring.khead = (unsigned int *)((char *)ring_ptr + reg.offsets.head);
+	rq_ring.ktail = (unsigned int *)((char *)ring_ptr + reg.offsets.tail);
+	rq_ring.rqes = (struct io_uring_zcrx_rqe *)((char *)ring_ptr + reg.offsets.rqes);
+	rq_ring.rq_tail = 0;
+	rq_ring.ring_entries = reg.rq_entries;
+
+	area_token = area_reg.rq_area_token;
+}
+
+static void add_accept(struct io_uring *ring, int sockfd)
+{
+	struct io_uring_sqe *sqe;
+
+	sqe = io_uring_get_sqe(ring);
+
+	io_uring_prep_accept(sqe, sockfd, NULL, NULL, 0);
+	sqe->user_data = 1;
+}
+
+static void add_recvzc(struct io_uring *ring, int sockfd)
+{
+	struct io_uring_sqe *sqe;
+
+	sqe = io_uring_get_sqe(ring);
+
+	io_uring_prep_rw(IORING_OP_RECV_ZC, sqe, sockfd, NULL, 0, 0);
+	sqe->ioprio |= IORING_RECV_MULTISHOT;
+	sqe->user_data = 2;
+}
+
+static void add_recvzc_oneshot(struct io_uring *ring, int sockfd, size_t len)
+{
+	struct io_uring_sqe *sqe;
+
+	sqe = io_uring_get_sqe(ring);
+
+	io_uring_prep_rw(IORING_OP_RECV_ZC, sqe, sockfd, NULL, len, 0);
+	sqe->ioprio |= IORING_RECV_MULTISHOT;
+	sqe->user_data = 2;
+}
+
+static void process_accept(struct io_uring *ring, struct io_uring_cqe *cqe)
+{
+	if (cqe->res < 0)
+		error(1, 0, "accept()");
+	if (connfd)
+		error(1, 0, "Unexpected second connection");
+
+	connfd = cqe->res;
+	if (cfg_oneshot)
+		add_recvzc_oneshot(ring, connfd, page_size);
+	else
+		add_recvzc(ring, connfd);
+}
+
+static void process_recvzc(struct io_uring *ring, struct io_uring_cqe *cqe)
+{
+	unsigned rq_mask = rq_ring.ring_entries - 1;
+	struct io_uring_zcrx_cqe *rcqe;
+	struct io_uring_zcrx_rqe *rqe;
+	struct io_uring_sqe *sqe;
+	uint64_t mask;
+	char *data;
+	ssize_t n;
+	int i;
+
+	if (cqe->res == 0 && cqe->flags == 0 && cfg_oneshot_recvs == 0) {
+		stop = true;
+		return;
+	}
+
+	if (cqe->res < 0)
+		error(1, 0, "recvzc(): %d", cqe->res);
+
+	if (cfg_oneshot) {
+		if (cqe->res == 0 && cqe->flags == 0 && cfg_oneshot_recvs) {
+			add_recvzc_oneshot(ring, connfd, page_size);
+			cfg_oneshot_recvs--;
+		}
+	} else if (!(cqe->flags & IORING_CQE_F_MORE)) {
+		add_recvzc(ring, connfd);
+	}
+
+	rcqe = (struct io_uring_zcrx_cqe *)(cqe + 1);
+
+	n = cqe->res;
+	mask = (1ULL << IORING_ZCRX_AREA_SHIFT) - 1;
+	data = (char *)area_ptr + (rcqe->off & mask);
+
+	for (i = 0; i < n; i++) {
+		if (*(data + i) != payload[(received + i)])
+			error(1, 0, "payload mismatch at %d", i);
+	}
+	received += n;
+
+	rqe = &rq_ring.rqes[(rq_ring.rq_tail & rq_mask)];
+	rqe->off = (rcqe->off & ~IORING_ZCRX_AREA_MASK) | area_token;
+	rqe->len = cqe->res;
+	io_uring_smp_store_release(rq_ring.ktail, ++rq_ring.rq_tail);
+}
+
+static void server_loop(struct io_uring *ring)
+{
+	struct io_uring_cqe *cqe;
+	unsigned int count = 0;
+	unsigned int head;
+	int i, ret;
+
+	io_uring_submit_and_wait(ring, 1);
+
+	io_uring_for_each_cqe(ring, head, cqe) {
+		if (cqe->user_data == 1)
+			process_accept(ring, cqe);
+		else if (cqe->user_data == 2)
+			process_recvzc(ring, cqe);
+		else
+			error(1, 0, "unknown cqe");
+		count++;
+	}
+	io_uring_cq_advance(ring, count);
+}
+
+static void run_server(void)
+{
+	unsigned int flags = 0;
+	struct io_uring ring;
+	int fd, enable, ret;
+	uint64_t tstop;
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (fd == -1)
+		error(1, 0, "socket()");
+
+	enable = 1;
+	ret = setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &enable, sizeof(int));
+	if (ret < 0)
+		error(1, 0, "setsockopt(SO_REUSEADDR)");
+
+	ret = bind(fd, (struct sockaddr *)&cfg_addr, sizeof(cfg_addr));
+	if (ret < 0)
+		error(1, 0, "bind()");
+
+	if (listen(fd, 1024) < 0)
+		error(1, 0, "listen()");
+
+	flags |= IORING_SETUP_COOP_TASKRUN;
+	flags |= IORING_SETUP_SINGLE_ISSUER;
+	flags |= IORING_SETUP_DEFER_TASKRUN;
+	flags |= IORING_SETUP_SUBMIT_ALL;
+	flags |= IORING_SETUP_CQE32;
+
+	io_uring_queue_init(512, &ring, flags);
+
+	setup_zcrx(&ring);
+
+	add_accept(&ring, fd);
+
+	tstop = gettimeofday_ms() + 5000;
+	while (!stop && gettimeofday_ms() < tstop)
+		server_loop(&ring);
+
+	if (!stop)
+		error(1, 0, "test failed\n");
+}
+
+static void run_client(void)
+{
+	ssize_t to_send = cfg_send_size;
+	ssize_t sent = 0;
+	ssize_t chunk, res;
+	int fd;
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (fd == -1)
+		error(1, 0, "socket()");
+
+	if (connect(fd, (struct sockaddr *)&cfg_addr, sizeof(cfg_addr)))
+		error(1, 0, "connect()");
+
+	while (to_send) {
+		void *src = &payload[sent];
+
+		chunk = min_t(ssize_t, cfg_payload_len, to_send);
+		res = send(fd, src, chunk, 0);
+		if (res < 0)
+			error(1, 0, "send(): %zd", sent);
+		sent += res;
+		to_send -= res;
+	}
+
+	close(fd);
+}
+
+static void usage(const char *filepath)
+{
+	error(1, 0, "Usage: %s (-4|-6) (-s|-c) -h<server_ip> -p<port> "
+		    "-l<payload_size> -i<ifname> -q<rxq_id>", filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	const int max_payload_len = SEND_SIZE -
+				    sizeof(struct ipv6hdr) -
+				    sizeof(struct tcphdr) -
+				    40 /* max tcp options */;
+	struct sockaddr_in6 *addr6 = (void *) &cfg_addr;
+	char *addr = NULL;
+	int ret;
+	int c;
+
+	if (argc <= 1)
+		usage(argv[0]);
+	cfg_payload_len = max_payload_len;
+
+	while ((c = getopt(argc, argv, "sch:p:l:i:q:o:z:")) != -1) {
+		switch (c) {
+		case 's':
+			if (cfg_client)
+				error(1, 0, "Pass one of -s or -c");
+			cfg_server = 1;
+			break;
+		case 'c':
+			if (cfg_server)
+				error(1, 0, "Pass one of -s or -c");
+			cfg_client = 1;
+			break;
+		case 'h':
+			addr = optarg;
+			break;
+		case 'p':
+			cfg_port = strtoul(optarg, NULL, 0);
+			break;
+		case 'l':
+			cfg_payload_len = strtoul(optarg, NULL, 0);
+			break;
+		case 'i':
+			cfg_ifname = optarg;
+			break;
+		case 'q':
+			cfg_queue_id = strtoul(optarg, NULL, 0);
+			break;
+		case 'o': {
+			cfg_oneshot = true;
+			cfg_oneshot_recvs = strtoul(optarg, NULL, 0);
+			break;
+		}
+		case 'z':
+			cfg_send_size = strtoul(optarg, NULL, 0);
+			break;
+		}
+	}
+
+	if (cfg_server && addr)
+		error(1, 0, "Receiver cannot have -h specified");
+
+	memset(addr6, 0, sizeof(*addr6));
+	addr6->sin6_family = AF_INET6;
+	addr6->sin6_port = htons(cfg_port);
+	addr6->sin6_addr = in6addr_any;
+	if (addr) {
+		ret = parse_address(addr, cfg_port, addr6);
+		if (ret)
+			error(1, 0, "receiver address parse error: %s", addr);
+	}
+
+	if (cfg_payload_len > max_payload_len)
+		error(1, 0, "-l: payload exceeds max (%d)", max_payload_len);
+}
+
+int main(int argc, char **argv)
+{
+	const char *cfg_test = argv[argc - 1];
+	int i;
+
+	page_size = sysconf(_SC_PAGESIZE);
+	if (page_size < 0)
+		return 1;
+
+	if (posix_memalign((void **)&payload, page_size, SEND_SIZE))
+		return 1;
+
+	parse_opts(argc, argv);
+
+	for (i = 0; i < SEND_SIZE; i++)
+		payload[i] = 'a' + (i % 26);
+
+	if (cfg_server)
+		run_server();
+	else if (cfg_client)
+		run_client();
+
+	return 0;
+}
diff --git a/tools/testing/selftests/drivers/net/hw/iou-zcrx.py b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py
new file mode 100755
index 000000000000..712c806508b5
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py
@@ -0,0 +1,145 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import re
+from os import path
+from lib.py import ksft_run, ksft_exit, KsftSkipEx
+from lib.py import NetDrvEpEnv
+from lib.py import bkg, cmd, defer, ethtool, rand_port, wait_port_listen
+
+
+def _get_current_settings(cfg):
+    output = ethtool(f"-g {cfg.ifname}", json=True)[0]
+    return (output['rx'], output['hds-thresh'])
+
+
+def _get_combined_channels(cfg):
+    output = ethtool(f"-l {cfg.ifname}").stdout
+    values = re.findall(r'Combined:\s+(\d+)', output)
+    return int(values[1])
+
+
+def _create_rss_ctx(cfg, chan):
+    output = ethtool(f"-X {cfg.ifname} context new start {chan} equal 1").stdout
+    values = re.search(r'New RSS context is (\d+)', output).group(1)
+    ctx_id = int(values)
+    return (ctx_id, defer(ethtool, f"-X {cfg.ifname} delete context {ctx_id}"))
+
+
+def _set_flow_rule(cfg, port, chan):
+    output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port {port} action {chan}").stdout
+    values = re.search(r'ID (\d+)', output).group(1)
+    return int(values)
+
+
+def _set_flow_rule_rss(cfg, port, ctx_id):
+    output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port {port} context {ctx_id}").stdout
+    values = re.search(r'ID (\d+)', output).group(1)
+    return int(values)
+
+
+def test_zcrx(cfg) -> None:
+    cfg.require_ipver('6')
+
+    combined_chans = _get_combined_channels(cfg)
+    if combined_chans < 2:
+        raise KsftSkipEx('at least 2 combined channels required')
+    (rx_ring, hds_thresh) = _get_current_settings(cfg)
+    port = rand_port()
+
+    ethtool(f"-G {cfg.ifname} tcp-data-split on")
+    defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto")
+
+    ethtool(f"-G {cfg.ifname} hds-thresh 0")
+    defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}")
+
+    ethtool(f"-G {cfg.ifname} rx 64")
+    defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}")
+
+    ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    flow_rule_id = _set_flow_rule(cfg, port, combined_chans - 1)
+    defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}")
+
+    rx_cmd = f"{cfg.bin_local} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1}"
+    tx_cmd = f"{cfg.bin_remote} -c -h {cfg.addr_v['6']} -p {port} -l 12840"
+    with bkg(rx_cmd, exit_wait=True):
+        wait_port_listen(port, proto="tcp")
+        cmd(tx_cmd, host=cfg.remote)
+
+
+def test_zcrx_oneshot(cfg) -> None:
+    cfg.require_ipver('6')
+
+    combined_chans = _get_combined_channels(cfg)
+    if combined_chans < 2:
+        raise KsftSkipEx('at least 2 combined channels required')
+    (rx_ring, hds_thresh) = _get_current_settings(cfg)
+    port = rand_port()
+
+    ethtool(f"-G {cfg.ifname} tcp-data-split on")
+    defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto")
+
+    ethtool(f"-G {cfg.ifname} hds-thresh 0")
+    defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}")
+
+    ethtool(f"-G {cfg.ifname} rx 64")
+    defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}")
+
+    ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    flow_rule_id = _set_flow_rule(cfg, port, combined_chans - 1)
+    defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}")
+
+    rx_cmd = f"{cfg.bin_local} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1} -o 4"
+    tx_cmd = f"{cfg.bin_remote} -c -h {cfg.addr_v['6']} -p {port} -l 4096 -z 16384"
+    with bkg(rx_cmd, exit_wait=True):
+        wait_port_listen(port, proto="tcp")
+        cmd(tx_cmd, host=cfg.remote)
+
+
+def test_zcrx_rss(cfg) -> None:
+    cfg.require_ipver('6')
+
+    combined_chans = _get_combined_channels(cfg)
+    if combined_chans < 2:
+        raise KsftSkipEx('at least 2 combined channels required')
+    (rx_ring, hds_thresh) = _get_current_settings(cfg)
+    port = rand_port()
+
+    ethtool(f"-G {cfg.ifname} tcp-data-split on")
+    defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto")
+
+    ethtool(f"-G {cfg.ifname} hds-thresh 0")
+    defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}")
+
+    ethtool(f"-G {cfg.ifname} rx 64")
+    defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}")
+
+    ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    (ctx_id, delete_ctx) = _create_rss_ctx(cfg, combined_chans - 1)
+    flow_rule_id = _set_flow_rule_rss(cfg, port, ctx_id)
+    defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}")
+
+    rx_cmd = f"{cfg.bin_local} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1}"
+    tx_cmd = f"{cfg.bin_remote} -c -h {cfg.addr_v['6']} -p {port} -l 12840"
+    with bkg(rx_cmd, exit_wait=True):
+        wait_port_listen(port, proto="tcp")
+        cmd(tx_cmd, host=cfg.remote)
+
+
+def main() -> None:
+    with NetDrvEpEnv(__file__) as cfg:
+        cfg.bin_local = path.abspath(path.dirname(__file__) + "/../../../drivers/net/hw/iou-zcrx")
+        cfg.bin_remote = cfg.remote.deploy(cfg.bin_local)
+
+        ksft_run(globs=globals(), case_pfx={"test_"}, args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/hw/irq.py b/tools/testing/selftests/drivers/net/hw/irq.py
new file mode 100755
index 000000000000..0699d6a8b4e2
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/irq.py
@@ -0,0 +1,99 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+from lib.py import ksft_run, ksft_exit
+from lib.py import ksft_ge, ksft_eq
+from lib.py import KsftSkipEx
+from lib.py import ksft_disruptive
+from lib.py import EthtoolFamily, NetdevFamily
+from lib.py import NetDrvEnv
+from lib.py import cmd, ip, defer
+
+
+def read_affinity(irq) -> str:
+    with open(f'/proc/irq/{irq}/smp_affinity', 'r') as fp:
+        return fp.read().lstrip("0,").strip()
+
+
+def write_affinity(irq, what) -> str:
+    if what != read_affinity(irq):
+        with open(f'/proc/irq/{irq}/smp_affinity', 'w') as fp:
+            fp.write(what)
+
+
+def check_irqs_reported(cfg) -> None:
+    """ Check that device reports IRQs for NAPI instances """
+    napis = cfg.netnl.napi_get({"ifindex": cfg.ifindex}, dump=True)
+    irqs = sum(['irq' in x for x in napis])
+
+    ksft_ge(irqs, 1)
+    ksft_eq(irqs, len(napis))
+
+
+def _check_reconfig(cfg, reconfig_cb) -> None:
+    napis = cfg.netnl.napi_get({"ifindex": cfg.ifindex}, dump=True)
+    for n in reversed(napis):
+        if 'irq' in n:
+            break
+    else:
+        raise KsftSkipEx(f"Device has no NAPI with IRQ attribute (#napis: {len(napis)}")
+
+    old = read_affinity(n['irq'])
+    # pick an affinity that's not the current one
+    new = "3" if old != "3" else "5"
+    write_affinity(n['irq'], new)
+    defer(write_affinity, n['irq'], old)
+
+    reconfig_cb(cfg)
+
+    ksft_eq(read_affinity(n['irq']), new, comment="IRQ affinity changed after reconfig")
+
+
+def check_reconfig_queues(cfg) -> None:
+    def reconfig(cfg) -> None:
+        channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+        if channels['combined-count'] == 0:
+            rx_type = 'rx'
+        else:
+            rx_type = 'combined'
+        cur_queue_cnt = channels[f'{rx_type}-count']
+        max_queue_cnt = channels[f'{rx_type}-max']
+
+        cmd(f"ethtool -L {cfg.ifname} {rx_type} 1")
+        cmd(f"ethtool -L {cfg.ifname} {rx_type} {max_queue_cnt}")
+        cmd(f"ethtool -L {cfg.ifname} {rx_type} {cur_queue_cnt}")
+
+    _check_reconfig(cfg, reconfig)
+
+
+def check_reconfig_xdp(cfg) -> None:
+    def reconfig(cfg) -> None:
+        ip(f"link set dev %s xdp obj %s sec xdp" %
+           (cfg.ifname, cfg.net_lib_dir / "xdp_dummy.bpf.o"))
+        ip(f"link set dev %s xdp off" % cfg.ifname)
+
+    _check_reconfig(cfg, reconfig)
+
+
+@ksft_disruptive
+def check_down(cfg) -> None:
+    def reconfig(cfg) -> None:
+        ip("link set dev %s down" % cfg.ifname)
+        ip("link set dev %s up" % cfg.ifname)
+
+    _check_reconfig(cfg, reconfig)
+
+
+def main() -> None:
+    with NetDrvEnv(__file__, nsim_test=False) as cfg:
+        cfg.ethnl = EthtoolFamily()
+        cfg.netnl = NetdevFamily()
+
+        ksft_run([check_irqs_reported, check_reconfig_queues,
+                  check_reconfig_xdp, check_down],
+                 args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py
new file mode 100644
index 000000000000..766bfc4ad842
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py
@@ -0,0 +1,52 @@
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+Driver test environment (hardware-only tests).
+NetDrvEnv and NetDrvEpEnv are the main environment classes.
+Former is for local host only tests, latter creates / connects
+to a remote endpoint. See NIPA wiki for more information about
+running and writing driver tests.
+"""
+
+import sys
+from pathlib import Path
+
+KSFT_DIR = (Path(__file__).parent / "../../../../..").resolve()
+
+try:
+    sys.path.append(KSFT_DIR.as_posix())
+
+    # Import one by one to avoid pylint false positives
+    from net.lib.py import NetNS, NetNSEnter, NetdevSimDev
+    from net.lib.py import EthtoolFamily, NetdevFamily, NetshaperFamily, \
+        NlError, RtnlFamily, DevlinkFamily, PSPFamily
+    from net.lib.py import CmdExitFailure
+    from net.lib.py import bkg, cmd, bpftool, bpftrace, defer, ethtool, \
+        fd_read_timeout, ip, rand_port, wait_port_listen, wait_file
+    from net.lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx
+    from net.lib.py import ksft_disruptive, ksft_exit, ksft_pr, ksft_run, \
+        ksft_setup, ksft_variants, KsftNamedVariant
+    from net.lib.py import ksft_eq, ksft_ge, ksft_in, ksft_is, ksft_lt, \
+        ksft_ne, ksft_not_in, ksft_raises, ksft_true, ksft_gt, ksft_not_none
+    from drivers.net.lib.py import GenerateTraffic, Remote, Iperf3Runner
+    from drivers.net.lib.py import NetDrvEnv, NetDrvEpEnv
+
+    __all__ = ["NetNS", "NetNSEnter", "NetdevSimDev",
+               "EthtoolFamily", "NetdevFamily", "NetshaperFamily",
+               "NlError", "RtnlFamily", "DevlinkFamily", "PSPFamily",
+               "CmdExitFailure",
+               "bkg", "cmd", "bpftool", "bpftrace", "defer", "ethtool",
+               "fd_read_timeout", "ip", "rand_port",
+               "wait_port_listen", "wait_file",
+               "KsftSkipEx", "KsftFailEx", "KsftXfailEx",
+               "ksft_disruptive", "ksft_exit", "ksft_pr", "ksft_run",
+               "ksft_setup", "ksft_variants", "KsftNamedVariant",
+               "ksft_eq", "ksft_ge", "ksft_in", "ksft_is", "ksft_lt",
+               "ksft_ne", "ksft_not_in", "ksft_raises", "ksft_true", "ksft_gt",
+               "ksft_not_none", "ksft_not_none",
+               "NetDrvEnv", "NetDrvEpEnv", "GenerateTraffic", "Remote",
+               "Iperf3Runner"]
+except ModuleNotFoundError as e:
+    print("Failed importing `net` library from kernel sources")
+    print(str(e))
+    sys.exit(4)
diff --git a/tools/testing/selftests/net/forwarding/loopback.sh b/tools/testing/selftests/drivers/net/hw/loopback.sh
index 8f4057310b5b..5acc3ff820aa 100755
--- a/tools/testing/selftests/net/forwarding/loopback.sh
+++ b/tools/testing/selftests/drivers/net/hw/loopback.sh
@@ -6,8 +6,9 @@ ksft_skip=4
 
 ALL_TESTS="loopback_test"
 NUM_NETIFS=2
-source tc_common.sh
-source lib.sh
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/forwarding/tc_common.sh
+source "$lib_dir"/../../../net/forwarding/lib.sh
 
 h1_create()
 {
diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
new file mode 100644
index 000000000000..3288ed04ce08
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
@@ -0,0 +1,1524 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * tcpdevmem netcat. Works similarly to netcat but does device memory TCP
+ * instead of regular TCP. Uses udmabuf to mock a dmabuf provider.
+ *
+ * Usage:
+ *
+ *     On server:
+ *     ncdevmem -s <server IP> [-c <client IP>] -f eth1 -l -p 5201
+ *
+ *     On client:
+ *     echo -n "hello\nworld" | \
+ *		ncdevmem -s <server IP> [-c <client IP>] -p 5201 -f eth1
+ *
+ * Note this is compatible with regular netcat. i.e. the sender or receiver can
+ * be replaced with regular netcat to test the RX or TX path in isolation.
+ *
+ * Test data validation (devmem TCP on RX only):
+ *
+ *     On server:
+ *     ncdevmem -s <server IP> [-c <client IP>] -f eth1 -l -p 5201 -v 7
+ *
+ *     On client:
+ *     yes $(echo -e \\x01\\x02\\x03\\x04\\x05\\x06) | \
+ *             head -c 1G | \
+ *             nc <server IP> 5201 -p 5201
+ *
+ * Test data validation (devmem TCP on RX and TX, validation happens on RX):
+ *
+ *	On server:
+ *	ncdevmem -s <server IP> [-c <client IP>] -l -p 5201 -v 8 -f eth1
+ *
+ *	On client:
+ *	yes $(echo -e \\x01\\x02\\x03\\x04\\x05\\x06\\x07) | \
+ *		head -c 1M | \
+ *		ncdevmem -s <server IP> [-c <client IP>] -p 5201 -f eth1
+ */
+#define _GNU_SOURCE
+#define __EXPORTED_HEADERS__
+
+#include <linux/uio.h>
+#include <stdarg.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdbool.h>
+#include <string.h>
+#include <errno.h>
+#define __iovec_defined
+#include <fcntl.h>
+#include <malloc.h>
+#include <error.h>
+#include <poll.h>
+
+#include <arpa/inet.h>
+#include <sys/socket.h>
+#include <sys/mman.h>
+#include <sys/ioctl.h>
+#include <sys/syscall.h>
+#include <sys/time.h>
+
+#include <linux/memfd.h>
+#include <linux/dma-buf.h>
+#include <linux/errqueue.h>
+#include <linux/udmabuf.h>
+#include <linux/types.h>
+#include <linux/netlink.h>
+#include <linux/genetlink.h>
+#include <linux/netdev.h>
+#include <linux/ethtool_netlink.h>
+#include <time.h>
+#include <net/if.h>
+
+#include "netdev-user.h"
+#include "ethtool-user.h"
+#include <ynl.h>
+
+#define PAGE_SHIFT 12
+#define TEST_PREFIX "ncdevmem"
+#define NUM_PAGES 16000
+
+#ifndef MSG_SOCK_DEVMEM
+#define MSG_SOCK_DEVMEM 0x2000000
+#endif
+
+#define MAX_IOV 1024
+
+static size_t max_chunk;
+static char *server_ip;
+static char *client_ip;
+static char *port;
+static size_t do_validation;
+static int start_queue = -1;
+static int num_queues = -1;
+static char *ifname;
+static unsigned int ifindex;
+static unsigned int dmabuf_id;
+static uint32_t tx_dmabuf_id;
+static int waittime_ms = 500;
+
+/* System state loaded by current_config_load() */
+#define MAX_FLOWS	8
+static int ntuple_ids[MAX_FLOWS] = { -1, -1, -1, -1, -1, -1, -1, -1, };
+
+struct memory_buffer {
+	int fd;
+	size_t size;
+
+	int devfd;
+	int memfd;
+	char *buf_mem;
+};
+
+struct memory_provider {
+	struct memory_buffer *(*alloc)(size_t size);
+	void (*free)(struct memory_buffer *ctx);
+	void (*memcpy_to_device)(struct memory_buffer *dst, size_t off,
+				 void *src, int n);
+	void (*memcpy_from_device)(void *dst, struct memory_buffer *src,
+				   size_t off, int n);
+};
+
+static void pr_err(const char *fmt, ...)
+{
+	va_list args;
+
+	fprintf(stderr, "%s: ", TEST_PREFIX);
+
+	va_start(args, fmt);
+	vfprintf(stderr, fmt, args);
+	va_end(args);
+
+	if (errno != 0)
+		fprintf(stderr, ": %s", strerror(errno));
+	fprintf(stderr, "\n");
+}
+
+static struct memory_buffer *udmabuf_alloc(size_t size)
+{
+	struct udmabuf_create create;
+	struct memory_buffer *ctx;
+	int ret;
+
+	ctx = malloc(sizeof(*ctx));
+	if (!ctx)
+		return NULL;
+
+	ctx->size = size;
+
+	ctx->devfd = open("/dev/udmabuf", O_RDWR);
+	if (ctx->devfd < 0) {
+		pr_err("[skip,no-udmabuf: Unable to access DMA buffer device file]");
+		goto err_free_ctx;
+	}
+
+	ctx->memfd = memfd_create("udmabuf-test", MFD_ALLOW_SEALING);
+	if (ctx->memfd < 0) {
+		pr_err("[skip,no-memfd]");
+		goto err_close_dev;
+	}
+
+	ret = fcntl(ctx->memfd, F_ADD_SEALS, F_SEAL_SHRINK);
+	if (ret < 0) {
+		pr_err("[skip,fcntl-add-seals]");
+		goto err_close_memfd;
+	}
+
+	ret = ftruncate(ctx->memfd, size);
+	if (ret == -1) {
+		pr_err("[FAIL,memfd-truncate]");
+		goto err_close_memfd;
+	}
+
+	memset(&create, 0, sizeof(create));
+
+	create.memfd = ctx->memfd;
+	create.offset = 0;
+	create.size = size;
+	ctx->fd = ioctl(ctx->devfd, UDMABUF_CREATE, &create);
+	if (ctx->fd < 0) {
+		pr_err("[FAIL, create udmabuf]");
+		goto err_close_fd;
+	}
+
+	ctx->buf_mem = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_SHARED,
+			    ctx->fd, 0);
+	if (ctx->buf_mem == MAP_FAILED) {
+		pr_err("[FAIL, map udmabuf]");
+		goto err_close_fd;
+	}
+
+	return ctx;
+
+err_close_fd:
+	close(ctx->fd);
+err_close_memfd:
+	close(ctx->memfd);
+err_close_dev:
+	close(ctx->devfd);
+err_free_ctx:
+	free(ctx);
+	return NULL;
+}
+
+static void udmabuf_free(struct memory_buffer *ctx)
+{
+	munmap(ctx->buf_mem, ctx->size);
+	close(ctx->fd);
+	close(ctx->memfd);
+	close(ctx->devfd);
+	free(ctx);
+}
+
+static void udmabuf_memcpy_to_device(struct memory_buffer *dst, size_t off,
+				     void *src, int n)
+{
+	struct dma_buf_sync sync = {};
+
+	sync.flags = DMA_BUF_SYNC_START | DMA_BUF_SYNC_WRITE;
+	ioctl(dst->fd, DMA_BUF_IOCTL_SYNC, &sync);
+
+	memcpy(dst->buf_mem + off, src, n);
+
+	sync.flags = DMA_BUF_SYNC_END | DMA_BUF_SYNC_WRITE;
+	ioctl(dst->fd, DMA_BUF_IOCTL_SYNC, &sync);
+}
+
+static void udmabuf_memcpy_from_device(void *dst, struct memory_buffer *src,
+				       size_t off, int n)
+{
+	struct dma_buf_sync sync = {};
+
+	sync.flags = DMA_BUF_SYNC_START;
+	ioctl(src->fd, DMA_BUF_IOCTL_SYNC, &sync);
+
+	memcpy(dst, src->buf_mem + off, n);
+
+	sync.flags = DMA_BUF_SYNC_END;
+	ioctl(src->fd, DMA_BUF_IOCTL_SYNC, &sync);
+}
+
+static struct memory_provider udmabuf_memory_provider = {
+	.alloc = udmabuf_alloc,
+	.free = udmabuf_free,
+	.memcpy_to_device = udmabuf_memcpy_to_device,
+	.memcpy_from_device = udmabuf_memcpy_from_device,
+};
+
+static struct memory_provider *provider = &udmabuf_memory_provider;
+
+static void print_nonzero_bytes(void *ptr, size_t size)
+{
+	unsigned char *p = ptr;
+	unsigned int i;
+
+	for (i = 0; i < size; i++)
+		putchar(p[i]);
+}
+
+int validate_buffer(void *line, size_t size)
+{
+	static unsigned char seed = 1;
+	unsigned char *ptr = line;
+	unsigned char expected;
+	static int errors;
+	size_t i;
+
+	for (i = 0; i < size; i++) {
+		expected = seed ? seed : '\n';
+		if (ptr[i] != expected) {
+			fprintf(stderr,
+				"Failed validation: expected=%u, actual=%u, index=%lu\n",
+				expected, ptr[i], i);
+			errors++;
+			if (errors > 20) {
+				pr_err("validation failed");
+				return -1;
+			}
+		}
+		seed++;
+		if (seed == do_validation)
+			seed = 0;
+	}
+
+	fprintf(stdout, "Validated buffer\n");
+	return 0;
+}
+
+static int
+__run_command(char *out, size_t outlen, const char *cmd, va_list args)
+{
+	char command[256];
+	FILE *fp;
+
+	vsnprintf(command, sizeof(command), cmd, args);
+
+	fprintf(stderr, "Running: %s\n", command);
+	fp = popen(command, "r");
+	if (!fp)
+		return -1;
+	if (out) {
+		size_t len;
+
+		if (!fgets(out, outlen, fp))
+			return -1;
+
+		/* Remove trailing newline if present */
+		len = strlen(out);
+		if (len && out[len - 1] == '\n')
+			out[len - 1] = '\0';
+	}
+	return pclose(fp);
+}
+
+static int run_command(const char *cmd, ...)
+{
+	va_list args;
+	int ret;
+
+	va_start(args, cmd);
+	ret = __run_command(NULL, 0, cmd, args);
+	va_end(args);
+
+	return ret;
+}
+
+static int ethtool_add_flow(const char *format, ...)
+{
+	char local_output[256], cmd[256];
+	const char *id_start;
+	int flow_idx, ret;
+	char *endptr;
+	long flow_id;
+	va_list args;
+
+	for (flow_idx = 0; flow_idx < MAX_FLOWS; flow_idx++)
+		if (ntuple_ids[flow_idx] == -1)
+			break;
+	if (flow_idx == MAX_FLOWS) {
+		fprintf(stderr, "Error: too many flows\n");
+		return -1;
+	}
+
+	snprintf(cmd, sizeof(cmd), "ethtool -N %s %s", ifname, format);
+
+	va_start(args, format);
+	ret = __run_command(local_output, sizeof(local_output), cmd, args);
+	va_end(args);
+
+	if (ret != 0)
+		return ret;
+
+	/* Extract the ID from the output */
+	id_start = strstr(local_output, "Added rule with ID ");
+	if (!id_start)
+		return -1;
+	id_start += strlen("Added rule with ID ");
+
+	flow_id = strtol(id_start, &endptr, 10);
+	if (endptr == id_start || flow_id < 0 || flow_id > INT_MAX)
+		return -1;
+
+	fprintf(stderr, "Added flow rule with ID %ld\n", flow_id);
+	ntuple_ids[flow_idx] = flow_id;
+	return flow_id;
+}
+
+static int rxq_num(int ifindex)
+{
+	struct ethtool_channels_get_req *req;
+	struct ethtool_channels_get_rsp *rsp;
+	struct ynl_error yerr;
+	struct ynl_sock *ys;
+	int num = -1;
+
+	ys = ynl_sock_create(&ynl_ethtool_family, &yerr);
+	if (!ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return -1;
+	}
+
+	req = ethtool_channels_get_req_alloc();
+	ethtool_channels_get_req_set_header_dev_index(req, ifindex);
+	rsp = ethtool_channels_get(ys, req);
+	if (rsp)
+		num = rsp->rx_count + rsp->combined_count;
+	ethtool_channels_get_req_free(req);
+	ethtool_channels_get_rsp_free(rsp);
+
+	ynl_sock_destroy(ys);
+
+	return num;
+}
+
+static void reset_flow_steering(void)
+{
+	int i;
+
+	for (i = 0; i < MAX_FLOWS; i++) {
+		if (ntuple_ids[i] == -1)
+			continue;
+		run_command("ethtool -N %s delete %d",
+			    ifname, ntuple_ids[i]);
+		ntuple_ids[i] = -1;
+	}
+}
+
+static const char *tcp_data_split_str(int val)
+{
+	switch (val) {
+	case 0:
+		return "off";
+	case 1:
+		return "auto";
+	case 2:
+		return "on";
+	default:
+		return "?";
+	}
+}
+
+static struct ethtool_rings_get_rsp *get_ring_config(void)
+{
+	struct ethtool_rings_get_req *get_req;
+	struct ethtool_rings_get_rsp *get_rsp;
+	struct ynl_error yerr;
+	struct ynl_sock *ys;
+
+	ys = ynl_sock_create(&ynl_ethtool_family, &yerr);
+	if (!ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return NULL;
+	}
+
+	get_req = ethtool_rings_get_req_alloc();
+	ethtool_rings_get_req_set_header_dev_index(get_req, ifindex);
+	get_rsp = ethtool_rings_get(ys, get_req);
+	ethtool_rings_get_req_free(get_req);
+
+	ynl_sock_destroy(ys);
+
+	return get_rsp;
+}
+
+static void restore_ring_config(const struct ethtool_rings_get_rsp *config)
+{
+	struct ethtool_rings_get_req *get_req;
+	struct ethtool_rings_get_rsp *get_rsp;
+	struct ethtool_rings_set_req *req;
+	struct ynl_error yerr;
+	struct ynl_sock *ys;
+	int ret;
+
+	if (!config)
+		return;
+
+	ys = ynl_sock_create(&ynl_ethtool_family, &yerr);
+	if (!ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return;
+	}
+
+	req = ethtool_rings_set_req_alloc();
+	ethtool_rings_set_req_set_header_dev_index(req, ifindex);
+	ethtool_rings_set_req_set_tcp_data_split(req,
+						ETHTOOL_TCP_DATA_SPLIT_UNKNOWN);
+	if (config->_present.hds_thresh)
+		ethtool_rings_set_req_set_hds_thresh(req, config->hds_thresh);
+
+	ret = ethtool_rings_set(ys, req);
+	if (ret < 0)
+		fprintf(stderr, "YNL restoring HDS cfg: %s\n", ys->err.msg);
+
+	get_req = ethtool_rings_get_req_alloc();
+	ethtool_rings_get_req_set_header_dev_index(get_req, ifindex);
+	get_rsp = ethtool_rings_get(ys, get_req);
+	ethtool_rings_get_req_free(get_req);
+
+	/* use explicit value if UKNOWN didn't give us the previous */
+	if (get_rsp->tcp_data_split != config->tcp_data_split) {
+		ethtool_rings_set_req_set_tcp_data_split(req,
+							config->tcp_data_split);
+		ret = ethtool_rings_set(ys, req);
+		if (ret < 0)
+			fprintf(stderr, "YNL restoring expl HDS cfg: %s\n",
+				ys->err.msg);
+	}
+
+	ethtool_rings_get_rsp_free(get_rsp);
+	ethtool_rings_set_req_free(req);
+
+	ynl_sock_destroy(ys);
+}
+
+static int
+configure_headersplit(const struct ethtool_rings_get_rsp *old, bool on)
+{
+	struct ethtool_rings_get_req *get_req;
+	struct ethtool_rings_get_rsp *get_rsp;
+	struct ethtool_rings_set_req *req;
+	struct ynl_error yerr;
+	struct ynl_sock *ys;
+	int ret;
+
+	ys = ynl_sock_create(&ynl_ethtool_family, &yerr);
+	if (!ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return -1;
+	}
+
+	req = ethtool_rings_set_req_alloc();
+	ethtool_rings_set_req_set_header_dev_index(req, ifindex);
+	if (on) {
+		ethtool_rings_set_req_set_tcp_data_split(req,
+						ETHTOOL_TCP_DATA_SPLIT_ENABLED);
+		if (old->_present.hds_thresh)
+			ethtool_rings_set_req_set_hds_thresh(req, 0);
+	} else {
+		ethtool_rings_set_req_set_tcp_data_split(req,
+						ETHTOOL_TCP_DATA_SPLIT_UNKNOWN);
+	}
+	ret = ethtool_rings_set(ys, req);
+	if (ret < 0)
+		fprintf(stderr, "YNL failed: %s\n", ys->err.msg);
+	ethtool_rings_set_req_free(req);
+
+	if (ret == 0) {
+		get_req = ethtool_rings_get_req_alloc();
+		ethtool_rings_get_req_set_header_dev_index(get_req, ifindex);
+		get_rsp = ethtool_rings_get(ys, get_req);
+		ethtool_rings_get_req_free(get_req);
+		if (get_rsp)
+			fprintf(stderr, "TCP header split: %s\n",
+				tcp_data_split_str(get_rsp->tcp_data_split));
+		ethtool_rings_get_rsp_free(get_rsp);
+	}
+
+	ynl_sock_destroy(ys);
+
+	return ret;
+}
+
+static int configure_rss(void)
+{
+	return run_command("ethtool -X %s equal %d >&2", ifname, start_queue);
+}
+
+static void reset_rss(void)
+{
+	run_command("ethtool -X %s default >&2", ifname, start_queue);
+}
+
+static int check_changing_channels(unsigned int rx, unsigned int tx)
+{
+	struct ethtool_channels_get_req *gchan;
+	struct ethtool_channels_set_req *schan;
+	struct ethtool_channels_get_rsp *chan;
+	struct ynl_error yerr;
+	struct ynl_sock *ys;
+	int ret;
+
+	fprintf(stderr, "setting channel count rx:%u tx:%u\n", rx, tx);
+
+	ys = ynl_sock_create(&ynl_ethtool_family, &yerr);
+	if (!ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return -1;
+	}
+
+	gchan = ethtool_channels_get_req_alloc();
+	if (!gchan) {
+		ret = -1;
+		goto exit_close_sock;
+	}
+
+	ethtool_channels_get_req_set_header_dev_index(gchan, ifindex);
+	chan = ethtool_channels_get(ys, gchan);
+	ethtool_channels_get_req_free(gchan);
+	if (!chan) {
+		fprintf(stderr, "YNL get channels: %s\n", ys->err.msg);
+		ret = -1;
+		goto exit_close_sock;
+	}
+
+	schan =	ethtool_channels_set_req_alloc();
+	if (!schan) {
+		ret = -1;
+		goto exit_free_chan;
+	}
+
+	ethtool_channels_set_req_set_header_dev_index(schan, ifindex);
+
+	if (chan->_present.combined_count) {
+		if (chan->_present.rx_count || chan->_present.tx_count) {
+			ethtool_channels_set_req_set_rx_count(schan, 0);
+			ethtool_channels_set_req_set_tx_count(schan, 0);
+		}
+
+		if (rx == tx) {
+			ethtool_channels_set_req_set_combined_count(schan, rx);
+		} else if (rx > tx) {
+			ethtool_channels_set_req_set_combined_count(schan, tx);
+			ethtool_channels_set_req_set_rx_count(schan, rx - tx);
+		} else {
+			ethtool_channels_set_req_set_combined_count(schan, rx);
+			ethtool_channels_set_req_set_tx_count(schan, tx - rx);
+		}
+
+	} else if (chan->_present.rx_count) {
+		ethtool_channels_set_req_set_rx_count(schan, rx);
+		ethtool_channels_set_req_set_tx_count(schan, tx);
+	} else {
+		fprintf(stderr, "Error: device has neither combined nor rx channels\n");
+		ret = -1;
+		goto exit_free_schan;
+	}
+
+	ret = ethtool_channels_set(ys, schan);
+	if (ret) {
+		fprintf(stderr, "YNL set channels: %s\n", ys->err.msg);
+	} else {
+		/* We were expecting a failure, go back to previous settings */
+		ethtool_channels_set_req_set_combined_count(schan,
+							    chan->combined_count);
+		ethtool_channels_set_req_set_rx_count(schan, chan->rx_count);
+		ethtool_channels_set_req_set_tx_count(schan, chan->tx_count);
+
+		ret = ethtool_channels_set(ys, schan);
+		if (ret)
+			fprintf(stderr, "YNL un-setting channels: %s\n",
+				ys->err.msg);
+	}
+
+exit_free_schan:
+	ethtool_channels_set_req_free(schan);
+exit_free_chan:
+	ethtool_channels_get_rsp_free(chan);
+exit_close_sock:
+	ynl_sock_destroy(ys);
+
+	return ret;
+}
+
+static int configure_flow_steering(struct sockaddr_in6 *server_sin)
+{
+	const char *type = "tcp6";
+	const char *server_addr;
+	char buf[40];
+	int flow_id;
+
+	inet_ntop(AF_INET6, &server_sin->sin6_addr, buf, sizeof(buf));
+	server_addr = buf;
+
+	if (IN6_IS_ADDR_V4MAPPED(&server_sin->sin6_addr)) {
+		type = "tcp4";
+		server_addr = strrchr(server_addr, ':') + 1;
+	}
+
+	/* Try configure 5-tuple */
+	flow_id = ethtool_add_flow("flow-type %s %s %s dst-ip %s %s %s dst-port %s queue %d",
+				   type,
+				   client_ip ? "src-ip" : "",
+				   client_ip ?: "",
+				   server_addr,
+				   client_ip ? "src-port" : "",
+				   client_ip ? port : "",
+				   port, start_queue);
+	if (flow_id < 0) {
+		/* If that fails, try configure 3-tuple */
+		flow_id = ethtool_add_flow("flow-type %s dst-ip %s dst-port %s queue %d",
+					   type, server_addr, port, start_queue);
+		if (flow_id < 0)
+			/* If that fails, return error */
+			return -1;
+	}
+
+	return 0;
+}
+
+static int bind_rx_queue(unsigned int ifindex, unsigned int dmabuf_fd,
+			 struct netdev_queue_id *queues,
+			 unsigned int n_queue_index, struct ynl_sock **ys)
+{
+	struct netdev_bind_rx_req *req = NULL;
+	struct netdev_bind_rx_rsp *rsp = NULL;
+	struct ynl_error yerr;
+
+	*ys = ynl_sock_create(&ynl_netdev_family, &yerr);
+	if (!*ys) {
+		netdev_queue_id_free(queues);
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return -1;
+	}
+
+	req = netdev_bind_rx_req_alloc();
+	netdev_bind_rx_req_set_ifindex(req, ifindex);
+	netdev_bind_rx_req_set_fd(req, dmabuf_fd);
+	__netdev_bind_rx_req_set_queues(req, queues, n_queue_index);
+
+	rsp = netdev_bind_rx(*ys, req);
+	if (!rsp) {
+		perror("netdev_bind_rx");
+		goto err_close;
+	}
+
+	if (!rsp->_present.id) {
+		perror("id not present");
+		goto err_close;
+	}
+
+	fprintf(stderr, "got dmabuf id=%d\n", rsp->id);
+	dmabuf_id = rsp->id;
+
+	netdev_bind_rx_req_free(req);
+	netdev_bind_rx_rsp_free(rsp);
+
+	return 0;
+
+err_close:
+	fprintf(stderr, "YNL failed: %s\n", (*ys)->err.msg);
+	netdev_bind_rx_req_free(req);
+	ynl_sock_destroy(*ys);
+	return -1;
+}
+
+static int bind_tx_queue(unsigned int ifindex, unsigned int dmabuf_fd,
+			 struct ynl_sock **ys)
+{
+	struct netdev_bind_tx_req *req = NULL;
+	struct netdev_bind_tx_rsp *rsp = NULL;
+	struct ynl_error yerr;
+
+	*ys = ynl_sock_create(&ynl_netdev_family, &yerr);
+	if (!*ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return -1;
+	}
+
+	req = netdev_bind_tx_req_alloc();
+	netdev_bind_tx_req_set_ifindex(req, ifindex);
+	netdev_bind_tx_req_set_fd(req, dmabuf_fd);
+
+	rsp = netdev_bind_tx(*ys, req);
+	if (!rsp) {
+		perror("netdev_bind_tx");
+		goto err_close;
+	}
+
+	if (!rsp->_present.id) {
+		perror("id not present");
+		goto err_close;
+	}
+
+	fprintf(stderr, "got tx dmabuf id=%d\n", rsp->id);
+	tx_dmabuf_id = rsp->id;
+
+	netdev_bind_tx_req_free(req);
+	netdev_bind_tx_rsp_free(rsp);
+
+	return 0;
+
+err_close:
+	fprintf(stderr, "YNL failed: %s\n", (*ys)->err.msg);
+	netdev_bind_tx_req_free(req);
+	ynl_sock_destroy(*ys);
+	return -1;
+}
+
+static int enable_reuseaddr(int fd)
+{
+	int opt = 1;
+	int ret;
+
+	ret = setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &opt, sizeof(opt));
+	if (ret) {
+		pr_err("SO_REUSEPORT failed");
+		return -1;
+	}
+
+	ret = setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt));
+	if (ret) {
+		pr_err("SO_REUSEADDR failed");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int parse_address(const char *str, int port, struct sockaddr_in6 *sin6)
+{
+	int ret;
+
+	sin6->sin6_family = AF_INET6;
+	sin6->sin6_port = htons(port);
+
+	ret = inet_pton(sin6->sin6_family, str, &sin6->sin6_addr);
+	if (ret != 1) {
+		/* fallback to plain IPv4 */
+		ret = inet_pton(AF_INET, str, &sin6->sin6_addr.s6_addr32[3]);
+		if (ret != 1)
+			return -1;
+
+		/* add ::ffff prefix */
+		sin6->sin6_addr.s6_addr32[0] = 0;
+		sin6->sin6_addr.s6_addr32[1] = 0;
+		sin6->sin6_addr.s6_addr16[4] = 0;
+		sin6->sin6_addr.s6_addr16[5] = 0xffff;
+	}
+
+	return 0;
+}
+
+static struct netdev_queue_id *create_queues(void)
+{
+	struct netdev_queue_id *queues;
+	size_t i = 0;
+
+	queues = netdev_queue_id_alloc(num_queues);
+	for (i = 0; i < num_queues; i++) {
+		netdev_queue_id_set_type(&queues[i], NETDEV_QUEUE_TYPE_RX);
+		netdev_queue_id_set_id(&queues[i], start_queue + i);
+	}
+
+	return queues;
+}
+
+static int do_server(struct memory_buffer *mem)
+{
+	struct ethtool_rings_get_rsp *ring_config;
+	char ctrl_data[sizeof(int) * 20000];
+	size_t non_page_aligned_frags = 0;
+	struct sockaddr_in6 client_addr;
+	struct sockaddr_in6 server_sin;
+	size_t page_aligned_frags = 0;
+	size_t total_received = 0;
+	socklen_t client_addr_len;
+	bool is_devmem = false;
+	char *tmp_mem = NULL;
+	struct ynl_sock *ys;
+	char iobuf[819200];
+	int ret, err = -1;
+	char buffer[256];
+	int socket_fd;
+	int client_fd;
+
+	ret = parse_address(server_ip, atoi(port), &server_sin);
+	if (ret < 0) {
+		pr_err("parse server address");
+		return -1;
+	}
+
+	ring_config = get_ring_config();
+	if (!ring_config) {
+		pr_err("Failed to get current ring configuration");
+		return -1;
+	}
+
+	if (configure_headersplit(ring_config, 1)) {
+		pr_err("Failed to enable TCP header split");
+		goto err_free_ring_config;
+	}
+
+	/* Configure RSS to divert all traffic from our devmem queues */
+	if (configure_rss()) {
+		pr_err("Failed to configure rss");
+		goto err_reset_headersplit;
+	}
+
+	/* Flow steer our devmem flows to start_queue */
+	if (configure_flow_steering(&server_sin)) {
+		pr_err("Failed to configure flow steering");
+		goto err_reset_rss;
+	}
+
+	if (bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys)) {
+		pr_err("Failed to bind");
+		goto err_reset_flow_steering;
+	}
+
+	tmp_mem = malloc(mem->size);
+	if (!tmp_mem)
+		goto err_unbind;
+
+	socket_fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (socket_fd < 0) {
+		pr_err("Failed to create socket");
+		goto err_free_tmp;
+	}
+
+	if (enable_reuseaddr(socket_fd))
+		goto err_close_socket;
+
+	fprintf(stderr, "binding to address %s:%d\n", server_ip,
+		ntohs(server_sin.sin6_port));
+
+	ret = bind(socket_fd, &server_sin, sizeof(server_sin));
+	if (ret) {
+		pr_err("Failed to bind");
+		goto err_close_socket;
+	}
+
+	ret = listen(socket_fd, 1);
+	if (ret) {
+		pr_err("Failed to listen");
+		goto err_close_socket;
+	}
+
+	client_addr_len = sizeof(client_addr);
+
+	inet_ntop(AF_INET6, &server_sin.sin6_addr, buffer,
+		  sizeof(buffer));
+	fprintf(stderr, "Waiting or connection on %s:%d\n", buffer,
+		ntohs(server_sin.sin6_port));
+	client_fd = accept(socket_fd, &client_addr, &client_addr_len);
+	if (client_fd < 0) {
+		pr_err("Failed to accept");
+		goto err_close_socket;
+	}
+
+	inet_ntop(AF_INET6, &client_addr.sin6_addr, buffer,
+		  sizeof(buffer));
+	fprintf(stderr, "Got connection from %s:%d\n", buffer,
+		ntohs(client_addr.sin6_port));
+
+	while (1) {
+		struct iovec iov = { .iov_base = iobuf,
+				     .iov_len = sizeof(iobuf) };
+		struct dmabuf_cmsg *dmabuf_cmsg = NULL;
+		struct cmsghdr *cm = NULL;
+		struct msghdr msg = { 0 };
+		struct dmabuf_token token;
+		ssize_t ret;
+
+		is_devmem = false;
+
+		msg.msg_iov = &iov;
+		msg.msg_iovlen = 1;
+		msg.msg_control = ctrl_data;
+		msg.msg_controllen = sizeof(ctrl_data);
+		ret = recvmsg(client_fd, &msg, MSG_SOCK_DEVMEM);
+		fprintf(stderr, "recvmsg ret=%ld\n", ret);
+		if (ret < 0 && (errno == EAGAIN || errno == EWOULDBLOCK))
+			continue;
+		if (ret < 0) {
+			perror("recvmsg");
+			if (errno == EFAULT) {
+				pr_err("received EFAULT, won't recover");
+				goto err_close_client;
+			}
+			continue;
+		}
+		if (ret == 0) {
+			errno = 0;
+			pr_err("client exited");
+			goto cleanup;
+		}
+
+		for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) {
+			if (cm->cmsg_level != SOL_SOCKET ||
+			    (cm->cmsg_type != SCM_DEVMEM_DMABUF &&
+			     cm->cmsg_type != SCM_DEVMEM_LINEAR)) {
+				fprintf(stderr, "skipping non-devmem cmsg\n");
+				continue;
+			}
+
+			dmabuf_cmsg = (struct dmabuf_cmsg *)CMSG_DATA(cm);
+			is_devmem = true;
+
+			if (cm->cmsg_type == SCM_DEVMEM_LINEAR) {
+				/* TODO: process data copied from skb's linear
+				 * buffer.
+				 */
+				fprintf(stderr,
+					"SCM_DEVMEM_LINEAR. dmabuf_cmsg->frag_size=%u\n",
+					dmabuf_cmsg->frag_size);
+
+				continue;
+			}
+
+			token.token_start = dmabuf_cmsg->frag_token;
+			token.token_count = 1;
+
+			total_received += dmabuf_cmsg->frag_size;
+			fprintf(stderr,
+				"received frag_page=%llu, in_page_offset=%llu, frag_offset=%llu, frag_size=%u, token=%u, total_received=%lu, dmabuf_id=%u\n",
+				dmabuf_cmsg->frag_offset >> PAGE_SHIFT,
+				dmabuf_cmsg->frag_offset % getpagesize(),
+				dmabuf_cmsg->frag_offset,
+				dmabuf_cmsg->frag_size, dmabuf_cmsg->frag_token,
+				total_received, dmabuf_cmsg->dmabuf_id);
+
+			if (dmabuf_cmsg->dmabuf_id != dmabuf_id) {
+				pr_err("received on wrong dmabuf_id: flow steering error");
+				goto err_close_client;
+			}
+
+			if (dmabuf_cmsg->frag_size % getpagesize())
+				non_page_aligned_frags++;
+			else
+				page_aligned_frags++;
+
+			provider->memcpy_from_device(tmp_mem, mem,
+						     dmabuf_cmsg->frag_offset,
+						     dmabuf_cmsg->frag_size);
+
+			if (do_validation) {
+				if (validate_buffer(tmp_mem,
+						    dmabuf_cmsg->frag_size))
+					goto err_close_client;
+			} else {
+				print_nonzero_bytes(tmp_mem,
+						    dmabuf_cmsg->frag_size);
+			}
+
+			ret = setsockopt(client_fd, SOL_SOCKET,
+					 SO_DEVMEM_DONTNEED, &token,
+					 sizeof(token));
+			if (ret != 1) {
+				pr_err("SO_DEVMEM_DONTNEED not enough tokens");
+				goto err_close_client;
+			}
+		}
+		if (!is_devmem) {
+			pr_err("flow steering error");
+			goto err_close_client;
+		}
+
+		fprintf(stderr, "total_received=%lu\n", total_received);
+	}
+
+	fprintf(stderr, "%s: ok\n", TEST_PREFIX);
+
+	fprintf(stderr, "page_aligned_frags=%lu, non_page_aligned_frags=%lu\n",
+		page_aligned_frags, non_page_aligned_frags);
+
+cleanup:
+	err = 0;
+
+err_close_client:
+	close(client_fd);
+err_close_socket:
+	close(socket_fd);
+err_free_tmp:
+	free(tmp_mem);
+err_unbind:
+	ynl_sock_destroy(ys);
+err_reset_flow_steering:
+	reset_flow_steering();
+err_reset_rss:
+	reset_rss();
+err_reset_headersplit:
+	restore_ring_config(ring_config);
+err_free_ring_config:
+	ethtool_rings_get_rsp_free(ring_config);
+	return err;
+}
+
+int run_devmem_tests(void)
+{
+	struct ethtool_rings_get_rsp *ring_config;
+	struct netdev_queue_id *queues;
+	struct memory_buffer *mem;
+	struct ynl_sock *ys;
+	int err = -1;
+
+	mem = provider->alloc(getpagesize() * NUM_PAGES);
+	if (!mem) {
+		pr_err("Failed to allocate memory buffer");
+		return -1;
+	}
+
+	ring_config = get_ring_config();
+	if (!ring_config) {
+		pr_err("Failed to get current ring configuration");
+		goto err_free_mem;
+	}
+
+	/* Configure RSS to divert all traffic from our devmem queues */
+	if (configure_rss()) {
+		pr_err("rss error");
+		goto err_free_ring_config;
+	}
+
+	if (configure_headersplit(ring_config, 1)) {
+		pr_err("Failed to configure header split");
+		goto err_reset_rss;
+	}
+
+	queues = netdev_queue_id_alloc(num_queues);
+	if (!queues) {
+		pr_err("Failed to allocate empty queues array");
+		goto err_reset_headersplit;
+	}
+
+	if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys)) {
+		pr_err("Binding empty queues array should have failed");
+		goto err_unbind;
+	}
+
+	if (configure_headersplit(ring_config, 0)) {
+		pr_err("Failed to configure header split");
+		goto err_reset_headersplit;
+	}
+
+	queues = create_queues();
+	if (!queues) {
+		pr_err("Failed to create queues");
+		goto err_reset_headersplit;
+	}
+
+	if (!bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys)) {
+		pr_err("Configure dmabuf with header split off should have failed");
+		goto err_unbind;
+	}
+
+	if (configure_headersplit(ring_config, 1)) {
+		pr_err("Failed to configure header split");
+		goto err_reset_headersplit;
+	}
+
+	queues = create_queues();
+	if (!queues) {
+		pr_err("Failed to create queues");
+		goto err_reset_headersplit;
+	}
+
+	if (bind_rx_queue(ifindex, mem->fd, queues, num_queues, &ys)) {
+		pr_err("Failed to bind");
+		goto err_reset_headersplit;
+	}
+
+	/* Deactivating a bound queue should not be legal */
+	if (!check_changing_channels(num_queues, num_queues)) {
+		pr_err("Deactivating a bound queue should be illegal");
+		goto err_unbind;
+	}
+
+	err = 0;
+	goto err_unbind;
+
+err_unbind:
+	ynl_sock_destroy(ys);
+err_reset_headersplit:
+	restore_ring_config(ring_config);
+err_reset_rss:
+	reset_rss();
+err_free_ring_config:
+	ethtool_rings_get_rsp_free(ring_config);
+err_free_mem:
+	provider->free(mem);
+	return err;
+}
+
+static uint64_t gettimeofday_ms(void)
+{
+	struct timeval tv;
+
+	gettimeofday(&tv, NULL);
+	return (tv.tv_sec * 1000ULL) + (tv.tv_usec / 1000ULL);
+}
+
+static int do_poll(int fd)
+{
+	struct pollfd pfd;
+	int ret;
+
+	pfd.revents = 0;
+	pfd.fd = fd;
+
+	ret = poll(&pfd, 1, waittime_ms);
+	if (ret == -1) {
+		pr_err("poll");
+		return -1;
+	}
+
+	return ret && (pfd.revents & POLLERR);
+}
+
+static int wait_compl(int fd)
+{
+	int64_t tstop = gettimeofday_ms() + waittime_ms;
+	char control[CMSG_SPACE(100)] = {};
+	struct sock_extended_err *serr;
+	struct msghdr msg = {};
+	struct cmsghdr *cm;
+	__u32 hi, lo;
+	int ret;
+
+	msg.msg_control = control;
+	msg.msg_controllen = sizeof(control);
+
+	while (gettimeofday_ms() < tstop) {
+		ret = do_poll(fd);
+		if (ret < 0)
+			return ret;
+		if (!ret)
+			continue;
+
+		ret = recvmsg(fd, &msg, MSG_ERRQUEUE);
+		if (ret < 0) {
+			if (errno == EAGAIN)
+				continue;
+			pr_err("recvmsg(MSG_ERRQUEUE)");
+			return -1;
+		}
+		if (msg.msg_flags & MSG_CTRUNC) {
+			pr_err("MSG_CTRUNC");
+			return -1;
+		}
+
+		for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) {
+			if (cm->cmsg_level != SOL_IP &&
+			    cm->cmsg_level != SOL_IPV6)
+				continue;
+			if (cm->cmsg_level == SOL_IP &&
+			    cm->cmsg_type != IP_RECVERR)
+				continue;
+			if (cm->cmsg_level == SOL_IPV6 &&
+			    cm->cmsg_type != IPV6_RECVERR)
+				continue;
+
+			serr = (void *)CMSG_DATA(cm);
+			if (serr->ee_origin != SO_EE_ORIGIN_ZEROCOPY) {
+				pr_err("wrong origin %u", serr->ee_origin);
+				return -1;
+			}
+			if (serr->ee_errno != 0) {
+				pr_err("wrong errno %d", serr->ee_errno);
+				return -1;
+			}
+
+			hi = serr->ee_data;
+			lo = serr->ee_info;
+
+			fprintf(stderr, "tx complete [%d,%d]\n", lo, hi);
+			return 0;
+		}
+	}
+
+	pr_err("did not receive tx completion");
+	return -1;
+}
+
+static int do_client(struct memory_buffer *mem)
+{
+	char ctrl_data[CMSG_SPACE(sizeof(__u32))];
+	struct sockaddr_in6 server_sin;
+	struct sockaddr_in6 client_sin;
+	struct ynl_sock *ys = NULL;
+	struct iovec iov[MAX_IOV];
+	struct msghdr msg = {};
+	ssize_t line_size = 0;
+	struct cmsghdr *cmsg;
+	char *line = NULL;
+	int ret, err = -1;
+	size_t len = 0;
+	int socket_fd;
+	__u32 ddmabuf;
+	int opt = 1;
+
+	ret = parse_address(server_ip, atoi(port), &server_sin);
+	if (ret < 0) {
+		pr_err("parse server address");
+		return -1;
+	}
+
+	if (client_ip) {
+		ret = parse_address(client_ip, atoi(port), &client_sin);
+		if (ret < 0) {
+			pr_err("parse client address");
+			return ret;
+		}
+	}
+
+	socket_fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (socket_fd < 0) {
+		pr_err("create socket");
+		return -1;
+	}
+
+	if (enable_reuseaddr(socket_fd))
+		goto err_close_socket;
+
+	ret = setsockopt(socket_fd, SOL_SOCKET, SO_BINDTODEVICE, ifname,
+			 strlen(ifname) + 1);
+	if (ret) {
+		pr_err("bindtodevice");
+		goto err_close_socket;
+	}
+
+	if (bind_tx_queue(ifindex, mem->fd, &ys)) {
+		pr_err("Failed to bind");
+		goto err_close_socket;
+	}
+
+	if (client_ip) {
+		ret = bind(socket_fd, &client_sin, sizeof(client_sin));
+		if (ret) {
+			pr_err("bind");
+			goto err_unbind;
+		}
+	}
+
+	ret = setsockopt(socket_fd, SOL_SOCKET, SO_ZEROCOPY, &opt, sizeof(opt));
+	if (ret) {
+		pr_err("set sock opt");
+		goto err_unbind;
+	}
+
+	fprintf(stderr, "Connect to %s %d (via %s)\n", server_ip,
+		ntohs(server_sin.sin6_port), ifname);
+
+	ret = connect(socket_fd, &server_sin, sizeof(server_sin));
+	if (ret) {
+		pr_err("connect");
+		goto err_unbind;
+	}
+
+	while (1) {
+		free(line);
+		line = NULL;
+		line_size = getline(&line, &len, stdin);
+
+		if (line_size < 0)
+			break;
+
+		if (max_chunk) {
+			msg.msg_iovlen =
+				(line_size + max_chunk - 1) / max_chunk;
+			if (msg.msg_iovlen > MAX_IOV) {
+				pr_err("can't partition %zd bytes into maximum of %d chunks",
+				       line_size, MAX_IOV);
+				goto err_free_line;
+			}
+
+			for (int i = 0; i < msg.msg_iovlen; i++) {
+				iov[i].iov_base = (void *)(i * max_chunk);
+				iov[i].iov_len = max_chunk;
+			}
+
+			iov[msg.msg_iovlen - 1].iov_len =
+				line_size - (msg.msg_iovlen - 1) * max_chunk;
+		} else {
+			iov[0].iov_base = 0;
+			iov[0].iov_len = line_size;
+			msg.msg_iovlen = 1;
+		}
+
+		msg.msg_iov = iov;
+		provider->memcpy_to_device(mem, 0, line, line_size);
+
+		msg.msg_control = ctrl_data;
+		msg.msg_controllen = sizeof(ctrl_data);
+
+		cmsg = CMSG_FIRSTHDR(&msg);
+		cmsg->cmsg_level = SOL_SOCKET;
+		cmsg->cmsg_type = SCM_DEVMEM_DMABUF;
+		cmsg->cmsg_len = CMSG_LEN(sizeof(__u32));
+
+		ddmabuf = tx_dmabuf_id;
+
+		*((__u32 *)CMSG_DATA(cmsg)) = ddmabuf;
+
+		ret = sendmsg(socket_fd, &msg, MSG_ZEROCOPY);
+		if (ret < 0) {
+			pr_err("Failed sendmsg");
+			goto err_free_line;
+		}
+
+		fprintf(stderr, "sendmsg_ret=%d\n", ret);
+
+		if (ret != line_size) {
+			pr_err("Did not send all bytes %d vs %zd", ret, line_size);
+			goto err_free_line;
+		}
+
+		if (wait_compl(socket_fd))
+			goto err_free_line;
+	}
+
+	fprintf(stderr, "%s: tx ok\n", TEST_PREFIX);
+
+	err = 0;
+
+err_free_line:
+	free(line);
+err_unbind:
+	ynl_sock_destroy(ys);
+err_close_socket:
+	close(socket_fd);
+	return err;
+}
+
+int main(int argc, char *argv[])
+{
+	struct memory_buffer *mem;
+	int is_server = 0, opt;
+	int ret, err = 1;
+
+	while ((opt = getopt(argc, argv, "ls:c:p:v:q:t:f:z:")) != -1) {
+		switch (opt) {
+		case 'l':
+			is_server = 1;
+			break;
+		case 's':
+			server_ip = optarg;
+			break;
+		case 'c':
+			client_ip = optarg;
+			break;
+		case 'p':
+			port = optarg;
+			break;
+		case 'v':
+			do_validation = atoll(optarg);
+			break;
+		case 'q':
+			num_queues = atoi(optarg);
+			break;
+		case 't':
+			start_queue = atoi(optarg);
+			break;
+		case 'f':
+			ifname = optarg;
+			break;
+		case 'z':
+			max_chunk = atoi(optarg);
+			break;
+		case '?':
+			fprintf(stderr, "unknown option: %c\n", optopt);
+			break;
+		}
+	}
+
+	if (!ifname) {
+		pr_err("Missing -f argument");
+		return 1;
+	}
+
+	ifindex = if_nametoindex(ifname);
+
+	fprintf(stderr, "using ifindex=%u\n", ifindex);
+
+	if (!server_ip && !client_ip) {
+		if (start_queue < 0 && num_queues < 0) {
+			num_queues = rxq_num(ifindex);
+			if (num_queues < 0) {
+				pr_err("couldn't detect number of queues");
+				return 1;
+			}
+			if (num_queues < 2) {
+				pr_err("number of device queues is too low");
+				return 1;
+			}
+			/* make sure can bind to multiple queues */
+			start_queue = num_queues / 2;
+			num_queues /= 2;
+		}
+
+		if (start_queue < 0 || num_queues < 0) {
+			pr_err("Both -t and -q are required");
+			return 1;
+		}
+
+		return run_devmem_tests();
+	}
+
+	if (start_queue < 0 && num_queues < 0) {
+		num_queues = rxq_num(ifindex);
+		if (num_queues < 2) {
+			pr_err("number of device queues is too low");
+			return 1;
+		}
+
+		num_queues = 1;
+		start_queue = rxq_num(ifindex) - num_queues;
+
+		if (start_queue < 0) {
+			pr_err("couldn't detect number of queues");
+			return 1;
+		}
+
+		fprintf(stderr, "using queues %d..%d\n", start_queue, start_queue + num_queues);
+	}
+
+	for (; optind < argc; optind++)
+		fprintf(stderr, "extra arguments: %s\n", argv[optind]);
+
+	if (start_queue < 0) {
+		pr_err("Missing -t argument");
+		return 1;
+	}
+
+	if (num_queues < 0) {
+		pr_err("Missing -q argument");
+		return 1;
+	}
+
+	if (!server_ip) {
+		pr_err("Missing -s argument");
+		return 1;
+	}
+
+	if (!port) {
+		pr_err("Missing -p argument");
+		return 1;
+	}
+
+	mem = provider->alloc(getpagesize() * NUM_PAGES);
+	if (!mem) {
+		pr_err("Failed to allocate memory buffer");
+		return 1;
+	}
+
+	ret = is_server ? do_server(mem) : do_client(mem);
+	if (ret)
+		goto err_free_mem;
+
+	err = 0;
+
+err_free_mem:
+	provider->free(mem);
+	return err;
+}
diff --git a/tools/testing/selftests/drivers/net/hw/nic_timestamp.py b/tools/testing/selftests/drivers/net/hw/nic_timestamp.py
new file mode 100755
index 000000000000..c1e943d53f19
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/nic_timestamp.py
@@ -0,0 +1,113 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+Tests related to configuration of HW timestamping
+"""
+
+import errno
+from lib.py import ksft_run, ksft_exit, ksft_ge, ksft_eq, KsftSkipEx
+from lib.py import NetDrvEnv, EthtoolFamily, NlError
+
+
+def __get_hwtimestamp_support(cfg):
+    """ Retrieve supported configuration information """
+
+    try:
+        tsinfo = cfg.ethnl.tsinfo_get({'header': {'dev-name': cfg.ifname}})
+    except NlError as e:
+        if e.error == errno.EOPNOTSUPP:
+            raise KsftSkipEx("timestamping configuration is not supported") from e
+        raise
+
+    ctx = {}
+    tx = tsinfo.get('tx-types', {})
+    rx = tsinfo.get('rx-filters', {})
+
+    bits = tx.get('bits', {})
+    ctx['tx'] = bits.get('bit', [])
+    bits = rx.get('bits', {})
+    ctx['rx'] = bits.get('bit', [])
+    return ctx
+
+
+def __get_hwtimestamp_config(cfg):
+    """ Retrieve current TS configuration information """
+
+    try:
+        tscfg = cfg.ethnl.tsconfig_get({'header': {'dev-name': cfg.ifname}})
+    except NlError as e:
+        if e.error == errno.EOPNOTSUPP:
+            raise KsftSkipEx("timestamping configuration is not supported via netlink") from e
+        raise
+    return tscfg
+
+
+def __set_hwtimestamp_config(cfg, ts):
+    """ Setup new TS configuration information """
+
+    ts['header'] = {'dev-name': cfg.ifname}
+    try:
+        res = cfg.ethnl.tsconfig_set(ts)
+    except NlError as e:
+        if e.error == errno.EOPNOTSUPP:
+            raise KsftSkipEx("timestamping configuration is not supported via netlink") from e
+        raise
+    return res
+
+
+def test_hwtstamp_tx(cfg):
+    """
+    Test TX timestamp configuration.
+    The driver should apply provided config and report back proper state.
+    """
+
+    orig_tscfg = __get_hwtimestamp_config(cfg)
+    ts = __get_hwtimestamp_support(cfg)
+    tx = ts['tx']
+    for t in tx:
+        tscfg = orig_tscfg
+        tscfg['tx-types']['bits']['bit'] = [t]
+        res = __set_hwtimestamp_config(cfg, tscfg)
+        if res is None:
+            res = __get_hwtimestamp_config(cfg)
+        ksft_eq(res['tx-types']['bits']['bit'], [t])
+    __set_hwtimestamp_config(cfg, orig_tscfg)
+
+
+def test_hwtstamp_rx(cfg):
+    """
+    Test RX timestamp configuration.
+    The filter configuration is taken from the list of supported filters.
+    The driver should apply the config without error and report back proper state.
+    Some extension of the timestamping scope is allowed for PTP filters.
+    """
+
+    orig_tscfg = __get_hwtimestamp_config(cfg)
+    ts = __get_hwtimestamp_support(cfg)
+    rx = ts['rx']
+    for r in rx:
+        tscfg = orig_tscfg
+        tscfg['rx-filters']['bits']['bit'] = [r]
+        res = __set_hwtimestamp_config(cfg, tscfg)
+        if res is None:
+            res = __get_hwtimestamp_config(cfg)
+        if r['index'] == 0 or r['index'] == 1:
+            ksft_eq(res['rx-filters']['bits']['bit'][0]['index'], r['index'])
+        else:
+            # the driver can fallback to some value which has higher coverage for timestamping
+            ksft_ge(res['rx-filters']['bits']['bit'][0]['index'], r['index'])
+    __set_hwtimestamp_config(cfg, orig_tscfg)
+
+
+def main() -> None:
+    """ Ksft boiler plate main """
+
+    with NetDrvEnv(__file__, nsim_test=False) as cfg:
+        cfg.ethnl = EthtoolFamily()
+        ksft_run([test_hwtstamp_tx, test_hwtstamp_rx], args=(cfg,))
+        ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py b/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py
new file mode 100755
index 000000000000..2a51b60df8a1
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py
@@ -0,0 +1,144 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+Test driver resilience vs page pool allocation failures.
+"""
+
+import errno
+import time
+import math
+import os
+from lib.py import ksft_run, ksft_exit, ksft_pr
+from lib.py import KsftSkipEx, KsftFailEx
+from lib.py import NetdevFamily, NlError
+from lib.py import NetDrvEpEnv
+from lib.py import cmd, tool, GenerateTraffic
+
+
+def _write_fail_config(config):
+    for key, value in config.items():
+        path = "/sys/kernel/debug/fail_function/"
+        with open(path + key, "w", encoding='ascii') as fp:
+            fp.write(str(value) + "\n")
+
+
+def _enable_pp_allocation_fail():
+    if not os.path.exists("/sys/kernel/debug/fail_function"):
+        raise KsftSkipEx("Kernel built without function error injection (or DebugFS)")
+
+    if not os.path.exists("/sys/kernel/debug/fail_function/page_pool_alloc_netmems"):
+        _write_fail_config({"inject": "page_pool_alloc_netmems"})
+
+    _write_fail_config({
+        "verbose": 0,
+        "interval": 511,
+        "probability": 100,
+        "times": -1,
+    })
+
+
+def _disable_pp_allocation_fail():
+    if not os.path.exists("/sys/kernel/debug/fail_function"):
+        return
+
+    if os.path.exists("/sys/kernel/debug/fail_function/page_pool_alloc_netmems"):
+        _write_fail_config({"inject": ""})
+
+    _write_fail_config({
+        "probability": 0,
+        "times": 0,
+    })
+
+
+def test_pp_alloc(cfg, netdevnl):
+    """
+    Configure page pool allocation fail injection while traffic is running.
+    """
+
+    def get_stats():
+        return netdevnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0]
+
+    def check_traffic_flowing():
+        stat1 = get_stats()
+        time.sleep(1)
+        stat2 = get_stats()
+        if stat2['rx-packets'] - stat1['rx-packets'] < 4000:
+            raise KsftFailEx("Traffic seems low:", stat2['rx-packets'] - stat1['rx-packets'])
+
+
+    try:
+        stats = get_stats()
+    except NlError as e:
+        if e.nl_msg.error == -errno.EOPNOTSUPP:
+            stats = {}
+        else:
+            raise
+    if 'rx-alloc-fail' not in stats:
+        raise KsftSkipEx("Driver does not report 'rx-alloc-fail' via qstats")
+
+    set_g = False
+    traffic = None
+    try:
+        traffic = GenerateTraffic(cfg)
+
+        check_traffic_flowing()
+
+        _enable_pp_allocation_fail()
+
+        s1 = get_stats()
+        time.sleep(3)
+        s2 = get_stats()
+
+        seen_fails = s2['rx-alloc-fail'] - s1['rx-alloc-fail']
+        if seen_fails < 1:
+            raise KsftSkipEx("Allocation failures not increasing")
+        pkts = s2['rx-packets'] - s1['rx-packets']
+        # Expecting one failure per 512 buffers, 3.1x safety margin
+        want_fails = math.floor(pkts / 512 / 3.1)
+        if seen_fails < want_fails:
+            raise KsftSkipEx("Allocation increasing too slowly", seen_fails,
+                             "packets:", pkts)
+        ksft_pr(f"Seen: pkts:{pkts} fails:{seen_fails} (pass thrs:{want_fails})")
+
+        # Basic failures are fine, try to wobble some settings to catch extra failures
+        check_traffic_flowing()
+        g = tool("ethtool", "-g " + cfg.ifname, json=True)[0]
+        if 'rx' in g and g["rx"] * 2 <= g["rx-max"]:
+            new_g = g['rx'] * 2
+        elif 'rx' in g:
+            new_g = g['rx'] // 2
+        else:
+            new_g = None
+
+        if new_g:
+            set_g = cmd(f"ethtool -G {cfg.ifname} rx {new_g}", fail=False).ret == 0
+            if set_g:
+                ksft_pr("ethtool -G change retval: success")
+            else:
+                ksft_pr("ethtool -G change retval: did not succeed", new_g)
+        else:
+            ksft_pr("ethtool -G change retval: did not try")
+
+        time.sleep(0.1)
+        check_traffic_flowing()
+    finally:
+        _disable_pp_allocation_fail()
+        if traffic:
+            traffic.stop()
+        time.sleep(0.1)
+        if set_g:
+            cmd(f"ethtool -G {cfg.ifname} rx {g['rx']}")
+
+
+def main() -> None:
+    """ Ksft boiler plate main """
+    netdevnl = NetdevFamily()
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+
+        ksft_run([test_pp_alloc], args=(cfg, netdevnl, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/hw/rss_api.py b/tools/testing/selftests/drivers/net/hw/rss_api.py
new file mode 100755
index 000000000000..19847f3d4a00
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/rss_api.py
@@ -0,0 +1,476 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+API level tests for RSS (mostly Netlink vs IOCTL).
+"""
+
+import errno
+import glob
+import random
+from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_is, ksft_ne, ksft_raises
+from lib.py import KsftSkipEx, KsftFailEx
+from lib.py import defer, ethtool, CmdExitFailure
+from lib.py import EthtoolFamily, NlError
+from lib.py import NetDrvEnv
+
+
+def _require_2qs(cfg):
+    qcnt = len(glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*"))
+    if qcnt < 2:
+        raise KsftSkipEx(f"Local has only {qcnt} queues")
+    return qcnt
+
+
+def _ethtool_create(cfg, act, opts):
+    output = ethtool(f"{act} {cfg.ifname} {opts}").stdout
+    # Output will be something like: "New RSS context is 1" or
+    # "Added rule with ID 7", we want the integer from the end
+    return int(output.split()[-1])
+
+
+def _ethtool_get_cfg(cfg, fl_type, to_nl=False):
+    descr = ethtool(f"-n {cfg.ifname} rx-flow-hash {fl_type}").stdout
+
+    if to_nl:
+        converter = {
+            "IP SA": "ip-src",
+            "IP DA": "ip-dst",
+            "L4 bytes 0 & 1 [TCP/UDP src port]": "l4-b-0-1",
+            "L4 bytes 2 & 3 [TCP/UDP dst port]": "l4-b-2-3",
+        }
+
+        ret = set()
+    else:
+        converter = {
+            "IP SA": "s",
+            "IP DA": "d",
+            "L3 proto": "t",
+            "L4 bytes 0 & 1 [TCP/UDP src port]": "f",
+            "L4 bytes 2 & 3 [TCP/UDP dst port]": "n",
+        }
+
+        ret = ""
+
+    for line in descr.split("\n")[1:-2]:
+        # if this raises we probably need to add more keys to converter above
+        if to_nl:
+            ret.add(converter[line])
+        else:
+            ret += converter[line]
+    return ret
+
+
+def test_rxfh_nl_set_fail(cfg):
+    """
+    Test error path of Netlink SET.
+    """
+    _require_2qs(cfg)
+
+    ethnl = EthtoolFamily()
+    ethnl.ntf_subscribe("monitor")
+
+    with ksft_raises(NlError):
+        ethnl.rss_set({"header": {"dev-name": "lo"},
+                       "indir": None})
+
+    with ksft_raises(NlError):
+        ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                       "indir": [100000]})
+    ntf = next(ethnl.poll_ntf(duration=0.2), None)
+    ksft_is(ntf, None)
+
+
+def test_rxfh_nl_set_indir(cfg):
+    """
+    Test setting indirection table via Netlink.
+    """
+    qcnt = _require_2qs(cfg)
+
+    # Test some SETs with a value
+    reset = defer(cfg.ethnl.rss_set,
+                  {"header": {"dev-index": cfg.ifindex}, "indir": None})
+    cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                       "indir": [1]})
+    rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    ksft_eq(set(rss.get("indir", [-1])), {1})
+
+    cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                       "indir": [0, 1]})
+    rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    ksft_eq(set(rss.get("indir", [-1])), {0, 1})
+
+    # Make sure we can't set the queue count below max queue used
+    with ksft_raises(CmdExitFailure):
+        ethtool(f"-L {cfg.ifname} combined 0 rx 1")
+    with ksft_raises(CmdExitFailure):
+        ethtool(f"-L {cfg.ifname} combined 1 rx 0")
+
+    # Test reset back to default
+    reset.exec()
+    rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    ksft_eq(set(rss.get("indir", [-1])), set(range(qcnt)))
+
+
+def test_rxfh_nl_set_indir_ctx(cfg):
+    """
+    Test setting indirection table for a custom context via Netlink.
+    """
+    _require_2qs(cfg)
+
+    # Get setting for ctx 0, we'll make sure they don't get clobbered
+    dflt = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+
+    # Create context
+    ctx_id = _ethtool_create(cfg, "-X", "context new")
+    defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete")
+
+    cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                       "context": ctx_id, "indir": [1]})
+    rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex},
+                             "context": ctx_id})
+    ksft_eq(set(rss.get("indir", [-1])), {1})
+
+    ctx0 = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    ksft_eq(ctx0, dflt)
+
+    cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                       "context": ctx_id, "indir": [0, 1]})
+    rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex},
+                             "context": ctx_id})
+    ksft_eq(set(rss.get("indir", [-1])), {0, 1})
+
+    ctx0 = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    ksft_eq(ctx0, dflt)
+
+    # Make sure we can't set the queue count below max queue used
+    with ksft_raises(CmdExitFailure):
+        ethtool(f"-L {cfg.ifname} combined 0 rx 1")
+    with ksft_raises(CmdExitFailure):
+        ethtool(f"-L {cfg.ifname} combined 1 rx 0")
+
+
+def test_rxfh_indir_ntf(cfg):
+    """
+    Check that Netlink notifications are generated when RSS indirection
+    table was modified.
+    """
+    _require_2qs(cfg)
+
+    ethnl = EthtoolFamily()
+    ethnl.ntf_subscribe("monitor")
+
+    ethtool(f"--disable-netlink -X {cfg.ifname} weight 0 1")
+    reset = defer(ethtool, f"-X {cfg.ifname} default")
+
+    ntf = next(ethnl.poll_ntf(duration=0.2), None)
+    if ntf is None:
+        raise KsftFailEx("No notification received")
+    ksft_eq(ntf["name"], "rss-ntf")
+    ksft_eq(set(ntf["msg"]["indir"]), {1})
+
+    reset.exec()
+    ntf = next(ethnl.poll_ntf(duration=0.2), None)
+    if ntf is None:
+        raise KsftFailEx("No notification received after reset")
+    ksft_eq(ntf["name"], "rss-ntf")
+    ksft_is(ntf["msg"].get("context"), None)
+    ksft_ne(set(ntf["msg"]["indir"]), {1})
+
+
+def test_rxfh_indir_ctx_ntf(cfg):
+    """
+    Check that Netlink notifications are generated when RSS indirection
+    table was modified on an additional RSS context.
+    """
+    _require_2qs(cfg)
+
+    ctx_id = _ethtool_create(cfg, "-X", "context new")
+    defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete")
+
+    ethnl = EthtoolFamily()
+    ethnl.ntf_subscribe("monitor")
+
+    ethtool(f"--disable-netlink -X {cfg.ifname} context {ctx_id} weight 0 1")
+
+    ntf = next(ethnl.poll_ntf(duration=0.2), None)
+    if ntf is None:
+        raise KsftFailEx("No notification received")
+    ksft_eq(ntf["name"], "rss-ntf")
+    ksft_eq(ntf["msg"].get("context"), ctx_id)
+    ksft_eq(set(ntf["msg"]["indir"]), {1})
+
+
+def test_rxfh_nl_set_key(cfg):
+    """
+    Test setting hashing key via Netlink.
+    """
+
+    dflt = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    defer(cfg.ethnl.rss_set,
+          {"header": {"dev-index": cfg.ifindex},
+           "hkey": dflt["hkey"], "indir": None})
+
+    # Empty key should error out
+    with ksft_raises(NlError) as cm:
+        cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                           "hkey": None})
+    ksft_eq(cm.exception.nl_msg.extack['bad-attr'], '.hkey')
+
+    # Set key to random
+    mod = random.randbytes(len(dflt["hkey"]))
+    cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                       "hkey": mod})
+    rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    ksft_eq(rss.get("hkey", [-1]), mod)
+
+    # Set key to random and indir tbl to something at once
+    mod = random.randbytes(len(dflt["hkey"]))
+    cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                       "indir": [0, 1], "hkey": mod})
+    rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    ksft_eq(rss.get("hkey", [-1]), mod)
+    ksft_eq(set(rss.get("indir", [-1])), {0, 1})
+
+
+def test_rxfh_fields(cfg):
+    """
+    Test reading Rx Flow Hash over Netlink.
+    """
+
+    flow_types = ["tcp4", "tcp6", "udp4", "udp6"]
+    ethnl = EthtoolFamily()
+
+    cfg_nl = ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    for fl_type in flow_types:
+        one = _ethtool_get_cfg(cfg, fl_type, to_nl=True)
+        ksft_eq(one, cfg_nl["flow-hash"][fl_type],
+                comment="Config for " + fl_type)
+
+
+def test_rxfh_fields_set(cfg):
+    """ Test configuring Rx Flow Hash over Netlink. """
+
+    flow_types = ["tcp4", "tcp6", "udp4", "udp6"]
+
+    # Collect current settings
+    cfg_old = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    # symmetric hashing is config-order-sensitive make sure we leave
+    # symmetric mode, or make the flow-hash sym-compatible first
+    changes = [{"flow-hash": cfg_old["flow-hash"],},
+               {"input-xfrm": cfg_old.get("input-xfrm", {}),}]
+    if cfg_old.get("input-xfrm"):
+        changes = list(reversed(changes))
+    for old in changes:
+        defer(cfg.ethnl.rss_set, {"header": {"dev-index": cfg.ifindex},} | old)
+
+    # symmetric hashing prevents some of the configs below
+    if cfg_old.get("input-xfrm"):
+        cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                           "input-xfrm": {}})
+
+    for fl_type in flow_types:
+        cur = _ethtool_get_cfg(cfg, fl_type)
+        if cur == "sdfn":
+            change_nl = {"ip-src", "ip-dst"}
+            change_ic = "sd"
+        else:
+            change_nl = {"l4-b-0-1", "l4-b-2-3", "ip-src", "ip-dst"}
+            change_ic = "sdfn"
+
+        cfg.ethnl.rss_set({
+            "header": {"dev-index": cfg.ifindex},
+            "flow-hash": {fl_type: change_nl}
+        })
+        reset = defer(ethtool, f"--disable-netlink -N {cfg.ifname} "
+                      f"rx-flow-hash {fl_type} {cur}")
+
+        cfg_nl = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+        ksft_eq(change_nl, cfg_nl["flow-hash"][fl_type],
+                comment=f"Config for {fl_type} over Netlink")
+        cfg_ic = _ethtool_get_cfg(cfg, fl_type)
+        ksft_eq(change_ic, cfg_ic,
+                comment=f"Config for {fl_type} over IOCTL")
+
+        reset.exec()
+        cfg_nl = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+        ksft_eq(cfg_old["flow-hash"][fl_type], cfg_nl["flow-hash"][fl_type],
+                comment=f"Un-config for {fl_type} over Netlink")
+        cfg_ic = _ethtool_get_cfg(cfg, fl_type)
+        ksft_eq(cur, cfg_ic, comment=f"Un-config for {fl_type} over IOCTL")
+
+    # Try to set multiple at once, the defer was already installed at the start
+    change = {"ip-src"}
+    if change == cfg_old["flow-hash"]["tcp4"]:
+        change = {"ip-dst"}
+    cfg.ethnl.rss_set({
+        "header": {"dev-index": cfg.ifindex},
+        "flow-hash": {x: change for x in flow_types}
+    })
+
+    cfg_nl = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    for fl_type in flow_types:
+        ksft_eq(change, cfg_nl["flow-hash"][fl_type],
+                comment=f"multi-config for {fl_type} over Netlink")
+
+
+def test_rxfh_fields_set_xfrm(cfg):
+    """ Test changing Rx Flow Hash vs xfrm_input at once.  """
+
+    def set_rss(cfg, xfrm, fh):
+        cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                           "input-xfrm": xfrm, "flow-hash": fh})
+
+    # Install the reset handler
+    cfg_old = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    # symmetric hashing is config-order-sensitive make sure we leave
+    # symmetric mode, or make the flow-hash sym-compatible first
+    changes = [{"flow-hash": cfg_old["flow-hash"],},
+               {"input-xfrm": cfg_old.get("input-xfrm", {}),}]
+    if cfg_old.get("input-xfrm"):
+        changes = list(reversed(changes))
+    for old in changes:
+        defer(cfg.ethnl.rss_set, {"header": {"dev-index": cfg.ifindex},} | old)
+
+    # Make sure we start with input-xfrm off, and tcp4 config non-sym
+    set_rss(cfg, {}, {})
+    set_rss(cfg, {}, {"tcp4": {"ip-src"}})
+
+    # Setting sym and fixing tcp4 config not expected to pass right now
+    with ksft_raises(NlError):
+        set_rss(cfg, {"sym-xor"}, {"tcp4": {"ip-src", "ip-dst"}})
+    # One at a time should work, hopefully
+    set_rss(cfg, 0, {"tcp4": {"ip-src", "ip-dst"}})
+    no_support = False
+    try:
+        set_rss(cfg, {"sym-xor"}, {})
+    except NlError:
+        try:
+            set_rss(cfg, {"sym-or-xor"}, {})
+        except NlError:
+            no_support = True
+    if no_support:
+        raise KsftSkipEx("no input-xfrm supported")
+    # Disabling two at once should not work either without kernel changes
+    with ksft_raises(NlError):
+        set_rss(cfg, {}, {"tcp4": {"ip-src"}})
+
+
+def test_rxfh_fields_ntf(cfg):
+    """ Test Rx Flow Hash notifications. """
+
+    cur = _ethtool_get_cfg(cfg, "tcp4")
+    if cur == "sdfn":
+        change = {"ip-src", "ip-dst"}
+    else:
+        change = {"l4-b-0-1", "l4-b-2-3", "ip-src", "ip-dst"}
+
+    ethnl = EthtoolFamily()
+    ethnl.ntf_subscribe("monitor")
+
+    ethnl.rss_set({
+        "header": {"dev-index": cfg.ifindex},
+        "flow-hash": {"tcp4": change}
+    })
+    reset = defer(ethtool,
+                  f"--disable-netlink -N {cfg.ifname} rx-flow-hash tcp4 {cur}")
+
+    ntf = next(ethnl.poll_ntf(duration=0.2), None)
+    if ntf is None:
+        raise KsftFailEx("No notification received after IOCTL change")
+    ksft_eq(ntf["name"], "rss-ntf")
+    ksft_eq(ntf["msg"]["flow-hash"]["tcp4"], change)
+    ksft_eq(next(ethnl.poll_ntf(duration=0.01), None), None)
+
+    reset.exec()
+    ntf = next(ethnl.poll_ntf(duration=0.2), None)
+    if ntf is None:
+        raise KsftFailEx("No notification received after Netlink change")
+    ksft_eq(ntf["name"], "rss-ntf")
+    ksft_ne(ntf["msg"]["flow-hash"]["tcp4"], change)
+    ksft_eq(next(ethnl.poll_ntf(duration=0.01), None), None)
+
+
+def test_rss_ctx_add(cfg):
+    """ Test creating an additional RSS context via Netlink """
+
+    _require_2qs(cfg)
+
+    # Test basic creation
+    ctx = cfg.ethnl.rss_create_act({"header": {"dev-index": cfg.ifindex}})
+    d = defer(ethtool, f"-X {cfg.ifname} context {ctx.get('context')} delete")
+    ksft_ne(ctx.get("context", 0), 0)
+    ksft_ne(set(ctx.get("indir", [0])), {0},
+            comment="Driver should init the indirection table")
+
+    # Try requesting the ID we just got allocated
+    with ksft_raises(NlError) as cm:
+        ctx = cfg.ethnl.rss_create_act({
+            "header": {"dev-index": cfg.ifindex},
+            "context": ctx.get("context"),
+        })
+        ethtool(f"-X {cfg.ifname} context {ctx.get('context')} delete")
+    d.exec()
+    ksft_eq(cm.exception.nl_msg.error, -errno.EBUSY)
+
+    # Test creating with a specified RSS table, and context ID
+    ctx_id = ctx.get("context")
+    ctx = cfg.ethnl.rss_create_act({
+        "header": {"dev-index": cfg.ifindex},
+        "context": ctx_id,
+        "indir": [1],
+    })
+    ethtool(f"-X {cfg.ifname} context {ctx.get('context')} delete")
+    ksft_eq(ctx.get("context"), ctx_id)
+    ksft_eq(set(ctx.get("indir", [0])), {1})
+
+
+def test_rss_ctx_ntf(cfg):
+    """ Test notifications for creating additional RSS contexts """
+
+    ethnl = EthtoolFamily()
+    ethnl.ntf_subscribe("monitor")
+
+    # Create / delete via Netlink
+    ctx = cfg.ethnl.rss_create_act({"header": {"dev-index": cfg.ifindex}})
+    cfg.ethnl.rss_delete_act({
+        "header": {"dev-index": cfg.ifindex},
+        "context": ctx["context"],
+    })
+
+    ntf = next(ethnl.poll_ntf(duration=0.2), None)
+    if ntf is None:
+        raise KsftFailEx("[NL] No notification after context creation")
+    ksft_eq(ntf["name"], "rss-create-ntf")
+    ksft_eq(ctx, ntf["msg"])
+
+    ntf = next(ethnl.poll_ntf(duration=0.2), None)
+    if ntf is None:
+        raise KsftFailEx("[NL] No notification after context deletion")
+    ksft_eq(ntf["name"], "rss-delete-ntf")
+
+    # Create / deleve via IOCTL
+    ctx_id = _ethtool_create(cfg, "--disable-netlink -X", "context new")
+    ethtool(f"--disable-netlink -X {cfg.ifname} context {ctx_id} delete")
+    ntf = next(ethnl.poll_ntf(duration=0.2), None)
+    if ntf is None:
+        raise KsftFailEx("[IOCTL] No notification after context creation")
+    ksft_eq(ntf["name"], "rss-create-ntf")
+
+    ntf = next(ethnl.poll_ntf(duration=0.2), None)
+    if ntf is None:
+        raise KsftFailEx("[IOCTL] No notification after context deletion")
+    ksft_eq(ntf["name"], "rss-delete-ntf")
+
+
+def main() -> None:
+    """ Ksft boiler plate main """
+
+    with NetDrvEnv(__file__, nsim_test=False) as cfg:
+        cfg.ethnl = EthtoolFamily()
+        ksft_run(globs=globals(), case_pfx={"test_"}, args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
new file mode 100755
index 000000000000..ed7e405682f0
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -0,0 +1,832 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import datetime
+import random
+import re
+from lib.py import ksft_run, ksft_pr, ksft_exit
+from lib.py import ksft_eq, ksft_ne, ksft_ge, ksft_in, ksft_lt, ksft_true, ksft_raises
+from lib.py import NetDrvEpEnv
+from lib.py import EthtoolFamily, NetdevFamily
+from lib.py import KsftSkipEx, KsftFailEx
+from lib.py import rand_port
+from lib.py import ethtool, ip, defer, GenerateTraffic, CmdExitFailure
+
+
+def _rss_key_str(key):
+    return ":".join(["{:02x}".format(x) for x in key])
+
+
+def _rss_key_rand(length):
+    return [random.randint(0, 255) for _ in range(length)]
+
+
+def _rss_key_check(cfg, data=None, context=0):
+    if data is None:
+        data = get_rss(cfg, context=context)
+    if 'rss-hash-key' not in data:
+        return
+    non_zero = [x for x in data['rss-hash-key'] if x != 0]
+    ksft_eq(bool(non_zero), True, comment=f"RSS key is all zero {data['rss-hash-key']}")
+
+
+def get_rss(cfg, context=0):
+    return ethtool(f"-x {cfg.ifname} context {context}", json=True)[0]
+
+
+def get_drop_err_sum(cfg):
+    stats = ip("-s -s link show dev " + cfg.ifname, json=True)[0]
+    cnt = 0
+    for key in ['errors', 'dropped', 'over_errors', 'fifo_errors',
+                'length_errors', 'crc_errors', 'missed_errors',
+                'frame_errors']:
+        cnt += stats["stats64"]["rx"][key]
+    return cnt, stats["stats64"]["tx"]["carrier_changes"]
+
+
+def ethtool_create(cfg, act, opts):
+    output = ethtool(f"{act} {cfg.ifname} {opts}").stdout
+    # Output will be something like: "New RSS context is 1" or
+    # "Added rule with ID 7", we want the integer from the end
+    return int(output.split()[-1])
+
+
+def require_ntuple(cfg):
+    features = ethtool(f"-k {cfg.ifname}", json=True)[0]
+    if not features["ntuple-filters"]["active"]:
+        # ntuple is more of a capability than a config knob, don't bother
+        # trying to enable it (until some driver actually needs it).
+        raise KsftSkipEx("Ntuple filters not enabled on the device: " + str(features["ntuple-filters"]))
+
+
+def require_context_cnt(cfg, need_cnt):
+    # There's no good API to get the context count, so the tests
+    # which try to add a lot opportunisitically set the count they
+    # discovered. Careful with test ordering!
+    if need_cnt and cfg.context_cnt and cfg.context_cnt < need_cnt:
+        raise KsftSkipEx(f"Test requires at least {need_cnt} contexts, but device only has {cfg.context_cnt}")
+
+
+# Get Rx packet counts for all queues, as a simple list of integers
+# if @prev is specified the prev counts will be subtracted
+def _get_rx_cnts(cfg, prev=None):
+    cfg.wait_hw_stats_settle()
+    data = cfg.netdevnl.qstats_get({"ifindex": cfg.ifindex, "scope": ["queue"]}, dump=True)
+    data = [x for x in data if x['queue-type'] == "rx"]
+    max_q = max([x["queue-id"] for x in data])
+    queue_stats = [0] * (max_q + 1)
+    for q in data:
+        queue_stats[q["queue-id"]] = q["rx-packets"]
+        if prev and q["queue-id"] < len(prev):
+            queue_stats[q["queue-id"]] -= prev[q["queue-id"]]
+    return queue_stats
+
+
+def _send_traffic_check(cfg, port, name, params):
+    # params is a dict with 3 possible keys:
+    #  - "target": required, which queues we expect to get iperf traffic
+    #  - "empty": optional, which queues should see no traffic at all
+    #  - "noise": optional, which queues we expect to see low traffic;
+    #             used for queues of the main context, since some background
+    #             OS activity may use those queues while we're testing
+    # the value for each is a list, or some other iterable containing queue ids.
+
+    cnts = _get_rx_cnts(cfg)
+    GenerateTraffic(cfg, port=port).wait_pkts_and_stop(20000)
+    cnts = _get_rx_cnts(cfg, prev=cnts)
+
+    directed = sum(cnts[i] for i in params['target'])
+
+    ksft_ge(directed, 20000, f"traffic on {name}: " + str(cnts))
+    if params.get('noise'):
+        ksft_lt(sum(cnts[i] for i in params['noise']), directed / 2,
+                f"traffic on other queues ({name})':" + str(cnts))
+    if params.get('empty'):
+        ksft_eq(sum(cnts[i] for i in params['empty']), 0,
+                f"traffic on inactive queues ({name}): " + str(cnts))
+
+
+def _ntuple_rule_check(cfg, rule_id, ctx_id):
+    """Check that ntuple rule references RSS context ID"""
+    text = ethtool(f"-n {cfg.ifname} rule {rule_id}").stdout
+    pattern = f"RSS Context (ID: )?{ctx_id}"
+    ksft_true(re.search(pattern, text), "RSS context not referenced in ntuple rule")
+
+
+def test_rss_key_indir(cfg):
+    """Test basics like updating the main RSS key and indirection table."""
+
+    qcnt = len(_get_rx_cnts(cfg))
+    if qcnt < 3:
+        raise KsftSkipEx("Device has fewer than 3 queues (or doesn't support queue stats)")
+
+    data = get_rss(cfg)
+    want_keys = ['rss-hash-key', 'rss-hash-function', 'rss-indirection-table']
+    for k in want_keys:
+        if k not in data:
+            raise KsftFailEx("ethtool results missing key: " + k)
+        if not data[k]:
+            raise KsftFailEx(f"ethtool results empty for '{k}': {data[k]}")
+
+    _rss_key_check(cfg, data=data)
+    key_len = len(data['rss-hash-key'])
+
+    # Set the key
+    key = _rss_key_rand(key_len)
+    ethtool(f"-X {cfg.ifname} hkey " + _rss_key_str(key))
+
+    data = get_rss(cfg)
+    ksft_eq(key, data['rss-hash-key'])
+
+    # Set the indirection table and the key together
+    key = _rss_key_rand(key_len)
+    ethtool(f"-X {cfg.ifname} equal 3 hkey " + _rss_key_str(key))
+    reset_indir = defer(ethtool, f"-X {cfg.ifname} default")
+
+    data = get_rss(cfg)
+    _rss_key_check(cfg, data=data)
+    ksft_eq(0, min(data['rss-indirection-table']))
+    ksft_eq(2, max(data['rss-indirection-table']))
+
+    # Reset indirection table and set the key
+    key = _rss_key_rand(key_len)
+    ethtool(f"-X {cfg.ifname} default hkey " + _rss_key_str(key))
+    data = get_rss(cfg)
+    _rss_key_check(cfg, data=data)
+    ksft_eq(0, min(data['rss-indirection-table']))
+    ksft_eq(qcnt - 1, max(data['rss-indirection-table']))
+
+    # Set the indirection table
+    ethtool(f"-X {cfg.ifname} equal 2")
+    data = get_rss(cfg)
+    ksft_eq(0, min(data['rss-indirection-table']))
+    ksft_eq(1, max(data['rss-indirection-table']))
+
+    # Check we only get traffic on the first 2 queues
+    cnts = _get_rx_cnts(cfg)
+    GenerateTraffic(cfg).wait_pkts_and_stop(20000)
+    cnts = _get_rx_cnts(cfg, prev=cnts)
+    # 2 queues, 20k packets, must be at least 5k per queue
+    ksft_ge(cnts[0], 5000, "traffic on main context (1/2): " + str(cnts))
+    ksft_ge(cnts[1], 5000, "traffic on main context (2/2): " + str(cnts))
+    # The other queues should be unused
+    ksft_eq(sum(cnts[2:]), 0, "traffic on unused queues: " + str(cnts))
+
+    # Restore, and check traffic gets spread again
+    reset_indir.exec()
+
+    cnts = _get_rx_cnts(cfg)
+    GenerateTraffic(cfg).wait_pkts_and_stop(20000)
+    cnts = _get_rx_cnts(cfg, prev=cnts)
+    if qcnt > 4:
+        # First two queues get less traffic than all the rest
+        ksft_lt(sum(cnts[:2]), sum(cnts[2:]),
+                "traffic distributed: " + str(cnts))
+    else:
+        # When queue count is low make sure third queue got significant pkts
+        ksft_ge(cnts[2], 3500, "traffic distributed: " + str(cnts))
+
+
+def test_rss_queue_reconfigure(cfg, main_ctx=True):
+    """Make sure queue changes can't override requested RSS config.
+
+    By default main RSS table should change to include all queues.
+    When user sets a specific RSS config the driver should preserve it,
+    even when queue count changes. Driver should refuse to deactivate
+    queues used in the user-set RSS config.
+    """
+
+    if not main_ctx:
+        require_ntuple(cfg)
+
+    # Start with 4 queues, an arbitrary known number.
+    try:
+        qcnt = len(_get_rx_cnts(cfg))
+        ethtool(f"-L {cfg.ifname} combined 4")
+        defer(ethtool, f"-L {cfg.ifname} combined {qcnt}")
+    except:
+        raise KsftSkipEx("Not enough queues for the test or qstat not supported")
+
+    if main_ctx:
+        ctx_id = 0
+        ctx_ref = ""
+    else:
+        ctx_id = ethtool_create(cfg, "-X", "context new")
+        ctx_ref = f"context {ctx_id}"
+        defer(ethtool, f"-X {cfg.ifname} {ctx_ref} delete")
+
+    # Indirection table should be distributing to all queues.
+    data = get_rss(cfg, context=ctx_id)
+    ksft_eq(0, min(data['rss-indirection-table']))
+    ksft_eq(3, max(data['rss-indirection-table']))
+
+    # Increase queues, indirection table should be distributing to all queues.
+    # It's unclear whether tables of additional contexts should be reset, too.
+    if main_ctx:
+        ethtool(f"-L {cfg.ifname} combined 5")
+        data = get_rss(cfg)
+        ksft_eq(0, min(data['rss-indirection-table']))
+        ksft_eq(4, max(data['rss-indirection-table']))
+        ethtool(f"-L {cfg.ifname} combined 4")
+
+    # Configure the table explicitly
+    port = rand_port()
+    ethtool(f"-X {cfg.ifname} {ctx_ref} weight 1 0 0 1")
+    if main_ctx:
+        other_key = 'empty'
+        defer(ethtool, f"-X {cfg.ifname} default")
+    else:
+        other_key = 'noise'
+        flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {port} context {ctx_id}"
+        ntuple = ethtool_create(cfg, "-N", flow)
+        defer(ethtool, f"-N {cfg.ifname} delete {ntuple}")
+
+    _send_traffic_check(cfg, port, ctx_ref, { 'target': (0, 3),
+                                              other_key: (1, 2) })
+
+    # We should be able to increase queues, but table should be left untouched
+    ethtool(f"-L {cfg.ifname} combined 5")
+    data = get_rss(cfg, context=ctx_id)
+    ksft_eq({0, 3}, set(data['rss-indirection-table']))
+
+    _send_traffic_check(cfg, port, ctx_ref, { 'target': (0, 3),
+                                              other_key: (1, 2, 4) })
+
+    # Setting queue count to 3 should fail, queue 3 is used
+    try:
+        ethtool(f"-L {cfg.ifname} combined 3")
+    except CmdExitFailure:
+        pass
+    else:
+        raise Exception(f"Driver didn't prevent us from deactivating a used queue (context {ctx_id})")
+
+    if not main_ctx:
+        ethtool(f"-L {cfg.ifname} combined 4")
+        flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {port} context {ctx_id} action 1"
+        try:
+            # this targets queue 4, which doesn't exist
+            ntuple2 = ethtool_create(cfg, "-N", flow)
+            defer(ethtool, f"-N {cfg.ifname} delete {ntuple2}")
+        except CmdExitFailure:
+            pass
+        else:
+            raise Exception(f"Driver didn't prevent us from targeting a nonexistent queue (context {ctx_id})")
+        # change the table to target queues 0 and 2
+        ethtool(f"-X {cfg.ifname} {ctx_ref} weight 1 0 1 0")
+        # ntuple rule therefore targets queues 1 and 3
+        try:
+            ntuple2 = ethtool_create(cfg, "-N", flow)
+        except CmdExitFailure:
+            ksft_pr("Driver does not support rss + queue offset")
+            return
+
+        defer(ethtool, f"-N {cfg.ifname} delete {ntuple2}")
+        # should replace existing filter
+        ksft_eq(ntuple, ntuple2)
+        _send_traffic_check(cfg, port, ctx_ref, { 'target': (1, 3),
+                                                  'noise' : (0, 2) })
+        # Setting queue count to 3 should fail, queue 3 is used
+        try:
+            ethtool(f"-L {cfg.ifname} combined 3")
+        except CmdExitFailure:
+            pass
+        else:
+            raise Exception(f"Driver didn't prevent us from deactivating a used queue (context {ctx_id})")
+
+
+def test_rss_resize(cfg):
+    """Test resizing of the RSS table.
+
+    Some devices dynamically increase and decrease the size of the RSS
+    indirection table based on the number of enabled queues.
+    When that happens driver must maintain the balance of entries
+    (preferably duplicating the smaller table).
+    """
+
+    channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+    ch_max = channels['combined-max']
+    qcnt = channels['combined-count']
+
+    if ch_max < 2:
+        raise KsftSkipEx(f"Not enough queues for the test: {ch_max}")
+
+    ethtool(f"-L {cfg.ifname} combined 2")
+    defer(ethtool, f"-L {cfg.ifname} combined {qcnt}")
+
+    ethtool(f"-X {cfg.ifname} weight 1 7")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    ethtool(f"-L {cfg.ifname} combined {ch_max}")
+    data = get_rss(cfg)
+    ksft_eq(0, min(data['rss-indirection-table']))
+    ksft_eq(1, max(data['rss-indirection-table']))
+
+    ksft_eq(7,
+            data['rss-indirection-table'].count(1) /
+            data['rss-indirection-table'].count(0),
+            f"Table imbalance after resize: {data['rss-indirection-table']}")
+
+
+def test_hitless_key_update(cfg):
+    """Test that flows may be rehashed without impacting traffic.
+
+    Some workloads may want to rehash the flows in response to an imbalance.
+    Most effective way to do that is changing the RSS key. Check that changing
+    the key does not cause link flaps or traffic disruption.
+
+    Disrupting traffic for key update is not a bug, but makes the key
+    update unusable for rehashing under load.
+    """
+    data = get_rss(cfg)
+    key_len = len(data['rss-hash-key'])
+
+    ethnl = EthtoolFamily()
+    key = random.randbytes(key_len)
+
+    tgen = GenerateTraffic(cfg)
+    try:
+        errors0, carrier0 = get_drop_err_sum(cfg)
+        t0 = datetime.datetime.now()
+        ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, "hkey": key})
+        t1 = datetime.datetime.now()
+        errors1, carrier1 = get_drop_err_sum(cfg)
+    finally:
+        tgen.wait_pkts_and_stop(5000)
+
+    ksft_lt((t1 - t0).total_seconds(), 0.15)
+    ksft_eq(errors1 - errors1, 0)
+    ksft_eq(carrier1 - carrier0, 0)
+
+
+def test_rss_context_dump(cfg):
+    """
+    Test dumping RSS contexts. This tests mostly exercises the kernel APIs.
+    """
+
+    # Get a random key of the right size
+    data = get_rss(cfg)
+    if 'rss-hash-key' in data:
+        key_data = _rss_key_rand(len(data['rss-hash-key']))
+        key = _rss_key_str(key_data)
+    else:
+        key_data = []
+        key = "ba:ad"
+
+    ids = []
+    try:
+        ids.append(ethtool_create(cfg, "-X", f"context new"))
+        defer(ethtool, f"-X {cfg.ifname} context {ids[-1]} delete")
+
+        ids.append(ethtool_create(cfg, "-X", f"context new weight 1 1"))
+        defer(ethtool, f"-X {cfg.ifname} context {ids[-1]} delete")
+
+        ids.append(ethtool_create(cfg, "-X", f"context new hkey {key}"))
+        defer(ethtool, f"-X {cfg.ifname} context {ids[-1]} delete")
+    except CmdExitFailure:
+        if not ids:
+            raise KsftSkipEx("Unable to add any contexts")
+        ksft_pr(f"Added only {len(ids)} out of 3 contexts")
+
+    expect_tuples = set([(cfg.ifname, -1)] + [(cfg.ifname, ctx_id) for ctx_id in ids])
+
+    # Dump all
+    ctxs = cfg.ethnl.rss_get({}, dump=True)
+    tuples = [(c['header']['dev-name'], c.get('context', -1)) for c in ctxs]
+    ksft_eq(len(tuples), len(set(tuples)), "duplicates in context dump")
+    ctx_tuples = set([ctx for ctx in tuples if ctx[0] == cfg.ifname])
+    ksft_eq(expect_tuples, ctx_tuples)
+
+    # Sanity-check the results
+    for data in ctxs:
+        ksft_ne(set(data.get('indir', [1])), {0}, "indir table is all zero")
+        ksft_ne(set(data.get('hkey', [1])), {0}, "key is all zero")
+
+        # More specific checks
+        if len(ids) > 1 and data.get('context') == ids[1]:
+            ksft_eq(set(data['indir']), {0, 1},
+                    "ctx1 - indir table mismatch")
+        if len(ids) > 2 and data.get('context') == ids[2]:
+            ksft_eq(data['hkey'], bytes(key_data), "ctx2 - key mismatch")
+
+    # Ifindex filter
+    ctxs = cfg.ethnl.rss_get({'header': {'dev-name': cfg.ifname}}, dump=True)
+    tuples = [(c['header']['dev-name'], c.get('context', -1)) for c in ctxs]
+    ctx_tuples = set(tuples)
+    ksft_eq(len(tuples), len(ctx_tuples), "duplicates in context dump")
+    ksft_eq(expect_tuples, ctx_tuples)
+
+    # Skip ctx 0
+    expect_tuples.remove((cfg.ifname, -1))
+
+    ctxs = cfg.ethnl.rss_get({'start-context': 1}, dump=True)
+    tuples = [(c['header']['dev-name'], c.get('context', -1)) for c in ctxs]
+    ksft_eq(len(tuples), len(set(tuples)), "duplicates in context dump")
+    ctx_tuples = set([ctx for ctx in tuples if ctx[0] == cfg.ifname])
+    ksft_eq(expect_tuples, ctx_tuples)
+
+    # And finally both with ifindex and skip main
+    ctxs = cfg.ethnl.rss_get({'header': {'dev-name': cfg.ifname}, 'start-context': 1}, dump=True)
+    ctx_tuples = set([(c['header']['dev-name'], c.get('context', -1)) for c in ctxs])
+    ksft_eq(expect_tuples, ctx_tuples)
+
+
+def test_rss_context(cfg, ctx_cnt=1, create_with_cfg=None):
+    """
+    Test separating traffic into RSS contexts.
+    The queues will be allocated 2 for each context:
+     ctx0  ctx1  ctx2  ctx3
+    [0 1] [2 3] [4 5] [6 7] ...
+    """
+
+    require_ntuple(cfg)
+
+    requested_ctx_cnt = ctx_cnt
+
+    # Try to allocate more queues when necessary
+    qcnt = len(_get_rx_cnts(cfg))
+    if qcnt < 2 + 2 * ctx_cnt:
+        try:
+            ksft_pr(f"Increasing queue count {qcnt} -> {2 + 2 * ctx_cnt}")
+            ethtool(f"-L {cfg.ifname} combined {2 + 2 * ctx_cnt}")
+            defer(ethtool, f"-L {cfg.ifname} combined {qcnt}")
+        except:
+            raise KsftSkipEx("Not enough queues for the test")
+
+    ports = []
+
+    # Use queues 0 and 1 for normal traffic
+    ethtool(f"-X {cfg.ifname} equal 2")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    for i in range(ctx_cnt):
+        want_cfg = f"start {2 + i * 2} equal 2"
+        create_cfg = want_cfg if create_with_cfg else ""
+
+        try:
+            ctx_id = ethtool_create(cfg, "-X", f"context new {create_cfg}")
+            defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete")
+        except CmdExitFailure:
+            # try to carry on and skip at the end
+            if i == 0:
+                raise
+            ksft_pr(f"Failed to create context {i + 1}, trying to test what we got")
+            ctx_cnt = i
+            if cfg.context_cnt is None:
+                cfg.context_cnt = ctx_cnt
+            break
+
+        _rss_key_check(cfg, context=ctx_id)
+
+        if not create_with_cfg:
+            ethtool(f"-X {cfg.ifname} context {ctx_id} {want_cfg}")
+            _rss_key_check(cfg, context=ctx_id)
+
+        # Sanity check the context we just created
+        data = get_rss(cfg, ctx_id)
+        ksft_eq(min(data['rss-indirection-table']), 2 + i * 2, "Unexpected context cfg: " + str(data))
+        ksft_eq(max(data['rss-indirection-table']), 2 + i * 2 + 1, "Unexpected context cfg: " + str(data))
+
+        ports.append(rand_port())
+        flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {ports[i]} context {ctx_id}"
+        ntuple = ethtool_create(cfg, "-N", flow)
+        defer(ethtool, f"-N {cfg.ifname} delete {ntuple}")
+
+        _ntuple_rule_check(cfg, ntuple, ctx_id)
+
+    for i in range(ctx_cnt):
+        _send_traffic_check(cfg, ports[i], f"context {i}",
+                            { 'target': (2+i*2, 3+i*2),
+                              'noise': (0, 1),
+                              'empty': list(range(2, 2+i*2)) + list(range(4+i*2, 2+2*ctx_cnt)) })
+
+    if requested_ctx_cnt != ctx_cnt:
+        raise KsftSkipEx(f"Tested only {ctx_cnt} contexts, wanted {requested_ctx_cnt}")
+
+
+def test_rss_context4(cfg):
+    test_rss_context(cfg, 4)
+
+
+def test_rss_context32(cfg):
+    test_rss_context(cfg, 32)
+
+
+def test_rss_context4_create_with_cfg(cfg):
+    test_rss_context(cfg, 4, create_with_cfg=True)
+
+
+def test_rss_context_queue_reconfigure(cfg):
+    test_rss_queue_reconfigure(cfg, main_ctx=False)
+
+
+def test_rss_context_out_of_order(cfg, ctx_cnt=4):
+    """
+    Test separating traffic into RSS contexts.
+    Contexts are removed in semi-random order, and steering re-tested
+    to make sure removal doesn't break steering to surviving contexts.
+    Test requires 3 contexts to work.
+    """
+
+    require_ntuple(cfg)
+    require_context_cnt(cfg, 4)
+
+    # Try to allocate more queues when necessary
+    qcnt = len(_get_rx_cnts(cfg))
+    if qcnt < 2 + 2 * ctx_cnt:
+        try:
+            ksft_pr(f"Increasing queue count {qcnt} -> {2 + 2 * ctx_cnt}")
+            ethtool(f"-L {cfg.ifname} combined {2 + 2 * ctx_cnt}")
+            defer(ethtool, f"-L {cfg.ifname} combined {qcnt}")
+        except:
+            raise KsftSkipEx("Not enough queues for the test")
+
+    ntuple = []
+    ctx = []
+    ports = []
+
+    def remove_ctx(idx):
+        ntuple[idx].exec()
+        ntuple[idx] = None
+        ctx[idx].exec()
+        ctx[idx] = None
+
+    def check_traffic():
+        for i in range(ctx_cnt):
+            if ctx[i]:
+                expected = {
+                    'target': (2+i*2, 3+i*2),
+                    'noise': (0, 1),
+                    'empty': list(range(2, 2+i*2)) + list(range(4+i*2, 2+2*ctx_cnt))
+                }
+            else:
+                expected = {
+                    'target': (0, 1),
+                    'empty':  range(2, 2+2*ctx_cnt)
+                }
+
+            _send_traffic_check(cfg, ports[i], f"context {i}", expected)
+
+    # Use queues 0 and 1 for normal traffic
+    ethtool(f"-X {cfg.ifname} equal 2")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    for i in range(ctx_cnt):
+        ctx_id = ethtool_create(cfg, "-X", f"context new start {2 + i * 2} equal 2")
+        ctx.append(defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete"))
+
+        ports.append(rand_port())
+        flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {ports[i]} context {ctx_id}"
+        ntuple_id = ethtool_create(cfg, "-N", flow)
+        ntuple.append(defer(ethtool, f"-N {cfg.ifname} delete {ntuple_id}"))
+
+    check_traffic()
+
+    # Remove middle context
+    remove_ctx(ctx_cnt // 2)
+    check_traffic()
+
+    # Remove first context
+    remove_ctx(0)
+    check_traffic()
+
+    # Remove last context
+    remove_ctx(-1)
+    check_traffic()
+
+
+def test_rss_context_overlap(cfg, other_ctx=0):
+    """
+    Test contexts overlapping with each other.
+    Use 4 queues for the main context, but only queues 2 and 3 for context 1.
+    """
+
+    require_ntuple(cfg)
+    if other_ctx:
+        require_context_cnt(cfg, 2)
+
+    queue_cnt = len(_get_rx_cnts(cfg))
+    if queue_cnt < 4:
+        try:
+            ksft_pr(f"Increasing queue count {queue_cnt} -> 4")
+            ethtool(f"-L {cfg.ifname} combined 4")
+            defer(ethtool, f"-L {cfg.ifname} combined {queue_cnt}")
+        except:
+            raise KsftSkipEx("Not enough queues for the test")
+
+    if other_ctx == 0:
+        ethtool(f"-X {cfg.ifname} equal 4")
+        defer(ethtool, f"-X {cfg.ifname} default")
+    else:
+        other_ctx = ethtool_create(cfg, "-X", "context new")
+        ethtool(f"-X {cfg.ifname} context {other_ctx} equal 4")
+        defer(ethtool, f"-X {cfg.ifname} context {other_ctx} delete")
+
+    ctx_id = ethtool_create(cfg, "-X", "context new")
+    ethtool(f"-X {cfg.ifname} context {ctx_id} start 2 equal 2")
+    defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete")
+
+    port = rand_port()
+    if other_ctx:
+        flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {port} context {other_ctx}"
+        ntuple_id = ethtool_create(cfg, "-N", flow)
+        ntuple = defer(ethtool, f"-N {cfg.ifname} delete {ntuple_id}")
+
+    # Test the main context
+    cnts = _get_rx_cnts(cfg)
+    GenerateTraffic(cfg, port=port).wait_pkts_and_stop(20000)
+    cnts = _get_rx_cnts(cfg, prev=cnts)
+
+    ksft_ge(sum(cnts[ :4]), 20000, "traffic on main context: " + str(cnts))
+    ksft_ge(sum(cnts[ :2]),  7000, "traffic on main context (1/2): " + str(cnts))
+    ksft_ge(sum(cnts[2:4]),  7000, "traffic on main context (2/2): " + str(cnts))
+    if other_ctx == 0:
+        ksft_eq(sum(cnts[4: ]),     0, "traffic on other queues: " + str(cnts))
+
+    # Now create a rule for context 1 and make sure traffic goes to a subset
+    if other_ctx:
+        ntuple.exec()
+    flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {port} context {ctx_id}"
+    ntuple_id = ethtool_create(cfg, "-N", flow)
+    defer(ethtool, f"-N {cfg.ifname} delete {ntuple_id}")
+
+    cnts = _get_rx_cnts(cfg)
+    GenerateTraffic(cfg, port=port).wait_pkts_and_stop(20000)
+    cnts = _get_rx_cnts(cfg, prev=cnts)
+
+    directed = sum(cnts[2:4])
+    ksft_lt(sum(cnts[ :2]), directed / 2, "traffic on main context: " + str(cnts))
+    ksft_ge(directed, 20000, "traffic on extra context: " + str(cnts))
+    if other_ctx == 0:
+        ksft_eq(sum(cnts[4: ]),     0, "traffic on other queues: " + str(cnts))
+
+
+def test_rss_context_overlap2(cfg):
+    test_rss_context_overlap(cfg, True)
+
+
+def test_flow_add_context_missing(cfg):
+    """
+    Test that we are not allowed to add a rule pointing to an RSS context
+    which was never created.
+    """
+
+    require_ntuple(cfg)
+
+    # Find a context which doesn't exist
+    for ctx_id in range(1, 100):
+        try:
+            get_rss(cfg, context=ctx_id)
+        except CmdExitFailure:
+            break
+
+    with ksft_raises(CmdExitFailure) as cm:
+        flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port 1234 context {ctx_id}"
+        ntuple_id = ethtool_create(cfg, "-N", flow)
+        ethtool(f"-N {cfg.ifname} delete {ntuple_id}")
+    if cm.exception:
+        ksft_in('Invalid argument', cm.exception.cmd.stderr)
+
+
+def test_delete_rss_context_busy(cfg):
+    """
+    Test that deletion returns -EBUSY when an rss context is being used
+    by an ntuple filter.
+    """
+
+    require_ntuple(cfg)
+
+    # create additional rss context
+    ctx_id = ethtool_create(cfg, "-X", "context new")
+    ctx_deleter = defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete")
+
+    # utilize context from ntuple filter
+    port = rand_port()
+    flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {port} context {ctx_id}"
+    ntuple_id = ethtool_create(cfg, "-N", flow)
+    defer(ethtool, f"-N {cfg.ifname} delete {ntuple_id}")
+
+    # attempt to delete in-use context
+    try:
+        ctx_deleter.exec_only()
+        ctx_deleter.cancel()
+        raise KsftFailEx(f"deleted context {ctx_id} used by rule {ntuple_id}")
+    except CmdExitFailure:
+        pass
+
+
+def test_rss_ntuple_addition(cfg):
+    """
+    Test that the queue offset (ring_cookie) of an ntuple rule is added
+    to the queue number read from the indirection table.
+    """
+
+    require_ntuple(cfg)
+
+    queue_cnt = len(_get_rx_cnts(cfg))
+    if queue_cnt < 4:
+        try:
+            ksft_pr(f"Increasing queue count {queue_cnt} -> 4")
+            ethtool(f"-L {cfg.ifname} combined 4")
+            defer(ethtool, f"-L {cfg.ifname} combined {queue_cnt}")
+        except:
+            raise KsftSkipEx("Not enough queues for the test")
+
+    # Use queue 0 for normal traffic
+    ethtool(f"-X {cfg.ifname} equal 1")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    # create additional rss context
+    ctx_id = ethtool_create(cfg, "-X", "context new equal 2")
+    defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete")
+
+    # utilize context from ntuple filter
+    port = rand_port()
+    flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {port} context {ctx_id} action 2"
+    try:
+        ntuple_id = ethtool_create(cfg, "-N", flow)
+    except CmdExitFailure:
+        raise KsftSkipEx("Ntuple filter with RSS and nonzero action not supported")
+    defer(ethtool, f"-N {cfg.ifname} delete {ntuple_id}")
+
+    _send_traffic_check(cfg, port, f"context {ctx_id}", { 'target': (2, 3),
+                                                          'empty' : (1,),
+                                                          'noise' : (0,) })
+
+
+def test_rss_default_context_rule(cfg):
+    """
+    Allocate a port, direct this port to context 0, then create a new RSS
+    context and steer all TCP traffic to it (context 1).  Verify that:
+      * Traffic to the specific port continues to use queues of the main
+        context (0/1).
+      * Traffic to any other TCP port is redirected to the new context
+        (queues 2/3).
+    """
+
+    require_ntuple(cfg)
+
+    queue_cnt = len(_get_rx_cnts(cfg))
+    if queue_cnt < 4:
+        try:
+            ksft_pr(f"Increasing queue count {queue_cnt} -> 4")
+            ethtool(f"-L {cfg.ifname} combined 4")
+            defer(ethtool, f"-L {cfg.ifname} combined {queue_cnt}")
+        except Exception as exc:
+            raise KsftSkipEx("Not enough queues for the test") from exc
+
+    # Use queues 0 and 1 for the main context
+    ethtool(f"-X {cfg.ifname} equal 2")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    # Create a new RSS context that uses queues 2 and 3
+    ctx_id = ethtool_create(cfg, "-X", "context new start 2 equal 2")
+    defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete")
+
+    # Generic low-priority rule: redirect all TCP traffic to the new context.
+    # Give it an explicit higher location number (lower priority).
+    flow_generic = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} context {ctx_id} loc 1"
+    ethtool(f"-N {cfg.ifname} {flow_generic}")
+    defer(ethtool, f"-N {cfg.ifname} delete 1")
+
+    # Specific high-priority rule for a random port that should stay on context 0.
+    # Assign loc 0 so it is evaluated before the generic rule.
+    port_main = rand_port()
+    flow_main = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {port_main} context 0 loc 0"
+    ethtool(f"-N {cfg.ifname} {flow_main}")
+    defer(ethtool, f"-N {cfg.ifname} delete 0")
+
+    _ntuple_rule_check(cfg, 1, ctx_id)
+
+    # Verify that traffic matching the specific rule still goes to queues 0/1
+    _send_traffic_check(cfg, port_main, "context 0",
+                        { 'target': (0, 1),
+                          'empty' : (2, 3) })
+
+    # And that traffic for any other port is steered to the new context
+    port_other = rand_port()
+    _send_traffic_check(cfg, port_other, f"context {ctx_id}",
+                        { 'target': (2, 3),
+                          'noise' : (0, 1) })
+
+
+def main() -> None:
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+        cfg.context_cnt = None
+        cfg.ethnl = EthtoolFamily()
+        cfg.netdevnl = NetdevFamily()
+
+        ksft_run([test_rss_key_indir, test_rss_queue_reconfigure,
+                  test_rss_resize, test_hitless_key_update,
+                  test_rss_context, test_rss_context4, test_rss_context32,
+                  test_rss_context_dump, test_rss_context_queue_reconfigure,
+                  test_rss_context_overlap, test_rss_context_overlap2,
+                  test_rss_context_out_of_order, test_rss_context4_create_with_cfg,
+                  test_flow_add_context_missing,
+                  test_delete_rss_context_busy, test_rss_ntuple_addition,
+                  test_rss_default_context_rule],
+                 args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/hw/rss_flow_label.py b/tools/testing/selftests/drivers/net/hw/rss_flow_label.py
new file mode 100755
index 000000000000..6fa95fe27c47
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/rss_flow_label.py
@@ -0,0 +1,167 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+Tests for RSS hashing on IPv6 Flow Label.
+"""
+
+import glob
+import os
+import socket
+from lib.py import CmdExitFailure
+from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ge, ksft_in, \
+    ksft_not_in, ksft_raises, KsftSkipEx
+from lib.py import bkg, cmd, defer, fd_read_timeout, rand_port
+from lib.py import NetDrvEpEnv
+
+
+def _check_system(cfg):
+    if not hasattr(socket, "SO_INCOMING_CPU"):
+        raise KsftSkipEx("socket.SO_INCOMING_CPU was added in Python 3.11")
+
+    qcnt = len(glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*"))
+    if qcnt < 2:
+        raise KsftSkipEx(f"Local has only {qcnt} queues")
+
+    for f in [f"/sys/class/net/{cfg.ifname}/queues/rx-0/rps_flow_cnt",
+              f"/sys/class/net/{cfg.ifname}/queues/rx-0/rps_cpus"]:
+        try:
+            with open(f, 'r') as fp:
+                setting = fp.read().strip()
+                # CPU mask will be zeros and commas
+                if setting.replace("0", "").replace(",", ""):
+                    raise KsftSkipEx(f"RPS/RFS is configured: {f}: {setting}")
+        except FileNotFoundError:
+            pass
+
+    # 1 is the default, if someone changed it we probably shouldn"t mess with it
+    af = cmd("cat /proc/sys/net/ipv6/auto_flowlabels", host=cfg.remote).stdout
+    if af.strip() != "1":
+        raise KsftSkipEx("Remote does not have auto_flowlabels enabled")
+
+
+def _ethtool_get_cfg(cfg, fl_type):
+    descr = cmd(f"ethtool -n {cfg.ifname} rx-flow-hash {fl_type}").stdout
+
+    converter = {
+        "IP SA": "s",
+        "IP DA": "d",
+        "L3 proto": "t",
+        "L4 bytes 0 & 1 [TCP/UDP src port]": "f",
+        "L4 bytes 2 & 3 [TCP/UDP dst port]": "n",
+        "IPv6 Flow Label": "l",
+    }
+
+    ret = ""
+    for line in descr.split("\n")[1:-2]:
+        # if this raises we probably need to add more keys to converter above
+        ret += converter[line]
+    return ret
+
+
+def _traffic(cfg, one_sock, one_cpu):
+    local_port  = rand_port(socket.SOCK_DGRAM)
+    remote_port = rand_port(socket.SOCK_DGRAM)
+
+    sock = socket.socket(socket.AF_INET6, socket.SOCK_DGRAM)
+    sock.bind(("", local_port))
+    sock.connect((cfg.remote_addr_v["6"], 0))
+    if one_sock:
+        send = f"exec 5<>/dev/udp/{cfg.addr_v['6']}/{local_port}; " \
+                "for i in `seq 20`; do echo a >&5; sleep 0.02; done; exec 5>&-"
+    else:
+        send = "for i in `seq 20`; do echo a | socat -t0.02 - UDP6:" \
+              f"[{cfg.addr_v['6']}]:{local_port},sourceport={remote_port}; done"
+
+    cpus = set()
+    with bkg(send, shell=True, host=cfg.remote, exit_wait=True):
+        for _ in range(20):
+            fd_read_timeout(sock.fileno(), 1)
+            cpu = sock.getsockopt(socket.SOL_SOCKET, socket.SO_INCOMING_CPU)
+            cpus.add(cpu)
+
+    if one_cpu:
+        ksft_eq(len(cpus), 1,
+                f"{one_sock=} - expected one CPU, got traffic on: {cpus=}")
+    else:
+        ksft_ge(len(cpus), 2,
+                f"{one_sock=} - expected many CPUs, got traffic on: {cpus=}")
+
+
+def test_rss_flow_label(cfg):
+    """
+    Test hashing on IPv6 flow label. Send traffic over a single socket
+    and over multiple sockets. Depend on the remote having auto-label
+    enabled so that it randomizes the label per socket.
+    """
+
+    cfg.require_ipver("6")
+    cfg.require_cmd("socat", remote=True)
+    _check_system(cfg)
+
+    # Enable flow label hashing for UDP6
+    initial = _ethtool_get_cfg(cfg, "udp6")
+    no_lbl = initial.replace("l", "")
+    if "l" not in initial:
+        try:
+            cmd(f"ethtool -N {cfg.ifname} rx-flow-hash udp6 l{no_lbl}")
+        except CmdExitFailure as exc:
+            raise KsftSkipEx("Device doesn't support Flow Label for UDP6") from exc
+
+        defer(cmd, f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {initial}")
+
+    _traffic(cfg, one_sock=True, one_cpu=True)
+    _traffic(cfg, one_sock=False, one_cpu=False)
+
+    # Disable it, we should see no hashing (reset was already defer()ed)
+    cmd(f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {no_lbl}")
+
+    _traffic(cfg, one_sock=False, one_cpu=True)
+
+
+def _check_v4_flow_types(cfg):
+    for fl_type in ["tcp4", "udp4", "ah4", "esp4", "sctp4"]:
+        try:
+            cur = cmd(f"ethtool -n {cfg.ifname} rx-flow-hash {fl_type}").stdout
+            ksft_not_in("Flow Label", cur,
+                        comment=f"{fl_type=} has Flow Label:" + cur)
+        except CmdExitFailure:
+            # Probably does not support this flow type
+            pass
+
+
+def test_rss_flow_label_6only(cfg):
+    """
+    Test interactions with IPv4 flow types. It should not be possible to set
+    IPv6 Flow Label hashing for an IPv4 flow type. The Flow Label should also
+    not appear in the IPv4 "current config".
+    """
+
+    with ksft_raises(CmdExitFailure) as cm:
+        cmd(f"ethtool -N {cfg.ifname} rx-flow-hash tcp4 sdfnl")
+    ksft_in("Invalid argument", cm.exception.cmd.stderr)
+
+    _check_v4_flow_types(cfg)
+
+    # Try to enable Flow Labels and check again, in case it leaks thru
+    initial = _ethtool_get_cfg(cfg, "udp6")
+    changed = initial.replace("l", "") if "l" in initial else initial + "l"
+
+    cmd(f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {changed}")
+    restore = defer(cmd, f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {initial}")
+
+    _check_v4_flow_types(cfg)
+    restore.exec()
+    _check_v4_flow_types(cfg)
+
+
+def main() -> None:
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+        ksft_run([test_rss_flow_label,
+                  test_rss_flow_label_6only],
+                 args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py
new file mode 100755
index 000000000000..72880e388478
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py
@@ -0,0 +1,92 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import multiprocessing
+import socket
+from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ge, cmd, fd_read_timeout
+from lib.py import NetDrvEpEnv
+from lib.py import EthtoolFamily, NetdevFamily
+from lib.py import KsftSkipEx, KsftFailEx
+from lib.py import rand_port
+
+
+def traffic(cfg, local_port, remote_port, ipver):
+    af_inet = socket.AF_INET if ipver == "4" else socket.AF_INET6
+    sock = socket.socket(af_inet, socket.SOCK_DGRAM)
+    sock.bind(("", local_port))
+    sock.connect((cfg.remote_addr_v[ipver], remote_port))
+    tgt = f"{ipver}:[{cfg.addr_v[ipver]}]:{local_port},sourceport={remote_port}"
+    cmd("echo a | socat - UDP" + tgt, host=cfg.remote)
+    fd_read_timeout(sock.fileno(), 5)
+    return sock.getsockopt(socket.SOL_SOCKET, socket.SO_INCOMING_CPU)
+
+
+def test_rss_input_xfrm(cfg, ipver):
+    """
+    Test symmetric input_xfrm.
+    If symmetric RSS hash is configured, send traffic twice, swapping the
+    src/dst UDP ports, and verify that the same queue is receiving the traffic
+    in both cases (IPs are constant).
+    """
+
+    if multiprocessing.cpu_count() < 2:
+        raise KsftSkipEx("Need at least two CPUs to test symmetric RSS hash")
+
+    cfg.require_cmd("socat", local=False, remote=True)
+
+    if not hasattr(socket, "SO_INCOMING_CPU"):
+        raise KsftSkipEx("socket.SO_INCOMING_CPU was added in Python 3.11")
+
+    rss = cfg.ethnl.rss_get({'header': {'dev-name': cfg.ifname}})
+    input_xfrm = set(filter(lambda x: 'sym' in x, rss.get('input-xfrm', {})))
+
+    # Check for symmetric xor/or-xor
+    if not input_xfrm:
+        raise KsftSkipEx("Symmetric RSS hash not requested")
+
+    cpus = set()
+    successful = 0
+    for _ in range(100):
+        try:
+            port1 = rand_port(socket.SOCK_DGRAM)
+            port2 = rand_port(socket.SOCK_DGRAM)
+            cpu1 = traffic(cfg, port1, port2, ipver)
+            cpu2 = traffic(cfg, port2, port1, ipver)
+            cpus.update([cpu1, cpu2])
+            ksft_eq(
+                cpu1, cpu2, comment=f"Received traffic on different cpus with ports ({port1 = }, {port2 = }) while symmetric hash is configured")
+
+            successful += 1
+            if successful == 10:
+                break
+        except:
+            continue
+    else:
+        raise KsftFailEx("Failed to run traffic")
+
+    ksft_ge(len(cpus), 2,
+            comment=f"Received traffic on less than two cpus {cpus = }")
+
+
+def test_rss_input_xfrm_ipv4(cfg):
+    cfg.require_ipver("4")
+    test_rss_input_xfrm(cfg, "4")
+
+
+def test_rss_input_xfrm_ipv6(cfg):
+    cfg.require_ipver("6")
+    test_rss_input_xfrm(cfg, "6")
+
+
+def main() -> None:
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+        cfg.ethnl = EthtoolFamily()
+        cfg.netdevnl = NetdevFamily()
+
+        ksft_run([test_rss_input_xfrm_ipv4, test_rss_input_xfrm_ipv6],
+                 args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/hw/settings b/tools/testing/selftests/drivers/net/hw/settings
new file mode 100644
index 000000000000..e7b9417537fb
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/settings
@@ -0,0 +1 @@
+timeout=0
diff --git a/tools/testing/selftests/net/toeplitz.c b/tools/testing/selftests/drivers/net/hw/toeplitz.c
index 90026a27eac0..d23b3b0c20a3 100644
--- a/tools/testing/selftests/net/toeplitz.c
+++ b/tools/testing/selftests/drivers/net/hw/toeplitz.c
@@ -52,7 +52,11 @@
 #include <sys/types.h>
 #include <unistd.h>
 
-#include "../kselftest.h"
+#include <ynl.h>
+#include "ethtool-user.h"
+
+#include "kselftest.h"
+#include "../../../net/lib/ksft.h"
 
 #define TOEPLITZ_KEY_MIN_LEN	40
 #define TOEPLITZ_KEY_MAX_LEN	60
@@ -64,6 +68,7 @@
 #define FOUR_TUPLE_MAX_LEN	((sizeof(struct in6_addr) * 2) + (sizeof(uint16_t) * 2))
 
 #define RSS_MAX_CPUS (1 << 16)	/* real constraint is PACKET_FANOUT_MAX */
+#define RSS_MAX_INDIR	(1 << 16)
 
 #define RPS_MAX_CPUS 16UL	/* must be a power of 2 */
 
@@ -101,6 +106,8 @@ struct ring_state {
 static unsigned int rx_irq_cpus[RSS_MAX_CPUS];	/* map from rxq to cpu */
 static int rps_silo_to_cpu[RPS_MAX_CPUS];
 static unsigned char toeplitz_key[TOEPLITZ_KEY_MAX_LEN];
+static unsigned int rss_indir_tbl[RSS_MAX_INDIR];
+static unsigned int rss_indir_tbl_size;
 static struct ring_state rings[RSS_MAX_CPUS];
 
 static inline uint32_t toeplitz(const unsigned char *four_tuple,
@@ -129,7 +136,12 @@ static inline uint32_t toeplitz(const unsigned char *four_tuple,
 /* Compare computed cpu with arrival cpu from packet_fanout_cpu */
 static void verify_rss(uint32_t rx_hash, int cpu)
 {
-	int queue = rx_hash % cfg_num_queues;
+	int queue;
+
+	if (rss_indir_tbl_size)
+		queue = rss_indir_tbl[rx_hash % rss_indir_tbl_size];
+	else
+		queue = rx_hash % cfg_num_queues;
 
 	log_verbose(" rxq %d (cpu %d)", queue, rx_irq_cpus[queue]);
 	if (rx_irq_cpus[queue] != cpu) {
@@ -215,7 +227,7 @@ static char *recv_frame(const struct ring_state *ring, char *frame)
 }
 
 /* A single TPACKET_V3 block can hold multiple frames */
-static void recv_block(struct ring_state *ring)
+static bool recv_block(struct ring_state *ring)
 {
 	struct tpacket_block_desc *block;
 	char *frame;
@@ -223,7 +235,7 @@ static void recv_block(struct ring_state *ring)
 
 	block = (void *)(ring->mmap + ring->idx * ring_block_sz);
 	if (!(block->hdr.bh1.block_status & TP_STATUS_USER))
-		return;
+		return false;
 
 	frame = (char *)block;
 	frame += block->hdr.bh1.offset_to_first_pkt;
@@ -235,6 +247,8 @@ static void recv_block(struct ring_state *ring)
 
 	block->hdr.bh1.block_status = TP_STATUS_KERNEL;
 	ring->idx = (ring->idx + 1) % ring_block_nr;
+
+	return true;
 }
 
 /* simple test: sleep once unconditionally and then process all rings */
@@ -245,7 +259,7 @@ static void process_rings(void)
 	usleep(1000 * cfg_timeout_msec);
 
 	for (i = 0; i < num_cpus; i++)
-		recv_block(&rings[i]);
+		do {} while (recv_block(&rings[i]));
 
 	fprintf(stderr, "count: pass=%u nohash=%u fail=%u\n",
 		frames_received - frames_nohash - frames_error,
@@ -257,12 +271,12 @@ static char *setup_ring(int fd)
 	struct tpacket_req3 req3 = {0};
 	void *ring;
 
-	req3.tp_retire_blk_tov = cfg_timeout_msec;
+	req3.tp_retire_blk_tov = cfg_timeout_msec / 8;
 	req3.tp_feature_req_word = TP_FT_REQ_FILL_RXHASH;
 
 	req3.tp_frame_size = 2048;
 	req3.tp_frame_nr = 1 << 10;
-	req3.tp_block_nr = 2;
+	req3.tp_block_nr = 16;
 
 	req3.tp_block_size = req3.tp_frame_size * req3.tp_frame_nr;
 	req3.tp_block_size /= req3.tp_block_nr;
@@ -480,6 +494,56 @@ static void parse_rps_bitmap(const char *arg)
 			rps_silo_to_cpu[cfg_num_rps_cpus++] = i;
 }
 
+static void read_rss_dev_info_ynl(void)
+{
+	struct ethtool_rss_get_req *req;
+	struct ethtool_rss_get_rsp *rsp;
+	struct ynl_sock *ys;
+
+	ys = ynl_sock_create(&ynl_ethtool_family, NULL);
+	if (!ys)
+		error(1, errno, "ynl_sock_create failed");
+
+	req = ethtool_rss_get_req_alloc();
+	if (!req)
+		error(1, errno, "ethtool_rss_get_req_alloc failed");
+
+	ethtool_rss_get_req_set_header_dev_name(req, cfg_ifname);
+
+	rsp = ethtool_rss_get(ys, req);
+	if (!rsp)
+		error(1, ys->err.code, "YNL: %s", ys->err.msg);
+
+	if (!rsp->_len.hkey)
+		error(1, 0, "RSS key not available for %s", cfg_ifname);
+
+	if (rsp->_len.hkey < TOEPLITZ_KEY_MIN_LEN ||
+	    rsp->_len.hkey > TOEPLITZ_KEY_MAX_LEN)
+		error(1, 0, "RSS key length %u out of bounds [%u, %u]",
+		      rsp->_len.hkey, TOEPLITZ_KEY_MIN_LEN,
+		      TOEPLITZ_KEY_MAX_LEN);
+
+	memcpy(toeplitz_key, rsp->hkey, rsp->_len.hkey);
+
+	if (rsp->_count.indir > RSS_MAX_INDIR)
+		error(1, 0, "RSS indirection table too large (%u > %u)",
+		      rsp->_count.indir, RSS_MAX_INDIR);
+
+	/* If indir table not available we'll fallback to simple modulo math */
+	if (rsp->_count.indir) {
+		memcpy(rss_indir_tbl, rsp->indir,
+		       rsp->_count.indir * sizeof(rss_indir_tbl[0]));
+		rss_indir_tbl_size = rsp->_count.indir;
+
+		log_verbose("RSS indirection table size: %u\n",
+			    rss_indir_tbl_size);
+	}
+
+	ethtool_rss_get_rsp_free(rsp);
+	ethtool_rss_get_req_free(req);
+	ynl_sock_destroy(ys);
+}
+
 static void parse_opts(int argc, char **argv)
 {
 	static struct option long_options[] = {
@@ -548,7 +612,7 @@ static void parse_opts(int argc, char **argv)
 	}
 
 	if (!have_toeplitz)
-		error(1, 0, "Must supply rss key ('-k')");
+		read_rss_dev_info_ynl();
 
 	num_cpus = get_nprocs();
 	if (num_cpus > RSS_MAX_CPUS)
@@ -574,6 +638,10 @@ int main(int argc, char **argv)
 		fd_sink = setup_sink();
 
 	setup_rings();
+
+	/* Signal to test framework that we're ready to receive */
+	ksft_ready();
+
 	process_rings();
 	cleanup_rings();
 
diff --git a/tools/testing/selftests/drivers/net/hw/toeplitz.py b/tools/testing/selftests/drivers/net/hw/toeplitz.py
new file mode 100755
index 000000000000..d2db5ee9e358
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/toeplitz.py
@@ -0,0 +1,211 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+Toeplitz Rx hashing test:
+ - rxhash (the hash value calculation itself);
+ - RSS mapping from rxhash to rx queue;
+ - RPS mapping from rxhash to cpu.
+"""
+
+import glob
+import os
+import socket
+from lib.py import ksft_run, ksft_exit, ksft_pr
+from lib.py import NetDrvEpEnv, EthtoolFamily, NetdevFamily
+from lib.py import cmd, bkg, rand_port, defer
+from lib.py import ksft_in
+from lib.py import ksft_variants, KsftNamedVariant, KsftSkipEx, KsftFailEx
+
+# "define" for the ID of the Toeplitz hash function
+ETH_RSS_HASH_TOP = 1
+
+
+def _check_rps_and_rfs_not_configured(cfg):
+    """Verify that RPS is not already configured."""
+
+    for rps_file in glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*/rps_cpus"):
+        with open(rps_file, "r", encoding="utf-8") as fp:
+            val = fp.read().strip()
+            if set(val) - {"0", ","}:
+                raise KsftSkipEx(f"RPS already configured on {rps_file}: {val}")
+
+    rfs_file = "/proc/sys/net/core/rps_sock_flow_entries"
+    with open(rfs_file, "r", encoding="utf-8") as fp:
+        val = fp.read().strip()
+        if val != "0":
+            raise KsftSkipEx(f"RFS already configured {rfs_file}: {val}")
+
+
+def _get_cpu_for_irq(irq):
+    with open(f"/proc/irq/{irq}/smp_affinity_list", "r",
+              encoding="utf-8") as fp:
+        data = fp.read().strip()
+        if "," in data or "-" in data:
+            raise KsftFailEx(f"IRQ{irq} is not mapped to a single core: {data}")
+        return int(data)
+
+
+def _get_irq_cpus(cfg):
+    """
+    Read the list of IRQs for the device Rx queues.
+    """
+    queues = cfg.netnl.queue_get({"ifindex": cfg.ifindex}, dump=True)
+    napis = cfg.netnl.napi_get({"ifindex": cfg.ifindex}, dump=True)
+
+    # Remap into ID-based dicts
+    napis = {n["id"]: n for n in napis}
+    queues = {f"{q['type']}{q['id']}": q for q in queues}
+
+    cpus = []
+    for rx in range(9999):
+        name = f"rx{rx}"
+        if name not in queues:
+            break
+        cpus.append(_get_cpu_for_irq(napis[queues[name]["napi-id"]]["irq"]))
+
+    return cpus
+
+
+def _get_unused_cpus(cfg, count=2):
+    """
+    Get CPUs that are not used by Rx queues.
+    Returns a list of at least 'count' CPU numbers.
+    """
+
+    # Get CPUs used by Rx queues
+    rx_cpus = set(_get_irq_cpus(cfg))
+
+    # Get total number of CPUs
+    num_cpus = os.cpu_count()
+
+    # Find unused CPUs
+    unused_cpus = [cpu for cpu in range(num_cpus) if cpu not in rx_cpus]
+
+    if len(unused_cpus) < count:
+        raise KsftSkipEx(f"Need at {count} CPUs not used by Rx queues, found {len(unused_cpus)}")
+
+    return unused_cpus[:count]
+
+
+def _configure_rps(cfg, rps_cpus):
+    """Configure RPS for all Rx queues."""
+
+    mask = 0
+    for cpu in rps_cpus:
+        mask |= (1 << cpu)
+    mask = hex(mask)[2:]
+
+    # Set RPS bitmap for all rx queues
+    for rps_file in glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*/rps_cpus"):
+        with open(rps_file, "w", encoding="utf-8") as fp:
+            fp.write(mask)
+
+    return mask
+
+
+def _send_traffic(cfg, proto_flag, ipver, port):
+    """Send 20 packets of requested type."""
+
+    # Determine protocol and IP version for socat
+    if proto_flag == "-u":
+        proto = "UDP"
+    else:
+        proto = "TCP"
+
+    baddr = f"[{cfg.addr_v['6']}]" if ipver == "6" else cfg.addr_v["4"]
+
+    # Run socat in a loop to send traffic periodically
+    # Use sh -c with a loop similar to toeplitz_client.sh
+    socat_cmd = f"""
+    for i in `seq 20`; do
+        echo "msg $i" | socat -{ipver} -t 0.1 - {proto}:{baddr}:{port};
+        sleep 0.001;
+    done
+    """
+
+    cmd(socat_cmd, shell=True, host=cfg.remote)
+
+
+def _test_variants():
+    for grp in ["", "rss", "rps"]:
+        for l4 in ["tcp", "udp"]:
+            for l3 in ["4", "6"]:
+                name = f"{l4}_ipv{l3}"
+                if grp:
+                    name = f"{grp}_{name}"
+                yield KsftNamedVariant(name, "-" + l4[0], l3, grp)
+
+
+@ksft_variants(_test_variants())
+def test(cfg, proto_flag, ipver, grp):
+    """Run a single toeplitz test."""
+
+    cfg.require_ipver(ipver)
+
+    # Check that rxhash is enabled
+    ksft_in("receive-hashing: on", cmd(f"ethtool -k {cfg.ifname}").stdout)
+
+    rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    # Make sure NIC is configured to use Toeplitz hash, and no key xfrm.
+    if rss.get('hfunc') != ETH_RSS_HASH_TOP or rss.get('input-xfrm'):
+        cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                           "hfunc": ETH_RSS_HASH_TOP,
+                           "input-xfrm": {}})
+        defer(cfg.ethnl.rss_set, {"header": {"dev-index": cfg.ifindex},
+                                  "hfunc": rss.get('hfunc'),
+                                  "input-xfrm": rss.get('input-xfrm', {})
+                                  })
+
+    port = rand_port(socket.SOCK_DGRAM)
+
+    toeplitz_path = cfg.test_dir / "toeplitz"
+    rx_cmd = [
+        str(toeplitz_path),
+        "-" + ipver,
+        proto_flag,
+        "-d", str(port),
+        "-i", cfg.ifname,
+        "-T", "4000",
+        "-s",
+        "-v"
+    ]
+
+    if grp:
+        _check_rps_and_rfs_not_configured(cfg)
+    if grp == "rss":
+        irq_cpus = ",".join([str(x) for x in _get_irq_cpus(cfg)])
+        rx_cmd += ["-C", irq_cpus]
+        ksft_pr(f"RSS using CPUs: {irq_cpus}")
+    elif grp == "rps":
+        # Get CPUs not used by Rx queues and configure them for RPS
+        rps_cpus = _get_unused_cpus(cfg, count=2)
+        rps_mask = _configure_rps(cfg, rps_cpus)
+        defer(_configure_rps, cfg, [])
+        rx_cmd += ["-r", rps_mask]
+        ksft_pr(f"RPS using CPUs: {rps_cpus}, mask: {rps_mask}")
+
+    # Run rx in background, it will exit once it has seen enough packets
+    with bkg(" ".join(rx_cmd), ksft_ready=True, exit_wait=True) as rx_proc:
+        while rx_proc.proc.poll() is None:
+            _send_traffic(cfg, proto_flag, ipver, port)
+
+    # Check rx result
+    ksft_pr("Receiver output:")
+    ksft_pr(rx_proc.stdout.strip().replace('\n', '\n# '))
+    if rx_proc.stderr:
+        ksft_pr(rx_proc.stderr.strip().replace('\n', '\n# '))
+
+
+def main() -> None:
+    """Ksft boilerplate main."""
+
+    with NetDrvEpEnv(__file__) as cfg:
+        cfg.ethnl = EthtoolFamily()
+        cfg.netnl = NetdevFamily()
+        ksft_run(cases=[test], args=(cfg,))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/hw/tso.py b/tools/testing/selftests/drivers/net/hw/tso.py
new file mode 100755
index 000000000000..0998e68ebaf0
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/tso.py
@@ -0,0 +1,261 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""Run the tools/testing/selftests/net/csum testsuite."""
+
+import fcntl
+import socket
+import struct
+import termios
+import time
+
+from lib.py import ksft_pr, ksft_run, ksft_exit, KsftSkipEx, KsftXfailEx
+from lib.py import ksft_eq, ksft_ge, ksft_lt
+from lib.py import EthtoolFamily, NetdevFamily, NetDrvEpEnv
+from lib.py import bkg, cmd, defer, ethtool, ip, rand_port, wait_port_listen
+
+
+def sock_wait_drain(sock, max_wait=1000):
+    """Wait for all pending write data on the socket to get ACKed."""
+    for _ in range(max_wait):
+        one = b'\0' * 4
+        outq = fcntl.ioctl(sock.fileno(), termios.TIOCOUTQ, one)
+        outq = struct.unpack("I", outq)[0]
+        if outq == 0:
+            break
+        time.sleep(0.01)
+    ksft_eq(outq, 0)
+
+
+def tcp_sock_get_retrans(sock):
+    """Get the number of retransmissions for the TCP socket."""
+    info = sock.getsockopt(socket.SOL_TCP, socket.TCP_INFO, 512)
+    return struct.unpack("I", info[100:104])[0]
+
+
+def run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso):
+    cfg.require_cmd("socat", local=False, remote=True)
+
+    port = rand_port()
+    listen_cmd = f"socat -{ipver} -t 2 -u TCP-LISTEN:{port},reuseport /dev/null,ignoreeof"
+
+    with bkg(listen_cmd, host=cfg.remote, exit_wait=True) as nc:
+        wait_port_listen(port, host=cfg.remote)
+
+        if ipver == "4":
+            sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+            sock.connect((remote_v4, port))
+        else:
+            sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
+            sock.connect((remote_v6, port))
+
+        # Small send to make sure the connection is working.
+        sock.send("ping".encode())
+        sock_wait_drain(sock)
+
+        # Send 4MB of data, record the LSO packet count.
+        qstat_old = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0]
+        buf = b"0" * 1024 * 1024 * 4
+        sock.send(buf)
+        sock_wait_drain(sock)
+        qstat_new = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0]
+
+        # Check that at least 90% of the data was sent as LSO packets.
+        # System noise may cause false negatives. Also header overheads
+        # will add up to 5% of extra packes... The check is best effort.
+        total_lso_wire  = len(buf) * 0.90 // cfg.dev["mtu"]
+        total_lso_super = len(buf) * 0.90 // cfg.dev["tso_max_size"]
+
+        # Make sure we have order of magnitude more LSO packets than
+        # retransmits, in case TCP retransmitted all the LSO packets.
+        ksft_lt(tcp_sock_get_retrans(sock), total_lso_wire / 4)
+        sock.close()
+
+        if should_lso:
+            if cfg.have_stat_super_count:
+                ksft_ge(qstat_new['tx-hw-gso-packets'] -
+                        qstat_old['tx-hw-gso-packets'],
+                        total_lso_super,
+                        comment="Number of LSO super-packets with LSO enabled")
+            if cfg.have_stat_wire_count:
+                ksft_ge(qstat_new['tx-hw-gso-wire-packets'] -
+                        qstat_old['tx-hw-gso-wire-packets'],
+                        total_lso_wire,
+                        comment="Number of LSO wire-packets with LSO enabled")
+        else:
+            if cfg.have_stat_super_count:
+                ksft_lt(qstat_new['tx-hw-gso-packets'] -
+                        qstat_old['tx-hw-gso-packets'],
+                        15, comment="Number of LSO super-packets with LSO disabled")
+            if cfg.have_stat_wire_count:
+                ksft_lt(qstat_new['tx-hw-gso-wire-packets'] -
+                        qstat_old['tx-hw-gso-wire-packets'],
+                        500, comment="Number of LSO wire-packets with LSO disabled")
+
+
+def build_tunnel(cfg, outer_ipver, tun_info):
+    local_v4  = NetDrvEpEnv.nsim_v4_pfx + "1"
+    local_v6  = NetDrvEpEnv.nsim_v6_pfx + "1"
+    remote_v4 = NetDrvEpEnv.nsim_v4_pfx + "2"
+    remote_v6 = NetDrvEpEnv.nsim_v6_pfx + "2"
+
+    local_addr  = cfg.addr_v[outer_ipver]
+    remote_addr = cfg.remote_addr_v[outer_ipver]
+
+    tun_type = tun_info[0]
+    tun_arg  = tun_info[1]
+    ip(f"link add {tun_type}-ksft type {tun_type} {tun_arg} local {local_addr} remote {remote_addr} dev {cfg.ifname}")
+    defer(ip, f"link del {tun_type}-ksft")
+    ip(f"link set dev {tun_type}-ksft up")
+    ip(f"addr add {local_v4}/24 dev {tun_type}-ksft")
+    ip(f"addr add {local_v6}/64 dev {tun_type}-ksft")
+
+    ip(f"link add {tun_type}-ksft type {tun_type} {tun_arg} local {remote_addr} remote {local_addr} dev {cfg.remote_ifname}",
+        host=cfg.remote)
+    defer(ip, f"link del {tun_type}-ksft", host=cfg.remote)
+    ip(f"link set dev {tun_type}-ksft up", host=cfg.remote)
+    ip(f"addr add {remote_v4}/24 dev {tun_type}-ksft", host=cfg.remote)
+    ip(f"addr add {remote_v6}/64 dev {tun_type}-ksft", host=cfg.remote)
+
+    return remote_v4, remote_v6
+
+
+def restore_wanted_features(cfg):
+    features_cmd = ""
+    for feature in cfg.hw_features:
+        setting = "on" if feature in cfg.wanted_features else "off"
+        features_cmd += f" {feature} {setting}"
+    try:
+        ethtool(f"-K {cfg.ifname} {features_cmd}")
+    except Exception as e:
+        ksft_pr(f"WARNING: failure restoring wanted features: {e}")
+
+
+def test_builder(name, cfg, outer_ipver, feature, tun=None, inner_ipver=None):
+    """Construct specific tests from the common template."""
+    def f(cfg):
+        cfg.require_ipver(outer_ipver)
+        defer(restore_wanted_features, cfg)
+
+        if not cfg.have_stat_super_count and \
+           not cfg.have_stat_wire_count:
+            raise KsftSkipEx(f"Device does not support LSO queue stats")
+
+        if feature not in cfg.hw_features:
+            raise KsftSkipEx(f"Device does not support {feature}")
+
+        ipver = outer_ipver
+        if tun:
+            remote_v4, remote_v6 = build_tunnel(cfg, ipver, tun)
+            ipver = inner_ipver
+        else:
+            remote_v4 = cfg.remote_addr_v["4"]
+            remote_v6 = cfg.remote_addr_v["6"]
+
+        # First test without the feature enabled.
+        ethtool(f"-K {cfg.ifname} {feature} off")
+        run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso=False)
+
+        ethtool(f"-K {cfg.ifname} tx-gso-partial off")
+        ethtool(f"-K {cfg.ifname} tx-tcp-mangleid-segmentation off")
+        if feature in cfg.partial_features:
+            ethtool(f"-K {cfg.ifname} tx-gso-partial on")
+            if ipver == "4":
+                ksft_pr("Testing with mangleid enabled")
+                ethtool(f"-K {cfg.ifname} tx-tcp-mangleid-segmentation on")
+
+        # Full feature enabled.
+        ethtool(f"-K {cfg.ifname} {feature} on")
+        run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso=True)
+
+    f.__name__ = name + ((outer_ipver + "_") if tun else "") + "ipv" + inner_ipver
+    return f
+
+
+def query_nic_features(cfg) -> None:
+    """Query and cache the NIC features."""
+    cfg.have_stat_super_count = False
+    cfg.have_stat_wire_count = False
+
+    features = cfg.ethnl.features_get({"header": {"dev-index": cfg.ifindex}})
+
+    cfg.wanted_features = set()
+    for f in features["wanted"]["bits"]["bit"]:
+        cfg.wanted_features.add(f["name"])
+
+    cfg.hw_features = set()
+    hw_all_features_cmd = ""
+    for f in features["hw"]["bits"]["bit"]:
+        if f.get("value", False):
+            feature = f["name"]
+            cfg.hw_features.add(feature)
+            hw_all_features_cmd += f" {feature} on"
+    try:
+        ethtool(f"-K {cfg.ifname} {hw_all_features_cmd}")
+    except Exception as e:
+        ksft_pr(f"WARNING: failure enabling all hw features: {e}")
+        ksft_pr("partial gso feature detection may be impacted")
+
+    # Check which features are supported via GSO partial
+    cfg.partial_features = set()
+    if 'tx-gso-partial' in cfg.hw_features:
+        ethtool(f"-K {cfg.ifname} tx-gso-partial off")
+
+        no_partial = set()
+        features = cfg.ethnl.features_get({"header": {"dev-index": cfg.ifindex}})
+        for f in features["active"]["bits"]["bit"]:
+            no_partial.add(f["name"])
+        cfg.partial_features = cfg.hw_features - no_partial
+        ethtool(f"-K {cfg.ifname} tx-gso-partial on")
+
+    restore_wanted_features(cfg)
+
+    stats = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)
+    if stats:
+        if 'tx-hw-gso-packets' in stats[0]:
+            ksft_pr("Detected qstat for LSO super-packets")
+            cfg.have_stat_super_count = True
+        if 'tx-hw-gso-wire-packets' in stats[0]:
+            ksft_pr("Detected qstat for LSO wire-packets")
+            cfg.have_stat_wire_count = True
+
+
+def main() -> None:
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+        cfg.ethnl = EthtoolFamily()
+        cfg.netnl = NetdevFamily()
+
+        query_nic_features(cfg)
+
+        test_info = (
+            # name,       v4/v6  ethtool_feature               tun:(type, args, inner ip versions)
+            ("",           "4", "tx-tcp-segmentation",         None),
+            ("",           "6", "tx-tcp6-segmentation",        None),
+            ("vxlan",      "4", "tx-udp_tnl-segmentation",     ("vxlan", "id 100 dstport 4789 noudpcsum", ("4", "6"))),
+            ("vxlan",      "6", "tx-udp_tnl-segmentation",     ("vxlan", "id 100 dstport 4789 udp6zerocsumtx udp6zerocsumrx", ("4", "6"))),
+            ("vxlan_csum", "", "tx-udp_tnl-csum-segmentation", ("vxlan", "id 100 dstport 4789 udpcsum", ("4", "6"))),
+            ("gre",        "4", "tx-gre-segmentation",         ("gre",   "", ("4", "6"))),
+            ("gre",        "6", "tx-gre-segmentation",         ("ip6gre","", ("4", "6"))),
+        )
+
+        cases = []
+        for outer_ipver in ["4", "6"]:
+            for info in test_info:
+                # Skip if test which only works for a specific IP version
+                if info[1] and outer_ipver != info[1]:
+                    continue
+
+                if info[3]:
+                    cases += [
+                        test_builder(info[0], cfg, outer_ipver, info[2], info[3], inner_ipver)
+                        for inner_ipver in info[3][2]
+                    ]
+                else:
+                    cases.append(test_builder(info[0], cfg, outer_ipver, info[2], None, outer_ipver))
+
+        ksft_run(cases=cases, args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/hw/xsk_reconfig.py b/tools/testing/selftests/drivers/net/hw/xsk_reconfig.py
new file mode 100755
index 000000000000..d19d1d518208
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/xsk_reconfig.py
@@ -0,0 +1,60 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+# This is intended to be run on a virtio-net guest interface.
+# The test binds the XDP socket to the interface without setting
+# the fill ring to trigger delayed refill_work. This helps to
+# make it easier to reproduce the deadlock when XDP program,
+# XDP socket bind/unbind, rx ring resize race with refill_work on
+# the buggy kernel.
+#
+# The Qemu command to setup virtio-net
+# -netdev tap,id=hostnet1,vhost=on,script=no,downscript=no
+# -device virtio-net-pci,netdev=hostnet1,iommu_platform=on,disable-legacy=on
+
+from lib.py import ksft_exit, ksft_run
+from lib.py import KsftSkipEx, KsftFailEx
+from lib.py import NetDrvEnv
+from lib.py import bkg, ip, cmd, ethtool
+import time
+
+def _get_rx_ring_entries(cfg):
+    output = ethtool(f"-g {cfg.ifname}", json=True)
+    return output[0]["rx"]
+
+def setup_xsk(cfg, xdp_queue_id = 0) -> bkg:
+    # Probe for support
+    xdp = cmd(f'{cfg.net_lib_dir / "xdp_helper"} - -', fail=False)
+    if xdp.ret == 255:
+        raise KsftSkipEx('AF_XDP unsupported')
+    elif xdp.ret > 0:
+        raise KsftFailEx('unable to create AF_XDP socket')
+
+    try:
+        return bkg(f'{cfg.net_lib_dir / "xdp_helper"} {cfg.ifindex} ' \
+                   '{xdp_queue_id} -z', ksft_wait=3)
+    except:
+        raise KsftSkipEx('Failed to bind XDP socket in zerocopy.\n' \
+                         'Please consider adding iommu_platform=on ' \
+                         'when setting up virtio-net-pci')
+
+def check_xdp_bind(cfg):
+    with setup_xsk(cfg):
+        ip(f"link set dev %s xdp obj %s sec xdp" %
+           (cfg.ifname, cfg.net_lib_dir / "xdp_dummy.bpf.o"))
+        ip(f"link set dev %s xdp off" % cfg.ifname)
+
+def check_rx_resize(cfg):
+    with setup_xsk(cfg):
+        rx_ring = _get_rx_ring_entries(cfg)
+        ethtool(f"-G %s rx %d" % (cfg.ifname, rx_ring // 2))
+        ethtool(f"-G %s rx %d" % (cfg.ifname, rx_ring))
+
+def main():
+    with NetDrvEnv(__file__, nsim_test=False) as cfg:
+        ksft_run([check_xdp_bind, check_rx_resize],
+                 args=(cfg, ))
+    ksft_exit()
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/lib/py/__init__.py b/tools/testing/selftests/drivers/net/lib/py/__init__.py
new file mode 100644
index 000000000000..8b75faa9af6d
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/lib/py/__init__.py
@@ -0,0 +1,55 @@
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+Driver test environment.
+NetDrvEnv and NetDrvEpEnv are the main environment classes.
+Former is for local host only tests, latter creates / connects
+to a remote endpoint. See NIPA wiki for more information about
+running and writing driver tests.
+"""
+
+import sys
+from pathlib import Path
+
+KSFT_DIR = (Path(__file__).parent / "../../../..").resolve()
+
+try:
+    sys.path.append(KSFT_DIR.as_posix())
+
+    # Import one by one to avoid pylint false positives
+    from net.lib.py import NetNS, NetNSEnter, NetdevSimDev
+    from net.lib.py import EthtoolFamily, NetdevFamily, NetshaperFamily, \
+        NlError, RtnlFamily, DevlinkFamily, PSPFamily
+    from net.lib.py import CmdExitFailure
+    from net.lib.py import bkg, cmd, bpftool, bpftrace, defer, ethtool, \
+        fd_read_timeout, ip, rand_port, wait_port_listen, wait_file
+    from net.lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx
+    from net.lib.py import ksft_disruptive, ksft_exit, ksft_pr, ksft_run, \
+        ksft_setup, ksft_variants, KsftNamedVariant
+    from net.lib.py import ksft_eq, ksft_ge, ksft_in, ksft_is, ksft_lt, \
+        ksft_ne, ksft_not_in, ksft_raises, ksft_true, ksft_gt, ksft_not_none
+
+    __all__ = ["NetNS", "NetNSEnter", "NetdevSimDev",
+               "EthtoolFamily", "NetdevFamily", "NetshaperFamily",
+               "NlError", "RtnlFamily", "DevlinkFamily", "PSPFamily",
+               "CmdExitFailure",
+               "bkg", "cmd", "bpftool", "bpftrace", "defer", "ethtool",
+               "fd_read_timeout", "ip", "rand_port",
+               "wait_port_listen", "wait_file",
+               "KsftSkipEx", "KsftFailEx", "KsftXfailEx",
+               "ksft_disruptive", "ksft_exit", "ksft_pr", "ksft_run",
+               "ksft_setup", "ksft_variants", "KsftNamedVariant",
+               "ksft_eq", "ksft_ge", "ksft_in", "ksft_is", "ksft_lt",
+               "ksft_ne", "ksft_not_in", "ksft_raises", "ksft_true", "ksft_gt",
+               "ksft_not_none", "ksft_not_none"]
+
+    from .env import NetDrvEnv, NetDrvEpEnv
+    from .load import GenerateTraffic, Iperf3Runner
+    from .remote import Remote
+
+    __all__ += ["NetDrvEnv", "NetDrvEpEnv", "GenerateTraffic", "Remote",
+                "Iperf3Runner"]
+except ModuleNotFoundError as e:
+    print("Failed importing `net` library from kernel sources")
+    print(str(e))
+    sys.exit(4)
diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py
new file mode 100644
index 000000000000..8b644fd84ff2
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/lib/py/env.py
@@ -0,0 +1,287 @@
+# SPDX-License-Identifier: GPL-2.0
+
+import os
+import time
+from pathlib import Path
+from lib.py import KsftSkipEx, KsftXfailEx
+from lib.py import ksft_setup, wait_file
+from lib.py import cmd, ethtool, ip, CmdExitFailure
+from lib.py import NetNS, NetdevSimDev
+from .remote import Remote
+
+
+class NetDrvEnvBase:
+    """
+    Base class for a NIC / host environments
+
+    Attributes:
+      test_dir: Path to the source directory of the test
+      net_lib_dir: Path to the net/lib directory
+    """
+    def __init__(self, src_path):
+        self.src_path = Path(src_path)
+        self.test_dir = self.src_path.parent.resolve()
+        self.net_lib_dir = (Path(__file__).parent / "../../../../net/lib").resolve()
+
+        self.env = self._load_env_file()
+
+        # Following attrs must be set be inheriting classes
+        self.dev = None
+
+    def _load_env_file(self):
+        env = os.environ.copy()
+
+        src_dir = Path(self.src_path).parent.resolve()
+        if not (src_dir / "net.config").exists():
+            return ksft_setup(env)
+
+        with open((src_dir / "net.config").as_posix(), 'r') as fp:
+            for line in fp.readlines():
+                full_file = line
+                # Strip comments
+                pos = line.find("#")
+                if pos >= 0:
+                    line = line[:pos]
+                line = line.strip()
+                if not line:
+                    continue
+                pair = line.split('=', maxsplit=1)
+                if len(pair) != 2:
+                    raise Exception("Can't parse configuration line:", full_file)
+                env[pair[0]] = pair[1]
+        return ksft_setup(env)
+
+    def __del__(self):
+        pass
+
+    def __enter__(self):
+        ip(f"link set dev {self.dev['ifname']} up")
+        wait_file(f"/sys/class/net/{self.dev['ifname']}/carrier",
+                  lambda x: x.strip() == "1")
+
+        return self
+
+    def __exit__(self, ex_type, ex_value, ex_tb):
+        """
+        __exit__ gets called at the end of a "with" block.
+        """
+        self.__del__()
+
+
+class NetDrvEnv(NetDrvEnvBase):
+    """
+    Class for a single NIC / host env, with no remote end
+    """
+    def __init__(self, src_path, nsim_test=None, **kwargs):
+        super().__init__(src_path)
+
+        self._ns = None
+
+        if 'NETIF' in self.env:
+            if nsim_test is True:
+                raise KsftXfailEx("Test only works on netdevsim")
+
+            self.dev = ip("-d link show dev " + self.env['NETIF'], json=True)[0]
+        else:
+            if nsim_test is False:
+                raise KsftXfailEx("Test does not work on netdevsim")
+
+            self._ns = NetdevSimDev(**kwargs)
+            self.dev = self._ns.nsims[0].dev
+        self.ifname = self.dev['ifname']
+        self.ifindex = self.dev['ifindex']
+
+    def __del__(self):
+        if self._ns:
+            self._ns.remove()
+            self._ns = None
+
+
+class NetDrvEpEnv(NetDrvEnvBase):
+    """
+    Class for an environment with a local device and "remote endpoint"
+    which can be used to send traffic in.
+
+    For local testing it creates two network namespaces and a pair
+    of netdevsim devices.
+    """
+
+    # Network prefixes used for local tests
+    nsim_v4_pfx = "192.0.2."
+    nsim_v6_pfx = "2001:db8::"
+
+    def __init__(self, src_path, nsim_test=None):
+        super().__init__(src_path)
+
+        self._stats_settle_time = None
+
+        # Things we try to destroy
+        self.remote = None
+        # These are for local testing state
+        self._netns = None
+        self._ns = None
+        self._ns_peer = None
+
+        self.addr_v        = { "4": None, "6": None }
+        self.remote_addr_v = { "4": None, "6": None }
+
+        if "NETIF" in self.env:
+            if nsim_test is True:
+                raise KsftXfailEx("Test only works on netdevsim")
+            self._check_env()
+
+            self.dev = ip("-d link show dev " + self.env['NETIF'], json=True)[0]
+
+            self.addr_v["4"] = self.env.get("LOCAL_V4")
+            self.addr_v["6"] = self.env.get("LOCAL_V6")
+            self.remote_addr_v["4"] = self.env.get("REMOTE_V4")
+            self.remote_addr_v["6"] = self.env.get("REMOTE_V6")
+            kind = self.env["REMOTE_TYPE"]
+            args = self.env["REMOTE_ARGS"]
+        else:
+            if nsim_test is False:
+                raise KsftXfailEx("Test does not work on netdevsim")
+
+            self.create_local()
+
+            self.dev = self._ns.nsims[0].dev
+
+            self.addr_v["4"] = self.nsim_v4_pfx + "1"
+            self.addr_v["6"] = self.nsim_v6_pfx + "1"
+            self.remote_addr_v["4"] = self.nsim_v4_pfx + "2"
+            self.remote_addr_v["6"] = self.nsim_v6_pfx + "2"
+            kind = "netns"
+            args = self._netns.name
+
+        self.remote = Remote(kind, args, src_path)
+
+        self.addr_ipver = "6" if self.addr_v["6"] else "4"
+        self.addr = self.addr_v[self.addr_ipver]
+        self.remote_addr = self.remote_addr_v[self.addr_ipver]
+
+        # Bracketed addresses, some commands need IPv6 to be inside []
+        self.baddr = f"[{self.addr_v['6']}]" if self.addr_v["6"] else self.addr_v["4"]
+        self.remote_baddr = f"[{self.remote_addr_v['6']}]" if self.remote_addr_v["6"] else self.remote_addr_v["4"]
+
+        self.ifname = self.dev['ifname']
+        self.ifindex = self.dev['ifindex']
+
+        # resolve remote interface name
+        self.remote_ifname = self.resolve_remote_ifc()
+        self.remote_dev = ip("-d link show dev " + self.remote_ifname,
+                             host=self.remote, json=True)[0]
+
+        self._required_cmd = {}
+
+    def create_local(self):
+        self._netns = NetNS()
+        self._ns = NetdevSimDev()
+        self._ns_peer = NetdevSimDev(ns=self._netns)
+
+        with open("/proc/self/ns/net") as nsfd0, \
+             open("/var/run/netns/" + self._netns.name) as nsfd1:
+            ifi0 = self._ns.nsims[0].ifindex
+            ifi1 = self._ns_peer.nsims[0].ifindex
+            NetdevSimDev.ctrl_write('link_device',
+                                    f'{nsfd0.fileno()}:{ifi0} {nsfd1.fileno()}:{ifi1}')
+
+        ip(f"   addr add dev {self._ns.nsims[0].ifname} {self.nsim_v4_pfx}1/24")
+        ip(f"-6 addr add dev {self._ns.nsims[0].ifname} {self.nsim_v6_pfx}1/64 nodad")
+        ip(f"   link set dev {self._ns.nsims[0].ifname} up")
+
+        ip(f"   addr add dev {self._ns_peer.nsims[0].ifname} {self.nsim_v4_pfx}2/24", ns=self._netns)
+        ip(f"-6 addr add dev {self._ns_peer.nsims[0].ifname} {self.nsim_v6_pfx}2/64 nodad", ns=self._netns)
+        ip(f"   link set dev {self._ns_peer.nsims[0].ifname} up", ns=self._netns)
+
+    def _check_env(self):
+        vars_needed = [
+            ["LOCAL_V4", "LOCAL_V6"],
+            ["REMOTE_V4", "REMOTE_V6"],
+            ["REMOTE_TYPE"],
+            ["REMOTE_ARGS"]
+        ]
+        missing = []
+
+        for choice in vars_needed:
+            for entry in choice:
+                if entry in self.env:
+                    break
+            else:
+                missing.append(choice)
+        # Make sure v4 / v6 configs are symmetric
+        if ("LOCAL_V6" in self.env) != ("REMOTE_V6" in self.env):
+            missing.append(["LOCAL_V6", "REMOTE_V6"])
+        if ("LOCAL_V4" in self.env) != ("REMOTE_V4" in self.env):
+            missing.append(["LOCAL_V4", "REMOTE_V4"])
+        if missing:
+            raise Exception("Invalid environment, missing configuration:", missing,
+                            "Please see tools/testing/selftests/drivers/net/README.rst")
+
+    def resolve_remote_ifc(self):
+        v4 = v6 = None
+        if self.remote_addr_v["4"]:
+            v4 = ip("addr show to " + self.remote_addr_v["4"], json=True, host=self.remote)
+        if self.remote_addr_v["6"]:
+            v6 = ip("addr show to " + self.remote_addr_v["6"], json=True, host=self.remote)
+        if v4 and v6 and v4[0]["ifname"] != v6[0]["ifname"]:
+            raise Exception("Can't resolve remote interface name, v4 and v6 don't match")
+        if (v4 and len(v4) > 1) or (v6 and len(v6) > 1):
+            raise Exception("Can't resolve remote interface name, multiple interfaces match")
+        return v6[0]["ifname"] if v6 else v4[0]["ifname"]
+
+    def __del__(self):
+        if self._ns:
+            self._ns.remove()
+            self._ns = None
+        if self._ns_peer:
+            self._ns_peer.remove()
+            self._ns_peer = None
+        if self._netns:
+            del self._netns
+            self._netns = None
+        if self.remote:
+            del self.remote
+            self.remote = None
+
+    def require_ipver(self, ipver):
+        if not self.addr_v[ipver] or not self.remote_addr_v[ipver]:
+            raise KsftSkipEx(f"Test requires IPv{ipver} connectivity")
+
+    def require_nsim(self):
+        if self._ns is None:
+            raise KsftXfailEx("Test only works on netdevsim")
+
+    def _require_cmd(self, comm, key, host=None):
+        cached = self._required_cmd.get(comm, {})
+        if cached.get(key) is None:
+            cached[key] = cmd("command -v -- " + comm, fail=False,
+                              shell=True, host=host).ret == 0
+        self._required_cmd[comm] = cached
+        return cached[key]
+
+    def require_cmd(self, comm, local=True, remote=False):
+        if local:
+            if not self._require_cmd(comm, "local"):
+                raise KsftSkipEx("Test requires command: " + comm)
+        if remote:
+            if not self._require_cmd(comm, "remote", host=self.remote):
+                raise KsftSkipEx("Test requires (remote) command: " + comm)
+
+    def wait_hw_stats_settle(self):
+        """
+        Wait for HW stats to become consistent, some devices DMA HW stats
+        periodically so events won't be reflected until next sync.
+        Good drivers will tell us via ethtool what their sync period is.
+        """
+        if self._stats_settle_time is None:
+            data = {}
+            try:
+                data = ethtool("-c " + self.ifname, json=True)[0]
+            except CmdExitFailure as e:
+                if "Operation not supported" not in e.cmd.stderr:
+                    raise
+
+            self._stats_settle_time = 0.025 + \
+                data.get('stats-block-usecs', 0) / 1000 / 1000
+
+        time.sleep(self._stats_settle_time)
diff --git a/tools/testing/selftests/drivers/net/lib/py/load.py b/tools/testing/selftests/drivers/net/lib/py/load.py
new file mode 100644
index 000000000000..f181fa2d38fc
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/lib/py/load.py
@@ -0,0 +1,139 @@
+# SPDX-License-Identifier: GPL-2.0
+
+import re
+import time
+import json
+
+from lib.py import ksft_pr, cmd, ip, rand_port, wait_port_listen
+
+
+class Iperf3Runner:
+    """
+    Sets up and runs iperf3 traffic.
+    """
+    def __init__(self, env, port=None, server_ip=None, client_ip=None):
+        env.require_cmd("iperf3", local=True, remote=True)
+        self.env = env
+        self.port = rand_port() if port is None else port
+        self.server_ip = server_ip
+        self.client_ip = client_ip
+
+    def _build_server(self):
+        cmdline = f"iperf3 -s -1 -p {self.port}"
+        if self.server_ip:
+            cmdline += f" -B {self.server_ip}"
+        return cmdline
+
+    def _build_client(self, streams, duration, reverse):
+        host = self.env.addr if self.server_ip is None else self.server_ip
+        cmdline = f"iperf3 -c {host} -p {self.port} -P {streams} -t {duration} -J"
+        if self.client_ip:
+            cmdline += f" -B {self.client_ip}"
+        if reverse:
+            cmdline += " --reverse"
+        return cmdline
+
+    def start_server(self):
+        """
+        Starts an iperf3 server with optional bind IP.
+        """
+        cmdline = self._build_server()
+        proc = cmd(cmdline, background=True)
+        wait_port_listen(self.port)
+        time.sleep(0.1)
+        return proc
+
+    def start_client(self, background=False, streams=1, duration=10, reverse=False):
+        """
+        Starts the iperf3 client with the configured options.
+        """
+        cmdline = self._build_client(streams, duration, reverse)
+        return cmd(cmdline, background=background, host=self.env.remote)
+
+    def measure_bandwidth(self, reverse=False):
+        """
+        Runs an iperf3 measurement and returns the average bandwidth (Gbps).
+        Discards the first and last few reporting intervals and uses only the
+        middle part of the run where throughput is typically stable.
+        """
+        self.start_server()
+        result = self.start_client(duration=10, reverse=reverse)
+
+        if result.ret != 0:
+            raise RuntimeError("iperf3 failed to run successfully")
+        try:
+            out = json.loads(result.stdout)
+        except json.JSONDecodeError as exc:
+            raise ValueError("Failed to parse iperf3 JSON output") from exc
+
+        intervals = out.get("intervals", [])
+        samples = [i["sum"]["bits_per_second"] / 1e9 for i in intervals]
+        if len(samples) < 10:
+            raise ValueError(f"iperf3 returned too few intervals: {len(samples)}")
+        # Discard potentially unstable first and last 3 seconds.
+        stable = samples[3:-3]
+
+        avg = sum(stable) / len(stable)
+
+        return avg
+
+
+class GenerateTraffic:
+    def __init__(self, env, port=None):
+        self.env = env
+        self.runner = Iperf3Runner(env, port)
+
+        self._iperf_server = self.runner.start_server()
+        self._iperf_client = self.runner.start_client(background=True, streams=16, duration=86400)
+
+        # Wait for traffic to ramp up
+        if not self._wait_pkts(pps=1000):
+            self.stop(verbose=True)
+            raise Exception("iperf3 traffic did not ramp up")
+
+    def _wait_pkts(self, pkt_cnt=None, pps=None):
+        """
+        Wait until we've seen pkt_cnt or until traffic ramps up to pps.
+        Only one of pkt_cnt or pss can be specified.
+        """
+        pkt_start = ip("-s link show dev " + self.env.ifname, json=True)[0]["stats64"]["rx"]["packets"]
+        for _ in range(50):
+            time.sleep(0.1)
+            pkt_now = ip("-s link show dev " + self.env.ifname, json=True)[0]["stats64"]["rx"]["packets"]
+            if pps:
+                if pkt_now - pkt_start > pps / 10:
+                    return True
+                pkt_start = pkt_now
+            elif pkt_cnt:
+                if pkt_now - pkt_start > pkt_cnt:
+                    return True
+        return False
+
+    def wait_pkts_and_stop(self, pkt_cnt):
+        failed = not self._wait_pkts(pkt_cnt=pkt_cnt)
+        self.stop(verbose=failed)
+
+    def stop(self, verbose=None):
+        self._iperf_client.process(terminate=True)
+        if verbose:
+            ksft_pr(">> Client:")
+            ksft_pr(self._iperf_client.stdout)
+            ksft_pr(self._iperf_client.stderr)
+        self._iperf_server.process(terminate=True)
+        if verbose:
+            ksft_pr(">> Server:")
+            ksft_pr(self._iperf_server.stdout)
+            ksft_pr(self._iperf_server.stderr)
+        self._wait_client_stopped()
+
+    def _wait_client_stopped(self, sleep=0.005, timeout=5):
+        end = time.monotonic() + timeout
+
+        live_port_pattern = re.compile(fr":{self.runner.port:04X} 0[^6] ")
+
+        while time.monotonic() < end:
+            data = cmd("cat /proc/net/tcp*", host=self.env.remote).stdout
+            if not live_port_pattern.search(data):
+                return
+            time.sleep(sleep)
+        raise Exception(f"Waiting for client to stop timed out after {timeout}s")
diff --git a/tools/testing/selftests/drivers/net/lib/py/remote.py b/tools/testing/selftests/drivers/net/lib/py/remote.py
new file mode 100644
index 000000000000..b1780b987722
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/lib/py/remote.py
@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0
+
+import os
+import importlib
+
+_modules = {}
+
+def Remote(kind, args, src_path):
+    global _modules
+
+    if kind not in _modules:
+        _modules[kind] = importlib.import_module("..remote_" + kind, __name__)
+
+    dir_path = os.path.abspath(src_path + "/../")
+    return getattr(_modules[kind], "Remote")(args, dir_path)
diff --git a/tools/testing/selftests/drivers/net/lib/py/remote_netns.py b/tools/testing/selftests/drivers/net/lib/py/remote_netns.py
new file mode 100644
index 000000000000..7d5eeb0271bc
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/lib/py/remote_netns.py
@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: GPL-2.0
+
+import os
+import subprocess
+
+from lib.py import cmd
+
+
+class Remote:
+    def __init__(self, name, dir_path):
+        self.name = name
+        self.dir_path = dir_path
+
+    def cmd(self, comm):
+        return subprocess.Popen(["ip", "netns", "exec", self.name, "bash", "-c", comm],
+                                 stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+
+    def deploy(self, what):
+        if os.path.isabs(what):
+            return what
+        return os.path.abspath(self.dir_path + "/" + what)
diff --git a/tools/testing/selftests/drivers/net/lib/py/remote_ssh.py b/tools/testing/selftests/drivers/net/lib/py/remote_ssh.py
new file mode 100644
index 000000000000..924addde19a3
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/lib/py/remote_ssh.py
@@ -0,0 +1,39 @@
+# SPDX-License-Identifier: GPL-2.0
+
+import os
+import string
+import subprocess
+import random
+
+from lib.py import cmd
+
+
+class Remote:
+    def __init__(self, name, dir_path):
+        self.name = name
+        self.dir_path = dir_path
+        self._tmpdir = None
+
+    def __del__(self):
+        if self._tmpdir:
+            cmd("rm -rf " + self._tmpdir, host=self)
+            self._tmpdir = None
+
+    def cmd(self, comm):
+        return subprocess.Popen(["ssh", "-q", self.name, comm],
+                                stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+
+    def _mktmp(self):
+        return ''.join(random.choice(string.ascii_lowercase) for _ in range(8))
+
+    def deploy(self, what):
+        if not self._tmpdir:
+            self._tmpdir = "/tmp/" + self._mktmp()
+            cmd("mkdir " + self._tmpdir, host=self)
+        file_name = self._tmpdir + "/" + self._mktmp() + os.path.basename(what)
+
+        if not os.path.isabs(what):
+            what = os.path.abspath(self.dir_path + "/" + what)
+
+        cmd(f"scp {what} {self.name}:{file_name}")
+        return file_name
diff --git a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh
new file mode 100644
index 000000000000..ae8abff4be40
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh
@@ -0,0 +1,419 @@
+#!/usr/bin/env bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This file contains functions and helpers to support the netconsole
+# selftests
+#
+# Author: Breno Leitao <leitao@debian.org>
+
+set -euo pipefail
+
+LIBDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")")
+
+SRCIF="" # to be populated later
+SRCIP="" # to be populated later
+SRCIP4="192.0.2.1"
+SRCIP6="fc00::1"
+DSTIF="" # to be populated later
+DSTIP="" # to be populated later
+DSTIP4="192.0.2.2"
+DSTIP6="fc00::2"
+
+PORT="6666"
+MSG="netconsole selftest"
+USERDATA_KEY="key"
+USERDATA_VALUE="value"
+TARGET=$(mktemp -u netcons_XXXXX)
+DEFAULT_PRINTK_VALUES=$(cat /proc/sys/kernel/printk)
+NETCONS_CONFIGFS="/sys/kernel/config/netconsole"
+NETCONS_PATH="${NETCONS_CONFIGFS}"/"${TARGET}"
+# NAMESPACE will be populated by setup_ns with a random value
+NAMESPACE=""
+
+# IDs for netdevsim. We either use NSIM_DEV_{1,2}_ID for standard test
+# or NSIM_BOND_{T,R}X_{1,2} for the bonding tests. Not both at the
+# same time.
+NSIM_DEV_1_ID=$((256 + RANDOM % 256))
+NSIM_DEV_2_ID=$((512 + RANDOM % 256))
+NSIM_BOND_TX_1=$((768 + RANDOM % 256))
+NSIM_BOND_TX_2=$((1024 + RANDOM % 256))
+NSIM_BOND_RX_1=$((1280 + RANDOM % 256))
+NSIM_BOND_RX_2=$((1536 + RANDOM % 256))
+NSIM_DEV_SYS_NEW="/sys/bus/netdevsim/new_device"
+NSIM_DEV_SYS_LINK="/sys/bus/netdevsim/link_device"
+
+# Used to create and delete namespaces
+source "${LIBDIR}"/../../../../net/lib.sh
+
+# Create netdevsim interfaces
+create_ifaces() {
+	echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_NEW"
+	echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_NEW"
+	udevadm settle 2> /dev/null || true
+
+	local NSIM1=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_1_ID"
+	local NSIM2=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_2_ID"
+
+	# These are global variables
+	SRCIF=$(find "$NSIM1"/net -maxdepth 1 -type d ! \
+		-path "$NSIM1"/net -exec basename {} \;)
+	DSTIF=$(find "$NSIM2"/net -maxdepth 1 -type d ! \
+		-path "$NSIM2"/net -exec basename {} \;)
+}
+
+link_ifaces() {
+	local NSIM_DEV_SYS_LINK="/sys/bus/netdevsim/link_device"
+	local SRCIF_IFIDX=$(cat /sys/class/net/"$SRCIF"/ifindex)
+	local DSTIF_IFIDX=$(cat /sys/class/net/"$DSTIF"/ifindex)
+
+	exec {NAMESPACE_FD}</var/run/netns/"${NAMESPACE}"
+	exec {INITNS_FD}</proc/self/ns/net
+
+	# Bind the dst interface to namespace
+	ip link set "${DSTIF}" netns "${NAMESPACE}"
+
+	# Linking one device to the other one (on the other namespace}
+	if ! echo "${INITNS_FD}:$SRCIF_IFIDX $NAMESPACE_FD:$DSTIF_IFIDX"  > $NSIM_DEV_SYS_LINK
+	then
+		echo "linking netdevsim1 with netdevsim2 should succeed"
+		cleanup
+		exit "${ksft_skip}"
+	fi
+}
+
+function configure_ip() {
+	# Configure the IPs for both interfaces
+	ip netns exec "${NAMESPACE}" ip addr add "${DSTIP}"/24 dev "${DSTIF}"
+	ip netns exec "${NAMESPACE}" ip link set "${DSTIF}" up
+
+	ip addr add "${SRCIP}"/24 dev "${SRCIF}"
+	ip link set "${SRCIF}" up
+}
+
+function select_ipv4_or_ipv6()
+{
+	local VERSION=${1}
+
+	if [[ "$VERSION" == "ipv6" ]]
+	then
+		DSTIP="${DSTIP6}"
+		SRCIP="${SRCIP6}"
+	else
+		DSTIP="${DSTIP4}"
+		SRCIP="${SRCIP4}"
+	fi
+}
+
+function set_network() {
+	local IP_VERSION=${1:-"ipv4"}
+
+	# setup_ns function is coming from lib.sh
+	setup_ns NAMESPACE
+
+	# Create both interfaces, and assign the destination to a different
+	# namespace
+	create_ifaces
+
+	# Link both interfaces back to back
+	link_ifaces
+
+	select_ipv4_or_ipv6 "${IP_VERSION}"
+	configure_ip
+}
+
+function _create_dynamic_target() {
+	local FORMAT="${1:?FORMAT parameter required}"
+	local NCPATH="${2:?NCPATH parameter required}"
+
+	DSTMAC=$(ip netns exec "${NAMESPACE}" \
+		 ip link show "${DSTIF}" | awk '/ether/ {print $2}')
+
+	# Create a dynamic target
+	mkdir "${NCPATH}"
+
+	echo "${DSTIP}" > "${NCPATH}"/remote_ip
+	echo "${SRCIP}" > "${NCPATH}"/local_ip
+	echo "${DSTMAC}" > "${NCPATH}"/remote_mac
+	echo "${SRCIF}" > "${NCPATH}"/dev_name
+
+	if [ "${FORMAT}" == "basic" ]
+	then
+		# Basic target does not support release
+		echo 0 > "${NCPATH}"/release
+		echo 0 > "${NCPATH}"/extended
+	elif [ "${FORMAT}" == "extended" ]
+	then
+		echo 1 > "${NCPATH}"/extended
+	fi
+}
+
+function create_dynamic_target() {
+	local FORMAT=${1:-"extended"}
+	local NCPATH=${2:-"$NETCONS_PATH"}
+	_create_dynamic_target "${FORMAT}" "${NCPATH}"
+
+	echo 1 > "${NCPATH}"/enabled
+
+	# This will make sure that the kernel was able to
+	# load the netconsole driver configuration. The console message
+	# gets more organized/sequential as well.
+	sleep 1
+}
+
+# Generate the command line argument for netconsole following:
+#  netconsole=[+][src-port]@[src-ip]/[<dev>],[tgt-port]@<tgt-ip>/[tgt-macaddr]
+function create_cmdline_str() {
+	local BINDMODE=${1:-"ifname"}
+	if [ "${BINDMODE}" == "ifname" ]
+	then
+		SRCDEV=${SRCIF}
+	else
+		SRCDEV=$(mac_get "${SRCIF}")
+	fi
+
+	DSTMAC=$(ip netns exec "${NAMESPACE}" \
+		 ip link show "${DSTIF}" | awk '/ether/ {print $2}')
+	SRCPORT="1514"
+	TGTPORT="6666"
+
+	echo "netconsole=\"+${SRCPORT}@${SRCIP}/${SRCDEV},${TGTPORT}@${DSTIP}/${DSTMAC}\""
+}
+
+# Do not append the release to the header of the message
+function disable_release_append() {
+	echo 0 > "${NETCONS_PATH}"/enabled
+	echo 0 > "${NETCONS_PATH}"/release
+	echo 1 > "${NETCONS_PATH}"/enabled
+}
+
+function do_cleanup() {
+	local NSIM_DEV_SYS_DEL="/sys/bus/netdevsim/del_device"
+
+	# Delete netdevsim devices
+	echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_DEL"
+	echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_DEL"
+
+	# this is coming from lib.sh
+	cleanup_all_ns
+
+	# Restoring printk configurations
+	echo "${DEFAULT_PRINTK_VALUES}" > /proc/sys/kernel/printk
+}
+
+function cleanup_netcons() {
+	# delete netconsole dynamic reconfiguration
+	# do not fail if the target is already disabled
+	if [[ ! -d "${NETCONS_PATH}" ]]
+	then
+		# in some cases this is called before netcons path is created
+		return
+	fi
+	if [[ $(cat "${NETCONS_PATH}"/enabled) != 0 ]]
+	then
+		echo 0 > "${NETCONS_PATH}"/enabled || true
+	fi
+	# Remove all the keys that got created during the selftest
+	find "${NETCONS_PATH}/userdata/" -mindepth 1 -type d -delete
+	# Remove the configfs entry
+	rmdir "${NETCONS_PATH}"
+}
+
+function cleanup() {
+	cleanup_netcons
+	do_cleanup
+}
+
+function set_user_data() {
+	if [[ ! -d "${NETCONS_PATH}""/userdata" ]]
+	then
+		echo "Userdata path not available in ${NETCONS_PATH}/userdata"
+		exit "${ksft_skip}"
+	fi
+
+	KEY_PATH="${NETCONS_PATH}/userdata/${USERDATA_KEY}"
+	mkdir -p "${KEY_PATH}"
+	VALUE_PATH="${KEY_PATH}""/value"
+	echo "${USERDATA_VALUE}" > "${VALUE_PATH}"
+}
+
+function listen_port_and_save_to() {
+	local OUTPUT=${1}
+	local IPVERSION=${2:-"ipv4"}
+
+	if [ "${IPVERSION}" == "ipv4" ]
+	then
+		SOCAT_MODE="UDP-LISTEN"
+	else
+		SOCAT_MODE="UDP6-LISTEN"
+	fi
+
+	# Just wait for 2 seconds
+	timeout 2 ip netns exec "${NAMESPACE}" \
+		socat "${SOCAT_MODE}":"${PORT}",fork "${OUTPUT}" 2> /dev/null
+}
+
+# Only validate that the message arrived properly
+function validate_msg() {
+	local TMPFILENAME="$1"
+
+	# Check if the file exists
+	if [ ! -f "$TMPFILENAME" ]; then
+		echo "FAIL: File was not generated." >&2
+		exit "${ksft_fail}"
+	fi
+
+	if ! grep -q "${MSG}" "${TMPFILENAME}"; then
+		echo "FAIL: ${MSG} not found in ${TMPFILENAME}" >&2
+		cat "${TMPFILENAME}" >&2
+		exit "${ksft_fail}"
+	fi
+}
+
+# Validate the message and userdata
+function validate_result() {
+	local TMPFILENAME="$1"
+
+	# TMPFILENAME will contain something like:
+	# 6.11.1-0_fbk0_rc13_509_g30d75cea12f7,13,1822,115075213798,-;netconsole selftest: netcons_gtJHM
+	#  key=value
+
+	validate_msg "${TMPFILENAME}"
+
+	# userdata is not supported on basic format target,
+	# thus, do not validate it.
+	if [ "${FORMAT}" != "basic" ];
+	then
+		if ! grep -q "${USERDATA_KEY}=${USERDATA_VALUE}" "${TMPFILENAME}"; then
+			echo "FAIL: ${USERDATA_KEY}=${USERDATA_VALUE} not found in ${TMPFILENAME}" >&2
+			cat "${TMPFILENAME}" >&2
+			exit "${ksft_fail}"
+		fi
+	fi
+
+	# Delete the file once it is validated, otherwise keep it
+	# for debugging purposes
+	rm "${TMPFILENAME}"
+}
+
+function check_for_dependencies() {
+	if [ "$(id -u)" -ne 0 ]; then
+		echo "This test must be run as root" >&2
+		exit "${ksft_skip}"
+	fi
+
+	if ! which socat > /dev/null ; then
+		echo "SKIP: socat(1) is not available" >&2
+		exit "${ksft_skip}"
+	fi
+
+	if ! which ip > /dev/null ; then
+		echo "SKIP: ip(1) is not available" >&2
+		exit "${ksft_skip}"
+	fi
+
+	if ! which udevadm > /dev/null ; then
+		echo "SKIP: udevadm(1) is not available" >&2
+		exit "${ksft_skip}"
+	fi
+
+	if [ ! -f /proc/net/if_inet6 ]; then
+		echo "SKIP: IPv6 not configured. Check if CONFIG_IPV6 is enabled" >&2
+		exit "${ksft_skip}"
+	fi
+
+	if [ ! -f "${NSIM_DEV_SYS_NEW}" ]; then
+		echo "SKIP: file ${NSIM_DEV_SYS_NEW} does not exist. Check if CONFIG_NETDEVSIM is enabled" >&2
+		exit "${ksft_skip}"
+	fi
+
+	if [ ! -d "${NETCONS_CONFIGFS}" ]; then
+		echo "SKIP: directory ${NETCONS_CONFIGFS} does not exist. Check if NETCONSOLE_DYNAMIC is enabled" >&2
+		exit "${ksft_skip}"
+	fi
+
+	if ip link show "${DSTIF}" 2> /dev/null; then
+		echo "SKIP: interface ${DSTIF} exists in the system. Not overwriting it." >&2
+		exit "${ksft_skip}"
+	fi
+
+	REGEXP4="inet.*(${SRCIP4}|${DSTIP4})"
+	REGEXP6="inet.*(${SRCIP6}|${DSTIP6})"
+	if ip addr list | grep -E "${REGEXP4}" 2> /dev/null; then
+		echo "SKIP: IPv4s already in use. Skipping it" >&2
+		exit "${ksft_skip}"
+	fi
+
+	if ip addr list | grep -E "${REGEXP6}" 2> /dev/null; then
+		echo "SKIP: IPv6s already in use. Skipping it" >&2
+		exit "${ksft_skip}"
+	fi
+}
+
+function check_for_taskset() {
+	if ! which taskset > /dev/null ; then
+		echo "SKIP: taskset(1) is not available" >&2
+		exit "${ksft_skip}"
+	fi
+}
+
+# This is necessary if running multiple tests in a row
+function pkill_socat() {
+	PROCESS_NAME4="socat UDP-LISTEN:6666,fork ${OUTPUT_FILE}"
+	PROCESS_NAME6="socat UDP6-LISTEN:6666,fork ${OUTPUT_FILE}"
+	# socat runs under timeout(1), kill it if it is still alive
+	# do not fail if socat doesn't exist anymore
+	set +e
+	pkill -f "${PROCESS_NAME4}"
+	pkill -f "${PROCESS_NAME6}"
+	set -e
+}
+
+# Check if netconsole was compiled as a module, otherwise exit
+function check_netconsole_module() {
+	if modinfo netconsole | grep filename: | grep -q builtin
+	then
+		echo "SKIP: netconsole should be compiled as a module" >&2
+		exit "${ksft_skip}"
+	fi
+}
+
+# A wrapper to translate protocol version to udp version
+function wait_for_port() {
+	local NAMESPACE=${1}
+	local PORT=${2}
+	IP_VERSION=${3}
+
+	if [ "${IP_VERSION}" == "ipv6" ]
+	then
+		PROTOCOL="udp6"
+	else
+		PROTOCOL="udp"
+	fi
+
+	wait_local_port_listen "${NAMESPACE}" "${PORT}" "${PROTOCOL}"
+	# even after the port is open, let's wait 1 second before writing
+	# otherwise the packet could be missed, and the test will fail. Happens
+	# more frequently on IPv6
+	sleep 1
+}
+
+# Clean up netdevsim ifaces created for bonding test
+function cleanup_bond_nsim() {
+	ip -n "${TXNS}" \
+		link delete "${BOND_TX_MAIN_IF}" type bond || true
+	ip -n "${RXNS}" \
+		link delete "${BOND_RX_MAIN_IF}" type bond || true
+
+	cleanup_netdevsim "$NSIM_BOND_TX_1"
+	cleanup_netdevsim "$NSIM_BOND_TX_2"
+	cleanup_netdevsim "$NSIM_BOND_RX_1"
+	cleanup_netdevsim "$NSIM_BOND_RX_2"
+}
+
+# cleanup tests that use bonding interfaces
+function cleanup_bond() {
+	cleanup_netcons
+	cleanup_bond_nsim
+	cleanup_all_ns
+	ip link delete "${VETH0}" || true
+}
diff --git a/tools/testing/selftests/drivers/net/microchip/ksz9477_qos.sh b/tools/testing/selftests/drivers/net/microchip/ksz9477_qos.sh
new file mode 100755
index 000000000000..82be5d013330
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/microchip/ksz9477_qos.sh
@@ -0,0 +1,668 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2024 Pengutronix, Oleksij Rempel <kernel@pengutronix.de>
+
+# The script is adopted to work with the Microchip KSZ switch driver.
+
+ETH_FCS_LEN=4
+
+WAIT_TIME=1
+NUM_NETIFS=4
+REQUIRE_JQ="yes"
+REQUIRE_MZ="yes"
+STABLE_MAC_ADDRS=yes
+NETIF_CREATE=no
+lib_dir=$(dirname $0)/../../../net/forwarding
+source $lib_dir/tc_common.sh
+source $lib_dir/lib.sh
+
+require_command dcb
+
+h1=${NETIFS[p1]}
+swp1=${NETIFS[p2]}
+swp2=${NETIFS[p3]}
+h2=${NETIFS[p4]}
+
+H1_IPV4="192.0.2.1"
+H2_IPV4="192.0.2.2"
+H1_IPV6="2001:db8:1::1"
+H2_IPV6="2001:db8:1::2"
+
+# On h1_ and h2_create do not set IP addresses to avoid interaction with the
+# system, to keep packet counters clean.
+h1_create()
+{
+	simple_if_init $h1
+	sysctl_set net.ipv6.conf.${h1}.disable_ipv6 1
+	# Get the MAC address of the interface to use it with mausezahn
+	h1_mac=$(ip -j link show dev ${h1} | jq -e '.[].address')
+}
+
+h1_destroy()
+{
+	sysctl_restore net.ipv6.conf.${h1}.disable_ipv6
+	simple_if_fini $h1
+}
+
+h2_create()
+{
+	simple_if_init $h2
+	sysctl_set net.ipv6.conf.${h2}.disable_ipv6 1
+	h2_mac=$(ip -j link show dev ${h2} | jq -e '.[].address')
+}
+
+h2_destroy()
+{
+	sysctl_restore net.ipv6.conf.${h2}.disable_ipv6
+	simple_if_fini $h2
+}
+
+switch_create()
+{
+	ip link set ${swp1} up
+	ip link set ${swp2} up
+	sysctl_set net.ipv6.conf.${swp1}.disable_ipv6 1
+	sysctl_set net.ipv6.conf.${swp2}.disable_ipv6 1
+
+	# Ports should trust VLAN PCP even with vlan_filtering=0
+	ip link add br0 type bridge
+	ip link set ${swp1} master br0
+	ip link set ${swp2} master br0
+	ip link set br0 up
+	sysctl_set net.ipv6.conf.br0.disable_ipv6 1
+}
+
+switch_destroy()
+{
+	sysctl_restore net.ipv6.conf.${swp2}.disable_ipv6
+	sysctl_restore net.ipv6.conf.${swp1}.disable_ipv6
+
+	ip link del br0
+}
+
+setup_prepare()
+{
+	vrf_prepare
+
+	h1_create
+	h2_create
+	switch_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	h2_destroy
+	h1_destroy
+	switch_destroy
+
+	vrf_cleanup
+}
+
+set_apptrust_order()
+{
+	local if_name=$1
+	local order=$2
+
+	dcb apptrust set dev ${if_name} order ${order}
+}
+
+# Function to extract a specified field from a given JSON stats string
+extract_network_stat() {
+	local stats_json=$1
+	local field_name=$2
+
+	echo $(echo "$stats_json" | jq -r "$field_name")
+}
+
+run_test()
+{
+	local test_name=$1;
+	local apptrust_order=$2;
+	local port_prio=$3;
+	local dscp_ipv=$4;
+	local dscp=$5;
+	local have_vlan=$6;
+	local pcp_ipv=$7;
+	local vlan_pcp=$8;
+	local ip_v6=$9
+
+	local rx_ipv
+	local tx_ipv
+
+	RET=0
+
+	# Send some packet to populate the switch MAC table
+	$MZ ${h2} -a ${h2_mac} -b ${h1_mac} -p 64 -t icmp echores -c 1
+
+	# Based on the apptrust order, set the expected Internal Priority values
+	# for the RX and TX paths.
+	if [ "${apptrust_order}" == "" ]; then
+		echo "Apptrust order not set."
+		rx_ipv=${port_prio}
+		tx_ipv=${port_prio}
+	elif [ "${apptrust_order}" == "dscp" ]; then
+		echo "Apptrust order is DSCP."
+		rx_ipv=${dscp_ipv}
+		tx_ipv=${dscp_ipv}
+	elif [ "${apptrust_order}" == "pcp" ]; then
+		echo "Apptrust order is PCP."
+		rx_ipv=${pcp_ipv}
+		tx_ipv=${pcp_ipv}
+	elif [ "${apptrust_order}" == "pcp dscp" ]; then
+		echo "Apptrust order is PCP DSCP."
+		if [ ${have_vlan} -eq 1 ]; then
+			rx_ipv=$((dscp_ipv > pcp_ipv ? dscp_ipv : pcp_ipv))
+			tx_ipv=${pcp_ipv}
+		else
+			rx_ipv=${dscp_ipv}
+			tx_ipv=${dscp_ipv}
+		fi
+	else
+		RET=1
+		echo "Error: Unknown apptrust order ${apptrust_order}"
+		log_test "${test_name}"
+		return
+	fi
+
+	# Most/all? of the KSZ switches do not provide per-TC counters. There
+	# are only tx_hi and rx_hi counters, which are used to count packets
+	# which are considered as high priority and most likely not assigned
+	# to the queue 0.
+	# On the ingress path, packets seem to get high priority status
+	# independently of the DSCP or PCP global mapping. On the egress path,
+	# the high priority status is assigned based on the DSCP or PCP global
+	# map configuration.
+	# The thresholds for the high priority status are not documented, but
+	# it seems that the switch considers packets as high priority on the
+	# ingress path if detected Internal Priority is greater than 0. On the
+	# egress path, the switch considers packets as high priority if
+	# detected Internal Priority is greater than 1.
+	if [ ${rx_ipv} -ge 1 ]; then
+		local expect_rx_high_prio=1
+	else
+		local expect_rx_high_prio=0
+	fi
+
+	if [ ${tx_ipv} -ge 2 ]; then
+		local expect_tx_high_prio=1
+	else
+		local expect_tx_high_prio=0
+	fi
+
+	# Use ip tool to get the current switch packet counters. ethool stats
+	# need to be recalculated to get the correct values.
+	local swp1_stats=$(ip -s -j link show dev ${swp1})
+	local swp2_stats=$(ip -s -j link show dev ${swp2})
+	local swp1_rx_packets_before=$(extract_network_stat "$swp1_stats" \
+				       '.[0].stats64.rx.packets')
+	local swp1_rx_bytes_before=$(extract_network_stat "$swp1_stats" \
+				     '.[0].stats64.rx.bytes')
+	local swp2_tx_packets_before=$(extract_network_stat "$swp2_stats" \
+				       '.[0].stats64.tx.packets')
+	local swp2_tx_bytes_before=$(extract_network_stat "$swp2_stats" \
+				     '.[0].stats64.tx.bytes')
+	local swp1_rx_hi_before=$(ethtool_stats_get ${swp1} "rx_hi")
+	local swp2_tx_hi_before=$(ethtool_stats_get ${swp2} "tx_hi")
+
+	# Assamble the mausezahn command based on the test parameters
+	# For the testis with ipv4 or ipv6, use icmp response packets,
+	# to avoid interaction with the system, to keep packet counters
+	# clean.
+	if [ ${ip_v6} -eq 0 ]; then
+		local ip="-a ${h1_mac} -b ${h2_mac} -A ${H1_IPV4} \
+			  -B ${H2_IPV4} -t icmp unreach,code=1,dscp=${dscp}"
+	else
+		local ip="-6 -a ${h1_mac} -b ${h2_mac} -A ${H1_IPV6} \
+			  -B ${H2_IPV6} -t icmp6 type=1,code=0,dscp=${dscp}"
+	fi
+
+	if [ ${have_vlan} -eq 1 ]; then
+		local vlan_pcp_opt="-Q ${vlan_pcp}:0"
+	else
+		local vlan_pcp_opt=""
+	fi
+	$MZ ${h1} ${ip} -c ${PING_COUNT} -d 10msec ${vlan_pcp_opt}
+
+	# Wait until the switch packet counters are updated
+	sleep 6
+
+	local swp1_stats=$(ip -s -j link show dev ${swp1})
+	local swp2_stats=$(ip -s -j link show dev ${swp2})
+
+	local swp1_rx_packets_after=$(extract_network_stat "$swp1_stats" \
+				      '.[0].stats64.rx.packets')
+	local swp1_rx_bytes_after=$(extract_network_stat "$swp1_stats" \
+				    '.[0].stats64.rx.bytes')
+	local swp2_tx_packets_after=$(extract_network_stat "$swp2_stats" \
+				      '.[0].stats64.tx.packets')
+	local swp2_tx_bytes_after=$(extract_network_stat "$swp2_stats" \
+				    '.[0].stats64.tx.bytes')
+
+	local swp1_rx_packets_diff=$((${swp1_rx_packets_after} - \
+				      ${swp1_rx_packets_before}))
+	local swp2_tx_packets_diff=$((${swp2_tx_packets_after} - \
+				      ${swp2_tx_packets_before}))
+
+	local swp1_rx_hi_after=$(ethtool_stats_get ${swp1} "rx_hi")
+	local swp2_tx_hi_after=$(ethtool_stats_get ${swp2} "tx_hi")
+
+	# Test if any packets were received on swp1, we will rx before and after
+	if [ ${swp1_rx_packets_diff} -lt ${PING_COUNT} ]; then
+		echo "Not expected amount of received packets on ${swp1}"
+		echo "before ${swp1_rx_packets_before} after ${swp1_rx_packets_after}"
+		RET=1
+	fi
+
+	# Test if any packets were transmitted on swp2, we will tx before and after
+	if [ ${swp2_tx_packets_diff} -lt ${PING_COUNT} ]; then
+		echo "Not expected amount of transmitted packets on ${swp2}"
+		echo "before ${swp2_tx_packets_before} after ${swp2_tx_packets_after}"
+		RET=1
+	fi
+
+	# tx/rx_hi counted in bytes. So, we need to compare the difference in bytes
+	local swp1_rx_bytes_diff=$(($swp1_rx_bytes_after - $swp1_rx_bytes_before))
+	local swp2_tx_bytes_diff=$(($swp2_tx_bytes_after - $swp2_tx_bytes_before))
+	local swp1_rx_hi_diff=$(($swp1_rx_hi_after - $swp1_rx_hi_before))
+	local swp2_tx_hi_diff=$(($swp2_tx_hi_after - $swp2_tx_hi_before))
+
+	if [ ${expect_rx_high_prio} -eq 1 ]; then
+		swp1_rx_hi_diff=$((${swp1_rx_hi_diff} - \
+				   ${swp1_rx_packets_diff} * ${ETH_FCS_LEN}))
+		if [ ${swp1_rx_hi_diff} -ne ${swp1_rx_bytes_diff} ]; then
+			echo "Not expected amount of high priority packets received on ${swp1}"
+			echo "RX hi diff: ${swp1_rx_hi_diff}, expected RX bytes diff: ${swp1_rx_bytes_diff}"
+			RET=1
+		fi
+	else
+		if [ ${swp1_rx_hi_diff} -ne 0 ]; then
+			echo "Unexpected amount of high priority packets received on ${swp1}"
+			echo "RX hi diff: ${swp1_rx_hi_diff}, expected 0"
+			RET=1
+		fi
+	fi
+
+	if [ ${expect_tx_high_prio} -eq 1 ]; then
+		swp2_tx_hi_diff=$((${swp2_tx_hi_diff} - \
+				   ${swp2_tx_packets_diff} * ${ETH_FCS_LEN}))
+		if [ ${swp2_tx_hi_diff} -ne ${swp2_tx_bytes_diff} ]; then
+			echo "Not expected amount of high priority packets transmitted on ${swp2}"
+			echo "TX hi diff: ${swp2_tx_hi_diff}, expected TX bytes diff: ${swp2_tx_bytes_diff}"
+			RET=1
+		fi
+	else
+		if [ ${swp2_tx_hi_diff} -ne 0 ]; then
+			echo "Unexpected amount of high priority packets transmitted on ${swp2}"
+			echo "TX hi diff: ${swp2_tx_hi_diff}, expected 0"
+			RET=1
+		fi
+	fi
+
+	log_test "${test_name}"
+}
+
+run_test_dscp()
+{
+	# IPv4 test
+	run_test "$1" "$2" "$3" "$4" "$5" 0 0 0 0
+	# IPv6 test
+	run_test "$1" "$2" "$3" "$4" "$5" 0 0 0 1
+}
+
+run_test_dscp_pcp()
+{
+	# IPv4 test
+	run_test "$1" "$2" "$3" "$4" "$5" 1 "$6" "$7" 0
+	# IPv6 test
+	run_test "$1" "$2" "$3" "$4" "$5" 1 "$6" "$7" 1
+}
+
+port_default_prio_get()
+{
+	local if_name=$1
+	local prio
+
+	prio="$(dcb -j app show dev ${if_name} default-prio | \
+		jq '.default_prio[]')"
+	if [ -z "${prio}" ]; then
+		prio=0
+	fi
+
+	echo ${prio}
+}
+
+test_port_default()
+{
+	local orig_apptrust=$(port_get_default_apptrust ${swp1})
+	local orig_prio=$(port_default_prio_get ${swp1})
+	local apptrust_order=""
+
+	RET=0
+
+	# Make sure no other priority sources will interfere with the test
+	set_apptrust_order ${swp1} "${apptrust_order}"
+
+	for val in $(seq 0 7); do
+		dcb app replace dev ${swp1} default-prio ${val}
+		if [ $val -ne $(port_default_prio_get ${swp1}) ]; then
+			RET=1
+			break
+		fi
+
+		run_test_dscp "Port-default QoS classification, prio: ${val}" \
+			"${apptrust_order}" ${val} 0 0
+	done
+
+	set_apptrust_order ${swp1} "${orig_apptrust}"
+	if [[ "$orig_apptrust" != "$(port_get_default_apptrust ${swp1})" ]]; then
+		RET=1
+	fi
+
+	dcb app replace dev ${swp1} default-prio ${orig_prio}
+	if [ $orig_prio -ne $(port_default_prio_get ${swp1}) ]; then
+		RET=1
+	fi
+
+	log_test "Port-default QoS classification"
+}
+
+port_get_default_apptrust()
+{
+	local if_name=$1
+
+	dcb -j apptrust show dev ${if_name} | jq -r '.order[]' | \
+		tr '\n' ' ' | xargs
+}
+
+test_port_apptrust()
+{
+	local original_dscp_prios_swp1=$(get_dscp_prios ${swp1})
+	local orig_apptrust=$(port_get_default_apptrust ${swp1})
+	local orig_port_prio=$(port_default_prio_get ${swp1})
+	local order_variants=("pcp dscp" "dscp" "pcp")
+	local apptrust_order
+	local port_prio
+	local dscp_prio
+	local pcp_prio
+	local dscp
+	local pcp
+
+	RET=0
+
+	# First, test if apptrust configuration as taken by the kernel
+	for order in "${order_variants[@]}"; do
+		set_apptrust_order ${swp1} "${order}"
+		if [[ "$order" != "$(port_get_default_apptrust ${swp1})" ]]; then
+			RET=1
+			break
+		fi
+	done
+
+	log_test "Apptrust, supported variants"
+
+	# To test if the apptrust configuration is working as expected, we need
+	# to set DSCP priorities for the switch port.
+	init_dscp_prios "${swp1}" "${original_dscp_prios_swp1}"
+
+	# Start with a simple test where all apptrust sources are disabled
+	# default port priority is 0, DSCP priority is mapped to 7.
+	# No high priority packets should be received or transmitted.
+	port_prio=0
+	dscp_prio=7
+	dscp=4
+
+	dcb app replace dev ${swp1} default-prio ${port_prio}
+	dcb app replace dev ${swp1} dscp-prio ${dscp}:${dscp_prio}
+
+	apptrust_order=""
+	set_apptrust_order ${swp1} "${apptrust_order}"
+	# Test with apptrust sources disabled, Packets should get port default
+	# priority which is 0
+	run_test_dscp "Apptrust, all disabled. DSCP-prio ${dscp}:${dscp_prio}" \
+		"${apptrust_order}" ${port_prio} ${dscp_prio} ${dscp}
+
+	apptrust_order="pcp"
+	set_apptrust_order ${swp1} "${apptrust_order}"
+	# If PCP is enabled, packets should get PCP priority, which is not
+	# set in this test (no VLAN tags are present in the packet). No high
+	# priority packets should be received or transmitted.
+	run_test_dscp "Apptrust, PCP enabled. DSCP-prio ${dscp}:${dscp_prio}" \
+		"${apptrust_order}" ${port_prio} ${dscp_prio} ${dscp}
+
+	apptrust_order="dscp"
+	set_apptrust_order ${swp1} "${apptrust_order}"
+	# If DSCP is enabled, packets should get DSCP priority which is set to 7
+	# in this test. High priority packets should be received and transmitted.
+	run_test_dscp "Apptrust, DSCP enabled. DSCP-prio ${dscp}:${dscp_prio}" \
+		"${apptrust_order}" ${port_prio} ${dscp_prio} ${dscp}
+
+	apptrust_order="pcp dscp"
+	set_apptrust_order ${swp1} "${apptrust_order}"
+	# If PCP and DSCP are enabled, PCP would have higher apptrust priority
+	# so packets should get PCP priority. But in this test VLAN PCP is not
+	# set, so it should get DSCP priority which is set to 7. High priority
+	# packets should be received and transmitted.
+	run_test_dscp "Apptrust, PCP and DSCP are enabled. DSCP-prio ${dscp}:${dscp_prio}" \
+		"${apptrust_order}" ${port_prio} ${dscp_prio} ${dscp}
+
+	# If VLAN PCP is set, it should have higher apptrust priority than DSCP
+	# so packets should get VLAN PCP priority. Send packets with VLAN PCP
+	# set to 0, DSCP set to 7. Packets should get VLAN PCP priority.
+	# No high priority packets should be transmitted. Due to nature of the
+	# switch, high priority packets will be received.
+	pcp_prio=0
+	pcp=0
+	run_test_dscp_pcp "Apptrust, PCP and DSCP are enabled. PCP ${pcp_prio}, DSCP-prio ${dscp}:${dscp_prio}" \
+		"${apptrust_order}" ${port_prio} ${dscp_prio} ${dscp} ${pcp_prio} ${pcp}
+
+	# If VLAN PCP is set to 7, it should have higher apptrust priority than
+	# DSCP so packets should get VLAN PCP priority. Send packets with VLAN
+	# PCP set to 7, DSCP set to 7. Packets should get VLAN PCP priority.
+	# High priority packets should be received and transmitted.
+	pcp_prio=7
+	pcp=7
+	run_test_dscp_pcp "Apptrust, PCP and DSCP are enabled. PCP ${pcp_prio}, DSCP-prio ${dscp}:${dscp_prio}" \
+		"${apptrust_order}" ${port_prio} ${dscp_prio} ${dscp} ${pcp_prio} ${pcp}
+	# Now make sure that the switch is able to handle the case where DSCP
+	# priority is set to 0 and PCP priority is set to 7. Packets should get
+	# PCP priority. High priority packets should be received and transmitted.
+	dscp_prio=0
+	dcb app replace dev ${swp1} dscp-prio ${dscp}:${dscp_prio}
+	run_test_dscp_pcp "Apptrust, PCP and DSCP are enabled. PCP ${pcp_prio}, DSCP-prio ${dscp}:${dscp_prio}" \
+		"${apptrust_order}" ${port_prio} ${dscp_prio} ${dscp} ${pcp_prio} ${pcp}
+	# If both VLAN PCP and DSCP are set to 0, packets should get 0 priority.
+	# No high priority packets should be received or transmitted.
+	pcp_prio=0
+	pcp=0
+	run_test_dscp_pcp "Apptrust, PCP and DSCP are enabled. PCP ${pcp_prio}, DSCP-prio ${dscp}:${dscp_prio}" \
+		"${apptrust_order}" ${port_prio} ${dscp_prio} ${dscp} ${pcp_prio} ${pcp}
+
+	# Restore original priorities
+	if ! restore_priorities "${swp1}" "${original_dscp_prios_swp1}"; then
+		RET=1
+	fi
+
+	set_apptrust_order ${swp1} "${orig_apptrust}"
+	if [ "$orig_apptrust" != "$(port_get_default_apptrust ${swp1})" ]; then
+		RET=1
+	fi
+
+	dcb app replace dev ${swp1} default-prio ${orig_port_prio}
+	if [ $orig_port_prio -ne $(port_default_prio_get ${swp1}) ]; then
+		RET=1
+	fi
+
+	log_test "Apptrust, restore original settings"
+}
+
+# Function to get current DSCP priorities
+get_dscp_prios() {
+	local if_name=$1
+	dcb -j app show dev ${if_name} | jq -c '.dscp_prio'
+}
+
+# Function to set a specific DSCP priority on a device
+replace_dscp_prio() {
+	local if_name=$1
+	local dscp=$2
+	local prio=$3
+	dcb app replace dev ${if_name} dscp-prio ${dscp}:${prio}
+}
+
+# Function to compare DSCP maps
+compare_dscp_maps() {
+	local old_json=$1
+	local new_json=$2
+	local dscp=$3
+	local prio=$4
+
+	# Create a modified old_json with the expected change for comparison
+	local modified_old_json=$(echo "$old_json" |
+		jq --argjson dscp $dscp --argjson prio $prio \
+			'map(if .[0] == $dscp then [$dscp, $prio] else . end)' |
+		tr -d " \n")
+
+	# Compare new_json with the modified_old_json
+	if [[ "$modified_old_json" == "$new_json" ]]; then
+		return 0
+	else
+		return 1
+	fi
+}
+
+# Function to set DSCP priorities
+set_and_verify_dscp() {
+	local port=$1
+	local dscp=$2
+	local new_prio=$3
+
+	local old_prios=$(get_dscp_prios $port)
+
+	replace_dscp_prio "$port" $dscp $new_prio
+
+	# Fetch current settings and compare
+	local current_prios=$(get_dscp_prios $port)
+	if ! compare_dscp_maps "$old_prios" "$current_prios" $dscp $new_prio; then
+		echo "Error: Unintended changes detected in DSCP map for $port after setting DSCP $dscp to $new_prio."
+		return 1
+	fi
+	return 0
+}
+
+# Function to restore original priorities
+restore_priorities() {
+	local port=$1
+	local original_prios=$2
+
+	echo "Removing test artifacts for $port"
+	local current_prios=$(get_dscp_prios $port)
+	local prio_str=$(echo "$current_prios" |
+		jq -r 'map("\(.[0]):\(.[1])") | join(" ")')
+	dcb app del dev $port dscp-prio $prio_str
+
+	echo "Restoring original DSCP priorities for $port"
+	local restore_str=$(echo "$original_prios" |
+		jq -r 'map("\(.[0]):\(.[1])") | join(" ")')
+	dcb app add dev $port dscp-prio $restore_str
+
+	local current_prios=$(get_dscp_prios $port)
+	if [[ "$original_prios" != "$current_prios" ]]; then
+		echo "Error: Failed to restore original DSCP priorities for $port"
+		return 1
+	fi
+	return 0
+}
+
+# Initialize DSCP priorities. Set them to predictable values for testing.
+init_dscp_prios() {
+	local port=$1
+	local original_prios=$2
+
+	echo "Removing any existing DSCP priority mappins for $port"
+	local prio_str=$(echo "$original_prios" |
+		jq -r 'map("\(.[0]):\(.[1])") | join(" ")')
+	dcb app del dev $port dscp-prio $prio_str
+
+	# Initialize DSCP priorities list
+	local dscp_prios=""
+	for dscp in {0..63}; do
+		dscp_prios+=("$dscp:0")
+	done
+
+	echo "Setting initial DSCP priorities map to 0 for $port"
+	dcb app add dev $port dscp-prio ${dscp_prios[@]}
+}
+
+# Main function to test global DSCP map across specified ports
+test_global_dscp_map() {
+	local ports=("$swp1" "$swp2")
+	local original_dscp_prios_port0=$(get_dscp_prios ${ports[0]})
+	local orig_apptrust=$(port_get_default_apptrust ${swp1})
+	local orig_port_prio=$(port_default_prio_get ${swp1})
+	local apptrust_order="dscp"
+	local port_prio=0
+	local dscp_prio
+	local dscp
+
+	RET=0
+
+	set_apptrust_order ${swp1} "${apptrust_order}"
+	dcb app replace dev ${swp1} default-prio ${port_prio}
+
+	# Initialize DSCP priorities
+	init_dscp_prios "${ports[0]}" "$original_dscp_prios_port0"
+
+	# Loop over each DSCP index
+	for dscp in {0..63}; do
+		# and test each Internal Priority value
+		for dscp_prio in {0..7}; do
+			# do it for each port. This is to test if the global DSCP map
+			# is accessible from all ports.
+			for port in "${ports[@]}"; do
+				if ! set_and_verify_dscp "$port" $dscp $dscp_prio; then
+					RET=1
+				fi
+			done
+
+			# Test if the DSCP priority is correctly applied to the packets
+			run_test_dscp "DSCP (${dscp}) QoS classification, prio: ${dscp_prio}" \
+				"${apptrust_order}" ${port_prio} ${dscp_prio} ${dscp}
+			if [ ${RET} -eq 1 ]; then
+				break
+			fi
+		done
+	done
+
+	# Restore original priorities
+	if ! restore_priorities "${ports[0]}" "${original_dscp_prios_port0}"; then
+		RET=1
+	fi
+
+	set_apptrust_order ${swp1} "${orig_apptrust}"
+	if [[ "$orig_apptrust" != "$(port_get_default_apptrust ${swp1})" ]]; then
+		RET=1
+	fi
+
+	dcb app replace dev ${swp1} default-prio ${orig_port_prio}
+	if [ $orig_port_prio -ne $(port_default_prio_get ${swp1}) ]; then
+		RET=1
+	fi
+
+	log_test "DSCP global map"
+}
+
+trap cleanup EXIT
+
+ALL_TESTS="
+	test_port_default
+	test_port_apptrust
+	test_global_dscp_map
+"
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh
index 89b55e946eed..36055279ba92 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh
@@ -116,7 +116,7 @@ dev_del_test()
 
 	log_test "Device delete"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 }
 
 trap cleanup EXIT
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh
index 160891dcb4bc..db5806d189bb 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh
@@ -595,7 +595,7 @@ irif_disabled_test()
 
 	log_test "Ingress RIF disabled"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	ip link set dev $rp1 nomaster
 	__addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64
 	ip link del dev br0 type bridge
@@ -645,7 +645,7 @@ erif_disabled_test()
 
 	log_test "Egress RIF disabled"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	__addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64
 	ip link del dev br0 type bridge
 	devlink_trap_action_set $trap_name "drop"
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh
index 190c1b6b5365..5d6d88b600f0 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh
@@ -202,7 +202,7 @@ mtu_value_is_too_small_test()
 
 	mtu_restore $rp2
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $h1 ingress protocol ip pref 1 handle 101 flower
 }
 
@@ -235,7 +235,7 @@ __ttl_value_is_too_small_test()
 
 	log_test "TTL value is too small: TTL=$ttl_val"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $h1 ingress protocol ip pref 1 handle 101 flower
 }
 
@@ -299,7 +299,7 @@ __mc_reverse_path_forwarding_test()
 
 	log_test "Multicast reverse path forwarding: $desc"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $rp2 egress protocol $proto pref 1 handle 101 flower
 }
 
@@ -347,7 +347,7 @@ __reject_route_test()
 
 	log_test "Reject route: $desc"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	ip route del unreachable $unreachable
 	tc filter del dev $h1 ingress protocol $proto pref 1 handle 101 flower
 }
@@ -542,7 +542,7 @@ ipv4_lpm_miss_test()
 
 	log_test "LPM miss: IPv4"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	vrf_without_routes_destroy
 }
 
@@ -569,7 +569,7 @@ ipv6_lpm_miss_test()
 
 	log_test "LPM miss: IPv6"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	vrf_without_routes_destroy
 }
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh
index 0bd5ffc218ac..e212ad8ccef6 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh
@@ -44,64 +44,51 @@ source $lib_dir/devlink_lib.sh
 
 h1_create()
 {
-	simple_if_init $h1 192.0.2.1/24
+	adf_simple_if_init $h1 192.0.2.1/24
+
 	mtu_set $h1 10000
+	defer mtu_restore $h1
 
 	ip -4 route add default vrf v$h1 nexthop via 192.0.2.2
-}
-
-h1_destroy()
-{
-	ip -4 route del default vrf v$h1 nexthop via 192.0.2.2
-
-	mtu_restore $h1
-	simple_if_fini $h1 192.0.2.1/24
+	defer ip -4 route del default vrf v$h1 nexthop via 192.0.2.2
 }
 
 h2_create()
 {
-	simple_if_init $h2 198.51.100.1/24
+	adf_simple_if_init $h2 198.51.100.1/24
+
 	mtu_set $h2 10000
+	defer mtu_restore $h2
 
 	ip -4 route add default vrf v$h2 nexthop via 198.51.100.2
-}
-
-h2_destroy()
-{
-	ip -4 route del default vrf v$h2 nexthop via 198.51.100.2
-
-	mtu_restore $h2
-	simple_if_fini $h2 198.51.100.1/24
+	defer ip -4 route del default vrf v$h2 nexthop via 198.51.100.2
 }
 
 router_create()
 {
 	ip link set dev $rp1 up
+	defer ip link set dev $rp1 down
+
 	ip link set dev $rp2 up
+	defer ip link set dev $rp2 down
 
 	__addr_add_del $rp1 add 192.0.2.2/24
+	defer __addr_add_del $rp1 del 192.0.2.2/24
+
 	__addr_add_del $rp2 add 198.51.100.2/24
+	defer __addr_add_del $rp2 del 198.51.100.2/24
+
 	mtu_set $rp1 10000
+	defer mtu_restore $rp1
+
 	mtu_set $rp2 10000
+	defer mtu_restore $rp2
 
 	ip -4 route add blackhole 198.51.100.100
+	defer ip -4 route del blackhole 198.51.100.100
 
 	devlink trap set $DEVLINK_DEV trap blackhole_route action trap
-}
-
-router_destroy()
-{
-	devlink trap set $DEVLINK_DEV trap blackhole_route action drop
-
-	ip -4 route del blackhole 198.51.100.100
-
-	mtu_restore $rp2
-	mtu_restore $rp1
-	__addr_add_del $rp2 del 198.51.100.2/24
-	__addr_add_del $rp1 del 192.0.2.2/24
-
-	ip link set dev $rp2 down
-	ip link set dev $rp1 down
+	defer devlink trap set $DEVLINK_DEV trap blackhole_route action drop
 }
 
 setup_prepare()
@@ -114,7 +101,10 @@ setup_prepare()
 
 	rp1_mac=$(mac_get $rp1)
 
-	vrf_prepare
+	# Reload to ensure devlink-trap settings are back to default.
+	defer devlink_reload
+
+	adf_vrf_prepare
 
 	h1_create
 	h2_create
@@ -122,21 +112,6 @@ setup_prepare()
 	router_create
 }
 
-cleanup()
-{
-	pre_cleanup
-
-	router_destroy
-
-	h2_destroy
-	h1_destroy
-
-	vrf_cleanup
-
-	# Reload to ensure devlink-trap settings are back to default.
-	devlink_reload
-}
-
 rate_limits_test()
 {
 	RET=0
@@ -214,7 +189,10 @@ __rate_test()
 	# by the policer. Make sure measured received rate is about 1000 pps
 	log_info "=== Tx rate: Highest, Policer rate: 1000 pps ==="
 
+	defer_scope_push
+
 	start_traffic $h1 192.0.2.1 198.51.100.100 $rp1_mac
+	defer stop_traffic $!
 
 	sleep 5 # Take measurements when rate is stable
 
@@ -229,13 +207,16 @@ __rate_test()
 	check_err $? "Expected non-zero policer drop rate, got 0"
 	log_info "Measured policer drop rate of $drop_rate pps"
 
-	stop_traffic
+	defer_scope_pop
 
 	# Send packets at a rate of 1000 pps and make sure they are not dropped
 	# by the policer
 	log_info "=== Tx rate: 1000 pps, Policer rate: 1000 pps ==="
 
+	defer_scope_push
+
 	start_traffic $h1 192.0.2.1 198.51.100.100 $rp1_mac -d 1msec
+	defer stop_traffic $!
 
 	sleep 5 # Take measurements when rate is stable
 
@@ -244,7 +225,7 @@ __rate_test()
 	check_err $? "Expected zero policer drop rate, got a drop rate of $drop_rate pps"
 	log_info "Measured policer drop rate of $drop_rate pps"
 
-	stop_traffic
+	defer_scope_pop
 
 	# Unbind the policer and send packets at highest possible rate. Make
 	# sure they are not dropped by the policer and that the measured
@@ -253,7 +234,10 @@ __rate_test()
 
 	devlink trap group set $DEVLINK_DEV group l3_drops nopolicer
 
+	defer_scope_push
+
 	start_traffic $h1 192.0.2.1 198.51.100.100 $rp1_mac
+	defer stop_traffic $!
 
 	rate=$(trap_rate_get)
 	(( rate > 1000 ))
@@ -265,7 +249,7 @@ __rate_test()
 	check_err $? "Expected zero policer drop rate, got a drop rate of $drop_rate pps"
 	log_info "Measured policer drop rate of $drop_rate pps"
 
-	stop_traffic
+	defer_scope_pop
 
 	log_test "Trap policer rate"
 }
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh
index e9a82cae8c9a..4ac1dae92d0f 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh
@@ -176,7 +176,7 @@ ecn_decap_test()
 
 	log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower
 }
 
@@ -207,7 +207,7 @@ no_matching_tunnel_test()
 
 	log_test "$desc"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower
 }
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh
index 878125041fc3..fce885184404 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh
@@ -176,7 +176,7 @@ ecn_decap_test()
 
 	log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower
 }
 
@@ -207,7 +207,7 @@ no_matching_tunnel_test()
 
 	log_test "$desc"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower
 }
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh
index 5f6eb965cfd1..7aca8e5922cf 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh
@@ -183,7 +183,7 @@ ecn_decap_test()
 
 	log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower
 }
 
@@ -253,7 +253,7 @@ corrupted_packet_test()
 
 	log_test "$desc"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower
 }
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh
index f6c16cbb6cf7..4599c331240b 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh
@@ -188,7 +188,7 @@ ecn_decap_test()
 
 	log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower
 }
 
@@ -262,7 +262,7 @@ corrupted_packet_test()
 
 	log_test "$desc"
 
-	kill $mz_pid && wait $mz_pid &> /dev/null
+	kill_process $mz_pid
 	tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower
 }
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/egress_vid_classification.sh b/tools/testing/selftests/drivers/net/mlxsw/egress_vid_classification.sh
index 0cf9e47e3209..a5c2aec52898 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/egress_vid_classification.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/egress_vid_classification.sh
@@ -16,10 +16,9 @@
 # +----------------|--+                   +--|-----------------+
 #                  |                         |
 # +----------------|-------------------------|-----------------+
-# | SW             |                         |                 |
+# | SW       $swp1 +                         + $swp2           |
+# |                |                         |                 |
 # | +--------------|-------------------------|---------------+ |
-# | |        $swp1 +                         + $swp2         | |
-# | |              |                         |               | |
 # | |     $swp1.10 +                         + $swp2.10      | |
 # | |                                                        | |
 # | |                           br0                          | |
diff --git a/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh b/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh
index 91891b9418d7..fe905a7f34b3 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh
@@ -2,6 +2,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
 lib_dir=$(dirname $0)/../../../net/forwarding
+ethtool_lib_dir=$(dirname $0)/../hw
 
 ALL_TESTS="
 	autoneg
@@ -11,7 +12,7 @@ ALL_TESTS="
 NUM_NETIFS=2
 : ${TIMEOUT:=30000} # ms
 source $lib_dir/lib.sh
-source $lib_dir/ethtool_lib.sh
+source $ethtool_lib_dir/ethtool_lib.sh
 
 setup_prepare()
 {
@@ -24,8 +25,8 @@ setup_prepare()
 	busywait "$TIMEOUT" wait_for_port_up ethtool $swp2
 	check_err $? "ports did not come up"
 
-	local lanes_exist=$(ethtool $swp1 | grep 'Lanes:')
-	if [[ -z $lanes_exist ]]; then
+	busywait $TIMEOUT sh -c "ethtool $swp1 | grep -q Lanes:"
+	if [[ $? -ne 0 ]]; then
 		log_test "SKIP: driver does not support lanes setting"
 		exit 1
 	fi
@@ -122,8 +123,9 @@ autoneg()
 			ethtool_set $swp1 speed $max_speed lanes $lanes
 			ip link set dev $swp1 up
 			ip link set dev $swp2 up
-			busywait "$TIMEOUT" wait_for_port_up ethtool $swp2
-			check_err $? "ports did not come up"
+
+			busywait $TIMEOUT sh -c "ethtool $swp1 | grep -q Lanes:"
+			check_err $? "Lanes parameter is not presented on time"
 
 			check_lanes $swp1 $lanes $max_speed
 			log_test "$lanes lanes is autonegotiated"
@@ -160,8 +162,9 @@ autoneg_force_mode()
 			ethtool_set $swp2 speed $max_speed lanes $lanes autoneg off
 			ip link set dev $swp1 up
 			ip link set dev $swp2 up
-			busywait "$TIMEOUT" wait_for_port_up ethtool $swp2
-			check_err $? "ports did not come up"
+
+			busywait $TIMEOUT sh -c "ethtool $swp1 | grep -q Lanes:"
+			check_err $? "Lanes parameter is not presented on time"
 
 			check_lanes $swp1 $lanes $max_speed
 			log_test "Autoneg off, $lanes lanes detected during force mode"
diff --git a/tools/testing/selftests/drivers/net/mlxsw/extack.sh b/tools/testing/selftests/drivers/net/mlxsw/extack.sh
index 7a0a99c1d22f..6fd422d38fe8 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/extack.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/extack.sh
@@ -35,7 +35,9 @@ netdev_pre_up_test()
 {
 	RET=0
 
-	ip link add name br1 up type bridge vlan_filtering 0 mcast_snooping 0
+	ip link add name br1 type bridge vlan_filtering 0 mcast_snooping 0
+	ip link set dev br1 addrgenmode none
+	ip link set dev br1 up
 	ip link add name vx1 up type vxlan id 1000 \
 		local 192.0.2.17 remote 192.0.2.18 \
 		dstport 4789 nolearning noudpcsum tos inherit ttl 100
@@ -46,7 +48,9 @@ netdev_pre_up_test()
 	ip link set dev $swp1 master br1
 	check_err $?
 
-	ip link add name br2 up type bridge vlan_filtering 0 mcast_snooping 0
+	ip link add name br2 type bridge vlan_filtering 0 mcast_snooping 0
+	ip link set dev br2 addrgenmode none
+	ip link set dev br2 up
 	ip link add name vx2 up type vxlan id 2000 \
 		local 192.0.2.17 remote 192.0.2.18 \
 		dstport 4789 nolearning noudpcsum tos inherit ttl 100
@@ -81,7 +85,9 @@ vxlan_vlan_add_test()
 {
 	RET=0
 
-	ip link add name br1 up type bridge vlan_filtering 1 mcast_snooping 0
+	ip link add name br1 type bridge vlan_filtering 1 mcast_snooping 0
+	ip link set dev br1 addrgenmode none
+	ip link set dev br1 up
 
 	# Unsupported configuration: mlxsw demands VXLAN with "noudpcsum".
 	ip link add name vx1 up type vxlan id 1000 \
@@ -117,7 +123,9 @@ vxlan_bridge_create_test()
 		dstport 4789 tos inherit ttl 100
 
 	# Test with VLAN-aware bridge.
-	ip link add name br1 up type bridge vlan_filtering 1 mcast_snooping 0
+	ip link add name br1 type bridge vlan_filtering 1 mcast_snooping 0
+	ip link set dev br1 addrgenmode none
+	ip link set dev br1 up
 
 	ip link set dev vx1 master br1
 
@@ -142,8 +150,12 @@ bridge_create_test()
 {
 	RET=0
 
-	ip link add name br1 up type bridge vlan_filtering 1
-	ip link add name br2 up type bridge vlan_filtering 1
+	ip link add name br1 type bridge vlan_filtering 1
+	ip link set dev br1 addrgenmode none
+	ip link set dev br1 up
+	ip link add name br2 type bridge vlan_filtering 1
+	ip link set dev br2 addrgenmode none
+	ip link set dev br2 up
 
 	ip link set dev $swp1 master br1
 	check_err $?
diff --git a/tools/testing/selftests/drivers/net/mlxsw/ingress_rif_conf_1d.sh b/tools/testing/selftests/drivers/net/mlxsw/ingress_rif_conf_1d.sh
index df2b09966886..7d7f862c809c 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/ingress_rif_conf_1d.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/ingress_rif_conf_1d.sh
@@ -15,10 +15,9 @@
 # +----------------|--+                   +--|-----------------+
 #                  |                         |
 # +----------------|-------------------------|-----------------+
-# | SW             |                         |                 |
+# | SW       $swp1 +                         + $swp2           |
+# |                |                         |                 |
 # | +--------------|-------------------------|---------------+ |
-# | |        $swp1 +                         + $swp2         | |
-# | |              |                         |               | |
 # | |     $swp1.10 +                         + $swp2.10      | |
 # | |                                                        | |
 # | |                           br0                          | |
diff --git a/tools/testing/selftests/drivers/net/mlxsw/mirror_gre.sh b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre.sh
index 76f1ab4898d9..e1ad623146d7 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/mirror_gre.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre.sh
@@ -15,6 +15,13 @@ source $lib_dir/mirror_lib.sh
 source $lib_dir/mirror_gre_lib.sh
 source $lib_dir/mirror_gre_topo_lib.sh
 
+ALL_TESTS="
+	test_keyful
+	test_soft
+	test_tos_fixed
+	test_ttl_inherit
+"
+
 setup_keyful()
 {
 	tunnel_create gt6-key ip6gretap 2001:db8:3::1 2001:db8:3::2 \
@@ -118,15 +125,15 @@ test_span_gre_ttl_inherit()
 	RET=0
 
 	ip link set dev $tundev type $type ttl inherit
-	mirror_install $swp1 ingress $tundev "matchall $tcflags"
-	fail_test_span_gre_dir $tundev ingress
+	mirror_install $swp1 ingress $tundev "matchall"
+	fail_test_span_gre_dir $tundev
 
 	ip link set dev $tundev type $type ttl 100
 
-	quick_test_span_gre_dir $tundev ingress
+	quick_test_span_gre_dir $tundev
 	mirror_uninstall $swp1 ingress
 
-	log_test "$what: no offload on TTL of inherit ($tcflags)"
+	log_test "$what: no offload on TTL of inherit"
 }
 
 test_span_gre_tos_fixed()
@@ -138,61 +145,49 @@ test_span_gre_tos_fixed()
 	RET=0
 
 	ip link set dev $tundev type $type tos 0x10
-	mirror_install $swp1 ingress $tundev "matchall $tcflags"
-	fail_test_span_gre_dir $tundev ingress
+	mirror_install $swp1 ingress $tundev "matchall"
+	fail_test_span_gre_dir $tundev
 
 	ip link set dev $tundev type $type tos inherit
-	quick_test_span_gre_dir $tundev ingress
+	quick_test_span_gre_dir $tundev
 	mirror_uninstall $swp1 ingress
 
-	log_test "$what: no offload on a fixed TOS ($tcflags)"
+	log_test "$what: no offload on a fixed TOS"
 }
 
 test_span_failable()
 {
-	local should_fail=$1; shift
 	local tundev=$1; shift
 	local what=$1; shift
 
 	RET=0
 
-	mirror_install $swp1 ingress $tundev "matchall $tcflags"
-	if ((should_fail)); then
-	    fail_test_span_gre_dir  $tundev ingress
-	else
-	    quick_test_span_gre_dir $tundev ingress
-	fi
+	mirror_install $swp1 ingress $tundev "matchall"
+	fail_test_span_gre_dir  $tundev
 	mirror_uninstall $swp1 ingress
 
-	log_test "$what: should_fail=$should_fail ($tcflags)"
+	log_test "fail $what"
 }
 
-test_failable()
+test_keyful()
 {
-	local should_fail=$1; shift
-
-	test_span_failable $should_fail gt6-key "mirror to keyful gretap"
-	test_span_failable $should_fail gt6-soft "mirror to gretap w/ soft underlay"
+	test_span_failable gt6-key "mirror to keyful gretap"
 }
 
-test_sw()
+test_soft()
 {
-	slow_path_trap_install $swp1 ingress
-	slow_path_trap_install $swp1 egress
-
-	test_failable 0
-
-	slow_path_trap_uninstall $swp1 egress
-	slow_path_trap_uninstall $swp1 ingress
+	test_span_failable gt6-soft "mirror to gretap w/ soft underlay"
 }
 
-test_hw()
+test_tos_fixed()
 {
-	test_failable 1
-
 	test_span_gre_tos_fixed gt4 gretap "mirror to gretap"
 	test_span_gre_tos_fixed gt6 ip6gretap "mirror to ip6gretap"
+}
+
 
+test_ttl_inherit()
+{
 	test_span_gre_ttl_inherit gt4 gretap "mirror to gretap"
 	test_span_gre_ttl_inherit gt6 ip6gretap "mirror to ip6gretap"
 }
@@ -202,16 +197,6 @@ trap cleanup EXIT
 setup_prepare
 setup_wait
 
-if ! tc_offload_check; then
-    check_err 1 "Could not test offloaded functionality"
-    log_test "mlxsw-specific tests for mirror to gretap"
-    exit
-fi
-
-tcflags="skip_hw"
-test_sw
-
-tcflags="skip_sw"
-test_hw
+tests_run
 
 exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh
index e00435753008..d43093310e23 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh
@@ -79,7 +79,7 @@ mirror_gre_tunnels_create()
 		cat >> $MIRROR_GRE_BATCH_FILE <<-EOF
 			filter add dev $swp1 ingress pref 1000 \
 				protocol ipv6 \
-				flower $tcflags dst_ip $match_dip \
+				flower skip_sw dst_ip $match_dip \
 				action mirred egress mirror dev $tun
 		EOF
 	done
@@ -107,7 +107,7 @@ mirror_gre_tunnels_destroy()
 	done
 }
 
-__mirror_gre_test()
+mirror_gre_test()
 {
 	local count=$1; shift
 	local should_fail=$1; shift
@@ -131,20 +131,6 @@ __mirror_gre_test()
 	done
 }
 
-mirror_gre_test()
-{
-	local count=$1; shift
-	local should_fail=$1; shift
-
-	if ! tc_offload_check $TC_FLOWER_NUM_NETIFS; then
-		check_err 1 "Could not test offloaded functionality"
-		return
-	fi
-
-	tcflags="skip_sw"
-	__mirror_gre_test $count $should_fail
-}
-
 mirror_gre_setup_prepare()
 {
 	h1=${NETIFS[p1]}
@@ -165,6 +151,7 @@ mirror_gre_setup_prepare()
 	simple_if_init $h3
 
 	ip link add name br1 type bridge vlan_filtering 1
+	ip link set dev br1 addrgenmode none
 	ip link set dev br1 up
 
 	ip link set dev $swp1 master br1
diff --git a/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh b/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh
index 6369927e9c37..48395cfd4f95 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh
@@ -42,7 +42,7 @@ __mlxsw_only_on_spectrum()
 	local src=$1; shift
 
 	if ! mlxsw_on_spectrum "$rev"; then
-		log_test_skip $src:$caller "(Spectrum-$rev only)"
+		log_test_xfail $src:$caller "(Spectrum-$rev only)"
 		return 1
 	fi
 }
diff --git a/tools/testing/selftests/drivers/net/mlxsw/one_armed_router.sh b/tools/testing/selftests/drivers/net/mlxsw/one_armed_router.sh
index f02d83e94576..fca0e1e642c6 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/one_armed_router.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/one_armed_router.sh
@@ -83,7 +83,8 @@ h2_destroy()
 
 switch_create()
 {
-	ip link add name br0 type bridge mcast_snooping 0
+	ip link add name br0 address $(mac_get $swp1) \
+		type bridge mcast_snooping 0
 	ip link set dev br0 up
 
 	ip link set dev $swp1 master br0
diff --git a/tools/testing/selftests/drivers/net/mlxsw/pci_reset.sh b/tools/testing/selftests/drivers/net/mlxsw/pci_reset.sh
new file mode 100755
index 000000000000..fe0343b95e6c
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/pci_reset.sh
@@ -0,0 +1,58 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test that PCI reset works correctly by verifying that only the expected reset
+# methods are supported and that after issuing the reset the ifindex of the
+# port changes.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+	pci_reset_test
+"
+NUM_NETIFS=1
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+pci_reset_test()
+{
+	RET=0
+
+	local bus=$(echo $DEVLINK_DEV | cut -d '/' -f 1)
+	local bdf=$(echo $DEVLINK_DEV | cut -d '/' -f 2)
+
+	if [ $bus != "pci" ]; then
+		check_err 1 "devlink device is not a PCI device"
+		log_test "pci reset"
+		return
+	fi
+
+	if [ ! -f /sys/bus/pci/devices/$bdf/reset_method ]; then
+		check_err 1 "reset is not supported"
+		log_test "pci reset"
+		return
+	fi
+
+	[[ $(cat /sys/bus/pci/devices/$bdf/reset_method) == "bus" ]]
+	check_err $? "only \"bus\" reset method should be supported"
+
+	local ifindex_pre=$(ip -j link show dev $swp1 | jq '.[]["ifindex"]')
+
+	echo 1 > /sys/bus/pci/devices/$bdf/reset
+	check_err $? "reset failed"
+
+	# Wait for udev to rename newly created netdev.
+	udevadm settle
+
+	local ifindex_post=$(ip -j link show dev $swp1 | jq '.[]["ifindex"]')
+
+	[[ $ifindex_pre != $ifindex_post ]]
+	check_err $? "reset not performed"
+
+	log_test "pci reset"
+}
+
+swp1=${NETIFS[p1]}
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/port_range_occ.sh b/tools/testing/selftests/drivers/net/mlxsw/port_range_occ.sh
new file mode 100755
index 000000000000..b1f0781f6b25
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/port_range_occ.sh
@@ -0,0 +1,111 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test that filters that match on the same port range, but with different
+# combination of IPv4/IPv6 and TCP/UDP all use the same port range register by
+# observing port range registers' occupancy via devlink-resource.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+	port_range_occ_test
+"
+NUM_NETIFS=2
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+h1_create()
+{
+	simple_if_init $h1
+}
+
+h1_destroy()
+{
+	simple_if_fini $h1
+}
+
+switch_create()
+{
+	simple_if_init $swp1
+	tc qdisc add dev $swp1 clsact
+}
+
+switch_destroy()
+{
+	tc qdisc del dev $swp1 clsact
+	simple_if_fini $swp1
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	vrf_prepare
+
+	h1_create
+	switch_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	switch_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+port_range_occ_get()
+{
+	devlink_resource_occ_get port_range_registers
+}
+
+port_range_occ_test()
+{
+	RET=0
+
+	local occ=$(port_range_occ_get)
+
+	# Two port range registers are used, for source and destination port
+	# ranges.
+	tc filter add dev $swp1 ingress pref 1 handle 101 proto ip \
+		flower skip_sw ip_proto udp src_port 1-100 dst_port 1-100 \
+		action pass
+	(( occ + 2 == $(port_range_occ_get) ))
+	check_err $? "Got occupancy $(port_range_occ_get), expected $((occ + 2))"
+
+	tc filter add dev $swp1 ingress pref 1 handle 102 proto ip \
+		flower skip_sw ip_proto tcp src_port 1-100 dst_port 1-100 \
+		action pass
+	tc filter add dev $swp1 ingress pref 2 handle 103 proto ipv6 \
+		flower skip_sw ip_proto udp src_port 1-100 dst_port 1-100 \
+		action pass
+	tc filter add dev $swp1 ingress pref 2 handle 104 proto ipv6 \
+		flower skip_sw ip_proto tcp src_port 1-100 dst_port 1-100 \
+		action pass
+	(( occ + 2 == $(port_range_occ_get) ))
+	check_err $? "Got occupancy $(port_range_occ_get), expected $((occ + 2))"
+
+	tc filter del dev $swp1 ingress pref 2 handle 104 flower
+	tc filter del dev $swp1 ingress pref 2 handle 103 flower
+	tc filter del dev $swp1 ingress pref 1 handle 102 flower
+	(( occ + 2 == $(port_range_occ_get) ))
+	check_err $? "Got occupancy $(port_range_occ_get), expected $((occ + 2))"
+
+	tc filter del dev $swp1 ingress pref 1 handle 101 flower
+	(( occ == $(port_range_occ_get) ))
+	check_err $? "Got occupancy $(port_range_occ_get), expected $occ"
+
+	log_test "port range occupancy"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/port_range_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/port_range_scale.sh
new file mode 100644
index 000000000000..2a70840ff14b
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/port_range_scale.sh
@@ -0,0 +1,95 @@
+# SPDX-License-Identifier: GPL-2.0
+
+PORT_RANGE_NUM_NETIFS=2
+
+port_range_h1_create()
+{
+	simple_if_init $h1
+}
+
+port_range_h1_destroy()
+{
+	simple_if_fini $h1
+}
+
+port_range_switch_create()
+{
+	simple_if_init $swp1
+	tc qdisc add dev $swp1 clsact
+}
+
+port_range_switch_destroy()
+{
+	tc qdisc del dev $swp1 clsact
+	simple_if_fini $swp1
+}
+
+port_range_rules_create()
+{
+	local count=$1; shift
+	local should_fail=$1; shift
+	local batch_file="$(mktemp)"
+
+	for ((i = 0; i < count; ++i)); do
+		cat >> $batch_file <<-EOF
+			filter add dev $swp1 ingress \
+				prot ipv4 \
+				pref 1000 \
+				flower skip_sw \
+				ip_proto udp dst_port 1-$((100 + i)) \
+				action pass
+		EOF
+	done
+
+	tc -b $batch_file
+	check_err_fail $should_fail $? "Rule insertion"
+
+	rm -f $batch_file
+}
+
+__port_range_test()
+{
+	local count=$1; shift
+	local should_fail=$1; shift
+
+	port_range_rules_create $count $should_fail
+
+	offload_count=$(tc -j filter show dev $swp1 ingress |
+			jq "[.[] | select(.options.in_hw == true)] | length")
+	((offload_count == count))
+	check_err_fail $should_fail $? "port range offload count"
+}
+
+port_range_test()
+{
+	local count=$1; shift
+	local should_fail=$1; shift
+
+	if ! tc_offload_check $PORT_RANGE_NUM_NETIFS; then
+		check_err 1 "Could not test offloaded functionality"
+		return
+	fi
+
+	__port_range_test $count $should_fail
+}
+
+port_range_setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	vrf_prepare
+
+	port_range_h1_create
+	port_range_switch_create
+}
+
+port_range_cleanup()
+{
+	pre_cleanup
+
+	port_range_switch_destroy
+	port_range_h1_destroy
+
+	vrf_cleanup
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/q_in_q_veto.sh b/tools/testing/selftests/drivers/net/mlxsw/q_in_q_veto.sh
index 7edaed8eb86a..00d55b0e98c1 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/q_in_q_veto.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/q_in_q_veto.sh
@@ -48,6 +48,7 @@ create_vlan_upper_on_top_of_bridge()
 
 	ip link add dev br0 type bridge vlan_filtering 1 \
 		vlan_protocol $bridge_proto vlan_default_pvid 0 mcast_snooping 0
+	ip link set dev br0 addrgenmode none
 
 	ip link set dev br0 up
 	ip link set dev $swp1 master br0
@@ -88,6 +89,7 @@ create_8021ad_vlan_upper_on_top_bridge_port()
 
 	ip link add dev br0 type bridge vlan_filtering 1 \
 		vlan_default_pvid 0 mcast_snooping 0
+	ip link set dev br0 addrgenmode none
 
 	ip link set dev $swp1 master br0
 	ip link set dev br0 up
@@ -155,6 +157,7 @@ create_vlan_upper_on_top_front_panel_enslaved_to_8021ad_bridge()
 
 	ip link add dev br0 type bridge vlan_filtering 1 \
 		vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0
+	ip link set dev br0 addrgenmode none
 	ip link set dev br0 up
 
 	ip link set dev $swp1 master br0
@@ -177,6 +180,7 @@ create_vlan_upper_on_top_lag_enslaved_to_8021ad_bridge()
 
 	ip link add dev br0 type bridge vlan_filtering 1 \
 		vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0
+	ip link set dev br0 addrgenmode none
 	ip link set dev br0 up
 
 	ip link add name bond1 type bond mode 802.3ad
@@ -203,6 +207,7 @@ enslave_front_panel_with_vlan_upper_to_8021ad_bridge()
 
 	ip link add dev br0 type bridge vlan_filtering 1 \
 		vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0
+	ip link set dev br0 addrgenmode none
 	ip link set dev br0 up
 
 	ip link add name $swp1.100 link $swp1 type vlan id 100
@@ -225,6 +230,7 @@ enslave_lag_with_vlan_upper_to_8021ad_bridge()
 
 	ip link add dev br0 type bridge vlan_filtering 1 \
 		vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0
+	ip link set dev br0 addrgenmode none
 	ip link set dev br0 up
 
 	ip link add name bond1 type bond mode 802.3ad
@@ -252,6 +258,7 @@ add_ip_address_to_8021ad_bridge()
 
 	ip link add dev br0 type bridge vlan_filtering 1 \
 		vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0
+	ip link set dev br0 addrgenmode none
 
 	ip link set dev br0 up
 	ip link set dev $swp1 master br0
@@ -273,6 +280,7 @@ switch_bridge_protocol_from_8021q_to_8021ad()
 
 	ip link add dev br0 type bridge vlan_filtering 1 \
 		vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0
+	ip link set dev br0 addrgenmode none
 
 	ip link set dev br0 up
 	ip link set dev $swp1 master br0
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh
index 71066bc4b886..5492fa5550d7 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_defprio.sh
@@ -5,18 +5,18 @@
 # prioritized according to the default priority specified at the port.
 # rx_octets_prio_* counters are used to verify the prioritization.
 #
-# +-----------------------+
-# | H1                    |
-# |    + $h1              |
-# |    | 192.0.2.1/28     |
-# +----|------------------+
+# +----------------------------------+
+# | H1                               |
+# |    + $h1                         |
+# |    | 192.0.2.1/28                |
+# +----|-----------------------------+
 #      |
-# +----|------------------+
-# | SW |                  |
-# |    + $swp1            |
-# |      192.0.2.2/28     |
-# |      APP=<prio>,1,0   |
-# +-----------------------+
+# +----|-----------------------------+
+# | SW |                             |
+# |    + $swp1                       |
+# |      192.0.2.2/28                |
+# |      dcb app default-prio <prio> |
+# +----------------------------------+
 
 ALL_TESTS="
 	ping_ipv4
@@ -29,42 +29,6 @@ NUM_NETIFS=2
 : ${HIT_TIMEOUT:=1000} # ms
 source $lib_dir/lib.sh
 
-declare -a APP
-
-defprio_install()
-{
-	local dev=$1; shift
-	local prio=$1; shift
-	local app="app=$prio,1,0"
-
-	lldptool -T -i $dev -V APP $app >/dev/null
-	lldpad_app_wait_set $dev
-	APP[$prio]=$app
-}
-
-defprio_uninstall()
-{
-	local dev=$1; shift
-	local prio=$1; shift
-	local app=${APP[$prio]}
-
-	lldptool -T -i $dev -V APP -d $app >/dev/null
-	lldpad_app_wait_del
-	unset APP[$prio]
-}
-
-defprio_flush()
-{
-	local dev=$1; shift
-	local prio
-
-	if ((${#APP[@]})); then
-		lldptool -T -i $dev -V APP -d ${APP[@]} >/dev/null
-	fi
-	lldpad_app_wait_del
-	APP=()
-}
-
 h1_create()
 {
 	simple_if_init $h1 192.0.2.1/28
@@ -83,7 +47,7 @@ switch_create()
 
 switch_destroy()
 {
-	defprio_flush $swp1
+	dcb app flush dev $swp1 default-prio
 	ip addr del dev $swp1 192.0.2.2/28
 	ip link set dev $swp1 down
 }
@@ -124,7 +88,7 @@ __test_defprio()
 
 	RET=0
 
-	defprio_install $swp1 $prio_install
+	dcb app add dev $swp1 default-prio $prio_install
 
 	local t0=$(ethtool_stats_get $swp1 rx_frames_prio_$prio_observe)
 	mausezahn -q $h1 -d 100m -c 10 -t arp reply
@@ -134,7 +98,7 @@ __test_defprio()
 	check_err $? "Default priority $prio_install/$prio_observe: Expected to capture 10 packets, got $((t1 - t0))."
 	log_test "Default priority $prio_install/$prio_observe"
 
-	defprio_uninstall $swp1 $prio_install
+	dcb app del dev $swp1 default-prio $prio_install
 }
 
 test_defprio()
@@ -145,7 +109,7 @@ test_defprio()
 		__test_defprio $prio $prio
 	done
 
-	defprio_install $swp1 3
+	dcb app add dev $swp1 default-prio 3
 	__test_defprio 0 3
 	__test_defprio 1 3
 	__test_defprio 2 3
@@ -153,7 +117,7 @@ test_defprio()
 	__test_defprio 5 5
 	__test_defprio 6 6
 	__test_defprio 7 7
-	defprio_uninstall $swp1 3
+	dcb app del dev $swp1 default-prio 3
 }
 
 trap cleanup EXIT
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh
index 28a570006d4d..914c63d6318a 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh
@@ -20,7 +20,7 @@
 # | SW |                                                                |     |
 # |  +-|----------------------------------------------------------------|-+   |
 # |  | + $swp1                       BR                           $swp2 + |   |
-# |  |   APP=0,5,10 .. 7,5,17                      APP=0,5,20 .. 7,5,27   |   |
+# |  |   dcb dscp-prio 10:0...17:7            dcb dscp-prio 20:0...27:7   |   |
 # |  +--------------------------------------------------------------------+   |
 # +---------------------------------------------------------------------------+
 
@@ -62,36 +62,24 @@ h2_destroy()
 	simple_if_fini $h2 192.0.2.2/28
 }
 
-dscp_map()
-{
-	local base=$1; shift
-	local prio
-
-	for prio in {0..7}; do
-		echo app=$prio,5,$((base + prio))
-	done
-}
-
 switch_create()
 {
 	ip link add name br1 type bridge vlan_filtering 1
+	ip link set dev br1 addrgenmode none
 	ip link set dev br1 up
 	ip link set dev $swp1 master br1
 	ip link set dev $swp1 up
 	ip link set dev $swp2 master br1
 	ip link set dev $swp2 up
 
-	lldptool -T -i $swp1 -V APP $(dscp_map 10) >/dev/null
-	lldptool -T -i $swp2 -V APP $(dscp_map 20) >/dev/null
-	lldpad_app_wait_set $swp1
-	lldpad_app_wait_set $swp2
+	dcb app add dev $swp1 dscp-prio 10:0 11:1 12:2 13:3 14:4 15:5 16:6 17:7
+	dcb app add dev $swp2 dscp-prio 20:0 21:1 22:2 23:3 24:4 25:5 26:6 27:7
 }
 
 switch_destroy()
 {
-	lldptool -T -i $swp2 -V APP -d $(dscp_map 20) >/dev/null
-	lldptool -T -i $swp1 -V APP -d $(dscp_map 10) >/dev/null
-	lldpad_app_wait_del
+	dcb app del dev $swp2 dscp-prio 20:0 21:1 22:2 23:3 24:4 25:5 26:6 27:7
+	dcb app del dev $swp1 dscp-prio 10:0 11:1 12:2 13:3 14:4 15:5 16:6 17:7
 
 	ip link set dev $swp2 down
 	ip link set dev $swp2 nomaster
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh
index 4cb2aa65278a..f6c23f84423e 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh
@@ -94,16 +94,6 @@ h2_destroy()
 	simple_if_fini $h2 192.0.2.18/28
 }
 
-dscp_map()
-{
-	local base=$1; shift
-	local prio
-
-	for prio in {0..7}; do
-		echo app=$prio,5,$((base + prio))
-	done
-}
-
 switch_create()
 {
 	simple_if_init $swp1 192.0.2.2/28
@@ -112,17 +102,14 @@ switch_create()
 	tc qdisc add dev $swp1 clsact
 	tc qdisc add dev $swp2 clsact
 
-	lldptool -T -i $swp1 -V APP $(dscp_map 0) >/dev/null
-	lldptool -T -i $swp2 -V APP $(dscp_map 0) >/dev/null
-	lldpad_app_wait_set $swp1
-	lldpad_app_wait_set $swp2
+	dcb app add dev $swp1 dscp-prio 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
+	dcb app add dev $swp2 dscp-prio 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
 }
 
 switch_destroy()
 {
-	lldptool -T -i $swp2 -V APP -d $(dscp_map 0) >/dev/null
-	lldptool -T -i $swp1 -V APP -d $(dscp_map 0) >/dev/null
-	lldpad_app_wait_del
+	dcb app del dev $swp2 dscp-prio 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
+	dcb app del dev $swp1 dscp-prio 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
 
 	tc qdisc del dev $swp2 clsact
 	tc qdisc del dev $swp1 clsact
@@ -265,13 +252,11 @@ test_dscp_leftover()
 {
 	echo "Test that last removed DSCP rule is deconfigured correctly"
 
-	lldptool -T -i $swp2 -V APP -d $(dscp_map 0) >/dev/null
-	lldpad_app_wait_del
+	dcb app del dev $swp2 dscp-prio 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
 
 	__test_update 0 zero
 
-	lldptool -T -i $swp2 -V APP $(dscp_map 0) >/dev/null
-	lldpad_app_wait_set $swp2
+	dcb app add dev $swp2 dscp-prio 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
 }
 
 trap cleanup EXIT
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh
index 690d8daa71b4..9ca340c5f3a6 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_ets_strict.sh
@@ -57,66 +57,60 @@ source qos_lib.sh
 
 h1_create()
 {
-	simple_if_init $h1
+	adf_simple_if_init $h1
+
 	mtu_set $h1 10000
+	defer mtu_restore $h1
 
 	vlan_create $h1 111 v$h1 192.0.2.33/28
+	defer vlan_destroy $h1 111
 	ip link set dev $h1.111 type vlan egress-qos-map 0:1
 }
 
-h1_destroy()
-{
-	vlan_destroy $h1 111
-
-	mtu_restore $h1
-	simple_if_fini $h1
-}
-
 h2_create()
 {
-	simple_if_init $h2
+	adf_simple_if_init $h2
+
 	mtu_set $h2 10000
+	defer mtu_restore $h2
 
 	vlan_create $h2 222 v$h2 192.0.2.65/28
+	defer vlan_destroy $h2 222
 	ip link set dev $h2.222 type vlan egress-qos-map 0:2
 }
 
-h2_destroy()
-{
-	vlan_destroy $h2 222
-
-	mtu_restore $h2
-	simple_if_fini $h2
-}
-
 h3_create()
 {
-	simple_if_init $h3
+	adf_simple_if_init $h3
+
 	mtu_set $h3 10000
+	defer mtu_restore $h3
 
 	vlan_create $h3 111 v$h3 192.0.2.34/28
-	vlan_create $h3 222 v$h3 192.0.2.66/28
-}
-
-h3_destroy()
-{
-	vlan_destroy $h3 222
-	vlan_destroy $h3 111
+	defer vlan_destroy $h3 111
 
-	mtu_restore $h3
-	simple_if_fini $h3
+	vlan_create $h3 222 v$h3 192.0.2.66/28
+	defer vlan_destroy $h3 222
 }
 
 switch_create()
 {
 	ip link set dev $swp1 up
+	defer ip link set dev $swp1 down
+
 	mtu_set $swp1 10000
+	defer mtu_restore $swp1
 
 	ip link set dev $swp2 up
+	defer ip link set dev $swp2 down
+
 	mtu_set $swp2 10000
+	defer mtu_restore $swp2
 
 	# prio n -> TC n, strict scheduling
 	lldptool -T -i $swp3 -V ETS-CFG up2tc=0:0,1:1,2:2,3:3,4:4,5:5,6:6,7:7
+	defer lldptool -T -i $swp3 -V ETS-CFG up2tc=0:0,1:0,2:0,3:0,4:0,5:0,6:0,7:0
+
 	lldptool -T -i $swp3 -V ETS-CFG tsa=$(
 			)"0:strict,"$(
 			)"1:strict,"$(
@@ -129,81 +123,90 @@ switch_create()
 	sleep 1
 
 	ip link set dev $swp3 up
+	defer ip link set dev $swp3 down
+
 	mtu_set $swp3 10000
+	defer mtu_restore $swp3
+
 	tc qdisc replace dev $swp3 root handle 101: tbf rate 1gbit \
 		burst 128K limit 1G
+	defer tc qdisc del dev $swp3 root handle 101:
 
 	vlan_create $swp1 111
+	defer vlan_destroy $swp1 111
+
 	vlan_create $swp2 222
+	defer vlan_destroy $swp2 222
+
 	vlan_create $swp3 111
+	defer vlan_destroy $swp3 111
+
 	vlan_create $swp3 222
+	defer vlan_destroy $swp3 222
+
+	ip link add name br111 type bridge vlan_filtering 0
+	defer ip link del dev br111
+	ip link set dev br111 addrgenmode none
+
+	ip link set dev br111 up
+	defer ip link set dev br111 down
 
-	ip link add name br111 up type bridge vlan_filtering 0
 	ip link set dev $swp1.111 master br111
+	defer ip link set dev $swp1.111 nomaster
+
 	ip link set dev $swp3.111 master br111
+	defer ip link set dev $swp3.111 nomaster
+
+	ip link add name br222 type bridge vlan_filtering 0
+	defer ip link del dev br222
+	ip link set dev br222 addrgenmode none
+
+	ip link set dev br222 up
+	defer ip link set dev br222 down
 
-	ip link add name br222 up type bridge vlan_filtering 0
 	ip link set dev $swp2.222 master br222
+	defer ip link set dev $swp2.222 nomaster
+
 	ip link set dev $swp3.222 master br222
+	defer ip link set dev $swp3.222 nomaster
 
 	# Make sure that ingress quotas are smaller than egress so that there is
 	# room for both streams of traffic to be admitted to shared buffer.
 	devlink_pool_size_thtype_save 0
 	devlink_pool_size_thtype_set 0 dynamic 10000000
+	defer devlink_pool_size_thtype_restore 0
+
 	devlink_pool_size_thtype_save 4
 	devlink_pool_size_thtype_set 4 dynamic 10000000
+	defer devlink_pool_size_thtype_restore 4
 
 	devlink_port_pool_th_save $swp1 0
 	devlink_port_pool_th_set $swp1 0 6
+	defer devlink_port_pool_th_restore $swp1 0
+
 	devlink_tc_bind_pool_th_save $swp1 1 ingress
 	devlink_tc_bind_pool_th_set $swp1 1 ingress 0 6
+	defer devlink_tc_bind_pool_th_restore $swp1 1 ingress
 
 	devlink_port_pool_th_save $swp2 0
 	devlink_port_pool_th_set $swp2 0 6
+	defer devlink_port_pool_th_restore $swp2 0
+
 	devlink_tc_bind_pool_th_save $swp2 2 ingress
 	devlink_tc_bind_pool_th_set $swp2 2 ingress 0 6
+	defer devlink_tc_bind_pool_th_restore $swp2 2 ingress
 
 	devlink_tc_bind_pool_th_save $swp3 1 egress
 	devlink_tc_bind_pool_th_set $swp3 1 egress 4 7
+	defer devlink_tc_bind_pool_th_restore $swp3 1 egress
+
 	devlink_tc_bind_pool_th_save $swp3 2 egress
 	devlink_tc_bind_pool_th_set $swp3 2 egress 4 7
+	defer devlink_tc_bind_pool_th_restore $swp3 2 egress
+
 	devlink_port_pool_th_save $swp3 4
 	devlink_port_pool_th_set $swp3 4 7
-}
-
-switch_destroy()
-{
-	devlink_port_pool_th_restore $swp3 4
-	devlink_tc_bind_pool_th_restore $swp3 2 egress
-	devlink_tc_bind_pool_th_restore $swp3 1 egress
-
-	devlink_tc_bind_pool_th_restore $swp2 2 ingress
-	devlink_port_pool_th_restore $swp2 0
-
-	devlink_tc_bind_pool_th_restore $swp1 1 ingress
-	devlink_port_pool_th_restore $swp1 0
-
-	devlink_pool_size_thtype_restore 4
-	devlink_pool_size_thtype_restore 0
-
-	ip link del dev br222
-	ip link del dev br111
-
-	vlan_destroy $swp3 222
-	vlan_destroy $swp3 111
-	vlan_destroy $swp2 222
-	vlan_destroy $swp1 111
-
-	tc qdisc del dev $swp3 root handle 101:
-	mtu_restore $swp3
-	ip link set dev $swp3 down
-	lldptool -T -i $swp3 -V ETS-CFG up2tc=0:0,1:0,2:0,3:0,4:0,5:0,6:0,7:0
-
-	mtu_restore $swp2
-	ip link set dev $swp2 down
-
-	mtu_restore $swp1
-	ip link set dev $swp1 down
+	defer devlink_port_pool_th_restore $swp3 4
 }
 
 setup_prepare()
@@ -219,7 +222,7 @@ setup_prepare()
 
 	h3mac=$(mac_get $h3)
 
-	vrf_prepare
+	adf_vrf_prepare
 
 	h1_create
 	h2_create
@@ -227,18 +230,6 @@ setup_prepare()
 	switch_create
 }
 
-cleanup()
-{
-	pre_cleanup
-
-	switch_destroy
-	h3_destroy
-	h2_destroy
-	h1_destroy
-
-	vrf_cleanup
-}
-
 ping_ipv4()
 {
 	ping_test $h1 192.0.2.34 " from H1"
@@ -257,21 +248,38 @@ rel()
 	"
 }
 
+__run_hi_measure_rate()
+{
+	local what=$1; shift
+	local -a uc_rate
+
+	start_traffic $h2.222 192.0.2.65 192.0.2.66 $h3mac
+	defer stop_traffic $!
+
+	uc_rate=($(measure_rate $swp2 $h3 rx_octets_prio_2 "$what"))
+	check_err $? "Could not get high enough $what ingress rate"
+
+	echo ${uc_rate[@]}
+}
+
+run_hi_measure_rate()
+{
+	in_defer_scope __run_hi_measure_rate "$@"
+}
+
 test_ets_strict()
 {
 	RET=0
 
 	# Run high-prio traffic on its own.
-	start_traffic $h2.222 192.0.2.65 192.0.2.66 $h3mac
 	local -a rate_2
-	rate_2=($(measure_rate $swp2 $h3 rx_octets_prio_2 "prio 2"))
-	check_err $? "Could not get high enough prio-2 ingress rate"
+	rate_2=($(run_hi_measure_rate "prio 2"))
 	local rate_2_in=${rate_2[0]}
 	local rate_2_eg=${rate_2[1]}
-	stop_traffic # $h2.222
 
 	# Start low-prio stream.
 	start_traffic $h1.111 192.0.2.33 192.0.2.34 $h3mac
+	defer stop_traffic $!
 
 	local -a rate_1
 	rate_1=($(measure_rate $swp1 $h3 rx_octets_prio_1 "prio 1"))
@@ -286,14 +294,9 @@ test_ets_strict()
 	check_err $(bc <<< "$rel21 > 105")
 
 	# Start the high-prio stream--now both streams run.
-	start_traffic $h2.222 192.0.2.65 192.0.2.66 $h3mac
-	rate_3=($(measure_rate $swp2 $h3 rx_octets_prio_2 "prio 2 w/ 1"))
-	check_err $? "Could not get high enough prio-2 ingress rate with prio-1"
+	rate_3=($(run_hi_measure_rate "prio 2+1"))
 	local rate_3_in=${rate_3[0]}
 	local rate_3_eg=${rate_3[1]}
-	stop_traffic # $h2.222
-
-	stop_traffic # $h1.111
 
 	# High-prio should have about the same throughput whether or not
 	# low-prio is in the system.
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_headroom.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_headroom.sh
index 3569ff45f7d5..88162b4027c0 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_headroom.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_headroom.sh
@@ -18,7 +18,6 @@ lib_dir=$(dirname $0)/../../../net/forwarding
 NUM_NETIFS=0
 source $lib_dir/lib.sh
 source $lib_dir/devlink_lib.sh
-source qos_lib.sh
 
 swp=$NETIF_NO_CABLE
 
@@ -371,7 +370,7 @@ test_tc_int_buf()
 	tc qdisc delete dev $swp root
 }
 
-bail_on_lldpad
+bail_on_lldpad "configure DCB" "configure Qdiscs"
 
 trap cleanup EXIT
 setup_wait
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh
index faa51012cdac..5ad092b9bf10 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_lib.sh
@@ -54,31 +54,3 @@ measure_rate()
 	echo $ir $er
 	return $ret
 }
-
-bail_on_lldpad()
-{
-	if systemctl is-active --quiet lldpad; then
-
-		cat >/dev/stderr <<-EOF
-		WARNING: lldpad is running
-
-			lldpad will likely configure DCB, and this test will
-			configure Qdiscs. mlxsw does not support both at the
-			same time, one of them is arbitrarily going to overwrite
-			the other. That will cause spurious failures (or,
-			unlikely, passes) of this test.
-		EOF
-
-		if [[ -z $ALLOW_LLDPAD ]]; then
-			cat >/dev/stderr <<-EOF
-
-				If you want to run the test anyway, please set
-				an environment variable ALLOW_LLDPAD to a
-				non-empty string.
-			EOF
-			exit 1
-		else
-			return
-		fi
-	fi
-}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_max_descriptors.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_max_descriptors.sh
index 5ac4f795e333..a4a25637fe2a 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_max_descriptors.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_max_descriptors.sh
@@ -68,128 +68,102 @@ mlxsw_only_on_spectrum 2+ || exit
 
 h1_create()
 {
-	simple_if_init $h1
+	adf_simple_if_init $h1
 
 	vlan_create $h1 111 v$h1 192.0.2.33/28
+	defer vlan_destroy $h1 111
 	ip link set dev $h1.111 type vlan egress-qos-map 0:1
 }
 
-h1_destroy()
-{
-	vlan_destroy $h1 111
-
-	simple_if_fini $h1
-}
-
 h2_create()
 {
-	simple_if_init $h2
+	adf_simple_if_init $h2
 
 	vlan_create $h2 111 v$h2 192.0.2.34/28
-}
-
-h2_destroy()
-{
-	vlan_destroy $h2 111
-
-	simple_if_fini $h2
+	defer vlan_destroy $h2 111
 }
 
 switch_create()
 {
 	# pools
 	# -----
+	# devlink_pool_size_thtype_restore needs to be done first so that we can
+	# reset the various limits to values that are only valid for the
+	# original static / dynamic setting.
 
 	devlink_pool_size_thtype_save 1
-	devlink_pool_size_thtype_save 6
-
-	devlink_port_pool_th_save $swp1 1
-	devlink_port_pool_th_save $swp2 6
-
-	devlink_tc_bind_pool_th_save $swp1 1 ingress
-	devlink_tc_bind_pool_th_save $swp2 1 egress
-
 	devlink_pool_size_thtype_set 1 dynamic $MAX_POOL_SIZE
+	defer_prio devlink_pool_size_thtype_restore 1
+
+	devlink_pool_size_thtype_save 6
 	devlink_pool_size_thtype_set 6 static $MAX_POOL_SIZE
+	defer_prio devlink_pool_size_thtype_restore 6
 
 	# $swp1
 	# -----
 
 	ip link set dev $swp1 up
+	defer ip link set dev $swp1 down
+
 	vlan_create $swp1 111
+	defer vlan_destroy $swp1 111
 	ip link set dev $swp1.111 type vlan ingress-qos-map 0:0 1:1
 
+	devlink_port_pool_th_save $swp1 1
 	devlink_port_pool_th_set $swp1 1 16
+	defer devlink_tc_bind_pool_th_restore $swp1 1 ingress
+
+	devlink_tc_bind_pool_th_save $swp1 1 ingress
 	devlink_tc_bind_pool_th_set $swp1 1 ingress 1 16
+	defer devlink_port_pool_th_restore $swp1 1
 
 	tc qdisc replace dev $swp1 root handle 1: \
 	   ets bands 8 strict 8 priomap 7 6
+	defer tc qdisc del dev $swp1 root
+
 	dcb buffer set dev $swp1 prio-buffer all:0 1:1
+	defer dcb buffer set dev $swp1 prio-buffer all:0
 
 	# $swp2
 	# -----
 
 	ip link set dev $swp2 up
+	defer ip link set dev $swp2 down
+
 	vlan_create $swp2 111
+	defer vlan_destroy $swp2 111
 	ip link set dev $swp2.111 type vlan egress-qos-map 0:0 1:1
 
+	devlink_port_pool_th_save $swp2 6
 	devlink_port_pool_th_set $swp2 6 $MAX_POOL_SIZE
+	defer devlink_tc_bind_pool_th_restore $swp2 1 egress
+
+	devlink_tc_bind_pool_th_save $swp2 1 egress
 	devlink_tc_bind_pool_th_set $swp2 1 egress 6 $MAX_POOL_SIZE
+	defer devlink_port_pool_th_restore $swp2 6
 
 	tc qdisc replace dev $swp2 root handle 1: tbf rate $SHAPER_RATE \
 		burst 128K limit 500M
+	defer tc qdisc del dev $swp2 root
+
 	tc qdisc replace dev $swp2 parent 1:1 handle 11: \
 		ets bands 8 strict 8 priomap 7 6
+	defer tc qdisc del dev $swp2 parent 1:1 handle 11:
 
 	# bridge
 	# ------
 
 	ip link add name br1 type bridge vlan_filtering 0
+	defer ip link del dev br1
+
 	ip link set dev $swp1.111 master br1
+	defer ip link set dev $swp1.111 nomaster
+
 	ip link set dev br1 up
+	defer ip link set dev br1 down
 
 	ip link set dev $swp2.111 master br1
-}
-
-switch_destroy()
-{
-	# Do this first so that we can reset the limits to values that are only
-	# valid for the original static / dynamic setting.
-	devlink_pool_size_thtype_restore 6
-	devlink_pool_size_thtype_restore 1
-
-	# bridge
-	# ------
-
-	ip link set dev $swp2.111 nomaster
-
-	ip link set dev br1 down
-	ip link set dev $swp1.111 nomaster
-	ip link del dev br1
-
-	# $swp2
-	# -----
-
-	tc qdisc del dev $swp2 parent 1:1 handle 11:
-	tc qdisc del dev $swp2 root
-
-	devlink_tc_bind_pool_th_restore $swp2 1 egress
-	devlink_port_pool_th_restore $swp2 6
-
-	vlan_destroy $swp2 111
-	ip link set dev $swp2 down
-
-	# $swp1
-	# -----
-
-	dcb buffer set dev $swp1 prio-buffer all:0
-	tc qdisc del dev $swp1 root
-
-	devlink_tc_bind_pool_th_restore $swp1 1 ingress
-	devlink_port_pool_th_restore $swp1 1
-
-	vlan_destroy $swp1 111
-	ip link set dev $swp1 down
+	defer ip link set dev $swp2.111 nomaster
 }
 
 setup_prepare()
@@ -202,24 +176,13 @@ setup_prepare()
 
 	h2mac=$(mac_get $h2)
 
-	vrf_prepare
+	adf_vrf_prepare
 
 	h1_create
 	h2_create
 	switch_create
 }
 
-cleanup()
-{
-	pre_cleanup
-
-	switch_destroy
-	h2_destroy
-	h1_destroy
-
-	vrf_cleanup
-}
-
 ping_ipv4()
 {
 	ping_test $h1 192.0.2.34 " h1->h2"
@@ -251,6 +214,7 @@ max_descriptors()
 
 	log_info "Send many small packets, packet size = $pktsize bytes"
 	start_traffic_pktsize $pktsize $h1.111 192.0.2.33 192.0.2.34 $h2mac
+	defer stop_traffic $!
 
 	# Sleep to wait for congestion.
 	sleep 5
@@ -268,9 +232,6 @@ max_descriptors()
 	check_err $(bc <<< "$perc_used < $exp_perc_used") \
 		"Expected > $exp_perc_used% of descriptors, handle $perc_used%"
 
-	stop_traffic
-	sleep 1
-
 	log_test "Maximum descriptors usage. The percentage used is $perc_used%"
 }
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
index c8e55fa91660..d8f8ae8533cd 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh
@@ -72,121 +72,112 @@ source qos_lib.sh
 
 h1_create()
 {
-	simple_if_init $h1 192.0.2.65/28
-	mtu_set $h1 10000
-}
+	adf_simple_if_init $h1 192.0.2.65/28
 
-h1_destroy()
-{
-	mtu_restore $h1
-	simple_if_fini $h1 192.0.2.65/28
+	mtu_set $h1 10000
+	defer mtu_restore $h1
 }
 
 h2_create()
 {
-	simple_if_init $h2
+	adf_simple_if_init $h2
+
 	mtu_set $h2 10000
+	defer mtu_restore $h2
 
 	vlan_create $h2 111 v$h2 192.0.2.129/28
+	defer vlan_destroy $h2 111
 	ip link set dev $h2.111 type vlan egress-qos-map 0:1
 }
 
-h2_destroy()
-{
-	vlan_destroy $h2 111
-
-	mtu_restore $h2
-	simple_if_fini $h2
-}
-
 h3_create()
 {
-	simple_if_init $h3 192.0.2.66/28
+	adf_simple_if_init $h3 192.0.2.66/28
+
 	mtu_set $h3 10000
+	defer mtu_restore $h3
 
 	vlan_create $h3 111 v$h3 192.0.2.130/28
-}
-
-h3_destroy()
-{
-	vlan_destroy $h3 111
-
-	mtu_restore $h3
-	simple_if_fini $h3 192.0.2.66/28
+	defer vlan_destroy $h3 111
 }
 
 switch_create()
 {
 	ip link set dev $swp1 up
+	defer ip link set dev $swp1 down
+
 	mtu_set $swp1 10000
+	defer mtu_restore $swp1
 
 	ip link set dev $swp2 up
+	defer ip link set dev $swp2 down
+
 	mtu_set $swp2 10000
+	defer mtu_restore $swp2
 
 	ip link set dev $swp3 up
+	defer ip link set dev $swp3 down
+
 	mtu_set $swp3 10000
+	defer mtu_restore $swp3
 
 	vlan_create $swp2 111
+	defer vlan_destroy $swp2 111
+
 	vlan_create $swp3 111
+	defer vlan_destroy $swp3 111
 
 	tc qdisc replace dev $swp3 root handle 3: tbf rate 1gbit \
 		burst 128K limit 1G
+	defer tc qdisc del dev $swp3 root handle 3:
+
 	tc qdisc replace dev $swp3 parent 3:3 handle 33: \
 		prio bands 8 priomap 7 7 7 7 7 7 7 7
+	defer tc qdisc del dev $swp3 parent 3:3 handle 33:
 
 	ip link add name br1 type bridge vlan_filtering 0
+	defer ip link del dev br1
+	ip link set dev br1 addrgenmode none
 	ip link set dev br1 up
+
 	ip link set dev $swp1 master br1
+	defer ip link set dev $swp1 nomaster
+
 	ip link set dev $swp3 master br1
+	defer ip link set dev $swp3 nomaster
 
 	ip link add name br111 type bridge vlan_filtering 0
+	defer ip link del dev br111
+	ip link set dev br111 addrgenmode none
 	ip link set dev br111 up
+
 	ip link set dev $swp2.111 master br111
+	defer ip link set dev $swp2.111 nomaster
+
 	ip link set dev $swp3.111 master br111
+	defer ip link set dev $swp3.111 nomaster
 
 	# Make sure that ingress quotas are smaller than egress so that there is
 	# room for both streams of traffic to be admitted to shared buffer.
 	devlink_port_pool_th_save $swp1 0
 	devlink_port_pool_th_set $swp1 0 5
+	defer devlink_port_pool_th_restore $swp1 0
+
 	devlink_tc_bind_pool_th_save $swp1 0 ingress
 	devlink_tc_bind_pool_th_set $swp1 0 ingress 0 5
+	defer devlink_tc_bind_pool_th_restore $swp1 0 ingress
 
 	devlink_port_pool_th_save $swp2 0
 	devlink_port_pool_th_set $swp2 0 5
+	defer devlink_port_pool_th_restore $swp2 0
+
 	devlink_tc_bind_pool_th_save $swp2 1 ingress
 	devlink_tc_bind_pool_th_set $swp2 1 ingress 0 5
+	defer devlink_tc_bind_pool_th_restore $swp2 1 ingress
 
 	devlink_port_pool_th_save $swp3 4
 	devlink_port_pool_th_set $swp3 4 12
-}
-
-switch_destroy()
-{
-	devlink_port_pool_th_restore $swp3 4
-
-	devlink_tc_bind_pool_th_restore $swp2 1 ingress
-	devlink_port_pool_th_restore $swp2 0
-
-	devlink_tc_bind_pool_th_restore $swp1 0 ingress
-	devlink_port_pool_th_restore $swp1 0
-
-	ip link del dev br111
-	ip link del dev br1
-
-	tc qdisc del dev $swp3 parent 3:3 handle 33:
-	tc qdisc del dev $swp3 root handle 3:
-
-	vlan_destroy $swp3 111
-	vlan_destroy $swp2 111
-
-	mtu_restore $swp3
-	ip link set dev $swp3 down
-
-	mtu_restore $swp2
-	ip link set dev $swp2 down
-
-	mtu_restore $swp1
-	ip link set dev $swp1 down
+	defer devlink_port_pool_th_restore $swp3 4
 }
 
 setup_prepare()
@@ -202,7 +193,7 @@ setup_prepare()
 
 	h3mac=$(mac_get $h3)
 
-	vrf_prepare
+	adf_vrf_prepare
 
 	h1_create
 	h2_create
@@ -210,45 +201,45 @@ setup_prepare()
 	switch_create
 }
 
-cleanup()
+ping_ipv4()
 {
-	pre_cleanup
+	ping_test $h2 192.0.2.130
+}
 
-	switch_destroy
-	h3_destroy
-	h2_destroy
-	h1_destroy
+__run_uc_measure_rate()
+{
+	local what=$1; shift
+	local -a uc_rate
+
+	start_traffic $h2.111 192.0.2.129 192.0.2.130 $h3mac
+	defer stop_traffic $!
+
+	uc_rate=($(measure_rate $swp2 $h3 rx_octets_prio_1 "$what"))
+	check_err $? "Could not get high enough $what ingress rate"
 
-	vrf_cleanup
+	echo ${uc_rate[@]}
 }
 
-ping_ipv4()
+run_uc_measure_rate()
 {
-	ping_test $h2 192.0.2.130
+	in_defer_scope __run_uc_measure_rate "$@"
 }
 
 test_mc_aware()
 {
 	RET=0
 
-	local -a uc_rate
-	start_traffic $h2.111 192.0.2.129 192.0.2.130 $h3mac
-	uc_rate=($(measure_rate $swp2 $h3 rx_octets_prio_1 "UC-only"))
-	check_err $? "Could not get high enough UC-only ingress rate"
-	stop_traffic
+	local -a uc_rate=($(run_uc_measure_rate "UC-only"))
 	local ucth1=${uc_rate[1]}
 
 	start_traffic $h1 192.0.2.65 bc bc
+	defer stop_traffic $!
 
 	local d0=$(date +%s)
 	local t0=$(ethtool_stats_get $h3 rx_octets_prio_0)
 	local u0=$(ethtool_stats_get $swp1 rx_octets_prio_0)
 
-	local -a uc_rate_2
-	start_traffic $h2.111 192.0.2.129 192.0.2.130 $h3mac
-	uc_rate_2=($(measure_rate $swp2 $h3 rx_octets_prio_1 "UC+MC"))
-	check_err $? "Could not get high enough UC+MC ingress rate"
-	stop_traffic
+	local -a uc_rate_2=($(run_uc_measure_rate "UC+MC"))
 	local ucth2=${uc_rate_2[1]}
 
 	local d1=$(date +%s)
@@ -270,8 +261,6 @@ test_mc_aware()
 	local mc_ir=$(rate $u0 $u1 $interval)
 	local mc_er=$(rate $t0 $t1 $interval)
 
-	stop_traffic
-
 	log_test "UC performance under MC overload"
 
 	echo "UC-only throughput  $(humanize $ucth1)"
@@ -295,6 +284,7 @@ test_uc_aware()
 	RET=0
 
 	start_traffic $h2.111 192.0.2.129 192.0.2.130 $h3mac
+	defer stop_traffic $!
 
 	local d0=$(date +%s)
 	local t0=$(ethtool_stats_get $h3 rx_octets_prio_1)
@@ -324,8 +314,6 @@ test_uc_aware()
 	((attempts == passes))
 	check_err $?
 
-	stop_traffic
-
 	log_test "MC performance under UC overload"
 	echo "    ingress UC throughput $(humanize ${uc_ir})"
 	echo "    egress UC throughput  $(humanize ${uc_er})"
diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
index f9858e221996..0f0f4f05807c 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh
@@ -40,7 +40,6 @@
 # |   + $swp1          $swp3 +                    + $swp4                     |
 # |   | iPOOL1        iPOOL0 |                    | iPOOL2                    |
 # |   | ePOOL4        ePOOL5 |                    | ePOOL4                    |
-# |   |                1Gbps |                    | 1Gbps                     |
 # |   |        PFC:enabled=1 |                    | PFC:enabled=1             |
 # | +-|----------------------|-+                +-|------------------------+  |
 # | | + $swp1.111  $swp3.111 + |                | + $swp4.111              |  |
@@ -79,7 +78,6 @@ lib_dir=$(dirname $0)/../../../net/forwarding
 NUM_NETIFS=6
 source $lib_dir/lib.sh
 source $lib_dir/devlink_lib.sh
-source qos_lib.sh
 
 _1KB=1000
 _100KB=$((100 * _1KB))
@@ -121,6 +119,9 @@ h2_destroy()
 
 switch_create()
 {
+	local lanes_swp4
+	local pg1_size
+
 	# pools
 	# -----
 
@@ -230,7 +231,20 @@ switch_create()
 	dcb pfc set dev $swp4 prio-pfc all:off 1:on
 	# PG0 will get autoconfigured to Xoff, give PG1 arbitrarily 100K, which
 	# is (-2*MTU) about 80K of delay provision.
-	dcb buffer set dev $swp4 buffer-size all:0 1:$_100KB
+	pg1_size=$_100KB
+
+	setup_wait_dev_with_timeout $swp4
+
+	lanes_swp4=$(ethtool $swp4 | grep 'Lanes:')
+	lanes_swp4=${lanes_swp4#*"Lanes: "}
+
+	# 8-lane ports use two buffers among which the configured buffer
+	# is split, so double the size to get twice (20K + 80K).
+	if [[ $lanes_swp4 -eq 8 ]]; then
+		pg1_size=$((pg1_size * 2))
+	fi
+
+	dcb buffer set dev $swp4 buffer-size all:0 1:$pg1_size
 
 	# bridges
 	# -------
@@ -393,7 +407,7 @@ test_qos_pfc()
 	log_test "PFC"
 }
 
-bail_on_lldpad
+bail_on_lldpad "configure DCB" "configure Qdiscs"
 
 trap cleanup EXIT
 setup_prepare
diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh
new file mode 100755
index 000000000000..4a11bf1d514a
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh
@@ -0,0 +1,184 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+	bridge_rif_add
+	bridge_rif_nomaster
+	bridge_rif_remaster
+	bridge_rif_nomaster_addr
+	bridge_rif_nomaster_port
+	bridge_rif_remaster_port
+"
+
+REQUIRE_TEAMD="yes"
+NUM_NETIFS=2
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+setup_prepare()
+{
+	swp1=${NETIFS[p1]}
+	swp2=${NETIFS[p2]}
+
+	team_create lag1 lacp
+	ip link set dev lag1 addrgenmode none
+	ip link set dev lag1 address $(mac_get $swp1)
+
+	team_create lag2 lacp
+	ip link set dev lag2 addrgenmode none
+	ip link set dev lag2 address $(mac_get $swp2)
+
+	ip link add name br1 type bridge vlan_filtering 1
+	ip link set dev br1 addrgenmode none
+	ip link set dev br1 address $(mac_get lag1)
+	ip link set dev br1 up
+
+	ip link set dev lag1 master br1
+
+	ip link set dev $swp1 master lag1
+	ip link set dev $swp1 up
+
+	ip link set dev $swp2 master lag2
+	ip link set dev $swp2 up
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ip link set dev $swp2 nomaster
+	ip link set dev $swp2 down
+
+	ip link set dev $swp1 nomaster
+	ip link set dev $swp1 down
+
+	ip link del dev lag2
+	ip link set dev lag1 nomaster
+	ip link del dev lag1
+
+	ip link del dev br1
+}
+
+bridge_rif_add()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	__addr_add_del br1 add 192.0.2.2/28
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 + 1))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Add RIF for bridge on address addition"
+}
+
+bridge_rif_nomaster()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	ip link set dev lag1 nomaster
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 - 1))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Drop RIF for bridge on LAG deslavement"
+}
+
+bridge_rif_remaster()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	ip link set dev lag1 master br1
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 + 1))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Add RIF for bridge on LAG reenslavement"
+}
+
+bridge_rif_nomaster_addr()
+{
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+
+	# Adding an address while the LAG is enslaved shouldn't generate a RIF.
+	__addr_add_del lag1 add 192.0.2.65/28
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "After adding IP: Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	# Removing the LAG from the bridge should drop RIF for the bridge (as
+	# tested in bridge_rif_lag_nomaster), but since the LAG now has an
+	# address, it should gain a RIF.
+	ip link set dev lag1 nomaster
+	sleep 1
+	local rifs_occ_t2=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0))
+
+	((expected_rifs == rifs_occ_t2))
+	check_err $? "After deslaving: Expected $expected_rifs RIFs, $rifs_occ_t2 are used"
+
+	log_test "Add RIF for LAG on deslavement from bridge"
+
+	__addr_add_del lag1 del 192.0.2.65/28
+	ip link set dev lag1 master br1
+	sleep 1
+}
+
+bridge_rif_nomaster_port()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	ip link set dev $swp1 nomaster
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 - 1))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Drop RIF for bridge on deslavement of port from LAG"
+}
+
+bridge_rif_remaster_port()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	ip link set dev $swp1 down
+	ip link set dev $swp1 master lag1
+	ip link set dev $swp1 up
+	setup_wait_dev $swp1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 + 1))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Add RIF for bridge on reenslavement of port to LAG"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh
new file mode 100755
index 000000000000..b8bbe94f4736
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh
@@ -0,0 +1,137 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+	lag_rif_add
+	lag_rif_nomaster
+	lag_rif_remaster
+	lag_rif_nomaster_addr
+"
+
+REQUIRE_TEAMD="yes"
+NUM_NETIFS=2
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+setup_prepare()
+{
+	swp1=${NETIFS[p1]}
+	swp2=${NETIFS[p2]}
+
+	team_create lag1 lacp
+	ip link set dev lag1 addrgenmode none
+	ip link set dev lag1 address $(mac_get $swp1)
+
+	team_create lag2 lacp
+	ip link set dev lag2 addrgenmode none
+	ip link set dev lag2 address $(mac_get $swp2)
+
+	ip link set dev $swp1 master lag1
+	ip link set dev $swp1 up
+
+	ip link set dev $swp2 master lag2
+	ip link set dev $swp2 up
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ip link set dev $swp2 nomaster
+	ip link set dev $swp2 down
+
+	ip link set dev $swp1 nomaster
+	ip link set dev $swp1 down
+
+	ip link del dev lag2
+	ip link del dev lag1
+}
+
+lag_rif_add()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	__addr_add_del lag1 add 192.0.2.2/28
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 + 1))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Add RIF for LAG on address addition"
+}
+
+lag_rif_nomaster()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	ip link set dev $swp1 nomaster
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 - 1))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Drop RIF for LAG on port deslavement"
+}
+
+lag_rif_remaster()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	ip link set dev $swp1 down
+	ip link set dev $swp1 master lag1
+	ip link set dev $swp1 up
+	setup_wait_dev $swp1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 + 1))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Add RIF for LAG on port reenslavement"
+}
+
+lag_rif_nomaster_addr()
+{
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+
+	# Adding an address while the port is LAG'd shouldn't generate a RIF.
+	__addr_add_del $swp1 add 192.0.2.65/28
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "After adding IP: Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	# Removing the port from LAG should drop RIF for the LAG (as tested in
+	# lag_rif_nomaster), but since the port now has an address, it should
+	# gain a RIF.
+	ip link set dev $swp1 nomaster
+	sleep 1
+	local rifs_occ_t2=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0))
+
+	((expected_rifs == rifs_occ_t2))
+	check_err $? "After deslaving: Expected $expected_rifs RIFs, $rifs_occ_t2 are used"
+
+	__addr_add_del $swp1 del 192.0.2.65/28
+	log_test "Add RIF for port on deslavement from LAG"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh
new file mode 100755
index 000000000000..d1a9d379eaf3
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh
@@ -0,0 +1,147 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+	lag_rif_add
+	lag_rif_nomaster
+	lag_rif_remaster
+	lag_rif_nomaster_addr
+"
+
+REQUIRE_TEAMD="yes"
+NUM_NETIFS=2
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+setup_prepare()
+{
+	swp1=${NETIFS[p1]}
+	swp2=${NETIFS[p2]}
+
+	team_create lag1 lacp
+	ip link set dev lag1 addrgenmode none
+	ip link set dev lag1 address $(mac_get $swp1)
+
+	team_create lag2 lacp
+	ip link set dev lag2 addrgenmode none
+	ip link set dev lag2 address $(mac_get $swp2)
+
+	ip link set dev $swp1 master lag1
+	ip link set dev $swp1 up
+
+	ip link set dev $swp2 master lag2
+	ip link set dev $swp2 up
+
+	vlan_create lag1 100
+	ip link set dev lag1.100 addrgenmode none
+
+	vlan_create lag1 200
+	ip link set dev lag1.200 addrgenmode none
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ip link del dev lag1.200
+	ip link del dev lag1.100
+
+	ip link set dev $swp2 nomaster
+	ip link set dev $swp2 down
+
+	ip link set dev $swp1 nomaster
+	ip link set dev $swp1 down
+
+	ip link del dev lag2
+	ip link del dev lag1
+}
+
+lag_rif_add()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	__addr_add_del lag1.100 add 192.0.2.2/28
+	__addr_add_del lag1.200 add 192.0.2.18/28
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 + 2))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Add RIFs for LAG VLANs on address addition"
+}
+
+lag_rif_nomaster()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	ip link set dev $swp1 nomaster
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 - 2))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Drop RIFs for LAG VLANs on port deslavement"
+}
+
+lag_rif_remaster()
+{
+	RET=0
+
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+	ip link set dev $swp1 down
+	ip link set dev $swp1 master lag1
+	ip link set dev $swp1 up
+	setup_wait_dev $swp1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 + 2))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	log_test "Add RIFs for LAG VLANs on port reenslavement"
+}
+
+lag_rif_nomaster_addr()
+{
+	local rifs_occ_t0=$(devlink_resource_occ_get rifs)
+
+	# Adding an address while the port is LAG'd shouldn't generate a RIF.
+	__addr_add_del $swp1 add 192.0.2.65/28
+	sleep 1
+	local rifs_occ_t1=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0))
+
+	((expected_rifs == rifs_occ_t1))
+	check_err $? "After adding IP: Expected $expected_rifs RIFs, $rifs_occ_t1 are used"
+
+	# Removing the port from LAG should drop two RIFs for the LAG VLANs (as
+	# tested in lag_rif_nomaster), but since the port now has an address, it
+	# should gain a RIF.
+	ip link set dev $swp1 nomaster
+	sleep 1
+	local rifs_occ_t2=$(devlink_resource_occ_get rifs)
+	local expected_rifs=$((rifs_occ_t0 - 1))
+
+	((expected_rifs == rifs_occ_t2))
+	check_err $? "After deslaving: Expected $expected_rifs RIFs, $rifs_occ_t2 are used"
+
+	__addr_add_del $swp1 del 192.0.2.65/28
+	log_test "Add RIF for port on deslavement from LAG"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/router_bridge_lag.sh b/tools/testing/selftests/drivers/net/mlxsw/router_bridge_lag.sh
new file mode 100755
index 000000000000..6ce317cfaf9b
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/router_bridge_lag.sh
@@ -0,0 +1,50 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test enslavement to LAG with a clean slate.
+# See $lib_dir/router_bridge_lag.sh for further details.
+
+ALL_TESTS="
+	config_devlink_reload
+	config_enslave_h1
+	config_enslave_h2
+	config_enslave_h3
+	config_enslave_h4
+	config_enslave_swp1
+	config_enslave_swp2
+	config_enslave_swp3
+	config_enslave_swp4
+	config_wait
+	ping_ipv4
+	ping_ipv6
+"
+
+config_devlink_reload()
+{
+	log_info "Devlink reload"
+	devlink_reload
+}
+
+config_enslave_h1()
+{
+	config_enslave $h1 lag1
+}
+
+config_enslave_h2()
+{
+	config_enslave $h2 lag4
+}
+
+config_enslave_h3()
+{
+	config_enslave $h3 lag4
+}
+
+config_enslave_h4()
+{
+	config_enslave $h4 lag1
+}
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+EXTRA_SOURCE="source $lib_dir/devlink_lib.sh"
+source $lib_dir/router_bridge_lag.sh
diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
index 5e89657857c7..45a569618424 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
@@ -16,7 +16,6 @@ ALL_TESTS="
 	bridge_deletion_test
 	bridge_vlan_flags_test
 	vlan_1_test
-	lag_bridge_upper_test
 	duplicate_vlans_test
 	vlan_rif_refcount_test
 	subport_rif_refcount_test
@@ -187,10 +186,7 @@ bridge_vlan_flags_test()
 
 	# If we did not handle references correctly, then this should produce a
 	# trace
-	devlink dev reload "$DEVLINK_DEV"
-
-	# Allow netdevices to be re-created following the reload
-	sleep 20
+	devlink_reload
 
 	log_test "bridge vlan flags"
 }
@@ -211,33 +207,6 @@ vlan_1_test()
 	ip link del dev $swp1.1
 }
 
-lag_bridge_upper_test()
-{
-	# Test that ports cannot be enslaved to LAG devices that have uppers
-	# and that failure is handled gracefully. See commit b3529af6bb0d
-	# ("spectrum: Reference count VLAN entries") for more details
-	RET=0
-
-	ip link add name bond1 type bond mode 802.3ad
-
-	ip link add name br0 type bridge vlan_filtering 1
-	ip link set dev bond1 master br0
-
-	ip link set dev $swp1 down
-	ip link set dev $swp1 master bond1 &> /dev/null
-	check_fail $? "managed to enslave port to lag when should not"
-
-	# This might generate a trace, if we did not handle the failure
-	# correctly
-	ip -6 address add 2001:db8:1::1/64 dev $swp1
-	ip -6 address del 2001:db8:1::1/64 dev $swp1
-
-	log_test "lag with bridge upper"
-
-	ip link del dev br0
-	ip link del dev bond1
-}
-
 duplicate_vlans_test()
 {
 	# Test that on a given port a VLAN is only used once. Either as VLAN
@@ -510,9 +479,6 @@ vlan_interface_uppers_test()
 	ip link set dev $swp1 master br0
 
 	ip link add link br0 name br0.10 type vlan id 10
-	ip link add link br0.10 name macvlan0 \
-		type macvlan mode private &> /dev/null
-	check_fail $? "managed to create a macvlan when should not"
 
 	ip -6 address add 2001:db8:1::1/64 dev br0.10
 	ip link add link br0.10 name macvlan0 type macvlan mode private
@@ -954,12 +920,9 @@ devlink_reload_test()
 	# devlink reload can be performed without errors
 	RET=0
 
-	devlink dev reload "$DEVLINK_DEV"
-	check_err $? "devlink reload failed"
+	devlink_reload
 
 	log_test "devlink reload - last test"
-
-	sleep 20
 }
 
 trap cleanup EXIT
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh
index ceaa76b17a43..4aaceb6b2b60 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_ets.sh
@@ -5,7 +5,6 @@
 lib_dir=$(dirname $0)/../../../net/forwarding
 source $lib_dir/sch_ets_core.sh
 source $lib_dir/devlink_lib.sh
-source qos_lib.sh
 
 ALL_TESTS="
 	ping_ipv4
@@ -22,6 +21,7 @@ switch_create()
 	# Create a bottleneck so that the DWRR process can kick in.
 	tc qdisc replace dev $swp2 root handle 3: tbf rate 1gbit \
 		burst 128K limit 1G
+	defer tc qdisc del dev $swp2 root handle 3:
 
 	ets_switch_create
 
@@ -31,16 +31,27 @@ switch_create()
 	# for the DWRR process.
 	devlink_port_pool_th_save $swp1 0
 	devlink_port_pool_th_set $swp1 0 12
+	defer devlink_port_pool_th_restore $swp1 0
+
 	devlink_tc_bind_pool_th_save $swp1 0 ingress
 	devlink_tc_bind_pool_th_set $swp1 0 ingress 0 12
+	defer devlink_tc_bind_pool_th_restore $swp1 0 ingress
+
 	devlink_port_pool_th_save $swp2 4
 	devlink_port_pool_th_set $swp2 4 12
+	defer devlink_port_pool_th_restore $swp2 4
+
 	devlink_tc_bind_pool_th_save $swp2 7 egress
 	devlink_tc_bind_pool_th_set $swp2 7 egress 4 5
+	defer devlink_tc_bind_pool_th_restore $swp2 7 egress
+
 	devlink_tc_bind_pool_th_save $swp2 6 egress
 	devlink_tc_bind_pool_th_set $swp2 6 egress 4 5
+	defer devlink_tc_bind_pool_th_restore $swp2 6 egress
+
 	devlink_tc_bind_pool_th_save $swp2 5 egress
 	devlink_tc_bind_pool_th_set $swp2 5 egress 4 5
+	defer devlink_tc_bind_pool_th_restore $swp2 5 egress
 
 	# Note: sch_ets_core.sh uses VLAN ingress-qos-map to assign packet
 	# priorities at $swp1 based on their 802.1p headers. ingress-qos-map is
@@ -48,20 +59,6 @@ switch_create()
 	# 1:1, which is the mapping currently hard-coded by the driver.
 }
 
-switch_destroy()
-{
-	devlink_tc_bind_pool_th_restore $swp2 5 egress
-	devlink_tc_bind_pool_th_restore $swp2 6 egress
-	devlink_tc_bind_pool_th_restore $swp2 7 egress
-	devlink_port_pool_th_restore $swp2 4
-	devlink_tc_bind_pool_th_restore $swp1 0 ingress
-	devlink_port_pool_th_restore $swp1 0
-
-	ets_switch_destroy
-
-	tc qdisc del dev $swp2 root handle 3:
-}
-
 # Callback from sch_ets_tests.sh
 collect_stats()
 {
@@ -78,5 +75,5 @@ collect_stats()
 	done
 }
 
-bail_on_lldpad
+bail_on_lldpad "configure DCB" "configure Qdiscs"
 ets_run
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
index 45b41b8f3232..47d2ffcf366e 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
@@ -74,7 +74,18 @@ lib_dir=$(dirname $0)/../../../net/forwarding
 source $lib_dir/lib.sh
 source $lib_dir/devlink_lib.sh
 source mlxsw_lib.sh
-source qos_lib.sh
+
+stop_traffic_sleep()
+{
+	local pid=$1; shift
+
+	# Issuing a kill still leaves a bunch of packets lingering in the
+	# buffers. This traffic then arrives at the point where a follow-up test
+	# is already running, and can confuse the test. Therefore sleep after
+	# stopping traffic to flush any leftover packets.
+	stop_traffic "$pid"
+	sleep 1
+}
 
 ipaddr()
 {
@@ -89,40 +100,31 @@ host_create()
 	local dev=$1; shift
 	local host=$1; shift
 
-	simple_if_init $dev
+	adf_simple_if_init $dev
+
 	mtu_set $dev 10000
+	defer mtu_restore $dev
 
 	vlan_create $dev 10 v$dev $(ipaddr $host 10)/28
+	defer vlan_destroy $dev 10
 	ip link set dev $dev.10 type vlan egress 0:0
 
 	vlan_create $dev 11 v$dev $(ipaddr $host 11)/28
+	defer vlan_destroy $dev 11
 	ip link set dev $dev.11 type vlan egress 0:1
 }
 
-host_destroy()
-{
-	local dev=$1; shift
-
-	vlan_destroy $dev 11
-	vlan_destroy $dev 10
-	mtu_restore $dev
-	simple_if_fini $dev
-}
-
 h1_create()
 {
 	host_create $h1 1
 }
 
-h1_destroy()
-{
-	host_destroy $h1
-}
-
 h2_create()
 {
 	host_create $h2 2
+
 	tc qdisc add dev $h2 clsact
+	defer tc qdisc del dev $h2 clsact
 
 	# Some of the tests in this suite use multicast traffic. As this traffic
 	# enters BR2_10 resp. BR2_11, it is flooded to all other ports. Thus
@@ -138,15 +140,9 @@ h2_create()
 	# Prevent this by adding a shaper which limits the traffic in $h2 to
 	# 1Gbps.
 
-	tc qdisc replace dev $h2 root handle 10: tbf rate 1gbit \
+	tc qdisc replace dev $h2 root handle 10: tbf rate 200mbit \
 		burst 128K limit 1G
-}
-
-h2_destroy()
-{
-	tc qdisc del dev $h2 root handle 10:
-	tc qdisc del dev $h2 clsact
-	host_destroy $h2
+	defer tc qdisc del dev $h2 root handle 10:
 }
 
 h3_create()
@@ -154,40 +150,54 @@ h3_create()
 	host_create $h3 3
 }
 
-h3_destroy()
-{
-	host_destroy $h3
-}
-
 switch_create()
 {
 	local intf
 	local vlan
 
 	ip link add dev br1_10 type bridge
+	defer ip link del dev br1_10
+
 	ip link add dev br1_11 type bridge
+	defer ip link del dev br1_11
 
 	ip link add dev br2_10 type bridge
+	defer ip link del dev br2_10
+
 	ip link add dev br2_11 type bridge
+	defer ip link del dev br2_11
 
 	for intf in $swp1 $swp2 $swp3 $swp4 $swp5; do
 		ip link set dev $intf up
+		defer ip link set dev $intf down
+
 		mtu_set $intf 10000
+		defer mtu_restore $intf
 	done
 
 	for intf in $swp1 $swp4; do
 		for vlan in 10 11; do
 			vlan_create $intf $vlan
+			defer vlan_destroy $intf $vlan
+
 			ip link set dev $intf.$vlan master br1_$vlan
+			defer ip link set dev $intf.$vlan nomaster
+
 			ip link set dev $intf.$vlan up
+			defer ip link set dev $intf.$vlan up
 		done
 	done
 
 	for intf in $swp2 $swp3 $swp5; do
 		for vlan in 10 11; do
 			vlan_create $intf $vlan
+			defer vlan_destroy $intf $vlan
+
 			ip link set dev $intf.$vlan master br2_$vlan
+			defer ip link set dev $intf.$vlan nomaster
+
 			ip link set dev $intf.$vlan up
+			defer ip link set dev $intf.$vlan up
 		done
 	done
 
@@ -200,51 +210,27 @@ switch_create()
 	done
 
 	for intf in $swp3 $swp4; do
-		tc qdisc replace dev $intf root handle 1: tbf rate 1gbit \
+		tc qdisc replace dev $intf root handle 1: tbf rate 200mbit \
 			burst 128K limit 1G
+		defer tc qdisc del dev $intf root handle 1:
 	done
 
 	ip link set dev br1_10 up
+	defer ip link set dev br1_10 down
+
 	ip link set dev br1_11 up
+	defer ip link set dev br1_11 down
+
 	ip link set dev br2_10 up
+	defer ip link set dev br2_10 down
+
 	ip link set dev br2_11 up
+	defer ip link set dev br2_11 down
 
 	local size=$(devlink_pool_size_thtype 0 | cut -d' ' -f 1)
 	devlink_port_pool_th_save $swp3 8
 	devlink_port_pool_th_set $swp3 8 $size
-}
-
-switch_destroy()
-{
-	local intf
-	local vlan
-
-	devlink_port_pool_th_restore $swp3 8
-
-	ip link set dev br2_11 down
-	ip link set dev br2_10 down
-	ip link set dev br1_11 down
-	ip link set dev br1_10 down
-
-	for intf in $swp4 $swp3; do
-		tc qdisc del dev $intf root handle 1:
-	done
-
-	for intf in $swp5 $swp3 $swp2 $swp4 $swp1; do
-		for vlan in 11 10; do
-			ip link set dev $intf.$vlan down
-			ip link set dev $intf.$vlan nomaster
-			vlan_destroy $intf $vlan
-		done
-
-		mtu_restore $intf
-		ip link set dev $intf down
-	done
-
-	ip link del dev br2_11
-	ip link del dev br2_10
-	ip link del dev br1_11
-	ip link del dev br1_10
+	defer devlink_port_pool_th_restore $swp3 8
 }
 
 setup_prepare()
@@ -263,7 +249,7 @@ setup_prepare()
 
 	h3_mac=$(mac_get $h3)
 
-	vrf_prepare
+	adf_vrf_prepare
 
 	h1_create
 	h2_create
@@ -271,18 +257,6 @@ setup_prepare()
 	switch_create
 }
 
-cleanup()
-{
-	pre_cleanup
-
-	switch_destroy
-	h3_destroy
-	h2_destroy
-	h1_destroy
-
-	vrf_cleanup
-}
-
 ping_ipv4()
 {
 	ping_test $h1.10 $(ipaddr 3 10) " from host 1, vlan 10"
@@ -373,6 +347,7 @@ build_backlog()
 	local i=0
 
 	while :; do
+		sleep 1
 		local cur=$(busywait 1100 until_counter_is "> $cur" \
 					    get_qdisc_backlog $vlan)
 		local diff=$((size - cur))
@@ -450,6 +425,7 @@ __do_ecn_test()
 
 	start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \
 			  $h3_mac tos=0x01
+	defer stop_traffic_sleep $!
 	sleep 1
 
 	ecn_test_common "$name" "$get_nmarked" $vlan $limit
@@ -461,9 +437,6 @@ __do_ecn_test()
 	build_backlog $vlan $((2 * limit)) udp >/dev/null
 	check_fail $? "UDP traffic went into backlog instead of being early-dropped"
 	log_test "TC $((vlan - 10)): $name backlog > limit: UDP early-dropped"
-
-	stop_traffic
-	sleep 1
 }
 
 do_ecn_test()
@@ -471,7 +444,8 @@ do_ecn_test()
 	local vlan=$1; shift
 	local limit=$1; shift
 
-	__do_ecn_test get_nmarked "$vlan" "$limit"
+	in_defer_scope \
+		__do_ecn_test get_nmarked "$vlan" "$limit"
 }
 
 do_ecn_test_perband()
@@ -480,10 +454,11 @@ do_ecn_test_perband()
 	local limit=$1; shift
 
 	mlxsw_only_on_spectrum 3+ || return
-	__do_ecn_test get_qdisc_nmarked "$vlan" "$limit" "per-band ECN"
+	in_defer_scope \
+		__do_ecn_test get_qdisc_nmarked "$vlan" "$limit" "per-band ECN"
 }
 
-do_ecn_nodrop_test()
+__do_ecn_nodrop_test()
 {
 	local vlan=$1; shift
 	local limit=$1; shift
@@ -491,6 +466,7 @@ do_ecn_nodrop_test()
 
 	start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \
 			  $h3_mac tos=0x01
+	defer stop_traffic_sleep $!
 	sleep 1
 
 	ecn_test_common "$name" get_nmarked $vlan $limit
@@ -502,12 +478,15 @@ do_ecn_nodrop_test()
 	build_backlog $vlan $((2 * limit)) udp >/dev/null
 	check_err $? "UDP traffic was early-dropped instead of getting into backlog"
 	log_test "TC $((vlan - 10)): $name backlog > limit: UDP not dropped"
+}
 
-	stop_traffic
-	sleep 1
+do_ecn_nodrop_test()
+{
+	in_defer_scope \
+		__do_ecn_nodrop_test "$@"
 }
 
-do_red_test()
+__do_red_test()
 {
 	local vlan=$1; shift
 	local limit=$1; shift
@@ -518,6 +497,7 @@ do_red_test()
 	# is above limit.
 	start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \
 			  $h3_mac tos=0x01
+	defer stop_traffic_sleep $!
 
 	# Pushing below the queue limit should work.
 	RET=0
@@ -533,17 +513,21 @@ do_red_test()
 	check_fail $? "Traffic went into backlog instead of being early-dropped"
 	pct=$(check_marking get_nmarked $vlan "== 0")
 	check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0."
+	backlog=$(get_qdisc_backlog $vlan)
 	local diff=$((limit - backlog))
 	pct=$((100 * diff / limit))
-	((-10 <= pct && pct <= 10))
-	check_err $? "backlog $backlog / $limit expected <= 10% distance"
+	((-15 <= pct && pct <= 15))
+	check_err $? "backlog $backlog / $limit expected <= 15% distance"
 	log_test "TC $((vlan - 10)): RED backlog > limit"
+}
 
-	stop_traffic
-	sleep 1
+do_red_test()
+{
+	in_defer_scope \
+		__do_red_test "$@"
 }
 
-do_mc_backlog_test()
+__do_mc_backlog_test()
 {
 	local vlan=$1; shift
 	local limit=$1; shift
@@ -553,7 +537,10 @@ do_mc_backlog_test()
 	RET=0
 
 	start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) bc
+	defer stop_traffic_sleep $!
+
 	start_tcp_traffic $h2.$vlan $(ipaddr 2 $vlan) $(ipaddr 3 $vlan) bc
+	defer stop_traffic_sleep $!
 
 	qbl=$(busywait 5000 until_counter_is ">= 500000" \
 		       get_qdisc_backlog $vlan)
@@ -566,13 +553,16 @@ do_mc_backlog_test()
 		       get_mc_transmit_queue $vlan)
 	check_err $? "MC backlog reported by qdisc not visible in ethtool"
 
-	stop_traffic
-	stop_traffic
-
 	log_test "TC $((vlan - 10)): Qdisc reports MC backlog"
 }
 
-do_mark_test()
+do_mc_backlog_test()
+{
+	in_defer_scope \
+		__do_mc_backlog_test "$@"
+}
+
+__do_mark_test()
 {
 	local vlan=$1; shift
 	local limit=$1; shift
@@ -587,6 +577,7 @@ do_mark_test()
 
 	start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \
 			  $h3_mac tos=0x01
+	defer stop_traffic_sleep $!
 
 	# Create a bit of a backlog and observe no mirroring due to marks.
 	qevent_rule_install_$subtest
@@ -601,7 +592,7 @@ do_mark_test()
 	# Above limit, everything should be mirrored, we should see lots of
 	# packets.
 	build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01 >/dev/null
-	busywait_for_counter 1100 +10000 \
+	busywait_for_counter 1100 +2500 \
 		 $fetch_counter > /dev/null
 	check_err_fail "$should_fail" $? "ECN-marked packets $subtest'd"
 
@@ -616,12 +607,15 @@ do_mark_test()
 	else
 		log_test "TC $((vlan - 10)): marked packets $subtest'd"
 	fi
+}
 
-	stop_traffic
-	sleep 1
+do_mark_test()
+{
+	in_defer_scope \
+		__do_mark_test "$@"
 }
 
-do_drop_test()
+__do_drop_test()
 {
 	local vlan=$1; shift
 	local limit=$1; shift
@@ -636,6 +630,7 @@ do_drop_test()
 	RET=0
 
 	start_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) $h3_mac
+	defer stop_traffic_sleep $!
 
 	# Create a bit of a backlog and observe no mirroring due to drops.
 	qevent_rule_install_$subtest
@@ -652,25 +647,30 @@ do_drop_test()
 	build_backlog $vlan $((3 * limit / 2)) udp >/dev/null
 
 	base=$($fetch_counter)
-	send_packets $vlan udp 11
+	send_packets $vlan udp 100
 
-	now=$(busywait 1100 until_counter_is ">= $((base + 10))" $fetch_counter)
-	check_err $? "Dropped packets not observed: 11 expected, $((now - base)) seen"
+	now=$(busywait 1100 until_counter_is ">= $((base + 95))" $fetch_counter)
+	check_err $? "${trigger}ped packets not observed: 100 expected, $((now - base)) seen"
 
 	# When no extra traffic is injected, there should be no mirroring.
-	busywait 1100 until_counter_is ">= $((base + 20))" $fetch_counter >/dev/null
+	busywait 1100 until_counter_is ">= $((base + 110))" \
+		 $fetch_counter >/dev/null
 	check_fail $? "Spurious packets observed"
 
 	# When the rule is uninstalled, there should be no mirroring.
 	qevent_rule_uninstall_$subtest
-	send_packets $vlan udp 11
-	busywait 1100 until_counter_is ">= $((base + 20))" $fetch_counter >/dev/null
-	check_fail $? "Spurious packets observed after uninstall"
+	send_packets $vlan udp 100
+	now=$(busywait 1100 until_counter_is ">= $((base + 110))" \
+		       $fetch_counter)
+	check_fail $? "$((now - base)) spurious packets observed after uninstall"
 
 	log_test "TC $((vlan - 10)): ${trigger}ped packets $subtest'd"
+}
 
-	stop_traffic
-	sleep 1
+do_drop_test()
+{
+	in_defer_scope \
+		__do_drop_test "$@"
 }
 
 qevent_rule_install_mirror()
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
index 0d01c7cd82a1..8902a115d9cd 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
@@ -20,8 +20,8 @@ source sch_red_core.sh
 # $BACKLOG2 are far enough not to overlap, so that we can assume that if we do
 # see (do not see) marking, it is actually due to the configuration of that one
 # TC, and not due to configuration of the other TC leaking over.
-BACKLOG1=200000
-BACKLOG2=500000
+BACKLOG1=400000
+BACKLOG2=1000000
 
 install_root_qdisc()
 {
@@ -35,7 +35,7 @@ install_qdisc_tc0()
 
 	tc qdisc add dev $swp3 parent 10:8 handle 108: red \
 	   limit 1000000 min $BACKLOG1 max $((BACKLOG1 + 1)) \
-	   probability 1.0 avpkt 8000 burst 38 "${args[@]}"
+	   probability 1.0 avpkt 8000 burst 51 "${args[@]}"
 }
 
 install_qdisc_tc1()
@@ -44,7 +44,7 @@ install_qdisc_tc1()
 
 	tc qdisc add dev $swp3 parent 10:7 handle 107: red \
 	   limit 1000000 min $BACKLOG2 max $((BACKLOG2 + 1)) \
-	   probability 1.0 avpkt 8000 burst 63 "${args[@]}"
+	   probability 1.0 avpkt 8000 burst 126 "${args[@]}"
 }
 
 install_qdisc()
@@ -80,36 +80,34 @@ uninstall_qdisc()
 ecn_test()
 {
 	install_qdisc ecn
+	defer uninstall_qdisc
 
 	do_ecn_test 10 $BACKLOG1
 	do_ecn_test 11 $BACKLOG2
-
-	uninstall_qdisc
 }
 
 ecn_test_perband()
 {
 	install_qdisc ecn
+	defer uninstall_qdisc
 
 	do_ecn_test_perband 10 $BACKLOG1
 	do_ecn_test_perband 11 $BACKLOG2
-
-	uninstall_qdisc
 }
 
 ecn_nodrop_test()
 {
 	install_qdisc ecn nodrop
+	defer uninstall_qdisc
 
 	do_ecn_nodrop_test 10 $BACKLOG1
 	do_ecn_nodrop_test 11 $BACKLOG2
-
-	uninstall_qdisc
 }
 
 red_test()
 {
 	install_qdisc
+	defer uninstall_qdisc
 
 	# Make sure that we get the non-zero value if there is any.
 	local cur=$(busywait 1100 until_counter_is "> 0" \
@@ -120,53 +118,47 @@ red_test()
 
 	do_red_test 10 $BACKLOG1
 	do_red_test 11 $BACKLOG2
-
-	uninstall_qdisc
 }
 
 mc_backlog_test()
 {
 	install_qdisc
+	defer uninstall_qdisc
 
 	# Note that the backlog numbers here do not correspond to RED
 	# configuration, but are arbitrary.
 	do_mc_backlog_test 10 $BACKLOG1
 	do_mc_backlog_test 11 $BACKLOG2
-
-	uninstall_qdisc
 }
 
 red_mirror_test()
 {
 	install_qdisc qevent early_drop block 10
+	defer uninstall_qdisc
 
 	do_drop_mirror_test 10 $BACKLOG1 early_drop
 	do_drop_mirror_test 11 $BACKLOG2 early_drop
-
-	uninstall_qdisc
 }
 
 red_trap_test()
 {
 	install_qdisc qevent early_drop block 10
+	defer uninstall_qdisc
 
 	do_drop_trap_test 10 $BACKLOG1 early_drop
 	do_drop_trap_test 11 $BACKLOG2 early_drop
-
-	uninstall_qdisc
 }
 
 ecn_mirror_test()
 {
 	install_qdisc ecn qevent mark block 10
+	defer uninstall_qdisc
 
 	do_mark_mirror_test 10 $BACKLOG1
 	do_mark_mirror_test 11 $BACKLOG2
-
-	uninstall_qdisc
 }
 
-bail_on_lldpad
+bail_on_lldpad "configure DCB" "configure Qdiscs"
 
 trap cleanup EXIT
 setup_prepare
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh
index 860205338e6f..e9043771787b 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh
@@ -32,48 +32,54 @@ uninstall_qdisc()
 ecn_test()
 {
 	install_qdisc ecn
+	defer uninstall_qdisc
+
 	do_ecn_test 10 $BACKLOG
-	uninstall_qdisc
 }
 
 ecn_test_perband()
 {
 	install_qdisc ecn
+	defer uninstall_qdisc
+
 	do_ecn_test_perband 10 $BACKLOG
-	uninstall_qdisc
 }
 
 ecn_nodrop_test()
 {
 	install_qdisc ecn nodrop
+	defer uninstall_qdisc
+
 	do_ecn_nodrop_test 10 $BACKLOG
-	uninstall_qdisc
 }
 
 red_test()
 {
 	install_qdisc
+	defer uninstall_qdisc
+
 	do_red_test 10 $BACKLOG
-	uninstall_qdisc
 }
 
 mc_backlog_test()
 {
 	install_qdisc
+	defer uninstall_qdisc
+
 	# Note that the backlog value here does not correspond to RED
 	# configuration, but is arbitrary.
 	do_mc_backlog_test 10 $BACKLOG
-	uninstall_qdisc
 }
 
 red_mirror_test()
 {
 	install_qdisc qevent early_drop block 10
+	defer uninstall_qdisc
+
 	do_drop_mirror_test 10 $BACKLOG
-	uninstall_qdisc
 }
 
-bail_on_lldpad
+bail_on_lldpad "configure DCB" "configure Qdiscs"
 
 trap cleanup EXIT
 setup_prepare
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_ets.sh
index c6ce0b448bf3..ecc3664376b3 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_ets.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_ets.sh
@@ -1,8 +1,10 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-source qos_lib.sh
-bail_on_lldpad
+sch_tbf_pre_hook()
+{
+	bail_on_lldpad "configure DCB" "configure Qdiscs"
+}
 
 lib_dir=$(dirname $0)/../../../net/forwarding
 TCFLAGS=skip_sw
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_prio.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_prio.sh
index 8d245f331619..2e0a4efb1703 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_prio.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_prio.sh
@@ -1,8 +1,10 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-source qos_lib.sh
-bail_on_lldpad
+sch_tbf_pre_hook()
+{
+	bail_on_lldpad "configure DCB" "configure Qdiscs"
+}
 
 lib_dir=$(dirname $0)/../../../net/forwarding
 TCFLAGS=skip_sw
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_root.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_root.sh
index 013886061f15..6679a338dfc4 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_root.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_tbf_root.sh
@@ -1,8 +1,10 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-source qos_lib.sh
-bail_on_lldpad
+sch_tbf_pre_hook()
+{
+	bail_on_lldpad "configure DCB" "configure Qdiscs"
+}
 
 lib_dir=$(dirname $0)/../../../net/forwarding
 TCFLAGS=skip_sw
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh
index 7d9e73a43a49..c068e6c2a580 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sharedbuffer.sh
@@ -22,20 +22,34 @@ SB_ITC=0
 h1_create()
 {
 	simple_if_init $h1 192.0.1.1/24
+	tc qdisc add dev $h1 clsact
+
+	# Add egress filter on $h1 that will guarantee that the packet sent,
+	# will be the only packet being passed to the device.
+	tc filter add dev $h1 egress pref 2 handle 102 matchall action drop
 }
 
 h1_destroy()
 {
+	tc filter del dev $h1 egress pref 2 handle 102 matchall action drop
+	tc qdisc del dev $h1 clsact
 	simple_if_fini $h1 192.0.1.1/24
 }
 
 h2_create()
 {
 	simple_if_init $h2 192.0.1.2/24
+	tc qdisc add dev $h2 clsact
+
+	# Add egress filter on $h2 that will guarantee that the packet sent,
+	# will be the only packet being passed to the device.
+	tc filter add dev $h2 egress pref 1 handle 101 matchall action drop
 }
 
 h2_destroy()
 {
+	tc filter del dev $h2 egress pref 1 handle 101 matchall action drop
+	tc qdisc del dev $h2 clsact
 	simple_if_fini $h2 192.0.1.2/24
 }
 
@@ -98,22 +112,22 @@ sb_occ_etc_check()
 
 port_pool_test()
 {
-	local exp_max_occ=288
+	local exp_max_occ=$(devlink_cell_size_get)
 	local max_occ
 
+	tc filter add dev $h1 egress protocol ip pref 1 handle 101 flower \
+		src_mac $h1mac dst_mac $h2mac \
+		src_ip 192.0.1.1 dst_ip 192.0.1.2 \
+		action pass
+
 	devlink sb occupancy clearmax $DEVLINK_DEV
 
-	$MZ $h1 -c 1 -p 160 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \
+	$MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \
 		-t ip -q
 
 	devlink sb occupancy snapshot $DEVLINK_DEV
 
 	RET=0
-	max_occ=$(sb_occ_pool_check $dl_port1 $SB_POOL_ING $exp_max_occ)
-	check_err $? "Expected iPool($SB_POOL_ING) max occupancy to be $exp_max_occ, but got $max_occ"
-	log_test "physical port's($h1) ingress pool"
-
-	RET=0
 	max_occ=$(sb_occ_pool_check $dl_port2 $SB_POOL_ING $exp_max_occ)
 	check_err $? "Expected iPool($SB_POOL_ING) max occupancy to be $exp_max_occ, but got $max_occ"
 	log_test "physical port's($h2) ingress pool"
@@ -122,16 +136,26 @@ port_pool_test()
 	max_occ=$(sb_occ_pool_check $cpu_dl_port $SB_POOL_EGR_CPU $exp_max_occ)
 	check_err $? "Expected ePool($SB_POOL_EGR_CPU) max occupancy to be $exp_max_occ, but got $max_occ"
 	log_test "CPU port's egress pool"
+
+	tc filter del dev $h1 egress protocol ip pref 1 handle 101 flower \
+		src_mac $h1mac dst_mac $h2mac \
+		src_ip 192.0.1.1 dst_ip 192.0.1.2 \
+		action pass
 }
 
 port_tc_ip_test()
 {
-	local exp_max_occ=288
+	local exp_max_occ=$(devlink_cell_size_get)
 	local max_occ
 
+	tc filter add dev $h1 egress protocol ip pref 1 handle 101 flower \
+		src_mac $h1mac dst_mac $h2mac \
+		src_ip 192.0.1.1 dst_ip 192.0.1.2 \
+		action pass
+
 	devlink sb occupancy clearmax $DEVLINK_DEV
 
-	$MZ $h1 -c 1 -p 160 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \
+	$MZ $h1 -c 1 -p 10 -a $h1mac -b $h2mac -A 192.0.1.1 -B 192.0.1.2 \
 		-t ip -q
 
 	devlink sb occupancy snapshot $DEVLINK_DEV
@@ -139,48 +163,45 @@ port_tc_ip_test()
 	RET=0
 	max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ)
 	check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ"
-	log_test "physical port's($h1) ingress TC - IP packet"
-
-	RET=0
-	max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ)
-	check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ"
 	log_test "physical port's($h2) ingress TC - IP packet"
 
 	RET=0
 	max_occ=$(sb_occ_etc_check $cpu_dl_port $SB_ITC_CPU_IP $exp_max_occ)
 	check_err $? "Expected egress TC($SB_ITC_CPU_IP) max occupancy to be $exp_max_occ, but got $max_occ"
 	log_test "CPU port's egress TC - IP packet"
+
+	tc filter del dev $h1 egress protocol ip pref 1 handle 101 flower \
+		src_mac $h1mac dst_mac $h2mac \
+		src_ip 192.0.1.1 dst_ip 192.0.1.2 \
+		action pass
 }
 
 port_tc_arp_test()
 {
-	local exp_max_occ=96
+	local exp_max_occ=$(devlink_cell_size_get)
 	local max_occ
 
-	if [[ $MLXSW_CHIP != "mlxsw_spectrum" ]]; then
-		exp_max_occ=144
-	fi
+	tc filter add dev $h1 egress protocol arp pref 1 handle 101 flower \
+		src_mac $h1mac action pass
 
 	devlink sb occupancy clearmax $DEVLINK_DEV
 
-	$MZ $h1 -c 1 -p 160 -a $h1mac -A 192.0.1.1 -t arp -q
+	$MZ $h1 -c 1 -p 10 -a $h1mac -A 192.0.1.1 -t arp -q
 
 	devlink sb occupancy snapshot $DEVLINK_DEV
 
 	RET=0
 	max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ)
 	check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ"
-	log_test "physical port's($h1) ingress TC - ARP packet"
-
-	RET=0
-	max_occ=$(sb_occ_itc_check $dl_port2 $SB_ITC $exp_max_occ)
-	check_err $? "Expected ingress TC($SB_ITC) max occupancy to be $exp_max_occ, but got $max_occ"
 	log_test "physical port's($h2) ingress TC - ARP packet"
 
 	RET=0
 	max_occ=$(sb_occ_etc_check $cpu_dl_port $SB_ITC_CPU_ARP $exp_max_occ)
 	check_err $? "Expected egress TC($SB_ITC_IP2ME) max occupancy to be $exp_max_occ, but got $max_occ"
 	log_test "CPU port's egress TC - ARP packet"
+
+	tc filter del dev $h1 egress protocol arp pref 1 handle 101 flower \
+		src_mac $h1mac action pass
 }
 
 setup_prepare()
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/port_range_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/port_range_scale.sh
new file mode 120000
index 000000000000..bd670d9dc4e5
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/port_range_scale.sh
@@ -0,0 +1 @@
+../spectrum/port_range_scale.sh
+\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
index 688338bbeb97..d7505b933aef 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
@@ -33,6 +33,7 @@ ALL_TESTS="
 	port
 	rif_mac_profile
 	rif_counter
+	port_range
 "
 
 for current_test in ${TESTS:-$ALL_TESTS}; do
@@ -46,12 +47,11 @@ for current_test in ${TESTS:-$ALL_TESTS}; do
 		RET=0
 		target=$(${current_test}_get_target "$should_fail")
 		if ((target == 0)); then
-			log_test_skip "'$current_test' should_fail=$should_fail test"
 			continue
 		fi
 
 		${current_test}_setup_prepare
-		setup_wait $num_netifs
+		setup_wait_n $num_netifs
 		# Update target in case occupancy of a certain resource changed
 		# following the test setup.
 		target=$(${current_test}_get_target "$should_fail")
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
index fb850e0ec837..4994bea5daf8 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
@@ -10,7 +10,8 @@ lib_dir=$(dirname $0)/../../../../net/forwarding
 ALL_TESTS="single_mask_test identical_filters_test two_masks_test \
 	multiple_masks_test ctcam_edge_cases_test delta_simple_test \
 	delta_two_masks_one_key_test delta_simple_rehash_test \
-	bloom_simple_test bloom_complex_test bloom_delta_test"
+	bloom_simple_test bloom_complex_test bloom_delta_test \
+	max_erp_entries_test max_group_size_test collision_test"
 NUM_NETIFS=2
 source $lib_dir/lib.sh
 source $lib_dir/tc_common.sh
@@ -456,7 +457,7 @@ delta_two_masks_one_key_test()
 {
 	# If 2 keys are the same and only differ in mask in a way that
 	# they belong under the same ERP (second is delta of the first),
-	# there should be no C-TCAM spill.
+	# there should be C-TCAM spill.
 
 	RET=0
 
@@ -473,8 +474,8 @@ delta_two_masks_one_key_test()
 	tp_record "mlxsw:*" "tc filter add dev $h2 ingress protocol ip \
 		   pref 2 handle 102 flower $tcflags dst_ip 192.0.2.2 \
 		   action drop"
-	tp_check_hits "mlxsw:mlxsw_sp_acl_atcam_entry_add_ctcam_spill" 0
-	check_err $? "incorrect C-TCAM spill while inserting the second rule"
+	tp_check_hits "mlxsw:mlxsw_sp_acl_atcam_entry_add_ctcam_spill" 1
+	check_err $? "C-TCAM spill did not happen while inserting the second rule"
 
 	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
 		-t ip -q
@@ -868,7 +869,7 @@ bloom_simple_test()
 bloom_complex_test()
 {
 	# Bloom filter index computation is affected from region ID, eRP
-	# ID and from the region key size. In order to excercise those parts
+	# ID and from the region key size. In order to exercise those parts
 	# of the Bloom filter code, use a series of regions, each with a
 	# different key size and send packet that should hit all of them.
 	local index
@@ -983,6 +984,156 @@ bloom_delta_test()
 	log_test "bloom delta test ($tcflags)"
 }
 
+max_erp_entries_test()
+{
+	# The number of eRP entries is limited. Once the maximum number of eRPs
+	# has been reached, filters cannot be added. This test verifies that
+	# when this limit is reached, inserstion fails without crashing.
+
+	RET=0
+
+	local num_masks=32
+	local num_regions=15
+	local chain_failed
+	local mask_failed
+	local ret
+
+	if [[ "$tcflags" != "skip_sw" ]]; then
+		return 0;
+	fi
+
+	for ((i=1; i < $num_regions; i++)); do
+		for ((j=$num_masks; j >= 0; j--)); do
+			tc filter add dev $h2 ingress chain $i protocol ip \
+				pref $i	handle $j flower $tcflags \
+				dst_ip 192.1.0.0/$j &> /dev/null
+			ret=$?
+
+			if [ $ret -ne 0 ]; then
+				chain_failed=$i
+				mask_failed=$j
+				break 2
+			fi
+		done
+	done
+
+	# We expect to exceed the maximum number of eRP entries, so that
+	# insertion eventually fails. Otherwise, the test should be adjusted to
+	# add more filters.
+	check_fail $ret "expected to exceed number of eRP entries"
+
+	for ((; i >= 1; i--)); do
+		for ((j=0; j <= $num_masks; j++)); do
+			tc filter del dev $h2 ingress chain $i protocol ip \
+				pref $i handle $j flower &> /dev/null
+		done
+	done
+
+	log_test "max eRP entries test ($tcflags). " \
+		"max chain $chain_failed, mask $mask_failed"
+}
+
+max_group_size_test()
+{
+	# The number of ACLs in an ACL group is limited. Once the maximum
+	# number of ACLs has been reached, filters cannot be added. This test
+	# verifies that when this limit is reached, insertion fails without
+	# crashing.
+
+	RET=0
+
+	local num_acls=32
+	local max_size
+	local ret
+
+	if [[ "$tcflags" != "skip_sw" ]]; then
+		return 0;
+	fi
+
+	for ((i=1; i < $num_acls; i++)); do
+		if [[ $(( i % 2 )) == 1 ]]; then
+			tc filter add dev $h2 ingress pref $i proto ipv4 \
+				flower $tcflags dst_ip 198.51.100.1/32 \
+				ip_proto tcp tcp_flags 0x01/0x01 \
+				action drop &> /dev/null
+		else
+			tc filter add dev $h2 ingress pref $i proto ipv6 \
+				flower $tcflags dst_ip 2001:db8:1::1/128 \
+				action drop &> /dev/null
+		fi
+
+		ret=$?
+		[[ $ret -ne 0 ]] && max_size=$((i - 1)) && break
+	done
+
+	# We expect to exceed the maximum number of ACLs in a group, so that
+	# insertion eventually fails. Otherwise, the test should be adjusted to
+	# add more filters.
+	check_fail $ret "expected to exceed number of ACLs in a group"
+
+	for ((; i >= 1; i--)); do
+		if [[ $(( i % 2 )) == 1 ]]; then
+			tc filter del dev $h2 ingress pref $i proto ipv4 \
+				flower $tcflags dst_ip 198.51.100.1/32 \
+				ip_proto tcp tcp_flags 0x01/0x01 \
+				action drop &> /dev/null
+		else
+			tc filter del dev $h2 ingress pref $i proto ipv6 \
+				flower $tcflags dst_ip 2001:db8:1::1/128 \
+				action drop &> /dev/null
+		fi
+	done
+
+	log_test "max ACL group size test ($tcflags). max size $max_size"
+}
+
+collision_test()
+{
+	# Filters cannot share an eRP if in the common unmasked part (i.e.,
+	# without the delta bits) they have the same values. If the driver does
+	# not prevent such configuration (by spilling into the C-TCAM), then
+	# multiple entries will be present in the device with the same key,
+	# leading to collisions and a reduced scale.
+	#
+	# Create such a scenario and make sure all the filters are successfully
+	# added.
+
+	RET=0
+
+	local ret
+
+	if [[ "$tcflags" != "skip_sw" ]]; then
+		return 0;
+	fi
+
+	# Add a single dst_ip/24 filter and multiple dst_ip/32 filters that all
+	# have the same values in the common unmasked part (dst_ip/24).
+
+	tc filter add dev $h2 ingress pref 1 proto ipv4 handle 101 \
+		flower $tcflags dst_ip 198.51.100.0/24 \
+		action drop
+
+	for i in {0..255}; do
+		tc filter add dev $h2 ingress pref 2 proto ipv4 \
+			handle $((102 + i)) \
+			flower $tcflags dst_ip 198.51.100.${i}/32 \
+			action drop
+		ret=$?
+		[[ $ret -ne 0 ]] && break
+	done
+
+	check_err $ret "failed to add all the filters"
+
+	for i in {255..0}; do
+		tc filter del dev $h2 ingress pref 2 proto ipv4 \
+			handle $((102 + i)) flower
+	done
+
+	tc filter del dev $h2 ingress pref 1 proto ipv4 handle 101 flower
+
+	log_test "collision test ($tcflags)"
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/port_range_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/port_range_scale.sh
new file mode 100644
index 000000000000..d0847e8ea270
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/port_range_scale.sh
@@ -0,0 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0
+source ../port_range_scale.sh
+
+port_range_get_target()
+{
+	local should_fail=$1; shift
+	local target
+
+	target=$(devlink_resource_size_get port_range_registers)
+
+	if ((! should_fail)); then
+		echo $target
+	else
+		echo $((target + 1))
+	fi
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/q_in_vni_veto.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/q_in_vni_veto.sh
index f0443b1b05b9..60753d46a2d4 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/q_in_vni_veto.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/q_in_vni_veto.sh
@@ -34,6 +34,7 @@ create_vxlan_on_top_of_8021ad_bridge()
 
 	ip link add dev br0 type bridge vlan_filtering 1 vlan_protocol 802.1ad \
 		vlan_default_pvid 0 mcast_snooping 0
+	ip link set dev br0 addrgenmode none
 	ip link set dev br0 up
 
 	ip link add name vx100 type vxlan id 1000 local 192.0.2.17 dstport \
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
index 95d9f710a630..7b98cdd0580d 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
@@ -30,6 +30,7 @@ ALL_TESTS="
 	port
 	rif_mac_profile
 	rif_counter
+	port_range
 "
 
 for current_test in ${TESTS:-$ALL_TESTS}; do
@@ -51,11 +52,10 @@ for current_test in ${TESTS:-$ALL_TESTS}; do
 			RET=0
 			target=$(${current_test}_get_target "$should_fail")
 			if ((target == 0)); then
-				log_test_skip "'$current_test' [$profile] should_fail=$should_fail test"
 				continue
 			fi
 			${current_test}_setup_prepare
-			setup_wait $num_netifs
+			setup_wait_n $num_netifs
 			# Update target in case occupancy of a certain resource
 			# changed following the test setup.
 			target=$(${current_test}_get_target "$should_fail")
diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
index 83a0210e7544..bc7ea2df49fb 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
@@ -218,7 +218,7 @@ psample_capture_start()
 
 psample_capture_stop()
 {
-	{ kill %% && wait %%; } 2>/dev/null
+	kill_process %%
 }
 
 __tc_sample_rate_test()
@@ -499,7 +499,7 @@ tc_sample_md_out_tc_occ_test()
 	backlog=$(tc -j -p -s qdisc show dev $rp2 | jq '.[0]["backlog"]')
 
 	# Kill mausezahn.
-	{ kill %% && wait %%; } 2>/dev/null
+	kill_process %%
 
 	psample_capture_stop
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
index 99a332b712f0..4687b0a7dffb 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan.sh
@@ -444,8 +444,12 @@ offload_indication_setup_create()
 {
 	# Create a simple setup with two bridges, each with a VxLAN device
 	# and one local port
-	ip link add name br0 up type bridge mcast_snooping 0
-	ip link add name br1 up type bridge mcast_snooping 0
+	ip link add name br0 type bridge mcast_snooping 0
+	ip link set dev br0 addrgenmode none
+	ip link set dev br0 up
+	ip link add name br1 type bridge mcast_snooping 0
+	ip link set dev br1 addrgenmode none
+	ip link set dev br1 up
 
 	ip link set dev $swp1 master br0
 	ip link set dev $swp2 master br1
@@ -646,8 +650,12 @@ offload_indication_decap_route_test()
 
 	RET=0
 
-	ip link add name br0 up type bridge mcast_snooping 0
-	ip link add name br1 up type bridge mcast_snooping 0
+	ip link add name br0 type bridge mcast_snooping 0
+	ip link set dev br0 addrgenmode none
+	ip link set dev br0 up
+	ip link add name br1 type bridge mcast_snooping 0
+	ip link set dev br1 addrgenmode none
+	ip link set dev br1 up
 	ip link set dev $swp1 master br0
 	ip link set dev $swp2 master br1
 	ip link set dev vxlan0 master br0
@@ -780,7 +788,9 @@ __offload_indication_join_vxlan_first()
 
 offload_indication_join_vxlan_first()
 {
-	ip link add dev br0 up type bridge mcast_snooping 0
+	ip link add dev br0 type bridge mcast_snooping 0
+	ip link set dev br0 addrgenmode none
+	ip link set dev br0 up
 	ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \
 		ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789
 
@@ -815,7 +825,9 @@ __offload_indication_join_vxlan_last()
 
 offload_indication_join_vxlan_last()
 {
-	ip link add dev br0 up type bridge mcast_snooping 0
+	ip link add dev br0 type bridge mcast_snooping 0
+	ip link set dev br0 addrgenmode none
+	ip link set dev br0 up
 	ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \
 		ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789
 
@@ -842,6 +854,7 @@ sanitization_vlan_aware_test()
 	RET=0
 
 	ip link add dev br0 type bridge mcast_snooping 0 vlan_filtering 1
+	ip link set dev br0 addrgenmode none
 
 	ip link add name vxlan10 up master br0 type vxlan id 10 nolearning \
 		$UDPCSUM_FLAFS ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789
@@ -915,8 +928,10 @@ offload_indication_vlan_aware_setup_create()
 {
 	# Create a simple setup with two VxLAN devices and a single VLAN-aware
 	# bridge
-	ip link add name br0 up type bridge mcast_snooping 0 vlan_filtering 1 \
+	ip link add name br0 type bridge mcast_snooping 0 vlan_filtering 1 \
 		vlan_default_pvid 0
+	ip link set dev br0 addrgenmode none
+	ip link set dev br0 up
 
 	ip link set dev $swp1 master br0
 
@@ -1060,8 +1075,10 @@ offload_indication_vlan_aware_decap_route_test()
 
 offload_indication_vlan_aware_join_vxlan_first()
 {
-	ip link add dev br0 up type bridge mcast_snooping 0 \
+	ip link add dev br0 type bridge mcast_snooping 0 \
 		vlan_filtering 1 vlan_default_pvid 1
+	ip link set dev br0 addrgenmode none
+	ip link set dev br0 up
 	ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \
 		ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789
 
@@ -1073,8 +1090,10 @@ offload_indication_vlan_aware_join_vxlan_first()
 
 offload_indication_vlan_aware_join_vxlan_last()
 {
-	ip link add dev br0 up type bridge mcast_snooping 0 \
+	ip link add dev br0 type bridge mcast_snooping 0 \
 		vlan_filtering 1 vlan_default_pvid 1
+	ip link set dev br0 addrgenmode none
+	ip link set dev br0 up
 	ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \
 		ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789
 
@@ -1091,8 +1110,10 @@ offload_indication_vlan_aware_l3vni_test()
 	RET=0
 
 	sysctl_set net.ipv6.conf.default.disable_ipv6 1
-	ip link add dev br0 up type bridge mcast_snooping 0 \
+	ip link add dev br0 type bridge mcast_snooping 0 \
 		vlan_filtering 1 vlan_default_pvid 0
+	ip link set dev br0 addrgenmode none
+	ip link set dev br0 up
 	ip link add name vxlan0 up type vxlan id 10 nolearning $UDPCSUM_FLAFS \
 		ttl 20 tos inherit local $LOCAL_IP_1 dstport 4789
 
diff --git a/tools/testing/selftests/drivers/net/napi_id.py b/tools/testing/selftests/drivers/net/napi_id.py
new file mode 100755
index 000000000000..d05eddcad539
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/napi_id.py
@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+from lib.py import ksft_run, ksft_exit
+from lib.py import ksft_eq, NetDrvEpEnv
+from lib.py import bkg, cmd, rand_port, NetNSEnter
+
+def test_napi_id(cfg) -> None:
+    port = rand_port()
+    listen_cmd = f"{cfg.test_dir}/napi_id_helper {cfg.addr} {port}"
+
+    with bkg(listen_cmd, ksft_wait=3) as server:
+        cmd(f"echo a | socat - TCP:{cfg.baddr}:{port}", host=cfg.remote, shell=True)
+
+    ksft_eq(0, server.ret)
+
+def main() -> None:
+    with NetDrvEpEnv(__file__) as cfg:
+        ksft_run([test_napi_id], args=(cfg,))
+    ksft_exit()
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/napi_id_helper.c b/tools/testing/selftests/drivers/net/napi_id_helper.c
new file mode 100644
index 000000000000..7f49ca6c8637
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/napi_id_helper.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <arpa/inet.h>
+#include <sys/socket.h>
+#include <netdb.h>
+
+#include "../../net/lib/ksft.h"
+
+int main(int argc, char *argv[])
+{
+	struct sockaddr_storage address;
+	struct addrinfo *result;
+	struct addrinfo hints;
+	unsigned int napi_id;
+	socklen_t addr_len;
+	socklen_t optlen;
+	char buf[1024];
+	int opt = 1;
+	int family;
+	int server;
+	int client;
+	int ret;
+
+	memset(&hints, 0, sizeof(hints));
+	hints.ai_family = AF_UNSPEC;
+	hints.ai_socktype = SOCK_STREAM;
+	hints.ai_flags = AI_PASSIVE;
+
+	ret = getaddrinfo(argv[1], argv[2], &hints, &result);
+	if (ret != 0) {
+		fprintf(stderr, "getaddrinfo: %s\n", gai_strerror(ret));
+		return 1;
+	}
+
+	family = result->ai_family;
+	addr_len = result->ai_addrlen;
+
+	server = socket(family, SOCK_STREAM, IPPROTO_TCP);
+	if (server < 0) {
+		perror("socket creation failed");
+		freeaddrinfo(result);
+		if (errno == EAFNOSUPPORT)
+			return -1;
+		return 1;
+	}
+
+	if (setsockopt(server, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt))) {
+		perror("setsockopt");
+		freeaddrinfo(result);
+		return 1;
+	}
+
+	memcpy(&address, result->ai_addr, result->ai_addrlen);
+	freeaddrinfo(result);
+
+	if (bind(server, (struct sockaddr *)&address, addr_len) < 0) {
+		perror("bind failed");
+		return 1;
+	}
+
+	if (listen(server, 1) < 0) {
+		perror("listen");
+		return 1;
+	}
+
+	ksft_ready();
+
+	client = accept(server, NULL, 0);
+	if (client < 0) {
+		perror("accept");
+		return 1;
+	}
+
+	optlen = sizeof(napi_id);
+	ret = getsockopt(client, SOL_SOCKET, SO_INCOMING_NAPI_ID, &napi_id,
+			 &optlen);
+	if (ret != 0) {
+		perror("getsockopt");
+		return 1;
+	}
+
+	read(client, buf, 1024);
+
+	ksft_wait();
+
+	if (napi_id == 0) {
+		fprintf(stderr, "napi ID is 0\n");
+		return 1;
+	}
+
+	close(client);
+	close(server);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/drivers/net/napi_threaded.py b/tools/testing/selftests/drivers/net/napi_threaded.py
new file mode 100755
index 000000000000..f4be72b2145a
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/napi_threaded.py
@@ -0,0 +1,143 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+Test napi threaded states.
+"""
+
+from lib.py import ksft_run, ksft_exit
+from lib.py import ksft_eq, ksft_ne, ksft_ge
+from lib.py import NetDrvEnv, NetdevFamily
+from lib.py import cmd, defer, ethtool
+
+
+def _assert_napi_threaded_enabled(nl, napi_id) -> None:
+    napi = nl.napi_get({'id': napi_id})
+    ksft_eq(napi['threaded'], 'enabled')
+    ksft_ne(napi.get('pid'), None)
+
+
+def _assert_napi_threaded_disabled(nl, napi_id) -> None:
+    napi = nl.napi_get({'id': napi_id})
+    ksft_eq(napi['threaded'], 'disabled')
+    ksft_eq(napi.get('pid'), None)
+
+
+def _set_threaded_state(cfg, threaded) -> None:
+    with open(f"/sys/class/net/{cfg.ifname}/threaded", "wb") as fp:
+        fp.write(str(threaded).encode('utf-8'))
+
+
+def _setup_deferred_cleanup(cfg) -> None:
+    combined = ethtool(f"-l {cfg.ifname}", json=True)[0].get("combined", 0)
+    ksft_ge(combined, 2)
+    defer(ethtool, f"-L {cfg.ifname} combined {combined}")
+
+    threaded = cmd(f"cat /sys/class/net/{cfg.ifname}/threaded").stdout
+    defer(_set_threaded_state, cfg, threaded)
+
+    return combined
+
+
+def napi_init(cfg, nl) -> None:
+    """
+    Test that threaded state (in the persistent NAPI config) gets updated
+    even when NAPI with given ID is not allocated at the time.
+    """
+
+    qcnt = _setup_deferred_cleanup(cfg)
+
+    _set_threaded_state(cfg, 1)
+    cmd(f"ethtool -L {cfg.ifname} combined 1")
+    _set_threaded_state(cfg, 0)
+    cmd(f"ethtool -L {cfg.ifname} combined {qcnt}")
+
+    napis = nl.napi_get({'ifindex': cfg.ifindex}, dump=True)
+    for napi in napis:
+        ksft_eq(napi['threaded'], 'disabled')
+        ksft_eq(napi.get('pid'), None)
+
+    cmd(f"ethtool -L {cfg.ifname} combined 1")
+    _set_threaded_state(cfg, 1)
+    cmd(f"ethtool -L {cfg.ifname} combined {qcnt}")
+
+    napis = nl.napi_get({'ifindex': cfg.ifindex}, dump=True)
+    for napi in napis:
+        ksft_eq(napi['threaded'], 'enabled')
+        ksft_ne(napi.get('pid'), None)
+
+
+def enable_dev_threaded_disable_napi_threaded(cfg, nl) -> None:
+    """
+    Test that when napi threaded is enabled at device level and
+    then disabled at napi level for one napi, the threaded state
+    of all napis is preserved after a change in number of queues.
+    """
+
+    napis = nl.napi_get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_ge(len(napis), 2)
+
+    napi0_id = napis[0]['id']
+    napi1_id = napis[1]['id']
+
+    qcnt = _setup_deferred_cleanup(cfg)
+
+    # set threaded
+    _set_threaded_state(cfg, 1)
+
+    # check napi threaded is set for both napis
+    _assert_napi_threaded_enabled(nl, napi0_id)
+    _assert_napi_threaded_enabled(nl, napi1_id)
+
+    # disable threaded for napi1
+    nl.napi_set({'id': napi1_id, 'threaded': 'disabled'})
+
+    cmd(f"ethtool -L {cfg.ifname} combined 1")
+    cmd(f"ethtool -L {cfg.ifname} combined {qcnt}")
+    _assert_napi_threaded_enabled(nl, napi0_id)
+    _assert_napi_threaded_disabled(nl, napi1_id)
+
+
+def change_num_queues(cfg, nl) -> None:
+    """
+    Test that when napi threaded is enabled at device level,
+    the napi threaded state is preserved after a change in
+    number of queues.
+    """
+
+    napis = nl.napi_get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_ge(len(napis), 2)
+
+    napi0_id = napis[0]['id']
+    napi1_id = napis[1]['id']
+
+    qcnt = _setup_deferred_cleanup(cfg)
+
+    # set threaded
+    _set_threaded_state(cfg, 1)
+
+    # check napi threaded is set for both napis
+    _assert_napi_threaded_enabled(nl, napi0_id)
+    _assert_napi_threaded_enabled(nl, napi1_id)
+
+    cmd(f"ethtool -L {cfg.ifname} combined 1")
+    cmd(f"ethtool -L {cfg.ifname} combined {qcnt}")
+
+    # check napi threaded is set for both napis
+    _assert_napi_threaded_enabled(nl, napi0_id)
+    _assert_napi_threaded_enabled(nl, napi1_id)
+
+
+def main() -> None:
+    """ Ksft boiler plate main """
+
+    with NetDrvEnv(__file__, queue_count=2) as cfg:
+        ksft_run([napi_init,
+                  change_num_queues,
+                  enable_dev_threaded_disable_napi_threaded],
+                 args=(cfg, NetdevFamily()))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/netcons_basic.sh b/tools/testing/selftests/drivers/net/netcons_basic.sh
new file mode 100755
index 000000000000..2022f3061738
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netcons_basic.sh
@@ -0,0 +1,74 @@
+#!/usr/bin/env bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test creates two netdevsim virtual interfaces, assigns one of them (the
+# "destination interface") to a new namespace, and assigns IP addresses to both
+# interfaces.
+#
+# It listens on the destination interface using socat and configures a dynamic
+# target on netconsole, pointing to the destination IP address.
+#
+# Finally, it checks whether the message was received properly on the
+# destination interface.  Note that this test may pollute the kernel log buffer
+# (dmesg) and relies on dynamic configuration and namespaces being configured.
+#
+# Author: Breno Leitao <leitao@debian.org>
+
+set -euo pipefail
+
+SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")")
+
+source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh
+
+modprobe netdevsim 2> /dev/null || true
+modprobe netconsole 2> /dev/null || true
+
+# The content of kmsg will be save to the following file
+OUTPUT_FILE="/tmp/${TARGET}"
+
+# Check for basic system dependency and exit if not found
+check_for_dependencies
+# Remove the namespace, interfaces and netconsole target on exit
+trap cleanup EXIT
+
+# Run the test twice, with different format modes
+for FORMAT in "basic" "extended"
+do
+	for IP_VERSION in "ipv6" "ipv4"
+	do
+		echo "Running with target mode: ${FORMAT} (${IP_VERSION})"
+		# Set current loglevel to KERN_INFO(6), and default to
+		# KERN_NOTICE(5)
+		echo "6 5" > /proc/sys/kernel/printk
+		# Create one namespace and two interfaces
+		set_network "${IP_VERSION}"
+		# Create a dynamic target for netconsole
+		create_dynamic_target "${FORMAT}"
+		# Only set userdata for extended format
+		if [ "$FORMAT" == "extended" ]
+		then
+			# Set userdata "key" with the "value" value
+			set_user_data
+		fi
+		# Listed for netconsole port inside the namespace and
+		# destination interface
+		listen_port_and_save_to "${OUTPUT_FILE}" "${IP_VERSION}" &
+		# Wait for socat to start and listen to the port.
+		wait_for_port "${NAMESPACE}" "${PORT}" "${IP_VERSION}"
+		# Send the message
+		echo "${MSG}: ${TARGET}" > /dev/kmsg
+		# Wait until socat saves the file to disk
+		busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}"
+
+		# Make sure the message was received in the dst part
+		# and exit
+		validate_result "${OUTPUT_FILE}" "${FORMAT}"
+		# kill socat in case it is still running
+		pkill_socat
+		cleanup
+		echo "${FORMAT} : ${IP_VERSION} : Test passed" >&2
+	done
+done
+
+trap - EXIT
+exit "${ksft_pass}"
diff --git a/tools/testing/selftests/drivers/net/netcons_cmdline.sh b/tools/testing/selftests/drivers/net/netcons_cmdline.sh
new file mode 100755
index 000000000000..d1d23dc67f99
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netcons_cmdline.sh
@@ -0,0 +1,65 @@
+#!/usr/bin/env bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This is a selftest to test cmdline arguments on netconsole.
+# It exercises loading of netconsole from cmdline instead of the dynamic
+# reconfiguration. This includes parsing the long netconsole= line and all the
+# flow through init_netconsole().
+#
+# Author: Breno Leitao <leitao@debian.org>
+
+set -euo pipefail
+
+SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")")
+
+source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh
+
+check_netconsole_module
+
+modprobe netdevsim 2> /dev/null || true
+rmmod netconsole 2> /dev/null || true
+
+# Check for basic system dependency and exit if not found
+# check_for_dependencies
+# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5)
+echo "6 5" > /proc/sys/kernel/printk
+# Remove the namespace and network interfaces
+trap do_cleanup EXIT
+# Create one namespace and two interfaces
+set_network
+
+# Run the test twice, with different cmdline parameters
+for BINDMODE in "ifname" "mac"
+do
+	echo "Running with bind mode: ${BINDMODE}" >&2
+	# Create the command line for netconsole, with the configuration from
+	# the function above
+	CMDLINE=$(create_cmdline_str "${BINDMODE}")
+
+	# The content of kmsg will be save to the following file
+	OUTPUT_FILE="/tmp/${TARGET}-${BINDMODE}"
+
+	# Load the module, with the cmdline set
+	modprobe netconsole "${CMDLINE}"
+
+	# Listed for netconsole port inside the namespace and destination
+	# interface
+	listen_port_and_save_to "${OUTPUT_FILE}" &
+	# Wait for socat to start and listen to the port.
+	wait_local_port_listen "${NAMESPACE}" "${PORT}" udp
+	# Send the message
+	echo "${MSG}: ${TARGET}" > /dev/kmsg
+	# Wait until socat saves the file to disk
+	busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}"
+	# Make sure the message was received in the dst part
+	# and exit
+	validate_msg "${OUTPUT_FILE}"
+
+	# kill socat in case it is still running
+	pkill_socat
+	# Unload the module
+	rmmod netconsole
+	echo "${BINDMODE} : Test passed" >&2
+done
+
+exit "${ksft_pass}"
diff --git a/tools/testing/selftests/drivers/net/netcons_fragmented_msg.sh b/tools/testing/selftests/drivers/net/netcons_fragmented_msg.sh
new file mode 100755
index 000000000000..4a71e01a230c
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netcons_fragmented_msg.sh
@@ -0,0 +1,122 @@
+#!/usr/bin/env bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test netconsole's message fragmentation functionality.
+#
+# When a message exceeds the maximum packet size, netconsole splits it into
+# multiple fragments for transmission. This test verifies:
+#  - Correct fragmentation of large messages
+#  - Proper reassembly of fragments at the receiver
+#  - Preservation of userdata across fragments
+#  - Behavior with and without kernel release version appending
+#
+# Author: Breno Leitao <leitao@debian.org>
+
+set -euo pipefail
+
+SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")")
+
+source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh
+
+modprobe netdevsim 2> /dev/null || true
+modprobe netconsole 2> /dev/null || true
+
+# The content of kmsg will be save to the following file
+OUTPUT_FILE="/tmp/${TARGET}"
+
+# set userdata to a long value. In this case, it is "1-2-3-4...50-"
+USERDATA_VALUE=$(printf -- '%.2s-' {1..60})
+
+# Convert the header string in a regexp, so, we can remove
+# the second header as well.
+# A header looks like "13,468,514729715,-,ncfrag=0/1135;". If
+# release is appended, you might find something like:L
+# "6.13.0-04048-g4f561a87745a,13,468,514729715,-,ncfrag=0/1135;"
+function header_to_regex() {
+	# header is everything before ;
+	local HEADER="${1}"
+	REGEX=$(echo "${HEADER}" | cut -d'=' -f1)
+	echo "${REGEX}=[0-9]*\/[0-9]*;"
+}
+
+# We have two headers in the message. Remove both to get the full message,
+# and extract the full message.
+function extract_msg() {
+	local MSGFILE="${1}"
+	# Extract the header, which is the very first thing that arrives in the
+	# first list.
+	HEADER=$(sed -n '1p' "${MSGFILE}" | cut -d';' -f1)
+	HEADER_REGEX=$(header_to_regex "${HEADER}")
+
+	# Remove the two headers from the received message
+	# This will return the message without any header, similarly to what
+	# was sent.
+	sed "s/""${HEADER_REGEX}""//g" "${MSGFILE}"
+}
+
+# Validate the message, which has two messages glued together.
+# unwrap them to make sure all the characters were transmitted.
+# File will look like the following:
+#  13,468,514729715,-,ncfrag=0/1135;<message>
+#   key=<part of key>-13,468,514729715,-,ncfrag=967/1135;<rest of the key>
+function validate_fragmented_result() {
+	# Discard the netconsole headers, and assemble the full message
+	RCVMSG=$(extract_msg "${1}")
+
+	# check for the main message
+	if ! echo "${RCVMSG}" | grep -q "${MSG}"; then
+		echo "Message body doesn't match." >&2
+		echo "msg received=" "${RCVMSG}" >&2
+		exit "${ksft_fail}"
+	fi
+
+	# check userdata
+	if ! echo "${RCVMSG}" | grep -q "${USERDATA_VALUE}"; then
+		echo "message userdata doesn't match" >&2
+		echo "msg received=" "${RCVMSG}" >&2
+		exit "${ksft_fail}"
+	fi
+	# test passed. hooray
+}
+
+# Check for basic system dependency and exit if not found
+check_for_dependencies
+# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5)
+echo "6 5" > /proc/sys/kernel/printk
+# Remove the namespace, interfaces and netconsole target on exit
+trap cleanup EXIT
+# Create one namespace and two interfaces
+set_network
+# Create a dynamic target for netconsole
+create_dynamic_target
+# Set userdata "key" with the "value" value
+set_user_data
+
+
+# TEST 1: Send message and userdata. They will fragment
+# =======
+MSG=$(printf -- 'MSG%.3s=' {1..150})
+
+# Listen for netconsole port inside the namespace and destination interface
+listen_port_and_save_to "${OUTPUT_FILE}" &
+# Wait for socat to start and listen to the port.
+wait_local_port_listen "${NAMESPACE}" "${PORT}" udp
+# Send the message
+echo "${MSG}: ${TARGET}" > /dev/kmsg
+# Wait until socat saves the file to disk
+busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}"
+# Check if the message was not corrupted
+validate_fragmented_result "${OUTPUT_FILE}"
+
+# TEST 2: Test with smaller message, and without release appended
+# =======
+MSG=$(printf -- 'FOOBAR%.3s=' {1..100})
+# Let's disable release and test again.
+disable_release_append
+
+listen_port_and_save_to "${OUTPUT_FILE}" &
+wait_local_port_listen "${NAMESPACE}" "${PORT}" udp
+echo "${MSG}: ${TARGET}" > /dev/kmsg
+busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}"
+validate_fragmented_result "${OUTPUT_FILE}"
+exit "${ksft_pass}"
diff --git a/tools/testing/selftests/drivers/net/netcons_overflow.sh b/tools/testing/selftests/drivers/net/netcons_overflow.sh
new file mode 100755
index 000000000000..06089643b771
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netcons_overflow.sh
@@ -0,0 +1,67 @@
+#!/usr/bin/env bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test verifies that users can successfully create up to
+# MAX_USERDATA_ITEMS userdata entries without encountering any failures.
+#
+# Additionally, it tests for expected failure when attempting to exceed this
+# maximum limit.
+#
+# Author: Breno Leitao <leitao@debian.org>
+
+set -euo pipefail
+
+SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")")
+
+source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh
+# This is coming from netconsole code. Check for it in drivers/net/netconsole.c
+MAX_USERDATA_ITEMS=256
+
+# Function to create userdata entries
+function create_userdata_max_entries() {
+	# All these keys should be created without any error
+	for i in $(seq $MAX_USERDATA_ITEMS)
+	do
+		# USERDATA_KEY is used by set_user_data
+		USERDATA_KEY="key"${i}
+		set_user_data
+	done
+}
+
+# Function to verify the entry limit
+function verify_entry_limit() {
+	# Allowing the test to fail without exiting, since the next command
+	# will fail
+	set +e
+	mkdir "${NETCONS_PATH}/userdata/key_that_will_fail" 2> /dev/null
+	ret="$?"
+	set -e
+	if [ "$ret" -eq 0 ];
+	then
+		echo "Adding more than ${MAX_USERDATA_ITEMS} entries in userdata should fail, but it didn't" >&2
+		ls "${NETCONS_PATH}/userdata/" >&2
+		exit "${ksft_fail}"
+	fi
+}
+
+# ========== #
+# Start here #
+# ========== #
+
+modprobe netdevsim 2> /dev/null || true
+modprobe netconsole 2> /dev/null || true
+
+# Check for basic system dependency and exit if not found
+check_for_dependencies
+
+# Remove the namespace, interfaces and netconsole target on exit
+trap cleanup EXIT
+# Create one namespace and two interfaces
+set_network
+# Create a dynamic target for netconsole
+create_dynamic_target
+# populate the maximum number of supported keys in userdata
+create_userdata_max_entries
+# Verify an additional entry is not allowed
+verify_entry_limit
+exit "${ksft_pass}"
diff --git a/tools/testing/selftests/drivers/net/netcons_sysdata.sh b/tools/testing/selftests/drivers/net/netcons_sysdata.sh
new file mode 100755
index 000000000000..baf69031089e
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netcons_sysdata.sh
@@ -0,0 +1,272 @@
+#!/usr/bin/env bash
+# SPDX-License-Identifier: GPL-2.0
+
+# A test that makes sure that sysdata runtime CPU data is properly set
+# when a message is sent.
+#
+# There are 3 different tests, every time sent using a random CPU.
+#  - Test #1
+#    * Only enable cpu_nr sysdata feature.
+#  - Test #2
+#    * Keep cpu_nr sysdata feature enable and enable userdata.
+#  - Test #3
+#    * keep userdata enabled, and disable sysdata cpu_nr feature.
+#
+# Author: Breno Leitao <leitao@debian.org>
+
+set -euo pipefail
+
+SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")")
+
+source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh
+
+# Enable the sysdata cpu_nr feature
+function set_cpu_nr() {
+	if [[ ! -f "${NETCONS_PATH}/userdata/cpu_nr_enabled" ]]
+	then
+		echo "Populate CPU configfs path not available in ${NETCONS_PATH}/userdata/cpu_nr_enabled" >&2
+		exit "${ksft_skip}"
+	fi
+
+	echo 1 > "${NETCONS_PATH}/userdata/cpu_nr_enabled"
+}
+
+# Enable the taskname to be appended to sysdata
+function set_taskname() {
+	if [[ ! -f "${NETCONS_PATH}/userdata/taskname_enabled" ]]
+	then
+		echo "Not able to enable taskname sysdata append. Configfs not available in ${NETCONS_PATH}/userdata/taskname_enabled" >&2
+		exit "${ksft_skip}"
+	fi
+
+	echo 1 > "${NETCONS_PATH}/userdata/taskname_enabled"
+}
+
+# Enable the release to be appended to sysdata
+function set_release() {
+	if [[ ! -f "${NETCONS_PATH}/userdata/release_enabled" ]]
+	then
+		echo "Not able to enable release sysdata append. Configfs not available in ${NETCONS_PATH}/userdata/release_enabled" >&2
+		exit "${ksft_skip}"
+	fi
+
+	echo 1 > "${NETCONS_PATH}/userdata/release_enabled"
+}
+
+# Enable the msgid to be appended to sysdata
+function set_msgid() {
+	if [[ ! -f "${NETCONS_PATH}/userdata/msgid_enabled" ]]
+	then
+		echo "Not able to enable msgid sysdata append. Configfs not available in ${NETCONS_PATH}/userdata/msgid_enabled" >&2
+		exit "${ksft_skip}"
+	fi
+
+	echo 1 > "${NETCONS_PATH}/userdata/msgid_enabled"
+}
+
+# Disable the sysdata cpu_nr feature
+function unset_cpu_nr() {
+	echo 0 > "${NETCONS_PATH}/userdata/cpu_nr_enabled"
+}
+
+# Once called, taskname=<..> will not be appended anymore
+function unset_taskname() {
+	echo 0 > "${NETCONS_PATH}/userdata/taskname_enabled"
+}
+
+function unset_release() {
+	echo 0 > "${NETCONS_PATH}/userdata/release_enabled"
+}
+
+function unset_msgid() {
+	echo 0 > "${NETCONS_PATH}/userdata/msgid_enabled"
+}
+
+# Test if MSG contains sysdata
+function validate_sysdata() {
+	# OUTPUT_FILE will contain something like:
+	# 6.11.1-0_fbk0_rc13_509_g30d75cea12f7,13,1822,115075213798,-;netconsole selftest: netcons_gtJHM
+	#  userdatakey=userdatavalue
+	#  cpu=X
+	#  taskname=<taskname>
+	#  msgid=<id>
+
+	# Echo is what this test uses to create the message. See runtest()
+	# function
+	SENDER="echo"
+
+	if [ ! -f "$OUTPUT_FILE" ]; then
+		echo "FAIL: File was not generated." >&2
+		exit "${ksft_fail}"
+	fi
+
+	if ! grep -q "${MSG}" "${OUTPUT_FILE}"; then
+		echo "FAIL: ${MSG} not found in ${OUTPUT_FILE}" >&2
+		cat "${OUTPUT_FILE}" >&2
+		exit "${ksft_fail}"
+	fi
+
+	# Check if cpu=XX exists in the file and matches the one used
+	# in taskset(1)
+	if ! grep -q "cpu=${CPU}\+" "${OUTPUT_FILE}"; then
+		echo "FAIL: 'cpu=${CPU}' not found in ${OUTPUT_FILE}" >&2
+		cat "${OUTPUT_FILE}" >&2
+		exit "${ksft_fail}"
+	fi
+
+	if ! grep -q "taskname=${SENDER}" "${OUTPUT_FILE}"; then
+		echo "FAIL: 'taskname=echo' not found in ${OUTPUT_FILE}" >&2
+		cat "${OUTPUT_FILE}" >&2
+		exit "${ksft_fail}"
+	fi
+
+	if ! grep -q "msgid=[0-9]\+$" "${OUTPUT_FILE}"; then
+		echo "FAIL: 'msgid=<id>' not found in ${OUTPUT_FILE}" >&2
+		cat "${OUTPUT_FILE}" >&2
+		exit "${ksft_fail}"
+	fi
+
+	rm "${OUTPUT_FILE}"
+	pkill_socat
+}
+
+function validate_release() {
+	RELEASE=$(uname -r)
+
+	if [ ! -f "$OUTPUT_FILE" ]; then
+		echo "FAIL: File was not generated." >&2
+		exit "${ksft_fail}"
+	fi
+
+	if ! grep -q "release=${RELEASE}" "${OUTPUT_FILE}"; then
+		echo "FAIL: 'release=${RELEASE}' not found in ${OUTPUT_FILE}" >&2
+		cat "${OUTPUT_FILE}" >&2
+		exit "${ksft_fail}"
+	fi
+}
+
+# Test if MSG content exists in OUTPUT_FILE but no `cpu=` and `taskname=`
+# strings
+function validate_no_sysdata() {
+	if [ ! -f "$OUTPUT_FILE" ]; then
+		echo "FAIL: File was not generated." >&2
+		exit "${ksft_fail}"
+	fi
+
+	if ! grep -q "${MSG}" "${OUTPUT_FILE}"; then
+		echo "FAIL: ${MSG} not found in ${OUTPUT_FILE}" >&2
+		cat "${OUTPUT_FILE}" >&2
+		exit "${ksft_fail}"
+	fi
+
+	if grep -q "cpu=" "${OUTPUT_FILE}"; then
+		echo "FAIL: 'cpu=  found in ${OUTPUT_FILE}" >&2
+		cat "${OUTPUT_FILE}" >&2
+		exit "${ksft_fail}"
+	fi
+
+	if grep -q "taskname=" "${OUTPUT_FILE}"; then
+		echo "FAIL: 'taskname=  found in ${OUTPUT_FILE}" >&2
+		cat "${OUTPUT_FILE}" >&2
+		exit "${ksft_fail}"
+	fi
+
+	if grep -q "release=" "${OUTPUT_FILE}"; then
+		echo "FAIL: 'release=  found in ${OUTPUT_FILE}" >&2
+		cat "${OUTPUT_FILE}" >&2
+		exit "${ksft_fail}"
+	fi
+
+	if grep -q "msgid=" "${OUTPUT_FILE}"; then
+		echo "FAIL: 'msgid=  found in ${OUTPUT_FILE}" >&2
+		cat "${OUTPUT_FILE}" >&2
+		exit "${ksft_fail}"
+	fi
+
+	rm "${OUTPUT_FILE}"
+}
+
+# Start socat, send the message and wait for the file to show up in the file
+# system
+function runtest {
+	# Listen for netconsole port inside the namespace and destination
+	# interface
+	listen_port_and_save_to "${OUTPUT_FILE}" &
+	# Wait for socat to start and listen to the port.
+	wait_local_port_listen "${NAMESPACE}" "${PORT}" udp
+	# Send the message
+	taskset -c "${CPU}" echo "${MSG}: ${TARGET}" > /dev/kmsg
+	# Wait until socat saves the file to disk
+	busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}"
+}
+
+# ========== #
+# Start here #
+# ========== #
+
+modprobe netdevsim 2> /dev/null || true
+modprobe netconsole 2> /dev/null || true
+
+# Check for basic system dependency and exit if not found
+check_for_dependencies
+# This test also depends on taskset(1). Check for it before starting the test
+check_for_taskset
+
+# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5)
+echo "6 5" > /proc/sys/kernel/printk
+# Remove the namespace, interfaces and netconsole target on exit
+trap cleanup EXIT
+# Create one namespace and two interfaces
+set_network
+# Create a dynamic target for netconsole
+create_dynamic_target
+
+#====================================================
+# TEST #1
+# Send message from a random CPU
+#====================================================
+# Random CPU in the system
+CPU=$((RANDOM % $(nproc)))
+OUTPUT_FILE="/tmp/${TARGET}_1"
+MSG="Test #1 from CPU${CPU}"
+# Enable the auto population of cpu_nr
+set_cpu_nr
+# Enable taskname to be appended to sysdata
+set_taskname
+set_release
+set_msgid
+runtest
+# Make sure the message was received in the dst part
+# and exit
+validate_release
+validate_sysdata
+
+#====================================================
+# TEST #2
+# This test now adds userdata together with sysdata
+# ===================================================
+# Get a new random CPU
+CPU=$((RANDOM % $(nproc)))
+OUTPUT_FILE="/tmp/${TARGET}_2"
+MSG="Test #2 from CPU${CPU}"
+set_user_data
+runtest
+validate_release
+validate_sysdata
+
+# ===================================================
+# TEST #3
+# Unset all sysdata, fail if any userdata is set
+# ===================================================
+CPU=$((RANDOM % $(nproc)))
+OUTPUT_FILE="/tmp/${TARGET}_3"
+MSG="Test #3 from CPU${CPU}"
+unset_cpu_nr
+unset_taskname
+unset_release
+unset_msgid
+runtest
+# At this time, cpu= shouldn't be present in the msg
+validate_no_sysdata
+
+exit "${ksft_pass}"
diff --git a/tools/testing/selftests/drivers/net/netcons_torture.sh b/tools/testing/selftests/drivers/net/netcons_torture.sh
new file mode 100755
index 000000000000..2ce9ee3719d1
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netcons_torture.sh
@@ -0,0 +1,130 @@
+#!/usr/bin/env bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Repeatedly send kernel messages, toggles netconsole targets on and off,
+# creates and deletes targets in parallel, and toggles the source interface to
+# simulate stress conditions.
+#
+# This test aims to verify the robustness of netconsole under dynamic
+# configurations and concurrent operations.
+#
+# The major goal is to run this test with LOCKDEP, Kmemleak and KASAN to make
+# sure no issues is reported.
+#
+# Author: Breno Leitao <leitao@debian.org>
+
+set -euo pipefail
+
+SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")")
+
+source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh
+
+# Number of times the main loop run
+ITERATIONS=${1:-150}
+
+# Only test extended format
+FORMAT="extended"
+# And ipv6 only
+IP_VERSION="ipv6"
+
+# Create, enable and delete some targets.
+create_and_delete_random_target() {
+	COUNT=2
+	RND_PREFIX=$(mktemp -u netcons_rnd_XXXX_)
+
+	if [ -d "${NETCONS_CONFIGFS}/${RND_PREFIX}${COUNT}"  ] || \
+	   [ -d "${NETCONS_CONFIGFS}/${RND_PREFIX}0" ]; then
+		echo "Function didn't finish yet, skipping it." >&2
+		return
+	fi
+
+	# enable COUNT targets
+	for i in $(seq ${COUNT})
+	do
+		RND_TARGET="${RND_PREFIX}"${i}
+		RND_TARGET_PATH="${NETCONS_CONFIGFS}"/"${RND_TARGET}"
+
+		# Basic population so the target can come up
+		_create_dynamic_target "${FORMAT}" "${RND_TARGET_PATH}"
+	done
+
+	echo "netconsole selftest: ${COUNT} additional targets were created" > /dev/kmsg
+	# disable them all
+	for i in $(seq ${COUNT})
+	do
+		RND_TARGET="${RND_PREFIX}"${i}
+		RND_TARGET_PATH="${NETCONS_CONFIGFS}"/"${RND_TARGET}"
+		if [[ $(cat "${RND_TARGET_PATH}/enabled") -eq 1 ]]
+		then
+			echo 0 > "${RND_TARGET_PATH}"/enabled
+		fi
+		rmdir "${RND_TARGET_PATH}"
+	done
+}
+
+# Disable and enable the target mid-air, while messages
+# are being transmitted.
+toggle_netcons_target() {
+	for i in $(seq 2)
+	do
+		if [ ! -d "${NETCONS_PATH}" ]
+		then
+			break
+		fi
+		echo 0 > "${NETCONS_PATH}"/enabled 2> /dev/null || true
+		# Try to enable a bit harder, given it might fail to enable
+		# Write to `enabled` might fail depending on the lock, which is
+		# highly contentious here
+		for _ in $(seq 5)
+		do
+			echo 1 > "${NETCONS_PATH}"/enabled 2> /dev/null || true
+		done
+	done
+}
+
+toggle_iface(){
+	ip link set "${SRCIF}" down
+	ip link set "${SRCIF}" up
+}
+
+# Start here
+
+modprobe netdevsim 2> /dev/null || true
+modprobe netconsole 2> /dev/null || true
+
+# Check for basic system dependency and exit if not found
+check_for_dependencies
+# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5)
+echo "6 5" > /proc/sys/kernel/printk
+# Remove the namespace, interfaces and netconsole target on exit
+trap cleanup EXIT
+# Create one namespace and two interfaces
+set_network "${IP_VERSION}"
+# Create a dynamic target for netconsole
+create_dynamic_target "${FORMAT}"
+
+for i in $(seq "$ITERATIONS")
+do
+	for _ in $(seq 10)
+	do
+		echo "${MSG}: ${TARGET} ${i}" > /dev/kmsg
+	done
+	wait
+
+	if (( i % 30 == 0 )); then
+		toggle_netcons_target &
+	fi
+
+	if (( i % 50 == 0 )); then
+		# create some targets, enable them, send msg and disable
+		# all in a parallel thread
+		create_and_delete_random_target &
+	fi
+
+	if (( i % 70 == 0 )); then
+		toggle_iface &
+	fi
+done
+wait
+
+exit "${EXIT_STATUS}"
diff --git a/tools/testing/selftests/drivers/net/netdevsim/Makefile b/tools/testing/selftests/drivers/net/netdevsim/Makefile
new file mode 100644
index 000000000000..1a228c5430f5
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/Makefile
@@ -0,0 +1,26 @@
+# SPDX-License-Identifier: GPL-2.0+ OR MIT
+
+TEST_PROGS := \
+	devlink.sh \
+	devlink_in_netns.sh \
+	devlink_trap.sh \
+	ethtool-coalesce.sh \
+	ethtool-features.sh \
+	ethtool-fec.sh \
+	ethtool-pause.sh \
+	fib.sh \
+	fib_notifications.sh \
+	hw_stats_l3.sh \
+	macsec-offload.sh \
+	nexthop.sh \
+	peer.sh \
+	psample.sh \
+	tc-mq-visibility.sh \
+	udp_tunnel_nic.sh \
+# end of TEST_PROGS
+
+TEST_FILES := \
+	ethtool-common.sh
+# end of TEST_FILES
+
+include ../../../lib.mk
diff --git a/tools/testing/selftests/drivers/net/netdevsim/config b/tools/testing/selftests/drivers/net/netdevsim/config
new file mode 100644
index 000000000000..5117c78ddf0a
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/config
@@ -0,0 +1,11 @@
+CONFIG_DUMMY=y
+CONFIG_GENEVE=m
+CONFIG_IPV6=y
+CONFIG_MACSEC=m
+CONFIG_NETDEVSIM=m
+CONFIG_NET_SCH_MQPRIO=y
+CONFIG_NET_SCH_MULTIQ=y
+CONFIG_NET_SCH_PRIO=y
+CONFIG_PSAMPLE=y
+CONFIG_PTP_1588_CLOCK_MOCK=y
+CONFIG_VXLAN=m
diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
index a08c02abde12..1b529ccaf050 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh
@@ -3,7 +3,8 @@
 
 lib_dir=$(dirname $0)/../../../net/forwarding
 
-ALL_TESTS="fw_flash_test params_test regions_test reload_test \
+ALL_TESTS="fw_flash_test params_test  \
+	   params_default_test regions_test reload_test \
 	   netns_reload_test resource_test dev_info_test \
 	   empty_reporter_test dummy_reporter_test rate_test"
 NUM_NETIFS=0
@@ -17,38 +18,59 @@ SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV_NAME/net/
 DEBUGFS_DIR=/sys/kernel/debug/netdevsim/$DEV_NAME/
 DL_HANDLE=netdevsim/$DEV_NAME
 
+wait_for_devlink()
+{
+	"$@" | grep -q $DL_HANDLE
+}
+
+devlink_wait()
+{
+	local timeout=$1
+
+	busywait "$timeout" wait_for_devlink devlink dev
+}
+
 fw_flash_test()
 {
+	DUMMYFILE=$(find /lib/firmware -type f -printf '%P\n' | head -1)
 	RET=0
 
-	devlink dev flash $DL_HANDLE file dummy
+	if [ -z "$DUMMYFILE" ]
+	then
+		echo "SKIP: unable to find suitable dummy firmware file"
+		return
+	fi
+
+	echo "10"> $DEBUGFS_DIR/fw_update_flash_chunk_time_ms
+
+	devlink dev flash $DL_HANDLE file $DUMMYFILE
 	check_err $? "Failed to flash with status updates on"
 
-	devlink dev flash $DL_HANDLE file dummy component fw.mgmt
+	devlink dev flash $DL_HANDLE file $DUMMYFILE component fw.mgmt
 	check_err $? "Failed to flash with component attribute"
 
-	devlink dev flash $DL_HANDLE file dummy overwrite settings
+	devlink dev flash $DL_HANDLE file $DUMMYFILE overwrite settings
 	check_fail $? "Flash with overwrite settings should be rejected"
 
 	echo "1"> $DEBUGFS_DIR/fw_update_overwrite_mask
 	check_err $? "Failed to change allowed overwrite mask"
 
-	devlink dev flash $DL_HANDLE file dummy overwrite settings
+	devlink dev flash $DL_HANDLE file $DUMMYFILE overwrite settings
 	check_err $? "Failed to flash with settings overwrite enabled"
 
-	devlink dev flash $DL_HANDLE file dummy overwrite identifiers
+	devlink dev flash $DL_HANDLE file $DUMMYFILE overwrite identifiers
 	check_fail $? "Flash with overwrite settings should be identifiers"
 
 	echo "3"> $DEBUGFS_DIR/fw_update_overwrite_mask
 	check_err $? "Failed to change allowed overwrite mask"
 
-	devlink dev flash $DL_HANDLE file dummy overwrite identifiers overwrite settings
+	devlink dev flash $DL_HANDLE file $DUMMYFILE overwrite identifiers overwrite settings
 	check_err $? "Failed to flash with settings and identifiers overwrite enabled"
 
 	echo "n"> $DEBUGFS_DIR/fw_update_status
 	check_err $? "Failed to disable status updates"
 
-	devlink dev flash $DL_HANDLE file dummy
+	devlink dev flash $DL_HANDLE file $DUMMYFILE
 	check_err $? "Failed to flash with status updates off"
 
 	log_test "fw flash test"
@@ -57,17 +79,28 @@ fw_flash_test()
 param_get()
 {
 	local name=$1
+	local attr=${2:-value}
+	local cmode=${3:-driverinit}
 
 	cmd_jq "devlink dev param show $DL_HANDLE name $name -j" \
-	       '.[][][].values[] | select(.cmode == "driverinit").value'
+	       '.[][][].values[] | select(.cmode == "'"$cmode"'").'"$attr"
 }
 
 param_set()
 {
 	local name=$1
 	local value=$2
+	local cmode=${3:-driverinit}
+
+	devlink dev param set $DL_HANDLE name $name cmode $cmode value $value
+}
+
+param_set_default()
+{
+	local name=$1
+	local cmode=${2:-driverinit}
 
-	devlink dev param set $DL_HANDLE name $name cmode driverinit value $value
+	devlink dev param set $DL_HANDLE name $name default cmode $cmode
 }
 
 check_value()
@@ -76,12 +109,18 @@ check_value()
 	local phase_name=$2
 	local expected_param_value=$3
 	local expected_debugfs_value=$4
+	local cmode=${5:-driverinit}
 	local value
+	local attr="value"
 
-	value=$(param_get $name)
-	check_err $? "Failed to get $name param value"
+	if [[ "$phase_name" == *"default"* ]]; then
+		attr="default"
+	fi
+
+	value=$(param_get $name $attr $cmode)
+	check_err $? "Failed to get $name param $attr"
 	[ "$value" == "$expected_param_value" ]
-	check_err $? "Unexpected $phase_name $name param value"
+	check_err $? "Unexpected $phase_name $name param $attr"
 	value=$(<$DEBUGFS_DIR/$name)
 	check_err $? "Failed to get $name debugfs value"
 	[ "$value" == "$expected_debugfs_value" ]
@@ -114,6 +153,92 @@ params_test()
 	log_test "params test"
 }
 
+value_to_debugfs()
+{
+	local value=$1
+
+	case "$value" in
+		true)
+			echo "Y"
+			;;
+		false)
+			echo "N"
+			;;
+		*)
+			echo "$value"
+			;;
+	esac
+}
+
+test_default()
+{
+	local param_name=$1
+	local new_value=$2
+	local expected_default=$3
+	local cmode=${4:-driverinit}
+	local default_debugfs
+	local new_debugfs
+	local expected_debugfs
+
+	default_debugfs=$(value_to_debugfs $expected_default)
+	new_debugfs=$(value_to_debugfs $new_value)
+
+	expected_debugfs=$default_debugfs
+	check_value $param_name initial-default $expected_default $expected_debugfs $cmode
+
+	param_set $param_name $new_value $cmode
+	check_err $? "Failed to set $param_name to $new_value"
+
+	expected_debugfs=$([ "$cmode" == "runtime" ] && echo "$new_debugfs" || echo "$default_debugfs")
+	check_value $param_name post-set $new_value $expected_debugfs $cmode
+
+	devlink dev reload $DL_HANDLE
+	check_err $? "Failed to reload device"
+
+	expected_debugfs=$new_debugfs
+	check_value $param_name post-reload-new-value $new_value $expected_debugfs $cmode
+
+	param_set_default $param_name $cmode
+	check_err $? "Failed to set $param_name to default"
+
+	expected_debugfs=$([ "$cmode" == "runtime" ] && echo "$default_debugfs" || echo "$new_debugfs")
+	check_value $param_name post-set-default $expected_default $expected_debugfs $cmode
+
+	devlink dev reload $DL_HANDLE
+	check_err $? "Failed to reload device"
+
+	expected_debugfs=$default_debugfs
+	check_value $param_name post-reload-default $expected_default $expected_debugfs $cmode
+}
+
+params_default_test()
+{
+	RET=0
+
+	if ! devlink dev param help 2>&1 | grep -q "value VALUE | default"; then
+		echo "SKIP: devlink cli missing default feature"
+		return
+	fi
+
+	# Remove side effects of previous tests. Use plain param_set, because
+	# param_set_default is a feature under test here.
+	param_set max_macs 32 driverinit
+	check_err $? "Failed to reset max_macs to default value"
+	param_set test1 true driverinit
+	check_err $? "Failed to reset test1 to default value"
+	param_set test2 1234 runtime
+	check_err $? "Failed to reset test2 to default value"
+
+	devlink dev reload $DL_HANDLE
+	check_err $? "Failed to reload device for clean state"
+
+	test_default max_macs 16 32 driverinit
+	test_default test1 false true driverinit
+	test_default test2 100 1234 runtime
+
+	log_test "params default test"
+}
+
 check_region_size()
 {
 	local name=$1
@@ -256,6 +381,9 @@ netns_reload_test()
 	ip netns del testns2
 	ip netns del testns1
 
+	# Wait until netns async cleanup is done.
+	devlink_wait 2000
+
 	log_test "netns reload test"
 }
 
@@ -348,6 +476,9 @@ resource_test()
 	ip netns del testns2
 	ip netns del testns1
 
+	# Wait until netns async cleanup is done.
+	devlink_wait 2000
+
 	log_test "resource test"
 }
 
@@ -583,6 +714,46 @@ rate_attr_parent_check()
 	check_err $? "Unexpected parent attr value $api_value != $parent"
 }
 
+rate_attr_tc_bw_check()
+{
+	local handle=$1
+	local tc_bw=$2
+	local debug_file=$3
+
+	local tc_bw_str=""
+	for bw in $tc_bw; do
+		local tc=${bw%%:*}
+		local value=${bw##*:}
+		tc_bw_str="$tc_bw_str $tc:$value"
+	done
+	tc_bw_str=${tc_bw_str# }
+
+	rate_attr_set "$handle" tc-bw "$tc_bw_str"
+	check_err $? "Failed to set tc-bw values"
+
+	for bw in $tc_bw; do
+		local tc=${bw%%:*}
+		local value=${bw##*:}
+		local debug_value
+		debug_value=$(cat "$debug_file"/tc"${tc}"_bw)
+		check_err $? "Failed to read tc-bw value from debugfs for tc$tc"
+		[ "$debug_value" == "$value" ]
+		check_err $? "Unexpected tc-bw debug value for tc$tc: $debug_value != $value"
+	done
+
+	for bw in $tc_bw; do
+		local tc=${bw%%:*}
+		local expected_value=${bw##*:}
+		local api_value
+		api_value=$(rate_attr_get "$handle" tc_"$tc")
+		if [ "$api_value" = "null" ]; then
+			api_value=0
+		fi
+		[ "$api_value" == "$expected_value" ]
+		check_err $? "Unexpected tc-bw value for tc$tc: $api_value != $expected_value"
+	done
+}
+
 rate_node_add()
 {
 	local handle=$1
@@ -624,6 +795,13 @@ rate_test()
 		rate=$(($rate+100))
 	done
 
+	local tc_bw="0:0 1:40 2:0 3:0 4:0 5:0 6:60 7:0"
+	for r_obj in $leafs
+	do
+		rate_attr_tc_bw_check "$r_obj" "$tc_bw" \
+			"$DEBUGFS_DIR"/ports/"${r_obj##*/}"
+	done
+
 	local node1_name='group1'
 	local node1="$DL_HANDLE/$node1_name"
 	rate_node_add "$node1"
@@ -641,6 +819,12 @@ rate_test()
 	rate_attr_tx_rate_check $node1 tx_max $node_tx_max \
 		$DEBUGFS_DIR/rate_nodes/${node1##*/}/tx_max
 
+
+	local tc_bw="0:20 1:0 2:0 3:0 4:0 5:20 6:60 7:0"
+	rate_attr_tc_bw_check $node1 "$tc_bw" \
+		"$DEBUGFS_DIR"/rate_nodes/"${node1##*/}"
+
+
 	rate_node_del "$node1"
 	check_err $? "Failed to delete node $node1"
 	local num_nodes=`rate_nodes_get $DL_HANDLE | wc -w`
diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh
index 922744059aaa..80160579e0cc 100644
--- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh
@@ -51,6 +51,7 @@ function make_netdev {
     fi
 
     echo $NSIM_ID $@ > /sys/bus/netdevsim/new_device
+    udevadm settle
     # get new device name
     ls /sys/bus/netdevsim/devices/netdevsim${NSIM_ID}/net/
 }
diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-features.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-features.sh
new file mode 100644
index 000000000000..bc210dc6ad2d
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-features.sh
@@ -0,0 +1,31 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+
+source ethtool-common.sh
+
+NSIM_NETDEV=$(make_netdev)
+
+set -o pipefail
+
+FEATS="
+  tx-checksum-ip-generic
+  tx-scatter-gather
+  tx-tcp-segmentation
+  generic-segmentation-offload
+  generic-receive-offload"
+
+for feat in $FEATS ; do
+    s=$(ethtool --json -k $NSIM_NETDEV | jq ".[].\"$feat\".active" 2>/dev/null)
+    check $? "$s" true
+
+    s=$(ethtool --json -k $NSIM_NETDEV | jq ".[].\"$feat\".fixed" 2>/dev/null)
+    check $? "$s" false
+done
+
+if [ $num_errors -eq 0 ]; then
+    echo "PASSED all $((num_passes)) checks"
+    exit 0
+else
+    echo "FAILED $num_errors/$((num_errors+num_passes)) checks"
+    exit 1
+fi
diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh
index 0c56746e9ce0..6c52ce1b0450 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-fec.sh
@@ -8,16 +8,20 @@ NSIM_NETDEV=$(make_netdev)
 
 set -o pipefail
 
+# Since commit 2b3ddcb35357 ("ethtool: fec: Change the prompt ...")
+# in ethtool CLI the Configured lines start with Supported/Configured.
+configured=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2 | head -1 | cut -d' ' -f1)
+
 # netdevsim starts out with None/None
 s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
-check $? "$s" "Configured FEC encodings: None
+check $? "$s" "$configured FEC encodings: None
 Active FEC encoding: None"
 
 # Test Auto
 $ETHTOOL --set-fec $NSIM_NETDEV encoding auto
 check $?
 s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
-check $? "$s" "Configured FEC encodings: Auto
+check $? "$s" "$configured FEC encodings: Auto
 Active FEC encoding: Off"
 
 # Test case in-sensitivity
@@ -25,7 +29,7 @@ for o in off Off OFF; do
     $ETHTOOL --set-fec $NSIM_NETDEV encoding $o
     check $?
     s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
-    check $? "$s" "Configured FEC encodings: Off
+    check $? "$s" "$configured FEC encodings: Off
 Active FEC encoding: Off"
 done
 
@@ -33,7 +37,7 @@ for o in BaseR baser BAser; do
     $ETHTOOL --set-fec $NSIM_NETDEV encoding $o
     check $?
     s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
-    check $? "$s" "Configured FEC encodings: BaseR
+    check $? "$s" "$configured FEC encodings: BaseR
 Active FEC encoding: BaseR"
 done
 
@@ -41,21 +45,21 @@ for o in llrs rs; do
     $ETHTOOL --set-fec $NSIM_NETDEV encoding $o
     check $?
     s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
-    check $? "$s" "Configured FEC encodings: ${o^^}
+    check $? "$s" "$configured FEC encodings: ${o^^}
 Active FEC encoding: ${o^^}"
 done
 
-# Test mutliple bits
+# Test multiple bits
 $ETHTOOL --set-fec $NSIM_NETDEV encoding rs llrs
 check $?
 s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
-check $? "$s" "Configured FEC encodings: RS LLRS
+check $? "$s" "$configured FEC encodings: RS LLRS
 Active FEC encoding: LLRS"
 
 $ETHTOOL --set-fec $NSIM_NETDEV encoding rs off auto
 check $?
 s=$($ETHTOOL --show-fec $NSIM_NETDEV | tail -2)
-check $? "$s" "Configured FEC encodings: Auto Off RS
+check $? "$s" "$configured FEC encodings: Auto Off RS
 Active FEC encoding: RS"
 
 # Make sure other link modes are rejected
diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-ring.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-ring.sh
deleted file mode 100755
index c969559ffa7a..000000000000
--- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-ring.sh
+++ /dev/null
@@ -1,85 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0-only
-
-source ethtool-common.sh
-
-function get_value {
-    local query="${SETTINGS_MAP[$1]}"
-
-    echo $(ethtool -g $NSIM_NETDEV | \
-        tail -n +$CURR_SETT_LINE | \
-        awk -F':' -v pattern="$query:" '$0 ~ pattern {gsub(/[\t ]/, "", $2); print $2}')
-}
-
-function update_current_settings {
-    for key in ${!SETTINGS_MAP[@]}; do
-        CURRENT_SETTINGS[$key]=$(get_value $key)
-    done
-    echo ${CURRENT_SETTINGS[@]}
-}
-
-if ! ethtool -h | grep -q set-ring >/dev/null; then
-    echo "SKIP: No --set-ring support in ethtool"
-    exit 4
-fi
-
-NSIM_NETDEV=$(make_netdev)
-
-set -o pipefail
-
-declare -A SETTINGS_MAP=(
-    ["rx"]="RX"
-    ["rx-mini"]="RX Mini"
-    ["rx-jumbo"]="RX Jumbo"
-    ["tx"]="TX"
-)
-
-declare -A EXPECTED_SETTINGS=(
-    ["rx"]=""
-    ["rx-mini"]=""
-    ["rx-jumbo"]=""
-    ["tx"]=""
-)
-
-declare -A CURRENT_SETTINGS=(
-    ["rx"]=""
-    ["rx-mini"]=""
-    ["rx-jumbo"]=""
-    ["tx"]=""
-)
-
-MAX_VALUE=$((RANDOM % $((2**32-1))))
-RING_MAX_LIST=$(ls $NSIM_DEV_DFS/ethtool/ring/)
-
-for ring_max_entry in $RING_MAX_LIST; do
-    echo $MAX_VALUE > $NSIM_DEV_DFS/ethtool/ring/$ring_max_entry
-done
-
-CURR_SETT_LINE=$(ethtool -g $NSIM_NETDEV | grep -i -m1 -n 'Current hardware settings' | cut -f1 -d:)
-
-# populate the expected settings map
-for key in ${!SETTINGS_MAP[@]}; do
-    EXPECTED_SETTINGS[$key]=$(get_value $key)
-done
-
-# test
-for key in ${!SETTINGS_MAP[@]}; do
-    value=$((RANDOM % $MAX_VALUE))
-
-    ethtool -G $NSIM_NETDEV "$key" "$value"
-
-    EXPECTED_SETTINGS[$key]="$value"
-    expected=${EXPECTED_SETTINGS[@]}
-    current=$(update_current_settings)
-
-    check $? "$current" "$expected"
-    set +x
-done
-
-if [ $num_errors -eq 0 ]; then
-    echo "PASSED all $((num_passes)) checks"
-    exit 0
-else
-    echo "FAILED $num_errors/$((num_errors+num_passes)) checks"
-    exit 1
-fi
diff --git a/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh b/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh
index 8d91191a098c..9896580c3d85 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh
@@ -94,7 +94,7 @@ route_addition_check()
 	sleep 1
 	$IP route add $route dev dummy1
 	sleep 1
-	kill %% && wait %% &> /dev/null
+	kill_process %%
 
 	route_notify_check $outfile $expected_num_notifications $offload_failed
 	rm -f $outfile
@@ -148,7 +148,7 @@ route_deletion_check()
 	sleep 1
 	$IP route del $route dev dummy1
 	sleep 1
-	kill %% && wait %% &> /dev/null
+	kill_process %%
 
 	route_notify_check $outfile $expected_num_notifications
 	rm -f $outfile
@@ -191,7 +191,7 @@ route_replacement_check()
 	sleep 1
 	$IP route replace $route dev dummy2
 	sleep 1
-	kill %% && wait %% &> /dev/null
+	kill_process %%
 
 	route_notify_check $outfile $expected_num_notifications
 	rm -f $outfile
diff --git a/tools/testing/selftests/drivers/net/netdevsim/macsec-offload.sh b/tools/testing/selftests/drivers/net/netdevsim/macsec-offload.sh
new file mode 100755
index 000000000000..98033e6667d2
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/macsec-offload.sh
@@ -0,0 +1,117 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+
+source ethtool-common.sh
+
+NSIM_NETDEV=$(make_netdev)
+MACSEC_NETDEV=macsec_nsim
+
+set -o pipefail
+
+if ! ethtool -k $NSIM_NETDEV | grep -q 'macsec-hw-offload: on'; then
+    echo "SKIP: netdevsim doesn't support MACsec offload"
+    exit 4
+fi
+
+if ! ip link add link $NSIM_NETDEV $MACSEC_NETDEV type macsec offload mac 2>/dev/null; then
+    echo "SKIP: couldn't create macsec device"
+    exit 4
+fi
+ip link del $MACSEC_NETDEV
+
+#
+# test macsec offload API
+#
+
+ip link add link $NSIM_NETDEV "${MACSEC_NETDEV}" type macsec port 4 offload mac
+check $?
+
+ip link add link $NSIM_NETDEV "${MACSEC_NETDEV}2" type macsec address "aa:bb:cc:dd:ee:ff" port 5 offload mac
+check $?
+
+ip link add link $NSIM_NETDEV "${MACSEC_NETDEV}3" type macsec sci abbacdde01020304 offload mac
+check $?
+
+ip link add link $NSIM_NETDEV "${MACSEC_NETDEV}4" type macsec port 8 offload mac 2> /dev/null
+check $? '' '' 1
+
+ip macsec add "${MACSEC_NETDEV}" tx sa 0 pn 1024 on key 01 12345678901234567890123456789012
+check $?
+
+ip macsec add "${MACSEC_NETDEV}" rx port 1234 address "1c:ed:de:ad:be:ef"
+check $?
+
+ip macsec add "${MACSEC_NETDEV}" rx port 1234 address "1c:ed:de:ad:be:ef" sa 0 pn 1 on \
+    key 00 0123456789abcdef0123456789abcdef
+check $?
+
+ip macsec add "${MACSEC_NETDEV}" rx port 1235 address "1c:ed:de:ad:be:ef" 2> /dev/null
+check $? '' '' 1
+
+# can't disable macsec offload when SAs are configured
+ip link set "${MACSEC_NETDEV}" type macsec offload off 2> /dev/null
+check $? '' '' 1
+
+ip macsec offload "${MACSEC_NETDEV}" off 2> /dev/null
+check $? '' '' 1
+
+# toggle macsec offload via rtnetlink
+ip link set "${MACSEC_NETDEV}2" type macsec offload off
+check $?
+
+ip link set "${MACSEC_NETDEV}2" type macsec offload mac
+check $?
+
+# toggle macsec offload via genetlink
+ip macsec offload "${MACSEC_NETDEV}2" off
+check $?
+
+ip macsec offload "${MACSEC_NETDEV}2" mac
+check $?
+
+for dev in ${MACSEC_NETDEV}{,2,3} ; do
+    ip link del $dev
+    check $?
+done
+
+
+#
+# test ethtool features when toggling offload
+#
+
+ip link add link $NSIM_NETDEV $MACSEC_NETDEV type macsec offload mac
+TMP_FEATS_ON_1="$(ethtool -k $MACSEC_NETDEV)"
+
+ip link set $MACSEC_NETDEV type macsec offload off
+TMP_FEATS_OFF_1="$(ethtool -k $MACSEC_NETDEV)"
+
+ip link set $MACSEC_NETDEV type macsec offload mac
+TMP_FEATS_ON_2="$(ethtool -k $MACSEC_NETDEV)"
+
+[ "$TMP_FEATS_ON_1" = "$TMP_FEATS_ON_2" ]
+check $?
+
+ip link del $MACSEC_NETDEV
+
+ip link add link $NSIM_NETDEV $MACSEC_NETDEV type macsec
+check $?
+
+TMP_FEATS_OFF_2="$(ethtool -k $MACSEC_NETDEV)"
+[ "$TMP_FEATS_OFF_1" = "$TMP_FEATS_OFF_2" ]
+check $?
+
+ip link set $MACSEC_NETDEV type macsec offload mac
+check $?
+
+TMP_FEATS_ON_3="$(ethtool -k $MACSEC_NETDEV)"
+[ "$TMP_FEATS_ON_1" = "$TMP_FEATS_ON_3" ]
+check $?
+
+
+if [ $num_errors -eq 0 ]; then
+    echo "PASSED all $((num_passes)) checks"
+    exit 0
+else
+    echo "FAILED $num_errors/$((num_errors+num_passes)) checks"
+    exit 1
+fi
diff --git a/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh b/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh
index e8e0dc088d6a..01d0c044a5fc 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh
@@ -1053,6 +1053,6 @@ trap cleanup EXIT
 
 setup_prepare
 
-tests_run
+xfail_on_slow tests_run
 
 exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/netdevsim/peer.sh b/tools/testing/selftests/drivers/net/netdevsim/peer.sh
new file mode 100755
index 000000000000..7f32b5600925
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/peer.sh
@@ -0,0 +1,144 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+
+lib_dir=$(dirname $0)/../../../net
+source $lib_dir/lib.sh
+
+NSIM_DEV_1_ID=$((256 + RANDOM % 256))
+NSIM_DEV_1_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_DEV_1_ID
+NSIM_DEV_2_ID=$((512 + RANDOM % 256))
+NSIM_DEV_2_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_DEV_2_ID
+
+NSIM_DEV_SYS_NEW=/sys/bus/netdevsim/new_device
+NSIM_DEV_SYS_DEL=/sys/bus/netdevsim/del_device
+NSIM_DEV_SYS_LINK=/sys/bus/netdevsim/link_device
+NSIM_DEV_SYS_UNLINK=/sys/bus/netdevsim/unlink_device
+
+socat_check()
+{
+	if [ ! -x "$(command -v socat)" ]; then
+		echo "socat command not found. Skipping test"
+		return 1
+	fi
+
+	return 0
+}
+
+setup_ns()
+{
+	set -e
+	ip netns add nssv
+	ip netns add nscl
+
+	NSIM_DEV_1_NAME=$(find $NSIM_DEV_1_SYS/net -maxdepth 1 -type d ! \
+		-path $NSIM_DEV_1_SYS/net -exec basename {} \;)
+	NSIM_DEV_2_NAME=$(find $NSIM_DEV_2_SYS/net -maxdepth 1 -type d ! \
+		-path $NSIM_DEV_2_SYS/net -exec basename {} \;)
+
+	ip link set $NSIM_DEV_1_NAME netns nssv
+	ip link set $NSIM_DEV_2_NAME netns nscl
+
+	ip netns exec nssv ip addr add '192.168.1.1/24' dev $NSIM_DEV_1_NAME
+	ip netns exec nscl ip addr add '192.168.1.2/24' dev $NSIM_DEV_2_NAME
+
+	ip netns exec nssv ip link set dev $NSIM_DEV_1_NAME up
+	ip netns exec nscl ip link set dev $NSIM_DEV_2_NAME up
+	set +e
+}
+
+cleanup_ns()
+{
+	ip netns del nscl
+	ip netns del nssv
+}
+
+###
+### Code start
+###
+
+socat_check || exit 4
+
+modprobe netdevsim
+
+# linking
+
+echo $NSIM_DEV_1_ID > $NSIM_DEV_SYS_NEW
+echo $NSIM_DEV_2_ID > $NSIM_DEV_SYS_NEW
+udevadm settle
+
+setup_ns
+
+NSIM_DEV_1_FD=$((256 + RANDOM % 256))
+exec {NSIM_DEV_1_FD}</var/run/netns/nssv
+NSIM_DEV_1_IFIDX=$(ip netns exec nssv cat /sys/class/net/$NSIM_DEV_1_NAME/ifindex)
+
+NSIM_DEV_2_FD=$((256 + RANDOM % 256))
+exec {NSIM_DEV_2_FD}</var/run/netns/nscl
+NSIM_DEV_2_IFIDX=$(ip netns exec nscl cat /sys/class/net/$NSIM_DEV_2_NAME/ifindex)
+
+echo "$NSIM_DEV_1_FD:$NSIM_DEV_1_IFIDX $NSIM_DEV_2_FD:2000" > $NSIM_DEV_SYS_LINK 2>/dev/null
+if [ $? -eq 0 ]; then
+	echo "linking with non-existent netdevsim should fail"
+	cleanup_ns
+	exit 1
+fi
+
+echo "$NSIM_DEV_1_FD:$NSIM_DEV_1_IFIDX 2000:$NSIM_DEV_2_IFIDX" > $NSIM_DEV_SYS_LINK 2>/dev/null
+if [ $? -eq 0 ]; then
+	echo "linking with non-existent netnsid should fail"
+	cleanup_ns
+	exit 1
+fi
+
+echo "$NSIM_DEV_1_FD:$NSIM_DEV_1_IFIDX $NSIM_DEV_1_FD:$NSIM_DEV_1_IFIDX" > $NSIM_DEV_SYS_LINK 2>/dev/null
+if [ $? -eq 0 ]; then
+	echo "linking with self should fail"
+	cleanup_ns
+	exit 1
+fi
+
+echo "$NSIM_DEV_1_FD:$NSIM_DEV_1_IFIDX $NSIM_DEV_2_FD:$NSIM_DEV_2_IFIDX" > $NSIM_DEV_SYS_LINK
+if [ $? -ne 0 ]; then
+	echo "linking netdevsim1 with netdevsim2 should succeed"
+	cleanup_ns
+	exit 1
+fi
+
+# argument error checking
+
+echo "$NSIM_DEV_1_FD:$NSIM_DEV_1_IFIDX $NSIM_DEV_2_FD:a" > $NSIM_DEV_SYS_LINK 2>/dev/null
+if [ $? -eq 0 ]; then
+	echo "invalid arg should fail"
+	cleanup_ns
+	exit 1
+fi
+
+# send/recv packets
+
+tmp_file=$(mktemp)
+ip netns exec nssv socat TCP-LISTEN:1234,fork $tmp_file &
+pid=$!
+res=0
+
+wait_local_port_listen nssv 1234 tcp
+
+echo "HI" | ip netns exec nscl socat STDIN TCP:192.168.1.1:1234
+
+count=$(cat $tmp_file | wc -c)
+if [[ $count -ne 3 ]]; then
+	echo "expected 3 bytes, got $count"
+	res=1
+fi
+
+echo "$NSIM_DEV_1_FD:$NSIM_DEV_1_IFIDX" > $NSIM_DEV_SYS_UNLINK
+
+echo $NSIM_DEV_2_ID > $NSIM_DEV_SYS_DEL
+
+kill $pid
+echo $NSIM_DEV_1_ID > $NSIM_DEV_SYS_DEL
+
+cleanup_ns
+
+modprobe -r netdevsim
+
+exit $res
diff --git a/tools/testing/selftests/drivers/net/netdevsim/settings b/tools/testing/selftests/drivers/net/netdevsim/settings
new file mode 100644
index 000000000000..a62d2fa1275c
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/settings
@@ -0,0 +1 @@
+timeout=600
diff --git a/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh b/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh
index fd13c8cfb7a8..b411fe66510f 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh
@@ -58,9 +58,12 @@ for root in mq mqprio; do
     ethtool -L $NDEV combined 4
     n_child_assert 4 "One real queue, rest default"
 
-    # Graft some
-    tcq replace parent 100:1 handle 204:
-    n_child_assert 3 "Grafted"
+    # Remove real one
+    tcq del parent 100:4 handle 204:
+
+    # Replace default with pfifo
+    tcq replace parent 100:1 handle 205: pfifo limit 1000
+    n_child_assert 3 "Deleting real one, replacing default one with pfifo"
 
     ethtool -L $NDEV combined 1
     n_child_assert 1 "Grafted, one"
diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh
index 1b08e042cf94..4c859ecdad94 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh
@@ -142,7 +142,7 @@ function pre_ethtool {
 }
 
 function check_table {
-    local path=$NSIM_DEV_DFS/ports/$port/udp_ports_table$1
+    local path=$NSIM_DEV_DFS/ports/$port/udp_ports/table$1
     local -n expected=$2
     local last=$3
 
@@ -212,7 +212,7 @@ function check_tables {
 }
 
 function print_table {
-    local path=$NSIM_DEV_DFS/ports/$port/udp_ports_table$1
+    local path=$NSIM_DEV_DFS/ports/$port/udp_ports/table$1
     read -a have < $path
 
     tree $NSIM_DEV_DFS/
@@ -233,6 +233,7 @@ function print_tables {
 function get_netdev_name {
     local -n old=$1
 
+    udevadm settle
     new=$(ls /sys/class/net)
 
     for netdev in $new; do
@@ -265,10 +266,10 @@ for port in 0 1; do
 	echo $NSIM_ID > /sys/bus/netdevsim/new_device
     else
 	echo 1 > $NSIM_DEV_DFS/udp_ports_open_only
-	echo 1 > $NSIM_DEV_DFS/udp_ports_sleep
 	echo 1 > $NSIM_DEV_SYS/new_port
     fi
     NSIM_NETDEV=`get_netdev_name old_netdevs`
+    ip link set dev $NSIM_NETDEV up
 
     msg="new NIC device created"
     exp0=( 0 0 0 0 )
@@ -282,8 +283,8 @@ for port in 0 1; do
 
     msg="VxLAN v4 devices go down"
     exp0=( 0 0 0 0 )
-    ifconfig vxlan1 down
-    ifconfig vxlan0 down
+    ip link set dev vxlan1 down
+    ip link set dev vxlan0 down
     check_tables
 
     msg="VxLAN v6 devices"
@@ -291,7 +292,7 @@ for port in 0 1; do
     new_vxlan vxlanA 4789 $NSIM_NETDEV 6
 
     for ifc in vxlan0 vxlan1; do
-	ifconfig $ifc up
+	ip link set dev $ifc up
     done
 
     new_vxlan vxlanB 4789 $NSIM_NETDEV 6
@@ -305,14 +306,14 @@ for port in 0 1; do
     new_geneve gnv0 6081
 
     msg="NIC device goes down"
-    ifconfig $NSIM_NETDEV down
+    ip link set dev $NSIM_NETDEV down
     if [ $port -eq 1 ]; then
 	exp0=( 0 0 0 0 )
 	exp1=( 0 0 0 0 )
     fi
     check_tables
     msg="NIC device goes up again"
-    ifconfig $NSIM_NETDEV up
+    ip link set dev $NSIM_NETDEV up
     exp0=( `mke 4789 1` `mke 4790 1` 0 0 )
     exp1=( `mke 6081 2` 0 0 0 )
     check_tables
@@ -348,23 +349,11 @@ old_netdevs=$(ls /sys/class/net)
 port=0
 echo $NSIM_ID > /sys/bus/netdevsim/new_device
 echo 0 > $NSIM_DEV_SYS/del_port
-echo 1000 > $NSIM_DEV_DFS/udp_ports_sleep
 echo 0 > $NSIM_DEV_SYS/new_port
 NSIM_NETDEV=`get_netdev_name old_netdevs`
 
 msg="create VxLANs"
-exp0=( 0 0 0 0 ) # sleep is longer than out wait
-new_vxlan vxlan0 10000 $NSIM_NETDEV
-
-modprobe -r vxlan
-modprobe -r udp_tunnel
-
-msg="remove tunnels"
-exp0=( 0 0 0 0 )
-check_tables
-
-msg="create VxLANs"
-exp0=( 0 0 0 0 ) # sleep is longer than out wait
+exp0=( `mke 10000 1` 0 0 0 )
 new_vxlan vxlan0 10000 $NSIM_NETDEV
 
 exp0=( 0 0 0 0 )
@@ -426,11 +415,11 @@ echo 0 > $NSIM_DEV_SYS/del_port
 for port in 0 1; do
     if [ $port -ne 0 ]; then
 	echo 1 > $NSIM_DEV_DFS/udp_ports_open_only
-	echo 1 > $NSIM_DEV_DFS/udp_ports_sleep
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
-    ifconfig $NSIM_NETDEV up
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
+    ip link set dev $NSIM_NETDEV up
 
     overflow_table0 "overflow NIC table"
     overflow_table1 "overflow NIC table"
@@ -483,11 +472,11 @@ echo 1 > $NSIM_DEV_DFS/udp_ports_sync_all
 for port in 0 1; do
     if [ $port -ne 0 ]; then
 	echo 1 > $NSIM_DEV_DFS/udp_ports_open_only
-	echo 1 > $NSIM_DEV_DFS/udp_ports_sleep
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
-    ifconfig $NSIM_NETDEV up
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
+    ip link set dev $NSIM_NETDEV up
 
     overflow_table0 "overflow NIC table"
     overflow_table1 "overflow NIC table"
@@ -539,11 +528,11 @@ echo 0 > $NSIM_DEV_SYS/del_port
 for port in 0 1; do
     if [ $port -ne 0 ]; then
 	echo 1 > $NSIM_DEV_DFS/udp_ports_open_only
-	echo 1 > $NSIM_DEV_DFS/udp_ports_sleep
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
-    ifconfig $NSIM_NETDEV up
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
+    ip link set dev $NSIM_NETDEV up
 
     overflow_table0 "destroy NIC"
     overflow_table1 "destroy NIC"
@@ -568,11 +557,11 @@ echo 1 > $NSIM_DEV_DFS/udp_ports_ipv4_only
 for port in 0 1; do
     if [ $port -ne 0 ]; then
 	echo 1 > $NSIM_DEV_DFS/udp_ports_open_only
-	echo 1 > $NSIM_DEV_DFS/udp_ports_sleep
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
-    ifconfig $NSIM_NETDEV up
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
+    ip link set dev $NSIM_NETDEV up
 
     msg="create VxLANs v6"
     new_vxlan vxlanA0 10000 $NSIM_NETDEV 6
@@ -628,13 +617,13 @@ echo 0 > $NSIM_DEV_SYS/del_port
 for port in 0 1; do
     if [ $port -ne 0 ]; then
 	echo 1 > $NSIM_DEV_DFS/udp_ports_open_only
-	echo 1 > $NSIM_DEV_DFS/udp_ports_sleep
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
-    ifconfig $NSIM_NETDEV up
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
+    ip link set dev $NSIM_NETDEV up
 
-    echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error
+    echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports/inject_error
 
     msg="1 - create VxLANs v6"
     exp0=( 0 0 0 0 )
@@ -656,7 +645,7 @@ for port in 0 1; do
     new_geneve gnv0 20000
 
     msg="2 - destroy GENEVE"
-    echo 2 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error
+    echo 2 > $NSIM_DEV_DFS/ports/$port/udp_ports/inject_error
     exp1=( `mke 20000 2` 0 0 0 )
     del_dev gnv0
 
@@ -683,11 +672,11 @@ echo 0 > $NSIM_DEV_SYS/del_port
 for port in 0 1; do
     if [ $port -ne 0 ]; then
 	echo 1 > $NSIM_DEV_DFS/udp_ports_open_only
-	echo 1 > $NSIM_DEV_DFS/udp_ports_sleep
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
-    ifconfig $NSIM_NETDEV up
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
+    ip link set dev $NSIM_NETDEV up
 
     msg="create VxLANs v6"
     exp0=( `mke 10000 1` 0 0 0 )
@@ -742,11 +731,11 @@ echo 0 > $NSIM_DEV_SYS/del_port
 for port in 0 1; do
     if [ $port -ne 0 ]; then
 	echo 1 > $NSIM_DEV_DFS/udp_ports_open_only
-	echo 1 > $NSIM_DEV_DFS/udp_ports_sleep
     fi
 
     echo $port > $NSIM_DEV_SYS/new_port
-    ifconfig $NSIM_NETDEV up
+    NSIM_NETDEV=`get_netdev_name old_netdevs`
+    ip link set dev $NSIM_NETDEV up
 
     msg="create VxLANs v6"
     exp0=( `mke 10000 1` 0 0 0 )
@@ -755,22 +744,22 @@ for port in 0 1; do
     msg="create VxLANs v4"
     new_vxlan vxlan0 10000 $NSIM_NETDEV
 
-    echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset
+    echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset
     check_tables
 
     msg="NIC device goes down"
-    ifconfig $NSIM_NETDEV down
+    ip link set dev $NSIM_NETDEV down
     if [ $port -eq 1 ]; then
 	exp0=( 0 0 0 0 )
 	exp1=( 0 0 0 0 )
     fi
     check_tables
 
-    echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset
+    echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset
     check_tables
 
     msg="NIC device goes up again"
-    ifconfig $NSIM_NETDEV up
+    ip link set dev $NSIM_NETDEV up
     exp0=( `mke 10000 1` 0 0 0 )
     check_tables
 
@@ -780,7 +769,7 @@ for port in 0 1; do
     del_dev vxlan0
     check_tables
 
-    echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset
+    echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset
     check_tables
 
     msg="destroy NIC"
@@ -800,7 +789,6 @@ echo $NSIM_ID > /sys/bus/netdevsim/new_device
 echo 0 > $NSIM_DEV_SYS/del_port
 
 echo 0 > $NSIM_DEV_DFS/udp_ports_open_only
-echo 1 > $NSIM_DEV_DFS/udp_ports_sleep
 echo 1 > $NSIM_DEV_DFS/udp_ports_shared
 
 old_netdevs=$(ls /sys/class/net)
@@ -818,12 +806,12 @@ new_vxlan vxlan1 4789 $NSIM_NETDEV2
 
 msg="VxLAN v4 devices go down"
 exp0=( 0 0 0 0 )
-ifconfig vxlan1 down
-ifconfig vxlan0 down
+ip link set dev vxlan1 down
+ip link set dev vxlan0 down
 check_tables
 
 for ifc in vxlan0 vxlan1; do
-    ifconfig $ifc up
+    ip link set dev $ifc up
 done
 
 msg="VxLAN v6 device"
@@ -835,11 +823,11 @@ exp1=( `mke 6081 2` 0 0 0 )
 new_geneve gnv0 6081
 
 msg="NIC device goes down"
-ifconfig $NSIM_NETDEV down
+ip link set dev $NSIM_NETDEV down
 check_tables
 
 msg="NIC device goes up again"
-ifconfig $NSIM_NETDEV up
+ip link set dev $NSIM_NETDEV up
 check_tables
 
 for i in `seq 2`; do
@@ -876,6 +864,7 @@ msg="re-add a port"
 
 echo 2 > $NSIM_DEV_SYS/del_port
 echo 2 > $NSIM_DEV_SYS/new_port
+NSIM_NETDEV=`get_netdev_name old_netdevs`
 check_tables
 
 msg="replace VxLAN in overflow table"
@@ -886,7 +875,7 @@ msg="vacate VxLAN in overflow table"
 exp0=( `mke 10000 1` `mke 10004 1` 0 `mke 10003 1` )
 del_dev vxlan2
 
-echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset
+echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset
 check_tables
 
 msg="tunnels destroyed 2"
diff --git a/tools/testing/selftests/drivers/net/netpoll_basic.py b/tools/testing/selftests/drivers/net/netpoll_basic.py
new file mode 100755
index 000000000000..408bd54d6779
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netpoll_basic.py
@@ -0,0 +1,396 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+# Author: Breno Leitao <leitao@debian.org>
+"""
+ This test aims to evaluate the netpoll polling mechanism (as in
+ netpoll_poll_dev()). It presents a complex scenario where the network
+ attempts to send a packet but fails, prompting it to poll the NIC from within
+ the netpoll TX side.
+
+ This has been a crucial path in netpoll that was previously untested. Jakub
+ suggested using a single RX/TX queue, pushing traffic to the NIC, and then
+ sending netpoll messages (via netconsole) to trigger the poll.
+
+ In parallel, bpftrace is used to detect if netpoll_poll_dev() was called. If
+ so, the test passes, otherwise it will be skipped. This test is very dependent on
+ the driver and environment, given we are trying to trigger a tricky scenario.
+"""
+
+import errno
+import logging
+import os
+import random
+import string
+import threading
+import time
+from typing import Optional
+
+from lib.py import (
+    bpftrace,
+    CmdExitFailure,
+    defer,
+    ethtool,
+    GenerateTraffic,
+    ksft_exit,
+    ksft_pr,
+    ksft_run,
+    KsftFailEx,
+    KsftSkipEx,
+    NetDrvEpEnv,
+    KsftXfailEx,
+)
+
+# Configure logging
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s - %(levelname)s - %(message)s",
+)
+
+NETCONSOLE_CONFIGFS_PATH: str = "/sys/kernel/config/netconsole"
+NETCONS_REMOTE_PORT: int = 6666
+NETCONS_LOCAL_PORT: int = 1514
+
+# Max number of netcons messages to send. Each iteration will setup
+# netconsole and send MAX_WRITES messages
+ITERATIONS: int = 20
+# Number of writes to /dev/kmsg per iteration
+MAX_WRITES: int = 40
+# MAPS contains the information coming from bpftrace it will have only one
+# key: "hits", which tells the number of times netpoll_poll_dev() was called
+MAPS: dict[str, int] = {}
+# Thread to run bpftrace in parallel
+BPF_THREAD: Optional[threading.Thread] = None
+# Time bpftrace will be running in parallel.
+BPFTRACE_TIMEOUT: int = 10
+
+
+def ethtool_get_ringsize(interface_name: str) -> tuple[int, int]:
+    """
+    Read the ringsize using ethtool. This will be used to restore it after the test
+    """
+    try:
+        ethtool_result = ethtool(f"-g {interface_name}", json=True)[0]
+        rxs = ethtool_result["rx"]
+        txs = ethtool_result["tx"]
+    except (KeyError, IndexError) as exception:
+        raise KsftSkipEx(
+            f"Failed to read RX/TX ringsize: {exception}. Not going to mess with them."
+        ) from exception
+
+    return rxs, txs
+
+
+def ethtool_set_ringsize(interface_name: str, ring_size: tuple[int, int]) -> bool:
+    """Try to the number of RX and TX ringsize."""
+    rxs = ring_size[0]
+    txs = ring_size[1]
+
+    logging.debug("Setting ring size to %d/%d", rxs, txs)
+    try:
+        ethtool(f"-G {interface_name} rx {rxs} tx {txs}")
+    except CmdExitFailure:
+        # This might fail on real device, retry with a higher value,
+        # worst case, keep it as it is.
+        return False
+
+    return True
+
+
+def ethtool_get_queues_cnt(interface_name: str) -> tuple[int, int, int]:
+    """Read the number of RX, TX and combined queues using ethtool"""
+
+    try:
+        ethtool_result = ethtool(f"-l {interface_name}", json=True)[0]
+        rxq = ethtool_result.get("rx", -1)
+        txq = ethtool_result.get("tx", -1)
+        combined = ethtool_result.get("combined", -1)
+
+    except IndexError as exception:
+        raise KsftSkipEx(
+            f"Failed to read queues numbers: {exception}. Not going to mess with them."
+        ) from exception
+
+    return rxq, txq, combined
+
+
+def ethtool_set_queues_cnt(interface_name: str, queues: tuple[int, int, int]) -> None:
+    """Set the number of RX, TX and combined queues using ethtool"""
+    rxq, txq, combined = queues
+
+    cmdline = f"-L {interface_name}"
+
+    if rxq != -1:
+        cmdline += f" rx {rxq}"
+    if txq != -1:
+        cmdline += f" tx {txq}"
+    if combined != -1:
+        cmdline += f" combined {combined}"
+
+    logging.debug("calling: ethtool %s", cmdline)
+
+    try:
+        ethtool(cmdline)
+    except CmdExitFailure as exception:
+        raise KsftSkipEx(
+            f"Failed to configure RX/TX queues: {exception}. Ethtool not available?"
+        ) from exception
+
+
+def netcons_generate_random_target_name() -> str:
+    """Generate a random target name starting with 'netcons'"""
+    random_suffix = "".join(random.choices(string.ascii_lowercase + string.digits, k=8))
+    return f"netcons_{random_suffix}"
+
+
+def netcons_create_target(
+    config_data: dict[str, str],
+    target_name: str,
+) -> None:
+    """Create a netconsole dynamic target against the interfaces"""
+    logging.debug("Using netconsole name: %s", target_name)
+    try:
+        os.makedirs(f"{NETCONSOLE_CONFIGFS_PATH}/{target_name}", exist_ok=True)
+        logging.debug(
+            "Created target directory: %s/%s", NETCONSOLE_CONFIGFS_PATH, target_name
+        )
+    except OSError as exception:
+        if exception.errno != errno.EEXIST:
+            raise KsftFailEx(
+                f"Failed to create netconsole target directory: {exception}"
+            ) from exception
+
+    try:
+        for key, value in config_data.items():
+            path = f"{NETCONSOLE_CONFIGFS_PATH}/{target_name}/{key}"
+            logging.debug("Writing %s to %s", key, path)
+            with open(path, "w", encoding="utf-8") as file:
+                # Always convert to string to write to file
+                file.write(str(value))
+
+        # Read all configuration values for debugging purposes
+        for debug_key in config_data.keys():
+            with open(
+                f"{NETCONSOLE_CONFIGFS_PATH}/{target_name}/{debug_key}",
+                "r",
+                encoding="utf-8",
+            ) as file:
+                content = file.read()
+                logging.debug(
+                    "%s/%s/%s : %s",
+                    NETCONSOLE_CONFIGFS_PATH,
+                    target_name,
+                    debug_key,
+                    content.strip(),
+                )
+
+    except Exception as exception:
+        raise KsftFailEx(
+            f"Failed to configure netconsole target: {exception}"
+        ) from exception
+
+
+def netcons_configure_target(
+    cfg: NetDrvEpEnv, interface_name: str, target_name: str
+) -> None:
+    """Configure netconsole on the interface with the given target name"""
+    config_data = {
+        "extended": "1",
+        "dev_name": interface_name,
+        "local_port": NETCONS_LOCAL_PORT,
+        "remote_port": NETCONS_REMOTE_PORT,
+        "local_ip": cfg.addr,
+        "remote_ip": cfg.remote_addr,
+        "remote_mac": "00:00:00:00:00:00",  # Not important for this test
+        "enabled": "1",
+    }
+
+    netcons_create_target(config_data, target_name)
+    logging.debug(
+        "Created netconsole target: %s on interface %s", target_name, interface_name
+    )
+
+
+def netcons_delete_target(name: str) -> None:
+    """Delete a netconsole dynamic target"""
+    target_path = f"{NETCONSOLE_CONFIGFS_PATH}/{name}"
+    try:
+        if os.path.exists(target_path):
+            os.rmdir(target_path)
+    except OSError as exception:
+        raise KsftFailEx(
+            f"Failed to delete netconsole target: {exception}"
+        ) from exception
+
+
+def netcons_load_module() -> None:
+    """Try to load the netconsole module"""
+    os.system("modprobe netconsole")
+
+
+def bpftrace_call() -> None:
+    """Call bpftrace to find how many times netpoll_poll_dev() is called.
+    Output is saved in the global variable `maps`"""
+
+    # This is going to update the global variable, that will be seen by the
+    # main function
+    global MAPS  # pylint: disable=W0603
+
+    # This will be passed to bpftrace as in bpftrace -e "expr"
+    expr = "kprobe:netpoll_poll_dev { @hits = count(); }"
+
+    MAPS = bpftrace(expr, timeout=BPFTRACE_TIMEOUT, json=True)
+    logging.debug("BPFtrace output: %s", MAPS)
+
+
+def bpftrace_start():
+    """Start a thread to call `call_bpf` in a parallel thread"""
+    global BPF_THREAD  # pylint: disable=W0603
+
+    BPF_THREAD = threading.Thread(target=bpftrace_call)
+    BPF_THREAD.start()
+    if not BPF_THREAD.is_alive():
+        raise KsftSkipEx("BPFtrace thread is not alive. Skipping test")
+
+
+def bpftrace_stop() -> None:
+    """Stop the bpftrace thread"""
+    if BPF_THREAD:
+        BPF_THREAD.join()
+
+
+def bpftrace_any_hit(join: bool) -> bool:
+    """Check if netpoll_poll_dev() was called by checking the global variable `maps`"""
+    if not BPF_THREAD:
+        raise KsftFailEx("BPFtrace didn't start")
+
+    if BPF_THREAD.is_alive():
+        if join:
+            # Wait for bpftrace to finish
+            BPF_THREAD.join()
+        else:
+            # bpftrace is still running, so, we will not check the result yet
+            return False
+
+    logging.debug("MAPS coming from bpftrace = %s", MAPS)
+    if "hits" not in MAPS.keys():
+        raise KsftFailEx(f"bpftrace failed to run!?: {MAPS}")
+
+    logging.debug("Got a total of %d hits", MAPS["hits"])
+    return MAPS["hits"] > 0
+
+
+def do_netpoll_flush_monitored(cfg: NetDrvEpEnv, ifname: str, target_name: str) -> None:
+    """Print messages to the console, trying to trigger a netpoll poll"""
+    # Start bpftrace in parallel, so, it is watching
+    # netpoll_poll_dev() while we are sending netconsole messages
+    bpftrace_start()
+    defer(bpftrace_stop)
+
+    do_netpoll_flush(cfg, ifname, target_name)
+
+    if bpftrace_any_hit(join=True):
+        ksft_pr("netpoll_poll_dev() was called. Success")
+        return
+
+    raise KsftXfailEx("netpoll_poll_dev() was not called during the test...")
+
+
+def do_netpoll_flush(cfg: NetDrvEpEnv, ifname: str, target_name: str) -> None:
+    """Print messages to the console, trying to trigger a netpoll poll"""
+    netcons_configure_target(cfg, ifname, target_name)
+    retry = 0
+
+    for i in range(int(ITERATIONS)):
+        if not BPF_THREAD.is_alive() or bpftrace_any_hit(join=False):
+            # bpftrace is done, stop sending messages
+            break
+
+        msg = f"netcons test #{i}"
+        with open("/dev/kmsg", "w", encoding="utf-8") as kmsg:
+            for j in range(MAX_WRITES):
+                try:
+                    kmsg.write(f"{msg}-{j}\n")
+                except OSError as exception:
+                    # in some cases, kmsg can be busy, so, we will retry
+                    time.sleep(1)
+                    retry += 1
+                    if retry < 5:
+                        logging.info("Failed to write to kmsg. Retrying")
+                        # Just retry a few times
+                        continue
+                    raise KsftFailEx(
+                        f"Failed to write to kmsg: {exception}"
+                    ) from exception
+
+        netcons_delete_target(target_name)
+        netcons_configure_target(cfg, ifname, target_name)
+        # If we sleep here, we will have a better chance of triggering
+        # This number is based on a few tests I ran while developing this test
+        time.sleep(0.4)
+
+
+def configure_network(ifname: str) -> None:
+    """Configure ring size and queue numbers"""
+
+    # Set defined queues to 1 to force congestion
+    prev_queues = ethtool_get_queues_cnt(ifname)
+    logging.debug("RX/TX/combined queues: %s", prev_queues)
+    # Only set the queues to 1 if they exists in the device. I.e, they are > 0
+    ethtool_set_queues_cnt(ifname, tuple(1 if x > 0 else x for x in prev_queues))
+    defer(ethtool_set_queues_cnt, ifname, prev_queues)
+
+    # Try to set the ring size to some low value.
+    # Do not fail if the hardware do not accepted desired values
+    prev_ring_size = ethtool_get_ringsize(ifname)
+    for size in [(1, 1), (128, 128), (256, 256)]:
+        if ethtool_set_ringsize(ifname, size):
+            # hardware accepted the desired ringsize
+            logging.debug("Set RX/TX ringsize to: %s from %s", size, prev_ring_size)
+            break
+    defer(ethtool_set_ringsize, ifname, prev_ring_size)
+
+
+def test_netpoll(cfg: NetDrvEpEnv) -> None:
+    """
+    Test netpoll by sending traffic to the interface and then sending
+    netconsole messages to trigger a poll
+    """
+
+    ifname = cfg.ifname
+    configure_network(ifname)
+    target_name = netcons_generate_random_target_name()
+    traffic = None
+
+    try:
+        traffic = GenerateTraffic(cfg)
+        do_netpoll_flush_monitored(cfg, ifname, target_name)
+    finally:
+        if traffic:
+            traffic.stop()
+
+        # Revert RX/TX queues
+        netcons_delete_target(target_name)
+
+
+def test_check_dependencies() -> None:
+    """Check if the dependencies are met"""
+    if not os.path.exists(NETCONSOLE_CONFIGFS_PATH):
+        raise KsftSkipEx(
+            f"Directory {NETCONSOLE_CONFIGFS_PATH} does not exist. CONFIG_NETCONSOLE_DYNAMIC might not be set."  # pylint: disable=C0301
+        )
+
+
+def main() -> None:
+    """Main function to run the test"""
+    netcons_load_module()
+    test_check_dependencies()
+    with NetDrvEpEnv(__file__) as cfg:
+        ksft_run(
+            [test_netpoll],
+            args=(cfg,),
+        )
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/ocelot/psfp.sh b/tools/testing/selftests/drivers/net/ocelot/psfp.sh
index bed748dde4b0..8972f42dfe03 100755
--- a/tools/testing/selftests/drivers/net/ocelot/psfp.sh
+++ b/tools/testing/selftests/drivers/net/ocelot/psfp.sh
@@ -266,18 +266,14 @@ run_test()
 		"${base_time}" \
 		"${CYCLE_TIME_NS}" \
 		"${SHIFT_TIME_NS}" \
+		"${GATE_DURATION_NS}" \
 		"${NUM_PKTS}" \
 		"${STREAM_VID}" \
 		"${STREAM_PRIO}" \
 		"" \
 		"${isochron_dat}"
 
-	# Count all received packets by looking at the non-zero RX timestamps
-	received=$(isochron report \
-		--input-file "${isochron_dat}" \
-		--printf-format "%u\n" --printf-args "R" | \
-		grep -w -v '0' | wc -l)
-
+	received=$(isochron_report_num_received "${isochron_dat}")
 	if [ "${received}" = "${expected}" ]; then
 		RET=0
 	else
diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
index 9c79bbcce5a8..aff0a59f92d9 100755
--- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
+++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
@@ -246,7 +246,7 @@ test_vlan_ingress_modify()
 	bridge vlan add dev $swp2 vid 300
 
 	tc filter add dev $swp1 ingress chain $(IS1 2) pref 3 \
-		protocol 802.1Q flower skip_sw vlan_id 200 \
+		protocol 802.1Q flower skip_sw vlan_id 200 src_mac $h1_mac \
 		action vlan modify id 300 \
 		action goto chain $(IS2 0 0)
 
diff --git a/tools/testing/selftests/drivers/net/ping.py b/tools/testing/selftests/drivers/net/ping.py
new file mode 100755
index 000000000000..da3623c5e8a9
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/ping.py
@@ -0,0 +1,241 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import os
+import random, string, time
+from lib.py import ksft_run, ksft_exit
+from lib.py import ksft_eq, KsftSkipEx, KsftFailEx
+from lib.py import EthtoolFamily, NetDrvEpEnv
+from lib.py import bkg, cmd, wait_port_listen, rand_port
+from lib.py import defer, ethtool, ip
+
+no_sleep=False
+
+def _test_v4(cfg) -> None:
+    if not cfg.addr_v["4"]:
+        return
+
+    cmd("ping -c 1 -W0.5 " + cfg.remote_addr_v["4"])
+    cmd("ping -c 1 -W0.5 " + cfg.addr_v["4"], host=cfg.remote)
+    cmd("ping -s 65000 -c 1 -W0.5 " + cfg.remote_addr_v["4"])
+    cmd("ping -s 65000 -c 1 -W0.5 " + cfg.addr_v["4"], host=cfg.remote)
+
+def _test_v6(cfg) -> None:
+    if not cfg.addr_v["6"]:
+        return
+
+    cmd("ping -c 1 -W5 " + cfg.remote_addr_v["6"])
+    cmd("ping -c 1 -W5 " + cfg.addr_v["6"], host=cfg.remote)
+    cmd("ping -s 65000 -c 1 -W0.5 " + cfg.remote_addr_v["6"])
+    cmd("ping -s 65000 -c 1 -W0.5 " + cfg.addr_v["6"], host=cfg.remote)
+
+def _test_tcp(cfg) -> None:
+    cfg.require_cmd("socat", local=False, remote=True)
+
+    port = rand_port()
+    listen_cmd = f"socat -{cfg.addr_ipver} -t 2 -u TCP-LISTEN:{port},reuseport STDOUT"
+
+    test_string = ''.join(random.choice(string.ascii_lowercase) for _ in range(65536))
+    with bkg(listen_cmd, exit_wait=True) as nc:
+        wait_port_listen(port)
+
+        cmd(f"echo {test_string} | socat -t 2 -u STDIN TCP:{cfg.baddr}:{port}",
+            shell=True, host=cfg.remote)
+    ksft_eq(nc.stdout.strip(), test_string)
+
+    test_string = ''.join(random.choice(string.ascii_lowercase) for _ in range(65536))
+    with bkg(listen_cmd, host=cfg.remote, exit_wait=True) as nc:
+        wait_port_listen(port, host=cfg.remote)
+
+        cmd(f"echo {test_string} | socat -t 2 -u STDIN TCP:{cfg.remote_baddr}:{port}", shell=True)
+    ksft_eq(nc.stdout.strip(), test_string)
+
+def _schedule_checksum_reset(cfg, netnl) -> None:
+    features = ethtool(f"-k {cfg.ifname}", json=True)
+    setting = ""
+    for side in ["tx", "rx"]:
+        f = features[0][side + "-checksumming"]
+        if not f["fixed"]:
+            setting += " " + side
+            setting += " " + ("on" if f["requested"] or f["active"] else "off")
+    defer(ethtool, f" -K {cfg.ifname} " + setting)
+
+def _set_offload_checksum(cfg, netnl, on) -> None:
+    try:
+        ethtool(f" -K {cfg.ifname} rx {on} tx {on} ")
+    except:
+        return
+
+def _set_xdp_generic_sb_on(cfg) -> None:
+    prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
+    cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+    cmd(f"ip link set dev {cfg.ifname} mtu 1500 xdpgeneric obj {prog} sec xdp", shell=True)
+    defer(cmd, f"ip link set dev {cfg.ifname} xdpgeneric off")
+
+    if no_sleep != True:
+        time.sleep(10)
+
+def _set_xdp_generic_mb_on(cfg) -> None:
+    prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
+    cmd(f"ip link set dev {cfg.remote_ifname} mtu 9000", shell=True, host=cfg.remote)
+    defer(ip, f"link set dev {cfg.remote_ifname} mtu 1500", host=cfg.remote)
+    ip("link set dev %s mtu 9000 xdpgeneric obj %s sec xdp.frags" % (cfg.ifname, prog))
+    defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdpgeneric off")
+
+    if no_sleep != True:
+        time.sleep(10)
+
+def _set_xdp_native_sb_on(cfg) -> None:
+    prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
+    cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+    cmd(f"ip -j link set dev {cfg.ifname} mtu 1500 xdp obj {prog} sec xdp", shell=True)
+    defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off")
+    xdp_info = ip("-d link show %s" % (cfg.ifname), json=True)[0]
+    if xdp_info['xdp']['mode'] != 1:
+        """
+        If the interface doesn't support native-mode, it falls back to generic mode.
+        The mode value 1 is native and 2 is generic.
+        So it raises an exception if mode is not 1(native mode).
+        """
+        raise KsftSkipEx('device does not support native-XDP')
+
+    if no_sleep != True:
+        time.sleep(10)
+
+def _set_xdp_native_mb_on(cfg) -> None:
+    prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
+    cmd(f"ip link set dev {cfg.remote_ifname} mtu 9000", shell=True, host=cfg.remote)
+    defer(ip, f"link set dev {cfg.remote_ifname} mtu 1500", host=cfg.remote)
+    try:
+        cmd(f"ip link set dev {cfg.ifname} mtu 9000 xdp obj {prog} sec xdp.frags", shell=True)
+        defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off")
+    except Exception as e:
+        raise KsftSkipEx('device does not support native-multi-buffer XDP')
+
+    if no_sleep != True:
+        time.sleep(10)
+
+def _set_xdp_offload_on(cfg) -> None:
+    prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
+    cmd(f"ip link set dev {cfg.ifname} mtu 1500", shell=True)
+    try:
+        cmd(f"ip link set dev {cfg.ifname} xdpoffload obj {prog} sec xdp", shell=True)
+    except Exception as e:
+        raise KsftSkipEx('device does not support offloaded XDP')
+    defer(ip, f"link set dev {cfg.ifname} xdpoffload off")
+    cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+
+    if no_sleep != True:
+        time.sleep(10)
+
+def get_interface_info(cfg) -> None:
+    global no_sleep
+
+    if cfg.remote_ifname == "":
+        raise KsftFailEx('Can not get remote interface')
+    local_info = ip("-d link show %s" % (cfg.ifname), json=True)[0]
+    if 'parentbus' in local_info and local_info['parentbus'] == "netdevsim":
+        no_sleep=True
+    if 'linkinfo' in local_info and local_info['linkinfo']['info_kind'] == "veth":
+        no_sleep=True
+
+def set_interface_init(cfg) -> None:
+    cmd(f"ip link set dev {cfg.ifname} mtu 1500", shell=True)
+    cmd(f"ip link set dev {cfg.ifname} xdp off ", shell=True)
+    cmd(f"ip link set dev {cfg.ifname} xdpgeneric off ", shell=True)
+    cmd(f"ip link set dev {cfg.ifname} xdpoffload off", shell=True)
+    cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+
+def test_default_v4(cfg, netnl) -> None:
+    cfg.require_ipver("4")
+
+    _schedule_checksum_reset(cfg, netnl)
+    _set_offload_checksum(cfg, netnl, "off")
+    _test_v4(cfg)
+    _test_tcp(cfg)
+    _set_offload_checksum(cfg, netnl, "on")
+    _test_v4(cfg)
+    _test_tcp(cfg)
+
+def test_default_v6(cfg, netnl) -> None:
+    cfg.require_ipver("6")
+
+    _schedule_checksum_reset(cfg, netnl)
+    _set_offload_checksum(cfg, netnl, "off")
+    _test_v6(cfg)
+    _test_tcp(cfg)
+    _set_offload_checksum(cfg, netnl, "on")
+    _test_v6(cfg)
+    _test_tcp(cfg)
+
+def test_xdp_generic_sb(cfg, netnl) -> None:
+    _schedule_checksum_reset(cfg, netnl)
+    _set_xdp_generic_sb_on(cfg)
+    _set_offload_checksum(cfg, netnl, "off")
+    _test_v4(cfg)
+    _test_v6(cfg)
+    _test_tcp(cfg)
+    _set_offload_checksum(cfg, netnl, "on")
+    _test_v4(cfg)
+    _test_v6(cfg)
+    _test_tcp(cfg)
+
+def test_xdp_generic_mb(cfg, netnl) -> None:
+    _schedule_checksum_reset(cfg, netnl)
+    _set_xdp_generic_mb_on(cfg)
+    _set_offload_checksum(cfg, netnl, "off")
+    _test_v4(cfg)
+    _test_v6(cfg)
+    _test_tcp(cfg)
+    _set_offload_checksum(cfg, netnl, "on")
+    _test_v4(cfg)
+    _test_v6(cfg)
+    _test_tcp(cfg)
+
+def test_xdp_native_sb(cfg, netnl) -> None:
+    _schedule_checksum_reset(cfg, netnl)
+    _set_xdp_native_sb_on(cfg)
+    _set_offload_checksum(cfg, netnl, "off")
+    _test_v4(cfg)
+    _test_v6(cfg)
+    _test_tcp(cfg)
+    _set_offload_checksum(cfg, netnl, "on")
+    _test_v4(cfg)
+    _test_v6(cfg)
+    _test_tcp(cfg)
+
+def test_xdp_native_mb(cfg, netnl) -> None:
+    _schedule_checksum_reset(cfg, netnl)
+    _set_xdp_native_mb_on(cfg)
+    _set_offload_checksum(cfg, netnl, "off")
+    _test_v4(cfg)
+    _test_v6(cfg)
+    _test_tcp(cfg)
+    _set_offload_checksum(cfg, netnl, "on")
+    _test_v4(cfg)
+    _test_v6(cfg)
+    _test_tcp(cfg)
+
+def test_xdp_offload(cfg, netnl) -> None:
+    _set_xdp_offload_on(cfg)
+    _test_v4(cfg)
+    _test_v6(cfg)
+    _test_tcp(cfg)
+
+def main() -> None:
+    with NetDrvEpEnv(__file__) as cfg:
+        get_interface_info(cfg)
+        set_interface_init(cfg)
+        ksft_run([test_default_v4,
+                  test_default_v6,
+                  test_xdp_generic_sb,
+                  test_xdp_generic_mb,
+                  test_xdp_native_sb,
+                  test_xdp_native_mb,
+                  test_xdp_offload],
+                 args=(cfg, EthtoolFamily()))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/psp.py b/tools/testing/selftests/drivers/net/psp.py
new file mode 100755
index 000000000000..06559ef49b9a
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/psp.py
@@ -0,0 +1,640 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""Test suite for PSP capable drivers."""
+
+import errno
+import fcntl
+import socket
+import struct
+import termios
+import time
+
+from lib.py import defer
+from lib.py import ksft_run, ksft_exit, ksft_pr
+from lib.py import ksft_true, ksft_eq, ksft_ne, ksft_gt, ksft_raises
+from lib.py import ksft_not_none
+from lib.py import KsftSkipEx
+from lib.py import NetDrvEpEnv, PSPFamily, NlError
+from lib.py import bkg, rand_port, wait_port_listen
+
+
+def _get_outq(s):
+    one = b'\0' * 4
+    outq = fcntl.ioctl(s.fileno(), termios.TIOCOUTQ, one)
+    return struct.unpack("I", outq)[0]
+
+
+def _send_with_ack(cfg, msg):
+    cfg.comm_sock.send(msg)
+    response = cfg.comm_sock.recv(4)
+    if response != b'ack\0':
+        raise RuntimeError("Unexpected server response", response)
+
+
+def _remote_read_len(cfg):
+    cfg.comm_sock.send(b'read len\0')
+    return int(cfg.comm_sock.recv(1024)[:-1].decode('utf-8'))
+
+
+def _make_clr_conn(cfg, ipver=None):
+    _send_with_ack(cfg, b'conn clr\0')
+    remote_addr = cfg.remote_addr_v[ipver] if ipver else cfg.remote_addr
+    s = socket.create_connection((remote_addr, cfg.comm_port), )
+    return s
+
+
+def _make_psp_conn(cfg, version=0, ipver=None):
+    _send_with_ack(cfg, b'conn psp\0' + struct.pack('BB', version, version))
+    remote_addr = cfg.remote_addr_v[ipver] if ipver else cfg.remote_addr
+    s = socket.create_connection((remote_addr, cfg.comm_port), )
+    return s
+
+
+def _close_conn(cfg, s):
+    _send_with_ack(cfg, b'data close\0')
+    s.close()
+
+
+def _close_psp_conn(cfg, s):
+    _close_conn(cfg, s)
+
+
+def _spi_xchg(s, rx):
+    s.send(struct.pack('I', rx['spi']) + rx['key'])
+    tx = s.recv(4 + len(rx['key']))
+    return {
+        'spi': struct.unpack('I', tx[:4])[0],
+        'key': tx[4:]
+    }
+
+
+def _send_careful(cfg, s, rounds):
+    data = b'0123456789' * 200
+    for i in range(rounds):
+        n = 0
+        for _ in range(10): # allow 10 retries
+            try:
+                n += s.send(data[n:], socket.MSG_DONTWAIT)
+                if n == len(data):
+                    break
+            except BlockingIOError:
+                time.sleep(0.05)
+        else:
+            rlen = _remote_read_len(cfg)
+            outq = _get_outq(s)
+            report = f'sent: {i * len(data) + n} remote len: {rlen} outq: {outq}'
+            raise RuntimeError(report)
+
+    return len(data) * rounds
+
+
+def _check_data_rx(cfg, exp_len):
+    read_len = -1
+    for _ in range(30):
+        cfg.comm_sock.send(b'read len\0')
+        read_len = int(cfg.comm_sock.recv(1024)[:-1].decode('utf-8'))
+        if read_len == exp_len:
+            break
+        time.sleep(0.01)
+    ksft_eq(read_len, exp_len)
+
+
+def _check_data_outq(s, exp_len, force_wait=False):
+    outq = 0
+    for _ in range(10):
+        outq = _get_outq(s)
+        if not force_wait and outq == exp_len:
+            break
+        time.sleep(0.01)
+    ksft_eq(outq, exp_len)
+
+
+def _get_stat(cfg, key):
+    return cfg.pspnl.get_stats({'dev-id': cfg.psp_dev_id})[key]
+
+#
+# Test case boiler plate
+#
+
+def _init_psp_dev(cfg):
+    if not hasattr(cfg, 'psp_dev_id'):
+        # Figure out which local device we are testing against
+        for dev in cfg.pspnl.dev_get({}, dump=True):
+            if dev['ifindex'] == cfg.ifindex:
+                cfg.psp_info = dev
+                cfg.psp_dev_id = cfg.psp_info['id']
+                break
+        else:
+            raise KsftSkipEx("No PSP devices found")
+
+    # Enable PSP if necessary
+    cap = cfg.psp_info['psp-versions-cap']
+    ena = cfg.psp_info['psp-versions-ena']
+    if cap != ena:
+        cfg.pspnl.dev_set({'id': cfg.psp_dev_id, 'psp-versions-ena': cap})
+        defer(cfg.pspnl.dev_set, {'id': cfg.psp_dev_id,
+                                  'psp-versions-ena': ena })
+
+#
+# Test cases
+#
+
+def dev_list_devices(cfg):
+    """ Dump all devices """
+    _init_psp_dev(cfg)
+
+    devices = cfg.pspnl.dev_get({}, dump=True)
+
+    found = False
+    for dev in devices:
+        found |= dev['id'] == cfg.psp_dev_id
+    ksft_true(found)
+
+
+def dev_get_device(cfg):
+    """ Get the device we intend to use """
+    _init_psp_dev(cfg)
+
+    dev = cfg.pspnl.dev_get({'id': cfg.psp_dev_id})
+    ksft_eq(dev['id'], cfg.psp_dev_id)
+
+
+def dev_get_device_bad(cfg):
+    """ Test getting device which doesn't exist """
+    raised = False
+    try:
+        cfg.pspnl.dev_get({'id': 1234567})
+    except NlError as e:
+        ksft_eq(e.nl_msg.error, -errno.ENODEV)
+        raised = True
+    ksft_true(raised)
+
+
+def dev_rotate(cfg):
+    """ Test key rotation """
+    _init_psp_dev(cfg)
+
+    prev_rotations = _get_stat(cfg, 'key-rotations')
+
+    rot = cfg.pspnl.key_rotate({"id": cfg.psp_dev_id})
+    ksft_eq(rot['id'], cfg.psp_dev_id)
+    rot = cfg.pspnl.key_rotate({"id": cfg.psp_dev_id})
+    ksft_eq(rot['id'], cfg.psp_dev_id)
+
+    cur_rotations = _get_stat(cfg, 'key-rotations')
+    ksft_eq(cur_rotations, prev_rotations + 2)
+
+
+def dev_rotate_spi(cfg):
+    """ Test key rotation and SPI check """
+    _init_psp_dev(cfg)
+
+    top_a = top_b = 0
+    with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s:
+        assoc_a = cfg.pspnl.rx_assoc({"version": 0,
+                                     "dev-id": cfg.psp_dev_id,
+                                     "sock-fd": s.fileno()})
+        top_a = assoc_a['rx-key']['spi'] >> 31
+        s.close()
+    rot = cfg.pspnl.key_rotate({"id": cfg.psp_dev_id})
+    with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s:
+        ksft_eq(rot['id'], cfg.psp_dev_id)
+        assoc_b = cfg.pspnl.rx_assoc({"version": 0,
+                                    "dev-id": cfg.psp_dev_id,
+                                    "sock-fd": s.fileno()})
+        top_b = assoc_b['rx-key']['spi'] >> 31
+        s.close()
+    ksft_ne(top_a, top_b)
+
+
+def assoc_basic(cfg):
+    """ Test creating associations """
+    _init_psp_dev(cfg)
+
+    with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s:
+        assoc = cfg.pspnl.rx_assoc({"version": 0,
+                                  "dev-id": cfg.psp_dev_id,
+                                  "sock-fd": s.fileno()})
+        ksft_eq(assoc['dev-id'], cfg.psp_dev_id)
+        ksft_gt(assoc['rx-key']['spi'], 0)
+        ksft_eq(len(assoc['rx-key']['key']), 16)
+
+        assoc = cfg.pspnl.tx_assoc({"dev-id": cfg.psp_dev_id,
+                                  "version": 0,
+                                  "tx-key": assoc['rx-key'],
+                                  "sock-fd": s.fileno()})
+        ksft_eq(len(assoc), 0)
+        s.close()
+
+
+def assoc_bad_dev(cfg):
+    """ Test creating associations with bad device ID """
+    _init_psp_dev(cfg)
+
+    with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s:
+        with ksft_raises(NlError) as cm:
+            cfg.pspnl.rx_assoc({"version": 0,
+                              "dev-id": cfg.psp_dev_id + 1234567,
+                              "sock-fd": s.fileno()})
+        ksft_eq(cm.exception.nl_msg.error, -errno.ENODEV)
+
+
+def assoc_sk_only_conn(cfg):
+    """ Test creating associations based on socket """
+    _init_psp_dev(cfg)
+
+    with _make_clr_conn(cfg) as s:
+        assoc = cfg.pspnl.rx_assoc({"version": 0,
+                                  "sock-fd": s.fileno()})
+        ksft_eq(assoc['dev-id'], cfg.psp_dev_id)
+        cfg.pspnl.tx_assoc({"version": 0,
+                          "tx-key": assoc['rx-key'],
+                          "sock-fd": s.fileno()})
+        _close_conn(cfg, s)
+
+
+def assoc_sk_only_mismatch(cfg):
+    """ Test creating associations based on socket (dev mismatch) """
+    _init_psp_dev(cfg)
+
+    with _make_clr_conn(cfg) as s:
+        with ksft_raises(NlError) as cm:
+            cfg.pspnl.rx_assoc({"version": 0,
+                              "dev-id": cfg.psp_dev_id + 1234567,
+                              "sock-fd": s.fileno()})
+        the_exception = cm.exception
+        ksft_eq(the_exception.nl_msg.extack['bad-attr'], ".dev-id")
+        ksft_eq(the_exception.nl_msg.error, -errno.EINVAL)
+
+
+def assoc_sk_only_mismatch_tx(cfg):
+    """ Test creating associations based on socket (dev mismatch) """
+    _init_psp_dev(cfg)
+
+    with _make_clr_conn(cfg) as s:
+        with ksft_raises(NlError) as cm:
+            assoc = cfg.pspnl.rx_assoc({"version": 0,
+                                      "sock-fd": s.fileno()})
+            cfg.pspnl.tx_assoc({"version": 0,
+                              "tx-key": assoc['rx-key'],
+                              "dev-id": cfg.psp_dev_id + 1234567,
+                              "sock-fd": s.fileno()})
+        the_exception = cm.exception
+        ksft_eq(the_exception.nl_msg.extack['bad-attr'], ".dev-id")
+        ksft_eq(the_exception.nl_msg.error, -errno.EINVAL)
+
+
+def assoc_sk_only_unconn(cfg):
+    """ Test creating associations based on socket (unconnected, should fail) """
+    _init_psp_dev(cfg)
+
+    with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s:
+        with ksft_raises(NlError) as cm:
+            cfg.pspnl.rx_assoc({"version": 0,
+                              "sock-fd": s.fileno()})
+        the_exception = cm.exception
+        ksft_eq(the_exception.nl_msg.extack['miss-type'], "dev-id")
+        ksft_eq(the_exception.nl_msg.error, -errno.EINVAL)
+
+
+def assoc_version_mismatch(cfg):
+    """ Test creating associations where Rx and Tx PSP versions do not match """
+    _init_psp_dev(cfg)
+
+    versions = list(cfg.psp_info['psp-versions-cap'])
+    if len(versions) < 2:
+        raise KsftSkipEx("Not enough PSP versions supported by the device for the test")
+
+    # Translate versions to integers
+    versions = [cfg.pspnl.consts["version"].entries[v].value for v in versions]
+
+    with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s:
+        rx = cfg.pspnl.rx_assoc({"version": versions[0],
+                                 "dev-id": cfg.psp_dev_id,
+                                 "sock-fd": s.fileno()})
+
+        for version in versions[1:]:
+            with ksft_raises(NlError) as cm:
+                cfg.pspnl.tx_assoc({"dev-id": cfg.psp_dev_id,
+                                    "version": version,
+                                    "tx-key": rx['rx-key'],
+                                    "sock-fd": s.fileno()})
+            the_exception = cm.exception
+            ksft_eq(the_exception.nl_msg.error, -errno.EINVAL)
+
+
+def assoc_twice(cfg):
+    """ Test reusing Tx assoc for two sockets """
+    _init_psp_dev(cfg)
+
+    def rx_assoc_check(s):
+        assoc = cfg.pspnl.rx_assoc({"version": 0,
+                                  "dev-id": cfg.psp_dev_id,
+                                  "sock-fd": s.fileno()})
+        ksft_eq(assoc['dev-id'], cfg.psp_dev_id)
+        ksft_gt(assoc['rx-key']['spi'], 0)
+        ksft_eq(len(assoc['rx-key']['key']), 16)
+
+        return assoc
+
+    with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s:
+        assoc = rx_assoc_check(s)
+        tx = cfg.pspnl.tx_assoc({"dev-id": cfg.psp_dev_id,
+                               "version": 0,
+                               "tx-key": assoc['rx-key'],
+                               "sock-fd": s.fileno()})
+        ksft_eq(len(tx), 0)
+
+        # Use the same Tx assoc second time
+        with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s2:
+            rx_assoc_check(s2)
+            tx = cfg.pspnl.tx_assoc({"dev-id": cfg.psp_dev_id,
+                                   "version": 0,
+                                   "tx-key": assoc['rx-key'],
+                                   "sock-fd": s2.fileno()})
+            ksft_eq(len(tx), 0)
+
+        s.close()
+
+
+def _data_basic_send(cfg, version, ipver):
+    """ Test basic data send """
+    _init_psp_dev(cfg)
+
+    # Version 0 is required by spec, don't let it skip
+    if version:
+        name = cfg.pspnl.consts["version"].entries_by_val[version].name
+        if name not in cfg.psp_info['psp-versions-cap']:
+            with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s:
+                with ksft_raises(NlError) as cm:
+                    cfg.pspnl.rx_assoc({"version": version,
+                                        "dev-id": cfg.psp_dev_id,
+                                        "sock-fd": s.fileno()})
+                ksft_eq(cm.exception.nl_msg.error, -errno.EOPNOTSUPP)
+            raise KsftSkipEx("PSP version not supported", name)
+
+    s = _make_psp_conn(cfg, version, ipver)
+
+    rx_assoc = cfg.pspnl.rx_assoc({"version": version,
+                                   "dev-id": cfg.psp_dev_id,
+                                   "sock-fd": s.fileno()})
+    rx = rx_assoc['rx-key']
+    tx = _spi_xchg(s, rx)
+
+    cfg.pspnl.tx_assoc({"dev-id": cfg.psp_dev_id,
+                        "version": version,
+                        "tx-key": tx,
+                        "sock-fd": s.fileno()})
+
+    data_len = _send_careful(cfg, s, 100)
+    _check_data_rx(cfg, data_len)
+    _close_psp_conn(cfg, s)
+
+
+def __bad_xfer_do(cfg, s, tx, version='hdr0-aes-gcm-128'):
+    # Make sure we accept the ACK for the SPI before we seal with the bad assoc
+    _check_data_outq(s, 0)
+
+    cfg.pspnl.tx_assoc({"dev-id": cfg.psp_dev_id,
+                        "version": version,
+                        "tx-key": tx,
+                        "sock-fd": s.fileno()})
+
+    data_len = _send_careful(cfg, s, 20)
+    _check_data_outq(s, data_len, force_wait=True)
+    _check_data_rx(cfg, 0)
+    _close_psp_conn(cfg, s)
+
+
+def data_send_bad_key(cfg):
+    """ Test send data with bad key """
+    _init_psp_dev(cfg)
+
+    s = _make_psp_conn(cfg)
+
+    rx_assoc = cfg.pspnl.rx_assoc({"version": 0,
+                                   "dev-id": cfg.psp_dev_id,
+                                   "sock-fd": s.fileno()})
+    rx = rx_assoc['rx-key']
+    tx = _spi_xchg(s, rx)
+    tx['key'] = (tx['key'][0] ^ 0xff).to_bytes(1, 'little') + tx['key'][1:]
+    __bad_xfer_do(cfg, s, tx)
+
+
+def data_send_disconnect(cfg):
+    """ Test socket close after sending data """
+    _init_psp_dev(cfg)
+
+    with _make_psp_conn(cfg) as s:
+        assoc = cfg.pspnl.rx_assoc({"version": 0,
+                                  "sock-fd": s.fileno()})
+        tx = _spi_xchg(s, assoc['rx-key'])
+        cfg.pspnl.tx_assoc({"version": 0,
+                          "tx-key": tx,
+                          "sock-fd": s.fileno()})
+
+        data_len = _send_careful(cfg, s, 100)
+        _check_data_rx(cfg, data_len)
+
+        s.shutdown(socket.SHUT_RDWR)
+        s.close()
+
+
+def _data_mss_adjust(cfg, ipver):
+    _init_psp_dev(cfg)
+
+    # First figure out what the MSS would be without any adjustments
+    s = _make_clr_conn(cfg, ipver)
+    s.send(b"0123456789abcdef" * 1024)
+    _check_data_rx(cfg, 16 * 1024)
+    mss = s.getsockopt(socket.IPPROTO_TCP, socket.TCP_MAXSEG)
+    _close_conn(cfg, s)
+
+    s = _make_psp_conn(cfg, 0, ipver)
+    try:
+        rx_assoc = cfg.pspnl.rx_assoc({"version": 0,
+                                     "dev-id": cfg.psp_dev_id,
+                                     "sock-fd": s.fileno()})
+        rx = rx_assoc['rx-key']
+        tx = _spi_xchg(s, rx)
+
+        rxmss = s.getsockopt(socket.IPPROTO_TCP, socket.TCP_MAXSEG)
+        ksft_eq(mss, rxmss)
+
+        cfg.pspnl.tx_assoc({"dev-id": cfg.psp_dev_id,
+                          "version": 0,
+                          "tx-key": tx,
+                          "sock-fd": s.fileno()})
+
+        txmss = s.getsockopt(socket.IPPROTO_TCP, socket.TCP_MAXSEG)
+        ksft_eq(mss, txmss + 40)
+
+        data_len = _send_careful(cfg, s, 100)
+        _check_data_rx(cfg, data_len)
+        _check_data_outq(s, 0)
+
+        txmss = s.getsockopt(socket.IPPROTO_TCP, socket.TCP_MAXSEG)
+        ksft_eq(mss, txmss + 40)
+    finally:
+        _close_psp_conn(cfg, s)
+
+
+def data_stale_key(cfg):
+    """ Test send on a double-rotated key """
+    _init_psp_dev(cfg)
+
+    prev_stale = _get_stat(cfg, 'stale-events')
+    s = _make_psp_conn(cfg)
+    try:
+        rx_assoc = cfg.pspnl.rx_assoc({"version": 0,
+                                     "dev-id": cfg.psp_dev_id,
+                                     "sock-fd": s.fileno()})
+        rx = rx_assoc['rx-key']
+        tx = _spi_xchg(s, rx)
+
+        cfg.pspnl.tx_assoc({"dev-id": cfg.psp_dev_id,
+                          "version": 0,
+                          "tx-key": tx,
+                          "sock-fd": s.fileno()})
+
+        data_len = _send_careful(cfg, s, 100)
+        _check_data_rx(cfg, data_len)
+        _check_data_outq(s, 0)
+
+        cfg.pspnl.key_rotate({"id": cfg.psp_dev_id})
+        cfg.pspnl.key_rotate({"id": cfg.psp_dev_id})
+
+        cur_stale = _get_stat(cfg, 'stale-events')
+        ksft_gt(cur_stale, prev_stale)
+
+        s.send(b'0123456789' * 200)
+        _check_data_outq(s, 2000, force_wait=True)
+    finally:
+        _close_psp_conn(cfg, s)
+
+
+def __nsim_psp_rereg(cfg):
+    # The PSP dev ID will change, remember what was there before
+    before = set([x['id'] for x in cfg.pspnl.dev_get({}, dump=True)])
+
+    cfg._ns.nsims[0].dfs_write('psp_rereg', '1')
+
+    after = set([x['id'] for x in cfg.pspnl.dev_get({}, dump=True)])
+
+    new_devs = list(after - before)
+    ksft_eq(len(new_devs), 1)
+    cfg.psp_dev_id = list(after - before)[0]
+
+
+def removal_device_rx(cfg):
+    """ Test removing a netdev / PSD with active Rx assoc """
+
+    # We could technically devlink reload real devices, too
+    # but that kills the control socket. So test this on
+    # netdevsim only for now
+    cfg.require_nsim()
+
+    s = _make_clr_conn(cfg)
+    try:
+        rx_assoc = cfg.pspnl.rx_assoc({"version": 0,
+                                       "dev-id": cfg.psp_dev_id,
+                                       "sock-fd": s.fileno()})
+        ksft_not_none(rx_assoc)
+
+        __nsim_psp_rereg(cfg)
+    finally:
+        _close_conn(cfg, s)
+
+
+def removal_device_bi(cfg):
+    """ Test removing a netdev / PSD with active Rx/Tx assoc """
+
+    # We could technically devlink reload real devices, too
+    # but that kills the control socket. So test this on
+    # netdevsim only for now
+    cfg.require_nsim()
+
+    s = _make_clr_conn(cfg)
+    try:
+        rx_assoc = cfg.pspnl.rx_assoc({"version": 0,
+                                       "dev-id": cfg.psp_dev_id,
+                                       "sock-fd": s.fileno()})
+        cfg.pspnl.tx_assoc({"dev-id": cfg.psp_dev_id,
+                            "version": 0,
+                            "tx-key": rx_assoc['rx-key'],
+                            "sock-fd": s.fileno()})
+        __nsim_psp_rereg(cfg)
+    finally:
+        _close_conn(cfg, s)
+
+
+def psp_ip_ver_test_builder(name, test_func, psp_ver, ipver):
+    """Build test cases for each combo of PSP version and IP version"""
+    def test_case(cfg):
+        cfg.require_ipver(ipver)
+        test_case.__name__ = f"{name}_v{psp_ver}_ip{ipver}"
+        test_func(cfg, psp_ver, ipver)
+    return test_case
+
+
+def ipver_test_builder(name, test_func, ipver):
+    """Build test cases for each IP version"""
+    def test_case(cfg):
+        cfg.require_ipver(ipver)
+        test_case.__name__ = f"{name}_ip{ipver}"
+        test_func(cfg, ipver)
+    return test_case
+
+
+def main() -> None:
+    """ Ksft boiler plate main """
+
+    with NetDrvEpEnv(__file__) as cfg:
+        cfg.pspnl = PSPFamily()
+
+        # Set up responder and communication sock
+        responder = cfg.remote.deploy("psp_responder")
+
+        cfg.comm_port = rand_port()
+        srv = None
+        try:
+            with bkg(responder + f" -p {cfg.comm_port}", host=cfg.remote,
+                     exit_wait=True) as srv:
+                wait_port_listen(cfg.comm_port, host=cfg.remote)
+
+                cfg.comm_sock = socket.create_connection((cfg.remote_addr,
+                                                          cfg.comm_port),
+                                                         timeout=1)
+
+                cases = [
+                    psp_ip_ver_test_builder(
+                        "data_basic_send", _data_basic_send, version, ipver
+                    )
+                    for version in range(0, 4)
+                    for ipver in ("4", "6")
+                ]
+                cases += [
+                    ipver_test_builder("data_mss_adjust", _data_mss_adjust, ipver)
+                    for ipver in ("4", "6")
+                ]
+
+                ksft_run(cases=cases, globs=globals(),
+                         case_pfx={"dev_", "data_", "assoc_", "removal_"},
+                         args=(cfg, ))
+
+                cfg.comm_sock.send(b"exit\0")
+                cfg.comm_sock.close()
+        finally:
+            if srv and (srv.stdout or srv.stderr):
+                ksft_pr("")
+                ksft_pr(f"Responder logs ({srv.ret}):")
+            if srv and srv.stdout:
+                ksft_pr("STDOUT:\n#  " + srv.stdout.strip().replace("\n", "\n#  "))
+            if srv and srv.stderr:
+                ksft_pr("STDERR:\n#  " + srv.stderr.strip().replace("\n", "\n#  "))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/psp_responder.c b/tools/testing/selftests/drivers/net/psp_responder.c
new file mode 100644
index 000000000000..f309e0d73cbf
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/psp_responder.c
@@ -0,0 +1,483 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdio.h>
+#include <string.h>
+#include <sys/poll.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <netinet/in.h>
+#include <unistd.h>
+
+#include <ynl.h>
+
+#include "psp-user.h"
+
+#define dbg(msg...)				\
+do {						\
+	if (opts->verbose)			\
+		fprintf(stderr, "DEBUG: " msg);	\
+} while (0)
+
+static bool should_quit;
+
+struct opts {
+	int port;
+	int devid;
+	bool verbose;
+};
+
+enum accept_cfg {
+	ACCEPT_CFG_NONE = 0,
+	ACCEPT_CFG_CLEAR,
+	ACCEPT_CFG_PSP,
+};
+
+static struct {
+	unsigned char tx;
+	unsigned char rx;
+} psp_vers;
+
+static int conn_setup_psp(struct ynl_sock *ys, struct opts *opts, int data_sock)
+{
+	struct psp_rx_assoc_rsp *rsp;
+	struct psp_rx_assoc_req *req;
+	struct psp_tx_assoc_rsp *tsp;
+	struct psp_tx_assoc_req *teq;
+	char info[300];
+	int key_len;
+	ssize_t sz;
+	__u32 spi;
+
+	dbg("create PSP connection\n");
+
+	// Rx assoc alloc
+	req = psp_rx_assoc_req_alloc();
+
+	psp_rx_assoc_req_set_sock_fd(req, data_sock);
+	psp_rx_assoc_req_set_version(req, psp_vers.rx);
+
+	rsp = psp_rx_assoc(ys, req);
+	psp_rx_assoc_req_free(req);
+
+	if (!rsp) {
+		perror("ERROR: failed to Rx assoc");
+		return -1;
+	}
+
+	// SPI exchange
+	key_len = rsp->rx_key._len.key;
+	memcpy(info, &rsp->rx_key.spi, sizeof(spi));
+	memcpy(&info[sizeof(spi)], rsp->rx_key.key, key_len);
+	sz = sizeof(spi) + key_len;
+
+	send(data_sock, info, sz, MSG_WAITALL);
+	psp_rx_assoc_rsp_free(rsp);
+
+	sz = recv(data_sock, info, sz, MSG_WAITALL);
+	if (sz < 0) {
+		perror("ERROR: failed to read PSP key from sock");
+		return -1;
+	}
+	memcpy(&spi, info, sizeof(spi));
+
+	// Setup Tx assoc
+	teq = psp_tx_assoc_req_alloc();
+
+	psp_tx_assoc_req_set_sock_fd(teq, data_sock);
+	psp_tx_assoc_req_set_version(teq, psp_vers.tx);
+	psp_tx_assoc_req_set_tx_key_spi(teq, spi);
+	psp_tx_assoc_req_set_tx_key_key(teq, &info[sizeof(spi)], key_len);
+
+	tsp = psp_tx_assoc(ys, teq);
+	psp_tx_assoc_req_free(teq);
+	if (!tsp) {
+		perror("ERROR: failed to Tx assoc");
+		return -1;
+	}
+	psp_tx_assoc_rsp_free(tsp);
+
+	return 0;
+}
+
+static void send_ack(int sock)
+{
+	send(sock, "ack", 4, MSG_WAITALL);
+}
+
+static void send_err(int sock)
+{
+	send(sock, "err", 4, MSG_WAITALL);
+}
+
+static void send_str(int sock, int value)
+{
+	char buf[128];
+	int ret;
+
+	ret = snprintf(buf, sizeof(buf), "%d", value);
+	send(sock, buf, ret + 1, MSG_WAITALL);
+}
+
+static void
+run_session(struct ynl_sock *ys, struct opts *opts,
+	    int server_sock, int comm_sock)
+{
+	enum accept_cfg accept_cfg = ACCEPT_CFG_NONE;
+	struct pollfd pfds[3];
+	size_t data_read = 0;
+	int data_sock = -1;
+
+	while (true) {
+		bool race_close = false;
+		int nfds;
+
+		memset(pfds, 0, sizeof(pfds));
+
+		pfds[0].fd = server_sock;
+		pfds[0].events = POLLIN;
+
+		pfds[1].fd = comm_sock;
+		pfds[1].events = POLLIN;
+
+		nfds = 2;
+		if (data_sock >= 0) {
+			pfds[2].fd = data_sock;
+			pfds[2].events = POLLIN;
+			nfds++;
+		}
+
+		dbg(" ...\n");
+		if (poll(pfds, nfds, -1) < 0) {
+			perror("poll");
+			break;
+		}
+
+		/* data sock */
+		if (pfds[2].revents & POLLIN) {
+			char buf[8192];
+			ssize_t n;
+
+			n = recv(data_sock, buf, sizeof(buf), 0);
+			if (n <= 0) {
+				if (n < 0)
+					perror("data read");
+				close(data_sock);
+				data_sock = -1;
+				dbg("data sock closed\n");
+			} else {
+				data_read += n;
+				dbg("data read %zd\n", data_read);
+			}
+		}
+
+		/* comm sock */
+		if (pfds[1].revents & POLLIN) {
+			static char buf[4096];
+			static ssize_t off;
+			bool consumed;
+			ssize_t n;
+
+			n = recv(comm_sock, &buf[off], sizeof(buf) - off, 0);
+			if (n <= 0) {
+				if (n < 0)
+					perror("comm read");
+				return;
+			}
+
+			off += n;
+			n = off;
+
+#define __consume(sz)						\
+		({						\
+			if (n == (sz)) {			\
+				off = 0;			\
+			} else {				\
+				off -= (sz);			\
+				memmove(buf, &buf[(sz)], off);	\
+			}					\
+		})
+
+#define cmd(_name)							\
+		({							\
+			ssize_t sz = sizeof(_name);			\
+			bool match = n >= sz &&	!memcmp(buf, _name, sz); \
+									\
+			if (match) {					\
+				dbg("command: " _name "\n");		\
+				__consume(sz);				\
+			}						\
+			consumed |= match;				\
+			match;						\
+		})
+
+			do {
+				consumed = false;
+
+				if (cmd("read len"))
+					send_str(comm_sock, data_read);
+
+				if (cmd("data echo")) {
+					if (data_sock >= 0)
+						send(data_sock, "echo", 5,
+						     MSG_WAITALL);
+					else
+						fprintf(stderr, "WARN: echo but no data sock\n");
+					send_ack(comm_sock);
+				}
+				if (cmd("data close")) {
+					if (data_sock >= 0) {
+						close(data_sock);
+						data_sock = -1;
+						send_ack(comm_sock);
+					} else {
+						race_close = true;
+					}
+				}
+				if (cmd("conn psp")) {
+					if (accept_cfg != ACCEPT_CFG_NONE)
+						fprintf(stderr, "WARN: old conn config still set!\n");
+					accept_cfg = ACCEPT_CFG_PSP;
+					send_ack(comm_sock);
+					/* next two bytes are versions */
+					if (off >= 2) {
+						memcpy(&psp_vers, buf, 2);
+						__consume(2);
+					} else {
+						fprintf(stderr, "WARN: short conn psp command!\n");
+					}
+				}
+				if (cmd("conn clr")) {
+					if (accept_cfg != ACCEPT_CFG_NONE)
+						fprintf(stderr, "WARN: old conn config still set!\n");
+					accept_cfg = ACCEPT_CFG_CLEAR;
+					send_ack(comm_sock);
+				}
+				if (cmd("exit"))
+					should_quit = true;
+#undef cmd
+
+				if (!consumed) {
+					fprintf(stderr, "WARN: unknown cmd: [%zd] %s\n",
+						off, buf);
+				}
+			} while (consumed && off);
+		}
+
+		/* server sock */
+		if (pfds[0].revents & POLLIN) {
+			if (data_sock >= 0) {
+				fprintf(stderr, "WARN: new data sock but old one still here\n");
+				close(data_sock);
+				data_sock = -1;
+			}
+			data_sock = accept(server_sock, NULL, NULL);
+			if (data_sock < 0) {
+				perror("accept");
+				continue;
+			}
+			data_read = 0;
+
+			if (accept_cfg == ACCEPT_CFG_CLEAR) {
+				dbg("new data sock: clear\n");
+				/* nothing to do */
+			} else if (accept_cfg == ACCEPT_CFG_PSP) {
+				dbg("new data sock: psp\n");
+				conn_setup_psp(ys, opts, data_sock);
+			} else {
+				fprintf(stderr, "WARN: new data sock but no config\n");
+			}
+			accept_cfg = ACCEPT_CFG_NONE;
+		}
+
+		if (race_close) {
+			if (data_sock >= 0) {
+				/* indeed, ordering problem, handle the close */
+				close(data_sock);
+				data_sock = -1;
+				send_ack(comm_sock);
+			} else {
+				fprintf(stderr, "WARN: close but no data sock\n");
+				send_err(comm_sock);
+			}
+		}
+	}
+	dbg("session ending\n");
+}
+
+static int spawn_server(struct opts *opts)
+{
+	struct sockaddr_in6 addr;
+	int fd;
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (fd < 0) {
+		perror("can't open socket");
+		return -1;
+	}
+
+	memset(&addr, 0, sizeof(addr));
+
+	addr.sin6_family = AF_INET6;
+	addr.sin6_addr = in6addr_any;
+	addr.sin6_port = htons(opts->port);
+
+	if (bind(fd, (struct sockaddr *)&addr, sizeof(addr))) {
+		perror("can't bind socket");
+		return -1;
+	}
+
+	if (listen(fd, 5)) {
+		perror("can't listen");
+		return -1;
+	}
+
+	return fd;
+}
+
+static int run_responder(struct ynl_sock *ys, struct opts *opts)
+{
+	int server_sock, comm;
+
+	server_sock = spawn_server(opts);
+	if (server_sock < 0)
+		return 4;
+
+	while (!should_quit) {
+		comm = accept(server_sock, NULL, NULL);
+		if (comm < 0) {
+			perror("accept failed");
+		} else {
+			run_session(ys, opts, server_sock, comm);
+			close(comm);
+		}
+	}
+
+	return 0;
+}
+
+static void usage(const char *name, const char *miss)
+{
+	if (miss)
+		fprintf(stderr, "Missing argument: %s\n", miss);
+
+	fprintf(stderr, "Usage: %s -p port [-v] [-d psp-dev-id]\n", name);
+	exit(EXIT_FAILURE);
+}
+
+static void parse_cmd_opts(int argc, char **argv, struct opts *opts)
+{
+	int opt;
+
+	while ((opt = getopt(argc, argv, "vp:d:")) != -1) {
+		switch (opt) {
+		case 'v':
+			opts->verbose = 1;
+			break;
+		case 'p':
+			opts->port = atoi(optarg);
+			break;
+		case 'd':
+			opts->devid = atoi(optarg);
+			break;
+		default:
+			usage(argv[0], NULL);
+		}
+	}
+}
+
+static int psp_dev_set_ena(struct ynl_sock *ys, __u32 dev_id, __u32 versions)
+{
+	struct psp_dev_set_req *sreq;
+	struct psp_dev_set_rsp *srsp;
+
+	fprintf(stderr, "Set PSP enable on device %d to 0x%x\n",
+		dev_id, versions);
+
+	sreq = psp_dev_set_req_alloc();
+
+	psp_dev_set_req_set_id(sreq, dev_id);
+	psp_dev_set_req_set_psp_versions_ena(sreq, versions);
+
+	srsp = psp_dev_set(ys, sreq);
+	psp_dev_set_req_free(sreq);
+	if (!srsp)
+		return 10;
+
+	psp_dev_set_rsp_free(srsp);
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	struct psp_dev_get_list *dev_list;
+	bool devid_found = false;
+	__u32 ver_ena, ver_cap;
+	struct opts opts = {};
+	struct ynl_error yerr;
+	struct ynl_sock *ys;
+	int first_id = 0;
+	int ret;
+
+	parse_cmd_opts(argc, argv, &opts);
+	if (!opts.port)
+		usage(argv[0], "port"); // exits
+
+	ys = ynl_sock_create(&ynl_psp_family, &yerr);
+	if (!ys) {
+		fprintf(stderr, "YNL: %s\n", yerr.msg);
+		return 1;
+	}
+
+	dev_list = psp_dev_get_dump(ys);
+	if (ynl_dump_empty(dev_list)) {
+		if (ys->err.code)
+			goto err_close;
+		fprintf(stderr, "No PSP devices\n");
+		goto err_close_silent;
+	}
+
+	ynl_dump_foreach(dev_list, d) {
+		if (opts.devid) {
+			devid_found = true;
+			ver_ena = d->psp_versions_ena;
+			ver_cap = d->psp_versions_cap;
+		} else if (!first_id) {
+			first_id = d->id;
+			ver_ena = d->psp_versions_ena;
+			ver_cap = d->psp_versions_cap;
+		} else {
+			fprintf(stderr, "Multiple PSP devices found\n");
+			goto err_close_silent;
+		}
+	}
+	psp_dev_get_list_free(dev_list);
+
+	if (opts.devid && !devid_found) {
+		fprintf(stderr, "PSP device %d requested on cmdline, not found\n",
+			opts.devid);
+		goto err_close_silent;
+	} else if (!opts.devid) {
+		opts.devid = first_id;
+	}
+
+	if (ver_ena != ver_cap) {
+		ret = psp_dev_set_ena(ys, opts.devid, ver_cap);
+		if (ret)
+			goto err_close;
+	}
+
+	ret = run_responder(ys, &opts);
+
+	if (ver_ena != ver_cap && psp_dev_set_ena(ys, opts.devid, ver_ena))
+		fprintf(stderr, "WARN: failed to set the PSP versions back\n");
+
+	ynl_sock_destroy(ys);
+
+	return ret;
+
+err_close:
+	fprintf(stderr, "YNL: %s\n", ys->err.msg);
+err_close_silent:
+	ynl_sock_destroy(ys);
+	return 2;
+}
diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py
new file mode 100755
index 000000000000..236005290a33
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/queues.py
@@ -0,0 +1,125 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+from lib.py import ksft_disruptive, ksft_exit, ksft_run
+from lib.py import ksft_eq, ksft_not_in, ksft_raises, KsftSkipEx, KsftFailEx
+from lib.py import EthtoolFamily, NetdevFamily, NlError
+from lib.py import NetDrvEnv
+from lib.py import bkg, cmd, defer, ip
+import errno
+import glob
+import os
+import socket
+import struct
+
+def sys_get_queues(ifname, qtype='rx') -> int:
+    folders = glob.glob(f'/sys/class/net/{ifname}/queues/{qtype}-*')
+    return len(folders)
+
+
+def nl_get_queues(cfg, nl, qtype='rx'):
+    queues = nl.queue_get({'ifindex': cfg.ifindex}, dump=True)
+    if queues:
+        return len([q for q in queues if q['type'] == qtype])
+    return None
+
+
+def check_xsk(cfg, nl, xdp_queue_id=0) -> None:
+    # Probe for support
+    xdp = cmd(f'{cfg.net_lib_dir / "xdp_helper"} - -', fail=False)
+    if xdp.ret == 255:
+        raise KsftSkipEx('AF_XDP unsupported')
+    elif xdp.ret > 0:
+        raise KsftFailEx('unable to create AF_XDP socket')
+
+    with bkg(f'{cfg.net_lib_dir / "xdp_helper"} {cfg.ifindex} {xdp_queue_id}',
+             ksft_wait=3):
+
+        rx = tx = False
+
+        queues = nl.queue_get({'ifindex': cfg.ifindex}, dump=True)
+        if not queues:
+            raise KsftSkipEx("Netlink reports no queues")
+
+        for q in queues:
+            if q['id'] == 0:
+                if q['type'] == 'rx':
+                    rx = True
+                if q['type'] == 'tx':
+                    tx = True
+
+                ksft_eq(q.get('xsk', None), {},
+                        comment="xsk attr on queue we configured")
+            else:
+                ksft_not_in('xsk', q,
+                            comment="xsk attr on queue we didn't configure")
+
+        ksft_eq(rx, True)
+        ksft_eq(tx, True)
+
+
+def get_queues(cfg, nl) -> None:
+    snl = NetdevFamily(recv_size=4096)
+
+    for qtype in ['rx', 'tx']:
+        queues = nl_get_queues(cfg, snl, qtype)
+        if not queues:
+            raise KsftSkipEx('queue-get not supported by device')
+
+        expected = sys_get_queues(cfg.dev['ifname'], qtype)
+        ksft_eq(queues, expected)
+
+
+def addremove_queues(cfg, nl) -> None:
+    queues = nl_get_queues(cfg, nl)
+    if not queues:
+        raise KsftSkipEx('queue-get not supported by device')
+
+    curr_queues = sys_get_queues(cfg.dev['ifname'])
+    if curr_queues == 1:
+        raise KsftSkipEx('cannot decrement queue: already at 1')
+
+    netnl = EthtoolFamily()
+    channels = netnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+    rx_type = 'rx'
+    if channels.get('combined-count', 0) > 0:
+            rx_type = 'combined'
+
+    expected = curr_queues - 1
+    cmd(f"ethtool -L {cfg.dev['ifname']} {rx_type} {expected}", timeout=10)
+    queues = nl_get_queues(cfg, nl)
+    ksft_eq(queues, expected)
+
+    expected = curr_queues
+    cmd(f"ethtool -L {cfg.dev['ifname']} {rx_type} {expected}", timeout=10)
+    queues = nl_get_queues(cfg, nl)
+    ksft_eq(queues, expected)
+
+
+@ksft_disruptive
+def check_down(cfg, nl) -> None:
+    # Check the NAPI IDs before interface goes down and hides them
+    napis = nl.napi_get({'ifindex': cfg.ifindex}, dump=True)
+
+    ip(f"link set dev {cfg.dev['ifname']} down")
+    defer(ip, f"link set dev {cfg.dev['ifname']} up")
+
+    with ksft_raises(NlError) as cm:
+        nl.queue_get({'ifindex': cfg.ifindex, 'id': 0, 'type': 'rx'})
+    ksft_eq(cm.exception.nl_msg.error, -errno.ENOENT)
+
+    if napis:
+        with ksft_raises(NlError) as cm:
+            nl.napi_get({'id': napis[0]['id']})
+        ksft_eq(cm.exception.nl_msg.error, -errno.ENOENT)
+
+
+def main() -> None:
+    with NetDrvEnv(__file__, queue_count=100) as cfg:
+        ksft_run([get_queues, addremove_queues, check_down, check_xsk],
+                 args=(cfg, NetdevFamily()))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/ring_reconfig.py b/tools/testing/selftests/drivers/net/ring_reconfig.py
new file mode 100755
index 000000000000..f9530a8b0856
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/ring_reconfig.py
@@ -0,0 +1,167 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+Test channel and ring size configuration via ethtool (-L / -G).
+"""
+
+from lib.py import ksft_run, ksft_exit, ksft_pr
+from lib.py import ksft_eq
+from lib.py import NetDrvEpEnv, EthtoolFamily, GenerateTraffic
+from lib.py import defer, NlError
+
+
+def channels(cfg) -> None:
+    """
+    Twiddle channel counts in various combinations of parameters.
+    We're only looking for driver adhering to the requested config
+    if the config is accepted and crashes.
+    """
+    ehdr = {'header':{'dev-index': cfg.ifindex}}
+    chans = cfg.eth.channels_get(ehdr)
+
+    all_keys = ["rx", "tx", "combined"]
+    mixes = [{"combined"}, {"rx", "tx"}, {"rx", "combined"}, {"tx", "combined"},
+             {"rx", "tx", "combined"},]
+
+    # Get the set of keys that device actually supports
+    restore = {}
+    supported = set()
+    for key in all_keys:
+        if key + "-max" in chans:
+            supported.add(key)
+            restore |= {key + "-count": chans[key + "-count"]}
+
+    defer(cfg.eth.channels_set, ehdr | restore)
+
+    def test_config(config):
+        try:
+            cfg.eth.channels_set(ehdr | config)
+            get = cfg.eth.channels_get(ehdr)
+            for k, v in config.items():
+                ksft_eq(get.get(k, 0), v)
+        except NlError as e:
+            failed.append(mix)
+            ksft_pr("Can't set", config, e)
+        else:
+            ksft_pr("Okay", config)
+
+    failed = []
+    for mix in mixes:
+        if not mix.issubset(supported):
+            continue
+
+        # Set all the values in the mix to 1, other supported to 0
+        config = {}
+        for key in all_keys:
+            config[key + "-count"] = 1 if key in mix else 0
+        test_config(config)
+
+    for mix in mixes:
+        if not mix.issubset(supported):
+            continue
+        if mix in failed:
+            continue
+
+        # Set all the values in the mix to max, other supported to 0
+        config = {}
+        for key in all_keys:
+            config[key + "-count"] = chans[key + '-max'] if key in mix else 0
+        test_config(config)
+
+
+def _configure_min_ring_cnt(cfg) -> None:
+    """ Try to configure a single Rx/Tx ring. """
+    ehdr = {'header':{'dev-index': cfg.ifindex}}
+    chans = cfg.eth.channels_get(ehdr)
+
+    all_keys = ["rx-count", "tx-count", "combined-count"]
+    restore = {}
+    config = {}
+    for key in all_keys:
+        if key in chans:
+            restore[key] = chans[key]
+            config[key] = 0
+
+    if chans.get('combined-count', 0) > 1:
+        config['combined-count'] = 1
+    elif chans.get('rx-count', 0) > 1 and chans.get('tx-count', 0) > 1:
+        config['tx-count'] = 1
+        config['rx-count'] = 1
+    else:
+        # looks like we're already on 1 channel
+        return
+
+    cfg.eth.channels_set(ehdr | config)
+    defer(cfg.eth.channels_set, ehdr | restore)
+
+
+def ringparam(cfg) -> None:
+    """
+    Tweak the ringparam configuration. Try to run some traffic over min
+    ring size to make sure it actually functions.
+    """
+    ehdr = {'header':{'dev-index': cfg.ifindex}}
+    rings = cfg.eth.rings_get(ehdr)
+
+    restore = {}
+    maxes = {}
+    params = set()
+    for key in rings.keys():
+        if 'max' in key:
+            param = key[:-4]
+            maxes[param] = rings[key]
+            params.add(param)
+            restore[param] = rings[param]
+
+    defer(cfg.eth.rings_set, ehdr | restore)
+
+    # Speed up the reconfig by configuring just one ring
+    _configure_min_ring_cnt(cfg)
+
+    # Try to reach min on all settings
+    for param in params:
+        val = rings[param]
+        while True:
+            try:
+                cfg.eth.rings_set({'header':{'dev-index': cfg.ifindex},
+                                   param: val // 2})
+                if val == 0:
+                    break
+                val //= 2
+            except NlError:
+                break
+
+        get = cfg.eth.rings_get(ehdr)
+        ksft_eq(get[param], val)
+
+        ksft_pr(f"Reached min for '{param}' at {val} (max {rings[param]})")
+
+    GenerateTraffic(cfg).wait_pkts_and_stop(10000)
+
+    # Try max across all params, if the driver supports large rings
+    # this may OOM so we ignore errors
+    try:
+        ksft_pr("Applying max settings")
+        config = {p: maxes[p] for p in params}
+        cfg.eth.rings_set(ehdr | config)
+    except NlError as e:
+        ksft_pr("Can't set max params", config, e)
+    else:
+        GenerateTraffic(cfg).wait_pkts_and_stop(10000)
+
+
+def main() -> None:
+    """ Ksft boiler plate main """
+
+    with NetDrvEpEnv(__file__) as cfg:
+        cfg.eth = EthtoolFamily()
+
+        ksft_run([channels,
+                  ringparam],
+                 args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/shaper.py b/tools/testing/selftests/drivers/net/shaper.py
new file mode 100755
index 000000000000..11310f19bfa0
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/shaper.py
@@ -0,0 +1,461 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_true, KsftSkipEx
+from lib.py import EthtoolFamily, NetshaperFamily
+from lib.py import NetDrvEnv
+from lib.py import NlError
+from lib.py import cmd
+
+def get_shapers(cfg, nl_shaper) -> None:
+    try:
+        shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    except NlError as e:
+        if e.error == 95:
+            raise KsftSkipEx("shapers not supported by the device")
+        raise
+
+    # Default configuration: no shapers configured.
+    ksft_eq(len(shapers), 0)
+
+def get_caps(cfg, nl_shaper) -> None:
+    try:
+        caps = nl_shaper.cap_get({'ifindex': cfg.ifindex}, dump=True)
+    except NlError as e:
+        if e.error == 95:
+            raise KsftSkipEx("shapers not supported by the device")
+        raise
+
+    # Each device implementing shaper support must support some
+    # features in at least a scope.
+    ksft_true(len(caps)> 0)
+
+def set_qshapers(cfg, nl_shaper) -> None:
+    try:
+        caps = nl_shaper.cap_get({'ifindex': cfg.ifindex,
+                                 'scope':'queue'})
+    except NlError as e:
+        if e.error == 95:
+            raise KsftSkipEx("shapers not supported by the device")
+        raise
+    if not 'support-bw-max' in caps or not 'support-metric-bps' in caps:
+        raise KsftSkipEx("device does not support queue scope shapers with bw_max and metric bps")
+
+    cfg.queues = True;
+    netnl = EthtoolFamily()
+    channels = netnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+    if channels['combined-count'] == 0:
+        cfg.rx_type = 'rx'
+        cfg.nr_queues = channels['rx-count']
+    else:
+        cfg.rx_type = 'combined'
+        cfg.nr_queues = channels['combined-count']
+    if cfg.nr_queues < 3:
+        raise KsftSkipEx(f"device does not support enough queues min 3 found {cfg.nr_queues}")
+
+    nl_shaper.set({'ifindex': cfg.ifindex,
+                   'handle': {'scope': 'queue', 'id': 1},
+                   'metric': 'bps',
+                   'bw-max': 10000})
+    nl_shaper.set({'ifindex': cfg.ifindex,
+                   'handle': {'scope': 'queue', 'id': 2},
+                   'metric': 'bps',
+                   'bw-max': 20000})
+
+    # Querying a specific shaper not yet configured must fail.
+    raised = False
+    try:
+        shaper_q0 = nl_shaper.get({'ifindex': cfg.ifindex,
+                                   'handle': {'scope': 'queue', 'id': 0}})
+    except (NlError):
+        raised = True
+    ksft_eq(raised, True)
+
+    shaper_q1 = nl_shaper.get({'ifindex': cfg.ifindex,
+                              'handle': {'scope': 'queue', 'id': 1}})
+    ksft_eq(shaper_q1, {'ifindex': cfg.ifindex,
+                        'parent': {'scope': 'netdev'},
+                        'handle': {'scope': 'queue', 'id': 1},
+                        'metric': 'bps',
+                        'bw-max': 10000})
+
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(shapers, [{'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'queue', 'id': 1},
+                       'metric': 'bps',
+                       'bw-max': 10000},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'queue', 'id': 2},
+                       'metric': 'bps',
+                       'bw-max': 20000}])
+
+def del_qshapers(cfg, nl_shaper) -> None:
+    if not cfg.queues:
+        raise KsftSkipEx("queue shapers not supported by device, skipping delete")
+
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'queue', 'id': 2}})
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'queue', 'id': 1}})
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(len(shapers), 0)
+
+def set_nshapers(cfg, nl_shaper) -> None:
+    # Check required features.
+    try:
+        caps = nl_shaper.cap_get({'ifindex': cfg.ifindex,
+                                  'scope':'netdev'})
+    except NlError as e:
+        if e.error == 95:
+            raise KsftSkipEx("shapers not supported by the device")
+        raise
+    if not 'support-bw-max' in caps or not 'support-metric-bps' in caps:
+        raise KsftSkipEx("device does not support nested netdev scope shapers with weight")
+
+    cfg.netdev = True;
+    nl_shaper.set({'ifindex': cfg.ifindex,
+                   'handle': {'scope': 'netdev', 'id': 0},
+                   'bw-max': 100000})
+
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(shapers, [{'ifindex': cfg.ifindex,
+                       'handle': {'scope': 'netdev'},
+                       'metric': 'bps',
+                       'bw-max': 100000}])
+
+def del_nshapers(cfg, nl_shaper) -> None:
+    if not cfg.netdev:
+        raise KsftSkipEx("netdev shaper not supported by device, skipping delete")
+
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'netdev'}})
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(len(shapers), 0)
+
+def basic_groups(cfg, nl_shaper) -> None:
+    if not cfg.netdev:
+        raise KsftSkipEx("netdev shaper not supported by the device")
+    if cfg.nr_queues < 3:
+        raise KsftSkipEx(f"netdev does not have enough queues min 3 reported {cfg.nr_queues}")
+
+    try:
+        caps = nl_shaper.cap_get({'ifindex': cfg.ifindex,
+                                  'scope':'queue'})
+    except NlError as e:
+        if e.error == 95:
+            raise KsftSkipEx("shapers not supported by the device")
+        raise
+    if not 'support-weight' in caps:
+        raise KsftSkipEx("device does not support queue scope shapers with weight")
+
+    node_handle = nl_shaper.group({
+                        'ifindex': cfg.ifindex,
+                        'leaves':[{'handle': {'scope': 'queue', 'id': 1},
+                                   'weight': 1},
+                                  {'handle': {'scope': 'queue', 'id': 2},
+                                   'weight': 2}],
+                         'handle': {'scope':'netdev'},
+                         'metric': 'bps',
+                         'bw-max': 10000})
+    ksft_eq(node_handle, {'ifindex': cfg.ifindex,
+                          'handle': {'scope': 'netdev'}})
+
+    shaper = nl_shaper.get({'ifindex': cfg.ifindex,
+                            'handle': {'scope': 'queue', 'id': 1}})
+    ksft_eq(shaper, {'ifindex': cfg.ifindex,
+                     'parent': {'scope': 'netdev'},
+                     'handle': {'scope': 'queue', 'id': 1},
+                     'weight': 1 })
+
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'queue', 'id': 2}})
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'queue', 'id': 1}})
+
+    # Deleting all the leaves shaper does not affect the node one
+    # when the latter has 'netdev' scope.
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(len(shapers), 1)
+
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'netdev'}})
+
+def qgroups(cfg, nl_shaper) -> None:
+    if cfg.nr_queues < 4:
+        raise KsftSkipEx(f"netdev does not have enough queues min 4 reported {cfg.nr_queues}")
+    try:
+        caps = nl_shaper.cap_get({'ifindex': cfg.ifindex,
+                                  'scope':'node'})
+    except NlError as e:
+        if e.error == 95:
+            raise KsftSkipEx("shapers not supported by the device")
+        raise
+    if not 'support-bw-max' in caps or not 'support-metric-bps' in caps:
+        raise KsftSkipEx("device does not support node scope shapers with bw_max and metric bps")
+    try:
+        caps = nl_shaper.cap_get({'ifindex': cfg.ifindex,
+                                  'scope':'queue'})
+    except NlError as e:
+        if e.error == 95:
+            raise KsftSkipEx("shapers not supported by the device")
+        raise
+    if not 'support-nesting' in caps or not 'support-weight' in caps or not 'support-metric-bps' in caps:
+            raise KsftSkipEx("device does not support nested queue scope shapers with weight")
+
+    cfg.groups = True;
+    node_handle = nl_shaper.group({
+                   'ifindex': cfg.ifindex,
+                   'leaves':[{'handle': {'scope': 'queue', 'id': 1},
+                              'weight': 3},
+                             {'handle': {'scope': 'queue', 'id': 2},
+                              'weight': 2}],
+                   'handle': {'scope':'node'},
+                   'metric': 'bps',
+                   'bw-max': 10000})
+    node_id = node_handle['handle']['id']
+
+    shaper = nl_shaper.get({'ifindex': cfg.ifindex,
+                            'handle': {'scope': 'queue', 'id': 1}})
+    ksft_eq(shaper, {'ifindex': cfg.ifindex,
+                     'parent': {'scope': 'node', 'id': node_id},
+                     'handle': {'scope': 'queue', 'id': 1},
+                     'weight': 3})
+    shaper = nl_shaper.get({'ifindex': cfg.ifindex,
+                            'handle': {'scope': 'node', 'id': node_id}})
+    ksft_eq(shaper, {'ifindex': cfg.ifindex,
+                     'handle': {'scope': 'node', 'id': node_id},
+                     'parent': {'scope': 'netdev'},
+                     'metric': 'bps',
+                     'bw-max': 10000})
+
+    # Grouping to a specified, not existing node scope shaper must fail
+    raised = False
+    try:
+        nl_shaper.group({
+                   'ifindex': cfg.ifindex,
+                   'leaves':[{'handle': {'scope': 'queue', 'id': 3},
+                              'weight': 3}],
+                   'handle': {'scope':'node', 'id': node_id + 1},
+                   'metric': 'bps',
+                   'bw-max': 10000})
+
+    except (NlError):
+        raised = True
+    ksft_eq(raised, True)
+
+    # Add to an existing node
+    node_handle = nl_shaper.group({
+                   'ifindex': cfg.ifindex,
+                   'leaves':[{'handle': {'scope': 'queue', 'id': 3},
+                              'weight': 4}],
+                   'handle': {'scope':'node', 'id': node_id}})
+    ksft_eq(node_handle, {'ifindex': cfg.ifindex,
+                          'handle': {'scope': 'node', 'id': node_id}})
+
+    shaper = nl_shaper.get({'ifindex': cfg.ifindex,
+                            'handle': {'scope': 'queue', 'id': 3}})
+    ksft_eq(shaper, {'ifindex': cfg.ifindex,
+                     'parent': {'scope': 'node', 'id': node_id},
+                     'handle': {'scope': 'queue', 'id': 3},
+                     'weight': 4})
+
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'queue', 'id': 2}})
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'queue', 'id': 1}})
+
+    # Deleting a non empty node will move the leaves downstream.
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'node', 'id': node_id}})
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(shapers, [{'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'queue', 'id': 3},
+                       'weight': 4}])
+
+    # Finish and verify the complete cleanup.
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'queue', 'id': 3}})
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(len(shapers), 0)
+
+def delegation(cfg, nl_shaper) -> None:
+    if not cfg.groups:
+        raise KsftSkipEx("device does not support node scope")
+    try:
+        caps = nl_shaper.cap_get({'ifindex': cfg.ifindex,
+                                  'scope':'node'})
+    except NlError as e:
+        if e.error == 95:
+            raise KsftSkipEx("node scope shapers not supported by the device")
+        raise
+    if not 'support-nesting' in caps:
+        raise KsftSkipEx("device does not support node scope shapers nesting")
+
+    node_handle = nl_shaper.group({
+                   'ifindex': cfg.ifindex,
+                   'leaves':[{'handle': {'scope': 'queue', 'id': 1},
+                              'weight': 3},
+                             {'handle': {'scope': 'queue', 'id': 2},
+                              'weight': 2},
+                             {'handle': {'scope': 'queue', 'id': 3},
+                              'weight': 1}],
+                   'handle': {'scope':'node'},
+                   'metric': 'bps',
+                   'bw-max': 10000})
+    node_id = node_handle['handle']['id']
+
+    # Create the nested node and validate the hierarchy
+    nested_node_handle = nl_shaper.group({
+                   'ifindex': cfg.ifindex,
+                   'leaves':[{'handle': {'scope': 'queue', 'id': 1},
+                              'weight': 3},
+                             {'handle': {'scope': 'queue', 'id': 2},
+                              'weight': 2}],
+                   'handle': {'scope':'node'},
+                   'metric': 'bps',
+                   'bw-max': 5000})
+    nested_node_id = nested_node_handle['handle']['id']
+    ksft_true(nested_node_id != node_id)
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(shapers, [{'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'node', 'id': nested_node_id},
+                       'handle': {'scope': 'queue', 'id': 1},
+                       'weight': 3},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'node', 'id': nested_node_id},
+                       'handle': {'scope': 'queue', 'id': 2},
+                       'weight': 2},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'node', 'id': node_id},
+                       'handle': {'scope': 'queue', 'id': 3},
+                       'weight': 1},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'node', 'id': node_id},
+                       'metric': 'bps',
+                       'bw-max': 10000},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'node', 'id': node_id},
+                       'handle': {'scope': 'node', 'id': nested_node_id},
+                       'metric': 'bps',
+                       'bw-max': 5000}])
+
+    # Deleting a non empty node will move the leaves downstream.
+    nl_shaper.delete({'ifindex': cfg.ifindex,
+                      'handle': {'scope': 'node', 'id': nested_node_id}})
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(shapers, [{'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'node', 'id': node_id},
+                       'handle': {'scope': 'queue', 'id': 1},
+                       'weight': 3},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'node', 'id': node_id},
+                       'handle': {'scope': 'queue', 'id': 2},
+                       'weight': 2},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'node', 'id': node_id},
+                       'handle': {'scope': 'queue', 'id': 3},
+                       'weight': 1},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'node', 'id': node_id},
+                       'metric': 'bps',
+                       'bw-max': 10000}])
+
+    # Final cleanup.
+    for i in range(1, 4):
+        nl_shaper.delete({'ifindex': cfg.ifindex,
+                          'handle': {'scope': 'queue', 'id': i}})
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(len(shapers), 0)
+
+def queue_update(cfg, nl_shaper) -> None:
+    if cfg.nr_queues < 4:
+        raise KsftSkipEx(f"netdev does not have enough queues min 4 reported {cfg.nr_queues}")
+    if not cfg.queues:
+        raise KsftSkipEx("device does not support queue scope")
+
+    for i in range(3):
+        nl_shaper.set({'ifindex': cfg.ifindex,
+                       'handle': {'scope': 'queue', 'id': i},
+                       'metric': 'bps',
+                       'bw-max': (i + 1) * 1000})
+    # Delete a channel, with no shapers configured on top of the related
+    # queue: no changes expected
+    cmd(f"ethtool -L {cfg.dev['ifname']} {cfg.rx_type} 3", timeout=10)
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(shapers, [{'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'queue', 'id': 0},
+                       'metric': 'bps',
+                       'bw-max': 1000},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'queue', 'id': 1},
+                       'metric': 'bps',
+                       'bw-max': 2000},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'queue', 'id': 2},
+                       'metric': 'bps',
+                       'bw-max': 3000}])
+
+    # Delete a channel, with a shaper configured on top of the related
+    # queue: the shaper must be deleted, too
+    cmd(f"ethtool -L {cfg.dev['ifname']} {cfg.rx_type} 2", timeout=10)
+
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(shapers, [{'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'queue', 'id': 0},
+                       'metric': 'bps',
+                       'bw-max': 1000},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'queue', 'id': 1},
+                       'metric': 'bps',
+                       'bw-max': 2000}])
+
+    # Restore the original channels number, no expected changes
+    cmd(f"ethtool -L {cfg.dev['ifname']} {cfg.rx_type} {cfg.nr_queues}", timeout=10)
+    shapers = nl_shaper.get({'ifindex': cfg.ifindex}, dump=True)
+    ksft_eq(shapers, [{'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'queue', 'id': 0},
+                       'metric': 'bps',
+                       'bw-max': 1000},
+                      {'ifindex': cfg.ifindex,
+                       'parent': {'scope': 'netdev'},
+                       'handle': {'scope': 'queue', 'id': 1},
+                       'metric': 'bps',
+                       'bw-max': 2000}])
+
+    # Final cleanup.
+    for i in range(0, 2):
+        nl_shaper.delete({'ifindex': cfg.ifindex,
+                          'handle': {'scope': 'queue', 'id': i}})
+
+def main() -> None:
+    with NetDrvEnv(__file__, queue_count=4) as cfg:
+        cfg.queues = False
+        cfg.netdev = False
+        cfg.groups = False
+        cfg.nr_queues = 0
+        ksft_run([get_shapers,
+                  get_caps,
+                  set_qshapers,
+                  del_qshapers,
+                  set_nshapers,
+                  del_nshapers,
+                  basic_groups,
+                  qgroups,
+                  delegation,
+                  queue_update], args=(cfg, NetshaperFamily()))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py
new file mode 100755
index 000000000000..b08e4d48b15c
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/stats.py
@@ -0,0 +1,321 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+Tests related to standard netdevice statistics.
+"""
+
+import errno
+import subprocess
+import time
+from lib.py import ksft_run, ksft_exit, ksft_pr
+from lib.py import ksft_ge, ksft_eq, ksft_is, ksft_in, ksft_lt, ksft_true, ksft_raises
+from lib.py import KsftSkipEx, KsftFailEx
+from lib.py import ksft_disruptive
+from lib.py import EthtoolFamily, NetdevFamily, RtnlFamily, NlError
+from lib.py import NetDrvEnv
+from lib.py import cmd, ip, defer
+
+ethnl = EthtoolFamily()
+netfam = NetdevFamily()
+rtnl = RtnlFamily()
+
+
+def check_pause(cfg) -> None:
+    """
+    Check that drivers which support Pause config also report standard
+    pause stats.
+    """
+
+    try:
+        ethnl.pause_get({"header": {"dev-index": cfg.ifindex}})
+    except NlError as e:
+        if e.error == errno.EOPNOTSUPP:
+            raise KsftSkipEx("pause not supported by the device") from e
+        raise
+
+    data = ethnl.pause_get({"header": {"dev-index": cfg.ifindex,
+                                       "flags": {'stats'}}})
+    ksft_true(data['stats'], "driver does not report stats")
+
+
+def check_fec(cfg) -> None:
+    """
+    Check that drivers which support FEC config also report standard
+    FEC stats.
+    """
+
+    try:
+        ethnl.fec_get({"header": {"dev-index": cfg.ifindex}})
+    except NlError as e:
+        if e.error == errno.EOPNOTSUPP:
+            raise KsftSkipEx("FEC not supported by the device") from e
+        raise
+
+    data = ethnl.fec_get({"header": {"dev-index": cfg.ifindex,
+                                     "flags": {'stats'}}})
+    ksft_true(data['stats'], "driver does not report stats")
+
+
+def check_fec_hist(cfg) -> None:
+    """
+    Check that drivers which support FEC histogram statistics report
+    reasonable values.
+    """
+
+    try:
+        data = ethnl.fec_get({"header": {"dev-index": cfg.ifindex,
+                                         "flags": {'stats'}}})
+    except NlError as e:
+        if e.error == errno.EOPNOTSUPP:
+            raise KsftSkipEx("FEC not supported by the device") from e
+        raise
+    if 'stats' not in data:
+        raise KsftSkipEx("FEC stats not supported by the device")
+    if 'hist' not in data['stats']:
+        raise KsftSkipEx("FEC histogram not supported by the device")
+
+    hist = data['stats']['hist']
+    for fec_bin in hist:
+        for key in ['bin-low', 'bin-high', 'bin-val']:
+            ksft_in(key, fec_bin,
+	            "Drivers should always report FEC bin range and value")
+        ksft_ge(fec_bin['bin-high'], fec_bin['bin-low'],
+                "FEC bin range should be valid")
+        if 'bin-val-per-lane' in fec_bin:
+            ksft_eq(sum(fec_bin['bin-val-per-lane']), fec_bin['bin-val'],
+                    "FEC bin value should be equal to sum of per-plane values")
+
+
+def pkt_byte_sum(cfg) -> None:
+    """
+    Check that qstat and interface stats match in value.
+    """
+
+    def get_qstat(test):
+        stats = netfam.qstats_get({}, dump=True)
+        if stats:
+            for qs in stats:
+                if qs["ifindex"]== test.ifindex:
+                    return qs
+        return None
+
+    qstat = get_qstat(cfg)
+    if qstat is None:
+        raise KsftSkipEx("qstats not supported by the device")
+
+    for key in ['tx-packets', 'tx-bytes', 'rx-packets', 'rx-bytes']:
+        ksft_in(key, qstat, "Drivers should always report basic keys")
+
+    # Compare stats, rtnl stats and qstats must match,
+    # but the interface may be up, so do a series of dumps
+    # each time the more "recent" stats must be higher or same.
+    def stat_cmp(rstat, qstat):
+        for key in ['tx-packets', 'tx-bytes', 'rx-packets', 'rx-bytes']:
+            if rstat[key] != qstat[key]:
+                return rstat[key] - qstat[key]
+        return 0
+
+    for _ in range(10):
+        rtstat = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64']
+        if stat_cmp(rtstat, qstat) < 0:
+            raise KsftFailEx("RTNL stats are lower, fetched later")
+        qstat = get_qstat(cfg)
+        if stat_cmp(rtstat, qstat) > 0:
+            raise KsftFailEx("Qstats are lower, fetched later")
+
+
+def qstat_by_ifindex(cfg) -> None:
+    """ Qstats Netlink API tests - querying by ifindex. """
+
+    # Construct a map ifindex -> [dump, by-index, dump]
+    ifindexes = {}
+    stats = netfam.qstats_get({}, dump=True)
+    for entry in stats:
+        ifindexes[entry['ifindex']] = [entry, None, None]
+
+    for ifindex in ifindexes:
+        entry = netfam.qstats_get({"ifindex": ifindex}, dump=True)
+        ksft_eq(len(entry), 1)
+        ifindexes[entry[0]['ifindex']][1] = entry[0]
+
+    stats = netfam.qstats_get({}, dump=True)
+    for entry in stats:
+        ifindexes[entry['ifindex']][2] = entry
+
+    if len(ifindexes) == 0:
+        raise KsftSkipEx("No ifindex supports qstats")
+
+    # Now make sure the stats match/make sense
+    for ifindex, triple in ifindexes.items():
+        all_keys = triple[0].keys() | triple[1].keys() | triple[2].keys()
+
+        for key in all_keys:
+            ksft_ge(triple[1][key], triple[0][key], comment="bad key: " + key)
+            ksft_ge(triple[2][key], triple[1][key], comment="bad key: " + key)
+
+    # Sanity check the dumps
+    queues = NetdevFamily(recv_size=4096).qstats_get({"scope": "queue"}, dump=True)
+    # Reformat the output into {ifindex: {rx: [id, id, ...], tx: [id, id, ...]}}
+    parsed = {}
+    for entry in queues:
+        ifindex = entry["ifindex"]
+        if ifindex not in parsed:
+            parsed[ifindex] = {"rx":[], "tx": []}
+        parsed[ifindex][entry["queue-type"]].append(entry['queue-id'])
+    # Now, validate
+    for ifindex, queues in parsed.items():
+        for qtype in ['rx', 'tx']:
+            ksft_eq(len(queues[qtype]), len(set(queues[qtype])),
+                    comment="repeated queue keys")
+            ksft_eq(len(queues[qtype]), max(queues[qtype]) + 1,
+                    comment="missing queue keys")
+
+    # Test invalid dumps
+    # 0 is invalid
+    with ksft_raises(NlError) as cm:
+        netfam.qstats_get({"ifindex": 0}, dump=True)
+    ksft_eq(cm.exception.nl_msg.error, -34)
+    ksft_eq(cm.exception.nl_msg.extack['bad-attr'], '.ifindex')
+
+    # loopback has no stats
+    with ksft_raises(NlError) as cm:
+        netfam.qstats_get({"ifindex": 1}, dump=True)
+    ksft_eq(cm.exception.nl_msg.error, -errno.EOPNOTSUPP)
+    ksft_eq(cm.exception.nl_msg.extack['bad-attr'], '.ifindex')
+
+    # Try to get stats for lowest unused ifindex but not 0
+    devs = rtnl.getlink({}, dump=True)
+    all_ifindexes = set(dev["ifi-index"] for dev in devs)
+    lowest = 2
+    while lowest in all_ifindexes:
+        lowest += 1
+
+    with ksft_raises(NlError) as cm:
+        netfam.qstats_get({"ifindex": lowest}, dump=True)
+    ksft_eq(cm.exception.nl_msg.error, -19)
+    ksft_eq(cm.exception.nl_msg.extack['bad-attr'], '.ifindex')
+
+
+@ksft_disruptive
+def check_down(cfg) -> None:
+    """ Test statistics (interface and qstat) are not impacted by ifdown """
+
+    try:
+        qstat = netfam.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0]
+    except NlError as e:
+        if e.error == errno.EOPNOTSUPP:
+            raise KsftSkipEx("qstats not supported by the device") from e
+        raise
+
+    ip(f"link set dev {cfg.dev['ifname']} down")
+    defer(ip, f"link set dev {cfg.dev['ifname']} up")
+
+    qstat2 = netfam.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0]
+    for k in qstat:
+        ksft_ge(qstat2[k], qstat[k], comment=f"{k} went backwards on device down")
+
+    # exercise per-queue API to make sure that "device down" state
+    # is handled correctly and doesn't crash
+    netfam.qstats_get({"ifindex": cfg.ifindex, "scope": "queue"}, dump=True)
+
+
+def __run_inf_loop(body):
+    body = body.strip()
+    if body[-1] != ';':
+        body += ';'
+
+    return subprocess.Popen(f"while true; do {body} done", shell=True,
+                            stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+
+
+def __stats_increase_sanely(old, new) -> None:
+    for k in old.keys():
+        ksft_ge(new[k], old[k])
+        ksft_lt(new[k] - old[k], 1 << 31, comment="likely wrapping error")
+
+
+def procfs_hammer(cfg) -> None:
+    """
+    Reading stats via procfs only holds the RCU lock, which is not an exclusive
+    lock, make sure drivers can handle parallel reads of stats.
+    """
+    one = __run_inf_loop("cat /proc/net/dev")
+    defer(one.kill)
+    two = __run_inf_loop("cat /proc/net/dev")
+    defer(two.kill)
+
+    time.sleep(1)
+    # Make sure the processes are running
+    ksft_is(one.poll(), None)
+    ksft_is(two.poll(), None)
+
+    rtstat1 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64']
+    time.sleep(2)
+    rtstat2 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64']
+    __stats_increase_sanely(rtstat1, rtstat2)
+    # defers will kill the loops
+
+
+@ksft_disruptive
+def procfs_downup_hammer(cfg) -> None:
+    """
+    Reading stats via procfs only holds the RCU lock, drivers often try
+    to sleep when reading the stats, or don't protect against races.
+    """
+    # Set a large number of queues,
+    # we'll flip between min(max_queues, 64) and 1
+    channels = ethnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+    if channels['combined-count'] == 0:
+        rx_type = 'rx'
+    else:
+        rx_type = 'combined'
+    cur_queue_cnt = channels[f'{rx_type}-count']
+    max_queue_cnt = min(channels[f'{rx_type}-max'], 64)
+
+    cmd(f"ethtool -L {cfg.ifname} {rx_type} {max_queue_cnt}")
+    defer(cmd, f"ethtool -L {cfg.ifname} {rx_type} {cur_queue_cnt}")
+
+    # Real test stats
+    stats = __run_inf_loop("cat /proc/net/dev")
+    defer(stats.kill)
+
+    ipset = f"ip link set dev {cfg.ifname}"
+    defer(ip, f"link set dev {cfg.ifname} up")
+    # The "echo -n 1" lets us count iterations below
+    updown = f"{ipset} down; sleep 0.05; {ipset} up; sleep 0.05; " + \
+             f"ethtool -L {cfg.ifname} {rx_type} 1; " + \
+             f"ethtool -L {cfg.ifname} {rx_type} {max_queue_cnt}; " + \
+              "echo -n 1"
+    updown = __run_inf_loop(updown)
+    kill_updown = defer(updown.kill)
+
+    time.sleep(1)
+    # Make sure the processes are running
+    ksft_is(stats.poll(), None)
+    ksft_is(updown.poll(), None)
+
+    rtstat1 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64']
+    # We're looking for crashes, give it extra time
+    time.sleep(9)
+    rtstat2 = rtnl.getlink({"ifi-index": cfg.ifindex})['stats64']
+    __stats_increase_sanely(rtstat1, rtstat2)
+
+    kill_updown.exec()
+    stdout, _ = updown.communicate(timeout=5)
+    ksft_pr("completed up/down cycles:", len(stdout.decode('utf-8')))
+
+
+def main() -> None:
+    """ Ksft boiler plate main """
+
+    with NetDrvEnv(__file__, queue_count=100) as cfg:
+        ksft_run([check_pause, check_fec, check_fec_hist, pkt_byte_sum,
+		  qstat_by_ifindex, check_down, procfs_hammer,
+		  procfs_downup_hammer],
+                 args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/team/Makefile b/tools/testing/selftests/drivers/net/team/Makefile
index 6a86e61e8bfe..1340b3df9c31 100644
--- a/tools/testing/selftests/drivers/net/team/Makefile
+++ b/tools/testing/selftests/drivers/net/team/Makefile
@@ -1,10 +1,18 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for net selftests
 
-TEST_PROGS := dev_addr_lists.sh
+TEST_PROGS := \
+	dev_addr_lists.sh \
+	options.sh \
+	propagation.sh \
+# end of TEST_PROGS
 
-TEST_FILES := \
-	lag_lib.sh \
-	net_forwarding_lib.sh
+TEST_INCLUDES := \
+	../bonding/lag_lib.sh \
+	../../../net/forwarding/lib.sh \
+	../../../net/in_netns.sh \
+	../../../net/lib.sh \
+	../../../net/lib/sh/defer.sh \
+# end of TEST_INCLUDES
 
 include ../../../lib.mk
diff --git a/tools/testing/selftests/drivers/net/team/config b/tools/testing/selftests/drivers/net/team/config
index 265b6882cc21..558e1d0cf565 100644
--- a/tools/testing/selftests/drivers/net/team/config
+++ b/tools/testing/selftests/drivers/net/team/config
@@ -1,3 +1,7 @@
+CONFIG_DUMMY=y
+CONFIG_IPV6=y
+CONFIG_MACVLAN=y
+CONFIG_NETDEVSIM=m
 CONFIG_NET_TEAM=y
+CONFIG_NET_TEAM_MODE_ACTIVEBACKUP=y
 CONFIG_NET_TEAM_MODE_LOADBALANCE=y
-CONFIG_MACVLAN=y
diff --git a/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh b/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh
index 33913112d5ca..b1ec7755b783 100755
--- a/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh
+++ b/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh
@@ -11,9 +11,9 @@ ALL_TESTS="
 REQUIRE_MZ=no
 NUM_NETIFS=0
 lib_dir=$(dirname "$0")
-source "$lib_dir"/net_forwarding_lib.sh
+source "$lib_dir"/../../../net/forwarding/lib.sh
 
-source "$lib_dir"/lag_lib.sh
+source "$lib_dir"/../bonding/lag_lib.sh
 
 
 destroy()
diff --git a/tools/testing/selftests/drivers/net/team/lag_lib.sh b/tools/testing/selftests/drivers/net/team/lag_lib.sh
deleted file mode 120000
index e1347a10afde..000000000000
--- a/tools/testing/selftests/drivers/net/team/lag_lib.sh
+++ /dev/null
@@ -1 +0,0 @@
-../bonding/lag_lib.sh
-\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/team/net_forwarding_lib.sh b/tools/testing/selftests/drivers/net/team/net_forwarding_lib.sh
deleted file mode 120000
index 39c96828c5ef..000000000000
--- a/tools/testing/selftests/drivers/net/team/net_forwarding_lib.sh
+++ /dev/null
@@ -1 +0,0 @@
-../../../net/forwarding/lib.sh
-\ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/team/options.sh b/tools/testing/selftests/drivers/net/team/options.sh
new file mode 100755
index 000000000000..44888f32b513
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/team/options.sh
@@ -0,0 +1,188 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# These tests verify basic set and get functionality of the team
+# driver options over netlink.
+
+# Run in private netns.
+test_dir="$(dirname "$0")"
+if [[ $# -eq 0 ]]; then
+        "${test_dir}"/../../../net/in_netns.sh "$0" __subprocess
+        exit $?
+fi
+
+ALL_TESTS="
+        team_test_options
+"
+
+source "${test_dir}/../../../net/lib.sh"
+
+TEAM_PORT="team0"
+MEMBER_PORT="dummy0"
+
+setup()
+{
+        ip link add name "${MEMBER_PORT}" type dummy
+        ip link add name "${TEAM_PORT}" type team
+}
+
+get_and_check_value()
+{
+        local option_name="$1"
+        local expected_value="$2"
+        local port_flag="$3"
+
+        local value_from_get
+
+        if ! value_from_get=$(teamnl "${TEAM_PORT}" getoption "${option_name}" \
+                        "${port_flag}"); then
+                echo "Could not get option '${option_name}'" >&2
+                return 1
+        fi
+
+        if [[ "${value_from_get}" != "${expected_value}" ]]; then
+                echo "Incorrect value for option '${option_name}'" >&2
+                echo "get (${value_from_get}) != set (${expected_value})" >&2
+                return 1
+        fi
+}
+
+set_and_check_get()
+{
+        local option_name="$1"
+        local option_value="$2"
+        local port_flag="$3"
+
+        local value_from_get
+
+        if ! teamnl "${TEAM_PORT}" setoption "${option_name}" \
+                        "${option_value}" "${port_flag}"; then
+                echo "'setoption ${option_name} ${option_value}' failed" >&2
+                return 1
+        fi
+
+        get_and_check_value "${option_name}" "${option_value}" "${port_flag}"
+        return $?
+}
+
+# Get a "port flag" to pass to the `teamnl` command.
+# E.g. $1="dummy0" -> "port=dummy0",
+#      $1=""       -> ""
+get_port_flag()
+{
+        local port_name="$1"
+
+        if [[ -n "${port_name}" ]]; then
+                echo "--port=${port_name}"
+        fi
+}
+
+attach_port_if_specified()
+{
+        local port_name="$1"
+
+        if [[ -n "${port_name}" ]]; then
+                ip link set dev "${port_name}" master "${TEAM_PORT}"
+                return $?
+        fi
+}
+
+detach_port_if_specified()
+{
+        local port_name="$1"
+
+        if [[ -n "${port_name}" ]]; then
+                ip link set dev "${port_name}" nomaster
+                return $?
+        fi
+}
+
+# Test that an option's get value matches its set value.
+# Globals:
+#   RET - Used by testing infra like `check_err`.
+#   EXIT_STATUS - Used by `log_test` for whole script exit value.
+# Arguments:
+#   option_name - The name of the option.
+#   value_1 - The first value to try setting.
+#   value_2 - The second value to try setting.
+#   port_name - The (optional) name of the attached port.
+team_test_option()
+{
+        local option_name="$1"
+        local value_1="$2"
+        local value_2="$3"
+        local possible_values="$2 $3 $2"
+        local port_name="$4"
+        local port_flag
+
+        RET=0
+
+        echo "Setting '${option_name}' to '${value_1}' and '${value_2}'"
+
+        attach_port_if_specified "${port_name}"
+        check_err $? "Couldn't attach ${port_name} to master"
+        port_flag=$(get_port_flag "${port_name}")
+
+        # Set and get both possible values.
+        for value in ${possible_values}; do
+                set_and_check_get "${option_name}" "${value}" "${port_flag}"
+                check_err $? "Failed to set '${option_name}' to '${value}'"
+        done
+
+        detach_port_if_specified "${port_name}"
+        check_err $? "Couldn't detach ${port_name} from its master"
+
+        log_test "Set + Get '${option_name}' test"
+}
+
+# Test that getting a non-existant option fails.
+# Globals:
+#   RET - Used by testing infra like `check_err`.
+#   EXIT_STATUS - Used by `log_test` for whole script exit value.
+# Arguments:
+#   option_name - The name of the option.
+#   port_name - The (optional) name of the attached port.
+team_test_get_option_fails()
+{
+        local option_name="$1"
+        local port_name="$2"
+        local port_flag
+
+        RET=0
+
+        attach_port_if_specified "${port_name}"
+        check_err $? "Couldn't attach ${port_name} to master"
+        port_flag=$(get_port_flag "${port_name}")
+
+        # Just confirm that getting the value fails.
+        teamnl "${TEAM_PORT}" getoption "${option_name}" "${port_flag}"
+        check_fail $? "Shouldn't be able to get option '${option_name}'"
+
+        detach_port_if_specified "${port_name}"
+
+        log_test "Get '${option_name}' fails"
+}
+
+team_test_options()
+{
+        # Wrong option name behavior.
+        team_test_get_option_fails fake_option1
+        team_test_get_option_fails fake_option2 "${MEMBER_PORT}"
+
+        # Correct set and get behavior.
+        team_test_option mode activebackup loadbalance
+        team_test_option notify_peers_count 0 5
+        team_test_option notify_peers_interval 0 5
+        team_test_option mcast_rejoin_count 0 5
+        team_test_option mcast_rejoin_interval 0 5
+        team_test_option enabled true false "${MEMBER_PORT}"
+        team_test_option user_linkup true false "${MEMBER_PORT}"
+        team_test_option user_linkup_enabled true false "${MEMBER_PORT}"
+        team_test_option priority 10 20 "${MEMBER_PORT}"
+        team_test_option queue_id 0 1 "${MEMBER_PORT}"
+}
+
+require_command teamnl
+setup
+tests_run
+exit "${EXIT_STATUS}"
diff --git a/tools/testing/selftests/drivers/net/team/propagation.sh b/tools/testing/selftests/drivers/net/team/propagation.sh
new file mode 100755
index 000000000000..4bea75b79878
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/team/propagation.sh
@@ -0,0 +1,80 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+NSIM_LRO_ID=$((256 + RANDOM % 256))
+NSIM_LRO_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_LRO_ID
+
+NSIM_DEV_SYS_NEW=/sys/bus/netdevsim/new_device
+NSIM_DEV_SYS_DEL=/sys/bus/netdevsim/del_device
+
+cleanup()
+{
+	set +e
+	ip link del dummyteam &>/dev/null
+	ip link del team0 &>/dev/null
+	echo $NSIM_LRO_ID > $NSIM_DEV_SYS_DEL
+	modprobe -r netdevsim
+}
+
+# Trigger LRO propagation to the lower.
+# https://lore.kernel.org/netdev/aBvOpkIoxcr9PfDg@mini-arch/
+team_lro()
+{
+	# using netdevsim because it supports NETIF_F_LRO
+	NSIM_LRO_NAME=$(find $NSIM_LRO_SYS/net -maxdepth 1 -type d ! \
+		-path $NSIM_LRO_SYS/net -exec basename {} \;)
+
+	ip link add name team0 type team
+	ip link set $NSIM_LRO_NAME down
+	ip link set dev $NSIM_LRO_NAME master team0
+	ip link set team0 up
+	ethtool -K team0 large-receive-offload off
+
+	ip link del team0
+}
+
+# Trigger promisc propagation to the lower during IFLA_MASTER.
+# https://lore.kernel.org/netdev/20250506032328.3003050-1-sdf@fomichev.me/
+team_promisc()
+{
+	ip link add name dummyteam type dummy
+	ip link add name team0 type team
+	ip link set dummyteam down
+	ip link set team0 promisc on
+	ip link set dev dummyteam master team0
+	ip link set team0 up
+
+	ip link del team0
+	ip link del dummyteam
+}
+
+# Trigger promisc propagation to the lower via netif_change_flags (aka
+# ndo_change_rx_flags).
+# https://lore.kernel.org/netdev/20250514220319.3505158-1-stfomichev@gmail.com/
+team_change_flags()
+{
+	ip link add name dummyteam type dummy
+	ip link add name team0 type team
+	ip link set dummyteam down
+	ip link set dev dummyteam master team0
+	ip link set team0 up
+	ip link set team0 promisc on
+
+	# Make sure we can add more L2 addresses without any issues.
+	ip link add link team0 address 00:00:00:00:00:01 team0.1 type macvlan
+	ip link set team0.1 up
+
+	ip link del team0.1
+	ip link del team0
+	ip link del dummyteam
+}
+
+trap cleanup EXIT
+modprobe netdevsim || :
+echo $NSIM_LRO_ID > $NSIM_DEV_SYS_NEW
+udevadm settle
+team_lro
+team_promisc
+team_change_flags
diff --git a/tools/testing/selftests/drivers/net/virtio_net/Makefile b/tools/testing/selftests/drivers/net/virtio_net/Makefile
new file mode 100644
index 000000000000..868ece3fea1f
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/virtio_net/Makefile
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0+ OR MIT
+
+TEST_PROGS = basic_features.sh
+
+TEST_FILES = virtio_net_common.sh
+
+TEST_INCLUDES = \
+	../../../net/forwarding/lib.sh \
+	../../../net/lib.sh \
+# end of TEST_INCLUDES
+
+include ../../../lib.mk
diff --git a/tools/testing/selftests/drivers/net/virtio_net/basic_features.sh b/tools/testing/selftests/drivers/net/virtio_net/basic_features.sh
new file mode 100755
index 000000000000..cf8cf816ed48
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/virtio_net/basic_features.sh
@@ -0,0 +1,131 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# See virtio_net_common.sh comments for more details about assumed setup
+
+ALL_TESTS="
+	initial_ping_test
+	f_mac_test
+"
+
+source virtio_net_common.sh
+
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/forwarding/lib.sh
+
+h1=${NETIFS[p1]}
+h2=${NETIFS[p2]}
+
+h1_create()
+{
+	simple_if_init $h1 $H1_IPV4/24 $H1_IPV6/64
+}
+
+h1_destroy()
+{
+	simple_if_fini $h1 $H1_IPV4/24 $H1_IPV6/64
+}
+
+h2_create()
+{
+	simple_if_init $h2 $H2_IPV4/24 $H2_IPV6/64
+}
+
+h2_destroy()
+{
+	simple_if_fini $h2 $H2_IPV4/24 $H2_IPV6/64
+}
+
+initial_ping_test()
+{
+	setup_cleanup
+	setup_prepare
+	ping_test $h1 $H2_IPV4 " simple"
+}
+
+f_mac_test()
+{
+	RET=0
+	local test_name="mac feature filtered"
+
+	virtio_feature_present $h1 $VIRTIO_NET_F_MAC
+	if [ $? -ne 0 ]; then
+		log_test_skip "$test_name" "Device $h1 is missing feature $VIRTIO_NET_F_MAC."
+		return 0
+	fi
+	virtio_feature_present $h1 $VIRTIO_NET_F_MAC
+	if [ $? -ne 0 ]; then
+		log_test_skip "$test_name" "Device $h2 is missing feature $VIRTIO_NET_F_MAC."
+		return 0
+	fi
+
+	setup_cleanup
+	setup_prepare
+
+	grep -q 0 /sys/class/net/$h1/addr_assign_type
+	check_err $? "Permanent address assign type for $h1 is not set"
+	grep -q 0 /sys/class/net/$h2/addr_assign_type
+	check_err $? "Permanent address assign type for $h2 is not set"
+
+	setup_cleanup
+	virtio_filter_feature_add $h1 $VIRTIO_NET_F_MAC
+	virtio_filter_feature_add $h2 $VIRTIO_NET_F_MAC
+	setup_prepare
+
+	grep -q 0 /sys/class/net/$h1/addr_assign_type
+	check_fail $? "Permanent address assign type for $h1 is set when F_MAC feature is filtered"
+	grep -q 0 /sys/class/net/$h2/addr_assign_type
+	check_fail $? "Permanent address assign type for $h2 is set when F_MAC feature is filtered"
+
+	ping_do $h1 $H2_IPV4
+	check_err $? "Ping failed"
+
+	log_test "$test_name"
+}
+
+setup_prepare()
+{
+	virtio_device_rebind $h1
+	virtio_device_rebind $h2
+	wait_for_dev $h1
+	wait_for_dev $h2
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+}
+
+setup_cleanup()
+{
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+
+	virtio_filter_features_clear $h1
+	virtio_filter_features_clear $h2
+	virtio_device_rebind $h1
+	virtio_device_rebind $h2
+	wait_for_dev $h1
+	wait_for_dev $h2
+}
+
+cleanup()
+{
+	pre_cleanup
+	setup_cleanup
+}
+
+check_driver $h1 "virtio_net"
+check_driver $h2 "virtio_net"
+check_virtio_debugfs $h1
+check_virtio_debugfs $h2
+
+trap cleanup EXIT
+
+setup_prepare
+
+tests_run
+
+exit "$EXIT_STATUS"
diff --git a/tools/testing/selftests/drivers/net/virtio_net/config b/tools/testing/selftests/drivers/net/virtio_net/config
new file mode 100644
index 000000000000..bcf7555eaffe
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/virtio_net/config
@@ -0,0 +1,8 @@
+CONFIG_BPF_SYSCALL=y
+CONFIG_CGROUP_BPF=y
+CONFIG_IPV6=y
+CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_NET_L3_MASTER_DEV=y
+CONFIG_NET_VRF=m
+CONFIG_VIRTIO_DEBUG=y
+CONFIG_VIRTIO_NET=y
diff --git a/tools/testing/selftests/drivers/net/virtio_net/virtio_net_common.sh b/tools/testing/selftests/drivers/net/virtio_net/virtio_net_common.sh
new file mode 100644
index 000000000000..57bd8055e2e5
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/virtio_net/virtio_net_common.sh
@@ -0,0 +1,99 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This assumes running on a host with two virtio interfaces connected
+# back to back. Example script to do such wire-up of tap devices would
+# look like this:
+#
+# =======================================================================================================
+# #!/bin/bash
+#
+# DEV1="$1"
+# DEV2="$2"
+#
+# sudo tc qdisc add dev $DEV1 clsact
+# sudo tc qdisc add dev $DEV2 clsact
+# sudo tc filter add dev $DEV1 ingress protocol all pref 1 matchall action mirred egress redirect dev $DEV2
+# sudo tc filter add dev $DEV2 ingress protocol all pref 1 matchall action mirred egress redirect dev $DEV1
+# sudo ip link set $DEV1 up
+# sudo ip link set $DEV2 up
+# =======================================================================================================
+
+REQUIRE_MZ="no"
+NETIF_CREATE="no"
+NETIF_FIND_DRIVER="virtio_net"
+NUM_NETIFS=2
+
+H1_IPV4="192.0.2.1"
+H2_IPV4="192.0.2.2"
+H1_IPV6="2001:db8:1::1"
+H2_IPV6="2001:db8:1::2"
+
+VIRTIO_NET_F_MAC=5
+
+virtio_device_get()
+{
+	local dev=$1; shift
+	local device_path="/sys/class/net/$dev/device/"
+
+	basename `realpath $device_path`
+}
+
+virtio_device_rebind()
+{
+	local dev=$1; shift
+	local device=`virtio_device_get $dev`
+
+	echo "$device" > /sys/bus/virtio/drivers/virtio_net/unbind
+	echo "$device" > /sys/bus/virtio/drivers/virtio_net/bind
+}
+
+virtio_debugfs_get()
+{
+	local dev=$1; shift
+	local device=`virtio_device_get $dev`
+
+	echo /sys/kernel/debug/virtio/$device/
+}
+
+check_virtio_debugfs()
+{
+	local dev=$1; shift
+	local debugfs=`virtio_debugfs_get $dev`
+
+	if [ ! -f "$debugfs/device_features" ] ||
+	   [ ! -f "$debugfs/filter_feature_add"  ] ||
+	   [ ! -f "$debugfs/filter_feature_del"  ] ||
+	   [ ! -f "$debugfs/filter_features"  ] ||
+	   [ ! -f "$debugfs/filter_features_clear"  ]; then
+		echo "SKIP: not possible to access debugfs for $dev"
+		exit $ksft_skip
+	fi
+}
+
+virtio_feature_present()
+{
+	local dev=$1; shift
+	local feature=$1; shift
+	local debugfs=`virtio_debugfs_get $dev`
+
+	cat $debugfs/device_features |grep "^$feature$" &> /dev/null
+	return $?
+}
+
+virtio_filter_features_clear()
+{
+	local dev=$1; shift
+	local debugfs=`virtio_debugfs_get $dev`
+
+	echo "1" > $debugfs/filter_features_clear
+}
+
+virtio_filter_feature_add()
+{
+	local dev=$1; shift
+	local feature=$1; shift
+	local debugfs=`virtio_debugfs_get $dev`
+
+	echo "$feature" > $debugfs/filter_feature_add
+}
diff --git a/tools/testing/selftests/drivers/net/xdp.py b/tools/testing/selftests/drivers/net/xdp.py
new file mode 100755
index 000000000000..e54df158dfe9
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/xdp.py
@@ -0,0 +1,779 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+This file contains tests to verify native XDP support in network drivers.
+The tests utilize the BPF program `xdp_native.bpf.o` from the `selftests.net.lib`
+directory, with each test focusing on a specific aspect of XDP functionality.
+"""
+import random
+import string
+from dataclasses import dataclass
+from enum import Enum
+
+from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ge, ksft_ne, ksft_pr
+from lib.py import KsftNamedVariant, ksft_variants
+from lib.py import KsftFailEx, NetDrvEpEnv
+from lib.py import EthtoolFamily, NetdevFamily, NlError
+from lib.py import bkg, cmd, rand_port, wait_port_listen
+from lib.py import ip, bpftool, defer
+
+
+class TestConfig(Enum):
+    """Enum for XDP configuration options."""
+    MODE = 0  # Configures the BPF program for a specific test
+    PORT = 1  # Port configuration to communicate with the remote host
+    ADJST_OFFSET = 2  # Tail/Head adjustment offset for extension/shrinking
+    ADJST_TAG = 3  # Adjustment tag to annotate the start and end of extension
+
+
+class XDPAction(Enum):
+    """Enum for XDP actions."""
+    PASS = 0  # Pass the packet up to the stack
+    DROP = 1  # Drop the packet
+    TX = 2    # Route the packet to the remote host
+    TAIL_ADJST = 3  # Adjust the tail of the packet
+    HEAD_ADJST = 4  # Adjust the head of the packet
+
+
+class XDPStats(Enum):
+    """Enum for XDP statistics."""
+    RX = 0    # Count of valid packets received for testing
+    PASS = 1  # Count of packets passed up to the stack
+    DROP = 2  # Count of packets dropped
+    TX = 3    # Count of incoming packets routed to the remote host
+    ABORT = 4 # Count of packets that were aborted
+
+
+@dataclass
+class BPFProgInfo:
+    """Data class to store information about a BPF program."""
+    name: str               # Name of the BPF program
+    file: str               # BPF program object file
+    xdp_sec: str = "xdp"    # XDP section name (e.g., "xdp" or "xdp.frags")
+    mtu: int = 1500         # Maximum Transmission Unit, default is 1500
+
+
+def _exchg_udp(cfg, port, test_string):
+    """
+    Exchanges UDP packets between a local and remote host using the socat tool.
+
+    Args:
+        cfg: Configuration object containing network settings.
+        port: Port number to use for the UDP communication.
+        test_string: String that the remote host will send.
+
+    Returns:
+        The string received by the test host.
+    """
+    cfg.require_cmd("socat", remote=True)
+
+    rx_udp_cmd = f"socat -{cfg.addr_ipver} -T 2 -u UDP-RECV:{port},reuseport STDOUT"
+    tx_udp_cmd = f"echo -n {test_string} | socat -t 2 -u STDIN UDP:{cfg.baddr}:{port}"
+
+    with bkg(rx_udp_cmd, exit_wait=True) as nc:
+        wait_port_listen(port, proto="udp")
+        cmd(tx_udp_cmd, host=cfg.remote, shell=True)
+
+    return nc.stdout.strip()
+
+
+def _test_udp(cfg, port, size=256):
+    """
+    Tests UDP packet exchange between a local and remote host.
+
+    Args:
+        cfg: Configuration object containing network settings.
+        port: Port number to use for the UDP communication.
+        size: The length of the test string to be exchanged, default is 256 characters.
+
+    Returns:
+        bool: True if the received string matches the sent string, False otherwise.
+    """
+    test_str = "".join(random.choice(string.ascii_lowercase) for _ in range(size))
+    recvd_str = _exchg_udp(cfg, port, test_str)
+
+    return recvd_str == test_str
+
+
+def _load_xdp_prog(cfg, bpf_info):
+    """
+    Loads an XDP program onto a network interface.
+
+    Args:
+        cfg: Configuration object containing network settings.
+        bpf_info: BPFProgInfo object containing information about the BPF program.
+
+    Returns:
+        dict: A dictionary containing the XDP program ID, name, and associated map IDs.
+    """
+    abs_path = cfg.net_lib_dir / bpf_info.file
+    prog_info = {}
+
+    cmd(f"ip link set dev {cfg.remote_ifname} mtu {bpf_info.mtu}", shell=True, host=cfg.remote)
+    defer(ip, f"link set dev {cfg.remote_ifname} mtu 1500", host=cfg.remote)
+
+    cmd(
+    f"ip link set dev {cfg.ifname} mtu {bpf_info.mtu} xdpdrv obj {abs_path} sec {bpf_info.xdp_sec}",
+    shell=True
+    )
+    defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdpdrv off")
+
+    xdp_info = ip(f"-d link show dev {cfg.ifname}", json=True)[0]
+    prog_info["id"] = xdp_info["xdp"]["prog"]["id"]
+    prog_info["name"] = xdp_info["xdp"]["prog"]["name"]
+    prog_id = prog_info["id"]
+
+    map_ids = bpftool(f"prog show id {prog_id}", json=True)["map_ids"]
+    prog_info["maps"] = {}
+    for map_id in map_ids:
+        name = bpftool(f"map show id {map_id}", json=True)["name"]
+        prog_info["maps"][name] = map_id
+
+    return prog_info
+
+
+def format_hex_bytes(value):
+    """
+    Helper function that converts an integer into a formatted hexadecimal byte string.
+
+    Args:
+        value: An integer representing the number to be converted.
+
+    Returns:
+        A string representing hexadecimal equivalent of value, with bytes separated by spaces.
+    """
+    hex_str = value.to_bytes(4, byteorder='little', signed=True)
+    return ' '.join(f'{byte:02x}' for byte in hex_str)
+
+
+def _set_xdp_map(map_name, key, value):
+    """
+    Updates an XDP map with a given key-value pair using bpftool.
+
+    Args:
+        map_name: The name of the XDP map to update.
+        key: The key to update in the map, formatted as a hexadecimal string.
+        value: The value to associate with the key, formatted as a hexadecimal string.
+    """
+    key_formatted = format_hex_bytes(key)
+    value_formatted = format_hex_bytes(value)
+    bpftool(
+        f"map update name {map_name} key hex {key_formatted} value hex {value_formatted}"
+    )
+
+
+def _get_stats(xdp_map_id):
+    """
+    Retrieves and formats statistics from an XDP map.
+
+    Args:
+        xdp_map_id: The ID of the XDP map from which to retrieve statistics.
+
+    Returns:
+        A dictionary containing formatted packet statistics for various XDP actions.
+        The keys are based on the XDPStats Enum values.
+
+    Raises:
+        KsftFailEx: If the stats retrieval fails.
+    """
+    stats_dump = bpftool(f"map dump id {xdp_map_id}", json=True)
+    if not stats_dump:
+        raise KsftFailEx(f"Failed to get stats for map {xdp_map_id}")
+
+    stats_formatted = {}
+    for key in range(0, 5):
+        val = stats_dump[key]["formatted"]["value"]
+        if stats_dump[key]["formatted"]["key"] == XDPStats.RX.value:
+            stats_formatted[XDPStats.RX.value] = val
+        elif stats_dump[key]["formatted"]["key"] == XDPStats.PASS.value:
+            stats_formatted[XDPStats.PASS.value] = val
+        elif stats_dump[key]["formatted"]["key"] == XDPStats.DROP.value:
+            stats_formatted[XDPStats.DROP.value] = val
+        elif stats_dump[key]["formatted"]["key"] == XDPStats.TX.value:
+            stats_formatted[XDPStats.TX.value] = val
+        elif stats_dump[key]["formatted"]["key"] == XDPStats.ABORT.value:
+            stats_formatted[XDPStats.ABORT.value] = val
+
+    return stats_formatted
+
+
+def _test_pass(cfg, bpf_info, msg_sz):
+    """
+    Tests the XDP_PASS action by exchanging UDP packets.
+
+    Args:
+        cfg: Configuration object containing network settings.
+        bpf_info: BPFProgInfo object containing information about the BPF program.
+        msg_sz: Size of the test message to send.
+    """
+
+    prog_info = _load_xdp_prog(cfg, bpf_info)
+    port = rand_port()
+
+    _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, XDPAction.PASS.value)
+    _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port)
+
+    ksft_eq(_test_udp(cfg, port, msg_sz), True, "UDP packet exchange failed")
+    stats = _get_stats(prog_info["maps"]["map_xdp_stats"])
+
+    ksft_ne(stats[XDPStats.RX.value], 0, "RX stats should not be zero")
+    ksft_eq(stats[XDPStats.RX.value], stats[XDPStats.PASS.value], "RX and PASS stats mismatch")
+
+
+def test_xdp_native_pass_sb(cfg):
+    """
+    Tests the XDP_PASS action for single buffer case.
+
+    Args:
+        cfg: Configuration object containing network settings.
+    """
+    bpf_info = BPFProgInfo("xdp_prog", "xdp_native.bpf.o", "xdp", 1500)
+
+    _test_pass(cfg, bpf_info, 256)
+
+
+def test_xdp_native_pass_mb(cfg):
+    """
+    Tests the XDP_PASS action for a multi-buff size.
+
+    Args:
+        cfg: Configuration object containing network settings.
+    """
+    bpf_info = BPFProgInfo("xdp_prog_frags", "xdp_native.bpf.o", "xdp.frags", 9000)
+
+    _test_pass(cfg, bpf_info, 8000)
+
+
+def _test_drop(cfg, bpf_info, msg_sz):
+    """
+    Tests the XDP_DROP action by exchanging UDP packets.
+
+    Args:
+        cfg: Configuration object containing network settings.
+        bpf_info: BPFProgInfo object containing information about the BPF program.
+        msg_sz: Size of the test message to send.
+    """
+
+    prog_info = _load_xdp_prog(cfg, bpf_info)
+    port = rand_port()
+
+    _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, XDPAction.DROP.value)
+    _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port)
+
+    ksft_eq(_test_udp(cfg, port, msg_sz), False, "UDP packet exchange should fail")
+    stats = _get_stats(prog_info["maps"]["map_xdp_stats"])
+
+    ksft_ne(stats[XDPStats.RX.value], 0, "RX stats should be zero")
+    ksft_eq(stats[XDPStats.RX.value], stats[XDPStats.DROP.value], "RX and DROP stats mismatch")
+
+
+def test_xdp_native_drop_sb(cfg):
+    """
+    Tests the XDP_DROP action for a signle-buff case.
+
+    Args:
+        cfg: Configuration object containing network settings.
+    """
+    bpf_info = BPFProgInfo("xdp_prog", "xdp_native.bpf.o", "xdp", 1500)
+
+    _test_drop(cfg, bpf_info, 256)
+
+
+def test_xdp_native_drop_mb(cfg):
+    """
+    Tests the XDP_DROP action for a multi-buff case.
+
+    Args:
+        cfg: Configuration object containing network settings.
+    """
+    bpf_info = BPFProgInfo("xdp_prog_frags", "xdp_native.bpf.o", "xdp.frags", 9000)
+
+    _test_drop(cfg, bpf_info, 8000)
+
+
+def _test_xdp_native_tx(cfg, bpf_info, payload_lens):
+    """
+    Tests the XDP_TX action.
+
+    Args:
+        cfg: Configuration object containing network settings.
+        bpf_info: BPFProgInfo object containing the BPF program metadata.
+        payload_lens: Array of packet lengths to send.
+    """
+    cfg.require_cmd("socat", remote=True)
+    prog_info = _load_xdp_prog(cfg, bpf_info)
+    port = rand_port()
+
+    _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, XDPAction.TX.value)
+    _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port)
+
+    expected_pkts = 0
+    for payload_len in payload_lens:
+        test_string = "".join(
+            random.choice(string.ascii_lowercase) for _ in range(payload_len)
+        )
+
+        rx_udp = f"socat -{cfg.addr_ipver} -T 2 " + \
+                 f"-u UDP-RECV:{port},reuseport STDOUT"
+
+        # Writing zero bytes to stdin gets ignored by socat,
+        # but with the shut-null flag socat generates a zero sized packet
+        # when the socket is closed.
+        tx_cmd_suffix = ",shut-null" if payload_len == 0 else ""
+        tx_udp = f"echo -n {test_string} | socat -t 2 " + \
+                 f"-u STDIN UDP:{cfg.baddr}:{port}{tx_cmd_suffix}"
+
+        with bkg(rx_udp, host=cfg.remote, exit_wait=True) as rnc:
+            wait_port_listen(port, proto="udp", host=cfg.remote)
+            cmd(tx_udp, host=cfg.remote, shell=True)
+
+        ksft_eq(rnc.stdout.strip(), test_string, "UDP packet exchange failed")
+
+        expected_pkts += 1
+        stats = _get_stats(prog_info["maps"]["map_xdp_stats"])
+        ksft_eq(stats[XDPStats.RX.value], expected_pkts, "RX stats mismatch")
+        ksft_eq(stats[XDPStats.TX.value], expected_pkts, "TX stats mismatch")
+
+
+def test_xdp_native_tx_sb(cfg):
+    """
+    Tests the XDP_TX action for a single-buff case.
+
+    Args:
+        cfg: Configuration object containing network settings.
+    """
+    bpf_info = BPFProgInfo("xdp_prog", "xdp_native.bpf.o", "xdp", 1500)
+
+    # Ensure there's enough room for an ETH / IP / UDP header
+    pkt_hdr_len = 42 if cfg.addr_ipver == "4" else 62
+
+    _test_xdp_native_tx(cfg, bpf_info, [0, 1500 // 2, 1500 - pkt_hdr_len])
+
+
+def test_xdp_native_tx_mb(cfg):
+    """
+    Tests the XDP_TX action for a multi-buff case.
+
+    Args:
+        cfg: Configuration object containing network settings.
+    """
+    bpf_info = BPFProgInfo("xdp_prog_frags", "xdp_native.bpf.o",
+                           "xdp.frags", 9000)
+    # The first packet ensures we exercise the fragmented code path.
+    # And the subsequent 0-sized packet ensures the driver
+    # reinitializes xdp_buff correctly.
+    _test_xdp_native_tx(cfg, bpf_info, [8000, 0])
+
+
+def _validate_res(res, offset_lst, pkt_sz_lst):
+    """
+    Validates the result of a test.
+
+    Args:
+        res: The result of the test, which should be a dictionary with a "status" key.
+
+    Raises:
+        KsftFailEx: If the test fails to pass any combination of offset and packet size.
+    """
+    if "status" not in res:
+        raise KsftFailEx("Missing 'status' key in result dictionary")
+
+    # Validate that not a single case was successful
+    if res["status"] == "fail":
+        if res["offset"] == offset_lst[0] and res["pkt_sz"] == pkt_sz_lst[0]:
+            raise KsftFailEx(f"{res['reason']}")
+
+        # Get the previous offset and packet size to report the successful run
+        tmp_idx = offset_lst.index(res["offset"])
+        prev_offset = offset_lst[tmp_idx - 1]
+        if tmp_idx == 0:
+            tmp_idx = pkt_sz_lst.index(res["pkt_sz"])
+            prev_pkt_sz = pkt_sz_lst[tmp_idx - 1]
+        else:
+            prev_pkt_sz = res["pkt_sz"]
+
+        # Use these values for error reporting
+        ksft_pr(
+        f"Failed run: pkt_sz {res['pkt_sz']}, offset {res['offset']}. "
+        f"Last successful run: pkt_sz {prev_pkt_sz}, offset {prev_offset}. "
+        f"Reason: {res['reason']}"
+        )
+
+
+def _check_for_failures(recvd_str, stats):
+    """
+    Checks for common failures while adjusting headroom or tailroom.
+
+    Args:
+        recvd_str: The string received from the remote host after sending a test string.
+        stats: A dictionary containing formatted packet statistics for various XDP actions.
+
+    Returns:
+        str: A string describing the failure reason if a failure is detected, otherwise None.
+    """
+
+    # Any adjustment failure result in an abort hence, we track this counter
+    if stats[XDPStats.ABORT.value] != 0:
+        return "Adjustment failed"
+
+    # Since we are using aggregate stats for a single test across all offsets and packet sizes
+    # we can't use RX stats only to track data exchange failure without taking a previous
+    # snapshot. An easier way is to simply check for non-zero length of received string.
+    if len(recvd_str) == 0:
+        return "Data exchange failed"
+
+    # Check for RX and PASS stats mismatch. Ideally, they should be equal for a successful run
+    if stats[XDPStats.RX.value] != stats[XDPStats.PASS.value]:
+        return "RX stats mismatch"
+
+    return None
+
+
+def _test_xdp_native_tail_adjst(cfg, pkt_sz_lst, offset_lst):
+    """
+    Tests the XDP tail adjustment functionality.
+
+    This function loads the appropriate XDP program based on the provided
+    program name and configures the XDP map for tail adjustment. It then
+    validates the tail adjustment by sending and receiving UDP packets
+    with specified packet sizes and offsets.
+
+    Args:
+        cfg: Configuration object containing network settings.
+        prog: Name of the XDP program to load.
+        pkt_sz_lst: List of packet sizes to test.
+        offset_lst: List of offsets to validate support for tail adjustment.
+
+    Returns:
+        dict: A dictionary with test status and failure details if applicable.
+    """
+    port = rand_port()
+    bpf_info = BPFProgInfo("xdp_prog_frags", "xdp_native.bpf.o", "xdp.frags", 9000)
+
+    prog_info = _load_xdp_prog(cfg, bpf_info)
+
+    # Configure the XDP map for tail adjustment
+    _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, XDPAction.TAIL_ADJST.value)
+    _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port)
+
+    for offset in offset_lst:
+        tag = format(random.randint(65, 90), "02x")
+
+        _set_xdp_map("map_xdp_setup", TestConfig.ADJST_OFFSET.value, offset)
+        if offset > 0:
+            _set_xdp_map("map_xdp_setup", TestConfig.ADJST_TAG.value, int(tag, 16))
+
+        for pkt_sz in pkt_sz_lst:
+            test_str = "".join(random.choice(string.ascii_lowercase) for _ in range(pkt_sz))
+            recvd_str = _exchg_udp(cfg, port, test_str)
+            stats = _get_stats(prog_info["maps"]["map_xdp_stats"])
+
+            failure = _check_for_failures(recvd_str, stats)
+            if failure is not None:
+                return {
+                    "status": "fail",
+                    "reason": failure,
+                    "offset": offset,
+                    "pkt_sz": pkt_sz,
+                }
+
+            # Validate data content based on offset direction
+            expected_data = None
+            if offset > 0:
+                expected_data = test_str + (offset * chr(int(tag, 16)))
+            else:
+                expected_data = test_str[0:pkt_sz + offset]
+
+            if recvd_str != expected_data:
+                return {
+                    "status": "fail",
+                    "reason": "Data mismatch",
+                    "offset": offset,
+                    "pkt_sz": pkt_sz,
+                }
+
+    return {"status": "pass"}
+
+
+def test_xdp_native_adjst_tail_grow_data(cfg):
+    """
+    Tests the XDP tail adjustment by growing packet data.
+
+    Args:
+        cfg: Configuration object containing network settings.
+    """
+    pkt_sz_lst = [512, 1024, 2048]
+    offset_lst = [1, 16, 32, 64, 128, 256]
+    res = _test_xdp_native_tail_adjst(
+        cfg,
+        pkt_sz_lst,
+        offset_lst,
+    )
+
+    _validate_res(res, offset_lst, pkt_sz_lst)
+
+
+def test_xdp_native_adjst_tail_shrnk_data(cfg):
+    """
+    Tests the XDP tail adjustment by shrinking packet data.
+
+    Args:
+        cfg: Configuration object containing network settings.
+    """
+    pkt_sz_lst = [512, 1024, 2048]
+    offset_lst = [-16, -32, -64, -128, -256]
+    res = _test_xdp_native_tail_adjst(
+        cfg,
+        pkt_sz_lst,
+        offset_lst,
+    )
+
+    _validate_res(res, offset_lst, pkt_sz_lst)
+
+
+def get_hds_thresh(cfg):
+    """
+    Retrieves the header data split (HDS) threshold for a network interface.
+
+    Args:
+        cfg: Configuration object containing network settings.
+
+    Returns:
+        The HDS threshold value. If the threshold is not supported or an error occurs,
+        a default value of 1500 is returned.
+    """
+    ethnl = cfg.ethnl
+    hds_thresh = 1500
+
+    try:
+        rings = ethnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+        if 'hds-thresh' not in rings:
+            ksft_pr(f'hds-thresh not supported. Using default: {hds_thresh}')
+            return hds_thresh
+        hds_thresh = rings['hds-thresh']
+    except NlError as e:
+        ksft_pr(f"Failed to get rings: {e}. Using default: {hds_thresh}")
+
+    return hds_thresh
+
+
+def _test_xdp_native_head_adjst(cfg, prog, pkt_sz_lst, offset_lst):
+    """
+    Tests the XDP head adjustment action for a multi-buffer case.
+
+    Args:
+        cfg: Configuration object containing network settings.
+        ethnl: Network namespace or link object (not used in this function).
+
+    This function sets up the packet size and offset lists, then performs
+    the head adjustment test by sending and receiving UDP packets.
+    """
+    cfg.require_cmd("socat", remote=True)
+
+    prog_info = _load_xdp_prog(cfg, BPFProgInfo(prog, "xdp_native.bpf.o", "xdp.frags", 9000))
+    port = rand_port()
+
+    _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, XDPAction.HEAD_ADJST.value)
+    _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port)
+
+    hds_thresh = get_hds_thresh(cfg)
+    for offset in offset_lst:
+        for pkt_sz in pkt_sz_lst:
+            # The "head" buffer must contain at least the Ethernet header
+            # after we eat into it. We send large-enough packets, but if HDS
+            # is enabled head will only contain headers. Don't try to eat
+            # more than 28 bytes (UDPv4 + eth hdr left: (14 + 20 + 8) - 14)
+            l2_cut_off = 28 if cfg.addr_ipver == 4 else 48
+            if pkt_sz > hds_thresh and offset > l2_cut_off:
+                ksft_pr(
+                f"Failed run: pkt_sz ({pkt_sz}) > HDS threshold ({hds_thresh}) and "
+                f"offset {offset} > {l2_cut_off}"
+                )
+                return {"status": "pass"}
+
+            test_str = ''.join(random.choice(string.ascii_lowercase) for _ in range(pkt_sz))
+            tag = format(random.randint(65, 90), '02x')
+
+            _set_xdp_map("map_xdp_setup",
+                     TestConfig.ADJST_OFFSET.value,
+                     offset)
+            _set_xdp_map("map_xdp_setup", TestConfig.ADJST_TAG.value, int(tag, 16))
+            _set_xdp_map("map_xdp_setup", TestConfig.ADJST_OFFSET.value, offset)
+
+            recvd_str = _exchg_udp(cfg, port, test_str)
+
+            # Check for failures around adjustment and data exchange
+            failure = _check_for_failures(recvd_str, _get_stats(prog_info['maps']['map_xdp_stats']))
+            if failure is not None:
+                return {
+                    "status": "fail",
+                    "reason": failure,
+                    "offset": offset,
+                    "pkt_sz": pkt_sz
+                }
+
+            # Validate data content based on offset direction
+            expected_data = None
+            if offset < 0:
+                expected_data = chr(int(tag, 16)) * (0 - offset) + test_str
+            else:
+                expected_data = test_str[offset:]
+
+            if recvd_str != expected_data:
+                return {
+                    "status": "fail",
+                    "reason": "Data mismatch",
+                    "offset": offset,
+                    "pkt_sz": pkt_sz
+                }
+
+    return {"status": "pass"}
+
+
+def test_xdp_native_adjst_head_grow_data(cfg):
+    """
+    Tests the XDP headroom growth support.
+
+    Args:
+        cfg: Configuration object containing network settings.
+
+    This function sets up the packet size and offset lists, then calls the
+    _test_xdp_native_head_adjst_mb function to perform the actual test. The
+    test is passed if the headroom is successfully extended for given packet
+    sizes and offsets.
+    """
+    pkt_sz_lst = [512, 1024, 2048]
+
+    # Negative values result in headroom shrinking, resulting in growing of payload
+    offset_lst = [-16, -32, -64, -128, -256]
+    res = _test_xdp_native_head_adjst(cfg, "xdp_prog_frags", pkt_sz_lst, offset_lst)
+
+    _validate_res(res, offset_lst, pkt_sz_lst)
+
+
+def test_xdp_native_adjst_head_shrnk_data(cfg):
+    """
+    Tests the XDP headroom shrinking support.
+
+    Args:
+        cfg: Configuration object containing network settings.
+
+    This function sets up the packet size and offset lists, then calls the
+    _test_xdp_native_head_adjst_mb function to perform the actual test. The
+    test is passed if the headroom is successfully shrunk for given packet
+    sizes and offsets.
+    """
+    pkt_sz_lst = [512, 1024, 2048]
+
+    # Positive values result in headroom growing, resulting in shrinking of payload
+    offset_lst = [16, 32, 64, 128, 256]
+    res = _test_xdp_native_head_adjst(cfg, "xdp_prog_frags", pkt_sz_lst, offset_lst)
+
+    _validate_res(res, offset_lst, pkt_sz_lst)
+
+
+@ksft_variants([
+    KsftNamedVariant("pass", XDPAction.PASS),
+    KsftNamedVariant("drop", XDPAction.DROP),
+    KsftNamedVariant("tx", XDPAction.TX),
+])
+def test_xdp_native_qstats(cfg, act):
+    """
+    Send 1000 messages. Expect XDP action specified in @act.
+    Make sure the packets were counted to interface level qstats
+    (Rx, and Tx if act is TX).
+    """
+
+    cfg.require_cmd("socat")
+
+    bpf_info = BPFProgInfo("xdp_prog", "xdp_native.bpf.o", "xdp", 1500)
+    prog_info = _load_xdp_prog(cfg, bpf_info)
+    port = rand_port()
+
+    _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, act.value)
+    _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port)
+
+    # Discard the input, but we need a listener to avoid ICMP errors
+    rx_udp = f"socat -{cfg.addr_ipver} -T 2 -u UDP-RECV:{port},reuseport " + \
+        "/dev/null"
+    # Listener runs on "remote" in case of XDP_TX
+    rx_host = cfg.remote if act == XDPAction.TX else None
+    # We want to spew 1000 packets quickly, bash seems to do a good enough job
+    # Each reopening of the socket gives us a differenot local port (for RSS)
+    tx_udp = "for _ in `seq 20`; do " \
+        f"exec 5<>/dev/udp/{cfg.addr}/{port}; " \
+        "for i in `seq 50`; do echo a >&5; done; " \
+        "exec 5>&-; done"
+
+    cfg.wait_hw_stats_settle()
+    # Qstats have more clearly defined semantics than rtnetlink.
+    # XDP is the "first layer of the stack" so XDP packets should be counted
+    # as received and sent as if the decision was made in the routing layer.
+    before = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0]
+
+    with bkg(rx_udp, host=rx_host, exit_wait=True):
+        wait_port_listen(port, proto="udp", host=rx_host)
+        cmd(tx_udp, host=cfg.remote, shell=True)
+
+    cfg.wait_hw_stats_settle()
+    after = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0]
+
+    expected_pkts = 1000
+    ksft_ge(after['rx-packets'] - before['rx-packets'], expected_pkts)
+    if act == XDPAction.TX:
+        ksft_ge(after['tx-packets'] - before['tx-packets'], expected_pkts)
+
+    stats = _get_stats(prog_info["maps"]["map_xdp_stats"])
+    ksft_eq(stats[XDPStats.RX.value], expected_pkts, "XDP RX stats mismatch")
+    if act == XDPAction.TX:
+        ksft_eq(stats[XDPStats.TX.value], expected_pkts, "XDP TX stats mismatch")
+
+    # Flip the ring count back and forth to make sure the stats from XDP rings
+    # don't get lost.
+    chans = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+    if chans.get('combined-count', 0) > 1:
+        cfg.ethnl.channels_set({'header': {'dev-index': cfg.ifindex},
+                                'combined-count': 1})
+        cfg.ethnl.channels_set({'header': {'dev-index': cfg.ifindex},
+                                'combined-count': chans['combined-count']})
+        before = after
+        after = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0]
+
+        ksft_ge(after['rx-packets'], before['rx-packets'])
+        if act == XDPAction.TX:
+            ksft_ge(after['tx-packets'], before['tx-packets'])
+
+
+def main():
+    """
+    Main function to execute the XDP tests.
+
+    This function runs a series of tests to validate the XDP support for
+    both the single and multi-buffer. It uses the NetDrvEpEnv context
+    manager to manage the network driver environment and the ksft_run
+    function to execute the tests.